Mercurial > hg
view i18n/posplit @ 51597:b4a6a1ff8fce
tags-cache: skip the filternode step if we are not going to use it
When warming the hgtagsfnodescache, we don't need the actual result, so we can
simply skip the part that "filter" fnode we read from the cache. So provide a
quite visible speed up to the top level `hg debugupdatecache` function.
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.debug.debug-update-cache
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.pre-state = warm
before: 19.947581
after: 18.916804 (-5.17%, -1.03)
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Wed, 13 Mar 2024 11:38:28 +0100 |
parents | 6000f5b25c9b |
children | f4733654f144 |
line wrap: on
line source
#!/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()