cubicweb/devtools/fix_po_encoding
author Laurent Peuch <cortex@worlddomination.be>
Tue, 21 May 2019 16:36:12 +0200
changeset 12685 84a8a8915512
parent 11057 0b59724cb3f2
child 12779 44147dab9d27
permissions -rwxr-xr-x
[cubicweb-ctl] move to accepting only once instance name per command The rationals behind this decision are: - while in the past managing all instances sytem wide made a lot of sens, pratices have evolved today and we've moved to managing one instance by one - this makes things easier to debug since commands since using them on several instances were making this harder (errors hidden in the middle) - also solve the problem of the return code to have, before it was always 0 which prevented to do things like: ipython --pdb $(which cubicweb-ctl) $command $instance or shell scripts that used it - this simplify the code and is always good to take

#!/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)