annotate hgext/churn.py @ 40736:0728d87a8631

store: append to fncache if there are only new files to write

Before this patch, if we have to add a new entry to fncache, we write the whole
fncache again which slows things down on large fncache which have millions of
entries. Addition of a new entry is common operation while pulling new files or
commiting a new file.

This patch adds a new fncache.addls set which keeps track of the additions
happening and store them. When we write the fncache, we will just read the addls
set and append those entries at the end of fncache.
We make sure that the entries are new entries by loading the fncache and making
sure entry does not exists there. In future if we can check if an entry is new
without loading the fncache, that will speed up things more.

Performance numbers for commiting a new file:

mercurial repo
before: 0.08784651756286621
after: 0.08474504947662354

mozilla-central
before: 1.83314049243927
after: 1.7054164409637451

netbeans
before: 0.7953150272369385
after: 0.7202838659286499

pypy
before: 0.17805707454681396
after: 0.13431048393249512

In our internal repo, the performance improvement is in seconds.

I have used octobus's ASV perf benchmark thing to get the above numbers. I also
see some minute perf improvements related to creating a new commit without a new
file, but I believe that's just some noise.

Differential Revision: https://phab.mercurial-scm.org/D5301

# 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))