view i18n/posplit @ 15462:2b1ec74c961f stable

mdiff/patch: fix bad hunk handling for unified diffs with zero context

Prior to this patch "hg diff -U0", i.e., zero lines of context, would
output hunk headers with a start line one greater than what GNU patch
and git output. Guido van Rossum documents the unified diff format[1]
as having a start line value "one lower than one would expect" for
zero length hunks.

Comparing the behaviour of the three systems prior to this patch in
transforming

  c1
  c3

to

  c1
  c2
  c3

- GNU "diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "git diff -U0" reports the hunk as "@@ -1,0 +2 @@"
- "hg diff -U0" reports the hunk as "@@ -2,0 +2,1 @@"

After this patch, "hg diff -U0" reports "@@ -1,0 +2,1 @@".

Since "hg export --config diff.unified=0" outputs zero-context unified
diffs, "hg import" has also been updated to account for start lines
one less than expected for zero length hunk ranges.

[1]: http://www.artima.com/weblogs/viewpost.jsp?thread=164293

#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

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[:] = []
    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:
                newentry = mkentry(entry, delta, msgid, msgstr)
                addentry(po, newentry, cache)
            delta += 2 + msgid.count('\n')
    po.save()