github链接 lua515子域
/*
** $Id: ltable.c,v 2.32.1.2 2007/12/28 15:32:23 roberto Exp $
** Lua tables (hash)
** See Copyright Notice in lua.h
*/
/*
** Implementation of tables (aka(又名) arrays, objects, or hash tables).
** Tables keep its elements in two parts: an array part and a hash part.
** Non-negative integer keys are all candidates(考虑) to be kept in the array
** part. The actual size of the array is the largest `n' such that at
** least half the slots between 0 and n are in use.
** Hash uses a mix of chained scatter(分散) table with Brent's variation.
** A main invariant(不变的) of these tables is that, if an element is not
** in its main position (i.e. the `original' position that its hash gives
** to it), then the colliding(碰撞的) element is in its own main position.
** Hence even when the load factor reaches 100%, performance remains good.
*/
/*
**
/* 和lstring的闭散列不同,这里采用的是开散列算法 https://blog.csdn.net/Boring_Wednesday/article/details/80316884
** 结合gc流程和table'insert的流程来看
**
** tbl[k]=nil,若k仅被此表引用,则此k会被gc回收,for中进行tbl[k]=nil的操作,并不会修改影响表遍历的完整性
** next函数有对此进行了专门的处理(deadkey)
**
** tbl[k]=nil后,node经过gc后被标记为deadkey,在此之前resize之前,此node是个"正常的node",可以被复用
** gc被标记为deadkey后,进入了dead流程,是一个deadkey了。没作用了
*/
#include <math.h>
#include <string.h>
#define ltable_c
#define LUA_CORE
#include "lua.h"
#include "ldebug.h"
#include "ldo.h"
#include "lgc.h"
#include "lmem.h"
#include "lobject.h"
#include "lstate.h"
#include "ltable.h"
/*
** max size of array part is 2^MAXBITS
*/
#if LUAI_BITSINT > 26
#define MAXBITS 26
#else
#define MAXBITS (LUAI_BITSINT-2)
#endif
#define MAXASIZE (1 << MAXBITS)
#define hashpow2(t,n) (gnode(t, lmod((n), sizenode(t))))
#define hashstr(t,str) hashpow2(t, (str)->tsv.hash)
#define hashboolean(t,p) hashpow2(t, p)
/*
** for some types, it is better to avoid modulus by power of 2, as
** they tend to have many 2 factors.
*/
#define hashmod(t,n) (gnode(t, ((n) % ((sizenode(t)-1)|1))))
#define hashpointer(t,p) hashmod(t, IntPoint(p))
/*
** number of ints inside a lua_Number
*/
#define numints cast_int(sizeof(lua_Number)/sizeof(int))
#define dummynode (&dummynode_)
static const Node dummynode_ = {
{{NULL}, LUA_TNIL}, /* value */
{{{NULL}, LUA_TNIL, NULL}} /* key */
};
/*
** hash for lua_Numbers
*/
static Node *hashnum (const Table *t, lua_Number n) {
unsigned int a[numints];
int i;
if (luai_numeq(n, 0)) /* avoid problems with -0 */
return gnode(t, 0);
memcpy(a, &n, sizeof(a));
for (i = 1; i < numints; i++) a[0] += a[i];
return hashmod(t, a[0]);
}
/*
** returns the `main' position of an element in a table (that is, the index
** of its hash value)
*/
static Node *mainposition (const Table *t, const TValue *key) {
switch (ttype(key)) {
case LUA_TNUMBER:
return hashnum(t, nvalue(key));
case LUA_TSTRING:
return hashstr(t, rawtsvalue(key));
case LUA_TBOOLEAN:
return hashboolean(t, bvalue(key));
case LUA_TLIGHTUSERDATA:
return hashpointer(t, pvalue(key));
default:
return hashpointer(t, gcvalue(key));
}
}
/*
** returns the index for `key' if `key' is an appropriate(合适的) key to live in
** the array part of the table, -1 otherwise.
*/
static int arrayindex (const TValue *key) {
if (ttisnumber(key)) {
lua_Number n = nvalue(key);
int k;
lua_number2int(k, n);
if (luai_numeq(cast_num(k), n))
return k;
}
return -1; /* `key' did not match some condition */
}
/*
** returns the index of a `key' for table traversals(遍历). First goes all
** elements in the array part, then elements in the hash part. The
** beginning of a traversal is signalled by -1.
*/
static int findindex (lua_State *L, Table *t, StkId key) {
int i;
if (ttisnil(key)) { /* 下面i++后,开始从数组的第一个slot开始匹配 */
return -1; /* first iteration */
}
i = arrayindex(key);
if (0 < i && i <= t->sizearray) /* is `key' inside array part? */
return i-1; /* yes; that's the index (corrected to C) */
else {
Node *n = mainposition(t, key);
do { /* check whether `key' is somewhere in the chain */
/* key may be dead already, but it is ok to use it in `next'
**
** for k,v pair(tbl) do
** tbl[k] = nil
** 可能的gc导致出现DEADKEY
** end
**
** LUA_TDEADKEY的key对应的mem可能被释放了,所以这里可能gcvalue(gkey(n) == gcvalue(key)) 这个判断不准确,要使其准确的前提是mem不释放,
** 上面for循环中k保持了对其引用所以不会导致mem释放,其它环境下调用tbl.next(deadKey)因为不确定mem是否被释放所以结果是未定义的,我的妈妈咪耶,搞明白了吗
**
** 不管是lua还是C调用,tbl[k]=nil导致deadkey,但k的存在使key对应的gc内存不被释放(k还引用着它呢)
** C中调用tbl[k]=nil导致死键后,top-=2,key也被抛弃,如果stack还有其它的slot引用key则key对应的内存
** 不会被释放,也可以再次利用key调用next,如果statck中没有其它的slot引用该key,则对应的内存可能会被释放
** 但key也不存在了,故而gcvalue(gkey(n)==gcvalue(key))中的key也不存在了,该判断就不可能成立了
*/
if (luaO_rawequalObj(key2tval(n), key) ||
/* 支持lua中的在next中tbl[k]=nil的操作后,k->k.next */
(ttype(gkey(n)) == LUA_TDEADKEY && iscollectable(key) && gcvalue(gkey(n)) == gcvalue(key))) {
i = cast_int(n - gnode(t, 0)); /* key index in hash table */
/* hash elements are numbered after array ones */
return i + t->sizearray;
}
else n = gnext(n);
} while (n);
luaG_runerror(L, "invalid key to " LUA_QL("next")); /* key not found */
return 0; /* to avoid warnings */
}
}
int luaH_next (lua_State *L, Table *t, StkId key) {
int i = findindex(L, t, key); /* find original element */
/* 这里先来个i++,配合着上面的findindex,就形成了如果传入的是nil,则从数组第一个slot开始查找
** 如果传入的是前面找到的oldKey,则在oldKey的下一个slot开始匹配,符合next函数定义
*/
for (i++; i < t->sizearray; i++) { /* try first array part */
if (!ttisnil(&t->array[i])) { /* a non-nil value? */
setnvalue(key, cast_num(i+1)); /* c下表从0开始,lua从1开始,所以这里要补1 */
setobj2s(L, key+1, &t->array[i]);
return 1;
}
}
for (i -= t->sizearray; i < sizenode(t); i++) { /* then hash part */
if (!ttisnil(gval(gnode(t, i)))) { /* a non-nil value? */
setobj2s(L, key, key2tval(gnode(t, i)));
setobj2s(L, key+1, gval(gnode(t, i)));
return 1;
}
}
return 0; /* no more elements */
}
/*
** {=============================================================
** Rehash
** ==============================================================
*/
static int computesizes (int nums[], int *narray) {
int i;
int twotoi; /* 2^i */
int a = 0; /* number of elements smaller than 2^i */
int na = 0; /* number of elements to go to array part */
int n = 0; /* optimal size for array part */
for (i = 0, twotoi = 1; twotoi/2 < *narray; i++, twotoi *= 2) {
if (nums[i] > 0) {
a += nums[i]; /* 加上当前区间 */
/* 截至到当前区间.left,利用率超过了1/2,存个档 */
if (a > twotoi/2) { /* more than half elements present? */
n = twotoi; /* optimal size (till now) */
na = a; /* all elements smaller than n will go to array part */
}
}
/* 所有已存在的元素都已统计完毕,无需再往后面统计了(nums[i+]及后面都是0了),这里提前跳出 */
if (a == *narray)
break; /* all elements already counted */
}
*narray = n;
lua_assert(*narray/2 <= na && na <= *narray);
return na;
}
static int countint (const TValue *key, int *nums) {
int k = arrayindex(key);
if (0 < k && k <= MAXASIZE) { /* is `key' an appropriate array index? */
nums[ceillog2(k)]++; /* count as such */
return 1;
}
else
return 0;
}
static int numusearray (const Table *t, int *nums) {
int lg;
int ttlg; /* 2^lg */
int ause = 0; /* summation of `nums' */
int i = 1; /* count to traverse all array keys */
for (lg=0, ttlg=1; lg<=MAXBITS; lg++, ttlg*=2) { /* for each slice */
int lc = 0; /* counter */
int lim = ttlg;
if (lim > t->sizearray) {
lim = t->sizearray; /* adjust upper limit */
if (i > lim) /* 下面的for循环中i提前++了。所以这里要对其评估 */
break; /* no more elements to count */
}
/* count elements in range (2^(lg-1), 2^lg] */
for (; i <= lim; i++) {
if (!ttisnil(&t->array[i-1])) /* 这里要-1,因为C的下标从0开始 */
lc++;
}
nums[lg] += lc; /* 更新区间内used的数量 */
ause += lc; /* 更新总的used数量 */
}
return ause; /* 返回 array中used的总数 */
}
/* 更新node中int的key到nums和pnasize中,返回node中key的总数 */
static int numusehash (const Table *t, int *nums, int *pnasize) {
int totaluse = 0; /* total number of elements */
int ause = 0; /* summation of `nums' */
int i = sizenode(t);
while (i--) {
Node *n = &t->node[i];
if (!ttisnil(gval(n))) { /* 这里没有判断gkey而是gval!!! */
ause += countint(key2tval(n), nums);
totaluse++;
}
}
*pnasize += ause;
return totaluse;
}
static void setarrayvector (lua_State *L, Table *t, int size) {
int i;
luaM_reallocvector(L, t->array, t->sizearray, size, TValue);
for (i=t->sizearray; i<size; i++) /* 多出来的数组部分填nil */
setnilvalue(&t->array[i]);
t->sizearray = size;
}
/* 按照新的node区大小size,申请新内存且将其全部set-nil */
static void setnodevector (lua_State *L, Table *t, int size) {
int lsize;
if (size == 0) { /* no elements to hash part? */
t->node = cast(Node *, dummynode); /* use common `dummynode' */
lsize = 0;
}
else {
int i;
lsize = ceillog2(size);
if (lsize > MAXBITS)
luaG_runerror(L, "table overflow");
size = twoto(lsize);
t->node = luaM_newvector(L, size, Node);
for (i=0; i<size; i++) {
Node *n = gnode(t, i);
gnext(n) = NULL;
setnilvalue(gkey(n));
setnilvalue(gval(n));
}
}
t->lsizenode = cast_byte(lsize);
t->lastfree = gnode(t, size); /* all positions are free */
}
/* nasize:调整后的数组大小
** nhsize:调整后node部分的元素个数
*/
static void resize (lua_State *L, Table *t, int nasize, int nhsize) {
int i;
int oldasize = t->sizearray;
int oldhsize = t->lsizenode;
Node *nold = t->node; /* save old hash ... */
if (nasize > oldasize) /* array part must grow? */
setarrayvector(L, t, nasize);
/* create new hash part with appropriate size
** 准备好全新的node,以便下面调整array时,接收array中溢出的slot
*/
setnodevector(L, t, nhsize);
if (nasize < oldasize) { /* array part must shrink? */
t->sizearray = nasize;
/* re-insert elements from vanishing slice */
for (i=nasize; i<oldasize; i++) { /* new的array-size下将数组溢出的slot移动到node区域去 */
if (!ttisnil(&t->array[i]))
setobjt2t(L, luaH_setnum(L, t, i+1), &t->array[i]);
}
/* shrink array */
luaM_reallocvector(L, t->array, oldasize, nasize, TValue);
}
/* re-insert elements from hash part */
for (i = twoto(oldhsize) - 1; i >= 0; i--) {
Node *old = nold+i;
if (!ttisnil(gval(old))) /* 这里没拿gkey判断!! */
setobjt2t(L, luaH_set(L, t, key2tval(old)), gval(old));
}
if (nold != dummynode)
luaM_freearray(L, nold, twoto(oldhsize), Node); /* free old array */
}
/* 供lvm调用,一次到位申请对应的array区域的内存 */
void luaH_resizearray (lua_State *L, Table *t, int nasize) {
int nsize = (t->node == dummynode) ? 0 : sizenode(t);
resize(L, t, nasize, nsize);
}
/* 尝试插入新的key(ek时发现空间不足,从而rehash) */
static void rehash (lua_State *L, Table *t, const TValue *ek) {
int nasize, na;
int nums[MAXBITS+1]; /* nums[i] = number of keys between 2^(i-1) and 2^i */
int i;
int totaluse; /* 所有元素总和 */
for (i=0; i<=MAXBITS; i++) nums[i] = 0; /* reset counts */
nasize = numusearray(t, nums); /* count keys in array part */
totaluse = nasize; /* all those keys are integer keys */
totaluse += numusehash(t, nums, &nasize); /* count keys in hash part */
/* count extra key */
nasize += countint(ek, nums);
totaluse++;
/* compute new size for array part */
na = computesizes(nums, &nasize); /* 计算下最优解下的nasize,以及即将落在array中的数量(na) */
/* resize the table to new computed sizes */
resize(L, t, nasize, totaluse - na);
}
/*
** }=============================================================
*/
Table *luaH_new (lua_State *L, int narray, int nhash) {
Table *t = luaM_new(L, Table);
luaC_link(L, obj2gco(t), LUA_TTABLE);
t->metatable = NULL;
t->flags = cast_byte(~0); /* 新表,tag'method都不存在 */
/* temporary values (kept only if some malloc fails) */
t->array = NULL;
t->sizearray = 0;
/* n的0次幂==1,这里不能简单的t->node==NULL */
t->lsizenode = 0;
t->node = cast(Node *, dummynode);
setarrayvector(L, t, narray);
setnodevector(L, t, nhash);
return t;
}
void luaH_free (lua_State *L, Table *t) {
if (t->node != dummynode)
luaM_freearray(L, t->node, sizenode(t), Node);
luaM_freearray(L, t->array, t->sizearray, TValue);
luaM_free(L, t);
}
static Node *getfreepos (Table *t) {
while (t->lastfree-- > t->node) {
if (ttisnil(gkey(t->lastfree)))
return t->lastfree;
}
return NULL; /* could not find a free place */
}
/*
** inserts a new key into a hash table; first, check whether key's main
** position is free. If not, check whether colliding node is in its main
** position or not: if it is not, move colliding node to an empty place and
** put new key in its main position; otherwise (colliding node is in its main
** position), new key goes to an empty position.
*/
static TValue *newkey (lua_State *L, Table *t, const TValue *key) {
Node *mp = mainposition(t, key);
if (!ttisnil(gval(mp)) || mp == dummynode) {
Node *othern;
Node *n = getfreepos(t); /* get a free place */
if (n == NULL) { /* cannot find a free place? */
rehash(L, t, key); /* grow table */
return luaH_set(L, t, key); /* re-insert key into grown table */
}
lua_assert(n != dummynode); /* mp==dummynode时,getfreepos必然返回NULL,不应该走到这里 */
othern = mainposition(t, key2tval(mp));
if (othern != mp) { /* is colliding node out of its main position? */
/* yes; move colliding node into free position */
while (gnext(othern) != mp) othern = gnext(othern); /* find previous */
/* 更新下链表 */
gnext(othern) = n; /* redo the chain with `n' in place of `mp' */
*n = *mp; /* copy colliding node into free pos. (mp->next also goes) */
gnext(mp) = NULL; /* now `mp' is free */
setnilvalue(gval(mp)); /* key在下面设置 */
}
else { /* colliding node is in its own main position */
/* new node will go into free position */
gnext(n) = gnext(mp); /* chain new position */
gnext(mp) = n;
mp = n;
}
}
gkey(mp)->value = key->value; gkey(mp)->tt = key->tt;
luaC_barriert(L, t, key);
lua_assert(ttisnil(gval(mp))); /* new的node,其val必然是一个崭新的,必须为nil */
return gval(mp);
}
/*
** search function for integers
*/
const TValue *luaH_getnum (Table *t, int key) {
/* (1 <= key && key <= t->sizearray) */
/* 如果key为负数,按照C的int->uint规则,转换的结果将是一个巨大的数,故而下面判断为false */
if (cast(unsigned int, key-1) < cast(unsigned int, t->sizearray))
return &t->array[key-1];
else {
lua_Number nk = cast_num(key);
Node *n = hashnum(t, nk);
do { /* check whether `key' is somewhere in the chain */
/* 由于Value是union,故而可能n=nk但!!!!! n对应的value的type和nk.对应的value不相等的情况
** 所以这里必须要有个ttisnumber的判断
*/
if (ttisnumber(gkey(n)) && luai_numeq(nvalue(gkey(n)), nk))
return gval(n); /* that's it */
else /* 如果key已存在于tbl,则必然在mp'link上,故而这里可以遍历列表来查找,下同 */
n = gnext(n);
} while (n);
return luaO_nilobject;
}
}
/*
** search function for strings
*/
const TValue *luaH_getstr (Table *t, TString *key) {
Node *n = hashstr(t, key);
do { /* check whether `key' is somewhere in the chain */
/* 这里ttisstring(gkey(n))的判断排除掉已经被gc标记为deadkey的key,和上面的value相等但type不相等的情况
** 如果运行了tbl[key]=nil,再到调用本函数之前,gc还没来得及将其node标记为deadkey,且还没调用resize
** 则是复用该node
*/
if (ttisstring(gkey(n)) && rawtsvalue(gkey(n)) == key)
return gval(n); /* that's it */
else
n = gnext(n);
} while (n);
return luaO_nilobject;
}
/*
** main search function
*/
const TValue *luaH_get (Table *t, const TValue *key) {
switch (ttype(key)) {
case LUA_TNIL: return luaO_nilobject;
case LUA_TSTRING: return luaH_getstr(t, rawtsvalue(key));
case LUA_TNUMBER: {
int k;
lua_Number n = nvalue(key);
lua_number2int(k, n);
if (luai_numeq(cast_num(k), nvalue(key))) /* index is int? */
return luaH_getnum(t, k); /* use specialized version */
/* else go through */ /* 所以这里没有break,看懂了吗? 非int的,走到default分支去了 */
}
default: {
Node *n = mainposition(t, key);
do { /* check whether `key' is somewhere in the chain */
if (luaO_rawequalObj(key2tval(n), key)) /* 这里必须rawequlObj进行type==type的判断,以忽略掉deadKey的Node,以及union带来的影响 */
return gval(n); /* that's it */
else n = gnext(n);
} while (n);
return luaO_nilobject;
}
}
}
TValue *luaH_set (lua_State *L, Table *t, const TValue *key) {
const TValue *p = luaH_get(t, key);
t->flags = 0; /* 如果本tbl当作meta,那么set后可能其tag有更新,这里索性假设所有的tag'methods都更新了,假设所有的tag'methaod都有了 */
if (p != luaO_nilobject)
return cast(TValue *, p);
else {
if (ttisnil(key)) luaG_runerror(L, "table index is nil");
else if (ttisnumber(key) && luai_numisnan(nvalue(key)))
luaG_runerror(L, "table index is NaN");
return newkey(L, t, key); /* 构造新的slot */
}
}
TValue *luaH_setnum (lua_State *L, Table *t, int key) {
const TValue *p = luaH_getnum(t, key);
if (p != luaO_nilobject)
return cast(TValue *, p);
else {
TValue k;
setnvalue(&k, cast_num(key));
return newkey(L, t, &k);
}
}
TValue *luaH_setstr (lua_State *L, Table *t, TString *key) {
const TValue *p = luaH_getstr(t, key); /* key现存,则直接返回node'key */
if (p != luaO_nilobject)
return cast(TValue *, p);
else {
TValue k;
setsvalue(L, &k, key);
return newkey(L, t, &k); /* 没有则构造一个new'node出来,其中node.key=key,并返回其node.val */
}
}
static int unbound_search (Table *t, unsigned int j) {
unsigned int i = j; /* i is zero or a present index */
j++;
/* find `i' and `j' such that i is present and j is not */
while (!ttisnil(luaH_getnum(t, j))) {
i = j;
j *= 2;
if (j > cast(unsigned int, MAX_INT)) { /* overflow? */
/* table was built with bad purposes: resort to linear search */
i = 1;
while (!ttisnil(luaH_getnum(t, i))) i++;
return i - 1;
}
}
/* now do a binary search between them */
while (j - i > 1) {
unsigned int m = (i+j)/2;
if (ttisnil(luaH_getnum(t, m))) j = m;
else i = m;
}
return i;
}
/*
** Try to find a boundary in table `t'. A `boundary' is an integer index
** such that t[i] is non-nil and t[i+1] is nil (and 0 if t[1] is nil).
*/
int luaH_getn (Table *t) {
unsigned int j = t->sizearray;
if (j > 0 && ttisnil(&t->array[j - 1])) {
/* there is a boundary in the array part: (binary) search for it */
unsigned int i = 0;
while (j - i > 1) {
unsigned int m = (i+j)/2;
if (ttisnil(&t->array[m - 1])) j = m;
else i = m;
}
return i;
}
/* else must find a boundary in hash part */
else if (t->node == dummynode) /* hash part is empty? */
return j; /* that is easy... */
else return unbound_search(t, j);
}
#if defined(LUA_DEBUG)
Node *luaH_mainposition (const Table *t, const TValue *key) {
return mainposition(t, key);
}
int luaH_isdummy (Node *n) { return n == dummynode; }
#endif