CI框架源码翻阅-Utf8.php

CI框架源码阅读---------Utf8.php
文件地址：./system/core/Utf8.php
主要作用：提供utf-8编码的环境支持
1.__construct() 构造函数确定utf8是否被支持
(1)日志记录 Utf8 Class Initialized
(2)将CodeIgniter.php中的$CFG调用进当前类。
(3)判断如果正则表达式支持utf8，iconv库已经安装，多字节字符串函数重载没有启用，应用程序字   符集是utf8,那么
(a)记录日志：UTF-8 Support Enabled。
(b)定义常量UTF8_ENABLED 值为 true
(c)如果加载了mbstring扩展我们设置内部编码
(d)我们会设置一个标记让我们不用多次使用extension_loaded() 函数
(4)判断如果正则表达式不支持utf8或者iconv库没有安装或者多字节字符串函数重载已经启用或者应用程序字符集不是utf8,那么
(a)记录日志：UTF-8 Support Disabled
(b)设置常量UTF8_ENABLED 为false


2.clean_string()  清理utf8编码的字符串
(1)判断如果字符串不是ASCII码
(2)使用iconv函数将字符串转码（关于iconv函数详情见 http://www.php.net/manual/zh/function.iconv.php）
(3)返回字符串


3.safe_ascii_for_xml() 删除所有在xml中可能导致问题的ASCII码字符，除了水平制表符，换行，回车。
(1) 直接调用remove_invisible_characters()来删除无效的字符并返回。
注：remove_invisible_characters 函数在common.php中定义


4.convert_to_utf8() 将字符串转换为utf8编码
(1)如果iconv函数存在，使用iconv转换
(2)如果mb_convert_encoding函数存在，使用mb_convert_encoding函数转换
(3)如果上面两个函数都不存在则不能转换返回false
(4)如果转换完成返回转换后的字符串


5._is_ascii()  测试一个字符串是不是ASCII码

(1) 使用正则拼配返回测试结果。

<?php if ( ! defined('BASEPATH')) exit('No direct script access allowed');
/**
 * CodeIgniter
 *
 * An open source application development framework for PHP 5.1.6 or newer
 *
 * @package		CodeIgniter
 * @author		ExpressionEngine Dev Team
 * @copyright	Copyright (c) 2008 - 2011, EllisLab, Inc.
 * @license		http://codeigniter.com/user_guide/license.html
 * @link		http://codeigniter.com
 * @since		Version 2.0
 * @filesource
 */

// ------------------------------------

/**
 * Utf8 Class
 *
 * Provides support for UTF-8 environments
 *
 * @package		CodeIgniter
 * @subpackage	Libraries
 * @category	UTF-8
 * @author		ExpressionEngine Dev Team
 * @link		http://codeigniter.com/user_guide/libraries/utf8.html
 */
class CI_Utf8 {

	/**
	 * Constructor
	 *
	 * Determines if UTF-8 support is to be enabled
	 *
	 */
	function __construct()
	{
		log_message('debug', "Utf8 Class Initialized");

		global $CFG;

		if (
			preg_match('/./u', 'é') === 1					// PCRE must support UTF-8
			AND function_exists('iconv')					// iconv must be installed
			AND ini_get('mbstring.func_overload') != 1		// Multibyte string function overloading cannot be enabled
			AND $CFG->item('charset') == 'UTF-8'			// Application charset must be UTF-8
			)
		{
			log_message('debug', "UTF-8 Support Enabled");

			define('UTF8_ENABLED', TRUE);

			// set internal 内部 encoding for multibyte 多字节 string functions if necessary 必需的
			// and set a flag so we don't have to repeatedly 多次 use extension_loaded()
			// or function_exists()
			if (extension_loaded('mbstring'))
			{
				define('MB_ENABLED', TRUE);
				mb_internal_encoding('UTF-8');
			}
			else
			{
				define('MB_ENABLED', FALSE);
			}
		}
		else
		{
			log_message('debug', "UTF-8 Support Disabled");
			define('UTF8_ENABLED', FALSE);
		}
	}

	// --------------------------------

	/**
	 * Clean UTF-8 strings
	 *
	 * Ensures 保证 strings are UTF-8
	 *
	 * @access	public
	 * @param	string
	 * @return	string
	 */
	function clean_string($str)
	{
		if ($this->_is_ascii($str) === FALSE)
		{
			$str = @iconv('UTF-8', 'UTF-8//IGNORE', $str);
		}

		return $str;
	}

	// --------------------------------

	/**
	 * Remove ASCII control characters
	 *
	 * Removes all ASCII control characters except horizontal tabs,
	 * line feeds, and carriage returns, as all others can cause
	 * problems in XML
	 *
	 * @access	public
	 * @param	string
	 * @return	string
	 */
	function safe_ascii_for_xml($str)
	{
		return remove_invisible_characters($str, FALSE);
	}

	// --------------------------------

	/**
	 * Convert to UTF-8
	 *
	 * Attempts 企图 to convert a string to UTF-8
	 *
	 * @access	public
	 * @param	string
	 * @param	string	- input encoding
	 * @return	string
	 */
	function convert_to_utf8($str, $encoding)
	{
		if (function_exists('iconv'))
		{
			$str = @iconv($encoding, 'UTF-8', $str);
		}
		elseif (function_exists('mb_convert_encoding'))
		{
			$str = @mb_convert_encoding($str, 'UTF-8', $encoding);
		}
		else
		{
			return FALSE;
		}

		return $str;
	}

	// --------------------------------

	/**
	 * Is ASCII?
	 *
	 * Tests if a string is standard 7-bit ASCII or not
	 *
	 * @access	public
	 * @param	string
	 * @return	bool
	 */
	function _is_ascii($str)
	{
		return (preg_match('/[^\x00-\x7F]/S', $str) == 0);
	}

	// --------------------------------

}
// End Utf8 Class

/* End of file Utf8.php */
/* Location: ./system/core/Utf8.php */