bundle2: inline debug logging
Profiling revealed that repeated calls to indebug() were
consuming a fair amount of CPU during bundle2 reading, with
most of the time spent in ui.configbool().
Inlining indebug() and avoiding extra attribute lookups speeds
things up substantially. Using `hg perfbundleread` with a Firefox
bundle:
! read(8k)
! wall 0.679730 comb 0.680000 user 0.140000 sys 0.540000 (best of 15)
! read(16k)
! wall 0.577228 comb 0.570000 user 0.080000 sys 0.490000 (best of 17)
! read(32k)
! wall 0.516060 comb 0.520000 user 0.040000 sys 0.480000 (best of 20)
! read(128k)
! wall 0.496378 comb 0.490000 user 0.010000 sys 0.480000 (best of 20)
! bundle2 iterparts()
! wall 6.983756 comb 6.980000 user 6.220000 sys 0.760000 (best of 3)
! wall 3.460903 comb 3.460000 user 2.760000 sys 0.700000 (best of 3)
! bundle2 iterparts() seekable
! wall 8.132131 comb 8.110000 user 7.160000 sys 0.950000 (best of 3)
! wall 4.312722 comb 4.310000 user 3.480000 sys 0.830000 (best of 3)
! bundle2 part seek()
! wall 10.860942 comb 10.840000 user 7.790000 sys 3.050000 (best of 3)
! wall 6.754764 comb 6.740000 user 3.970000 sys 2.770000 (best of 3)
! bundle2 part read(8k)
! wall 7.258035 comb 7.260000 user 6.470000 sys 0.790000 (best of 3)
! wall 3.668004 comb 3.660000 user 2.960000 sys 0.700000 (best of 3)
! bundle2 part read(16k)
! wall 7.099891 comb 7.080000 user 6.310000 sys 0.770000 (best of 3)
! wall 3.489196 comb 3.480000 user 2.750000 sys 0.730000 (best of 3)
! bundle2 part read(32k)
! wall 6.964685 comb 6.950000 user 6.130000 sys 0.820000 (best of 3)
! wall 3.388569 comb 3.380000 user 2.640000 sys 0.740000 (best of 3)
! bundle2 part read(128k)
! wall 6.852867 comb 6.850000 user 6.060000 sys 0.790000 (best of 3)
! wall 3.276415 comb 3.270000 user 2.560000 sys 0.710000 (best of 4)
Differential Revision: https://phab.mercurial-scm.org/D1391
#!/usr/bin/env python
#
# hggettext - carefully extract docstrings for Mercurial
#
# Copyright 2009 Matt Mackall <mpm@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
# The normalize function is taken from pygettext which is distributed
# with Python under the Python License, which is GPL compatible.
"""Extract docstrings from Mercurial commands.
Compared to pygettext, this script knows about the cmdtable and table
dictionaries used by Mercurial, and will only extract docstrings from
functions mentioned therein.
Use xgettext like normal to extract strings marked as translatable and
join the message cataloges to get the final catalog.
"""
from __future__ import absolute_import, print_function
import inspect
import os
import re
import sys
def escape(s):
# The order is important, the backslash must be escaped first
# since the other replacements introduce new backslashes
# themselves.
s = s.replace('\\', '\\\\')
s = s.replace('\n', '\\n')
s = s.replace('\r', '\\r')
s = s.replace('\t', '\\t')
s = s.replace('"', '\\"')
return s
def normalize(s):
# This converts the various Python string types into a format that
# is appropriate for .po files, namely much closer to C style.
lines = s.split('\n')
if len(lines) == 1:
s = '"' + escape(s) + '"'
else:
if not lines[-1]:
del lines[-1]
lines[-1] = lines[-1] + '\n'
lines = map(escape, lines)
lineterm = '\\n"\n"'
s = '""\n"' + lineterm.join(lines) + '"'
return s
def poentry(path, lineno, s):
return ('#: %s:%d\n' % (path, lineno) +
'msgid %s\n' % normalize(s) +
'msgstr ""\n')
doctestre = re.compile(r'^ +>>> ', re.MULTILINE)
def offset(src, doc, name, default):
"""Compute offset or issue a warning on stdout."""
# remove doctest part, in order to avoid backslash mismatching
m = doctestre.search(doc)
if m:
doc = doc[:m.start()]
# Backslashes in doc appear doubled in src.
end = src.find(doc.replace('\\', '\\\\'))
if end == -1:
# This can happen if the docstring contains unnecessary escape
# sequences such as \" in a triple-quoted string. The problem
# is that \" is turned into " and so doc wont appear in src.
sys.stderr.write("warning: unknown offset in %s, assuming %d lines\n"
% (name, default))
return default
else:
return src.count('\n', 0, end)
def importpath(path):
"""Import a path like foo/bar/baz.py and return the baz module."""
if path.endswith('.py'):
path = path[:-3]
if path.endswith('/__init__'):
path = path[:-9]
path = path.replace('/', '.')
mod = __import__(path)
for comp in path.split('.')[1:]:
mod = getattr(mod, comp)
return mod
def docstrings(path):
"""Extract docstrings from path.
This respects the Mercurial cmdtable/table convention and will
only extract docstrings from functions mentioned in these tables.
"""
mod = importpath(path)
if not path.startswith('mercurial/') and mod.__doc__:
src = open(path).read()
lineno = 1 + offset(src, mod.__doc__, path, 7)
print(poentry(path, lineno, mod.__doc__))
functions = list(getattr(mod, 'i18nfunctions', []))
functions = [(f, True) for f in functions]
cmdtable = getattr(mod, 'cmdtable', {})
if not cmdtable:
# Maybe we are processing mercurial.commands?
cmdtable = getattr(mod, 'table', {})
functions.extend((c[0], False) for c in cmdtable.itervalues())
for func, rstrip in functions:
if func.__doc__:
docobj = func # this might be a proxy to provide formatted doc
func = getattr(func, '_origfunc', func)
funcmod = inspect.getmodule(func)
extra = ''
if funcmod.__package__ == funcmod.__name__:
extra = '/__init__'
actualpath = '%s%s.py' % (funcmod.__name__.replace('.', '/'), extra)
src = inspect.getsource(func)
name = "%s.%s" % (actualpath, func.__name__)
lineno = inspect.getsourcelines(func)[1]
doc = docobj.__doc__
origdoc = getattr(docobj, '_origdoc', '')
if rstrip:
doc = doc.rstrip()
origdoc = origdoc.rstrip()
if origdoc:
lineno += offset(src, origdoc, name, 1)
else:
lineno += offset(src, doc, name, 1)
print(poentry(actualpath, lineno, doc))
def rawtext(path):
src = open(path).read()
print(poentry(path, 1, src))
if __name__ == "__main__":
# It is very important that we import the Mercurial modules from
# the source tree where hggettext is executed. Otherwise we might
# accidentally import and extract strings from a Mercurial
# installation mentioned in PYTHONPATH.
sys.path.insert(0, os.getcwd())
from mercurial import demandimport; demandimport.enable()
for path in sys.argv[1:]:
if path.endswith('.txt'):
rawtext(path)
else:
docstrings(path)