i18n/posplit

largefiles: optimize status when files are specified (issue3144)

This fixes a performance issue with 'hg status' when files are specified
on the command-line.  Previously, a large amount of largefiles code was
executed, even if files were specified on the command-line and those files
were not largefiles.  This patch fixes the problem by first checking if
non-largefiles were specified on the command-line and, just letting the
normal status function handle the case if they were.

On a brand new machine, the execution time for 'hg status filename' on
a repository with largefiles was:

real    0m0.636s
user    0m0.512s
sys     0m0.120s

versus the following (the same repository, with largefiles disabled):

real    0m0.215s
user    0m0.180s
sys     0m0.032s

After this patch, the performance of 'hg status filename' on the same
repository, with largefiles enabled is:

real    0m0.228s
user    0m0.189s
sys     0m0.036s

This performance boost is also true when patterns (rather than specific
files) are specified on the command-line.

In the case where patterns are specified in addition to a file list, we
just defer to the normal codepath in order to not spend extra time
expanding the patterns to just risk having to expand them again later.

#!/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()