view i18n/posplit @ 29021:92d37fb3f1aa stable

verify: don't init subrepo when missing one is referenced (issue5128) (API)

Initializing a subrepo when one doesn't exist is the right thing to do when the
parent is being updated, but in few other cases.  Unfortunately, there isn't
enough context in the subrepo module to distinguish this case.  This same issue
can be caused with other subrepo aware commands, so there is a general issue
here beyond the scope of this fix.

A simpler attempt I tried was to add an '_updating' boolean to localrepo, and
set/clear it around the call to mergemod.update() in hg.updaterepo().  That
mostly worked, but doesn't handle the case where archive will clone the subrepo
if it is missing.  (I vaguely recall that there may be other commands that will
clone if needed like this, but certainly not all do.  It seems both handy, and a
bit surprising for what should be a read only operation.  It might be nice if
all commands did this consistently, but we probably need Angel's subrepo caching
first, to not make a mess of the working directory.)

I originally handled 'Exception' in order to pick up the Aborts raised in
subrepo.state(), but this turns out to be unnecessary because that is called
once and cached by ctx.sub() when iterating the subrepos.

It was suggested in the bug discussion to skip looking at the subrepo links
unless -S is specified.  I don't really like that idea because missing a subrepo
or (less likely, but worse) a corrupt .hgsubstate is a problem of the parent
repo when checking out a revision.  The -S option seems like a better fit for
functionality that would recurse into each subrepo and do a full verification.

Ultimately, the default value for 'allowcreate' should probably be flipped, but
since the default behavior was to allow creation, this is less risky for now.

#!/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
                        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()