annotate i18n/posplit @ 19892:77872b002e73

convert: update source shamap when using filemap, just as when not using filemap

The reverse mapping was introduced in 2147a734dcf9 to make roundtrip
conversions possible ... but it did not work when using filemap.

Roundtrips with filemaps will of course only work flawlessly if inverse
mappings are used.

Especially, if a lossy convert mapping is used in one direction, then only
linear lines of development can be converted in the other direction. With this
constraint convert will do the right thing by assuming that excluded files
haven't been changed.)

A test case with general coverage of hg-hg roundtrips with filemap is added.

(There a cases where adding records of converted revisions to the shamap in the
source repository doesn't work - especially when converting the same repo to
several other repos and back. It would arguably be better if convert only
updated the shamaps in the target repo but read shamaps from both the source
and and target repo ... but that is a different story. Making the stuff we have
work consistently is step forward no matter what.)

#!/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()