annotate i18n/posplit @ 24998:c8a97fa742b7

rebase: use dirstateguard instead of dirstate.invalidate

Before this patch, "rebase.concludenode()" uses "dirstate.invalidate()"
as a kind of "restore .hg/dirstate to the original status" during a failure.

But it just discards changes in memory, and doesn't actually restore
".hg/dirstate". Then, it can't work as expected, if "dirstate.write()"
is executed while processing.

This patch uses "dirstateguard" instead of "dirstate.invalidate()" to
restore ".hg/dirstate" during a failure even if "dirstate.write()" is
executed before a failure.

This patch also removes "beginparentchage()" and "endparentchange()",
because "dirstateguard" makes them useless.

This is a part of preparations to fix the issue that the recent (in
memory) dirstate isn't visible to external processes (e.g. "precommit"
hook).

After this patch, the changed dirstate becomes visible to external
"precommit" hooks during "hg rebase" in "test-largefiles-misc.t",
because "dirstateguard()" writes it out. But this content isn't yet
correct, because:

  - "normal3" should be marked as "A"(dded) at committing

    It is newly added in the changeset being rebased.

  - but it is marked as "M"(odified)

    The result of "repo.setparents()" after "dirstateguard()" isn't
    yet written out before "precommit". So, merging is still in
    progress for "hg status" in it.

    This causes marking the file newly added on "other" branch as "A".

This will be fixed by subsequent patch.

#!/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()