git: skeleton of a new extension to _directly_ operate on git repos
This is based in part of work I did years ago in hgit, but it's mostly
new code since I'm using pygit2 instead of dulwich and the hg storage
interfaces have improved. Some cleanup of old hgit code by Pulkit,
which I greatly appreciate.
test-git-interop.t does not cover a whole lot of cases, but it
passes. It includes status, diff, making a new commit, and `hg annotate`
working on the git repository.
This is _not_ (yet) production quality code: this is an
experiment. Known technical debt lurking in this implementation:
* Writing bookmarks just totally ignores transactions.
* The way progress is threaded down into the gitstore is awful.
* Ideally we'd find a way to incrementally reindex DAGs. I'm not sure
how to do that efficiently, so we might need a "known only fast-forwards"
mode on the DAG indexer for use on `hg commit` and friends.
* We don't even _try_ to do anything reasonable for `hg pull` or `hg push`.
* Mercurial need an interface for the changelog type.
Tests currently require git 2.24 as far as I'm aware: `git status` has
some changed output that I didn't try and handle in a compatible way.
This patch has produced some interesting cleanups, most recently on
the manifest type. I expect continuing down this road will produce
other meritorious cleanups throughout our code.
Differential Revision: https://phab.mercurial-scm.org/D6734
# 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 __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('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('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('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))