devtools/fix_po_encoding
author Julien Cristau <julien.cristau@logilab.fr>
Wed, 23 Oct 2013 14:18:58 +0200
branchstable
changeset 9305 f7a738afc295
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
[notification] avoid leaking cnxsets (closes #3243810) When sending notifications, we get each recipient as either an email address or a CWUser. In the latter case, we create a temporary session for that user and use it to send the mail. However, if we later decided to not send the mail after all, we'd leak the session and its cnxset. Add a try block inside the loop to make sure the temporary sessions are closed properly.

#!/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)