view i18n/posplit @ 25343:7fbef7932af9

revset: optimize 'or' operation of trivial revisions to a list

As seen in issue4565 and issue4624, GUI wrappers and automated scripts are
likely to generate a long query that just has numeric revisions joined by 'or'.
One reason why is that they allows users to choose arbitrary revisions from
a list. Because this use case isn't handled well by smartset, let's optimize
it to a plain old list.

Benchmarks:

1) reduce nesting of chained 'or' operations
2) optimize to a list (this patch)

revset #0: 0 + 1 + 2 + ... + 1000
1) wall 0.483341 comb 0.480000 user 0.480000 sys 0.000000 (best of 20)
2) wall 0.025393 comb 0.020000 user 0.020000 sys 0.000000 (best of 107)

revset #1: sort(0 + 1 + 2 + ... + 1000)
1) wall 0.035240 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
2) wall 0.026432 comb 0.030000 user 0.030000 sys 0.000000 (best of 102)

revset #2: first(0 + 1 + 2 + ... + 1000)
1) wall 0.028949 comb 0.030000 user 0.030000 sys 0.000000 (best of 100)
2) wall 0.025503 comb 0.030000 user 0.030000 sys 0.000000 (best of 106)

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

import re
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[:] = []
    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
                        continue
                    directive = mdirective.group(1)
                    if directive in ('container', 'include'):
                        if msgid.rstrip('\n').count('\n') == 0:
                            # only rst syntax, nothing to translate
                            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()