diff: do not concatenate immutable bytes while building a/b bodies (issue6445)
Use bytearray instead. I don't know what's changed since Python 2, but bytes
concatenation is 100x slow on Python 3.
% python2.7 -m timeit -s "s = b''" "for i in range(10000): s += b'line'"
1000 loops, best of 3: 321 usec per loop
% python3.9 -m timeit -s "s = b''" "for i in range(10000): s += b'line'"
5 loops, best of 5: 39.2 msec per loop
Benchmark using tailwind.css (measuring the fast path, a is empty):
% HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \
--color=always --config diff.word-diff=true >/dev/null
(prev) time: real 1.580 secs (user 1.560+0.000 sys 0.020+0.000)
(this) time: real 1.610 secs (user 1.570+0.000 sys 0.030+0.000)
% HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \
--color=always --config diff.word-diff=true >/dev/null
(prev) time: real 114.500 secs (user 114.460+0.000 sys 0.030+0.000)
(this) time: real 2.180 secs (user 2.140+0.000 sys 0.040+0.000)
Benchmark using random tabular text data (not the fast path):
% dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf
% hg ci -ma
% dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf
% hg ci -mb
% HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \
--color=always --config diff.word-diff=true >/dev/null
(prev) time: real 3.240 secs (user 3.040+0.000 sys 0.200+0.000
(this) time: real 3.230 secs (user 3.070+0.000 sys 0.160+0.000)
% HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \
--color=always --config diff.word-diff=true >/dev/null
(prev) time: real 44.130 secs (user 43.850+0.000 sys 0.270+0.000)
(this) time: real 4.170 secs (user 3.850+0.000 sys 0.310+0.000)
#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#
from __future__ import absolute_import, print_function
import polib
import re
import sys
def addentry(po, entry, cache):
e = cache.get(entry.msgid)
if e:
e.occurrences.extend(entry.occurrences)
# merge comments from entry
for comment in entry.comment.split('\n'):
if comment and comment not in e.comment:
if not e.comment:
e.comment = comment
else:
e.comment += '\n' + comment
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
delta += 2
continue
directive = mdirective.group(1)
if directive in ('container', 'include'):
if msgid.rstrip('\n').count('\n') == 0:
# only rst syntax, nothing to translate
delta += 2
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()