##// 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:

r36401:24b48166 default
r36838:f33a87cf default
Show More
fancyopts.py
368 lines | 10.9 KiB | text/x-python | PythonLexer
# fancyopts.py - better command line parsing
#
# Copyright 2005-2009 Matt Mackall <mpm@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.
from __future__ import absolute_import
import abc
import functools
from .i18n import _
from . import (
error,
pycompat,
)
# Set of flags to not apply boolean negation logic on
nevernegate = {
# avoid --no-noninteractive
'noninteractive',
# These two flags are special because they cause hg to do one
# thing and then exit, and so aren't suitable for use in things
# like aliases anyway.
'help',
'version',
}
def _earlyoptarg(arg, shortlist, namelist):
"""Check if the given arg is a valid unabbreviated option
Returns (flag_str, has_embedded_value?, embedded_value, takes_value?)
>>> def opt(arg):
... return _earlyoptarg(arg, b'R:q', [b'cwd=', b'debugger'])
long form:
>>> opt(b'--cwd')
('--cwd', False, '', True)
>>> opt(b'--cwd=')
('--cwd', True, '', True)
>>> opt(b'--cwd=foo')
('--cwd', True, 'foo', True)
>>> opt(b'--debugger')
('--debugger', False, '', False)
>>> opt(b'--debugger=') # invalid but parsable
('--debugger', True, '', False)
short form:
>>> opt(b'-R')
('-R', False, '', True)
>>> opt(b'-Rfoo')
('-R', True, 'foo', True)
>>> opt(b'-q')
('-q', False, '', False)
>>> opt(b'-qfoo') # invalid but parsable
('-q', True, 'foo', False)
unknown or invalid:
>>> opt(b'--unknown')
('', False, '', False)
>>> opt(b'-u')
('', False, '', False)
>>> opt(b'-ufoo')
('', False, '', False)
>>> opt(b'--')
('', False, '', False)
>>> opt(b'-')
('', False, '', False)
>>> opt(b'-:')
('', False, '', False)
>>> opt(b'-:foo')
('', False, '', False)
"""
if arg.startswith('--'):
flag, eq, val = arg.partition('=')
if flag[2:] in namelist:
return flag, bool(eq), val, False
if flag[2:] + '=' in namelist:
return flag, bool(eq), val, True
elif arg.startswith('-') and arg != '-' and not arg.startswith('-:'):
flag, val = arg[:2], arg[2:]
i = shortlist.find(flag[1:])
if i >= 0:
return flag, bool(val), val, shortlist.startswith(':', i + 1)
return '', False, '', False
def earlygetopt(args, shortlist, namelist, gnu=False, keepsep=False):
"""Parse options like getopt, but ignores unknown options and abbreviated
forms
If gnu=False, this stops processing options as soon as a non/unknown-option
argument is encountered. Otherwise, option and non-option arguments may be
intermixed, and unknown-option arguments are taken as non-option.
If keepsep=True, '--' won't be removed from the list of arguments left.
This is useful for stripping early options from a full command arguments.
>>> def get(args, gnu=False, keepsep=False):
... return earlygetopt(args, b'R:q', [b'cwd=', b'debugger'],
... gnu=gnu, keepsep=keepsep)
default parsing rules for early options:
>>> get([b'x', b'--cwd', b'foo', b'-Rbar', b'-q', b'y'], gnu=True)
([('--cwd', 'foo'), ('-R', 'bar'), ('-q', '')], ['x', 'y'])
>>> get([b'x', b'--cwd=foo', b'y', b'-R', b'bar', b'--debugger'], gnu=True)
([('--cwd', 'foo'), ('-R', 'bar'), ('--debugger', '')], ['x', 'y'])
>>> get([b'--unknown', b'--cwd=foo', b'--', '--debugger'], gnu=True)
([('--cwd', 'foo')], ['--unknown', '--debugger'])
restricted parsing rules (early options must come first):
>>> get([b'--cwd', b'foo', b'-Rbar', b'x', b'-q', b'y'], gnu=False)
([('--cwd', 'foo'), ('-R', 'bar')], ['x', '-q', 'y'])
>>> get([b'--cwd=foo', b'x', b'y', b'-R', b'bar', b'--debugger'], gnu=False)
([('--cwd', 'foo')], ['x', 'y', '-R', 'bar', '--debugger'])
>>> get([b'--unknown', b'--cwd=foo', b'--', '--debugger'], gnu=False)
([], ['--unknown', '--cwd=foo', '--', '--debugger'])
stripping early options (without loosing '--'):
>>> get([b'x', b'-Rbar', b'--', '--debugger'], gnu=True, keepsep=True)[1]
['x', '--', '--debugger']
last argument:
>>> get([b'--cwd'])
([], ['--cwd'])
>>> get([b'--cwd=foo'])
([('--cwd', 'foo')], [])
>>> get([b'-R'])
([], ['-R'])
>>> get([b'-Rbar'])
([('-R', 'bar')], [])
>>> get([b'-q'])
([('-q', '')], [])
>>> get([b'-q', b'--'])
([('-q', '')], [])
'--' may be a value:
>>> get([b'-R', b'--', b'x'])
([('-R', '--')], ['x'])
>>> get([b'--cwd', b'--', b'x'])
([('--cwd', '--')], ['x'])
value passed to bool options:
>>> get([b'--debugger=foo', b'x'])
([], ['--debugger=foo', 'x'])
>>> get([b'-qfoo', b'x'])
([], ['-qfoo', 'x'])
short option isn't separated with '=':
>>> get([b'-R=bar'])
([('-R', '=bar')], [])
':' may be in shortlist, but shouldn't be taken as an option letter:
>>> get([b'-:', b'y'])
([], ['-:', 'y'])
'-' is a valid non-option argument:
>>> get([b'-', b'y'])
([], ['-', 'y'])
"""
parsedopts = []
parsedargs = []
pos = 0
while pos < len(args):
arg = args[pos]
if arg == '--':
pos += not keepsep
break
flag, hasval, val, takeval = _earlyoptarg(arg, shortlist, namelist)
if not hasval and takeval and pos + 1 >= len(args):
# missing last argument
break
if not flag or hasval and not takeval:
# non-option argument or -b/--bool=INVALID_VALUE
if gnu:
parsedargs.append(arg)
pos += 1
else:
break
elif hasval == takeval:
# -b/--bool or -s/--str=VALUE
parsedopts.append((flag, val))
pos += 1
else:
# -s/--str VALUE
parsedopts.append((flag, args[pos + 1]))
pos += 2
parsedargs.extend(args[pos:])
return parsedopts, parsedargs
class customopt(object):
"""Manage defaults and mutations for any type of opt."""
__metaclass__ = abc.ABCMeta
def __init__(self, defaultvalue):
self.defaultvalue = defaultvalue
def _isboolopt(self):
return False
@abc.abstractmethod
def newstate(self, oldstate, newparam, abort):
"""Adds newparam to oldstate and returns the new state.
On failure, abort can be called with a string error message."""
class _simpleopt(customopt):
def _isboolopt(self):
return isinstance(self.defaultvalue, (bool, type(None)))
def newstate(self, oldstate, newparam, abort):
return newparam
class _callableopt(customopt):
def __init__(self, callablefn):
self.callablefn = callablefn
super(_callableopt, self).__init__(None)
def newstate(self, oldstate, newparam, abort):
return self.callablefn(newparam)
class _listopt(customopt):
def newstate(self, oldstate, newparam, abort):
oldstate.append(newparam)
return oldstate
class _intopt(customopt):
def newstate(self, oldstate, newparam, abort):
try:
return int(newparam)
except ValueError:
abort(_('expected int'))
def _defaultopt(default):
"""Returns a default opt implementation, given a default value."""
if isinstance(default, customopt):
return default
elif callable(default):
return _callableopt(default)
elif isinstance(default, list):
return _listopt(default[:])
elif type(default) is type(1):
return _intopt(default)
else:
return _simpleopt(default)
def fancyopts(args, options, state, gnu=False, early=False, optaliases=None):
"""
read args, parse options, and store options in state
each option is a tuple of:
short option or ''
long option
default value
description
option value label(optional)
option types include:
boolean or none - option sets variable in state to true
string - parameter string is stored in state
list - parameter string is added to a list
integer - parameter strings is stored as int
function - call function with parameter
customopt - subclass of 'customopt'
optaliases is a mapping from a canonical option name to a list of
additional long options. This exists for preserving backward compatibility
of early options. If we want to use it extensively, please consider moving
the functionality to the options table (e.g separate long options by '|'.)
non-option args are returned
"""
if optaliases is None:
optaliases = {}
namelist = []
shortlist = ''
argmap = {}
defmap = {}
negations = {}
alllong = set(o[1] for o in options)
for option in options:
if len(option) == 5:
short, name, default, comment, dummy = option
else:
short, name, default, comment = option
# convert opts to getopt format
onames = [name]
onames.extend(optaliases.get(name, []))
name = name.replace('-', '_')
argmap['-' + short] = name
for n in onames:
argmap['--' + n] = name
defmap[name] = _defaultopt(default)
# copy defaults to state
state[name] = defmap[name].defaultvalue
# does it take a parameter?
if not defmap[name]._isboolopt():
if short:
short += ':'
onames = [n + '=' for n in onames]
elif name not in nevernegate:
for n in onames:
if n.startswith('no-'):
insert = n[3:]
else:
insert = 'no-' + n
# backout (as a practical example) has both --commit and
# --no-commit options, so we don't want to allow the
# negations of those flags.
if insert not in alllong:
assert ('--' + n) not in negations
negations['--' + insert] = '--' + n
namelist.append(insert)
if short:
shortlist += short
if name:
namelist.extend(onames)
# parse arguments
if early:
parse = functools.partial(earlygetopt, gnu=gnu)
elif gnu:
parse = pycompat.gnugetoptb
else:
parse = pycompat.getoptb
opts, args = parse(args, shortlist, namelist)
# transfer result to state
for opt, val in opts:
boolval = True
negation = negations.get(opt, False)
if negation:
opt = negation
boolval = False
name = argmap[opt]
obj = defmap[name]
if obj._isboolopt():
state[name] = boolval
else:
def abort(s):
raise error.Abort(
_('invalid value %r for option %s, %s') % (val, opt, s))
state[name] = defmap[name].newstate(state[name], val, abort)
# return unparsed args
return args