i18n/posplit
author Pierre-Yves David <pierre-yves.david@octobus.net>
Sat, 13 Apr 2024 23:40:28 +0200
changeset 51592 24844407fa0d
parent 48875 6000f5b25c9b
permissions -rwxr-xr-x
perf: clear vfs audit_cache before each run When generating a stream clone, we spend a large amount of time auditing path. Before this changes, the first run was warming the vfs cache for the other runs, leading to a large runtime difference and a "faulty" reported timing for the operation. We now clear this important cache between run to get a more realistic timing. Below are some example of median time change when clearing these cases. The maximum time for a run did not changed significantly. ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # benchmark.name = hg.perf.exchange.stream.generate # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.version = latest no-clearing: 17.289905 cache-clearing: 21.587965 (+24.86%, +4.30) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog no-clearing: 32.670748 cache-clearing: 40.467095 (+23.86%, +7.80) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog no-clearing: 37.838858 cache-clearing: 46.072749 (+21.76%, +8.23) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog no-clearing: 32.969395 cache-clearing: 39.646209 (+20.25%, +6.68) In addition, this significantly reduce the timing difference between the performance command, from the perf extensions and a `real `hg bundle` call producing a stream bundle. Some significant differences remain especially on the "mozilla-try" repositories, but they are now smaller. Note that some of that difference will actually not be attributable to the stream generation (like maybe phases or branch map computation). Below are some benchmarks done on a currently draft changeset fixing some unrelated slowness in `hg bundle` (34a78972af409d1ff37c29e60f6ca811ad1a457d) ### data-env-vars.name = mozilla-central-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default hg.perf.exchange.stream.generate: 21.587965 hg.command.bundle: 24.301799 (+12.57%, +2.71) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 40.467095 hg.command.bundle: 44.831317 (+10.78%, +4.36) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 39.646209 hg.command.bundle: 45.395258 (+14.50%, +5.75) ## data-env-vars.name = mozilla-try-2019-02-18-zstd-sparse-revlog hg.perf.exchange.stream.generate: 46.072749 hg.command.bundle: 55.882608 (+21.29%, +9.81) ## data-env-vars.name = mozilla-try-2023-03-22-zlib-general-delta hg.perf.exchange.stream.generate: 334.716708 hg.command.bundle: 377.856767 (+12.89%, +43.14) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog hg.perf.exchange.stream.generate: 302.972301 hg.command.bundle: 326.098755 (+7.63%, +23.13)

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


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()