view hgext/commitextras.py @ 45773:210f9b8d7bbd stable

diff: do not concatenate immutable bytes while building a/b bodies (issue6445)

Use bytearray instead. I don't know what's changed since Python 2, but bytes
concatenation is 100x slow on Python 3.

  % python2.7 -m timeit -s "s = b''" "for i in range(10000): s += b'line'"
  1000 loops, best of 3: 321 usec per loop

  % python3.9 -m timeit -s "s = b''" "for i in range(10000): s += b'line'"
  5 loops, best of 5: 39.2 msec per loop

Benchmark using tailwind.css (measuring the fast path, a is empty):

  % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \
  --color=always --config diff.word-diff=true >/dev/null
  (prev) time: real 1.580 secs (user 1.560+0.000 sys 0.020+0.000)
  (this) time: real 1.610 secs (user 1.570+0.000 sys 0.030+0.000)

  % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \
  --color=always --config diff.word-diff=true >/dev/null
  (prev) time: real 114.500 secs (user 114.460+0.000 sys 0.030+0.000)
  (this) time: real 2.180 secs (user 2.140+0.000 sys 0.040+0.000)

Benchmark using random tabular text data (not the fast path):

  % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf
  % hg ci -ma
  % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf
  % hg ci -mb

  % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \
  --color=always --config diff.word-diff=true >/dev/null
  (prev) time: real 3.240 secs (user 3.040+0.000 sys 0.200+0.000
  (this) time: real 3.230 secs (user 3.070+0.000 sys 0.160+0.000)

  % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \
  --color=always --config diff.word-diff=true >/dev/null
  (prev) time: real 44.130 secs (user 43.850+0.000 sys 0.270+0.000)
  (this) time: real 4.170 secs (user 3.850+0.000 sys 0.310+0.000)

# commitextras.py
#
# Copyright 2013 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''adds a new flag extras to commit (ADVANCED)'''

from __future__ import absolute_import

import re

from mercurial.i18n import _
from mercurial import (
    commands,
    error,
    extensions,
    registrar,
    util,
)

cmdtable = {}
command = registrar.command(cmdtable)
testedwith = b'ships-with-hg-core'

usedinternally = {
    b'amend_source',
    b'branch',
    b'close',
    b'histedit_source',
    b'topic',
    b'rebase_source',
    b'intermediate-source',
    b'__touch-noise__',
    b'source',
    b'transplant_source',
}


def extsetup(ui):
    entry = extensions.wrapcommand(commands.table, b'commit', _commit)
    options = entry[1]
    options.append(
        (
            b'',
            b'extra',
            [],
            _(b'set a changeset\'s extra values'),
            _(b"KEY=VALUE"),
        )
    )


def _commit(orig, ui, repo, *pats, **opts):
    if util.safehasattr(repo, 'unfiltered'):
        repo = repo.unfiltered()

    class repoextra(repo.__class__):
        def commit(self, *innerpats, **inneropts):
            extras = opts.get('extra')
            for raw in extras:
                if b'=' not in raw:
                    msg = _(
                        b"unable to parse '%s', should follow "
                        b"KEY=VALUE format"
                    )
                    raise error.Abort(msg % raw)
                k, v = raw.split(b'=', 1)
                if not k:
                    msg = _(b"unable to parse '%s', keys can't be empty")
                    raise error.Abort(msg % raw)
                if re.search(br'[^\w-]', k):
                    msg = _(
                        b"keys can only contain ascii letters, digits,"
                        b" '_' and '-'"
                    )
                    raise error.Abort(msg)
                if k in usedinternally:
                    msg = _(
                        b"key '%s' is used internally, can't be set "
                        b"manually"
                    )
                    raise error.Abort(msg % k)
                inneropts['extra'][k] = v
            return super(repoextra, self).commit(*innerpats, **inneropts)

    repo.__class__ = repoextra
    return orig(ui, repo, *pats, **opts)