##// 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:

r51252:2761ce77 stable
r51286:81c7d04f stable
Show More
hook.py
366 lines | 11.6 KiB | text/x-python | PythonLexer
# hook.py - hook support for mercurial
#
# Copyright 2007 Olivia Mackall <olivia@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import contextlib
import errno
import os
import sys
from .i18n import _
from .pycompat import getattr
from . import (
demandimport,
encoding,
error,
extensions,
pycompat,
util,
)
from .utils import (
procutil,
resourceutil,
stringutil,
)
def pythonhook(ui, repo, htype, hname, funcname, args, throw):
"""call python hook. hook is callable object, looked up as
name in python module. if callable returns "true", hook
fails, else passes. if hook raises exception, treated as
hook failure. exception propagates if throw is "true".
reason for "true" meaning "hook failed" is so that
unmodified commands (e.g. mercurial.commands.update) can
be run as hooks without wrappers to convert return values."""
if callable(funcname):
obj = funcname
funcname = pycompat.sysbytes(obj.__module__ + "." + obj.__name__)
else:
d = funcname.rfind(b'.')
if d == -1:
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" not in a module')
% (hname, funcname)
)
modname = funcname[:d]
oldpaths = sys.path
if resourceutil.mainfrozen():
# binary installs require sys.path manipulation
modpath, modfile = os.path.split(modname)
if modpath and modfile:
sys.path = sys.path[:] + [modpath]
modname = modfile
with demandimport.deactivated():
try:
obj = __import__(pycompat.sysstr(modname))
except (ImportError, SyntaxError):
e1 = sys.exc_info()
try:
# extensions are loaded with hgext_ prefix
obj = __import__("hgext_%s" % pycompat.sysstr(modname))
except (ImportError, SyntaxError):
e2 = sys.exc_info()
if ui.tracebackflag:
ui.warn(
_(
b'exception from first failed import '
b'attempt:\n'
)
)
ui.traceback(e1)
if ui.tracebackflag:
ui.warn(
_(
b'exception from second failed import '
b'attempt:\n'
)
)
ui.traceback(e2)
if not ui.tracebackflag:
tracebackhint = _(
b'run with --traceback for stack trace'
)
else:
tracebackhint = None
raise error.HookLoadError(
_(b'%s hook is invalid: import of "%s" failed')
% (hname, modname),
hint=tracebackhint,
)
sys.path = oldpaths
try:
for p in funcname.split(b'.')[1:]:
obj = getattr(obj, p)
except AttributeError:
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" is not defined')
% (hname, funcname)
)
if not callable(obj):
raise error.HookLoadError(
_(b'%s hook is invalid: "%s" is not callable')
% (hname, funcname)
)
ui.note(_(b"calling hook %s: %s\n") % (hname, funcname))
starttime = util.timer()
try:
r = obj(ui=ui, repo=repo, hooktype=htype, **pycompat.strkwargs(args))
except Exception as exc:
if isinstance(exc, error.Abort):
ui.warn(_(b'error: %s hook failed: %s\n') % (hname, exc.args[0]))
else:
ui.warn(
_(b'error: %s hook raised an exception: %s\n')
% (hname, stringutil.forcebytestr(exc))
)
if throw:
raise
if not ui.tracebackflag:
ui.warn(_(b'(run with --traceback for stack trace)\n'))
ui.traceback()
return True, True
finally:
duration = util.timer() - starttime
ui.log(
b'pythonhook',
b'pythonhook-%s: %s finished in %0.2f seconds\n',
htype,
funcname,
duration,
)
if r:
if throw:
raise error.HookAbort(_(b'%s hook failed') % hname)
ui.warn(_(b'warning: %s hook failed\n') % hname)
return r, False
def _exthook(ui, repo, htype, name, cmd, args, throw):
starttime = util.timer()
env = {}
# make in-memory changes visible to external process
if repo is not None:
tr = repo.currenttransaction()
repo.dirstate.write(tr)
if tr and tr.writepending():
env[b'HG_PENDING'] = repo.root
env[b'HG_HOOKTYPE'] = htype
env[b'HG_HOOKNAME'] = name
if ui.config(b'hooks', b'%s:run-with-plain' % name) == b'auto':
plain = ui.plain()
else:
plain = ui.configbool(b'hooks', b'%s:run-with-plain' % name)
if plain:
env[b'HGPLAIN'] = b'1'
else:
env[b'HGPLAIN'] = b''
for k, v in args.items():
# transaction changes can accumulate MBs of data, so skip it
# for external hooks
if k == b'changes':
continue
if callable(v):
v = v()
if isinstance(v, (dict, list)):
v = stringutil.pprint(v)
env[b'HG_' + k.upper()] = v
if ui.configbool(b'hooks', b'tonative.%s' % name, False):
oldcmd = cmd
cmd = procutil.shelltonative(cmd, env)
if cmd != oldcmd:
ui.note(_(b'converting hook "%s" to native\n') % name)
ui.note(_(b"running hook %s: %s\n") % (name, cmd))
if repo:
cwd = repo.root
else:
cwd = encoding.getcwd()
r = ui.system(cmd, environ=env, cwd=cwd, blockedtag=b'exthook-%s' % (name,))
if repo is not None and repo.currentwlock() is None:
repo.invalidatedirstate()
if repo is not None and repo.currentlock() is None:
repo.invalidate()
duration = util.timer() - starttime
ui.log(
b'exthook',
b'exthook-%s: %s finished in %0.2f seconds\n',
name,
cmd,
duration,
)
if r:
desc = procutil.explainexit(r)
if throw:
raise error.HookAbort(_(b'%s hook %s') % (name, desc))
ui.warn(_(b'warning: %s hook %s\n') % (name, desc))
return r
# represent an untrusted hook command
_fromuntrusted = object()
def _allhooks(ui):
"""return a list of (hook-id, cmd) pairs sorted by priority"""
hooks = _hookitems(ui)
# Be careful in this section, propagating the real commands from untrusted
# sources would create a security vulnerability, make sure anything altered
# in that section uses "_fromuntrusted" as its command.
untrustedhooks = _hookitems(ui, _untrusted=True)
for name, value in untrustedhooks.items():
trustedvalue = hooks.get(name, ((), (), name, _fromuntrusted))
if value != trustedvalue:
(lp, lo, lk, lv) = trustedvalue
hooks[name] = (lp, lo, lk, _fromuntrusted)
# (end of the security sensitive section)
return [(k, v) for p, o, k, v in sorted(hooks.values())]
def _hookitems(ui, _untrusted=False):
"""return all hooks items ready to be sorted"""
hooks = {}
for name, cmd in ui.configitems(b'hooks', untrusted=_untrusted):
if (
name.startswith(b'priority.')
or name.startswith(b'tonative.')
or b':' in name
):
continue
priority = ui.configint(b'hooks', b'priority.%s' % name, 0)
hooks[name] = ((-priority,), (len(hooks),), name, cmd)
return hooks
_redirect = False
def redirect(state):
global _redirect
_redirect = state
def hashook(ui, htype):
"""return True if a hook is configured for 'htype'"""
if not ui.callhooks:
return False
for hname, cmd in _allhooks(ui):
if hname.split(b'.')[0] == htype and cmd:
return True
return False
def hook(ui, repo, htype, throw=False, **args):
if not ui.callhooks:
return False
hooks = []
for hname, cmd in _allhooks(ui):
if hname.split(b'.')[0] == htype and cmd:
hooks.append((hname, cmd))
res = runhooks(ui, repo, htype, hooks, throw=throw, **args)
r = False
for hname, cmd in hooks:
r = res[hname][0] or r
return r
@contextlib.contextmanager
def redirect_stdio():
"""Redirects stdout to stderr, if possible."""
oldstdout = -1
try:
if _redirect:
try:
stdoutno = procutil.stdout.fileno()
stderrno = procutil.stderr.fileno()
# temporarily redirect stdout to stderr, if possible
if stdoutno >= 0 and stderrno >= 0:
procutil.stdout.flush()
oldstdout = os.dup(stdoutno)
os.dup2(stderrno, stdoutno)
except (OSError, AttributeError):
# files seem to be bogus, give up on redirecting (WSGI, etc)
pass
yield
finally:
# The stderr is fully buffered on Windows when connected to a pipe.
# A forcible flush is required to make small stderr data in the
# remote side available to the client immediately.
try:
procutil.stderr.flush()
except IOError as err:
if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
raise error.StdioError(err)
if _redirect and oldstdout >= 0:
try:
procutil.stdout.flush() # write hook output to stderr fd
except IOError as err:
if err.errno not in (errno.EPIPE, errno.EIO, errno.EBADF):
raise error.StdioError(err)
os.dup2(oldstdout, stdoutno)
os.close(oldstdout)
def runhooks(ui, repo, htype, hooks, throw=False, **args):
args = pycompat.byteskwargs(args)
res = {}
with redirect_stdio():
for hname, cmd in hooks:
if cmd is _fromuntrusted:
if throw:
raise error.HookAbort(
_(b'untrusted hook %s not executed') % hname,
hint=_(b"see 'hg help config.trusted'"),
)
ui.warn(_(b'warning: untrusted hook %s not executed\n') % hname)
r = 1
raised = False
elif callable(cmd):
r, raised = pythonhook(ui, repo, htype, hname, cmd, args, throw)
elif cmd.startswith(b'python:'):
if cmd.count(b':') >= 2:
path, cmd = cmd[7:].rsplit(b':', 1)
path = util.expandpath(path)
if repo:
path = os.path.join(repo.root, path)
try:
mod = extensions.loadpath(path, b'hghook.%s' % hname)
except Exception:
ui.write(_(b"loading %s hook failed:\n") % hname)
raise
hookfn = getattr(mod, cmd)
else:
hookfn = cmd[7:].strip()
r, raised = pythonhook(
ui, repo, htype, hname, hookfn, args, throw
)
else:
r = _exthook(ui, repo, htype, hname, cmd, args, throw)
raised = False
res[hname] = r, raised
return res