##// END OF EJS Templates
bdiff: replace hash algorithm...
bdiff: replace hash algorithm This patch replaces lyhash with the hash algorithm used by diffutils. The algorithm has its origins in Git commit 2e9d1410, which is all the way back from 1992. The license header in the code at that revision in GPL v2. I have not performed an extensive analysis of the distribution (and therefore buckets) of hash output. However, `hg perfbdiff` gives some clear wins. I'd like to think that if it is good enough for diffutils it is good enough for us? From the mozilla-unified repository: $ perfbdiff -m 3041e4d59df2 ! wall 0.053271 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) ! wall 0.035827 comb 0.040000 user 0.040000 sys 0.000000 (best of 100) $ perfbdiff 0e9928989e9c --alldata --count 100 ! wall 6.204277 comb 6.200000 user 6.200000 sys 0.000000 (best of 3) ! wall 4.309710 comb 4.300000 user 4.300000 sys 0.000000 (best of 3) From the hg repo: $ perfbdiff 35000 --alldata --count 1000 ! wall 0.660358 comb 0.660000 user 0.660000 sys 0.000000 (best of 15) ! wall 0.534092 comb 0.530000 user 0.530000 sys 0.000000 (best of 19) Looking at the generated assembly and statistical profiler output from the kernel level, I believe there is room to make this function even faster. Namely, we're still consuming data character by character instead of at the word level. This translates to more loop iterations and more instructions. At this juncture though, the real performance killer is that we're hashing every line. We should get a significant speedup if we change the algorithm to find the longest prefix, longest suffix, treat those as single "lines" and then only do the line splitting and hashing on the parts that are different. That will require a lot of C code, however. I'm optimistic this approach could result in a ~2x speedup.

File last commit:

r29841:d5883fd0 default
r30318:e1d6aa0e default
Show More
churn.py
211 lines | 7.0 KiB | text/x-python | PythonLexer
# churn.py - create a graph of revisions count grouped by template
#
# Copyright 2006 Josef "Jeff" Sipek <jeffpc@josefsipek.net>
# Copyright 2008 Alexander Solovyov <piranha@piranha.org.ua>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
'''command to display statistics about repository history'''
from __future__ import absolute_import
import datetime
import os
import time
from mercurial.i18n import _
from mercurial import (
cmdutil,
commands,
encoding,
patch,
scmutil,
util,
)
cmdtable = {}
command = cmdutil.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
# be specifying the version(s) of Mercurial they are tested with, or
# leave the attribute unspecified.
testedwith = 'ships-with-hg-core'
def maketemplater(ui, repo, tmpl):
return cmdutil.changeset_templater(ui, repo, False, None, tmpl, None, False)
def changedlines(ui, repo, ctx1, ctx2, fns):
added, removed = 0, 0
fmatch = scmutil.matchfiles(repo, fns)
diff = ''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
for l in diff.split('\n'):
if l.startswith("+") and not l.startswith("+++ "):
added += 1
elif l.startswith("-") and not l.startswith("--- "):
removed += 1
return (added, removed)
def countrate(ui, repo, amap, *pats, **opts):
"""Calculate stats"""
if opts.get('dateformat'):
def getkey(ctx):
t, tz = ctx.date()
date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
return date.strftime(opts['dateformat'])
else:
tmpl = opts.get('oldtemplate') or opts.get('template')
tmpl = maketemplater(ui, repo, tmpl)
def getkey(ctx):
ui.pushbuffer()
tmpl.show(ctx)
return ui.popbuffer()
state = {'count': 0}
rate = {}
df = False
if opts.get('date'):
df = util.matchdate(opts['date'])
m = scmutil.match(repo[None], pats, opts)
def prep(ctx, fns):
rev = ctx.rev()
if df and not df(ctx.date()[0]): # doesn't match date format
return
key = getkey(ctx).strip()
key = amap.get(key, key) # alias remap
if opts.get('changesets'):
rate[key] = (rate.get(key, (0,))[0] + 1, 0)
else:
parents = ctx.parents()
if len(parents) > 1:
ui.note(_('revision %d is a merge, ignoring...\n') % (rev,))
return
ctx1 = parents[0]
lines = changedlines(ui, repo, ctx1, ctx, fns)
rate[key] = [r + l for r, l in zip(rate.get(key, (0, 0)), lines)]
state['count'] += 1
ui.progress(_('analyzing'), state['count'], total=len(repo),
unit=_('revisions'))
for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
continue
ui.progress(_('analyzing'), None)
return rate
@command('churn',
[('r', 'rev', [],
_('count rate for the specified revision or revset'), _('REV')),
('d', 'date', '',
_('count rate for revisions matching date spec'), _('DATE')),
('t', 'oldtemplate', '',
_('template to group changesets (DEPRECATED)'), _('TEMPLATE')),
('T', 'template', '{author|email}',
_('template to group changesets'), _('TEMPLATE')),
('f', 'dateformat', '',
_('strftime-compatible format for grouping by date'), _('FORMAT')),
('c', 'changesets', False, _('count rate by number of changesets')),
('s', 'sort', False, _('sort by key (default: sort by count)')),
('', 'diffstat', False, _('display added/removed lines separately')),
('', 'aliases', '', _('file with email aliases'), _('FILE')),
] + commands.walkopts,
_("hg churn [-d DATE] [-r REV] [--aliases FILE] [FILE]"),
inferrepo=True)
def churn(ui, repo, *pats, **opts):
'''histogram of changes to the repository
This command will display a histogram representing the number
of changed lines or revisions, grouped according to the given
template. The default template will group changes by author.
The --dateformat option may be used to group the results by
date instead.
Statistics are based on the number of changed lines, or
alternatively the number of matching revisions if the
--changesets option is specified.
Examples::
# display count of changed lines for every committer
hg churn -t "{author|email}"
# display daily activity graph
hg churn -f "%H" -s -c
# display activity of developers by month
hg churn -f "%Y-%m" -s -c
# display count of lines changed in every year
hg churn -f "%Y" -s
It is possible to map alternate email addresses to a main address
by providing a file using the following format::
<alias email> = <actual email>
Such a file may be specified with the --aliases option, otherwise
a .hgchurn file will be looked for in the working directory root.
Aliases will be split from the rightmost "=".
'''
def pad(s, l):
return s + " " * (l - encoding.colwidth(s))
amap = {}
aliases = opts.get('aliases')
if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
aliases = repo.wjoin('.hgchurn')
if aliases:
for l in open(aliases, "r"):
try:
alias, actual = l.rsplit('=' in l and '=' or None, 1)
amap[alias.strip()] = actual.strip()
except ValueError:
l = l.strip()
if l:
ui.warn(_("skipping malformed alias: %s\n") % l)
continue
rate = countrate(ui, repo, amap, *pats, **opts).items()
if not rate:
return
if opts.get('sort'):
rate.sort()
else:
rate.sort(key=lambda x: (-sum(x[1]), x))
# Be careful not to have a zero maxcount (issue833)
maxcount = float(max(sum(v) for k, v in rate)) or 1.0
maxname = max(len(k) for k, v in rate)
ttywidth = ui.termwidth()
ui.debug("assuming %i character terminal\n" % ttywidth)
width = ttywidth - maxname - 2 - 2 - 2
if opts.get('diffstat'):
width -= 15
def format(name, diffstat):
added, removed = diffstat
return "%s %15s %s%s\n" % (pad(name, maxname),
'+%d/-%d' % (added, removed),
ui.label('+' * charnum(added),
'diffstat.inserted'),
ui.label('-' * charnum(removed),
'diffstat.deleted'))
else:
width -= 6
def format(name, count):
return "%s %6d %s\n" % (pad(name, maxname), sum(count),
'*' * charnum(sum(count)))
def charnum(count):
return int(round(count * width / maxcount))
for name, count in rate:
ui.write(format(name, count))