Analysis of the pros and cons of mysqli_set_charset and SET NAMES in php

 //php-5.2.11-SRC/ext/mysqli/mysqli_nonapi.c line 342
  PHP_FUNCTION(mysqli_set_charset)
  {
      MY_MYSQL*mysql;
      zval*mysql_link;
      char *cs_name = NULL;
      unsigned int len;

      if (zend_parse_method_parameters(ZEND_NUM_ARGS() TSRMLS_CC, getThis()
           , "Os", &mysql_link, mysqli_link_class_entry, &cs_name, &len) == FAILURE) {
         return;
     }
     MYSQLI_FETCH_RESOURCE(mysql, MY_MYSQL*, &mysql_link, "mysqli_link"
         , MYSQLI_STATUS_VALID);

     if (mysql_set_character_set(mysql->mysql, cs_name)) {
           //**Call the corresponding function of libmysql
 RETURN_FALSE;
 }
 RETURN_TRUE;
 }
?>

Then what does mysql_set_character_set do?

 //mysql-5.1.30-SRC/libmysql/client.c, line 3166:
 int STDCALLmysql_set_character_set(MYSQL*mysql, const char *cs_name)
 {
 structcharset_info_st *cs;
 const char *save_csdir= charsets_dir;

 if (mysql->options.charset_dir)
 charsets_dir= mysql->options.charset_dir;

 if (strlen(cs_name) < MY_CS_NAME_SIZE &&
 (cs= get_charset_by_csname(cs_name , MY_CS_PRIMARY, MYF(0))))
 {
 char buff[MY_CS_NAME_SIZE + 10];
 charsets_dir= save_csdir;
 /* Skip execution of "SET NAMES" for pre-4.1 servers*/
     if (mysql_get_server_version(mysql) < 40100)
       return 0;
     sprintf(buff, "SET NAMES %s", cs_name);
     if (!mysql_real_query(mysql, buff, strlen(buff)))
     {
       mysql->charset= cs;
     }
   }
   //以下省略
?>

我们可以看到, mysqli_set_charset除了做了”SET NAMES”以外, 还多做了一步:

 sprintf(buff, "SET NAMES %s", cs_name);
 if (!mysql_real_query(mysql, buff, strlen(buff)))
 {
   mysql->charset= cs;
 }
?>

而对于mysql这个核心结构的成员charset又有什么作用呢?

这就要说说mysql_real_escape_string()了, 这个函数和mysql_escape_string的区别就是, 它会考虑”当前”字符集. 那么这个当前字符集从哪里来呢?

对了, 你猜的没错, 就是mysql->charset.

mysql_real_string在判断宽字符集的字符的时候, 就根据这个成员变量来分别采用不同的策略, 比如如果是utf-8, 那么就会采用libmysql/ctype-utf8.c.

看个实例, 默认mysql连接字符集是latin-1, (经典的5c问题):

      $db = mysql_connect('localhost:3737', 'root' ,'123456');
     mysql_select_db("test");
     $a = "x91x5c";//"慭"的gbk编码, 低字节为5c, 也就是ascii中的""

     var_dump(addslashes($a));
     var_dump(mysql_real_escape_string($a, $db));

     mysql_query("set names gbk");
     var_dump(mysql_real_escape_string($a, $db));

     mysql_set_charset("gbk");
     var_dump(mysql_real_escape_string($a, $db));
?>

因为, “慭”的gbk编码低字节为5c, 也就是ascii中的””, 而因为除了mysql(i)_set_charset影响mysql->charset以外, 其他时刻mysql->charset都为默认值, 所以, 结果就是: $ php -f 5c.php string(3) "慭" string(3) "慭" string(3) "慭" string(2) "慭"

本文转自：http://www.laruence.com/2010/04/12/1396.html