Mercurial > hg
view i18n/posplit @ 18894:ed46c2b98b0d
dicthelpers.diff: compare against default for missing values
This is not only a bit faster, but also aligns with callers' expectations
better since we can legitimately have manifestdict's _flags set to '' instead
of unset.
hg perfmergecalculate -r .
before: ! wall 0.139582 comb 0.140000 user 0.140000 sys 0.000000 (best of 59)
after: ! wall 0.126154 comb 0.120000 user 0.120000 sys 0.000000 (best of 74)
hg perfmergecalculate -r .^
before: ! wall 0.236333 comb 0.240000 user 0.240000 sys 0.000000 (best of 36)
after: ! wall 0.212265 comb 0.210000 user 0.210000 sys 0.000000 (best of 45)
author | Siddharth Agarwal <sid0@fb.com> |
---|---|
date | Wed, 10 Apr 2013 12:31:07 -0700 |
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()