view i18n/posplit @ 20528:1a9ebc83a74c

win32: improve the performance of win32.unlink() over CIFS

Emulating POSIX unlink() behavior with os.rename() and os.unlink() is often slow
especially over CIFS from Windows clients due to its protocol overhead. This
patch changes win32.unlink() to try first an exclusive open with the Win32
delete-on-close flag, and if a sharing violation is detected, to fall back to
the original emulation.

This patch also removes a test with os.path.isdir() since we expect opening a
directory shall fail as os.unlink() would.

Example measurements (repeated 3-times after 1-time calibration):

(Without this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 19.871 secs (user 0.328+0.000 sys 1.794+0.000)
time: real 19.622 secs (user 0.312+0.000 sys 2.044+0.000)
time: real 19.138 secs (user 0.250+0.000 sys 1.872+0.000)

(Without this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 35.158 secs (user 0.156+0.000 sys 2.512+0.000)
time: real 35.272 secs (user 0.250+0.000 sys 2.512+0.000)
time: real 36.569 secs (user 0.203+0.000 sys 2.387+0.000)

(With this patch: hg update from null to default)
127 files updated, 0 files merged, 0 files removed, 0 files unresolved
time: real 17.893 secs (user 0.328+0.000 sys 1.700+0.000)
time: real 18.512 secs (user 0.265+0.000 sys 1.529+0.000)
time: real 20.238 secs (user 0.312+0.000 sys 1.685+0.000)

(With this patch: hg update from default to null)
0 files updated, 0 files merged, 127 files removed, 0 files unresolved
time: real 12.312 secs (user 0.250+0.000 sys 0.811+0.000)
time: real 12.471 secs (user 0.156+0.000 sys 0.889+0.000)
time: real 9.727 secs (user 0.125+0.000 sys 0.858+0.000)

#!/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()