php5.6的雜湊表比較噁心，php7也對雜湊表進行了改造，先介紹下php5.6的雜湊表

原來大家都清楚，我們看一下更細的一部分，如何更新插入：

static zend_never_inline zval **_get_zval_cv_lookup_BP_VAR_W(zval ***ptr, zend_uint var TSRMLS_DC)
{
	zend_compiled_variable *cv = &CV_DEF_OF(var);

	if (!EG(active_symbol_table)) {
		Z_ADDREF(EG(uninitialized_zval));
		*ptr = (zval**)EX_CV_NUM(EG(current_execute_data), EG(active_op_array)->last_var + var);
		**ptr = &EG(uninitialized_zval);
	} else if (zend_hash_quick_find(EG(active_symbol_table), cv->name, cv->name_len+1, cv->hash_value, (void **)ptr)==FAILURE) {
		Z_ADDREF(EG(uninitialized_zval));
		zend_hash_quick_update(EG(active_symbol_table), cv->name, cv->name_len+1, cv->hash_value, &EG(uninitialized_zval_ptr), sizeof(zval *), (void **)ptr);
	}
	return *ptr;
}
 

ZEND_API int _zend_hash_quick_add_or_update(HashTable *ht, const char *arKey, uint nKeyLength, ulong h, void *pData, uint nDataSize, void **pDest, int flag ZEND_FILE_LINE_DC);

zend_hash_quick_update(EG(active_symbol_table), cv->name, cv->name_len+1, cv->hash_value, &EG(uninitialized_zval_ptr), sizeof
 
(zval *), (void **)ptr);

首先要注意看的是&EG(uninitialized_zval_ptr)是一個**zval結構指標， 把它存進去的目的是初始化，也就是讓hash表結構指標有所指向，一個固定位置，後續會根據pDest指標進行賦值。

其次是pDest是二級指標，為什麼會是二級指標，因為c語言函式傳遞都是值傳遞，要改變指標值只能將指標地址傳入。

但是雖然是二級指標，事實呼叫的卻是用的三級真值***ptr,那是因為符號表變數存的永遠是**zval結構，加上ptr變數地址，所以三級就是這樣來的。

#define UPDATE_DATA(ht, p, pData, nDataSize)											\
	if (nDataSize == sizeof(void*)) {													\
		if ((p)->pData != &(p)->pDataPtr) {												\
			pefree_rel((p)->pData, (ht)->persistent);									\
		}																				\
		memcpy(&(p)->pDataPtr, pData, sizeof(void *));									\
		(p)->pData = &(p)->pDataPtr;													\
	} else {																			\
		if ((p)->pData == &(p)->pDataPtr) {												\
			(p)->pData = (void *) pemalloc_rel(nDataSize, (ht)->persistent);			\
			(p)->pDataPtr=NULL;															\
		} else {																		\
			(p)->pData = (void *) perealloc_rel((p)->pData, nDataSize, (ht)->persistent);	\
			/* (p)->pDataPtr is already NULL so no need to initialize it */				\
		}																				\
		memcpy((p)->pData, pData, nDataSize);											\
	}
 

具體看下面畫的很難看的圖

接下來是php7的資料結構:

struct _zend_string {
	zend_refcounted_h gc;
	zend_ulong        h;                /* hash value */
	size_t            len;
	char              val[1];
};

typedef struct _Bucket {
	zval              val;
	zend_ulong        h;                /* hash value (or numeric index)   */
	zend_string      *key;              /* string key or NULL for numerics */
} Bucket;

typedef struct _zend_array HashTable;

struct _zend_array {
	zend_refcounted_h gc;
	union {
		struct {
			ZEND_ENDIAN_LOHI_4(
				zend_uchar    flags,
				zend_uchar    nApplyCount,
				zend_uchar    nIteratorsCount,
				zend_uchar    reserve)
		} v;
		uint32_t flags;
	} u;
	uint32_t          nTableMask;
	Bucket           *arData;
	uint32_t          nNumUsed;
	uint32_t          nNumOfElements;
	uint32_t          nTableSize;
	uint32_t          nInternalPointer;
	zend_long         nNextFreeElement;
	dtor_func_t       pDestructor;
};

/*
 * HashTable Data Layout
 * =====================
 *
 *                 +=============================+
 *                 | HT_HASH(ht, ht->nTableMask) |
 *                 | ...                         |
 *                 | HT_HASH(ht, -1)             |
 *                 +-----------------------------+
 * ht->arData ---> | Bucket[0]                   |
 *                 | ...                         |
 *                 | Bucket[ht->nTableSize-1]    |
 *                 +=============================+
 */

ht->arData僅是一級指標，分為上下兩部分，上部分是索引根據hash值偏移獲取下半部分的index，從而拿到內容

<pre style="font-family: NSimSun; font-size: 16px; background: white;"><span style="color:blue;">#define</span> HT_HASH_EX(data, idx) \
	((uint32_t*)(data))[(int32_t)(idx)]

根據hash值獲取int型別的偏移量，通常idx為負數見初始化：

static void zend_always_inline zend_hash_real_init_ex(HashTable *ht, int packed)
{
	HT_ASSERT(GC_REFCOUNT(ht) == 1);
	ZEND_ASSERT(!((ht)->u.flags & HASH_FLAG_INITIALIZED));
	if (packed) {
		HT_SET_DATA_ADDR(ht, pemalloc(HT_SIZE(ht), (ht)->u.flags & HASH_FLAG_PERSISTENT));
		(ht)->u.flags |= HASH_FLAG_INITIALIZED | HASH_FLAG_PACKED;
		HT_HASH_RESET_PACKED(ht);
	} else {
		(ht)->nTableMask = -(ht)->nTableSize;
		HT_SET_DATA_ADDR(ht, pemalloc(HT_SIZE(ht), (ht)->u.flags & HASH_FLAG_PERSISTENT));
		(ht)->u.flags |= HASH_FLAG_INITIALIZED;
		if (EXPECTED(ht->nTableMask == -8)) {
			Bucket *arData = ht->arData;

			HT_HASH_EX(arData, -8) = -1;
			HT_HASH_EX(arData, -7) = -1;
			HT_HASH_EX(arData, -6) = -1;
			HT_HASH_EX(arData, -5) = -1;
			HT_HASH_EX(arData, -4) = -1;
			HT_HASH_EX(arData, -3) = -1;
			HT_HASH_EX(arData, -2) = -1;
			HT_HASH_EX(arData, -1) = -1;
		} else {
			HT_HASH_RESET(ht);
		}
	}
}

# define HT_HASH_TO_BUCKET_EX(data, idx) \
	((Bucket*)((char*)(data) + (idx)))

可見增加元素的方法

add_to_hash:
	HANDLE_BLOCK_INTERRUPTIONS();
	idx = ht->nNumUsed++;
	ht->nNumOfElements++;
	if (ht->nInternalPointer == HT_INVALID_IDX) {
		ht->nInternalPointer = idx;
	}
	zend_hash_iterators_update(ht, HT_INVALID_IDX, idx);
	p = ht->arData + idx;
	p->key = key;
	if (!ZSTR_IS_INTERNED(key)) {
		zend_string_addref(key);
		ht->u.flags &= ~HASH_FLAG_STATIC_KEYS;
		zend_string_hash_val(key);
	}
	p->h = h = ZSTR_H(key);
	ZVAL_COPY_VALUE(&p->val, pData);
	nIndex = h | ht->nTableMask;
	Z_NEXT(p->val) = HT_HASH(ht, nIndex);
	HT_HASH(ht, nIndex) = HT_IDX_TO_HASH(idx);
	HANDLE_UNBLOCK_INTERRUPTIONS();

首先zval元素的位置是順序儲存的，就是ht->arData的下半部分，然後通過hash算出nIndex位移即上部分，首先將上部分的初始位置(-1)賦值給下半部分zval的next屬性，然後賦值為下部分的位置（1），如此迴圈，當加入一個新的hash相同的資料時，此時將1賦值給新的zval的next，上部分的值為2。

2  $var = 1

php7解析過程 :

compile_file -> zendparse(yyparse) -> zend_compile_top_stmt -> zend_compile_stmt

獲取opcode