i18n/posplit
author Adrian Buehlmann <adrian@cadifra.com>
Wed, 06 Apr 2011 18:09:43 +0200
changeset 13916 98ee3dd5bab4
parent 11389 4fd49329a1b5
child 20359 ff6ab0b2ebf7
permissions -rwxr-xr-x
path_auditor: check filenames for basic platform validity (issue2755) Example (on Windows): $ hg parents $ hg manifest tip con.xml $ hg update abort: filename contains 'con', which is reserved on Windows: con.xml Before this patch, update produced (as explained in issue2755): $ hg update abort: No usable temporary filename found I've added the new function checkwinfilename to util.py and not to windows.py, so that we can later call it when running on posix platforms too, for when we decide to implement a (configurable) warning message on 'hg add'. As per this patch, checkwinfilename is currently only used when running on Windwows. path_auditor calls checkosfilename, which is a NOP on posix and an alias for checkwinfilename on Windows.

#!/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()