devtools/fix_po_encoding
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Wed, 25 Aug 2010 10:29:18 +0200
changeset 6142 8bc6eac1fac1
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[session] cleanup hook / operation / entity edition api Operation api ~~~~~~~~~~~~~ * commit_event killed, recently introduced postcommit_event is enough and has a better name * kill SingleOperation class, it's a) currently never used b) superseeded by set_operation if needed. Entity edition api ~~~~~~~~~~~~~~~~~~ edited_attributes turned into a special object holding edition specific attributes: - attributes to be edited (simply mirrored in cw_attr_cache, actual values are there) - former _cw_skip_security set (cw_edited) and querier_pending_relations It has also been renamed to `cw_edited` on the way (it may also contains inlined relations) The entity dict interface has been deprecated. One should explicitly use either cw_attr_cache or cw_edited according to the need. Also, there is now a control that we don't try to hi-jack edited attributes once this has no more effect (eg modification have already been saved) At last, _cw_set_defaults/cw_check internal methods have been moved to this special object Hook api ~~~~~~~~ hook.entity_oldnewvalue function now moved to a method of cw_edited object.

#!/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)