Created
March 31, 2013 09:37
-
-
Save vivisidea/5280131 to your computer and use it in GitHub Desktop.
linux's iconv tool SUCKS when processing Chinese character building my own simple file encoding conversion tools using python.
make sure you know the original encoding
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 | |
# -*- encoding=utf-8 -*- | |
# | |
# convert files from encoding to another encoding | |
# | |
import os | |
directory = '.' | |
surfix='.txt' | |
fromenc='gbk' | |
toenc='utf8' | |
printmode=False # use printmode=True is you are not sure. | |
def convert(directory, surfix='', fromenc='gbk', toenc='utf8'): | |
''' | |
convert the files match surfix in directory from $fromenc to $toenc, recursively. | |
''' | |
if os.path.isdir(directory): | |
for f in os.listdir(directory): | |
f = os.path.join(directory, f) # relative path | |
if os.path.isdir(f): | |
print '%s is a directory ...' % f | |
convert(f, surfix, fromenc, toenc) | |
elif f.endswith(surfix): | |
fobj = open(f, 'rb') | |
if printmode: | |
for line in fobj: | |
line = line.decode(fromenc,'ignore').encode(toenc) | |
print line, | |
fobj.close() | |
else: | |
tmpfile = f+'.'+toenc | |
tmp = open(tmpfile, 'wb') # write the output to a temorary file | |
try: | |
for line in fobj: | |
line = line.decode(fromenc, 'ignore').encode(toenc) # ignore the conversion error, replace with '?' mark | |
tmp.write(line) | |
except Exception, e: | |
print 'error processing %s, error=%s' % (f,e) | |
if os.path.exists(tmpfile): | |
os.remove(tmpfile) | |
print 'processing %s ...' % f | |
fobj.close() | |
tmp.close() | |
if os.path.exists(tmpfile): | |
os.rename(tmpfile, f) # override the original file, DO YOUR OWN BACKUP !!! | |
if __name__ == '__main__': | |
choice = raw_input('it\'s highly recommended that you do your own backup before continue, continue?(Y/N)') | |
if choice.lower() == 'y': | |
convert('.', '.txt', 'gbk', 'utf8') | |
else: | |
print 'aborted.' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment