view hgext/churn.py @ 25561:50a6c3c55db1 stable

parsers: do not cache RevlogError type (issue4451)

Index lookups raise RevlogError when the lookup fails. The previous
implementation was caching a reference to the RevlogError type in a
static variable. This assumed that the "mercurial.error" module was
only loaded once and there was only a single copy of it floating
around in memory. Unfortunately, in some situations - including
certain mod_wsgi configurations - this was not the case: the
"mercurial.error" module could be reloaded. It was possible for a
"RevlogError" reference from the first interpreter to be used by
a second interpreter. While the underlying thing was a
"mercurial.error.RevlogError," the object IDs were different, so
the Python code in revlog.py was failing to catch the exception! This
error has existed since the C index lookup code was implemented in
changeset e8d37b78acfb, which was first released in Mercurial 2.2 in
2012.
http://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/#static-variables-are-shared
contains more details.

This patch removes the caching of the RevlogError type from the
function.

Since pretty much the entire function was refactored and the return
value of the function wasn't used, I changed the function signature
to not return anything.

For reasons unknown to me, we were calling PyErr_SetObject()
with the type of RevlogError and an instance of RevlogError. This
was equivalent to the Python code "raise RevlogError(RevlogError)".
This seemed wonky and completely unnecessary. The Python code only
cares about the type of the exception, not its contents. So I got
rid of this complexity.

This is my first Python C extension patch. Please give extra scrutiny
to it during review.

# 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 mercurial.i18n import _
from mercurial import patch, cmdutil, scmutil, util, templater, commands
from mercurial import encoding
import os
import time, datetime

cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'

def maketemplater(ui, repo, tmpl):
    tmpl = templater.parsestring(tmpl, quoted=False)
    try:
        t = cmdutil.changeset_templater(ui, repo, False, None, tmpl,
                                        None, False)
    except SyntaxError, inst:
        raise util.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))