i18n/posplit
author Brodie Rao <brodie@sf.io>
Sun, 17 Nov 2013 18:04:28 -0500
changeset 20179 5bb3826bdac4
parent 11389 4fd49329a1b5
child 20359 ff6ab0b2ebf7
permissions -rwxr-xr-x
revlog: read/cache chunks in fixed windows of 64 KB When reading a revlog chunk, instead of reading up to 64 KB ahead of the request offset and caching that, this change caches a fixed window before and after the requested data that falls on 64 KB boundaries. This increases cache hits when reading revlogs backwards. Running perfmoonwalk on the Mercurial repo (with almost 20,000 changesets) on Mac OS X with an SSD, before this change: $ hg perfmoonwalk ! wall 2.307994 comb 2.310000 user 2.120000 sys 0.190000 (best of 5) (Each run has 10,668 cache hits and 9,304 misses.) After this change: $ hg perfmoonwalk ! wall 1.814117 comb 1.810000 user 1.810000 sys 0.000000 (best of 6) (19,931 cache hits, 62 misses.) On a busy NFS share, before this change: $ hg perfmoonwalk ! wall 17.000034 comb 4.100000 user 3.270000 sys 0.830000 (best of 3) After: $ hg perfmoonwalk ! wall 1.746115 comb 1.670000 user 1.660000 sys 0.010000 (best of 5)

#!/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()