首页  >  文章  >  后端开发  >  PHP汉字转拼音的两种方法+PHP提取汉字(中文)方法_PHP教程

PHP汉字转拼音的两种方法+PHP提取汉字(中文)方法_PHP教程

WBOY
WBOY原创
2016-07-13 10:29:151045浏览

方法一:根据ASCII码转换,GB2312库对多音字也无能为力。

GB2312标准共收录6763个汉字,不在范围内的汉字是无法转换,如:中国前总理朱镕基的“镕”字。

GB2312中对所收汉字进行了“分区”处理,每区含有94个汉字/符号。这种表示方式也称为区位码。
01-09区为特殊符号。
16-55区为一级汉字,按拼音排序。(3755个)
56-87区为二级汉字,按部首/笔画排序。(3008个)
10-15区及88-94区则未有编码。
占用的码位是72*94=6768。其中有5个空位是D7FA-D7FE。所以实际共6763个汉字。其中一级汉字3755个,二级汉字3008个。而此类算法实际只能转换3755个汉字。


优点:没有使用大文字库,文件相对较小,没有使用正则表达式,性能相对较高。支持首字母转换。
缺点:没有在GB2312中收录的汉字无法转换,多音字无法识别。
(如果对拼音转换要求不高的朋友,建议使用这个。)

 

[php] view plaincopy在CODE上查看代码片派生到我的代码片
 
  •   
  • // 此类是根据ASCII码转换,GB2312库对多音字也无能为力。  
  • // GB2312标准共收录6763个汉字,不在范围内的汉字是无法转换,如:中国前总理朱镕基的“镕”字。  
  • class pinyin{  
  •     public static function utf8_to($s, $isfirst = false) {  
  •         return self::to(self::utf8_to_gb2312($s), $isfirst);  
  •     }  
  •   
  •     public static function utf8_to_gb2312($s) {  
  •         return iconv('UTF-8', 'GB2312//IGNORE', $s);  
  •     }  
  •   
  •     // 字符串必须为GB2312编码  
  •     public static function to($s, $isfirst = false) {  
  •         $res = '';  
  •         $len = strlen($s);  
  •         $pinyin_arr = self::get_pinyin_array();  
  •         for($i=0; $i
  •             $ascii = ord($s{$i});  
  •             if($ascii > 0x80) {  
  •                 $ascii2 = ord($s{++$i});  
  •                 $ascii = $ascii * 256 + $ascii2 - 65536;  
  •             }  
  •   
  •             if($ascii  0) {  
  •                 if(($ascii >= 48 && $ascii = 97 && $ascii 
  •                     $res .= $s{$i}; // 0-9 a-z  
  •                 }elseif($ascii >= 65 && $ascii 
  •                     $res .= strtolower($s{$i}); // A-Z  
  •                 }else{  
  •                     $res .= '_';  
  •                 }  
  •             }elseif($ascii  -10247) {  
  •                 $res .= '_';  
  •             }else{  
  •                 foreach($pinyin_arr as $py=>$asc) {  
  •                     if($asc 
  •                         $res .= $isfirst ? $py{0} : $py;  
  •                         break;  
  •                     }  
  •                 }  
  •             }  
  •         }  
  •         return $res;  
  •     }  
  •   
  •     public static function to_first($s) {  
  •         $ascii = ord($s{0});  
  •         if($ascii > 0xE0) {  
  •             $s = self::utf8_to_gb2312($s{0}.$s{1}.$s{2});  
  •         }elseif($ascii 
  •             if($ascii >= 65 && $ascii 
  •                 return strtolower($s{0});  
  •             }elseif($ascii >= 97 && $ascii 
  •                 return $s{0};  
  •             }else{  
  •                 return false;  
  •             }  
  •         }  
  •   
  •         if(strlen($s) 
  •             return false;  
  •         }  
  •   
  •         $asc = ord($s{0}) * 256 + ord($s{1}) - 65536;  
  •   
  •         if($asc>=-20319 && $asc
  •         if($asc>=-20283 && $asc
  •         if($asc>=-19775 && $asc
  •         if($asc>=-19218 && $asc
  •         if($asc>=-18710 && $asc
  •         if($asc>=-18526 && $asc
  •         if($asc>=-18239 && $asc
  •         if($asc>=-17922 && $asc
  •         if($asc>=-17417 && $asc
  •         if($asc>=-16474 && $asc
  •         if($asc>=-16212 && $asc
  •         if($asc>=-15640 && $asc
  •         if($asc>=-15165 && $asc
  •         if($asc>=-14922 && $asc
  •         if($asc>=-14914 && $asc
  •         if($asc>=-14630 && $asc
  •         if($asc>=-14149 && $asc
  •         if($asc>=-14090 && $asc
  •         if($asc>=-13318 && $asc
  •         if($asc>=-12838 && $asc
  •         if($asc>=-12556 && $asc
  •         if($asc>=-11847 && $asc
  •         if($asc>=-11055 && $asc
  •         return false;  
  •     }  
  •   
  •     public static function get_pinyin_array() {  
  •         static $py_arr;  
  •         if(isset($py_arr)) return $py_arr;  
  •   
  •         $k = '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';  
  •         $v = '-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';  
  •         $key = explode('|', $k);  
  •         $val = explode('|', $v);  
  •         $py_arr = array_combine($key, $val);  
  •         arsort($py_arr);  
  •   
  •         return $py_arr;  
  •     }  
  • }  
  •   
  • /* 
  • var_dump(0xE0); 
  • for($i=0; $i
  •     var_dump("$i :". chr($i)); 
  • */  
  •   
  • var_dump(pinyin::utf8_to('PHP汉字转拼音类'));  
  • var_dump(pinyin::utf8_to('GB2312标准共收录6763个汉字,不在范围内的汉字是无法转换,如:中国前总理朱镕基的“镕”字。'));  
  • var_dump(pinyin::utf8_to('`1234567890-=QWERTYUIOP[]ASDFGHJKL;ZXCVBNM,./abcdefghijklmnopqrstuvwxyz'));  
  •   
  •  
  • var_dump(pinyin::utf8_to('PHP汉字转拼音类', 1));  
  • var_dump(pinyin::utf8_to('GB2312标准共收录6763个汉字,不在范围内的汉字是无法转换,如:中国前总理朱镕基的“镕”字。', 1));  
  • var_dump(pinyin::utf8_to('`1234567890-=QWERTYUIOP[]ASDFGHJKL;ZXCVBNM,./abcdefghijklmnopqrstuvwxyz', 1));  
  •   
  • var_dump(pinyin::to_first('PHP汉字转拼音类'));  
  • var_dump(pinyin::to_first('GB2312标准共收录6763个汉字,不在范围内的汉字是无法转换,如:中国前总理朱镕基的“镕”字。'));  
  • var_dump(pinyin::to_first('▂`1234567890-=QWERTYUIOP[]ASDFGHJKL;ZXCVBNM,./abcdefghijklmnopqrstuvwxyz'));  
  •   
  • ?>  

  • 方法二:根据拼音组合数组检索

     

     

    [php] view plaincopy在CODE上查看代码片派生到我的代码片
     
  • class pinyin{  
  •     private $d=array(  
  •        array("a",-20319),  
  •        array("ai",-20317),  
  •        array("an",-20304),  
  •        array("ang",-20295),  
  •        array("ao",-20292),  
  •        array("ba",-20283),  
  •        array("bai",-20265),  
  •        array("ban",-20257),  
  •        array("bang",-20242),  
  •        array("bao",-20230),  
  •        array("bei",-20051),  
  •        array("ben",-20036),  
  •        array("beng",-20032),  
  •        array("bi",-20026),  
  •        array("bian",-20002),  
  •        array("biao",-19990),  
  •        array("bie",-19986),  
  •        array("bin",-19982),  
  •        array("bing",-19976),  
  •        array("bo",-19805),  
  •        array("bu",-19784),  
  • 声明:
    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