dadfab5b23
Supplementary Plane characters can exist in UTF-16 files, but they are not valid UCS-2 characters. For example, this python interpreter code: >>> import codecs >>> codecs.encode(u'\U00010300', 'utf-16') '\xff\xfe\x00\xd8\x00\xdf' Therefore the UCS-4 0x00010300 character is encoded as two 16-bit numbers (0xd800 0xdf00) in a little endian UTF-16 file. For more information, see: http://en.wikipedia.org/wiki/UTF-16#U.2B10000_to_U.2B10FFFF This test checks to make sure that BaseTools will reject these characters in UTF-16 files. The range of 0xd800 - 0xdfff should also be rejected as unicode code points because they are reserved for the surrogate pair usage in UTF-16 files. This test was fixed by the previous commit: "BaseTools/UniClassObject: Verify valid UCS-2 chars in UTF-16 .uni files" Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Jordan Justen <jordan.l.justen@intel.com> Reviewed-by: Laszlo Ersek <lersek@redhat.com> Reviewed-by: Michael D Kinney <michael.d.kinney@intel.com> Reviewed-by: Yingke Liu <yingke.d.liu@intel.com> git-svn-id: https://svn.code.sf.net/p/edk2/code/trunk/edk2@17695 6f19259b-4bc3-4df7-8a09-765794883524
122 lines
3.9 KiB
Python
122 lines
3.9 KiB
Python
## @file
|
|
# Unit tests for AutoGen.UniClassObject
|
|
#
|
|
# Copyright (c) 2015, Intel Corporation. All rights reserved.<BR>
|
|
#
|
|
# This program and the accompanying materials
|
|
# are licensed and made available under the terms and conditions of the BSD License
|
|
# which accompanies this distribution. The full text of the license may be found at
|
|
# http://opensource.org/licenses/bsd-license.php
|
|
#
|
|
# THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
|
|
#
|
|
|
|
##
|
|
# Import Modules
|
|
#
|
|
import os
|
|
import unittest
|
|
|
|
import codecs
|
|
|
|
import TestTools
|
|
|
|
from Common.Misc import PathClass
|
|
import AutoGen.UniClassObject as BtUni
|
|
|
|
from Common import EdkLogger
|
|
EdkLogger.InitializeForUnitTest()
|
|
|
|
class Tests(TestTools.BaseToolsTest):
|
|
|
|
SampleData = u'''
|
|
#langdef en-US "English"
|
|
#string STR_A #language en-US "STR_A for en-US"
|
|
'''
|
|
|
|
def EncodeToFile(self, encoding, string=None):
|
|
if string is None:
|
|
string = self.SampleData
|
|
if encoding is not None:
|
|
data = codecs.encode(string, encoding)
|
|
else:
|
|
data = string
|
|
path = 'input.uni'
|
|
self.WriteTmpFile(path, data)
|
|
return PathClass(self.GetTmpFilePath(path))
|
|
|
|
def ErrorFailure(self, error, encoding, shouldPass):
|
|
msg = error + ' should '
|
|
if shouldPass:
|
|
msg += 'not '
|
|
msg += 'be generated for '
|
|
msg += '%s data in a .uni file' % encoding
|
|
self.fail(msg)
|
|
|
|
def UnicodeErrorFailure(self, encoding, shouldPass):
|
|
self.ErrorFailure('UnicodeError', encoding, shouldPass)
|
|
|
|
def EdkErrorFailure(self, encoding, shouldPass):
|
|
self.ErrorFailure('EdkLogger.FatalError', encoding, shouldPass)
|
|
|
|
def CheckFile(self, encoding, shouldPass, string=None):
|
|
path = self.EncodeToFile(encoding, string)
|
|
try:
|
|
BtUni.UniFileClassObject([path])
|
|
if shouldPass:
|
|
return
|
|
except UnicodeError:
|
|
if not shouldPass:
|
|
return
|
|
else:
|
|
self.UnicodeErrorFailure(encoding, shouldPass)
|
|
except EdkLogger.FatalError:
|
|
if not shouldPass:
|
|
return
|
|
else:
|
|
self.EdkErrorFailure(encoding, shouldPass)
|
|
except Exception:
|
|
pass
|
|
|
|
self.EdkErrorFailure(encoding, shouldPass)
|
|
|
|
def testUtf16InUniFile(self):
|
|
self.CheckFile('utf_16', shouldPass=True)
|
|
|
|
def testSupplementaryPlaneUnicodeCharInUtf16File(self):
|
|
#
|
|
# Supplementary Plane characters can exist in UTF-16 files,
|
|
# but they are not valid UCS-2 characters.
|
|
#
|
|
# This test makes sure that BaseTools rejects these characters
|
|
# if seen in a .uni file.
|
|
#
|
|
data = u'''
|
|
#langdef en-US "English"
|
|
#string STR_A #language en-US "CodePoint (\U00010300) > 0xFFFF"
|
|
'''
|
|
|
|
self.CheckFile('utf_16', shouldPass=False, string=data)
|
|
|
|
def testSurrogatePairUnicodeCharInUtf16File(self):
|
|
#
|
|
# Surrogate Pair code points are used in UTF-16 files to
|
|
# encode the Supplementary Plane characters. But, a Surrogate
|
|
# Pair code point which is not followed by another Surrogate
|
|
# Pair code point might be interpreted as a single code point
|
|
# with the Surrogate Pair code point.
|
|
#
|
|
# This test makes sure that BaseTools rejects these characters
|
|
# if seen in a .uni file.
|
|
#
|
|
data = codecs.BOM_UTF16_LE + '//\x01\xd8 '
|
|
|
|
self.CheckFile(encoding=None, shouldPass=False, string=data)
|
|
|
|
TheTestSuite = TestTools.MakeTheTestSuite(locals())
|
|
|
|
if __name__ == '__main__':
|
|
allTests = TheTestSuite()
|
|
unittest.TextTestRunner().run(allTests)
|