i18n/posplit

filemerge: make the 'local' path match the format that 'base' and 'other' use

If we pass a separate '$output' arg to the merge tool, we produce four files:
local, base, other, and output.  In this situation, 'output' will be the
original filename, 'base' and 'other' are temporary files, and previously
'local' would be the backup file (so if 'output' was foo.txt, 'local' would be
foo.txt.orig).

This change makes it so that 'local' follows the same pattern as 'base' and
'other' - it will be a temporary file either in the
`experimental.mergetempdirprefix`-controlled directory with a name like
foo~local.txt, or in the normal system-wide temp dir with a name like
foo~local.RaNd0m.txt.

For the cases where the merge tool does not use an '$output' arg, 'local' is
still the destination filename, and 'base' and 'other' are unchanged.

The hope is that this is much easier for people to reason about; rather than
having a tool like Meld pop up with three panes, one of them with the filename
"foo.txt.orig", one with the filename "foo.txt", and one with
"foo~other.StuFf2.txt", we can (when the merge temp dir stuff is enabled) make
it show up as "foo~local.txt", "foo.txt" and "foo~other.txt", respectively.

This also opens the door to future customization, such as getting the
operation-provided labels and a hash prefix into the filenames (so we see
something like "foo~dest.abc123", "foo.txt", and "foo~src.d4e5f6").

Differential Revision: https://phab.mercurial-scm.org/D2889

#!/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()