##// END OF EJS Templates
bdiff: improve worst case behavior by 100x....
bdiff: improve worst case behavior by 100x. on 5.8MB (244.000 lines) text file with similar lines, hash before this change made diff against empty file take 75 seconds. this change improves performance to 0.6 seconds. result is that clone of smallish repo (137MB) with some files like this takes 1 minute instead of 10 minutes. common case of diff is 10% slower now, probably because of worse cache locality. but diff does not affect overall performance in common case (less than 1% of runtime is in diff when it is working ok), so this tradeoff looks good.

File last commit:

r2470:fe168927 default
r2577:fa76c5d6 default
Show More
changegroup.py
43 lines | 1.1 KiB | text/x-python | PythonLexer
"""
changegroup.py - Mercurial changegroup manipulation functions
Copyright 2006 Matt Mackall <mpm@selenic.com>
This software may be used and distributed according to the terms
of the GNU General Public License, incorporated herein by reference.
"""
from i18n import gettext as _
from demandload import *
demandload(globals(), "struct util")
def getchunk(source):
"""get a chunk from a changegroup"""
d = source.read(4)
if not d:
return ""
l = struct.unpack(">l", d)[0]
if l <= 4:
return ""
d = source.read(l - 4)
if len(d) < l - 4:
raise util.Abort(_("premature EOF reading chunk"
" (got %d bytes, expected %d)")
% (len(d), l - 4))
return d
def chunkiter(source):
"""iterate through the chunks in source"""
while 1:
c = getchunk(source)
if not c:
break
yield c
def genchunk(data):
"""build a changegroup chunk"""
header = struct.pack(">l", len(data)+ 4)
return "%s%s" % (header, data)
def closechunk():
return struct.pack(">l", 0)