PHP 中国語文字からピンイン ソース コードへ (GB2312 クラス ライブラリ、約 6000 文字の中国語をサポート)

最近のプロジェクトでは、フロントエンドのデータを提供する開発言語として PHP が使用され、文字でソートできるようにするために、このプロジェクトを使用して変換するスクリプトを作成しました。中国語の文字をピンインに変換します。スクリプトは比較的単純で、コメントは比較的詳細です。ここではこれ以上は説明しません。コードに直接進みましょう。

$py = new PinYin();
           $all_py = $py->get_all_py("吴国伟"); //输出 ['wu','guo','wei']，输出字符串调用join方法,join('',$all_py)
           $first_py = $py->get_first_py($all_py);//输出 wgw
           $first_letter = $py->get_first_letter($all_py);// 输出 w

ソースコード:

<?php
 
/**
 * +------------------------------------------------------
 *    PHP 汉字转拼音
 * +------------------------------------------------------
 *    使用方法:
 *           $py = new PinYin();
 *           $all_py = $py->get_all_py("吴国伟"); //输出 [&#39;wu&#39;,&#39;guo&#39;,&#39;wei&#39;]，输出字符串调用join方法,join(&#39;&#39;,$all_py)
 *           $first_py = $py->get_first_py($all_py);//输出 wgw
 *           $first_letter = $py->get_first_letter($all_py);// 输出 w
 *
 * +------------------------------------------------------
 */
class PinYin
{
 
    private $dict_list = array(
        &#39;a&#39; => -20319, &#39;ai&#39; => -20317, &#39;an&#39; => -20304, &#39;ang&#39; => -20295, &#39;ao&#39; => -20292,
        &#39;ba&#39; => -20283, &#39;bai&#39; => -20265, &#39;ban&#39; => -20257, &#39;bang&#39; => -20242, &#39;bao&#39; => -20230, &#39;bei&#39; => -20051, &#39;ben&#39; => -20036, &#39;beng&#39; => -20032, &#39;bi&#39; => -20026, &#39;bian&#39; => -20002, &#39;biao&#39; => -19990, &#39;bie&#39; => -19986, &#39;bin&#39; => -19982, &#39;bing&#39; => -19976, &#39;bo&#39; => -19805, &#39;bu&#39; => -19784,
        &#39;ca&#39; => -19775, &#39;cai&#39; => -19774, &#39;can&#39; => -19763, &#39;cang&#39; => -19756, &#39;cao&#39; => -19751, &#39;ce&#39; => -19746, &#39;ceng&#39; => -19741, &#39;cha&#39; => -19739, &#39;chai&#39; => -19728, &#39;chan&#39; => -19725, &#39;chang&#39; => -19715, &#39;chao&#39; => -19540, &#39;che&#39; => -19531, &#39;chen&#39; => -19525, &#39;cheng&#39; => -19515, &#39;chi&#39; => -19500, &#39;chong&#39; => -19484, &#39;chou&#39; => -19479, &#39;chu&#39; => -19467, &#39;chuai&#39; => -19289, &#39;chuan&#39; => -19288, &#39;chuang&#39; => -19281, &#39;chui&#39; => -19275, &#39;chun&#39; => -19270, &#39;chuo&#39; => -19263, &#39;ci&#39; => -19261, &#39;cong&#39; => -19249, &#39;cou&#39; => -19243, &#39;cu&#39; => -19242, &#39;cuan&#39; => -19238, &#39;cui&#39; => -19235, &#39;cun&#39; => -19227, &#39;cuo&#39; => -19224,
        &#39;da&#39; => -19218, &#39;dai&#39; => -19212, &#39;dan&#39; => -19038, &#39;dang&#39; => -19023, &#39;dao&#39; => -19018, &#39;de&#39; => -19006, &#39;deng&#39; => -19003, &#39;di&#39; => -18996, &#39;dian&#39; => -18977, &#39;diao&#39; => -18961, &#39;die&#39; => -18952, &#39;ding&#39; => -18783, &#39;diu&#39; => -18774, &#39;dong&#39; => -18773, &#39;dou&#39; => -18763, &#39;du&#39; => -18756, &#39;duan&#39; => -18741, &#39;dui&#39; => -18735, &#39;dun&#39; => -18731, &#39;duo&#39; => -18722,
        &#39;e&#39; => -18710, &#39;en&#39; => -18697, &#39;er&#39; => -18696,
        &#39;fa&#39; => -18526, &#39;fan&#39; => -18518, &#39;fang&#39; => -18501, &#39;fei&#39; => -18490, &#39;fen&#39; => -18478, &#39;feng&#39; => -18463, &#39;fo&#39; => -18448, &#39;fou&#39; => -18447, &#39;fu&#39; => -18446,
        &#39;ga&#39; => -18239, &#39;gai&#39; => -18237, &#39;gan&#39; => -18231, &#39;gang&#39; => -18220, &#39;gao&#39; => -18211, &#39;ge&#39; => -18201, &#39;gei&#39; => -18184, &#39;gen&#39; => -18183, &#39;geng&#39; => -18181, &#39;gong&#39; => -18012, &#39;gou&#39; => -17997, &#39;gu&#39; => -17988, &#39;gua&#39; => -17970, &#39;guai&#39; => -17964, &#39;guan&#39; => -17961, &#39;guang&#39; => -17950, &#39;gui&#39; => -17947,
        &#39;gun&#39; => -17931, &#39;guo&#39; => -17928,
        &#39;ha&#39; => -17922, &#39;hai&#39; => -17759, &#39;han&#39; => -17752, &#39;hang&#39; => -17733, &#39;hao&#39; => -17730, &#39;he&#39; => -17721, &#39;hei&#39; => -17703, &#39;hen&#39; => -17701, &#39;heng&#39; => -17697, &#39;hong&#39; => -17692, &#39;hou&#39; => -17683, &#39;hu&#39; => -17676, &#39;hua&#39; => -17496, &#39;huai&#39; => -17487, &#39;huan&#39; => -17482, &#39;huang&#39; => -17468, &#39;hui&#39; => -17454,
        &#39;hun&#39; => -17433, &#39;huo&#39; => -17427,
        &#39;ji&#39; => -17417, &#39;jia&#39; => -17202, &#39;jian&#39; => -17185, &#39;jiang&#39; => -16983, &#39;jiao&#39; => -16970, &#39;jie&#39; => -16942, &#39;jin&#39; => -16915, &#39;jing&#39; => -16733, &#39;jiong&#39; => -16708, &#39;jiu&#39; => -16706, &#39;ju&#39; => -16689, &#39;juan&#39; => -16664, &#39;jue&#39; => -16657, &#39;jun&#39; => -16647,
        &#39;ka&#39; => -16474, &#39;kai&#39; => -16470, &#39;kan&#39; => -16465, &#39;kang&#39; => -16459, &#39;kao&#39; => -16452, &#39;ke&#39; => -16448, &#39;ken&#39; => -16433, &#39;keng&#39; => -16429, &#39;kong&#39; => -16427, &#39;kou&#39; => -16423, &#39;ku&#39; => -16419, &#39;kua&#39; => -16412, &#39;kuai&#39; => -16407, &#39;kuan&#39; => -16403, &#39;kuang&#39; => -16401, &#39;kui&#39; => -16393, &#39;kun&#39; => -16220, &#39;kuo&#39; => -16216,
        &#39;la&#39; => -16212, &#39;lai&#39; => -16205, &#39;lan&#39; => -16202, &#39;lang&#39; => -16187, &#39;lao&#39; => -16180, &#39;le&#39; => -16171, &#39;lei&#39; => -16169, &#39;leng&#39; => -16158, &#39;li&#39; => -16155, &#39;lia&#39; => -15959, &#39;lian&#39; => -15958, &#39;liang&#39; => -15944, &#39;liao&#39; => -15933, &#39;lie&#39; => -15920, &#39;lin&#39; => -15915, &#39;ling&#39; => -15903, &#39;liu&#39; => -15889,
        &#39;long&#39; => -15878, &#39;lou&#39; => -15707, &#39;lu&#39; => -15701, &#39;lv&#39; => -15681, &#39;luan&#39; => -15667, &#39;lue&#39; => -15661, &#39;lun&#39; => -15659, &#39;luo&#39; => -15652,
        &#39;ma&#39; => -15640, &#39;mai&#39; => -15631, &#39;man&#39; => -15625, &#39;mang&#39; => -15454, &#39;mao&#39; => -15448, &#39;me&#39; => -15436, &#39;mei&#39; => -15435, &#39;men&#39; => -15419, &#39;meng&#39; => -15416, &#39;mi&#39; => -15408, &#39;mian&#39; => -15394, &#39;miao&#39; => -15385, &#39;mie&#39; => -15377, &#39;min&#39; => -15375, &#39;ming&#39; => -15369, &#39;miu&#39; => -15363, &#39;mo&#39; => -15362, &#39;mou&#39; => -15183, &#39;mu&#39; => -15180,
        &#39;na&#39; => -15165, &#39;nai&#39; => -15158, &#39;nan&#39; => -15153, &#39;nang&#39; => -15150, &#39;nao&#39; => -15149, &#39;ne&#39; => -15144, &#39;nei&#39; => -15143, &#39;nen&#39; => -15141, &#39;neng&#39; => -15140, &#39;ni&#39; => -15139, &#39;nian&#39; => -15128, &#39;niang&#39; => -15121, &#39;niao&#39; => -15119, &#39;nie&#39; => -15117, &#39;nin&#39; => -15110, &#39;ning&#39; => -15109, &#39;niu&#39; => -14941,
        &#39;nong&#39; => -14937, &#39;nu&#39; => -14933, &#39;nv&#39; => -14930, &#39;nuan&#39; => -14929, &#39;nue&#39; => -14928, &#39;nuo&#39; => -14926,
        &#39;o&#39; => -14922, &#39;ou&#39; => -14921,
        &#39;pa&#39; => -14914, &#39;pai&#39; => -14908, &#39;pan&#39; => -14902, &#39;pang&#39; => -14894, &#39;pao&#39; => -14889, &#39;pei&#39; => -14882, &#39;pen&#39; => -14873, &#39;peng&#39; => -14871, &#39;pi&#39; => -14857, &#39;pian&#39; => -14678, &#39;piao&#39; => -14674, &#39;pie&#39; => -14670, &#39;pin&#39; => -14668, &#39;ping&#39; => -14663, &#39;po&#39; => -14654, &#39;pu&#39; => -14645,
        &#39;qi&#39; => -14630, &#39;qia&#39; => -14594, &#39;qian&#39; => -14429, &#39;qiang&#39; => -14407, &#39;qiao&#39; => -14399, &#39;qie&#39; => -14384, &#39;qin&#39; => -14379, &#39;qing&#39; => -14368, &#39;qiong&#39; => -14355, &#39;qiu&#39; => -14353, &#39;qu&#39; => -14345, &#39;quan&#39; => -14170, &#39;que&#39; => -14159, &#39;qun&#39; => -14151,
        &#39;ran&#39; => -14149, &#39;rang&#39; => -14145, &#39;rao&#39; => -14140, &#39;re&#39; => -14137, &#39;ren&#39; => -14135, &#39;reng&#39; => -14125, &#39;ri&#39; => -14123, &#39;rong&#39; => -14122, &#39;rou&#39; => -14112, &#39;ru&#39; => -14109, &#39;ruan&#39; => -14099, &#39;rui&#39; => -14097, &#39;run&#39; => -14094, &#39;ruo&#39; => -14092,
        &#39;sa&#39; => -14090, &#39;sai&#39; => -14087, &#39;san&#39; => -14083, &#39;sang&#39; => -13917, &#39;sao&#39; => -13914, &#39;se&#39; => -13910, &#39;sen&#39; => -13907, &#39;seng&#39; => -13906, &#39;sha&#39; => -13905, &#39;shai&#39; => -13896, &#39;shan&#39; => -13894, &#39;shang&#39; => -13878, &#39;shao&#39; => -13870, &#39;she&#39; => -13859, &#39;shen&#39; => -13847, &#39;sheng&#39; => -13831, &#39;shi&#39; => -13658, &#39;shou&#39; => -13611, &#39;shu&#39; => -13601, &#39;shua&#39; => -13406, &#39;shuai&#39; => -13404, &#39;shuan&#39; => -13400, &#39;shuang&#39; => -13398, &#39;shui&#39; => -13395, &#39;shun&#39; => -13391, &#39;shuo&#39; => -13387, &#39;si&#39; => -13383, &#39;song&#39; => -13367, &#39;sou&#39; => -13359, &#39;su&#39; => -13356, &#39;suan&#39; => -13343, &#39;sui&#39; => -13340, &#39;sun&#39; => -13329, &#39;suo&#39; => -13326,
        &#39;ta&#39; => -13318, &#39;tai&#39; => -13147, &#39;tan&#39; => -13138, &#39;tang&#39; => -13120, &#39;tao&#39; => -13107, &#39;te&#39; => -13096, &#39;teng&#39; => -13095, &#39;ti&#39; => -13091, &#39;tian&#39; => -13076, &#39;tiao&#39; => -13068, &#39;tie&#39; => -13063, &#39;ting&#39; => -13060, &#39;tong&#39; => -12888, &#39;tou&#39; => -12875, &#39;tu&#39; => -12871, &#39;tuan&#39; => -12860, &#39;tui&#39; => -12858, &#39;tun&#39; => -12852, &#39;tuo&#39; => -12849,
        &#39;wa&#39; => -12838, &#39;wai&#39; => -12831, &#39;wan&#39; => -12829, &#39;wang&#39; => -12812, &#39;wei&#39; => -12802, &#39;wen&#39; => -12607, &#39;weng&#39; => -12597, &#39;wo&#39; => -12594, &#39;wu&#39; => -12585,
        &#39;xi&#39; => -12556, &#39;xia&#39; => -12359, &#39;xian&#39; => -12346, &#39;xiang&#39; => -12320, &#39;xiao&#39; => -12300, &#39;xie&#39; => -12120, &#39;xin&#39; => -12099, &#39;xing&#39; => -12089, &#39;xiong&#39; => -12074, &#39;xiu&#39; => -12067, &#39;xu&#39; => -12058, &#39;xuan&#39; => -12039, &#39;xue&#39; => -11867, &#39;xun&#39; => -11861,
        &#39;ya&#39; => -11847, &#39;yan&#39; => -11831, &#39;yang&#39; => -11798, &#39;yao&#39; => -11781, &#39;ye&#39; => -11604, &#39;yi&#39; => -11589, &#39;yin&#39; => -11536, &#39;ying&#39; => -11358, &#39;yo&#39; => -11340, &#39;yong&#39; => -11339, &#39;you&#39; => -11324, &#39;yu&#39; => -11303, &#39;yuan&#39; => -11097, &#39;yue&#39; => -11077, &#39;yun&#39; => -11067,
        &#39;za&#39; => -11055, &#39;zai&#39; => -11052, &#39;zan&#39; => -11045, &#39;zang&#39; => -11041, &#39;zao&#39; => -11038, &#39;ze&#39; => -11024, &#39;zei&#39; => -11020, &#39;zen&#39; => -11019, &#39;zeng&#39; => -11018, &#39;zha&#39; => -11014, &#39;zhai&#39; => -10838, &#39;zhan&#39; => -10832, &#39;zhang&#39; => -10815, &#39;zhao&#39; => -10800, &#39;zhe&#39; => -10790, &#39;zhen&#39; => -10780, &#39;zheng&#39; => -10764, &#39;zhi&#39; => -10587, &#39;zhong&#39; => -10544, &#39;zhou&#39; => -10533, &#39;zhu&#39; => -10519, &#39;zhua&#39; => -10331, &#39;zhuai&#39; => -10329, &#39;zhuan&#39; => -10328, &#39;zhuang&#39; => -10322, &#39;zhui&#39; => -10315, &#39;zhun&#39; => -10309, &#39;zhuo&#39; => -10307, &#39;zi&#39; => -10296, &#39;zong&#39; => -10281, &#39;zou&#39; => -10274, &#39;zu&#39; => -10270, &#39;zuan&#39; => -10262,
        &#39;zui&#39; => -10260, &#39;zun&#39; => -10256, &#39;zuo&#39; => -10254
    );
 
 
    /**
     * 获取全部拼音，返回拼音的数组,如 &#39;张三丰&#39;  ==>  [&#39;zhang&#39;,&#39;san&#39;,&#39;feng&#39;]
     * @param $chinese
     * @param string $charset
     * @return array
     */
    public function get_all_py($chinese, $charset = &#39;utf-8&#39;)
    {
        if ($charset != &#39;gb2312&#39;) $chinese = $this->_U2_Utf8_Gb($chinese);
        $py = $this->zh_to_pys($chinese);
 
        return $py;
    }
 
    /**
     * 获取拼音首字母，如[&#39;zhang&#39;,&#39;san&#39;,&#39;feng&#39;]  ==> zsf
     * @param $all_pys
     * @return string
     */
    public function get_first_py($all_pys)
    {
        if (count($all_pys) <= 0) {
            return &#39;&#39;;
        }
 
        $result = [];
        foreach ($all_pys as $one) {
            if (is_null($one) || strlen($one) <= 0) {
                continue;
            }
            $result[] = substr($one, 0, 1);
        }
 
        return join(&#39;&#39;, $result);
    }
 
    /**
     * 获取拼音首字母，如[&#39;zhang&#39;,&#39;san&#39;,&#39;feng&#39;]  ==> z
     * @param $all_pys
     * @return string
     */
    public function get_first_letter($all_pys)
    {
        if (count($all_pys) <= 0) {
            return &#39;&#39;;
        }
 
        foreach ($all_pys as $one) {
            if (is_null($one) || strlen($one) <= 0) {
                continue;
            }
            return substr($one, 0, 1);
        }
 
        return &#39;&#39;;
    }
 
    private function _U2_Utf8_Gb($_C)
    {
        $_String = &#39;&#39;;
        if ($_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(&#39;UTF-8&#39;, &#39;GB2312&#39;, $_String);
    }
 
    private function zh_to_py($num, $blank = &#39;&#39;)
    {
        if ($num > 0 && $num < 160) {
            return chr($num);
        } elseif ($num < -20319 || $num > -10247) {
            return $blank;
        } else {
            foreach ($this->dict_list as $py => $code) {
                if ($code > $num) break;
                $result = $py;
            }
            return $result;
        }
    }
 
    private function zh_to_pys($chinese)
    {
        $result = array();
        for ($i = 0; $i < strlen($chinese); $i++) {
            $p = ord(substr($chinese, $i, 1));
            if ($p > 160) {
                $q = ord(substr($chinese, ++$i, 1));
                $p = $p * 256 + $q - 65536;
            }
            $result[] = $this->zh_to_py($p);
        }
        return $result;
    }
}