view i18n/posplit @ 39604:335ae4d0a552

bundlerepo: dynamically create repository type from base repository

Previously, bundlerepository inherited from localrepo.localrepository.
You simply instantiated a bundlerepository and its __init__ called
localrepo.localrepository.__init__. Things were simple.

Unfortunately, this strategy is limiting because it assumes that
the base repository is a localrepository instance. And it assumes
various properties of localrepository, such as the arguments its
__init__ takes. And it prevents us from changing behavior of
localrepository.__init__ without also having to change derived classes.

Previous and ongoing work to abstract storage revealed these
limitations.

This commit changes the initialization strategy of bundle repositories
to dynamically create a type to represent the repository. Instead of
a static type, we instantiate a new local repo instance via
localrepo.instance(). We then combine its __class__ with
bundlerepository to produce a new type. This ensures that no matter
how localrepo.instance() decides to create a repository object, we
can derive a bundle repo object from it. i.e. localrepo.instance()
could return a type that isn't a localrepository and it would "just
work."

Well, it would "just work" if bundlerepository's custom implementations
only accessed attributes in the documented repository interface. I'm
pretty sure it violates the interface contract in a handful of
places. But we can worry about that another day. This change gets us
closer to doing more clever things around instantiating repository
instances without having to worry about teaching bundlerepository about
them.

.. api::

   ``bundlerepo.bundlerepository`` is no longer usable on its own.

   The class is combined with the class of the base repository it is
   associated with at run-time.

   New bundlerepository instances can be obtained by calling
   ``bundlerepo.instance()`` or ``bundlerepo.makebundlerepository()``.

Differential Revision: https://phab.mercurial-scm.org/D4555

#!/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)

        # merge comments from entry
        for comment in entry.comment.split('\n'):
            if comment and comment not in e.comment:
                if not e.comment:
                    e.comment = comment
                else:
                    e.comment += '\n' + comment
    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()