Mercurial > hg
view mercurial/thirdparty/xdiff/xutils.c @ 36822:882657a9f768
xdiff: replace {unsigned ,}long with {u,}int64_t
MSVC treats "long" as 4-byte. That could cause overflows since the xdiff
code uses "long" in places where "size_t" or "ssize_t" should be used.
Let's use explicit 8 byte integers to avoid
FWIW git avoids that overflow by limiting diff size to 1GB [1]. After
examining the code, I think the remaining risk (the use of "int") is low
since "int" is only used for return values and hash table size. Although a
wrong hash table size would not affect the correctness of the code, but that
could make the code extremely slow. The next patch will change hash table
size to 8-byte integer so the 1GB limit is unlikely needed.
This patch was done by using `sed`.
[1]: https://github.com/git/git/commit/dcd1742e56ebb944c4ff62346da4548e1e3be67
Differential Revision: https://phab.mercurial-scm.org/D2762
author | Jun Wu <quark@fb.com> |
---|---|
date | Fri, 09 Mar 2018 14:24:27 -0800 |
parents | 90f8fe72446c |
children | 49fe6249937a |
line wrap: on
line source
/* * LibXDiff by Davide Libenzi ( File Differential Library ) * Copyright (C) 2003 Davide Libenzi * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with this library; if not, see * <http://www.gnu.org/licenses/>. * * Davide Libenzi <davidel@xmailserver.org> * */ #include <limits.h> #include <assert.h> #include "xinclude.h" int64_t xdl_bogosqrt(int64_t n) { int64_t i; /* * Classical integer square root approximation using shifts. */ for (i = 1; n > 0; n >>= 2) i <<= 1; return i; } void *xdl_mmfile_first(mmfile_t *mmf, int64_t *size) { *size = mmf->size; return mmf->ptr; } int64_t xdl_mmfile_size(mmfile_t *mmf) { return mmf->size; } int xdl_cha_init(chastore_t *cha, int64_t isize, int64_t icount) { cha->head = cha->tail = NULL; cha->isize = isize; cha->nsize = icount * isize; cha->ancur = cha->sncur = NULL; cha->scurr = 0; return 0; } void xdl_cha_free(chastore_t *cha) { chanode_t *cur, *tmp; for (cur = cha->head; (tmp = cur) != NULL;) { cur = cur->next; xdl_free(tmp); } } void *xdl_cha_alloc(chastore_t *cha) { chanode_t *ancur; void *data; if (!(ancur = cha->ancur) || ancur->icurr == cha->nsize) { if (!(ancur = (chanode_t *) xdl_malloc(sizeof(chanode_t) + cha->nsize))) { return NULL; } ancur->icurr = 0; ancur->next = NULL; if (cha->tail) cha->tail->next = ancur; if (!cha->head) cha->head = ancur; cha->tail = ancur; cha->ancur = ancur; } data = (char *) ancur + sizeof(chanode_t) + ancur->icurr; ancur->icurr += cha->isize; return data; } int64_t xdl_guess_lines(mmfile_t *mf, int64_t sample) { int64_t nl = 0, size, tsize = 0; char const *data, *cur, *top; if ((cur = data = xdl_mmfile_first(mf, &size)) != NULL) { for (top = data + size; nl < sample && cur < top; ) { nl++; if (!(cur = memchr(cur, '\n', top - cur))) cur = top; else cur++; } tsize += (long) (cur - data); } if (nl && tsize) nl = xdl_mmfile_size(mf) / (tsize / nl); return nl + 1; } int xdl_recmatch(const char *l1, int64_t s1, const char *l2, int64_t s2, int64_t flags) { if (s1 == s2 && !memcmp(l1, l2, s1)) return 1; return 0; } uint64_t xdl_hash_record(char const **data, char const *top, int64_t flags) { uint64_t ha = 5381; char const *ptr = *data; for (; ptr < top && *ptr != '\n'; ptr++) { ha += (ha << 5); ha ^= (unsigned long) *ptr; } *data = ptr < top ? ptr + 1: ptr; return ha; } unsigned int xdl_hashbits(unsigned int size) { unsigned int val = 1, bits = 0; for (; val < size && bits < CHAR_BIT * sizeof(unsigned int); val <<= 1, bits++); return bits ? bits: 1; }