view hgext/churn.py @ 33649:377e8ddaebef stable

pathauditor: disable cache of audited paths by default (issue5628)

The initial attempt was to discard cache when appropriate, but it appears
to be error prone. We had to carefully inspect all places where audit() is
called e.g. without actually updating filesystem, before removing files and
directories, etc.

So, this patch disables the cache of audited paths by default, and enables
it only for the following cases:

 - short-lived auditor objects
 - repo.vfs, repo.svfs, and repo.cachevfs, which are managed directories
   and considered sort of append-only (a file/directory would never be
   replaced with a symlink)

There would be more cacheable vfs objects (e.g. mq.queue.opener), but I
decided not to inspect all of them in this patch. We can make them cached
later.

Benchmark result:

- using old clone of http://selenic.com/repo/linux-2.6/ (38319 files)
- on tmpfs
- run HGRCPATH=/dev/null hg up -q --time tip && hg up -q null
- try 4 times and take the last three results

original:
real 7.480 secs (user 1.140+22.760 sys 0.150+1.690)
real 8.010 secs (user 1.070+22.280 sys 0.170+2.120)
real 7.470 secs (user 1.120+22.390 sys 0.120+1.910)

clearcache (the other series):
real 7.680 secs (user 1.120+23.420 sys 0.140+1.970)
real 7.670 secs (user 1.110+23.620 sys 0.130+1.810)
real 7.740 secs (user 1.090+23.510 sys 0.160+1.940)

enable cache only for vfs and svfs (this series):
real 8.730 secs (user 1.500+25.190 sys 0.260+2.260)
real 8.750 secs (user 1.490+25.170 sys 0.250+2.340)
real 9.010 secs (user 1.680+25.340 sys 0.280+2.540)

remove cache function at all (for reference):
real 9.620 secs (user 1.440+27.120 sys 0.250+2.980)
real 9.420 secs (user 1.400+26.940 sys 0.320+3.130)
real 9.760 secs (user 1.530+27.270 sys 0.250+2.970)

# churn.py - create a graph of revisions count grouped by template
#
# Copyright 2006 Josef "Jeff" Sipek <[e-mail]>
# Copyright 2008 Alexander Solovyov <[e-mail]>
#
# 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,
    encoding,
    patch,
    registrar,
    scmutil,
    util,
)

cmdtable = {}
command = registrar.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 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 = cmdutil.makelogtemplater(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')),
    ] + cmdutil.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))