深入php内核之php in array

先给大家介绍php in array函数基本知识热热身。

定义和用法

in_array() 函数在数组中搜索给定的值。

语法
in_array(value,array,type)

参数	描述
value	必需。规定要在数组搜索的值。
array	必需。规定要搜索的数组。
type	可选。如果设置该参数为 true，则检查搜索的数据与数组的值的类型是否相同。

 说明

如果给定的值 value 存在于数组 array 中则返回 true。如果第三个参数设置为 true，函数只有在元素存在于数组中且数据类型与给定值相同时才返回 true。

如果没有在数组中找到参数，函数返回 false。

注释：如果 value 参数是字符串，且 type 参数设置为 true，则搜索区分大小写。

无意中看到一段代码

<?php    
$y="1800";
$x = array();
for($j=0;$j<50000;$j++){
 $x[]= "{$j}";
}
for($i=0;$i<30000;$i++){
 if(in_array($y,$x)){
  continue;
 } 
}

测试了一下

[root@dev tmp]# time php b.php
real    0m9.517s
user    0m4.486s
sys     0m0.015s

竟然需要9s

in_array是这个样子的

bool in_array ( mixed $needle , array $haystack [, bool $strict = false ] )

在 haystack 中搜索 needle，如果没有设置 strict 则使用宽松的比较。

needle

待搜索的值。如果 needle 是字符串，则比较是区分大小写的。

haystack

这个数组。

strict

如果第三个参数 strict 的值为 true 则 in_array() 函数还会检查 needle 的类型是否和 haystack 中的相同。

那么我看一下源代码

第一步 在ext/standard/array.c 文件中

/* }}} */              
/* {{{ proto bool in_array(mixed needle, array haystack [, bool strict])
 checks if the given value exists in the array */   
php_function(in_array)          
{                
 php_search_array(internal_function_param_passthru, 0); 
}                
/* }}} */             
/* {{{ proto mixed array_search(mixed needle, array haystack [, bool strict])
 searches the array for a given value and returns the corresponding key if successful */
php_function(array_search)         
{            
 php_search_array(internal_function_param_passthru, 1); 
}                
/* }}} */ 

顺便看到了array_search，原来和in_array的内部实现基本一致

其中函数的参数 在./zend.h中

#define internal_function_param_passthru ht, return_value, return_value_ptr, this_ptr, return_value_used tsrmls_cc

第二步 在ext/standard/array.c 文件中 查看php_search_array原型

/* void php_search_array(internal_function_parameters, int behavior)
 * 0 = return boolean
 * 1 = return key
 */  
static void php_search_array(internal_function_parameters, int behavior) /* {{{ */
{  
 zval *value,   /* value to check for */
   *array,   /* array to check in */
   **entry,   /* pointer to array entry */
   res;    /* comparison result */
 hashposition pos;  /* hash iterator */
 zend_bool strict = 0;  /* strict comparison or not */
 ulong num_key;
 uint str_key_len;
 char *string_key;
 int (*is_equal_func)(zval *, zval *, zval * tsrmls_dc) = is_equal_function;
 if (zend_parse_parameters(zend_num_args() tsrmls_cc, "za|b", &value, &array, &strict) == failure) {
  return;
 } 
 if (strict) {
  is_equal_func = is_identical_function;
 } 
 zend_hash_internal_pointer_reset_ex(z_arrval_p(array), &pos);
 while (zend_hash_get_current_data_ex(z_arrval_p(array), (void **)&entry, &pos) == success) {
  is_equal_func(&res, value, *entry tsrmls_cc);
  if (z_lval(res)) {
   if (behavior == 0) {
    return_true;
   } else {
    /* return current key */
    switch (zend_hash_get_current_key_ex(z_arrval_p(array), &string_key, &str_key_len, &num_key, 0, &pos)) {
     case hash_key_is_string:
      return_stringl(string_key, str_key_len - 1, 1);
      break;
     case hash_key_is_long:
      return_long(num_key);
      break;
    }
   }
  }
  zend_hash_move_forward_ex(z_arrval_p(array), &pos);
 } 
 return_false;
}  
/* }}} */
/* {{{ proto bool in_array(mixed needle, array haystack [, bool strict])
 checks if the given value exists in the array */

我们发现 strict  这个值的不同有两种比较方式，看一下两个函数的不同之处

is_identical_function 检查类型是否相同

zend_api int is_identical_function(zval *result, zval *op1, zval *op2 tsrmls_dc) /* {{{ */
{  
 z_type_p(result) = is_bool;
 if (z_type_p(op1) != z_type_p(op2)) {
  z_lval_p(result) = 0;
  return success;
 } 
 switch (z_type_p(op1)) {
  case is_null:
   z_lval_p(result) = 1;
   break;
  case is_bool:
  case is_long:
  case is_resource:
   z_lval_p(result) = (z_lval_p(op1) == z_lval_p(op2));
   break;
  case is_double:
   z_lval_p(result) = (z_dval_p(op1) == z_dval_p(op2));
   break;
  case is_string:
   z_lval_p(result) = ((z_strlen_p(op1) == z_strlen_p(op2))
   && (!memcmp(z_strval_p(op1), z_strval_p(op2), z_strlen_p(op1))));
   break;
  case is_array:
   z_lval_p(result) = (z_arrval_p(op1) == z_arrval_p(op2)
   zend_hash_compare(z_arrval_p(op1), z_arrval_p(op2), (compare_func_t) hash_zval_identical_function, 1 tsrmls_cc)==0);
   break;
  case is_object:
   if (z_obj_ht_p(op1) == z_obj_ht_p(op2)) {
   z_lval_p(result) = (z_obj_handle_p(op1) == z_obj_handle_p(op2));
   } else {
   z_lval_p(result) = 0;
   }
   break;
  default:
   z_lval_p(result) = 0;
   return failure;
 } 
 return success;
}  
/* }}} */

is_equal_function 不检查类型是否相同，所以需要隐式转换

zend_api int is_equal_function(zval *result, zval *op1, zval *op2 tsrmls_dc) /* {{{ */
{  
 if (compare_function(result, op1, op2 tsrmls_cc) == failure) {
  return failure;
 } 
 zval_bool(result, (z_lval_p(result) == 0));
 return success;
}  
/* }}} */
==》compare_function

zend_api int compare_function(zval *result, zval *op1, zval *op2 tsrmls_dc) /* {{{ */
{   
 int ret;
 int converted = 0;
 zval op1_copy, op2_copy;
 zval *op_free;
 while (1) {
  switch (type_pair(z_type_p(op1), z_type_p(op2))) {
   case type_pair(is_long, is_long):
   zval_long(result, z_lval_p(op1)>z_lval_p(op2)?1:(z_lval_p(op1)<z_lval_p(op2)?-1:0));
   return success;
   case type_pair(is_double, is_long):
   z_dval_p(result) = z_dval_p(op1) - (double)z_lval_p(op2);
   zval_long(result, zend_normalize_bool(z_dval_p(result)));
   return success;
   case type_pair(is_long, is_double):
   z_dval_p(result) = (double)z_lval_p(op1) - z_dval_p(op2);
   zval_long(result, zend_normalize_bool(z_dval_p(result)));
   return success;
   case type_pair(is_double, is_double):
   if (z_dval_p(op1) == z_dval_p(op2)) {
    zval_long(result, 0);
   } else {
    z_dval_p(result) = z_dval_p(op1) - z_dval_p(op2);
    zval_long(result, zend_normalize_bool(z_dval_p(result)));
   }
   return success;
   case type_pair(is_array, is_array):
   zend_compare_arrays(result, op1, op2 tsrmls_cc);
   return success;
   case type_pair(is_null, is_null):
   zval_long(result, 0);
   return success;
   case type_pair(is_null, is_bool):
   zval_long(result, z_lval_p(op2) ? -1 : 0);
   return success;
   case type_pair(is_bool, is_null):
   zval_long(result, z_lval_p(op1) ? 1 : 0);
   return success;
   case type_pair(is_bool, is_bool):
   zval_long(result, zend_normalize_bool(z_lval_p(op1) - z_lval_p(op2)));
   return success;
   case type_pair(is_string, is_string):
   zendi_smart_strcmp(result, op1, op2);
   return success;
   case type_pair(is_null, is_string):
   zval_long(result, zend_binary_strcmp("", 0, z_strval_p(op2), z_strlen_p(op2)));
   return success;
   case type_pair(is_string, is_null):
   zval_long(result, zend_binary_strcmp(z_strval_p(op1), z_strlen_p(op1), "", 0));
   return success;
   case type_pair(is_object, is_null):
   zval_long(result, 1);
   return success;
   case type_pair(is_null, is_object):
   zval_long(result, -1);
   return success;
   case type_pair(is_object, is_object):
   /* if both are objects sharing the same comparision handler then use is */
   if (z_obj_handler_p(op1,compare_objects) == z_obj_handler_p(op2,compare_objects)) {
    if (z_obj_handle_p(op1) == z_obj_handle_p(op2)) {
     /* object handles are identical, apparently this is the same object */
     zval_long(result, 0);
     return success;
    }
    zval_long(result, z_obj_ht_p(op1)->compare_objects(op1, op2 tsrmls_cc));
    return success;
   }
   /* break missing intentionally */
   default:
   if (z_type_p(op1) == is_object) {
    if (z_obj_ht_p(op1)->get) {
     op_free = z_obj_ht_p(op1)->get(op1 tsrmls_cc);
     ret = compare_function(result, op_free, op2 tsrmls_cc);
     zend_free_obj_get_result(op_free tsrmls_cc);
     return ret;
    } else if (z_type_p(op2) != is_object && z_obj_ht_p(op1)->cast_object) {
     alloc_init_zval(op_free);
     if (z_obj_ht_p(op1)->cast_object(op1, op_free, z_type_p(op2) tsrmls_cc) == failure) {
      zval_long(result, 1);
      zend_free_obj_get_result(op_free tsrmls_cc);
      return success;
     }
     ret = compare_function(result, op_free, op2 tsrmls_cc);
     zend_free_obj_get_result(op_free tsrmls_cc);
     return ret;
    }
   }
   if (z_type_p(op2) == is_object) {
    if (z_obj_ht_p(op2)->get) {
     op_free = z_obj_ht_p(op2)->get(op2 tsrmls_cc);
     ret = compare_function(result, op1, op_free tsrmls_cc);
     zend_free_obj_get_result(op_free tsrmls_cc);
     return ret;
    } else if (z_type_p(op1) != is_object && z_obj_ht_p(op2)->cast_object) {
     alloc_init_zval(op_free);
     if (z_obj_ht_p(op2)->cast_object(op2, op_free, z_type_p(op1) tsrmls_cc) == failure) {
      zval_long(result, -1);
      zend_free_obj_get_result(op_free tsrmls_cc);
      return success;
     }
     ret = compare_function(result, op1, op_free tsrmls_cc);
     zend_free_obj_get_result(op_free tsrmls_cc);
     return ret;
    } else if (z_type_p(op1) == is_object) {
     zval_long(result, 1);
     return success;
    }
   }
   if (!converted) {
    if (z_type_p(op1) == is_null) {
     zendi_convert_to_boolean(op2, op2_copy, result);
     zval_long(result, z_lval_p(op2) ? -1 : 0);
     return success;
    } else if (z_type_p(op2) == is_null) {
     zendi_convert_to_boolean(op1, op1_copy, result);
     zval_long(result, z_lval_p(op1) ? 1 : 0);
     return success;
    } else if (z_type_p(op1) == is_bool) {
     zendi_convert_to_boolean(op2, op2_copy, result);
     zval_long(result, zend_normalize_bool(z_lval_p(op1) - z_lval_p(op2)));
     return success;
    } else if (z_type_p(op2) == is_bool) {
     zendi_convert_to_boolean(op1, op1_copy, result);
     zval_long(result, zend_normalize_bool(z_lval_p(op1) - z_lval_p(op2)));
     return success;
    } else {
     zendi_convert_scalar_to_number(op1, op1_copy, result);
     zendi_convert_scalar_to_number(op2, op2_copy, result);
     converted = 1;
    }
   } else if (z_type_p(op1)==is_array) {
    zval_long(result, 1);
    return success;
   } else if (z_type_p(op2)==is_array) {
    zval_long(result, -1);
    return success;
   } else if (z_type_p(op1)==is_object) {
    zval_long(result, 1);
    return success;
   } else if (z_type_p(op2)==is_object) {
    zval_long(result, -1);
    return success;
   } else {
    zval_long(result, 0);
    return failure;
   }
  } 
 }  
}   
/* }}} */