Oracle 学习笔记 10 -- 约束

lua字符串内部存储分为短字符串和长字符串，可以从下面的宏看出：

#define LUA_TSTRING		4
/* Variant tags for strings */
#define LUA_TSHRSTR	(LUA_TSTRING | (0 << 4))  /* short strings */
#define LUA_TLNGSTR	(LUA_TSTRING | (1 << 4))  /* long strings */

TString类型定义为lobejct里：

/*
** Header for string value; string bytes follow the end of this structure
*/
typedef union TString {
  L_Umaxalign dummy;  /* ensures maximum alignment for strings */
  struct {
    CommonHeader;
    lu_byte extra;  /* 对于段字符串表示是否为保留字；对于长字符串用于lazy hash*/
    unsigned int hash;
    size_t len;  /* 字符串长度【lua内string不以‘\0‘结尾，所以需要显式指定大小】 */
  } tsv;
} TString;

#define LUAI_USER_ALIGNMENT_T	union { double u; void *s; long l; }

TString也是个union，因此大小一定是8的倍数，这就保证了TString大小一定是8的倍数。

字符串作为经常被用到的数据类型，会在很多场景下被创建：

比如：

LUA_API const char *lua_pushlstring (lua_State *L, const char *s, size_t len) {
  TString *ts;
  lua_lock(L);
  luaC_checkGC(L);
  ts = luaS_newlstr(L, s, len);
  setsvalue2s(L, L->top, ts);
  api_incr_top(L);
  lua_unlock(L);
  return getstr(ts);
}

/*
** 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 {
    if (l + 1 > (MAX_SIZET - sizeof(TString))/sizeof(char))
      luaM_toobig(L);
    return createstrobj(L, str, l, LUA_TLNGSTR, G(L)->seed, NULL);
  }
}

如果长度太大，就报错；否则 开始创建。

那首先看看如何内部化：

/*
** 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) {
  GCObject *o;
  global_State *g = G(L);
  unsigned int h = luaS_hash(str, l, g->seed);
  for (o = g->strt.hash[lmod(h, g->strt.size)];
       o != NULL;
       o = gch(o)->next) {
    TString *ts = rawgco2ts(o);
    if (h == ts->tsv.hash &&
        l == ts->tsv.len &&
        (memcmp(str, getstr(ts), l * sizeof(char)) == 0)) {
      if (isdead(G(L), o))  /* string is dead (but was not collected yet)? */
        changewhite(o);  /* resurrect it */
      return ts;
    }
  }
  return newshrstr(L, str, l, h);  /* not found; create a new string */
}

当然如果没找到，就要第一次分配对象：

/*
** creates a new short string, inserting it into string table
*/
static TString *newshrstr (lua_State *L, const char *str, size_t l,
                                       unsigned int h) {
  GCObject **list;  /* (pointer to) list where it will be inserted */
  stringtable *tb = &G(L)->strt;
  TString *s;
  if (tb->nuse >= cast(lu_int32, tb->size) && tb->size <= MAX_INT/2)
    luaS_resize(L, tb->size*2);  /* too crowded */
  list = &tb->hash[lmod(h, tb->size)];
  s = createstrobj(L, str, l, LUA_TSHRSTR, h, list);
  tb->nuse++;
  return s;
}

这时候才开始真正分配新string：

/*
** creates a new string object
*/
static TString *createstrobj (lua_State *L, const char *str, size_t l,
                              int tag, unsigned int h, GCObject **list) {
  TString *ts;
  size_t totalsize;  /* total size of TString object */
  totalsize = sizeof(TString) + ((l + 1) * sizeof(char));
  ts = &luaC_newobj(L, tag, totalsize, list, 0)->ts;
  ts->tsv.len = l;
  ts->tsv.hash = h;
  ts->tsv.extra = 0;
  memcpy(ts+1, str, l*sizeof(char));
  ((char *)(ts+1))[l] = ‘\0‘;  /* ending 0 */
  return ts;
}

然后再来一层 创建对象：

/*
** create a new collectable object (with given type and size) and link
** it to ‘*list‘. ‘offset‘ tells how many bytes to allocate before the
** object itself (used only by states).
*/
GCObject *luaC_newobj (lua_State *L, int tt, size_t sz, GCObject **list,
                       int offset) {
  global_State *g = G(L);
  char *raw = cast(char *, luaM_newobject(L, novariant(tt), sz));
  GCObject *o = obj2gco(raw + offset);
  if (list == NULL)
    list = &g->allgc;  /* standard list for collectable objects */
  gch(o)->marked = luaC_white(g);
  gch(o)->tt = tt;
  gch(o)->next = *list;
  *list = o;
  return o;
}

好吧，字符串的创建分析完了。

参考：云风《lua源码赏析》

分析的不对的地方请斧正，哈哈。

Oracle 学习笔记 10 -- 约束,布布扣,bubuko.com

Oracle 学习笔记 10 -- 约束

原文：http://blog.csdn.net/topyuluo/article/details/24103465