devtools/fix_po_encoding
author Aurelien Campeas <aurelien.campeas@logilab.fr>
Mon, 26 Aug 2013 16:14:09 +0200
changeset 9256 697a8181ba30
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
remove 3.9 bw compat In cw 3.9, interfaces are deprecated and replaced with adapters, yielding a lot of bw compat in many places -- most if this patch is concerned with the interface bw compat - cwvreg: interface cleanup - doc/adapters.rst: interface cleanup - entities/adapters.py, wfobjs.py: interfaces bw compat - entity.py: interfaces bw compat, also get_value, delete, attr_metadata, has_perm, set_related_cache, clear_related_cache, clear_related_cache, related_rql - predicates.py: score_interfaces & implements - interfaces.py & mixins.py: 100% gone - view.py: implement_adapter_compat, unwrap_adapter_compat - calendar.py, editcontroller.py, ibreadcrumbs.py, navigation.py, xmlrss.py: interface bw compat - treeview.py: salvage one function from mixins.py 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)