view i18n/posplit @ 31972:ba7e4a4a7f32

obsolescence: add test case D-4 for obsolescence markers exchange

About 3 years ago, in August 2014, the logic to select what markers to select on
push was ported from the evolve extension to Mercurial core. However, for some
unclear reasons, the tests for that logic were not ported alongside.
I realised it a couple of weeks ago while working on another push related issue.
I've made a clean up pass on the tests and they are now ready to integrate the
core test suite. This series of changesets do not change any logic. I just adds
test for logic that has been around for about 10 versions of Mercurial.

They are a patch for each test case. It makes it easier to review and postpone
one with documentation issues without rejecting the wholes series.

This patch introduce case D-4: unknown changeset in between known on

Each test case comes it in own test file. It help parallelism and does not
introduce a significant overhead from having a single unified giant test file.
Here are timing  to support this claim.

# Multiple test files version:
# run-tests.py --local -j 1 test-exchange-*.t
53.40s user 6.82s system 85% cpu 1:10.76 total
52.79s user 6.97s system 85% cpu 1:09.97 total
52.94s user 6.82s system 85% cpu 1:09.69 total

# Single test file version:
# run-tests.py --local -j 1 test-exchange-obsmarkers.t
52.97s user 6.85s system 85% cpu 1:10.10 total
52.64s user 6.79s system 85% cpu 1:09.63 total
53.70s user 7.00s system 85% cpu 1:11.17 total

#!/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)
    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()