##// 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:

r14698:df902fe3 stable
r15141:16dc9a32 default
Show More
treediscovery.py
150 lines | 5.0 KiB | text/x-python | PythonLexer
# discovery.py - protocol changeset discovery functions
#
# Copyright 2010 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 node import nullid, short
from i18n import _
import util, error
def findcommonincoming(repo, remote, heads=None, force=False):
"""Return a tuple (common, fetch, heads) used to identify the common
subset of nodes between repo and remote.
"common" is a list of (at least) the heads of the common subset.
"fetch" is a list of roots of the nodes that would be incoming, to be
supplied to changegroupsubset.
"heads" is either the supplied heads, or else the remote's heads.
"""
m = repo.changelog.nodemap
search = []
fetch = set()
seen = set()
seenbranch = set()
base = set()
if not heads:
heads = remote.heads()
if repo.changelog.tip() == nullid:
base.add(nullid)
if heads != [nullid]:
return [nullid], [nullid], list(heads)
return [nullid], [], heads
# assume we're closer to the tip than the root
# and start by examining the heads
repo.ui.status(_("searching for changes\n"))
unknown = []
for h in heads:
if h not in m:
unknown.append(h)
else:
base.add(h)
if not unknown:
return list(base), [], list(heads)
req = set(unknown)
reqcnt = 0
# search through remote branches
# a 'branch' here is a linear segment of history, with four parts:
# head, root, first parent, second parent
# (a branch always has two parents (or none) by definition)
unknown = remote.branches(unknown)
while unknown:
r = []
while unknown:
n = unknown.pop(0)
if n[0] in seen:
continue
repo.ui.debug("examining %s:%s\n"
% (short(n[0]), short(n[1])))
if n[0] == nullid: # found the end of the branch
pass
elif n in seenbranch:
repo.ui.debug("branch already found\n")
continue
elif n[1] and n[1] in m: # do we know the base?
repo.ui.debug("found incomplete branch %s:%s\n"
% (short(n[0]), short(n[1])))
search.append(n[0:2]) # schedule branch range for scanning
seenbranch.add(n)
else:
if n[1] not in seen and n[1] not in fetch:
if n[2] in m and n[3] in m:
repo.ui.debug("found new changeset %s\n" %
short(n[1]))
fetch.add(n[1]) # earliest unknown
for p in n[2:4]:
if p in m:
base.add(p) # latest known
for p in n[2:4]:
if p not in req and p not in m:
r.append(p)
req.add(p)
seen.add(n[0])
if r:
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
repo.ui.debug("request %d: %s\n" %
(reqcnt, " ".join(map(short, r))))
for p in xrange(0, len(r), 10):
for b in remote.branches(r[p:p + 10]):
repo.ui.debug("received %s:%s\n" %
(short(b[0]), short(b[1])))
unknown.append(b)
# do binary search on the branches we found
while search:
newsearch = []
reqcnt += 1
repo.ui.progress(_('searching'), reqcnt, unit=_('queries'))
for n, l in zip(search, remote.between(search)):
l.append(n[1])
p = n[0]
f = 1
for i in l:
repo.ui.debug("narrowing %d:%d %s\n" % (f, len(l), short(i)))
if i in m:
if f <= 2:
repo.ui.debug("found new branch changeset %s\n" %
short(p))
fetch.add(p)
base.add(i)
else:
repo.ui.debug("narrowed branch search to %s:%s\n"
% (short(p), short(i)))
newsearch.append((p, i))
break
p, f = i, f * 2
search = newsearch
# sanity check our fetch list
for f in fetch:
if f in m:
raise error.RepoError(_("already have changeset ")
+ short(f[:4]))
base = list(base)
if base == [nullid]:
if force:
repo.ui.warn(_("warning: repository is unrelated\n"))
else:
raise util.Abort(_("repository is unrelated"))
repo.ui.debug("found new changesets starting at " +
" ".join([short(f) for f in fetch]) + "\n")
repo.ui.progress(_('searching'), None)
repo.ui.debug("%d total queries\n" % reqcnt)
return base, list(fetch), heads