PHP将汉字转换为拼音及获取词语首字母的方法

墨辰丷
发布: 2018-05-18 13:37:35
原创
3442人浏览过

这篇文章主要介绍了php将汉字转换为拼音及获取词语首字母的方法,涉及php字符串、数组的遍历及编码转换相关操作技巧,需要的朋友可以参考下

具体如下:

最近要开发将汉字转换为拼音和得到首字的功能记录下来哈子:呵呵~

class Pinyin{
  private $_outEncoding = "GB2312";
  public function getPinyin($str,$pix=' ',$code = 'gb2312'){
    $_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";
    $_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";
    $_TDataKey = explode ( '|', $_DataKey );
    $_TDataValue = explode ( '|', $_DataValue );
    $data = (PHP_VERSION >= '5.0') ? array_combine ( $_TDataKey, $_TDataValue ) : $this->_Array_Combine( $_TDataKey, $_TDataValue );
    arsort ( $data );
    reset ( $data );
    $str = $this->safe_encoding ( $str );
    $_Res = '';
    for($i = 0; $i < strlen ( $str ); $i ++) {
      $_P = ord ( substr ( $str, $i, 1 ) );
      if ($_P > 160) {
        $_Q = ord ( substr ( $str, ++ $i, 1 ) );
        $_P = $_P * 256 + $_Q - 65536;
      }
      $_Res .= $this->_Pinyin ( $_P, $data ).$pix;
    }
    return preg_replace ( "/[^a-z0-9".$pix."]*/", '', $_Res );
  }
  private function _Pinyin($_Num, $_Data) {
    if ($_Num > 0 && $_Num < 160)
      return chr ( $_Num );
    elseif ($_Num < - 20319 || $_Num > - 10247)
      return '';
    else {
      foreach ( $_Data as $k => $v ) {
        if ($v <= $_Num)
          break;
      }
      return $k;
    }
  }
  public function getFirstChar($str=''){
    if( !$str ) return null;
    $fchar=ord($str{0});
    if($fchar>=ord("A") and $fchar<=ord("z") )return strtoupper($str{0});
    $s= $this->safe_encoding($str);
    $asc=ord($s{0})*256+ord($s{1})-65536;
    if($asc>=-20319 and $asc<=-20284)return "A";
    if($asc>=-20283 and $asc<=-19776)return "B";
    if($asc>=-19775 and $asc<=-19219)return "C";
    if($asc>=-19218 and $asc<=-18711)return "D";
    if($asc>=-18710 and $asc<=-18527)return "E";
    if($asc>=-18526 and $asc<=-18240)return "F";
    if($asc>=-18239 and $asc<=-17923)return "G";
    if($asc>=-17922 and $asc<=-17418)return "H";
    if($asc>=-17417 and $asc<=-16475)return "J";
    if($asc>=-16474 and $asc<=-16213)return "K";
    if($asc>=-16212 and $asc<=-15641)return "L";
    if($asc>=-15640 and $asc<=-15166)return "M";
    if($asc>=-15165 and $asc<=-14923)return "N";
    if($asc>=-14922 and $asc<=-14915)return "O";
    if($asc>=-14914 and $asc<=-14631)return "P";
    if($asc>=-14630 and $asc<=-14150)return "Q";
    if($asc>=-14149 and $asc<=-14091)return "R";
    if($asc>=-14090 and $asc<=-13319)return "S";
    if($asc>=-13318 and $asc<=-12839)return "T";
    if($asc>=-12838 and $asc<=-12557)return "W";
    if($asc>=-12556 and $asc<=-11848)return "X";
    if($asc>=-11847 and $asc<=-11056)return "Y";
    if($asc>=-11055 and $asc<=-10247)return "Z";
    return null;
  }
  function safe_encoding($string) {
    $encoding="UTF-8";
    for($i=0;$i<strlen($string);$i++) {
      if(ord($string{$i})<128) continue;
      if((ord($string{$i})&224)==224) { //第一个字节判断通过
        $char=$string{++$i};
        if((ord($char)&128)==128) { //第二个字节判断通过
          $char=$string{++$i};
          if((ord($char)&128)==128) {
            $encoding="UTF-8";
            break;
          }
        }
      }
      if((ord($string{$i})&192)==192) { //第一个字节判断通过
        $char=$string{++$i};
        if((ord($char)&128)==128) { //第二个字节判断通过
          $encoding="GB2312";
          break;
        }
      }
    }
    if(strtoupper($encoding)==strtoupper($this->_outEncoding))
      return $string;
    else
      return iconv($encoding,$this->_outEncoding,$string);
  }
  private function _Array_Combine($_Arr1, $_Arr2){
    for($i = 0; $i < count ( $_Arr1 ); $i ++)
      $_Res [$_Arr1 [$i]] = $_Arr2 [$i];
    return $_Res;
  }
}
登录后复制

测试代码如下:

立即学习PHP免费学习笔记(深入)”;

$pinyin = new Pinyin();
echo $pinyin->getFirstChar("湖北武汉")."<br/>";
echo $pinyin->getPinyin("北上广")."<br/>";
echo $pinyin->getPinyin("火影")."<br/>";
echo $pinyin->getFirstChar("获得")."<br/>";
echo $pinyin->getFirstChar("TOM")."<br/>";
登录后复制

运行结果:

Find JSON Path Online
Find JSON Path Online

Easily find JSON paths within JSON objects using our intuitive Json Path Finder

Find JSON Path Online 193
查看详情 Find JSON Path Online

H
bei shang guang 
huo ying 
H
T
登录后复制

相关推荐:

php如何将汉字转换为拼音

Java 实现汉字转换为拼音的实例

php将汉字转换为拼音

以上就是PHP将汉字转换为拼音及获取词语首字母的方法的详细内容,更多请关注php中文网其它相关文章!

相关标签:
php
PHP速学教程(入门到精通)
PHP速学教程(入门到精通)

PHP怎么学习?PHP怎么入门?PHP在哪学?PHP怎么学才快?不用担心,这里为大家提供了PHP速学教程(入门到精通),有需要的小伙伴保存下载就能学习啦!

下载
来源:php中文网
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系admin@php.cn
作者最新文章
最新问题
开源免费商场系统广告
热门教程
更多>
最新下载
更多>
网站特效
网站源码
网站素材
前端模板
关于我们 免责申明 举报中心 意见反馈 讲师合作 广告合作 最新更新
php中文网:公益在线php培训,帮助PHP学习者快速成长!
关注服务号 技术交流群
PHP中文网订阅号
每天精选资源文章推送

Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号