devtools/fix_po_encoding
author Rémi Cardona <remi.cardona@logilab.fr>
Wed, 13 Mar 2013 18:36:49 +0100
branchstable
changeset 8730 d4d9f33fd01b
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[web/request] Prune extraneous 'pageid' from generated ajax URL parameters (closes #2758130) If 'pageid' is given through extraparams, it is sent twice to the browser. On the JS side, the final URL loadxhtml() will end up using will have 'pageid' set twice which CubicWeb will readily accept as a list. Pruning this parameter makes sure it is exactly once.

#!/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)