##// END OF EJS Templates
match: match explicit file using a set...
match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)

File last commit:

r49730:6000f5b2 default
r51286:81c7d04f stable
Show More
rcutil.py
118 lines | 3.5 KiB | text/x-python | PythonLexer
# rcutil.py - utilities about config paths, special config sections etc.
#
# Copyright Mercurial Contributors
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import os
from . import (
encoding,
pycompat,
util,
)
from .utils import resourceutil
if pycompat.iswindows:
from . import scmwindows as scmplatform
else:
from . import scmposix as scmplatform
fallbackpager = scmplatform.fallbackpager
systemrcpath = scmplatform.systemrcpath
userrcpath = scmplatform.userrcpath
def _expandrcpath(path):
'''path could be a file or a directory. return a list of file paths'''
p = util.expandpath(path)
if os.path.isdir(p):
join = os.path.join
return sorted(
join(p, f) for f, k in util.listdir(p) if f.endswith(b'.rc')
)
return [p]
def envrcitems(env=None):
"""Return [(section, name, value, source)] config items.
The config items are extracted from environment variables specified by env,
used to override systemrc, but not userrc.
If env is not provided, encoding.environ will be used.
"""
if env is None:
env = encoding.environ
checklist = [
(b'EDITOR', b'ui', b'editor'),
(b'VISUAL', b'ui', b'editor'),
(b'PAGER', b'pager', b'pager'),
]
result = []
for envname, section, configname in checklist:
if envname not in env:
continue
result.append((section, configname, env[envname], b'$%s' % envname))
return result
def default_rc_resources():
"""return rc resource IDs in defaultrc"""
rsrcs = resourceutil.contents(b'mercurial.defaultrc')
return [
(b'mercurial.defaultrc', r)
for r in sorted(rsrcs)
if resourceutil.is_resource(b'mercurial.defaultrc', r)
and r.endswith(b'.rc')
]
def rccomponents():
"""return an ordered [(type, obj)] about where to load configs.
respect $HGRCPATH. if $HGRCPATH is empty, only .hg/hgrc of current repo is
used. if $HGRCPATH is not set, the platform default will be used.
if a directory is provided, *.rc files under it will be used.
type could be either 'path', 'items' or 'resource'. If type is 'path',
obj is a string, and is the config file path. if type is 'items', obj is a
list of (section, name, value, source) that should fill the config directly.
If type is 'resource', obj is a tuple of (package name, resource name).
"""
envrc = (b'items', envrcitems())
if b'HGRCPATH' in encoding.environ:
# assume HGRCPATH is all about user configs so environments can be
# overridden.
_rccomponents = [envrc]
for p in encoding.environ[b'HGRCPATH'].split(pycompat.ospathsep):
if not p:
continue
_rccomponents.extend((b'path', p) for p in _expandrcpath(p))
else:
_rccomponents = [(b'resource', r) for r in default_rc_resources()]
normpaths = lambda paths: [
(b'path', os.path.normpath(p)) for p in paths
]
_rccomponents.extend(normpaths(systemrcpath()))
_rccomponents.append(envrc)
_rccomponents.extend(normpaths(userrcpath()))
return _rccomponents
def defaultpagerenv():
"""return a dict of default environment variables and their values,
intended to be set before starting a pager.
"""
return {b'LESS': b'FRX', b'LV': b'-c'}
def use_repo_hgrc():
"""True if repositories `.hg/hgrc` config should be read"""
return b'HGRCSKIPREPO' not in encoding.environ