view i18n/posplit @ 22668:13e3f07d74a3

templater: add count template filter, plus tests

Previously there was no way of telling how much children or bookmarks or tags a
certain changeset has in a template. It was possible to tell if a changeset has
either 0 or not 0 bookmarks, but not to tell if it has 1 or 2 of them, for
example.

This filter, simply named count, makes it possible to count the number of items
in a list or the length of a string (or, anything that python's len can count).
E.g.: {children|count}, {bookmarks|count}, {file_adds|count}.

Testing the filter on node hash and shortened node hash is chosen because they
both have defined length.

As for lists of strings - children, tags and file_adds are used, because they
provide some variety and also prove that what's counted is the number of string
items in the list, and not the list stringified (they are lists of non-empty,
multi-character strings).

Additionally, revset template function is used for testing the filter, since
the combination is very flexible and will possibly be used together a lot.

(The previous version of this patch had an incorrect email subject and was
apparently lost - patchwork says the patch has been accepted, but it's not so.
The changes between that and this patch are minimal: now the filter does not
disturb the alphabetical order of function definitions and dict keys.)

#!/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()