php汉字转拼音首字母问题。

PHP获取拼音首字母

程序运行后，发现字符串中有些文字转换不了。如果是单独输入这些字，直接去转换可以读取出拼音开头字母。
在字符串中就不行。程序代码如下：
 
 function getfirstchar($s0){     

     $fchar = ord($s0{0});  

     if($fchar >= ord("a") and $fchar 
     $s1 = iconv("UTF-8","gb2312", $s0);  

     $s2 = iconv("gb2312","UTF-8", $s1);  

     if($s2 == $s0){$s = $s1;}else{$s = $s0;}  

     $asc = ord($s{0}) * 256 + ord($s{1}) - 65536;  

     if($asc >= -20319 and $asc 
     if($asc >= -20283 and $asc 
     if($asc >= -19775 and $asc 
     if($asc >= -19218 and $asc   
     if($asc >= -18710 and $asc 
     if($asc >= -18526 and $asc 
     if($asc >= -18239 and $asc 
     if($asc >= -17922 and $asc 
     if($asc >= -17417 and $asc 
     if($asc >= -16474 and $asc 
     if($asc >= -16212 and $asc 
     if($asc >= -15640 and $asc 
     if($asc >= -15165 and $asc 
     if($asc >= -14922 and $asc 
     if($asc >= -14914 and $asc 
     if($asc >= -14630 and $asc 
     if($asc >= -14149 and $asc 
     if($asc >= -14090 and $asc 
     if($asc >= -13318 and $asc 
     if($asc >= -12838 and $asc    
     if($asc >= -12556 and $asc 
     if($asc >= -11847 and $asc 
     if($asc >= -11055 and $asc 
     return null;  

 }   

 function pinyin1($zh){  

     $ret = "";  

     $s1 = iconv("UTF-8","gb2312", $zh);  

     $s2 = iconv("gb2312","UTF-8", $s1);  

     if($s2 == $zh){$zh = $s1;}  

     for($i = 0; $i 
         $s1 = substr($zh,$i,1);  

         $p = ord($s1); 

         if($p > 160){  

             $s2 = substr($zh,$i++,2);  

             $ret .= getfirstchar($s2); 

         }else{  

             $ret .= $s1;  

         }  

     }  

     return $ret;  

 }  

 echo "邮政路小学";  

 echo pinyin1('邮政路小学');    

 ?> 
输出结果为：邮政路小学YZLX  

单独输入小字，用getfirstchar("小")可以转换成功。      

回复讨论(解决方案)

你的算法只适用于 gb2312 一级字库
没有研习的必要

用qq提供的词典

<?php  if ( ! defined('BASEPATH')) exit('No direct script access allowed');    /**     *     * 汉字转换拼音函数     *     * @param $str string 需要转换的字符串     * @param $ishead bool 是否只显示第一个字母     * @param $ucfirst bool 是否第一个字母大写,默认为以下划线分割字之间:eg wo_men_da_jia，如果第三个参数是TRUE则为驼峰式     * @return String 把汉字转化为拼音的字符串     */    function GetPinyin($str,$ishead = FALSE,$ucfirst = FALSE)    {        $pinyins = array();        $restr = '';        $str = trim(iconv('UTF-8','GB2312',$str));        $slen = strlen($str);        if($slen<2)        {            return $str;        }        if(count($pinyins)==0)        {            $fp = fopen(APPPATH.'/resources/pinyin.dat','r');            while(!feof($fp))            {                $line = trim(fgets($fp));                $pinyins[$line[0].$line[1]] = substr($line,3,strlen($line)-3);            }            fclose($fp);        }        for($i=0;$i<$slen;$i++)        {            if(ord($str[$i])>0x80)            {                $c = $str[$i].$str[$i+1];                $i++;                if(isset($pinyins[$c]))                {                    if( ! $ishead AND $ucfirst)                    {                        $restr .= ucfirst($pinyins[$c]);                    }                    elseif( ! $ishead AND ! $ucfirst)                    {                        $restr .= '_'.$pinyins[$c];                    }                    else                    {                        $restr .= $pinyins[$c][0];                    }                }                else                {                    $restr .= "_";                }            }            else if( preg_match("/[a-z0-9]/",$str[$i]) )            {                $restr .= $str[$i];            }            else            {                $restr .= "_";            }        }        if($restr[0] == '_')        {            return substr($restr,1);        }        else        {            return $restr;        }    }/* End of file pinyin_helper.php *//* Location ./application/helpers/pinyin_helper.php */

function Pinyin($_String,$_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,  $_TDataValue) : _Array_Combine($_TDataKey, $_TDataValue);         arsort($_Data);         reset($_Data);          if($_Code != 'gb2312') $_String = _U2_Utf8_Gb($_String);         $_Res = '';         for($i=0; $i<strlen($_String); $i++)         {                 $_P = ord(substr($_String, $i, 1));                 if($_P>160) { $_Q = ord(substr($_String, ++$i, 1)); $_P = $_P*256 + $_Q - 65536; }                 $_Res .= _Pinyin($_P, $_Data);         }         return preg_replace("/[^a-z0-9]*/",'', $_Res); }  function _Pinyin($_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 $k;         } }  function _U2_Utf8_Gb($_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', $_String); }  function _Array_Combine($_Arr1, $_Arr2) {         for($i=0; $i<count($_Arr1); $i++) $_Res[$_Arr1[$i]] = $_Arr2[$i];         return $_Res; } echo Pinyin('山东菏泽牡丹区'); //默认是gb编码echo Pinyin('这是中国山东菏泽牡丹区',1); //第二个参数随意设置即为utf8编码?>

谢谢。我试试

用qq提供的词典

词典在哪，给个下载地址啊。。。源码中bat地址换上去就可以了吗

pinyin.dat 下载地址搜索
http://www.baidu.com/s?wd=pinyin.dat&ie=utf-8