##// END OF EJS Templates
mdiff: speed up showfunc for large diffs...
mdiff: speed up showfunc for large diffs This addresses the following issues with showfunc: - Silly usage of regular expressions. - Doing str.rstrip() needlessly in an inner loop. - Doing catastrophic backtracking when trying to find a function line. Finding function text is now at worst O(n lines in the old file), and at best close to O(n hunks). Given a diff like this[1]: src/main/antlr3/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunker.g | 4 +- src/main/java/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunkerLexer.java | 2 +- src/main/java/uk/ac/cam/ch/wwmm/pregenerated/ChemicalChunkerParser.java | 29189 +++++---- 3 files changed, 14741 insertions(+), 14454 deletions(-) [1]: https://bitbucket.org/wwmm/chemicaltagger/changeset/d2bfbaecd4fc/raw Without this change, hg log --stat --config diff.showfunc=1 takes an absurdly long time to complete: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 32813 0 80.3546 40.6086 mercurial.mdiff:160(yieldhunk) +65062746 0 25.7227 25.7227 +<method 'match' of '_sre.SRE_Pattern' objects> +65062746 0 14.0221 14.0221 +<method 'rstrip' of 'str' objects> +1809 0 0.0009 0.0009 +mercurial.mdiff:148(contextend) +1809 0 0.0003 0.0003 +<len> 65062746 0 25.7227 25.7227 <method 'match' of '_sre.SRE_Pattern' objects> 65062763 0 14.0221 14.0221 <method 'rstrip' of 'str' objects> 543 0 0.1631 0.1631 <zlib.decompress> 3 0 0.0505 0.0505 <mercurial.bdiff.blocks> 31007 0 80.4564 0.0477 mercurial.mdiff:147(_unidiff) +32813 0 80.3546 40.6086 +mercurial.mdiff:160(yieldhunk) +3 0 0.0505 0.0505 +<mercurial.bdiff.blocks> +3618 0 0.0022 0.0022 +mercurial.mdiff:154(contextstart) +5427 0 0.0013 0.0013 +<len> +3 0 0.0001 0.0000 +re:188(compile) 1 0 80.8381 0.0322 mercurial.patch:1777(diffstatdata) +107499 0 0.0235 0.0235 +<method 'startswith' of 'str' objects> +31014 0 80.7820 0.0071 +mercurial.util:1284(iterlines) +3 0 0.0000 0.0000 +<method 'search' of '_sre.SRE_Pattern' objects> +4 0 0.0000 0.0000 +mercurial.patch:1783(addresult) +3 0 0.0000 0.0000 +<method 'group' of '_sre.SRE_Match' objects> 6 0 0.0444 0.0283 mercurial.mdiff:12(splitnewlines) +6 0 0.0160 0.0160 +<method 'split' of 'str' objects> 32 0 0.0246 0.0246 <method 'update' of '_hashlib.HASH' objects> 11 0 0.0236 0.0236 <method 'read' of 'file' objects> Time: real 80.880 secs (user 80.200+0.000 sys 0.380+0.000) With this change, it's almost as fast as not using showfunc at all: CallCount Recursive Total(ms) Inline(ms) module:lineno(function) 543 0 0.1699 0.1699 <zlib.decompress> 3 0 0.0501 0.0501 <mercurial.bdiff.blocks> 32813 0 0.0415 0.0348 mercurial.mdiff:161(yieldhunk) +70837 0 0.0058 0.0058 +<method 'isalnum' of 'str' objects> +1809 0 0.0006 0.0006 +mercurial.mdiff:148(contextend) +1809 0 0.0002 0.0002 +<len> 1 0 0.4879 0.0310 mercurial.patch:1777(diffstatdata) +107499 0 0.0230 0.0230 +<method 'startswith' of 'str' objects> +31014 0 0.4335 0.0065 +mercurial.util:1284(iterlines) +3 0 0.0000 0.0000 +<method 'search' of '_sre.SRE_Pattern' objects> +4 0 0.0000 0.0000 +mercurial.patch:1783(addresult) +1 0 0.0004 0.0000 +re:188(compile) 32 0 0.0293 0.0293 <method 'update' of '_hashlib.HASH' objects> 6 0 0.0427 0.0279 mercurial.mdiff:12(splitnewlines) +6 0 0.0147 0.0147 +<method 'split' of 'str' objects> 31007 0 0.1169 0.0235 mercurial.mdiff:147(_unidiff) +3 0 0.0501 0.0501 +<mercurial.bdiff.blocks> +32813 0 0.0415 0.0348 +mercurial.mdiff:161(yieldhunk) +3618 0 0.0012 0.0012 +mercurial.mdiff:154(contextstart) +5427 0 0.0006 0.0006 +<len> 107597 0 0.0230 0.0230 <method 'startswith' of 'str' objects> 16 0 0.0213 0.0213 <mercurial.mpatch.patches> 194 0 0.0149 0.0149 <method 'split' of 'str' objects> Time: real 0.530 secs (user 0.450+0.000 sys 0.070+0.000)

File last commit:

r14941:4a28cb4d default
r15141:16dc9a32 default
Show More
help.py
109 lines | 3.9 KiB | text/x-python | PythonLexer
# help.py - help data for mercurial
#
# Copyright 2006 Matt Mackall <mpm@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from i18n import gettext, _
import sys, os
import extensions, revset, fileset, templatekw, templatefilters
import util
def listexts(header, exts, indent=1):
'''return a text listing of the given extensions'''
if not exts:
return ''
maxlength = max(len(e) for e in exts)
result = '\n%s\n\n' % header
for name, desc in sorted(exts.iteritems()):
result += '%s%-*s %s\n' % (' ' * indent, maxlength + 2,
':%s:' % name, desc)
return result
def extshelp():
doc = loaddoc('extensions')()
doc += listexts(_('enabled extensions:'), extensions.enabled())
doc += listexts(_('disabled extensions:'), extensions.disabled())
return doc
def loaddoc(topic):
"""Return a delayed loader for help/topic.txt."""
def loader():
if util.mainfrozen():
module = sys.executable
else:
module = __file__
base = os.path.dirname(module)
for dir in ('.', '..'):
docdir = os.path.join(base, dir, 'help')
if os.path.isdir(docdir):
break
path = os.path.join(docdir, topic + ".txt")
doc = gettext(util.readfile(path))
for rewriter in helphooks.get(topic, []):
doc = rewriter(topic, doc)
return doc
return loader
helptable = sorted([
(["config", "hgrc"], _("Configuration Files"), loaddoc('config')),
(["dates"], _("Date Formats"), loaddoc('dates')),
(["patterns"], _("File Name Patterns"), loaddoc('patterns')),
(['environment', 'env'], _('Environment Variables'),
loaddoc('environment')),
(['revs', 'revisions'], _('Specifying Single Revisions'),
loaddoc('revisions')),
(['mrevs', 'multirevs'], _('Specifying Multiple Revisions'),
loaddoc('multirevs')),
(['revset', 'revsets'], _("Specifying Revision Sets"), loaddoc('revsets')),
(['fileset', 'filesets'], _("Specifying File Sets"), loaddoc('filesets')),
(['diffs'], _('Diff Formats'), loaddoc('diffs')),
(['merge-tools'], _('Merge Tools'), loaddoc('merge-tools')),
(['templating', 'templates'], _('Template Usage'),
loaddoc('templates')),
(['urls'], _('URL Paths'), loaddoc('urls')),
(["extensions"], _("Using additional features"), extshelp),
(["subrepo", "subrepos"], _("Subrepositories"), loaddoc('subrepos')),
(["hgweb"], _("Configuring hgweb"), loaddoc('hgweb')),
(["glossary"], _("Glossary"), loaddoc('glossary')),
(["hgignore", "ignore"], _("syntax for Mercurial ignore files"),
loaddoc('hgignore')),
])
# Map topics to lists of callable taking the current topic help and
# returning the updated version
helphooks = {}
def addtopichook(topic, rewriter):
helphooks.setdefault(topic, []).append(rewriter)
def makeitemsdoc(topic, doc, marker, items):
"""Extract docstring from the items key to function mapping, build a
.single documentation block and use it to overwrite the marker in doc
"""
entries = []
for name in sorted(items):
text = (items[name].__doc__ or '').rstrip()
if not text:
continue
text = gettext(text)
lines = text.splitlines()
lines[1:] = [(' ' + l.strip()) for l in lines[1:]]
entries.append('\n'.join(lines))
entries = '\n\n'.join(entries)
return doc.replace(marker, entries)
def addtopicsymbols(topic, marker, symbols):
def add(topic, doc):
return makeitemsdoc(topic, doc, marker, symbols)
addtopichook(topic, add)
addtopicsymbols('filesets', '.. predicatesmarker', fileset.symbols)
addtopicsymbols('revsets', '.. predicatesmarker', revset.symbols)
addtopicsymbols('templates', '.. keywordsmarker', templatekw.keywords)
addtopicsymbols('templates', '.. filtersmarker', templatefilters.filters)