##// END OF EJS Templates
diff: do not concatenate immutable bytes while building a/b bodies (issue6445)...
diff: do not concatenate immutable bytes while building a/b bodies (issue6445) Use bytearray instead. I don't know what's changed since Python 2, but bytes concatenation is 100x slow on Python 3. % python2.7 -m timeit -s "s = b''" "for i in range(10000): s += b'line'" 1000 loops, best of 3: 321 usec per loop % python3.9 -m timeit -s "s = b''" "for i in range(10000): s += b'line'" 5 loops, best of 5: 39.2 msec per loop Benchmark using tailwind.css (measuring the fast path, a is empty): % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 1.580 secs (user 1.560+0.000 sys 0.020+0.000) (this) time: real 1.610 secs (user 1.570+0.000 sys 0.030+0.000) % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 114.500 secs (user 114.460+0.000 sys 0.030+0.000) (this) time: real 2.180 secs (user 2.140+0.000 sys 0.040+0.000) Benchmark using random tabular text data (not the fast path): % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf % hg ci -ma % dd if=/dev/urandom bs=1k count=1000 | hexdump -v -e '16/1 "%3u," "\n"' > ttf % hg ci -mb % HGRCPATH=/dev/null python2.7 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 3.240 secs (user 3.040+0.000 sys 0.200+0.000 (this) time: real 3.230 secs (user 3.070+0.000 sys 0.160+0.000) % HGRCPATH=/dev/null python3.9 ./hg log -R /tmp/issue6445 -p --time \ --color=always --config diff.word-diff=true >/dev/null (prev) time: real 44.130 secs (user 43.850+0.000 sys 0.270+0.000) (this) time: real 4.170 secs (user 3.850+0.000 sys 0.310+0.000)

File last commit:

r46554:89a2afe3 default
r46624:210f9b8d stable
Show More
mpatch.py
136 lines | 3.3 KiB | text/x-python | PythonLexer
# mpatch.py - Python implementation of mpatch.c
#
# Copyright 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 struct
from .. import pycompat
stringio = pycompat.bytesio
class mpatchError(Exception):
"""error raised when a delta cannot be decoded
"""
# This attempts to apply a series of patches in time proportional to
# the total size of the patches, rather than patches * len(text). This
# means rather than shuffling strings around, we shuffle around
# pointers to fragments with fragment lists.
#
# When the fragment lists get too long, we collapse them. To do this
# efficiently, we do all our operations inside a buffer created by
# mmap and simply use memmove. This avoids creating a bunch of large
# temporary string buffers.
def _pull(dst, src, l): # pull l bytes from src
while l:
f = src.pop()
if f[0] > l: # do we need to split?
src.append((f[0] - l, f[1] + l))
dst.append((l, f[1]))
return
dst.append(f)
l -= f[0]
def _move(m, dest, src, count):
"""move count bytes from src to dest
The file pointer is left at the end of dest.
"""
m.seek(src)
buf = m.read(count)
m.seek(dest)
m.write(buf)
def _collect(m, buf, list):
start = buf
for l, p in reversed(list):
_move(m, buf, p, l)
buf += l
return (buf - start, start)
def patches(a, bins):
if not bins:
return a
plens = [len(x) for x in bins]
pl = sum(plens)
bl = len(a) + pl
tl = bl + bl + pl # enough for the patches and two working texts
b1, b2 = 0, bl
if not tl:
return a
m = stringio()
# load our original text
m.write(a)
frags = [(len(a), b1)]
# copy all the patches into our segment so we can memmove from them
pos = b2 + bl
m.seek(pos)
for p in bins:
m.write(p)
for plen in plens:
# if our list gets too long, execute it
if len(frags) > 128:
b2, b1 = b1, b2
frags = [_collect(m, b1, frags)]
new = []
end = pos + plen
last = 0
while pos < end:
m.seek(pos)
try:
p1, p2, l = struct.unpack(b">lll", m.read(12))
except struct.error:
raise mpatchError(b"patch cannot be decoded")
_pull(new, frags, p1 - last) # what didn't change
_pull([], frags, p2 - p1) # what got deleted
new.append((l, pos + 12)) # what got added
pos += l + 12
last = p2
frags.extend(reversed(new)) # what was left at the end
t = _collect(m, b2, frags)
m.seek(t[1])
return m.read(t[0])
def patchedsize(orig, delta):
outlen, last, bin = 0, 0, 0
binend = len(delta)
data = 12
while data <= binend:
decode = delta[bin : bin + 12]
start, end, length = struct.unpack(b">lll", decode)
if start > end:
break
bin = data + length
data = bin + 12
outlen += start - last
last = end
outlen += length
if bin != binend:
raise mpatchError(b"patch cannot be decoded")
outlen += orig - last
return outlen