devtools/fix_po_encoding
author Alexandre Fayolle <alexandre.fayolle@logilab.fr>
Tue, 25 Jan 2011 12:09:59 +0100
branchstable
changeset 6889 37668bf302f5
parent 0 b97547f5f1fa
permissions -rwxr-xr-x
improve massive deletion performance change hooks.integrity._DelayedDeleteOp implementation to give it a chance of processing the entities by chunks of reasonnable size (500 entities at a time) adapt ssplanner.DeleteEntitiesStep to call a variant of glob_delete_entity with several entities. That variant calls all the before_delete_entities hooks in one go, then performs the deletion, and then calls all the after_delete_entities hooks. The deletion is performed by grouping together entities by etype and by source. adapt the HooksManager to call the hooks on a list of entities instead of on a single entity. adapt the sources to be able to delete several entities of the same etype at once. changed the source fti_(un)index_entity methods to fti_(un)index_entities taking a collection of entities.

#!/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)