cubicweb/devtools/fix_po_encoding
author Denis Laxalde <denis.laxalde@logilab.fr>
Sat, 16 Jan 2016 13:48:51 +0100
changeset 11057 0b59724cb3f2
parent 0 devtools/fix_po_encoding@b97547f5f1fa
child 12779 44147dab9d27
permissions -rwxr-xr-x
Reorganize source tree to have a "cubicweb" top-level package Basically: mkdir cubicweb hg mv *.py -X setup.py cubicweb hg mv dataimport devtools entities etwist ext hooks i18n misc schemas server skeleton sobjects test web wsgi cubicweb Other changes: * adjust path to cubicweb-ctl in devtools tests * update setup.py to avoid importing __pkginfo__ (exec it instead), replace os.path.walk by os.walk and prepend `modname` here and there * update tox.ini to account for new test locations * update doc/conf.py so that it still finds __pkginfo__.py and CWDIR in doc/Makefile

#!/usr/bin/python

"""usage: fix-po-encodings [filename...]
change the encoding of the po files passed as arguments to utf-8
"""
import sys
import re
import codecs

def change_encoding(filename, target='UTF-8'):
    fdesc = open(filename)
    data = fdesc.read()
    fdesc.close()
    encoding = find_encoding(data)
    if encoding == target:
        return
    data = fix_encoding(data, target)
    data = unicode(data, encoding)
    fdesc = codecs.open(filename, 'wb', encoding=target)
    fdesc.write(data)
    fdesc.close()

def find_encoding(data):
    regexp = re.compile(r'"Content-Type:.* charset=([a-zA-Z0-9-]+)\\n"', re.M)
    mo = regexp.search(data)
    if mo is None:
        raise ValueError('No encoding declaration')
    return mo.group(1)

def fix_encoding(data, target_encoding):
    regexp = re.compile(r'("Content-Type:.* charset=)(.*)(\\n")', re.M)
    return regexp.sub(r'\1%s\3' % target_encoding, data)
    


for filename in sys.argv[1:]:
    print filename
    change_encoding(filename)