i18n/posplit
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 26 Apr 2019 00:48:12 +0200
changeset 42485 4a3abb33380a
parent 41768 aaad36b88298
child 43731 47ef023d0165
permissions -rwxr-xr-x
deltas: set estimated compression upper bound to "3x" instead of "10x" In pratice, we very rarely observer compression better than "3x" on manifest deltas. Having a more aggressive estimate significantly helps our pathological use case on a private repository. Here are a comparison of timings using different upper bound. Estimated compression | ø | ×10 | ×5 | ×3 | timing | 14.11 | 2.61 | 1.96 | 1.53 | We also tested the impact of this series on an array of public repositories. This shown no impact in either size nor timing. Full data set below for those interested. Size ---- Regarding size, not significant impact have been noticed on neither public nor private repositories. Here are the number we gathered on public repositories: zlib/upperbound | no | 10x | 5x | 3x mercurial | 5 875 730 | 5 875 730 | 5 875 730 | 5 875 730 pypy | 27 782 913 | 27 782 913 | 27 782 913 | 27 782 913 netbeans | 159 161 207 | 159 161 207 | 159 161 207 | 159 959 879 (+0.5%) mozilla-central | 323 841 642 | 323 841 642 | 323 841 642 | 319 867 519 (-2.5%) mozilla-try | 746 649 123 | 746 649 123 | 746 649 123 | 741 155 568 (-0.7%) private-repo | 1 485 287 294 | 1 485 287 294 | 1 485 287 294 | 1 409 248 382 (-5.1%) zstd/upperbound | no | 10x | 5x | 3x mercurial | 5 895 206 | 5 895 206 | 5 895 206 | 5 895 206 pypy | 28 689 230 | 28 689 230 | 28 689 230 | 28 689 230 netbeans | 157 636 387 | 157 636 387 | 157 636 387 | 159 692 678 (+1.3%) mozilla-central | 317 650 281 | 317 650 281 | 317 650 281 | 319 613 603 (+0.6%) mozilla-try | 737 555 275 | 737 555 275 | 737 555 275 | 738 079 473 (+0.1%) private-repo | 1 352 362 982 | 1 352 362 982 | 1 346 961 880 | 1 361 327 384 (+0.7%) Speed ------ Timing gathered using `hg perfrevlogwrite -m`. Value are in seconds. mercurial zlib | no | 10x | 5x | 3x | total | 65.551783 | 65.388887 | 65.260658 | 65.321199 | max | 0.034544 | 0.034571 | 0.034659 | 0.034521 | 99.99% | 0.034544 | 0.034571 | 0.034659 | 0.034521 | zstd | no | 10x | 5x | 3x | total | 49.118449 | 49.054062 | 48.753588 | 48.740230 | max | 0.009338 | 0.009239 | 0.009202 | 0.009178 | 99.99% | 0.007618 | 0.007639 | 0.007626 | 0.007621 | pypy zlib | no | 10x | 5x | 3x | total | 560.865984 | 558.983817 | 559.083815 | 559.349152 | max | 0.219614 | 0.215922 | 0.218112 | 0.218107 | 99.99% | 0.219614 | 0.215922 | 0.218112 | 0.218107 | zstd | no | 10x | 5x | 3x | total | 349.393280 | 347.395819 | 347.185407 | 345.643985 | max | 0.084143 | 0.083536 | 0.081834 | 0.082178 | 99.99% | 0.039445 | 0.039639 | 0.039612 | 0.039175 | netbeans zlib | no | 10x | 5x | 3x | total | 33103.327727 | 33314.932260 | 33211.745233 | 33345.891778 | max | 2.666852 | 2.672059 | 2.662453 | 2.662936 | 99.99% | 2.058772 | 2.070429 | 2.069569 | 2.064653 | zstd | no | 10x | 5x | 3x | total | 20112.102708 | 20095.879719 | 20083.390300 | 20123.221859 | max | 2.063482 | 2.062851 | 2.065229 | 2.060147 | 99.99% | 1.146647 | 1.143794 | 1.142933 | 1.146529 | mozilla zlib | no | 10x | 5x | 3x | total | 41374.102138 | 41418.816773 | 41381.956370 | 41334.280732 | max | 3.383474 | 3.387400 | 3.405711 | 3.387316 | 99.99% | 1.006755 | 1.005954 | 1.007700 | 1.007373 | zstd | no | 10x | 5x | 3x | total | 24689.691520 | 24643.939662 | 24664.630027 | 24664.512714 | max | 1.460822 | 1.449640 | 1.439747 | 1.465304 | 99.99% | 0.527111 | 0.527377 | 0.527807 | 0.527226 |

#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

from __future__ import absolute_import, print_function

import polib
import re
import sys

def addentry(po, entry, cache):
    e = cache.get(entry.msgid)
    if e:
        e.occurrences.extend(entry.occurrences)

        # merge comments from entry
        for comment in entry.comment.split('\n'):
            if comment and comment not in e.comment:
                if not e.comment:
                    e.comment = comment
                else:
                    e.comment += '\n' + comment
    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[:] = []
    findd = re.compile(r' *\.\. (\w+)::') # for finding directives
    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 and msgid != '::':
                newentry = mkentry(entry, delta, msgid, msgstr)
                mdirective = findd.match(msgid)
                if mdirective:
                    if not msgid[mdirective.end():].rstrip():
                        # only directive, nothing to translate here
                        delta += 2
                        continue
                    directive = mdirective.group(1)
                    if directive in ('container', 'include'):
                        if msgid.rstrip('\n').count('\n') == 0:
                            # only rst syntax, nothing to translate
                            delta += 2
                            continue
                        else:
                            # lines following directly, unexpected
                            print('Warning: text follows line with directive'
                                  ' %s' % directive)
                    comment = 'do not translate: .. %s::' % directive
                    if not newentry.comment:
                        newentry.comment = comment
                    elif comment not in newentry.comment:
                        newentry.comment += '\n' + comment
                addentry(po, newentry, cache)
            delta += 2 + msgid.count('\n')
    po.save()