Created
May 19, 2011 19:10
-
-
Save JakeWharton/981486 to your computer and use it in GitHub Desktop.
Python script to fix common CRLF and Unicode problems when working with Visual Studio and git.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import sys | |
if sys.version_info < (2, 6): | |
raise RuntimeError("Python 2.6+ is required.") | |
import codecs | |
import logging | |
import optparse | |
import os | |
import unittest | |
CRLF_OFFSET_ERROR = '\r\0\r\n\0' | |
CRLF_OFFSET_FIX = '\r\0\n\0' | |
def fsckByteString(content=None, log=None): | |
if not content: | |
raise ArgumentException('Content must not be empty.') | |
if content.startswith(codecs.BOM_UTF16): | |
if log: log.info('Detected UTF-16 BOM.') | |
if CRLF_OFFSET_ERROR in content: | |
if log: log.error('Byte shift due to improper line ending conversion!') | |
if log: log.info('Correcting line endings...') | |
content = content.replace(CRLF_OFFSET_ERROR, CRLF_OFFSET_FIX) | |
if log: log.info('Converting to UTF-8...') | |
return content.decode("utf16").encode("utf8") | |
if content.startswith(codecs.BOM_UTF8): | |
if log: log.warn('Detected unneccessary UTF-8 BOM.') | |
if log: log.info('Removing BOM...') | |
return content[len(codecs.BOM_UTF8):] | |
if log: log.info('No action required.') | |
return content | |
class fscker(unittest.TestCase): | |
DATA = "simple\r\ntest\r\nof\r\nencodings" | |
EXPECTED = DATA.encode("utf8") | |
def test_valid_utf8(self): | |
value = self.DATA.encode("utf8") | |
actual = fsckByteString(value) | |
self.assertEqual(self.EXPECTED, actual) | |
def test_valid_utf8_with_bom(self): | |
value = codecs.BOM_UTF8 + self.DATA.encode("utf8") | |
actual = fsckByteString(value) | |
self.assertEqual(self.EXPECTED, actual) | |
def test_valid_utf16_to_utf8(self): | |
value = self.DATA.encode("utf16") | |
actual = fsckByteString(value) | |
self.assertEqual(self.EXPECTED, actual) | |
def test_invalid_utf16_to_utf8(self): | |
value = self.DATA.encode("utf16").replace('\n', '\r\n') | |
actual = fsckByteString(value) | |
self.assertEqual(self.EXPECTED, actual) | |
if __name__ == '__main__': | |
parser = optparse.OptionParser(usage='Usage: %prog [options] file1 [... fileN]') | |
parser.add_option('--test', dest='is_testing', action='store_true', default=False, help='run test suite') | |
options, files = parser.parse_args() | |
logging.basicConfig(format='%(name)s %(levelname)s: %(message)s', level=logging.INFO) | |
if options.is_testing: | |
unittest.TextTestRunner(verbosity=2).run(unittest.TestSuite( | |
unittest.defaultTestLoader.loadTestsFromTestCase(fscker) | |
)) | |
elif files: | |
for fname in files: | |
log = logging.getLogger(os.path.basename(fname)) | |
try: | |
content = None | |
with open(fname, 'rb') as f: | |
content = fsckByteString(f.read(), log) | |
with open(fname, 'wb') as f: | |
f.write(content) | |
except Exception, e: | |
log.error('"%s" could not be checked.', fname) | |
log.error(e) | |
else: | |
parser.print_help() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment