##// 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:

r43347:687b865b default
r46624:210f9b8d stable
Show More
mpatch.py
49 lines | 1.4 KiB | text/x-python | PythonLexer
# mpatch.py - CFFI implementation of mpatch.c
#
# Copyright 2016 Maciej Fijalkowski <fijall@gmail.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
from ..pure.mpatch import *
from ..pure.mpatch import mpatchError # silence pyflakes
from . import _mpatch
ffi = _mpatch.ffi
lib = _mpatch.lib
@ffi.def_extern()
def cffi_get_next_item(arg, pos):
all, bins = ffi.from_handle(arg)
container = ffi.new(b"struct mpatch_flist*[1]")
to_pass = ffi.new(b"char[]", str(bins[pos]))
all.append(to_pass)
r = lib.mpatch_decode(to_pass, len(to_pass) - 1, container)
if r < 0:
return ffi.NULL
return container[0]
def patches(text, bins):
lgt = len(bins)
all = []
if not lgt:
return text
arg = (all, bins)
patch = lib.mpatch_fold(ffi.new_handle(arg), lib.cffi_get_next_item, 0, lgt)
if not patch:
raise mpatchError(b"cannot decode chunk")
outlen = lib.mpatch_calcsize(len(text), patch)
if outlen < 0:
lib.mpatch_lfree(patch)
raise mpatchError(b"inconsistency detected")
buf = ffi.new(b"char[]", outlen)
if lib.mpatch_apply(buf, text, len(text), patch) < 0:
lib.mpatch_lfree(patch)
raise mpatchError(b"error applying patches")
res = ffi.buffer(buf, outlen)[:]
lib.mpatch_lfree(patch)
return res