i18n/posplit
author Pierre-Yves David <pierre-yves.david@logilab.fr>
Wed, 18 Jan 2012 16:52:26 +0100
changeset 15919 69e792cf7851
parent 11389 4fd49329a1b5
child 20359 ff6ab0b2ebf7
permissions -rwxr-xr-x
config: have a way to backup and restore value in config This is introduce to allow temporary overwriting of a config value while being able to reinstall the old value once done. The main advantage over using ``config`` and ``setconfig`` is that backup and restore will properly restore the lack of any config. Restoring the fact that there was no value is important to allow config user to keep using meaniful default value. A more naive approach will result in the following scenario:: Before: config(section, item, my_default) --> my_default temporal overwrite old = config(section, item) … setconfig(section, item, old) After config(section, item, my_default) --> None The first user of this feature should be mq to overwriting minimal phase of future commit.

#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

import sys
import polib

def addentry(po, entry, cache):
    e = cache.get(entry.msgid)
    if e:
        e.occurrences.extend(entry.occurrences)
    else:
        po.append(entry)
        cache[entry.msgid] = entry

def mkentry(orig, delta, msgid, msgstr):
    entry = polib.POEntry()
    entry.merge(orig)
    entry.msgid = msgid or orig.msgid
    entry.msgstr = msgstr or orig.msgstr
    entry.occurrences = [(p, int(l) + delta) for (p, l) in orig.occurrences]
    return entry

if __name__ == "__main__":
    po = polib.pofile(sys.argv[1])

    cache = {}
    entries = po[:]
    po[:] = []
    for entry in entries:
        msgids = entry.msgid.split(u'\n\n')
        if entry.msgstr:
            msgstrs = entry.msgstr.split(u'\n\n')
        else:
            msgstrs = [u''] * len(msgids)

        if len(msgids) != len(msgstrs):
            # places the whole existing translation as a fuzzy
            # translation for each paragraph, to give the
            # translator a chance to recover part of the old
            # translation - erasing extra paragraphs is
            # probably better than retranslating all from start
            if 'fuzzy' not in entry.flags:
                entry.flags.append('fuzzy')
            msgstrs = [entry.msgstr] * len(msgids)

        delta = 0
        for msgid, msgstr in zip(msgids, msgstrs):
            if msgid:
                newentry = mkentry(entry, delta, msgid, msgstr)
                addentry(po, newentry, cache)
            delta += 2 + msgid.count('\n')
    po.save()