view i18n/posplit @ 21883:87aa279f7073

largefiles: show also how many data entities are outgoing at "hg outgoing"

Before this patch, "hg outgoing --large" shows which largefiles are
changed or added in outgoing revisions only in the point of the view
of filenames.

For example, according to the list of outgoing largefiles shown in "hg
outgoing" output, users should expect that the former below costs much
more to upload outgoing largefiles than the latter.

  - outgoing revisions add a hundred largefiles, but all of them refer
    the same data entity

    in this case, only one data entity is outgoing, even though "hg
    summary" says that a hundred largefiles are outgoing.

  - a hundred outgoing revisions change only one largefile with
    distinct data

    in this case, a hundred data entities are outgoing, even though
    "hg summary" says that only one largefile is outgoing.

But the latter costs much more than the former, in fact.

This patch shows also how many data entities are outgoing at "hg
outgoing" by counting number of unique hash values for outgoing
largefiles.

When "--debug" is specified, this patch also shows what entities (in
hash) are outgoing for each largefiles listed up, for debug purpose.

In "ui.debugflag" route, "addfunc()" can append given "lfhash" to the
list "toupload[fn]" always without duplication check, because
de-duplication is already done in "_getoutgoings()".

#!/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()