PHP 實現漢字轉拼音的完整類庫代碼與使用指南

前言

在 PHP 開發中，將漢字轉換為拼音是常見需求，例如生成 URL 別名、搜索索引或排序。本文提供一個不依賴擴展、純 PHP 實現的 pin 類，支援 GB2312 與 UTF-8 編碼，內建完整拼音映射表，可直接引入專案使用。

核心原理

該類別基於 GB2312 編碼區位碼與拼音的對應關係：

• 將漢字按 GB2312 編碼轉為區位碼（雙字節）
• 通過預設的映射表（$_DataKey / $_DataValue）查找對應拼音
• 支援 UTF-8 輸入時自動轉碼處理

完整類代碼

<?php
/*************
 * 漢字轉換拼音 Class
 *************/
class pin {
    /**
     * 公開方法：將字串轉為拼音
     * @param string $_String 待轉換字串
     * @param string $_Code 編碼：'gb2312' 或 'utf-8' (預設 gb2312)
     * @return string 拼音字串（小寫、無分隔符）
     */
    function Pinyin($_String, $_Code = 'gb2312') {
        // 拼音索引鍵（按區位碼順序）
        $_DataKey = "a|ai|an|ang|ao|ba|bai|ban|bang|bao|bei|ben|beng|bi|bian|biao|bie|bin|bing|bo|bu|ca|cai|can|cang|cao|ce|ceng|cha".
            "|chai|chan|chang|chao|che|chen|cheng|chi|chong|chou|chu|chuai|chuan|chuang|chui|chun|chuo|ci|cong|cou|cu|".
            "cuan|cui|cun|cuo|da|dai|dan|dang|dao|de|deng|di|dian|diao|die|ding|diu|dong|dou|du|duan|dui|dun|duo|e|en|er".
            "|fa|fan|fang|fei|fen|feng|fo|fou|fu|ga|gai|gan|gang|gao|ge|gei|gen|geng|gong|gou|gu|gua|guai|guan|guang|gui".
            "|gun|guo|ha|hai|han|hang|hao|he|hei|hen|heng|hong|hou|hu|hua|huai|huan|huang|hui|hun|huo|ji|jia|jian|jiang".
            "|jiao|jie|jin|jing|jiong|jiu|ju|juan|jue|jun|ka|kai|kan|kang|kao|ke|ken|keng|kong|kou|ku|kua|kuai|kuan|kuang".
            "|kui|kun|kuo|la|lai|lan|lang|lao|le|lei|leng|li|lia|lian|liang|liao|lie|lin|ling|liu|long|lou|lu|lv|luan|lue".
            "|lun|luo|ma|mai|man|mang|mao|me|mei|men|meng|mi|mian|miao|mie|min|ming|miu|mo|mou|mu|na|nai|nan|nang|nao|ne".
            "|nei|nen|neng|ni|nian|niang|niao|nie|nin|ning|niu|nong|nu|nv|nuan|nue|nuo|o|ou|pa|pai|pan|pang|pao|pei|pen".
            "|peng|pi|pian|piao|pie|pin|ping|po|pu|qi|qia|qian|qiang|qiao|qie|qin|qing|qiong|qiu|qu|quan|que|qun|ran|rang".
            "|rao|re|ren|reng|ri|rong|rou|ru|ruan|rui|run|ruo|sa|sai|san|sang|sao|se|sen|seng|sha|shai|shan|shang|shao|".
            "she|shen|sheng|shi|shou|shu|shua|shuai|shuan|shuang|shui|shun|shuo|si|song|sou|su|suan|sui|sun|suo|ta|tai|".
            "tan|tang|tao|te|teng|ti|tian|tiao|tie|ting|tong|tou|tu|tuan|tui|tun|tuo|wa|wai|wan|wang|wei|wen|weng|wo|wu".
            "|xi|xia|xian|xiang|xiao|xie|xin|xing|xiong|xiu|xu|xuan|xue|xun|ya|yan|yang|yao|ye|yi|yin|ying|yo|yong|you".
            "|yu|yuan|yue|yun|za|zai|zan|zang|zao|ze|zei|zen|zeng|zha|zhai|zhan|zhang|zhao|zhe|zhen|zheng|zhi|zhong|".
            "zhou|zhu|zhua|zhuai|zhuan|zhuang|zhui|zhun|zhuo|zi|zong|zou|zu|zuan|zui|zun|zuo";

        // 對應區位碼偏移量（負數）
        $_DataValue = "-20319|-20317|-20304|-20295|-20292|-20283|-20265|-20257|-20242|-20230|-20051|-20036|-20032|-20026|-20002|-19990".
            "|-19986|-19982|-19976|-19805|-19784|-19775|-19774|-19763|-19756|-19751|-19746|-19741|-19739|-19728|-19725".
            "|-19715|-19540|-19531|-19525|-19515|-19500|-19484|-19479|-19467|-19289|-19288|-19281|-19275|-19270|-19263".
            "|-19261|-19249|-19243|-19242|-19238|-19235|-19227|-19224|-19218|-19212|-19038|-19023|-19018|-19006|-19003".
            "|-18996|-18977|-18961|-18952|-18783|-18774|-18773|-18763|-18756|-18741|-18735|-18731|-18722|-18710|-18697".
            "|-18696|-18526|-18518|-18501|-18490|-18478|-18463|-18448|-18447|-18446|-18239|-18237|-18231|-18220|-18211".
            "|-18201|-18184|-18183|-18181|-18012|-17997|-17988|-17970|-17964|-17961|-17950|-17947|-17931|-17928|-17922".
            "|-17759|-17752|-17733|-17730|-17721|-17703|-17701|-17697|-17692|-17683|-17676|-17496|-17487|-17482|-17468".
            "|-17454|-17433|-17427|-17417|-17202|-17185|-16983|-16970|-16942|-16915|-16733|-16708|-16706|-16689|-16664".
            "|-16657|-16647|-16474|-16470|-16465|-16459|-16452|-16448|-16433|-16429|-16427|-16423|-16419|-16412|-16407".
            "|-16403|-16401|-16393|-16220|-16216|-16212|-16205|-16202|-16187|-16180|-16171|-16169|-16158|-16155|-15959".
            "|-15958|-15944|-15933|-15920|-15915|-15903|-15889|-15878|-15707|-15701|-15681|-15667|-15661|-15659|-15652".
            "|-15640|-15631|-15625|-15454|-15448|-15436|-15435|-15419|-15416|-15408|-15394|-15385|-15377|-15375|-15369".
            "|-15363|-15362|-15183|-15180|-15165|-15158|-15153|-15150|-15149|-15144|-15143|-15141|-15140|-15139|-15128".
            "|-15121|-15119|-15117|-15110|-15109|-14941|-14937|-14933|-14930|-14929|-14928|-14926|-14922|-14921|-14914".
            "|-14908|-14902|-14894|-14889|-14882|-14873|-14871|-14857|-14678|-14674|-14670|-14668|-14663|-14654|-14645".
            "|-14630|-14594|-14429|-14407|-14399|-14384|-14379|-14368|-14355|-14353|-14345|-14170|-14159|-14151|-14149".
            "|-14145|-14140|-14137|-14135|-14125|-14123|-14122|-14112|-14109|-14099|-14097|-14094|-14092|-14090|-14087".
            "|-14083|-13917|-13914|-13910|-13907|-13906|-13905|-13896|-13894|-13878|-13870|-13859|-13847|-13831|-13658".
            "|-13611|-13601|-13406|-13404|-13400|-13398|-13395|-13391|-13387|-13383|-13367|-13359|-13356|-13343|-13340".
            "|-13329|-13326|-13318|-13147|-13138|-13120|-13107|-13096|-13095|-13091|-13076|-13068|-13063|-13060|-12888".
            "|-12875|-12871|-12860|-12858|-12852|-12849|-12838|-12831|-12829|-12812|-12802|-12607|-12597|-12594|-12585".
            "|-12556|-12359|-12346|-12320|-12300|-12120|-12099|-12089|-12074|-12067|-12058|-12039|-11867|-11861|-11847".
            "|-11831|-11798|-11781|-11604|-11589|-11536|-11358|-11340|-11339|-11324|-11303|-11097|-11077|-11067|-11055".
            "|-11052|-11045|-11041|-11038|-11024|-11020|-11019|-11018|-11014|-10838|-10832|-10815|-10800|-10790|-10780".
            "|-10764|-10587|-10544|-10533|-10519|-10331|-10329|-10328|-10322|-10315|-10309|-10307|-10296|-10281|-10274".
            "|-10270|-10262|-10260|-10256|-10254";

        // 建立查找陣列：拼音 => 區位碼偏移量
        $_TDataKey = explode('|', $_DataKey);
        $_TDataValue = explode('|', $_DataValue);
        $_Data = (PHP_VERSION >= '5.0') ? array_combine($_TDataKey, $_TDataValue) : $this->Arr_Combine($_TDataKey, $_TDataValue);
        arsort($_Data); // 降序排列，便於查找
        reset($_Data);

        // 編碼轉換：非 gb2312 視為 UTF-8
        if ($_Code != 'gb2312') $_String = $this->U2_Utf8_Gb($_String);

        $_Res = '';
        for ($i = 0; $i < strlen($_String); $i++) {
            $_P = ord(substr($_String, $i, 1));
            if ($_P > 160) { // 雙字節漢字
                $_Q = ord(substr($_String, ++$i, 1));
                $_P = $_P * 256 + $_Q - 65536; // 計算區位碼偏移量
            }
            $_Res .= $this->Pinyins($_P, $_Data);
        }
        return $_Res;
    }

    /**
     * 根據區位碼查找單個拼音
     */
    function Pinyins($_Num, $_Data) {
        if ($_Num > 0 && $_Num < 160) return chr($_Num); // ASCII 字符直接返回
        elseif ($_Num < -20319 || $_Num > -10247) return ''; // 超出範圍
        else {
            foreach ($_Data as $k => $v) {
                if ($v <= $_Num) break;
            }
            return $k;
        }
    }

    /**
     * UTF-8 轉 GB2312（單字符）
     */
    function U2_Utf8_Gb($_C) {
        $_String = '';
        if ($_C < 0x80) {
            $_String .= $_C;
        } elseif ($_C < 0x800) {
            $_String .= chr(0xC0 | $_C >> 6);
            $_String .= chr(0x80 | $_C & 0x3F);
        } elseif ($_C < 0x10000) {
            $_String .= chr(0xE0 | $_C >> 12);
            $_String .= chr(0x80 | $_C >> 6 & 0x3F);
            $_String .= chr(0x80 | $_C & 0x3F);
        } elseif ($_C < 0x200000) {
            $_String .= chr(0xF0 | $_C >> 18);
            $_String .= chr(0x80 | $_C >> 12 & 0x3F);
            $_String .= chr(0x80 | $_C >> 6 & 0x3F);
            $_String .= chr(0x80 | $_C & 0x3F);
        }
        return iconv('UTF-8', 'GB2312', $_String);
    }

    /**
     * PHP 4 兼容的 array_combine
     */
    function Arr_Combine($_Arr1, $_Arr2) {
        for ($i = 0; $i < count($_Arr1); $i++) $_Res[$_Arr1[$i]] = $_Arr2[$i];
        return $_Res;
    }
}

// 使用範例
$pin = new pin();
// 參數二留空為 gb2312，傳任意值（如 'UTF8'）則視為 UTF-8
echo $pin->Pinyin('中華人民', 'UTF8'); // 輸出：zhonghuarenmin
?>

使用說明與注意事項

1. 編碼參數：第二個參數留空或 'gb2312' 時按 GB2312 處理；傳入任意非空值（如 'UTF8'、'utf-8'）則按 UTF-8 處理。
2. 輸出格式：返回小寫拼音字母連接字串，無分隔符、無聲調。
3. 效能考量：映射表較大，建議單例模式或靜態緩存實例，避免重複構建陣列。
4. 局限性：僅支援 GB2312 字符集範圍內的漢字；生僻字、繁體字、擴展字符集可能無法轉換。

進階優化建議

• 若專案已安裝 intl 擴展，可改用 Transliterator::create('Any-Latin; Latin-ASCII; Lower()') 獲得更完整的 Unicode 支援。
• 需保留聲調或分詞時，建議引入 overtrue/pinyin 等成熟 Composer 套件。