view i18n/posplit @ 15551:1fa41d1f1351 stable

posix: add extended support for OS X path folding OS X does the following transformation on paths for comparisons: a) 8-bit strings are decoded as UTF-8 to UTF-16 b) undecodable bytes are percent-escaped c) accented characters are converted to NFD decomposed form, approximately d) characters are converted to _lowercase_ using internal tables Both (c) and (d) are done using internal tables that vary from release to release and match Unicode specs to greater or lesser extent. We approximate these functions using Python's internal Unicode data. With this change, Mercurial will (in almost all cases) match OS X folding and not report unknown file aliases for files in UTF-8 or other encodings.
author Matt Mackall <mpm@selenic.com>
date Tue, 22 Nov 2011 17:26:32 -0600
parents 4fd49329a1b5
children ff6ab0b2ebf7
line wrap: on
line source

#!/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()