devtools/fix_po_encoding
author Pierre-Yves David <pierre-yves.david@logilab.fr>
Thu, 13 Jun 2013 18:50:19 +0200
changeset 9017 aa709bc6b6c1
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[application/connect] simplify connection logic ``application.connect`` now either sets a full featured ``DBAPISession`` to the ``WebRequest`` object or raises ``AuthenticationError``. The creation and usage of a fake DBAPISession is now handled by ``main_handle_request`` when needed. This means that fake DBAPISession are no longer tracked by the session manager and that user are not given anyway to retrieve them for a later request. This fake DBAPISession is still passed to ``core_handle`` because multiple cubes like registration or forgotten password need this behavior. We would like to get ride of it in the future. This clarification of the connection API greatly simplifies ``DBAPISession`` retrieval//creation process opening the way to improvements in this area. Related to #2503918

#!/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)