[PHP知识库]php特殊字符不解析处理

方案： 将特殊字母数字通过unicode值将其映射至正常字母数字

<?php
class UnicodeUTF8Tool {

    /**
     * [utf8ToUnicode utf8 转换为 unicode]
     */
    public static function utf8ToUnicode($raw_string) {
        while (!empty($raw_string)) {
            #字符串第一个字节的字节数
            $first_character_byte_num = self::returnCharacterByteNum($raw_string);
            #第一个字符
            $character   = substr($raw_string, 0, $first_character_byte_num);
            #剩余的字符
            $raw_string  = substr($raw_string, $first_character_byte_num);
            #第一个字符的unicode序号
            $unicode     = self::characterToUnicode($character);
            #第一个字符的unicode 十六进制
            $unicode_hex = dechex($unicode);
            $unicode_hex = '\u'. self::hexAddZero($unicode_hex);

            #第一个字符的信息
            $info = compact('character', 'unicode', 'unicode_hex');
            $res[] = $info;
        }
        return $res;
    }

    /**
     * [processCharacter 特殊字符处理转正常]
     */
    public static function processCharacter($raw_string) {
        $res = '';
        while (!empty($raw_string)) {
            #字符串第一个字节的字节数
            $first_character_byte_num = self::returnCharacterByteNum($raw_string);
            #第一个字符
            $character   = substr($raw_string, 0, $first_character_byte_num);
            #剩余的字符
            $raw_string  = substr($raw_string, $first_character_byte_num);
            #第一个字符的unicode序号
            $unicode     = self::characterToUnicode($character);
            if($unicode>= 120812 &&  $unicode <= 120821){//数字映射
                $unicode = $unicode - 120764;
                $character = self::unicodeToCharacter($unicode);
            } elseif ($unicode>= 120276 &&  $unicode <= 120301) {//大写字母映射
                $unicode = $unicode - 120211;
                $character = self::unicodeToCharacter($unicode);
            } elseif ($unicode>= 120302 &&  $unicode <= 120327) {//小写字母映射
                $unicode = $unicode - 120205;
                $character = self::unicodeToCharacter($unicode);
            }
            $res .= $character;

        }
        return $res;
    }

    /**
     * [unicodeToCharacter unicode 转换为 utf8]
     */
    public static function  unicodeToCharacter($unicode_num) {
        if($unicode_num <= 0x7F ){
            return chr($unicode_num);
        }
        if($unicode_num <= 0x7FF){
            return chr(($unicode_num >> 6) + 192).
                chr(($unicode_num & 63) + 128);
        }
        if($unicode_num <= 0xFFFF){
            return chr(($unicode_num >> 12) + 224).
                chr((($unicode_num >> 6) & 63) + 128).
                chr(($unicode_num & 63) + 128);
        }
        if($unicode_num <= 0x1FFFFF){
            return chr(($unicode_num >> 18) + 240).
                chr((($unicode_num >> 12) & 63) + 128).
                chr((($unicode_num >> 6) & 63)+ 128).
                chr(($unicode_num & 63) + 128);
        }
        return '';
    }

    /**
     * [hexAddZero 十六进制补0]
     */
    public static function hexAddZero($num){
        if(strlen($num) == 1) return '000'. $num;
        if(strlen($num) == 2) return '00'. $num;
        if(strlen($num) == 3) return '0'. $num;
        return $num;
    }

    /**
     * [characterToUnicode 单个utf8 字符转换为 unicode]
     */
    public static function characterToUnicode($character) {
        #取表情的第一个字节
        $character_first = ord($character[0]);
        if ($character_first >=0 && $character_first <= 127){
            return $character_first;
        }

        #取表情的第二个字节
        $character_second = ord($character[1]);
        if ($character_first >= 192 && $character_first <= 223){
            return ($character_first - 192) * 64 + ($character_second - 128);
        }

        #取表情的第三个字节
        $character_third = ord($character[2]);
        if ($character_first >= 224 && $character_first <= 239){
            return ($character_first-224)*4096 + ($character_second - 128)*64 + ($character_third - 128);
        }

        #取表情的第四个字节
        $character_fourth = ord($character[3]);
        if ($character_first >= 240 && $character_first <= 247) {
            return ($character_first - 240) * 262144 + ($character_second - 128) * 4096 + ($character_third - 128) * 64 + ($character_fourth - 128);
        }
        return false;
    }

    /**
     * [returnCharacterLength 返回字符的字节数]
     */
    public static function returnCharacterByteNum($character) {
        #根据第一个字节大小判断几个字节
        $num = ord($character[0]);
        if ($num >= 0 && $num <= 127){
            return 1;
        }
        if ($num >= 192 && $num <= 223){
            return 2;
        }
        if ($num >= 224 && $num <= 239){
            return 3;
        }
        if ($num >= 240 && $num <= 247) {
            return 4;
        }
    }
}

查询unicode值链接：https://codepoints.net/mathematical_alphanumeric_symbols

代码来源：https://github.com/xaozhuge/php_class/blob/master/UnicodeUTF8Model.class.php