字符串结构定义
Lua中字符串结构体定义:
/*
** Common Header for all collectable objects (in macro form, to be
** included in other objects)
*/
#define CommonHeader GCObject *next; lu_byte tt; lu_byte marked
/*
** Header for string value; string bytes follow the end of this structure
** (aligned according to 'UTString'; see next).
*/
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;
} TString;
/*
** Ensures that address after this type is always fully aligned.
*/
typedef union UTString {
L_Umaxalign dummy; /* ensures maximum alignment for strings */
TString tsv;
} UTString;
字符串缓存
在创建字符串时,首先会从global_State的strcache缓存中查找看是否存在:
// #define STRCACHE_N 53
// #define STRCACHE_M 2
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++) {
// strcmp == 0,两个str相同
// getstr --> TString转string
if (strcmp(str, getstr(p[j])) == 0)
return p[j]; // 找到相同str
}
for (j = STRCACHE_M - 1; j > 0; j--)
p[j] = p[j - 1]; // 移动元素
// 新元素会插入到list最前端
p[0] = luaS_newlstr(L, str, strlen(str));
return p[0];
}
创建一个字符串的时候,首先会在strcache中查找,第7行根据str计算出该str在strcache的索引位置,在该strcache位置上又有一个大小为2( STRCACHE_M )的TString数组,若在这个数组中找到相同的字符串,则返回cache中字符串对应的TString;若未找到,会将p[0]位置的TString挪到p[1]位置,而p[0]位置存放luaS_newlstr
新创建的TString。
创建字符串
// #define LUAI_MAXSHORTLEN 40
/*
** 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 (l >= (MAX_SIZE - sizeof(TString))/sizeof(char))
luaM_toobig(L);
ts = luaS_createlngstrobj(L, l);
memcpy(getstr(ts), str, l * sizeof(char));
return ts;
}
}
新建一个TString时,会判断字符串长度是否大于40( LUAI_MAXSHORTLEN ),对于长度大于40的str,会直接创建TString并返回,而对于长度40以内的short string,会从global_State中的一个stringtable(strt)查找并记录:
/*
** 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);
unsigned int h = luaS_hash(str, l, g->seed);
TString **list = &g->strt.hash[lmod(h, g->strt.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;
}
}
// list中如果没找到
// resize 扩容
if (g->strt.nuse >= g->strt.size && g->strt.size <= MAX_INT/2) {
luaS_resize(L, g->strt.size * 2);
list = &g->strt.hash[lmod(h, g->strt.size)]; /* recompute with new size */
}
// 不需要扩容的情况
ts = createstrobj(L, l, LUA_TSHRSTR, h);
memcpy(getstr(ts), str, l * sizeof(char));
ts->shrlen = cast_byte(l);
ts->u.hnext = *list;
*list = ts;
g->strt.nuse++;
return ts;
}
strt的数据结构类似于HashMap,它的初始化的数组长度为128,首先根据str计算得到的hash值(0~127),找到数组对应的下标索引,取出对应下标的list链表,10 ~ 18行是对该list进行遍历,若找到则直接返回;如未找到,则继续向下走。第21行, 如果 nuse(当前strt中TSring总数) 超过容量size(初始128)值,就会进行luaS_resize
扩容操作(后续细讲),strt的容量将扩为原来的2倍。如果不需要扩容,第26行开始,会创建一个新的TString,并将其插入到当前list的头部。
扩容
/*
** resizes the string table
*/
void luaS_resize (lua_State *L, int newsize) {
int i;
stringtable *tb = &G(L)->strt;
if (newsize > tb->size) { /* grow table if needed */
luaM_reallocvector(L, tb->hash, tb->size, newsize, TString *);
for (i = tb->size; i < newsize; i++)
tb->hash[i] = NULL;
}
for (i = 0; i < tb->size; i++) { /* rehash */
TString *p = tb->hash[i];
tb->hash[i] = NULL;
while (p) { // 遍历每一个节点
TString *hnext = p->u.hnext;
unsigned int h = lmod(p->hash, newsize);
p->u.hnext = tb->hash[h];
tb->hash[h] = p;
p = hnext;
}
}
if (newsize < tb->size) { /* shrink table if needed */
/* vanishing slice should be empty */
lua_assert(tb->hash[newsize] == NULL && tb->hash[tb->size - 1] == NULL);
luaM_reallocvector(L, tb->hash, tb->size, newsize, TString *);
}
tb->size = newsize;
}
第7行,如果需要扩容,则调用luaM_reallocvector
将 tb->hash 数组扩大到newsize (2倍),12行~22行对每一个数组位置list链表中每一个TString节点的元素重新计算hash值,并将其插入到对应数组中的链表头部位置处。