This examines characters in coreboot's sourcecode to look for values that are not TAB, or in the range of space (0x20) to ~ (0x7F). It specifically excludes copyright lines so that names with high- ASCII characters are not flagged. Change-Id: I40f7e61fd403cbad19cf0746e2017c53e7379bf8 Signed-off-by: Martin Roth <martinroth@google.com> Reviewed-on: https://review.coreboot.org/15979 Tested-by: build bot (Jenkins) Reviewed-by: Patrick Georgi <pgeorgi@google.com>
		
			
				
	
	
		
			44 lines
		
	
	
		
			1.8 KiB
		
	
	
	
		
			Bash
		
	
	
		
			Executable File
		
	
	
	
	
			
		
		
	
	
			44 lines
		
	
	
		
			1.8 KiB
		
	
	
	
		
			Bash
		
	
	
		
			Executable File
		
	
	
	
	
| #!/bin/sh
 | |
| # This file is part of the coreboot project.
 | |
| #
 | |
| # Copyright (C) 2016 Google Inc.
 | |
| #
 | |
| # This program is free software; you can redistribute it and/or modify
 | |
| # it under the terms of the GNU General Public License as published by
 | |
| # the Free Software Foundation; version 2 of the License.
 | |
| #
 | |
| # This program is distributed in the hope that it will be useful,
 | |
| # but WITHOUT ANY WARRANTY; without even the implied warranty of
 | |
| # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 | |
| # GNU General Public License for more details.
 | |
| #
 | |
| # DESCR: Check for non-ASCII and unprintable characters
 | |
| 
 | |
| LC_ALL=C export LC_ALL
 | |
| 
 | |
| INCLUDED_FILES='\.[chsS]$\|\.asl$\|\.cb$\|\.inc$\|Kconfig\|\.ld$|\.txt\|\.hex'
 | |
| EXCLUDED_DIRS='^payloads/\|^src/vendorcode/\|^Documentation/\|^build/\|^3rdparty/\|^\.git/\|^coreboot-builds/\|^util/nvidia/cbootimage'
 | |
| EXCLUDED_FILES='to-wiki/towiki\.sh$\|vga/vga_font\|video/font\|PDCurses.*x11'
 | |
| EXCLUDED_PHRASES='Copyright\|Ported to\|Intel®\|°C\|°F\|Athlon™\|Copyright.*©\|A-Za-zÀ-ÿ'
 | |
| 
 | |
| # Use git ls-files if the code is in a git repo, otherwise use find.
 | |
| if [ -n "$(command -v git)" ] && [ -d .git ]; then
 | |
| 	FIND_FILES="git ls-files"
 | |
| else
 | |
| 	FIND_FILES="find . "
 | |
| fi
 | |
| 
 | |
| # 1. Get the list of files to parse and send them through grep
 | |
| # 2. Find any characters that aren't TAB, or space (0x20) to ~ (0x7F)
 | |
| #    LF (0x10) isn't included, as it ends the grep line
 | |
| # 3. Remove common phrases and names that have been found
 | |
| # 4. Run the result through grep again to highlight the issues that were
 | |
| #    found.  Without this step, the characters can be difficult to see.
 | |
| grep -n "[^	 -~]" \
 | |
| 	$(${FIND_FILES} | sed 's|^\./||' | sort | \
 | |
| 		grep "$INCLUDED_FILES" | \
 | |
| 		grep -v "$EXCLUDED_DIRS" | \
 | |
| 		grep -v "$EXCLUDED_FILES") | \
 | |
| 	grep -iv "$EXCLUDED_PHRASES" | \
 | |
| 	grep --color='auto' "[^	 -~]"
 |