##// END OF EJS Templates
dirs: resolve fuzzer OOM situation by disallowing deep directory hierarchies...
dirs: resolve fuzzer OOM situation by disallowing deep directory hierarchies It seems like 2048 directories ought to be enough for any reasonable use of Mercurial? A previous version of this patch scanned for slashes before any allocations occurred. That approach is slower than this in the happy path, but much faster than this in the case that too many slashes are encountered. We may want to revisit it in the future using memchr() so it'll be well-optimized by the libc we're using. .. bc: Mercurial will now defend against OOMs by refusing to operate on paths with 2048 or more components. This means that _extremely_ deep path hierarchies will be rejected, but we anticipate nobody is using hierarchies this deep. Differential Revision: https://phab.mercurial-scm.org/D7411

File last commit:

r43347:687b865b default
r44057:0796e266 default
Show More
bdiff.py
99 lines | 2.4 KiB | text/x-python | PythonLexer
# bdiff.py - Python implementation of bdiff.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 difflib
import re
import struct
def splitnewlines(text):
'''like str.splitlines, but only split on newlines.'''
lines = [l + b'\n' for l in text.split(b'\n')]
if lines:
if lines[-1] == b'\n':
lines.pop()
else:
lines[-1] = lines[-1][:-1]
return lines
def _normalizeblocks(a, b, blocks):
prev = None
r = []
for curr in blocks:
if prev is None:
prev = curr
continue
shift = 0
a1, b1, l1 = prev
a1end = a1 + l1
b1end = b1 + l1
a2, b2, l2 = curr
a2end = a2 + l2
b2end = b2 + l2
if a1end == a2:
while (
a1end + shift < a2end and a[a1end + shift] == b[b1end + shift]
):
shift += 1
elif b1end == b2:
while (
b1end + shift < b2end and a[a1end + shift] == b[b1end + shift]
):
shift += 1
r.append((a1, b1, l1 + shift))
prev = a2 + shift, b2 + shift, l2 - shift
r.append(prev)
return r
def bdiff(a, b):
a = bytes(a).splitlines(True)
b = bytes(b).splitlines(True)
if not a:
s = b"".join(b)
return s and (struct.pack(b">lll", 0, 0, len(s)) + s)
bin = []
p = [0]
for i in a:
p.append(p[-1] + len(i))
d = difflib.SequenceMatcher(None, a, b).get_matching_blocks()
d = _normalizeblocks(a, b, d)
la = 0
lb = 0
for am, bm, size in d:
s = b"".join(b[lb:bm])
if am > la or s:
bin.append(struct.pack(b">lll", p[la], p[am], len(s)) + s)
la = am + size
lb = bm + size
return b"".join(bin)
def blocks(a, b):
an = splitnewlines(a)
bn = splitnewlines(b)
d = difflib.SequenceMatcher(None, an, bn).get_matching_blocks()
d = _normalizeblocks(an, bn, d)
return [(i, i + n, j, j + n) for (i, j, n) in d]
def fixws(text, allws):
if allws:
text = re.sub(b'[ \t\r]+', b'', text)
else:
text = re.sub(b'[ \t\r]+', b' ', text)
text = text.replace(b' \n', b'\n')
return text