hgext/churn.py

copies: compute the exact set of revision to walk

This change make the code clearer by removing the revision queue. It comes
without very noticeable performance impact. However the simpler code will be
easier to update in later changesets.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 1.430082 comb 1.430000 user 1.390000 sys 0.040000 (median of 10)
after:  ! wall 1.405192 comb 1.410000 user 1.390000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 1.971366 comb 1.970000 user 1.950000 sys 0.020000 (median of 10)
after:  ! wall 1.892541 comb 1.890000 user 1.870000 sys 0.020000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.252594 comb 0.250000 user 0.240000 sys 0.010000 (median of 38)
after:  ! wall 0.240075 comb 0.240000 user 0.240000 sys 0.000000 (median of 40)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013100 comb 0.010000 user 0.010000 sys 0.000000 (median of 226)
after:  ! wall 0.013247 comb 0.010000 user 0.010000 sys 0.000000 (median of 223)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.001633 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after:  ! wall 0.001670 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000078 comb 0.000000 user 0.000000 sys 0.000000 (median of 11984)
after:  ! wall 0.000119 comb 0.000000 user 0.000000 sys 0.000000 (median of 7982)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.207093 comb 0.210000 user 0.210000 sys 0.000000 (median of 47)
after:  ! wall 0.201551 comb 0.200000 user 0.200000 sys 0.000000 (median of 48)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.038462 comb 0.040000 user 0.040000 sys 0.000000 (median of 100)
after:  ! wall 0.036578 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)

Differential Revision: https://phab.mercurial-scm.org/D7076

# 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.pycompat import open
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 = b'ships-with-hg-core'


def changedlines(ui, repo, ctx1, ctx2, fns):
    added, removed = 0, 0
    fmatch = scmutil.matchfiles(repo, fns)
    diff = b''.join(patch.diff(repo, ctx1.node(), ctx2.node(), fmatch))
    for l in diff.split(b'\n'):
        if l.startswith(b"+") and not l.startswith(b"+++ "):
            added += 1
        elif l.startswith(b"-") and not l.startswith(b"--- "):
            removed += 1
    return (added, removed)


def countrate(ui, repo, amap, *pats, **opts):
    """Calculate stats"""
    opts = pycompat.byteskwargs(opts)
    if opts.get(b'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[b'dateformat']))
            )

    else:
        tmpl = opts.get(b'oldtemplate') or opts.get(b'template')
        tmpl = logcmdutil.maketemplater(ui, repo, tmpl)

        def getkey(ctx):
            ui.pushbuffer()
            tmpl.show(ctx)
            return ui.popbuffer()

    progress = ui.makeprogress(
        _(b'analyzing'), unit=_(b'revisions'), total=len(repo)
    )
    rate = {}
    df = False
    if opts.get(b'date'):
        df = dateutil.matchdate(opts[b'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(b'changesets'):
            rate[key] = (rate.get(key, (0,))[0] + 1, 0)
        else:
            parents = ctx.parents()
            if len(parents) > 1:
                ui.note(_(b'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(
    b'churn',
    [
        (
            b'r',
            b'rev',
            [],
            _(b'count rate for the specified revision or revset'),
            _(b'REV'),
        ),
        (
            b'd',
            b'date',
            b'',
            _(b'count rate for revisions matching date spec'),
            _(b'DATE'),
        ),
        (
            b't',
            b'oldtemplate',
            b'',
            _(b'template to group changesets (DEPRECATED)'),
            _(b'TEMPLATE'),
        ),
        (
            b'T',
            b'template',
            b'{author|email}',
            _(b'template to group changesets'),
            _(b'TEMPLATE'),
        ),
        (
            b'f',
            b'dateformat',
            b'',
            _(b'strftime-compatible format for grouping by date'),
            _(b'FORMAT'),
        ),
        (b'c', b'changesets', False, _(b'count rate by number of changesets')),
        (b's', b'sort', False, _(b'sort by key (default: sort by count)')),
        (b'', b'diffstat', False, _(b'display added/removed lines separately')),
        (b'', b'aliases', b'', _(b'file with email aliases'), _(b'FILE')),
    ]
    + cmdutil.walkopts,
    _(b"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 + b" " * (l - encoding.colwidth(s))

    amap = {}
    aliases = opts.get(r'aliases')
    if not aliases and os.path.exists(repo.wjoin(b'.hgchurn')):
        aliases = repo.wjoin(b'.hgchurn')
    if aliases:
        for l in open(aliases, b"rb"):
            try:
                alias, actual = l.rsplit(b'=' in l and b'=' or None, 1)
                amap[alias.strip()] = actual.strip()
            except ValueError:
                l = l.strip()
                if l:
                    ui.warn(_(b"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(b"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 b"%s %15s %s%s\n" % (
                pad(name, maxname),
                b'+%d/-%d' % (added, removed),
                ui.label(b'+' * charnum(added), b'diffstat.inserted'),
                ui.label(b'-' * charnum(removed), b'diffstat.deleted'),
            )

    else:
        width -= 6

        def format(name, count):
            return b"%s %6d %s\n" % (
                pad(name, maxname),
                sum(count),
                b'*' * charnum(sum(count)),
            )

    def charnum(count):
        return int(count * width // maxcount)

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