view hgext/churn.py @ 41276:5affe1583e1d

revset: use changelog's `headrevs` method to compute heads

Instead of implementing our own algorithm, we reuse a more generic one. This
previous algorithm did not leave much room for laziness so we do not really
regress in that regards. A small impact is visible for first/last value in
some of the simpler cases. The time needed to compute all values improves
overall. Small optimization in the dagop.headrevs function will help to buy
this back in the next changesets.

There is room to introduce actual laziness in this algorithm, but this is out
of scope for this series.

This has no visible effect on expensive cases:

revset: heads(matching(tip, "author"))
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 7.574666      7.545950      7.570743      7.578697      7.525725      7.509929      7.443854      7.488442      7.452880      7.445411      7.689107
1) 7.549390      7.389162      7.529790      7.536297      7.450467      7.555347      7.404586      7.514948      7.542794      7.524787      7.536918

revset: heads(matching(tip, "author")) and -10000:-1
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 7.512533      7.605877      7.382894      7.462109      7.420086      7.575034      7.448452      7.549374      7.457880      7.450308      7.515019
1) 7.548677      7.551832      7.629598      7.494857      7.550554      7.521838      7.451794      error         7.321781      7.546885      7.557523

revset: (-10000:-1) and heads(matching(tip, "author"))
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 7.465419      7.570089      7.439594      7.521221      7.498716      7.492922      7.479108      7.552397      7.407888      error         7.468264
1) 7.539866      7.548045      7.491761      7.517170      7.469824      7.501990      7.579102      7.502568      7.578102      7.555754      7.567622

In simpler cases, we see a 10-15% impact when retrieving a single value, the
full computation time is equivalent or improved:

revset: (-5000:-1000) and heads(-10000:-1)
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 0.004244      0.003368      0.003313      0.003367      0.003327      0.004325      0.003401      0.003379      0.004310      0.003359      0.003396
1) 0.003969  93% 0.003862 114% 0.003834 115% 0.003810 113% 0.003822 114% 0.003940  91% 0.003908 114% 0.003814 112% 0.003986  92% 0.003954 117% 0.003816 112%

revset: heads(all())
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 0.036503      0.032564      0.030024      0.032378      0.030887      0.036367      0.031713      0.032205      0.036467      0.032286      0.030300
1) 0.036668      0.035347 108% 0.035611 118% 0.035358 109% 0.035726 115% 0.036411      0.035261 111% 0.036096 112% 0.036052      0.035095 108% 0.035792 118%

revset: heads(-10000:-1)
   plain         min           max           first         last          reverse       rev..rst      rev..ast      sort          sor..rst      sor..ast
0) 0.003936      0.003218      0.003227      0.003302      0.003328      0.003848      0.003305      0.003252      0.003839      0.003306      0.003279
1) 0.003870      0.003785 117% 0.003821 118% 0.003780 114% 0.003769 113% 0.003776      0.003792 114% 0.003805 117% 0.003810      0.003798 114% 0.003840 117%

# 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, division

import datetime
import os
import time

from mercurial.i18n import _
from mercurial import (
    cmdutil,
    encoding,
    logcmdutil,
    patch,
    pycompat,
    registrar,
    scmutil,
)
from mercurial.utils import dateutil

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"""
    opts = pycompat.byteskwargs(opts)
    if opts.get('dateformat'):
        def getkey(ctx):
            t, tz = ctx.date()
            date = datetime.datetime(*time.gmtime(float(t) - tz)[:6])
            return encoding.strtolocal(
                date.strftime(encoding.strfromlocal(opts['dateformat'])))
    else:
        tmpl = opts.get('oldtemplate') or opts.get('template')
        tmpl = logcmdutil.maketemplater(ui, repo, tmpl)
        def getkey(ctx):
            ui.pushbuffer()
            tmpl.show(ctx)
            return ui.popbuffer()

    progress = ui.makeprogress(_('analyzing'), unit=_('revisions'),
                               total=len(repo))
    rate = {}
    df = False
    if opts.get('date'):
        df = dateutil.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)]

        progress.increment()

    for ctx in cmdutil.walkchangerevs(repo, m, opts, prep):
        continue

    progress.complete()

    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]"),
    helpcategory=command.CATEGORY_MAINTENANCE,
    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(r'aliases')
    if not aliases and os.path.exists(repo.wjoin('.hgchurn')):
        aliases = repo.wjoin('.hgchurn')
    if aliases:
        for l in open(aliases, "rb"):
            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 = list(countrate(ui, repo, amap, *pats, **opts).items())
    if not rate:
        return

    if opts.get(r'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(r'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(count * width // maxcount)

    for name, count in rate:
        ui.write(format(name, count))