view mercurial/utils/resourceutil.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)

# resourceutil.py - utility for looking up resources
#
#  Copyright 2005 K. Thananchayan <[e-mail]>
#  Copyright 2005-2007 Matt Mackall <[e-mail]>
#  Copyright 2006 Vadim Gelfer <[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

import imp
import os
import sys

from .. import pycompat


def mainfrozen():
    """return True if we are a frozen executable.

    The code supports py2exe (most common, Windows only) and tools/freeze
    (portable, not much used).
    """
    return (
        pycompat.safehasattr(sys, "frozen")  # new py2exe
        or pycompat.safehasattr(sys, "importers")  # old py2exe
        or imp.is_frozen("__main__")  # tools/freeze
    )


# the location of data files matching the source code
if mainfrozen() and getattr(sys, "frozen", None) != "macosx_app":
    # executable version (py2exe) doesn't support __file__
    datapath = os.path.dirname(pycompat.sysexecutable)
    _rootpath = datapath

    # The installers store the files outside of library.zip, like
    # C:\Program Files\Mercurial\defaultrc\*.rc.  This strips the
    # leading "mercurial." off of the package name, so that these
    # pseudo resources are found in their directory next to the
    # executable.
    def _package_path(package):
        dirs = package.split(b".")
        assert dirs[0] == b"mercurial"
        return os.path.join(_rootpath, *dirs[1:])


else:
    datapath = os.path.dirname(os.path.dirname(pycompat.fsencode(__file__)))
    _rootpath = os.path.dirname(datapath)

    def _package_path(package):
        return os.path.join(_rootpath, *package.split(b"."))


try:
    # importlib.resources exists from Python 3.7; see fallback in except clause
    # further down
    from importlib import resources

    from .. import encoding

    # Force loading of the resources module
    resources.open_binary  # pytype: disable=module-attr

    def open_resource(package, name):
        return resources.open_binary(  # pytype: disable=module-attr
            pycompat.sysstr(package), pycompat.sysstr(name)
        )

    def is_resource(package, name):
        return resources.is_resource(
            pycompat.sysstr(package), encoding.strfromlocal(name)
        )

    def contents(package):
        for r in resources.contents(pycompat.sysstr(package)):
            yield encoding.strtolocal(r)


except (ImportError, AttributeError):
    # importlib.resources was not found (almost definitely because we're on a
    # Python version before 3.7)

    def open_resource(package, name):
        path = os.path.join(_package_path(package), name)
        return open(path, "rb")

    def is_resource(package, name):
        path = os.path.join(_package_path(package), name)

        try:
            return os.path.isfile(pycompat.fsdecode(path))
        except (IOError, OSError):
            return False

    def contents(package):
        path = pycompat.fsdecode(_package_path(package))

        for p in os.listdir(path):
            yield pycompat.fsencode(p)