cubicweb/devtools/fix_po_encoding
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Wed, 09 Nov 2016 16:14:17 +0100
changeset 11888 0849a5eb57b8
parent 11057 0b59724cb3f2
child 12779 44147dab9d27
permissions -rwxr-xr-x
[rtags] Allow to 'derive' rtags Since some releases, rtags (structure underlying uicfg) have selector and may be copied using something like: new_rtags = deepcopy(original_rtags) new_rtags.__module__ = __name__ new_rtags.__select__ = custom_selector The problem is that starting from that, both rtags wil diverge and changes in original_rtags won't be considered, while we usually want to set a few specific rules only in new_rtags. To fix this problem, this cset introduces the notion of "derivated/parent" rtag, eg: new_rtags = original_rtags.derive(__name__, custom_selector) Beside easier copying, when using the above method changes in original_rtags which are not overriden by new_rtags will be considered since it only hold its specific rules but look among its parent chain for non-found keys. Along the way, flake8 unittest_rtags. Closes #16164880

#!/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)