view i18n/posplit @ 22196:23fe278bde43

largefiles: keep largefiles from colliding with normal one during linear merge Before this patch, linear merging of modified or newly added largefile causes unexpected result, if (1) largefile collides with same name normal one in the target revision and (2) "local" largefile is chosen, even though branch merging between such revisions doesn't. Expected result of such linear merging is: (1) (not yet recorded) largefile is kept in the working directory (2) largefile is marked as (re-)"added" (3) colliding normal file is marked as "removed" But actual result is: (1) largefile in the working directory is unlinked (2) largefile is marked as "normal" (so treated as "missing") (3) the dirstate entry for colliding normal file is just dropped (1) is very serious, because there is no way to restore temporarily modified largefiles. (3) prevents the next commit from adding the manifest with correct "removal of (normal) file" information for newly created changeset. The root cause of this problem is putting "lfile" into "actions['r']" in linear-merging case. At liner merging, "actions['r']" causes: - unlinking "target file" in the working directory, but "lfile" as "target file" is also largefile itself in this case - dropping the dirstate entry for target file "actions['f']" (= "forget") does only the latter, and this is reason why this patch doesn't choose putting "lfile" into it instead of "actions['r']". This patch newly introduces action "lfmr" (LargeFiles: Mark as Removed) to mark colliding normal file as "removed" without unlinking it. This patch uses "hg debugdirstate" instead of "hg status" in test, because: - choosing "local largefile" hides "removed" status of "remote normal file" in "hg status" output, and - "hg status" for "large2" in this case has another problem fixed in the subsequent patch
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
date Fri, 15 Aug 2014 20:28:51 +0900
parents e3ee7ec85a15
children a1924bc6e267
line wrap: on
line source

#!/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()