hgext/churn.py

match: express anypats(), not prefix(), in terms of the others

When I added prefix() in 9789b4a7c595 (match: introduce boolean
prefix() method, 2014-10-28), we already had always(), isexact(), and
anypats(), so it made sense to write it in terms of them (a prefix
matcher is one that isn't any of the other types). It's only now that
I realize that it's much more natural to define prefix() explicitly
(it's one that uses path: patterns, roughly speaking) and let
anypats() be defined in terms of the others. Remember that these
methods are all used for determining which fast paths are
possible. anypats() simply means that no fast paths are possible (it
could be called complex() instead). Further evidence is that
rootfilesin:some/dir does not have any patterns, but it's still
considered to be an anypats() matcher. That's because anypats() really
just means that it's not a prefix() matcher (and not always() and not
isexact()).

This patch thus changes prefix() to return False by default and
anypats() to return True only if the other three are False. Having
anypats() be True by default also seems like a good thing, because it
means forgetting to override it will lead only to performance bugs,
not correctness bugs.

Since the base class's implementation changes, we're also forced to
update the subclasses. That change exposed and fixed a bug in the
differencematcher: for example when both its two input matchers were
prefix matchers, we would say that the result was also a prefix
matcher, which is incorrect, because e.g "path:dir - path:dir/foo" no
longer matches everything under "dir" (which is what prefix() means).

# 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))