devtools/fix_po_encoding
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Mon, 23 Jan 2012 13:25:02 +0100
changeset 8190 2a3c1b787688
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[vreg] move base registry implementation to logilab.common. Closes #1916014 A new logilab.common.registry module has been created with content from * cw.vreg (the whole things that was in there) * cw.appobject (base selectors and all). In the process, we've done some renaming: * former selector functions are now known as "predicate", though you still use predicates to build an object'selector * hence `objectify_selector` decorator is now `objectify_predicate` * the top level registry is now `RegistryStore` (was `VRegistry`) Also there is no more need for the @lltrace decorator. On the CubicWeb side, the `selectors` module has been renamed to `predicates`. There should be full backward compat with proper deprecation warnings.

#!/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)