+ -
当前位置:首页 → 问答吧 → 一个将汉字翻译成拼音的类,很好用,而且还可以自动识别编码

一个将汉字翻译成拼音的类,很好用,而且还可以自动识别编码

时间:2009-12-24

来源:互联网

今天看到人家的程序可以将汉字翻译成拼音,觉得很酷,于是上网找了一个可以实现此功能的函数,但是不能自动识别编码,于是了,我又上网找了一个自动识别编码的函数,于是将他们整合到一个类里面,现在贴出来,大家分享一下,虽然拼音翻译功能不常用,但是有时候还是可以用用的,虽然都是些小功能,但是会让程序更加人性化。
复制代码
  1. <?php
  2. class pinyin{
  3. function pinyin($string=""){
  4.     return $this -> cntoPinyin($string,$this -> checkEncoding($string));
  5. }
  6. function checkEncoding($string,$outEncoding = 'UTF-8'){
  7.     $encoding = "UTF-8";
  8.     for($i=0;$i<strlen($string);$i++){
  9.         if(ord($string{$i})<128)
  10.             continue;
  11.         if((ord($string{$i})&224)==224){
  12.             //第一个字节判断通过
  13.             $char = $string{++$i};
  14.             if((ord($char)&128)==128){
  15.                 //第二个字节判断通过
  16.                 $char = $string{++$i};
  17.                 if((ord($char)&128)==128){
  18.                     $encoding = "UTF-8";
  19.                     break;
  20.                 }
  21.             }
  22.         }
  23.         if((ord($string{$i})&192)==192){
  24.             //第一个字节判断通过
  25.             $char = $string{++$i};
  26.             if((ord($char)&128)==128){
  27.                 //第二个字节判断通过
  28.                 $encoding = "gb2312";
  29.                 break;
  30.             }
  31.         }
  32.     }
  33.     return $encoding;
  34. }
  35. function cntoPinyin($_String, $_Code='gb2312')
  36. {
  37.         $_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".
  38.                 "|chai|chan|chang|chao|che|chen|cheng|chi|chong|chou|chu|chuai|chuan|chuang|chui|chun|chuo|ci|cong|cou|cu|".
  39.                 "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".
  40.                 "|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".
  41.                 "|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".
  42.                 "|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".
  43.                 "|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".
  44.                 "|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".
  45.                 "|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".
  46.                 "|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".
  47.                 "|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|".
  48.                 "she|shen|sheng|shi|shou|shu|shua|shuai|shuan|shuang|shui|shun|shuo|si|song|sou|su|suan|sui|sun|suo|ta|tai|".
  49.                 "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".
  50.                 "|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".
  51.                 "|yu|yuan|yue|yun|za|zai|zan|zang|zao|ze|zei|zen|zeng|zha|zhai|zhan|zhang|zhao|zhe|zhen|zheng|zhi|zhong|".
  52.                 "zhou|zhu|zhua|zhuai|zhuan|zhuang|zhui|zhun|zhuo|zi|zong|zou|zu|zuan|zui|zun|zuo";
  53.         $_DataValue = "-20319|-20317|-20304|-20295|-20292|-20283|-20265|-20257|-20242|-20230|-20051|-20036|-20032|-20026|-20002|-19990".
  54.                 "|-19986|-19982|-19976|-19805|-19784|-19775|-19774|-19763|-19756|-19751|-19746|-19741|-19739|-19728|-19725".
  55.                 "|-19715|-19540|-19531|-19525|-19515|-19500|-19484|-19479|-19467|-19289|-19288|-19281|-19275|-19270|-19263".
  56.                 "|-19261|-19249|-19243|-19242|-19238|-19235|-19227|-19224|-19218|-19212|-19038|-19023|-19018|-19006|-19003".
  57.                 "|-18996|-18977|-18961|-18952|-18783|-18774|-18773|-18763|-18756|-18741|-18735|-18731|-18722|-18710|-18697".
  58.                 "|-18696|-18526|-18518|-18501|-18490|-18478|-18463|-18448|-18447|-18446|-18239|-18237|-18231|-18220|-18211".
  59.                 "|-18201|-18184|-18183|-18181|-18012|-17997|-17988|-17970|-17964|-17961|-17950|-17947|-17931|-17928|-17922".
  60.                 "|-17759|-17752|-17733|-17730|-17721|-17703|-17701|-17697|-17692|-17683|-17676|-17496|-17487|-17482|-17468".
  61.                 "|-17454|-17433|-17427|-17417|-17202|-17185|-16983|-16970|-16942|-16915|-16733|-16708|-16706|-16689|-16664".
  62.                 "|-16657|-16647|-16474|-16470|-16465|-16459|-16452|-16448|-16433|-16429|-16427|-16423|-16419|-16412|-16407".
  63.                 "|-16403|-16401|-16393|-16220|-16216|-16212|-16205|-16202|-16187|-16180|-16171|-16169|-16158|-16155|-15959".
  64.                 "|-15958|-15944|-15933|-15920|-15915|-15903|-15889|-15878|-15707|-15701|-15681|-15667|-15661|-15659|-15652".
  65.                 "|-15640|-15631|-15625|-15454|-15448|-15436|-15435|-15419|-15416|-15408|-15394|-15385|-15377|-15375|-15369".
  66.                 "|-15363|-15362|-15183|-15180|-15165|-15158|-15153|-15150|-15149|-15144|-15143|-15141|-15140|-15139|-15128".
  67.                 "|-15121|-15119|-15117|-15110|-15109|-14941|-14937|-14933|-14930|-14929|-14928|-14926|-14922|-14921|-14914".
  68.                 "|-14908|-14902|-14894|-14889|-14882|-14873|-14871|-14857|-14678|-14674|-14670|-14668|-14663|-14654|-14645".
  69.                 "|-14630|-14594|-14429|-14407|-14399|-14384|-14379|-14368|-14355|-14353|-14345|-14170|-14159|-14151|-14149".
  70.                 "|-14145|-14140|-14137|-14135|-14125|-14123|-14122|-14112|-14109|-14099|-14097|-14094|-14092|-14090|-14087".
  71.                 "|-14083|-13917|-13914|-13910|-13907|-13906|-13905|-13896|-13894|-13878|-13870|-13859|-13847|-13831|-13658".
  72.                 "|-13611|-13601|-13406|-13404|-13400|-13398|-13395|-13391|-13387|-13383|-13367|-13359|-13356|-13343|-13340".
  73.                 "|-13329|-13326|-13318|-13147|-13138|-13120|-13107|-13096|-13095|-13091|-13076|-13068|-13063|-13060|-12888".
  74.                 "|-12875|-12871|-12860|-12858|-12852|-12849|-12838|-12831|-12829|-12812|-12802|-12607|-12597|-12594|-12585".
  75.                 "|-12556|-12359|-12346|-12320|-12300|-12120|-12099|-12089|-12074|-12067|-12058|-12039|-11867|-11861|-11847".
  76.                 "|-11831|-11798|-11781|-11604|-11589|-11536|-11358|-11340|-11339|-11324|-11303|-11097|-11077|-11067|-11055".
  77.                 "|-11052|-11045|-11041|-11038|-11024|-11020|-11019|-11018|-11014|-10838|-10832|-10815|-10800|-10790|-10780".
  78.                 "|-10764|-10587|-10544|-10533|-10519|-10331|-10329|-10328|-10322|-10315|-10309|-10307|-10296|-10281|-10274".
  79.                 "|-10270|-10262|-10260|-10256|-10254";
  80.         $_TDataKey   = explode('|', $_DataKey);
  81.         $_TDataValue = explode('|', $_DataValue);
  82.         $_String = strtolower($_String);
  83.         $_Data = (PHP_VERSION>='5.0') ? array_combine($_TDataKey, $_TDataValue) : _Array_Combine($_TDataKey, $_TDataValue);
  84.         arsort($_Data);
  85.         reset($_Data);
  86.         if($_Code != 'gb2312') $_String = $this -> _U2_Utf8_Gb($_String);
  87.         $_Res = '';
  88.         for($i=0; $i<strlen($_String); $i++)
  89.         {
  90.                 $_P = ord(substr($_String, $i, 1));
  91.                 if($_P>160) { $_Q = ord(substr($_String, ++$i, 1)); $_P = $_P*256 + $_Q - 65536; }
  92.                 $_Res .= $this -> _Pinyin($_P, $_Data);
  93.         }
  94.         return preg_replace("/[^a-z0-9-_]*/", '', $_Res);
  95. }
  96. function _Pinyin($_Num, $_Data)
  97. {
  98.         if    ($_Num>0      && $_Num<160   ) return chr($_Num);
  99.         elseif($_Num<-20319 || $_Num>-10247) return '';
  100.         else {
  101.                 foreach($_Data as $k=>$v){ if($v<=$_Num) break; }
  102.                 return $k;
  103.         }
  104. }
  105. function _U2_Utf8_Gb($_C)
  106. {
  107.         $_String = '';
  108.         if($_C < 0x80) $_String .= $_C;
  109.         elseif($_C < 0x800)
  110.         {
  111.                 $_String .= chr(0xC0 | $_C>>6);
  112.                 $_String .= chr(0x80 | $_C & 0x3F);
  113.         }elseif($_C < 0x10000){
  114.                 $_String .= chr(0xE0 | $_C>>12);
  115.                 $_String .= chr(0x80 | $_C>>6 & 0x3F);
  116.                 $_String .= chr(0x80 | $_C & 0x3F);
  117.         } elseif($_C < 0x200000) {
  118.                 $_String .= chr(0xF0 | $_C>>18);
  119.                 $_String .= chr(0x80 | $_C>>12 & 0x3F);
  120.                 $_String .= chr(0x80 | $_C>>6 & 0x3F);
  121.                 $_String .= chr(0x80 | $_C & 0x3F);
  122.         }
  123.         return iconv('UTF-8', 'GB2312', $_String);
  124. }
  125. function _Array_Combine($_Arr1, $_Arr2){
  126.         for($i=0; $i<count($_Arr1); $i++) $_Res[$_Arr1[$i]] = $_Arr2[$i];
  127.         return $_Res;
  128.     }
  129. }
  130. //调用方法
  131. $pinyin = new pinyin();
  132. echo $pinyin -> pinyin("媒体-报道_采访wo");
  133. //输出结果为 meiti-baodao_caifangwo
  134. ?>

作者: mylanglang   发布时间: 2009-12-24

收下了,谢谢。

作者: moro   发布时间: 2009-12-25

ascii

作者: cain   发布时间: 2009-12-25

下了,谢谢。  

作者: php初学者   发布时间: 2009-12-25

收藏先

作者: ^淡如清风   发布时间: 2009-12-29