devtools/fix_po_encoding
author Adrien Chauve <adrien.chauve@logilab.fr>
Tue, 06 Apr 2010 16:50:53 +0200
changeset 5155 1dea6e0fdfc1
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
Switched from TwistedWeb2 to TwistedWeb - added HTTPResponse class in etwist/http.py (could be then abstracted in cubicweb/web) - added twisted.web2 http_headers.py file in cubicweb/web to handle HTTP headers conversion between raw headers and python object - deleted caching for base views (except for startup views). A better solution would be using weak entity tags (but they don't seem to be implemented in twisted.web). - added forbidden access message when browsing static local directories - tested with TwistedWeb 8, 9 and 10 TODO: ===== - Handle file uploading in forms. twisted.web seems to keep very little information (only file content) about uploaded files in twisted_request.args['input_field_name']. But it doesn't seem to keep track of filenames. Possible solutions : - use web2 code to parse raw request content still stored and available in twisted_request.content - find a magic function in twisted.web API to get the filenames - More tests.

#!/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)