devtools/fix_po_encoding
author Sylvain Thénault <sylvain.thenault@logilab.fr>
Thu, 13 Feb 2014 13:58:28 +0100
changeset 9954 79d34ba48612
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[CWEP002] refactor rql read security checking Split 'check_read_perms' into 'check_relations_perms' which checks relations 'read' permissions and 'get_local_checks' which build dictionary of local security checks (rql expression) for variables. This allows to check relations 'read' permissions earlier in the process and so to prepare insertion of the rql rewriter: we want to check permissions of the computed relation, not permissions of relations introduced by the associated rule, to conform to the CWEP. Related to #3546717

#!/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)