i18n/posplit
author Pierre-Yves David <pierre-yves.david@octobus.net>
Tue, 03 Sep 2024 11:11:17 +0200
changeset 51977 42a116f1cdc1
parent 51863 f4733654f144
permissions -rwxr-xr-x
branchmap-v3: introduce a "stop_rev" argument to `headsrevs` The `headsrevs` method of the revlog already have a `revs` argument to compute the headrevs of a limited set of heads. However, it disable the use of the native compiled code to compute the heads, which slows down the branchmap v3 code a lot. The branchmap v3 usage is actually quite constrained as we will always only ignores a part at the top of the graph. So we could be significantly faster. We start by making small change to the python side to improve the situation and introduce the new API. More collaboration with the native code are coming later. This massively speedup operation and close most of the remaining gaps between branchmap-v3 and branchmap-v2. especially on repository with many revs like mozilla-try. A small overhead remains mostly because the `headrevs` logic currently has some inefficiently. We will look into them from there. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.368769 (+57.79%, +0.14) branch-v3 after: 0.239857 (+2.63%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.372460 (+58.34%, +0.14) branch-v3 after: 0.240972 (+2.44%, +0.01) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.318907 (+24.78%, +0.06) branch-v3 after: 0.268560 (+5.08%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.349752 (+3.17%, +0.01) branch-v3 after: 0.349389 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.354300 (+2.24%, +0.01) branch-v3 after: 0.355661 (+2.64%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.396293 (+4.23%, +0.02) branch-v3 after: 0.408851 (+7.54%, +0.03) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.424769 (+3.06%, +0.01) branch-v3 after: 0.427782 (+3.79%, +0.02) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.421796 (+2.28%, +0.01) branch-v3 after: 0.422354 (+2.41%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.443849 (+3.34%, +0.01) branch-v3 after: 0.443197 (+3.19%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.234055 (+83.18%, +2.83) branch-v3 after: 3.819477 (+12.23%, +0.42) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.307813 (+82.58%, +2.85) branch-v3 after: 3.590284 (+3.92%, +0.14) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.176076 (+49.36%, +1.71) branch-v3 after: 3.633278 (+4.84%, +0.17)

#!/usr/bin/env python3
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

from __future__ import annotations

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()