hgext/churn.py
author timeless <timeless@mozdev.org>
Wed, 23 Dec 2015 19:07:34 +0000
changeset 27568 34b01a51bd42
parent 26587 56b2bcea2529
child 28094 79fc627578ac
permissions -rw-r--r--
parents: correct help revset replacements Implementing `hg parents -r REV FILE` correctly is hard. The output can be 0, 1, or 2 revs. First, you can't use parents(), because it sorts its output... Consider: echo $a echo par@rev: `hg log -r "parents($a)" -q` echo p12@rev: `hg log -r "p1($a)+p2($a)" -q` echo parents: `hg parents -q -r $a` (Merge 1 into 0) 3 par@rev: 0:d9612eafe8ec 1:070fe4290d06 p12@rev: 0:d9612eafe8ec 1:070fe4290d06 parents: 0:d9612eafe8ec 1:070fe4290d06 (Merge 4 into 5) 6 par@rev: 4:db73392995c3 5:c26e7dd67644 p12@rev: 5:c26e7dd67644 4:db73392995c3 parents: 5:c26e7dd67644 4:db73392995c3 (Merge 7 into 8) 9 par@rev: 7:d84f47462f70 8:9597bcab36e0 p12@rev: 8:9597bcab36e0 7:d84f47462f70 parents: 8:9597bcab36e0 7:d84f47462f70 You also can't use parents or/p1/p2 alone with a set, as in: -r "parents(::REV and file(FILE))" -r "parents(::REV - REV and file(FILE))" ... because each will return all parents for each candidate revision, and the :: gives too many candidates. Thus, we need a max and a p1/p2. Also, anything of this form: max(::REV - REV and file(FILE)) ... is wrong, because max will return only one revision, and for a proper parents, you need to return two occasionally. Lastly, it doesn't help that `hg parents -r REV FILE` is buggy due to a quirk in filelogs. Here's a repository to consider when evaluating whether your revset is correct: $ hg log -G --template '{rev} {files}\n'; @ 10 a | o 9 a b |\ | o 8 a | | o | 7 a | | +---o 6 b | |/ | o 5 b | | o | 4 b | | +---o 3 | |/ +---o 2 | |/ | o 1 b | o 0 a revs 4 and 5 create a conflict. The conflict is resolved in the same way by both 6 and 9. You would hope that parents around 9/10 would point to 9, but `hg parents` will point to 6 due to the aforementioned bug. Here's the winning solution test script and its output. echo $a; echo rp12-max: `hg log -r "max(::p1($a) and file(b)) + max(::p2($a) and file(b))" -q` 2> /dev/null; echo expected: `hg parents -q -r $a b` 2> /dev/null; Note that for 10, the output differs, but again, this is because of the aforementioned bug. The rp12-max output is "correct", whereas "expected" is just an unfortunate bug. The abort output is due to something else. I'm not sure why someone thought it was important to abort to stdio instead of stderr, but that's really not my problem here. 10 rp12-max: 9:184ebefc2fce expected: 6:dd558142b03f 9 rp12-max: 5:c26e7dd67644 4:db73392995c3 expected: 5:c26e7dd67644 4:db73392995c3 8 rp12-max: 5:c26e7dd67644 expected: 5:c26e7dd67644 7 rp12-max: 4:db73392995c3 expected: 4:db73392995c3 6 rp12-max: 5:c26e7dd67644 4:db73392995c3 expected: 5:c26e7dd67644 4:db73392995c3 5 rp12-max: 1:070fe4290d06 expected: 1:070fe4290d06 4 rp12-max: abort: 'b' not found in manifest! expected: 3 rp12-max: 1:070fe4290d06 expected: 1:070fe4290d06 2 rp12-max: 1:070fe4290d06 expected: 1:070fe4290d06 1 rp12-max: abort: 'b' not found in manifest! expected: 0 rp12-max: abort: 'b' not found in manifest! expected:

# 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, error
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 as inst:
        raise error.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))