devtools/fix_po_encoding
author Aurelien Campeas <aurelien.campeas@logilab.fr>
Mon, 26 Aug 2013 16:15:29 +0200
changeset 9257 ce338133c92c
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
remove cw 3.9 bw compat (bw compat other than the interface -> adapter changes) - cwconfig, doc/admin/setup: docstring adjustment wrt 3.9 & virtualenv - testing/rst: windmill (which is gone from the testing infrastructure) - other docs: "stuff introduced in 3.9" cleanup, as we don't care about the version old features were introduced - server/hooky.py: bw compat for propagation hooks - server/schemaserial.py: pre CWUniqueTogetherConstraint migration support - web.__init__.py: dumps bw import - autoform.py: .action ppty is gone, also deprecate set_action and get_action - baseviews: CSVView.subvid gone long ago, secondary view removal - primary.py: _render_attribute & _render_relation signature change - reledit.py: rvid/default_value bw compat, should_edit_* dropped - webconfig.py: resourcefile is gone - formfields.py: old vocabulary handling - request.py: build_ajax_replace_url, external_resource Related to #2782004.

#!/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)