devtools/fix_po_encoding
author Pierre-Yves David <pierre-yves.david@logilab.fr>
Tue, 11 Oct 2011 16:01:44 +0200
branchstable
changeset 7939 e107204d3b27
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
Add a hidden input:submit field in facets form (closes #1988784) <Enter> is supposed to submit the form only if there is a single input:text field. However most browsers will submit the form on <Enter> anyway if there is an input:submit field. see: http://www.w3.org/MarkUp/html-spec/html-spec_8.html#SEC8.2 Firefox 7.0.1 does not submit form on <Enter> if there is more than a input:text field and not input:submit but does it if there is an input:submit. IE 6 or Firefox 2 behave the same way.

#!/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)