##// END OF EJS Templates
xdiff: add a preprocessing step that trims files...
xdiff: add a preprocessing step that trims files xdiff has a `xdl_trim_ends` step that removes common lines, unmatchable lines. That is in theory good, but happens too late - after splitting, hashing, and adjusting the hash values so they are unique. Those splitting, hashing and adjusting hash values steps could have noticeable overhead. Diffing two large files with minor (one-line-ish) changes are not uncommon. In that case, the raw performance of those preparation steps seriously matter. Even allocating an O(N) array and storing line offsets to it is expensive. Therefore my previous attempts [1] [2] cannot be good enough since they do not remove the O(N) array assignment. This patch adds a preprocessing step - `xdl_trim_files` that runs before other preprocessing steps. It counts common prefix and suffix and lines in them (needed for displaying line number), without doing anything else. Testing with a crafted large (169MB) file, with minor change: ``` open('a','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6000000)) open('b','w').write(''.join('%s\n' % (i % 100000) for i in xrange(30000000) if i != 6003000)) ``` Running xdiff by a simple binary [3], this patch improves the xdiff perf by more than 10x for the above case: ``` # xdiff before this patch 2.41s user 1.13s system 98% cpu 3.592 total # xdiff after this patch 0.14s user 0.16s system 98% cpu 0.309 total # gnu diffutils 0.12s user 0.15s system 98% cpu 0.272 total # (best of 20 runs) ``` It's still slightly slower than GNU diffutils. But it's pretty close now. Testing with real repo data: For the whole repo, this patch makes xdiff 25% faster: ``` # hg perfbdiff --count 100 --alldata -c d334afc585e2 --blocks [--xdiff] # xdiff, after ! wall 0.058861 comb 0.050000 user 0.050000 sys 0.000000 (best of 100) # xdiff, before ! wall 0.077816 comb 0.080000 user 0.080000 sys 0.000000 (best of 91) # bdiff ! wall 0.117473 comb 0.120000 user 0.120000 sys 0.000000 (best of 67) ``` For files that are long (ex. commands.py), the speedup is more than 3x, very significant: ``` # hg perfbdiff --count 3000 --blocks commands.py.i 1 [--xdiff] # xdiff, after ! wall 0.690583 comb 0.690000 user 0.690000 sys 0.000000 (best of 12) # xdiff, before ! wall 2.240361 comb 2.210000 user 2.210000 sys 0.000000 (best of 4) # bdiff ! wall 2.469852 comb 2.440000 user 2.440000 sys 0.000000 (best of 4) ``` [1]: https://phab.mercurial-scm.org/D2631 [2]: https://phab.mercurial-scm.org/D2634 [3]: ``` // Code to run xdiff from command line. No proper error handling. #include <stdlib.h> #include <unistd.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include "mercurial/thirdparty/xdiff/xdiff.h" #define ensure(x) if (!(x)) exit(255); mmfile_t readfile(const char *path) { struct stat st; int fd = open(path, O_RDONLY); fstat(fd, &st); mmfile_t file = { malloc(st.st_size), st.st_size }; ensure(read(fd, file.ptr, st.st_size) == st.st_size); close(fd); return file; } int main(int argc, char const *argv[]) { mmfile_t a = readfile(argv[1]), b = readfile(argv[2]); xpparam_t xpp = {0}; xdemitconf_t xecfg = {0}; xdemitcb_t ecb = {0}; xdl_diff(&a, &b, &xpp, &xecfg, &ecb); return 0; } ``` Differential Revision: https://phab.mercurial-scm.org/D2686

File last commit:

r36125:c4146cf4 default
r36838:f33a87cf default
Show More
hook.py
279 lines | 10.0 KiB | text/x-python | PythonLexer
# hook.py - hook support for mercurial
#
# Copyright 2007 Matt Mackall <mpm@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.
from __future__ import absolute_import
import os
import sys
from .i18n import _
from . import (
demandimport,
encoding,
error,
extensions,
pycompat,
util,
)
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__ + r"." + obj.__name__)
else:
d = funcname.rfind('.')
if d == -1:
raise error.HookLoadError(
_('%s hook is invalid: "%s" not in a module')
% (hname, funcname))
modname = funcname[:d]
oldpaths = sys.path
if util.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__(r"hgext_%s" % pycompat.sysstr(modname))
except (ImportError, SyntaxError):
e2 = sys.exc_info()
if ui.tracebackflag:
ui.warn(_('exception from first failed import '
'attempt:\n'))
ui.traceback(e1)
if ui.tracebackflag:
ui.warn(_('exception from second failed import '
'attempt:\n'))
ui.traceback(e2)
if not ui.tracebackflag:
tracebackhint = _(
'run with --traceback for stack trace')
else:
tracebackhint = None
raise error.HookLoadError(
_('%s hook is invalid: import of "%s" failed') %
(hname, modname), hint=tracebackhint)
sys.path = oldpaths
try:
for p in funcname.split('.')[1:]:
obj = getattr(obj, p)
except AttributeError:
raise error.HookLoadError(
_('%s hook is invalid: "%s" is not defined')
% (hname, funcname))
if not callable(obj):
raise error.HookLoadError(
_('%s hook is invalid: "%s" is not callable')
% (hname, funcname))
ui.note(_("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(_('error: %s hook failed: %s\n') %
(hname, exc.args[0]))
else:
ui.warn(_('error: %s hook raised an exception: '
'%s\n') % (hname, encoding.strtolocal(str(exc))))
if throw:
raise
if not ui.tracebackflag:
ui.warn(_('(run with --traceback for stack trace)\n'))
ui.traceback()
return True, True
finally:
duration = util.timer() - starttime
ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n',
htype, funcname, duration)
if r:
if throw:
raise error.HookAbort(_('%s hook failed') % hname)
ui.warn(_('warning: %s hook failed\n') % hname)
return r, False
def _exthook(ui, repo, htype, name, cmd, args, throw):
ui.note(_("running hook %s: %s\n") % (name, cmd))
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['HG_PENDING'] = repo.root
env['HG_HOOKTYPE'] = htype
env['HG_HOOKNAME'] = name
for k, v in args.iteritems():
if callable(v):
v = v()
if isinstance(v, dict):
# make the dictionary element order stable across Python
# implementations
v = ('{' +
', '.join('%r: %r' % i for i in sorted(v.iteritems())) +
'}')
env['HG_' + k.upper()] = v
if repo:
cwd = repo.root
else:
cwd = pycompat.getcwd()
r = ui.system(cmd, environ=env, cwd=cwd, blockedtag='exthook-%s' % (name,))
duration = util.timer() - starttime
ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n',
name, cmd, duration)
if r:
desc, r = util.explainexit(r)
if throw:
raise error.HookAbort(_('%s hook %s') % (name, desc))
ui.warn(_('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, (None, None, 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('hooks', untrusted=_untrusted):
if not name.startswith('priority'):
priority = ui.configint('hooks', '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('.')[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('.')[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
def runhooks(ui, repo, htype, hooks, throw=False, **args):
args = pycompat.byteskwargs(args)
res = {}
oldstdout = -1
try:
for hname, cmd in hooks:
if oldstdout == -1 and _redirect:
try:
stdoutno = util.stdout.fileno()
stderrno = util.stderr.fileno()
# temporarily redirect stdout to stderr, if possible
if stdoutno >= 0 and stderrno >= 0:
util.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
if cmd is _fromuntrusted:
if throw:
raise error.HookAbort(
_('untrusted hook %s not executed') % hname,
hint = _("see 'hg help config.trusted'"))
ui.warn(_('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('python:'):
if cmd.count(':') >= 2:
path, cmd = cmd[7:].rsplit(':', 1)
path = util.expandpath(path)
if repo:
path = os.path.join(repo.root, path)
try:
mod = extensions.loadpath(path, 'hghook.%s' % hname)
except Exception:
ui.write(_("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
# 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.
util.stderr.flush()
finally:
if _redirect and oldstdout >= 0:
util.stdout.flush() # write hook output to stderr fd
os.dup2(oldstdout, stdoutno)
os.close(oldstdout)
return res