i18n/posplit

largefiles: access to specific fields only if largefiles enabled (issue4547)

Even if largefiles extension is enabled in a repository, "repo"
object, which isn't "largefiles.reposetup()"-ed, is passed to
overridden functions in the cases below unexpectedly, because
extensions are enabled for each repositories strictly.

  (1) clone without -U:
  (2) pull with -U:
  (3) pull with --rebase:

    combination of "enabled@src", "disabled@dst" and
    "not-required@src" cause this situation.

       largefiles     requirement
    @src     @dst     @src            result
    -------- -------- --------------- --------------------
    enabled  disabled not-required    aborted unexpectedly
                      required        requirement error (intentional)
    -------- -------- --------------- --------------------
    enabled  enabled  *               success
    -------- -------- --------------- --------------------
    disabled enabled  *               success (only for "pull")
    -------- -------- --------------- --------------------
    disabled disabled not-required    success
                      required        requirement error (intentional)
    -------- -------- --------------- --------------------

  (4) update/revert with a subrepo disabling largefiles

In these cases, overridden functions cause accessing to largefiles
specific fields of not "largefiles.reposetup()"-ed "repo" object, and
execution is aborted.

  - (1), (2), (4) cause accessing to "_lfstatuswriters" in
    "getstatuswriter()" invoked via "updatelfiles()"

  - (3) causes accessing to "_lfcommithooks" in "overriderebase()"

For safe accessing to these fields, this patch examines whether passed
"repo" object is "largefiles.reposetup()"-ed or not before accessing
to them.

This patch chooses examining existence of newly introduced
"_largefilesenabled" instead of "_lfcommithooks" and
"_lfstatuswriters" directly, because the former is better name for the
generic "largefiles is enabled in this repo" mark than the latter.

In the future, all other overridden functions should avoid largefiles
specific processing for efficiency, and "_largefilesenabled" is better
also for such purpose.

BTW, "lfstatus" can't be used for such purpose, because some code
paths set it forcibly regardless of existence of it in specified
"repo" object.

#!/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()