view i18n/posplit @ 13039:dd24f3e7ca9e stable

util.datestr: do not crash on revisions with negative timestamp (issue2513)

Python's time.gmtime(lt) fails on Windows, producing a traceback with

  ValueError: (22, 'Invalid argument')

if lt < -43200.

We get a local time boundary value of -43200 if we take "the epoch"

   Thu Jan 01 00:00:00 1970 = time.gmtime(0)

from timezone 'UTC+0' into timezone 'UTC-12'. All other timezones will have
larger local time values for that point in time.

Aborting with a traceback on 'hg log' for revisions with a timestamp value
< -43200 is clearly not acceptable.

Returning "invalid timestamp" or similar as string representation is not an
option either, since that may crash other tools which parse the output of
'hg log'.

Instead, we teach util.datestr() to return the epoch in timezone UTC+0 on
*all platforms*, represented by the string

  Thu Jan 01 00:00:00 1970 +0000

if the timestamp's unix time value is negative.

(based on a patch originally proposed by Benjamin Pollack)

#!/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()