##// END OF EJS Templates
pathcopies: give up any optimization based on `introrev`...
pathcopies: give up any optimization based on `introrev` Between 8a0136f69027 and d98fb3f42f33, we sped up the search for the introduction revision during path copies. However, further checking show that finding the introduction revision is still expensive and that we are better off without it. So we simply drop it and only rely on the linkrev optimisation. I ran `perfpathcopies` on 6989 pair of revision in the pypy repository (`hg perfhelper-pathcopies`. The result is massively in favor of dropping this condition. The result of the copy tracing are unchanged. Attempt to use a smaller changes preserving linkrev usage were unsuccessful, it can return wrong result. The following changesets broke test-mv-cp-st-diff.t - if not f.isintroducedafter(limit): + if limit >= 0 and f.linkrev() < limit: return None Here are various numbers (before this changeset/after this changesets) source destination before after saved-time ratio worth cases e66f24650daf 695dfb0f493b 1.062843 1.246369 -0.183526 1.172675 c979853a3b6a 8d60fe293e79 1.036985 1.196414 -0.159429 1.153743 22349fa2fc33 fbb1c9fd86c0 0.879926 1.038682 -0.158756 1.180420 682b98f3e672 a4878080a536 0.909952 1.063801 -0.153849 1.169074 5adabc9b9848 920958a93997 0.993622 1.147452 -0.153830 1.154817 worse 1% dbfbfcf077e9 aea8f2fd3593 1.016595 1.082999 -0.066404 1.065320 worse 5% c95f1ced15f2 7d29d5e39734 0.453694 0.471156 -0.017462 1.038488 worse 10% 3e144ed1d5b7 2aef0e942480 0.035140 0.037535 -0.002395 1.068156 worse 25% 321fc60db035 801748ba582a 0.009267 0.009325 -0.000058 1.006259 median 2088ce763fc2 e6991321d78b 0.000665 0.000651 0.000014 0.978947 best 25% 915631a97de6 385b31354be6 0.040743 0.040363 0.000380 0.990673 best 10% ad495c36a765 19c10384d3e7 0.431658 0.411490 0.020168 0.953278 best 5% d13ae7d283ae 813c99f810ac 1.141404 1.075346 0.066058 0.942126 best 1% 81593cb4a496 99ae11866969 1.833297 0.063823 1.769474 0.034813 best cases c3b14617fbd7 743a0fcaa4eb 1101.811740 2.735970 1099.075770 0.002483 c3b14617fbd7 9ba6ab77fd29 1116.753953 2.800729 1113.953224 0.002508 058b99d6e81f 57e249b7a3ea 1246.128485 3.042762 1243.085723 0.002442 9a8c361aab49 0354a250d371 1253.111894 3.085796 1250.026098 0.002463 442dbbc53c68 3ec1002a818c 1261.786294 3.138607 1258.647687 0.002487 As one can see, the average case is not really impacted. However, the worth case we get after this changeset are much better than the one we had before it. We have 30 pairs where improvements are above 10 minutes. This reflect in the combined time for all pairs before: 26256s after: 1300s (-95%) If we remove these pathological 30 cases, we still see a significant improvements: before: 1631s after: 1245s (-24%)

File last commit:

r43346:2372284d default
r43469:c16fe77e default
Show More
check-translation.py
272 lines | 7.4 KiB | text/x-python | PythonLexer
/ i18n / check-translation.py
#!/usr/bin/env python
#
# check-translation.py - check Mercurial specific translation problems
from __future__ import absolute_import
import re
import polib
scanners = []
checkers = []
def scanner():
def decorator(func):
scanners.append(func)
return func
return decorator
def levelchecker(level, msgidpat):
def decorator(func):
if msgidpat:
match = re.compile(msgidpat).search
else:
match = lambda msgid: True
checkers.append((func, level))
func.match = match
return func
return decorator
def match(checker, pe):
"""Examine whether POEntry "pe" is target of specified checker or not
"""
if not checker.match(pe.msgid):
return
# examine suppression by translator comment
nochecker = 'no-%s-check' % checker.__name__
for tc in pe.tcomment.split():
if nochecker == tc:
return
return True
####################
def fatalchecker(msgidpat=None):
return levelchecker('fatal', msgidpat)
@fatalchecker(r'\$\$')
def promptchoice(pe):
"""Check translation of the string given to "ui.promptchoice()"
>>> pe = polib.POEntry(
... msgid ='prompt$$missing &sep$$missing &amp$$followed by &none',
... msgstr='prompt missing &sep$$missing amp$$followed by none&')
>>> match(promptchoice, pe)
True
>>> for e in promptchoice(pe): print(e)
number of choices differs between msgid and msgstr
msgstr has invalid choice missing '&'
msgstr has invalid '&' followed by none
"""
idchoices = [c.rstrip(' ') for c in pe.msgid.split('$$')[1:]]
strchoices = [c.rstrip(' ') for c in pe.msgstr.split('$$')[1:]]
if len(idchoices) != len(strchoices):
yield "number of choices differs between msgid and msgstr"
indices = [(c, c.find('&')) for c in strchoices]
if [c for c, i in indices if i == -1]:
yield "msgstr has invalid choice missing '&'"
if [c for c, i in indices if len(c) == i + 1]:
yield "msgstr has invalid '&' followed by none"
deprecatedpe = None
@scanner()
def deprecatedsetup(pofile):
pes = [p for p in pofile if p.msgid == '(DEPRECATED)' and p.msgstr]
if len(pes):
global deprecatedpe
deprecatedpe = pes[0]
@fatalchecker(r'\(DEPRECATED\)')
def deprecated(pe):
"""Check for DEPRECATED
>>> ped = polib.POEntry(
... msgid = '(DEPRECATED)',
... msgstr= '(DETACERPED)')
>>> deprecatedsetup([ped])
>>> pe = polib.POEntry(
... msgid = 'Something (DEPRECATED)',
... msgstr= 'something (DEPRECATED)')
>>> match(deprecated, pe)
True
>>> for e in deprecated(pe): print(e)
>>> pe = polib.POEntry(
... msgid = 'Something (DEPRECATED)',
... msgstr= 'something (DETACERPED)')
>>> match(deprecated, pe)
True
>>> for e in deprecated(pe): print(e)
>>> pe = polib.POEntry(
... msgid = 'Something (DEPRECATED)',
... msgstr= 'something')
>>> match(deprecated, pe)
True
>>> for e in deprecated(pe): print(e)
msgstr inconsistently translated (DEPRECATED)
>>> pe = polib.POEntry(
... msgid = 'Something (DEPRECATED, foo bar)',
... msgstr= 'something (DETACERPED, foo bar)')
>>> match(deprecated, pe)
"""
if not (
'(DEPRECATED)' in pe.msgstr
or (deprecatedpe and deprecatedpe.msgstr in pe.msgstr)
):
yield "msgstr inconsistently translated (DEPRECATED)"
####################
def warningchecker(msgidpat=None):
return levelchecker('warning', msgidpat)
@warningchecker()
def taildoublecolons(pe):
"""Check equality of tail '::'-ness between msgid and msgstr
>>> pe = polib.POEntry(
... msgid ='ends with ::',
... msgstr='ends with ::')
>>> for e in taildoublecolons(pe): print(e)
>>> pe = polib.POEntry(
... msgid ='ends with ::',
... msgstr='ends without double-colons')
>>> for e in taildoublecolons(pe): print(e)
tail '::'-ness differs between msgid and msgstr
>>> pe = polib.POEntry(
... msgid ='ends without double-colons',
... msgstr='ends with ::')
>>> for e in taildoublecolons(pe): print(e)
tail '::'-ness differs between msgid and msgstr
"""
if pe.msgid.endswith('::') != pe.msgstr.endswith('::'):
yield "tail '::'-ness differs between msgid and msgstr"
@warningchecker()
def indentation(pe):
"""Check equality of initial indentation between msgid and msgstr
This may report unexpected warning, because this doesn't aware
the syntax of rst document and the context of msgstr.
>>> pe = polib.POEntry(
... msgid =' indented text',
... msgstr=' narrowed indentation')
>>> for e in indentation(pe): print(e)
initial indentation width differs betweeen msgid and msgstr
"""
idindent = len(pe.msgid) - len(pe.msgid.lstrip())
strindent = len(pe.msgstr) - len(pe.msgstr.lstrip())
if idindent != strindent:
yield "initial indentation width differs betweeen msgid and msgstr"
####################
def check(pofile, fatal=True, warning=False):
targetlevel = {'fatal': fatal, 'warning': warning}
targetcheckers = [
(checker, level) for checker, level in checkers if targetlevel[level]
]
if not targetcheckers:
return []
detected = []
for checker in scanners:
checker(pofile)
for pe in pofile.translated_entries():
errors = []
for checker, level in targetcheckers:
if match(checker, pe):
errors.extend(
(level, checker.__name__, error) for error in checker(pe)
)
if errors:
detected.append((pe, errors))
return detected
########################################
if __name__ == "__main__":
import sys
import optparse
optparser = optparse.OptionParser(
"""%prog [options] pofile ...
This checks Mercurial specific translation problems in specified
'*.po' files.
Each detected problems are shown in the format below::
filename:linenum:type(checker): problem detail .....
"type" is "fatal" or "warning". "checker" is the name of the function
detecting corresponded error.
Checking by checker "foo" on the specific msgstr can be suppressed by
the "translator comment" like below. Multiple "no-xxxx-check" should
be separated by whitespaces::
# no-foo-check
msgid = "....."
msgstr = "....."
"""
)
optparser.add_option(
"",
"--warning",
help="show also warning level problems",
action="store_true",
)
optparser.add_option(
"",
"--doctest",
help="run doctest of this tool, instead of check",
action="store_true",
)
(options, args) = optparser.parse_args()
if options.doctest:
import os
if 'TERM' in os.environ:
del os.environ['TERM']
import doctest
failures, tests = doctest.testmod()
sys.exit(failures and 1 or 0)
detected = []
warning = options.warning
for f in args:
detected.extend(
(f, pe, errors)
for pe, errors in check(polib.pofile(f), warning=warning)
)
if detected:
for f, pe, errors in detected:
for level, checker, error in errors:
sys.stderr.write(
'%s:%d:%s(%s): %s\n'
% (f, pe.linenum, level, checker, error)
)
sys.exit(1)