view mercurial/pushkey.py @ 46020:210f9b8d7bbd 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)

# pushkey.py - dispatching for pushing and pulling keys
#
# Copyright 2010 Matt Mackall <[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.

from __future__ import absolute_import

from . import (
    bookmarks,
    encoding,
    obsolete,
    phases,
)


def _nslist(repo):
    n = {}
    for k in _namespaces:
        n[k] = b""
    if not obsolete.isenabled(repo, obsolete.exchangeopt):
        n.pop(b'obsolete')
    return n


_namespaces = {
    b"namespaces": (lambda *x: False, _nslist),
    b"bookmarks": (bookmarks.pushbookmark, bookmarks.listbookmarks),
    b"phases": (phases.pushphase, phases.listphases),
    b"obsolete": (obsolete.pushmarker, obsolete.listmarkers),
}


def register(namespace, pushkey, listkeys):
    _namespaces[namespace] = (pushkey, listkeys)


def _get(namespace):
    return _namespaces.get(namespace, (lambda *x: False, lambda *x: {}))


def push(repo, namespace, key, old, new):
    '''should succeed iff value was old'''
    pk = _get(namespace)[0]
    return pk(repo, key, old, new)


def list(repo, namespace):
    '''return a dict'''
    lk = _get(namespace)[1]
    return lk(repo)


encode = encoding.fromlocal

decode = encoding.tolocal


def encodekeys(keys):
    """encode the content of a pushkey namespace for exchange over the wire"""
    return b'\n'.join([b'%s\t%s' % (encode(k), encode(v)) for k, v in keys])


def decodekeys(data):
    """decode the content of a pushkey namespace from exchange over the wire"""
    result = {}
    for l in data.splitlines():
        k, v = l.split(b'\t')
        result[decode(k)] = decode(v)
    return result