view i18n/posplit @ 16749:eab8ca175262

bdiff: use Py_ssize_t instead of int Reduces the conversion warnings mercurial/bdiff.c(61) : warning C4244: '=' : conversion from '__int64' to 'int', possible loss of data mercurial/bdiff.c(307) : warning C4244: 'function' : conversion from 'Py_ssize_t' to 'int', possible loss of data mercurial/bdiff.c(308) : warning C4244: 'function' : conversion from 'Py_ssize_t' to 'int', possible loss of data mercurial/bdiff.c(362) : warning C4244: '+=' : conversion from '__int64' to 'int', possible loss of data mercurial/bdiff.c(380) : warning C4244: '=' : conversion from '__int64' to 'int', possible loss of data mercurial/bdiff.c(381) : warning C4244: 'function' : conversion from '__int64' to 'uint32_t', possible loss of data mercurial/bdiff.c(382) : warning C4244: 'function' : conversion from '__int64' to 'uint32_t', possible loss of data mercurial/bdiff.c(416) : warning C4244: '=' : conversion from 'Py_ssize_t' to 'int', possible loss of data to mercurial/bdiff.c(383) : warning C4244: 'function' : conversion from '__int64' to 'uint32_t', possible loss of data mercurial/bdiff.c(384) : warning C4244: 'function' : conversion from '__int64' to 'uint32_t', possible loss of data mercurial/bdiff.c(385) : warning C4244: 'function' : conversion from 'Py_ssize_t' to 'uint32_t', possible loss of data on the three putbe32() calls in the function bdiff when compiling for Windows x64 target using the Microsoft compiler.
author Adrian Buehlmann <adrian@cadifra.com>
date Tue, 15 May 2012 22:36:27 +0200
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()