nik/lush
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Hash always use all characters in a long string

Browse Source 
Hashes for long strings are computed only when they are used as keys
in a table, not a too common case. And, in that case, it is to easy to
force collisions changing only the characters which are not part of the
hash.
This commit is contained in:
Roberto Ierusalimschy
2020-10-12 10:02:37 -03:00
parent c23cc86c54
commit 9a89fb1c9d
4 changed files with 6 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
lstring.c
View File

@@ -22,16 +22,6 @@
#include "lstring.h"
/*
** Lua will use at most ~(2^LUAI_HASHLIMIT) bytes from a long string to
** compute its hash
*/
#if !defined(LUAI_HASHLIMIT)
#define LUAI_HASHLIMIT 5
#endif
/*
** Maximum size for string table.
*/
@@ -50,10 +40,9 @@ int luaS_eqlngstr (TString *a, TString *b) {
}
unsigned int luaS_hash (const char *str, size_t l, unsigned int seed,
size_t step) {
unsigned int luaS_hash (const char *str, size_t l, unsigned int seed) {
unsigned int h = seed ^ cast_uint(l);
for (; l >= step; l -= step)
for (; l > 0; l--)
h ^= ((h<<5) + (h>>2) + cast_byte(str[l - 1]));
return h;
}
@@ -63,8 +52,7 @@ unsigned int luaS_hashlongstr (TString *ts) {
lua_assert(ts->tt == LUA_VLNGSTR);
if (ts->extra == 0) { /* no hash? */
size_t len = ts->u.lnglen;
size_t step = (len >> LUAI_HASHLIMIT) + 1;
ts->hash = luaS_hash(getstr(ts), len, ts->hash, step);
ts->hash = luaS_hash(getstr(ts), len, ts->hash);
ts->extra = 1; /* now it has its hash */
}
return ts->hash;
@@ -201,7 +189,7 @@ static TString *internshrstr (lua_State *L, const char *str, size_t l) {
TString *ts;
global_State *g = G(L);
stringtable *tb = &g->strt;
unsigned int h = luaS_hash(str, l, g->seed, 1);
unsigned int h = luaS_hash(str, l, g->seed);
TString **list = &tb->hash[lmod(h, tb->size)];
lua_assert(str != NULL); /* otherwise 'memcmp'/'memcpy' are undefined */
for (ts = *list; ts != NULL; ts = ts->u.hnext) {