largefiles: simplify cachelfiles - don't spend a lot of time checking hashes
cachelfiles jumped through loops to handle merges and modified files ... but it
did apparently no longer have a valid reason to do so. It should just always
make sure that the largefiles referenced from the standins are present - no
matter which actual largefile is stored in the working directory. If there is
no standin then there is nothing to fetch.
The old code usually verified the hash of all largefiles every time this
function was invoked - for examply by 'update'.
This change makes a trivial noop update 5-10 seconds faster on our repo (with
the other 50% spent doing another unnecessary hashing of all largefiles).
#!/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()