phases: really fix native phase computation
For some reason (probably rebase issue, leprechaun or badly resolved .rej)
1635579f9baf contains only half of the emailed patches and do not fix the bug.
This patch adds the other half and enable the sweet native computation for real.
As expected this provide massive speedup along the board.
revset #0: not public()
plain first
0) 0.011960 0.010523
1) 0.000465 3% 0.000492 4%
revset #1: (tip~1000::) - public()
plain first
0) 0.025700 0.025169
1) 0.002864 11% 0.001899 7%
revset #2: not public() and branch("default")
plain first
0) 0.022842 0.020863
1) 0.011418 49% 0.010948 52%
However, it has a less impact (even bad) on first result time in simple
situation. This comes from the overhead of building the set and filtering it.
This is especially true on my Mercurial repository (used here) where about 1/3
of the changesets are non public and hidden. This could be mitigated by a
caching of the set and a better usage of smartset in '_notpublic'. (But this
won't happen in this patch because the win is massive everywhere else).
revset #0: not public()
last
0) 0.000081
1) 0.000493 x6.1 <-- bad impact
revset #1: (tip~1000::) - public()
last
0) 0.013966
1) 0.002737 19%
revset #2: not public() and branch("default")
last
0) 0.011021
1) 0.011038
The effect mostly disappear when the number of non-public changesets is small
and/or the repo get bigger. Result for Mozilla central:
Mozilla
revset #0: not public()
plain first last
0) 0.092787 0.084094 0.000080
1) 0.000054 0% 0.000083 0% 0.000083
revset #1: (tip~1000::) - public()
plain first last
0) 0.215607 0.183996 0.124962
1) 0.031620 14% 0.006616 3% 0.031168 24%
revset #2: not public() and branch("default")
plain first last
0) 0.092626 0.082687 0.000162
1) 0.000139 0% 0.000165 0% 0.000167
# 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 mercurial.i18n import _
from mercurial import patch, cmdutil, scmutil, util, commands
from mercurial import encoding
import os
import time, datetime
cmdtable = {}
command = cmdutil.command(cmdtable)
# Note for extension authors: ONLY specify testedwith = 'internal' 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 = 'internal'
def maketemplater(ui, repo, tmpl):
try:
t = cmdutil.changeset_templater(ui, repo, False, None, tmpl,
None, False)
except SyntaxError, inst:
raise util.Abort(inst.args[0])
return t
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))
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))