##// END OF EJS Templates
bdiff: don't check border condition in loop...
bdiff: don't check border condition in loop `plast = a + len - 1`. So, this "for" loop iterates from "a" to "plast", inclusive. So, `p == plast` can only be true on the final iteration of the loop. So checking for it on every loop iteration is wasteful. This patch simply decreases the upper bound of the loop by 1 and adds an explicit check after iteration for the `p == plast` case. We can't simply add 1 to the initial value for "i" because that doesn't do the correct thing on empty input strings. `perfbdiff -m 3041e4d59df2` on the Firefox repo becomes significantly faster: ! wall 0.072763 comb 0.070000 user 0.070000 sys 0.000000 (best of 100) ! wall 0.053221 comb 0.060000 user 0.060000 sys 0.000000 (best of 100) For the curious, this code has its origins in 8b067bde6679, which is the changeset that introduced bdiff.c in 2005. Also, GNU diffutils is able to perform a similar line-based diff in under 20ms. So there's likely more perf wins to be found in this code. One of them is the hashing algorithm. But it looks like mpm spent some time testing hash collisions in d0c48891dd4a. I'd like to do the same before switching away from lyhash, just to be on the safe side.

File last commit:

r30303:ad40d307 default
r30308:d500ddae default
Show More
pycompat.py
210 lines | 5.5 KiB | text/x-python | PythonLexer
# pycompat.py - portability shim for python 3
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Mercurial portability shim for python 3.
This contains aliases to hide python version-specific details from the core.
"""
from __future__ import absolute_import
import os
import sys
ispy3 = (sys.version_info[0] >= 3)
if not ispy3:
import cPickle as pickle
import cStringIO as io
import httplib
import Queue as _queue
import SocketServer as socketserver
import urlparse
import xmlrpclib
else:
import http.client as httplib
import io
import pickle
import queue as _queue
import socketserver
import urllib.parse as urlparse
import xmlrpc.client as xmlrpclib
if ispy3:
import builtins
import functools
fsencode = os.fsencode
fsdecode = os.fsdecode
# A bytes version of os.name.
osname = os.name.encode('ascii')
ospathsep = os.pathsep.encode('ascii')
ossep = os.sep.encode('ascii')
def sysstr(s):
"""Return a keyword str to be passed to Python functions such as
getattr() and str.encode()
This never raises UnicodeDecodeError. Non-ascii characters are
considered invalid and mapped to arbitrary but unique code points
such that 'sysstr(a) != sysstr(b)' for all 'a != b'.
"""
if isinstance(s, builtins.str):
return s
return s.decode(u'latin-1')
def _wrapattrfunc(f):
@functools.wraps(f)
def w(object, name, *args):
return f(object, sysstr(name), *args)
return w
# these wrappers are automagically imported by hgloader
delattr = _wrapattrfunc(builtins.delattr)
getattr = _wrapattrfunc(builtins.getattr)
hasattr = _wrapattrfunc(builtins.hasattr)
setattr = _wrapattrfunc(builtins.setattr)
xrange = builtins.range
else:
def sysstr(s):
return s
# Partial backport from os.py in Python 3, which only accepts bytes.
# In Python 2, our paths should only ever be bytes, a unicode path
# indicates a bug.
def fsencode(filename):
if isinstance(filename, str):
return filename
else:
raise TypeError(
"expect str, not %s" % type(filename).__name__)
# In Python 2, fsdecode() has a very chance to receive bytes. So it's
# better not to touch Python 2 part as it's already working fine.
def fsdecode(filename):
return filename
osname = os.name
ospathsep = os.pathsep
ossep = os.sep
stringio = io.StringIO
empty = _queue.Empty
queue = _queue.Queue
class _pycompatstub(object):
def __init__(self):
self._aliases = {}
def _registeraliases(self, origin, items):
"""Add items that will be populated at the first access"""
items = map(sysstr, items)
self._aliases.update(
(item.replace(sysstr('_'), sysstr('')).lower(), (origin, item))
for item in items)
def __getattr__(self, name):
try:
origin, item = self._aliases[name]
except KeyError:
raise AttributeError(name)
self.__dict__[name] = obj = getattr(origin, item)
return obj
httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()
if not ispy3:
import BaseHTTPServer
import CGIHTTPServer
import SimpleHTTPServer
import urllib2
import urllib
urlreq._registeraliases(urllib, (
"addclosehook",
"addinfourl",
"ftpwrapper",
"pathname2url",
"quote",
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"unquote",
"url2pathname",
"urlencode",
))
urlreq._registeraliases(urllib2, (
"AbstractHTTPHandler",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPHandler",
"HTTPPasswordMgrWithDefaultRealm",
"HTTPSHandler",
"install_opener",
"ProxyHandler",
"Request",
"urlopen",
))
urlerr._registeraliases(urllib2, (
"HTTPError",
"URLError",
))
httpserver._registeraliases(BaseHTTPServer, (
"HTTPServer",
"BaseHTTPRequestHandler",
))
httpserver._registeraliases(SimpleHTTPServer, (
"SimpleHTTPRequestHandler",
))
httpserver._registeraliases(CGIHTTPServer, (
"CGIHTTPRequestHandler",
))
else:
import urllib.request
urlreq._registeraliases(urllib.request, (
"AbstractHTTPHandler",
"addclosehook",
"addinfourl",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"ftpwrapper",
"HTTPHandler",
"HTTPSHandler",
"install_opener",
"pathname2url",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPPasswordMgrWithDefaultRealm",
"ProxyHandler",
"quote",
"Request",
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"unquote",
"url2pathname",
"urlopen",
))
import urllib.error
urlerr._registeraliases(urllib.error, (
"HTTPError",
"URLError",
))
import http.server
httpserver._registeraliases(http.server, (
"HTTPServer",
"BaseHTTPRequestHandler",
"SimpleHTTPRequestHandler",
"CGIHTTPRequestHandler",
))