lua字串通過操作演演算法和記憶體管理,有以下優點:
問題:
typedef struct TString {
CommonHeader;
lu_byte extra; /* reserved words for short strings; "has hash" for longs */
lu_byte shrlen; /* length for short strings */
unsigned int hash;
union {
size_t lnglen; /* length for long strings */
struct TString *hnext; /* linked list for hash table */
} u;
char contents[1];
} TString;
typedef struct stringtable {
TString **hash;
int nuse; /* number of elements */
int size;
} stringtable;
/*
** Create or reuse a zero-terminated string, first checking in the
** cache (using the string address as a key). The cache can contain
** only zero-terminated strings, so it is safe to use 'strcmp' to
** check hits.
*/
TString *luaS_new (lua_State *L, const char *str) {
unsigned int i = point2uint(str) % STRCACHE_N; /* hash */
int j;
TString **p = G(L)->strcache[i];
for (j = 0; j < STRCACHE_M; j++) {
if (strcmp(str, getstr(p[j])) == 0) /* hit? */
return p[j]; /* that is it */
}
/* normal route */
for (j = STRCACHE_M - 1; j > 0; j--)
p[j] = p[j - 1]; /* move out last element */
/* new element is first in the list */
p[0] = luaS_newlstr(L, str, strlen(str));
return p[0];
}
/*
** new string (with explicit length)
*/
TString *luaS_newlstr (lua_State *L, const char *str, size_t l) {
if (l <= LUAI_MAXSHORTLEN) /* short string? */
return internshrstr(L, str, l);
else {
TString *ts;
if (unlikely(l >= (MAX_SIZE - sizeof(TString))/sizeof(char)))
luaM_toobig(L);
ts = luaS_createlngstrobj(L, l);
memcpy(getstr(ts), str, l * sizeof(char));
return ts;
}
}
/*
** Checks whether short string exists and reuses it or creates a new one.
*/
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);
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) {
if (l == ts->shrlen && (memcmp(str, getstr(ts), l * sizeof(char)) == 0)) {
/* found! */
if (isdead(g, ts)) /* dead (but not collected yet)? */
changewhite(ts); /* resurrect it */
return ts;
}
}
/* else must create a new string */
if (tb->nuse >= tb->size) { /* need to grow string table? */
growstrtab(L, tb);
list = &tb->hash[lmod(h, tb->size)]; /* rehash with new size */
}
ts = createstrobj(L, l, LUA_VSHRSTR, h);
memcpy(getstr(ts), str, l * sizeof(char));
ts->shrlen = cast_byte(l);
ts->u.hnext = *list;
*list = ts;
tb->nuse++;
return ts;
}
/*
** creates a new string object
*/
static TString *createstrobj (lua_State *L, size_t l, int tag, unsigned int h) {
TString *ts;
GCObject *o;
size_t totalsize; /* total size of TString object */
totalsize = sizelstring(l);
o = luaC_newobj(L, tag, totalsize);
ts = gco2ts(o);
ts->hash = h;
ts->extra = 0;
getstr(ts)[l] = '\0'; /* ending 0 */
return ts;
}
#define offsetof(s,m) ((size_t)&(((s*)0)->m))
#define sizelstring(l) (offsetof(TString, contents) + ((l) + 1) * sizeof(char))
static void growstrtab (lua_State *L, stringtable *tb) {
if (unlikely(tb->nuse == MAX_INT)) { /* too many strings? */
luaC_fullgc(L, 1); /* try to free some... */
if (tb->nuse == MAX_INT) /* still too many? */
luaM_error(L); /* cannot even create a message... */
}
if (tb->size <= MAXSTRTB / 2) /* can grow string table? */
luaS_resize(L, tb->size * 2);
}
/*
** Resize the string table. If allocation fails, keep the current size.
** (This can degrade performance, but any non-zero size should work
** correctly.)
*/
void luaS_resize (lua_State *L, int nsize) {
stringtable *tb = &G(L)->strt;
int osize = tb->size;
TString **newvect;
if (nsize < osize) /* shrinking table? */
tablerehash(tb->hash, osize, nsize); /* depopulate shrinking part */
newvect = luaM_reallocvector(L, tb->hash, osize, nsize, TString*);
if (unlikely(newvect == NULL)) { /* reallocation failed? */
if (nsize < osize) /* was it shrinking table? */
tablerehash(tb->hash, nsize, osize); /* restore to original size */
/* leave table as it was */
}
else { /* allocation succeeded */
tb->hash = newvect;
tb->size = nsize;
if (nsize > osize)
tablerehash(newvect, osize, nsize); /* rehash for new size */
}
}
static void tablerehash (TString **vect, int osize, int nsize) {
int i;
for (i = osize; i < nsize; i++) /* clear new elements */
vect[i] = NULL;
for (i = 0; i < osize; i++) { /* rehash old part of the array */
TString *p = vect[i];
vect[i] = NULL;
while (p) { /* for each string in the list */
TString *hnext = p->u.hnext; /* save next */
unsigned int h = lmod(p->hash, nsize); /* new position */
p->u.hnext = vect[h]; /* chain it into array */
vect[h] = p;
p = hnext;
}
}
}
unsigned int luaS_hash (const char *str, size_t l, unsigned int seed,
size_t step) {
unsigned int h = seed ^ cast_uint(l);
for (; l >= step; l -= step)
h ^= ((h<<5) + (h>>2) + cast_byte(str[l - 1]));
return h;
}
/*
** 'module' operation for hashing (size is always a power of 2)
*/
#define lmod(s,size) \
(check_exp((size&(size-1))==0, (cast_int((s) & ((size)-1)))))
#define firsttry(g,block,os,ns) ((*g->frealloc)(g->ud, block, os, ns))
/*
** Generic allocation routine.
** If allocation fails while shrinking a block, do not try again; the
** GC shrinks some blocks and it is not reentrant.
*/
void *luaM_realloc_ (lua_State *L, void *block, size_t osize, size_t nsize) {
void *newblock;
global_State *g = G(L);
lua_assert((osize == 0) == (block == NULL));
newblock = firsttry(g, block, osize, nsize);
if (unlikely(newblock == NULL && nsize > 0)) {
if (nsize > osize) /* not shrinking a block? */
newblock = tryagain(L, block, osize, nsize);
if (newblock == NULL) /* still no memory? */
return NULL; /* do not update 'GCdebt' */
}
lua_assert((nsize == 0) == (newblock == NULL));
g->GCdebt = (g->GCdebt + nsize) - osize;
return newblock;
}
#define luaM_reallocvector(L, v,oldn,n,t) \
(cast(t *, luaM_realloc_(L, v, cast_sizet(oldn) * sizeof(t), \
cast_sizet(n) * sizeof(t))))