AppPkg/Applications/Python/Python-2.7.10: Initial Checkin part 4/5.
The Lib directory from the cPython 2.7.10 distribution. These files are unchanged and set the baseline for subsequent commits. Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Daryl McDaniel <edk2-lists@mc2research.org> git-svn-id: https://svn.code.sf.net/p/edk2/code/trunk/edk2@18740 6f19259b-4bc3-4df7-8a09-765794883524
This commit is contained in:
Daryl McDaniel
committed by
darylm503
darylm503
parent
53b2ba5790
commit
3257aa9932
603
AppPkg/Applications/Python/Python-2.7.10/Lib/BaseHTTPServer.py
Normal file
603
AppPkg/Applications/Python/Python-2.7.10/Lib/BaseHTTPServer.py
Normal file
@@ -0,0 +1,603 @@
|
||||
"""HTTP server base class.
|
||||
|
||||
Note: the class in this module doesn't implement any HTTP request; see
|
||||
SimpleHTTPServer for simple implementations of GET, HEAD and POST
|
||||
(including CGI scripts). It does, however, optionally implement HTTP/1.1
|
||||
persistent connections, as of version 0.3.
|
||||
|
||||
Contents:
|
||||
|
||||
- BaseHTTPRequestHandler: HTTP request handler base class
|
||||
- test: test function
|
||||
|
||||
XXX To do:
|
||||
|
||||
- log requests even later (to capture byte count)
|
||||
- log user-agent header and other interesting goodies
|
||||
- send error log to separate file
|
||||
"""
|
||||
|
||||
|
||||
# See also:
|
||||
#
|
||||
# HTTP Working Group T. Berners-Lee
|
||||
# INTERNET-DRAFT R. T. Fielding
|
||||
# <draft-ietf-http-v10-spec-00.txt> H. Frystyk Nielsen
|
||||
# Expires September 8, 1995 March 8, 1995
|
||||
#
|
||||
# URL: http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt
|
||||
#
|
||||
# and
|
||||
#
|
||||
# Network Working Group R. Fielding
|
||||
# Request for Comments: 2616 et al
|
||||
# Obsoletes: 2068 June 1999
|
||||
# Category: Standards Track
|
||||
#
|
||||
# URL: http://www.faqs.org/rfcs/rfc2616.html
|
||||
|
||||
# Log files
|
||||
# ---------
|
||||
#
|
||||
# Here's a quote from the NCSA httpd docs about log file format.
|
||||
#
|
||||
# | The logfile format is as follows. Each line consists of:
|
||||
# |
|
||||
# | host rfc931 authuser [DD/Mon/YYYY:hh:mm:ss] "request" ddd bbbb
|
||||
# |
|
||||
# | host: Either the DNS name or the IP number of the remote client
|
||||
# | rfc931: Any information returned by identd for this person,
|
||||
# | - otherwise.
|
||||
# | authuser: If user sent a userid for authentication, the user name,
|
||||
# | - otherwise.
|
||||
# | DD: Day
|
||||
# | Mon: Month (calendar name)
|
||||
# | YYYY: Year
|
||||
# | hh: hour (24-hour format, the machine's timezone)
|
||||
# | mm: minutes
|
||||
# | ss: seconds
|
||||
# | request: The first line of the HTTP request as sent by the client.
|
||||
# | ddd: the status code returned by the server, - if not available.
|
||||
# | bbbb: the total number of bytes sent,
|
||||
# | *not including the HTTP/1.0 header*, - if not available
|
||||
# |
|
||||
# | You can determine the name of the file accessed through request.
|
||||
#
|
||||
# (Actually, the latter is only true if you know the server configuration
|
||||
# at the time the request was made!)
|
||||
|
||||
__version__ = "0.3"
|
||||
|
||||
__all__ = ["HTTPServer", "BaseHTTPRequestHandler"]
|
||||
|
||||
import sys
|
||||
import time
|
||||
import socket # For gethostbyaddr()
|
||||
from warnings import filterwarnings, catch_warnings
|
||||
with catch_warnings():
|
||||
if sys.py3kwarning:
|
||||
filterwarnings("ignore", ".*mimetools has been removed",
|
||||
DeprecationWarning)
|
||||
import mimetools
|
||||
import SocketServer
|
||||
|
||||
# Default error message template
|
||||
DEFAULT_ERROR_MESSAGE = """\
|
||||
<head>
|
||||
<title>Error response</title>
|
||||
</head>
|
||||
<body>
|
||||
<h1>Error response</h1>
|
||||
<p>Error code %(code)d.
|
||||
<p>Message: %(message)s.
|
||||
<p>Error code explanation: %(code)s = %(explain)s.
|
||||
</body>
|
||||
"""
|
||||
|
||||
DEFAULT_ERROR_CONTENT_TYPE = "text/html"
|
||||
|
||||
def _quote_html(html):
|
||||
return html.replace("&", "&").replace("<", "<").replace(">", ">")
|
||||
|
||||
class HTTPServer(SocketServer.TCPServer):
|
||||
|
||||
allow_reuse_address = 1 # Seems to make sense in testing environment
|
||||
|
||||
def server_bind(self):
|
||||
"""Override server_bind to store the server name."""
|
||||
SocketServer.TCPServer.server_bind(self)
|
||||
host, port = self.socket.getsockname()[:2]
|
||||
self.server_name = socket.getfqdn(host)
|
||||
self.server_port = port
|
||||
|
||||
|
||||
class BaseHTTPRequestHandler(SocketServer.StreamRequestHandler):
|
||||
|
||||
"""HTTP request handler base class.
|
||||
|
||||
The following explanation of HTTP serves to guide you through the
|
||||
code as well as to expose any misunderstandings I may have about
|
||||
HTTP (so you don't need to read the code to figure out I'm wrong
|
||||
:-).
|
||||
|
||||
HTTP (HyperText Transfer Protocol) is an extensible protocol on
|
||||
top of a reliable stream transport (e.g. TCP/IP). The protocol
|
||||
recognizes three parts to a request:
|
||||
|
||||
1. One line identifying the request type and path
|
||||
2. An optional set of RFC-822-style headers
|
||||
3. An optional data part
|
||||
|
||||
The headers and data are separated by a blank line.
|
||||
|
||||
The first line of the request has the form
|
||||
|
||||
<command> <path> <version>
|
||||
|
||||
where <command> is a (case-sensitive) keyword such as GET or POST,
|
||||
<path> is a string containing path information for the request,
|
||||
and <version> should be the string "HTTP/1.0" or "HTTP/1.1".
|
||||
<path> is encoded using the URL encoding scheme (using %xx to signify
|
||||
the ASCII character with hex code xx).
|
||||
|
||||
The specification specifies that lines are separated by CRLF but
|
||||
for compatibility with the widest range of clients recommends
|
||||
servers also handle LF. Similarly, whitespace in the request line
|
||||
is treated sensibly (allowing multiple spaces between components
|
||||
and allowing trailing whitespace).
|
||||
|
||||
Similarly, for output, lines ought to be separated by CRLF pairs
|
||||
but most clients grok LF characters just fine.
|
||||
|
||||
If the first line of the request has the form
|
||||
|
||||
<command> <path>
|
||||
|
||||
(i.e. <version> is left out) then this is assumed to be an HTTP
|
||||
0.9 request; this form has no optional headers and data part and
|
||||
the reply consists of just the data.
|
||||
|
||||
The reply form of the HTTP 1.x protocol again has three parts:
|
||||
|
||||
1. One line giving the response code
|
||||
2. An optional set of RFC-822-style headers
|
||||
3. The data
|
||||
|
||||
Again, the headers and data are separated by a blank line.
|
||||
|
||||
The response code line has the form
|
||||
|
||||
<version> <responsecode> <responsestring>
|
||||
|
||||
where <version> is the protocol version ("HTTP/1.0" or "HTTP/1.1"),
|
||||
<responsecode> is a 3-digit response code indicating success or
|
||||
failure of the request, and <responsestring> is an optional
|
||||
human-readable string explaining what the response code means.
|
||||
|
||||
This server parses the request and the headers, and then calls a
|
||||
function specific to the request type (<command>). Specifically,
|
||||
a request SPAM will be handled by a method do_SPAM(). If no
|
||||
such method exists the server sends an error response to the
|
||||
client. If it exists, it is called with no arguments:
|
||||
|
||||
do_SPAM()
|
||||
|
||||
Note that the request name is case sensitive (i.e. SPAM and spam
|
||||
are different requests).
|
||||
|
||||
The various request details are stored in instance variables:
|
||||
|
||||
- client_address is the client IP address in the form (host,
|
||||
port);
|
||||
|
||||
- command, path and version are the broken-down request line;
|
||||
|
||||
- headers is an instance of mimetools.Message (or a derived
|
||||
class) containing the header information;
|
||||
|
||||
- rfile is a file object open for reading positioned at the
|
||||
start of the optional input data part;
|
||||
|
||||
- wfile is a file object open for writing.
|
||||
|
||||
IT IS IMPORTANT TO ADHERE TO THE PROTOCOL FOR WRITING!
|
||||
|
||||
The first thing to be written must be the response line. Then
|
||||
follow 0 or more header lines, then a blank line, and then the
|
||||
actual data (if any). The meaning of the header lines depends on
|
||||
the command executed by the server; in most cases, when data is
|
||||
returned, there should be at least one header line of the form
|
||||
|
||||
Content-type: <type>/<subtype>
|
||||
|
||||
where <type> and <subtype> should be registered MIME types,
|
||||
e.g. "text/html" or "text/plain".
|
||||
|
||||
"""
|
||||
|
||||
# The Python system version, truncated to its first component.
|
||||
sys_version = "Python/" + sys.version.split()[0]
|
||||
|
||||
# The server software version. You may want to override this.
|
||||
# The format is multiple whitespace-separated strings,
|
||||
# where each string is of the form name[/version].
|
||||
server_version = "BaseHTTP/" + __version__
|
||||
|
||||
# The default request version. This only affects responses up until
|
||||
# the point where the request line is parsed, so it mainly decides what
|
||||
# the client gets back when sending a malformed request line.
|
||||
# Most web servers default to HTTP 0.9, i.e. don't send a status line.
|
||||
default_request_version = "HTTP/0.9"
|
||||
|
||||
def parse_request(self):
|
||||
"""Parse a request (internal).
|
||||
|
||||
The request should be stored in self.raw_requestline; the results
|
||||
are in self.command, self.path, self.request_version and
|
||||
self.headers.
|
||||
|
||||
Return True for success, False for failure; on failure, an
|
||||
error is sent back.
|
||||
|
||||
"""
|
||||
self.command = None # set in case of error on the first line
|
||||
self.request_version = version = self.default_request_version
|
||||
self.close_connection = 1
|
||||
requestline = self.raw_requestline
|
||||
requestline = requestline.rstrip('\r\n')
|
||||
self.requestline = requestline
|
||||
words = requestline.split()
|
||||
if len(words) == 3:
|
||||
command, path, version = words
|
||||
if version[:5] != 'HTTP/':
|
||||
self.send_error(400, "Bad request version (%r)" % version)
|
||||
return False
|
||||
try:
|
||||
base_version_number = version.split('/', 1)[1]
|
||||
version_number = base_version_number.split(".")
|
||||
# RFC 2145 section 3.1 says there can be only one "." and
|
||||
# - major and minor numbers MUST be treated as
|
||||
# separate integers;
|
||||
# - HTTP/2.4 is a lower version than HTTP/2.13, which in
|
||||
# turn is lower than HTTP/12.3;
|
||||
# - Leading zeros MUST be ignored by recipients.
|
||||
if len(version_number) != 2:
|
||||
raise ValueError
|
||||
version_number = int(version_number[0]), int(version_number[1])
|
||||
except (ValueError, IndexError):
|
||||
self.send_error(400, "Bad request version (%r)" % version)
|
||||
return False
|
||||
if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":
|
||||
self.close_connection = 0
|
||||
if version_number >= (2, 0):
|
||||
self.send_error(505,
|
||||
"Invalid HTTP Version (%s)" % base_version_number)
|
||||
return False
|
||||
elif len(words) == 2:
|
||||
command, path = words
|
||||
self.close_connection = 1
|
||||
if command != 'GET':
|
||||
self.send_error(400,
|
||||
"Bad HTTP/0.9 request type (%r)" % command)
|
||||
return False
|
||||
elif not words:
|
||||
return False
|
||||
else:
|
||||
self.send_error(400, "Bad request syntax (%r)" % requestline)
|
||||
return False
|
||||
self.command, self.path, self.request_version = command, path, version
|
||||
|
||||
# Examine the headers and look for a Connection directive
|
||||
self.headers = self.MessageClass(self.rfile, 0)
|
||||
|
||||
conntype = self.headers.get('Connection', "")
|
||||
if conntype.lower() == 'close':
|
||||
self.close_connection = 1
|
||||
elif (conntype.lower() == 'keep-alive' and
|
||||
self.protocol_version >= "HTTP/1.1"):
|
||||
self.close_connection = 0
|
||||
return True
|
||||
|
||||
def handle_one_request(self):
|
||||
"""Handle a single HTTP request.
|
||||
|
||||
You normally don't need to override this method; see the class
|
||||
__doc__ string for information on how to handle specific HTTP
|
||||
commands such as GET and POST.
|
||||
|
||||
"""
|
||||
try:
|
||||
self.raw_requestline = self.rfile.readline(65537)
|
||||
if len(self.raw_requestline) > 65536:
|
||||
self.requestline = ''
|
||||
self.request_version = ''
|
||||
self.command = ''
|
||||
self.send_error(414)
|
||||
return
|
||||
if not self.raw_requestline:
|
||||
self.close_connection = 1
|
||||
return
|
||||
if not self.parse_request():
|
||||
# An error code has been sent, just exit
|
||||
return
|
||||
mname = 'do_' + self.command
|
||||
if not hasattr(self, mname):
|
||||
self.send_error(501, "Unsupported method (%r)" % self.command)
|
||||
return
|
||||
method = getattr(self, mname)
|
||||
method()
|
||||
self.wfile.flush() #actually send the response if not already done.
|
||||
except socket.timeout, e:
|
||||
#a read or a write timed out. Discard this connection
|
||||
self.log_error("Request timed out: %r", e)
|
||||
self.close_connection = 1
|
||||
return
|
||||
|
||||
def handle(self):
|
||||
"""Handle multiple requests if necessary."""
|
||||
self.close_connection = 1
|
||||
|
||||
self.handle_one_request()
|
||||
while not self.close_connection:
|
||||
self.handle_one_request()
|
||||
|
||||
def send_error(self, code, message=None):
|
||||
"""Send and log an error reply.
|
||||
|
||||
Arguments are the error code, and a detailed message.
|
||||
The detailed message defaults to the short entry matching the
|
||||
response code.
|
||||
|
||||
This sends an error response (so it must be called before any
|
||||
output has been generated), logs the error, and finally sends
|
||||
a piece of HTML explaining the error to the user.
|
||||
|
||||
"""
|
||||
|
||||
try:
|
||||
short, long = self.responses[code]
|
||||
except KeyError:
|
||||
short, long = '???', '???'
|
||||
if message is None:
|
||||
message = short
|
||||
explain = long
|
||||
self.log_error("code %d, message %s", code, message)
|
||||
# using _quote_html to prevent Cross Site Scripting attacks (see bug #1100201)
|
||||
content = (self.error_message_format %
|
||||
{'code': code, 'message': _quote_html(message), 'explain': explain})
|
||||
self.send_response(code, message)
|
||||
self.send_header("Content-Type", self.error_content_type)
|
||||
self.send_header('Connection', 'close')
|
||||
self.end_headers()
|
||||
if self.command != 'HEAD' and code >= 200 and code not in (204, 304):
|
||||
self.wfile.write(content)
|
||||
|
||||
error_message_format = DEFAULT_ERROR_MESSAGE
|
||||
error_content_type = DEFAULT_ERROR_CONTENT_TYPE
|
||||
|
||||
def send_response(self, code, message=None):
|
||||
"""Send the response header and log the response code.
|
||||
|
||||
Also send two standard headers with the server software
|
||||
version and the current date.
|
||||
|
||||
"""
|
||||
self.log_request(code)
|
||||
if message is None:
|
||||
if code in self.responses:
|
||||
message = self.responses[code][0]
|
||||
else:
|
||||
message = ''
|
||||
if self.request_version != 'HTTP/0.9':
|
||||
self.wfile.write("%s %d %s\r\n" %
|
||||
(self.protocol_version, code, message))
|
||||
# print (self.protocol_version, code, message)
|
||||
self.send_header('Server', self.version_string())
|
||||
self.send_header('Date', self.date_time_string())
|
||||
|
||||
def send_header(self, keyword, value):
|
||||
"""Send a MIME header."""
|
||||
if self.request_version != 'HTTP/0.9':
|
||||
self.wfile.write("%s: %s\r\n" % (keyword, value))
|
||||
|
||||
if keyword.lower() == 'connection':
|
||||
if value.lower() == 'close':
|
||||
self.close_connection = 1
|
||||
elif value.lower() == 'keep-alive':
|
||||
self.close_connection = 0
|
||||
|
||||
def end_headers(self):
|
||||
"""Send the blank line ending the MIME headers."""
|
||||
if self.request_version != 'HTTP/0.9':
|
||||
self.wfile.write("\r\n")
|
||||
|
||||
def log_request(self, code='-', size='-'):
|
||||
"""Log an accepted request.
|
||||
|
||||
This is called by send_response().
|
||||
|
||||
"""
|
||||
|
||||
self.log_message('"%s" %s %s',
|
||||
self.requestline, str(code), str(size))
|
||||
|
||||
def log_error(self, format, *args):
|
||||
"""Log an error.
|
||||
|
||||
This is called when a request cannot be fulfilled. By
|
||||
default it passes the message on to log_message().
|
||||
|
||||
Arguments are the same as for log_message().
|
||||
|
||||
XXX This should go to the separate error log.
|
||||
|
||||
"""
|
||||
|
||||
self.log_message(format, *args)
|
||||
|
||||
def log_message(self, format, *args):
|
||||
"""Log an arbitrary message.
|
||||
|
||||
This is used by all other logging functions. Override
|
||||
it if you have specific logging wishes.
|
||||
|
||||
The first argument, FORMAT, is a format string for the
|
||||
message to be logged. If the format string contains
|
||||
any % escapes requiring parameters, they should be
|
||||
specified as subsequent arguments (it's just like
|
||||
printf!).
|
||||
|
||||
The client ip address and current date/time are prefixed to every
|
||||
message.
|
||||
|
||||
"""
|
||||
|
||||
sys.stderr.write("%s - - [%s] %s\n" %
|
||||
(self.client_address[0],
|
||||
self.log_date_time_string(),
|
||||
format%args))
|
||||
|
||||
def version_string(self):
|
||||
"""Return the server software version string."""
|
||||
return self.server_version + ' ' + self.sys_version
|
||||
|
||||
def date_time_string(self, timestamp=None):
|
||||
"""Return the current date and time formatted for a message header."""
|
||||
if timestamp is None:
|
||||
timestamp = time.time()
|
||||
year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp)
|
||||
s = "%s, %02d %3s %4d %02d:%02d:%02d GMT" % (
|
||||
self.weekdayname[wd],
|
||||
day, self.monthname[month], year,
|
||||
hh, mm, ss)
|
||||
return s
|
||||
|
||||
def log_date_time_string(self):
|
||||
"""Return the current time formatted for logging."""
|
||||
now = time.time()
|
||||
year, month, day, hh, mm, ss, x, y, z = time.localtime(now)
|
||||
s = "%02d/%3s/%04d %02d:%02d:%02d" % (
|
||||
day, self.monthname[month], year, hh, mm, ss)
|
||||
return s
|
||||
|
||||
weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
|
||||
|
||||
monthname = [None,
|
||||
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
|
||||
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
|
||||
|
||||
def address_string(self):
|
||||
"""Return the client address formatted for logging.
|
||||
|
||||
This version looks up the full hostname using gethostbyaddr(),
|
||||
and tries to find a name that contains at least one dot.
|
||||
|
||||
"""
|
||||
|
||||
host, port = self.client_address[:2]
|
||||
return socket.getfqdn(host)
|
||||
|
||||
# Essentially static class variables
|
||||
|
||||
# The version of the HTTP protocol we support.
|
||||
# Set this to HTTP/1.1 to enable automatic keepalive
|
||||
protocol_version = "HTTP/1.0"
|
||||
|
||||
# The Message-like class used to parse headers
|
||||
MessageClass = mimetools.Message
|
||||
|
||||
# Table mapping response codes to messages; entries have the
|
||||
# form {code: (shortmessage, longmessage)}.
|
||||
# See RFC 2616.
|
||||
responses = {
|
||||
100: ('Continue', 'Request received, please continue'),
|
||||
101: ('Switching Protocols',
|
||||
'Switching to new protocol; obey Upgrade header'),
|
||||
|
||||
200: ('OK', 'Request fulfilled, document follows'),
|
||||
201: ('Created', 'Document created, URL follows'),
|
||||
202: ('Accepted',
|
||||
'Request accepted, processing continues off-line'),
|
||||
203: ('Non-Authoritative Information', 'Request fulfilled from cache'),
|
||||
204: ('No Content', 'Request fulfilled, nothing follows'),
|
||||
205: ('Reset Content', 'Clear input form for further input.'),
|
||||
206: ('Partial Content', 'Partial content follows.'),
|
||||
|
||||
300: ('Multiple Choices',
|
||||
'Object has several resources -- see URI list'),
|
||||
301: ('Moved Permanently', 'Object moved permanently -- see URI list'),
|
||||
302: ('Found', 'Object moved temporarily -- see URI list'),
|
||||
303: ('See Other', 'Object moved -- see Method and URL list'),
|
||||
304: ('Not Modified',
|
||||
'Document has not changed since given time'),
|
||||
305: ('Use Proxy',
|
||||
'You must use proxy specified in Location to access this '
|
||||
'resource.'),
|
||||
307: ('Temporary Redirect',
|
||||
'Object moved temporarily -- see URI list'),
|
||||
|
||||
400: ('Bad Request',
|
||||
'Bad request syntax or unsupported method'),
|
||||
401: ('Unauthorized',
|
||||
'No permission -- see authorization schemes'),
|
||||
402: ('Payment Required',
|
||||
'No payment -- see charging schemes'),
|
||||
403: ('Forbidden',
|
||||
'Request forbidden -- authorization will not help'),
|
||||
404: ('Not Found', 'Nothing matches the given URI'),
|
||||
405: ('Method Not Allowed',
|
||||
'Specified method is invalid for this resource.'),
|
||||
406: ('Not Acceptable', 'URI not available in preferred format.'),
|
||||
407: ('Proxy Authentication Required', 'You must authenticate with '
|
||||
'this proxy before proceeding.'),
|
||||
408: ('Request Timeout', 'Request timed out; try again later.'),
|
||||
409: ('Conflict', 'Request conflict.'),
|
||||
410: ('Gone',
|
||||
'URI no longer exists and has been permanently removed.'),
|
||||
411: ('Length Required', 'Client must specify Content-Length.'),
|
||||
412: ('Precondition Failed', 'Precondition in headers is false.'),
|
||||
413: ('Request Entity Too Large', 'Entity is too large.'),
|
||||
414: ('Request-URI Too Long', 'URI is too long.'),
|
||||
415: ('Unsupported Media Type', 'Entity body in unsupported format.'),
|
||||
416: ('Requested Range Not Satisfiable',
|
||||
'Cannot satisfy request range.'),
|
||||
417: ('Expectation Failed',
|
||||
'Expect condition could not be satisfied.'),
|
||||
|
||||
500: ('Internal Server Error', 'Server got itself in trouble'),
|
||||
501: ('Not Implemented',
|
||||
'Server does not support this operation'),
|
||||
502: ('Bad Gateway', 'Invalid responses from another server/proxy.'),
|
||||
503: ('Service Unavailable',
|
||||
'The server cannot process the request due to a high load'),
|
||||
504: ('Gateway Timeout',
|
||||
'The gateway server did not receive a timely response'),
|
||||
505: ('HTTP Version Not Supported', 'Cannot fulfill request.'),
|
||||
}
|
||||
|
||||
|
||||
def test(HandlerClass = BaseHTTPRequestHandler,
|
||||
ServerClass = HTTPServer, protocol="HTTP/1.0"):
|
||||
"""Test the HTTP request handler class.
|
||||
|
||||
This runs an HTTP server on port 8000 (or the first command line
|
||||
argument).
|
||||
|
||||
"""
|
||||
|
||||
if sys.argv[1:]:
|
||||
port = int(sys.argv[1])
|
||||
else:
|
||||
port = 8000
|
||||
server_address = ('', port)
|
||||
|
||||
HandlerClass.protocol_version = protocol
|
||||
httpd = ServerClass(server_address, HandlerClass)
|
||||
|
||||
sa = httpd.socket.getsockname()
|
||||
print "Serving HTTP on", sa[0], "port", sa[1], "..."
|
||||
httpd.serve_forever()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
test()
|
||||
475
AppPkg/Applications/Python/Python-2.7.10/Lib/HTMLParser.py
Normal file
475
AppPkg/Applications/Python/Python-2.7.10/Lib/HTMLParser.py
Normal file
@@ -0,0 +1,475 @@
|
||||
"""A parser for HTML and XHTML."""
|
||||
|
||||
# This file is based on sgmllib.py, but the API is slightly different.
|
||||
|
||||
# XXX There should be a way to distinguish between PCDATA (parsed
|
||||
# character data -- the normal case), RCDATA (replaceable character
|
||||
# data -- only char and entity references and end tags are special)
|
||||
# and CDATA (character data -- only end tags are special).
|
||||
|
||||
|
||||
import markupbase
|
||||
import re
|
||||
|
||||
# Regular expressions used for parsing
|
||||
|
||||
interesting_normal = re.compile('[&<]')
|
||||
incomplete = re.compile('&[a-zA-Z#]')
|
||||
|
||||
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
|
||||
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
|
||||
|
||||
starttagopen = re.compile('<[a-zA-Z]')
|
||||
piclose = re.compile('>')
|
||||
commentclose = re.compile(r'--\s*>')
|
||||
|
||||
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
|
||||
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
|
||||
# note: if you change tagfind/attrfind remember to update locatestarttagend too
|
||||
tagfind = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
|
||||
# this regex is currently unused, but left for backward compatibility
|
||||
tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
|
||||
|
||||
attrfind = re.compile(
|
||||
r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
|
||||
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
|
||||
|
||||
locatestarttagend = re.compile(r"""
|
||||
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
|
||||
(?:[\s/]* # optional whitespace before attribute name
|
||||
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
|
||||
(?:\s*=+\s* # value indicator
|
||||
(?:'[^']*' # LITA-enclosed value
|
||||
|"[^"]*" # LIT-enclosed value
|
||||
|(?!['"])[^>\s]* # bare value
|
||||
)
|
||||
)?(?:\s|/(?!>))*
|
||||
)*
|
||||
)?
|
||||
\s* # trailing whitespace
|
||||
""", re.VERBOSE)
|
||||
endendtag = re.compile('>')
|
||||
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
|
||||
# </ and the tag name, so maybe this should be fixed
|
||||
endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
|
||||
|
||||
|
||||
class HTMLParseError(Exception):
|
||||
"""Exception raised for all parse errors."""
|
||||
|
||||
def __init__(self, msg, position=(None, None)):
|
||||
assert msg
|
||||
self.msg = msg
|
||||
self.lineno = position[0]
|
||||
self.offset = position[1]
|
||||
|
||||
def __str__(self):
|
||||
result = self.msg
|
||||
if self.lineno is not None:
|
||||
result = result + ", at line %d" % self.lineno
|
||||
if self.offset is not None:
|
||||
result = result + ", column %d" % (self.offset + 1)
|
||||
return result
|
||||
|
||||
|
||||
class HTMLParser(markupbase.ParserBase):
|
||||
"""Find tags and other markup and call handler functions.
|
||||
|
||||
Usage:
|
||||
p = HTMLParser()
|
||||
p.feed(data)
|
||||
...
|
||||
p.close()
|
||||
|
||||
Start tags are handled by calling self.handle_starttag() or
|
||||
self.handle_startendtag(); end tags by self.handle_endtag(). The
|
||||
data between tags is passed from the parser to the derived class
|
||||
by calling self.handle_data() with the data as argument (the data
|
||||
may be split up in arbitrary chunks). Entity references are
|
||||
passed by calling self.handle_entityref() with the entity
|
||||
reference as the argument. Numeric character references are
|
||||
passed to self.handle_charref() with the string containing the
|
||||
reference as the argument.
|
||||
"""
|
||||
|
||||
CDATA_CONTENT_ELEMENTS = ("script", "style")
|
||||
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize and reset this instance."""
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
"""Reset this instance. Loses all unprocessed data."""
|
||||
self.rawdata = ''
|
||||
self.lasttag = '???'
|
||||
self.interesting = interesting_normal
|
||||
self.cdata_elem = None
|
||||
markupbase.ParserBase.reset(self)
|
||||
|
||||
def feed(self, data):
|
||||
r"""Feed data to the parser.
|
||||
|
||||
Call this as often as you want, with as little or as much text
|
||||
as you want (may include '\n').
|
||||
"""
|
||||
self.rawdata = self.rawdata + data
|
||||
self.goahead(0)
|
||||
|
||||
def close(self):
|
||||
"""Handle any buffered data."""
|
||||
self.goahead(1)
|
||||
|
||||
def error(self, message):
|
||||
raise HTMLParseError(message, self.getpos())
|
||||
|
||||
__starttag_text = None
|
||||
|
||||
def get_starttag_text(self):
|
||||
"""Return full source of start tag: '<...>'."""
|
||||
return self.__starttag_text
|
||||
|
||||
def set_cdata_mode(self, elem):
|
||||
self.cdata_elem = elem.lower()
|
||||
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
|
||||
|
||||
def clear_cdata_mode(self):
|
||||
self.interesting = interesting_normal
|
||||
self.cdata_elem = None
|
||||
|
||||
# Internal -- handle data as far as reasonable. May leave state
|
||||
# and data to be processed by a subsequent call. If 'end' is
|
||||
# true, force handling all data as if followed by EOF marker.
|
||||
def goahead(self, end):
|
||||
rawdata = self.rawdata
|
||||
i = 0
|
||||
n = len(rawdata)
|
||||
while i < n:
|
||||
match = self.interesting.search(rawdata, i) # < or &
|
||||
if match:
|
||||
j = match.start()
|
||||
else:
|
||||
if self.cdata_elem:
|
||||
break
|
||||
j = n
|
||||
if i < j: self.handle_data(rawdata[i:j])
|
||||
i = self.updatepos(i, j)
|
||||
if i == n: break
|
||||
startswith = rawdata.startswith
|
||||
if startswith('<', i):
|
||||
if starttagopen.match(rawdata, i): # < + letter
|
||||
k = self.parse_starttag(i)
|
||||
elif startswith("</", i):
|
||||
k = self.parse_endtag(i)
|
||||
elif startswith("<!--", i):
|
||||
k = self.parse_comment(i)
|
||||
elif startswith("<?", i):
|
||||
k = self.parse_pi(i)
|
||||
elif startswith("<!", i):
|
||||
k = self.parse_html_declaration(i)
|
||||
elif (i + 1) < n:
|
||||
self.handle_data("<")
|
||||
k = i + 1
|
||||
else:
|
||||
break
|
||||
if k < 0:
|
||||
if not end:
|
||||
break
|
||||
k = rawdata.find('>', i + 1)
|
||||
if k < 0:
|
||||
k = rawdata.find('<', i + 1)
|
||||
if k < 0:
|
||||
k = i + 1
|
||||
else:
|
||||
k += 1
|
||||
self.handle_data(rawdata[i:k])
|
||||
i = self.updatepos(i, k)
|
||||
elif startswith("&#", i):
|
||||
match = charref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group()[2:-1]
|
||||
self.handle_charref(name)
|
||||
k = match.end()
|
||||
if not startswith(';', k-1):
|
||||
k = k - 1
|
||||
i = self.updatepos(i, k)
|
||||
continue
|
||||
else:
|
||||
if ";" in rawdata[i:]: # bail by consuming '&#'
|
||||
self.handle_data(rawdata[i:i+2])
|
||||
i = self.updatepos(i, i+2)
|
||||
break
|
||||
elif startswith('&', i):
|
||||
match = entityref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_entityref(name)
|
||||
k = match.end()
|
||||
if not startswith(';', k-1):
|
||||
k = k - 1
|
||||
i = self.updatepos(i, k)
|
||||
continue
|
||||
match = incomplete.match(rawdata, i)
|
||||
if match:
|
||||
# match.group() will contain at least 2 chars
|
||||
if end and match.group() == rawdata[i:]:
|
||||
self.error("EOF in middle of entity or char ref")
|
||||
# incomplete
|
||||
break
|
||||
elif (i + 1) < n:
|
||||
# not the end of the buffer, and can't be confused
|
||||
# with some other construct
|
||||
self.handle_data("&")
|
||||
i = self.updatepos(i, i + 1)
|
||||
else:
|
||||
break
|
||||
else:
|
||||
assert 0, "interesting.search() lied"
|
||||
# end while
|
||||
if end and i < n and not self.cdata_elem:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = self.updatepos(i, n)
|
||||
self.rawdata = rawdata[i:]
|
||||
|
||||
# Internal -- parse html declarations, return length or -1 if not terminated
|
||||
# See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
|
||||
# See also parse_declaration in _markupbase
|
||||
def parse_html_declaration(self, i):
|
||||
rawdata = self.rawdata
|
||||
if rawdata[i:i+2] != '<!':
|
||||
self.error('unexpected call to parse_html_declaration()')
|
||||
if rawdata[i:i+4] == '<!--':
|
||||
# this case is actually already handled in goahead()
|
||||
return self.parse_comment(i)
|
||||
elif rawdata[i:i+3] == '<![':
|
||||
return self.parse_marked_section(i)
|
||||
elif rawdata[i:i+9].lower() == '<!doctype':
|
||||
# find the closing >
|
||||
gtpos = rawdata.find('>', i+9)
|
||||
if gtpos == -1:
|
||||
return -1
|
||||
self.handle_decl(rawdata[i+2:gtpos])
|
||||
return gtpos+1
|
||||
else:
|
||||
return self.parse_bogus_comment(i)
|
||||
|
||||
# Internal -- parse bogus comment, return length or -1 if not terminated
|
||||
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
|
||||
def parse_bogus_comment(self, i, report=1):
|
||||
rawdata = self.rawdata
|
||||
if rawdata[i:i+2] not in ('<!', '</'):
|
||||
self.error('unexpected call to parse_comment()')
|
||||
pos = rawdata.find('>', i+2)
|
||||
if pos == -1:
|
||||
return -1
|
||||
if report:
|
||||
self.handle_comment(rawdata[i+2:pos])
|
||||
return pos + 1
|
||||
|
||||
# Internal -- parse processing instr, return end or -1 if not terminated
|
||||
def parse_pi(self, i):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
|
||||
match = piclose.search(rawdata, i+2) # >
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start()
|
||||
self.handle_pi(rawdata[i+2: j])
|
||||
j = match.end()
|
||||
return j
|
||||
|
||||
# Internal -- handle starttag, return end or -1 if not terminated
|
||||
def parse_starttag(self, i):
|
||||
self.__starttag_text = None
|
||||
endpos = self.check_for_whole_start_tag(i)
|
||||
if endpos < 0:
|
||||
return endpos
|
||||
rawdata = self.rawdata
|
||||
self.__starttag_text = rawdata[i:endpos]
|
||||
|
||||
# Now parse the data between i+1 and j into a tag and attrs
|
||||
attrs = []
|
||||
match = tagfind.match(rawdata, i+1)
|
||||
assert match, 'unexpected call to parse_starttag()'
|
||||
k = match.end()
|
||||
self.lasttag = tag = match.group(1).lower()
|
||||
|
||||
while k < endpos:
|
||||
m = attrfind.match(rawdata, k)
|
||||
if not m:
|
||||
break
|
||||
attrname, rest, attrvalue = m.group(1, 2, 3)
|
||||
if not rest:
|
||||
attrvalue = None
|
||||
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
|
||||
attrvalue[:1] == '"' == attrvalue[-1:]:
|
||||
attrvalue = attrvalue[1:-1]
|
||||
if attrvalue:
|
||||
attrvalue = self.unescape(attrvalue)
|
||||
attrs.append((attrname.lower(), attrvalue))
|
||||
k = m.end()
|
||||
|
||||
end = rawdata[k:endpos].strip()
|
||||
if end not in (">", "/>"):
|
||||
lineno, offset = self.getpos()
|
||||
if "\n" in self.__starttag_text:
|
||||
lineno = lineno + self.__starttag_text.count("\n")
|
||||
offset = len(self.__starttag_text) \
|
||||
- self.__starttag_text.rfind("\n")
|
||||
else:
|
||||
offset = offset + len(self.__starttag_text)
|
||||
self.handle_data(rawdata[i:endpos])
|
||||
return endpos
|
||||
if end.endswith('/>'):
|
||||
# XHTML-style empty tag: <span attr="value" />
|
||||
self.handle_startendtag(tag, attrs)
|
||||
else:
|
||||
self.handle_starttag(tag, attrs)
|
||||
if tag in self.CDATA_CONTENT_ELEMENTS:
|
||||
self.set_cdata_mode(tag)
|
||||
return endpos
|
||||
|
||||
# Internal -- check to see if we have a complete starttag; return end
|
||||
# or -1 if incomplete.
|
||||
def check_for_whole_start_tag(self, i):
|
||||
rawdata = self.rawdata
|
||||
m = locatestarttagend.match(rawdata, i)
|
||||
if m:
|
||||
j = m.end()
|
||||
next = rawdata[j:j+1]
|
||||
if next == ">":
|
||||
return j + 1
|
||||
if next == "/":
|
||||
if rawdata.startswith("/>", j):
|
||||
return j + 2
|
||||
if rawdata.startswith("/", j):
|
||||
# buffer boundary
|
||||
return -1
|
||||
# else bogus input
|
||||
self.updatepos(i, j + 1)
|
||||
self.error("malformed empty start tag")
|
||||
if next == "":
|
||||
# end of input
|
||||
return -1
|
||||
if next in ("abcdefghijklmnopqrstuvwxyz=/"
|
||||
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
|
||||
# end of input in or before attribute value, or we have the
|
||||
# '/' from a '/>' ending
|
||||
return -1
|
||||
if j > i:
|
||||
return j
|
||||
else:
|
||||
return i + 1
|
||||
raise AssertionError("we should not get here!")
|
||||
|
||||
# Internal -- parse endtag, return end or -1 if incomplete
|
||||
def parse_endtag(self, i):
|
||||
rawdata = self.rawdata
|
||||
assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
|
||||
match = endendtag.search(rawdata, i+1) # >
|
||||
if not match:
|
||||
return -1
|
||||
gtpos = match.end()
|
||||
match = endtagfind.match(rawdata, i) # </ + tag + >
|
||||
if not match:
|
||||
if self.cdata_elem is not None:
|
||||
self.handle_data(rawdata[i:gtpos])
|
||||
return gtpos
|
||||
# find the name: w3.org/TR/html5/tokenization.html#tag-name-state
|
||||
namematch = tagfind.match(rawdata, i+2)
|
||||
if not namematch:
|
||||
# w3.org/TR/html5/tokenization.html#end-tag-open-state
|
||||
if rawdata[i:i+3] == '</>':
|
||||
return i+3
|
||||
else:
|
||||
return self.parse_bogus_comment(i)
|
||||
tagname = namematch.group(1).lower()
|
||||
# consume and ignore other stuff between the name and the >
|
||||
# Note: this is not 100% correct, since we might have things like
|
||||
# </tag attr=">">, but looking for > after tha name should cover
|
||||
# most of the cases and is much simpler
|
||||
gtpos = rawdata.find('>', namematch.end())
|
||||
self.handle_endtag(tagname)
|
||||
return gtpos+1
|
||||
|
||||
elem = match.group(1).lower() # script or style
|
||||
if self.cdata_elem is not None:
|
||||
if elem != self.cdata_elem:
|
||||
self.handle_data(rawdata[i:gtpos])
|
||||
return gtpos
|
||||
|
||||
self.handle_endtag(elem)
|
||||
self.clear_cdata_mode()
|
||||
return gtpos
|
||||
|
||||
# Overridable -- finish processing of start+end tag: <tag.../>
|
||||
def handle_startendtag(self, tag, attrs):
|
||||
self.handle_starttag(tag, attrs)
|
||||
self.handle_endtag(tag)
|
||||
|
||||
# Overridable -- handle start tag
|
||||
def handle_starttag(self, tag, attrs):
|
||||
pass
|
||||
|
||||
# Overridable -- handle end tag
|
||||
def handle_endtag(self, tag):
|
||||
pass
|
||||
|
||||
# Overridable -- handle character reference
|
||||
def handle_charref(self, name):
|
||||
pass
|
||||
|
||||
# Overridable -- handle entity reference
|
||||
def handle_entityref(self, name):
|
||||
pass
|
||||
|
||||
# Overridable -- handle data
|
||||
def handle_data(self, data):
|
||||
pass
|
||||
|
||||
# Overridable -- handle comment
|
||||
def handle_comment(self, data):
|
||||
pass
|
||||
|
||||
# Overridable -- handle declaration
|
||||
def handle_decl(self, decl):
|
||||
pass
|
||||
|
||||
# Overridable -- handle processing instruction
|
||||
def handle_pi(self, data):
|
||||
pass
|
||||
|
||||
def unknown_decl(self, data):
|
||||
pass
|
||||
|
||||
# Internal -- helper to remove special character quoting
|
||||
entitydefs = None
|
||||
def unescape(self, s):
|
||||
if '&' not in s:
|
||||
return s
|
||||
def replaceEntities(s):
|
||||
s = s.groups()[0]
|
||||
try:
|
||||
if s[0] == "#":
|
||||
s = s[1:]
|
||||
if s[0] in ['x','X']:
|
||||
c = int(s[1:], 16)
|
||||
else:
|
||||
c = int(s)
|
||||
return unichr(c)
|
||||
except ValueError:
|
||||
return '&#'+s+';'
|
||||
else:
|
||||
# Cannot use name2codepoint directly, because HTMLParser supports apos,
|
||||
# which is not part of HTML 4
|
||||
import htmlentitydefs
|
||||
if HTMLParser.entitydefs is None:
|
||||
entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
|
||||
for k, v in htmlentitydefs.name2codepoint.iteritems():
|
||||
entitydefs[k] = unichr(v)
|
||||
try:
|
||||
return self.entitydefs[s]
|
||||
except KeyError:
|
||||
return '&'+s+';'
|
||||
|
||||
return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)
|
||||
235
AppPkg/Applications/Python/Python-2.7.10/Lib/SimpleHTTPServer.py
Normal file
235
AppPkg/Applications/Python/Python-2.7.10/Lib/SimpleHTTPServer.py
Normal file
@@ -0,0 +1,235 @@
|
||||
"""Simple HTTP Server.
|
||||
|
||||
This module builds on BaseHTTPServer by implementing the standard GET
|
||||
and HEAD requests in a fairly straightforward manner.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
__version__ = "0.6"
|
||||
|
||||
__all__ = ["SimpleHTTPRequestHandler"]
|
||||
|
||||
import os
|
||||
import posixpath
|
||||
import BaseHTTPServer
|
||||
import urllib
|
||||
import urlparse
|
||||
import cgi
|
||||
import sys
|
||||
import shutil
|
||||
import mimetypes
|
||||
try:
|
||||
from cStringIO import StringIO
|
||||
except ImportError:
|
||||
from StringIO import StringIO
|
||||
|
||||
|
||||
class SimpleHTTPRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
|
||||
|
||||
"""Simple HTTP request handler with GET and HEAD commands.
|
||||
|
||||
This serves files from the current directory and any of its
|
||||
subdirectories. The MIME type for files is determined by
|
||||
calling the .guess_type() method.
|
||||
|
||||
The GET and HEAD requests are identical except that the HEAD
|
||||
request omits the actual contents of the file.
|
||||
|
||||
"""
|
||||
|
||||
server_version = "SimpleHTTP/" + __version__
|
||||
|
||||
def do_GET(self):
|
||||
"""Serve a GET request."""
|
||||
f = self.send_head()
|
||||
if f:
|
||||
try:
|
||||
self.copyfile(f, self.wfile)
|
||||
finally:
|
||||
f.close()
|
||||
|
||||
def do_HEAD(self):
|
||||
"""Serve a HEAD request."""
|
||||
f = self.send_head()
|
||||
if f:
|
||||
f.close()
|
||||
|
||||
def send_head(self):
|
||||
"""Common code for GET and HEAD commands.
|
||||
|
||||
This sends the response code and MIME headers.
|
||||
|
||||
Return value is either a file object (which has to be copied
|
||||
to the outputfile by the caller unless the command was HEAD,
|
||||
and must be closed by the caller under all circumstances), or
|
||||
None, in which case the caller has nothing further to do.
|
||||
|
||||
"""
|
||||
path = self.translate_path(self.path)
|
||||
f = None
|
||||
if os.path.isdir(path):
|
||||
parts = urlparse.urlsplit(self.path)
|
||||
if not parts.path.endswith('/'):
|
||||
# redirect browser - doing basically what apache does
|
||||
self.send_response(301)
|
||||
new_parts = (parts[0], parts[1], parts[2] + '/',
|
||||
parts[3], parts[4])
|
||||
new_url = urlparse.urlunsplit(new_parts)
|
||||
self.send_header("Location", new_url)
|
||||
self.end_headers()
|
||||
return None
|
||||
for index in "index.html", "index.htm":
|
||||
index = os.path.join(path, index)
|
||||
if os.path.exists(index):
|
||||
path = index
|
||||
break
|
||||
else:
|
||||
return self.list_directory(path)
|
||||
ctype = self.guess_type(path)
|
||||
try:
|
||||
# Always read in binary mode. Opening files in text mode may cause
|
||||
# newline translations, making the actual size of the content
|
||||
# transmitted *less* than the content-length!
|
||||
f = open(path, 'rb')
|
||||
except IOError:
|
||||
self.send_error(404, "File not found")
|
||||
return None
|
||||
try:
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", ctype)
|
||||
fs = os.fstat(f.fileno())
|
||||
self.send_header("Content-Length", str(fs[6]))
|
||||
self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
|
||||
self.end_headers()
|
||||
return f
|
||||
except:
|
||||
f.close()
|
||||
raise
|
||||
|
||||
def list_directory(self, path):
|
||||
"""Helper to produce a directory listing (absent index.html).
|
||||
|
||||
Return value is either a file object, or None (indicating an
|
||||
error). In either case, the headers are sent, making the
|
||||
interface the same as for send_head().
|
||||
|
||||
"""
|
||||
try:
|
||||
list = os.listdir(path)
|
||||
except os.error:
|
||||
self.send_error(404, "No permission to list directory")
|
||||
return None
|
||||
list.sort(key=lambda a: a.lower())
|
||||
f = StringIO()
|
||||
displaypath = cgi.escape(urllib.unquote(self.path))
|
||||
f.write('<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">')
|
||||
f.write("<html>\n<title>Directory listing for %s</title>\n" % displaypath)
|
||||
f.write("<body>\n<h2>Directory listing for %s</h2>\n" % displaypath)
|
||||
f.write("<hr>\n<ul>\n")
|
||||
for name in list:
|
||||
fullname = os.path.join(path, name)
|
||||
displayname = linkname = name
|
||||
# Append / for directories or @ for symbolic links
|
||||
if os.path.isdir(fullname):
|
||||
displayname = name + "/"
|
||||
linkname = name + "/"
|
||||
if os.path.islink(fullname):
|
||||
displayname = name + "@"
|
||||
# Note: a link to a directory displays with @ and links with /
|
||||
f.write('<li><a href="%s">%s</a>\n'
|
||||
% (urllib.quote(linkname), cgi.escape(displayname)))
|
||||
f.write("</ul>\n<hr>\n</body>\n</html>\n")
|
||||
length = f.tell()
|
||||
f.seek(0)
|
||||
self.send_response(200)
|
||||
encoding = sys.getfilesystemencoding()
|
||||
self.send_header("Content-type", "text/html; charset=%s" % encoding)
|
||||
self.send_header("Content-Length", str(length))
|
||||
self.end_headers()
|
||||
return f
|
||||
|
||||
def translate_path(self, path):
|
||||
"""Translate a /-separated PATH to the local filename syntax.
|
||||
|
||||
Components that mean special things to the local file system
|
||||
(e.g. drive or directory names) are ignored. (XXX They should
|
||||
probably be diagnosed.)
|
||||
|
||||
"""
|
||||
# abandon query parameters
|
||||
path = path.split('?',1)[0]
|
||||
path = path.split('#',1)[0]
|
||||
# Don't forget explicit trailing slash when normalizing. Issue17324
|
||||
trailing_slash = path.rstrip().endswith('/')
|
||||
path = posixpath.normpath(urllib.unquote(path))
|
||||
words = path.split('/')
|
||||
words = filter(None, words)
|
||||
path = os.getcwd()
|
||||
for word in words:
|
||||
drive, word = os.path.splitdrive(word)
|
||||
head, word = os.path.split(word)
|
||||
if word in (os.curdir, os.pardir): continue
|
||||
path = os.path.join(path, word)
|
||||
if trailing_slash:
|
||||
path += '/'
|
||||
return path
|
||||
|
||||
def copyfile(self, source, outputfile):
|
||||
"""Copy all data between two file objects.
|
||||
|
||||
The SOURCE argument is a file object open for reading
|
||||
(or anything with a read() method) and the DESTINATION
|
||||
argument is a file object open for writing (or
|
||||
anything with a write() method).
|
||||
|
||||
The only reason for overriding this would be to change
|
||||
the block size or perhaps to replace newlines by CRLF
|
||||
-- note however that this the default server uses this
|
||||
to copy binary data as well.
|
||||
|
||||
"""
|
||||
shutil.copyfileobj(source, outputfile)
|
||||
|
||||
def guess_type(self, path):
|
||||
"""Guess the type of a file.
|
||||
|
||||
Argument is a PATH (a filename).
|
||||
|
||||
Return value is a string of the form type/subtype,
|
||||
usable for a MIME Content-type header.
|
||||
|
||||
The default implementation looks the file's extension
|
||||
up in the table self.extensions_map, using application/octet-stream
|
||||
as a default; however it would be permissible (if
|
||||
slow) to look inside the data to make a better guess.
|
||||
|
||||
"""
|
||||
|
||||
base, ext = posixpath.splitext(path)
|
||||
if ext in self.extensions_map:
|
||||
return self.extensions_map[ext]
|
||||
ext = ext.lower()
|
||||
if ext in self.extensions_map:
|
||||
return self.extensions_map[ext]
|
||||
else:
|
||||
return self.extensions_map['']
|
||||
|
||||
if not mimetypes.inited:
|
||||
mimetypes.init() # try to read system mime.types
|
||||
extensions_map = mimetypes.types_map.copy()
|
||||
extensions_map.update({
|
||||
'': 'application/octet-stream', # Default
|
||||
'.py': 'text/plain',
|
||||
'.c': 'text/plain',
|
||||
'.h': 'text/plain',
|
||||
})
|
||||
|
||||
|
||||
def test(HandlerClass = SimpleHTTPRequestHandler,
|
||||
ServerClass = BaseHTTPServer.HTTPServer):
|
||||
BaseHTTPServer.test(HandlerClass, ServerClass)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
test()
|
||||
737
AppPkg/Applications/Python/Python-2.7.10/Lib/SocketServer.py
Normal file
737
AppPkg/Applications/Python/Python-2.7.10/Lib/SocketServer.py
Normal file
@@ -0,0 +1,737 @@
|
||||
"""Generic socket server classes.
|
||||
|
||||
This module tries to capture the various aspects of defining a server:
|
||||
|
||||
For socket-based servers:
|
||||
|
||||
- address family:
|
||||
- AF_INET{,6}: IP (Internet Protocol) sockets (default)
|
||||
- AF_UNIX: Unix domain sockets
|
||||
- others, e.g. AF_DECNET are conceivable (see <socket.h>
|
||||
- socket type:
|
||||
- SOCK_STREAM (reliable stream, e.g. TCP)
|
||||
- SOCK_DGRAM (datagrams, e.g. UDP)
|
||||
|
||||
For request-based servers (including socket-based):
|
||||
|
||||
- client address verification before further looking at the request
|
||||
(This is actually a hook for any processing that needs to look
|
||||
at the request before anything else, e.g. logging)
|
||||
- how to handle multiple requests:
|
||||
- synchronous (one request is handled at a time)
|
||||
- forking (each request is handled by a new process)
|
||||
- threading (each request is handled by a new thread)
|
||||
|
||||
The classes in this module favor the server type that is simplest to
|
||||
write: a synchronous TCP/IP server. This is bad class design, but
|
||||
save some typing. (There's also the issue that a deep class hierarchy
|
||||
slows down method lookups.)
|
||||
|
||||
There are five classes in an inheritance diagram, four of which represent
|
||||
synchronous servers of four types:
|
||||
|
||||
+------------+
|
||||
| BaseServer |
|
||||
+------------+
|
||||
|
|
||||
v
|
||||
+-----------+ +------------------+
|
||||
| TCPServer |------->| UnixStreamServer |
|
||||
+-----------+ +------------------+
|
||||
|
|
||||
v
|
||||
+-----------+ +--------------------+
|
||||
| UDPServer |------->| UnixDatagramServer |
|
||||
+-----------+ +--------------------+
|
||||
|
||||
Note that UnixDatagramServer derives from UDPServer, not from
|
||||
UnixStreamServer -- the only difference between an IP and a Unix
|
||||
stream server is the address family, which is simply repeated in both
|
||||
unix server classes.
|
||||
|
||||
Forking and threading versions of each type of server can be created
|
||||
using the ForkingMixIn and ThreadingMixIn mix-in classes. For
|
||||
instance, a threading UDP server class is created as follows:
|
||||
|
||||
class ThreadingUDPServer(ThreadingMixIn, UDPServer): pass
|
||||
|
||||
The Mix-in class must come first, since it overrides a method defined
|
||||
in UDPServer! Setting the various member variables also changes
|
||||
the behavior of the underlying server mechanism.
|
||||
|
||||
To implement a service, you must derive a class from
|
||||
BaseRequestHandler and redefine its handle() method. You can then run
|
||||
various versions of the service by combining one of the server classes
|
||||
with your request handler class.
|
||||
|
||||
The request handler class must be different for datagram or stream
|
||||
services. This can be hidden by using the request handler
|
||||
subclasses StreamRequestHandler or DatagramRequestHandler.
|
||||
|
||||
Of course, you still have to use your head!
|
||||
|
||||
For instance, it makes no sense to use a forking server if the service
|
||||
contains state in memory that can be modified by requests (since the
|
||||
modifications in the child process would never reach the initial state
|
||||
kept in the parent process and passed to each child). In this case,
|
||||
you can use a threading server, but you will probably have to use
|
||||
locks to avoid two requests that come in nearly simultaneous to apply
|
||||
conflicting changes to the server state.
|
||||
|
||||
On the other hand, if you are building e.g. an HTTP server, where all
|
||||
data is stored externally (e.g. in the file system), a synchronous
|
||||
class will essentially render the service "deaf" while one request is
|
||||
being handled -- which may be for a very long time if a client is slow
|
||||
to read all the data it has requested. Here a threading or forking
|
||||
server is appropriate.
|
||||
|
||||
In some cases, it may be appropriate to process part of a request
|
||||
synchronously, but to finish processing in a forked child depending on
|
||||
the request data. This can be implemented by using a synchronous
|
||||
server and doing an explicit fork in the request handler class
|
||||
handle() method.
|
||||
|
||||
Another approach to handling multiple simultaneous requests in an
|
||||
environment that supports neither threads nor fork (or where these are
|
||||
too expensive or inappropriate for the service) is to maintain an
|
||||
explicit table of partially finished requests and to use select() to
|
||||
decide which request to work on next (or whether to handle a new
|
||||
incoming request). This is particularly important for stream services
|
||||
where each client can potentially be connected for a long time (if
|
||||
threads or subprocesses cannot be used).
|
||||
|
||||
Future work:
|
||||
- Standard classes for Sun RPC (which uses either UDP or TCP)
|
||||
- Standard mix-in classes to implement various authentication
|
||||
and encryption schemes
|
||||
- Standard framework for select-based multiplexing
|
||||
|
||||
XXX Open problems:
|
||||
- What to do with out-of-band data?
|
||||
|
||||
BaseServer:
|
||||
- split generic "request" functionality out into BaseServer class.
|
||||
Copyright (C) 2000 Luke Kenneth Casson Leighton <lkcl@samba.org>
|
||||
|
||||
example: read entries from a SQL database (requires overriding
|
||||
get_request() to return a table entry from the database).
|
||||
entry is processed by a RequestHandlerClass.
|
||||
|
||||
"""
|
||||
|
||||
# Author of the BaseServer patch: Luke Kenneth Casson Leighton
|
||||
|
||||
# XXX Warning!
|
||||
# There is a test suite for this module, but it cannot be run by the
|
||||
# standard regression test.
|
||||
# To run it manually, run Lib/test/test_socketserver.py.
|
||||
|
||||
__version__ = "0.4"
|
||||
|
||||
|
||||
import socket
|
||||
import select
|
||||
import sys
|
||||
import os
|
||||
import errno
|
||||
try:
|
||||
import threading
|
||||
except ImportError:
|
||||
import dummy_threading as threading
|
||||
|
||||
__all__ = ["TCPServer","UDPServer","ForkingUDPServer","ForkingTCPServer",
|
||||
"ThreadingUDPServer","ThreadingTCPServer","BaseRequestHandler",
|
||||
"StreamRequestHandler","DatagramRequestHandler",
|
||||
"ThreadingMixIn", "ForkingMixIn"]
|
||||
if hasattr(socket, "AF_UNIX"):
|
||||
__all__.extend(["UnixStreamServer","UnixDatagramServer",
|
||||
"ThreadingUnixStreamServer",
|
||||
"ThreadingUnixDatagramServer"])
|
||||
|
||||
def _eintr_retry(func, *args):
|
||||
"""restart a system call interrupted by EINTR"""
|
||||
while True:
|
||||
try:
|
||||
return func(*args)
|
||||
except (OSError, select.error) as e:
|
||||
if e.args[0] != errno.EINTR:
|
||||
raise
|
||||
|
||||
class BaseServer:
|
||||
|
||||
"""Base class for server classes.
|
||||
|
||||
Methods for the caller:
|
||||
|
||||
- __init__(server_address, RequestHandlerClass)
|
||||
- serve_forever(poll_interval=0.5)
|
||||
- shutdown()
|
||||
- handle_request() # if you do not use serve_forever()
|
||||
- fileno() -> int # for select()
|
||||
|
||||
Methods that may be overridden:
|
||||
|
||||
- server_bind()
|
||||
- server_activate()
|
||||
- get_request() -> request, client_address
|
||||
- handle_timeout()
|
||||
- verify_request(request, client_address)
|
||||
- server_close()
|
||||
- process_request(request, client_address)
|
||||
- shutdown_request(request)
|
||||
- close_request(request)
|
||||
- handle_error()
|
||||
|
||||
Methods for derived classes:
|
||||
|
||||
- finish_request(request, client_address)
|
||||
|
||||
Class variables that may be overridden by derived classes or
|
||||
instances:
|
||||
|
||||
- timeout
|
||||
- address_family
|
||||
- socket_type
|
||||
- allow_reuse_address
|
||||
|
||||
Instance variables:
|
||||
|
||||
- RequestHandlerClass
|
||||
- socket
|
||||
|
||||
"""
|
||||
|
||||
timeout = None
|
||||
|
||||
def __init__(self, server_address, RequestHandlerClass):
|
||||
"""Constructor. May be extended, do not override."""
|
||||
self.server_address = server_address
|
||||
self.RequestHandlerClass = RequestHandlerClass
|
||||
self.__is_shut_down = threading.Event()
|
||||
self.__shutdown_request = False
|
||||
|
||||
def server_activate(self):
|
||||
"""Called by constructor to activate the server.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
def serve_forever(self, poll_interval=0.5):
|
||||
"""Handle one request at a time until shutdown.
|
||||
|
||||
Polls for shutdown every poll_interval seconds. Ignores
|
||||
self.timeout. If you need to do periodic tasks, do them in
|
||||
another thread.
|
||||
"""
|
||||
self.__is_shut_down.clear()
|
||||
try:
|
||||
while not self.__shutdown_request:
|
||||
# XXX: Consider using another file descriptor or
|
||||
# connecting to the socket to wake this up instead of
|
||||
# polling. Polling reduces our responsiveness to a
|
||||
# shutdown request and wastes cpu at all other times.
|
||||
r, w, e = _eintr_retry(select.select, [self], [], [],
|
||||
poll_interval)
|
||||
if self in r:
|
||||
self._handle_request_noblock()
|
||||
finally:
|
||||
self.__shutdown_request = False
|
||||
self.__is_shut_down.set()
|
||||
|
||||
def shutdown(self):
|
||||
"""Stops the serve_forever loop.
|
||||
|
||||
Blocks until the loop has finished. This must be called while
|
||||
serve_forever() is running in another thread, or it will
|
||||
deadlock.
|
||||
"""
|
||||
self.__shutdown_request = True
|
||||
self.__is_shut_down.wait()
|
||||
|
||||
# The distinction between handling, getting, processing and
|
||||
# finishing a request is fairly arbitrary. Remember:
|
||||
#
|
||||
# - handle_request() is the top-level call. It calls
|
||||
# select, get_request(), verify_request() and process_request()
|
||||
# - get_request() is different for stream or datagram sockets
|
||||
# - process_request() is the place that may fork a new process
|
||||
# or create a new thread to finish the request
|
||||
# - finish_request() instantiates the request handler class;
|
||||
# this constructor will handle the request all by itself
|
||||
|
||||
def handle_request(self):
|
||||
"""Handle one request, possibly blocking.
|
||||
|
||||
Respects self.timeout.
|
||||
"""
|
||||
# Support people who used socket.settimeout() to escape
|
||||
# handle_request before self.timeout was available.
|
||||
timeout = self.socket.gettimeout()
|
||||
if timeout is None:
|
||||
timeout = self.timeout
|
||||
elif self.timeout is not None:
|
||||
timeout = min(timeout, self.timeout)
|
||||
fd_sets = _eintr_retry(select.select, [self], [], [], timeout)
|
||||
if not fd_sets[0]:
|
||||
self.handle_timeout()
|
||||
return
|
||||
self._handle_request_noblock()
|
||||
|
||||
def _handle_request_noblock(self):
|
||||
"""Handle one request, without blocking.
|
||||
|
||||
I assume that select.select has returned that the socket is
|
||||
readable before this function was called, so there should be
|
||||
no risk of blocking in get_request().
|
||||
"""
|
||||
try:
|
||||
request, client_address = self.get_request()
|
||||
except socket.error:
|
||||
return
|
||||
if self.verify_request(request, client_address):
|
||||
try:
|
||||
self.process_request(request, client_address)
|
||||
except:
|
||||
self.handle_error(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
|
||||
def handle_timeout(self):
|
||||
"""Called if no new request arrives within self.timeout.
|
||||
|
||||
Overridden by ForkingMixIn.
|
||||
"""
|
||||
pass
|
||||
|
||||
def verify_request(self, request, client_address):
|
||||
"""Verify the request. May be overridden.
|
||||
|
||||
Return True if we should proceed with this request.
|
||||
|
||||
"""
|
||||
return True
|
||||
|
||||
def process_request(self, request, client_address):
|
||||
"""Call finish_request.
|
||||
|
||||
Overridden by ForkingMixIn and ThreadingMixIn.
|
||||
|
||||
"""
|
||||
self.finish_request(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
|
||||
def server_close(self):
|
||||
"""Called to clean-up the server.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
def finish_request(self, request, client_address):
|
||||
"""Finish one request by instantiating RequestHandlerClass."""
|
||||
self.RequestHandlerClass(request, client_address, self)
|
||||
|
||||
def shutdown_request(self, request):
|
||||
"""Called to shutdown and close an individual request."""
|
||||
self.close_request(request)
|
||||
|
||||
def close_request(self, request):
|
||||
"""Called to clean up an individual request."""
|
||||
pass
|
||||
|
||||
def handle_error(self, request, client_address):
|
||||
"""Handle an error gracefully. May be overridden.
|
||||
|
||||
The default is to print a traceback and continue.
|
||||
|
||||
"""
|
||||
print '-'*40
|
||||
print 'Exception happened during processing of request from',
|
||||
print client_address
|
||||
import traceback
|
||||
traceback.print_exc() # XXX But this goes to stderr!
|
||||
print '-'*40
|
||||
|
||||
|
||||
class TCPServer(BaseServer):
|
||||
|
||||
"""Base class for various socket-based server classes.
|
||||
|
||||
Defaults to synchronous IP stream (i.e., TCP).
|
||||
|
||||
Methods for the caller:
|
||||
|
||||
- __init__(server_address, RequestHandlerClass, bind_and_activate=True)
|
||||
- serve_forever(poll_interval=0.5)
|
||||
- shutdown()
|
||||
- handle_request() # if you don't use serve_forever()
|
||||
- fileno() -> int # for select()
|
||||
|
||||
Methods that may be overridden:
|
||||
|
||||
- server_bind()
|
||||
- server_activate()
|
||||
- get_request() -> request, client_address
|
||||
- handle_timeout()
|
||||
- verify_request(request, client_address)
|
||||
- process_request(request, client_address)
|
||||
- shutdown_request(request)
|
||||
- close_request(request)
|
||||
- handle_error()
|
||||
|
||||
Methods for derived classes:
|
||||
|
||||
- finish_request(request, client_address)
|
||||
|
||||
Class variables that may be overridden by derived classes or
|
||||
instances:
|
||||
|
||||
- timeout
|
||||
- address_family
|
||||
- socket_type
|
||||
- request_queue_size (only for stream sockets)
|
||||
- allow_reuse_address
|
||||
|
||||
Instance variables:
|
||||
|
||||
- server_address
|
||||
- RequestHandlerClass
|
||||
- socket
|
||||
|
||||
"""
|
||||
|
||||
address_family = socket.AF_INET
|
||||
|
||||
socket_type = socket.SOCK_STREAM
|
||||
|
||||
request_queue_size = 5
|
||||
|
||||
allow_reuse_address = False
|
||||
|
||||
def __init__(self, server_address, RequestHandlerClass, bind_and_activate=True):
|
||||
"""Constructor. May be extended, do not override."""
|
||||
BaseServer.__init__(self, server_address, RequestHandlerClass)
|
||||
self.socket = socket.socket(self.address_family,
|
||||
self.socket_type)
|
||||
if bind_and_activate:
|
||||
try:
|
||||
self.server_bind()
|
||||
self.server_activate()
|
||||
except:
|
||||
self.server_close()
|
||||
raise
|
||||
|
||||
def server_bind(self):
|
||||
"""Called by constructor to bind the socket.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
if self.allow_reuse_address:
|
||||
self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
|
||||
self.socket.bind(self.server_address)
|
||||
self.server_address = self.socket.getsockname()
|
||||
|
||||
def server_activate(self):
|
||||
"""Called by constructor to activate the server.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
self.socket.listen(self.request_queue_size)
|
||||
|
||||
def server_close(self):
|
||||
"""Called to clean-up the server.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
self.socket.close()
|
||||
|
||||
def fileno(self):
|
||||
"""Return socket file number.
|
||||
|
||||
Interface required by select().
|
||||
|
||||
"""
|
||||
return self.socket.fileno()
|
||||
|
||||
def get_request(self):
|
||||
"""Get the request and client address from the socket.
|
||||
|
||||
May be overridden.
|
||||
|
||||
"""
|
||||
return self.socket.accept()
|
||||
|
||||
def shutdown_request(self, request):
|
||||
"""Called to shutdown and close an individual request."""
|
||||
try:
|
||||
#explicitly shutdown. socket.close() merely releases
|
||||
#the socket and waits for GC to perform the actual close.
|
||||
request.shutdown(socket.SHUT_WR)
|
||||
except socket.error:
|
||||
pass #some platforms may raise ENOTCONN here
|
||||
self.close_request(request)
|
||||
|
||||
def close_request(self, request):
|
||||
"""Called to clean up an individual request."""
|
||||
request.close()
|
||||
|
||||
|
||||
class UDPServer(TCPServer):
|
||||
|
||||
"""UDP server class."""
|
||||
|
||||
allow_reuse_address = False
|
||||
|
||||
socket_type = socket.SOCK_DGRAM
|
||||
|
||||
max_packet_size = 8192
|
||||
|
||||
def get_request(self):
|
||||
data, client_addr = self.socket.recvfrom(self.max_packet_size)
|
||||
return (data, self.socket), client_addr
|
||||
|
||||
def server_activate(self):
|
||||
# No need to call listen() for UDP.
|
||||
pass
|
||||
|
||||
def shutdown_request(self, request):
|
||||
# No need to shutdown anything.
|
||||
self.close_request(request)
|
||||
|
||||
def close_request(self, request):
|
||||
# No need to close anything.
|
||||
pass
|
||||
|
||||
class ForkingMixIn:
|
||||
|
||||
"""Mix-in class to handle each request in a new process."""
|
||||
|
||||
timeout = 300
|
||||
active_children = None
|
||||
max_children = 40
|
||||
|
||||
def collect_children(self):
|
||||
"""Internal routine to wait for children that have exited."""
|
||||
if self.active_children is None:
|
||||
return
|
||||
|
||||
# If we're above the max number of children, wait and reap them until
|
||||
# we go back below threshold. Note that we use waitpid(-1) below to be
|
||||
# able to collect children in size(<defunct children>) syscalls instead
|
||||
# of size(<children>): the downside is that this might reap children
|
||||
# which we didn't spawn, which is why we only resort to this when we're
|
||||
# above max_children.
|
||||
while len(self.active_children) >= self.max_children:
|
||||
try:
|
||||
pid, _ = os.waitpid(-1, 0)
|
||||
self.active_children.discard(pid)
|
||||
except OSError as e:
|
||||
if e.errno == errno.ECHILD:
|
||||
# we don't have any children, we're done
|
||||
self.active_children.clear()
|
||||
elif e.errno != errno.EINTR:
|
||||
break
|
||||
|
||||
# Now reap all defunct children.
|
||||
for pid in self.active_children.copy():
|
||||
try:
|
||||
pid, _ = os.waitpid(pid, os.WNOHANG)
|
||||
# if the child hasn't exited yet, pid will be 0 and ignored by
|
||||
# discard() below
|
||||
self.active_children.discard(pid)
|
||||
except OSError as e:
|
||||
if e.errno == errno.ECHILD:
|
||||
# someone else reaped it
|
||||
self.active_children.discard(pid)
|
||||
|
||||
def handle_timeout(self):
|
||||
"""Wait for zombies after self.timeout seconds of inactivity.
|
||||
|
||||
May be extended, do not override.
|
||||
"""
|
||||
self.collect_children()
|
||||
|
||||
def process_request(self, request, client_address):
|
||||
"""Fork a new subprocess to process the request."""
|
||||
self.collect_children()
|
||||
pid = os.fork()
|
||||
if pid:
|
||||
# Parent process
|
||||
if self.active_children is None:
|
||||
self.active_children = set()
|
||||
self.active_children.add(pid)
|
||||
self.close_request(request) #close handle in parent process
|
||||
return
|
||||
else:
|
||||
# Child process.
|
||||
# This must never return, hence os._exit()!
|
||||
try:
|
||||
self.finish_request(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
os._exit(0)
|
||||
except:
|
||||
try:
|
||||
self.handle_error(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
finally:
|
||||
os._exit(1)
|
||||
|
||||
|
||||
class ThreadingMixIn:
|
||||
"""Mix-in class to handle each request in a new thread."""
|
||||
|
||||
# Decides how threads will act upon termination of the
|
||||
# main process
|
||||
daemon_threads = False
|
||||
|
||||
def process_request_thread(self, request, client_address):
|
||||
"""Same as in BaseServer but as a thread.
|
||||
|
||||
In addition, exception handling is done here.
|
||||
|
||||
"""
|
||||
try:
|
||||
self.finish_request(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
except:
|
||||
self.handle_error(request, client_address)
|
||||
self.shutdown_request(request)
|
||||
|
||||
def process_request(self, request, client_address):
|
||||
"""Start a new thread to process the request."""
|
||||
t = threading.Thread(target = self.process_request_thread,
|
||||
args = (request, client_address))
|
||||
t.daemon = self.daemon_threads
|
||||
t.start()
|
||||
|
||||
|
||||
class ForkingUDPServer(ForkingMixIn, UDPServer): pass
|
||||
class ForkingTCPServer(ForkingMixIn, TCPServer): pass
|
||||
|
||||
class ThreadingUDPServer(ThreadingMixIn, UDPServer): pass
|
||||
class ThreadingTCPServer(ThreadingMixIn, TCPServer): pass
|
||||
|
||||
if hasattr(socket, 'AF_UNIX'):
|
||||
|
||||
class UnixStreamServer(TCPServer):
|
||||
address_family = socket.AF_UNIX
|
||||
|
||||
class UnixDatagramServer(UDPServer):
|
||||
address_family = socket.AF_UNIX
|
||||
|
||||
class ThreadingUnixStreamServer(ThreadingMixIn, UnixStreamServer): pass
|
||||
|
||||
class ThreadingUnixDatagramServer(ThreadingMixIn, UnixDatagramServer): pass
|
||||
|
||||
class BaseRequestHandler:
|
||||
|
||||
"""Base class for request handler classes.
|
||||
|
||||
This class is instantiated for each request to be handled. The
|
||||
constructor sets the instance variables request, client_address
|
||||
and server, and then calls the handle() method. To implement a
|
||||
specific service, all you need to do is to derive a class which
|
||||
defines a handle() method.
|
||||
|
||||
The handle() method can find the request as self.request, the
|
||||
client address as self.client_address, and the server (in case it
|
||||
needs access to per-server information) as self.server. Since a
|
||||
separate instance is created for each request, the handle() method
|
||||
can define arbitrary other instance variariables.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, request, client_address, server):
|
||||
self.request = request
|
||||
self.client_address = client_address
|
||||
self.server = server
|
||||
self.setup()
|
||||
try:
|
||||
self.handle()
|
||||
finally:
|
||||
self.finish()
|
||||
|
||||
def setup(self):
|
||||
pass
|
||||
|
||||
def handle(self):
|
||||
pass
|
||||
|
||||
def finish(self):
|
||||
pass
|
||||
|
||||
|
||||
# The following two classes make it possible to use the same service
|
||||
# class for stream or datagram servers.
|
||||
# Each class sets up these instance variables:
|
||||
# - rfile: a file object from which receives the request is read
|
||||
# - wfile: a file object to which the reply is written
|
||||
# When the handle() method returns, wfile is flushed properly
|
||||
|
||||
|
||||
class StreamRequestHandler(BaseRequestHandler):
|
||||
|
||||
"""Define self.rfile and self.wfile for stream sockets."""
|
||||
|
||||
# Default buffer sizes for rfile, wfile.
|
||||
# We default rfile to buffered because otherwise it could be
|
||||
# really slow for large data (a getc() call per byte); we make
|
||||
# wfile unbuffered because (a) often after a write() we want to
|
||||
# read and we need to flush the line; (b) big writes to unbuffered
|
||||
# files are typically optimized by stdio even when big reads
|
||||
# aren't.
|
||||
rbufsize = -1
|
||||
wbufsize = 0
|
||||
|
||||
# A timeout to apply to the request socket, if not None.
|
||||
timeout = None
|
||||
|
||||
# Disable nagle algorithm for this socket, if True.
|
||||
# Use only when wbufsize != 0, to avoid small packets.
|
||||
disable_nagle_algorithm = False
|
||||
|
||||
def setup(self):
|
||||
self.connection = self.request
|
||||
if self.timeout is not None:
|
||||
self.connection.settimeout(self.timeout)
|
||||
if self.disable_nagle_algorithm:
|
||||
self.connection.setsockopt(socket.IPPROTO_TCP,
|
||||
socket.TCP_NODELAY, True)
|
||||
self.rfile = self.connection.makefile('rb', self.rbufsize)
|
||||
self.wfile = self.connection.makefile('wb', self.wbufsize)
|
||||
|
||||
def finish(self):
|
||||
if not self.wfile.closed:
|
||||
try:
|
||||
self.wfile.flush()
|
||||
except socket.error:
|
||||
# An final socket error may have occurred here, such as
|
||||
# the local error ECONNABORTED.
|
||||
pass
|
||||
self.wfile.close()
|
||||
self.rfile.close()
|
||||
|
||||
|
||||
class DatagramRequestHandler(BaseRequestHandler):
|
||||
|
||||
# XXX Regrettably, I cannot get this working on Linux;
|
||||
# s.recvfrom() doesn't return a meaningful client address.
|
||||
|
||||
"""Define self.rfile and self.wfile for datagram sockets."""
|
||||
|
||||
def setup(self):
|
||||
try:
|
||||
from cStringIO import StringIO
|
||||
except ImportError:
|
||||
from StringIO import StringIO
|
||||
self.packet, self.socket = self.request
|
||||
self.rfile = StringIO(self.packet)
|
||||
self.wfile = StringIO()
|
||||
|
||||
def finish(self):
|
||||
self.socket.sendto(self.wfile.getvalue(), self.client_address)
|
||||
324
AppPkg/Applications/Python/Python-2.7.10/Lib/StringIO.py
Normal file
324
AppPkg/Applications/Python/Python-2.7.10/Lib/StringIO.py
Normal file
@@ -0,0 +1,324 @@
|
||||
r"""File-like objects that read from or write to a string buffer.
|
||||
|
||||
This implements (nearly) all stdio methods.
|
||||
|
||||
f = StringIO() # ready for writing
|
||||
f = StringIO(buf) # ready for reading
|
||||
f.close() # explicitly release resources held
|
||||
flag = f.isatty() # always false
|
||||
pos = f.tell() # get current position
|
||||
f.seek(pos) # set current position
|
||||
f.seek(pos, mode) # mode 0: absolute; 1: relative; 2: relative to EOF
|
||||
buf = f.read() # read until EOF
|
||||
buf = f.read(n) # read up to n bytes
|
||||
buf = f.readline() # read until end of line ('\n') or EOF
|
||||
list = f.readlines()# list of f.readline() results until EOF
|
||||
f.truncate([size]) # truncate file at to at most size (default: current pos)
|
||||
f.write(buf) # write at current position
|
||||
f.writelines(list) # for line in list: f.write(line)
|
||||
f.getvalue() # return whole file's contents as a string
|
||||
|
||||
Notes:
|
||||
- Using a real file is often faster (but less convenient).
|
||||
- There's also a much faster implementation in C, called cStringIO, but
|
||||
it's not subclassable.
|
||||
- fileno() is left unimplemented so that code which uses it triggers
|
||||
an exception early.
|
||||
- Seeking far beyond EOF and then writing will insert real null
|
||||
bytes that occupy space in the buffer.
|
||||
- There's a simple test set (see end of this file).
|
||||
"""
|
||||
try:
|
||||
from errno import EINVAL
|
||||
except ImportError:
|
||||
EINVAL = 22
|
||||
|
||||
__all__ = ["StringIO"]
|
||||
|
||||
def _complain_ifclosed(closed):
|
||||
if closed:
|
||||
raise ValueError, "I/O operation on closed file"
|
||||
|
||||
class StringIO:
|
||||
"""class StringIO([buffer])
|
||||
|
||||
When a StringIO object is created, it can be initialized to an existing
|
||||
string by passing the string to the constructor. If no string is given,
|
||||
the StringIO will start empty.
|
||||
|
||||
The StringIO object can accept either Unicode or 8-bit strings, but
|
||||
mixing the two may take some care. If both are used, 8-bit strings that
|
||||
cannot be interpreted as 7-bit ASCII (that use the 8th bit) will cause
|
||||
a UnicodeError to be raised when getvalue() is called.
|
||||
"""
|
||||
def __init__(self, buf = ''):
|
||||
# Force self.buf to be a string or unicode
|
||||
if not isinstance(buf, basestring):
|
||||
buf = str(buf)
|
||||
self.buf = buf
|
||||
self.len = len(buf)
|
||||
self.buflist = []
|
||||
self.pos = 0
|
||||
self.closed = False
|
||||
self.softspace = 0
|
||||
|
||||
def __iter__(self):
|
||||
return self
|
||||
|
||||
def next(self):
|
||||
"""A file object is its own iterator, for example iter(f) returns f
|
||||
(unless f is closed). When a file is used as an iterator, typically
|
||||
in a for loop (for example, for line in f: print line), the next()
|
||||
method is called repeatedly. This method returns the next input line,
|
||||
or raises StopIteration when EOF is hit.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
r = self.readline()
|
||||
if not r:
|
||||
raise StopIteration
|
||||
return r
|
||||
|
||||
def close(self):
|
||||
"""Free the memory buffer.
|
||||
"""
|
||||
if not self.closed:
|
||||
self.closed = True
|
||||
del self.buf, self.pos
|
||||
|
||||
def isatty(self):
|
||||
"""Returns False because StringIO objects are not connected to a
|
||||
tty-like device.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
return False
|
||||
|
||||
def seek(self, pos, mode = 0):
|
||||
"""Set the file's current position.
|
||||
|
||||
The mode argument is optional and defaults to 0 (absolute file
|
||||
positioning); other values are 1 (seek relative to the current
|
||||
position) and 2 (seek relative to the file's end).
|
||||
|
||||
There is no return value.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if self.buflist:
|
||||
self.buf += ''.join(self.buflist)
|
||||
self.buflist = []
|
||||
if mode == 1:
|
||||
pos += self.pos
|
||||
elif mode == 2:
|
||||
pos += self.len
|
||||
self.pos = max(0, pos)
|
||||
|
||||
def tell(self):
|
||||
"""Return the file's current position."""
|
||||
_complain_ifclosed(self.closed)
|
||||
return self.pos
|
||||
|
||||
def read(self, n = -1):
|
||||
"""Read at most size bytes from the file
|
||||
(less if the read hits EOF before obtaining size bytes).
|
||||
|
||||
If the size argument is negative or omitted, read all data until EOF
|
||||
is reached. The bytes are returned as a string object. An empty
|
||||
string is returned when EOF is encountered immediately.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if self.buflist:
|
||||
self.buf += ''.join(self.buflist)
|
||||
self.buflist = []
|
||||
if n is None or n < 0:
|
||||
newpos = self.len
|
||||
else:
|
||||
newpos = min(self.pos+n, self.len)
|
||||
r = self.buf[self.pos:newpos]
|
||||
self.pos = newpos
|
||||
return r
|
||||
|
||||
def readline(self, length=None):
|
||||
r"""Read one entire line from the file.
|
||||
|
||||
A trailing newline character is kept in the string (but may be absent
|
||||
when a file ends with an incomplete line). If the size argument is
|
||||
present and non-negative, it is a maximum byte count (including the
|
||||
trailing newline) and an incomplete line may be returned.
|
||||
|
||||
An empty string is returned only when EOF is encountered immediately.
|
||||
|
||||
Note: Unlike stdio's fgets(), the returned string contains null
|
||||
characters ('\0') if they occurred in the input.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if self.buflist:
|
||||
self.buf += ''.join(self.buflist)
|
||||
self.buflist = []
|
||||
i = self.buf.find('\n', self.pos)
|
||||
if i < 0:
|
||||
newpos = self.len
|
||||
else:
|
||||
newpos = i+1
|
||||
if length is not None and length >= 0:
|
||||
if self.pos + length < newpos:
|
||||
newpos = self.pos + length
|
||||
r = self.buf[self.pos:newpos]
|
||||
self.pos = newpos
|
||||
return r
|
||||
|
||||
def readlines(self, sizehint = 0):
|
||||
"""Read until EOF using readline() and return a list containing the
|
||||
lines thus read.
|
||||
|
||||
If the optional sizehint argument is present, instead of reading up
|
||||
to EOF, whole lines totalling approximately sizehint bytes (or more
|
||||
to accommodate a final whole line).
|
||||
"""
|
||||
total = 0
|
||||
lines = []
|
||||
line = self.readline()
|
||||
while line:
|
||||
lines.append(line)
|
||||
total += len(line)
|
||||
if 0 < sizehint <= total:
|
||||
break
|
||||
line = self.readline()
|
||||
return lines
|
||||
|
||||
def truncate(self, size=None):
|
||||
"""Truncate the file's size.
|
||||
|
||||
If the optional size argument is present, the file is truncated to
|
||||
(at most) that size. The size defaults to the current position.
|
||||
The current file position is not changed unless the position
|
||||
is beyond the new file size.
|
||||
|
||||
If the specified size exceeds the file's current size, the
|
||||
file remains unchanged.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if size is None:
|
||||
size = self.pos
|
||||
elif size < 0:
|
||||
raise IOError(EINVAL, "Negative size not allowed")
|
||||
elif size < self.pos:
|
||||
self.pos = size
|
||||
self.buf = self.getvalue()[:size]
|
||||
self.len = size
|
||||
|
||||
def write(self, s):
|
||||
"""Write a string to the file.
|
||||
|
||||
There is no return value.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if not s: return
|
||||
# Force s to be a string or unicode
|
||||
if not isinstance(s, basestring):
|
||||
s = str(s)
|
||||
spos = self.pos
|
||||
slen = self.len
|
||||
if spos == slen:
|
||||
self.buflist.append(s)
|
||||
self.len = self.pos = spos + len(s)
|
||||
return
|
||||
if spos > slen:
|
||||
self.buflist.append('\0'*(spos - slen))
|
||||
slen = spos
|
||||
newpos = spos + len(s)
|
||||
if spos < slen:
|
||||
if self.buflist:
|
||||
self.buf += ''.join(self.buflist)
|
||||
self.buflist = [self.buf[:spos], s, self.buf[newpos:]]
|
||||
self.buf = ''
|
||||
if newpos > slen:
|
||||
slen = newpos
|
||||
else:
|
||||
self.buflist.append(s)
|
||||
slen = newpos
|
||||
self.len = slen
|
||||
self.pos = newpos
|
||||
|
||||
def writelines(self, iterable):
|
||||
"""Write a sequence of strings to the file. The sequence can be any
|
||||
iterable object producing strings, typically a list of strings. There
|
||||
is no return value.
|
||||
|
||||
(The name is intended to match readlines(); writelines() does not add
|
||||
line separators.)
|
||||
"""
|
||||
write = self.write
|
||||
for line in iterable:
|
||||
write(line)
|
||||
|
||||
def flush(self):
|
||||
"""Flush the internal buffer
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
|
||||
def getvalue(self):
|
||||
"""
|
||||
Retrieve the entire contents of the "file" at any time before
|
||||
the StringIO object's close() method is called.
|
||||
|
||||
The StringIO object can accept either Unicode or 8-bit strings,
|
||||
but mixing the two may take some care. If both are used, 8-bit
|
||||
strings that cannot be interpreted as 7-bit ASCII (that use the
|
||||
8th bit) will cause a UnicodeError to be raised when getvalue()
|
||||
is called.
|
||||
"""
|
||||
_complain_ifclosed(self.closed)
|
||||
if self.buflist:
|
||||
self.buf += ''.join(self.buflist)
|
||||
self.buflist = []
|
||||
return self.buf
|
||||
|
||||
|
||||
# A little test suite
|
||||
|
||||
def test():
|
||||
import sys
|
||||
if sys.argv[1:]:
|
||||
file = sys.argv[1]
|
||||
else:
|
||||
file = '/etc/passwd'
|
||||
lines = open(file, 'r').readlines()
|
||||
text = open(file, 'r').read()
|
||||
f = StringIO()
|
||||
for line in lines[:-2]:
|
||||
f.write(line)
|
||||
f.writelines(lines[-2:])
|
||||
if f.getvalue() != text:
|
||||
raise RuntimeError, 'write failed'
|
||||
length = f.tell()
|
||||
print 'File length =', length
|
||||
f.seek(len(lines[0]))
|
||||
f.write(lines[1])
|
||||
f.seek(0)
|
||||
print 'First line =', repr(f.readline())
|
||||
print 'Position =', f.tell()
|
||||
line = f.readline()
|
||||
print 'Second line =', repr(line)
|
||||
f.seek(-len(line), 1)
|
||||
line2 = f.read(len(line))
|
||||
if line != line2:
|
||||
raise RuntimeError, 'bad result after seek back'
|
||||
f.seek(len(line2), 1)
|
||||
list = f.readlines()
|
||||
line = list[-1]
|
||||
f.seek(f.tell() - len(line))
|
||||
line2 = f.read()
|
||||
if line != line2:
|
||||
raise RuntimeError, 'bad result after seek back from EOF'
|
||||
print 'Read', len(list), 'more lines'
|
||||
print 'File length =', f.tell()
|
||||
if f.tell() != length:
|
||||
raise RuntimeError, 'bad length'
|
||||
f.truncate(length/2)
|
||||
f.seek(0, 2)
|
||||
print 'Truncated length =', f.tell()
|
||||
if f.tell() != length/2:
|
||||
raise RuntimeError, 'truncate did not adjust length'
|
||||
f.close()
|
||||
|
||||
if __name__ == '__main__':
|
||||
test()
|
||||
180
AppPkg/Applications/Python/Python-2.7.10/Lib/UserDict.py
Normal file
180
AppPkg/Applications/Python/Python-2.7.10/Lib/UserDict.py
Normal file
@@ -0,0 +1,180 @@
|
||||
"""A more or less complete user-defined wrapper around dictionary objects."""
|
||||
|
||||
class UserDict:
|
||||
def __init__(self, dict=None, **kwargs):
|
||||
self.data = {}
|
||||
if dict is not None:
|
||||
self.update(dict)
|
||||
if len(kwargs):
|
||||
self.update(kwargs)
|
||||
def __repr__(self): return repr(self.data)
|
||||
def __cmp__(self, dict):
|
||||
if isinstance(dict, UserDict):
|
||||
return cmp(self.data, dict.data)
|
||||
else:
|
||||
return cmp(self.data, dict)
|
||||
__hash__ = None # Avoid Py3k warning
|
||||
def __len__(self): return len(self.data)
|
||||
def __getitem__(self, key):
|
||||
if key in self.data:
|
||||
return self.data[key]
|
||||
if hasattr(self.__class__, "__missing__"):
|
||||
return self.__class__.__missing__(self, key)
|
||||
raise KeyError(key)
|
||||
def __setitem__(self, key, item): self.data[key] = item
|
||||
def __delitem__(self, key): del self.data[key]
|
||||
def clear(self): self.data.clear()
|
||||
def copy(self):
|
||||
if self.__class__ is UserDict:
|
||||
return UserDict(self.data.copy())
|
||||
import copy
|
||||
data = self.data
|
||||
try:
|
||||
self.data = {}
|
||||
c = copy.copy(self)
|
||||
finally:
|
||||
self.data = data
|
||||
c.update(self)
|
||||
return c
|
||||
def keys(self): return self.data.keys()
|
||||
def items(self): return self.data.items()
|
||||
def iteritems(self): return self.data.iteritems()
|
||||
def iterkeys(self): return self.data.iterkeys()
|
||||
def itervalues(self): return self.data.itervalues()
|
||||
def values(self): return self.data.values()
|
||||
def has_key(self, key): return key in self.data
|
||||
def update(self, dict=None, **kwargs):
|
||||
if dict is None:
|
||||
pass
|
||||
elif isinstance(dict, UserDict):
|
||||
self.data.update(dict.data)
|
||||
elif isinstance(dict, type({})) or not hasattr(dict, 'items'):
|
||||
self.data.update(dict)
|
||||
else:
|
||||
for k, v in dict.items():
|
||||
self[k] = v
|
||||
if len(kwargs):
|
||||
self.data.update(kwargs)
|
||||
def get(self, key, failobj=None):
|
||||
if key not in self:
|
||||
return failobj
|
||||
return self[key]
|
||||
def setdefault(self, key, failobj=None):
|
||||
if key not in self:
|
||||
self[key] = failobj
|
||||
return self[key]
|
||||
def pop(self, key, *args):
|
||||
return self.data.pop(key, *args)
|
||||
def popitem(self):
|
||||
return self.data.popitem()
|
||||
def __contains__(self, key):
|
||||
return key in self.data
|
||||
@classmethod
|
||||
def fromkeys(cls, iterable, value=None):
|
||||
d = cls()
|
||||
for key in iterable:
|
||||
d[key] = value
|
||||
return d
|
||||
|
||||
class IterableUserDict(UserDict):
|
||||
def __iter__(self):
|
||||
return iter(self.data)
|
||||
|
||||
import _abcoll
|
||||
_abcoll.MutableMapping.register(IterableUserDict)
|
||||
|
||||
|
||||
class DictMixin:
|
||||
# Mixin defining all dictionary methods for classes that already have
|
||||
# a minimum dictionary interface including getitem, setitem, delitem,
|
||||
# and keys. Without knowledge of the subclass constructor, the mixin
|
||||
# does not define __init__() or copy(). In addition to the four base
|
||||
# methods, progressively more efficiency comes with defining
|
||||
# __contains__(), __iter__(), and iteritems().
|
||||
|
||||
# second level definitions support higher levels
|
||||
def __iter__(self):
|
||||
for k in self.keys():
|
||||
yield k
|
||||
def has_key(self, key):
|
||||
try:
|
||||
self[key]
|
||||
except KeyError:
|
||||
return False
|
||||
return True
|
||||
def __contains__(self, key):
|
||||
return self.has_key(key)
|
||||
|
||||
# third level takes advantage of second level definitions
|
||||
def iteritems(self):
|
||||
for k in self:
|
||||
yield (k, self[k])
|
||||
def iterkeys(self):
|
||||
return self.__iter__()
|
||||
|
||||
# fourth level uses definitions from lower levels
|
||||
def itervalues(self):
|
||||
for _, v in self.iteritems():
|
||||
yield v
|
||||
def values(self):
|
||||
return [v for _, v in self.iteritems()]
|
||||
def items(self):
|
||||
return list(self.iteritems())
|
||||
def clear(self):
|
||||
for key in self.keys():
|
||||
del self[key]
|
||||
def setdefault(self, key, default=None):
|
||||
try:
|
||||
return self[key]
|
||||
except KeyError:
|
||||
self[key] = default
|
||||
return default
|
||||
def pop(self, key, *args):
|
||||
if len(args) > 1:
|
||||
raise TypeError, "pop expected at most 2 arguments, got "\
|
||||
+ repr(1 + len(args))
|
||||
try:
|
||||
value = self[key]
|
||||
except KeyError:
|
||||
if args:
|
||||
return args[0]
|
||||
raise
|
||||
del self[key]
|
||||
return value
|
||||
def popitem(self):
|
||||
try:
|
||||
k, v = self.iteritems().next()
|
||||
except StopIteration:
|
||||
raise KeyError, 'container is empty'
|
||||
del self[k]
|
||||
return (k, v)
|
||||
def update(self, other=None, **kwargs):
|
||||
# Make progressively weaker assumptions about "other"
|
||||
if other is None:
|
||||
pass
|
||||
elif hasattr(other, 'iteritems'): # iteritems saves memory and lookups
|
||||
for k, v in other.iteritems():
|
||||
self[k] = v
|
||||
elif hasattr(other, 'keys'):
|
||||
for k in other.keys():
|
||||
self[k] = other[k]
|
||||
else:
|
||||
for k, v in other:
|
||||
self[k] = v
|
||||
if kwargs:
|
||||
self.update(kwargs)
|
||||
def get(self, key, default=None):
|
||||
try:
|
||||
return self[key]
|
||||
except KeyError:
|
||||
return default
|
||||
def __repr__(self):
|
||||
return repr(dict(self.iteritems()))
|
||||
def __cmp__(self, other):
|
||||
if other is None:
|
||||
return 1
|
||||
if isinstance(other, DictMixin):
|
||||
other = dict(other.iteritems())
|
||||
return cmp(dict(self.iteritems()), other)
|
||||
def __len__(self):
|
||||
return len(self.keys())
|
||||
692
AppPkg/Applications/Python/Python-2.7.10/Lib/_abcoll.py
Normal file
692
AppPkg/Applications/Python/Python-2.7.10/Lib/_abcoll.py
Normal file
@@ -0,0 +1,692 @@
|
||||
# Copyright 2007 Google, Inc. All Rights Reserved.
|
||||
# Licensed to PSF under a Contributor Agreement.
|
||||
|
||||
"""Abstract Base Classes (ABCs) for collections, according to PEP 3119.
|
||||
|
||||
DON'T USE THIS MODULE DIRECTLY! The classes here should be imported
|
||||
via collections; they are defined here only to alleviate certain
|
||||
bootstrapping issues. Unit tests are in test_collections.
|
||||
"""
|
||||
|
||||
from abc import ABCMeta, abstractmethod
|
||||
import sys
|
||||
|
||||
__all__ = ["Hashable", "Iterable", "Iterator",
|
||||
"Sized", "Container", "Callable",
|
||||
"Set", "MutableSet",
|
||||
"Mapping", "MutableMapping",
|
||||
"MappingView", "KeysView", "ItemsView", "ValuesView",
|
||||
"Sequence", "MutableSequence",
|
||||
]
|
||||
|
||||
### ONE-TRICK PONIES ###
|
||||
|
||||
def _hasattr(C, attr):
|
||||
try:
|
||||
return any(attr in B.__dict__ for B in C.__mro__)
|
||||
except AttributeError:
|
||||
# Old-style class
|
||||
return hasattr(C, attr)
|
||||
|
||||
|
||||
class Hashable:
|
||||
__metaclass__ = ABCMeta
|
||||
|
||||
@abstractmethod
|
||||
def __hash__(self):
|
||||
return 0
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Hashable:
|
||||
try:
|
||||
for B in C.__mro__:
|
||||
if "__hash__" in B.__dict__:
|
||||
if B.__dict__["__hash__"]:
|
||||
return True
|
||||
break
|
||||
except AttributeError:
|
||||
# Old-style class
|
||||
if getattr(C, "__hash__", None):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
|
||||
class Iterable:
|
||||
__metaclass__ = ABCMeta
|
||||
|
||||
@abstractmethod
|
||||
def __iter__(self):
|
||||
while False:
|
||||
yield None
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Iterable:
|
||||
if _hasattr(C, "__iter__"):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
Iterable.register(str)
|
||||
|
||||
|
||||
class Iterator(Iterable):
|
||||
|
||||
@abstractmethod
|
||||
def next(self):
|
||||
'Return the next item from the iterator. When exhausted, raise StopIteration'
|
||||
raise StopIteration
|
||||
|
||||
def __iter__(self):
|
||||
return self
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Iterator:
|
||||
if _hasattr(C, "next") and _hasattr(C, "__iter__"):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
|
||||
class Sized:
|
||||
__metaclass__ = ABCMeta
|
||||
|
||||
@abstractmethod
|
||||
def __len__(self):
|
||||
return 0
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Sized:
|
||||
if _hasattr(C, "__len__"):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
|
||||
class Container:
|
||||
__metaclass__ = ABCMeta
|
||||
|
||||
@abstractmethod
|
||||
def __contains__(self, x):
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Container:
|
||||
if _hasattr(C, "__contains__"):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
|
||||
class Callable:
|
||||
__metaclass__ = ABCMeta
|
||||
|
||||
@abstractmethod
|
||||
def __call__(self, *args, **kwds):
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def __subclasshook__(cls, C):
|
||||
if cls is Callable:
|
||||
if _hasattr(C, "__call__"):
|
||||
return True
|
||||
return NotImplemented
|
||||
|
||||
|
||||
### SETS ###
|
||||
|
||||
|
||||
class Set(Sized, Iterable, Container):
|
||||
"""A set is a finite, iterable container.
|
||||
|
||||
This class provides concrete generic implementations of all
|
||||
methods except for __contains__, __iter__ and __len__.
|
||||
|
||||
To override the comparisons (presumably for speed, as the
|
||||
semantics are fixed), redefine __le__ and __ge__,
|
||||
then the other operations will automatically follow suit.
|
||||
"""
|
||||
|
||||
def __le__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
return NotImplemented
|
||||
if len(self) > len(other):
|
||||
return False
|
||||
for elem in self:
|
||||
if elem not in other:
|
||||
return False
|
||||
return True
|
||||
|
||||
def __lt__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
return NotImplemented
|
||||
return len(self) < len(other) and self.__le__(other)
|
||||
|
||||
def __gt__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
return NotImplemented
|
||||
return len(self) > len(other) and self.__ge__(other)
|
||||
|
||||
def __ge__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
return NotImplemented
|
||||
if len(self) < len(other):
|
||||
return False
|
||||
for elem in other:
|
||||
if elem not in self:
|
||||
return False
|
||||
return True
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
return NotImplemented
|
||||
return len(self) == len(other) and self.__le__(other)
|
||||
|
||||
def __ne__(self, other):
|
||||
return not (self == other)
|
||||
|
||||
@classmethod
|
||||
def _from_iterable(cls, it):
|
||||
'''Construct an instance of the class from any iterable input.
|
||||
|
||||
Must override this method if the class constructor signature
|
||||
does not accept an iterable for an input.
|
||||
'''
|
||||
return cls(it)
|
||||
|
||||
def __and__(self, other):
|
||||
if not isinstance(other, Iterable):
|
||||
return NotImplemented
|
||||
return self._from_iterable(value for value in other if value in self)
|
||||
|
||||
__rand__ = __and__
|
||||
|
||||
def isdisjoint(self, other):
|
||||
'Return True if two sets have a null intersection.'
|
||||
for value in other:
|
||||
if value in self:
|
||||
return False
|
||||
return True
|
||||
|
||||
def __or__(self, other):
|
||||
if not isinstance(other, Iterable):
|
||||
return NotImplemented
|
||||
chain = (e for s in (self, other) for e in s)
|
||||
return self._from_iterable(chain)
|
||||
|
||||
__ror__ = __or__
|
||||
|
||||
def __sub__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
if not isinstance(other, Iterable):
|
||||
return NotImplemented
|
||||
other = self._from_iterable(other)
|
||||
return self._from_iterable(value for value in self
|
||||
if value not in other)
|
||||
|
||||
def __rsub__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
if not isinstance(other, Iterable):
|
||||
return NotImplemented
|
||||
other = self._from_iterable(other)
|
||||
return self._from_iterable(value for value in other
|
||||
if value not in self)
|
||||
|
||||
def __xor__(self, other):
|
||||
if not isinstance(other, Set):
|
||||
if not isinstance(other, Iterable):
|
||||
return NotImplemented
|
||||
other = self._from_iterable(other)
|
||||
return (self - other) | (other - self)
|
||||
|
||||
__rxor__ = __xor__
|
||||
|
||||
# Sets are not hashable by default, but subclasses can change this
|
||||
__hash__ = None
|
||||
|
||||
def _hash(self):
|
||||
"""Compute the hash value of a set.
|
||||
|
||||
Note that we don't define __hash__: not all sets are hashable.
|
||||
But if you define a hashable set type, its __hash__ should
|
||||
call this function.
|
||||
|
||||
This must be compatible __eq__.
|
||||
|
||||
All sets ought to compare equal if they contain the same
|
||||
elements, regardless of how they are implemented, and
|
||||
regardless of the order of the elements; so there's not much
|
||||
freedom for __eq__ or __hash__. We match the algorithm used
|
||||
by the built-in frozenset type.
|
||||
"""
|
||||
MAX = sys.maxint
|
||||
MASK = 2 * MAX + 1
|
||||
n = len(self)
|
||||
h = 1927868237 * (n + 1)
|
||||
h &= MASK
|
||||
for x in self:
|
||||
hx = hash(x)
|
||||
h ^= (hx ^ (hx << 16) ^ 89869747) * 3644798167
|
||||
h &= MASK
|
||||
h = h * 69069 + 907133923
|
||||
h &= MASK
|
||||
if h > MAX:
|
||||
h -= MASK + 1
|
||||
if h == -1:
|
||||
h = 590923713
|
||||
return h
|
||||
|
||||
Set.register(frozenset)
|
||||
|
||||
|
||||
class MutableSet(Set):
|
||||
"""A mutable set is a finite, iterable container.
|
||||
|
||||
This class provides concrete generic implementations of all
|
||||
methods except for __contains__, __iter__, __len__,
|
||||
add(), and discard().
|
||||
|
||||
To override the comparisons (presumably for speed, as the
|
||||
semantics are fixed), all you have to do is redefine __le__ and
|
||||
then the other operations will automatically follow suit.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def add(self, value):
|
||||
"""Add an element."""
|
||||
raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
def discard(self, value):
|
||||
"""Remove an element. Do not raise an exception if absent."""
|
||||
raise NotImplementedError
|
||||
|
||||
def remove(self, value):
|
||||
"""Remove an element. If not a member, raise a KeyError."""
|
||||
if value not in self:
|
||||
raise KeyError(value)
|
||||
self.discard(value)
|
||||
|
||||
def pop(self):
|
||||
"""Return the popped value. Raise KeyError if empty."""
|
||||
it = iter(self)
|
||||
try:
|
||||
value = next(it)
|
||||
except StopIteration:
|
||||
raise KeyError
|
||||
self.discard(value)
|
||||
return value
|
||||
|
||||
def clear(self):
|
||||
"""This is slow (creates N new iterators!) but effective."""
|
||||
try:
|
||||
while True:
|
||||
self.pop()
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
def __ior__(self, it):
|
||||
for value in it:
|
||||
self.add(value)
|
||||
return self
|
||||
|
||||
def __iand__(self, it):
|
||||
for value in (self - it):
|
||||
self.discard(value)
|
||||
return self
|
||||
|
||||
def __ixor__(self, it):
|
||||
if it is self:
|
||||
self.clear()
|
||||
else:
|
||||
if not isinstance(it, Set):
|
||||
it = self._from_iterable(it)
|
||||
for value in it:
|
||||
if value in self:
|
||||
self.discard(value)
|
||||
else:
|
||||
self.add(value)
|
||||
return self
|
||||
|
||||
def __isub__(self, it):
|
||||
if it is self:
|
||||
self.clear()
|
||||
else:
|
||||
for value in it:
|
||||
self.discard(value)
|
||||
return self
|
||||
|
||||
MutableSet.register(set)
|
||||
|
||||
|
||||
### MAPPINGS ###
|
||||
|
||||
|
||||
class Mapping(Sized, Iterable, Container):
|
||||
|
||||
"""A Mapping is a generic container for associating key/value
|
||||
pairs.
|
||||
|
||||
This class provides concrete generic implementations of all
|
||||
methods except for __getitem__, __iter__, and __len__.
|
||||
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def __getitem__(self, key):
|
||||
raise KeyError
|
||||
|
||||
def get(self, key, default=None):
|
||||
'D.get(k[,d]) -> D[k] if k in D, else d. d defaults to None.'
|
||||
try:
|
||||
return self[key]
|
||||
except KeyError:
|
||||
return default
|
||||
|
||||
def __contains__(self, key):
|
||||
try:
|
||||
self[key]
|
||||
except KeyError:
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def iterkeys(self):
|
||||
'D.iterkeys() -> an iterator over the keys of D'
|
||||
return iter(self)
|
||||
|
||||
def itervalues(self):
|
||||
'D.itervalues() -> an iterator over the values of D'
|
||||
for key in self:
|
||||
yield self[key]
|
||||
|
||||
def iteritems(self):
|
||||
'D.iteritems() -> an iterator over the (key, value) items of D'
|
||||
for key in self:
|
||||
yield (key, self[key])
|
||||
|
||||
def keys(self):
|
||||
"D.keys() -> list of D's keys"
|
||||
return list(self)
|
||||
|
||||
def items(self):
|
||||
"D.items() -> list of D's (key, value) pairs, as 2-tuples"
|
||||
return [(key, self[key]) for key in self]
|
||||
|
||||
def values(self):
|
||||
"D.values() -> list of D's values"
|
||||
return [self[key] for key in self]
|
||||
|
||||
# Mappings are not hashable by default, but subclasses can change this
|
||||
__hash__ = None
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, Mapping):
|
||||
return NotImplemented
|
||||
return dict(self.items()) == dict(other.items())
|
||||
|
||||
def __ne__(self, other):
|
||||
return not (self == other)
|
||||
|
||||
class MappingView(Sized):
|
||||
|
||||
def __init__(self, mapping):
|
||||
self._mapping = mapping
|
||||
|
||||
def __len__(self):
|
||||
return len(self._mapping)
|
||||
|
||||
def __repr__(self):
|
||||
return '{0.__class__.__name__}({0._mapping!r})'.format(self)
|
||||
|
||||
|
||||
class KeysView(MappingView, Set):
|
||||
|
||||
@classmethod
|
||||
def _from_iterable(self, it):
|
||||
return set(it)
|
||||
|
||||
def __contains__(self, key):
|
||||
return key in self._mapping
|
||||
|
||||
def __iter__(self):
|
||||
for key in self._mapping:
|
||||
yield key
|
||||
|
||||
|
||||
class ItemsView(MappingView, Set):
|
||||
|
||||
@classmethod
|
||||
def _from_iterable(self, it):
|
||||
return set(it)
|
||||
|
||||
def __contains__(self, item):
|
||||
key, value = item
|
||||
try:
|
||||
v = self._mapping[key]
|
||||
except KeyError:
|
||||
return False
|
||||
else:
|
||||
return v == value
|
||||
|
||||
def __iter__(self):
|
||||
for key in self._mapping:
|
||||
yield (key, self._mapping[key])
|
||||
|
||||
|
||||
class ValuesView(MappingView):
|
||||
|
||||
def __contains__(self, value):
|
||||
for key in self._mapping:
|
||||
if value == self._mapping[key]:
|
||||
return True
|
||||
return False
|
||||
|
||||
def __iter__(self):
|
||||
for key in self._mapping:
|
||||
yield self._mapping[key]
|
||||
|
||||
|
||||
class MutableMapping(Mapping):
|
||||
|
||||
"""A MutableMapping is a generic container for associating
|
||||
key/value pairs.
|
||||
|
||||
This class provides concrete generic implementations of all
|
||||
methods except for __getitem__, __setitem__, __delitem__,
|
||||
__iter__, and __len__.
|
||||
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def __setitem__(self, key, value):
|
||||
raise KeyError
|
||||
|
||||
@abstractmethod
|
||||
def __delitem__(self, key):
|
||||
raise KeyError
|
||||
|
||||
__marker = object()
|
||||
|
||||
def pop(self, key, default=__marker):
|
||||
'''D.pop(k[,d]) -> v, remove specified key and return the corresponding value.
|
||||
If key is not found, d is returned if given, otherwise KeyError is raised.
|
||||
'''
|
||||
try:
|
||||
value = self[key]
|
||||
except KeyError:
|
||||
if default is self.__marker:
|
||||
raise
|
||||
return default
|
||||
else:
|
||||
del self[key]
|
||||
return value
|
||||
|
||||
def popitem(self):
|
||||
'''D.popitem() -> (k, v), remove and return some (key, value) pair
|
||||
as a 2-tuple; but raise KeyError if D is empty.
|
||||
'''
|
||||
try:
|
||||
key = next(iter(self))
|
||||
except StopIteration:
|
||||
raise KeyError
|
||||
value = self[key]
|
||||
del self[key]
|
||||
return key, value
|
||||
|
||||
def clear(self):
|
||||
'D.clear() -> None. Remove all items from D.'
|
||||
try:
|
||||
while True:
|
||||
self.popitem()
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
def update(*args, **kwds):
|
||||
''' D.update([E, ]**F) -> None. Update D from mapping/iterable E and F.
|
||||
If E present and has a .keys() method, does: for k in E: D[k] = E[k]
|
||||
If E present and lacks .keys() method, does: for (k, v) in E: D[k] = v
|
||||
In either case, this is followed by: for k, v in F.items(): D[k] = v
|
||||
'''
|
||||
if not args:
|
||||
raise TypeError("descriptor 'update' of 'MutableMapping' object "
|
||||
"needs an argument")
|
||||
self = args[0]
|
||||
args = args[1:]
|
||||
if len(args) > 1:
|
||||
raise TypeError('update expected at most 1 arguments, got %d' %
|
||||
len(args))
|
||||
if args:
|
||||
other = args[0]
|
||||
if isinstance(other, Mapping):
|
||||
for key in other:
|
||||
self[key] = other[key]
|
||||
elif hasattr(other, "keys"):
|
||||
for key in other.keys():
|
||||
self[key] = other[key]
|
||||
else:
|
||||
for key, value in other:
|
||||
self[key] = value
|
||||
for key, value in kwds.items():
|
||||
self[key] = value
|
||||
|
||||
def setdefault(self, key, default=None):
|
||||
'D.setdefault(k[,d]) -> D.get(k,d), also set D[k]=d if k not in D'
|
||||
try:
|
||||
return self[key]
|
||||
except KeyError:
|
||||
self[key] = default
|
||||
return default
|
||||
|
||||
MutableMapping.register(dict)
|
||||
|
||||
|
||||
### SEQUENCES ###
|
||||
|
||||
|
||||
class Sequence(Sized, Iterable, Container):
|
||||
"""All the operations on a read-only sequence.
|
||||
|
||||
Concrete subclasses must override __new__ or __init__,
|
||||
__getitem__, and __len__.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def __getitem__(self, index):
|
||||
raise IndexError
|
||||
|
||||
def __iter__(self):
|
||||
i = 0
|
||||
try:
|
||||
while True:
|
||||
v = self[i]
|
||||
yield v
|
||||
i += 1
|
||||
except IndexError:
|
||||
return
|
||||
|
||||
def __contains__(self, value):
|
||||
for v in self:
|
||||
if v == value:
|
||||
return True
|
||||
return False
|
||||
|
||||
def __reversed__(self):
|
||||
for i in reversed(range(len(self))):
|
||||
yield self[i]
|
||||
|
||||
def index(self, value):
|
||||
'''S.index(value) -> integer -- return first index of value.
|
||||
Raises ValueError if the value is not present.
|
||||
'''
|
||||
for i, v in enumerate(self):
|
||||
if v == value:
|
||||
return i
|
||||
raise ValueError
|
||||
|
||||
def count(self, value):
|
||||
'S.count(value) -> integer -- return number of occurrences of value'
|
||||
return sum(1 for v in self if v == value)
|
||||
|
||||
Sequence.register(tuple)
|
||||
Sequence.register(basestring)
|
||||
Sequence.register(buffer)
|
||||
Sequence.register(xrange)
|
||||
|
||||
|
||||
class MutableSequence(Sequence):
|
||||
|
||||
"""All the operations on a read-only sequence.
|
||||
|
||||
Concrete subclasses must provide __new__ or __init__,
|
||||
__getitem__, __setitem__, __delitem__, __len__, and insert().
|
||||
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def __setitem__(self, index, value):
|
||||
raise IndexError
|
||||
|
||||
@abstractmethod
|
||||
def __delitem__(self, index):
|
||||
raise IndexError
|
||||
|
||||
@abstractmethod
|
||||
def insert(self, index, value):
|
||||
'S.insert(index, object) -- insert object before index'
|
||||
raise IndexError
|
||||
|
||||
def append(self, value):
|
||||
'S.append(object) -- append object to the end of the sequence'
|
||||
self.insert(len(self), value)
|
||||
|
||||
def reverse(self):
|
||||
'S.reverse() -- reverse *IN PLACE*'
|
||||
n = len(self)
|
||||
for i in range(n//2):
|
||||
self[i], self[n-i-1] = self[n-i-1], self[i]
|
||||
|
||||
def extend(self, values):
|
||||
'S.extend(iterable) -- extend sequence by appending elements from the iterable'
|
||||
for v in values:
|
||||
self.append(v)
|
||||
|
||||
def pop(self, index=-1):
|
||||
'''S.pop([index]) -> item -- remove and return item at index (default last).
|
||||
Raise IndexError if list is empty or index is out of range.
|
||||
'''
|
||||
v = self[index]
|
||||
del self[index]
|
||||
return v
|
||||
|
||||
def remove(self, value):
|
||||
'''S.remove(value) -- remove first occurrence of value.
|
||||
Raise ValueError if the value is not present.
|
||||
'''
|
||||
del self[self.index(value)]
|
||||
|
||||
def __iadd__(self, values):
|
||||
self.extend(values)
|
||||
return self
|
||||
|
||||
MutableSequence.register(list)
|
||||
204
AppPkg/Applications/Python/Python-2.7.10/Lib/_weakrefset.py
Normal file
204
AppPkg/Applications/Python/Python-2.7.10/Lib/_weakrefset.py
Normal file
@@ -0,0 +1,204 @@
|
||||
# Access WeakSet through the weakref module.
|
||||
# This code is separated-out because it is needed
|
||||
# by abc.py to load everything else at startup.
|
||||
|
||||
from _weakref import ref
|
||||
|
||||
__all__ = ['WeakSet']
|
||||
|
||||
|
||||
class _IterationGuard(object):
|
||||
# This context manager registers itself in the current iterators of the
|
||||
# weak container, such as to delay all removals until the context manager
|
||||
# exits.
|
||||
# This technique should be relatively thread-safe (since sets are).
|
||||
|
||||
def __init__(self, weakcontainer):
|
||||
# Don't create cycles
|
||||
self.weakcontainer = ref(weakcontainer)
|
||||
|
||||
def __enter__(self):
|
||||
w = self.weakcontainer()
|
||||
if w is not None:
|
||||
w._iterating.add(self)
|
||||
return self
|
||||
|
||||
def __exit__(self, e, t, b):
|
||||
w = self.weakcontainer()
|
||||
if w is not None:
|
||||
s = w._iterating
|
||||
s.remove(self)
|
||||
if not s:
|
||||
w._commit_removals()
|
||||
|
||||
|
||||
class WeakSet(object):
|
||||
def __init__(self, data=None):
|
||||
self.data = set()
|
||||
def _remove(item, selfref=ref(self)):
|
||||
self = selfref()
|
||||
if self is not None:
|
||||
if self._iterating:
|
||||
self._pending_removals.append(item)
|
||||
else:
|
||||
self.data.discard(item)
|
||||
self._remove = _remove
|
||||
# A list of keys to be removed
|
||||
self._pending_removals = []
|
||||
self._iterating = set()
|
||||
if data is not None:
|
||||
self.update(data)
|
||||
|
||||
def _commit_removals(self):
|
||||
l = self._pending_removals
|
||||
discard = self.data.discard
|
||||
while l:
|
||||
discard(l.pop())
|
||||
|
||||
def __iter__(self):
|
||||
with _IterationGuard(self):
|
||||
for itemref in self.data:
|
||||
item = itemref()
|
||||
if item is not None:
|
||||
# Caveat: the iterator will keep a strong reference to
|
||||
# `item` until it is resumed or closed.
|
||||
yield item
|
||||
|
||||
def __len__(self):
|
||||
return len(self.data) - len(self._pending_removals)
|
||||
|
||||
def __contains__(self, item):
|
||||
try:
|
||||
wr = ref(item)
|
||||
except TypeError:
|
||||
return False
|
||||
return wr in self.data
|
||||
|
||||
def __reduce__(self):
|
||||
return (self.__class__, (list(self),),
|
||||
getattr(self, '__dict__', None))
|
||||
|
||||
__hash__ = None
|
||||
|
||||
def add(self, item):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
self.data.add(ref(item, self._remove))
|
||||
|
||||
def clear(self):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
self.data.clear()
|
||||
|
||||
def copy(self):
|
||||
return self.__class__(self)
|
||||
|
||||
def pop(self):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
while True:
|
||||
try:
|
||||
itemref = self.data.pop()
|
||||
except KeyError:
|
||||
raise KeyError('pop from empty WeakSet')
|
||||
item = itemref()
|
||||
if item is not None:
|
||||
return item
|
||||
|
||||
def remove(self, item):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
self.data.remove(ref(item))
|
||||
|
||||
def discard(self, item):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
self.data.discard(ref(item))
|
||||
|
||||
def update(self, other):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
for element in other:
|
||||
self.add(element)
|
||||
|
||||
def __ior__(self, other):
|
||||
self.update(other)
|
||||
return self
|
||||
|
||||
def difference(self, other):
|
||||
newset = self.copy()
|
||||
newset.difference_update(other)
|
||||
return newset
|
||||
__sub__ = difference
|
||||
|
||||
def difference_update(self, other):
|
||||
self.__isub__(other)
|
||||
def __isub__(self, other):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
if self is other:
|
||||
self.data.clear()
|
||||
else:
|
||||
self.data.difference_update(ref(item) for item in other)
|
||||
return self
|
||||
|
||||
def intersection(self, other):
|
||||
return self.__class__(item for item in other if item in self)
|
||||
__and__ = intersection
|
||||
|
||||
def intersection_update(self, other):
|
||||
self.__iand__(other)
|
||||
def __iand__(self, other):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
self.data.intersection_update(ref(item) for item in other)
|
||||
return self
|
||||
|
||||
def issubset(self, other):
|
||||
return self.data.issubset(ref(item) for item in other)
|
||||
__le__ = issubset
|
||||
|
||||
def __lt__(self, other):
|
||||
return self.data < set(ref(item) for item in other)
|
||||
|
||||
def issuperset(self, other):
|
||||
return self.data.issuperset(ref(item) for item in other)
|
||||
__ge__ = issuperset
|
||||
|
||||
def __gt__(self, other):
|
||||
return self.data > set(ref(item) for item in other)
|
||||
|
||||
def __eq__(self, other):
|
||||
if not isinstance(other, self.__class__):
|
||||
return NotImplemented
|
||||
return self.data == set(ref(item) for item in other)
|
||||
|
||||
def __ne__(self, other):
|
||||
opposite = self.__eq__(other)
|
||||
if opposite is NotImplemented:
|
||||
return NotImplemented
|
||||
return not opposite
|
||||
|
||||
def symmetric_difference(self, other):
|
||||
newset = self.copy()
|
||||
newset.symmetric_difference_update(other)
|
||||
return newset
|
||||
__xor__ = symmetric_difference
|
||||
|
||||
def symmetric_difference_update(self, other):
|
||||
self.__ixor__(other)
|
||||
def __ixor__(self, other):
|
||||
if self._pending_removals:
|
||||
self._commit_removals()
|
||||
if self is other:
|
||||
self.data.clear()
|
||||
else:
|
||||
self.data.symmetric_difference_update(ref(item, self._remove) for item in other)
|
||||
return self
|
||||
|
||||
def union(self, other):
|
||||
return self.__class__(e for s in (self, other) for e in s)
|
||||
__or__ = union
|
||||
|
||||
def isdisjoint(self, other):
|
||||
return len(self.intersection(other)) == 0
|
||||
185
AppPkg/Applications/Python/Python-2.7.10/Lib/abc.py
Normal file
185
AppPkg/Applications/Python/Python-2.7.10/Lib/abc.py
Normal file
@@ -0,0 +1,185 @@
|
||||
# Copyright 2007 Google, Inc. All Rights Reserved.
|
||||
# Licensed to PSF under a Contributor Agreement.
|
||||
|
||||
"""Abstract Base Classes (ABCs) according to PEP 3119."""
|
||||
|
||||
import types
|
||||
|
||||
from _weakrefset import WeakSet
|
||||
|
||||
# Instance of old-style class
|
||||
class _C: pass
|
||||
_InstanceType = type(_C())
|
||||
|
||||
|
||||
def abstractmethod(funcobj):
|
||||
"""A decorator indicating abstract methods.
|
||||
|
||||
Requires that the metaclass is ABCMeta or derived from it. A
|
||||
class that has a metaclass derived from ABCMeta cannot be
|
||||
instantiated unless all of its abstract methods are overridden.
|
||||
The abstract methods can be called using any of the normal
|
||||
'super' call mechanisms.
|
||||
|
||||
Usage:
|
||||
|
||||
class C:
|
||||
__metaclass__ = ABCMeta
|
||||
@abstractmethod
|
||||
def my_abstract_method(self, ...):
|
||||
...
|
||||
"""
|
||||
funcobj.__isabstractmethod__ = True
|
||||
return funcobj
|
||||
|
||||
|
||||
class abstractproperty(property):
|
||||
"""A decorator indicating abstract properties.
|
||||
|
||||
Requires that the metaclass is ABCMeta or derived from it. A
|
||||
class that has a metaclass derived from ABCMeta cannot be
|
||||
instantiated unless all of its abstract properties are overridden.
|
||||
The abstract properties can be called using any of the normal
|
||||
'super' call mechanisms.
|
||||
|
||||
Usage:
|
||||
|
||||
class C:
|
||||
__metaclass__ = ABCMeta
|
||||
@abstractproperty
|
||||
def my_abstract_property(self):
|
||||
...
|
||||
|
||||
This defines a read-only property; you can also define a read-write
|
||||
abstract property using the 'long' form of property declaration:
|
||||
|
||||
class C:
|
||||
__metaclass__ = ABCMeta
|
||||
def getx(self): ...
|
||||
def setx(self, value): ...
|
||||
x = abstractproperty(getx, setx)
|
||||
"""
|
||||
__isabstractmethod__ = True
|
||||
|
||||
|
||||
class ABCMeta(type):
|
||||
|
||||
"""Metaclass for defining Abstract Base Classes (ABCs).
|
||||
|
||||
Use this metaclass to create an ABC. An ABC can be subclassed
|
||||
directly, and then acts as a mix-in class. You can also register
|
||||
unrelated concrete classes (even built-in classes) and unrelated
|
||||
ABCs as 'virtual subclasses' -- these and their descendants will
|
||||
be considered subclasses of the registering ABC by the built-in
|
||||
issubclass() function, but the registering ABC won't show up in
|
||||
their MRO (Method Resolution Order) nor will method
|
||||
implementations defined by the registering ABC be callable (not
|
||||
even via super()).
|
||||
|
||||
"""
|
||||
|
||||
# A global counter that is incremented each time a class is
|
||||
# registered as a virtual subclass of anything. It forces the
|
||||
# negative cache to be cleared before its next use.
|
||||
_abc_invalidation_counter = 0
|
||||
|
||||
def __new__(mcls, name, bases, namespace):
|
||||
cls = super(ABCMeta, mcls).__new__(mcls, name, bases, namespace)
|
||||
# Compute set of abstract method names
|
||||
abstracts = set(name
|
||||
for name, value in namespace.items()
|
||||
if getattr(value, "__isabstractmethod__", False))
|
||||
for base in bases:
|
||||
for name in getattr(base, "__abstractmethods__", set()):
|
||||
value = getattr(cls, name, None)
|
||||
if getattr(value, "__isabstractmethod__", False):
|
||||
abstracts.add(name)
|
||||
cls.__abstractmethods__ = frozenset(abstracts)
|
||||
# Set up inheritance registry
|
||||
cls._abc_registry = WeakSet()
|
||||
cls._abc_cache = WeakSet()
|
||||
cls._abc_negative_cache = WeakSet()
|
||||
cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter
|
||||
return cls
|
||||
|
||||
def register(cls, subclass):
|
||||
"""Register a virtual subclass of an ABC."""
|
||||
if not isinstance(subclass, (type, types.ClassType)):
|
||||
raise TypeError("Can only register classes")
|
||||
if issubclass(subclass, cls):
|
||||
return # Already a subclass
|
||||
# Subtle: test for cycles *after* testing for "already a subclass";
|
||||
# this means we allow X.register(X) and interpret it as a no-op.
|
||||
if issubclass(cls, subclass):
|
||||
# This would create a cycle, which is bad for the algorithm below
|
||||
raise RuntimeError("Refusing to create an inheritance cycle")
|
||||
cls._abc_registry.add(subclass)
|
||||
ABCMeta._abc_invalidation_counter += 1 # Invalidate negative cache
|
||||
|
||||
def _dump_registry(cls, file=None):
|
||||
"""Debug helper to print the ABC registry."""
|
||||
print >> file, "Class: %s.%s" % (cls.__module__, cls.__name__)
|
||||
print >> file, "Inv.counter: %s" % ABCMeta._abc_invalidation_counter
|
||||
for name in sorted(cls.__dict__.keys()):
|
||||
if name.startswith("_abc_"):
|
||||
value = getattr(cls, name)
|
||||
print >> file, "%s: %r" % (name, value)
|
||||
|
||||
def __instancecheck__(cls, instance):
|
||||
"""Override for isinstance(instance, cls)."""
|
||||
# Inline the cache checking when it's simple.
|
||||
subclass = getattr(instance, '__class__', None)
|
||||
if subclass is not None and subclass in cls._abc_cache:
|
||||
return True
|
||||
subtype = type(instance)
|
||||
# Old-style instances
|
||||
if subtype is _InstanceType:
|
||||
subtype = subclass
|
||||
if subtype is subclass or subclass is None:
|
||||
if (cls._abc_negative_cache_version ==
|
||||
ABCMeta._abc_invalidation_counter and
|
||||
subtype in cls._abc_negative_cache):
|
||||
return False
|
||||
# Fall back to the subclass check.
|
||||
return cls.__subclasscheck__(subtype)
|
||||
return (cls.__subclasscheck__(subclass) or
|
||||
cls.__subclasscheck__(subtype))
|
||||
|
||||
def __subclasscheck__(cls, subclass):
|
||||
"""Override for issubclass(subclass, cls)."""
|
||||
# Check cache
|
||||
if subclass in cls._abc_cache:
|
||||
return True
|
||||
# Check negative cache; may have to invalidate
|
||||
if cls._abc_negative_cache_version < ABCMeta._abc_invalidation_counter:
|
||||
# Invalidate the negative cache
|
||||
cls._abc_negative_cache = WeakSet()
|
||||
cls._abc_negative_cache_version = ABCMeta._abc_invalidation_counter
|
||||
elif subclass in cls._abc_negative_cache:
|
||||
return False
|
||||
# Check the subclass hook
|
||||
ok = cls.__subclasshook__(subclass)
|
||||
if ok is not NotImplemented:
|
||||
assert isinstance(ok, bool)
|
||||
if ok:
|
||||
cls._abc_cache.add(subclass)
|
||||
else:
|
||||
cls._abc_negative_cache.add(subclass)
|
||||
return ok
|
||||
# Check if it's a direct subclass
|
||||
if cls in getattr(subclass, '__mro__', ()):
|
||||
cls._abc_cache.add(subclass)
|
||||
return True
|
||||
# Check if it's a subclass of a registered class (recursive)
|
||||
for rcls in cls._abc_registry:
|
||||
if issubclass(subclass, rcls):
|
||||
cls._abc_cache.add(subclass)
|
||||
return True
|
||||
# Check if it's a subclass of a subclass (recursive)
|
||||
for scls in cls.__subclasses__():
|
||||
if issubclass(subclass, scls):
|
||||
cls._abc_cache.add(subclass)
|
||||
return True
|
||||
# No dice; update negative cache
|
||||
cls._abc_negative_cache.add(subclass)
|
||||
return False
|
||||
2374
AppPkg/Applications/Python/Python-2.7.10/Lib/argparse.py
Normal file
2374
AppPkg/Applications/Python/Python-2.7.10/Lib/argparse.py
Normal file
File diff suppressed because it is too large
Load Diff
311
AppPkg/Applications/Python/Python-2.7.10/Lib/ast.py
Normal file
311
AppPkg/Applications/Python/Python-2.7.10/Lib/ast.py
Normal file
@@ -0,0 +1,311 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
ast
|
||||
~~~
|
||||
|
||||
The `ast` module helps Python applications to process trees of the Python
|
||||
abstract syntax grammar. The abstract syntax itself might change with
|
||||
each Python release; this module helps to find out programmatically what
|
||||
the current grammar looks like and allows modifications of it.
|
||||
|
||||
An abstract syntax tree can be generated by passing `ast.PyCF_ONLY_AST` as
|
||||
a flag to the `compile()` builtin function or by using the `parse()`
|
||||
function from this module. The result will be a tree of objects whose
|
||||
classes all inherit from `ast.AST`.
|
||||
|
||||
A modified abstract syntax tree can be compiled into a Python code object
|
||||
using the built-in `compile()` function.
|
||||
|
||||
Additionally various helper functions are provided that make working with
|
||||
the trees simpler. The main intention of the helper functions and this
|
||||
module in general is to provide an easy to use interface for libraries
|
||||
that work tightly with the python syntax (template engines for example).
|
||||
|
||||
|
||||
:copyright: Copyright 2008 by Armin Ronacher.
|
||||
:license: Python License.
|
||||
"""
|
||||
from _ast import *
|
||||
from _ast import __version__
|
||||
|
||||
|
||||
def parse(source, filename='<unknown>', mode='exec'):
|
||||
"""
|
||||
Parse the source into an AST node.
|
||||
Equivalent to compile(source, filename, mode, PyCF_ONLY_AST).
|
||||
"""
|
||||
return compile(source, filename, mode, PyCF_ONLY_AST)
|
||||
|
||||
|
||||
def literal_eval(node_or_string):
|
||||
"""
|
||||
Safely evaluate an expression node or a string containing a Python
|
||||
expression. The string or node provided may only consist of the following
|
||||
Python literal structures: strings, numbers, tuples, lists, dicts, booleans,
|
||||
and None.
|
||||
"""
|
||||
_safe_names = {'None': None, 'True': True, 'False': False}
|
||||
if isinstance(node_or_string, basestring):
|
||||
node_or_string = parse(node_or_string, mode='eval')
|
||||
if isinstance(node_or_string, Expression):
|
||||
node_or_string = node_or_string.body
|
||||
def _convert(node):
|
||||
if isinstance(node, Str):
|
||||
return node.s
|
||||
elif isinstance(node, Num):
|
||||
return node.n
|
||||
elif isinstance(node, Tuple):
|
||||
return tuple(map(_convert, node.elts))
|
||||
elif isinstance(node, List):
|
||||
return list(map(_convert, node.elts))
|
||||
elif isinstance(node, Dict):
|
||||
return dict((_convert(k), _convert(v)) for k, v
|
||||
in zip(node.keys, node.values))
|
||||
elif isinstance(node, Name):
|
||||
if node.id in _safe_names:
|
||||
return _safe_names[node.id]
|
||||
elif isinstance(node, BinOp) and \
|
||||
isinstance(node.op, (Add, Sub)) and \
|
||||
isinstance(node.right, Num) and \
|
||||
isinstance(node.right.n, complex) and \
|
||||
isinstance(node.left, Num) and \
|
||||
isinstance(node.left.n, (int, long, float)):
|
||||
left = node.left.n
|
||||
right = node.right.n
|
||||
if isinstance(node.op, Add):
|
||||
return left + right
|
||||
else:
|
||||
return left - right
|
||||
raise ValueError('malformed string')
|
||||
return _convert(node_or_string)
|
||||
|
||||
|
||||
def dump(node, annotate_fields=True, include_attributes=False):
|
||||
"""
|
||||
Return a formatted dump of the tree in *node*. This is mainly useful for
|
||||
debugging purposes. The returned string will show the names and the values
|
||||
for fields. This makes the code impossible to evaluate, so if evaluation is
|
||||
wanted *annotate_fields* must be set to False. Attributes such as line
|
||||
numbers and column offsets are not dumped by default. If this is wanted,
|
||||
*include_attributes* can be set to True.
|
||||
"""
|
||||
def _format(node):
|
||||
if isinstance(node, AST):
|
||||
fields = [(a, _format(b)) for a, b in iter_fields(node)]
|
||||
rv = '%s(%s' % (node.__class__.__name__, ', '.join(
|
||||
('%s=%s' % field for field in fields)
|
||||
if annotate_fields else
|
||||
(b for a, b in fields)
|
||||
))
|
||||
if include_attributes and node._attributes:
|
||||
rv += fields and ', ' or ' '
|
||||
rv += ', '.join('%s=%s' % (a, _format(getattr(node, a)))
|
||||
for a in node._attributes)
|
||||
return rv + ')'
|
||||
elif isinstance(node, list):
|
||||
return '[%s]' % ', '.join(_format(x) for x in node)
|
||||
return repr(node)
|
||||
if not isinstance(node, AST):
|
||||
raise TypeError('expected AST, got %r' % node.__class__.__name__)
|
||||
return _format(node)
|
||||
|
||||
|
||||
def copy_location(new_node, old_node):
|
||||
"""
|
||||
Copy source location (`lineno` and `col_offset` attributes) from
|
||||
*old_node* to *new_node* if possible, and return *new_node*.
|
||||
"""
|
||||
for attr in 'lineno', 'col_offset':
|
||||
if attr in old_node._attributes and attr in new_node._attributes \
|
||||
and hasattr(old_node, attr):
|
||||
setattr(new_node, attr, getattr(old_node, attr))
|
||||
return new_node
|
||||
|
||||
|
||||
def fix_missing_locations(node):
|
||||
"""
|
||||
When you compile a node tree with compile(), the compiler expects lineno and
|
||||
col_offset attributes for every node that supports them. This is rather
|
||||
tedious to fill in for generated nodes, so this helper adds these attributes
|
||||
recursively where not already set, by setting them to the values of the
|
||||
parent node. It works recursively starting at *node*.
|
||||
"""
|
||||
def _fix(node, lineno, col_offset):
|
||||
if 'lineno' in node._attributes:
|
||||
if not hasattr(node, 'lineno'):
|
||||
node.lineno = lineno
|
||||
else:
|
||||
lineno = node.lineno
|
||||
if 'col_offset' in node._attributes:
|
||||
if not hasattr(node, 'col_offset'):
|
||||
node.col_offset = col_offset
|
||||
else:
|
||||
col_offset = node.col_offset
|
||||
for child in iter_child_nodes(node):
|
||||
_fix(child, lineno, col_offset)
|
||||
_fix(node, 1, 0)
|
||||
return node
|
||||
|
||||
|
||||
def increment_lineno(node, n=1):
|
||||
"""
|
||||
Increment the line number of each node in the tree starting at *node* by *n*.
|
||||
This is useful to "move code" to a different location in a file.
|
||||
"""
|
||||
for child in walk(node):
|
||||
if 'lineno' in child._attributes:
|
||||
child.lineno = getattr(child, 'lineno', 0) + n
|
||||
return node
|
||||
|
||||
|
||||
def iter_fields(node):
|
||||
"""
|
||||
Yield a tuple of ``(fieldname, value)`` for each field in ``node._fields``
|
||||
that is present on *node*.
|
||||
"""
|
||||
for field in node._fields:
|
||||
try:
|
||||
yield field, getattr(node, field)
|
||||
except AttributeError:
|
||||
pass
|
||||
|
||||
|
||||
def iter_child_nodes(node):
|
||||
"""
|
||||
Yield all direct child nodes of *node*, that is, all fields that are nodes
|
||||
and all items of fields that are lists of nodes.
|
||||
"""
|
||||
for name, field in iter_fields(node):
|
||||
if isinstance(field, AST):
|
||||
yield field
|
||||
elif isinstance(field, list):
|
||||
for item in field:
|
||||
if isinstance(item, AST):
|
||||
yield item
|
||||
|
||||
|
||||
def get_docstring(node, clean=True):
|
||||
"""
|
||||
Return the docstring for the given node or None if no docstring can
|
||||
be found. If the node provided does not have docstrings a TypeError
|
||||
will be raised.
|
||||
"""
|
||||
if not isinstance(node, (FunctionDef, ClassDef, Module)):
|
||||
raise TypeError("%r can't have docstrings" % node.__class__.__name__)
|
||||
if node.body and isinstance(node.body[0], Expr) and \
|
||||
isinstance(node.body[0].value, Str):
|
||||
if clean:
|
||||
import inspect
|
||||
return inspect.cleandoc(node.body[0].value.s)
|
||||
return node.body[0].value.s
|
||||
|
||||
|
||||
def walk(node):
|
||||
"""
|
||||
Recursively yield all descendant nodes in the tree starting at *node*
|
||||
(including *node* itself), in no specified order. This is useful if you
|
||||
only want to modify nodes in place and don't care about the context.
|
||||
"""
|
||||
from collections import deque
|
||||
todo = deque([node])
|
||||
while todo:
|
||||
node = todo.popleft()
|
||||
todo.extend(iter_child_nodes(node))
|
||||
yield node
|
||||
|
||||
|
||||
class NodeVisitor(object):
|
||||
"""
|
||||
A node visitor base class that walks the abstract syntax tree and calls a
|
||||
visitor function for every node found. This function may return a value
|
||||
which is forwarded by the `visit` method.
|
||||
|
||||
This class is meant to be subclassed, with the subclass adding visitor
|
||||
methods.
|
||||
|
||||
Per default the visitor functions for the nodes are ``'visit_'`` +
|
||||
class name of the node. So a `TryFinally` node visit function would
|
||||
be `visit_TryFinally`. This behavior can be changed by overriding
|
||||
the `visit` method. If no visitor function exists for a node
|
||||
(return value `None`) the `generic_visit` visitor is used instead.
|
||||
|
||||
Don't use the `NodeVisitor` if you want to apply changes to nodes during
|
||||
traversing. For this a special visitor exists (`NodeTransformer`) that
|
||||
allows modifications.
|
||||
"""
|
||||
|
||||
def visit(self, node):
|
||||
"""Visit a node."""
|
||||
method = 'visit_' + node.__class__.__name__
|
||||
visitor = getattr(self, method, self.generic_visit)
|
||||
return visitor(node)
|
||||
|
||||
def generic_visit(self, node):
|
||||
"""Called if no explicit visitor function exists for a node."""
|
||||
for field, value in iter_fields(node):
|
||||
if isinstance(value, list):
|
||||
for item in value:
|
||||
if isinstance(item, AST):
|
||||
self.visit(item)
|
||||
elif isinstance(value, AST):
|
||||
self.visit(value)
|
||||
|
||||
|
||||
class NodeTransformer(NodeVisitor):
|
||||
"""
|
||||
A :class:`NodeVisitor` subclass that walks the abstract syntax tree and
|
||||
allows modification of nodes.
|
||||
|
||||
The `NodeTransformer` will walk the AST and use the return value of the
|
||||
visitor methods to replace or remove the old node. If the return value of
|
||||
the visitor method is ``None``, the node will be removed from its location,
|
||||
otherwise it is replaced with the return value. The return value may be the
|
||||
original node in which case no replacement takes place.
|
||||
|
||||
Here is an example transformer that rewrites all occurrences of name lookups
|
||||
(``foo``) to ``data['foo']``::
|
||||
|
||||
class RewriteName(NodeTransformer):
|
||||
|
||||
def visit_Name(self, node):
|
||||
return copy_location(Subscript(
|
||||
value=Name(id='data', ctx=Load()),
|
||||
slice=Index(value=Str(s=node.id)),
|
||||
ctx=node.ctx
|
||||
), node)
|
||||
|
||||
Keep in mind that if the node you're operating on has child nodes you must
|
||||
either transform the child nodes yourself or call the :meth:`generic_visit`
|
||||
method for the node first.
|
||||
|
||||
For nodes that were part of a collection of statements (that applies to all
|
||||
statement nodes), the visitor may also return a list of nodes rather than
|
||||
just a single node.
|
||||
|
||||
Usually you use the transformer like this::
|
||||
|
||||
node = YourTransformer().visit(node)
|
||||
"""
|
||||
|
||||
def generic_visit(self, node):
|
||||
for field, old_value in iter_fields(node):
|
||||
old_value = getattr(node, field, None)
|
||||
if isinstance(old_value, list):
|
||||
new_values = []
|
||||
for value in old_value:
|
||||
if isinstance(value, AST):
|
||||
value = self.visit(value)
|
||||
if value is None:
|
||||
continue
|
||||
elif not isinstance(value, AST):
|
||||
new_values.extend(value)
|
||||
continue
|
||||
new_values.append(value)
|
||||
old_value[:] = new_values
|
||||
elif isinstance(old_value, AST):
|
||||
new_node = self.visit(old_value)
|
||||
if new_node is None:
|
||||
delattr(node, field)
|
||||
else:
|
||||
setattr(node, field, new_node)
|
||||
return node
|
||||
65
AppPkg/Applications/Python/Python-2.7.10/Lib/atexit.py
Normal file
65
AppPkg/Applications/Python/Python-2.7.10/Lib/atexit.py
Normal file
@@ -0,0 +1,65 @@
|
||||
"""
|
||||
atexit.py - allow programmer to define multiple exit functions to be executed
|
||||
upon normal program termination.
|
||||
|
||||
One public function, register, is defined.
|
||||
"""
|
||||
|
||||
__all__ = ["register"]
|
||||
|
||||
import sys
|
||||
|
||||
_exithandlers = []
|
||||
def _run_exitfuncs():
|
||||
"""run any registered exit functions
|
||||
|
||||
_exithandlers is traversed in reverse order so functions are executed
|
||||
last in, first out.
|
||||
"""
|
||||
|
||||
exc_info = None
|
||||
while _exithandlers:
|
||||
func, targs, kargs = _exithandlers.pop()
|
||||
try:
|
||||
func(*targs, **kargs)
|
||||
except SystemExit:
|
||||
exc_info = sys.exc_info()
|
||||
except:
|
||||
import traceback
|
||||
print >> sys.stderr, "Error in atexit._run_exitfuncs:"
|
||||
traceback.print_exc()
|
||||
exc_info = sys.exc_info()
|
||||
|
||||
if exc_info is not None:
|
||||
raise exc_info[0], exc_info[1], exc_info[2]
|
||||
|
||||
|
||||
def register(func, *targs, **kargs):
|
||||
"""register a function to be executed upon normal program termination
|
||||
|
||||
func - function to be called at exit
|
||||
targs - optional arguments to pass to func
|
||||
kargs - optional keyword arguments to pass to func
|
||||
|
||||
func is returned to facilitate usage as a decorator.
|
||||
"""
|
||||
_exithandlers.append((func, targs, kargs))
|
||||
return func
|
||||
|
||||
if hasattr(sys, "exitfunc"):
|
||||
# Assume it's another registered exit function - append it to our list
|
||||
register(sys.exitfunc)
|
||||
sys.exitfunc = _run_exitfuncs
|
||||
|
||||
if __name__ == "__main__":
|
||||
def x1():
|
||||
print "running x1"
|
||||
def x2(n):
|
||||
print "running x2(%r)" % (n,)
|
||||
def x3(n, kwd=None):
|
||||
print "running x3(%r, kwd=%r)" % (n, kwd)
|
||||
|
||||
register(x1)
|
||||
register(x2, 12)
|
||||
register(x3, 5, "bar")
|
||||
register(x3, "no kwd args")
|
||||
518
AppPkg/Applications/Python/Python-2.7.10/Lib/binhex.py
Normal file
518
AppPkg/Applications/Python/Python-2.7.10/Lib/binhex.py
Normal file
@@ -0,0 +1,518 @@
|
||||
"""Macintosh binhex compression/decompression.
|
||||
|
||||
easy interface:
|
||||
binhex(inputfilename, outputfilename)
|
||||
hexbin(inputfilename, outputfilename)
|
||||
"""
|
||||
|
||||
#
|
||||
# Jack Jansen, CWI, August 1995.
|
||||
#
|
||||
# The module is supposed to be as compatible as possible. Especially the
|
||||
# easy interface should work "as expected" on any platform.
|
||||
# XXXX Note: currently, textfiles appear in mac-form on all platforms.
|
||||
# We seem to lack a simple character-translate in python.
|
||||
# (we should probably use ISO-Latin-1 on all but the mac platform).
|
||||
# XXXX The simple routines are too simple: they expect to hold the complete
|
||||
# files in-core. Should be fixed.
|
||||
# XXXX It would be nice to handle AppleDouble format on unix
|
||||
# (for servers serving macs).
|
||||
# XXXX I don't understand what happens when you get 0x90 times the same byte on
|
||||
# input. The resulting code (xx 90 90) would appear to be interpreted as an
|
||||
# escaped *value* of 0x90. All coders I've seen appear to ignore this nicety...
|
||||
#
|
||||
import sys
|
||||
import os
|
||||
import struct
|
||||
import binascii
|
||||
|
||||
__all__ = ["binhex","hexbin","Error"]
|
||||
|
||||
class Error(Exception):
|
||||
pass
|
||||
|
||||
# States (what have we written)
|
||||
_DID_HEADER = 0
|
||||
_DID_DATA = 1
|
||||
|
||||
# Various constants
|
||||
REASONABLY_LARGE=32768 # Minimal amount we pass the rle-coder
|
||||
LINELEN=64
|
||||
RUNCHAR=chr(0x90) # run-length introducer
|
||||
|
||||
#
|
||||
# This code is no longer byte-order dependent
|
||||
|
||||
#
|
||||
# Workarounds for non-mac machines.
|
||||
try:
|
||||
from Carbon.File import FSSpec, FInfo
|
||||
from MacOS import openrf
|
||||
|
||||
def getfileinfo(name):
|
||||
finfo = FSSpec(name).FSpGetFInfo()
|
||||
dir, file = os.path.split(name)
|
||||
# XXX Get resource/data sizes
|
||||
fp = open(name, 'rb')
|
||||
fp.seek(0, 2)
|
||||
dlen = fp.tell()
|
||||
fp = openrf(name, '*rb')
|
||||
fp.seek(0, 2)
|
||||
rlen = fp.tell()
|
||||
return file, finfo, dlen, rlen
|
||||
|
||||
def openrsrc(name, *mode):
|
||||
if not mode:
|
||||
mode = '*rb'
|
||||
else:
|
||||
mode = '*' + mode[0]
|
||||
return openrf(name, mode)
|
||||
|
||||
except ImportError:
|
||||
#
|
||||
# Glue code for non-macintosh usage
|
||||
#
|
||||
|
||||
class FInfo:
|
||||
def __init__(self):
|
||||
self.Type = '????'
|
||||
self.Creator = '????'
|
||||
self.Flags = 0
|
||||
|
||||
def getfileinfo(name):
|
||||
finfo = FInfo()
|
||||
# Quick check for textfile
|
||||
fp = open(name)
|
||||
data = open(name).read(256)
|
||||
for c in data:
|
||||
if not c.isspace() and (c<' ' or ord(c) > 0x7f):
|
||||
break
|
||||
else:
|
||||
finfo.Type = 'TEXT'
|
||||
fp.seek(0, 2)
|
||||
dsize = fp.tell()
|
||||
fp.close()
|
||||
dir, file = os.path.split(name)
|
||||
file = file.replace(':', '-', 1)
|
||||
return file, finfo, dsize, 0
|
||||
|
||||
class openrsrc:
|
||||
def __init__(self, *args):
|
||||
pass
|
||||
|
||||
def read(self, *args):
|
||||
return ''
|
||||
|
||||
def write(self, *args):
|
||||
pass
|
||||
|
||||
def close(self):
|
||||
pass
|
||||
|
||||
class _Hqxcoderengine:
|
||||
"""Write data to the coder in 3-byte chunks"""
|
||||
|
||||
def __init__(self, ofp):
|
||||
self.ofp = ofp
|
||||
self.data = ''
|
||||
self.hqxdata = ''
|
||||
self.linelen = LINELEN-1
|
||||
|
||||
def write(self, data):
|
||||
self.data = self.data + data
|
||||
datalen = len(self.data)
|
||||
todo = (datalen//3)*3
|
||||
data = self.data[:todo]
|
||||
self.data = self.data[todo:]
|
||||
if not data:
|
||||
return
|
||||
self.hqxdata = self.hqxdata + binascii.b2a_hqx(data)
|
||||
self._flush(0)
|
||||
|
||||
def _flush(self, force):
|
||||
first = 0
|
||||
while first <= len(self.hqxdata)-self.linelen:
|
||||
last = first + self.linelen
|
||||
self.ofp.write(self.hqxdata[first:last]+'\n')
|
||||
self.linelen = LINELEN
|
||||
first = last
|
||||
self.hqxdata = self.hqxdata[first:]
|
||||
if force:
|
||||
self.ofp.write(self.hqxdata + ':\n')
|
||||
|
||||
def close(self):
|
||||
if self.data:
|
||||
self.hqxdata = \
|
||||
self.hqxdata + binascii.b2a_hqx(self.data)
|
||||
self._flush(1)
|
||||
self.ofp.close()
|
||||
del self.ofp
|
||||
|
||||
class _Rlecoderengine:
|
||||
"""Write data to the RLE-coder in suitably large chunks"""
|
||||
|
||||
def __init__(self, ofp):
|
||||
self.ofp = ofp
|
||||
self.data = ''
|
||||
|
||||
def write(self, data):
|
||||
self.data = self.data + data
|
||||
if len(self.data) < REASONABLY_LARGE:
|
||||
return
|
||||
rledata = binascii.rlecode_hqx(self.data)
|
||||
self.ofp.write(rledata)
|
||||
self.data = ''
|
||||
|
||||
def close(self):
|
||||
if self.data:
|
||||
rledata = binascii.rlecode_hqx(self.data)
|
||||
self.ofp.write(rledata)
|
||||
self.ofp.close()
|
||||
del self.ofp
|
||||
|
||||
class BinHex:
|
||||
def __init__(self, name_finfo_dlen_rlen, ofp):
|
||||
name, finfo, dlen, rlen = name_finfo_dlen_rlen
|
||||
if type(ofp) == type(''):
|
||||
ofname = ofp
|
||||
ofp = open(ofname, 'w')
|
||||
ofp.write('(This file must be converted with BinHex 4.0)\n\n:')
|
||||
hqxer = _Hqxcoderengine(ofp)
|
||||
self.ofp = _Rlecoderengine(hqxer)
|
||||
self.crc = 0
|
||||
if finfo is None:
|
||||
finfo = FInfo()
|
||||
self.dlen = dlen
|
||||
self.rlen = rlen
|
||||
self._writeinfo(name, finfo)
|
||||
self.state = _DID_HEADER
|
||||
|
||||
def _writeinfo(self, name, finfo):
|
||||
nl = len(name)
|
||||
if nl > 63:
|
||||
raise Error, 'Filename too long'
|
||||
d = chr(nl) + name + '\0'
|
||||
d2 = finfo.Type + finfo.Creator
|
||||
|
||||
# Force all structs to be packed with big-endian
|
||||
d3 = struct.pack('>h', finfo.Flags)
|
||||
d4 = struct.pack('>ii', self.dlen, self.rlen)
|
||||
info = d + d2 + d3 + d4
|
||||
self._write(info)
|
||||
self._writecrc()
|
||||
|
||||
def _write(self, data):
|
||||
self.crc = binascii.crc_hqx(data, self.crc)
|
||||
self.ofp.write(data)
|
||||
|
||||
def _writecrc(self):
|
||||
# XXXX Should this be here??
|
||||
# self.crc = binascii.crc_hqx('\0\0', self.crc)
|
||||
if self.crc < 0:
|
||||
fmt = '>h'
|
||||
else:
|
||||
fmt = '>H'
|
||||
self.ofp.write(struct.pack(fmt, self.crc))
|
||||
self.crc = 0
|
||||
|
||||
def write(self, data):
|
||||
if self.state != _DID_HEADER:
|
||||
raise Error, 'Writing data at the wrong time'
|
||||
self.dlen = self.dlen - len(data)
|
||||
self._write(data)
|
||||
|
||||
def close_data(self):
|
||||
if self.dlen != 0:
|
||||
raise Error, 'Incorrect data size, diff=%r' % (self.rlen,)
|
||||
self._writecrc()
|
||||
self.state = _DID_DATA
|
||||
|
||||
def write_rsrc(self, data):
|
||||
if self.state < _DID_DATA:
|
||||
self.close_data()
|
||||
if self.state != _DID_DATA:
|
||||
raise Error, 'Writing resource data at the wrong time'
|
||||
self.rlen = self.rlen - len(data)
|
||||
self._write(data)
|
||||
|
||||
def close(self):
|
||||
if self.state is None:
|
||||
return
|
||||
try:
|
||||
if self.state < _DID_DATA:
|
||||
self.close_data()
|
||||
if self.state != _DID_DATA:
|
||||
raise Error, 'Close at the wrong time'
|
||||
if self.rlen != 0:
|
||||
raise Error, \
|
||||
"Incorrect resource-datasize, diff=%r" % (self.rlen,)
|
||||
self._writecrc()
|
||||
finally:
|
||||
self.state = None
|
||||
ofp = self.ofp
|
||||
del self.ofp
|
||||
ofp.close()
|
||||
|
||||
def binhex(inp, out):
|
||||
"""(infilename, outfilename) - Create binhex-encoded copy of a file"""
|
||||
finfo = getfileinfo(inp)
|
||||
ofp = BinHex(finfo, out)
|
||||
|
||||
ifp = open(inp, 'rb')
|
||||
# XXXX Do textfile translation on non-mac systems
|
||||
while 1:
|
||||
d = ifp.read(128000)
|
||||
if not d: break
|
||||
ofp.write(d)
|
||||
ofp.close_data()
|
||||
ifp.close()
|
||||
|
||||
ifp = openrsrc(inp, 'rb')
|
||||
while 1:
|
||||
d = ifp.read(128000)
|
||||
if not d: break
|
||||
ofp.write_rsrc(d)
|
||||
ofp.close()
|
||||
ifp.close()
|
||||
|
||||
class _Hqxdecoderengine:
|
||||
"""Read data via the decoder in 4-byte chunks"""
|
||||
|
||||
def __init__(self, ifp):
|
||||
self.ifp = ifp
|
||||
self.eof = 0
|
||||
|
||||
def read(self, totalwtd):
|
||||
"""Read at least wtd bytes (or until EOF)"""
|
||||
decdata = ''
|
||||
wtd = totalwtd
|
||||
#
|
||||
# The loop here is convoluted, since we don't really now how
|
||||
# much to decode: there may be newlines in the incoming data.
|
||||
while wtd > 0:
|
||||
if self.eof: return decdata
|
||||
wtd = ((wtd+2)//3)*4
|
||||
data = self.ifp.read(wtd)
|
||||
#
|
||||
# Next problem: there may not be a complete number of
|
||||
# bytes in what we pass to a2b. Solve by yet another
|
||||
# loop.
|
||||
#
|
||||
while 1:
|
||||
try:
|
||||
decdatacur, self.eof = \
|
||||
binascii.a2b_hqx(data)
|
||||
break
|
||||
except binascii.Incomplete:
|
||||
pass
|
||||
newdata = self.ifp.read(1)
|
||||
if not newdata:
|
||||
raise Error, \
|
||||
'Premature EOF on binhex file'
|
||||
data = data + newdata
|
||||
decdata = decdata + decdatacur
|
||||
wtd = totalwtd - len(decdata)
|
||||
if not decdata and not self.eof:
|
||||
raise Error, 'Premature EOF on binhex file'
|
||||
return decdata
|
||||
|
||||
def close(self):
|
||||
self.ifp.close()
|
||||
|
||||
class _Rledecoderengine:
|
||||
"""Read data via the RLE-coder"""
|
||||
|
||||
def __init__(self, ifp):
|
||||
self.ifp = ifp
|
||||
self.pre_buffer = ''
|
||||
self.post_buffer = ''
|
||||
self.eof = 0
|
||||
|
||||
def read(self, wtd):
|
||||
if wtd > len(self.post_buffer):
|
||||
self._fill(wtd-len(self.post_buffer))
|
||||
rv = self.post_buffer[:wtd]
|
||||
self.post_buffer = self.post_buffer[wtd:]
|
||||
return rv
|
||||
|
||||
def _fill(self, wtd):
|
||||
self.pre_buffer = self.pre_buffer + self.ifp.read(wtd+4)
|
||||
if self.ifp.eof:
|
||||
self.post_buffer = self.post_buffer + \
|
||||
binascii.rledecode_hqx(self.pre_buffer)
|
||||
self.pre_buffer = ''
|
||||
return
|
||||
|
||||
#
|
||||
# Obfuscated code ahead. We have to take care that we don't
|
||||
# end up with an orphaned RUNCHAR later on. So, we keep a couple
|
||||
# of bytes in the buffer, depending on what the end of
|
||||
# the buffer looks like:
|
||||
# '\220\0\220' - Keep 3 bytes: repeated \220 (escaped as \220\0)
|
||||
# '?\220' - Keep 2 bytes: repeated something-else
|
||||
# '\220\0' - Escaped \220: Keep 2 bytes.
|
||||
# '?\220?' - Complete repeat sequence: decode all
|
||||
# otherwise: keep 1 byte.
|
||||
#
|
||||
mark = len(self.pre_buffer)
|
||||
if self.pre_buffer[-3:] == RUNCHAR + '\0' + RUNCHAR:
|
||||
mark = mark - 3
|
||||
elif self.pre_buffer[-1] == RUNCHAR:
|
||||
mark = mark - 2
|
||||
elif self.pre_buffer[-2:] == RUNCHAR + '\0':
|
||||
mark = mark - 2
|
||||
elif self.pre_buffer[-2] == RUNCHAR:
|
||||
pass # Decode all
|
||||
else:
|
||||
mark = mark - 1
|
||||
|
||||
self.post_buffer = self.post_buffer + \
|
||||
binascii.rledecode_hqx(self.pre_buffer[:mark])
|
||||
self.pre_buffer = self.pre_buffer[mark:]
|
||||
|
||||
def close(self):
|
||||
self.ifp.close()
|
||||
|
||||
class HexBin:
|
||||
def __init__(self, ifp):
|
||||
if type(ifp) == type(''):
|
||||
ifp = open(ifp)
|
||||
#
|
||||
# Find initial colon.
|
||||
#
|
||||
while 1:
|
||||
ch = ifp.read(1)
|
||||
if not ch:
|
||||
raise Error, "No binhex data found"
|
||||
# Cater for \r\n terminated lines (which show up as \n\r, hence
|
||||
# all lines start with \r)
|
||||
if ch == '\r':
|
||||
continue
|
||||
if ch == ':':
|
||||
break
|
||||
if ch != '\n':
|
||||
dummy = ifp.readline()
|
||||
|
||||
hqxifp = _Hqxdecoderengine(ifp)
|
||||
self.ifp = _Rledecoderengine(hqxifp)
|
||||
self.crc = 0
|
||||
self._readheader()
|
||||
|
||||
def _read(self, len):
|
||||
data = self.ifp.read(len)
|
||||
self.crc = binascii.crc_hqx(data, self.crc)
|
||||
return data
|
||||
|
||||
def _checkcrc(self):
|
||||
filecrc = struct.unpack('>h', self.ifp.read(2))[0] & 0xffff
|
||||
#self.crc = binascii.crc_hqx('\0\0', self.crc)
|
||||
# XXXX Is this needed??
|
||||
self.crc = self.crc & 0xffff
|
||||
if filecrc != self.crc:
|
||||
raise Error, 'CRC error, computed %x, read %x' \
|
||||
%(self.crc, filecrc)
|
||||
self.crc = 0
|
||||
|
||||
def _readheader(self):
|
||||
len = self._read(1)
|
||||
fname = self._read(ord(len))
|
||||
rest = self._read(1+4+4+2+4+4)
|
||||
self._checkcrc()
|
||||
|
||||
type = rest[1:5]
|
||||
creator = rest[5:9]
|
||||
flags = struct.unpack('>h', rest[9:11])[0]
|
||||
self.dlen = struct.unpack('>l', rest[11:15])[0]
|
||||
self.rlen = struct.unpack('>l', rest[15:19])[0]
|
||||
|
||||
self.FName = fname
|
||||
self.FInfo = FInfo()
|
||||
self.FInfo.Creator = creator
|
||||
self.FInfo.Type = type
|
||||
self.FInfo.Flags = flags
|
||||
|
||||
self.state = _DID_HEADER
|
||||
|
||||
def read(self, *n):
|
||||
if self.state != _DID_HEADER:
|
||||
raise Error, 'Read data at wrong time'
|
||||
if n:
|
||||
n = n[0]
|
||||
n = min(n, self.dlen)
|
||||
else:
|
||||
n = self.dlen
|
||||
rv = ''
|
||||
while len(rv) < n:
|
||||
rv = rv + self._read(n-len(rv))
|
||||
self.dlen = self.dlen - n
|
||||
return rv
|
||||
|
||||
def close_data(self):
|
||||
if self.state != _DID_HEADER:
|
||||
raise Error, 'close_data at wrong time'
|
||||
if self.dlen:
|
||||
dummy = self._read(self.dlen)
|
||||
self._checkcrc()
|
||||
self.state = _DID_DATA
|
||||
|
||||
def read_rsrc(self, *n):
|
||||
if self.state == _DID_HEADER:
|
||||
self.close_data()
|
||||
if self.state != _DID_DATA:
|
||||
raise Error, 'Read resource data at wrong time'
|
||||
if n:
|
||||
n = n[0]
|
||||
n = min(n, self.rlen)
|
||||
else:
|
||||
n = self.rlen
|
||||
self.rlen = self.rlen - n
|
||||
return self._read(n)
|
||||
|
||||
def close(self):
|
||||
if self.state is None:
|
||||
return
|
||||
try:
|
||||
if self.rlen:
|
||||
dummy = self.read_rsrc(self.rlen)
|
||||
self._checkcrc()
|
||||
finally:
|
||||
self.state = None
|
||||
self.ifp.close()
|
||||
|
||||
def hexbin(inp, out):
|
||||
"""(infilename, outfilename) - Decode binhexed file"""
|
||||
ifp = HexBin(inp)
|
||||
finfo = ifp.FInfo
|
||||
if not out:
|
||||
out = ifp.FName
|
||||
|
||||
ofp = open(out, 'wb')
|
||||
# XXXX Do translation on non-mac systems
|
||||
while 1:
|
||||
d = ifp.read(128000)
|
||||
if not d: break
|
||||
ofp.write(d)
|
||||
ofp.close()
|
||||
ifp.close_data()
|
||||
|
||||
d = ifp.read_rsrc(128000)
|
||||
if d:
|
||||
ofp = openrsrc(out, 'wb')
|
||||
ofp.write(d)
|
||||
while 1:
|
||||
d = ifp.read_rsrc(128000)
|
||||
if not d: break
|
||||
ofp.write(d)
|
||||
ofp.close()
|
||||
|
||||
ifp.close()
|
||||
|
||||
def _test():
|
||||
fname = sys.argv[1]
|
||||
binhex(fname, fname+'.hqx')
|
||||
hexbin(fname+'.hqx', fname+'.viahqx')
|
||||
#hexbin(fname, fname+'.unpacked')
|
||||
sys.exit(1)
|
||||
|
||||
if __name__ == '__main__':
|
||||
_test()
|
||||
92
AppPkg/Applications/Python/Python-2.7.10/Lib/bisect.py
Normal file
92
AppPkg/Applications/Python/Python-2.7.10/Lib/bisect.py
Normal file
@@ -0,0 +1,92 @@
|
||||
"""Bisection algorithms."""
|
||||
|
||||
def insort_right(a, x, lo=0, hi=None):
|
||||
"""Insert item x in list a, and keep it sorted assuming a is sorted.
|
||||
|
||||
If x is already in a, insert it to the right of the rightmost x.
|
||||
|
||||
Optional args lo (default 0) and hi (default len(a)) bound the
|
||||
slice of a to be searched.
|
||||
"""
|
||||
|
||||
if lo < 0:
|
||||
raise ValueError('lo must be non-negative')
|
||||
if hi is None:
|
||||
hi = len(a)
|
||||
while lo < hi:
|
||||
mid = (lo+hi)//2
|
||||
if x < a[mid]: hi = mid
|
||||
else: lo = mid+1
|
||||
a.insert(lo, x)
|
||||
|
||||
insort = insort_right # backward compatibility
|
||||
|
||||
def bisect_right(a, x, lo=0, hi=None):
|
||||
"""Return the index where to insert item x in list a, assuming a is sorted.
|
||||
|
||||
The return value i is such that all e in a[:i] have e <= x, and all e in
|
||||
a[i:] have e > x. So if x already appears in the list, a.insert(x) will
|
||||
insert just after the rightmost x already there.
|
||||
|
||||
Optional args lo (default 0) and hi (default len(a)) bound the
|
||||
slice of a to be searched.
|
||||
"""
|
||||
|
||||
if lo < 0:
|
||||
raise ValueError('lo must be non-negative')
|
||||
if hi is None:
|
||||
hi = len(a)
|
||||
while lo < hi:
|
||||
mid = (lo+hi)//2
|
||||
if x < a[mid]: hi = mid
|
||||
else: lo = mid+1
|
||||
return lo
|
||||
|
||||
bisect = bisect_right # backward compatibility
|
||||
|
||||
def insort_left(a, x, lo=0, hi=None):
|
||||
"""Insert item x in list a, and keep it sorted assuming a is sorted.
|
||||
|
||||
If x is already in a, insert it to the left of the leftmost x.
|
||||
|
||||
Optional args lo (default 0) and hi (default len(a)) bound the
|
||||
slice of a to be searched.
|
||||
"""
|
||||
|
||||
if lo < 0:
|
||||
raise ValueError('lo must be non-negative')
|
||||
if hi is None:
|
||||
hi = len(a)
|
||||
while lo < hi:
|
||||
mid = (lo+hi)//2
|
||||
if a[mid] < x: lo = mid+1
|
||||
else: hi = mid
|
||||
a.insert(lo, x)
|
||||
|
||||
|
||||
def bisect_left(a, x, lo=0, hi=None):
|
||||
"""Return the index where to insert item x in list a, assuming a is sorted.
|
||||
|
||||
The return value i is such that all e in a[:i] have e < x, and all e in
|
||||
a[i:] have e >= x. So if x already appears in the list, a.insert(x) will
|
||||
insert just before the leftmost x already there.
|
||||
|
||||
Optional args lo (default 0) and hi (default len(a)) bound the
|
||||
slice of a to be searched.
|
||||
"""
|
||||
|
||||
if lo < 0:
|
||||
raise ValueError('lo must be non-negative')
|
||||
if hi is None:
|
||||
hi = len(a)
|
||||
while lo < hi:
|
||||
mid = (lo+hi)//2
|
||||
if a[mid] < x: lo = mid+1
|
||||
else: hi = mid
|
||||
return lo
|
||||
|
||||
# Overwrite above definitions with a fast C implementation
|
||||
try:
|
||||
from _bisect import *
|
||||
except ImportError:
|
||||
pass
|
||||
713
AppPkg/Applications/Python/Python-2.7.10/Lib/calendar.py
Normal file
713
AppPkg/Applications/Python/Python-2.7.10/Lib/calendar.py
Normal file
@@ -0,0 +1,713 @@
|
||||
"""Calendar printing functions
|
||||
|
||||
Note when comparing these calendars to the ones printed by cal(1): By
|
||||
default, these calendars have Monday as the first day of the week, and
|
||||
Sunday as the last (the European convention). Use setfirstweekday() to
|
||||
set the first day of the week (0=Monday, 6=Sunday)."""
|
||||
|
||||
import sys
|
||||
import datetime
|
||||
import locale as _locale
|
||||
|
||||
__all__ = ["IllegalMonthError", "IllegalWeekdayError", "setfirstweekday",
|
||||
"firstweekday", "isleap", "leapdays", "weekday", "monthrange",
|
||||
"monthcalendar", "prmonth", "month", "prcal", "calendar",
|
||||
"timegm", "month_name", "month_abbr", "day_name", "day_abbr"]
|
||||
|
||||
# Exception raised for bad input (with string parameter for details)
|
||||
error = ValueError
|
||||
|
||||
# Exceptions raised for bad input
|
||||
class IllegalMonthError(ValueError):
|
||||
def __init__(self, month):
|
||||
self.month = month
|
||||
def __str__(self):
|
||||
return "bad month number %r; must be 1-12" % self.month
|
||||
|
||||
|
||||
class IllegalWeekdayError(ValueError):
|
||||
def __init__(self, weekday):
|
||||
self.weekday = weekday
|
||||
def __str__(self):
|
||||
return "bad weekday number %r; must be 0 (Monday) to 6 (Sunday)" % self.weekday
|
||||
|
||||
|
||||
# Constants for months referenced later
|
||||
January = 1
|
||||
February = 2
|
||||
|
||||
# Number of days per month (except for February in leap years)
|
||||
mdays = [0, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
|
||||
|
||||
# This module used to have hard-coded lists of day and month names, as
|
||||
# English strings. The classes following emulate a read-only version of
|
||||
# that, but supply localized names. Note that the values are computed
|
||||
# fresh on each call, in case the user changes locale between calls.
|
||||
|
||||
class _localized_month:
|
||||
|
||||
_months = [datetime.date(2001, i+1, 1).strftime for i in range(12)]
|
||||
_months.insert(0, lambda x: "")
|
||||
|
||||
def __init__(self, format):
|
||||
self.format = format
|
||||
|
||||
def __getitem__(self, i):
|
||||
funcs = self._months[i]
|
||||
if isinstance(i, slice):
|
||||
return [f(self.format) for f in funcs]
|
||||
else:
|
||||
return funcs(self.format)
|
||||
|
||||
def __len__(self):
|
||||
return 13
|
||||
|
||||
|
||||
class _localized_day:
|
||||
|
||||
# January 1, 2001, was a Monday.
|
||||
_days = [datetime.date(2001, 1, i+1).strftime for i in range(7)]
|
||||
|
||||
def __init__(self, format):
|
||||
self.format = format
|
||||
|
||||
def __getitem__(self, i):
|
||||
funcs = self._days[i]
|
||||
if isinstance(i, slice):
|
||||
return [f(self.format) for f in funcs]
|
||||
else:
|
||||
return funcs(self.format)
|
||||
|
||||
def __len__(self):
|
||||
return 7
|
||||
|
||||
|
||||
# Full and abbreviated names of weekdays
|
||||
day_name = _localized_day('%A')
|
||||
day_abbr = _localized_day('%a')
|
||||
|
||||
# Full and abbreviated names of months (1-based arrays!!!)
|
||||
month_name = _localized_month('%B')
|
||||
month_abbr = _localized_month('%b')
|
||||
|
||||
# Constants for weekdays
|
||||
(MONDAY, TUESDAY, WEDNESDAY, THURSDAY, FRIDAY, SATURDAY, SUNDAY) = range(7)
|
||||
|
||||
|
||||
def isleap(year):
|
||||
"""Return True for leap years, False for non-leap years."""
|
||||
return year % 4 == 0 and (year % 100 != 0 or year % 400 == 0)
|
||||
|
||||
|
||||
def leapdays(y1, y2):
|
||||
"""Return number of leap years in range [y1, y2).
|
||||
Assume y1 <= y2."""
|
||||
y1 -= 1
|
||||
y2 -= 1
|
||||
return (y2//4 - y1//4) - (y2//100 - y1//100) + (y2//400 - y1//400)
|
||||
|
||||
|
||||
def weekday(year, month, day):
|
||||
"""Return weekday (0-6 ~ Mon-Sun) for year (1970-...), month (1-12),
|
||||
day (1-31)."""
|
||||
return datetime.date(year, month, day).weekday()
|
||||
|
||||
|
||||
def monthrange(year, month):
|
||||
"""Return weekday (0-6 ~ Mon-Sun) and number of days (28-31) for
|
||||
year, month."""
|
||||
if not 1 <= month <= 12:
|
||||
raise IllegalMonthError(month)
|
||||
day1 = weekday(year, month, 1)
|
||||
ndays = mdays[month] + (month == February and isleap(year))
|
||||
return day1, ndays
|
||||
|
||||
|
||||
class Calendar(object):
|
||||
"""
|
||||
Base calendar class. This class doesn't do any formatting. It simply
|
||||
provides data to subclasses.
|
||||
"""
|
||||
|
||||
def __init__(self, firstweekday=0):
|
||||
self.firstweekday = firstweekday # 0 = Monday, 6 = Sunday
|
||||
|
||||
def getfirstweekday(self):
|
||||
return self._firstweekday % 7
|
||||
|
||||
def setfirstweekday(self, firstweekday):
|
||||
self._firstweekday = firstweekday
|
||||
|
||||
firstweekday = property(getfirstweekday, setfirstweekday)
|
||||
|
||||
def iterweekdays(self):
|
||||
"""
|
||||
Return a iterator for one week of weekday numbers starting with the
|
||||
configured first one.
|
||||
"""
|
||||
for i in range(self.firstweekday, self.firstweekday + 7):
|
||||
yield i%7
|
||||
|
||||
def itermonthdates(self, year, month):
|
||||
"""
|
||||
Return an iterator for one month. The iterator will yield datetime.date
|
||||
values and will always iterate through complete weeks, so it will yield
|
||||
dates outside the specified month.
|
||||
"""
|
||||
date = datetime.date(year, month, 1)
|
||||
# Go back to the beginning of the week
|
||||
days = (date.weekday() - self.firstweekday) % 7
|
||||
date -= datetime.timedelta(days=days)
|
||||
oneday = datetime.timedelta(days=1)
|
||||
while True:
|
||||
yield date
|
||||
try:
|
||||
date += oneday
|
||||
except OverflowError:
|
||||
# Adding one day could fail after datetime.MAXYEAR
|
||||
break
|
||||
if date.month != month and date.weekday() == self.firstweekday:
|
||||
break
|
||||
|
||||
def itermonthdays2(self, year, month):
|
||||
"""
|
||||
Like itermonthdates(), but will yield (day number, weekday number)
|
||||
tuples. For days outside the specified month the day number is 0.
|
||||
"""
|
||||
for date in self.itermonthdates(year, month):
|
||||
if date.month != month:
|
||||
yield (0, date.weekday())
|
||||
else:
|
||||
yield (date.day, date.weekday())
|
||||
|
||||
def itermonthdays(self, year, month):
|
||||
"""
|
||||
Like itermonthdates(), but will yield day numbers. For days outside
|
||||
the specified month the day number is 0.
|
||||
"""
|
||||
for date in self.itermonthdates(year, month):
|
||||
if date.month != month:
|
||||
yield 0
|
||||
else:
|
||||
yield date.day
|
||||
|
||||
def monthdatescalendar(self, year, month):
|
||||
"""
|
||||
Return a matrix (list of lists) representing a month's calendar.
|
||||
Each row represents a week; week entries are datetime.date values.
|
||||
"""
|
||||
dates = list(self.itermonthdates(year, month))
|
||||
return [ dates[i:i+7] for i in range(0, len(dates), 7) ]
|
||||
|
||||
def monthdays2calendar(self, year, month):
|
||||
"""
|
||||
Return a matrix representing a month's calendar.
|
||||
Each row represents a week; week entries are
|
||||
(day number, weekday number) tuples. Day numbers outside this month
|
||||
are zero.
|
||||
"""
|
||||
days = list(self.itermonthdays2(year, month))
|
||||
return [ days[i:i+7] for i in range(0, len(days), 7) ]
|
||||
|
||||
def monthdayscalendar(self, year, month):
|
||||
"""
|
||||
Return a matrix representing a month's calendar.
|
||||
Each row represents a week; days outside this month are zero.
|
||||
"""
|
||||
days = list(self.itermonthdays(year, month))
|
||||
return [ days[i:i+7] for i in range(0, len(days), 7) ]
|
||||
|
||||
def yeardatescalendar(self, year, width=3):
|
||||
"""
|
||||
Return the data for the specified year ready for formatting. The return
|
||||
value is a list of month rows. Each month row contains up to width months.
|
||||
Each month contains between 4 and 6 weeks and each week contains 1-7
|
||||
days. Days are datetime.date objects.
|
||||
"""
|
||||
months = [
|
||||
self.monthdatescalendar(year, i)
|
||||
for i in range(January, January+12)
|
||||
]
|
||||
return [months[i:i+width] for i in range(0, len(months), width) ]
|
||||
|
||||
def yeardays2calendar(self, year, width=3):
|
||||
"""
|
||||
Return the data for the specified year ready for formatting (similar to
|
||||
yeardatescalendar()). Entries in the week lists are
|
||||
(day number, weekday number) tuples. Day numbers outside this month are
|
||||
zero.
|
||||
"""
|
||||
months = [
|
||||
self.monthdays2calendar(year, i)
|
||||
for i in range(January, January+12)
|
||||
]
|
||||
return [months[i:i+width] for i in range(0, len(months), width) ]
|
||||
|
||||
def yeardayscalendar(self, year, width=3):
|
||||
"""
|
||||
Return the data for the specified year ready for formatting (similar to
|
||||
yeardatescalendar()). Entries in the week lists are day numbers.
|
||||
Day numbers outside this month are zero.
|
||||
"""
|
||||
months = [
|
||||
self.monthdayscalendar(year, i)
|
||||
for i in range(January, January+12)
|
||||
]
|
||||
return [months[i:i+width] for i in range(0, len(months), width) ]
|
||||
|
||||
|
||||
class TextCalendar(Calendar):
|
||||
"""
|
||||
Subclass of Calendar that outputs a calendar as a simple plain text
|
||||
similar to the UNIX program cal.
|
||||
"""
|
||||
|
||||
def prweek(self, theweek, width):
|
||||
"""
|
||||
Print a single week (no newline).
|
||||
"""
|
||||
print self.formatweek(theweek, width),
|
||||
|
||||
def formatday(self, day, weekday, width):
|
||||
"""
|
||||
Returns a formatted day.
|
||||
"""
|
||||
if day == 0:
|
||||
s = ''
|
||||
else:
|
||||
s = '%2i' % day # right-align single-digit days
|
||||
return s.center(width)
|
||||
|
||||
def formatweek(self, theweek, width):
|
||||
"""
|
||||
Returns a single week in a string (no newline).
|
||||
"""
|
||||
return ' '.join(self.formatday(d, wd, width) for (d, wd) in theweek)
|
||||
|
||||
def formatweekday(self, day, width):
|
||||
"""
|
||||
Returns a formatted week day name.
|
||||
"""
|
||||
if width >= 9:
|
||||
names = day_name
|
||||
else:
|
||||
names = day_abbr
|
||||
return names[day][:width].center(width)
|
||||
|
||||
def formatweekheader(self, width):
|
||||
"""
|
||||
Return a header for a week.
|
||||
"""
|
||||
return ' '.join(self.formatweekday(i, width) for i in self.iterweekdays())
|
||||
|
||||
def formatmonthname(self, theyear, themonth, width, withyear=True):
|
||||
"""
|
||||
Return a formatted month name.
|
||||
"""
|
||||
s = month_name[themonth]
|
||||
if withyear:
|
||||
s = "%s %r" % (s, theyear)
|
||||
return s.center(width)
|
||||
|
||||
def prmonth(self, theyear, themonth, w=0, l=0):
|
||||
"""
|
||||
Print a month's calendar.
|
||||
"""
|
||||
print self.formatmonth(theyear, themonth, w, l),
|
||||
|
||||
def formatmonth(self, theyear, themonth, w=0, l=0):
|
||||
"""
|
||||
Return a month's calendar string (multi-line).
|
||||
"""
|
||||
w = max(2, w)
|
||||
l = max(1, l)
|
||||
s = self.formatmonthname(theyear, themonth, 7 * (w + 1) - 1)
|
||||
s = s.rstrip()
|
||||
s += '\n' * l
|
||||
s += self.formatweekheader(w).rstrip()
|
||||
s += '\n' * l
|
||||
for week in self.monthdays2calendar(theyear, themonth):
|
||||
s += self.formatweek(week, w).rstrip()
|
||||
s += '\n' * l
|
||||
return s
|
||||
|
||||
def formatyear(self, theyear, w=2, l=1, c=6, m=3):
|
||||
"""
|
||||
Returns a year's calendar as a multi-line string.
|
||||
"""
|
||||
w = max(2, w)
|
||||
l = max(1, l)
|
||||
c = max(2, c)
|
||||
colwidth = (w + 1) * 7 - 1
|
||||
v = []
|
||||
a = v.append
|
||||
a(repr(theyear).center(colwidth*m+c*(m-1)).rstrip())
|
||||
a('\n'*l)
|
||||
header = self.formatweekheader(w)
|
||||
for (i, row) in enumerate(self.yeardays2calendar(theyear, m)):
|
||||
# months in this row
|
||||
months = range(m*i+1, min(m*(i+1)+1, 13))
|
||||
a('\n'*l)
|
||||
names = (self.formatmonthname(theyear, k, colwidth, False)
|
||||
for k in months)
|
||||
a(formatstring(names, colwidth, c).rstrip())
|
||||
a('\n'*l)
|
||||
headers = (header for k in months)
|
||||
a(formatstring(headers, colwidth, c).rstrip())
|
||||
a('\n'*l)
|
||||
# max number of weeks for this row
|
||||
height = max(len(cal) for cal in row)
|
||||
for j in range(height):
|
||||
weeks = []
|
||||
for cal in row:
|
||||
if j >= len(cal):
|
||||
weeks.append('')
|
||||
else:
|
||||
weeks.append(self.formatweek(cal[j], w))
|
||||
a(formatstring(weeks, colwidth, c).rstrip())
|
||||
a('\n' * l)
|
||||
return ''.join(v)
|
||||
|
||||
def pryear(self, theyear, w=0, l=0, c=6, m=3):
|
||||
"""Print a year's calendar."""
|
||||
print self.formatyear(theyear, w, l, c, m)
|
||||
|
||||
|
||||
class HTMLCalendar(Calendar):
|
||||
"""
|
||||
This calendar returns complete HTML pages.
|
||||
"""
|
||||
|
||||
# CSS classes for the day <td>s
|
||||
cssclasses = ["mon", "tue", "wed", "thu", "fri", "sat", "sun"]
|
||||
|
||||
def formatday(self, day, weekday):
|
||||
"""
|
||||
Return a day as a table cell.
|
||||
"""
|
||||
if day == 0:
|
||||
return '<td class="noday"> </td>' # day outside month
|
||||
else:
|
||||
return '<td class="%s">%d</td>' % (self.cssclasses[weekday], day)
|
||||
|
||||
def formatweek(self, theweek):
|
||||
"""
|
||||
Return a complete week as a table row.
|
||||
"""
|
||||
s = ''.join(self.formatday(d, wd) for (d, wd) in theweek)
|
||||
return '<tr>%s</tr>' % s
|
||||
|
||||
def formatweekday(self, day):
|
||||
"""
|
||||
Return a weekday name as a table header.
|
||||
"""
|
||||
return '<th class="%s">%s</th>' % (self.cssclasses[day], day_abbr[day])
|
||||
|
||||
def formatweekheader(self):
|
||||
"""
|
||||
Return a header for a week as a table row.
|
||||
"""
|
||||
s = ''.join(self.formatweekday(i) for i in self.iterweekdays())
|
||||
return '<tr>%s</tr>' % s
|
||||
|
||||
def formatmonthname(self, theyear, themonth, withyear=True):
|
||||
"""
|
||||
Return a month name as a table row.
|
||||
"""
|
||||
if withyear:
|
||||
s = '%s %s' % (month_name[themonth], theyear)
|
||||
else:
|
||||
s = '%s' % month_name[themonth]
|
||||
return '<tr><th colspan="7" class="month">%s</th></tr>' % s
|
||||
|
||||
def formatmonth(self, theyear, themonth, withyear=True):
|
||||
"""
|
||||
Return a formatted month as a table.
|
||||
"""
|
||||
v = []
|
||||
a = v.append
|
||||
a('<table border="0" cellpadding="0" cellspacing="0" class="month">')
|
||||
a('\n')
|
||||
a(self.formatmonthname(theyear, themonth, withyear=withyear))
|
||||
a('\n')
|
||||
a(self.formatweekheader())
|
||||
a('\n')
|
||||
for week in self.monthdays2calendar(theyear, themonth):
|
||||
a(self.formatweek(week))
|
||||
a('\n')
|
||||
a('</table>')
|
||||
a('\n')
|
||||
return ''.join(v)
|
||||
|
||||
def formatyear(self, theyear, width=3):
|
||||
"""
|
||||
Return a formatted year as a table of tables.
|
||||
"""
|
||||
v = []
|
||||
a = v.append
|
||||
width = max(width, 1)
|
||||
a('<table border="0" cellpadding="0" cellspacing="0" class="year">')
|
||||
a('\n')
|
||||
a('<tr><th colspan="%d" class="year">%s</th></tr>' % (width, theyear))
|
||||
for i in range(January, January+12, width):
|
||||
# months in this row
|
||||
months = range(i, min(i+width, 13))
|
||||
a('<tr>')
|
||||
for m in months:
|
||||
a('<td>')
|
||||
a(self.formatmonth(theyear, m, withyear=False))
|
||||
a('</td>')
|
||||
a('</tr>')
|
||||
a('</table>')
|
||||
return ''.join(v)
|
||||
|
||||
def formatyearpage(self, theyear, width=3, css='calendar.css', encoding=None):
|
||||
"""
|
||||
Return a formatted year as a complete HTML page.
|
||||
"""
|
||||
if encoding is None:
|
||||
encoding = sys.getdefaultencoding()
|
||||
v = []
|
||||
a = v.append
|
||||
a('<?xml version="1.0" encoding="%s"?>\n' % encoding)
|
||||
a('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">\n')
|
||||
a('<html>\n')
|
||||
a('<head>\n')
|
||||
a('<meta http-equiv="Content-Type" content="text/html; charset=%s" />\n' % encoding)
|
||||
if css is not None:
|
||||
a('<link rel="stylesheet" type="text/css" href="%s" />\n' % css)
|
||||
a('<title>Calendar for %d</title>\n' % theyear)
|
||||
a('</head>\n')
|
||||
a('<body>\n')
|
||||
a(self.formatyear(theyear, width))
|
||||
a('</body>\n')
|
||||
a('</html>\n')
|
||||
return ''.join(v).encode(encoding, "xmlcharrefreplace")
|
||||
|
||||
|
||||
class TimeEncoding:
|
||||
def __init__(self, locale):
|
||||
self.locale = locale
|
||||
|
||||
def __enter__(self):
|
||||
self.oldlocale = _locale.getlocale(_locale.LC_TIME)
|
||||
_locale.setlocale(_locale.LC_TIME, self.locale)
|
||||
return _locale.getlocale(_locale.LC_TIME)[1]
|
||||
|
||||
def __exit__(self, *args):
|
||||
_locale.setlocale(_locale.LC_TIME, self.oldlocale)
|
||||
|
||||
|
||||
class LocaleTextCalendar(TextCalendar):
|
||||
"""
|
||||
This class can be passed a locale name in the constructor and will return
|
||||
month and weekday names in the specified locale. If this locale includes
|
||||
an encoding all strings containing month and weekday names will be returned
|
||||
as unicode.
|
||||
"""
|
||||
|
||||
def __init__(self, firstweekday=0, locale=None):
|
||||
TextCalendar.__init__(self, firstweekday)
|
||||
if locale is None:
|
||||
locale = _locale.getdefaultlocale()
|
||||
self.locale = locale
|
||||
|
||||
def formatweekday(self, day, width):
|
||||
with TimeEncoding(self.locale) as encoding:
|
||||
if width >= 9:
|
||||
names = day_name
|
||||
else:
|
||||
names = day_abbr
|
||||
name = names[day]
|
||||
if encoding is not None:
|
||||
name = name.decode(encoding)
|
||||
return name[:width].center(width)
|
||||
|
||||
def formatmonthname(self, theyear, themonth, width, withyear=True):
|
||||
with TimeEncoding(self.locale) as encoding:
|
||||
s = month_name[themonth]
|
||||
if encoding is not None:
|
||||
s = s.decode(encoding)
|
||||
if withyear:
|
||||
s = "%s %r" % (s, theyear)
|
||||
return s.center(width)
|
||||
|
||||
|
||||
class LocaleHTMLCalendar(HTMLCalendar):
|
||||
"""
|
||||
This class can be passed a locale name in the constructor and will return
|
||||
month and weekday names in the specified locale. If this locale includes
|
||||
an encoding all strings containing month and weekday names will be returned
|
||||
as unicode.
|
||||
"""
|
||||
def __init__(self, firstweekday=0, locale=None):
|
||||
HTMLCalendar.__init__(self, firstweekday)
|
||||
if locale is None:
|
||||
locale = _locale.getdefaultlocale()
|
||||
self.locale = locale
|
||||
|
||||
def formatweekday(self, day):
|
||||
with TimeEncoding(self.locale) as encoding:
|
||||
s = day_abbr[day]
|
||||
if encoding is not None:
|
||||
s = s.decode(encoding)
|
||||
return '<th class="%s">%s</th>' % (self.cssclasses[day], s)
|
||||
|
||||
def formatmonthname(self, theyear, themonth, withyear=True):
|
||||
with TimeEncoding(self.locale) as encoding:
|
||||
s = month_name[themonth]
|
||||
if encoding is not None:
|
||||
s = s.decode(encoding)
|
||||
if withyear:
|
||||
s = '%s %s' % (s, theyear)
|
||||
return '<tr><th colspan="7" class="month">%s</th></tr>' % s
|
||||
|
||||
|
||||
# Support for old module level interface
|
||||
c = TextCalendar()
|
||||
|
||||
firstweekday = c.getfirstweekday
|
||||
|
||||
def setfirstweekday(firstweekday):
|
||||
try:
|
||||
firstweekday.__index__
|
||||
except AttributeError:
|
||||
raise IllegalWeekdayError(firstweekday)
|
||||
if not MONDAY <= firstweekday <= SUNDAY:
|
||||
raise IllegalWeekdayError(firstweekday)
|
||||
c.firstweekday = firstweekday
|
||||
|
||||
monthcalendar = c.monthdayscalendar
|
||||
prweek = c.prweek
|
||||
week = c.formatweek
|
||||
weekheader = c.formatweekheader
|
||||
prmonth = c.prmonth
|
||||
month = c.formatmonth
|
||||
calendar = c.formatyear
|
||||
prcal = c.pryear
|
||||
|
||||
|
||||
# Spacing of month columns for multi-column year calendar
|
||||
_colwidth = 7*3 - 1 # Amount printed by prweek()
|
||||
_spacing = 6 # Number of spaces between columns
|
||||
|
||||
|
||||
def format(cols, colwidth=_colwidth, spacing=_spacing):
|
||||
"""Prints multi-column formatting for year calendars"""
|
||||
print formatstring(cols, colwidth, spacing)
|
||||
|
||||
|
||||
def formatstring(cols, colwidth=_colwidth, spacing=_spacing):
|
||||
"""Returns a string formatted from n strings, centered within n columns."""
|
||||
spacing *= ' '
|
||||
return spacing.join(c.center(colwidth) for c in cols)
|
||||
|
||||
|
||||
EPOCH = 1970
|
||||
_EPOCH_ORD = datetime.date(EPOCH, 1, 1).toordinal()
|
||||
|
||||
|
||||
def timegm(tuple):
|
||||
"""Unrelated but handy function to calculate Unix timestamp from GMT."""
|
||||
year, month, day, hour, minute, second = tuple[:6]
|
||||
days = datetime.date(year, month, 1).toordinal() - _EPOCH_ORD + day - 1
|
||||
hours = days*24 + hour
|
||||
minutes = hours*60 + minute
|
||||
seconds = minutes*60 + second
|
||||
return seconds
|
||||
|
||||
|
||||
def main(args):
|
||||
import optparse
|
||||
parser = optparse.OptionParser(usage="usage: %prog [options] [year [month]]")
|
||||
parser.add_option(
|
||||
"-w", "--width",
|
||||
dest="width", type="int", default=2,
|
||||
help="width of date column (default 2, text only)"
|
||||
)
|
||||
parser.add_option(
|
||||
"-l", "--lines",
|
||||
dest="lines", type="int", default=1,
|
||||
help="number of lines for each week (default 1, text only)"
|
||||
)
|
||||
parser.add_option(
|
||||
"-s", "--spacing",
|
||||
dest="spacing", type="int", default=6,
|
||||
help="spacing between months (default 6, text only)"
|
||||
)
|
||||
parser.add_option(
|
||||
"-m", "--months",
|
||||
dest="months", type="int", default=3,
|
||||
help="months per row (default 3, text only)"
|
||||
)
|
||||
parser.add_option(
|
||||
"-c", "--css",
|
||||
dest="css", default="calendar.css",
|
||||
help="CSS to use for page (html only)"
|
||||
)
|
||||
parser.add_option(
|
||||
"-L", "--locale",
|
||||
dest="locale", default=None,
|
||||
help="locale to be used from month and weekday names"
|
||||
)
|
||||
parser.add_option(
|
||||
"-e", "--encoding",
|
||||
dest="encoding", default=None,
|
||||
help="Encoding to use for output"
|
||||
)
|
||||
parser.add_option(
|
||||
"-t", "--type",
|
||||
dest="type", default="text",
|
||||
choices=("text", "html"),
|
||||
help="output type (text or html)"
|
||||
)
|
||||
|
||||
(options, args) = parser.parse_args(args)
|
||||
|
||||
if options.locale and not options.encoding:
|
||||
parser.error("if --locale is specified --encoding is required")
|
||||
sys.exit(1)
|
||||
|
||||
locale = options.locale, options.encoding
|
||||
|
||||
if options.type == "html":
|
||||
if options.locale:
|
||||
cal = LocaleHTMLCalendar(locale=locale)
|
||||
else:
|
||||
cal = HTMLCalendar()
|
||||
encoding = options.encoding
|
||||
if encoding is None:
|
||||
encoding = sys.getdefaultencoding()
|
||||
optdict = dict(encoding=encoding, css=options.css)
|
||||
if len(args) == 1:
|
||||
print cal.formatyearpage(datetime.date.today().year, **optdict)
|
||||
elif len(args) == 2:
|
||||
print cal.formatyearpage(int(args[1]), **optdict)
|
||||
else:
|
||||
parser.error("incorrect number of arguments")
|
||||
sys.exit(1)
|
||||
else:
|
||||
if options.locale:
|
||||
cal = LocaleTextCalendar(locale=locale)
|
||||
else:
|
||||
cal = TextCalendar()
|
||||
optdict = dict(w=options.width, l=options.lines)
|
||||
if len(args) != 3:
|
||||
optdict["c"] = options.spacing
|
||||
optdict["m"] = options.months
|
||||
if len(args) == 1:
|
||||
result = cal.formatyear(datetime.date.today().year, **optdict)
|
||||
elif len(args) == 2:
|
||||
result = cal.formatyear(int(args[1]), **optdict)
|
||||
elif len(args) == 3:
|
||||
result = cal.formatmonth(int(args[1]), int(args[2]), **optdict)
|
||||
else:
|
||||
parser.error("incorrect number of arguments")
|
||||
sys.exit(1)
|
||||
if options.encoding:
|
||||
result = result.encode(options.encoding)
|
||||
print result
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main(sys.argv)
|
||||
404
AppPkg/Applications/Python/Python-2.7.10/Lib/cmd.py
Normal file
404
AppPkg/Applications/Python/Python-2.7.10/Lib/cmd.py
Normal file
@@ -0,0 +1,404 @@
|
||||
"""A generic class to build line-oriented command interpreters.
|
||||
|
||||
Interpreters constructed with this class obey the following conventions:
|
||||
|
||||
1. End of file on input is processed as the command 'EOF'.
|
||||
2. A command is parsed out of each line by collecting the prefix composed
|
||||
of characters in the identchars member.
|
||||
3. A command `foo' is dispatched to a method 'do_foo()'; the do_ method
|
||||
is passed a single argument consisting of the remainder of the line.
|
||||
4. Typing an empty line repeats the last command. (Actually, it calls the
|
||||
method `emptyline', which may be overridden in a subclass.)
|
||||
5. There is a predefined `help' method. Given an argument `topic', it
|
||||
calls the command `help_topic'. With no arguments, it lists all topics
|
||||
with defined help_ functions, broken into up to three topics; documented
|
||||
commands, miscellaneous help topics, and undocumented commands.
|
||||
6. The command '?' is a synonym for `help'. The command '!' is a synonym
|
||||
for `shell', if a do_shell method exists.
|
||||
7. If completion is enabled, completing commands will be done automatically,
|
||||
and completing of commands args is done by calling complete_foo() with
|
||||
arguments text, line, begidx, endidx. text is string we are matching
|
||||
against, all returned matches must begin with it. line is the current
|
||||
input line (lstripped), begidx and endidx are the beginning and end
|
||||
indexes of the text being matched, which could be used to provide
|
||||
different completion depending upon which position the argument is in.
|
||||
|
||||
The `default' method may be overridden to intercept commands for which there
|
||||
is no do_ method.
|
||||
|
||||
The `completedefault' method may be overridden to intercept completions for
|
||||
commands that have no complete_ method.
|
||||
|
||||
The data member `self.ruler' sets the character used to draw separator lines
|
||||
in the help messages. If empty, no ruler line is drawn. It defaults to "=".
|
||||
|
||||
If the value of `self.intro' is nonempty when the cmdloop method is called,
|
||||
it is printed out on interpreter startup. This value may be overridden
|
||||
via an optional argument to the cmdloop() method.
|
||||
|
||||
The data members `self.doc_header', `self.misc_header', and
|
||||
`self.undoc_header' set the headers used for the help function's
|
||||
listings of documented functions, miscellaneous topics, and undocumented
|
||||
functions respectively.
|
||||
|
||||
These interpreters use raw_input; thus, if the readline module is loaded,
|
||||
they automatically support Emacs-like command history and editing features.
|
||||
"""
|
||||
|
||||
import string
|
||||
|
||||
__all__ = ["Cmd"]
|
||||
|
||||
PROMPT = '(Cmd) '
|
||||
IDENTCHARS = string.ascii_letters + string.digits + '_'
|
||||
|
||||
class Cmd:
|
||||
"""A simple framework for writing line-oriented command interpreters.
|
||||
|
||||
These are often useful for test harnesses, administrative tools, and
|
||||
prototypes that will later be wrapped in a more sophisticated interface.
|
||||
|
||||
A Cmd instance or subclass instance is a line-oriented interpreter
|
||||
framework. There is no good reason to instantiate Cmd itself; rather,
|
||||
it's useful as a superclass of an interpreter class you define yourself
|
||||
in order to inherit Cmd's methods and encapsulate action methods.
|
||||
|
||||
"""
|
||||
prompt = PROMPT
|
||||
identchars = IDENTCHARS
|
||||
ruler = '='
|
||||
lastcmd = ''
|
||||
intro = None
|
||||
doc_leader = ""
|
||||
doc_header = "Documented commands (type help <topic>):"
|
||||
misc_header = "Miscellaneous help topics:"
|
||||
undoc_header = "Undocumented commands:"
|
||||
nohelp = "*** No help on %s"
|
||||
use_rawinput = 1
|
||||
|
||||
def __init__(self, completekey='tab', stdin=None, stdout=None):
|
||||
"""Instantiate a line-oriented interpreter framework.
|
||||
|
||||
The optional argument 'completekey' is the readline name of a
|
||||
completion key; it defaults to the Tab key. If completekey is
|
||||
not None and the readline module is available, command completion
|
||||
is done automatically. The optional arguments stdin and stdout
|
||||
specify alternate input and output file objects; if not specified,
|
||||
sys.stdin and sys.stdout are used.
|
||||
|
||||
"""
|
||||
import sys
|
||||
if stdin is not None:
|
||||
self.stdin = stdin
|
||||
else:
|
||||
self.stdin = sys.stdin
|
||||
if stdout is not None:
|
||||
self.stdout = stdout
|
||||
else:
|
||||
self.stdout = sys.stdout
|
||||
self.cmdqueue = []
|
||||
self.completekey = completekey
|
||||
|
||||
def cmdloop(self, intro=None):
|
||||
"""Repeatedly issue a prompt, accept input, parse an initial prefix
|
||||
off the received input, and dispatch to action methods, passing them
|
||||
the remainder of the line as argument.
|
||||
|
||||
"""
|
||||
|
||||
self.preloop()
|
||||
if self.use_rawinput and self.completekey:
|
||||
try:
|
||||
import readline
|
||||
self.old_completer = readline.get_completer()
|
||||
readline.set_completer(self.complete)
|
||||
readline.parse_and_bind(self.completekey+": complete")
|
||||
except ImportError:
|
||||
pass
|
||||
try:
|
||||
if intro is not None:
|
||||
self.intro = intro
|
||||
if self.intro:
|
||||
self.stdout.write(str(self.intro)+"\n")
|
||||
stop = None
|
||||
while not stop:
|
||||
if self.cmdqueue:
|
||||
line = self.cmdqueue.pop(0)
|
||||
else:
|
||||
if self.use_rawinput:
|
||||
try:
|
||||
line = raw_input(self.prompt)
|
||||
except EOFError:
|
||||
line = 'EOF'
|
||||
else:
|
||||
self.stdout.write(self.prompt)
|
||||
self.stdout.flush()
|
||||
line = self.stdin.readline()
|
||||
if not len(line):
|
||||
line = 'EOF'
|
||||
else:
|
||||
line = line.rstrip('\r\n')
|
||||
line = self.precmd(line)
|
||||
stop = self.onecmd(line)
|
||||
stop = self.postcmd(stop, line)
|
||||
self.postloop()
|
||||
finally:
|
||||
if self.use_rawinput and self.completekey:
|
||||
try:
|
||||
import readline
|
||||
readline.set_completer(self.old_completer)
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
|
||||
def precmd(self, line):
|
||||
"""Hook method executed just before the command line is
|
||||
interpreted, but after the input prompt is generated and issued.
|
||||
|
||||
"""
|
||||
return line
|
||||
|
||||
def postcmd(self, stop, line):
|
||||
"""Hook method executed just after a command dispatch is finished."""
|
||||
return stop
|
||||
|
||||
def preloop(self):
|
||||
"""Hook method executed once when the cmdloop() method is called."""
|
||||
pass
|
||||
|
||||
def postloop(self):
|
||||
"""Hook method executed once when the cmdloop() method is about to
|
||||
return.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
def parseline(self, line):
|
||||
"""Parse the line into a command name and a string containing
|
||||
the arguments. Returns a tuple containing (command, args, line).
|
||||
'command' and 'args' may be None if the line couldn't be parsed.
|
||||
"""
|
||||
line = line.strip()
|
||||
if not line:
|
||||
return None, None, line
|
||||
elif line[0] == '?':
|
||||
line = 'help ' + line[1:]
|
||||
elif line[0] == '!':
|
||||
if hasattr(self, 'do_shell'):
|
||||
line = 'shell ' + line[1:]
|
||||
else:
|
||||
return None, None, line
|
||||
i, n = 0, len(line)
|
||||
while i < n and line[i] in self.identchars: i = i+1
|
||||
cmd, arg = line[:i], line[i:].strip()
|
||||
return cmd, arg, line
|
||||
|
||||
def onecmd(self, line):
|
||||
"""Interpret the argument as though it had been typed in response
|
||||
to the prompt.
|
||||
|
||||
This may be overridden, but should not normally need to be;
|
||||
see the precmd() and postcmd() methods for useful execution hooks.
|
||||
The return value is a flag indicating whether interpretation of
|
||||
commands by the interpreter should stop.
|
||||
|
||||
"""
|
||||
cmd, arg, line = self.parseline(line)
|
||||
if not line:
|
||||
return self.emptyline()
|
||||
if cmd is None:
|
||||
return self.default(line)
|
||||
self.lastcmd = line
|
||||
if line == 'EOF' :
|
||||
self.lastcmd = ''
|
||||
if cmd == '':
|
||||
return self.default(line)
|
||||
else:
|
||||
try:
|
||||
func = getattr(self, 'do_' + cmd)
|
||||
except AttributeError:
|
||||
return self.default(line)
|
||||
return func(arg)
|
||||
|
||||
def emptyline(self):
|
||||
"""Called when an empty line is entered in response to the prompt.
|
||||
|
||||
If this method is not overridden, it repeats the last nonempty
|
||||
command entered.
|
||||
|
||||
"""
|
||||
if self.lastcmd:
|
||||
return self.onecmd(self.lastcmd)
|
||||
|
||||
def default(self, line):
|
||||
"""Called on an input line when the command prefix is not recognized.
|
||||
|
||||
If this method is not overridden, it prints an error message and
|
||||
returns.
|
||||
|
||||
"""
|
||||
self.stdout.write('*** Unknown syntax: %s\n'%line)
|
||||
|
||||
def completedefault(self, *ignored):
|
||||
"""Method called to complete an input line when no command-specific
|
||||
complete_*() method is available.
|
||||
|
||||
By default, it returns an empty list.
|
||||
|
||||
"""
|
||||
return []
|
||||
|
||||
def completenames(self, text, *ignored):
|
||||
dotext = 'do_'+text
|
||||
return [a[3:] for a in self.get_names() if a.startswith(dotext)]
|
||||
|
||||
def complete(self, text, state):
|
||||
"""Return the next possible completion for 'text'.
|
||||
|
||||
If a command has not been entered, then complete against command list.
|
||||
Otherwise try to call complete_<command> to get list of completions.
|
||||
"""
|
||||
if state == 0:
|
||||
import readline
|
||||
origline = readline.get_line_buffer()
|
||||
line = origline.lstrip()
|
||||
stripped = len(origline) - len(line)
|
||||
begidx = readline.get_begidx() - stripped
|
||||
endidx = readline.get_endidx() - stripped
|
||||
if begidx>0:
|
||||
cmd, args, foo = self.parseline(line)
|
||||
if cmd == '':
|
||||
compfunc = self.completedefault
|
||||
else:
|
||||
try:
|
||||
compfunc = getattr(self, 'complete_' + cmd)
|
||||
except AttributeError:
|
||||
compfunc = self.completedefault
|
||||
else:
|
||||
compfunc = self.completenames
|
||||
self.completion_matches = compfunc(text, line, begidx, endidx)
|
||||
try:
|
||||
return self.completion_matches[state]
|
||||
except IndexError:
|
||||
return None
|
||||
|
||||
def get_names(self):
|
||||
# This method used to pull in base class attributes
|
||||
# at a time dir() didn't do it yet.
|
||||
return dir(self.__class__)
|
||||
|
||||
def complete_help(self, *args):
|
||||
commands = set(self.completenames(*args))
|
||||
topics = set(a[5:] for a in self.get_names()
|
||||
if a.startswith('help_' + args[0]))
|
||||
return list(commands | topics)
|
||||
|
||||
def do_help(self, arg):
|
||||
'List available commands with "help" or detailed help with "help cmd".'
|
||||
if arg:
|
||||
# XXX check arg syntax
|
||||
try:
|
||||
func = getattr(self, 'help_' + arg)
|
||||
except AttributeError:
|
||||
try:
|
||||
doc=getattr(self, 'do_' + arg).__doc__
|
||||
if doc:
|
||||
self.stdout.write("%s\n"%str(doc))
|
||||
return
|
||||
except AttributeError:
|
||||
pass
|
||||
self.stdout.write("%s\n"%str(self.nohelp % (arg,)))
|
||||
return
|
||||
func()
|
||||
else:
|
||||
names = self.get_names()
|
||||
cmds_doc = []
|
||||
cmds_undoc = []
|
||||
help = {}
|
||||
for name in names:
|
||||
if name[:5] == 'help_':
|
||||
help[name[5:]]=1
|
||||
names.sort()
|
||||
# There can be duplicates if routines overridden
|
||||
prevname = ''
|
||||
for name in names:
|
||||
if name[:3] == 'do_':
|
||||
if name == prevname:
|
||||
continue
|
||||
prevname = name
|
||||
cmd=name[3:]
|
||||
if cmd in help:
|
||||
cmds_doc.append(cmd)
|
||||
del help[cmd]
|
||||
elif getattr(self, name).__doc__:
|
||||
cmds_doc.append(cmd)
|
||||
else:
|
||||
cmds_undoc.append(cmd)
|
||||
self.stdout.write("%s\n"%str(self.doc_leader))
|
||||
self.print_topics(self.doc_header, cmds_doc, 15,80)
|
||||
self.print_topics(self.misc_header, help.keys(),15,80)
|
||||
self.print_topics(self.undoc_header, cmds_undoc, 15,80)
|
||||
|
||||
def print_topics(self, header, cmds, cmdlen, maxcol):
|
||||
if cmds:
|
||||
self.stdout.write("%s\n"%str(header))
|
||||
if self.ruler:
|
||||
self.stdout.write("%s\n"%str(self.ruler * len(header)))
|
||||
self.columnize(cmds, maxcol-1)
|
||||
self.stdout.write("\n")
|
||||
|
||||
def columnize(self, list, displaywidth=80):
|
||||
"""Display a list of strings as a compact set of columns.
|
||||
|
||||
Each column is only as wide as necessary.
|
||||
Columns are separated by two spaces (one was not legible enough).
|
||||
"""
|
||||
if not list:
|
||||
self.stdout.write("<empty>\n")
|
||||
return
|
||||
nonstrings = [i for i in range(len(list))
|
||||
if not isinstance(list[i], str)]
|
||||
if nonstrings:
|
||||
raise TypeError, ("list[i] not a string for i in %s" %
|
||||
", ".join(map(str, nonstrings)))
|
||||
size = len(list)
|
||||
if size == 1:
|
||||
self.stdout.write('%s\n'%str(list[0]))
|
||||
return
|
||||
# Try every row count from 1 upwards
|
||||
for nrows in range(1, len(list)):
|
||||
ncols = (size+nrows-1) // nrows
|
||||
colwidths = []
|
||||
totwidth = -2
|
||||
for col in range(ncols):
|
||||
colwidth = 0
|
||||
for row in range(nrows):
|
||||
i = row + nrows*col
|
||||
if i >= size:
|
||||
break
|
||||
x = list[i]
|
||||
colwidth = max(colwidth, len(x))
|
||||
colwidths.append(colwidth)
|
||||
totwidth += colwidth + 2
|
||||
if totwidth > displaywidth:
|
||||
break
|
||||
if totwidth <= displaywidth:
|
||||
break
|
||||
else:
|
||||
nrows = len(list)
|
||||
ncols = 1
|
||||
colwidths = [0]
|
||||
for row in range(nrows):
|
||||
texts = []
|
||||
for col in range(ncols):
|
||||
i = row + nrows*col
|
||||
if i >= size:
|
||||
x = ""
|
||||
else:
|
||||
x = list[i]
|
||||
texts.append(x)
|
||||
while texts and not texts[-1]:
|
||||
del texts[-1]
|
||||
for col in range(len(texts)):
|
||||
texts[col] = texts[col].ljust(colwidths[col])
|
||||
self.stdout.write("%s\n"%str(" ".join(texts)))
|
||||
1101
AppPkg/Applications/Python/Python-2.7.10/Lib/codecs.py
Normal file
1101
AppPkg/Applications/Python/Python-2.7.10/Lib/codecs.py
Normal file
File diff suppressed because it is too large
Load Diff
730
AppPkg/Applications/Python/Python-2.7.10/Lib/collections.py
Normal file
730
AppPkg/Applications/Python/Python-2.7.10/Lib/collections.py
Normal file
@@ -0,0 +1,730 @@
|
||||
__all__ = ['Counter', 'deque', 'defaultdict', 'namedtuple', 'OrderedDict']
|
||||
# For bootstrapping reasons, the collection ABCs are defined in _abcoll.py.
|
||||
# They should however be considered an integral part of collections.py.
|
||||
from _abcoll import *
|
||||
import _abcoll
|
||||
__all__ += _abcoll.__all__
|
||||
|
||||
from _collections import deque, defaultdict
|
||||
from operator import itemgetter as _itemgetter, eq as _eq
|
||||
from keyword import iskeyword as _iskeyword
|
||||
import sys as _sys
|
||||
import heapq as _heapq
|
||||
from itertools import repeat as _repeat, chain as _chain, starmap as _starmap
|
||||
from itertools import imap as _imap
|
||||
|
||||
try:
|
||||
from thread import get_ident as _get_ident
|
||||
except ImportError:
|
||||
from dummy_thread import get_ident as _get_ident
|
||||
|
||||
|
||||
################################################################################
|
||||
### OrderedDict
|
||||
################################################################################
|
||||
|
||||
class OrderedDict(dict):
|
||||
'Dictionary that remembers insertion order'
|
||||
# An inherited dict maps keys to values.
|
||||
# The inherited dict provides __getitem__, __len__, __contains__, and get.
|
||||
# The remaining methods are order-aware.
|
||||
# Big-O running times for all methods are the same as regular dictionaries.
|
||||
|
||||
# The internal self.__map dict maps keys to links in a doubly linked list.
|
||||
# The circular doubly linked list starts and ends with a sentinel element.
|
||||
# The sentinel element never gets deleted (this simplifies the algorithm).
|
||||
# Each link is stored as a list of length three: [PREV, NEXT, KEY].
|
||||
|
||||
def __init__(*args, **kwds):
|
||||
'''Initialize an ordered dictionary. The signature is the same as
|
||||
regular dictionaries, but keyword arguments are not recommended because
|
||||
their insertion order is arbitrary.
|
||||
|
||||
'''
|
||||
if not args:
|
||||
raise TypeError("descriptor '__init__' of 'OrderedDict' object "
|
||||
"needs an argument")
|
||||
self = args[0]
|
||||
args = args[1:]
|
||||
if len(args) > 1:
|
||||
raise TypeError('expected at most 1 arguments, got %d' % len(args))
|
||||
try:
|
||||
self.__root
|
||||
except AttributeError:
|
||||
self.__root = root = [] # sentinel node
|
||||
root[:] = [root, root, None]
|
||||
self.__map = {}
|
||||
self.__update(*args, **kwds)
|
||||
|
||||
def __setitem__(self, key, value, dict_setitem=dict.__setitem__):
|
||||
'od.__setitem__(i, y) <==> od[i]=y'
|
||||
# Setting a new item creates a new link at the end of the linked list,
|
||||
# and the inherited dictionary is updated with the new key/value pair.
|
||||
if key not in self:
|
||||
root = self.__root
|
||||
last = root[0]
|
||||
last[1] = root[0] = self.__map[key] = [last, root, key]
|
||||
return dict_setitem(self, key, value)
|
||||
|
||||
def __delitem__(self, key, dict_delitem=dict.__delitem__):
|
||||
'od.__delitem__(y) <==> del od[y]'
|
||||
# Deleting an existing item uses self.__map to find the link which gets
|
||||
# removed by updating the links in the predecessor and successor nodes.
|
||||
dict_delitem(self, key)
|
||||
link_prev, link_next, _ = self.__map.pop(key)
|
||||
link_prev[1] = link_next # update link_prev[NEXT]
|
||||
link_next[0] = link_prev # update link_next[PREV]
|
||||
|
||||
def __iter__(self):
|
||||
'od.__iter__() <==> iter(od)'
|
||||
# Traverse the linked list in order.
|
||||
root = self.__root
|
||||
curr = root[1] # start at the first node
|
||||
while curr is not root:
|
||||
yield curr[2] # yield the curr[KEY]
|
||||
curr = curr[1] # move to next node
|
||||
|
||||
def __reversed__(self):
|
||||
'od.__reversed__() <==> reversed(od)'
|
||||
# Traverse the linked list in reverse order.
|
||||
root = self.__root
|
||||
curr = root[0] # start at the last node
|
||||
while curr is not root:
|
||||
yield curr[2] # yield the curr[KEY]
|
||||
curr = curr[0] # move to previous node
|
||||
|
||||
def clear(self):
|
||||
'od.clear() -> None. Remove all items from od.'
|
||||
root = self.__root
|
||||
root[:] = [root, root, None]
|
||||
self.__map.clear()
|
||||
dict.clear(self)
|
||||
|
||||
# -- the following methods do not depend on the internal structure --
|
||||
|
||||
def keys(self):
|
||||
'od.keys() -> list of keys in od'
|
||||
return list(self)
|
||||
|
||||
def values(self):
|
||||
'od.values() -> list of values in od'
|
||||
return [self[key] for key in self]
|
||||
|
||||
def items(self):
|
||||
'od.items() -> list of (key, value) pairs in od'
|
||||
return [(key, self[key]) for key in self]
|
||||
|
||||
def iterkeys(self):
|
||||
'od.iterkeys() -> an iterator over the keys in od'
|
||||
return iter(self)
|
||||
|
||||
def itervalues(self):
|
||||
'od.itervalues -> an iterator over the values in od'
|
||||
for k in self:
|
||||
yield self[k]
|
||||
|
||||
def iteritems(self):
|
||||
'od.iteritems -> an iterator over the (key, value) pairs in od'
|
||||
for k in self:
|
||||
yield (k, self[k])
|
||||
|
||||
update = MutableMapping.update
|
||||
|
||||
__update = update # let subclasses override update without breaking __init__
|
||||
|
||||
__marker = object()
|
||||
|
||||
def pop(self, key, default=__marker):
|
||||
'''od.pop(k[,d]) -> v, remove specified key and return the corresponding
|
||||
value. If key is not found, d is returned if given, otherwise KeyError
|
||||
is raised.
|
||||
|
||||
'''
|
||||
if key in self:
|
||||
result = self[key]
|
||||
del self[key]
|
||||
return result
|
||||
if default is self.__marker:
|
||||
raise KeyError(key)
|
||||
return default
|
||||
|
||||
def setdefault(self, key, default=None):
|
||||
'od.setdefault(k[,d]) -> od.get(k,d), also set od[k]=d if k not in od'
|
||||
if key in self:
|
||||
return self[key]
|
||||
self[key] = default
|
||||
return default
|
||||
|
||||
def popitem(self, last=True):
|
||||
'''od.popitem() -> (k, v), return and remove a (key, value) pair.
|
||||
Pairs are returned in LIFO order if last is true or FIFO order if false.
|
||||
|
||||
'''
|
||||
if not self:
|
||||
raise KeyError('dictionary is empty')
|
||||
key = next(reversed(self) if last else iter(self))
|
||||
value = self.pop(key)
|
||||
return key, value
|
||||
|
||||
def __repr__(self, _repr_running={}):
|
||||
'od.__repr__() <==> repr(od)'
|
||||
call_key = id(self), _get_ident()
|
||||
if call_key in _repr_running:
|
||||
return '...'
|
||||
_repr_running[call_key] = 1
|
||||
try:
|
||||
if not self:
|
||||
return '%s()' % (self.__class__.__name__,)
|
||||
return '%s(%r)' % (self.__class__.__name__, self.items())
|
||||
finally:
|
||||
del _repr_running[call_key]
|
||||
|
||||
def __reduce__(self):
|
||||
'Return state information for pickling'
|
||||
items = [[k, self[k]] for k in self]
|
||||
inst_dict = vars(self).copy()
|
||||
for k in vars(OrderedDict()):
|
||||
inst_dict.pop(k, None)
|
||||
if inst_dict:
|
||||
return (self.__class__, (items,), inst_dict)
|
||||
return self.__class__, (items,)
|
||||
|
||||
def copy(self):
|
||||
'od.copy() -> a shallow copy of od'
|
||||
return self.__class__(self)
|
||||
|
||||
@classmethod
|
||||
def fromkeys(cls, iterable, value=None):
|
||||
'''OD.fromkeys(S[, v]) -> New ordered dictionary with keys from S.
|
||||
If not specified, the value defaults to None.
|
||||
|
||||
'''
|
||||
self = cls()
|
||||
for key in iterable:
|
||||
self[key] = value
|
||||
return self
|
||||
|
||||
def __eq__(self, other):
|
||||
'''od.__eq__(y) <==> od==y. Comparison to another OD is order-sensitive
|
||||
while comparison to a regular mapping is order-insensitive.
|
||||
|
||||
'''
|
||||
if isinstance(other, OrderedDict):
|
||||
return dict.__eq__(self, other) and all(_imap(_eq, self, other))
|
||||
return dict.__eq__(self, other)
|
||||
|
||||
def __ne__(self, other):
|
||||
'od.__ne__(y) <==> od!=y'
|
||||
return not self == other
|
||||
|
||||
# -- the following methods support python 3.x style dictionary views --
|
||||
|
||||
def viewkeys(self):
|
||||
"od.viewkeys() -> a set-like object providing a view on od's keys"
|
||||
return KeysView(self)
|
||||
|
||||
def viewvalues(self):
|
||||
"od.viewvalues() -> an object providing a view on od's values"
|
||||
return ValuesView(self)
|
||||
|
||||
def viewitems(self):
|
||||
"od.viewitems() -> a set-like object providing a view on od's items"
|
||||
return ItemsView(self)
|
||||
|
||||
|
||||
################################################################################
|
||||
### namedtuple
|
||||
################################################################################
|
||||
|
||||
_class_template = '''\
|
||||
class {typename}(tuple):
|
||||
'{typename}({arg_list})'
|
||||
|
||||
__slots__ = ()
|
||||
|
||||
_fields = {field_names!r}
|
||||
|
||||
def __new__(_cls, {arg_list}):
|
||||
'Create new instance of {typename}({arg_list})'
|
||||
return _tuple.__new__(_cls, ({arg_list}))
|
||||
|
||||
@classmethod
|
||||
def _make(cls, iterable, new=tuple.__new__, len=len):
|
||||
'Make a new {typename} object from a sequence or iterable'
|
||||
result = new(cls, iterable)
|
||||
if len(result) != {num_fields:d}:
|
||||
raise TypeError('Expected {num_fields:d} arguments, got %d' % len(result))
|
||||
return result
|
||||
|
||||
def __repr__(self):
|
||||
'Return a nicely formatted representation string'
|
||||
return '{typename}({repr_fmt})' % self
|
||||
|
||||
def _asdict(self):
|
||||
'Return a new OrderedDict which maps field names to their values'
|
||||
return OrderedDict(zip(self._fields, self))
|
||||
|
||||
def _replace(_self, **kwds):
|
||||
'Return a new {typename} object replacing specified fields with new values'
|
||||
result = _self._make(map(kwds.pop, {field_names!r}, _self))
|
||||
if kwds:
|
||||
raise ValueError('Got unexpected field names: %r' % kwds.keys())
|
||||
return result
|
||||
|
||||
def __getnewargs__(self):
|
||||
'Return self as a plain tuple. Used by copy and pickle.'
|
||||
return tuple(self)
|
||||
|
||||
__dict__ = _property(_asdict)
|
||||
|
||||
def __getstate__(self):
|
||||
'Exclude the OrderedDict from pickling'
|
||||
pass
|
||||
|
||||
{field_defs}
|
||||
'''
|
||||
|
||||
_repr_template = '{name}=%r'
|
||||
|
||||
_field_template = '''\
|
||||
{name} = _property(_itemgetter({index:d}), doc='Alias for field number {index:d}')
|
||||
'''
|
||||
|
||||
def namedtuple(typename, field_names, verbose=False, rename=False):
|
||||
"""Returns a new subclass of tuple with named fields.
|
||||
|
||||
>>> Point = namedtuple('Point', ['x', 'y'])
|
||||
>>> Point.__doc__ # docstring for the new class
|
||||
'Point(x, y)'
|
||||
>>> p = Point(11, y=22) # instantiate with positional args or keywords
|
||||
>>> p[0] + p[1] # indexable like a plain tuple
|
||||
33
|
||||
>>> x, y = p # unpack like a regular tuple
|
||||
>>> x, y
|
||||
(11, 22)
|
||||
>>> p.x + p.y # fields also accessable by name
|
||||
33
|
||||
>>> d = p._asdict() # convert to a dictionary
|
||||
>>> d['x']
|
||||
11
|
||||
>>> Point(**d) # convert from a dictionary
|
||||
Point(x=11, y=22)
|
||||
>>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
|
||||
Point(x=100, y=22)
|
||||
|
||||
"""
|
||||
|
||||
# Validate the field names. At the user's option, either generate an error
|
||||
# message or automatically replace the field name with a valid name.
|
||||
if isinstance(field_names, basestring):
|
||||
field_names = field_names.replace(',', ' ').split()
|
||||
field_names = map(str, field_names)
|
||||
typename = str(typename)
|
||||
if rename:
|
||||
seen = set()
|
||||
for index, name in enumerate(field_names):
|
||||
if (not all(c.isalnum() or c=='_' for c in name)
|
||||
or _iskeyword(name)
|
||||
or not name
|
||||
or name[0].isdigit()
|
||||
or name.startswith('_')
|
||||
or name in seen):
|
||||
field_names[index] = '_%d' % index
|
||||
seen.add(name)
|
||||
for name in [typename] + field_names:
|
||||
if type(name) != str:
|
||||
raise TypeError('Type names and field names must be strings')
|
||||
if not all(c.isalnum() or c=='_' for c in name):
|
||||
raise ValueError('Type names and field names can only contain '
|
||||
'alphanumeric characters and underscores: %r' % name)
|
||||
if _iskeyword(name):
|
||||
raise ValueError('Type names and field names cannot be a '
|
||||
'keyword: %r' % name)
|
||||
if name[0].isdigit():
|
||||
raise ValueError('Type names and field names cannot start with '
|
||||
'a number: %r' % name)
|
||||
seen = set()
|
||||
for name in field_names:
|
||||
if name.startswith('_') and not rename:
|
||||
raise ValueError('Field names cannot start with an underscore: '
|
||||
'%r' % name)
|
||||
if name in seen:
|
||||
raise ValueError('Encountered duplicate field name: %r' % name)
|
||||
seen.add(name)
|
||||
|
||||
# Fill-in the class template
|
||||
class_definition = _class_template.format(
|
||||
typename = typename,
|
||||
field_names = tuple(field_names),
|
||||
num_fields = len(field_names),
|
||||
arg_list = repr(tuple(field_names)).replace("'", "")[1:-1],
|
||||
repr_fmt = ', '.join(_repr_template.format(name=name)
|
||||
for name in field_names),
|
||||
field_defs = '\n'.join(_field_template.format(index=index, name=name)
|
||||
for index, name in enumerate(field_names))
|
||||
)
|
||||
if verbose:
|
||||
print class_definition
|
||||
|
||||
# Execute the template string in a temporary namespace and support
|
||||
# tracing utilities by setting a value for frame.f_globals['__name__']
|
||||
namespace = dict(_itemgetter=_itemgetter, __name__='namedtuple_%s' % typename,
|
||||
OrderedDict=OrderedDict, _property=property, _tuple=tuple)
|
||||
try:
|
||||
exec class_definition in namespace
|
||||
except SyntaxError as e:
|
||||
raise SyntaxError(e.message + ':\n' + class_definition)
|
||||
result = namespace[typename]
|
||||
|
||||
# For pickling to work, the __module__ variable needs to be set to the frame
|
||||
# where the named tuple is created. Bypass this step in environments where
|
||||
# sys._getframe is not defined (Jython for example) or sys._getframe is not
|
||||
# defined for arguments greater than 0 (IronPython).
|
||||
try:
|
||||
result.__module__ = _sys._getframe(1).f_globals.get('__name__', '__main__')
|
||||
except (AttributeError, ValueError):
|
||||
pass
|
||||
|
||||
return result
|
||||
|
||||
|
||||
########################################################################
|
||||
### Counter
|
||||
########################################################################
|
||||
|
||||
class Counter(dict):
|
||||
'''Dict subclass for counting hashable items. Sometimes called a bag
|
||||
or multiset. Elements are stored as dictionary keys and their counts
|
||||
are stored as dictionary values.
|
||||
|
||||
>>> c = Counter('abcdeabcdabcaba') # count elements from a string
|
||||
|
||||
>>> c.most_common(3) # three most common elements
|
||||
[('a', 5), ('b', 4), ('c', 3)]
|
||||
>>> sorted(c) # list all unique elements
|
||||
['a', 'b', 'c', 'd', 'e']
|
||||
>>> ''.join(sorted(c.elements())) # list elements with repetitions
|
||||
'aaaaabbbbcccdde'
|
||||
>>> sum(c.values()) # total of all counts
|
||||
15
|
||||
|
||||
>>> c['a'] # count of letter 'a'
|
||||
5
|
||||
>>> for elem in 'shazam': # update counts from an iterable
|
||||
... c[elem] += 1 # by adding 1 to each element's count
|
||||
>>> c['a'] # now there are seven 'a'
|
||||
7
|
||||
>>> del c['b'] # remove all 'b'
|
||||
>>> c['b'] # now there are zero 'b'
|
||||
0
|
||||
|
||||
>>> d = Counter('simsalabim') # make another counter
|
||||
>>> c.update(d) # add in the second counter
|
||||
>>> c['a'] # now there are nine 'a'
|
||||
9
|
||||
|
||||
>>> c.clear() # empty the counter
|
||||
>>> c
|
||||
Counter()
|
||||
|
||||
Note: If a count is set to zero or reduced to zero, it will remain
|
||||
in the counter until the entry is deleted or the counter is cleared:
|
||||
|
||||
>>> c = Counter('aaabbc')
|
||||
>>> c['b'] -= 2 # reduce the count of 'b' by two
|
||||
>>> c.most_common() # 'b' is still in, but its count is zero
|
||||
[('a', 3), ('c', 1), ('b', 0)]
|
||||
|
||||
'''
|
||||
# References:
|
||||
# http://en.wikipedia.org/wiki/Multiset
|
||||
# http://www.gnu.org/software/smalltalk/manual-base/html_node/Bag.html
|
||||
# http://www.demo2s.com/Tutorial/Cpp/0380__set-multiset/Catalog0380__set-multiset.htm
|
||||
# http://code.activestate.com/recipes/259174/
|
||||
# Knuth, TAOCP Vol. II section 4.6.3
|
||||
|
||||
def __init__(*args, **kwds):
|
||||
'''Create a new, empty Counter object. And if given, count elements
|
||||
from an input iterable. Or, initialize the count from another mapping
|
||||
of elements to their counts.
|
||||
|
||||
>>> c = Counter() # a new, empty counter
|
||||
>>> c = Counter('gallahad') # a new counter from an iterable
|
||||
>>> c = Counter({'a': 4, 'b': 2}) # a new counter from a mapping
|
||||
>>> c = Counter(a=4, b=2) # a new counter from keyword args
|
||||
|
||||
'''
|
||||
if not args:
|
||||
raise TypeError("descriptor '__init__' of 'Counter' object "
|
||||
"needs an argument")
|
||||
self = args[0]
|
||||
args = args[1:]
|
||||
if len(args) > 1:
|
||||
raise TypeError('expected at most 1 arguments, got %d' % len(args))
|
||||
super(Counter, self).__init__()
|
||||
self.update(*args, **kwds)
|
||||
|
||||
def __missing__(self, key):
|
||||
'The count of elements not in the Counter is zero.'
|
||||
# Needed so that self[missing_item] does not raise KeyError
|
||||
return 0
|
||||
|
||||
def most_common(self, n=None):
|
||||
'''List the n most common elements and their counts from the most
|
||||
common to the least. If n is None, then list all element counts.
|
||||
|
||||
>>> Counter('abcdeabcdabcaba').most_common(3)
|
||||
[('a', 5), ('b', 4), ('c', 3)]
|
||||
|
||||
'''
|
||||
# Emulate Bag.sortedByCount from Smalltalk
|
||||
if n is None:
|
||||
return sorted(self.iteritems(), key=_itemgetter(1), reverse=True)
|
||||
return _heapq.nlargest(n, self.iteritems(), key=_itemgetter(1))
|
||||
|
||||
def elements(self):
|
||||
'''Iterator over elements repeating each as many times as its count.
|
||||
|
||||
>>> c = Counter('ABCABC')
|
||||
>>> sorted(c.elements())
|
||||
['A', 'A', 'B', 'B', 'C', 'C']
|
||||
|
||||
# Knuth's example for prime factors of 1836: 2**2 * 3**3 * 17**1
|
||||
>>> prime_factors = Counter({2: 2, 3: 3, 17: 1})
|
||||
>>> product = 1
|
||||
>>> for factor in prime_factors.elements(): # loop over factors
|
||||
... product *= factor # and multiply them
|
||||
>>> product
|
||||
1836
|
||||
|
||||
Note, if an element's count has been set to zero or is a negative
|
||||
number, elements() will ignore it.
|
||||
|
||||
'''
|
||||
# Emulate Bag.do from Smalltalk and Multiset.begin from C++.
|
||||
return _chain.from_iterable(_starmap(_repeat, self.iteritems()))
|
||||
|
||||
# Override dict methods where necessary
|
||||
|
||||
@classmethod
|
||||
def fromkeys(cls, iterable, v=None):
|
||||
# There is no equivalent method for counters because setting v=1
|
||||
# means that no element can have a count greater than one.
|
||||
raise NotImplementedError(
|
||||
'Counter.fromkeys() is undefined. Use Counter(iterable) instead.')
|
||||
|
||||
def update(*args, **kwds):
|
||||
'''Like dict.update() but add counts instead of replacing them.
|
||||
|
||||
Source can be an iterable, a dictionary, or another Counter instance.
|
||||
|
||||
>>> c = Counter('which')
|
||||
>>> c.update('witch') # add elements from another iterable
|
||||
>>> d = Counter('watch')
|
||||
>>> c.update(d) # add elements from another counter
|
||||
>>> c['h'] # four 'h' in which, witch, and watch
|
||||
4
|
||||
|
||||
'''
|
||||
# The regular dict.update() operation makes no sense here because the
|
||||
# replace behavior results in the some of original untouched counts
|
||||
# being mixed-in with all of the other counts for a mismash that
|
||||
# doesn't have a straight-forward interpretation in most counting
|
||||
# contexts. Instead, we implement straight-addition. Both the inputs
|
||||
# and outputs are allowed to contain zero and negative counts.
|
||||
|
||||
if not args:
|
||||
raise TypeError("descriptor 'update' of 'Counter' object "
|
||||
"needs an argument")
|
||||
self = args[0]
|
||||
args = args[1:]
|
||||
if len(args) > 1:
|
||||
raise TypeError('expected at most 1 arguments, got %d' % len(args))
|
||||
iterable = args[0] if args else None
|
||||
if iterable is not None:
|
||||
if isinstance(iterable, Mapping):
|
||||
if self:
|
||||
self_get = self.get
|
||||
for elem, count in iterable.iteritems():
|
||||
self[elem] = self_get(elem, 0) + count
|
||||
else:
|
||||
super(Counter, self).update(iterable) # fast path when counter is empty
|
||||
else:
|
||||
self_get = self.get
|
||||
for elem in iterable:
|
||||
self[elem] = self_get(elem, 0) + 1
|
||||
if kwds:
|
||||
self.update(kwds)
|
||||
|
||||
def subtract(*args, **kwds):
|
||||
'''Like dict.update() but subtracts counts instead of replacing them.
|
||||
Counts can be reduced below zero. Both the inputs and outputs are
|
||||
allowed to contain zero and negative counts.
|
||||
|
||||
Source can be an iterable, a dictionary, or another Counter instance.
|
||||
|
||||
>>> c = Counter('which')
|
||||
>>> c.subtract('witch') # subtract elements from another iterable
|
||||
>>> c.subtract(Counter('watch')) # subtract elements from another counter
|
||||
>>> c['h'] # 2 in which, minus 1 in witch, minus 1 in watch
|
||||
0
|
||||
>>> c['w'] # 1 in which, minus 1 in witch, minus 1 in watch
|
||||
-1
|
||||
|
||||
'''
|
||||
if not args:
|
||||
raise TypeError("descriptor 'subtract' of 'Counter' object "
|
||||
"needs an argument")
|
||||
self = args[0]
|
||||
args = args[1:]
|
||||
if len(args) > 1:
|
||||
raise TypeError('expected at most 1 arguments, got %d' % len(args))
|
||||
iterable = args[0] if args else None
|
||||
if iterable is not None:
|
||||
self_get = self.get
|
||||
if isinstance(iterable, Mapping):
|
||||
for elem, count in iterable.items():
|
||||
self[elem] = self_get(elem, 0) - count
|
||||
else:
|
||||
for elem in iterable:
|
||||
self[elem] = self_get(elem, 0) - 1
|
||||
if kwds:
|
||||
self.subtract(kwds)
|
||||
|
||||
def copy(self):
|
||||
'Return a shallow copy.'
|
||||
return self.__class__(self)
|
||||
|
||||
def __reduce__(self):
|
||||
return self.__class__, (dict(self),)
|
||||
|
||||
def __delitem__(self, elem):
|
||||
'Like dict.__delitem__() but does not raise KeyError for missing values.'
|
||||
if elem in self:
|
||||
super(Counter, self).__delitem__(elem)
|
||||
|
||||
def __repr__(self):
|
||||
if not self:
|
||||
return '%s()' % self.__class__.__name__
|
||||
items = ', '.join(map('%r: %r'.__mod__, self.most_common()))
|
||||
return '%s({%s})' % (self.__class__.__name__, items)
|
||||
|
||||
# Multiset-style mathematical operations discussed in:
|
||||
# Knuth TAOCP Volume II section 4.6.3 exercise 19
|
||||
# and at http://en.wikipedia.org/wiki/Multiset
|
||||
#
|
||||
# Outputs guaranteed to only include positive counts.
|
||||
#
|
||||
# To strip negative and zero counts, add-in an empty counter:
|
||||
# c += Counter()
|
||||
|
||||
def __add__(self, other):
|
||||
'''Add counts from two counters.
|
||||
|
||||
>>> Counter('abbb') + Counter('bcc')
|
||||
Counter({'b': 4, 'c': 2, 'a': 1})
|
||||
|
||||
'''
|
||||
if not isinstance(other, Counter):
|
||||
return NotImplemented
|
||||
result = Counter()
|
||||
for elem, count in self.items():
|
||||
newcount = count + other[elem]
|
||||
if newcount > 0:
|
||||
result[elem] = newcount
|
||||
for elem, count in other.items():
|
||||
if elem not in self and count > 0:
|
||||
result[elem] = count
|
||||
return result
|
||||
|
||||
def __sub__(self, other):
|
||||
''' Subtract count, but keep only results with positive counts.
|
||||
|
||||
>>> Counter('abbbc') - Counter('bccd')
|
||||
Counter({'b': 2, 'a': 1})
|
||||
|
||||
'''
|
||||
if not isinstance(other, Counter):
|
||||
return NotImplemented
|
||||
result = Counter()
|
||||
for elem, count in self.items():
|
||||
newcount = count - other[elem]
|
||||
if newcount > 0:
|
||||
result[elem] = newcount
|
||||
for elem, count in other.items():
|
||||
if elem not in self and count < 0:
|
||||
result[elem] = 0 - count
|
||||
return result
|
||||
|
||||
def __or__(self, other):
|
||||
'''Union is the maximum of value in either of the input counters.
|
||||
|
||||
>>> Counter('abbb') | Counter('bcc')
|
||||
Counter({'b': 3, 'c': 2, 'a': 1})
|
||||
|
||||
'''
|
||||
if not isinstance(other, Counter):
|
||||
return NotImplemented
|
||||
result = Counter()
|
||||
for elem, count in self.items():
|
||||
other_count = other[elem]
|
||||
newcount = other_count if count < other_count else count
|
||||
if newcount > 0:
|
||||
result[elem] = newcount
|
||||
for elem, count in other.items():
|
||||
if elem not in self and count > 0:
|
||||
result[elem] = count
|
||||
return result
|
||||
|
||||
def __and__(self, other):
|
||||
''' Intersection is the minimum of corresponding counts.
|
||||
|
||||
>>> Counter('abbb') & Counter('bcc')
|
||||
Counter({'b': 1})
|
||||
|
||||
'''
|
||||
if not isinstance(other, Counter):
|
||||
return NotImplemented
|
||||
result = Counter()
|
||||
for elem, count in self.items():
|
||||
other_count = other[elem]
|
||||
newcount = count if count < other_count else other_count
|
||||
if newcount > 0:
|
||||
result[elem] = newcount
|
||||
return result
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# verify that instances can be pickled
|
||||
from cPickle import loads, dumps
|
||||
Point = namedtuple('Point', 'x, y', True)
|
||||
p = Point(x=10, y=20)
|
||||
assert p == loads(dumps(p))
|
||||
|
||||
# test and demonstrate ability to override methods
|
||||
class Point(namedtuple('Point', 'x y')):
|
||||
__slots__ = ()
|
||||
@property
|
||||
def hypot(self):
|
||||
return (self.x ** 2 + self.y ** 2) ** 0.5
|
||||
def __str__(self):
|
||||
return 'Point: x=%6.3f y=%6.3f hypot=%6.3f' % (self.x, self.y, self.hypot)
|
||||
|
||||
for p in Point(3, 4), Point(14, 5/7.):
|
||||
print p
|
||||
|
||||
class Point(namedtuple('Point', 'x y')):
|
||||
'Point class with optimized _make() and _replace() without error-checking'
|
||||
__slots__ = ()
|
||||
_make = classmethod(tuple.__new__)
|
||||
def _replace(self, _map=map, **kwds):
|
||||
return self._make(_map(kwds.get, ('x', 'y'), self))
|
||||
|
||||
print Point(11, 22)._replace(x=100)
|
||||
|
||||
Point3D = namedtuple('Point3D', Point._fields + ('z',))
|
||||
print Point3D.__doc__
|
||||
|
||||
import doctest
|
||||
TestResults = namedtuple('TestResults', 'failed attempted')
|
||||
print TestResults(*doctest.testmod())
|
||||
227
AppPkg/Applications/Python/Python-2.7.10/Lib/compileall.py
Normal file
227
AppPkg/Applications/Python/Python-2.7.10/Lib/compileall.py
Normal file
@@ -0,0 +1,227 @@
|
||||
"""Module/script to byte-compile all .py files to .pyc (or .pyo) files.
|
||||
|
||||
When called as a script with arguments, this compiles the directories
|
||||
given as arguments recursively; the -l option prevents it from
|
||||
recursing into directories.
|
||||
|
||||
Without arguments, if compiles all modules on sys.path, without
|
||||
recursing into subdirectories. (Even though it should do so for
|
||||
packages -- for now, you'll have to deal with packages separately.)
|
||||
|
||||
See module py_compile for details of the actual byte-compilation.
|
||||
"""
|
||||
import os
|
||||
import sys
|
||||
import py_compile
|
||||
import struct
|
||||
import imp
|
||||
|
||||
__all__ = ["compile_dir","compile_file","compile_path"]
|
||||
|
||||
def compile_dir(dir, maxlevels=10, ddir=None,
|
||||
force=0, rx=None, quiet=0):
|
||||
"""Byte-compile all modules in the given directory tree.
|
||||
|
||||
Arguments (only dir is required):
|
||||
|
||||
dir: the directory to byte-compile
|
||||
maxlevels: maximum recursion level (default 10)
|
||||
ddir: the directory that will be prepended to the path to the
|
||||
file as it is compiled into each byte-code file.
|
||||
force: if 1, force compilation, even if timestamps are up-to-date
|
||||
quiet: if 1, be quiet during compilation
|
||||
"""
|
||||
if not quiet:
|
||||
print 'Listing', dir, '...'
|
||||
try:
|
||||
names = os.listdir(dir)
|
||||
except os.error:
|
||||
print "Can't list", dir
|
||||
names = []
|
||||
names.sort()
|
||||
success = 1
|
||||
for name in names:
|
||||
fullname = os.path.join(dir, name)
|
||||
if ddir is not None:
|
||||
dfile = os.path.join(ddir, name)
|
||||
else:
|
||||
dfile = None
|
||||
if not os.path.isdir(fullname):
|
||||
if not compile_file(fullname, ddir, force, rx, quiet):
|
||||
success = 0
|
||||
elif maxlevels > 0 and \
|
||||
name != os.curdir and name != os.pardir and \
|
||||
os.path.isdir(fullname) and \
|
||||
not os.path.islink(fullname):
|
||||
if not compile_dir(fullname, maxlevels - 1, dfile, force, rx,
|
||||
quiet):
|
||||
success = 0
|
||||
return success
|
||||
|
||||
def compile_file(fullname, ddir=None, force=0, rx=None, quiet=0):
|
||||
"""Byte-compile one file.
|
||||
|
||||
Arguments (only fullname is required):
|
||||
|
||||
fullname: the file to byte-compile
|
||||
ddir: if given, the directory name compiled in to the
|
||||
byte-code file.
|
||||
force: if 1, force compilation, even if timestamps are up-to-date
|
||||
quiet: if 1, be quiet during compilation
|
||||
"""
|
||||
success = 1
|
||||
name = os.path.basename(fullname)
|
||||
if ddir is not None:
|
||||
dfile = os.path.join(ddir, name)
|
||||
else:
|
||||
dfile = None
|
||||
if rx is not None:
|
||||
mo = rx.search(fullname)
|
||||
if mo:
|
||||
return success
|
||||
if os.path.isfile(fullname):
|
||||
head, tail = name[:-3], name[-3:]
|
||||
if tail == '.py':
|
||||
if not force:
|
||||
try:
|
||||
mtime = int(os.stat(fullname).st_mtime)
|
||||
expect = struct.pack('<4sl', imp.get_magic(), mtime)
|
||||
cfile = fullname + (__debug__ and 'c' or 'o')
|
||||
with open(cfile, 'rb') as chandle:
|
||||
actual = chandle.read(8)
|
||||
if expect == actual:
|
||||
return success
|
||||
except IOError:
|
||||
pass
|
||||
if not quiet:
|
||||
print 'Compiling', fullname, '...'
|
||||
try:
|
||||
ok = py_compile.compile(fullname, None, dfile, True)
|
||||
except py_compile.PyCompileError,err:
|
||||
if quiet:
|
||||
print 'Compiling', fullname, '...'
|
||||
print err.msg
|
||||
success = 0
|
||||
except IOError, e:
|
||||
print "Sorry", e
|
||||
success = 0
|
||||
else:
|
||||
if ok == 0:
|
||||
success = 0
|
||||
return success
|
||||
|
||||
def compile_path(skip_curdir=1, maxlevels=0, force=0, quiet=0):
|
||||
"""Byte-compile all module on sys.path.
|
||||
|
||||
Arguments (all optional):
|
||||
|
||||
skip_curdir: if true, skip current directory (default true)
|
||||
maxlevels: max recursion level (default 0)
|
||||
force: as for compile_dir() (default 0)
|
||||
quiet: as for compile_dir() (default 0)
|
||||
"""
|
||||
success = 1
|
||||
for dir in sys.path:
|
||||
if (not dir or dir == os.curdir) and skip_curdir:
|
||||
print 'Skipping current directory'
|
||||
else:
|
||||
success = success and compile_dir(dir, maxlevels, None,
|
||||
force, quiet=quiet)
|
||||
return success
|
||||
|
||||
def expand_args(args, flist):
|
||||
"""read names in flist and append to args"""
|
||||
expanded = args[:]
|
||||
if flist:
|
||||
try:
|
||||
if flist == '-':
|
||||
fd = sys.stdin
|
||||
else:
|
||||
fd = open(flist)
|
||||
while 1:
|
||||
line = fd.readline()
|
||||
if not line:
|
||||
break
|
||||
expanded.append(line[:-1])
|
||||
except IOError:
|
||||
print "Error reading file list %s" % flist
|
||||
raise
|
||||
return expanded
|
||||
|
||||
def main():
|
||||
"""Script main program."""
|
||||
import getopt
|
||||
try:
|
||||
opts, args = getopt.getopt(sys.argv[1:], 'lfqd:x:i:')
|
||||
except getopt.error, msg:
|
||||
print msg
|
||||
print "usage: python compileall.py [-l] [-f] [-q] [-d destdir] " \
|
||||
"[-x regexp] [-i list] [directory|file ...]"
|
||||
print
|
||||
print "arguments: zero or more file and directory names to compile; " \
|
||||
"if no arguments given, "
|
||||
print " defaults to the equivalent of -l sys.path"
|
||||
print
|
||||
print "options:"
|
||||
print "-l: don't recurse into subdirectories"
|
||||
print "-f: force rebuild even if timestamps are up-to-date"
|
||||
print "-q: output only error messages"
|
||||
print "-d destdir: directory to prepend to file paths for use in " \
|
||||
"compile-time tracebacks and in"
|
||||
print " runtime tracebacks in cases where the source " \
|
||||
"file is unavailable"
|
||||
print "-x regexp: skip files matching the regular expression regexp; " \
|
||||
"the regexp is searched for"
|
||||
print " in the full path of each file considered for " \
|
||||
"compilation"
|
||||
print "-i file: add all the files and directories listed in file to " \
|
||||
"the list considered for"
|
||||
print ' compilation; if "-", names are read from stdin'
|
||||
|
||||
sys.exit(2)
|
||||
maxlevels = 10
|
||||
ddir = None
|
||||
force = 0
|
||||
quiet = 0
|
||||
rx = None
|
||||
flist = None
|
||||
for o, a in opts:
|
||||
if o == '-l': maxlevels = 0
|
||||
if o == '-d': ddir = a
|
||||
if o == '-f': force = 1
|
||||
if o == '-q': quiet = 1
|
||||
if o == '-x':
|
||||
import re
|
||||
rx = re.compile(a)
|
||||
if o == '-i': flist = a
|
||||
if ddir:
|
||||
if len(args) != 1 and not os.path.isdir(args[0]):
|
||||
print "-d destdir require exactly one directory argument"
|
||||
sys.exit(2)
|
||||
success = 1
|
||||
try:
|
||||
if args or flist:
|
||||
try:
|
||||
if flist:
|
||||
args = expand_args(args, flist)
|
||||
except IOError:
|
||||
success = 0
|
||||
if success:
|
||||
for arg in args:
|
||||
if os.path.isdir(arg):
|
||||
if not compile_dir(arg, maxlevels, ddir,
|
||||
force, rx, quiet):
|
||||
success = 0
|
||||
else:
|
||||
if not compile_file(arg, ddir, force, rx, quiet):
|
||||
success = 0
|
||||
else:
|
||||
success = compile_path()
|
||||
except KeyboardInterrupt:
|
||||
print "\n[interrupted]"
|
||||
success = 0
|
||||
return success
|
||||
|
||||
if __name__ == '__main__':
|
||||
exit_status = int(not main())
|
||||
sys.exit(exit_status)
|
||||
433
AppPkg/Applications/Python/Python-2.7.10/Lib/copy.py
Normal file
433
AppPkg/Applications/Python/Python-2.7.10/Lib/copy.py
Normal file
@@ -0,0 +1,433 @@
|
||||
"""Generic (shallow and deep) copying operations.
|
||||
|
||||
Interface summary:
|
||||
|
||||
import copy
|
||||
|
||||
x = copy.copy(y) # make a shallow copy of y
|
||||
x = copy.deepcopy(y) # make a deep copy of y
|
||||
|
||||
For module specific errors, copy.Error is raised.
|
||||
|
||||
The difference between shallow and deep copying is only relevant for
|
||||
compound objects (objects that contain other objects, like lists or
|
||||
class instances).
|
||||
|
||||
- A shallow copy constructs a new compound object and then (to the
|
||||
extent possible) inserts *the same objects* into it that the
|
||||
original contains.
|
||||
|
||||
- A deep copy constructs a new compound object and then, recursively,
|
||||
inserts *copies* into it of the objects found in the original.
|
||||
|
||||
Two problems often exist with deep copy operations that don't exist
|
||||
with shallow copy operations:
|
||||
|
||||
a) recursive objects (compound objects that, directly or indirectly,
|
||||
contain a reference to themselves) may cause a recursive loop
|
||||
|
||||
b) because deep copy copies *everything* it may copy too much, e.g.
|
||||
administrative data structures that should be shared even between
|
||||
copies
|
||||
|
||||
Python's deep copy operation avoids these problems by:
|
||||
|
||||
a) keeping a table of objects already copied during the current
|
||||
copying pass
|
||||
|
||||
b) letting user-defined classes override the copying operation or the
|
||||
set of components copied
|
||||
|
||||
This version does not copy types like module, class, function, method,
|
||||
nor stack trace, stack frame, nor file, socket, window, nor array, nor
|
||||
any similar types.
|
||||
|
||||
Classes can use the same interfaces to control copying that they use
|
||||
to control pickling: they can define methods called __getinitargs__(),
|
||||
__getstate__() and __setstate__(). See the documentation for module
|
||||
"pickle" for information on these methods.
|
||||
"""
|
||||
|
||||
import types
|
||||
import weakref
|
||||
from copy_reg import dispatch_table
|
||||
|
||||
class Error(Exception):
|
||||
pass
|
||||
error = Error # backward compatibility
|
||||
|
||||
try:
|
||||
from org.python.core import PyStringMap
|
||||
except ImportError:
|
||||
PyStringMap = None
|
||||
|
||||
__all__ = ["Error", "copy", "deepcopy"]
|
||||
|
||||
def copy(x):
|
||||
"""Shallow copy operation on arbitrary Python objects.
|
||||
|
||||
See the module's __doc__ string for more info.
|
||||
"""
|
||||
|
||||
cls = type(x)
|
||||
|
||||
copier = _copy_dispatch.get(cls)
|
||||
if copier:
|
||||
return copier(x)
|
||||
|
||||
copier = getattr(cls, "__copy__", None)
|
||||
if copier:
|
||||
return copier(x)
|
||||
|
||||
reductor = dispatch_table.get(cls)
|
||||
if reductor:
|
||||
rv = reductor(x)
|
||||
else:
|
||||
reductor = getattr(x, "__reduce_ex__", None)
|
||||
if reductor:
|
||||
rv = reductor(2)
|
||||
else:
|
||||
reductor = getattr(x, "__reduce__", None)
|
||||
if reductor:
|
||||
rv = reductor()
|
||||
else:
|
||||
raise Error("un(shallow)copyable object of type %s" % cls)
|
||||
|
||||
return _reconstruct(x, rv, 0)
|
||||
|
||||
|
||||
_copy_dispatch = d = {}
|
||||
|
||||
def _copy_immutable(x):
|
||||
return x
|
||||
for t in (type(None), int, long, float, bool, str, tuple,
|
||||
frozenset, type, xrange, types.ClassType,
|
||||
types.BuiltinFunctionType, type(Ellipsis),
|
||||
types.FunctionType, weakref.ref):
|
||||
d[t] = _copy_immutable
|
||||
for name in ("ComplexType", "UnicodeType", "CodeType"):
|
||||
t = getattr(types, name, None)
|
||||
if t is not None:
|
||||
d[t] = _copy_immutable
|
||||
|
||||
def _copy_with_constructor(x):
|
||||
return type(x)(x)
|
||||
for t in (list, dict, set):
|
||||
d[t] = _copy_with_constructor
|
||||
|
||||
def _copy_with_copy_method(x):
|
||||
return x.copy()
|
||||
if PyStringMap is not None:
|
||||
d[PyStringMap] = _copy_with_copy_method
|
||||
|
||||
def _copy_inst(x):
|
||||
if hasattr(x, '__copy__'):
|
||||
return x.__copy__()
|
||||
if hasattr(x, '__getinitargs__'):
|
||||
args = x.__getinitargs__()
|
||||
y = x.__class__(*args)
|
||||
else:
|
||||
y = _EmptyClass()
|
||||
y.__class__ = x.__class__
|
||||
if hasattr(x, '__getstate__'):
|
||||
state = x.__getstate__()
|
||||
else:
|
||||
state = x.__dict__
|
||||
if hasattr(y, '__setstate__'):
|
||||
y.__setstate__(state)
|
||||
else:
|
||||
y.__dict__.update(state)
|
||||
return y
|
||||
d[types.InstanceType] = _copy_inst
|
||||
|
||||
del d
|
||||
|
||||
def deepcopy(x, memo=None, _nil=[]):
|
||||
"""Deep copy operation on arbitrary Python objects.
|
||||
|
||||
See the module's __doc__ string for more info.
|
||||
"""
|
||||
|
||||
if memo is None:
|
||||
memo = {}
|
||||
|
||||
d = id(x)
|
||||
y = memo.get(d, _nil)
|
||||
if y is not _nil:
|
||||
return y
|
||||
|
||||
cls = type(x)
|
||||
|
||||
copier = _deepcopy_dispatch.get(cls)
|
||||
if copier:
|
||||
y = copier(x, memo)
|
||||
else:
|
||||
try:
|
||||
issc = issubclass(cls, type)
|
||||
except TypeError: # cls is not a class (old Boost; see SF #502085)
|
||||
issc = 0
|
||||
if issc:
|
||||
y = _deepcopy_atomic(x, memo)
|
||||
else:
|
||||
copier = getattr(x, "__deepcopy__", None)
|
||||
if copier:
|
||||
y = copier(memo)
|
||||
else:
|
||||
reductor = dispatch_table.get(cls)
|
||||
if reductor:
|
||||
rv = reductor(x)
|
||||
else:
|
||||
reductor = getattr(x, "__reduce_ex__", None)
|
||||
if reductor:
|
||||
rv = reductor(2)
|
||||
else:
|
||||
reductor = getattr(x, "__reduce__", None)
|
||||
if reductor:
|
||||
rv = reductor()
|
||||
else:
|
||||
raise Error(
|
||||
"un(deep)copyable object of type %s" % cls)
|
||||
y = _reconstruct(x, rv, 1, memo)
|
||||
|
||||
memo[d] = y
|
||||
_keep_alive(x, memo) # Make sure x lives at least as long as d
|
||||
return y
|
||||
|
||||
_deepcopy_dispatch = d = {}
|
||||
|
||||
def _deepcopy_atomic(x, memo):
|
||||
return x
|
||||
d[type(None)] = _deepcopy_atomic
|
||||
d[type(Ellipsis)] = _deepcopy_atomic
|
||||
d[int] = _deepcopy_atomic
|
||||
d[long] = _deepcopy_atomic
|
||||
d[float] = _deepcopy_atomic
|
||||
d[bool] = _deepcopy_atomic
|
||||
try:
|
||||
d[complex] = _deepcopy_atomic
|
||||
except NameError:
|
||||
pass
|
||||
d[str] = _deepcopy_atomic
|
||||
try:
|
||||
d[unicode] = _deepcopy_atomic
|
||||
except NameError:
|
||||
pass
|
||||
try:
|
||||
d[types.CodeType] = _deepcopy_atomic
|
||||
except AttributeError:
|
||||
pass
|
||||
d[type] = _deepcopy_atomic
|
||||
d[xrange] = _deepcopy_atomic
|
||||
d[types.ClassType] = _deepcopy_atomic
|
||||
d[types.BuiltinFunctionType] = _deepcopy_atomic
|
||||
d[types.FunctionType] = _deepcopy_atomic
|
||||
d[weakref.ref] = _deepcopy_atomic
|
||||
|
||||
def _deepcopy_list(x, memo):
|
||||
y = []
|
||||
memo[id(x)] = y
|
||||
for a in x:
|
||||
y.append(deepcopy(a, memo))
|
||||
return y
|
||||
d[list] = _deepcopy_list
|
||||
|
||||
def _deepcopy_tuple(x, memo):
|
||||
y = []
|
||||
for a in x:
|
||||
y.append(deepcopy(a, memo))
|
||||
d = id(x)
|
||||
try:
|
||||
return memo[d]
|
||||
except KeyError:
|
||||
pass
|
||||
for i in range(len(x)):
|
||||
if x[i] is not y[i]:
|
||||
y = tuple(y)
|
||||
break
|
||||
else:
|
||||
y = x
|
||||
memo[d] = y
|
||||
return y
|
||||
d[tuple] = _deepcopy_tuple
|
||||
|
||||
def _deepcopy_dict(x, memo):
|
||||
y = {}
|
||||
memo[id(x)] = y
|
||||
for key, value in x.iteritems():
|
||||
y[deepcopy(key, memo)] = deepcopy(value, memo)
|
||||
return y
|
||||
d[dict] = _deepcopy_dict
|
||||
if PyStringMap is not None:
|
||||
d[PyStringMap] = _deepcopy_dict
|
||||
|
||||
def _deepcopy_method(x, memo): # Copy instance methods
|
||||
return type(x)(x.im_func, deepcopy(x.im_self, memo), x.im_class)
|
||||
_deepcopy_dispatch[types.MethodType] = _deepcopy_method
|
||||
|
||||
def _keep_alive(x, memo):
|
||||
"""Keeps a reference to the object x in the memo.
|
||||
|
||||
Because we remember objects by their id, we have
|
||||
to assure that possibly temporary objects are kept
|
||||
alive by referencing them.
|
||||
We store a reference at the id of the memo, which should
|
||||
normally not be used unless someone tries to deepcopy
|
||||
the memo itself...
|
||||
"""
|
||||
try:
|
||||
memo[id(memo)].append(x)
|
||||
except KeyError:
|
||||
# aha, this is the first one :-)
|
||||
memo[id(memo)]=[x]
|
||||
|
||||
def _deepcopy_inst(x, memo):
|
||||
if hasattr(x, '__deepcopy__'):
|
||||
return x.__deepcopy__(memo)
|
||||
if hasattr(x, '__getinitargs__'):
|
||||
args = x.__getinitargs__()
|
||||
args = deepcopy(args, memo)
|
||||
y = x.__class__(*args)
|
||||
else:
|
||||
y = _EmptyClass()
|
||||
y.__class__ = x.__class__
|
||||
memo[id(x)] = y
|
||||
if hasattr(x, '__getstate__'):
|
||||
state = x.__getstate__()
|
||||
else:
|
||||
state = x.__dict__
|
||||
state = deepcopy(state, memo)
|
||||
if hasattr(y, '__setstate__'):
|
||||
y.__setstate__(state)
|
||||
else:
|
||||
y.__dict__.update(state)
|
||||
return y
|
||||
d[types.InstanceType] = _deepcopy_inst
|
||||
|
||||
def _reconstruct(x, info, deep, memo=None):
|
||||
if isinstance(info, str):
|
||||
return x
|
||||
assert isinstance(info, tuple)
|
||||
if memo is None:
|
||||
memo = {}
|
||||
n = len(info)
|
||||
assert n in (2, 3, 4, 5)
|
||||
callable, args = info[:2]
|
||||
if n > 2:
|
||||
state = info[2]
|
||||
else:
|
||||
state = {}
|
||||
if n > 3:
|
||||
listiter = info[3]
|
||||
else:
|
||||
listiter = None
|
||||
if n > 4:
|
||||
dictiter = info[4]
|
||||
else:
|
||||
dictiter = None
|
||||
if deep:
|
||||
args = deepcopy(args, memo)
|
||||
y = callable(*args)
|
||||
memo[id(x)] = y
|
||||
|
||||
if state:
|
||||
if deep:
|
||||
state = deepcopy(state, memo)
|
||||
if hasattr(y, '__setstate__'):
|
||||
y.__setstate__(state)
|
||||
else:
|
||||
if isinstance(state, tuple) and len(state) == 2:
|
||||
state, slotstate = state
|
||||
else:
|
||||
slotstate = None
|
||||
if state is not None:
|
||||
y.__dict__.update(state)
|
||||
if slotstate is not None:
|
||||
for key, value in slotstate.iteritems():
|
||||
setattr(y, key, value)
|
||||
|
||||
if listiter is not None:
|
||||
for item in listiter:
|
||||
if deep:
|
||||
item = deepcopy(item, memo)
|
||||
y.append(item)
|
||||
if dictiter is not None:
|
||||
for key, value in dictiter:
|
||||
if deep:
|
||||
key = deepcopy(key, memo)
|
||||
value = deepcopy(value, memo)
|
||||
y[key] = value
|
||||
return y
|
||||
|
||||
del d
|
||||
|
||||
del types
|
||||
|
||||
# Helper for instance creation without calling __init__
|
||||
class _EmptyClass:
|
||||
pass
|
||||
|
||||
def _test():
|
||||
l = [None, 1, 2L, 3.14, 'xyzzy', (1, 2L), [3.14, 'abc'],
|
||||
{'abc': 'ABC'}, (), [], {}]
|
||||
l1 = copy(l)
|
||||
print l1==l
|
||||
l1 = map(copy, l)
|
||||
print l1==l
|
||||
l1 = deepcopy(l)
|
||||
print l1==l
|
||||
class C:
|
||||
def __init__(self, arg=None):
|
||||
self.a = 1
|
||||
self.arg = arg
|
||||
if __name__ == '__main__':
|
||||
import sys
|
||||
file = sys.argv[0]
|
||||
else:
|
||||
file = __file__
|
||||
self.fp = open(file)
|
||||
self.fp.close()
|
||||
def __getstate__(self):
|
||||
return {'a': self.a, 'arg': self.arg}
|
||||
def __setstate__(self, state):
|
||||
for key, value in state.iteritems():
|
||||
setattr(self, key, value)
|
||||
def __deepcopy__(self, memo=None):
|
||||
new = self.__class__(deepcopy(self.arg, memo))
|
||||
new.a = self.a
|
||||
return new
|
||||
c = C('argument sketch')
|
||||
l.append(c)
|
||||
l2 = copy(l)
|
||||
print l == l2
|
||||
print l
|
||||
print l2
|
||||
l2 = deepcopy(l)
|
||||
print l == l2
|
||||
print l
|
||||
print l2
|
||||
l.append({l[1]: l, 'xyz': l[2]})
|
||||
l3 = copy(l)
|
||||
import repr
|
||||
print map(repr.repr, l)
|
||||
print map(repr.repr, l1)
|
||||
print map(repr.repr, l2)
|
||||
print map(repr.repr, l3)
|
||||
l3 = deepcopy(l)
|
||||
import repr
|
||||
print map(repr.repr, l)
|
||||
print map(repr.repr, l1)
|
||||
print map(repr.repr, l2)
|
||||
print map(repr.repr, l3)
|
||||
class odict(dict):
|
||||
def __init__(self, d = {}):
|
||||
self.a = 99
|
||||
dict.__init__(self, d)
|
||||
def __setitem__(self, k, i):
|
||||
dict.__setitem__(self, k, i)
|
||||
self.a
|
||||
o = odict({"A" : "B"})
|
||||
x = deepcopy(o)
|
||||
print(o, x)
|
||||
|
||||
if __name__ == '__main__':
|
||||
_test()
|
||||
201
AppPkg/Applications/Python/Python-2.7.10/Lib/copy_reg.py
Normal file
201
AppPkg/Applications/Python/Python-2.7.10/Lib/copy_reg.py
Normal file
@@ -0,0 +1,201 @@
|
||||
"""Helper to provide extensibility for pickle/cPickle.
|
||||
|
||||
This is only useful to add pickle support for extension types defined in
|
||||
C, not for instances of user-defined classes.
|
||||
"""
|
||||
|
||||
from types import ClassType as _ClassType
|
||||
|
||||
__all__ = ["pickle", "constructor",
|
||||
"add_extension", "remove_extension", "clear_extension_cache"]
|
||||
|
||||
dispatch_table = {}
|
||||
|
||||
def pickle(ob_type, pickle_function, constructor_ob=None):
|
||||
if type(ob_type) is _ClassType:
|
||||
raise TypeError("copy_reg is not intended for use with classes")
|
||||
|
||||
if not hasattr(pickle_function, '__call__'):
|
||||
raise TypeError("reduction functions must be callable")
|
||||
dispatch_table[ob_type] = pickle_function
|
||||
|
||||
# The constructor_ob function is a vestige of safe for unpickling.
|
||||
# There is no reason for the caller to pass it anymore.
|
||||
if constructor_ob is not None:
|
||||
constructor(constructor_ob)
|
||||
|
||||
def constructor(object):
|
||||
if not hasattr(object, '__call__'):
|
||||
raise TypeError("constructors must be callable")
|
||||
|
||||
# Example: provide pickling support for complex numbers.
|
||||
|
||||
try:
|
||||
complex
|
||||
except NameError:
|
||||
pass
|
||||
else:
|
||||
|
||||
def pickle_complex(c):
|
||||
return complex, (c.real, c.imag)
|
||||
|
||||
pickle(complex, pickle_complex, complex)
|
||||
|
||||
# Support for pickling new-style objects
|
||||
|
||||
def _reconstructor(cls, base, state):
|
||||
if base is object:
|
||||
obj = object.__new__(cls)
|
||||
else:
|
||||
obj = base.__new__(cls, state)
|
||||
if base.__init__ != object.__init__:
|
||||
base.__init__(obj, state)
|
||||
return obj
|
||||
|
||||
_HEAPTYPE = 1<<9
|
||||
|
||||
# Python code for object.__reduce_ex__ for protocols 0 and 1
|
||||
|
||||
def _reduce_ex(self, proto):
|
||||
assert proto < 2
|
||||
for base in self.__class__.__mro__:
|
||||
if hasattr(base, '__flags__') and not base.__flags__ & _HEAPTYPE:
|
||||
break
|
||||
else:
|
||||
base = object # not really reachable
|
||||
if base is object:
|
||||
state = None
|
||||
else:
|
||||
if base is self.__class__:
|
||||
raise TypeError, "can't pickle %s objects" % base.__name__
|
||||
state = base(self)
|
||||
args = (self.__class__, base, state)
|
||||
try:
|
||||
getstate = self.__getstate__
|
||||
except AttributeError:
|
||||
if getattr(self, "__slots__", None):
|
||||
raise TypeError("a class that defines __slots__ without "
|
||||
"defining __getstate__ cannot be pickled")
|
||||
try:
|
||||
dict = self.__dict__
|
||||
except AttributeError:
|
||||
dict = None
|
||||
else:
|
||||
dict = getstate()
|
||||
if dict:
|
||||
return _reconstructor, args, dict
|
||||
else:
|
||||
return _reconstructor, args
|
||||
|
||||
# Helper for __reduce_ex__ protocol 2
|
||||
|
||||
def __newobj__(cls, *args):
|
||||
return cls.__new__(cls, *args)
|
||||
|
||||
def _slotnames(cls):
|
||||
"""Return a list of slot names for a given class.
|
||||
|
||||
This needs to find slots defined by the class and its bases, so we
|
||||
can't simply return the __slots__ attribute. We must walk down
|
||||
the Method Resolution Order and concatenate the __slots__ of each
|
||||
class found there. (This assumes classes don't modify their
|
||||
__slots__ attribute to misrepresent their slots after the class is
|
||||
defined.)
|
||||
"""
|
||||
|
||||
# Get the value from a cache in the class if possible
|
||||
names = cls.__dict__.get("__slotnames__")
|
||||
if names is not None:
|
||||
return names
|
||||
|
||||
# Not cached -- calculate the value
|
||||
names = []
|
||||
if not hasattr(cls, "__slots__"):
|
||||
# This class has no slots
|
||||
pass
|
||||
else:
|
||||
# Slots found -- gather slot names from all base classes
|
||||
for c in cls.__mro__:
|
||||
if "__slots__" in c.__dict__:
|
||||
slots = c.__dict__['__slots__']
|
||||
# if class has a single slot, it can be given as a string
|
||||
if isinstance(slots, basestring):
|
||||
slots = (slots,)
|
||||
for name in slots:
|
||||
# special descriptors
|
||||
if name in ("__dict__", "__weakref__"):
|
||||
continue
|
||||
# mangled names
|
||||
elif name.startswith('__') and not name.endswith('__'):
|
||||
names.append('_%s%s' % (c.__name__, name))
|
||||
else:
|
||||
names.append(name)
|
||||
|
||||
# Cache the outcome in the class if at all possible
|
||||
try:
|
||||
cls.__slotnames__ = names
|
||||
except:
|
||||
pass # But don't die if we can't
|
||||
|
||||
return names
|
||||
|
||||
# A registry of extension codes. This is an ad-hoc compression
|
||||
# mechanism. Whenever a global reference to <module>, <name> is about
|
||||
# to be pickled, the (<module>, <name>) tuple is looked up here to see
|
||||
# if it is a registered extension code for it. Extension codes are
|
||||
# universal, so that the meaning of a pickle does not depend on
|
||||
# context. (There are also some codes reserved for local use that
|
||||
# don't have this restriction.) Codes are positive ints; 0 is
|
||||
# reserved.
|
||||
|
||||
_extension_registry = {} # key -> code
|
||||
_inverted_registry = {} # code -> key
|
||||
_extension_cache = {} # code -> object
|
||||
# Don't ever rebind those names: cPickle grabs a reference to them when
|
||||
# it's initialized, and won't see a rebinding.
|
||||
|
||||
def add_extension(module, name, code):
|
||||
"""Register an extension code."""
|
||||
code = int(code)
|
||||
if not 1 <= code <= 0x7fffffff:
|
||||
raise ValueError, "code out of range"
|
||||
key = (module, name)
|
||||
if (_extension_registry.get(key) == code and
|
||||
_inverted_registry.get(code) == key):
|
||||
return # Redundant registrations are benign
|
||||
if key in _extension_registry:
|
||||
raise ValueError("key %s is already registered with code %s" %
|
||||
(key, _extension_registry[key]))
|
||||
if code in _inverted_registry:
|
||||
raise ValueError("code %s is already in use for key %s" %
|
||||
(code, _inverted_registry[code]))
|
||||
_extension_registry[key] = code
|
||||
_inverted_registry[code] = key
|
||||
|
||||
def remove_extension(module, name, code):
|
||||
"""Unregister an extension code. For testing only."""
|
||||
key = (module, name)
|
||||
if (_extension_registry.get(key) != code or
|
||||
_inverted_registry.get(code) != key):
|
||||
raise ValueError("key %s is not registered with code %s" %
|
||||
(key, code))
|
||||
del _extension_registry[key]
|
||||
del _inverted_registry[code]
|
||||
if code in _extension_cache:
|
||||
del _extension_cache[code]
|
||||
|
||||
def clear_extension_cache():
|
||||
_extension_cache.clear()
|
||||
|
||||
# Standard extension code assignments
|
||||
|
||||
# Reserved ranges
|
||||
|
||||
# First Last Count Purpose
|
||||
# 1 127 127 Reserved for Python standard library
|
||||
# 128 191 64 Reserved for Zope
|
||||
# 192 239 48 Reserved for 3rd parties
|
||||
# 240 255 16 Reserved for private use (will never be assigned)
|
||||
# 256 Inf Inf Reserved for future assignment
|
||||
|
||||
# Extension codes are assigned by the Python Software Foundation.
|
||||
456
AppPkg/Applications/Python/Python-2.7.10/Lib/csv.py
Normal file
456
AppPkg/Applications/Python/Python-2.7.10/Lib/csv.py
Normal file
@@ -0,0 +1,456 @@
|
||||
|
||||
"""
|
||||
csv.py - read/write/investigate CSV files
|
||||
"""
|
||||
|
||||
import re
|
||||
from functools import reduce
|
||||
from _csv import Error, __version__, writer, reader, register_dialect, \
|
||||
unregister_dialect, get_dialect, list_dialects, \
|
||||
field_size_limit, \
|
||||
QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE, \
|
||||
__doc__
|
||||
from _csv import Dialect as _Dialect
|
||||
|
||||
try:
|
||||
from cStringIO import StringIO
|
||||
except ImportError:
|
||||
from StringIO import StringIO
|
||||
|
||||
__all__ = [ "QUOTE_MINIMAL", "QUOTE_ALL", "QUOTE_NONNUMERIC", "QUOTE_NONE",
|
||||
"Error", "Dialect", "__doc__", "excel", "excel_tab",
|
||||
"field_size_limit", "reader", "writer",
|
||||
"register_dialect", "get_dialect", "list_dialects", "Sniffer",
|
||||
"unregister_dialect", "__version__", "DictReader", "DictWriter" ]
|
||||
|
||||
class Dialect:
|
||||
"""Describe an Excel dialect.
|
||||
|
||||
This must be subclassed (see csv.excel). Valid attributes are:
|
||||
delimiter, quotechar, escapechar, doublequote, skipinitialspace,
|
||||
lineterminator, quoting.
|
||||
|
||||
"""
|
||||
_name = ""
|
||||
_valid = False
|
||||
# placeholders
|
||||
delimiter = None
|
||||
quotechar = None
|
||||
escapechar = None
|
||||
doublequote = None
|
||||
skipinitialspace = None
|
||||
lineterminator = None
|
||||
quoting = None
|
||||
|
||||
def __init__(self):
|
||||
if self.__class__ != Dialect:
|
||||
self._valid = True
|
||||
self._validate()
|
||||
|
||||
def _validate(self):
|
||||
try:
|
||||
_Dialect(self)
|
||||
except TypeError, e:
|
||||
# We do this for compatibility with py2.3
|
||||
raise Error(str(e))
|
||||
|
||||
class excel(Dialect):
|
||||
"""Describe the usual properties of Excel-generated CSV files."""
|
||||
delimiter = ','
|
||||
quotechar = '"'
|
||||
doublequote = True
|
||||
skipinitialspace = False
|
||||
lineterminator = '\r\n'
|
||||
quoting = QUOTE_MINIMAL
|
||||
register_dialect("excel", excel)
|
||||
|
||||
class excel_tab(excel):
|
||||
"""Describe the usual properties of Excel-generated TAB-delimited files."""
|
||||
delimiter = '\t'
|
||||
register_dialect("excel-tab", excel_tab)
|
||||
|
||||
|
||||
class DictReader:
|
||||
def __init__(self, f, fieldnames=None, restkey=None, restval=None,
|
||||
dialect="excel", *args, **kwds):
|
||||
self._fieldnames = fieldnames # list of keys for the dict
|
||||
self.restkey = restkey # key to catch long rows
|
||||
self.restval = restval # default value for short rows
|
||||
self.reader = reader(f, dialect, *args, **kwds)
|
||||
self.dialect = dialect
|
||||
self.line_num = 0
|
||||
|
||||
def __iter__(self):
|
||||
return self
|
||||
|
||||
@property
|
||||
def fieldnames(self):
|
||||
if self._fieldnames is None:
|
||||
try:
|
||||
self._fieldnames = self.reader.next()
|
||||
except StopIteration:
|
||||
pass
|
||||
self.line_num = self.reader.line_num
|
||||
return self._fieldnames
|
||||
|
||||
# Issue 20004: Because DictReader is a classic class, this setter is
|
||||
# ignored. At this point in 2.7's lifecycle, it is too late to change the
|
||||
# base class for fear of breaking working code. If you want to change
|
||||
# fieldnames without overwriting the getter, set _fieldnames directly.
|
||||
@fieldnames.setter
|
||||
def fieldnames(self, value):
|
||||
self._fieldnames = value
|
||||
|
||||
def next(self):
|
||||
if self.line_num == 0:
|
||||
# Used only for its side effect.
|
||||
self.fieldnames
|
||||
row = self.reader.next()
|
||||
self.line_num = self.reader.line_num
|
||||
|
||||
# unlike the basic reader, we prefer not to return blanks,
|
||||
# because we will typically wind up with a dict full of None
|
||||
# values
|
||||
while row == []:
|
||||
row = self.reader.next()
|
||||
d = dict(zip(self.fieldnames, row))
|
||||
lf = len(self.fieldnames)
|
||||
lr = len(row)
|
||||
if lf < lr:
|
||||
d[self.restkey] = row[lf:]
|
||||
elif lf > lr:
|
||||
for key in self.fieldnames[lr:]:
|
||||
d[key] = self.restval
|
||||
return d
|
||||
|
||||
|
||||
class DictWriter:
|
||||
def __init__(self, f, fieldnames, restval="", extrasaction="raise",
|
||||
dialect="excel", *args, **kwds):
|
||||
self.fieldnames = fieldnames # list of keys for the dict
|
||||
self.restval = restval # for writing short dicts
|
||||
if extrasaction.lower() not in ("raise", "ignore"):
|
||||
raise ValueError, \
|
||||
("extrasaction (%s) must be 'raise' or 'ignore'" %
|
||||
extrasaction)
|
||||
self.extrasaction = extrasaction
|
||||
self.writer = writer(f, dialect, *args, **kwds)
|
||||
|
||||
def writeheader(self):
|
||||
header = dict(zip(self.fieldnames, self.fieldnames))
|
||||
self.writerow(header)
|
||||
|
||||
def _dict_to_list(self, rowdict):
|
||||
if self.extrasaction == "raise":
|
||||
wrong_fields = [k for k in rowdict if k not in self.fieldnames]
|
||||
if wrong_fields:
|
||||
raise ValueError("dict contains fields not in fieldnames: "
|
||||
+ ", ".join([repr(x) for x in wrong_fields]))
|
||||
return [rowdict.get(key, self.restval) for key in self.fieldnames]
|
||||
|
||||
def writerow(self, rowdict):
|
||||
return self.writer.writerow(self._dict_to_list(rowdict))
|
||||
|
||||
def writerows(self, rowdicts):
|
||||
rows = []
|
||||
for rowdict in rowdicts:
|
||||
rows.append(self._dict_to_list(rowdict))
|
||||
return self.writer.writerows(rows)
|
||||
|
||||
# Guard Sniffer's type checking against builds that exclude complex()
|
||||
try:
|
||||
complex
|
||||
except NameError:
|
||||
complex = float
|
||||
|
||||
class Sniffer:
|
||||
'''
|
||||
"Sniffs" the format of a CSV file (i.e. delimiter, quotechar)
|
||||
Returns a Dialect object.
|
||||
'''
|
||||
def __init__(self):
|
||||
# in case there is more than one possible delimiter
|
||||
self.preferred = [',', '\t', ';', ' ', ':']
|
||||
|
||||
|
||||
def sniff(self, sample, delimiters=None):
|
||||
"""
|
||||
Returns a dialect (or None) corresponding to the sample
|
||||
"""
|
||||
|
||||
quotechar, doublequote, delimiter, skipinitialspace = \
|
||||
self._guess_quote_and_delimiter(sample, delimiters)
|
||||
if not delimiter:
|
||||
delimiter, skipinitialspace = self._guess_delimiter(sample,
|
||||
delimiters)
|
||||
|
||||
if not delimiter:
|
||||
raise Error, "Could not determine delimiter"
|
||||
|
||||
class dialect(Dialect):
|
||||
_name = "sniffed"
|
||||
lineterminator = '\r\n'
|
||||
quoting = QUOTE_MINIMAL
|
||||
# escapechar = ''
|
||||
|
||||
dialect.doublequote = doublequote
|
||||
dialect.delimiter = delimiter
|
||||
# _csv.reader won't accept a quotechar of ''
|
||||
dialect.quotechar = quotechar or '"'
|
||||
dialect.skipinitialspace = skipinitialspace
|
||||
|
||||
return dialect
|
||||
|
||||
|
||||
def _guess_quote_and_delimiter(self, data, delimiters):
|
||||
"""
|
||||
Looks for text enclosed between two identical quotes
|
||||
(the probable quotechar) which are preceded and followed
|
||||
by the same character (the probable delimiter).
|
||||
For example:
|
||||
,'some text',
|
||||
The quote with the most wins, same with the delimiter.
|
||||
If there is no quotechar the delimiter can't be determined
|
||||
this way.
|
||||
"""
|
||||
|
||||
matches = []
|
||||
for restr in ('(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
|
||||
'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?",
|
||||
'(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?"
|
||||
'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space)
|
||||
regexp = re.compile(restr, re.DOTALL | re.MULTILINE)
|
||||
matches = regexp.findall(data)
|
||||
if matches:
|
||||
break
|
||||
|
||||
if not matches:
|
||||
# (quotechar, doublequote, delimiter, skipinitialspace)
|
||||
return ('', False, None, 0)
|
||||
quotes = {}
|
||||
delims = {}
|
||||
spaces = 0
|
||||
for m in matches:
|
||||
n = regexp.groupindex['quote'] - 1
|
||||
key = m[n]
|
||||
if key:
|
||||
quotes[key] = quotes.get(key, 0) + 1
|
||||
try:
|
||||
n = regexp.groupindex['delim'] - 1
|
||||
key = m[n]
|
||||
except KeyError:
|
||||
continue
|
||||
if key and (delimiters is None or key in delimiters):
|
||||
delims[key] = delims.get(key, 0) + 1
|
||||
try:
|
||||
n = regexp.groupindex['space'] - 1
|
||||
except KeyError:
|
||||
continue
|
||||
if m[n]:
|
||||
spaces += 1
|
||||
|
||||
quotechar = reduce(lambda a, b, quotes = quotes:
|
||||
(quotes[a] > quotes[b]) and a or b, quotes.keys())
|
||||
|
||||
if delims:
|
||||
delim = reduce(lambda a, b, delims = delims:
|
||||
(delims[a] > delims[b]) and a or b, delims.keys())
|
||||
skipinitialspace = delims[delim] == spaces
|
||||
if delim == '\n': # most likely a file with a single column
|
||||
delim = ''
|
||||
else:
|
||||
# there is *no* delimiter, it's a single column of quoted data
|
||||
delim = ''
|
||||
skipinitialspace = 0
|
||||
|
||||
# if we see an extra quote between delimiters, we've got a
|
||||
# double quoted format
|
||||
dq_regexp = re.compile(
|
||||
r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
|
||||
{'delim':re.escape(delim), 'quote':quotechar}, re.MULTILINE)
|
||||
|
||||
|
||||
|
||||
if dq_regexp.search(data):
|
||||
doublequote = True
|
||||
else:
|
||||
doublequote = False
|
||||
|
||||
return (quotechar, doublequote, delim, skipinitialspace)
|
||||
|
||||
|
||||
def _guess_delimiter(self, data, delimiters):
|
||||
"""
|
||||
The delimiter /should/ occur the same number of times on
|
||||
each row. However, due to malformed data, it may not. We don't want
|
||||
an all or nothing approach, so we allow for small variations in this
|
||||
number.
|
||||
1) build a table of the frequency of each character on every line.
|
||||
2) build a table of frequencies of this frequency (meta-frequency?),
|
||||
e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows,
|
||||
7 times in 2 rows'
|
||||
3) use the mode of the meta-frequency to determine the /expected/
|
||||
frequency for that character
|
||||
4) find out how often the character actually meets that goal
|
||||
5) the character that best meets its goal is the delimiter
|
||||
For performance reasons, the data is evaluated in chunks, so it can
|
||||
try and evaluate the smallest portion of the data possible, evaluating
|
||||
additional chunks as necessary.
|
||||
"""
|
||||
|
||||
data = filter(None, data.split('\n'))
|
||||
|
||||
ascii = [chr(c) for c in range(127)] # 7-bit ASCII
|
||||
|
||||
# build frequency tables
|
||||
chunkLength = min(10, len(data))
|
||||
iteration = 0
|
||||
charFrequency = {}
|
||||
modes = {}
|
||||
delims = {}
|
||||
start, end = 0, min(chunkLength, len(data))
|
||||
while start < len(data):
|
||||
iteration += 1
|
||||
for line in data[start:end]:
|
||||
for char in ascii:
|
||||
metaFrequency = charFrequency.get(char, {})
|
||||
# must count even if frequency is 0
|
||||
freq = line.count(char)
|
||||
# value is the mode
|
||||
metaFrequency[freq] = metaFrequency.get(freq, 0) + 1
|
||||
charFrequency[char] = metaFrequency
|
||||
|
||||
for char in charFrequency.keys():
|
||||
items = charFrequency[char].items()
|
||||
if len(items) == 1 and items[0][0] == 0:
|
||||
continue
|
||||
# get the mode of the frequencies
|
||||
if len(items) > 1:
|
||||
modes[char] = reduce(lambda a, b: a[1] > b[1] and a or b,
|
||||
items)
|
||||
# adjust the mode - subtract the sum of all
|
||||
# other frequencies
|
||||
items.remove(modes[char])
|
||||
modes[char] = (modes[char][0], modes[char][1]
|
||||
- reduce(lambda a, b: (0, a[1] + b[1]),
|
||||
items)[1])
|
||||
else:
|
||||
modes[char] = items[0]
|
||||
|
||||
# build a list of possible delimiters
|
||||
modeList = modes.items()
|
||||
total = float(chunkLength * iteration)
|
||||
# (rows of consistent data) / (number of rows) = 100%
|
||||
consistency = 1.0
|
||||
# minimum consistency threshold
|
||||
threshold = 0.9
|
||||
while len(delims) == 0 and consistency >= threshold:
|
||||
for k, v in modeList:
|
||||
if v[0] > 0 and v[1] > 0:
|
||||
if ((v[1]/total) >= consistency and
|
||||
(delimiters is None or k in delimiters)):
|
||||
delims[k] = v
|
||||
consistency -= 0.01
|
||||
|
||||
if len(delims) == 1:
|
||||
delim = delims.keys()[0]
|
||||
skipinitialspace = (data[0].count(delim) ==
|
||||
data[0].count("%c " % delim))
|
||||
return (delim, skipinitialspace)
|
||||
|
||||
# analyze another chunkLength lines
|
||||
start = end
|
||||
end += chunkLength
|
||||
|
||||
if not delims:
|
||||
return ('', 0)
|
||||
|
||||
# if there's more than one, fall back to a 'preferred' list
|
||||
if len(delims) > 1:
|
||||
for d in self.preferred:
|
||||
if d in delims.keys():
|
||||
skipinitialspace = (data[0].count(d) ==
|
||||
data[0].count("%c " % d))
|
||||
return (d, skipinitialspace)
|
||||
|
||||
# nothing else indicates a preference, pick the character that
|
||||
# dominates(?)
|
||||
items = [(v,k) for (k,v) in delims.items()]
|
||||
items.sort()
|
||||
delim = items[-1][1]
|
||||
|
||||
skipinitialspace = (data[0].count(delim) ==
|
||||
data[0].count("%c " % delim))
|
||||
return (delim, skipinitialspace)
|
||||
|
||||
|
||||
def has_header(self, sample):
|
||||
# Creates a dictionary of types of data in each column. If any
|
||||
# column is of a single type (say, integers), *except* for the first
|
||||
# row, then the first row is presumed to be labels. If the type
|
||||
# can't be determined, it is assumed to be a string in which case
|
||||
# the length of the string is the determining factor: if all of the
|
||||
# rows except for the first are the same length, it's a header.
|
||||
# Finally, a 'vote' is taken at the end for each column, adding or
|
||||
# subtracting from the likelihood of the first row being a header.
|
||||
|
||||
rdr = reader(StringIO(sample), self.sniff(sample))
|
||||
|
||||
header = rdr.next() # assume first row is header
|
||||
|
||||
columns = len(header)
|
||||
columnTypes = {}
|
||||
for i in range(columns): columnTypes[i] = None
|
||||
|
||||
checked = 0
|
||||
for row in rdr:
|
||||
# arbitrary number of rows to check, to keep it sane
|
||||
if checked > 20:
|
||||
break
|
||||
checked += 1
|
||||
|
||||
if len(row) != columns:
|
||||
continue # skip rows that have irregular number of columns
|
||||
|
||||
for col in columnTypes.keys():
|
||||
|
||||
for thisType in [int, long, float, complex]:
|
||||
try:
|
||||
thisType(row[col])
|
||||
break
|
||||
except (ValueError, OverflowError):
|
||||
pass
|
||||
else:
|
||||
# fallback to length of string
|
||||
thisType = len(row[col])
|
||||
|
||||
# treat longs as ints
|
||||
if thisType == long:
|
||||
thisType = int
|
||||
|
||||
if thisType != columnTypes[col]:
|
||||
if columnTypes[col] is None: # add new column type
|
||||
columnTypes[col] = thisType
|
||||
else:
|
||||
# type is inconsistent, remove column from
|
||||
# consideration
|
||||
del columnTypes[col]
|
||||
|
||||
# finally, compare results against first row and "vote"
|
||||
# on whether it's a header
|
||||
hasHeader = 0
|
||||
for col, colType in columnTypes.items():
|
||||
if type(colType) == type(0): # it's a length
|
||||
if len(header[col]) != colType:
|
||||
hasHeader += 1
|
||||
else:
|
||||
hasHeader -= 1
|
||||
else: # attempt typecast
|
||||
try:
|
||||
colType(header[col])
|
||||
except (ValueError, TypeError):
|
||||
hasHeader += 1
|
||||
else:
|
||||
hasHeader -= 1
|
||||
|
||||
return hasHeader > 0
|
||||
224
AppPkg/Applications/Python/Python-2.7.10/Lib/dis.py
Normal file
224
AppPkg/Applications/Python/Python-2.7.10/Lib/dis.py
Normal file
@@ -0,0 +1,224 @@
|
||||
"""Disassembler of Python byte code into mnemonics."""
|
||||
|
||||
import sys
|
||||
import types
|
||||
|
||||
from opcode import *
|
||||
from opcode import __all__ as _opcodes_all
|
||||
|
||||
__all__ = ["dis", "disassemble", "distb", "disco",
|
||||
"findlinestarts", "findlabels"] + _opcodes_all
|
||||
del _opcodes_all
|
||||
|
||||
_have_code = (types.MethodType, types.FunctionType, types.CodeType,
|
||||
types.ClassType, type)
|
||||
|
||||
def dis(x=None):
|
||||
"""Disassemble classes, methods, functions, or code.
|
||||
|
||||
With no argument, disassemble the last traceback.
|
||||
|
||||
"""
|
||||
if x is None:
|
||||
distb()
|
||||
return
|
||||
if isinstance(x, types.InstanceType):
|
||||
x = x.__class__
|
||||
if hasattr(x, 'im_func'):
|
||||
x = x.im_func
|
||||
if hasattr(x, 'func_code'):
|
||||
x = x.func_code
|
||||
if hasattr(x, '__dict__'):
|
||||
items = x.__dict__.items()
|
||||
items.sort()
|
||||
for name, x1 in items:
|
||||
if isinstance(x1, _have_code):
|
||||
print "Disassembly of %s:" % name
|
||||
try:
|
||||
dis(x1)
|
||||
except TypeError, msg:
|
||||
print "Sorry:", msg
|
||||
print
|
||||
elif hasattr(x, 'co_code'):
|
||||
disassemble(x)
|
||||
elif isinstance(x, str):
|
||||
disassemble_string(x)
|
||||
else:
|
||||
raise TypeError, \
|
||||
"don't know how to disassemble %s objects" % \
|
||||
type(x).__name__
|
||||
|
||||
def distb(tb=None):
|
||||
"""Disassemble a traceback (default: last traceback)."""
|
||||
if tb is None:
|
||||
try:
|
||||
tb = sys.last_traceback
|
||||
except AttributeError:
|
||||
raise RuntimeError, "no last traceback to disassemble"
|
||||
while tb.tb_next: tb = tb.tb_next
|
||||
disassemble(tb.tb_frame.f_code, tb.tb_lasti)
|
||||
|
||||
def disassemble(co, lasti=-1):
|
||||
"""Disassemble a code object."""
|
||||
code = co.co_code
|
||||
labels = findlabels(code)
|
||||
linestarts = dict(findlinestarts(co))
|
||||
n = len(code)
|
||||
i = 0
|
||||
extended_arg = 0
|
||||
free = None
|
||||
while i < n:
|
||||
c = code[i]
|
||||
op = ord(c)
|
||||
if i in linestarts:
|
||||
if i > 0:
|
||||
print
|
||||
print "%3d" % linestarts[i],
|
||||
else:
|
||||
print ' ',
|
||||
|
||||
if i == lasti: print '-->',
|
||||
else: print ' ',
|
||||
if i in labels: print '>>',
|
||||
else: print ' ',
|
||||
print repr(i).rjust(4),
|
||||
print opname[op].ljust(20),
|
||||
i = i+1
|
||||
if op >= HAVE_ARGUMENT:
|
||||
oparg = ord(code[i]) + ord(code[i+1])*256 + extended_arg
|
||||
extended_arg = 0
|
||||
i = i+2
|
||||
if op == EXTENDED_ARG:
|
||||
extended_arg = oparg*65536L
|
||||
print repr(oparg).rjust(5),
|
||||
if op in hasconst:
|
||||
print '(' + repr(co.co_consts[oparg]) + ')',
|
||||
elif op in hasname:
|
||||
print '(' + co.co_names[oparg] + ')',
|
||||
elif op in hasjrel:
|
||||
print '(to ' + repr(i + oparg) + ')',
|
||||
elif op in haslocal:
|
||||
print '(' + co.co_varnames[oparg] + ')',
|
||||
elif op in hascompare:
|
||||
print '(' + cmp_op[oparg] + ')',
|
||||
elif op in hasfree:
|
||||
if free is None:
|
||||
free = co.co_cellvars + co.co_freevars
|
||||
print '(' + free[oparg] + ')',
|
||||
print
|
||||
|
||||
def disassemble_string(code, lasti=-1, varnames=None, names=None,
|
||||
constants=None):
|
||||
labels = findlabels(code)
|
||||
n = len(code)
|
||||
i = 0
|
||||
while i < n:
|
||||
c = code[i]
|
||||
op = ord(c)
|
||||
if i == lasti: print '-->',
|
||||
else: print ' ',
|
||||
if i in labels: print '>>',
|
||||
else: print ' ',
|
||||
print repr(i).rjust(4),
|
||||
print opname[op].ljust(15),
|
||||
i = i+1
|
||||
if op >= HAVE_ARGUMENT:
|
||||
oparg = ord(code[i]) + ord(code[i+1])*256
|
||||
i = i+2
|
||||
print repr(oparg).rjust(5),
|
||||
if op in hasconst:
|
||||
if constants:
|
||||
print '(' + repr(constants[oparg]) + ')',
|
||||
else:
|
||||
print '(%d)'%oparg,
|
||||
elif op in hasname:
|
||||
if names is not None:
|
||||
print '(' + names[oparg] + ')',
|
||||
else:
|
||||
print '(%d)'%oparg,
|
||||
elif op in hasjrel:
|
||||
print '(to ' + repr(i + oparg) + ')',
|
||||
elif op in haslocal:
|
||||
if varnames:
|
||||
print '(' + varnames[oparg] + ')',
|
||||
else:
|
||||
print '(%d)' % oparg,
|
||||
elif op in hascompare:
|
||||
print '(' + cmp_op[oparg] + ')',
|
||||
print
|
||||
|
||||
disco = disassemble # XXX For backwards compatibility
|
||||
|
||||
def findlabels(code):
|
||||
"""Detect all offsets in a byte code which are jump targets.
|
||||
|
||||
Return the list of offsets.
|
||||
|
||||
"""
|
||||
labels = []
|
||||
n = len(code)
|
||||
i = 0
|
||||
while i < n:
|
||||
c = code[i]
|
||||
op = ord(c)
|
||||
i = i+1
|
||||
if op >= HAVE_ARGUMENT:
|
||||
oparg = ord(code[i]) + ord(code[i+1])*256
|
||||
i = i+2
|
||||
label = -1
|
||||
if op in hasjrel:
|
||||
label = i+oparg
|
||||
elif op in hasjabs:
|
||||
label = oparg
|
||||
if label >= 0:
|
||||
if label not in labels:
|
||||
labels.append(label)
|
||||
return labels
|
||||
|
||||
def findlinestarts(code):
|
||||
"""Find the offsets in a byte code which are start of lines in the source.
|
||||
|
||||
Generate pairs (offset, lineno) as described in Python/compile.c.
|
||||
|
||||
"""
|
||||
byte_increments = [ord(c) for c in code.co_lnotab[0::2]]
|
||||
line_increments = [ord(c) for c in code.co_lnotab[1::2]]
|
||||
|
||||
lastlineno = None
|
||||
lineno = code.co_firstlineno
|
||||
addr = 0
|
||||
for byte_incr, line_incr in zip(byte_increments, line_increments):
|
||||
if byte_incr:
|
||||
if lineno != lastlineno:
|
||||
yield (addr, lineno)
|
||||
lastlineno = lineno
|
||||
addr += byte_incr
|
||||
lineno += line_incr
|
||||
if lineno != lastlineno:
|
||||
yield (addr, lineno)
|
||||
|
||||
def _test():
|
||||
"""Simple test program to disassemble a file."""
|
||||
if sys.argv[1:]:
|
||||
if sys.argv[2:]:
|
||||
sys.stderr.write("usage: python dis.py [-|file]\n")
|
||||
sys.exit(2)
|
||||
fn = sys.argv[1]
|
||||
if not fn or fn == "-":
|
||||
fn = None
|
||||
else:
|
||||
fn = None
|
||||
if fn is None:
|
||||
f = sys.stdin
|
||||
else:
|
||||
f = open(fn)
|
||||
source = f.read()
|
||||
if fn is not None:
|
||||
f.close()
|
||||
else:
|
||||
fn = "<stdin>"
|
||||
code = compile(source, fn, "exec")
|
||||
dis(code)
|
||||
|
||||
if __name__ == "__main__":
|
||||
_test()
|
||||
145
AppPkg/Applications/Python/Python-2.7.10/Lib/dummy_thread.py
Normal file
145
AppPkg/Applications/Python/Python-2.7.10/Lib/dummy_thread.py
Normal file
@@ -0,0 +1,145 @@
|
||||
"""Drop-in replacement for the thread module.
|
||||
|
||||
Meant to be used as a brain-dead substitute so that threaded code does
|
||||
not need to be rewritten for when the thread module is not present.
|
||||
|
||||
Suggested usage is::
|
||||
|
||||
try:
|
||||
import thread
|
||||
except ImportError:
|
||||
import dummy_thread as thread
|
||||
|
||||
"""
|
||||
# Exports only things specified by thread documentation;
|
||||
# skipping obsolete synonyms allocate(), start_new(), exit_thread().
|
||||
__all__ = ['error', 'start_new_thread', 'exit', 'get_ident', 'allocate_lock',
|
||||
'interrupt_main', 'LockType']
|
||||
|
||||
import traceback as _traceback
|
||||
|
||||
class error(Exception):
|
||||
"""Dummy implementation of thread.error."""
|
||||
|
||||
def __init__(self, *args):
|
||||
self.args = args
|
||||
|
||||
def start_new_thread(function, args, kwargs={}):
|
||||
"""Dummy implementation of thread.start_new_thread().
|
||||
|
||||
Compatibility is maintained by making sure that ``args`` is a
|
||||
tuple and ``kwargs`` is a dictionary. If an exception is raised
|
||||
and it is SystemExit (which can be done by thread.exit()) it is
|
||||
caught and nothing is done; all other exceptions are printed out
|
||||
by using traceback.print_exc().
|
||||
|
||||
If the executed function calls interrupt_main the KeyboardInterrupt will be
|
||||
raised when the function returns.
|
||||
|
||||
"""
|
||||
if type(args) != type(tuple()):
|
||||
raise TypeError("2nd arg must be a tuple")
|
||||
if type(kwargs) != type(dict()):
|
||||
raise TypeError("3rd arg must be a dict")
|
||||
global _main
|
||||
_main = False
|
||||
try:
|
||||
function(*args, **kwargs)
|
||||
except SystemExit:
|
||||
pass
|
||||
except:
|
||||
_traceback.print_exc()
|
||||
_main = True
|
||||
global _interrupt
|
||||
if _interrupt:
|
||||
_interrupt = False
|
||||
raise KeyboardInterrupt
|
||||
|
||||
def exit():
|
||||
"""Dummy implementation of thread.exit()."""
|
||||
raise SystemExit
|
||||
|
||||
def get_ident():
|
||||
"""Dummy implementation of thread.get_ident().
|
||||
|
||||
Since this module should only be used when threadmodule is not
|
||||
available, it is safe to assume that the current process is the
|
||||
only thread. Thus a constant can be safely returned.
|
||||
"""
|
||||
return -1
|
||||
|
||||
def allocate_lock():
|
||||
"""Dummy implementation of thread.allocate_lock()."""
|
||||
return LockType()
|
||||
|
||||
def stack_size(size=None):
|
||||
"""Dummy implementation of thread.stack_size()."""
|
||||
if size is not None:
|
||||
raise error("setting thread stack size not supported")
|
||||
return 0
|
||||
|
||||
class LockType(object):
|
||||
"""Class implementing dummy implementation of thread.LockType.
|
||||
|
||||
Compatibility is maintained by maintaining self.locked_status
|
||||
which is a boolean that stores the state of the lock. Pickling of
|
||||
the lock, though, should not be done since if the thread module is
|
||||
then used with an unpickled ``lock()`` from here problems could
|
||||
occur from this class not having atomic methods.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.locked_status = False
|
||||
|
||||
def acquire(self, waitflag=None):
|
||||
"""Dummy implementation of acquire().
|
||||
|
||||
For blocking calls, self.locked_status is automatically set to
|
||||
True and returned appropriately based on value of
|
||||
``waitflag``. If it is non-blocking, then the value is
|
||||
actually checked and not set if it is already acquired. This
|
||||
is all done so that threading.Condition's assert statements
|
||||
aren't triggered and throw a little fit.
|
||||
|
||||
"""
|
||||
if waitflag is None or waitflag:
|
||||
self.locked_status = True
|
||||
return True
|
||||
else:
|
||||
if not self.locked_status:
|
||||
self.locked_status = True
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
__enter__ = acquire
|
||||
|
||||
def __exit__(self, typ, val, tb):
|
||||
self.release()
|
||||
|
||||
def release(self):
|
||||
"""Release the dummy lock."""
|
||||
# XXX Perhaps shouldn't actually bother to test? Could lead
|
||||
# to problems for complex, threaded code.
|
||||
if not self.locked_status:
|
||||
raise error
|
||||
self.locked_status = False
|
||||
return True
|
||||
|
||||
def locked(self):
|
||||
return self.locked_status
|
||||
|
||||
# Used to signal that interrupt_main was called in a "thread"
|
||||
_interrupt = False
|
||||
# True when not executing in a "thread"
|
||||
_main = True
|
||||
|
||||
def interrupt_main():
|
||||
"""Set _interrupt flag to True to have start_new_thread raise
|
||||
KeyboardInterrupt upon exiting."""
|
||||
if _main:
|
||||
raise KeyboardInterrupt
|
||||
else:
|
||||
global _interrupt
|
||||
_interrupt = True
|
||||
@@ -0,0 +1,157 @@
|
||||
""" Standard "encodings" Package
|
||||
|
||||
Standard Python encoding modules are stored in this package
|
||||
directory.
|
||||
|
||||
Codec modules must have names corresponding to normalized encoding
|
||||
names as defined in the normalize_encoding() function below, e.g.
|
||||
'utf-8' must be implemented by the module 'utf_8.py'.
|
||||
|
||||
Each codec module must export the following interface:
|
||||
|
||||
* getregentry() -> codecs.CodecInfo object
|
||||
The getregentry() API must a CodecInfo object with encoder, decoder,
|
||||
incrementalencoder, incrementaldecoder, streamwriter and streamreader
|
||||
atttributes which adhere to the Python Codec Interface Standard.
|
||||
|
||||
In addition, a module may optionally also define the following
|
||||
APIs which are then used by the package's codec search function:
|
||||
|
||||
* getaliases() -> sequence of encoding name strings to use as aliases
|
||||
|
||||
Alias names returned by getaliases() must be normalized encoding
|
||||
names as defined by normalize_encoding().
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
from encodings import aliases
|
||||
import __builtin__
|
||||
|
||||
_cache = {}
|
||||
_unknown = '--unknown--'
|
||||
_import_tail = ['*']
|
||||
_norm_encoding_map = (' . '
|
||||
'0123456789 ABCDEFGHIJKLMNOPQRSTUVWXYZ '
|
||||
' abcdefghijklmnopqrstuvwxyz '
|
||||
' '
|
||||
' '
|
||||
' ')
|
||||
_aliases = aliases.aliases
|
||||
|
||||
class CodecRegistryError(LookupError, SystemError):
|
||||
pass
|
||||
|
||||
def normalize_encoding(encoding):
|
||||
|
||||
""" Normalize an encoding name.
|
||||
|
||||
Normalization works as follows: all non-alphanumeric
|
||||
characters except the dot used for Python package names are
|
||||
collapsed and replaced with a single underscore, e.g. ' -;#'
|
||||
becomes '_'. Leading and trailing underscores are removed.
|
||||
|
||||
Note that encoding names should be ASCII only; if they do use
|
||||
non-ASCII characters, these must be Latin-1 compatible.
|
||||
|
||||
"""
|
||||
# Make sure we have an 8-bit string, because .translate() works
|
||||
# differently for Unicode strings.
|
||||
if hasattr(__builtin__, "unicode") and isinstance(encoding, unicode):
|
||||
# Note that .encode('latin-1') does *not* use the codec
|
||||
# registry, so this call doesn't recurse. (See unicodeobject.c
|
||||
# PyUnicode_AsEncodedString() for details)
|
||||
encoding = encoding.encode('latin-1')
|
||||
return '_'.join(encoding.translate(_norm_encoding_map).split())
|
||||
|
||||
def search_function(encoding):
|
||||
|
||||
# Cache lookup
|
||||
entry = _cache.get(encoding, _unknown)
|
||||
if entry is not _unknown:
|
||||
return entry
|
||||
|
||||
# Import the module:
|
||||
#
|
||||
# First try to find an alias for the normalized encoding
|
||||
# name and lookup the module using the aliased name, then try to
|
||||
# lookup the module using the standard import scheme, i.e. first
|
||||
# try in the encodings package, then at top-level.
|
||||
#
|
||||
norm_encoding = normalize_encoding(encoding)
|
||||
aliased_encoding = _aliases.get(norm_encoding) or \
|
||||
_aliases.get(norm_encoding.replace('.', '_'))
|
||||
if aliased_encoding is not None:
|
||||
modnames = [aliased_encoding,
|
||||
norm_encoding]
|
||||
else:
|
||||
modnames = [norm_encoding]
|
||||
for modname in modnames:
|
||||
if not modname or '.' in modname:
|
||||
continue
|
||||
try:
|
||||
# Import is absolute to prevent the possibly malicious import of a
|
||||
# module with side-effects that is not in the 'encodings' package.
|
||||
mod = __import__('encodings.' + modname, fromlist=_import_tail,
|
||||
level=0)
|
||||
except ImportError:
|
||||
pass
|
||||
else:
|
||||
break
|
||||
else:
|
||||
mod = None
|
||||
|
||||
try:
|
||||
getregentry = mod.getregentry
|
||||
except AttributeError:
|
||||
# Not a codec module
|
||||
mod = None
|
||||
|
||||
if mod is None:
|
||||
# Cache misses
|
||||
_cache[encoding] = None
|
||||
return None
|
||||
|
||||
# Now ask the module for the registry entry
|
||||
entry = getregentry()
|
||||
if not isinstance(entry, codecs.CodecInfo):
|
||||
if not 4 <= len(entry) <= 7:
|
||||
raise CodecRegistryError,\
|
||||
'module "%s" (%s) failed to register' % \
|
||||
(mod.__name__, mod.__file__)
|
||||
if not hasattr(entry[0], '__call__') or \
|
||||
not hasattr(entry[1], '__call__') or \
|
||||
(entry[2] is not None and not hasattr(entry[2], '__call__')) or \
|
||||
(entry[3] is not None and not hasattr(entry[3], '__call__')) or \
|
||||
(len(entry) > 4 and entry[4] is not None and not hasattr(entry[4], '__call__')) or \
|
||||
(len(entry) > 5 and entry[5] is not None and not hasattr(entry[5], '__call__')):
|
||||
raise CodecRegistryError,\
|
||||
'incompatible codecs in module "%s" (%s)' % \
|
||||
(mod.__name__, mod.__file__)
|
||||
if len(entry)<7 or entry[6] is None:
|
||||
entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],)
|
||||
entry = codecs.CodecInfo(*entry)
|
||||
|
||||
# Cache the codec registry entry
|
||||
_cache[encoding] = entry
|
||||
|
||||
# Register its aliases (without overwriting previously registered
|
||||
# aliases)
|
||||
try:
|
||||
codecaliases = mod.getaliases()
|
||||
except AttributeError:
|
||||
pass
|
||||
else:
|
||||
for alias in codecaliases:
|
||||
if alias not in _aliases:
|
||||
_aliases[alias] = modname
|
||||
|
||||
# Return the registry entry
|
||||
return entry
|
||||
|
||||
# Register the search_function in the Python codec registry
|
||||
codecs.register(search_function)
|
||||
@@ -0,0 +1,527 @@
|
||||
""" Encoding Aliases Support
|
||||
|
||||
This module is used by the encodings package search function to
|
||||
map encodings names to module names.
|
||||
|
||||
Note that the search function normalizes the encoding names before
|
||||
doing the lookup, so the mapping will have to map normalized
|
||||
encoding names to module names.
|
||||
|
||||
Contents:
|
||||
|
||||
The following aliases dictionary contains mappings of all IANA
|
||||
character set names for which the Python core library provides
|
||||
codecs. In addition to these, a few Python specific codec
|
||||
aliases have also been added.
|
||||
|
||||
"""
|
||||
aliases = {
|
||||
|
||||
# Please keep this list sorted alphabetically by value !
|
||||
|
||||
# ascii codec
|
||||
'646' : 'ascii',
|
||||
'ansi_x3.4_1968' : 'ascii',
|
||||
'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name
|
||||
'ansi_x3.4_1986' : 'ascii',
|
||||
'cp367' : 'ascii',
|
||||
'csascii' : 'ascii',
|
||||
'ibm367' : 'ascii',
|
||||
'iso646_us' : 'ascii',
|
||||
'iso_646.irv_1991' : 'ascii',
|
||||
'iso_ir_6' : 'ascii',
|
||||
'us' : 'ascii',
|
||||
'us_ascii' : 'ascii',
|
||||
|
||||
# base64_codec codec
|
||||
'base64' : 'base64_codec',
|
||||
'base_64' : 'base64_codec',
|
||||
|
||||
# big5 codec
|
||||
'big5_tw' : 'big5',
|
||||
'csbig5' : 'big5',
|
||||
|
||||
# big5hkscs codec
|
||||
'big5_hkscs' : 'big5hkscs',
|
||||
'hkscs' : 'big5hkscs',
|
||||
|
||||
# bz2_codec codec
|
||||
'bz2' : 'bz2_codec',
|
||||
|
||||
# cp037 codec
|
||||
'037' : 'cp037',
|
||||
'csibm037' : 'cp037',
|
||||
'ebcdic_cp_ca' : 'cp037',
|
||||
'ebcdic_cp_nl' : 'cp037',
|
||||
'ebcdic_cp_us' : 'cp037',
|
||||
'ebcdic_cp_wt' : 'cp037',
|
||||
'ibm037' : 'cp037',
|
||||
'ibm039' : 'cp037',
|
||||
|
||||
# cp1026 codec
|
||||
'1026' : 'cp1026',
|
||||
'csibm1026' : 'cp1026',
|
||||
'ibm1026' : 'cp1026',
|
||||
|
||||
# cp1140 codec
|
||||
'1140' : 'cp1140',
|
||||
'ibm1140' : 'cp1140',
|
||||
|
||||
# cp1250 codec
|
||||
'1250' : 'cp1250',
|
||||
'windows_1250' : 'cp1250',
|
||||
|
||||
# cp1251 codec
|
||||
'1251' : 'cp1251',
|
||||
'windows_1251' : 'cp1251',
|
||||
|
||||
# cp1252 codec
|
||||
'1252' : 'cp1252',
|
||||
'windows_1252' : 'cp1252',
|
||||
|
||||
# cp1253 codec
|
||||
'1253' : 'cp1253',
|
||||
'windows_1253' : 'cp1253',
|
||||
|
||||
# cp1254 codec
|
||||
'1254' : 'cp1254',
|
||||
'windows_1254' : 'cp1254',
|
||||
|
||||
# cp1255 codec
|
||||
'1255' : 'cp1255',
|
||||
'windows_1255' : 'cp1255',
|
||||
|
||||
# cp1256 codec
|
||||
'1256' : 'cp1256',
|
||||
'windows_1256' : 'cp1256',
|
||||
|
||||
# cp1257 codec
|
||||
'1257' : 'cp1257',
|
||||
'windows_1257' : 'cp1257',
|
||||
|
||||
# cp1258 codec
|
||||
'1258' : 'cp1258',
|
||||
'windows_1258' : 'cp1258',
|
||||
|
||||
# cp424 codec
|
||||
'424' : 'cp424',
|
||||
'csibm424' : 'cp424',
|
||||
'ebcdic_cp_he' : 'cp424',
|
||||
'ibm424' : 'cp424',
|
||||
|
||||
# cp437 codec
|
||||
'437' : 'cp437',
|
||||
'cspc8codepage437' : 'cp437',
|
||||
'ibm437' : 'cp437',
|
||||
|
||||
# cp500 codec
|
||||
'500' : 'cp500',
|
||||
'csibm500' : 'cp500',
|
||||
'ebcdic_cp_be' : 'cp500',
|
||||
'ebcdic_cp_ch' : 'cp500',
|
||||
'ibm500' : 'cp500',
|
||||
|
||||
# cp775 codec
|
||||
'775' : 'cp775',
|
||||
'cspc775baltic' : 'cp775',
|
||||
'ibm775' : 'cp775',
|
||||
|
||||
# cp850 codec
|
||||
'850' : 'cp850',
|
||||
'cspc850multilingual' : 'cp850',
|
||||
'ibm850' : 'cp850',
|
||||
|
||||
# cp852 codec
|
||||
'852' : 'cp852',
|
||||
'cspcp852' : 'cp852',
|
||||
'ibm852' : 'cp852',
|
||||
|
||||
# cp855 codec
|
||||
'855' : 'cp855',
|
||||
'csibm855' : 'cp855',
|
||||
'ibm855' : 'cp855',
|
||||
|
||||
# cp857 codec
|
||||
'857' : 'cp857',
|
||||
'csibm857' : 'cp857',
|
||||
'ibm857' : 'cp857',
|
||||
|
||||
# cp858 codec
|
||||
'858' : 'cp858',
|
||||
'csibm858' : 'cp858',
|
||||
'ibm858' : 'cp858',
|
||||
|
||||
# cp860 codec
|
||||
'860' : 'cp860',
|
||||
'csibm860' : 'cp860',
|
||||
'ibm860' : 'cp860',
|
||||
|
||||
# cp861 codec
|
||||
'861' : 'cp861',
|
||||
'cp_is' : 'cp861',
|
||||
'csibm861' : 'cp861',
|
||||
'ibm861' : 'cp861',
|
||||
|
||||
# cp862 codec
|
||||
'862' : 'cp862',
|
||||
'cspc862latinhebrew' : 'cp862',
|
||||
'ibm862' : 'cp862',
|
||||
|
||||
# cp863 codec
|
||||
'863' : 'cp863',
|
||||
'csibm863' : 'cp863',
|
||||
'ibm863' : 'cp863',
|
||||
|
||||
# cp864 codec
|
||||
'864' : 'cp864',
|
||||
'csibm864' : 'cp864',
|
||||
'ibm864' : 'cp864',
|
||||
|
||||
# cp865 codec
|
||||
'865' : 'cp865',
|
||||
'csibm865' : 'cp865',
|
||||
'ibm865' : 'cp865',
|
||||
|
||||
# cp866 codec
|
||||
'866' : 'cp866',
|
||||
'csibm866' : 'cp866',
|
||||
'ibm866' : 'cp866',
|
||||
|
||||
# cp869 codec
|
||||
'869' : 'cp869',
|
||||
'cp_gr' : 'cp869',
|
||||
'csibm869' : 'cp869',
|
||||
'ibm869' : 'cp869',
|
||||
|
||||
# cp932 codec
|
||||
'932' : 'cp932',
|
||||
'ms932' : 'cp932',
|
||||
'mskanji' : 'cp932',
|
||||
'ms_kanji' : 'cp932',
|
||||
|
||||
# cp949 codec
|
||||
'949' : 'cp949',
|
||||
'ms949' : 'cp949',
|
||||
'uhc' : 'cp949',
|
||||
|
||||
# cp950 codec
|
||||
'950' : 'cp950',
|
||||
'ms950' : 'cp950',
|
||||
|
||||
# euc_jis_2004 codec
|
||||
'jisx0213' : 'euc_jis_2004',
|
||||
'eucjis2004' : 'euc_jis_2004',
|
||||
'euc_jis2004' : 'euc_jis_2004',
|
||||
|
||||
# euc_jisx0213 codec
|
||||
'eucjisx0213' : 'euc_jisx0213',
|
||||
|
||||
# euc_jp codec
|
||||
'eucjp' : 'euc_jp',
|
||||
'ujis' : 'euc_jp',
|
||||
'u_jis' : 'euc_jp',
|
||||
|
||||
# euc_kr codec
|
||||
'euckr' : 'euc_kr',
|
||||
'korean' : 'euc_kr',
|
||||
'ksc5601' : 'euc_kr',
|
||||
'ks_c_5601' : 'euc_kr',
|
||||
'ks_c_5601_1987' : 'euc_kr',
|
||||
'ksx1001' : 'euc_kr',
|
||||
'ks_x_1001' : 'euc_kr',
|
||||
|
||||
# gb18030 codec
|
||||
'gb18030_2000' : 'gb18030',
|
||||
|
||||
# gb2312 codec
|
||||
'chinese' : 'gb2312',
|
||||
'csiso58gb231280' : 'gb2312',
|
||||
'euc_cn' : 'gb2312',
|
||||
'euccn' : 'gb2312',
|
||||
'eucgb2312_cn' : 'gb2312',
|
||||
'gb2312_1980' : 'gb2312',
|
||||
'gb2312_80' : 'gb2312',
|
||||
'iso_ir_58' : 'gb2312',
|
||||
|
||||
# gbk codec
|
||||
'936' : 'gbk',
|
||||
'cp936' : 'gbk',
|
||||
'ms936' : 'gbk',
|
||||
|
||||
# hex_codec codec
|
||||
'hex' : 'hex_codec',
|
||||
|
||||
# hp_roman8 codec
|
||||
'roman8' : 'hp_roman8',
|
||||
'r8' : 'hp_roman8',
|
||||
'csHPRoman8' : 'hp_roman8',
|
||||
|
||||
# hz codec
|
||||
'hzgb' : 'hz',
|
||||
'hz_gb' : 'hz',
|
||||
'hz_gb_2312' : 'hz',
|
||||
|
||||
# iso2022_jp codec
|
||||
'csiso2022jp' : 'iso2022_jp',
|
||||
'iso2022jp' : 'iso2022_jp',
|
||||
'iso_2022_jp' : 'iso2022_jp',
|
||||
|
||||
# iso2022_jp_1 codec
|
||||
'iso2022jp_1' : 'iso2022_jp_1',
|
||||
'iso_2022_jp_1' : 'iso2022_jp_1',
|
||||
|
||||
# iso2022_jp_2 codec
|
||||
'iso2022jp_2' : 'iso2022_jp_2',
|
||||
'iso_2022_jp_2' : 'iso2022_jp_2',
|
||||
|
||||
# iso2022_jp_2004 codec
|
||||
'iso_2022_jp_2004' : 'iso2022_jp_2004',
|
||||
'iso2022jp_2004' : 'iso2022_jp_2004',
|
||||
|
||||
# iso2022_jp_3 codec
|
||||
'iso2022jp_3' : 'iso2022_jp_3',
|
||||
'iso_2022_jp_3' : 'iso2022_jp_3',
|
||||
|
||||
# iso2022_jp_ext codec
|
||||
'iso2022jp_ext' : 'iso2022_jp_ext',
|
||||
'iso_2022_jp_ext' : 'iso2022_jp_ext',
|
||||
|
||||
# iso2022_kr codec
|
||||
'csiso2022kr' : 'iso2022_kr',
|
||||
'iso2022kr' : 'iso2022_kr',
|
||||
'iso_2022_kr' : 'iso2022_kr',
|
||||
|
||||
# iso8859_10 codec
|
||||
'csisolatin6' : 'iso8859_10',
|
||||
'iso_8859_10' : 'iso8859_10',
|
||||
'iso_8859_10_1992' : 'iso8859_10',
|
||||
'iso_ir_157' : 'iso8859_10',
|
||||
'l6' : 'iso8859_10',
|
||||
'latin6' : 'iso8859_10',
|
||||
|
||||
# iso8859_11 codec
|
||||
'thai' : 'iso8859_11',
|
||||
'iso_8859_11' : 'iso8859_11',
|
||||
'iso_8859_11_2001' : 'iso8859_11',
|
||||
|
||||
# iso8859_13 codec
|
||||
'iso_8859_13' : 'iso8859_13',
|
||||
'l7' : 'iso8859_13',
|
||||
'latin7' : 'iso8859_13',
|
||||
|
||||
# iso8859_14 codec
|
||||
'iso_8859_14' : 'iso8859_14',
|
||||
'iso_8859_14_1998' : 'iso8859_14',
|
||||
'iso_celtic' : 'iso8859_14',
|
||||
'iso_ir_199' : 'iso8859_14',
|
||||
'l8' : 'iso8859_14',
|
||||
'latin8' : 'iso8859_14',
|
||||
|
||||
# iso8859_15 codec
|
||||
'iso_8859_15' : 'iso8859_15',
|
||||
'l9' : 'iso8859_15',
|
||||
'latin9' : 'iso8859_15',
|
||||
|
||||
# iso8859_16 codec
|
||||
'iso_8859_16' : 'iso8859_16',
|
||||
'iso_8859_16_2001' : 'iso8859_16',
|
||||
'iso_ir_226' : 'iso8859_16',
|
||||
'l10' : 'iso8859_16',
|
||||
'latin10' : 'iso8859_16',
|
||||
|
||||
# iso8859_2 codec
|
||||
'csisolatin2' : 'iso8859_2',
|
||||
'iso_8859_2' : 'iso8859_2',
|
||||
'iso_8859_2_1987' : 'iso8859_2',
|
||||
'iso_ir_101' : 'iso8859_2',
|
||||
'l2' : 'iso8859_2',
|
||||
'latin2' : 'iso8859_2',
|
||||
|
||||
# iso8859_3 codec
|
||||
'csisolatin3' : 'iso8859_3',
|
||||
'iso_8859_3' : 'iso8859_3',
|
||||
'iso_8859_3_1988' : 'iso8859_3',
|
||||
'iso_ir_109' : 'iso8859_3',
|
||||
'l3' : 'iso8859_3',
|
||||
'latin3' : 'iso8859_3',
|
||||
|
||||
# iso8859_4 codec
|
||||
'csisolatin4' : 'iso8859_4',
|
||||
'iso_8859_4' : 'iso8859_4',
|
||||
'iso_8859_4_1988' : 'iso8859_4',
|
||||
'iso_ir_110' : 'iso8859_4',
|
||||
'l4' : 'iso8859_4',
|
||||
'latin4' : 'iso8859_4',
|
||||
|
||||
# iso8859_5 codec
|
||||
'csisolatincyrillic' : 'iso8859_5',
|
||||
'cyrillic' : 'iso8859_5',
|
||||
'iso_8859_5' : 'iso8859_5',
|
||||
'iso_8859_5_1988' : 'iso8859_5',
|
||||
'iso_ir_144' : 'iso8859_5',
|
||||
|
||||
# iso8859_6 codec
|
||||
'arabic' : 'iso8859_6',
|
||||
'asmo_708' : 'iso8859_6',
|
||||
'csisolatinarabic' : 'iso8859_6',
|
||||
'ecma_114' : 'iso8859_6',
|
||||
'iso_8859_6' : 'iso8859_6',
|
||||
'iso_8859_6_1987' : 'iso8859_6',
|
||||
'iso_ir_127' : 'iso8859_6',
|
||||
|
||||
# iso8859_7 codec
|
||||
'csisolatingreek' : 'iso8859_7',
|
||||
'ecma_118' : 'iso8859_7',
|
||||
'elot_928' : 'iso8859_7',
|
||||
'greek' : 'iso8859_7',
|
||||
'greek8' : 'iso8859_7',
|
||||
'iso_8859_7' : 'iso8859_7',
|
||||
'iso_8859_7_1987' : 'iso8859_7',
|
||||
'iso_ir_126' : 'iso8859_7',
|
||||
|
||||
# iso8859_8 codec
|
||||
'csisolatinhebrew' : 'iso8859_8',
|
||||
'hebrew' : 'iso8859_8',
|
||||
'iso_8859_8' : 'iso8859_8',
|
||||
'iso_8859_8_1988' : 'iso8859_8',
|
||||
'iso_ir_138' : 'iso8859_8',
|
||||
|
||||
# iso8859_9 codec
|
||||
'csisolatin5' : 'iso8859_9',
|
||||
'iso_8859_9' : 'iso8859_9',
|
||||
'iso_8859_9_1989' : 'iso8859_9',
|
||||
'iso_ir_148' : 'iso8859_9',
|
||||
'l5' : 'iso8859_9',
|
||||
'latin5' : 'iso8859_9',
|
||||
|
||||
# johab codec
|
||||
'cp1361' : 'johab',
|
||||
'ms1361' : 'johab',
|
||||
|
||||
# koi8_r codec
|
||||
'cskoi8r' : 'koi8_r',
|
||||
|
||||
# latin_1 codec
|
||||
#
|
||||
# Note that the latin_1 codec is implemented internally in C and a
|
||||
# lot faster than the charmap codec iso8859_1 which uses the same
|
||||
# encoding. This is why we discourage the use of the iso8859_1
|
||||
# codec and alias it to latin_1 instead.
|
||||
#
|
||||
'8859' : 'latin_1',
|
||||
'cp819' : 'latin_1',
|
||||
'csisolatin1' : 'latin_1',
|
||||
'ibm819' : 'latin_1',
|
||||
'iso8859' : 'latin_1',
|
||||
'iso8859_1' : 'latin_1',
|
||||
'iso_8859_1' : 'latin_1',
|
||||
'iso_8859_1_1987' : 'latin_1',
|
||||
'iso_ir_100' : 'latin_1',
|
||||
'l1' : 'latin_1',
|
||||
'latin' : 'latin_1',
|
||||
'latin1' : 'latin_1',
|
||||
|
||||
# mac_cyrillic codec
|
||||
'maccyrillic' : 'mac_cyrillic',
|
||||
|
||||
# mac_greek codec
|
||||
'macgreek' : 'mac_greek',
|
||||
|
||||
# mac_iceland codec
|
||||
'maciceland' : 'mac_iceland',
|
||||
|
||||
# mac_latin2 codec
|
||||
'maccentraleurope' : 'mac_latin2',
|
||||
'maclatin2' : 'mac_latin2',
|
||||
|
||||
# mac_roman codec
|
||||
'macroman' : 'mac_roman',
|
||||
|
||||
# mac_turkish codec
|
||||
'macturkish' : 'mac_turkish',
|
||||
|
||||
# mbcs codec
|
||||
'dbcs' : 'mbcs',
|
||||
|
||||
# ptcp154 codec
|
||||
'csptcp154' : 'ptcp154',
|
||||
'pt154' : 'ptcp154',
|
||||
'cp154' : 'ptcp154',
|
||||
'cyrillic_asian' : 'ptcp154',
|
||||
|
||||
# quopri_codec codec
|
||||
'quopri' : 'quopri_codec',
|
||||
'quoted_printable' : 'quopri_codec',
|
||||
'quotedprintable' : 'quopri_codec',
|
||||
|
||||
# rot_13 codec
|
||||
'rot13' : 'rot_13',
|
||||
|
||||
# shift_jis codec
|
||||
'csshiftjis' : 'shift_jis',
|
||||
'shiftjis' : 'shift_jis',
|
||||
'sjis' : 'shift_jis',
|
||||
's_jis' : 'shift_jis',
|
||||
|
||||
# shift_jis_2004 codec
|
||||
'shiftjis2004' : 'shift_jis_2004',
|
||||
'sjis_2004' : 'shift_jis_2004',
|
||||
's_jis_2004' : 'shift_jis_2004',
|
||||
|
||||
# shift_jisx0213 codec
|
||||
'shiftjisx0213' : 'shift_jisx0213',
|
||||
'sjisx0213' : 'shift_jisx0213',
|
||||
's_jisx0213' : 'shift_jisx0213',
|
||||
|
||||
# tactis codec
|
||||
'tis260' : 'tactis',
|
||||
|
||||
# tis_620 codec
|
||||
'tis620' : 'tis_620',
|
||||
'tis_620_0' : 'tis_620',
|
||||
'tis_620_2529_0' : 'tis_620',
|
||||
'tis_620_2529_1' : 'tis_620',
|
||||
'iso_ir_166' : 'tis_620',
|
||||
|
||||
# utf_16 codec
|
||||
'u16' : 'utf_16',
|
||||
'utf16' : 'utf_16',
|
||||
|
||||
# utf_16_be codec
|
||||
'unicodebigunmarked' : 'utf_16_be',
|
||||
'utf_16be' : 'utf_16_be',
|
||||
|
||||
# utf_16_le codec
|
||||
'unicodelittleunmarked' : 'utf_16_le',
|
||||
'utf_16le' : 'utf_16_le',
|
||||
|
||||
# utf_32 codec
|
||||
'u32' : 'utf_32',
|
||||
'utf32' : 'utf_32',
|
||||
|
||||
# utf_32_be codec
|
||||
'utf_32be' : 'utf_32_be',
|
||||
|
||||
# utf_32_le codec
|
||||
'utf_32le' : 'utf_32_le',
|
||||
|
||||
# utf_7 codec
|
||||
'u7' : 'utf_7',
|
||||
'utf7' : 'utf_7',
|
||||
'unicode_1_1_utf_7' : 'utf_7',
|
||||
|
||||
# utf_8 codec
|
||||
'u8' : 'utf_8',
|
||||
'utf' : 'utf_8',
|
||||
'utf8' : 'utf_8',
|
||||
'utf8_ucs2' : 'utf_8',
|
||||
'utf8_ucs4' : 'utf_8',
|
||||
|
||||
# uu_codec codec
|
||||
'uu' : 'uu_codec',
|
||||
|
||||
# zlib_codec codec
|
||||
'zip' : 'zlib_codec',
|
||||
'zlib' : 'zlib_codec',
|
||||
|
||||
}
|
||||
@@ -0,0 +1,50 @@
|
||||
""" Python 'ascii' Codec
|
||||
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
||||
|
||||
"""
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
# Note: Binding these as C functions will result in the class not
|
||||
# converting them to methods. This is intended.
|
||||
encode = codecs.ascii_encode
|
||||
decode = codecs.ascii_decode
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.ascii_encode(input, self.errors)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.ascii_decode(input, self.errors)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
class StreamConverter(StreamWriter,StreamReader):
|
||||
|
||||
encode = codecs.ascii_decode
|
||||
decode = codecs.ascii_encode
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='ascii',
|
||||
encode=Codec.encode,
|
||||
decode=Codec.decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
@@ -0,0 +1,79 @@
|
||||
""" Python 'base64_codec' Codec - base64 content transfer encoding
|
||||
|
||||
Unlike most of the other codecs which target Unicode, this codec
|
||||
will return Python string objects for both encode and decode.
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
"""
|
||||
import codecs, base64
|
||||
|
||||
### Codec APIs
|
||||
|
||||
def base64_encode(input,errors='strict'):
|
||||
|
||||
""" Encodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = base64.encodestring(input)
|
||||
return (output, len(input))
|
||||
|
||||
def base64_decode(input,errors='strict'):
|
||||
|
||||
""" Decodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
input must be an object which provides the bf_getreadbuf
|
||||
buffer slot. Python strings, buffer objects and memory
|
||||
mapped files are examples of objects providing this slot.
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = base64.decodestring(input)
|
||||
return (output, len(input))
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self, input,errors='strict'):
|
||||
return base64_encode(input,errors)
|
||||
def decode(self, input,errors='strict'):
|
||||
return base64_decode(input,errors)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
assert self.errors == 'strict'
|
||||
return base64.encodestring(input)
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
assert self.errors == 'strict'
|
||||
return base64.decodestring(input)
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='base64',
|
||||
encode=base64_encode,
|
||||
decode=base64_decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# big5.py: Python Unicode Codec for BIG5
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_tw, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_tw.getcodec('big5')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='big5',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# big5hkscs.py: Python Unicode Codec for BIG5HKSCS
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_hk, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_hk.getcodec('big5hkscs')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='big5hkscs',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,102 @@
|
||||
""" Python 'bz2_codec' Codec - bz2 compression encoding
|
||||
|
||||
Unlike most of the other codecs which target Unicode, this codec
|
||||
will return Python string objects for both encode and decode.
|
||||
|
||||
Adapted by Raymond Hettinger from zlib_codec.py which was written
|
||||
by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
"""
|
||||
import codecs
|
||||
import bz2 # this codec needs the optional bz2 module !
|
||||
|
||||
### Codec APIs
|
||||
|
||||
def bz2_encode(input,errors='strict'):
|
||||
|
||||
""" Encodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = bz2.compress(input)
|
||||
return (output, len(input))
|
||||
|
||||
def bz2_decode(input,errors='strict'):
|
||||
|
||||
""" Decodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
input must be an object which provides the bf_getreadbuf
|
||||
buffer slot. Python strings, buffer objects and memory
|
||||
mapped files are examples of objects providing this slot.
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = bz2.decompress(input)
|
||||
return (output, len(input))
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self, input, errors='strict'):
|
||||
return bz2_encode(input, errors)
|
||||
def decode(self, input, errors='strict'):
|
||||
return bz2_decode(input, errors)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def __init__(self, errors='strict'):
|
||||
assert errors == 'strict'
|
||||
self.errors = errors
|
||||
self.compressobj = bz2.BZ2Compressor()
|
||||
|
||||
def encode(self, input, final=False):
|
||||
if final:
|
||||
c = self.compressobj.compress(input)
|
||||
return c + self.compressobj.flush()
|
||||
else:
|
||||
return self.compressobj.compress(input)
|
||||
|
||||
def reset(self):
|
||||
self.compressobj = bz2.BZ2Compressor()
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def __init__(self, errors='strict'):
|
||||
assert errors == 'strict'
|
||||
self.errors = errors
|
||||
self.decompressobj = bz2.BZ2Decompressor()
|
||||
|
||||
def decode(self, input, final=False):
|
||||
try:
|
||||
return self.decompressobj.decompress(input)
|
||||
except EOFError:
|
||||
return ''
|
||||
|
||||
def reset(self):
|
||||
self.decompressobj = bz2.BZ2Decompressor()
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name="bz2",
|
||||
encode=bz2_encode,
|
||||
decode=bz2_decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
@@ -0,0 +1,69 @@
|
||||
""" Generic Python Character Mapping Codec.
|
||||
|
||||
Use this codec directly rather than through the automatic
|
||||
conversion mechanisms supplied by unicode() and .encode().
|
||||
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
# Note: Binding these as C functions will result in the class not
|
||||
# converting them to methods. This is intended.
|
||||
encode = codecs.charmap_encode
|
||||
decode = codecs.charmap_decode
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def __init__(self, errors='strict', mapping=None):
|
||||
codecs.IncrementalEncoder.__init__(self, errors)
|
||||
self.mapping = mapping
|
||||
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input, self.errors, self.mapping)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def __init__(self, errors='strict', mapping=None):
|
||||
codecs.IncrementalDecoder.__init__(self, errors)
|
||||
self.mapping = mapping
|
||||
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input, self.errors, self.mapping)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
|
||||
def __init__(self,stream,errors='strict',mapping=None):
|
||||
codecs.StreamWriter.__init__(self,stream,errors)
|
||||
self.mapping = mapping
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return Codec.encode(input,errors,self.mapping)
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
|
||||
def __init__(self,stream,errors='strict',mapping=None):
|
||||
codecs.StreamReader.__init__(self,stream,errors)
|
||||
self.mapping = mapping
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return Codec.decode(input,errors,self.mapping)
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='charmap',
|
||||
encode=Codec.encode,
|
||||
decode=Codec.decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp037.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp037.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp037',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> CONTROL
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> CONTROL
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> CONTROL
|
||||
u'\x8d' # 0x09 -> CONTROL
|
||||
u'\x8e' # 0x0A -> CONTROL
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> CONTROL
|
||||
u'\x85' # 0x15 -> CONTROL
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> CONTROL
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> CONTROL
|
||||
u'\x8f' # 0x1B -> CONTROL
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> CONTROL
|
||||
u'\x81' # 0x21 -> CONTROL
|
||||
u'\x82' # 0x22 -> CONTROL
|
||||
u'\x83' # 0x23 -> CONTROL
|
||||
u'\x84' # 0x24 -> CONTROL
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> CONTROL
|
||||
u'\x89' # 0x29 -> CONTROL
|
||||
u'\x8a' # 0x2A -> CONTROL
|
||||
u'\x8b' # 0x2B -> CONTROL
|
||||
u'\x8c' # 0x2C -> CONTROL
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> CONTROL
|
||||
u'\x91' # 0x31 -> CONTROL
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> CONTROL
|
||||
u'\x94' # 0x34 -> CONTROL
|
||||
u'\x95' # 0x35 -> CONTROL
|
||||
u'\x96' # 0x36 -> CONTROL
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> CONTROL
|
||||
u'\x99' # 0x39 -> CONTROL
|
||||
u'\x9a' # 0x3A -> CONTROL
|
||||
u'\x9b' # 0x3B -> CONTROL
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> CONTROL
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\xa0' # 0x41 -> NO-BREAK SPACE
|
||||
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xa2' # 0x4A -> CENT SIGN
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'|' # 0x4F -> VERTICAL LINE
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u'!' # 0x5A -> EXCLAMATION MARK
|
||||
u'$' # 0x5B -> DOLLAR SIGN
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'\xac' # 0x5F -> NOT SIGN
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xa6' # 0x6A -> BROKEN BAR
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'`' # 0x79 -> GRAVE ACCENT
|
||||
u':' # 0x7A -> COLON
|
||||
u'#' # 0x7B -> NUMBER SIGN
|
||||
u'@' # 0x7C -> COMMERCIAL AT
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'"' # 0x7F -> QUOTATION MARK
|
||||
u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
|
||||
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
|
||||
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
|
||||
u'\xb8' # 0x9D -> CEDILLA
|
||||
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xa4' # 0x9F -> CURRENCY SIGN
|
||||
u'\xb5' # 0xA0 -> MICRO SIGN
|
||||
u'~' # 0xA1 -> TILDE
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
|
||||
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
|
||||
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
|
||||
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
|
||||
u'\xae' # 0xAF -> REGISTERED SIGN
|
||||
u'^' # 0xB0 -> CIRCUMFLEX ACCENT
|
||||
u'\xa3' # 0xB1 -> POUND SIGN
|
||||
u'\xa5' # 0xB2 -> YEN SIGN
|
||||
u'\xb7' # 0xB3 -> MIDDLE DOT
|
||||
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
|
||||
u'\xa7' # 0xB5 -> SECTION SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'[' # 0xBA -> LEFT SQUARE BRACKET
|
||||
u']' # 0xBB -> RIGHT SQUARE BRACKET
|
||||
u'\xaf' # 0xBC -> MACRON
|
||||
u'\xa8' # 0xBD -> DIAERESIS
|
||||
u'\xb4' # 0xBE -> ACUTE ACCENT
|
||||
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
|
||||
u'{' # 0xC0 -> LEFT CURLY BRACKET
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'}' # 0xD0 -> RIGHT CURLY BRACKET
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
|
||||
u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\\' # 0xE0 -> REVERSE SOLIDUS
|
||||
u'\xf7' # 0xE1 -> DIVISION SIGN
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\x9f' # 0xFF -> CONTROL
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1006.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1006.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1006',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO
|
||||
u'\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE
|
||||
u'\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO
|
||||
u'\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE
|
||||
u'\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR
|
||||
u'\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE
|
||||
u'\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX
|
||||
u'\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN
|
||||
u'\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT
|
||||
u'\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE
|
||||
u'\u060c' # 0xAB -> ARABIC COMMA
|
||||
u'\u061b' # 0xAC -> ARABIC SEMICOLON
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u061f' # 0xAE -> ARABIC QUESTION MARK
|
||||
u'\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
u'\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM
|
||||
u'\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM
|
||||
u'\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM
|
||||
u'\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM
|
||||
u'\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM
|
||||
u'\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM
|
||||
u'\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM
|
||||
u'\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM
|
||||
u'\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM
|
||||
u'\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM
|
||||
u'\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM
|
||||
u'\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM
|
||||
u'\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM
|
||||
u'\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM
|
||||
u'\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM
|
||||
u'\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM
|
||||
u'\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM
|
||||
u'\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM
|
||||
u'\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM
|
||||
u'\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM
|
||||
u'\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM
|
||||
u'\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM
|
||||
u'\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM
|
||||
u'\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN
|
||||
u'\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM
|
||||
u'\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM
|
||||
u'\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM
|
||||
u'\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM
|
||||
u'\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM
|
||||
u'\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM
|
||||
u'\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM
|
||||
u'\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM
|
||||
u'\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM
|
||||
u'\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM
|
||||
u'\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM
|
||||
u'\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM
|
||||
u'\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM
|
||||
u'\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM
|
||||
u'\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM
|
||||
u'\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM
|
||||
u'\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM
|
||||
u'\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM
|
||||
u'\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM
|
||||
u'\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM
|
||||
u'\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM
|
||||
u'\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM
|
||||
u'\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM
|
||||
u'\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM
|
||||
u'\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM
|
||||
u'\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM
|
||||
u'\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM
|
||||
u'\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM
|
||||
u'\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM
|
||||
u'\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM
|
||||
u'\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM
|
||||
u'\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM
|
||||
u'\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM
|
||||
u'\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM
|
||||
u'\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM
|
||||
u'\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM
|
||||
u'\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM
|
||||
u'\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM
|
||||
u'\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM
|
||||
u'\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM
|
||||
u'\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM
|
||||
u'\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM
|
||||
u'\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM
|
||||
u'\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM
|
||||
u'\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM
|
||||
u'\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM
|
||||
u'\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
|
||||
u'\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM
|
||||
u'\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM
|
||||
u'\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM
|
||||
u'\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM
|
||||
u'\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM
|
||||
u'\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1026.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1026.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1026',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> CONTROL
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> CONTROL
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> CONTROL
|
||||
u'\x8d' # 0x09 -> CONTROL
|
||||
u'\x8e' # 0x0A -> CONTROL
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> CONTROL
|
||||
u'\x85' # 0x15 -> CONTROL
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> CONTROL
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> CONTROL
|
||||
u'\x8f' # 0x1B -> CONTROL
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> CONTROL
|
||||
u'\x81' # 0x21 -> CONTROL
|
||||
u'\x82' # 0x22 -> CONTROL
|
||||
u'\x83' # 0x23 -> CONTROL
|
||||
u'\x84' # 0x24 -> CONTROL
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> CONTROL
|
||||
u'\x89' # 0x29 -> CONTROL
|
||||
u'\x8a' # 0x2A -> CONTROL
|
||||
u'\x8b' # 0x2B -> CONTROL
|
||||
u'\x8c' # 0x2C -> CONTROL
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> CONTROL
|
||||
u'\x91' # 0x31 -> CONTROL
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> CONTROL
|
||||
u'\x94' # 0x34 -> CONTROL
|
||||
u'\x95' # 0x35 -> CONTROL
|
||||
u'\x96' # 0x36 -> CONTROL
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> CONTROL
|
||||
u'\x99' # 0x39 -> CONTROL
|
||||
u'\x9a' # 0x3A -> CONTROL
|
||||
u'\x9b' # 0x3B -> CONTROL
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> CONTROL
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\xa0' # 0x41 -> NO-BREAK SPACE
|
||||
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'{' # 0x48 -> LEFT CURLY BRACKET
|
||||
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'!' # 0x4F -> EXCLAMATION MARK
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u'\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE
|
||||
u'\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'^' # 0x5F -> CIRCUMFLEX ACCENT
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'[' # 0x68 -> LEFT SQUARE BRACKET
|
||||
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I
|
||||
u':' # 0x7A -> COLON
|
||||
u'\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'}' # 0x8C -> RIGHT CURLY BRACKET
|
||||
u'`' # 0x8D -> GRAVE ACCENT
|
||||
u'\xa6' # 0x8E -> BROKEN BAR
|
||||
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
|
||||
u'\xb8' # 0x9D -> CEDILLA
|
||||
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xa4' # 0x9F -> CURRENCY SIGN
|
||||
u'\xb5' # 0xA0 -> MICRO SIGN
|
||||
u'\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
|
||||
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
|
||||
u']' # 0xAC -> RIGHT SQUARE BRACKET
|
||||
u'$' # 0xAD -> DOLLAR SIGN
|
||||
u'@' # 0xAE -> COMMERCIAL AT
|
||||
u'\xae' # 0xAF -> REGISTERED SIGN
|
||||
u'\xa2' # 0xB0 -> CENT SIGN
|
||||
u'\xa3' # 0xB1 -> POUND SIGN
|
||||
u'\xa5' # 0xB2 -> YEN SIGN
|
||||
u'\xb7' # 0xB3 -> MIDDLE DOT
|
||||
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
|
||||
u'\xa7' # 0xB5 -> SECTION SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xac' # 0xBA -> NOT SIGN
|
||||
u'|' # 0xBB -> VERTICAL LINE
|
||||
u'\xaf' # 0xBC -> MACRON
|
||||
u'\xa8' # 0xBD -> DIAERESIS
|
||||
u'\xb4' # 0xBE -> ACUTE ACCENT
|
||||
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
|
||||
u'\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'~' # 0xCC -> TILDE
|
||||
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
|
||||
u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\\' # 0xDC -> REVERSE SOLIDUS
|
||||
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xf7' # 0xE1 -> DIVISION SIGN
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'#' # 0xEC -> NUMBER SIGN
|
||||
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'"' # 0xFC -> QUOTATION MARK
|
||||
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\x9f' # 0xFF -> CONTROL
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1140.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1140.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1140',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> CONTROL
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> CONTROL
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> CONTROL
|
||||
u'\x8d' # 0x09 -> CONTROL
|
||||
u'\x8e' # 0x0A -> CONTROL
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> CONTROL
|
||||
u'\x85' # 0x15 -> CONTROL
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> CONTROL
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> CONTROL
|
||||
u'\x8f' # 0x1B -> CONTROL
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> CONTROL
|
||||
u'\x81' # 0x21 -> CONTROL
|
||||
u'\x82' # 0x22 -> CONTROL
|
||||
u'\x83' # 0x23 -> CONTROL
|
||||
u'\x84' # 0x24 -> CONTROL
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> CONTROL
|
||||
u'\x89' # 0x29 -> CONTROL
|
||||
u'\x8a' # 0x2A -> CONTROL
|
||||
u'\x8b' # 0x2B -> CONTROL
|
||||
u'\x8c' # 0x2C -> CONTROL
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> CONTROL
|
||||
u'\x91' # 0x31 -> CONTROL
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> CONTROL
|
||||
u'\x94' # 0x34 -> CONTROL
|
||||
u'\x95' # 0x35 -> CONTROL
|
||||
u'\x96' # 0x36 -> CONTROL
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> CONTROL
|
||||
u'\x99' # 0x39 -> CONTROL
|
||||
u'\x9a' # 0x3A -> CONTROL
|
||||
u'\x9b' # 0x3B -> CONTROL
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> CONTROL
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\xa0' # 0x41 -> NO-BREAK SPACE
|
||||
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xa2' # 0x4A -> CENT SIGN
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'|' # 0x4F -> VERTICAL LINE
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u'!' # 0x5A -> EXCLAMATION MARK
|
||||
u'$' # 0x5B -> DOLLAR SIGN
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'\xac' # 0x5F -> NOT SIGN
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xa6' # 0x6A -> BROKEN BAR
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'`' # 0x79 -> GRAVE ACCENT
|
||||
u':' # 0x7A -> COLON
|
||||
u'#' # 0x7B -> NUMBER SIGN
|
||||
u'@' # 0x7C -> COMMERCIAL AT
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'"' # 0x7F -> QUOTATION MARK
|
||||
u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
|
||||
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
|
||||
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
|
||||
u'\xb8' # 0x9D -> CEDILLA
|
||||
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
|
||||
u'\u20ac' # 0x9F -> EURO SIGN
|
||||
u'\xb5' # 0xA0 -> MICRO SIGN
|
||||
u'~' # 0xA1 -> TILDE
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
|
||||
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
|
||||
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
|
||||
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
|
||||
u'\xae' # 0xAF -> REGISTERED SIGN
|
||||
u'^' # 0xB0 -> CIRCUMFLEX ACCENT
|
||||
u'\xa3' # 0xB1 -> POUND SIGN
|
||||
u'\xa5' # 0xB2 -> YEN SIGN
|
||||
u'\xb7' # 0xB3 -> MIDDLE DOT
|
||||
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
|
||||
u'\xa7' # 0xB5 -> SECTION SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'[' # 0xBA -> LEFT SQUARE BRACKET
|
||||
u']' # 0xBB -> RIGHT SQUARE BRACKET
|
||||
u'\xaf' # 0xBC -> MACRON
|
||||
u'\xa8' # 0xBD -> DIAERESIS
|
||||
u'\xb4' # 0xBE -> ACUTE ACCENT
|
||||
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
|
||||
u'{' # 0xC0 -> LEFT CURLY BRACKET
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'}' # 0xD0 -> RIGHT CURLY BRACKET
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
|
||||
u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\\' # 0xE0 -> REVERSE SOLIDUS
|
||||
u'\xf7' # 0xE1 -> DIVISION SIGN
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\x9f' # 0xFF -> CONTROL
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1250.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1250.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1250',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\ufffe' # 0x83 -> UNDEFINED
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\ufffe' # 0x88 -> UNDEFINED
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON
|
||||
u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\ufffe' # 0x98 -> UNDEFINED
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON
|
||||
u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u02c7' # 0xA1 -> CARON
|
||||
u'\u02d8' # 0xA2 -> BREVE
|
||||
u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\u02db' # 0xB2 -> OGONEK
|
||||
u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON
|
||||
u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT
|
||||
u'\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON
|
||||
u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE
|
||||
u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON
|
||||
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON
|
||||
u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE
|
||||
u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON
|
||||
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON
|
||||
u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA
|
||||
u'\u02d9' # 0xFF -> DOT ABOVE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1251.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1251.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1251',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE
|
||||
u'\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u20ac' # 0x88 -> EURO SIGN
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE
|
||||
u'\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE
|
||||
u'\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE
|
||||
u'\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE
|
||||
u'\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\ufffe' # 0x98 -> UNDEFINED
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE
|
||||
u'\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE
|
||||
u'\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE
|
||||
u'\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U
|
||||
u'\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U
|
||||
u'\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO
|
||||
u'\u2116' # 0xB9 -> NUMERO SIGN
|
||||
u'\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE
|
||||
u'\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE
|
||||
u'\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE
|
||||
u'\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI
|
||||
u'\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A
|
||||
u'\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE
|
||||
u'\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE
|
||||
u'\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE
|
||||
u'\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE
|
||||
u'\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE
|
||||
u'\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE
|
||||
u'\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE
|
||||
u'\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I
|
||||
u'\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I
|
||||
u'\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA
|
||||
u'\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL
|
||||
u'\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM
|
||||
u'\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN
|
||||
u'\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O
|
||||
u'\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE
|
||||
u'\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER
|
||||
u'\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES
|
||||
u'\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE
|
||||
u'\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U
|
||||
u'\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF
|
||||
u'\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA
|
||||
u'\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE
|
||||
u'\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE
|
||||
u'\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA
|
||||
u'\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA
|
||||
u'\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
u'\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU
|
||||
u'\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
u'\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E
|
||||
u'\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU
|
||||
u'\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA
|
||||
u'\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A
|
||||
u'\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE
|
||||
u'\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE
|
||||
u'\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE
|
||||
u'\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE
|
||||
u'\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE
|
||||
u'\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE
|
||||
u'\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE
|
||||
u'\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I
|
||||
u'\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I
|
||||
u'\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA
|
||||
u'\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL
|
||||
u'\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM
|
||||
u'\u043d' # 0xED -> CYRILLIC SMALL LETTER EN
|
||||
u'\u043e' # 0xEE -> CYRILLIC SMALL LETTER O
|
||||
u'\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE
|
||||
u'\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER
|
||||
u'\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES
|
||||
u'\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE
|
||||
u'\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U
|
||||
u'\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF
|
||||
u'\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA
|
||||
u'\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE
|
||||
u'\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE
|
||||
u'\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA
|
||||
u'\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA
|
||||
u'\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN
|
||||
u'\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU
|
||||
u'\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN
|
||||
u'\u044d' # 0xFD -> CYRILLIC SMALL LETTER E
|
||||
u'\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU
|
||||
u'\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1252.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1252.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1252',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\u02dc' # 0x98 -> SMALL TILDE
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1253.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1253.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1253',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\ufffe' # 0x88 -> UNDEFINED
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\ufffe' # 0x8A -> UNDEFINED
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x8C -> UNDEFINED
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\ufffe' # 0x98 -> UNDEFINED
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x9C -> UNDEFINED
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\ufffe' # 0x9F -> UNDEFINED
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS
|
||||
u'\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\ufffe' # 0xAA -> UNDEFINED
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\u2015' # 0xAF -> HORIZONTAL BAR
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\u0384' # 0xB4 -> GREEK TONOS
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
u'\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
u'\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
u'\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
u'\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
u'\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA
|
||||
u'\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA
|
||||
u'\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA
|
||||
u'\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON
|
||||
u'\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA
|
||||
u'\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA
|
||||
u'\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA
|
||||
u'\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA
|
||||
u'\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA
|
||||
u'\u039c' # 0xCC -> GREEK CAPITAL LETTER MU
|
||||
u'\u039d' # 0xCD -> GREEK CAPITAL LETTER NU
|
||||
u'\u039e' # 0xCE -> GREEK CAPITAL LETTER XI
|
||||
u'\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON
|
||||
u'\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI
|
||||
u'\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO
|
||||
u'\ufffe' # 0xD2 -> UNDEFINED
|
||||
u'\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU
|
||||
u'\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON
|
||||
u'\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI
|
||||
u'\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI
|
||||
u'\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
u'\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
u'\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS
|
||||
u'\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS
|
||||
u'\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
u'\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA
|
||||
u'\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA
|
||||
u'\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA
|
||||
u'\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA
|
||||
u'\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON
|
||||
u'\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA
|
||||
u'\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA
|
||||
u'\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA
|
||||
u'\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA
|
||||
u'\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA
|
||||
u'\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA
|
||||
u'\u03bc' # 0xEC -> GREEK SMALL LETTER MU
|
||||
u'\u03bd' # 0xED -> GREEK SMALL LETTER NU
|
||||
u'\u03be' # 0xEE -> GREEK SMALL LETTER XI
|
||||
u'\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON
|
||||
u'\u03c0' # 0xF0 -> GREEK SMALL LETTER PI
|
||||
u'\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO
|
||||
u'\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA
|
||||
u'\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA
|
||||
u'\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU
|
||||
u'\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON
|
||||
u'\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI
|
||||
u'\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI
|
||||
u'\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI
|
||||
u'\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA
|
||||
u'\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
u'\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
u'\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
u'\ufffe' # 0xFF -> UNDEFINED
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1254.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1254.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1254',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\u02dc' # 0x98 -> SMALL TILDE
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
u'\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I
|
||||
u'\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1255.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1255.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1255',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\ufffe' # 0x8A -> UNDEFINED
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x8C -> UNDEFINED
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\u02dc' # 0x98 -> SMALL TILDE
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x9C -> UNDEFINED
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\ufffe' # 0x9F -> UNDEFINED
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\u20aa' # 0xA4 -> NEW SHEQEL SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xd7' # 0xAA -> MULTIPLICATION SIGN
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xf7' # 0xBA -> DIVISION SIGN
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\u05b0' # 0xC0 -> HEBREW POINT SHEVA
|
||||
u'\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL
|
||||
u'\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH
|
||||
u'\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS
|
||||
u'\u05b4' # 0xC4 -> HEBREW POINT HIRIQ
|
||||
u'\u05b5' # 0xC5 -> HEBREW POINT TSERE
|
||||
u'\u05b6' # 0xC6 -> HEBREW POINT SEGOL
|
||||
u'\u05b7' # 0xC7 -> HEBREW POINT PATAH
|
||||
u'\u05b8' # 0xC8 -> HEBREW POINT QAMATS
|
||||
u'\u05b9' # 0xC9 -> HEBREW POINT HOLAM
|
||||
u'\ufffe' # 0xCA -> UNDEFINED
|
||||
u'\u05bb' # 0xCB -> HEBREW POINT QUBUTS
|
||||
u'\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ
|
||||
u'\u05bd' # 0xCD -> HEBREW POINT METEG
|
||||
u'\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF
|
||||
u'\u05bf' # 0xCF -> HEBREW POINT RAFE
|
||||
u'\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ
|
||||
u'\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT
|
||||
u'\u05c2' # 0xD2 -> HEBREW POINT SIN DOT
|
||||
u'\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ
|
||||
u'\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV
|
||||
u'\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD
|
||||
u'\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD
|
||||
u'\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH
|
||||
u'\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM
|
||||
u'\ufffe' # 0xD9 -> UNDEFINED
|
||||
u'\ufffe' # 0xDA -> UNDEFINED
|
||||
u'\ufffe' # 0xDB -> UNDEFINED
|
||||
u'\ufffe' # 0xDC -> UNDEFINED
|
||||
u'\ufffe' # 0xDD -> UNDEFINED
|
||||
u'\ufffe' # 0xDE -> UNDEFINED
|
||||
u'\ufffe' # 0xDF -> UNDEFINED
|
||||
u'\u05d0' # 0xE0 -> HEBREW LETTER ALEF
|
||||
u'\u05d1' # 0xE1 -> HEBREW LETTER BET
|
||||
u'\u05d2' # 0xE2 -> HEBREW LETTER GIMEL
|
||||
u'\u05d3' # 0xE3 -> HEBREW LETTER DALET
|
||||
u'\u05d4' # 0xE4 -> HEBREW LETTER HE
|
||||
u'\u05d5' # 0xE5 -> HEBREW LETTER VAV
|
||||
u'\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN
|
||||
u'\u05d7' # 0xE7 -> HEBREW LETTER HET
|
||||
u'\u05d8' # 0xE8 -> HEBREW LETTER TET
|
||||
u'\u05d9' # 0xE9 -> HEBREW LETTER YOD
|
||||
u'\u05da' # 0xEA -> HEBREW LETTER FINAL KAF
|
||||
u'\u05db' # 0xEB -> HEBREW LETTER KAF
|
||||
u'\u05dc' # 0xEC -> HEBREW LETTER LAMED
|
||||
u'\u05dd' # 0xED -> HEBREW LETTER FINAL MEM
|
||||
u'\u05de' # 0xEE -> HEBREW LETTER MEM
|
||||
u'\u05df' # 0xEF -> HEBREW LETTER FINAL NUN
|
||||
u'\u05e0' # 0xF0 -> HEBREW LETTER NUN
|
||||
u'\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH
|
||||
u'\u05e2' # 0xF2 -> HEBREW LETTER AYIN
|
||||
u'\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE
|
||||
u'\u05e4' # 0xF4 -> HEBREW LETTER PE
|
||||
u'\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI
|
||||
u'\u05e6' # 0xF6 -> HEBREW LETTER TSADI
|
||||
u'\u05e7' # 0xF7 -> HEBREW LETTER QOF
|
||||
u'\u05e8' # 0xF8 -> HEBREW LETTER RESH
|
||||
u'\u05e9' # 0xF9 -> HEBREW LETTER SHIN
|
||||
u'\u05ea' # 0xFA -> HEBREW LETTER TAV
|
||||
u'\ufffe' # 0xFB -> UNDEFINED
|
||||
u'\ufffe' # 0xFC -> UNDEFINED
|
||||
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
|
||||
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
|
||||
u'\ufffe' # 0xFF -> UNDEFINED
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1256.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1256.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1256',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\u067e' # 0x81 -> ARABIC LETTER PEH
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\u0679' # 0x8A -> ARABIC LETTER TTEH
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
|
||||
u'\u0686' # 0x8D -> ARABIC LETTER TCHEH
|
||||
u'\u0698' # 0x8E -> ARABIC LETTER JEH
|
||||
u'\u0688' # 0x8F -> ARABIC LETTER DDAL
|
||||
u'\u06af' # 0x90 -> ARABIC LETTER GAF
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\u06a9' # 0x98 -> ARABIC LETTER KEHEH
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\u0691' # 0x9A -> ARABIC LETTER RREH
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
|
||||
u'\u200c' # 0x9D -> ZERO WIDTH NON-JOINER
|
||||
u'\u200d' # 0x9E -> ZERO WIDTH JOINER
|
||||
u'\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u060c' # 0xA1 -> ARABIC COMMA
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\u061b' # 0xBA -> ARABIC SEMICOLON
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\u061f' # 0xBF -> ARABIC QUESTION MARK
|
||||
u'\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL
|
||||
u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA
|
||||
u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
u'\u0627' # 0xC7 -> ARABIC LETTER ALEF
|
||||
u'\u0628' # 0xC8 -> ARABIC LETTER BEH
|
||||
u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA
|
||||
u'\u062a' # 0xCA -> ARABIC LETTER TEH
|
||||
u'\u062b' # 0xCB -> ARABIC LETTER THEH
|
||||
u'\u062c' # 0xCC -> ARABIC LETTER JEEM
|
||||
u'\u062d' # 0xCD -> ARABIC LETTER HAH
|
||||
u'\u062e' # 0xCE -> ARABIC LETTER KHAH
|
||||
u'\u062f' # 0xCF -> ARABIC LETTER DAL
|
||||
u'\u0630' # 0xD0 -> ARABIC LETTER THAL
|
||||
u'\u0631' # 0xD1 -> ARABIC LETTER REH
|
||||
u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN
|
||||
u'\u0633' # 0xD3 -> ARABIC LETTER SEEN
|
||||
u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN
|
||||
u'\u0635' # 0xD5 -> ARABIC LETTER SAD
|
||||
u'\u0636' # 0xD6 -> ARABIC LETTER DAD
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u0637' # 0xD8 -> ARABIC LETTER TAH
|
||||
u'\u0638' # 0xD9 -> ARABIC LETTER ZAH
|
||||
u'\u0639' # 0xDA -> ARABIC LETTER AIN
|
||||
u'\u063a' # 0xDB -> ARABIC LETTER GHAIN
|
||||
u'\u0640' # 0xDC -> ARABIC TATWEEL
|
||||
u'\u0641' # 0xDD -> ARABIC LETTER FEH
|
||||
u'\u0642' # 0xDE -> ARABIC LETTER QAF
|
||||
u'\u0643' # 0xDF -> ARABIC LETTER KAF
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\u0644' # 0xE1 -> ARABIC LETTER LAM
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0645' # 0xE3 -> ARABIC LETTER MEEM
|
||||
u'\u0646' # 0xE4 -> ARABIC LETTER NOON
|
||||
u'\u0647' # 0xE5 -> ARABIC LETTER HEH
|
||||
u'\u0648' # 0xE6 -> ARABIC LETTER WAW
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA
|
||||
u'\u064a' # 0xED -> ARABIC LETTER YEH
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\u064b' # 0xF0 -> ARABIC FATHATAN
|
||||
u'\u064c' # 0xF1 -> ARABIC DAMMATAN
|
||||
u'\u064d' # 0xF2 -> ARABIC KASRATAN
|
||||
u'\u064e' # 0xF3 -> ARABIC FATHA
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u064f' # 0xF5 -> ARABIC DAMMA
|
||||
u'\u0650' # 0xF6 -> ARABIC KASRA
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u0651' # 0xF8 -> ARABIC SHADDA
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\u0652' # 0xFA -> ARABIC SUKUN
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u200e' # 0xFD -> LEFT-TO-RIGHT MARK
|
||||
u'\u200f' # 0xFE -> RIGHT-TO-LEFT MARK
|
||||
u'\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1257.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1257.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1257',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\ufffe' # 0x83 -> UNDEFINED
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\ufffe' # 0x88 -> UNDEFINED
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\ufffe' # 0x8A -> UNDEFINED
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x8C -> UNDEFINED
|
||||
u'\xa8' # 0x8D -> DIAERESIS
|
||||
u'\u02c7' # 0x8E -> CARON
|
||||
u'\xb8' # 0x8F -> CEDILLA
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\ufffe' # 0x98 -> UNDEFINED
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x9C -> UNDEFINED
|
||||
u'\xaf' # 0x9D -> MACRON
|
||||
u'\u02db' # 0x9E -> OGONEK
|
||||
u'\ufffe' # 0x9F -> UNDEFINED
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\ufffe' # 0xA1 -> UNDEFINED
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\ufffe' # 0xA5 -> UNDEFINED
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xe6' # 0xBF -> LATIN SMALL LETTER AE
|
||||
u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK
|
||||
u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON
|
||||
u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON
|
||||
u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK
|
||||
u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK
|
||||
u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON
|
||||
u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA
|
||||
u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA
|
||||
u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON
|
||||
u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA
|
||||
u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK
|
||||
u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u02d9' # 0xFF -> DOT ABOVE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1258.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp1258.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp1258',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK
|
||||
u'\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\u2020' # 0x86 -> DAGGER
|
||||
u'\u2021' # 0x87 -> DOUBLE DAGGER
|
||||
u'\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
u'\u2030' # 0x89 -> PER MILLE SIGN
|
||||
u'\ufffe' # 0x8A -> UNDEFINED
|
||||
u'\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\u02dc' # 0x98 -> SMALL TILDE
|
||||
u'\u2122' # 0x99 -> TRADE MARK SIGN
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
||||
u'\u0153' # 0x9C -> LATIN SMALL LIGATURE OE
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u0300' # 0xCC -> COMBINING GRAVE ACCENT
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\u0309' # 0xD2 -> COMBINING HOOK ABOVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN
|
||||
u'\u0303' # 0xDE -> COMBINING TILDE
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u0301' # 0xEC -> COMBINING ACUTE ACCENT
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\u0323' # 0xF2 -> COMBINING DOT BELOW
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN
|
||||
u'\u20ab' # 0xFE -> DONG SIGN
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp424.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp424.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp424',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> SELECT
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> REQUIRED NEW LINE
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> GRAPHIC ESCAPE
|
||||
u'\x8d' # 0x09 -> SUPERSCRIPT
|
||||
u'\x8e' # 0x0A -> REPEAT
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION
|
||||
u'\x85' # 0x15 -> NEW LINE
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> UNIT BACK SPACE
|
||||
u'\x8f' # 0x1B -> CUSTOMER USE ONE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> DIGIT SELECT
|
||||
u'\x81' # 0x21 -> START OF SIGNIFICANCE
|
||||
u'\x82' # 0x22 -> FIELD SEPARATOR
|
||||
u'\x83' # 0x23 -> WORD UNDERSCORE
|
||||
u'\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> SET ATTRIBUTE
|
||||
u'\x89' # 0x29 -> START FIELD EXTENDED
|
||||
u'\x8a' # 0x2A -> SET MODE OR SWITCH
|
||||
u'\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX
|
||||
u'\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> <reserved>
|
||||
u'\x91' # 0x31 -> <reserved>
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> INDEX RETURN
|
||||
u'\x94' # 0x34 -> PRESENTATION POSITION
|
||||
u'\x95' # 0x35 -> TRANSPARENT
|
||||
u'\x96' # 0x36 -> NUMERIC BACKSPACE
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> SUBSCRIPT
|
||||
u'\x99' # 0x39 -> INDENT TABULATION
|
||||
u'\x9a' # 0x3A -> REVERSE FORM FEED
|
||||
u'\x9b' # 0x3B -> CUSTOMER USE THREE
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> <reserved>
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\u05d0' # 0x41 -> HEBREW LETTER ALEF
|
||||
u'\u05d1' # 0x42 -> HEBREW LETTER BET
|
||||
u'\u05d2' # 0x43 -> HEBREW LETTER GIMEL
|
||||
u'\u05d3' # 0x44 -> HEBREW LETTER DALET
|
||||
u'\u05d4' # 0x45 -> HEBREW LETTER HE
|
||||
u'\u05d5' # 0x46 -> HEBREW LETTER VAV
|
||||
u'\u05d6' # 0x47 -> HEBREW LETTER ZAYIN
|
||||
u'\u05d7' # 0x48 -> HEBREW LETTER HET
|
||||
u'\u05d8' # 0x49 -> HEBREW LETTER TET
|
||||
u'\xa2' # 0x4A -> CENT SIGN
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'|' # 0x4F -> VERTICAL LINE
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\u05d9' # 0x51 -> HEBREW LETTER YOD
|
||||
u'\u05da' # 0x52 -> HEBREW LETTER FINAL KAF
|
||||
u'\u05db' # 0x53 -> HEBREW LETTER KAF
|
||||
u'\u05dc' # 0x54 -> HEBREW LETTER LAMED
|
||||
u'\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM
|
||||
u'\u05de' # 0x56 -> HEBREW LETTER MEM
|
||||
u'\u05df' # 0x57 -> HEBREW LETTER FINAL NUN
|
||||
u'\u05e0' # 0x58 -> HEBREW LETTER NUN
|
||||
u'\u05e1' # 0x59 -> HEBREW LETTER SAMEKH
|
||||
u'!' # 0x5A -> EXCLAMATION MARK
|
||||
u'$' # 0x5B -> DOLLAR SIGN
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'\xac' # 0x5F -> NOT SIGN
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\u05e2' # 0x62 -> HEBREW LETTER AYIN
|
||||
u'\u05e3' # 0x63 -> HEBREW LETTER FINAL PE
|
||||
u'\u05e4' # 0x64 -> HEBREW LETTER PE
|
||||
u'\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI
|
||||
u'\u05e6' # 0x66 -> HEBREW LETTER TSADI
|
||||
u'\u05e7' # 0x67 -> HEBREW LETTER QOF
|
||||
u'\u05e8' # 0x68 -> HEBREW LETTER RESH
|
||||
u'\u05e9' # 0x69 -> HEBREW LETTER SHIN
|
||||
u'\xa6' # 0x6A -> BROKEN BAR
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\ufffe' # 0x70 -> UNDEFINED
|
||||
u'\u05ea' # 0x71 -> HEBREW LETTER TAV
|
||||
u'\ufffe' # 0x72 -> UNDEFINED
|
||||
u'\ufffe' # 0x73 -> UNDEFINED
|
||||
u'\xa0' # 0x74 -> NO-BREAK SPACE
|
||||
u'\ufffe' # 0x75 -> UNDEFINED
|
||||
u'\ufffe' # 0x76 -> UNDEFINED
|
||||
u'\ufffe' # 0x77 -> UNDEFINED
|
||||
u'\u2017' # 0x78 -> DOUBLE LOW LINE
|
||||
u'`' # 0x79 -> GRAVE ACCENT
|
||||
u':' # 0x7A -> COLON
|
||||
u'#' # 0x7B -> NUMBER SIGN
|
||||
u'@' # 0x7C -> COMMERCIAL AT
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'"' # 0x7F -> QUOTATION MARK
|
||||
u'\ufffe' # 0x80 -> UNDEFINED
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\ufffe' # 0x8C -> UNDEFINED
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\ufffe' # 0x9B -> UNDEFINED
|
||||
u'\ufffe' # 0x9C -> UNDEFINED
|
||||
u'\xb8' # 0x9D -> CEDILLA
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\xa4' # 0x9F -> CURRENCY SIGN
|
||||
u'\xb5' # 0xA0 -> MICRO SIGN
|
||||
u'~' # 0xA1 -> TILDE
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\ufffe' # 0xAA -> UNDEFINED
|
||||
u'\ufffe' # 0xAB -> UNDEFINED
|
||||
u'\ufffe' # 0xAC -> UNDEFINED
|
||||
u'\ufffe' # 0xAD -> UNDEFINED
|
||||
u'\ufffe' # 0xAE -> UNDEFINED
|
||||
u'\xae' # 0xAF -> REGISTERED SIGN
|
||||
u'^' # 0xB0 -> CIRCUMFLEX ACCENT
|
||||
u'\xa3' # 0xB1 -> POUND SIGN
|
||||
u'\xa5' # 0xB2 -> YEN SIGN
|
||||
u'\xb7' # 0xB3 -> MIDDLE DOT
|
||||
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
|
||||
u'\xa7' # 0xB5 -> SECTION SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'[' # 0xBA -> LEFT SQUARE BRACKET
|
||||
u']' # 0xBB -> RIGHT SQUARE BRACKET
|
||||
u'\xaf' # 0xBC -> MACRON
|
||||
u'\xa8' # 0xBD -> DIAERESIS
|
||||
u'\xb4' # 0xBE -> ACUTE ACCENT
|
||||
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
|
||||
u'{' # 0xC0 -> LEFT CURLY BRACKET
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\ufffe' # 0xCB -> UNDEFINED
|
||||
u'\ufffe' # 0xCC -> UNDEFINED
|
||||
u'\ufffe' # 0xCD -> UNDEFINED
|
||||
u'\ufffe' # 0xCE -> UNDEFINED
|
||||
u'\ufffe' # 0xCF -> UNDEFINED
|
||||
u'}' # 0xD0 -> RIGHT CURLY BRACKET
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
|
||||
u'\ufffe' # 0xDB -> UNDEFINED
|
||||
u'\ufffe' # 0xDC -> UNDEFINED
|
||||
u'\ufffe' # 0xDD -> UNDEFINED
|
||||
u'\ufffe' # 0xDE -> UNDEFINED
|
||||
u'\ufffe' # 0xDF -> UNDEFINED
|
||||
u'\\' # 0xE0 -> REVERSE SOLIDUS
|
||||
u'\xf7' # 0xE1 -> DIVISION SIGN
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\ufffe' # 0xEB -> UNDEFINED
|
||||
u'\ufffe' # 0xEC -> UNDEFINED
|
||||
u'\ufffe' # 0xED -> UNDEFINED
|
||||
u'\ufffe' # 0xEE -> UNDEFINED
|
||||
u'\ufffe' # 0xEF -> UNDEFINED
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\ufffe' # 0xFB -> UNDEFINED
|
||||
u'\ufffe' # 0xFC -> UNDEFINED
|
||||
u'\ufffe' # 0xFD -> UNDEFINED
|
||||
u'\ufffe' # 0xFE -> UNDEFINED
|
||||
u'\x9f' # 0xFF -> EIGHT ONES
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp437.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp437.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec cp437 generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp437',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00a2, # CENT SIGN
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00a5, # YEN SIGN
|
||||
0x009e: 0x20a7, # PESETA SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x2310, # REVERSED NOT SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xa2' # 0x009b -> CENT SIGN
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xa5' # 0x009d -> YEN SIGN
|
||||
u'\u20a7' # 0x009e -> PESETA SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\u2310' # 0x00a9 -> REVERSED NOT SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x009b, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a5: 0x009d, # YEN SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x20a7: 0x009e, # PESETA SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2310: 0x00a9, # REVERSED NOT SIGN
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp500.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp500.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp500',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> CONTROL
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> CONTROL
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> CONTROL
|
||||
u'\x8d' # 0x09 -> CONTROL
|
||||
u'\x8e' # 0x0A -> CONTROL
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> CONTROL
|
||||
u'\x85' # 0x15 -> CONTROL
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> CONTROL
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> CONTROL
|
||||
u'\x8f' # 0x1B -> CONTROL
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> CONTROL
|
||||
u'\x81' # 0x21 -> CONTROL
|
||||
u'\x82' # 0x22 -> CONTROL
|
||||
u'\x83' # 0x23 -> CONTROL
|
||||
u'\x84' # 0x24 -> CONTROL
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> CONTROL
|
||||
u'\x89' # 0x29 -> CONTROL
|
||||
u'\x8a' # 0x2A -> CONTROL
|
||||
u'\x8b' # 0x2B -> CONTROL
|
||||
u'\x8c' # 0x2C -> CONTROL
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> CONTROL
|
||||
u'\x91' # 0x31 -> CONTROL
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> CONTROL
|
||||
u'\x94' # 0x34 -> CONTROL
|
||||
u'\x95' # 0x35 -> CONTROL
|
||||
u'\x96' # 0x36 -> CONTROL
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> CONTROL
|
||||
u'\x99' # 0x39 -> CONTROL
|
||||
u'\x9a' # 0x3A -> CONTROL
|
||||
u'\x9b' # 0x3B -> CONTROL
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> CONTROL
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\xa0' # 0x41 -> NO-BREAK SPACE
|
||||
u'\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'[' # 0x4A -> LEFT SQUARE BRACKET
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'!' # 0x4F -> EXCLAMATION MARK
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u']' # 0x5A -> RIGHT SQUARE BRACKET
|
||||
u'$' # 0x5B -> DOLLAR SIGN
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'^' # 0x5F -> CIRCUMFLEX ACCENT
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xa6' # 0x6A -> BROKEN BAR
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'`' # 0x79 -> GRAVE ACCENT
|
||||
u':' # 0x7A -> COLON
|
||||
u'#' # 0x7B -> NUMBER SIGN
|
||||
u'@' # 0x7C -> COMMERCIAL AT
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'"' # 0x7F -> QUOTATION MARK
|
||||
u'\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC)
|
||||
u'\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC)
|
||||
u'\xb1' # 0x8F -> PLUS-MINUS SIGN
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xe6' # 0x9C -> LATIN SMALL LIGATURE AE
|
||||
u'\xb8' # 0x9D -> CEDILLA
|
||||
u'\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xa4' # 0x9F -> CURRENCY SIGN
|
||||
u'\xb5' # 0xA0 -> MICRO SIGN
|
||||
u'~' # 0xA1 -> TILDE
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\xa1' # 0xAA -> INVERTED EXCLAMATION MARK
|
||||
u'\xbf' # 0xAB -> INVERTED QUESTION MARK
|
||||
u'\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC)
|
||||
u'\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC)
|
||||
u'\xae' # 0xAF -> REGISTERED SIGN
|
||||
u'\xa2' # 0xB0 -> CENT SIGN
|
||||
u'\xa3' # 0xB1 -> POUND SIGN
|
||||
u'\xa5' # 0xB2 -> YEN SIGN
|
||||
u'\xb7' # 0xB3 -> MIDDLE DOT
|
||||
u'\xa9' # 0xB4 -> COPYRIGHT SIGN
|
||||
u'\xa7' # 0xB5 -> SECTION SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xac' # 0xBA -> NOT SIGN
|
||||
u'|' # 0xBB -> VERTICAL LINE
|
||||
u'\xaf' # 0xBC -> MACRON
|
||||
u'\xa8' # 0xBD -> DIAERESIS
|
||||
u'\xb4' # 0xBE -> ACUTE ACCENT
|
||||
u'\xd7' # 0xBF -> MULTIPLICATION SIGN
|
||||
u'{' # 0xC0 -> LEFT CURLY BRACKET
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'}' # 0xD0 -> RIGHT CURLY BRACKET
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb9' # 0xDA -> SUPERSCRIPT ONE
|
||||
u'\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\\' # 0xE0 -> REVERSE SOLIDUS
|
||||
u'\xf7' # 0xE1 -> DIVISION SIGN
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\x9f' # 0xFF -> CONTROL
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
309
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp720.py
Normal file
309
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp720.py
Normal file
@@ -0,0 +1,309 @@
|
||||
"""Python Character Mapping Codec cp720 generated on Windows:
|
||||
Vista 6.0.6002 SP2 Multiprocessor Free with the command:
|
||||
python Tools/unicode/genwincodec.py 720
|
||||
"""#"
|
||||
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp720',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> CONTROL CHARACTER
|
||||
u'\x01' # 0x01 -> CONTROL CHARACTER
|
||||
u'\x02' # 0x02 -> CONTROL CHARACTER
|
||||
u'\x03' # 0x03 -> CONTROL CHARACTER
|
||||
u'\x04' # 0x04 -> CONTROL CHARACTER
|
||||
u'\x05' # 0x05 -> CONTROL CHARACTER
|
||||
u'\x06' # 0x06 -> CONTROL CHARACTER
|
||||
u'\x07' # 0x07 -> CONTROL CHARACTER
|
||||
u'\x08' # 0x08 -> CONTROL CHARACTER
|
||||
u'\t' # 0x09 -> CONTROL CHARACTER
|
||||
u'\n' # 0x0A -> CONTROL CHARACTER
|
||||
u'\x0b' # 0x0B -> CONTROL CHARACTER
|
||||
u'\x0c' # 0x0C -> CONTROL CHARACTER
|
||||
u'\r' # 0x0D -> CONTROL CHARACTER
|
||||
u'\x0e' # 0x0E -> CONTROL CHARACTER
|
||||
u'\x0f' # 0x0F -> CONTROL CHARACTER
|
||||
u'\x10' # 0x10 -> CONTROL CHARACTER
|
||||
u'\x11' # 0x11 -> CONTROL CHARACTER
|
||||
u'\x12' # 0x12 -> CONTROL CHARACTER
|
||||
u'\x13' # 0x13 -> CONTROL CHARACTER
|
||||
u'\x14' # 0x14 -> CONTROL CHARACTER
|
||||
u'\x15' # 0x15 -> CONTROL CHARACTER
|
||||
u'\x16' # 0x16 -> CONTROL CHARACTER
|
||||
u'\x17' # 0x17 -> CONTROL CHARACTER
|
||||
u'\x18' # 0x18 -> CONTROL CHARACTER
|
||||
u'\x19' # 0x19 -> CONTROL CHARACTER
|
||||
u'\x1a' # 0x1A -> CONTROL CHARACTER
|
||||
u'\x1b' # 0x1B -> CONTROL CHARACTER
|
||||
u'\x1c' # 0x1C -> CONTROL CHARACTER
|
||||
u'\x1d' # 0x1D -> CONTROL CHARACTER
|
||||
u'\x1e' # 0x1E -> CONTROL CHARACTER
|
||||
u'\x1f' # 0x1F -> CONTROL CHARACTER
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> CONTROL CHARACTER
|
||||
u'\x80'
|
||||
u'\x81'
|
||||
u'\xe9' # 0x82 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x83 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\x84'
|
||||
u'\xe0' # 0x85 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\x86'
|
||||
u'\xe7' # 0x87 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x88 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x89 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x8A -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x8B -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x8C -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\x8d'
|
||||
u'\x8e'
|
||||
u'\x8f'
|
||||
u'\x90'
|
||||
u'\u0651' # 0x91 -> ARABIC SHADDA
|
||||
u'\u0652' # 0x92 -> ARABIC SUKUN
|
||||
u'\xf4' # 0x93 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xa4' # 0x94 -> CURRENCY SIGN
|
||||
u'\u0640' # 0x95 -> ARABIC TATWEEL
|
||||
u'\xfb' # 0x96 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x97 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\u0621' # 0x98 -> ARABIC LETTER HAMZA
|
||||
u'\u0622' # 0x99 -> ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
u'\u0623' # 0x9A -> ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
u'\u0624' # 0x9B -> ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
u'\xa3' # 0x9C -> POUND SIGN
|
||||
u'\u0625' # 0x9D -> ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
u'\u0626' # 0x9E -> ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
u'\u0627' # 0x9F -> ARABIC LETTER ALEF
|
||||
u'\u0628' # 0xA0 -> ARABIC LETTER BEH
|
||||
u'\u0629' # 0xA1 -> ARABIC LETTER TEH MARBUTA
|
||||
u'\u062a' # 0xA2 -> ARABIC LETTER TEH
|
||||
u'\u062b' # 0xA3 -> ARABIC LETTER THEH
|
||||
u'\u062c' # 0xA4 -> ARABIC LETTER JEEM
|
||||
u'\u062d' # 0xA5 -> ARABIC LETTER HAH
|
||||
u'\u062e' # 0xA6 -> ARABIC LETTER KHAH
|
||||
u'\u062f' # 0xA7 -> ARABIC LETTER DAL
|
||||
u'\u0630' # 0xA8 -> ARABIC LETTER THAL
|
||||
u'\u0631' # 0xA9 -> ARABIC LETTER REH
|
||||
u'\u0632' # 0xAA -> ARABIC LETTER ZAIN
|
||||
u'\u0633' # 0xAB -> ARABIC LETTER SEEN
|
||||
u'\u0634' # 0xAC -> ARABIC LETTER SHEEN
|
||||
u'\u0635' # 0xAD -> ARABIC LETTER SAD
|
||||
u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0xB0 -> LIGHT SHADE
|
||||
u'\u2592' # 0xB1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0xB2 -> DARK SHADE
|
||||
u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0xB5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0xB6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0xB8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0xBD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0xBE -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0xC6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0xC7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0xCF -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0xD0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0xD1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0xD2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0xD3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0xD4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0xD5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0xD6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0xD7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0xD8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0xDB -> FULL BLOCK
|
||||
u'\u2584' # 0xDC -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0xDD -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0xDE -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0xDF -> UPPER HALF BLOCK
|
||||
u'\u0636' # 0xE0 -> ARABIC LETTER DAD
|
||||
u'\u0637' # 0xE1 -> ARABIC LETTER TAH
|
||||
u'\u0638' # 0xE2 -> ARABIC LETTER ZAH
|
||||
u'\u0639' # 0xE3 -> ARABIC LETTER AIN
|
||||
u'\u063a' # 0xE4 -> ARABIC LETTER GHAIN
|
||||
u'\u0641' # 0xE5 -> ARABIC LETTER FEH
|
||||
u'\xb5' # 0xE6 -> MICRO SIGN
|
||||
u'\u0642' # 0xE7 -> ARABIC LETTER QAF
|
||||
u'\u0643' # 0xE8 -> ARABIC LETTER KAF
|
||||
u'\u0644' # 0xE9 -> ARABIC LETTER LAM
|
||||
u'\u0645' # 0xEA -> ARABIC LETTER MEEM
|
||||
u'\u0646' # 0xEB -> ARABIC LETTER NOON
|
||||
u'\u0647' # 0xEC -> ARABIC LETTER HEH
|
||||
u'\u0648' # 0xED -> ARABIC LETTER WAW
|
||||
u'\u0649' # 0xEE -> ARABIC LETTER ALEF MAKSURA
|
||||
u'\u064a' # 0xEF -> ARABIC LETTER YEH
|
||||
u'\u2261' # 0xF0 -> IDENTICAL TO
|
||||
u'\u064b' # 0xF1 -> ARABIC FATHATAN
|
||||
u'\u064c' # 0xF2 -> ARABIC DAMMATAN
|
||||
u'\u064d' # 0xF3 -> ARABIC KASRATAN
|
||||
u'\u064e' # 0xF4 -> ARABIC FATHA
|
||||
u'\u064f' # 0xF5 -> ARABIC DAMMA
|
||||
u'\u0650' # 0xF6 -> ARABIC KASRA
|
||||
u'\u2248' # 0xF7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0xF8 -> DEGREE SIGN
|
||||
u'\u2219' # 0xF9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0xFA -> MIDDLE DOT
|
||||
u'\u221a' # 0xFB -> SQUARE ROOT
|
||||
u'\u207f' # 0xFC -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0xFD -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0xFE -> BLACK SQUARE
|
||||
u'\xa0' # 0xFF -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp737.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp737.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec cp737 generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp737',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x0391, # GREEK CAPITAL LETTER ALPHA
|
||||
0x0081: 0x0392, # GREEK CAPITAL LETTER BETA
|
||||
0x0082: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0083: 0x0394, # GREEK CAPITAL LETTER DELTA
|
||||
0x0084: 0x0395, # GREEK CAPITAL LETTER EPSILON
|
||||
0x0085: 0x0396, # GREEK CAPITAL LETTER ZETA
|
||||
0x0086: 0x0397, # GREEK CAPITAL LETTER ETA
|
||||
0x0087: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x0088: 0x0399, # GREEK CAPITAL LETTER IOTA
|
||||
0x0089: 0x039a, # GREEK CAPITAL LETTER KAPPA
|
||||
0x008a: 0x039b, # GREEK CAPITAL LETTER LAMDA
|
||||
0x008b: 0x039c, # GREEK CAPITAL LETTER MU
|
||||
0x008c: 0x039d, # GREEK CAPITAL LETTER NU
|
||||
0x008d: 0x039e, # GREEK CAPITAL LETTER XI
|
||||
0x008e: 0x039f, # GREEK CAPITAL LETTER OMICRON
|
||||
0x008f: 0x03a0, # GREEK CAPITAL LETTER PI
|
||||
0x0090: 0x03a1, # GREEK CAPITAL LETTER RHO
|
||||
0x0091: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x0092: 0x03a4, # GREEK CAPITAL LETTER TAU
|
||||
0x0093: 0x03a5, # GREEK CAPITAL LETTER UPSILON
|
||||
0x0094: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x0095: 0x03a7, # GREEK CAPITAL LETTER CHI
|
||||
0x0096: 0x03a8, # GREEK CAPITAL LETTER PSI
|
||||
0x0097: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x0098: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x0099: 0x03b2, # GREEK SMALL LETTER BETA
|
||||
0x009a: 0x03b3, # GREEK SMALL LETTER GAMMA
|
||||
0x009b: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x009c: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x009d: 0x03b6, # GREEK SMALL LETTER ZETA
|
||||
0x009e: 0x03b7, # GREEK SMALL LETTER ETA
|
||||
0x009f: 0x03b8, # GREEK SMALL LETTER THETA
|
||||
0x00a0: 0x03b9, # GREEK SMALL LETTER IOTA
|
||||
0x00a1: 0x03ba, # GREEK SMALL LETTER KAPPA
|
||||
0x00a2: 0x03bb, # GREEK SMALL LETTER LAMDA
|
||||
0x00a3: 0x03bc, # GREEK SMALL LETTER MU
|
||||
0x00a4: 0x03bd, # GREEK SMALL LETTER NU
|
||||
0x00a5: 0x03be, # GREEK SMALL LETTER XI
|
||||
0x00a6: 0x03bf, # GREEK SMALL LETTER OMICRON
|
||||
0x00a7: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00a8: 0x03c1, # GREEK SMALL LETTER RHO
|
||||
0x00a9: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00aa: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
|
||||
0x00ab: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00ac: 0x03c5, # GREEK SMALL LETTER UPSILON
|
||||
0x00ad: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ae: 0x03c7, # GREEK SMALL LETTER CHI
|
||||
0x00af: 0x03c8, # GREEK SMALL LETTER PSI
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03c9, # GREEK SMALL LETTER OMEGA
|
||||
0x00e1: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0x00e2: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0x00e3: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
|
||||
0x00e4: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0x00e5: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0x00e6: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0x00e7: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0x00e8: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0x00e9: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
0x00ea: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0x00eb: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0x00ec: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0x00ed: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0x00ee: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0x00ef: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0x00f0: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0x00f5: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\u0391' # 0x0080 -> GREEK CAPITAL LETTER ALPHA
|
||||
u'\u0392' # 0x0081 -> GREEK CAPITAL LETTER BETA
|
||||
u'\u0393' # 0x0082 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u0394' # 0x0083 -> GREEK CAPITAL LETTER DELTA
|
||||
u'\u0395' # 0x0084 -> GREEK CAPITAL LETTER EPSILON
|
||||
u'\u0396' # 0x0085 -> GREEK CAPITAL LETTER ZETA
|
||||
u'\u0397' # 0x0086 -> GREEK CAPITAL LETTER ETA
|
||||
u'\u0398' # 0x0087 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u0399' # 0x0088 -> GREEK CAPITAL LETTER IOTA
|
||||
u'\u039a' # 0x0089 -> GREEK CAPITAL LETTER KAPPA
|
||||
u'\u039b' # 0x008a -> GREEK CAPITAL LETTER LAMDA
|
||||
u'\u039c' # 0x008b -> GREEK CAPITAL LETTER MU
|
||||
u'\u039d' # 0x008c -> GREEK CAPITAL LETTER NU
|
||||
u'\u039e' # 0x008d -> GREEK CAPITAL LETTER XI
|
||||
u'\u039f' # 0x008e -> GREEK CAPITAL LETTER OMICRON
|
||||
u'\u03a0' # 0x008f -> GREEK CAPITAL LETTER PI
|
||||
u'\u03a1' # 0x0090 -> GREEK CAPITAL LETTER RHO
|
||||
u'\u03a3' # 0x0091 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03a4' # 0x0092 -> GREEK CAPITAL LETTER TAU
|
||||
u'\u03a5' # 0x0093 -> GREEK CAPITAL LETTER UPSILON
|
||||
u'\u03a6' # 0x0094 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u03a7' # 0x0095 -> GREEK CAPITAL LETTER CHI
|
||||
u'\u03a8' # 0x0096 -> GREEK CAPITAL LETTER PSI
|
||||
u'\u03a9' # 0x0097 -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b1' # 0x0098 -> GREEK SMALL LETTER ALPHA
|
||||
u'\u03b2' # 0x0099 -> GREEK SMALL LETTER BETA
|
||||
u'\u03b3' # 0x009a -> GREEK SMALL LETTER GAMMA
|
||||
u'\u03b4' # 0x009b -> GREEK SMALL LETTER DELTA
|
||||
u'\u03b5' # 0x009c -> GREEK SMALL LETTER EPSILON
|
||||
u'\u03b6' # 0x009d -> GREEK SMALL LETTER ZETA
|
||||
u'\u03b7' # 0x009e -> GREEK SMALL LETTER ETA
|
||||
u'\u03b8' # 0x009f -> GREEK SMALL LETTER THETA
|
||||
u'\u03b9' # 0x00a0 -> GREEK SMALL LETTER IOTA
|
||||
u'\u03ba' # 0x00a1 -> GREEK SMALL LETTER KAPPA
|
||||
u'\u03bb' # 0x00a2 -> GREEK SMALL LETTER LAMDA
|
||||
u'\u03bc' # 0x00a3 -> GREEK SMALL LETTER MU
|
||||
u'\u03bd' # 0x00a4 -> GREEK SMALL LETTER NU
|
||||
u'\u03be' # 0x00a5 -> GREEK SMALL LETTER XI
|
||||
u'\u03bf' # 0x00a6 -> GREEK SMALL LETTER OMICRON
|
||||
u'\u03c0' # 0x00a7 -> GREEK SMALL LETTER PI
|
||||
u'\u03c1' # 0x00a8 -> GREEK SMALL LETTER RHO
|
||||
u'\u03c3' # 0x00a9 -> GREEK SMALL LETTER SIGMA
|
||||
u'\u03c2' # 0x00aa -> GREEK SMALL LETTER FINAL SIGMA
|
||||
u'\u03c4' # 0x00ab -> GREEK SMALL LETTER TAU
|
||||
u'\u03c5' # 0x00ac -> GREEK SMALL LETTER UPSILON
|
||||
u'\u03c6' # 0x00ad -> GREEK SMALL LETTER PHI
|
||||
u'\u03c7' # 0x00ae -> GREEK SMALL LETTER CHI
|
||||
u'\u03c8' # 0x00af -> GREEK SMALL LETTER PSI
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03c9' # 0x00e0 -> GREEK SMALL LETTER OMEGA
|
||||
u'\u03ac' # 0x00e1 -> GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
u'\u03ad' # 0x00e2 -> GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
u'\u03ae' # 0x00e3 -> GREEK SMALL LETTER ETA WITH TONOS
|
||||
u'\u03ca' # 0x00e4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03af' # 0x00e5 -> GREEK SMALL LETTER IOTA WITH TONOS
|
||||
u'\u03cc' # 0x00e6 -> GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
u'\u03cd' # 0x00e7 -> GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
u'\u03cb' # 0x00e8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\u03ce' # 0x00e9 -> GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
u'\u0386' # 0x00ea -> GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
u'\u0388' # 0x00eb -> GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
u'\u0389' # 0x00ec -> GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
u'\u038a' # 0x00ed -> GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
u'\u038c' # 0x00ee -> GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
u'\u038e' # 0x00ef -> GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
u'\u038f' # 0x00f0 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u03aa' # 0x00f4 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03ab' # 0x00f5 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x0386: 0x00ea, # GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0x0388: 0x00eb, # GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0x0389: 0x00ec, # GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0x038a: 0x00ed, # GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0x038c: 0x00ee, # GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0x038e: 0x00ef, # GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0x038f: 0x00f0, # GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0x0391: 0x0080, # GREEK CAPITAL LETTER ALPHA
|
||||
0x0392: 0x0081, # GREEK CAPITAL LETTER BETA
|
||||
0x0393: 0x0082, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0394: 0x0083, # GREEK CAPITAL LETTER DELTA
|
||||
0x0395: 0x0084, # GREEK CAPITAL LETTER EPSILON
|
||||
0x0396: 0x0085, # GREEK CAPITAL LETTER ZETA
|
||||
0x0397: 0x0086, # GREEK CAPITAL LETTER ETA
|
||||
0x0398: 0x0087, # GREEK CAPITAL LETTER THETA
|
||||
0x0399: 0x0088, # GREEK CAPITAL LETTER IOTA
|
||||
0x039a: 0x0089, # GREEK CAPITAL LETTER KAPPA
|
||||
0x039b: 0x008a, # GREEK CAPITAL LETTER LAMDA
|
||||
0x039c: 0x008b, # GREEK CAPITAL LETTER MU
|
||||
0x039d: 0x008c, # GREEK CAPITAL LETTER NU
|
||||
0x039e: 0x008d, # GREEK CAPITAL LETTER XI
|
||||
0x039f: 0x008e, # GREEK CAPITAL LETTER OMICRON
|
||||
0x03a0: 0x008f, # GREEK CAPITAL LETTER PI
|
||||
0x03a1: 0x0090, # GREEK CAPITAL LETTER RHO
|
||||
0x03a3: 0x0091, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a4: 0x0092, # GREEK CAPITAL LETTER TAU
|
||||
0x03a5: 0x0093, # GREEK CAPITAL LETTER UPSILON
|
||||
0x03a6: 0x0094, # GREEK CAPITAL LETTER PHI
|
||||
0x03a7: 0x0095, # GREEK CAPITAL LETTER CHI
|
||||
0x03a8: 0x0096, # GREEK CAPITAL LETTER PSI
|
||||
0x03a9: 0x0097, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03aa: 0x00f4, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0x03ab: 0x00f5, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0x03ac: 0x00e1, # GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0x03ad: 0x00e2, # GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0x03ae: 0x00e3, # GREEK SMALL LETTER ETA WITH TONOS
|
||||
0x03af: 0x00e5, # GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0x03b1: 0x0098, # GREEK SMALL LETTER ALPHA
|
||||
0x03b2: 0x0099, # GREEK SMALL LETTER BETA
|
||||
0x03b3: 0x009a, # GREEK SMALL LETTER GAMMA
|
||||
0x03b4: 0x009b, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x009c, # GREEK SMALL LETTER EPSILON
|
||||
0x03b6: 0x009d, # GREEK SMALL LETTER ZETA
|
||||
0x03b7: 0x009e, # GREEK SMALL LETTER ETA
|
||||
0x03b8: 0x009f, # GREEK SMALL LETTER THETA
|
||||
0x03b9: 0x00a0, # GREEK SMALL LETTER IOTA
|
||||
0x03ba: 0x00a1, # GREEK SMALL LETTER KAPPA
|
||||
0x03bb: 0x00a2, # GREEK SMALL LETTER LAMDA
|
||||
0x03bc: 0x00a3, # GREEK SMALL LETTER MU
|
||||
0x03bd: 0x00a4, # GREEK SMALL LETTER NU
|
||||
0x03be: 0x00a5, # GREEK SMALL LETTER XI
|
||||
0x03bf: 0x00a6, # GREEK SMALL LETTER OMICRON
|
||||
0x03c0: 0x00a7, # GREEK SMALL LETTER PI
|
||||
0x03c1: 0x00a8, # GREEK SMALL LETTER RHO
|
||||
0x03c2: 0x00aa, # GREEK SMALL LETTER FINAL SIGMA
|
||||
0x03c3: 0x00a9, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00ab, # GREEK SMALL LETTER TAU
|
||||
0x03c5: 0x00ac, # GREEK SMALL LETTER UPSILON
|
||||
0x03c6: 0x00ad, # GREEK SMALL LETTER PHI
|
||||
0x03c7: 0x00ae, # GREEK SMALL LETTER CHI
|
||||
0x03c8: 0x00af, # GREEK SMALL LETTER PSI
|
||||
0x03c9: 0x00e0, # GREEK SMALL LETTER OMEGA
|
||||
0x03ca: 0x00e4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0x03cb: 0x00e8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0x03cc: 0x00e6, # GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0x03cd: 0x00e7, # GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0x03ce: 0x00e9, # GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
697
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp775.py
Normal file
697
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp775.py
Normal file
@@ -0,0 +1,697 @@
|
||||
""" Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp775',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x0101, # LATIN SMALL LETTER A WITH MACRON
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x0107, # LATIN SMALL LETTER C WITH ACUTE
|
||||
0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE
|
||||
0x0089: 0x0113, # LATIN SMALL LETTER E WITH MACRON
|
||||
0x008a: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0x008b: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA
|
||||
0x008c: 0x012b, # LATIN SMALL LETTER I WITH MACRON
|
||||
0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x014d, # LATIN SMALL LETTER O WITH MACRON
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0x0096: 0x00a2, # CENT SIGN
|
||||
0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x009f: 0x00a4, # CURRENCY SIGN
|
||||
0x00a0: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON
|
||||
0x00a1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0x00a4: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0x00a5: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0x00a6: 0x201d, # RIGHT DOUBLE QUOTATION MARK
|
||||
0x00a7: 0x00a6, # BROKEN BAR
|
||||
0x00a8: 0x00a9, # COPYRIGHT SIGN
|
||||
0x00a9: 0x00ae, # REGISTERED SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0x00b6: 0x010c, # LATIN CAPITAL LETTER C WITH CARON
|
||||
0x00b7: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0x00b8: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0x00be: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0x00c7: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x00d0: 0x0105, # LATIN SMALL LETTER A WITH OGONEK
|
||||
0x00d1: 0x010d, # LATIN SMALL LETTER C WITH CARON
|
||||
0x00d2: 0x0119, # LATIN SMALL LETTER E WITH OGONEK
|
||||
0x00d3: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0x00d4: 0x012f, # LATIN SMALL LETTER I WITH OGONEK
|
||||
0x00d5: 0x0161, # LATIN SMALL LETTER S WITH CARON
|
||||
0x00d6: 0x0173, # LATIN SMALL LETTER U WITH OGONEK
|
||||
0x00d7: 0x016b, # LATIN SMALL LETTER U WITH MACRON
|
||||
0x00d8: 0x017e, # LATIN SMALL LETTER Z WITH CARON
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
0x00e2: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON
|
||||
0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x0144, # LATIN SMALL LETTER N WITH ACUTE
|
||||
0x00e8: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0x00e9: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA
|
||||
0x00ea: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0x00eb: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA
|
||||
0x00ec: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA
|
||||
0x00ed: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON
|
||||
0x00ee: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0x00ef: 0x2019, # RIGHT SINGLE QUOTATION MARK
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x201c, # LEFT DOUBLE QUOTATION MARK
|
||||
0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00f4: 0x00b6, # PILCROW SIGN
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x201e, # DOUBLE LOW-9 QUOTATION MARK
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x00b9, # SUPERSCRIPT ONE
|
||||
0x00fc: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\u0106' # 0x0080 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u0101' # 0x0083 -> LATIN SMALL LETTER A WITH MACRON
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u0123' # 0x0085 -> LATIN SMALL LETTER G WITH CEDILLA
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\u0107' # 0x0087 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\u0113' # 0x0089 -> LATIN SMALL LETTER E WITH MACRON
|
||||
u'\u0156' # 0x008a -> LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
u'\u0157' # 0x008b -> LATIN SMALL LETTER R WITH CEDILLA
|
||||
u'\u012b' # 0x008c -> LATIN SMALL LETTER I WITH MACRON
|
||||
u'\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\u014d' # 0x0093 -> LATIN SMALL LETTER O WITH MACRON
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\u0122' # 0x0095 -> LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
u'\xa2' # 0x0096 -> CENT SIGN
|
||||
u'\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd7' # 0x009e -> MULTIPLICATION SIGN
|
||||
u'\xa4' # 0x009f -> CURRENCY SIGN
|
||||
u'\u0100' # 0x00a0 -> LATIN CAPITAL LETTER A WITH MACRON
|
||||
u'\u012a' # 0x00a1 -> LATIN CAPITAL LETTER I WITH MACRON
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\u017b' # 0x00a3 -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\u017c' # 0x00a4 -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u017a' # 0x00a5 -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u201d' # 0x00a6 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\xa6' # 0x00a7 -> BROKEN BAR
|
||||
u'\xa9' # 0x00a8 -> COPYRIGHT SIGN
|
||||
u'\xae' # 0x00a9 -> REGISTERED SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\u0141' # 0x00ad -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u0104' # 0x00b5 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u010c' # 0x00b6 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\u0118' # 0x00b7 -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\u0116' # 0x00b8 -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u012e' # 0x00bd -> LATIN CAPITAL LETTER I WITH OGONEK
|
||||
u'\u0160' # 0x00be -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u0172' # 0x00c6 -> LATIN CAPITAL LETTER U WITH OGONEK
|
||||
u'\u016a' # 0x00c7 -> LATIN CAPITAL LETTER U WITH MACRON
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u017d' # 0x00cf -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\u0105' # 0x00d0 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u010d' # 0x00d1 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\u0119' # 0x00d2 -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\u0117' # 0x00d3 -> LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
u'\u012f' # 0x00d4 -> LATIN SMALL LETTER I WITH OGONEK
|
||||
u'\u0161' # 0x00d5 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0173' # 0x00d6 -> LATIN SMALL LETTER U WITH OGONEK
|
||||
u'\u016b' # 0x00d7 -> LATIN SMALL LETTER U WITH MACRON
|
||||
u'\u017e' # 0x00d8 -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u'\u014c' # 0x00e2 -> LATIN CAPITAL LETTER O WITH MACRON
|
||||
u'\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u0144' # 0x00e7 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0136' # 0x00e8 -> LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
u'\u0137' # 0x00e9 -> LATIN SMALL LETTER K WITH CEDILLA
|
||||
u'\u013b' # 0x00ea -> LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
u'\u013c' # 0x00eb -> LATIN SMALL LETTER L WITH CEDILLA
|
||||
u'\u0146' # 0x00ec -> LATIN SMALL LETTER N WITH CEDILLA
|
||||
u'\u0112' # 0x00ed -> LATIN CAPITAL LETTER E WITH MACRON
|
||||
u'\u0145' # 0x00ee -> LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
u'\u2019' # 0x00ef -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u201c' # 0x00f2 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xb6' # 0x00f4 -> PILCROW SIGN
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u201e' # 0x00f7 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\xb9' # 0x00fb -> SUPERSCRIPT ONE
|
||||
u'\xb3' # 0x00fc -> SUPERSCRIPT THREE
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a2: 0x0096, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x009f, # CURRENCY SIGN
|
||||
0x00a6: 0x00a7, # BROKEN BAR
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a9: 0x00a8, # COPYRIGHT SIGN
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00ae: 0x00a9, # REGISTERED SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x00fc, # SUPERSCRIPT THREE
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b6: 0x00f4, # PILCROW SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00b9: 0x00fb, # SUPERSCRIPT ONE
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d7: 0x009e, # MULTIPLICATION SIGN
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0100: 0x00a0, # LATIN CAPITAL LETTER A WITH MACRON
|
||||
0x0101: 0x0083, # LATIN SMALL LETTER A WITH MACRON
|
||||
0x0104: 0x00b5, # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0x0105: 0x00d0, # LATIN SMALL LETTER A WITH OGONEK
|
||||
0x0106: 0x0080, # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0x0107: 0x0087, # LATIN SMALL LETTER C WITH ACUTE
|
||||
0x010c: 0x00b6, # LATIN CAPITAL LETTER C WITH CARON
|
||||
0x010d: 0x00d1, # LATIN SMALL LETTER C WITH CARON
|
||||
0x0112: 0x00ed, # LATIN CAPITAL LETTER E WITH MACRON
|
||||
0x0113: 0x0089, # LATIN SMALL LETTER E WITH MACRON
|
||||
0x0116: 0x00b8, # LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
0x0117: 0x00d3, # LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
0x0118: 0x00b7, # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0x0119: 0x00d2, # LATIN SMALL LETTER E WITH OGONEK
|
||||
0x0122: 0x0095, # LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
0x0123: 0x0085, # LATIN SMALL LETTER G WITH CEDILLA
|
||||
0x012a: 0x00a1, # LATIN CAPITAL LETTER I WITH MACRON
|
||||
0x012b: 0x008c, # LATIN SMALL LETTER I WITH MACRON
|
||||
0x012e: 0x00bd, # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
0x012f: 0x00d4, # LATIN SMALL LETTER I WITH OGONEK
|
||||
0x0136: 0x00e8, # LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
0x0137: 0x00e9, # LATIN SMALL LETTER K WITH CEDILLA
|
||||
0x013b: 0x00ea, # LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
0x013c: 0x00eb, # LATIN SMALL LETTER L WITH CEDILLA
|
||||
0x0141: 0x00ad, # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE
|
||||
0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0x0144: 0x00e7, # LATIN SMALL LETTER N WITH ACUTE
|
||||
0x0145: 0x00ee, # LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
0x0146: 0x00ec, # LATIN SMALL LETTER N WITH CEDILLA
|
||||
0x014c: 0x00e2, # LATIN CAPITAL LETTER O WITH MACRON
|
||||
0x014d: 0x0093, # LATIN SMALL LETTER O WITH MACRON
|
||||
0x0156: 0x008a, # LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
0x0157: 0x008b, # LATIN SMALL LETTER R WITH CEDILLA
|
||||
0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE
|
||||
0x0160: 0x00be, # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x0161: 0x00d5, # LATIN SMALL LETTER S WITH CARON
|
||||
0x016a: 0x00c7, # LATIN CAPITAL LETTER U WITH MACRON
|
||||
0x016b: 0x00d7, # LATIN SMALL LETTER U WITH MACRON
|
||||
0x0172: 0x00c6, # LATIN CAPITAL LETTER U WITH OGONEK
|
||||
0x0173: 0x00d6, # LATIN SMALL LETTER U WITH OGONEK
|
||||
0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0x017a: 0x00a5, # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0x017b: 0x00a3, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0x017c: 0x00a4, # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0x017d: 0x00cf, # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x017e: 0x00d8, # LATIN SMALL LETTER Z WITH CARON
|
||||
0x2019: 0x00ef, # RIGHT SINGLE QUOTATION MARK
|
||||
0x201c: 0x00f2, # LEFT DOUBLE QUOTATION MARK
|
||||
0x201d: 0x00a6, # RIGHT DOUBLE QUOTATION MARK
|
||||
0x201e: 0x00f7, # DOUBLE LOW-9 QUOTATION MARK
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp850.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp850.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP850.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp850',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x00ae, # REGISTERED SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00b8: 0x00a9, # COPYRIGHT SIGN
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x00a2, # CENT SIGN
|
||||
0x00be: 0x00a5, # YEN SIGN
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x00a4, # CURRENCY SIGN
|
||||
0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
|
||||
0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
|
||||
0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I
|
||||
0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x00a6, # BROKEN BAR
|
||||
0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
|
||||
0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
|
||||
0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00ee: 0x00af, # MACRON
|
||||
0x00ef: 0x00b4, # ACUTE ACCENT
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2017, # DOUBLE LOW LINE
|
||||
0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00f4: 0x00b6, # PILCROW SIGN
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x00b8, # CEDILLA
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x00a8, # DIAERESIS
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x00b9, # SUPERSCRIPT ONE
|
||||
0x00fc: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd7' # 0x009e -> MULTIPLICATION SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\xae' # 0x00a9 -> REGISTERED SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xa9' # 0x00b8 -> COPYRIGHT SIGN
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\xa2' # 0x00bd -> CENT SIGN
|
||||
u'\xa5' # 0x00be -> YEN SIGN
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0x00cf -> CURRENCY SIGN
|
||||
u'\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH
|
||||
u'\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH
|
||||
u'\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\u0131' # 0x00d5 -> LATIN SMALL LETTER DOTLESS I
|
||||
u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\xa6' # 0x00dd -> BROKEN BAR
|
||||
u'\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN
|
||||
u'\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN
|
||||
u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xaf' # 0x00ee -> MACRON
|
||||
u'\xb4' # 0x00ef -> ACUTE ACCENT
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2017' # 0x00f2 -> DOUBLE LOW LINE
|
||||
u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xb6' # 0x00f4 -> PILCROW SIGN
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\xb8' # 0x00f7 -> CEDILLA
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\xa8' # 0x00f9 -> DIAERESIS
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\xb9' # 0x00fb -> SUPERSCRIPT ONE
|
||||
u'\xb3' # 0x00fc -> SUPERSCRIPT THREE
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x00bd, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x00cf, # CURRENCY SIGN
|
||||
0x00a5: 0x00be, # YEN SIGN
|
||||
0x00a6: 0x00dd, # BROKEN BAR
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a8: 0x00f9, # DIAERESIS
|
||||
0x00a9: 0x00b8, # COPYRIGHT SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00ae: 0x00a9, # REGISTERED SIGN
|
||||
0x00af: 0x00ee, # MACRON
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x00fc, # SUPERSCRIPT THREE
|
||||
0x00b4: 0x00ef, # ACUTE ACCENT
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b6: 0x00f4, # PILCROW SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00b8: 0x00f7, # CEDILLA
|
||||
0x00b9: 0x00fb, # SUPERSCRIPT ONE
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d7: 0x009e, # MULTIPLICATION SIGN
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f0: 0x00d0, # LATIN SMALL LETTER ETH
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00fe: 0x00e7, # LATIN SMALL LETTER THORN
|
||||
0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0131: 0x00d5, # LATIN SMALL LETTER DOTLESS I
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x2017: 0x00f2, # DOUBLE LOW LINE
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp852.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp852.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP852.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp852',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE
|
||||
0x0086: 0x0107, # LATIN SMALL LETTER C WITH ACUTE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
0x008b: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE
|
||||
0x0092: 0x013a, # LATIN SMALL LETTER L WITH ACUTE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x013d, # LATIN CAPITAL LETTER L WITH CARON
|
||||
0x0096: 0x013e, # LATIN SMALL LETTER L WITH CARON
|
||||
0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x0164, # LATIN CAPITAL LETTER T WITH CARON
|
||||
0x009c: 0x0165, # LATIN SMALL LETTER T WITH CARON
|
||||
0x009d: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0x009e: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x009f: 0x010d, # LATIN SMALL LETTER C WITH CARON
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0x00a5: 0x0105, # LATIN SMALL LETTER A WITH OGONEK
|
||||
0x00a6: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x00a7: 0x017e, # LATIN SMALL LETTER Z WITH CARON
|
||||
0x00a8: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0x00a9: 0x0119, # LATIN SMALL LETTER E WITH OGONEK
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0x00ac: 0x010c, # LATIN CAPITAL LETTER C WITH CARON
|
||||
0x00ad: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00b7: 0x011a, # LATIN CAPITAL LETTER E WITH CARON
|
||||
0x00b8: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0x00be: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x0102, # LATIN CAPITAL LETTER A WITH BREVE
|
||||
0x00c7: 0x0103, # LATIN SMALL LETTER A WITH BREVE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x00a4, # CURRENCY SIGN
|
||||
0x00d0: 0x0111, # LATIN SMALL LETTER D WITH STROKE
|
||||
0x00d1: 0x0110, # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0x00d2: 0x010e, # LATIN CAPITAL LETTER D WITH CARON
|
||||
0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00d4: 0x010f, # LATIN SMALL LETTER D WITH CARON
|
||||
0x00d5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON
|
||||
0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00d8: 0x011b, # LATIN SMALL LETTER E WITH CARON
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x0162, # LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
0x00de: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0x00e4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE
|
||||
0x00e5: 0x0148, # LATIN SMALL LETTER N WITH CARON
|
||||
0x00e6: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x00e7: 0x0161, # LATIN SMALL LETTER S WITH CARON
|
||||
0x00e8: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE
|
||||
0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00ea: 0x0155, # LATIN SMALL LETTER R WITH ACUTE
|
||||
0x00eb: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00ee: 0x0163, # LATIN SMALL LETTER T WITH CEDILLA
|
||||
0x00ef: 0x00b4, # ACUTE ACCENT
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x02dd, # DOUBLE ACUTE ACCENT
|
||||
0x00f2: 0x02db, # OGONEK
|
||||
0x00f3: 0x02c7, # CARON
|
||||
0x00f4: 0x02d8, # BREVE
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x00b8, # CEDILLA
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x00a8, # DIAERESIS
|
||||
0x00fa: 0x02d9, # DOT ABOVE
|
||||
0x00fb: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
0x00fc: 0x0158, # LATIN CAPITAL LETTER R WITH CARON
|
||||
0x00fd: 0x0159, # LATIN SMALL LETTER R WITH CARON
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u016f' # 0x0085 -> LATIN SMALL LETTER U WITH RING ABOVE
|
||||
u'\u0107' # 0x0086 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u0150' # 0x008a -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
u'\u0151' # 0x008b -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\u0106' # 0x008f -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0139' # 0x0091 -> LATIN CAPITAL LETTER L WITH ACUTE
|
||||
u'\u013a' # 0x0092 -> LATIN SMALL LETTER L WITH ACUTE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\u013d' # 0x0095 -> LATIN CAPITAL LETTER L WITH CARON
|
||||
u'\u013e' # 0x0096 -> LATIN SMALL LETTER L WITH CARON
|
||||
u'\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u0164' # 0x009b -> LATIN CAPITAL LETTER T WITH CARON
|
||||
u'\u0165' # 0x009c -> LATIN SMALL LETTER T WITH CARON
|
||||
u'\u0141' # 0x009d -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\xd7' # 0x009e -> MULTIPLICATION SIGN
|
||||
u'\u010d' # 0x009f -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\u0104' # 0x00a4 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u0105' # 0x00a5 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u017d' # 0x00a6 -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\u017e' # 0x00a7 -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u0118' # 0x00a8 -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\u0119' # 0x00a9 -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\u017a' # 0x00ab -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u010c' # 0x00ac -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\u015f' # 0x00ad -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\u011a' # 0x00b7 -> LATIN CAPITAL LETTER E WITH CARON
|
||||
u'\u015e' # 0x00b8 -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u017b' # 0x00bd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\u017c' # 0x00be -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u0102' # 0x00c6 -> LATIN CAPITAL LETTER A WITH BREVE
|
||||
u'\u0103' # 0x00c7 -> LATIN SMALL LETTER A WITH BREVE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0x00cf -> CURRENCY SIGN
|
||||
u'\u0111' # 0x00d0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0110' # 0x00d1 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u010e' # 0x00d2 -> LATIN CAPITAL LETTER D WITH CARON
|
||||
u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u010f' # 0x00d4 -> LATIN SMALL LETTER D WITH CARON
|
||||
u'\u0147' # 0x00d5 -> LATIN CAPITAL LETTER N WITH CARON
|
||||
u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\u011b' # 0x00d8 -> LATIN SMALL LETTER E WITH CARON
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u0162' # 0x00dd -> LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
u'\u016e' # 0x00de -> LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\u0144' # 0x00e4 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0148' # 0x00e5 -> LATIN SMALL LETTER N WITH CARON
|
||||
u'\u0160' # 0x00e6 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u0161' # 0x00e7 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0154' # 0x00e8 -> LATIN CAPITAL LETTER R WITH ACUTE
|
||||
u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\u0155' # 0x00ea -> LATIN SMALL LETTER R WITH ACUTE
|
||||
u'\u0170' # 0x00eb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\u0163' # 0x00ee -> LATIN SMALL LETTER T WITH CEDILLA
|
||||
u'\xb4' # 0x00ef -> ACUTE ACCENT
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\u02dd' # 0x00f1 -> DOUBLE ACUTE ACCENT
|
||||
u'\u02db' # 0x00f2 -> OGONEK
|
||||
u'\u02c7' # 0x00f3 -> CARON
|
||||
u'\u02d8' # 0x00f4 -> BREVE
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\xb8' # 0x00f7 -> CEDILLA
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\xa8' # 0x00f9 -> DIAERESIS
|
||||
u'\u02d9' # 0x00fa -> DOT ABOVE
|
||||
u'\u0171' # 0x00fb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
u'\u0158' # 0x00fc -> LATIN CAPITAL LETTER R WITH CARON
|
||||
u'\u0159' # 0x00fd -> LATIN SMALL LETTER R WITH CARON
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a4: 0x00cf, # CURRENCY SIGN
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a8: 0x00f9, # DIAERESIS
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b4: 0x00ef, # ACUTE ACCENT
|
||||
0x00b8: 0x00f7, # CEDILLA
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d7: 0x009e, # MULTIPLICATION SIGN
|
||||
0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x0102: 0x00c6, # LATIN CAPITAL LETTER A WITH BREVE
|
||||
0x0103: 0x00c7, # LATIN SMALL LETTER A WITH BREVE
|
||||
0x0104: 0x00a4, # LATIN CAPITAL LETTER A WITH OGONEK
|
||||
0x0105: 0x00a5, # LATIN SMALL LETTER A WITH OGONEK
|
||||
0x0106: 0x008f, # LATIN CAPITAL LETTER C WITH ACUTE
|
||||
0x0107: 0x0086, # LATIN SMALL LETTER C WITH ACUTE
|
||||
0x010c: 0x00ac, # LATIN CAPITAL LETTER C WITH CARON
|
||||
0x010d: 0x009f, # LATIN SMALL LETTER C WITH CARON
|
||||
0x010e: 0x00d2, # LATIN CAPITAL LETTER D WITH CARON
|
||||
0x010f: 0x00d4, # LATIN SMALL LETTER D WITH CARON
|
||||
0x0110: 0x00d1, # LATIN CAPITAL LETTER D WITH STROKE
|
||||
0x0111: 0x00d0, # LATIN SMALL LETTER D WITH STROKE
|
||||
0x0118: 0x00a8, # LATIN CAPITAL LETTER E WITH OGONEK
|
||||
0x0119: 0x00a9, # LATIN SMALL LETTER E WITH OGONEK
|
||||
0x011a: 0x00b7, # LATIN CAPITAL LETTER E WITH CARON
|
||||
0x011b: 0x00d8, # LATIN SMALL LETTER E WITH CARON
|
||||
0x0139: 0x0091, # LATIN CAPITAL LETTER L WITH ACUTE
|
||||
0x013a: 0x0092, # LATIN SMALL LETTER L WITH ACUTE
|
||||
0x013d: 0x0095, # LATIN CAPITAL LETTER L WITH CARON
|
||||
0x013e: 0x0096, # LATIN SMALL LETTER L WITH CARON
|
||||
0x0141: 0x009d, # LATIN CAPITAL LETTER L WITH STROKE
|
||||
0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE
|
||||
0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE
|
||||
0x0144: 0x00e4, # LATIN SMALL LETTER N WITH ACUTE
|
||||
0x0147: 0x00d5, # LATIN CAPITAL LETTER N WITH CARON
|
||||
0x0148: 0x00e5, # LATIN SMALL LETTER N WITH CARON
|
||||
0x0150: 0x008a, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
0x0151: 0x008b, # LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
0x0154: 0x00e8, # LATIN CAPITAL LETTER R WITH ACUTE
|
||||
0x0155: 0x00ea, # LATIN SMALL LETTER R WITH ACUTE
|
||||
0x0158: 0x00fc, # LATIN CAPITAL LETTER R WITH CARON
|
||||
0x0159: 0x00fd, # LATIN SMALL LETTER R WITH CARON
|
||||
0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE
|
||||
0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE
|
||||
0x015e: 0x00b8, # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0x015f: 0x00ad, # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0x0160: 0x00e6, # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x0161: 0x00e7, # LATIN SMALL LETTER S WITH CARON
|
||||
0x0162: 0x00dd, # LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
0x0163: 0x00ee, # LATIN SMALL LETTER T WITH CEDILLA
|
||||
0x0164: 0x009b, # LATIN CAPITAL LETTER T WITH CARON
|
||||
0x0165: 0x009c, # LATIN SMALL LETTER T WITH CARON
|
||||
0x016e: 0x00de, # LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
0x016f: 0x0085, # LATIN SMALL LETTER U WITH RING ABOVE
|
||||
0x0170: 0x00eb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
0x0171: 0x00fb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
0x017a: 0x00ab, # LATIN SMALL LETTER Z WITH ACUTE
|
||||
0x017b: 0x00bd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
0x017c: 0x00be, # LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
0x017d: 0x00a6, # LATIN CAPITAL LETTER Z WITH CARON
|
||||
0x017e: 0x00a7, # LATIN SMALL LETTER Z WITH CARON
|
||||
0x02c7: 0x00f3, # CARON
|
||||
0x02d8: 0x00f4, # BREVE
|
||||
0x02d9: 0x00fa, # DOT ABOVE
|
||||
0x02db: 0x00f2, # OGONEK
|
||||
0x02dd: 0x00f1, # DOUBLE ACUTE ACCENT
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp855.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp855.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP855.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp855',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE
|
||||
0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE
|
||||
0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE
|
||||
0x0083: 0x0403, # CYRILLIC CAPITAL LETTER GJE
|
||||
0x0084: 0x0451, # CYRILLIC SMALL LETTER IO
|
||||
0x0085: 0x0401, # CYRILLIC CAPITAL LETTER IO
|
||||
0x0086: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0x0087: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0x0088: 0x0455, # CYRILLIC SMALL LETTER DZE
|
||||
0x0089: 0x0405, # CYRILLIC CAPITAL LETTER DZE
|
||||
0x008a: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0x008b: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0x008c: 0x0457, # CYRILLIC SMALL LETTER YI
|
||||
0x008d: 0x0407, # CYRILLIC CAPITAL LETTER YI
|
||||
0x008e: 0x0458, # CYRILLIC SMALL LETTER JE
|
||||
0x008f: 0x0408, # CYRILLIC CAPITAL LETTER JE
|
||||
0x0090: 0x0459, # CYRILLIC SMALL LETTER LJE
|
||||
0x0091: 0x0409, # CYRILLIC CAPITAL LETTER LJE
|
||||
0x0092: 0x045a, # CYRILLIC SMALL LETTER NJE
|
||||
0x0093: 0x040a, # CYRILLIC CAPITAL LETTER NJE
|
||||
0x0094: 0x045b, # CYRILLIC SMALL LETTER TSHE
|
||||
0x0095: 0x040b, # CYRILLIC CAPITAL LETTER TSHE
|
||||
0x0096: 0x045c, # CYRILLIC SMALL LETTER KJE
|
||||
0x0097: 0x040c, # CYRILLIC CAPITAL LETTER KJE
|
||||
0x0098: 0x045e, # CYRILLIC SMALL LETTER SHORT U
|
||||
0x0099: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U
|
||||
0x009a: 0x045f, # CYRILLIC SMALL LETTER DZHE
|
||||
0x009b: 0x040f, # CYRILLIC CAPITAL LETTER DZHE
|
||||
0x009c: 0x044e, # CYRILLIC SMALL LETTER YU
|
||||
0x009d: 0x042e, # CYRILLIC CAPITAL LETTER YU
|
||||
0x009e: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0x009f: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0x00a0: 0x0430, # CYRILLIC SMALL LETTER A
|
||||
0x00a1: 0x0410, # CYRILLIC CAPITAL LETTER A
|
||||
0x00a2: 0x0431, # CYRILLIC SMALL LETTER BE
|
||||
0x00a3: 0x0411, # CYRILLIC CAPITAL LETTER BE
|
||||
0x00a4: 0x0446, # CYRILLIC SMALL LETTER TSE
|
||||
0x00a5: 0x0426, # CYRILLIC CAPITAL LETTER TSE
|
||||
0x00a6: 0x0434, # CYRILLIC SMALL LETTER DE
|
||||
0x00a7: 0x0414, # CYRILLIC CAPITAL LETTER DE
|
||||
0x00a8: 0x0435, # CYRILLIC SMALL LETTER IE
|
||||
0x00a9: 0x0415, # CYRILLIC CAPITAL LETTER IE
|
||||
0x00aa: 0x0444, # CYRILLIC SMALL LETTER EF
|
||||
0x00ab: 0x0424, # CYRILLIC CAPITAL LETTER EF
|
||||
0x00ac: 0x0433, # CYRILLIC SMALL LETTER GHE
|
||||
0x00ad: 0x0413, # CYRILLIC CAPITAL LETTER GHE
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x0445, # CYRILLIC SMALL LETTER HA
|
||||
0x00b6: 0x0425, # CYRILLIC CAPITAL LETTER HA
|
||||
0x00b7: 0x0438, # CYRILLIC SMALL LETTER I
|
||||
0x00b8: 0x0418, # CYRILLIC CAPITAL LETTER I
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x0439, # CYRILLIC SMALL LETTER SHORT I
|
||||
0x00be: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x043a, # CYRILLIC SMALL LETTER KA
|
||||
0x00c7: 0x041a, # CYRILLIC CAPITAL LETTER KA
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x00a4, # CURRENCY SIGN
|
||||
0x00d0: 0x043b, # CYRILLIC SMALL LETTER EL
|
||||
0x00d1: 0x041b, # CYRILLIC CAPITAL LETTER EL
|
||||
0x00d2: 0x043c, # CYRILLIC SMALL LETTER EM
|
||||
0x00d3: 0x041c, # CYRILLIC CAPITAL LETTER EM
|
||||
0x00d4: 0x043d, # CYRILLIC SMALL LETTER EN
|
||||
0x00d5: 0x041d, # CYRILLIC CAPITAL LETTER EN
|
||||
0x00d6: 0x043e, # CYRILLIC SMALL LETTER O
|
||||
0x00d7: 0x041e, # CYRILLIC CAPITAL LETTER O
|
||||
0x00d8: 0x043f, # CYRILLIC SMALL LETTER PE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x041f, # CYRILLIC CAPITAL LETTER PE
|
||||
0x00de: 0x044f, # CYRILLIC SMALL LETTER YA
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x042f, # CYRILLIC CAPITAL LETTER YA
|
||||
0x00e1: 0x0440, # CYRILLIC SMALL LETTER ER
|
||||
0x00e2: 0x0420, # CYRILLIC CAPITAL LETTER ER
|
||||
0x00e3: 0x0441, # CYRILLIC SMALL LETTER ES
|
||||
0x00e4: 0x0421, # CYRILLIC CAPITAL LETTER ES
|
||||
0x00e5: 0x0442, # CYRILLIC SMALL LETTER TE
|
||||
0x00e6: 0x0422, # CYRILLIC CAPITAL LETTER TE
|
||||
0x00e7: 0x0443, # CYRILLIC SMALL LETTER U
|
||||
0x00e8: 0x0423, # CYRILLIC CAPITAL LETTER U
|
||||
0x00e9: 0x0436, # CYRILLIC SMALL LETTER ZHE
|
||||
0x00ea: 0x0416, # CYRILLIC CAPITAL LETTER ZHE
|
||||
0x00eb: 0x0432, # CYRILLIC SMALL LETTER VE
|
||||
0x00ec: 0x0412, # CYRILLIC CAPITAL LETTER VE
|
||||
0x00ed: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0x00ee: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0x00ef: 0x2116, # NUMERO SIGN
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x044b, # CYRILLIC SMALL LETTER YERU
|
||||
0x00f2: 0x042b, # CYRILLIC CAPITAL LETTER YERU
|
||||
0x00f3: 0x0437, # CYRILLIC SMALL LETTER ZE
|
||||
0x00f4: 0x0417, # CYRILLIC CAPITAL LETTER ZE
|
||||
0x00f5: 0x0448, # CYRILLIC SMALL LETTER SHA
|
||||
0x00f6: 0x0428, # CYRILLIC CAPITAL LETTER SHA
|
||||
0x00f7: 0x044d, # CYRILLIC SMALL LETTER E
|
||||
0x00f8: 0x042d, # CYRILLIC CAPITAL LETTER E
|
||||
0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA
|
||||
0x00fa: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0x00fb: 0x0447, # CYRILLIC SMALL LETTER CHE
|
||||
0x00fc: 0x0427, # CYRILLIC CAPITAL LETTER CHE
|
||||
0x00fd: 0x00a7, # SECTION SIGN
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\u0452' # 0x0080 -> CYRILLIC SMALL LETTER DJE
|
||||
u'\u0402' # 0x0081 -> CYRILLIC CAPITAL LETTER DJE
|
||||
u'\u0453' # 0x0082 -> CYRILLIC SMALL LETTER GJE
|
||||
u'\u0403' # 0x0083 -> CYRILLIC CAPITAL LETTER GJE
|
||||
u'\u0451' # 0x0084 -> CYRILLIC SMALL LETTER IO
|
||||
u'\u0401' # 0x0085 -> CYRILLIC CAPITAL LETTER IO
|
||||
u'\u0454' # 0x0086 -> CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
u'\u0404' # 0x0087 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
u'\u0455' # 0x0088 -> CYRILLIC SMALL LETTER DZE
|
||||
u'\u0405' # 0x0089 -> CYRILLIC CAPITAL LETTER DZE
|
||||
u'\u0456' # 0x008a -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0406' # 0x008b -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0457' # 0x008c -> CYRILLIC SMALL LETTER YI
|
||||
u'\u0407' # 0x008d -> CYRILLIC CAPITAL LETTER YI
|
||||
u'\u0458' # 0x008e -> CYRILLIC SMALL LETTER JE
|
||||
u'\u0408' # 0x008f -> CYRILLIC CAPITAL LETTER JE
|
||||
u'\u0459' # 0x0090 -> CYRILLIC SMALL LETTER LJE
|
||||
u'\u0409' # 0x0091 -> CYRILLIC CAPITAL LETTER LJE
|
||||
u'\u045a' # 0x0092 -> CYRILLIC SMALL LETTER NJE
|
||||
u'\u040a' # 0x0093 -> CYRILLIC CAPITAL LETTER NJE
|
||||
u'\u045b' # 0x0094 -> CYRILLIC SMALL LETTER TSHE
|
||||
u'\u040b' # 0x0095 -> CYRILLIC CAPITAL LETTER TSHE
|
||||
u'\u045c' # 0x0096 -> CYRILLIC SMALL LETTER KJE
|
||||
u'\u040c' # 0x0097 -> CYRILLIC CAPITAL LETTER KJE
|
||||
u'\u045e' # 0x0098 -> CYRILLIC SMALL LETTER SHORT U
|
||||
u'\u040e' # 0x0099 -> CYRILLIC CAPITAL LETTER SHORT U
|
||||
u'\u045f' # 0x009a -> CYRILLIC SMALL LETTER DZHE
|
||||
u'\u040f' # 0x009b -> CYRILLIC CAPITAL LETTER DZHE
|
||||
u'\u044e' # 0x009c -> CYRILLIC SMALL LETTER YU
|
||||
u'\u042e' # 0x009d -> CYRILLIC CAPITAL LETTER YU
|
||||
u'\u044a' # 0x009e -> CYRILLIC SMALL LETTER HARD SIGN
|
||||
u'\u042a' # 0x009f -> CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
u'\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A
|
||||
u'\u0410' # 0x00a1 -> CYRILLIC CAPITAL LETTER A
|
||||
u'\u0431' # 0x00a2 -> CYRILLIC SMALL LETTER BE
|
||||
u'\u0411' # 0x00a3 -> CYRILLIC CAPITAL LETTER BE
|
||||
u'\u0446' # 0x00a4 -> CYRILLIC SMALL LETTER TSE
|
||||
u'\u0426' # 0x00a5 -> CYRILLIC CAPITAL LETTER TSE
|
||||
u'\u0434' # 0x00a6 -> CYRILLIC SMALL LETTER DE
|
||||
u'\u0414' # 0x00a7 -> CYRILLIC CAPITAL LETTER DE
|
||||
u'\u0435' # 0x00a8 -> CYRILLIC SMALL LETTER IE
|
||||
u'\u0415' # 0x00a9 -> CYRILLIC CAPITAL LETTER IE
|
||||
u'\u0444' # 0x00aa -> CYRILLIC SMALL LETTER EF
|
||||
u'\u0424' # 0x00ab -> CYRILLIC CAPITAL LETTER EF
|
||||
u'\u0433' # 0x00ac -> CYRILLIC SMALL LETTER GHE
|
||||
u'\u0413' # 0x00ad -> CYRILLIC CAPITAL LETTER GHE
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u0445' # 0x00b5 -> CYRILLIC SMALL LETTER HA
|
||||
u'\u0425' # 0x00b6 -> CYRILLIC CAPITAL LETTER HA
|
||||
u'\u0438' # 0x00b7 -> CYRILLIC SMALL LETTER I
|
||||
u'\u0418' # 0x00b8 -> CYRILLIC CAPITAL LETTER I
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u0439' # 0x00bd -> CYRILLIC SMALL LETTER SHORT I
|
||||
u'\u0419' # 0x00be -> CYRILLIC CAPITAL LETTER SHORT I
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u043a' # 0x00c6 -> CYRILLIC SMALL LETTER KA
|
||||
u'\u041a' # 0x00c7 -> CYRILLIC CAPITAL LETTER KA
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0x00cf -> CURRENCY SIGN
|
||||
u'\u043b' # 0x00d0 -> CYRILLIC SMALL LETTER EL
|
||||
u'\u041b' # 0x00d1 -> CYRILLIC CAPITAL LETTER EL
|
||||
u'\u043c' # 0x00d2 -> CYRILLIC SMALL LETTER EM
|
||||
u'\u041c' # 0x00d3 -> CYRILLIC CAPITAL LETTER EM
|
||||
u'\u043d' # 0x00d4 -> CYRILLIC SMALL LETTER EN
|
||||
u'\u041d' # 0x00d5 -> CYRILLIC CAPITAL LETTER EN
|
||||
u'\u043e' # 0x00d6 -> CYRILLIC SMALL LETTER O
|
||||
u'\u041e' # 0x00d7 -> CYRILLIC CAPITAL LETTER O
|
||||
u'\u043f' # 0x00d8 -> CYRILLIC SMALL LETTER PE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u041f' # 0x00dd -> CYRILLIC CAPITAL LETTER PE
|
||||
u'\u044f' # 0x00de -> CYRILLIC SMALL LETTER YA
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u042f' # 0x00e0 -> CYRILLIC CAPITAL LETTER YA
|
||||
u'\u0440' # 0x00e1 -> CYRILLIC SMALL LETTER ER
|
||||
u'\u0420' # 0x00e2 -> CYRILLIC CAPITAL LETTER ER
|
||||
u'\u0441' # 0x00e3 -> CYRILLIC SMALL LETTER ES
|
||||
u'\u0421' # 0x00e4 -> CYRILLIC CAPITAL LETTER ES
|
||||
u'\u0442' # 0x00e5 -> CYRILLIC SMALL LETTER TE
|
||||
u'\u0422' # 0x00e6 -> CYRILLIC CAPITAL LETTER TE
|
||||
u'\u0443' # 0x00e7 -> CYRILLIC SMALL LETTER U
|
||||
u'\u0423' # 0x00e8 -> CYRILLIC CAPITAL LETTER U
|
||||
u'\u0436' # 0x00e9 -> CYRILLIC SMALL LETTER ZHE
|
||||
u'\u0416' # 0x00ea -> CYRILLIC CAPITAL LETTER ZHE
|
||||
u'\u0432' # 0x00eb -> CYRILLIC SMALL LETTER VE
|
||||
u'\u0412' # 0x00ec -> CYRILLIC CAPITAL LETTER VE
|
||||
u'\u044c' # 0x00ed -> CYRILLIC SMALL LETTER SOFT SIGN
|
||||
u'\u042c' # 0x00ee -> CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
u'\u2116' # 0x00ef -> NUMERO SIGN
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\u044b' # 0x00f1 -> CYRILLIC SMALL LETTER YERU
|
||||
u'\u042b' # 0x00f2 -> CYRILLIC CAPITAL LETTER YERU
|
||||
u'\u0437' # 0x00f3 -> CYRILLIC SMALL LETTER ZE
|
||||
u'\u0417' # 0x00f4 -> CYRILLIC CAPITAL LETTER ZE
|
||||
u'\u0448' # 0x00f5 -> CYRILLIC SMALL LETTER SHA
|
||||
u'\u0428' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHA
|
||||
u'\u044d' # 0x00f7 -> CYRILLIC SMALL LETTER E
|
||||
u'\u042d' # 0x00f8 -> CYRILLIC CAPITAL LETTER E
|
||||
u'\u0449' # 0x00f9 -> CYRILLIC SMALL LETTER SHCHA
|
||||
u'\u0429' # 0x00fa -> CYRILLIC CAPITAL LETTER SHCHA
|
||||
u'\u0447' # 0x00fb -> CYRILLIC SMALL LETTER CHE
|
||||
u'\u0427' # 0x00fc -> CYRILLIC CAPITAL LETTER CHE
|
||||
u'\xa7' # 0x00fd -> SECTION SIGN
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a4: 0x00cf, # CURRENCY SIGN
|
||||
0x00a7: 0x00fd, # SECTION SIGN
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x0401: 0x0085, # CYRILLIC CAPITAL LETTER IO
|
||||
0x0402: 0x0081, # CYRILLIC CAPITAL LETTER DJE
|
||||
0x0403: 0x0083, # CYRILLIC CAPITAL LETTER GJE
|
||||
0x0404: 0x0087, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0x0405: 0x0089, # CYRILLIC CAPITAL LETTER DZE
|
||||
0x0406: 0x008b, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0x0407: 0x008d, # CYRILLIC CAPITAL LETTER YI
|
||||
0x0408: 0x008f, # CYRILLIC CAPITAL LETTER JE
|
||||
0x0409: 0x0091, # CYRILLIC CAPITAL LETTER LJE
|
||||
0x040a: 0x0093, # CYRILLIC CAPITAL LETTER NJE
|
||||
0x040b: 0x0095, # CYRILLIC CAPITAL LETTER TSHE
|
||||
0x040c: 0x0097, # CYRILLIC CAPITAL LETTER KJE
|
||||
0x040e: 0x0099, # CYRILLIC CAPITAL LETTER SHORT U
|
||||
0x040f: 0x009b, # CYRILLIC CAPITAL LETTER DZHE
|
||||
0x0410: 0x00a1, # CYRILLIC CAPITAL LETTER A
|
||||
0x0411: 0x00a3, # CYRILLIC CAPITAL LETTER BE
|
||||
0x0412: 0x00ec, # CYRILLIC CAPITAL LETTER VE
|
||||
0x0413: 0x00ad, # CYRILLIC CAPITAL LETTER GHE
|
||||
0x0414: 0x00a7, # CYRILLIC CAPITAL LETTER DE
|
||||
0x0415: 0x00a9, # CYRILLIC CAPITAL LETTER IE
|
||||
0x0416: 0x00ea, # CYRILLIC CAPITAL LETTER ZHE
|
||||
0x0417: 0x00f4, # CYRILLIC CAPITAL LETTER ZE
|
||||
0x0418: 0x00b8, # CYRILLIC CAPITAL LETTER I
|
||||
0x0419: 0x00be, # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0x041a: 0x00c7, # CYRILLIC CAPITAL LETTER KA
|
||||
0x041b: 0x00d1, # CYRILLIC CAPITAL LETTER EL
|
||||
0x041c: 0x00d3, # CYRILLIC CAPITAL LETTER EM
|
||||
0x041d: 0x00d5, # CYRILLIC CAPITAL LETTER EN
|
||||
0x041e: 0x00d7, # CYRILLIC CAPITAL LETTER O
|
||||
0x041f: 0x00dd, # CYRILLIC CAPITAL LETTER PE
|
||||
0x0420: 0x00e2, # CYRILLIC CAPITAL LETTER ER
|
||||
0x0421: 0x00e4, # CYRILLIC CAPITAL LETTER ES
|
||||
0x0422: 0x00e6, # CYRILLIC CAPITAL LETTER TE
|
||||
0x0423: 0x00e8, # CYRILLIC CAPITAL LETTER U
|
||||
0x0424: 0x00ab, # CYRILLIC CAPITAL LETTER EF
|
||||
0x0425: 0x00b6, # CYRILLIC CAPITAL LETTER HA
|
||||
0x0426: 0x00a5, # CYRILLIC CAPITAL LETTER TSE
|
||||
0x0427: 0x00fc, # CYRILLIC CAPITAL LETTER CHE
|
||||
0x0428: 0x00f6, # CYRILLIC CAPITAL LETTER SHA
|
||||
0x0429: 0x00fa, # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0x042a: 0x009f, # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0x042b: 0x00f2, # CYRILLIC CAPITAL LETTER YERU
|
||||
0x042c: 0x00ee, # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0x042d: 0x00f8, # CYRILLIC CAPITAL LETTER E
|
||||
0x042e: 0x009d, # CYRILLIC CAPITAL LETTER YU
|
||||
0x042f: 0x00e0, # CYRILLIC CAPITAL LETTER YA
|
||||
0x0430: 0x00a0, # CYRILLIC SMALL LETTER A
|
||||
0x0431: 0x00a2, # CYRILLIC SMALL LETTER BE
|
||||
0x0432: 0x00eb, # CYRILLIC SMALL LETTER VE
|
||||
0x0433: 0x00ac, # CYRILLIC SMALL LETTER GHE
|
||||
0x0434: 0x00a6, # CYRILLIC SMALL LETTER DE
|
||||
0x0435: 0x00a8, # CYRILLIC SMALL LETTER IE
|
||||
0x0436: 0x00e9, # CYRILLIC SMALL LETTER ZHE
|
||||
0x0437: 0x00f3, # CYRILLIC SMALL LETTER ZE
|
||||
0x0438: 0x00b7, # CYRILLIC SMALL LETTER I
|
||||
0x0439: 0x00bd, # CYRILLIC SMALL LETTER SHORT I
|
||||
0x043a: 0x00c6, # CYRILLIC SMALL LETTER KA
|
||||
0x043b: 0x00d0, # CYRILLIC SMALL LETTER EL
|
||||
0x043c: 0x00d2, # CYRILLIC SMALL LETTER EM
|
||||
0x043d: 0x00d4, # CYRILLIC SMALL LETTER EN
|
||||
0x043e: 0x00d6, # CYRILLIC SMALL LETTER O
|
||||
0x043f: 0x00d8, # CYRILLIC SMALL LETTER PE
|
||||
0x0440: 0x00e1, # CYRILLIC SMALL LETTER ER
|
||||
0x0441: 0x00e3, # CYRILLIC SMALL LETTER ES
|
||||
0x0442: 0x00e5, # CYRILLIC SMALL LETTER TE
|
||||
0x0443: 0x00e7, # CYRILLIC SMALL LETTER U
|
||||
0x0444: 0x00aa, # CYRILLIC SMALL LETTER EF
|
||||
0x0445: 0x00b5, # CYRILLIC SMALL LETTER HA
|
||||
0x0446: 0x00a4, # CYRILLIC SMALL LETTER TSE
|
||||
0x0447: 0x00fb, # CYRILLIC SMALL LETTER CHE
|
||||
0x0448: 0x00f5, # CYRILLIC SMALL LETTER SHA
|
||||
0x0449: 0x00f9, # CYRILLIC SMALL LETTER SHCHA
|
||||
0x044a: 0x009e, # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0x044b: 0x00f1, # CYRILLIC SMALL LETTER YERU
|
||||
0x044c: 0x00ed, # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0x044d: 0x00f7, # CYRILLIC SMALL LETTER E
|
||||
0x044e: 0x009c, # CYRILLIC SMALL LETTER YU
|
||||
0x044f: 0x00de, # CYRILLIC SMALL LETTER YA
|
||||
0x0451: 0x0084, # CYRILLIC SMALL LETTER IO
|
||||
0x0452: 0x0080, # CYRILLIC SMALL LETTER DJE
|
||||
0x0453: 0x0082, # CYRILLIC SMALL LETTER GJE
|
||||
0x0454: 0x0086, # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0x0455: 0x0088, # CYRILLIC SMALL LETTER DZE
|
||||
0x0456: 0x008a, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
0x0457: 0x008c, # CYRILLIC SMALL LETTER YI
|
||||
0x0458: 0x008e, # CYRILLIC SMALL LETTER JE
|
||||
0x0459: 0x0090, # CYRILLIC SMALL LETTER LJE
|
||||
0x045a: 0x0092, # CYRILLIC SMALL LETTER NJE
|
||||
0x045b: 0x0094, # CYRILLIC SMALL LETTER TSHE
|
||||
0x045c: 0x0096, # CYRILLIC SMALL LETTER KJE
|
||||
0x045e: 0x0098, # CYRILLIC SMALL LETTER SHORT U
|
||||
0x045f: 0x009a, # CYRILLIC SMALL LETTER DZHE
|
||||
0x2116: 0x00ef, # NUMERO SIGN
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp856.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp856.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp856',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u05d0' # 0x80 -> HEBREW LETTER ALEF
|
||||
u'\u05d1' # 0x81 -> HEBREW LETTER BET
|
||||
u'\u05d2' # 0x82 -> HEBREW LETTER GIMEL
|
||||
u'\u05d3' # 0x83 -> HEBREW LETTER DALET
|
||||
u'\u05d4' # 0x84 -> HEBREW LETTER HE
|
||||
u'\u05d5' # 0x85 -> HEBREW LETTER VAV
|
||||
u'\u05d6' # 0x86 -> HEBREW LETTER ZAYIN
|
||||
u'\u05d7' # 0x87 -> HEBREW LETTER HET
|
||||
u'\u05d8' # 0x88 -> HEBREW LETTER TET
|
||||
u'\u05d9' # 0x89 -> HEBREW LETTER YOD
|
||||
u'\u05da' # 0x8A -> HEBREW LETTER FINAL KAF
|
||||
u'\u05db' # 0x8B -> HEBREW LETTER KAF
|
||||
u'\u05dc' # 0x8C -> HEBREW LETTER LAMED
|
||||
u'\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM
|
||||
u'\u05de' # 0x8E -> HEBREW LETTER MEM
|
||||
u'\u05df' # 0x8F -> HEBREW LETTER FINAL NUN
|
||||
u'\u05e0' # 0x90 -> HEBREW LETTER NUN
|
||||
u'\u05e1' # 0x91 -> HEBREW LETTER SAMEKH
|
||||
u'\u05e2' # 0x92 -> HEBREW LETTER AYIN
|
||||
u'\u05e3' # 0x93 -> HEBREW LETTER FINAL PE
|
||||
u'\u05e4' # 0x94 -> HEBREW LETTER PE
|
||||
u'\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI
|
||||
u'\u05e6' # 0x96 -> HEBREW LETTER TSADI
|
||||
u'\u05e7' # 0x97 -> HEBREW LETTER QOF
|
||||
u'\u05e8' # 0x98 -> HEBREW LETTER RESH
|
||||
u'\u05e9' # 0x99 -> HEBREW LETTER SHIN
|
||||
u'\u05ea' # 0x9A -> HEBREW LETTER TAV
|
||||
u'\ufffe' # 0x9B -> UNDEFINED
|
||||
u'\xa3' # 0x9C -> POUND SIGN
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\xd7' # 0x9E -> MULTIPLICATION SIGN
|
||||
u'\ufffe' # 0x9F -> UNDEFINED
|
||||
u'\ufffe' # 0xA0 -> UNDEFINED
|
||||
u'\ufffe' # 0xA1 -> UNDEFINED
|
||||
u'\ufffe' # 0xA2 -> UNDEFINED
|
||||
u'\ufffe' # 0xA3 -> UNDEFINED
|
||||
u'\ufffe' # 0xA4 -> UNDEFINED
|
||||
u'\ufffe' # 0xA5 -> UNDEFINED
|
||||
u'\ufffe' # 0xA6 -> UNDEFINED
|
||||
u'\ufffe' # 0xA7 -> UNDEFINED
|
||||
u'\ufffe' # 0xA8 -> UNDEFINED
|
||||
u'\xae' # 0xA9 -> REGISTERED SIGN
|
||||
u'\xac' # 0xAA -> NOT SIGN
|
||||
u'\xbd' # 0xAB -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\ufffe' # 0xAD -> UNDEFINED
|
||||
u'\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0xB0 -> LIGHT SHADE
|
||||
u'\u2592' # 0xB1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0xB2 -> DARK SHADE
|
||||
u'\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\ufffe' # 0xB5 -> UNDEFINED
|
||||
u'\ufffe' # 0xB6 -> UNDEFINED
|
||||
u'\ufffe' # 0xB7 -> UNDEFINED
|
||||
u'\xa9' # 0xB8 -> COPYRIGHT SIGN
|
||||
u'\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\xa2' # 0xBD -> CENT SIGN
|
||||
u'\xa5' # 0xBE -> YEN SIGN
|
||||
u'\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\ufffe' # 0xC6 -> UNDEFINED
|
||||
u'\ufffe' # 0xC7 -> UNDEFINED
|
||||
u'\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0xCF -> CURRENCY SIGN
|
||||
u'\ufffe' # 0xD0 -> UNDEFINED
|
||||
u'\ufffe' # 0xD1 -> UNDEFINED
|
||||
u'\ufffe' # 0xD2 -> UNDEFINED
|
||||
u'\ufffe' # 0xD3 -> UNDEFINEDS
|
||||
u'\ufffe' # 0xD4 -> UNDEFINED
|
||||
u'\ufffe' # 0xD5 -> UNDEFINED
|
||||
u'\ufffe' # 0xD6 -> UNDEFINEDE
|
||||
u'\ufffe' # 0xD7 -> UNDEFINED
|
||||
u'\ufffe' # 0xD8 -> UNDEFINED
|
||||
u'\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0xDB -> FULL BLOCK
|
||||
u'\u2584' # 0xDC -> LOWER HALF BLOCK
|
||||
u'\xa6' # 0xDD -> BROKEN BAR
|
||||
u'\ufffe' # 0xDE -> UNDEFINED
|
||||
u'\u2580' # 0xDF -> UPPER HALF BLOCK
|
||||
u'\ufffe' # 0xE0 -> UNDEFINED
|
||||
u'\ufffe' # 0xE1 -> UNDEFINED
|
||||
u'\ufffe' # 0xE2 -> UNDEFINED
|
||||
u'\ufffe' # 0xE3 -> UNDEFINED
|
||||
u'\ufffe' # 0xE4 -> UNDEFINED
|
||||
u'\ufffe' # 0xE5 -> UNDEFINED
|
||||
u'\xb5' # 0xE6 -> MICRO SIGN
|
||||
u'\ufffe' # 0xE7 -> UNDEFINED
|
||||
u'\ufffe' # 0xE8 -> UNDEFINED
|
||||
u'\ufffe' # 0xE9 -> UNDEFINED
|
||||
u'\ufffe' # 0xEA -> UNDEFINED
|
||||
u'\ufffe' # 0xEB -> UNDEFINED
|
||||
u'\ufffe' # 0xEC -> UNDEFINED
|
||||
u'\ufffe' # 0xED -> UNDEFINED
|
||||
u'\xaf' # 0xEE -> MACRON
|
||||
u'\xb4' # 0xEF -> ACUTE ACCENT
|
||||
u'\xad' # 0xF0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0xF1 -> PLUS-MINUS SIGN
|
||||
u'\u2017' # 0xF2 -> DOUBLE LOW LINE
|
||||
u'\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xb6' # 0xF4 -> PILCROW SIGN
|
||||
u'\xa7' # 0xF5 -> SECTION SIGN
|
||||
u'\xf7' # 0xF6 -> DIVISION SIGN
|
||||
u'\xb8' # 0xF7 -> CEDILLA
|
||||
u'\xb0' # 0xF8 -> DEGREE SIGN
|
||||
u'\xa8' # 0xF9 -> DIAERESIS
|
||||
u'\xb7' # 0xFA -> MIDDLE DOT
|
||||
u'\xb9' # 0xFB -> SUPERSCRIPT ONE
|
||||
u'\xb3' # 0xFC -> SUPERSCRIPT THREE
|
||||
u'\xb2' # 0xFD -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0xFE -> BLACK SQUARE
|
||||
u'\xa0' # 0xFF -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
694
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp857.py
Normal file
694
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp857.py
Normal file
@@ -0,0 +1,694 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP857.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp857',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x0131, # LATIN SMALL LETTER DOTLESS I
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0x009f: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE
|
||||
0x00a7: 0x011f, # LATIN SMALL LETTER G WITH BREVE
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x00ae, # REGISTERED SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00b8: 0x00a9, # COPYRIGHT SIGN
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x00a2, # CENT SIGN
|
||||
0x00be: 0x00a5, # YEN SIGN
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x00a4, # CURRENCY SIGN
|
||||
0x00d0: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00d1: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00d5: None, # UNDEFINED
|
||||
0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x00a6, # BROKEN BAR
|
||||
0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: None, # UNDEFINED
|
||||
0x00e8: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00ed: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x00ee: 0x00af, # MACRON
|
||||
0x00ef: 0x00b4, # ACUTE ACCENT
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: None, # UNDEFINED
|
||||
0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00f4: 0x00b6, # PILCROW SIGN
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x00b8, # CEDILLA
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x00a8, # DIAERESIS
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x00b9, # SUPERSCRIPT ONE
|
||||
0x00fc: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u0131' # 0x008d -> LATIN SMALL LETTER DOTLESS I
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\u0130' # 0x0098 -> LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\u015e' # 0x009e -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\u015f' # 0x009f -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\u011e' # 0x00a6 -> LATIN CAPITAL LETTER G WITH BREVE
|
||||
u'\u011f' # 0x00a7 -> LATIN SMALL LETTER G WITH BREVE
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\xae' # 0x00a9 -> REGISTERED SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xa9' # 0x00b8 -> COPYRIGHT SIGN
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\xa2' # 0x00bd -> CENT SIGN
|
||||
u'\xa5' # 0x00be -> YEN SIGN
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0x00cf -> CURRENCY SIGN
|
||||
u'\xba' # 0x00d0 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xaa' # 0x00d1 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\ufffe' # 0x00d5 -> UNDEFINED
|
||||
u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\xa6' # 0x00dd -> BROKEN BAR
|
||||
u'\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\ufffe' # 0x00e7 -> UNDEFINED
|
||||
u'\xd7' # 0x00e8 -> MULTIPLICATION SIGN
|
||||
u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xec' # 0x00ec -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xff' # 0x00ed -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xaf' # 0x00ee -> MACRON
|
||||
u'\xb4' # 0x00ef -> ACUTE ACCENT
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\ufffe' # 0x00f2 -> UNDEFINED
|
||||
u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xb6' # 0x00f4 -> PILCROW SIGN
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\xb8' # 0x00f7 -> CEDILLA
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\xa8' # 0x00f9 -> DIAERESIS
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\xb9' # 0x00fb -> SUPERSCRIPT ONE
|
||||
u'\xb3' # 0x00fc -> SUPERSCRIPT THREE
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x00bd, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x00cf, # CURRENCY SIGN
|
||||
0x00a5: 0x00be, # YEN SIGN
|
||||
0x00a6: 0x00dd, # BROKEN BAR
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a8: 0x00f9, # DIAERESIS
|
||||
0x00a9: 0x00b8, # COPYRIGHT SIGN
|
||||
0x00aa: 0x00d1, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00ae: 0x00a9, # REGISTERED SIGN
|
||||
0x00af: 0x00ee, # MACRON
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x00fc, # SUPERSCRIPT THREE
|
||||
0x00b4: 0x00ef, # ACUTE ACCENT
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b6: 0x00f4, # PILCROW SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00b8: 0x00f7, # CEDILLA
|
||||
0x00b9: 0x00fb, # SUPERSCRIPT ONE
|
||||
0x00ba: 0x00d0, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d7: 0x00e8, # MULTIPLICATION SIGN
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ec: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00ff: 0x00ed, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x011e: 0x00a6, # LATIN CAPITAL LETTER G WITH BREVE
|
||||
0x011f: 0x00a7, # LATIN SMALL LETTER G WITH BREVE
|
||||
0x0130: 0x0098, # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0x0131: 0x008d, # LATIN SMALL LETTER DOTLESS I
|
||||
0x015e: 0x009e, # LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
0x015f: 0x009f, # LATIN SMALL LETTER S WITH CEDILLA
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp858.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp858.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec for CP858, modified from cp850.
|
||||
|
||||
"""
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp858',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x00ae, # REGISTERED SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00b8: 0x00a9, # COPYRIGHT SIGN
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x00a2, # CENT SIGN
|
||||
0x00be: 0x00a5, # YEN SIGN
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x00a4, # CURRENCY SIGN
|
||||
0x00d0: 0x00f0, # LATIN SMALL LETTER ETH
|
||||
0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH
|
||||
0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00d5: 0x20ac, # EURO SIGN
|
||||
0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x00a6, # BROKEN BAR
|
||||
0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x00fe, # LATIN SMALL LETTER THORN
|
||||
0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN
|
||||
0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00ee: 0x00af, # MACRON
|
||||
0x00ef: 0x00b4, # ACUTE ACCENT
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2017, # DOUBLE LOW LINE
|
||||
0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00f4: 0x00b6, # PILCROW SIGN
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x00b8, # CEDILLA
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x00a8, # DIAERESIS
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x00b9, # SUPERSCRIPT ONE
|
||||
0x00fc: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd7' # 0x009e -> MULTIPLICATION SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\xae' # 0x00a9 -> REGISTERED SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xa9' # 0x00b8 -> COPYRIGHT SIGN
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\xa2' # 0x00bd -> CENT SIGN
|
||||
u'\xa5' # 0x00be -> YEN SIGN
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\xa4' # 0x00cf -> CURRENCY SIGN
|
||||
u'\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH
|
||||
u'\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH
|
||||
u'\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\u20ac' # 0x00d5 -> EURO SIGN
|
||||
u'\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\xa6' # 0x00dd -> BROKEN BAR
|
||||
u'\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN
|
||||
u'\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN
|
||||
u'\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xaf' # 0x00ee -> MACRON
|
||||
u'\xb4' # 0x00ef -> ACUTE ACCENT
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2017' # 0x00f2 -> DOUBLE LOW LINE
|
||||
u'\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xb6' # 0x00f4 -> PILCROW SIGN
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\xb8' # 0x00f7 -> CEDILLA
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\xa8' # 0x00f9 -> DIAERESIS
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\xb9' # 0x00fb -> SUPERSCRIPT ONE
|
||||
u'\xb3' # 0x00fc -> SUPERSCRIPT THREE
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x00bd, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x00cf, # CURRENCY SIGN
|
||||
0x00a5: 0x00be, # YEN SIGN
|
||||
0x00a6: 0x00dd, # BROKEN BAR
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a8: 0x00f9, # DIAERESIS
|
||||
0x00a9: 0x00b8, # COPYRIGHT SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00ae: 0x00a9, # REGISTERED SIGN
|
||||
0x00af: 0x00ee, # MACRON
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x00fc, # SUPERSCRIPT THREE
|
||||
0x00b4: 0x00ef, # ACUTE ACCENT
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b6: 0x00f4, # PILCROW SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00b8: 0x00f7, # CEDILLA
|
||||
0x00b9: 0x00fb, # SUPERSCRIPT ONE
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d7: 0x009e, # MULTIPLICATION SIGN
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f0: 0x00d0, # LATIN SMALL LETTER ETH
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00fe: 0x00e7, # LATIN SMALL LETTER THORN
|
||||
0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x20ac: 0x00d5, # EURO SIGN
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x2017: 0x00f2, # DOUBLE LOW LINE
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp860.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp860.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP860.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp860',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x008c: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x008e: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x008f: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x0092: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x0099: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00a2, # CENT SIGN
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x009e: 0x20a7, # PESETA SIGN
|
||||
0x009f: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0x0084 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0x0086 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xca' # 0x0089 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xcd' # 0x008b -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xd4' # 0x008c -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xc3' # 0x008e -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc2' # 0x008f -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xc0' # 0x0091 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc8' # 0x0092 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0x0094 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xda' # 0x0096 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xcc' # 0x0098 -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xd5' # 0x0099 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xa2' # 0x009b -> CENT SIGN
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\u20a7' # 0x009e -> PESETA SIGN
|
||||
u'\xd3' # 0x009f -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\xd2' # 0x00a9 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x009b, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c0: 0x0091, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00c1: 0x0086, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c2: 0x008f, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c3: 0x008e, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c8: 0x0092, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00ca: 0x0089, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00cc: 0x0098, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00cd: 0x008b, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d2: 0x00a9, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00d3: 0x009f, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d4: 0x008c, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d5: 0x0099, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00da: 0x0096, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e3: 0x0084, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f5: 0x0094, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x20a7: 0x009e, # PESETA SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp861.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp861.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP861.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp861',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00d0, # LATIN CAPITAL LETTER ETH
|
||||
0x008c: 0x00f0, # LATIN SMALL LETTER ETH
|
||||
0x008d: 0x00de, # LATIN CAPITAL LETTER THORN
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00fe, # LATIN SMALL LETTER THORN
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x0098: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x20a7, # PESETA SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00a5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00a6: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00a7: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x2310, # REVERSED NOT SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xd0' # 0x008b -> LATIN CAPITAL LETTER ETH
|
||||
u'\xf0' # 0x008c -> LATIN SMALL LETTER ETH
|
||||
u'\xde' # 0x008d -> LATIN CAPITAL LETTER THORN
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xfe' # 0x0095 -> LATIN SMALL LETTER THORN
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdd' # 0x0097 -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xfd' # 0x0098 -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\u20a7' # 0x009e -> PESETA SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xc1' # 0x00a4 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xcd' # 0x00a5 -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xd3' # 0x00a6 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xda' # 0x00a7 -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\u2310' # 0x00a9 -> REVERSED NOT SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c1: 0x00a4, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00cd: 0x00a5, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00d0: 0x008b, # LATIN CAPITAL LETTER ETH
|
||||
0x00d3: 0x00a6, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00da: 0x00a7, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00dd: 0x0097, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00de: 0x008d, # LATIN CAPITAL LETTER THORN
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00f0: 0x008c, # LATIN SMALL LETTER ETH
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00fd: 0x0098, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00fe: 0x0095, # LATIN SMALL LETTER THORN
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x20a7: 0x009e, # PESETA SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2310: 0x00a9, # REVERSED NOT SIGN
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp862.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp862.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP862.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp862',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x05d0, # HEBREW LETTER ALEF
|
||||
0x0081: 0x05d1, # HEBREW LETTER BET
|
||||
0x0082: 0x05d2, # HEBREW LETTER GIMEL
|
||||
0x0083: 0x05d3, # HEBREW LETTER DALET
|
||||
0x0084: 0x05d4, # HEBREW LETTER HE
|
||||
0x0085: 0x05d5, # HEBREW LETTER VAV
|
||||
0x0086: 0x05d6, # HEBREW LETTER ZAYIN
|
||||
0x0087: 0x05d7, # HEBREW LETTER HET
|
||||
0x0088: 0x05d8, # HEBREW LETTER TET
|
||||
0x0089: 0x05d9, # HEBREW LETTER YOD
|
||||
0x008a: 0x05da, # HEBREW LETTER FINAL KAF
|
||||
0x008b: 0x05db, # HEBREW LETTER KAF
|
||||
0x008c: 0x05dc, # HEBREW LETTER LAMED
|
||||
0x008d: 0x05dd, # HEBREW LETTER FINAL MEM
|
||||
0x008e: 0x05de, # HEBREW LETTER MEM
|
||||
0x008f: 0x05df, # HEBREW LETTER FINAL NUN
|
||||
0x0090: 0x05e0, # HEBREW LETTER NUN
|
||||
0x0091: 0x05e1, # HEBREW LETTER SAMEKH
|
||||
0x0092: 0x05e2, # HEBREW LETTER AYIN
|
||||
0x0093: 0x05e3, # HEBREW LETTER FINAL PE
|
||||
0x0094: 0x05e4, # HEBREW LETTER PE
|
||||
0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI
|
||||
0x0096: 0x05e6, # HEBREW LETTER TSADI
|
||||
0x0097: 0x05e7, # HEBREW LETTER QOF
|
||||
0x0098: 0x05e8, # HEBREW LETTER RESH
|
||||
0x0099: 0x05e9, # HEBREW LETTER SHIN
|
||||
0x009a: 0x05ea, # HEBREW LETTER TAV
|
||||
0x009b: 0x00a2, # CENT SIGN
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00a5, # YEN SIGN
|
||||
0x009e: 0x20a7, # PESETA SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x2310, # REVERSED NOT SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\u05d0' # 0x0080 -> HEBREW LETTER ALEF
|
||||
u'\u05d1' # 0x0081 -> HEBREW LETTER BET
|
||||
u'\u05d2' # 0x0082 -> HEBREW LETTER GIMEL
|
||||
u'\u05d3' # 0x0083 -> HEBREW LETTER DALET
|
||||
u'\u05d4' # 0x0084 -> HEBREW LETTER HE
|
||||
u'\u05d5' # 0x0085 -> HEBREW LETTER VAV
|
||||
u'\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN
|
||||
u'\u05d7' # 0x0087 -> HEBREW LETTER HET
|
||||
u'\u05d8' # 0x0088 -> HEBREW LETTER TET
|
||||
u'\u05d9' # 0x0089 -> HEBREW LETTER YOD
|
||||
u'\u05da' # 0x008a -> HEBREW LETTER FINAL KAF
|
||||
u'\u05db' # 0x008b -> HEBREW LETTER KAF
|
||||
u'\u05dc' # 0x008c -> HEBREW LETTER LAMED
|
||||
u'\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM
|
||||
u'\u05de' # 0x008e -> HEBREW LETTER MEM
|
||||
u'\u05df' # 0x008f -> HEBREW LETTER FINAL NUN
|
||||
u'\u05e0' # 0x0090 -> HEBREW LETTER NUN
|
||||
u'\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH
|
||||
u'\u05e2' # 0x0092 -> HEBREW LETTER AYIN
|
||||
u'\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE
|
||||
u'\u05e4' # 0x0094 -> HEBREW LETTER PE
|
||||
u'\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI
|
||||
u'\u05e6' # 0x0096 -> HEBREW LETTER TSADI
|
||||
u'\u05e7' # 0x0097 -> HEBREW LETTER QOF
|
||||
u'\u05e8' # 0x0098 -> HEBREW LETTER RESH
|
||||
u'\u05e9' # 0x0099 -> HEBREW LETTER SHIN
|
||||
u'\u05ea' # 0x009a -> HEBREW LETTER TAV
|
||||
u'\xa2' # 0x009b -> CENT SIGN
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xa5' # 0x009d -> YEN SIGN
|
||||
u'\u20a7' # 0x009e -> PESETA SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\u2310' # 0x00a9 -> REVERSED NOT SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a2: 0x009b, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a5: 0x009d, # YEN SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN)
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x05d0: 0x0080, # HEBREW LETTER ALEF
|
||||
0x05d1: 0x0081, # HEBREW LETTER BET
|
||||
0x05d2: 0x0082, # HEBREW LETTER GIMEL
|
||||
0x05d3: 0x0083, # HEBREW LETTER DALET
|
||||
0x05d4: 0x0084, # HEBREW LETTER HE
|
||||
0x05d5: 0x0085, # HEBREW LETTER VAV
|
||||
0x05d6: 0x0086, # HEBREW LETTER ZAYIN
|
||||
0x05d7: 0x0087, # HEBREW LETTER HET
|
||||
0x05d8: 0x0088, # HEBREW LETTER TET
|
||||
0x05d9: 0x0089, # HEBREW LETTER YOD
|
||||
0x05da: 0x008a, # HEBREW LETTER FINAL KAF
|
||||
0x05db: 0x008b, # HEBREW LETTER KAF
|
||||
0x05dc: 0x008c, # HEBREW LETTER LAMED
|
||||
0x05dd: 0x008d, # HEBREW LETTER FINAL MEM
|
||||
0x05de: 0x008e, # HEBREW LETTER MEM
|
||||
0x05df: 0x008f, # HEBREW LETTER FINAL NUN
|
||||
0x05e0: 0x0090, # HEBREW LETTER NUN
|
||||
0x05e1: 0x0091, # HEBREW LETTER SAMEKH
|
||||
0x05e2: 0x0092, # HEBREW LETTER AYIN
|
||||
0x05e3: 0x0093, # HEBREW LETTER FINAL PE
|
||||
0x05e4: 0x0094, # HEBREW LETTER PE
|
||||
0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI
|
||||
0x05e6: 0x0096, # HEBREW LETTER TSADI
|
||||
0x05e7: 0x0097, # HEBREW LETTER QOF
|
||||
0x05e8: 0x0098, # HEBREW LETTER RESH
|
||||
0x05e9: 0x0099, # HEBREW LETTER SHIN
|
||||
0x05ea: 0x009a, # HEBREW LETTER TAV
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x20a7: 0x009e, # PESETA SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2310: 0x00a9, # REVERSED NOT SIGN
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp863.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp863.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP863.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp863',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00b6, # PILCROW SIGN
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x2017, # DOUBLE LOW LINE
|
||||
0x008e: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x008f: 0x00a7, # SECTION SIGN
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x0092: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x0095: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00a4, # CURRENCY SIGN
|
||||
0x0099: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00a2, # CENT SIGN
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x009e: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00a6, # BROKEN BAR
|
||||
0x00a1: 0x00b4, # ACUTE ACCENT
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00a8, # DIAERESIS
|
||||
0x00a5: 0x00b8, # CEDILLA
|
||||
0x00a6: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x00a7: 0x00af, # MACRON
|
||||
0x00a8: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00a9: 0x2310, # REVERSED NOT SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc2' # 0x0084 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xb6' # 0x0086 -> PILCROW SIGN
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u2017' # 0x008d -> DOUBLE LOW LINE
|
||||
u'\xc0' # 0x008e -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xa7' # 0x008f -> SECTION SIGN
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xc8' # 0x0091 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xca' # 0x0092 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xcb' # 0x0094 -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcf' # 0x0095 -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xa4' # 0x0098 -> CURRENCY SIGN
|
||||
u'\xd4' # 0x0099 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xa2' # 0x009b -> CENT SIGN
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xdb' # 0x009e -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xa6' # 0x00a0 -> BROKEN BAR
|
||||
u'\xb4' # 0x00a1 -> ACUTE ACCENT
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xa8' # 0x00a4 -> DIAERESIS
|
||||
u'\xb8' # 0x00a5 -> CEDILLA
|
||||
u'\xb3' # 0x00a6 -> SUPERSCRIPT THREE
|
||||
u'\xaf' # 0x00a7 -> MACRON
|
||||
u'\xce' # 0x00a8 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\u2310' # 0x00a9 -> REVERSED NOT SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbe' # 0x00ad -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a2: 0x009b, # CENT SIGN
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x0098, # CURRENCY SIGN
|
||||
0x00a6: 0x00a0, # BROKEN BAR
|
||||
0x00a7: 0x008f, # SECTION SIGN
|
||||
0x00a8: 0x00a4, # DIAERESIS
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00af: 0x00a7, # MACRON
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x00a6, # SUPERSCRIPT THREE
|
||||
0x00b4: 0x00a1, # ACUTE ACCENT
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b6: 0x0086, # PILCROW SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00b8: 0x00a5, # CEDILLA
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00be: 0x00ad, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00c0: 0x008e, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00c2: 0x0084, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c8: 0x0091, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00ca: 0x0092, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00cb: 0x0094, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00ce: 0x00a8, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00cf: 0x0095, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00d4: 0x0099, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00db: 0x009e, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x2017: 0x008d, # DOUBLE LOW LINE
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2310: 0x00a9, # REVERSED NOT SIGN
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
690
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp864.py
Normal file
690
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp864.py
Normal file
@@ -0,0 +1,690 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP864.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp864',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0025: 0x066a, # ARABIC PERCENT SIGN
|
||||
0x0080: 0x00b0, # DEGREE SIGN
|
||||
0x0081: 0x00b7, # MIDDLE DOT
|
||||
0x0082: 0x2219, # BULLET OPERATOR
|
||||
0x0083: 0x221a, # SQUARE ROOT
|
||||
0x0084: 0x2592, # MEDIUM SHADE
|
||||
0x0085: 0x2500, # FORMS LIGHT HORIZONTAL
|
||||
0x0086: 0x2502, # FORMS LIGHT VERTICAL
|
||||
0x0087: 0x253c, # FORMS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x0088: 0x2524, # FORMS LIGHT VERTICAL AND LEFT
|
||||
0x0089: 0x252c, # FORMS LIGHT DOWN AND HORIZONTAL
|
||||
0x008a: 0x251c, # FORMS LIGHT VERTICAL AND RIGHT
|
||||
0x008b: 0x2534, # FORMS LIGHT UP AND HORIZONTAL
|
||||
0x008c: 0x2510, # FORMS LIGHT DOWN AND LEFT
|
||||
0x008d: 0x250c, # FORMS LIGHT DOWN AND RIGHT
|
||||
0x008e: 0x2514, # FORMS LIGHT UP AND RIGHT
|
||||
0x008f: 0x2518, # FORMS LIGHT UP AND LEFT
|
||||
0x0090: 0x03b2, # GREEK SMALL BETA
|
||||
0x0091: 0x221e, # INFINITY
|
||||
0x0092: 0x03c6, # GREEK SMALL PHI
|
||||
0x0093: 0x00b1, # PLUS-OR-MINUS SIGN
|
||||
0x0094: 0x00bd, # FRACTION 1/2
|
||||
0x0095: 0x00bc, # FRACTION 1/4
|
||||
0x0096: 0x2248, # ALMOST EQUAL TO
|
||||
0x0097: 0x00ab, # LEFT POINTING GUILLEMET
|
||||
0x0098: 0x00bb, # RIGHT POINTING GUILLEMET
|
||||
0x0099: 0xfef7, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
0x009a: 0xfef8, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
0x009b: None, # UNDEFINED
|
||||
0x009c: None, # UNDEFINED
|
||||
0x009d: 0xfefb, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
|
||||
0x009e: 0xfefc, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM
|
||||
0x009f: None, # UNDEFINED
|
||||
0x00a1: 0x00ad, # SOFT HYPHEN
|
||||
0x00a2: 0xfe82, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
|
||||
0x00a5: 0xfe84, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
0x00a6: None, # UNDEFINED
|
||||
0x00a7: None, # UNDEFINED
|
||||
0x00a8: 0xfe8e, # ARABIC LETTER ALEF FINAL FORM
|
||||
0x00a9: 0xfe8f, # ARABIC LETTER BEH ISOLATED FORM
|
||||
0x00aa: 0xfe95, # ARABIC LETTER TEH ISOLATED FORM
|
||||
0x00ab: 0xfe99, # ARABIC LETTER THEH ISOLATED FORM
|
||||
0x00ac: 0x060c, # ARABIC COMMA
|
||||
0x00ad: 0xfe9d, # ARABIC LETTER JEEM ISOLATED FORM
|
||||
0x00ae: 0xfea1, # ARABIC LETTER HAH ISOLATED FORM
|
||||
0x00af: 0xfea5, # ARABIC LETTER KHAH ISOLATED FORM
|
||||
0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO
|
||||
0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE
|
||||
0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO
|
||||
0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE
|
||||
0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR
|
||||
0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE
|
||||
0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX
|
||||
0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN
|
||||
0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT
|
||||
0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE
|
||||
0x00ba: 0xfed1, # ARABIC LETTER FEH ISOLATED FORM
|
||||
0x00bb: 0x061b, # ARABIC SEMICOLON
|
||||
0x00bc: 0xfeb1, # ARABIC LETTER SEEN ISOLATED FORM
|
||||
0x00bd: 0xfeb5, # ARABIC LETTER SHEEN ISOLATED FORM
|
||||
0x00be: 0xfeb9, # ARABIC LETTER SAD ISOLATED FORM
|
||||
0x00bf: 0x061f, # ARABIC QUESTION MARK
|
||||
0x00c0: 0x00a2, # CENT SIGN
|
||||
0x00c1: 0xfe80, # ARABIC LETTER HAMZA ISOLATED FORM
|
||||
0x00c2: 0xfe81, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
0x00c3: 0xfe83, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
0x00c4: 0xfe85, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
|
||||
0x00c5: 0xfeca, # ARABIC LETTER AIN FINAL FORM
|
||||
0x00c6: 0xfe8b, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
|
||||
0x00c7: 0xfe8d, # ARABIC LETTER ALEF ISOLATED FORM
|
||||
0x00c8: 0xfe91, # ARABIC LETTER BEH INITIAL FORM
|
||||
0x00c9: 0xfe93, # ARABIC LETTER TEH MARBUTA ISOLATED FORM
|
||||
0x00ca: 0xfe97, # ARABIC LETTER TEH INITIAL FORM
|
||||
0x00cb: 0xfe9b, # ARABIC LETTER THEH INITIAL FORM
|
||||
0x00cc: 0xfe9f, # ARABIC LETTER JEEM INITIAL FORM
|
||||
0x00cd: 0xfea3, # ARABIC LETTER HAH INITIAL FORM
|
||||
0x00ce: 0xfea7, # ARABIC LETTER KHAH INITIAL FORM
|
||||
0x00cf: 0xfea9, # ARABIC LETTER DAL ISOLATED FORM
|
||||
0x00d0: 0xfeab, # ARABIC LETTER THAL ISOLATED FORM
|
||||
0x00d1: 0xfead, # ARABIC LETTER REH ISOLATED FORM
|
||||
0x00d2: 0xfeaf, # ARABIC LETTER ZAIN ISOLATED FORM
|
||||
0x00d3: 0xfeb3, # ARABIC LETTER SEEN INITIAL FORM
|
||||
0x00d4: 0xfeb7, # ARABIC LETTER SHEEN INITIAL FORM
|
||||
0x00d5: 0xfebb, # ARABIC LETTER SAD INITIAL FORM
|
||||
0x00d6: 0xfebf, # ARABIC LETTER DAD INITIAL FORM
|
||||
0x00d7: 0xfec1, # ARABIC LETTER TAH ISOLATED FORM
|
||||
0x00d8: 0xfec5, # ARABIC LETTER ZAH ISOLATED FORM
|
||||
0x00d9: 0xfecb, # ARABIC LETTER AIN INITIAL FORM
|
||||
0x00da: 0xfecf, # ARABIC LETTER GHAIN INITIAL FORM
|
||||
0x00db: 0x00a6, # BROKEN VERTICAL BAR
|
||||
0x00dc: 0x00ac, # NOT SIGN
|
||||
0x00dd: 0x00f7, # DIVISION SIGN
|
||||
0x00de: 0x00d7, # MULTIPLICATION SIGN
|
||||
0x00df: 0xfec9, # ARABIC LETTER AIN ISOLATED FORM
|
||||
0x00e0: 0x0640, # ARABIC TATWEEL
|
||||
0x00e1: 0xfed3, # ARABIC LETTER FEH INITIAL FORM
|
||||
0x00e2: 0xfed7, # ARABIC LETTER QAF INITIAL FORM
|
||||
0x00e3: 0xfedb, # ARABIC LETTER KAF INITIAL FORM
|
||||
0x00e4: 0xfedf, # ARABIC LETTER LAM INITIAL FORM
|
||||
0x00e5: 0xfee3, # ARABIC LETTER MEEM INITIAL FORM
|
||||
0x00e6: 0xfee7, # ARABIC LETTER NOON INITIAL FORM
|
||||
0x00e7: 0xfeeb, # ARABIC LETTER HEH INITIAL FORM
|
||||
0x00e8: 0xfeed, # ARABIC LETTER WAW ISOLATED FORM
|
||||
0x00e9: 0xfeef, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM
|
||||
0x00ea: 0xfef3, # ARABIC LETTER YEH INITIAL FORM
|
||||
0x00eb: 0xfebd, # ARABIC LETTER DAD ISOLATED FORM
|
||||
0x00ec: 0xfecc, # ARABIC LETTER AIN MEDIAL FORM
|
||||
0x00ed: 0xfece, # ARABIC LETTER GHAIN FINAL FORM
|
||||
0x00ee: 0xfecd, # ARABIC LETTER GHAIN ISOLATED FORM
|
||||
0x00ef: 0xfee1, # ARABIC LETTER MEEM ISOLATED FORM
|
||||
0x00f0: 0xfe7d, # ARABIC SHADDA MEDIAL FORM
|
||||
0x00f1: 0x0651, # ARABIC SHADDAH
|
||||
0x00f2: 0xfee5, # ARABIC LETTER NOON ISOLATED FORM
|
||||
0x00f3: 0xfee9, # ARABIC LETTER HEH ISOLATED FORM
|
||||
0x00f4: 0xfeec, # ARABIC LETTER HEH MEDIAL FORM
|
||||
0x00f5: 0xfef0, # ARABIC LETTER ALEF MAKSURA FINAL FORM
|
||||
0x00f6: 0xfef2, # ARABIC LETTER YEH FINAL FORM
|
||||
0x00f7: 0xfed0, # ARABIC LETTER GHAIN MEDIAL FORM
|
||||
0x00f8: 0xfed5, # ARABIC LETTER QAF ISOLATED FORM
|
||||
0x00f9: 0xfef5, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
0x00fa: 0xfef6, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
|
||||
0x00fb: 0xfedd, # ARABIC LETTER LAM ISOLATED FORM
|
||||
0x00fc: 0xfed9, # ARABIC LETTER KAF ISOLATED FORM
|
||||
0x00fd: 0xfef1, # ARABIC LETTER YEH ISOLATED FORM
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: None, # UNDEFINED
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'\u066a' # 0x0025 -> ARABIC PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xb0' # 0x0080 -> DEGREE SIGN
|
||||
u'\xb7' # 0x0081 -> MIDDLE DOT
|
||||
u'\u2219' # 0x0082 -> BULLET OPERATOR
|
||||
u'\u221a' # 0x0083 -> SQUARE ROOT
|
||||
u'\u2592' # 0x0084 -> MEDIUM SHADE
|
||||
u'\u2500' # 0x0085 -> FORMS LIGHT HORIZONTAL
|
||||
u'\u2502' # 0x0086 -> FORMS LIGHT VERTICAL
|
||||
u'\u253c' # 0x0087 -> FORMS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u2524' # 0x0088 -> FORMS LIGHT VERTICAL AND LEFT
|
||||
u'\u252c' # 0x0089 -> FORMS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x008a -> FORMS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2534' # 0x008b -> FORMS LIGHT UP AND HORIZONTAL
|
||||
u'\u2510' # 0x008c -> FORMS LIGHT DOWN AND LEFT
|
||||
u'\u250c' # 0x008d -> FORMS LIGHT DOWN AND RIGHT
|
||||
u'\u2514' # 0x008e -> FORMS LIGHT UP AND RIGHT
|
||||
u'\u2518' # 0x008f -> FORMS LIGHT UP AND LEFT
|
||||
u'\u03b2' # 0x0090 -> GREEK SMALL BETA
|
||||
u'\u221e' # 0x0091 -> INFINITY
|
||||
u'\u03c6' # 0x0092 -> GREEK SMALL PHI
|
||||
u'\xb1' # 0x0093 -> PLUS-OR-MINUS SIGN
|
||||
u'\xbd' # 0x0094 -> FRACTION 1/2
|
||||
u'\xbc' # 0x0095 -> FRACTION 1/4
|
||||
u'\u2248' # 0x0096 -> ALMOST EQUAL TO
|
||||
u'\xab' # 0x0097 -> LEFT POINTING GUILLEMET
|
||||
u'\xbb' # 0x0098 -> RIGHT POINTING GUILLEMET
|
||||
u'\ufef7' # 0x0099 -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufef8' # 0x009a -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
u'\ufffe' # 0x009b -> UNDEFINED
|
||||
u'\ufffe' # 0x009c -> UNDEFINED
|
||||
u'\ufefb' # 0x009d -> ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
|
||||
u'\ufefc' # 0x009e -> ARABIC LIGATURE LAM WITH ALEF FINAL FORM
|
||||
u'\ufffe' # 0x009f -> UNDEFINED
|
||||
u'\xa0' # 0x00a0 -> NON-BREAKING SPACE
|
||||
u'\xad' # 0x00a1 -> SOFT HYPHEN
|
||||
u'\ufe82' # 0x00a2 -> ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
|
||||
u'\xa3' # 0x00a3 -> POUND SIGN
|
||||
u'\xa4' # 0x00a4 -> CURRENCY SIGN
|
||||
u'\ufe84' # 0x00a5 -> ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
u'\ufffe' # 0x00a6 -> UNDEFINED
|
||||
u'\ufffe' # 0x00a7 -> UNDEFINED
|
||||
u'\ufe8e' # 0x00a8 -> ARABIC LETTER ALEF FINAL FORM
|
||||
u'\ufe8f' # 0x00a9 -> ARABIC LETTER BEH ISOLATED FORM
|
||||
u'\ufe95' # 0x00aa -> ARABIC LETTER TEH ISOLATED FORM
|
||||
u'\ufe99' # 0x00ab -> ARABIC LETTER THEH ISOLATED FORM
|
||||
u'\u060c' # 0x00ac -> ARABIC COMMA
|
||||
u'\ufe9d' # 0x00ad -> ARABIC LETTER JEEM ISOLATED FORM
|
||||
u'\ufea1' # 0x00ae -> ARABIC LETTER HAH ISOLATED FORM
|
||||
u'\ufea5' # 0x00af -> ARABIC LETTER KHAH ISOLATED FORM
|
||||
u'\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO
|
||||
u'\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE
|
||||
u'\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO
|
||||
u'\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE
|
||||
u'\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR
|
||||
u'\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE
|
||||
u'\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX
|
||||
u'\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN
|
||||
u'\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT
|
||||
u'\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE
|
||||
u'\ufed1' # 0x00ba -> ARABIC LETTER FEH ISOLATED FORM
|
||||
u'\u061b' # 0x00bb -> ARABIC SEMICOLON
|
||||
u'\ufeb1' # 0x00bc -> ARABIC LETTER SEEN ISOLATED FORM
|
||||
u'\ufeb5' # 0x00bd -> ARABIC LETTER SHEEN ISOLATED FORM
|
||||
u'\ufeb9' # 0x00be -> ARABIC LETTER SAD ISOLATED FORM
|
||||
u'\u061f' # 0x00bf -> ARABIC QUESTION MARK
|
||||
u'\xa2' # 0x00c0 -> CENT SIGN
|
||||
u'\ufe80' # 0x00c1 -> ARABIC LETTER HAMZA ISOLATED FORM
|
||||
u'\ufe81' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
u'\ufe83' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufe85' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
|
||||
u'\ufeca' # 0x00c5 -> ARABIC LETTER AIN FINAL FORM
|
||||
u'\ufe8b' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
|
||||
u'\ufe8d' # 0x00c7 -> ARABIC LETTER ALEF ISOLATED FORM
|
||||
u'\ufe91' # 0x00c8 -> ARABIC LETTER BEH INITIAL FORM
|
||||
u'\ufe93' # 0x00c9 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM
|
||||
u'\ufe97' # 0x00ca -> ARABIC LETTER TEH INITIAL FORM
|
||||
u'\ufe9b' # 0x00cb -> ARABIC LETTER THEH INITIAL FORM
|
||||
u'\ufe9f' # 0x00cc -> ARABIC LETTER JEEM INITIAL FORM
|
||||
u'\ufea3' # 0x00cd -> ARABIC LETTER HAH INITIAL FORM
|
||||
u'\ufea7' # 0x00ce -> ARABIC LETTER KHAH INITIAL FORM
|
||||
u'\ufea9' # 0x00cf -> ARABIC LETTER DAL ISOLATED FORM
|
||||
u'\ufeab' # 0x00d0 -> ARABIC LETTER THAL ISOLATED FORM
|
||||
u'\ufead' # 0x00d1 -> ARABIC LETTER REH ISOLATED FORM
|
||||
u'\ufeaf' # 0x00d2 -> ARABIC LETTER ZAIN ISOLATED FORM
|
||||
u'\ufeb3' # 0x00d3 -> ARABIC LETTER SEEN INITIAL FORM
|
||||
u'\ufeb7' # 0x00d4 -> ARABIC LETTER SHEEN INITIAL FORM
|
||||
u'\ufebb' # 0x00d5 -> ARABIC LETTER SAD INITIAL FORM
|
||||
u'\ufebf' # 0x00d6 -> ARABIC LETTER DAD INITIAL FORM
|
||||
u'\ufec1' # 0x00d7 -> ARABIC LETTER TAH ISOLATED FORM
|
||||
u'\ufec5' # 0x00d8 -> ARABIC LETTER ZAH ISOLATED FORM
|
||||
u'\ufecb' # 0x00d9 -> ARABIC LETTER AIN INITIAL FORM
|
||||
u'\ufecf' # 0x00da -> ARABIC LETTER GHAIN INITIAL FORM
|
||||
u'\xa6' # 0x00db -> BROKEN VERTICAL BAR
|
||||
u'\xac' # 0x00dc -> NOT SIGN
|
||||
u'\xf7' # 0x00dd -> DIVISION SIGN
|
||||
u'\xd7' # 0x00de -> MULTIPLICATION SIGN
|
||||
u'\ufec9' # 0x00df -> ARABIC LETTER AIN ISOLATED FORM
|
||||
u'\u0640' # 0x00e0 -> ARABIC TATWEEL
|
||||
u'\ufed3' # 0x00e1 -> ARABIC LETTER FEH INITIAL FORM
|
||||
u'\ufed7' # 0x00e2 -> ARABIC LETTER QAF INITIAL FORM
|
||||
u'\ufedb' # 0x00e3 -> ARABIC LETTER KAF INITIAL FORM
|
||||
u'\ufedf' # 0x00e4 -> ARABIC LETTER LAM INITIAL FORM
|
||||
u'\ufee3' # 0x00e5 -> ARABIC LETTER MEEM INITIAL FORM
|
||||
u'\ufee7' # 0x00e6 -> ARABIC LETTER NOON INITIAL FORM
|
||||
u'\ufeeb' # 0x00e7 -> ARABIC LETTER HEH INITIAL FORM
|
||||
u'\ufeed' # 0x00e8 -> ARABIC LETTER WAW ISOLATED FORM
|
||||
u'\ufeef' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA ISOLATED FORM
|
||||
u'\ufef3' # 0x00ea -> ARABIC LETTER YEH INITIAL FORM
|
||||
u'\ufebd' # 0x00eb -> ARABIC LETTER DAD ISOLATED FORM
|
||||
u'\ufecc' # 0x00ec -> ARABIC LETTER AIN MEDIAL FORM
|
||||
u'\ufece' # 0x00ed -> ARABIC LETTER GHAIN FINAL FORM
|
||||
u'\ufecd' # 0x00ee -> ARABIC LETTER GHAIN ISOLATED FORM
|
||||
u'\ufee1' # 0x00ef -> ARABIC LETTER MEEM ISOLATED FORM
|
||||
u'\ufe7d' # 0x00f0 -> ARABIC SHADDA MEDIAL FORM
|
||||
u'\u0651' # 0x00f1 -> ARABIC SHADDAH
|
||||
u'\ufee5' # 0x00f2 -> ARABIC LETTER NOON ISOLATED FORM
|
||||
u'\ufee9' # 0x00f3 -> ARABIC LETTER HEH ISOLATED FORM
|
||||
u'\ufeec' # 0x00f4 -> ARABIC LETTER HEH MEDIAL FORM
|
||||
u'\ufef0' # 0x00f5 -> ARABIC LETTER ALEF MAKSURA FINAL FORM
|
||||
u'\ufef2' # 0x00f6 -> ARABIC LETTER YEH FINAL FORM
|
||||
u'\ufed0' # 0x00f7 -> ARABIC LETTER GHAIN MEDIAL FORM
|
||||
u'\ufed5' # 0x00f8 -> ARABIC LETTER QAF ISOLATED FORM
|
||||
u'\ufef5' # 0x00f9 -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
u'\ufef6' # 0x00fa -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
|
||||
u'\ufedd' # 0x00fb -> ARABIC LETTER LAM ISOLATED FORM
|
||||
u'\ufed9' # 0x00fc -> ARABIC LETTER KAF ISOLATED FORM
|
||||
u'\ufef1' # 0x00fd -> ARABIC LETTER YEH ISOLATED FORM
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\ufffe' # 0x00ff -> UNDEFINED
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00a0, # NON-BREAKING SPACE
|
||||
0x00a2: 0x00c0, # CENT SIGN
|
||||
0x00a3: 0x00a3, # POUND SIGN
|
||||
0x00a4: 0x00a4, # CURRENCY SIGN
|
||||
0x00a6: 0x00db, # BROKEN VERTICAL BAR
|
||||
0x00ab: 0x0097, # LEFT POINTING GUILLEMET
|
||||
0x00ac: 0x00dc, # NOT SIGN
|
||||
0x00ad: 0x00a1, # SOFT HYPHEN
|
||||
0x00b0: 0x0080, # DEGREE SIGN
|
||||
0x00b1: 0x0093, # PLUS-OR-MINUS SIGN
|
||||
0x00b7: 0x0081, # MIDDLE DOT
|
||||
0x00bb: 0x0098, # RIGHT POINTING GUILLEMET
|
||||
0x00bc: 0x0095, # FRACTION 1/4
|
||||
0x00bd: 0x0094, # FRACTION 1/2
|
||||
0x00d7: 0x00de, # MULTIPLICATION SIGN
|
||||
0x00f7: 0x00dd, # DIVISION SIGN
|
||||
0x03b2: 0x0090, # GREEK SMALL BETA
|
||||
0x03c6: 0x0092, # GREEK SMALL PHI
|
||||
0x060c: 0x00ac, # ARABIC COMMA
|
||||
0x061b: 0x00bb, # ARABIC SEMICOLON
|
||||
0x061f: 0x00bf, # ARABIC QUESTION MARK
|
||||
0x0640: 0x00e0, # ARABIC TATWEEL
|
||||
0x0651: 0x00f1, # ARABIC SHADDAH
|
||||
0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO
|
||||
0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE
|
||||
0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO
|
||||
0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE
|
||||
0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR
|
||||
0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE
|
||||
0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX
|
||||
0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN
|
||||
0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT
|
||||
0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE
|
||||
0x066a: 0x0025, # ARABIC PERCENT SIGN
|
||||
0x2219: 0x0082, # BULLET OPERATOR
|
||||
0x221a: 0x0083, # SQUARE ROOT
|
||||
0x221e: 0x0091, # INFINITY
|
||||
0x2248: 0x0096, # ALMOST EQUAL TO
|
||||
0x2500: 0x0085, # FORMS LIGHT HORIZONTAL
|
||||
0x2502: 0x0086, # FORMS LIGHT VERTICAL
|
||||
0x250c: 0x008d, # FORMS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x008c, # FORMS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x008e, # FORMS LIGHT UP AND RIGHT
|
||||
0x2518: 0x008f, # FORMS LIGHT UP AND LEFT
|
||||
0x251c: 0x008a, # FORMS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x0088, # FORMS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x0089, # FORMS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x008b, # FORMS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x0087, # FORMS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2592: 0x0084, # MEDIUM SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
0xfe7d: 0x00f0, # ARABIC SHADDA MEDIAL FORM
|
||||
0xfe80: 0x00c1, # ARABIC LETTER HAMZA ISOLATED FORM
|
||||
0xfe81: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
0xfe82: 0x00a2, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM
|
||||
0xfe83: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
0xfe84: 0x00a5, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
0xfe85: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM
|
||||
0xfe8b: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM
|
||||
0xfe8d: 0x00c7, # ARABIC LETTER ALEF ISOLATED FORM
|
||||
0xfe8e: 0x00a8, # ARABIC LETTER ALEF FINAL FORM
|
||||
0xfe8f: 0x00a9, # ARABIC LETTER BEH ISOLATED FORM
|
||||
0xfe91: 0x00c8, # ARABIC LETTER BEH INITIAL FORM
|
||||
0xfe93: 0x00c9, # ARABIC LETTER TEH MARBUTA ISOLATED FORM
|
||||
0xfe95: 0x00aa, # ARABIC LETTER TEH ISOLATED FORM
|
||||
0xfe97: 0x00ca, # ARABIC LETTER TEH INITIAL FORM
|
||||
0xfe99: 0x00ab, # ARABIC LETTER THEH ISOLATED FORM
|
||||
0xfe9b: 0x00cb, # ARABIC LETTER THEH INITIAL FORM
|
||||
0xfe9d: 0x00ad, # ARABIC LETTER JEEM ISOLATED FORM
|
||||
0xfe9f: 0x00cc, # ARABIC LETTER JEEM INITIAL FORM
|
||||
0xfea1: 0x00ae, # ARABIC LETTER HAH ISOLATED FORM
|
||||
0xfea3: 0x00cd, # ARABIC LETTER HAH INITIAL FORM
|
||||
0xfea5: 0x00af, # ARABIC LETTER KHAH ISOLATED FORM
|
||||
0xfea7: 0x00ce, # ARABIC LETTER KHAH INITIAL FORM
|
||||
0xfea9: 0x00cf, # ARABIC LETTER DAL ISOLATED FORM
|
||||
0xfeab: 0x00d0, # ARABIC LETTER THAL ISOLATED FORM
|
||||
0xfead: 0x00d1, # ARABIC LETTER REH ISOLATED FORM
|
||||
0xfeaf: 0x00d2, # ARABIC LETTER ZAIN ISOLATED FORM
|
||||
0xfeb1: 0x00bc, # ARABIC LETTER SEEN ISOLATED FORM
|
||||
0xfeb3: 0x00d3, # ARABIC LETTER SEEN INITIAL FORM
|
||||
0xfeb5: 0x00bd, # ARABIC LETTER SHEEN ISOLATED FORM
|
||||
0xfeb7: 0x00d4, # ARABIC LETTER SHEEN INITIAL FORM
|
||||
0xfeb9: 0x00be, # ARABIC LETTER SAD ISOLATED FORM
|
||||
0xfebb: 0x00d5, # ARABIC LETTER SAD INITIAL FORM
|
||||
0xfebd: 0x00eb, # ARABIC LETTER DAD ISOLATED FORM
|
||||
0xfebf: 0x00d6, # ARABIC LETTER DAD INITIAL FORM
|
||||
0xfec1: 0x00d7, # ARABIC LETTER TAH ISOLATED FORM
|
||||
0xfec5: 0x00d8, # ARABIC LETTER ZAH ISOLATED FORM
|
||||
0xfec9: 0x00df, # ARABIC LETTER AIN ISOLATED FORM
|
||||
0xfeca: 0x00c5, # ARABIC LETTER AIN FINAL FORM
|
||||
0xfecb: 0x00d9, # ARABIC LETTER AIN INITIAL FORM
|
||||
0xfecc: 0x00ec, # ARABIC LETTER AIN MEDIAL FORM
|
||||
0xfecd: 0x00ee, # ARABIC LETTER GHAIN ISOLATED FORM
|
||||
0xfece: 0x00ed, # ARABIC LETTER GHAIN FINAL FORM
|
||||
0xfecf: 0x00da, # ARABIC LETTER GHAIN INITIAL FORM
|
||||
0xfed0: 0x00f7, # ARABIC LETTER GHAIN MEDIAL FORM
|
||||
0xfed1: 0x00ba, # ARABIC LETTER FEH ISOLATED FORM
|
||||
0xfed3: 0x00e1, # ARABIC LETTER FEH INITIAL FORM
|
||||
0xfed5: 0x00f8, # ARABIC LETTER QAF ISOLATED FORM
|
||||
0xfed7: 0x00e2, # ARABIC LETTER QAF INITIAL FORM
|
||||
0xfed9: 0x00fc, # ARABIC LETTER KAF ISOLATED FORM
|
||||
0xfedb: 0x00e3, # ARABIC LETTER KAF INITIAL FORM
|
||||
0xfedd: 0x00fb, # ARABIC LETTER LAM ISOLATED FORM
|
||||
0xfedf: 0x00e4, # ARABIC LETTER LAM INITIAL FORM
|
||||
0xfee1: 0x00ef, # ARABIC LETTER MEEM ISOLATED FORM
|
||||
0xfee3: 0x00e5, # ARABIC LETTER MEEM INITIAL FORM
|
||||
0xfee5: 0x00f2, # ARABIC LETTER NOON ISOLATED FORM
|
||||
0xfee7: 0x00e6, # ARABIC LETTER NOON INITIAL FORM
|
||||
0xfee9: 0x00f3, # ARABIC LETTER HEH ISOLATED FORM
|
||||
0xfeeb: 0x00e7, # ARABIC LETTER HEH INITIAL FORM
|
||||
0xfeec: 0x00f4, # ARABIC LETTER HEH MEDIAL FORM
|
||||
0xfeed: 0x00e8, # ARABIC LETTER WAW ISOLATED FORM
|
||||
0xfeef: 0x00e9, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM
|
||||
0xfef0: 0x00f5, # ARABIC LETTER ALEF MAKSURA FINAL FORM
|
||||
0xfef1: 0x00fd, # ARABIC LETTER YEH ISOLATED FORM
|
||||
0xfef2: 0x00f6, # ARABIC LETTER YEH FINAL FORM
|
||||
0xfef3: 0x00ea, # ARABIC LETTER YEH INITIAL FORM
|
||||
0xfef5: 0x00f9, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM
|
||||
0xfef6: 0x00fa, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM
|
||||
0xfef7: 0x0099, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM
|
||||
0xfef8: 0x009a, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM
|
||||
0xfefb: 0x009d, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM
|
||||
0xfefc: 0x009e, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp865.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp865.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP865.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp865',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x0091: 0x00e6, # LATIN SMALL LIGATURE AE
|
||||
0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE
|
||||
0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x009e: 0x20a7, # PESETA SIGN
|
||||
0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00a8: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00a9: 0x2310, # REVERSED NOT SIGN
|
||||
0x00aa: 0x00ac, # NOT SIGN
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00a4, # CURRENCY SIGN
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S
|
||||
0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00e3: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00e6: 0x00b5, # MICRO SIGN
|
||||
0x00e7: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00ec: 0x221e, # INFINITY
|
||||
0x00ed: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00ef: 0x2229, # INTERSECTION
|
||||
0x00f0: 0x2261, # IDENTICAL TO
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO
|
||||
0x00f3: 0x2264, # LESS-THAN OR EQUAL TO
|
||||
0x00f4: 0x2320, # TOP HALF INTEGRAL
|
||||
0x00f5: 0x2321, # BOTTOM HALF INTEGRAL
|
||||
0x00f6: 0x00f7, # DIVISION SIGN
|
||||
0x00f7: 0x2248, # ALMOST EQUAL TO
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x00fd: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE
|
||||
u'\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE
|
||||
u'\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
u'\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\u20a7' # 0x009e -> PESETA SIGN
|
||||
u'\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK
|
||||
u'\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR
|
||||
u'\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbf' # 0x00a8 -> INVERTED QUESTION MARK
|
||||
u'\u2310' # 0x00a9 -> REVERSED NOT SIGN
|
||||
u'\xac' # 0x00aa -> NOT SIGN
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xa4' # 0x00af -> CURRENCY SIGN
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA
|
||||
u'\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI
|
||||
u'\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA
|
||||
u'\xb5' # 0x00e6 -> MICRO SIGN
|
||||
u'\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU
|
||||
u'\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA
|
||||
u'\u221e' # 0x00ec -> INFINITY
|
||||
u'\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI
|
||||
u'\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2229' # 0x00ef -> INTERSECTION
|
||||
u'\u2261' # 0x00f0 -> IDENTICAL TO
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO
|
||||
u'\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO
|
||||
u'\u2320' # 0x00f4 -> TOP HALF INTEGRAL
|
||||
u'\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL
|
||||
u'\xf7' # 0x00f6 -> DIVISION SIGN
|
||||
u'\u2248' # 0x00f7 -> ALMOST EQUAL TO
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N
|
||||
u'\xb2' # 0x00fd -> SUPERSCRIPT TWO
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a4: 0x00af, # CURRENCY SIGN
|
||||
0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x00aa, # NOT SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x00fd, # SUPERSCRIPT TWO
|
||||
0x00b5: 0x00e6, # MICRO SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR
|
||||
0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x00bf: 0x00a8, # INVERTED QUESTION MARK
|
||||
0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE
|
||||
0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S
|
||||
0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00e6: 0x0091, # LATIN SMALL LIGATURE AE
|
||||
0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00f7: 0x00f6, # DIVISION SIGN
|
||||
0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA
|
||||
0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI
|
||||
0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA
|
||||
0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON
|
||||
0x03c0: 0x00e3, # GREEK SMALL LETTER PI
|
||||
0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00e7, # GREEK SMALL LETTER TAU
|
||||
0x03c6: 0x00ed, # GREEK SMALL LETTER PHI
|
||||
0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N
|
||||
0x20a7: 0x009e, # PESETA SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x221e: 0x00ec, # INFINITY
|
||||
0x2229: 0x00ef, # INTERSECTION
|
||||
0x2248: 0x00f7, # ALMOST EQUAL TO
|
||||
0x2261: 0x00f0, # IDENTICAL TO
|
||||
0x2264: 0x00f3, # LESS-THAN OR EQUAL TO
|
||||
0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO
|
||||
0x2310: 0x00a9, # REVERSED NOT SIGN
|
||||
0x2320: 0x00f4, # TOP HALF INTEGRAL
|
||||
0x2321: 0x00f5, # BOTTOM HALF INTEGRAL
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp866.py
Normal file
698
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp866.py
Normal file
@@ -0,0 +1,698 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP866.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp866',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A
|
||||
0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE
|
||||
0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE
|
||||
0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE
|
||||
0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE
|
||||
0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE
|
||||
0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE
|
||||
0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE
|
||||
0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I
|
||||
0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA
|
||||
0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL
|
||||
0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM
|
||||
0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN
|
||||
0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O
|
||||
0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE
|
||||
0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER
|
||||
0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES
|
||||
0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE
|
||||
0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U
|
||||
0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF
|
||||
0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA
|
||||
0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE
|
||||
0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE
|
||||
0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA
|
||||
0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU
|
||||
0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E
|
||||
0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU
|
||||
0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA
|
||||
0x00a0: 0x0430, # CYRILLIC SMALL LETTER A
|
||||
0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE
|
||||
0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE
|
||||
0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE
|
||||
0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE
|
||||
0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE
|
||||
0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE
|
||||
0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE
|
||||
0x00a8: 0x0438, # CYRILLIC SMALL LETTER I
|
||||
0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I
|
||||
0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA
|
||||
0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL
|
||||
0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM
|
||||
0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN
|
||||
0x00ae: 0x043e, # CYRILLIC SMALL LETTER O
|
||||
0x00af: 0x043f, # CYRILLIC SMALL LETTER PE
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x258c, # LEFT HALF BLOCK
|
||||
0x00de: 0x2590, # RIGHT HALF BLOCK
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER
|
||||
0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES
|
||||
0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE
|
||||
0x00e3: 0x0443, # CYRILLIC SMALL LETTER U
|
||||
0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF
|
||||
0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA
|
||||
0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE
|
||||
0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE
|
||||
0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA
|
||||
0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA
|
||||
0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU
|
||||
0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0x00ed: 0x044d, # CYRILLIC SMALL LETTER E
|
||||
0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU
|
||||
0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA
|
||||
0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO
|
||||
0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO
|
||||
0x00f2: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0x00f3: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0x00f4: 0x0407, # CYRILLIC CAPITAL LETTER YI
|
||||
0x00f5: 0x0457, # CYRILLIC SMALL LETTER YI
|
||||
0x00f6: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U
|
||||
0x00f7: 0x045e, # CYRILLIC SMALL LETTER SHORT U
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x2219, # BULLET OPERATOR
|
||||
0x00fa: 0x00b7, # MIDDLE DOT
|
||||
0x00fb: 0x221a, # SQUARE ROOT
|
||||
0x00fc: 0x2116, # NUMERO SIGN
|
||||
0x00fd: 0x00a4, # CURRENCY SIGN
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A
|
||||
u'\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE
|
||||
u'\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE
|
||||
u'\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE
|
||||
u'\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE
|
||||
u'\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE
|
||||
u'\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE
|
||||
u'\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE
|
||||
u'\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I
|
||||
u'\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I
|
||||
u'\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA
|
||||
u'\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL
|
||||
u'\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM
|
||||
u'\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN
|
||||
u'\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O
|
||||
u'\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE
|
||||
u'\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER
|
||||
u'\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES
|
||||
u'\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE
|
||||
u'\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U
|
||||
u'\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF
|
||||
u'\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA
|
||||
u'\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE
|
||||
u'\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE
|
||||
u'\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA
|
||||
u'\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA
|
||||
u'\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
u'\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU
|
||||
u'\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
u'\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E
|
||||
u'\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU
|
||||
u'\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA
|
||||
u'\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A
|
||||
u'\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE
|
||||
u'\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE
|
||||
u'\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE
|
||||
u'\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE
|
||||
u'\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE
|
||||
u'\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE
|
||||
u'\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE
|
||||
u'\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I
|
||||
u'\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I
|
||||
u'\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA
|
||||
u'\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL
|
||||
u'\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM
|
||||
u'\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN
|
||||
u'\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O
|
||||
u'\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
u'\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
u'\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
u'\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
u'\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
u'\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
u'\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
u'\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
u'\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
u'\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
u'\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u258c' # 0x00dd -> LEFT HALF BLOCK
|
||||
u'\u2590' # 0x00de -> RIGHT HALF BLOCK
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER
|
||||
u'\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES
|
||||
u'\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE
|
||||
u'\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U
|
||||
u'\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF
|
||||
u'\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA
|
||||
u'\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE
|
||||
u'\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE
|
||||
u'\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA
|
||||
u'\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA
|
||||
u'\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN
|
||||
u'\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU
|
||||
u'\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN
|
||||
u'\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E
|
||||
u'\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU
|
||||
u'\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA
|
||||
u'\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO
|
||||
u'\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO
|
||||
u'\u0404' # 0x00f2 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
u'\u0454' # 0x00f3 -> CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
u'\u0407' # 0x00f4 -> CYRILLIC CAPITAL LETTER YI
|
||||
u'\u0457' # 0x00f5 -> CYRILLIC SMALL LETTER YI
|
||||
u'\u040e' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHORT U
|
||||
u'\u045e' # 0x00f7 -> CYRILLIC SMALL LETTER SHORT U
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\u2219' # 0x00f9 -> BULLET OPERATOR
|
||||
u'\xb7' # 0x00fa -> MIDDLE DOT
|
||||
u'\u221a' # 0x00fb -> SQUARE ROOT
|
||||
u'\u2116' # 0x00fc -> NUMERO SIGN
|
||||
u'\xa4' # 0x00fd -> CURRENCY SIGN
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a4: 0x00fd, # CURRENCY SIGN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b7: 0x00fa, # MIDDLE DOT
|
||||
0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO
|
||||
0x0404: 0x00f2, # CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
0x0407: 0x00f4, # CYRILLIC CAPITAL LETTER YI
|
||||
0x040e: 0x00f6, # CYRILLIC CAPITAL LETTER SHORT U
|
||||
0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A
|
||||
0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE
|
||||
0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE
|
||||
0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE
|
||||
0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE
|
||||
0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE
|
||||
0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE
|
||||
0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE
|
||||
0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I
|
||||
0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I
|
||||
0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA
|
||||
0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL
|
||||
0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM
|
||||
0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN
|
||||
0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O
|
||||
0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE
|
||||
0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER
|
||||
0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES
|
||||
0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE
|
||||
0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U
|
||||
0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF
|
||||
0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA
|
||||
0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE
|
||||
0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE
|
||||
0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA
|
||||
0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA
|
||||
0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU
|
||||
0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E
|
||||
0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU
|
||||
0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA
|
||||
0x0430: 0x00a0, # CYRILLIC SMALL LETTER A
|
||||
0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE
|
||||
0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE
|
||||
0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE
|
||||
0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE
|
||||
0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE
|
||||
0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE
|
||||
0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE
|
||||
0x0438: 0x00a8, # CYRILLIC SMALL LETTER I
|
||||
0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I
|
||||
0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA
|
||||
0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL
|
||||
0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM
|
||||
0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN
|
||||
0x043e: 0x00ae, # CYRILLIC SMALL LETTER O
|
||||
0x043f: 0x00af, # CYRILLIC SMALL LETTER PE
|
||||
0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER
|
||||
0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES
|
||||
0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE
|
||||
0x0443: 0x00e3, # CYRILLIC SMALL LETTER U
|
||||
0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF
|
||||
0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA
|
||||
0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE
|
||||
0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE
|
||||
0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA
|
||||
0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA
|
||||
0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN
|
||||
0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU
|
||||
0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN
|
||||
0x044d: 0x00ed, # CYRILLIC SMALL LETTER E
|
||||
0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU
|
||||
0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA
|
||||
0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO
|
||||
0x0454: 0x00f3, # CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
0x0457: 0x00f5, # CYRILLIC SMALL LETTER YI
|
||||
0x045e: 0x00f7, # CYRILLIC SMALL LETTER SHORT U
|
||||
0x2116: 0x00fc, # NUMERO SIGN
|
||||
0x2219: 0x00f9, # BULLET OPERATOR
|
||||
0x221a: 0x00fb, # SQUARE ROOT
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE
|
||||
0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE
|
||||
0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE
|
||||
0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE
|
||||
0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE
|
||||
0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE
|
||||
0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE
|
||||
0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE
|
||||
0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x258c: 0x00dd, # LEFT HALF BLOCK
|
||||
0x2590: 0x00de, # RIGHT HALF BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
689
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp869.py
Normal file
689
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp869.py
Normal file
@@ -0,0 +1,689 @@
|
||||
""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP869.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp869',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x0080: None, # UNDEFINED
|
||||
0x0081: None, # UNDEFINED
|
||||
0x0082: None, # UNDEFINED
|
||||
0x0083: None, # UNDEFINED
|
||||
0x0084: None, # UNDEFINED
|
||||
0x0085: None, # UNDEFINED
|
||||
0x0086: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0x0087: None, # UNDEFINED
|
||||
0x0088: 0x00b7, # MIDDLE DOT
|
||||
0x0089: 0x00ac, # NOT SIGN
|
||||
0x008a: 0x00a6, # BROKEN BAR
|
||||
0x008b: 0x2018, # LEFT SINGLE QUOTATION MARK
|
||||
0x008c: 0x2019, # RIGHT SINGLE QUOTATION MARK
|
||||
0x008d: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0x008e: 0x2015, # HORIZONTAL BAR
|
||||
0x008f: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0x0090: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0x0091: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0x0092: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0x0093: None, # UNDEFINED
|
||||
0x0094: None, # UNDEFINED
|
||||
0x0095: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0x0096: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0x0097: 0x00a9, # COPYRIGHT SIGN
|
||||
0x0098: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0x0099: 0x00b2, # SUPERSCRIPT TWO
|
||||
0x009a: 0x00b3, # SUPERSCRIPT THREE
|
||||
0x009b: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0x009c: 0x00a3, # POUND SIGN
|
||||
0x009d: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0x009e: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS
|
||||
0x009f: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0x00a0: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0x00a1: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
0x00a2: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0x00a3: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0x00a4: 0x0391, # GREEK CAPITAL LETTER ALPHA
|
||||
0x00a5: 0x0392, # GREEK CAPITAL LETTER BETA
|
||||
0x00a6: 0x0393, # GREEK CAPITAL LETTER GAMMA
|
||||
0x00a7: 0x0394, # GREEK CAPITAL LETTER DELTA
|
||||
0x00a8: 0x0395, # GREEK CAPITAL LETTER EPSILON
|
||||
0x00a9: 0x0396, # GREEK CAPITAL LETTER ZETA
|
||||
0x00aa: 0x0397, # GREEK CAPITAL LETTER ETA
|
||||
0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00ac: 0x0398, # GREEK CAPITAL LETTER THETA
|
||||
0x00ad: 0x0399, # GREEK CAPITAL LETTER IOTA
|
||||
0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00b0: 0x2591, # LIGHT SHADE
|
||||
0x00b1: 0x2592, # MEDIUM SHADE
|
||||
0x00b2: 0x2593, # DARK SHADE
|
||||
0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x00b5: 0x039a, # GREEK CAPITAL LETTER KAPPA
|
||||
0x00b6: 0x039b, # GREEK CAPITAL LETTER LAMDA
|
||||
0x00b7: 0x039c, # GREEK CAPITAL LETTER MU
|
||||
0x00b8: 0x039d, # GREEK CAPITAL LETTER NU
|
||||
0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x00bd: 0x039e, # GREEK CAPITAL LETTER XI
|
||||
0x00be: 0x039f, # GREEK CAPITAL LETTER OMICRON
|
||||
0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x00c6: 0x03a0, # GREEK CAPITAL LETTER PI
|
||||
0x00c7: 0x03a1, # GREEK CAPITAL LETTER RHO
|
||||
0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x00cf: 0x03a3, # GREEK CAPITAL LETTER SIGMA
|
||||
0x00d0: 0x03a4, # GREEK CAPITAL LETTER TAU
|
||||
0x00d1: 0x03a5, # GREEK CAPITAL LETTER UPSILON
|
||||
0x00d2: 0x03a6, # GREEK CAPITAL LETTER PHI
|
||||
0x00d3: 0x03a7, # GREEK CAPITAL LETTER CHI
|
||||
0x00d4: 0x03a8, # GREEK CAPITAL LETTER PSI
|
||||
0x00d5: 0x03a9, # GREEK CAPITAL LETTER OMEGA
|
||||
0x00d6: 0x03b1, # GREEK SMALL LETTER ALPHA
|
||||
0x00d7: 0x03b2, # GREEK SMALL LETTER BETA
|
||||
0x00d8: 0x03b3, # GREEK SMALL LETTER GAMMA
|
||||
0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x00db: 0x2588, # FULL BLOCK
|
||||
0x00dc: 0x2584, # LOWER HALF BLOCK
|
||||
0x00dd: 0x03b4, # GREEK SMALL LETTER DELTA
|
||||
0x00de: 0x03b5, # GREEK SMALL LETTER EPSILON
|
||||
0x00df: 0x2580, # UPPER HALF BLOCK
|
||||
0x00e0: 0x03b6, # GREEK SMALL LETTER ZETA
|
||||
0x00e1: 0x03b7, # GREEK SMALL LETTER ETA
|
||||
0x00e2: 0x03b8, # GREEK SMALL LETTER THETA
|
||||
0x00e3: 0x03b9, # GREEK SMALL LETTER IOTA
|
||||
0x00e4: 0x03ba, # GREEK SMALL LETTER KAPPA
|
||||
0x00e5: 0x03bb, # GREEK SMALL LETTER LAMDA
|
||||
0x00e6: 0x03bc, # GREEK SMALL LETTER MU
|
||||
0x00e7: 0x03bd, # GREEK SMALL LETTER NU
|
||||
0x00e8: 0x03be, # GREEK SMALL LETTER XI
|
||||
0x00e9: 0x03bf, # GREEK SMALL LETTER OMICRON
|
||||
0x00ea: 0x03c0, # GREEK SMALL LETTER PI
|
||||
0x00eb: 0x03c1, # GREEK SMALL LETTER RHO
|
||||
0x00ec: 0x03c3, # GREEK SMALL LETTER SIGMA
|
||||
0x00ed: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA
|
||||
0x00ee: 0x03c4, # GREEK SMALL LETTER TAU
|
||||
0x00ef: 0x0384, # GREEK TONOS
|
||||
0x00f0: 0x00ad, # SOFT HYPHEN
|
||||
0x00f1: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00f2: 0x03c5, # GREEK SMALL LETTER UPSILON
|
||||
0x00f3: 0x03c6, # GREEK SMALL LETTER PHI
|
||||
0x00f4: 0x03c7, # GREEK SMALL LETTER CHI
|
||||
0x00f5: 0x00a7, # SECTION SIGN
|
||||
0x00f6: 0x03c8, # GREEK SMALL LETTER PSI
|
||||
0x00f7: 0x0385, # GREEK DIALYTIKA TONOS
|
||||
0x00f8: 0x00b0, # DEGREE SIGN
|
||||
0x00f9: 0x00a8, # DIAERESIS
|
||||
0x00fa: 0x03c9, # GREEK SMALL LETTER OMEGA
|
||||
0x00fb: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0x00fc: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
0x00fd: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
0x00fe: 0x25a0, # BLACK SQUARE
|
||||
0x00ff: 0x00a0, # NO-BREAK SPACE
|
||||
})
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x0000 -> NULL
|
||||
u'\x01' # 0x0001 -> START OF HEADING
|
||||
u'\x02' # 0x0002 -> START OF TEXT
|
||||
u'\x03' # 0x0003 -> END OF TEXT
|
||||
u'\x04' # 0x0004 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x0005 -> ENQUIRY
|
||||
u'\x06' # 0x0006 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x0007 -> BELL
|
||||
u'\x08' # 0x0008 -> BACKSPACE
|
||||
u'\t' # 0x0009 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x000a -> LINE FEED
|
||||
u'\x0b' # 0x000b -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x000c -> FORM FEED
|
||||
u'\r' # 0x000d -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x000e -> SHIFT OUT
|
||||
u'\x0f' # 0x000f -> SHIFT IN
|
||||
u'\x10' # 0x0010 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x0011 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x0012 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x0013 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x0014 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x0016 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x0017 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x0018 -> CANCEL
|
||||
u'\x19' # 0x0019 -> END OF MEDIUM
|
||||
u'\x1a' # 0x001a -> SUBSTITUTE
|
||||
u'\x1b' # 0x001b -> ESCAPE
|
||||
u'\x1c' # 0x001c -> FILE SEPARATOR
|
||||
u'\x1d' # 0x001d -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x001e -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x001f -> UNIT SEPARATOR
|
||||
u' ' # 0x0020 -> SPACE
|
||||
u'!' # 0x0021 -> EXCLAMATION MARK
|
||||
u'"' # 0x0022 -> QUOTATION MARK
|
||||
u'#' # 0x0023 -> NUMBER SIGN
|
||||
u'$' # 0x0024 -> DOLLAR SIGN
|
||||
u'%' # 0x0025 -> PERCENT SIGN
|
||||
u'&' # 0x0026 -> AMPERSAND
|
||||
u"'" # 0x0027 -> APOSTROPHE
|
||||
u'(' # 0x0028 -> LEFT PARENTHESIS
|
||||
u')' # 0x0029 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x002a -> ASTERISK
|
||||
u'+' # 0x002b -> PLUS SIGN
|
||||
u',' # 0x002c -> COMMA
|
||||
u'-' # 0x002d -> HYPHEN-MINUS
|
||||
u'.' # 0x002e -> FULL STOP
|
||||
u'/' # 0x002f -> SOLIDUS
|
||||
u'0' # 0x0030 -> DIGIT ZERO
|
||||
u'1' # 0x0031 -> DIGIT ONE
|
||||
u'2' # 0x0032 -> DIGIT TWO
|
||||
u'3' # 0x0033 -> DIGIT THREE
|
||||
u'4' # 0x0034 -> DIGIT FOUR
|
||||
u'5' # 0x0035 -> DIGIT FIVE
|
||||
u'6' # 0x0036 -> DIGIT SIX
|
||||
u'7' # 0x0037 -> DIGIT SEVEN
|
||||
u'8' # 0x0038 -> DIGIT EIGHT
|
||||
u'9' # 0x0039 -> DIGIT NINE
|
||||
u':' # 0x003a -> COLON
|
||||
u';' # 0x003b -> SEMICOLON
|
||||
u'<' # 0x003c -> LESS-THAN SIGN
|
||||
u'=' # 0x003d -> EQUALS SIGN
|
||||
u'>' # 0x003e -> GREATER-THAN SIGN
|
||||
u'?' # 0x003f -> QUESTION MARK
|
||||
u'@' # 0x0040 -> COMMERCIAL AT
|
||||
u'A' # 0x0041 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x0042 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x0043 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x0044 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x0045 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x0046 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x0047 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x0048 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x0049 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x004a -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x004b -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x004c -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x004d -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x004e -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x004f -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x0050 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x0051 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x0052 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x0053 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x0054 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x0055 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x0056 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x0057 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x0058 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x0059 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x005a -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x005b -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x005c -> REVERSE SOLIDUS
|
||||
u']' # 0x005d -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x005e -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x005f -> LOW LINE
|
||||
u'`' # 0x0060 -> GRAVE ACCENT
|
||||
u'a' # 0x0061 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x0062 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x0063 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x0064 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x0065 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x0066 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x0067 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x0068 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x0069 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x006a -> LATIN SMALL LETTER J
|
||||
u'k' # 0x006b -> LATIN SMALL LETTER K
|
||||
u'l' # 0x006c -> LATIN SMALL LETTER L
|
||||
u'm' # 0x006d -> LATIN SMALL LETTER M
|
||||
u'n' # 0x006e -> LATIN SMALL LETTER N
|
||||
u'o' # 0x006f -> LATIN SMALL LETTER O
|
||||
u'p' # 0x0070 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x0071 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x0072 -> LATIN SMALL LETTER R
|
||||
u's' # 0x0073 -> LATIN SMALL LETTER S
|
||||
u't' # 0x0074 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x0075 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x0076 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x0077 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x0078 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x0079 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x007a -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x007b -> LEFT CURLY BRACKET
|
||||
u'|' # 0x007c -> VERTICAL LINE
|
||||
u'}' # 0x007d -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x007e -> TILDE
|
||||
u'\x7f' # 0x007f -> DELETE
|
||||
u'\ufffe' # 0x0080 -> UNDEFINED
|
||||
u'\ufffe' # 0x0081 -> UNDEFINED
|
||||
u'\ufffe' # 0x0082 -> UNDEFINED
|
||||
u'\ufffe' # 0x0083 -> UNDEFINED
|
||||
u'\ufffe' # 0x0084 -> UNDEFINED
|
||||
u'\ufffe' # 0x0085 -> UNDEFINED
|
||||
u'\u0386' # 0x0086 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
u'\ufffe' # 0x0087 -> UNDEFINED
|
||||
u'\xb7' # 0x0088 -> MIDDLE DOT
|
||||
u'\xac' # 0x0089 -> NOT SIGN
|
||||
u'\xa6' # 0x008a -> BROKEN BAR
|
||||
u'\u2018' # 0x008b -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x008c -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u0388' # 0x008d -> GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
u'\u2015' # 0x008e -> HORIZONTAL BAR
|
||||
u'\u0389' # 0x008f -> GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
u'\u038a' # 0x0090 -> GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
u'\u03aa' # 0x0091 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u038c' # 0x0092 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
u'\ufffe' # 0x0093 -> UNDEFINED
|
||||
u'\ufffe' # 0x0094 -> UNDEFINED
|
||||
u'\u038e' # 0x0095 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
u'\u03ab' # 0x0096 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\xa9' # 0x0097 -> COPYRIGHT SIGN
|
||||
u'\u038f' # 0x0098 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
u'\xb2' # 0x0099 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0x009a -> SUPERSCRIPT THREE
|
||||
u'\u03ac' # 0x009b -> GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
u'\xa3' # 0x009c -> POUND SIGN
|
||||
u'\u03ad' # 0x009d -> GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
u'\u03ae' # 0x009e -> GREEK SMALL LETTER ETA WITH TONOS
|
||||
u'\u03af' # 0x009f -> GREEK SMALL LETTER IOTA WITH TONOS
|
||||
u'\u03ca' # 0x00a0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u0390' # 0x00a1 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
u'\u03cc' # 0x00a2 -> GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
u'\u03cd' # 0x00a3 -> GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
u'\u0391' # 0x00a4 -> GREEK CAPITAL LETTER ALPHA
|
||||
u'\u0392' # 0x00a5 -> GREEK CAPITAL LETTER BETA
|
||||
u'\u0393' # 0x00a6 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u0394' # 0x00a7 -> GREEK CAPITAL LETTER DELTA
|
||||
u'\u0395' # 0x00a8 -> GREEK CAPITAL LETTER EPSILON
|
||||
u'\u0396' # 0x00a9 -> GREEK CAPITAL LETTER ZETA
|
||||
u'\u0397' # 0x00aa -> GREEK CAPITAL LETTER ETA
|
||||
u'\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF
|
||||
u'\u0398' # 0x00ac -> GREEK CAPITAL LETTER THETA
|
||||
u'\u0399' # 0x00ad -> GREEK CAPITAL LETTER IOTA
|
||||
u'\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u2591' # 0x00b0 -> LIGHT SHADE
|
||||
u'\u2592' # 0x00b1 -> MEDIUM SHADE
|
||||
u'\u2593' # 0x00b2 -> DARK SHADE
|
||||
u'\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL
|
||||
u'\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
u'\u039a' # 0x00b5 -> GREEK CAPITAL LETTER KAPPA
|
||||
u'\u039b' # 0x00b6 -> GREEK CAPITAL LETTER LAMDA
|
||||
u'\u039c' # 0x00b7 -> GREEK CAPITAL LETTER MU
|
||||
u'\u039d' # 0x00b8 -> GREEK CAPITAL LETTER NU
|
||||
u'\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
u'\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL
|
||||
u'\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
u'\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
u'\u039e' # 0x00bd -> GREEK CAPITAL LETTER XI
|
||||
u'\u039f' # 0x00be -> GREEK CAPITAL LETTER OMICRON
|
||||
u'\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
u'\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
u'\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
u'\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
u'\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
u'\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL
|
||||
u'\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
u'\u03a0' # 0x00c6 -> GREEK CAPITAL LETTER PI
|
||||
u'\u03a1' # 0x00c7 -> GREEK CAPITAL LETTER RHO
|
||||
u'\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
u'\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
u'\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
u'\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
u'\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
u'\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
u'\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
u'\u03a3' # 0x00cf -> GREEK CAPITAL LETTER SIGMA
|
||||
u'\u03a4' # 0x00d0 -> GREEK CAPITAL LETTER TAU
|
||||
u'\u03a5' # 0x00d1 -> GREEK CAPITAL LETTER UPSILON
|
||||
u'\u03a6' # 0x00d2 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u03a7' # 0x00d3 -> GREEK CAPITAL LETTER CHI
|
||||
u'\u03a8' # 0x00d4 -> GREEK CAPITAL LETTER PSI
|
||||
u'\u03a9' # 0x00d5 -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03b1' # 0x00d6 -> GREEK SMALL LETTER ALPHA
|
||||
u'\u03b2' # 0x00d7 -> GREEK SMALL LETTER BETA
|
||||
u'\u03b3' # 0x00d8 -> GREEK SMALL LETTER GAMMA
|
||||
u'\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT
|
||||
u'\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
u'\u2588' # 0x00db -> FULL BLOCK
|
||||
u'\u2584' # 0x00dc -> LOWER HALF BLOCK
|
||||
u'\u03b4' # 0x00dd -> GREEK SMALL LETTER DELTA
|
||||
u'\u03b5' # 0x00de -> GREEK SMALL LETTER EPSILON
|
||||
u'\u2580' # 0x00df -> UPPER HALF BLOCK
|
||||
u'\u03b6' # 0x00e0 -> GREEK SMALL LETTER ZETA
|
||||
u'\u03b7' # 0x00e1 -> GREEK SMALL LETTER ETA
|
||||
u'\u03b8' # 0x00e2 -> GREEK SMALL LETTER THETA
|
||||
u'\u03b9' # 0x00e3 -> GREEK SMALL LETTER IOTA
|
||||
u'\u03ba' # 0x00e4 -> GREEK SMALL LETTER KAPPA
|
||||
u'\u03bb' # 0x00e5 -> GREEK SMALL LETTER LAMDA
|
||||
u'\u03bc' # 0x00e6 -> GREEK SMALL LETTER MU
|
||||
u'\u03bd' # 0x00e7 -> GREEK SMALL LETTER NU
|
||||
u'\u03be' # 0x00e8 -> GREEK SMALL LETTER XI
|
||||
u'\u03bf' # 0x00e9 -> GREEK SMALL LETTER OMICRON
|
||||
u'\u03c0' # 0x00ea -> GREEK SMALL LETTER PI
|
||||
u'\u03c1' # 0x00eb -> GREEK SMALL LETTER RHO
|
||||
u'\u03c3' # 0x00ec -> GREEK SMALL LETTER SIGMA
|
||||
u'\u03c2' # 0x00ed -> GREEK SMALL LETTER FINAL SIGMA
|
||||
u'\u03c4' # 0x00ee -> GREEK SMALL LETTER TAU
|
||||
u'\u0384' # 0x00ef -> GREEK TONOS
|
||||
u'\xad' # 0x00f0 -> SOFT HYPHEN
|
||||
u'\xb1' # 0x00f1 -> PLUS-MINUS SIGN
|
||||
u'\u03c5' # 0x00f2 -> GREEK SMALL LETTER UPSILON
|
||||
u'\u03c6' # 0x00f3 -> GREEK SMALL LETTER PHI
|
||||
u'\u03c7' # 0x00f4 -> GREEK SMALL LETTER CHI
|
||||
u'\xa7' # 0x00f5 -> SECTION SIGN
|
||||
u'\u03c8' # 0x00f6 -> GREEK SMALL LETTER PSI
|
||||
u'\u0385' # 0x00f7 -> GREEK DIALYTIKA TONOS
|
||||
u'\xb0' # 0x00f8 -> DEGREE SIGN
|
||||
u'\xa8' # 0x00f9 -> DIAERESIS
|
||||
u'\u03c9' # 0x00fa -> GREEK SMALL LETTER OMEGA
|
||||
u'\u03cb' # 0x00fb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\u03b0' # 0x00fc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
u'\u03ce' # 0x00fd -> GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
u'\u25a0' # 0x00fe -> BLACK SQUARE
|
||||
u'\xa0' # 0x00ff -> NO-BREAK SPACE
|
||||
)
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = {
|
||||
0x0000: 0x0000, # NULL
|
||||
0x0001: 0x0001, # START OF HEADING
|
||||
0x0002: 0x0002, # START OF TEXT
|
||||
0x0003: 0x0003, # END OF TEXT
|
||||
0x0004: 0x0004, # END OF TRANSMISSION
|
||||
0x0005: 0x0005, # ENQUIRY
|
||||
0x0006: 0x0006, # ACKNOWLEDGE
|
||||
0x0007: 0x0007, # BELL
|
||||
0x0008: 0x0008, # BACKSPACE
|
||||
0x0009: 0x0009, # HORIZONTAL TABULATION
|
||||
0x000a: 0x000a, # LINE FEED
|
||||
0x000b: 0x000b, # VERTICAL TABULATION
|
||||
0x000c: 0x000c, # FORM FEED
|
||||
0x000d: 0x000d, # CARRIAGE RETURN
|
||||
0x000e: 0x000e, # SHIFT OUT
|
||||
0x000f: 0x000f, # SHIFT IN
|
||||
0x0010: 0x0010, # DATA LINK ESCAPE
|
||||
0x0011: 0x0011, # DEVICE CONTROL ONE
|
||||
0x0012: 0x0012, # DEVICE CONTROL TWO
|
||||
0x0013: 0x0013, # DEVICE CONTROL THREE
|
||||
0x0014: 0x0014, # DEVICE CONTROL FOUR
|
||||
0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE
|
||||
0x0016: 0x0016, # SYNCHRONOUS IDLE
|
||||
0x0017: 0x0017, # END OF TRANSMISSION BLOCK
|
||||
0x0018: 0x0018, # CANCEL
|
||||
0x0019: 0x0019, # END OF MEDIUM
|
||||
0x001a: 0x001a, # SUBSTITUTE
|
||||
0x001b: 0x001b, # ESCAPE
|
||||
0x001c: 0x001c, # FILE SEPARATOR
|
||||
0x001d: 0x001d, # GROUP SEPARATOR
|
||||
0x001e: 0x001e, # RECORD SEPARATOR
|
||||
0x001f: 0x001f, # UNIT SEPARATOR
|
||||
0x0020: 0x0020, # SPACE
|
||||
0x0021: 0x0021, # EXCLAMATION MARK
|
||||
0x0022: 0x0022, # QUOTATION MARK
|
||||
0x0023: 0x0023, # NUMBER SIGN
|
||||
0x0024: 0x0024, # DOLLAR SIGN
|
||||
0x0025: 0x0025, # PERCENT SIGN
|
||||
0x0026: 0x0026, # AMPERSAND
|
||||
0x0027: 0x0027, # APOSTROPHE
|
||||
0x0028: 0x0028, # LEFT PARENTHESIS
|
||||
0x0029: 0x0029, # RIGHT PARENTHESIS
|
||||
0x002a: 0x002a, # ASTERISK
|
||||
0x002b: 0x002b, # PLUS SIGN
|
||||
0x002c: 0x002c, # COMMA
|
||||
0x002d: 0x002d, # HYPHEN-MINUS
|
||||
0x002e: 0x002e, # FULL STOP
|
||||
0x002f: 0x002f, # SOLIDUS
|
||||
0x0030: 0x0030, # DIGIT ZERO
|
||||
0x0031: 0x0031, # DIGIT ONE
|
||||
0x0032: 0x0032, # DIGIT TWO
|
||||
0x0033: 0x0033, # DIGIT THREE
|
||||
0x0034: 0x0034, # DIGIT FOUR
|
||||
0x0035: 0x0035, # DIGIT FIVE
|
||||
0x0036: 0x0036, # DIGIT SIX
|
||||
0x0037: 0x0037, # DIGIT SEVEN
|
||||
0x0038: 0x0038, # DIGIT EIGHT
|
||||
0x0039: 0x0039, # DIGIT NINE
|
||||
0x003a: 0x003a, # COLON
|
||||
0x003b: 0x003b, # SEMICOLON
|
||||
0x003c: 0x003c, # LESS-THAN SIGN
|
||||
0x003d: 0x003d, # EQUALS SIGN
|
||||
0x003e: 0x003e, # GREATER-THAN SIGN
|
||||
0x003f: 0x003f, # QUESTION MARK
|
||||
0x0040: 0x0040, # COMMERCIAL AT
|
||||
0x0041: 0x0041, # LATIN CAPITAL LETTER A
|
||||
0x0042: 0x0042, # LATIN CAPITAL LETTER B
|
||||
0x0043: 0x0043, # LATIN CAPITAL LETTER C
|
||||
0x0044: 0x0044, # LATIN CAPITAL LETTER D
|
||||
0x0045: 0x0045, # LATIN CAPITAL LETTER E
|
||||
0x0046: 0x0046, # LATIN CAPITAL LETTER F
|
||||
0x0047: 0x0047, # LATIN CAPITAL LETTER G
|
||||
0x0048: 0x0048, # LATIN CAPITAL LETTER H
|
||||
0x0049: 0x0049, # LATIN CAPITAL LETTER I
|
||||
0x004a: 0x004a, # LATIN CAPITAL LETTER J
|
||||
0x004b: 0x004b, # LATIN CAPITAL LETTER K
|
||||
0x004c: 0x004c, # LATIN CAPITAL LETTER L
|
||||
0x004d: 0x004d, # LATIN CAPITAL LETTER M
|
||||
0x004e: 0x004e, # LATIN CAPITAL LETTER N
|
||||
0x004f: 0x004f, # LATIN CAPITAL LETTER O
|
||||
0x0050: 0x0050, # LATIN CAPITAL LETTER P
|
||||
0x0051: 0x0051, # LATIN CAPITAL LETTER Q
|
||||
0x0052: 0x0052, # LATIN CAPITAL LETTER R
|
||||
0x0053: 0x0053, # LATIN CAPITAL LETTER S
|
||||
0x0054: 0x0054, # LATIN CAPITAL LETTER T
|
||||
0x0055: 0x0055, # LATIN CAPITAL LETTER U
|
||||
0x0056: 0x0056, # LATIN CAPITAL LETTER V
|
||||
0x0057: 0x0057, # LATIN CAPITAL LETTER W
|
||||
0x0058: 0x0058, # LATIN CAPITAL LETTER X
|
||||
0x0059: 0x0059, # LATIN CAPITAL LETTER Y
|
||||
0x005a: 0x005a, # LATIN CAPITAL LETTER Z
|
||||
0x005b: 0x005b, # LEFT SQUARE BRACKET
|
||||
0x005c: 0x005c, # REVERSE SOLIDUS
|
||||
0x005d: 0x005d, # RIGHT SQUARE BRACKET
|
||||
0x005e: 0x005e, # CIRCUMFLEX ACCENT
|
||||
0x005f: 0x005f, # LOW LINE
|
||||
0x0060: 0x0060, # GRAVE ACCENT
|
||||
0x0061: 0x0061, # LATIN SMALL LETTER A
|
||||
0x0062: 0x0062, # LATIN SMALL LETTER B
|
||||
0x0063: 0x0063, # LATIN SMALL LETTER C
|
||||
0x0064: 0x0064, # LATIN SMALL LETTER D
|
||||
0x0065: 0x0065, # LATIN SMALL LETTER E
|
||||
0x0066: 0x0066, # LATIN SMALL LETTER F
|
||||
0x0067: 0x0067, # LATIN SMALL LETTER G
|
||||
0x0068: 0x0068, # LATIN SMALL LETTER H
|
||||
0x0069: 0x0069, # LATIN SMALL LETTER I
|
||||
0x006a: 0x006a, # LATIN SMALL LETTER J
|
||||
0x006b: 0x006b, # LATIN SMALL LETTER K
|
||||
0x006c: 0x006c, # LATIN SMALL LETTER L
|
||||
0x006d: 0x006d, # LATIN SMALL LETTER M
|
||||
0x006e: 0x006e, # LATIN SMALL LETTER N
|
||||
0x006f: 0x006f, # LATIN SMALL LETTER O
|
||||
0x0070: 0x0070, # LATIN SMALL LETTER P
|
||||
0x0071: 0x0071, # LATIN SMALL LETTER Q
|
||||
0x0072: 0x0072, # LATIN SMALL LETTER R
|
||||
0x0073: 0x0073, # LATIN SMALL LETTER S
|
||||
0x0074: 0x0074, # LATIN SMALL LETTER T
|
||||
0x0075: 0x0075, # LATIN SMALL LETTER U
|
||||
0x0076: 0x0076, # LATIN SMALL LETTER V
|
||||
0x0077: 0x0077, # LATIN SMALL LETTER W
|
||||
0x0078: 0x0078, # LATIN SMALL LETTER X
|
||||
0x0079: 0x0079, # LATIN SMALL LETTER Y
|
||||
0x007a: 0x007a, # LATIN SMALL LETTER Z
|
||||
0x007b: 0x007b, # LEFT CURLY BRACKET
|
||||
0x007c: 0x007c, # VERTICAL LINE
|
||||
0x007d: 0x007d, # RIGHT CURLY BRACKET
|
||||
0x007e: 0x007e, # TILDE
|
||||
0x007f: 0x007f, # DELETE
|
||||
0x00a0: 0x00ff, # NO-BREAK SPACE
|
||||
0x00a3: 0x009c, # POUND SIGN
|
||||
0x00a6: 0x008a, # BROKEN BAR
|
||||
0x00a7: 0x00f5, # SECTION SIGN
|
||||
0x00a8: 0x00f9, # DIAERESIS
|
||||
0x00a9: 0x0097, # COPYRIGHT SIGN
|
||||
0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00ac: 0x0089, # NOT SIGN
|
||||
0x00ad: 0x00f0, # SOFT HYPHEN
|
||||
0x00b0: 0x00f8, # DEGREE SIGN
|
||||
0x00b1: 0x00f1, # PLUS-MINUS SIGN
|
||||
0x00b2: 0x0099, # SUPERSCRIPT TWO
|
||||
0x00b3: 0x009a, # SUPERSCRIPT THREE
|
||||
0x00b7: 0x0088, # MIDDLE DOT
|
||||
0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF
|
||||
0x0384: 0x00ef, # GREEK TONOS
|
||||
0x0385: 0x00f7, # GREEK DIALYTIKA TONOS
|
||||
0x0386: 0x0086, # GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
0x0388: 0x008d, # GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
0x0389: 0x008f, # GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
0x038a: 0x0090, # GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
0x038c: 0x0092, # GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
0x038e: 0x0095, # GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
0x038f: 0x0098, # GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
0x0390: 0x00a1, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
0x0391: 0x00a4, # GREEK CAPITAL LETTER ALPHA
|
||||
0x0392: 0x00a5, # GREEK CAPITAL LETTER BETA
|
||||
0x0393: 0x00a6, # GREEK CAPITAL LETTER GAMMA
|
||||
0x0394: 0x00a7, # GREEK CAPITAL LETTER DELTA
|
||||
0x0395: 0x00a8, # GREEK CAPITAL LETTER EPSILON
|
||||
0x0396: 0x00a9, # GREEK CAPITAL LETTER ZETA
|
||||
0x0397: 0x00aa, # GREEK CAPITAL LETTER ETA
|
||||
0x0398: 0x00ac, # GREEK CAPITAL LETTER THETA
|
||||
0x0399: 0x00ad, # GREEK CAPITAL LETTER IOTA
|
||||
0x039a: 0x00b5, # GREEK CAPITAL LETTER KAPPA
|
||||
0x039b: 0x00b6, # GREEK CAPITAL LETTER LAMDA
|
||||
0x039c: 0x00b7, # GREEK CAPITAL LETTER MU
|
||||
0x039d: 0x00b8, # GREEK CAPITAL LETTER NU
|
||||
0x039e: 0x00bd, # GREEK CAPITAL LETTER XI
|
||||
0x039f: 0x00be, # GREEK CAPITAL LETTER OMICRON
|
||||
0x03a0: 0x00c6, # GREEK CAPITAL LETTER PI
|
||||
0x03a1: 0x00c7, # GREEK CAPITAL LETTER RHO
|
||||
0x03a3: 0x00cf, # GREEK CAPITAL LETTER SIGMA
|
||||
0x03a4: 0x00d0, # GREEK CAPITAL LETTER TAU
|
||||
0x03a5: 0x00d1, # GREEK CAPITAL LETTER UPSILON
|
||||
0x03a6: 0x00d2, # GREEK CAPITAL LETTER PHI
|
||||
0x03a7: 0x00d3, # GREEK CAPITAL LETTER CHI
|
||||
0x03a8: 0x00d4, # GREEK CAPITAL LETTER PSI
|
||||
0x03a9: 0x00d5, # GREEK CAPITAL LETTER OMEGA
|
||||
0x03aa: 0x0091, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
0x03ab: 0x0096, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
0x03ac: 0x009b, # GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
0x03ad: 0x009d, # GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
0x03ae: 0x009e, # GREEK SMALL LETTER ETA WITH TONOS
|
||||
0x03af: 0x009f, # GREEK SMALL LETTER IOTA WITH TONOS
|
||||
0x03b0: 0x00fc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
0x03b1: 0x00d6, # GREEK SMALL LETTER ALPHA
|
||||
0x03b2: 0x00d7, # GREEK SMALL LETTER BETA
|
||||
0x03b3: 0x00d8, # GREEK SMALL LETTER GAMMA
|
||||
0x03b4: 0x00dd, # GREEK SMALL LETTER DELTA
|
||||
0x03b5: 0x00de, # GREEK SMALL LETTER EPSILON
|
||||
0x03b6: 0x00e0, # GREEK SMALL LETTER ZETA
|
||||
0x03b7: 0x00e1, # GREEK SMALL LETTER ETA
|
||||
0x03b8: 0x00e2, # GREEK SMALL LETTER THETA
|
||||
0x03b9: 0x00e3, # GREEK SMALL LETTER IOTA
|
||||
0x03ba: 0x00e4, # GREEK SMALL LETTER KAPPA
|
||||
0x03bb: 0x00e5, # GREEK SMALL LETTER LAMDA
|
||||
0x03bc: 0x00e6, # GREEK SMALL LETTER MU
|
||||
0x03bd: 0x00e7, # GREEK SMALL LETTER NU
|
||||
0x03be: 0x00e8, # GREEK SMALL LETTER XI
|
||||
0x03bf: 0x00e9, # GREEK SMALL LETTER OMICRON
|
||||
0x03c0: 0x00ea, # GREEK SMALL LETTER PI
|
||||
0x03c1: 0x00eb, # GREEK SMALL LETTER RHO
|
||||
0x03c2: 0x00ed, # GREEK SMALL LETTER FINAL SIGMA
|
||||
0x03c3: 0x00ec, # GREEK SMALL LETTER SIGMA
|
||||
0x03c4: 0x00ee, # GREEK SMALL LETTER TAU
|
||||
0x03c5: 0x00f2, # GREEK SMALL LETTER UPSILON
|
||||
0x03c6: 0x00f3, # GREEK SMALL LETTER PHI
|
||||
0x03c7: 0x00f4, # GREEK SMALL LETTER CHI
|
||||
0x03c8: 0x00f6, # GREEK SMALL LETTER PSI
|
||||
0x03c9: 0x00fa, # GREEK SMALL LETTER OMEGA
|
||||
0x03ca: 0x00a0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
0x03cb: 0x00fb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
0x03cc: 0x00a2, # GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
0x03cd: 0x00a3, # GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
0x03ce: 0x00fd, # GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
0x2015: 0x008e, # HORIZONTAL BAR
|
||||
0x2018: 0x008b, # LEFT SINGLE QUOTATION MARK
|
||||
0x2019: 0x008c, # RIGHT SINGLE QUOTATION MARK
|
||||
0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL
|
||||
0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL
|
||||
0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT
|
||||
0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT
|
||||
0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT
|
||||
0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT
|
||||
0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT
|
||||
0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT
|
||||
0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL
|
||||
0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL
|
||||
0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL
|
||||
0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL
|
||||
0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL
|
||||
0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT
|
||||
0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT
|
||||
0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT
|
||||
0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT
|
||||
0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT
|
||||
0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT
|
||||
0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL
|
||||
0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL
|
||||
0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL
|
||||
0x2580: 0x00df, # UPPER HALF BLOCK
|
||||
0x2584: 0x00dc, # LOWER HALF BLOCK
|
||||
0x2588: 0x00db, # FULL BLOCK
|
||||
0x2591: 0x00b0, # LIGHT SHADE
|
||||
0x2592: 0x00b1, # MEDIUM SHADE
|
||||
0x2593: 0x00b2, # DARK SHADE
|
||||
0x25a0: 0x00fe, # BLACK SQUARE
|
||||
}
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp874.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp874.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp874',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\u20ac' # 0x80 -> EURO SIGN
|
||||
u'\ufffe' # 0x81 -> UNDEFINED
|
||||
u'\ufffe' # 0x82 -> UNDEFINED
|
||||
u'\ufffe' # 0x83 -> UNDEFINED
|
||||
u'\ufffe' # 0x84 -> UNDEFINED
|
||||
u'\u2026' # 0x85 -> HORIZONTAL ELLIPSIS
|
||||
u'\ufffe' # 0x86 -> UNDEFINED
|
||||
u'\ufffe' # 0x87 -> UNDEFINED
|
||||
u'\ufffe' # 0x88 -> UNDEFINED
|
||||
u'\ufffe' # 0x89 -> UNDEFINED
|
||||
u'\ufffe' # 0x8A -> UNDEFINED
|
||||
u'\ufffe' # 0x8B -> UNDEFINED
|
||||
u'\ufffe' # 0x8C -> UNDEFINED
|
||||
u'\ufffe' # 0x8D -> UNDEFINED
|
||||
u'\ufffe' # 0x8E -> UNDEFINED
|
||||
u'\ufffe' # 0x8F -> UNDEFINED
|
||||
u'\ufffe' # 0x90 -> UNDEFINED
|
||||
u'\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\u2022' # 0x95 -> BULLET
|
||||
u'\u2013' # 0x96 -> EN DASH
|
||||
u'\u2014' # 0x97 -> EM DASH
|
||||
u'\ufffe' # 0x98 -> UNDEFINED
|
||||
u'\ufffe' # 0x99 -> UNDEFINED
|
||||
u'\ufffe' # 0x9A -> UNDEFINED
|
||||
u'\ufffe' # 0x9B -> UNDEFINED
|
||||
u'\ufffe' # 0x9C -> UNDEFINED
|
||||
u'\ufffe' # 0x9D -> UNDEFINED
|
||||
u'\ufffe' # 0x9E -> UNDEFINED
|
||||
u'\ufffe' # 0x9F -> UNDEFINED
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI
|
||||
u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI
|
||||
u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT
|
||||
u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI
|
||||
u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON
|
||||
u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG
|
||||
u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU
|
||||
u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN
|
||||
u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING
|
||||
u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG
|
||||
u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO
|
||||
u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE
|
||||
u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING
|
||||
u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA
|
||||
u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK
|
||||
u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN
|
||||
u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO
|
||||
u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO
|
||||
u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN
|
||||
u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK
|
||||
u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO
|
||||
u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG
|
||||
u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN
|
||||
u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG
|
||||
u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU
|
||||
u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI
|
||||
u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA
|
||||
u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG
|
||||
u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA
|
||||
u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN
|
||||
u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN
|
||||
u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO
|
||||
u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA
|
||||
u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK
|
||||
u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA
|
||||
u'\u0e24' # 0xC4 -> THAI CHARACTER RU
|
||||
u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING
|
||||
u'\u0e26' # 0xC6 -> THAI CHARACTER LU
|
||||
u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN
|
||||
u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA
|
||||
u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI
|
||||
u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA
|
||||
u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP
|
||||
u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA
|
||||
u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG
|
||||
u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK
|
||||
u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI
|
||||
u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A
|
||||
u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT
|
||||
u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA
|
||||
u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM
|
||||
u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I
|
||||
u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II
|
||||
u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE
|
||||
u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE
|
||||
u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U
|
||||
u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU
|
||||
u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU
|
||||
u'\ufffe' # 0xDB -> UNDEFINED
|
||||
u'\ufffe' # 0xDC -> UNDEFINED
|
||||
u'\ufffe' # 0xDD -> UNDEFINED
|
||||
u'\ufffe' # 0xDE -> UNDEFINED
|
||||
u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT
|
||||
u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E
|
||||
u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE
|
||||
u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O
|
||||
u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN
|
||||
u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI
|
||||
u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO
|
||||
u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK
|
||||
u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU
|
||||
u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK
|
||||
u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO
|
||||
u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI
|
||||
u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA
|
||||
u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT
|
||||
u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT
|
||||
u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN
|
||||
u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN
|
||||
u'\u0e50' # 0xF0 -> THAI DIGIT ZERO
|
||||
u'\u0e51' # 0xF1 -> THAI DIGIT ONE
|
||||
u'\u0e52' # 0xF2 -> THAI DIGIT TWO
|
||||
u'\u0e53' # 0xF3 -> THAI DIGIT THREE
|
||||
u'\u0e54' # 0xF4 -> THAI DIGIT FOUR
|
||||
u'\u0e55' # 0xF5 -> THAI DIGIT FIVE
|
||||
u'\u0e56' # 0xF6 -> THAI DIGIT SIX
|
||||
u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN
|
||||
u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT
|
||||
u'\u0e59' # 0xF9 -> THAI DIGIT NINE
|
||||
u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU
|
||||
u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT
|
||||
u'\ufffe' # 0xFC -> UNDEFINED
|
||||
u'\ufffe' # 0xFD -> UNDEFINED
|
||||
u'\ufffe' # 0xFE -> UNDEFINED
|
||||
u'\ufffe' # 0xFF -> UNDEFINED
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp875.py
Normal file
307
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/cp875.py
Normal file
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp875',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x9c' # 0x04 -> CONTROL
|
||||
u'\t' # 0x05 -> HORIZONTAL TABULATION
|
||||
u'\x86' # 0x06 -> CONTROL
|
||||
u'\x7f' # 0x07 -> DELETE
|
||||
u'\x97' # 0x08 -> CONTROL
|
||||
u'\x8d' # 0x09 -> CONTROL
|
||||
u'\x8e' # 0x0A -> CONTROL
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x9d' # 0x14 -> CONTROL
|
||||
u'\x85' # 0x15 -> CONTROL
|
||||
u'\x08' # 0x16 -> BACKSPACE
|
||||
u'\x87' # 0x17 -> CONTROL
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x92' # 0x1A -> CONTROL
|
||||
u'\x8f' # 0x1B -> CONTROL
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u'\x80' # 0x20 -> CONTROL
|
||||
u'\x81' # 0x21 -> CONTROL
|
||||
u'\x82' # 0x22 -> CONTROL
|
||||
u'\x83' # 0x23 -> CONTROL
|
||||
u'\x84' # 0x24 -> CONTROL
|
||||
u'\n' # 0x25 -> LINE FEED
|
||||
u'\x17' # 0x26 -> END OF TRANSMISSION BLOCK
|
||||
u'\x1b' # 0x27 -> ESCAPE
|
||||
u'\x88' # 0x28 -> CONTROL
|
||||
u'\x89' # 0x29 -> CONTROL
|
||||
u'\x8a' # 0x2A -> CONTROL
|
||||
u'\x8b' # 0x2B -> CONTROL
|
||||
u'\x8c' # 0x2C -> CONTROL
|
||||
u'\x05' # 0x2D -> ENQUIRY
|
||||
u'\x06' # 0x2E -> ACKNOWLEDGE
|
||||
u'\x07' # 0x2F -> BELL
|
||||
u'\x90' # 0x30 -> CONTROL
|
||||
u'\x91' # 0x31 -> CONTROL
|
||||
u'\x16' # 0x32 -> SYNCHRONOUS IDLE
|
||||
u'\x93' # 0x33 -> CONTROL
|
||||
u'\x94' # 0x34 -> CONTROL
|
||||
u'\x95' # 0x35 -> CONTROL
|
||||
u'\x96' # 0x36 -> CONTROL
|
||||
u'\x04' # 0x37 -> END OF TRANSMISSION
|
||||
u'\x98' # 0x38 -> CONTROL
|
||||
u'\x99' # 0x39 -> CONTROL
|
||||
u'\x9a' # 0x3A -> CONTROL
|
||||
u'\x9b' # 0x3B -> CONTROL
|
||||
u'\x14' # 0x3C -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x9e' # 0x3E -> CONTROL
|
||||
u'\x1a' # 0x3F -> SUBSTITUTE
|
||||
u' ' # 0x40 -> SPACE
|
||||
u'\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA
|
||||
u'\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA
|
||||
u'\u0393' # 0x43 -> GREEK CAPITAL LETTER GAMMA
|
||||
u'\u0394' # 0x44 -> GREEK CAPITAL LETTER DELTA
|
||||
u'\u0395' # 0x45 -> GREEK CAPITAL LETTER EPSILON
|
||||
u'\u0396' # 0x46 -> GREEK CAPITAL LETTER ZETA
|
||||
u'\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA
|
||||
u'\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA
|
||||
u'\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA
|
||||
u'[' # 0x4A -> LEFT SQUARE BRACKET
|
||||
u'.' # 0x4B -> FULL STOP
|
||||
u'<' # 0x4C -> LESS-THAN SIGN
|
||||
u'(' # 0x4D -> LEFT PARENTHESIS
|
||||
u'+' # 0x4E -> PLUS SIGN
|
||||
u'!' # 0x4F -> EXCLAMATION MARK
|
||||
u'&' # 0x50 -> AMPERSAND
|
||||
u'\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA
|
||||
u'\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA
|
||||
u'\u039c' # 0x53 -> GREEK CAPITAL LETTER MU
|
||||
u'\u039d' # 0x54 -> GREEK CAPITAL LETTER NU
|
||||
u'\u039e' # 0x55 -> GREEK CAPITAL LETTER XI
|
||||
u'\u039f' # 0x56 -> GREEK CAPITAL LETTER OMICRON
|
||||
u'\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI
|
||||
u'\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO
|
||||
u'\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA
|
||||
u']' # 0x5A -> RIGHT SQUARE BRACKET
|
||||
u'$' # 0x5B -> DOLLAR SIGN
|
||||
u'*' # 0x5C -> ASTERISK
|
||||
u')' # 0x5D -> RIGHT PARENTHESIS
|
||||
u';' # 0x5E -> SEMICOLON
|
||||
u'^' # 0x5F -> CIRCUMFLEX ACCENT
|
||||
u'-' # 0x60 -> HYPHEN-MINUS
|
||||
u'/' # 0x61 -> SOLIDUS
|
||||
u'\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU
|
||||
u'\u03a5' # 0x63 -> GREEK CAPITAL LETTER UPSILON
|
||||
u'\u03a6' # 0x64 -> GREEK CAPITAL LETTER PHI
|
||||
u'\u03a7' # 0x65 -> GREEK CAPITAL LETTER CHI
|
||||
u'\u03a8' # 0x66 -> GREEK CAPITAL LETTER PSI
|
||||
u'\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA
|
||||
u'\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA
|
||||
u'|' # 0x6A -> VERTICAL LINE
|
||||
u',' # 0x6B -> COMMA
|
||||
u'%' # 0x6C -> PERCENT SIGN
|
||||
u'_' # 0x6D -> LOW LINE
|
||||
u'>' # 0x6E -> GREATER-THAN SIGN
|
||||
u'?' # 0x6F -> QUESTION MARK
|
||||
u'\xa8' # 0x70 -> DIAERESIS
|
||||
u'\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS
|
||||
u'\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS
|
||||
u'\u0389' # 0x73 -> GREEK CAPITAL LETTER ETA WITH TONOS
|
||||
u'\xa0' # 0x74 -> NO-BREAK SPACE
|
||||
u'\u038a' # 0x75 -> GREEK CAPITAL LETTER IOTA WITH TONOS
|
||||
u'\u038c' # 0x76 -> GREEK CAPITAL LETTER OMICRON WITH TONOS
|
||||
u'\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS
|
||||
u'\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS
|
||||
u'`' # 0x79 -> GRAVE ACCENT
|
||||
u':' # 0x7A -> COLON
|
||||
u'#' # 0x7B -> NUMBER SIGN
|
||||
u'@' # 0x7C -> COMMERCIAL AT
|
||||
u"'" # 0x7D -> APOSTROPHE
|
||||
u'=' # 0x7E -> EQUALS SIGN
|
||||
u'"' # 0x7F -> QUOTATION MARK
|
||||
u'\u0385' # 0x80 -> GREEK DIALYTIKA TONOS
|
||||
u'a' # 0x81 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x82 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x83 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x84 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x85 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x86 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x87 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x88 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x89 -> LATIN SMALL LETTER I
|
||||
u'\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA
|
||||
u'\u03b2' # 0x8B -> GREEK SMALL LETTER BETA
|
||||
u'\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA
|
||||
u'\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA
|
||||
u'\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON
|
||||
u'\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA
|
||||
u'\xb0' # 0x90 -> DEGREE SIGN
|
||||
u'j' # 0x91 -> LATIN SMALL LETTER J
|
||||
u'k' # 0x92 -> LATIN SMALL LETTER K
|
||||
u'l' # 0x93 -> LATIN SMALL LETTER L
|
||||
u'm' # 0x94 -> LATIN SMALL LETTER M
|
||||
u'n' # 0x95 -> LATIN SMALL LETTER N
|
||||
u'o' # 0x96 -> LATIN SMALL LETTER O
|
||||
u'p' # 0x97 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x98 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x99 -> LATIN SMALL LETTER R
|
||||
u'\u03b7' # 0x9A -> GREEK SMALL LETTER ETA
|
||||
u'\u03b8' # 0x9B -> GREEK SMALL LETTER THETA
|
||||
u'\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA
|
||||
u'\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA
|
||||
u'\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA
|
||||
u'\u03bc' # 0x9F -> GREEK SMALL LETTER MU
|
||||
u'\xb4' # 0xA0 -> ACUTE ACCENT
|
||||
u'~' # 0xA1 -> TILDE
|
||||
u's' # 0xA2 -> LATIN SMALL LETTER S
|
||||
u't' # 0xA3 -> LATIN SMALL LETTER T
|
||||
u'u' # 0xA4 -> LATIN SMALL LETTER U
|
||||
u'v' # 0xA5 -> LATIN SMALL LETTER V
|
||||
u'w' # 0xA6 -> LATIN SMALL LETTER W
|
||||
u'x' # 0xA7 -> LATIN SMALL LETTER X
|
||||
u'y' # 0xA8 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0xA9 -> LATIN SMALL LETTER Z
|
||||
u'\u03bd' # 0xAA -> GREEK SMALL LETTER NU
|
||||
u'\u03be' # 0xAB -> GREEK SMALL LETTER XI
|
||||
u'\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON
|
||||
u'\u03c0' # 0xAD -> GREEK SMALL LETTER PI
|
||||
u'\u03c1' # 0xAE -> GREEK SMALL LETTER RHO
|
||||
u'\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA
|
||||
u'\xa3' # 0xB0 -> POUND SIGN
|
||||
u'\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS
|
||||
u'\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS
|
||||
u'\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS
|
||||
u'\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA
|
||||
u'\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS
|
||||
u'\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS
|
||||
u'\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS
|
||||
u'\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA
|
||||
u'\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS
|
||||
u'\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA
|
||||
u'\u03c4' # 0xBB -> GREEK SMALL LETTER TAU
|
||||
u'\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON
|
||||
u'\u03c6' # 0xBD -> GREEK SMALL LETTER PHI
|
||||
u'\u03c7' # 0xBE -> GREEK SMALL LETTER CHI
|
||||
u'\u03c8' # 0xBF -> GREEK SMALL LETTER PSI
|
||||
u'{' # 0xC0 -> LEFT CURLY BRACKET
|
||||
u'A' # 0xC1 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0xC2 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0xC3 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0xC4 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0xC5 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0xC6 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0xC7 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0xC8 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0xC9 -> LATIN CAPITAL LETTER I
|
||||
u'\xad' # 0xCA -> SOFT HYPHEN
|
||||
u'\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA
|
||||
u'\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
u'\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
u'\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK
|
||||
u'\u2015' # 0xCF -> HORIZONTAL BAR
|
||||
u'}' # 0xD0 -> RIGHT CURLY BRACKET
|
||||
u'J' # 0xD1 -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0xD2 -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0xD3 -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0xD4 -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0xD5 -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0xD6 -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0xD7 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0xD8 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0xD9 -> LATIN CAPITAL LETTER R
|
||||
u'\xb1' # 0xDA -> PLUS-MINUS SIGN
|
||||
u'\xbd' # 0xDB -> VULGAR FRACTION ONE HALF
|
||||
u'\x1a' # 0xDC -> SUBSTITUTE
|
||||
u'\u0387' # 0xDD -> GREEK ANO TELEIA
|
||||
u'\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK
|
||||
u'\xa6' # 0xDF -> BROKEN BAR
|
||||
u'\\' # 0xE0 -> REVERSE SOLIDUS
|
||||
u'\x1a' # 0xE1 -> SUBSTITUTE
|
||||
u'S' # 0xE2 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0xE3 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0xE4 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0xE5 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0xE6 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0xE7 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0xE8 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0xE9 -> LATIN CAPITAL LETTER Z
|
||||
u'\xb2' # 0xEA -> SUPERSCRIPT TWO
|
||||
u'\xa7' # 0xEB -> SECTION SIGN
|
||||
u'\x1a' # 0xEC -> SUBSTITUTE
|
||||
u'\x1a' # 0xED -> SUBSTITUTE
|
||||
u'\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xEF -> NOT SIGN
|
||||
u'0' # 0xF0 -> DIGIT ZERO
|
||||
u'1' # 0xF1 -> DIGIT ONE
|
||||
u'2' # 0xF2 -> DIGIT TWO
|
||||
u'3' # 0xF3 -> DIGIT THREE
|
||||
u'4' # 0xF4 -> DIGIT FOUR
|
||||
u'5' # 0xF5 -> DIGIT FIVE
|
||||
u'6' # 0xF6 -> DIGIT SIX
|
||||
u'7' # 0xF7 -> DIGIT SEVEN
|
||||
u'8' # 0xF8 -> DIGIT EIGHT
|
||||
u'9' # 0xF9 -> DIGIT NINE
|
||||
u'\xb3' # 0xFA -> SUPERSCRIPT THREE
|
||||
u'\xa9' # 0xFB -> COPYRIGHT SIGN
|
||||
u'\x1a' # 0xFC -> SUBSTITUTE
|
||||
u'\x1a' # 0xFD -> SUBSTITUTE
|
||||
u'\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\x9f' # 0xFF -> CONTROL
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# cp932.py: Python Unicode Codec for CP932
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_jp, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_jp.getcodec('cp932')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp932',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# cp949.py: Python Unicode Codec for CP949
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_kr, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_kr.getcodec('cp949')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp949',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# cp950.py: Python Unicode Codec for CP950
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_tw, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_tw.getcodec('cp950')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='cp950',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# euc_jis_2004.py: Python Unicode Codec for EUC_JIS_2004
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_jp, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_jp.getcodec('euc_jis_2004')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='euc_jis_2004',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# euc_jisx0213.py: Python Unicode Codec for EUC_JISX0213
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_jp, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_jp.getcodec('euc_jisx0213')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='euc_jisx0213',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# euc_jp.py: Python Unicode Codec for EUC_JP
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_jp, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_jp.getcodec('euc_jp')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='euc_jp',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# euc_kr.py: Python Unicode Codec for EUC_KR
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_kr, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_kr.getcodec('euc_kr')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='euc_kr',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# gb18030.py: Python Unicode Codec for GB18030
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_cn, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_cn.getcodec('gb18030')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='gb18030',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# gb2312.py: Python Unicode Codec for GB2312
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_cn, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_cn.getcodec('gb2312')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='gb2312',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# gbk.py: Python Unicode Codec for GBK
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_cn, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_cn.getcodec('gbk')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='gbk',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,79 @@
|
||||
""" Python 'hex_codec' Codec - 2-digit hex content transfer encoding
|
||||
|
||||
Unlike most of the other codecs which target Unicode, this codec
|
||||
will return Python string objects for both encode and decode.
|
||||
|
||||
Written by Marc-Andre Lemburg (mal@lemburg.com).
|
||||
|
||||
"""
|
||||
import codecs, binascii
|
||||
|
||||
### Codec APIs
|
||||
|
||||
def hex_encode(input,errors='strict'):
|
||||
|
||||
""" Encodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = binascii.b2a_hex(input)
|
||||
return (output, len(input))
|
||||
|
||||
def hex_decode(input,errors='strict'):
|
||||
|
||||
""" Decodes the object input and returns a tuple (output
|
||||
object, length consumed).
|
||||
|
||||
input must be an object which provides the bf_getreadbuf
|
||||
buffer slot. Python strings, buffer objects and memory
|
||||
mapped files are examples of objects providing this slot.
|
||||
|
||||
errors defines the error handling to apply. It defaults to
|
||||
'strict' handling which is the only currently supported
|
||||
error handling for this codec.
|
||||
|
||||
"""
|
||||
assert errors == 'strict'
|
||||
output = binascii.a2b_hex(input)
|
||||
return (output, len(input))
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self, input,errors='strict'):
|
||||
return hex_encode(input,errors)
|
||||
def decode(self, input,errors='strict'):
|
||||
return hex_decode(input,errors)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
assert self.errors == 'strict'
|
||||
return binascii.b2a_hex(input)
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
assert self.errors == 'strict'
|
||||
return binascii.a2b_hex(input)
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='hex',
|
||||
encode=hex_encode,
|
||||
decode=hex_decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
@@ -0,0 +1,152 @@
|
||||
""" Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py.
|
||||
|
||||
Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen)
|
||||
|
||||
Original source: LaserJet IIP Printer User's Manual HP part no
|
||||
33471-90901, Hewlet-Packard, June 1989.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_map)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_map)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_map)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_map)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='hp-roman8',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
|
||||
### Decoding Map
|
||||
|
||||
decoding_map = codecs.make_identity_dict(range(256))
|
||||
decoding_map.update({
|
||||
0x00a1: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE
|
||||
0x00a2: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
0x00a3: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE
|
||||
0x00a4: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
0x00a5: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
0x00a6: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
0x00a7: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
0x00a8: 0x00b4, # ACUTE ACCENT
|
||||
0x00a9: 0x02cb, # MODIFIER LETTER GRAVE ACCENT (Mandarin Chinese fourth tone)
|
||||
0x00aa: 0x02c6, # MODIFIER LETTER CIRCUMFLEX ACCENT
|
||||
0x00ab: 0x00a8, # DIAERESIS
|
||||
0x00ac: 0x02dc, # SMALL TILDE
|
||||
0x00ad: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE
|
||||
0x00ae: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
0x00af: 0x20a4, # LIRA SIGN
|
||||
0x00b0: 0x00af, # MACRON
|
||||
0x00b1: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
0x00b2: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE
|
||||
0x00b3: 0x00b0, # DEGREE SIGN
|
||||
0x00b4: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
0x00b5: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA
|
||||
0x00b6: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE
|
||||
0x00b7: 0x00f1, # LATIN SMALL LETTER N WITH TILDE
|
||||
0x00b8: 0x00a1, # INVERTED EXCLAMATION MARK
|
||||
0x00b9: 0x00bf, # INVERTED QUESTION MARK
|
||||
0x00ba: 0x00a4, # CURRENCY SIGN
|
||||
0x00bb: 0x00a3, # POUND SIGN
|
||||
0x00bc: 0x00a5, # YEN SIGN
|
||||
0x00bd: 0x00a7, # SECTION SIGN
|
||||
0x00be: 0x0192, # LATIN SMALL LETTER F WITH HOOK
|
||||
0x00bf: 0x00a2, # CENT SIGN
|
||||
0x00c0: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
0x00c1: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
0x00c2: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
0x00c3: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
0x00c4: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE
|
||||
0x00c5: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE
|
||||
0x00c6: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE
|
||||
0x00c7: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE
|
||||
0x00c8: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE
|
||||
0x00c9: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE
|
||||
0x00ca: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE
|
||||
0x00cb: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE
|
||||
0x00cc: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS
|
||||
0x00cd: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS
|
||||
0x00ce: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS
|
||||
0x00cf: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS
|
||||
0x00d0: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
0x00d1: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
0x00d2: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE
|
||||
0x00d3: 0x00c6, # LATIN CAPITAL LETTER AE
|
||||
0x00d4: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE
|
||||
0x00d5: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE
|
||||
0x00d6: 0x00f8, # LATIN SMALL LETTER O WITH STROKE
|
||||
0x00d7: 0x00e6, # LATIN SMALL LETTER AE
|
||||
0x00d8: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
0x00d9: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE
|
||||
0x00da: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
0x00db: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
0x00dc: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE
|
||||
0x00dd: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS
|
||||
0x00de: 0x00df, # LATIN SMALL LETTER SHARP S (German)
|
||||
0x00df: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
0x00e0: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE
|
||||
0x00e1: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE
|
||||
0x00e2: 0x00e3, # LATIN SMALL LETTER A WITH TILDE
|
||||
0x00e3: 0x00d0, # LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
0x00e4: 0x00f0, # LATIN SMALL LETTER ETH (Icelandic)
|
||||
0x00e5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0x00e6: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
0x00e7: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE
|
||||
0x00e8: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE
|
||||
0x00e9: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE
|
||||
0x00ea: 0x00f5, # LATIN SMALL LETTER O WITH TILDE
|
||||
0x00eb: 0x0160, # LATIN CAPITAL LETTER S WITH CARON
|
||||
0x00ec: 0x0161, # LATIN SMALL LETTER S WITH CARON
|
||||
0x00ed: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE
|
||||
0x00ee: 0x0178, # LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
0x00ef: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
0x00f0: 0x00de, # LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
0x00f1: 0x00fe, # LATIN SMALL LETTER THORN (Icelandic)
|
||||
0x00f2: 0x00b7, # MIDDLE DOT
|
||||
0x00f3: 0x00b5, # MICRO SIGN
|
||||
0x00f4: 0x00b6, # PILCROW SIGN
|
||||
0x00f5: 0x00be, # VULGAR FRACTION THREE QUARTERS
|
||||
0x00f6: 0x2014, # EM DASH
|
||||
0x00f7: 0x00bc, # VULGAR FRACTION ONE QUARTER
|
||||
0x00f8: 0x00bd, # VULGAR FRACTION ONE HALF
|
||||
0x00f9: 0x00aa, # FEMININE ORDINAL INDICATOR
|
||||
0x00fa: 0x00ba, # MASCULINE ORDINAL INDICATOR
|
||||
0x00fb: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00fc: 0x25a0, # BLACK SQUARE
|
||||
0x00fd: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
0x00fe: 0x00b1, # PLUS-MINUS SIGN
|
||||
0x00ff: None,
|
||||
})
|
||||
|
||||
### Encoding Map
|
||||
|
||||
encoding_map = codecs.make_encoding_map(decoding_map)
|
||||
39
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/hz.py
Normal file
39
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/hz.py
Normal file
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# hz.py: Python Unicode Codec for HZ
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_cn, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_cn.getcodec('hz')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='hz',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
288
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/idna.py
Normal file
288
AppPkg/Applications/Python/Python-2.7.10/Lib/encodings/idna.py
Normal file
@@ -0,0 +1,288 @@
|
||||
# This module implements the RFCs 3490 (IDNA) and 3491 (Nameprep)
|
||||
|
||||
import stringprep, re, codecs
|
||||
from unicodedata import ucd_3_2_0 as unicodedata
|
||||
|
||||
# IDNA section 3.1
|
||||
dots = re.compile(u"[\u002E\u3002\uFF0E\uFF61]")
|
||||
|
||||
# IDNA section 5
|
||||
ace_prefix = "xn--"
|
||||
uace_prefix = unicode(ace_prefix, "ascii")
|
||||
|
||||
# This assumes query strings, so AllowUnassigned is true
|
||||
def nameprep(label):
|
||||
# Map
|
||||
newlabel = []
|
||||
for c in label:
|
||||
if stringprep.in_table_b1(c):
|
||||
# Map to nothing
|
||||
continue
|
||||
newlabel.append(stringprep.map_table_b2(c))
|
||||
label = u"".join(newlabel)
|
||||
|
||||
# Normalize
|
||||
label = unicodedata.normalize("NFKC", label)
|
||||
|
||||
# Prohibit
|
||||
for c in label:
|
||||
if stringprep.in_table_c12(c) or \
|
||||
stringprep.in_table_c22(c) or \
|
||||
stringprep.in_table_c3(c) or \
|
||||
stringprep.in_table_c4(c) or \
|
||||
stringprep.in_table_c5(c) or \
|
||||
stringprep.in_table_c6(c) or \
|
||||
stringprep.in_table_c7(c) or \
|
||||
stringprep.in_table_c8(c) or \
|
||||
stringprep.in_table_c9(c):
|
||||
raise UnicodeError("Invalid character %r" % c)
|
||||
|
||||
# Check bidi
|
||||
RandAL = map(stringprep.in_table_d1, label)
|
||||
for c in RandAL:
|
||||
if c:
|
||||
# There is a RandAL char in the string. Must perform further
|
||||
# tests:
|
||||
# 1) The characters in section 5.8 MUST be prohibited.
|
||||
# This is table C.8, which was already checked
|
||||
# 2) If a string contains any RandALCat character, the string
|
||||
# MUST NOT contain any LCat character.
|
||||
if filter(stringprep.in_table_d2, label):
|
||||
raise UnicodeError("Violation of BIDI requirement 2")
|
||||
|
||||
# 3) If a string contains any RandALCat character, a
|
||||
# RandALCat character MUST be the first character of the
|
||||
# string, and a RandALCat character MUST be the last
|
||||
# character of the string.
|
||||
if not RandAL[0] or not RandAL[-1]:
|
||||
raise UnicodeError("Violation of BIDI requirement 3")
|
||||
|
||||
return label
|
||||
|
||||
def ToASCII(label):
|
||||
try:
|
||||
# Step 1: try ASCII
|
||||
label = label.encode("ascii")
|
||||
except UnicodeError:
|
||||
pass
|
||||
else:
|
||||
# Skip to step 3: UseSTD3ASCIIRules is false, so
|
||||
# Skip to step 8.
|
||||
if 0 < len(label) < 64:
|
||||
return label
|
||||
raise UnicodeError("label empty or too long")
|
||||
|
||||
# Step 2: nameprep
|
||||
label = nameprep(label)
|
||||
|
||||
# Step 3: UseSTD3ASCIIRules is false
|
||||
# Step 4: try ASCII
|
||||
try:
|
||||
label = label.encode("ascii")
|
||||
except UnicodeError:
|
||||
pass
|
||||
else:
|
||||
# Skip to step 8.
|
||||
if 0 < len(label) < 64:
|
||||
return label
|
||||
raise UnicodeError("label empty or too long")
|
||||
|
||||
# Step 5: Check ACE prefix
|
||||
if label.startswith(uace_prefix):
|
||||
raise UnicodeError("Label starts with ACE prefix")
|
||||
|
||||
# Step 6: Encode with PUNYCODE
|
||||
label = label.encode("punycode")
|
||||
|
||||
# Step 7: Prepend ACE prefix
|
||||
label = ace_prefix + label
|
||||
|
||||
# Step 8: Check size
|
||||
if 0 < len(label) < 64:
|
||||
return label
|
||||
raise UnicodeError("label empty or too long")
|
||||
|
||||
def ToUnicode(label):
|
||||
# Step 1: Check for ASCII
|
||||
if isinstance(label, str):
|
||||
pure_ascii = True
|
||||
else:
|
||||
try:
|
||||
label = label.encode("ascii")
|
||||
pure_ascii = True
|
||||
except UnicodeError:
|
||||
pure_ascii = False
|
||||
if not pure_ascii:
|
||||
# Step 2: Perform nameprep
|
||||
label = nameprep(label)
|
||||
# It doesn't say this, but apparently, it should be ASCII now
|
||||
try:
|
||||
label = label.encode("ascii")
|
||||
except UnicodeError:
|
||||
raise UnicodeError("Invalid character in IDN label")
|
||||
# Step 3: Check for ACE prefix
|
||||
if not label.startswith(ace_prefix):
|
||||
return unicode(label, "ascii")
|
||||
|
||||
# Step 4: Remove ACE prefix
|
||||
label1 = label[len(ace_prefix):]
|
||||
|
||||
# Step 5: Decode using PUNYCODE
|
||||
result = label1.decode("punycode")
|
||||
|
||||
# Step 6: Apply ToASCII
|
||||
label2 = ToASCII(result)
|
||||
|
||||
# Step 7: Compare the result of step 6 with the one of step 3
|
||||
# label2 will already be in lower case.
|
||||
if label.lower() != label2:
|
||||
raise UnicodeError("IDNA does not round-trip", label, label2)
|
||||
|
||||
# Step 8: return the result of step 5
|
||||
return result
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
def encode(self,input,errors='strict'):
|
||||
|
||||
if errors != 'strict':
|
||||
# IDNA is quite clear that implementations must be strict
|
||||
raise UnicodeError("unsupported error handling "+errors)
|
||||
|
||||
if not input:
|
||||
return "", 0
|
||||
|
||||
result = []
|
||||
labels = dots.split(input)
|
||||
if labels and len(labels[-1])==0:
|
||||
trailing_dot = '.'
|
||||
del labels[-1]
|
||||
else:
|
||||
trailing_dot = ''
|
||||
for label in labels:
|
||||
result.append(ToASCII(label))
|
||||
# Join with U+002E
|
||||
return ".".join(result)+trailing_dot, len(input)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
|
||||
if errors != 'strict':
|
||||
raise UnicodeError("Unsupported error handling "+errors)
|
||||
|
||||
if not input:
|
||||
return u"", 0
|
||||
|
||||
# IDNA allows decoding to operate on Unicode strings, too.
|
||||
if isinstance(input, unicode):
|
||||
labels = dots.split(input)
|
||||
else:
|
||||
# Must be ASCII string
|
||||
input = str(input)
|
||||
unicode(input, "ascii")
|
||||
labels = input.split(".")
|
||||
|
||||
if labels and len(labels[-1]) == 0:
|
||||
trailing_dot = u'.'
|
||||
del labels[-1]
|
||||
else:
|
||||
trailing_dot = u''
|
||||
|
||||
result = []
|
||||
for label in labels:
|
||||
result.append(ToUnicode(label))
|
||||
|
||||
return u".".join(result)+trailing_dot, len(input)
|
||||
|
||||
class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
|
||||
def _buffer_encode(self, input, errors, final):
|
||||
if errors != 'strict':
|
||||
# IDNA is quite clear that implementations must be strict
|
||||
raise UnicodeError("unsupported error handling "+errors)
|
||||
|
||||
if not input:
|
||||
return ("", 0)
|
||||
|
||||
labels = dots.split(input)
|
||||
trailing_dot = u''
|
||||
if labels:
|
||||
if not labels[-1]:
|
||||
trailing_dot = '.'
|
||||
del labels[-1]
|
||||
elif not final:
|
||||
# Keep potentially unfinished label until the next call
|
||||
del labels[-1]
|
||||
if labels:
|
||||
trailing_dot = '.'
|
||||
|
||||
result = []
|
||||
size = 0
|
||||
for label in labels:
|
||||
result.append(ToASCII(label))
|
||||
if size:
|
||||
size += 1
|
||||
size += len(label)
|
||||
|
||||
# Join with U+002E
|
||||
result = ".".join(result) + trailing_dot
|
||||
size += len(trailing_dot)
|
||||
return (result, size)
|
||||
|
||||
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
|
||||
def _buffer_decode(self, input, errors, final):
|
||||
if errors != 'strict':
|
||||
raise UnicodeError("Unsupported error handling "+errors)
|
||||
|
||||
if not input:
|
||||
return (u"", 0)
|
||||
|
||||
# IDNA allows decoding to operate on Unicode strings, too.
|
||||
if isinstance(input, unicode):
|
||||
labels = dots.split(input)
|
||||
else:
|
||||
# Must be ASCII string
|
||||
input = str(input)
|
||||
unicode(input, "ascii")
|
||||
labels = input.split(".")
|
||||
|
||||
trailing_dot = u''
|
||||
if labels:
|
||||
if not labels[-1]:
|
||||
trailing_dot = u'.'
|
||||
del labels[-1]
|
||||
elif not final:
|
||||
# Keep potentially unfinished label until the next call
|
||||
del labels[-1]
|
||||
if labels:
|
||||
trailing_dot = u'.'
|
||||
|
||||
result = []
|
||||
size = 0
|
||||
for label in labels:
|
||||
result.append(ToUnicode(label))
|
||||
if size:
|
||||
size += 1
|
||||
size += len(label)
|
||||
|
||||
result = u".".join(result) + trailing_dot
|
||||
size += len(trailing_dot)
|
||||
return (result, size)
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='idna',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamwriter=StreamWriter,
|
||||
streamreader=StreamReader,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp.py: Python Unicode Codec for ISO2022_JP
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp_1.py: Python Unicode Codec for ISO2022_JP_1
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp_1')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp_1',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp_2.py: Python Unicode Codec for ISO2022_JP_2
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp_2')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp_2',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp_2004.py: Python Unicode Codec for ISO2022_JP_2004
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp_2004')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp_2004',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp_3.py: Python Unicode Codec for ISO2022_JP_3
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp_3')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp_3',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_jp_ext.py: Python Unicode Codec for ISO2022_JP_EXT
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_jp_ext')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_jp_ext',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,39 @@
|
||||
#
|
||||
# iso2022_kr.py: Python Unicode Codec for ISO2022_KR
|
||||
#
|
||||
# Written by Hye-Shik Chang <perky@FreeBSD.org>
|
||||
#
|
||||
|
||||
import _codecs_iso2022, codecs
|
||||
import _multibytecodec as mbc
|
||||
|
||||
codec = _codecs_iso2022.getcodec('iso2022_kr')
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
encode = codec.encode
|
||||
decode = codec.decode
|
||||
|
||||
class IncrementalEncoder(mbc.MultibyteIncrementalEncoder,
|
||||
codecs.IncrementalEncoder):
|
||||
codec = codec
|
||||
|
||||
class IncrementalDecoder(mbc.MultibyteIncrementalDecoder,
|
||||
codecs.IncrementalDecoder):
|
||||
codec = codec
|
||||
|
||||
class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader):
|
||||
codec = codec
|
||||
|
||||
class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter):
|
||||
codec = codec
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso2022_kr',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_1 generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-1',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic)
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic)
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_10 generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-10',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u0112' # 0xA2 -> LATIN CAPITAL LETTER E WITH MACRON
|
||||
u'\u0122' # 0xA3 -> LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
u'\u012a' # 0xA4 -> LATIN CAPITAL LETTER I WITH MACRON
|
||||
u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE
|
||||
u'\u0136' # 0xA6 -> LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\u013b' # 0xA8 -> LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
u'\u0110' # 0xA9 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u0160' # 0xAA -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u0166' # 0xAB -> LATIN CAPITAL LETTER T WITH STROKE
|
||||
u'\u017d' # 0xAC -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u016a' # 0xAE -> LATIN CAPITAL LETTER U WITH MACRON
|
||||
u'\u014a' # 0xAF -> LATIN CAPITAL LETTER ENG
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u0113' # 0xB2 -> LATIN SMALL LETTER E WITH MACRON
|
||||
u'\u0123' # 0xB3 -> LATIN SMALL LETTER G WITH CEDILLA
|
||||
u'\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON
|
||||
u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE
|
||||
u'\u0137' # 0xB6 -> LATIN SMALL LETTER K WITH CEDILLA
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\u013c' # 0xB8 -> LATIN SMALL LETTER L WITH CEDILLA
|
||||
u'\u0111' # 0xB9 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0161' # 0xBA -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0167' # 0xBB -> LATIN SMALL LETTER T WITH STROKE
|
||||
u'\u017e' # 0xBC -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u2015' # 0xBD -> HORIZONTAL BAR
|
||||
u'\u016b' # 0xBE -> LATIN SMALL LETTER U WITH MACRON
|
||||
u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG
|
||||
u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic)
|
||||
u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\u0168' # 0xD7 -> LATIN CAPITAL LETTER U WITH TILDE
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic)
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
|
||||
u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic)
|
||||
u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA
|
||||
u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\u0169' # 0xF7 -> LATIN SMALL LETTER U WITH TILDE
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic)
|
||||
u'\u0138' # 0xFF -> LATIN SMALL LETTER KRA
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_11 generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-11',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0e01' # 0xA1 -> THAI CHARACTER KO KAI
|
||||
u'\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI
|
||||
u'\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT
|
||||
u'\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI
|
||||
u'\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON
|
||||
u'\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG
|
||||
u'\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU
|
||||
u'\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN
|
||||
u'\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING
|
||||
u'\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG
|
||||
u'\u0e0b' # 0xAB -> THAI CHARACTER SO SO
|
||||
u'\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE
|
||||
u'\u0e0d' # 0xAD -> THAI CHARACTER YO YING
|
||||
u'\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA
|
||||
u'\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK
|
||||
u'\u0e10' # 0xB0 -> THAI CHARACTER THO THAN
|
||||
u'\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO
|
||||
u'\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO
|
||||
u'\u0e13' # 0xB3 -> THAI CHARACTER NO NEN
|
||||
u'\u0e14' # 0xB4 -> THAI CHARACTER DO DEK
|
||||
u'\u0e15' # 0xB5 -> THAI CHARACTER TO TAO
|
||||
u'\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG
|
||||
u'\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN
|
||||
u'\u0e18' # 0xB8 -> THAI CHARACTER THO THONG
|
||||
u'\u0e19' # 0xB9 -> THAI CHARACTER NO NU
|
||||
u'\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI
|
||||
u'\u0e1b' # 0xBB -> THAI CHARACTER PO PLA
|
||||
u'\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG
|
||||
u'\u0e1d' # 0xBD -> THAI CHARACTER FO FA
|
||||
u'\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN
|
||||
u'\u0e1f' # 0xBF -> THAI CHARACTER FO FAN
|
||||
u'\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO
|
||||
u'\u0e21' # 0xC1 -> THAI CHARACTER MO MA
|
||||
u'\u0e22' # 0xC2 -> THAI CHARACTER YO YAK
|
||||
u'\u0e23' # 0xC3 -> THAI CHARACTER RO RUA
|
||||
u'\u0e24' # 0xC4 -> THAI CHARACTER RU
|
||||
u'\u0e25' # 0xC5 -> THAI CHARACTER LO LING
|
||||
u'\u0e26' # 0xC6 -> THAI CHARACTER LU
|
||||
u'\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN
|
||||
u'\u0e28' # 0xC8 -> THAI CHARACTER SO SALA
|
||||
u'\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI
|
||||
u'\u0e2a' # 0xCA -> THAI CHARACTER SO SUA
|
||||
u'\u0e2b' # 0xCB -> THAI CHARACTER HO HIP
|
||||
u'\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA
|
||||
u'\u0e2d' # 0xCD -> THAI CHARACTER O ANG
|
||||
u'\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK
|
||||
u'\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI
|
||||
u'\u0e30' # 0xD0 -> THAI CHARACTER SARA A
|
||||
u'\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT
|
||||
u'\u0e32' # 0xD2 -> THAI CHARACTER SARA AA
|
||||
u'\u0e33' # 0xD3 -> THAI CHARACTER SARA AM
|
||||
u'\u0e34' # 0xD4 -> THAI CHARACTER SARA I
|
||||
u'\u0e35' # 0xD5 -> THAI CHARACTER SARA II
|
||||
u'\u0e36' # 0xD6 -> THAI CHARACTER SARA UE
|
||||
u'\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE
|
||||
u'\u0e38' # 0xD8 -> THAI CHARACTER SARA U
|
||||
u'\u0e39' # 0xD9 -> THAI CHARACTER SARA UU
|
||||
u'\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT
|
||||
u'\u0e40' # 0xE0 -> THAI CHARACTER SARA E
|
||||
u'\u0e41' # 0xE1 -> THAI CHARACTER SARA AE
|
||||
u'\u0e42' # 0xE2 -> THAI CHARACTER SARA O
|
||||
u'\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN
|
||||
u'\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI
|
||||
u'\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO
|
||||
u'\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK
|
||||
u'\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU
|
||||
u'\u0e48' # 0xE8 -> THAI CHARACTER MAI EK
|
||||
u'\u0e49' # 0xE9 -> THAI CHARACTER MAI THO
|
||||
u'\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI
|
||||
u'\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA
|
||||
u'\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT
|
||||
u'\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT
|
||||
u'\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN
|
||||
u'\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN
|
||||
u'\u0e50' # 0xF0 -> THAI DIGIT ZERO
|
||||
u'\u0e51' # 0xF1 -> THAI DIGIT ONE
|
||||
u'\u0e52' # 0xF2 -> THAI DIGIT TWO
|
||||
u'\u0e53' # 0xF3 -> THAI DIGIT THREE
|
||||
u'\u0e54' # 0xF4 -> THAI DIGIT FOUR
|
||||
u'\u0e55' # 0xF5 -> THAI DIGIT FIVE
|
||||
u'\u0e56' # 0xF6 -> THAI DIGIT SIX
|
||||
u'\u0e57' # 0xF7 -> THAI DIGIT SEVEN
|
||||
u'\u0e58' # 0xF8 -> THAI DIGIT EIGHT
|
||||
u'\u0e59' # 0xF9 -> THAI DIGIT NINE
|
||||
u'\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU
|
||||
u'\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_13 generated from 'MAPPINGS/ISO8859/8859-13.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-13',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u201d' # 0xA1 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\xa6' # 0xA6 -> BROKEN BAR
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xc6' # 0xAF -> LATIN CAPITAL LETTER AE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\u201c' # 0xB4 -> LEFT DOUBLE QUOTATION MARK
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS
|
||||
u'\xe6' # 0xBF -> LATIN SMALL LETTER AE
|
||||
u'\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK
|
||||
u'\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON
|
||||
u'\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
u'\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
u'\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
u'\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON
|
||||
u'\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
u'\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK
|
||||
u'\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German)
|
||||
u'\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK
|
||||
u'\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON
|
||||
u'\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
u'\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA
|
||||
u'\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA
|
||||
u'\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON
|
||||
u'\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA
|
||||
u'\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK
|
||||
u'\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u2019' # 0xFF -> RIGHT SINGLE QUOTATION MARK
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_14 generated from 'MAPPINGS/ISO8859/8859-14.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-14',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u1e02' # 0xA1 -> LATIN CAPITAL LETTER B WITH DOT ABOVE
|
||||
u'\u1e03' # 0xA2 -> LATIN SMALL LETTER B WITH DOT ABOVE
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\u010a' # 0xA4 -> LATIN CAPITAL LETTER C WITH DOT ABOVE
|
||||
u'\u010b' # 0xA5 -> LATIN SMALL LETTER C WITH DOT ABOVE
|
||||
u'\u1e0a' # 0xA6 -> LATIN CAPITAL LETTER D WITH DOT ABOVE
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\u1e80' # 0xA8 -> LATIN CAPITAL LETTER W WITH GRAVE
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u1e82' # 0xAA -> LATIN CAPITAL LETTER W WITH ACUTE
|
||||
u'\u1e0b' # 0xAB -> LATIN SMALL LETTER D WITH DOT ABOVE
|
||||
u'\u1ef2' # 0xAC -> LATIN CAPITAL LETTER Y WITH GRAVE
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\u0178' # 0xAF -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\u1e1e' # 0xB0 -> LATIN CAPITAL LETTER F WITH DOT ABOVE
|
||||
u'\u1e1f' # 0xB1 -> LATIN SMALL LETTER F WITH DOT ABOVE
|
||||
u'\u0120' # 0xB2 -> LATIN CAPITAL LETTER G WITH DOT ABOVE
|
||||
u'\u0121' # 0xB3 -> LATIN SMALL LETTER G WITH DOT ABOVE
|
||||
u'\u1e40' # 0xB4 -> LATIN CAPITAL LETTER M WITH DOT ABOVE
|
||||
u'\u1e41' # 0xB5 -> LATIN SMALL LETTER M WITH DOT ABOVE
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\u1e56' # 0xB7 -> LATIN CAPITAL LETTER P WITH DOT ABOVE
|
||||
u'\u1e81' # 0xB8 -> LATIN SMALL LETTER W WITH GRAVE
|
||||
u'\u1e57' # 0xB9 -> LATIN SMALL LETTER P WITH DOT ABOVE
|
||||
u'\u1e83' # 0xBA -> LATIN SMALL LETTER W WITH ACUTE
|
||||
u'\u1e60' # 0xBB -> LATIN CAPITAL LETTER S WITH DOT ABOVE
|
||||
u'\u1ef3' # 0xBC -> LATIN SMALL LETTER Y WITH GRAVE
|
||||
u'\u1e84' # 0xBD -> LATIN CAPITAL LETTER W WITH DIAERESIS
|
||||
u'\u1e85' # 0xBE -> LATIN SMALL LETTER W WITH DIAERESIS
|
||||
u'\u1e61' # 0xBF -> LATIN SMALL LETTER S WITH DOT ABOVE
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u0174' # 0xD0 -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\u1e6a' # 0xD7 -> LATIN CAPITAL LETTER T WITH DOT ABOVE
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\u0176' # 0xDE -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\u0175' # 0xF0 -> LATIN SMALL LETTER W WITH CIRCUMFLEX
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\u1e6b' # 0xF7 -> LATIN SMALL LETTER T WITH DOT ABOVE
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\u0177' # 0xFE -> LATIN SMALL LETTER Y WITH CIRCUMFLEX
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_15 generated from 'MAPPINGS/ISO8859/8859-15.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-15',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK
|
||||
u'\xa2' # 0xA2 -> CENT SIGN
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\u20ac' # 0xA4 -> EURO SIGN
|
||||
u'\xa5' # 0xA5 -> YEN SIGN
|
||||
u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\xac' # 0xAC -> NOT SIGN
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\xae' # 0xAE -> REGISTERED SIGN
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\xb9' # 0xB9 -> SUPERSCRIPT ONE
|
||||
u'\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE
|
||||
u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE
|
||||
u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\xbf' # 0xBF -> INVERTED QUESTION MARK
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\xde' # 0xDE -> LATIN CAPITAL LETTER THORN
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\xf0' # 0xF0 -> LATIN SMALL LETTER ETH
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\xfe' # 0xFE -> LATIN SMALL LETTER THORN
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_16 generated from 'MAPPINGS/ISO8859/8859-16.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-16',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u0105' # 0xA2 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\u20ac' # 0xA4 -> EURO SIGN
|
||||
u'\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK
|
||||
u'\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\xa9' # 0xA9 -> COPYRIGHT SIGN
|
||||
u'\u0218' # 0xAA -> LATIN CAPITAL LETTER S WITH COMMA BELOW
|
||||
u'\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u017a' # 0xAE -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\xb1' # 0xB1 -> PLUS-MINUS SIGN
|
||||
u'\u010c' # 0xB2 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\u201d' # 0xB5 -> RIGHT DOUBLE QUOTATION MARK
|
||||
u'\xb6' # 0xB6 -> PILCROW SIGN
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u010d' # 0xB9 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\u0219' # 0xBA -> LATIN SMALL LETTER S WITH COMMA BELOW
|
||||
u'\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
|
||||
u'\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE
|
||||
u'\u0153' # 0xBD -> LATIN SMALL LIGATURE OE
|
||||
u'\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS
|
||||
u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\u0106' # 0xC5 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\u015a' # 0xD7 -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\u0170' # 0xD8 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u0118' # 0xDD -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u0107' # 0xE5 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\u015b' # 0xF7 -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\u0171' # 0xF8 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u0119' # 0xFD -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\u021b' # 0xFE -> LATIN SMALL LETTER T WITH COMMA BELOW
|
||||
u'\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_2 generated from 'MAPPINGS/ISO8859/8859-2.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-2',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u02d8' # 0xA2 -> BREVE
|
||||
u'\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\u013d' # 0xA5 -> LATIN CAPITAL LETTER L WITH CARON
|
||||
u'\u015a' # 0xA6 -> LATIN CAPITAL LETTER S WITH ACUTE
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\u0164' # 0xAB -> LATIN CAPITAL LETTER T WITH CARON
|
||||
u'\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u02db' # 0xB2 -> OGONEK
|
||||
u'\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\u013e' # 0xB5 -> LATIN SMALL LETTER L WITH CARON
|
||||
u'\u015b' # 0xB6 -> LATIN SMALL LETTER S WITH ACUTE
|
||||
u'\u02c7' # 0xB7 -> CARON
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\u0165' # 0xBB -> LATIN SMALL LETTER T WITH CARON
|
||||
u'\u017a' # 0xBC -> LATIN SMALL LETTER Z WITH ACUTE
|
||||
u'\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT
|
||||
u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE
|
||||
u'\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON
|
||||
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE
|
||||
u'\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON
|
||||
u'\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE
|
||||
u'\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE
|
||||
u'\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON
|
||||
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE
|
||||
u'\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON
|
||||
u'\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE
|
||||
u'\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA
|
||||
u'\u02d9' # 0xFF -> DOT ABOVE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_3 generated from 'MAPPINGS/ISO8859/8859-3.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-3',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0126' # 0xA1 -> LATIN CAPITAL LETTER H WITH STROKE
|
||||
u'\u02d8' # 0xA2 -> BREVE
|
||||
u'\xa3' # 0xA3 -> POUND SIGN
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\ufffe'
|
||||
u'\u0124' # 0xA6 -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\u0130' # 0xA9 -> LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
u'\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA
|
||||
u'\u011e' # 0xAB -> LATIN CAPITAL LETTER G WITH BREVE
|
||||
u'\u0134' # 0xAC -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\ufffe'
|
||||
u'\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\u0127' # 0xB1 -> LATIN SMALL LETTER H WITH STROKE
|
||||
u'\xb2' # 0xB2 -> SUPERSCRIPT TWO
|
||||
u'\xb3' # 0xB3 -> SUPERSCRIPT THREE
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\xb5' # 0xB5 -> MICRO SIGN
|
||||
u'\u0125' # 0xB6 -> LATIN SMALL LETTER H WITH CIRCUMFLEX
|
||||
u'\xb7' # 0xB7 -> MIDDLE DOT
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\u0131' # 0xB9 -> LATIN SMALL LETTER DOTLESS I
|
||||
u'\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA
|
||||
u'\u011f' # 0xBB -> LATIN SMALL LETTER G WITH BREVE
|
||||
u'\u0135' # 0xBC -> LATIN SMALL LETTER J WITH CIRCUMFLEX
|
||||
u'\xbd' # 0xBD -> VULGAR FRACTION ONE HALF
|
||||
u'\ufffe'
|
||||
u'\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE
|
||||
u'\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\ufffe'
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\u010a' # 0xC5 -> LATIN CAPITAL LETTER C WITH DOT ABOVE
|
||||
u'\u0108' # 0xC6 -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX
|
||||
u'\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA
|
||||
u'\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS
|
||||
u'\ufffe'
|
||||
u'\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE
|
||||
u'\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE
|
||||
u'\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0120' # 0xD5 -> LATIN CAPITAL LETTER G WITH DOT ABOVE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\u011c' # 0xD8 -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX
|
||||
u'\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u016c' # 0xDD -> LATIN CAPITAL LETTER U WITH BREVE
|
||||
u'\u015c' # 0xDE -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\ufffe'
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\u010b' # 0xE5 -> LATIN SMALL LETTER C WITH DOT ABOVE
|
||||
u'\u0109' # 0xE6 -> LATIN SMALL LETTER C WITH CIRCUMFLEX
|
||||
u'\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA
|
||||
u'\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS
|
||||
u'\ufffe'
|
||||
u'\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE
|
||||
u'\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE
|
||||
u'\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\u0121' # 0xF5 -> LATIN SMALL LETTER G WITH DOT ABOVE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\u011d' # 0xF8 -> LATIN SMALL LETTER G WITH CIRCUMFLEX
|
||||
u'\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u016d' # 0xFD -> LATIN SMALL LETTER U WITH BREVE
|
||||
u'\u015d' # 0xFE -> LATIN SMALL LETTER S WITH CIRCUMFLEX
|
||||
u'\u02d9' # 0xFF -> DOT ABOVE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_4 generated from 'MAPPINGS/ISO8859/8859-4.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-4',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK
|
||||
u'\u0138' # 0xA2 -> LATIN SMALL LETTER KRA
|
||||
u'\u0156' # 0xA3 -> LATIN CAPITAL LETTER R WITH CEDILLA
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE
|
||||
u'\u013b' # 0xA6 -> LATIN CAPITAL LETTER L WITH CEDILLA
|
||||
u'\xa7' # 0xA7 -> SECTION SIGN
|
||||
u'\xa8' # 0xA8 -> DIAERESIS
|
||||
u'\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON
|
||||
u'\u0112' # 0xAA -> LATIN CAPITAL LETTER E WITH MACRON
|
||||
u'\u0122' # 0xAB -> LATIN CAPITAL LETTER G WITH CEDILLA
|
||||
u'\u0166' # 0xAC -> LATIN CAPITAL LETTER T WITH STROKE
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON
|
||||
u'\xaf' # 0xAF -> MACRON
|
||||
u'\xb0' # 0xB0 -> DEGREE SIGN
|
||||
u'\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK
|
||||
u'\u02db' # 0xB2 -> OGONEK
|
||||
u'\u0157' # 0xB3 -> LATIN SMALL LETTER R WITH CEDILLA
|
||||
u'\xb4' # 0xB4 -> ACUTE ACCENT
|
||||
u'\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE
|
||||
u'\u013c' # 0xB6 -> LATIN SMALL LETTER L WITH CEDILLA
|
||||
u'\u02c7' # 0xB7 -> CARON
|
||||
u'\xb8' # 0xB8 -> CEDILLA
|
||||
u'\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON
|
||||
u'\u0113' # 0xBA -> LATIN SMALL LETTER E WITH MACRON
|
||||
u'\u0123' # 0xBB -> LATIN SMALL LETTER G WITH CEDILLA
|
||||
u'\u0167' # 0xBC -> LATIN SMALL LETTER T WITH STROKE
|
||||
u'\u014a' # 0xBD -> LATIN CAPITAL LETTER ENG
|
||||
u'\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON
|
||||
u'\u014b' # 0xBF -> LATIN SMALL LETTER ENG
|
||||
u'\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON
|
||||
u'\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE
|
||||
u'\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX
|
||||
u'\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE
|
||||
u'\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS
|
||||
u'\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE
|
||||
u'\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE
|
||||
u'\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK
|
||||
u'\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON
|
||||
u'\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE
|
||||
u'\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK
|
||||
u'\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS
|
||||
u'\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE
|
||||
u'\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE
|
||||
u'\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX
|
||||
u'\u012a' # 0xCF -> LATIN CAPITAL LETTER I WITH MACRON
|
||||
u'\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE
|
||||
u'\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA
|
||||
u'\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON
|
||||
u'\u0136' # 0xD3 -> LATIN CAPITAL LETTER K WITH CEDILLA
|
||||
u'\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX
|
||||
u'\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE
|
||||
u'\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS
|
||||
u'\xd7' # 0xD7 -> MULTIPLICATION SIGN
|
||||
u'\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE
|
||||
u'\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK
|
||||
u'\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE
|
||||
u'\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX
|
||||
u'\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS
|
||||
u'\u0168' # 0xDD -> LATIN CAPITAL LETTER U WITH TILDE
|
||||
u'\u016a' # 0xDE -> LATIN CAPITAL LETTER U WITH MACRON
|
||||
u'\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S
|
||||
u'\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON
|
||||
u'\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE
|
||||
u'\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX
|
||||
u'\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE
|
||||
u'\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS
|
||||
u'\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE
|
||||
u'\xe6' # 0xE6 -> LATIN SMALL LETTER AE
|
||||
u'\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK
|
||||
u'\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON
|
||||
u'\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE
|
||||
u'\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK
|
||||
u'\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS
|
||||
u'\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE
|
||||
u'\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE
|
||||
u'\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX
|
||||
u'\u012b' # 0xEF -> LATIN SMALL LETTER I WITH MACRON
|
||||
u'\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE
|
||||
u'\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA
|
||||
u'\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON
|
||||
u'\u0137' # 0xF3 -> LATIN SMALL LETTER K WITH CEDILLA
|
||||
u'\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX
|
||||
u'\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE
|
||||
u'\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS
|
||||
u'\xf7' # 0xF7 -> DIVISION SIGN
|
||||
u'\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE
|
||||
u'\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK
|
||||
u'\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE
|
||||
u'\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX
|
||||
u'\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS
|
||||
u'\u0169' # 0xFD -> LATIN SMALL LETTER U WITH TILDE
|
||||
u'\u016b' # 0xFE -> LATIN SMALL LETTER U WITH MACRON
|
||||
u'\u02d9' # 0xFF -> DOT ABOVE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_5 generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-5',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\u0401' # 0xA1 -> CYRILLIC CAPITAL LETTER IO
|
||||
u'\u0402' # 0xA2 -> CYRILLIC CAPITAL LETTER DJE
|
||||
u'\u0403' # 0xA3 -> CYRILLIC CAPITAL LETTER GJE
|
||||
u'\u0404' # 0xA4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE
|
||||
u'\u0405' # 0xA5 -> CYRILLIC CAPITAL LETTER DZE
|
||||
u'\u0406' # 0xA6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0407' # 0xA7 -> CYRILLIC CAPITAL LETTER YI
|
||||
u'\u0408' # 0xA8 -> CYRILLIC CAPITAL LETTER JE
|
||||
u'\u0409' # 0xA9 -> CYRILLIC CAPITAL LETTER LJE
|
||||
u'\u040a' # 0xAA -> CYRILLIC CAPITAL LETTER NJE
|
||||
u'\u040b' # 0xAB -> CYRILLIC CAPITAL LETTER TSHE
|
||||
u'\u040c' # 0xAC -> CYRILLIC CAPITAL LETTER KJE
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\u040e' # 0xAE -> CYRILLIC CAPITAL LETTER SHORT U
|
||||
u'\u040f' # 0xAF -> CYRILLIC CAPITAL LETTER DZHE
|
||||
u'\u0410' # 0xB0 -> CYRILLIC CAPITAL LETTER A
|
||||
u'\u0411' # 0xB1 -> CYRILLIC CAPITAL LETTER BE
|
||||
u'\u0412' # 0xB2 -> CYRILLIC CAPITAL LETTER VE
|
||||
u'\u0413' # 0xB3 -> CYRILLIC CAPITAL LETTER GHE
|
||||
u'\u0414' # 0xB4 -> CYRILLIC CAPITAL LETTER DE
|
||||
u'\u0415' # 0xB5 -> CYRILLIC CAPITAL LETTER IE
|
||||
u'\u0416' # 0xB6 -> CYRILLIC CAPITAL LETTER ZHE
|
||||
u'\u0417' # 0xB7 -> CYRILLIC CAPITAL LETTER ZE
|
||||
u'\u0418' # 0xB8 -> CYRILLIC CAPITAL LETTER I
|
||||
u'\u0419' # 0xB9 -> CYRILLIC CAPITAL LETTER SHORT I
|
||||
u'\u041a' # 0xBA -> CYRILLIC CAPITAL LETTER KA
|
||||
u'\u041b' # 0xBB -> CYRILLIC CAPITAL LETTER EL
|
||||
u'\u041c' # 0xBC -> CYRILLIC CAPITAL LETTER EM
|
||||
u'\u041d' # 0xBD -> CYRILLIC CAPITAL LETTER EN
|
||||
u'\u041e' # 0xBE -> CYRILLIC CAPITAL LETTER O
|
||||
u'\u041f' # 0xBF -> CYRILLIC CAPITAL LETTER PE
|
||||
u'\u0420' # 0xC0 -> CYRILLIC CAPITAL LETTER ER
|
||||
u'\u0421' # 0xC1 -> CYRILLIC CAPITAL LETTER ES
|
||||
u'\u0422' # 0xC2 -> CYRILLIC CAPITAL LETTER TE
|
||||
u'\u0423' # 0xC3 -> CYRILLIC CAPITAL LETTER U
|
||||
u'\u0424' # 0xC4 -> CYRILLIC CAPITAL LETTER EF
|
||||
u'\u0425' # 0xC5 -> CYRILLIC CAPITAL LETTER HA
|
||||
u'\u0426' # 0xC6 -> CYRILLIC CAPITAL LETTER TSE
|
||||
u'\u0427' # 0xC7 -> CYRILLIC CAPITAL LETTER CHE
|
||||
u'\u0428' # 0xC8 -> CYRILLIC CAPITAL LETTER SHA
|
||||
u'\u0429' # 0xC9 -> CYRILLIC CAPITAL LETTER SHCHA
|
||||
u'\u042a' # 0xCA -> CYRILLIC CAPITAL LETTER HARD SIGN
|
||||
u'\u042b' # 0xCB -> CYRILLIC CAPITAL LETTER YERU
|
||||
u'\u042c' # 0xCC -> CYRILLIC CAPITAL LETTER SOFT SIGN
|
||||
u'\u042d' # 0xCD -> CYRILLIC CAPITAL LETTER E
|
||||
u'\u042e' # 0xCE -> CYRILLIC CAPITAL LETTER YU
|
||||
u'\u042f' # 0xCF -> CYRILLIC CAPITAL LETTER YA
|
||||
u'\u0430' # 0xD0 -> CYRILLIC SMALL LETTER A
|
||||
u'\u0431' # 0xD1 -> CYRILLIC SMALL LETTER BE
|
||||
u'\u0432' # 0xD2 -> CYRILLIC SMALL LETTER VE
|
||||
u'\u0433' # 0xD3 -> CYRILLIC SMALL LETTER GHE
|
||||
u'\u0434' # 0xD4 -> CYRILLIC SMALL LETTER DE
|
||||
u'\u0435' # 0xD5 -> CYRILLIC SMALL LETTER IE
|
||||
u'\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE
|
||||
u'\u0437' # 0xD7 -> CYRILLIC SMALL LETTER ZE
|
||||
u'\u0438' # 0xD8 -> CYRILLIC SMALL LETTER I
|
||||
u'\u0439' # 0xD9 -> CYRILLIC SMALL LETTER SHORT I
|
||||
u'\u043a' # 0xDA -> CYRILLIC SMALL LETTER KA
|
||||
u'\u043b' # 0xDB -> CYRILLIC SMALL LETTER EL
|
||||
u'\u043c' # 0xDC -> CYRILLIC SMALL LETTER EM
|
||||
u'\u043d' # 0xDD -> CYRILLIC SMALL LETTER EN
|
||||
u'\u043e' # 0xDE -> CYRILLIC SMALL LETTER O
|
||||
u'\u043f' # 0xDF -> CYRILLIC SMALL LETTER PE
|
||||
u'\u0440' # 0xE0 -> CYRILLIC SMALL LETTER ER
|
||||
u'\u0441' # 0xE1 -> CYRILLIC SMALL LETTER ES
|
||||
u'\u0442' # 0xE2 -> CYRILLIC SMALL LETTER TE
|
||||
u'\u0443' # 0xE3 -> CYRILLIC SMALL LETTER U
|
||||
u'\u0444' # 0xE4 -> CYRILLIC SMALL LETTER EF
|
||||
u'\u0445' # 0xE5 -> CYRILLIC SMALL LETTER HA
|
||||
u'\u0446' # 0xE6 -> CYRILLIC SMALL LETTER TSE
|
||||
u'\u0447' # 0xE7 -> CYRILLIC SMALL LETTER CHE
|
||||
u'\u0448' # 0xE8 -> CYRILLIC SMALL LETTER SHA
|
||||
u'\u0449' # 0xE9 -> CYRILLIC SMALL LETTER SHCHA
|
||||
u'\u044a' # 0xEA -> CYRILLIC SMALL LETTER HARD SIGN
|
||||
u'\u044b' # 0xEB -> CYRILLIC SMALL LETTER YERU
|
||||
u'\u044c' # 0xEC -> CYRILLIC SMALL LETTER SOFT SIGN
|
||||
u'\u044d' # 0xED -> CYRILLIC SMALL LETTER E
|
||||
u'\u044e' # 0xEE -> CYRILLIC SMALL LETTER YU
|
||||
u'\u044f' # 0xEF -> CYRILLIC SMALL LETTER YA
|
||||
u'\u2116' # 0xF0 -> NUMERO SIGN
|
||||
u'\u0451' # 0xF1 -> CYRILLIC SMALL LETTER IO
|
||||
u'\u0452' # 0xF2 -> CYRILLIC SMALL LETTER DJE
|
||||
u'\u0453' # 0xF3 -> CYRILLIC SMALL LETTER GJE
|
||||
u'\u0454' # 0xF4 -> CYRILLIC SMALL LETTER UKRAINIAN IE
|
||||
u'\u0455' # 0xF5 -> CYRILLIC SMALL LETTER DZE
|
||||
u'\u0456' # 0xF6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
|
||||
u'\u0457' # 0xF7 -> CYRILLIC SMALL LETTER YI
|
||||
u'\u0458' # 0xF8 -> CYRILLIC SMALL LETTER JE
|
||||
u'\u0459' # 0xF9 -> CYRILLIC SMALL LETTER LJE
|
||||
u'\u045a' # 0xFA -> CYRILLIC SMALL LETTER NJE
|
||||
u'\u045b' # 0xFB -> CYRILLIC SMALL LETTER TSHE
|
||||
u'\u045c' # 0xFC -> CYRILLIC SMALL LETTER KJE
|
||||
u'\xa7' # 0xFD -> SECTION SIGN
|
||||
u'\u045e' # 0xFE -> CYRILLIC SMALL LETTER SHORT U
|
||||
u'\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
@@ -0,0 +1,307 @@
|
||||
""" Python Character Mapping Codec iso8859_6 generated from 'MAPPINGS/ISO8859/8859-6.TXT' with gencodec.py.
|
||||
|
||||
"""#"
|
||||
|
||||
import codecs
|
||||
|
||||
### Codec APIs
|
||||
|
||||
class Codec(codecs.Codec):
|
||||
|
||||
def encode(self,input,errors='strict'):
|
||||
return codecs.charmap_encode(input,errors,encoding_table)
|
||||
|
||||
def decode(self,input,errors='strict'):
|
||||
return codecs.charmap_decode(input,errors,decoding_table)
|
||||
|
||||
class IncrementalEncoder(codecs.IncrementalEncoder):
|
||||
def encode(self, input, final=False):
|
||||
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
|
||||
|
||||
class IncrementalDecoder(codecs.IncrementalDecoder):
|
||||
def decode(self, input, final=False):
|
||||
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
|
||||
|
||||
class StreamWriter(Codec,codecs.StreamWriter):
|
||||
pass
|
||||
|
||||
class StreamReader(Codec,codecs.StreamReader):
|
||||
pass
|
||||
|
||||
### encodings module API
|
||||
|
||||
def getregentry():
|
||||
return codecs.CodecInfo(
|
||||
name='iso8859-6',
|
||||
encode=Codec().encode,
|
||||
decode=Codec().decode,
|
||||
incrementalencoder=IncrementalEncoder,
|
||||
incrementaldecoder=IncrementalDecoder,
|
||||
streamreader=StreamReader,
|
||||
streamwriter=StreamWriter,
|
||||
)
|
||||
|
||||
|
||||
### Decoding Table
|
||||
|
||||
decoding_table = (
|
||||
u'\x00' # 0x00 -> NULL
|
||||
u'\x01' # 0x01 -> START OF HEADING
|
||||
u'\x02' # 0x02 -> START OF TEXT
|
||||
u'\x03' # 0x03 -> END OF TEXT
|
||||
u'\x04' # 0x04 -> END OF TRANSMISSION
|
||||
u'\x05' # 0x05 -> ENQUIRY
|
||||
u'\x06' # 0x06 -> ACKNOWLEDGE
|
||||
u'\x07' # 0x07 -> BELL
|
||||
u'\x08' # 0x08 -> BACKSPACE
|
||||
u'\t' # 0x09 -> HORIZONTAL TABULATION
|
||||
u'\n' # 0x0A -> LINE FEED
|
||||
u'\x0b' # 0x0B -> VERTICAL TABULATION
|
||||
u'\x0c' # 0x0C -> FORM FEED
|
||||
u'\r' # 0x0D -> CARRIAGE RETURN
|
||||
u'\x0e' # 0x0E -> SHIFT OUT
|
||||
u'\x0f' # 0x0F -> SHIFT IN
|
||||
u'\x10' # 0x10 -> DATA LINK ESCAPE
|
||||
u'\x11' # 0x11 -> DEVICE CONTROL ONE
|
||||
u'\x12' # 0x12 -> DEVICE CONTROL TWO
|
||||
u'\x13' # 0x13 -> DEVICE CONTROL THREE
|
||||
u'\x14' # 0x14 -> DEVICE CONTROL FOUR
|
||||
u'\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE
|
||||
u'\x16' # 0x16 -> SYNCHRONOUS IDLE
|
||||
u'\x17' # 0x17 -> END OF TRANSMISSION BLOCK
|
||||
u'\x18' # 0x18 -> CANCEL
|
||||
u'\x19' # 0x19 -> END OF MEDIUM
|
||||
u'\x1a' # 0x1A -> SUBSTITUTE
|
||||
u'\x1b' # 0x1B -> ESCAPE
|
||||
u'\x1c' # 0x1C -> FILE SEPARATOR
|
||||
u'\x1d' # 0x1D -> GROUP SEPARATOR
|
||||
u'\x1e' # 0x1E -> RECORD SEPARATOR
|
||||
u'\x1f' # 0x1F -> UNIT SEPARATOR
|
||||
u' ' # 0x20 -> SPACE
|
||||
u'!' # 0x21 -> EXCLAMATION MARK
|
||||
u'"' # 0x22 -> QUOTATION MARK
|
||||
u'#' # 0x23 -> NUMBER SIGN
|
||||
u'$' # 0x24 -> DOLLAR SIGN
|
||||
u'%' # 0x25 -> PERCENT SIGN
|
||||
u'&' # 0x26 -> AMPERSAND
|
||||
u"'" # 0x27 -> APOSTROPHE
|
||||
u'(' # 0x28 -> LEFT PARENTHESIS
|
||||
u')' # 0x29 -> RIGHT PARENTHESIS
|
||||
u'*' # 0x2A -> ASTERISK
|
||||
u'+' # 0x2B -> PLUS SIGN
|
||||
u',' # 0x2C -> COMMA
|
||||
u'-' # 0x2D -> HYPHEN-MINUS
|
||||
u'.' # 0x2E -> FULL STOP
|
||||
u'/' # 0x2F -> SOLIDUS
|
||||
u'0' # 0x30 -> DIGIT ZERO
|
||||
u'1' # 0x31 -> DIGIT ONE
|
||||
u'2' # 0x32 -> DIGIT TWO
|
||||
u'3' # 0x33 -> DIGIT THREE
|
||||
u'4' # 0x34 -> DIGIT FOUR
|
||||
u'5' # 0x35 -> DIGIT FIVE
|
||||
u'6' # 0x36 -> DIGIT SIX
|
||||
u'7' # 0x37 -> DIGIT SEVEN
|
||||
u'8' # 0x38 -> DIGIT EIGHT
|
||||
u'9' # 0x39 -> DIGIT NINE
|
||||
u':' # 0x3A -> COLON
|
||||
u';' # 0x3B -> SEMICOLON
|
||||
u'<' # 0x3C -> LESS-THAN SIGN
|
||||
u'=' # 0x3D -> EQUALS SIGN
|
||||
u'>' # 0x3E -> GREATER-THAN SIGN
|
||||
u'?' # 0x3F -> QUESTION MARK
|
||||
u'@' # 0x40 -> COMMERCIAL AT
|
||||
u'A' # 0x41 -> LATIN CAPITAL LETTER A
|
||||
u'B' # 0x42 -> LATIN CAPITAL LETTER B
|
||||
u'C' # 0x43 -> LATIN CAPITAL LETTER C
|
||||
u'D' # 0x44 -> LATIN CAPITAL LETTER D
|
||||
u'E' # 0x45 -> LATIN CAPITAL LETTER E
|
||||
u'F' # 0x46 -> LATIN CAPITAL LETTER F
|
||||
u'G' # 0x47 -> LATIN CAPITAL LETTER G
|
||||
u'H' # 0x48 -> LATIN CAPITAL LETTER H
|
||||
u'I' # 0x49 -> LATIN CAPITAL LETTER I
|
||||
u'J' # 0x4A -> LATIN CAPITAL LETTER J
|
||||
u'K' # 0x4B -> LATIN CAPITAL LETTER K
|
||||
u'L' # 0x4C -> LATIN CAPITAL LETTER L
|
||||
u'M' # 0x4D -> LATIN CAPITAL LETTER M
|
||||
u'N' # 0x4E -> LATIN CAPITAL LETTER N
|
||||
u'O' # 0x4F -> LATIN CAPITAL LETTER O
|
||||
u'P' # 0x50 -> LATIN CAPITAL LETTER P
|
||||
u'Q' # 0x51 -> LATIN CAPITAL LETTER Q
|
||||
u'R' # 0x52 -> LATIN CAPITAL LETTER R
|
||||
u'S' # 0x53 -> LATIN CAPITAL LETTER S
|
||||
u'T' # 0x54 -> LATIN CAPITAL LETTER T
|
||||
u'U' # 0x55 -> LATIN CAPITAL LETTER U
|
||||
u'V' # 0x56 -> LATIN CAPITAL LETTER V
|
||||
u'W' # 0x57 -> LATIN CAPITAL LETTER W
|
||||
u'X' # 0x58 -> LATIN CAPITAL LETTER X
|
||||
u'Y' # 0x59 -> LATIN CAPITAL LETTER Y
|
||||
u'Z' # 0x5A -> LATIN CAPITAL LETTER Z
|
||||
u'[' # 0x5B -> LEFT SQUARE BRACKET
|
||||
u'\\' # 0x5C -> REVERSE SOLIDUS
|
||||
u']' # 0x5D -> RIGHT SQUARE BRACKET
|
||||
u'^' # 0x5E -> CIRCUMFLEX ACCENT
|
||||
u'_' # 0x5F -> LOW LINE
|
||||
u'`' # 0x60 -> GRAVE ACCENT
|
||||
u'a' # 0x61 -> LATIN SMALL LETTER A
|
||||
u'b' # 0x62 -> LATIN SMALL LETTER B
|
||||
u'c' # 0x63 -> LATIN SMALL LETTER C
|
||||
u'd' # 0x64 -> LATIN SMALL LETTER D
|
||||
u'e' # 0x65 -> LATIN SMALL LETTER E
|
||||
u'f' # 0x66 -> LATIN SMALL LETTER F
|
||||
u'g' # 0x67 -> LATIN SMALL LETTER G
|
||||
u'h' # 0x68 -> LATIN SMALL LETTER H
|
||||
u'i' # 0x69 -> LATIN SMALL LETTER I
|
||||
u'j' # 0x6A -> LATIN SMALL LETTER J
|
||||
u'k' # 0x6B -> LATIN SMALL LETTER K
|
||||
u'l' # 0x6C -> LATIN SMALL LETTER L
|
||||
u'm' # 0x6D -> LATIN SMALL LETTER M
|
||||
u'n' # 0x6E -> LATIN SMALL LETTER N
|
||||
u'o' # 0x6F -> LATIN SMALL LETTER O
|
||||
u'p' # 0x70 -> LATIN SMALL LETTER P
|
||||
u'q' # 0x71 -> LATIN SMALL LETTER Q
|
||||
u'r' # 0x72 -> LATIN SMALL LETTER R
|
||||
u's' # 0x73 -> LATIN SMALL LETTER S
|
||||
u't' # 0x74 -> LATIN SMALL LETTER T
|
||||
u'u' # 0x75 -> LATIN SMALL LETTER U
|
||||
u'v' # 0x76 -> LATIN SMALL LETTER V
|
||||
u'w' # 0x77 -> LATIN SMALL LETTER W
|
||||
u'x' # 0x78 -> LATIN SMALL LETTER X
|
||||
u'y' # 0x79 -> LATIN SMALL LETTER Y
|
||||
u'z' # 0x7A -> LATIN SMALL LETTER Z
|
||||
u'{' # 0x7B -> LEFT CURLY BRACKET
|
||||
u'|' # 0x7C -> VERTICAL LINE
|
||||
u'}' # 0x7D -> RIGHT CURLY BRACKET
|
||||
u'~' # 0x7E -> TILDE
|
||||
u'\x7f' # 0x7F -> DELETE
|
||||
u'\x80' # 0x80 -> <control>
|
||||
u'\x81' # 0x81 -> <control>
|
||||
u'\x82' # 0x82 -> <control>
|
||||
u'\x83' # 0x83 -> <control>
|
||||
u'\x84' # 0x84 -> <control>
|
||||
u'\x85' # 0x85 -> <control>
|
||||
u'\x86' # 0x86 -> <control>
|
||||
u'\x87' # 0x87 -> <control>
|
||||
u'\x88' # 0x88 -> <control>
|
||||
u'\x89' # 0x89 -> <control>
|
||||
u'\x8a' # 0x8A -> <control>
|
||||
u'\x8b' # 0x8B -> <control>
|
||||
u'\x8c' # 0x8C -> <control>
|
||||
u'\x8d' # 0x8D -> <control>
|
||||
u'\x8e' # 0x8E -> <control>
|
||||
u'\x8f' # 0x8F -> <control>
|
||||
u'\x90' # 0x90 -> <control>
|
||||
u'\x91' # 0x91 -> <control>
|
||||
u'\x92' # 0x92 -> <control>
|
||||
u'\x93' # 0x93 -> <control>
|
||||
u'\x94' # 0x94 -> <control>
|
||||
u'\x95' # 0x95 -> <control>
|
||||
u'\x96' # 0x96 -> <control>
|
||||
u'\x97' # 0x97 -> <control>
|
||||
u'\x98' # 0x98 -> <control>
|
||||
u'\x99' # 0x99 -> <control>
|
||||
u'\x9a' # 0x9A -> <control>
|
||||
u'\x9b' # 0x9B -> <control>
|
||||
u'\x9c' # 0x9C -> <control>
|
||||
u'\x9d' # 0x9D -> <control>
|
||||
u'\x9e' # 0x9E -> <control>
|
||||
u'\x9f' # 0x9F -> <control>
|
||||
u'\xa0' # 0xA0 -> NO-BREAK SPACE
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\xa4' # 0xA4 -> CURRENCY SIGN
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\u060c' # 0xAC -> ARABIC COMMA
|
||||
u'\xad' # 0xAD -> SOFT HYPHEN
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\u061b' # 0xBB -> ARABIC SEMICOLON
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\u061f' # 0xBF -> ARABIC QUESTION MARK
|
||||
u'\ufffe'
|
||||
u'\u0621' # 0xC1 -> ARABIC LETTER HAMZA
|
||||
u'\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE
|
||||
u'\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE
|
||||
u'\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE
|
||||
u'\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW
|
||||
u'\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE
|
||||
u'\u0627' # 0xC7 -> ARABIC LETTER ALEF
|
||||
u'\u0628' # 0xC8 -> ARABIC LETTER BEH
|
||||
u'\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA
|
||||
u'\u062a' # 0xCA -> ARABIC LETTER TEH
|
||||
u'\u062b' # 0xCB -> ARABIC LETTER THEH
|
||||
u'\u062c' # 0xCC -> ARABIC LETTER JEEM
|
||||
u'\u062d' # 0xCD -> ARABIC LETTER HAH
|
||||
u'\u062e' # 0xCE -> ARABIC LETTER KHAH
|
||||
u'\u062f' # 0xCF -> ARABIC LETTER DAL
|
||||
u'\u0630' # 0xD0 -> ARABIC LETTER THAL
|
||||
u'\u0631' # 0xD1 -> ARABIC LETTER REH
|
||||
u'\u0632' # 0xD2 -> ARABIC LETTER ZAIN
|
||||
u'\u0633' # 0xD3 -> ARABIC LETTER SEEN
|
||||
u'\u0634' # 0xD4 -> ARABIC LETTER SHEEN
|
||||
u'\u0635' # 0xD5 -> ARABIC LETTER SAD
|
||||
u'\u0636' # 0xD6 -> ARABIC LETTER DAD
|
||||
u'\u0637' # 0xD7 -> ARABIC LETTER TAH
|
||||
u'\u0638' # 0xD8 -> ARABIC LETTER ZAH
|
||||
u'\u0639' # 0xD9 -> ARABIC LETTER AIN
|
||||
u'\u063a' # 0xDA -> ARABIC LETTER GHAIN
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\u0640' # 0xE0 -> ARABIC TATWEEL
|
||||
u'\u0641' # 0xE1 -> ARABIC LETTER FEH
|
||||
u'\u0642' # 0xE2 -> ARABIC LETTER QAF
|
||||
u'\u0643' # 0xE3 -> ARABIC LETTER KAF
|
||||
u'\u0644' # 0xE4 -> ARABIC LETTER LAM
|
||||
u'\u0645' # 0xE5 -> ARABIC LETTER MEEM
|
||||
u'\u0646' # 0xE6 -> ARABIC LETTER NOON
|
||||
u'\u0647' # 0xE7 -> ARABIC LETTER HEH
|
||||
u'\u0648' # 0xE8 -> ARABIC LETTER WAW
|
||||
u'\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA
|
||||
u'\u064a' # 0xEA -> ARABIC LETTER YEH
|
||||
u'\u064b' # 0xEB -> ARABIC FATHATAN
|
||||
u'\u064c' # 0xEC -> ARABIC DAMMATAN
|
||||
u'\u064d' # 0xED -> ARABIC KASRATAN
|
||||
u'\u064e' # 0xEE -> ARABIC FATHA
|
||||
u'\u064f' # 0xEF -> ARABIC DAMMA
|
||||
u'\u0650' # 0xF0 -> ARABIC KASRA
|
||||
u'\u0651' # 0xF1 -> ARABIC SHADDA
|
||||
u'\u0652' # 0xF2 -> ARABIC SUKUN
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
u'\ufffe'
|
||||
)
|
||||
|
||||
### Encoding table
|
||||
encoding_table=codecs.charmap_build(decoding_table)
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user