##// 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:

r49801:642e31cb default
r51286:81c7d04f stable
Show More
config.py
257 lines | 8.5 KiB | text/x-python | PythonLexer
# config.py - configuration parsing for Mercurial
#
# Copyright 2009 Olivia Mackall <olivia@selenic.com> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import errno
import os
from .i18n import _
from .pycompat import getattr
from . import (
encoding,
error,
util,
)
class config:
def __init__(self, data=None):
self._current_source_level = 0
self._data = {}
self._unset = []
if data:
for k in data._data:
self._data[k] = data[k].copy()
self._current_source_level = data._current_source_level + 1
def new_source(self):
"""increment the source counter
This is used to define source priority when reading"""
self._current_source_level += 1
def copy(self):
return config(self)
def __contains__(self, section):
return section in self._data
def hasitem(self, section, item):
return item in self._data.get(section, {})
def __getitem__(self, section):
return self._data.get(section, {})
def __iter__(self):
for d in self.sections():
yield d
def update(self, src):
current_level = self._current_source_level
current_level += 1
max_level = self._current_source_level
for s, n in src._unset:
ds = self._data.get(s, None)
if ds is not None and n in ds:
self._data[s] = ds.preparewrite()
del self._data[s][n]
for s in src:
ds = self._data.get(s, None)
if ds:
self._data[s] = ds.preparewrite()
else:
self._data[s] = util.cowsortdict()
for k, v in src._data[s].items():
value, source, level = v
level += current_level
max_level = max(level, current_level)
self._data[s][k] = (value, source, level)
self._current_source_level = max_level
def _get(self, section, item):
return self._data.get(section, {}).get(item)
def get(self, section, item, default=None):
result = self._get(section, item)
if result is None:
return default
return result[0]
def backup(self, section, key):
"""return a tuple allowing restore to reinstall a previous value
The main reason we need it is because it handles the "no data" case.
"""
try:
item = self._data[section][key]
except KeyError:
return (section, key)
else:
return (section, key) + item
def source(self, section, item):
result = self._get(section, item)
if result is None:
return b""
return result[1]
def level(self, section, item):
result = self._get(section, item)
if result is None:
return None
return result[2]
def sections(self):
return sorted(self._data.keys())
def items(self, section):
items = self._data.get(section, {}).items()
return [(k, v[0]) for (k, v) in items]
def set(self, section, item, value, source=b""):
assert not isinstance(
section, str
), b'config section may not be unicode strings on Python 3'
assert not isinstance(
item, str
), b'config item may not be unicode strings on Python 3'
assert not isinstance(
value, str
), b'config values may not be unicode strings on Python 3'
if section not in self:
self._data[section] = util.cowsortdict()
else:
self._data[section] = self._data[section].preparewrite()
self._data[section][item] = (value, source, self._current_source_level)
def alter(self, section, key, new_value):
"""alter a value without altering its source or level
This method is meant to be used by `ui.fixconfig` only."""
item = self._data[section][key]
size = len(item)
new_item = (new_value,) + item[1:]
assert len(new_item) == size
self._data[section][key] = new_item
def restore(self, data):
"""restore data returned by self.backup"""
if len(data) != 2:
# restore old data
section, key = data[:2]
item = data[2:]
self._data[section] = self._data[section].preparewrite()
self._data[section][key] = item
else:
# no data before, remove everything
section, item = data
if section in self._data:
self._data[section].pop(item, None)
def parse(self, src, data, sections=None, remap=None, include=None):
sectionre = util.re.compile(br'\[([^\[]+)\]')
itemre = util.re.compile(br'([^=\s][^=]*?)\s*=\s*(.*\S|)')
contre = util.re.compile(br'\s+(\S|\S.*\S)\s*$')
emptyre = util.re.compile(br'(;|#|\s*$)')
commentre = util.re.compile(br'(;|#)')
unsetre = util.re.compile(br'%unset\s+(\S+)')
includere = util.re.compile(br'%include\s+(\S|\S.*\S)\s*$')
section = b""
item = None
line = 0
cont = False
if remap:
section = remap.get(section, section)
for l in data.splitlines(True):
line += 1
if line == 1 and l.startswith(b'\xef\xbb\xbf'):
# Someone set us up the BOM
l = l[3:]
if cont:
if commentre.match(l):
continue
m = contre.match(l)
if m:
if sections and section not in sections:
continue
v = self.get(section, item) + b"\n" + m.group(1)
self.set(section, item, v, b"%s:%d" % (src, line))
continue
item = None
cont = False
m = includere.match(l)
if m and include:
expanded = util.expandpath(m.group(1))
try:
include(expanded, remap=remap, sections=sections)
except IOError as inst:
if inst.errno != errno.ENOENT:
raise error.ConfigError(
_(b"cannot include %s (%s)")
% (expanded, encoding.strtolocal(inst.strerror)),
b"%s:%d" % (src, line),
)
continue
if emptyre.match(l):
continue
m = sectionre.match(l)
if m:
section = m.group(1)
if remap:
section = remap.get(section, section)
if section not in self:
self._data[section] = util.cowsortdict()
continue
m = itemre.match(l)
if m:
item = m.group(1)
cont = True
if sections and section not in sections:
continue
self.set(section, item, m.group(2), b"%s:%d" % (src, line))
continue
m = unsetre.match(l)
if m:
name = m.group(1)
if sections and section not in sections:
continue
if self.get(section, name) is not None:
self._data[section] = self._data[section].preparewrite()
del self._data[section][name]
self._unset.append((section, name))
continue
message = l.rstrip()
if l.startswith(b' '):
message = b"unexpected leading whitespace: %s" % message
raise error.ConfigError(message, (b"%s:%d" % (src, line)))
def read(self, path, fp=None, sections=None, remap=None):
self.new_source()
if not fp:
fp = util.posixfile(path, b'rb')
assert (
getattr(fp, 'mode', 'rb') == 'rb'
), b'config files must be opened in binary mode, got fp=%r mode=%r' % (
fp,
fp.mode,
)
dir = os.path.dirname(path)
def include(rel, remap, sections):
abs = os.path.normpath(os.path.join(dir, rel))
self.read(abs, remap=remap, sections=sections)
# anything after the include has a higher level
self.new_source()
self.parse(
path, fp.read(), sections=sections, remap=remap, include=include
)