devtools/fix_po_encoding
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Tue, 26 Jan 2010 13:32:54 +0100
changeset 4364 766359c69f2f
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[uicfg] fix autoform_section rtags initialization 1. when a relation is marked as inlined in the 'main' form type, we want its opposite (eg when one the other side of the relation) to be marked as hidden in the 'inlined' form type 2. when no section is specified for the 'inlined' form type, use the same as in the 'main' form type to do this properly, we need two initialization stages. The first one to handle 1., the second to handle what was done before and 2. We can't do this in a single stage because we've to know the bare value of the "opposite" tag.

#!/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)