汉字转换字母,可以取首字母,也可以取全拼

Posted on 2011-09-22 15:01  bingfeng  阅读(3132)  评论(0编辑  收藏  举报

工作需要,需要写个汉字转换成字符并取出首字母作为缩小,方便查询。因此就找资料研究,并完善一个转换方法,目前能实现:1.汉字转换成拼音

         2.转换的拼音可以取首字母,也可以取全拼

         3.带过滤功能,可以把制定的过滤汉字剔除。

         4.可以选择使用的编码,内置编码转换功能

         5.提供两种转换字母的方式,选择一种。

/***

*  $_String 要转换拼音的汉字

*  $_Code 使用的编码

*  $_type  使用的转换方式  1为使用字典方式(默认),2为使用编码范围方式

*/

类名:PingYin

初始化方法:Pinyin($_String, $_Code='gb2312',$_type=1)

实现基本思想:

 1.获取汉字字符串,选择使用的编码和转换方式

 2.内部指定过滤数组和要选出的前n个汉字的字母(指定输出n个汉字的首字母)

 3.判断编码,转换编码

 4.程序先过滤字符串中需要过滤掉得字符串或字符

 5.把每个汉字转换后取出首字母

 6.拼接字母,然后输出。

使用方法:

$str="你想要看到的字母";

  $appCom= new PinYin();

  $code= $appCom->PinYin($str,1,1);

   echo $code;

输出:nxy

  1 <?php
2 class PinYin extends Action{
3 /***
4 * $_String 要转换拼音的汉字
5 * $_Code 使用的编码
6 * $_type 使用的转换方式 1为使用字典方式(默认),2为使用编码范围方式
7 *
8 */
9
10 function Pinyin($_String, $_Code='gb2312',$_type=1){
11 $checkstr=array("内蒙古","内蒙","包头市","包头","昆区","昆都仑区","青山区","东河区","东河","青山","九原区","九原","郊区");
12 $len=3; //取字符串的长度
13 $_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".
14 "|chai|chan|chang|chao|che|chen|cheng|chi|chong|chou|chu|chuai|chuan|chuang|chui|chun|chuo|ci|cong|cou|cu|".
15 "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".
16 "|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".
17 "|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".
18 "|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".
19 "|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".
20 "|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".
21 "|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".
22 "|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".
23 "|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|".
24 "she|shen|sheng|shi|shou|shu|shua|shuai|shuan|shuang|shui|shun|shuo|si|song|sou|su|suan|sui|sun|suo|ta|tai|".
25 "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".
26 "|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".
27 "|yu|yuan|yue|yun|za|zai|zan|zang|zao|ze|zei|zen|zeng|zha|zhai|zhan|zhang|zhao|zhe|zhen|zheng|zhi|zhong|".
28 "zhou|zhu|zhua|zhuai|zhuan|zhuang|zhui|zhun|zhuo|zi|zong|zou|zu|zuan|zui|zun|zuo";
29 $_DataValue = "-20319|-20317|-20304|-20295|-20292|-20283|-20265|-20257|-20242|-20230|-20051|-20036|-20032|-20026|-20002|-19990".
30 "|-19986|-19982|-19976|-19805|-19784|-19775|-19774|-19763|-19756|-19751|-19746|-19741|-19739|-19728|-19725".
31 "|-19715|-19540|-19531|-19525|-19515|-19500|-19484|-19479|-19467|-19289|-19288|-19281|-19275|-19270|-19263".
32 "|-19261|-19249|-19243|-19242|-19238|-19235|-19227|-19224|-19218|-19212|-19038|-19023|-19018|-19006|-19003".
33 "|-18996|-18977|-18961|-18952|-18783|-18774|-18773|-18763|-18756|-18741|-18735|-18731|-18722|-18710|-18697".
34 "|-18696|-18526|-18518|-18501|-18490|-18478|-18463|-18448|-18447|-18446|-18239|-18237|-18231|-18220|-18211".
35 "|-18201|-18184|-18183|-18181|-18012|-17997|-17988|-17970|-17964|-17961|-17950|-17947|-17931|-17928|-17922".
36 "|-17759|-17752|-17733|-17730|-17721|-17703|-17701|-17697|-17692|-17683|-17676|-17496|-17487|-17482|-17468".
37 "|-17454|-17433|-17427|-17417|-17202|-17185|-16983|-16970|-16942|-16915|-16733|-16708|-16706|-16689|-16664".
38 "|-16657|-16647|-16474|-16470|-16465|-16459|-16452|-16448|-16433|-16429|-16427|-16423|-16419|-16412|-16407".
39 "|-16403|-16401|-16393|-16220|-16216|-16212|-16205|-16202|-16187|-16180|-16171|-16169|-16158|-16155|-15959".
40 "|-15958|-15944|-15933|-15920|-15915|-15903|-15889|-15878|-15707|-15701|-15681|-15667|-15661|-15659|-15652".
41 "|-15640|-15631|-15625|-15454|-15448|-15436|-15435|-15419|-15416|-15408|-15394|-15385|-15377|-15375|-15369".
42 "|-15363|-15362|-15183|-15180|-15165|-15158|-15153|-15150|-15149|-15144|-15143|-15141|-15140|-15139|-15128".
43 "|-15121|-15119|-15117|-15110|-15109|-14941|-14937|-14933|-14930|-14929|-14928|-14926|-14922|-14921|-14914".
44 "|-14908|-14902|-14894|-14889|-14882|-14873|-14871|-14857|-14678|-14674|-14670|-14668|-14663|-14654|-14645".
45 "|-14630|-14594|-14429|-14407|-14399|-14384|-14379|-14368|-14355|-14353|-14345|-14170|-14159|-14151|-14149".
46 "|-14145|-14140|-14137|-14135|-14125|-14123|-14122|-14112|-14109|-14099|-14097|-14094|-14092|-14090|-14087".
47 "|-14083|-13917|-13914|-13910|-13907|-13906|-13905|-13896|-13894|-13878|-13870|-13859|-13847|-13831|-13658".
48 "|-13611|-13601|-13406|-13404|-13400|-13398|-13395|-13391|-13387|-13383|-13367|-13359|-13356|-13343|-13340".
49 "|-13329|-13326|-13318|-13147|-13138|-13120|-13107|-13096|-13095|-13091|-13076|-13068|-13063|-13060|-12888".
50 "|-12875|-12871|-12860|-12858|-12852|-12849|-12838|-12831|-12829|-12812|-12802|-12607|-12597|-12594|-12585".
51 "|-12556|-12359|-12346|-12320|-12300|-12120|-12099|-12089|-12074|-12067|-12058|-12039|-11867|-11861|-11847".
52 "|-11831|-11798|-11781|-11604|-11589|-11536|-11358|-11340|-11339|-11324|-11303|-11097|-11077|-11067|-11055".
53 "|-11052|-11045|-11041|-11038|-11024|-11020|-11019|-11018|-11014|-10838|-10832|-10815|-10800|-10790|-10780".
54 "|-10764|-10587|-10544|-10533|-10519|-10331|-10329|-10328|-10322|-10315|-10309|-10307|-10296|-10281|-10274".
55 "|-10270|-10262|-10260|-10256|-10254";
56 $_TDataKey = explode('|', $_DataKey);
57 $_TDataValue = explode('|', $_DataValue);
58 $_Data = array_combine($_TDataKey, $_TDataValue);
59 arsort($_Data);
60 reset($_Data);
61 if($_Code!= 'gb2312') $_String = $this->_U2_Utf8_Gb($_String);
62 $_Res = '';
63 foreach($checkstr as $v)
64 {
65 $v=iconv("utf-8","gb2312",$v);
66 $reg="/$v/";
67 $_String=preg_replace($reg,"",$_String);
68 }
69 if(strlen($_String)>=$len)
70 {
71 $countlen=$len;
72 }
73 else
74 {
75 $countlen=strlen($_String);
76 }
77 for($i=0; $i<$countlen+2; $i++) {
78
79 $_P = ord(substr($_String, $i, 1));
80 if($_P>160) {
81 $_Q = ord(substr($_String, ++$i, 1));
82 $_P = $_P*256 + $_Q - 65536;
83 }
84 if($_type ==1)
85 {
86 //使用字典方式判断
87 $_Res .= $this->_Pinyin($_P, $_Data);
88 }
89 else
90 {
91 //使用编码范围来判断
92 $_Res .= $this->_changeCode($_P);
93 }
94
95 }
96 // return $i."<br/>".$countlen."<br/>".$_String."<br/>".$_Res."<br/>".preg_replace("/[^a-z0-9]*/", '', $_Res);
97 return preg_replace("/[^a-z0-9A-Z]*/", '', $_Res);
98 }
99 function _Pinyin($_Num, $_Data){
100 if($_Num>0 && $_Num<160 ){
101 return chr($_Num);
102 }elseif($_Num<-20319 || $_Num>-10247){
103 return 'v';
104 }else{
105 foreach($_Data as $k=>$v){ if($v<=$_Num) break; }
106 return substr($k,0,1);
107 }
108 }
109 function _U2_Utf8_Gb($_C){
110 $_String = '';
111 if($_C < 0x80){
112 $_String .= $_C;
113 }elseif($_C < 0x800) {
114 $_String .= chr(0xC0 | $_C>>6);
115 $_String .= chr(0x80 | $_C & 0x3F);
116 }elseif($_C < 0x10000){
117 $_String .= chr(0xE0 | $_C>>12);
118 $_String .= chr(0x80 | $_C>>6 & 0x3F);
119 $_String .= chr(0x80 | $_C & 0x3F);
120 }elseif($_C < 0x200000) {
121 $_String .= chr(0xF0 | $_C>>18);
122 $_String .= chr(0x80 | $_C>>12 & 0x3F);
123 $_String .= chr(0x80 | $_C>>6 & 0x3F);
124 $_String .= chr(0x80 | $_C & 0x3F);
125 }
126 return iconv('UTF-8', 'GB2312', $_String);
127 }
128
129 function _changeCode($p)
130 {
131 $strCode=$p;
132 if (($strCode >=65 and $strCode <= 91) or ($strCode>=48 and $strCode<=57))
133 return chr($strCode);
134 //$s=iconv("utf-8","gb2312",$str);
135 $asc=$p;
136 if($asc>=-20319 and $asc<=-20284)return "A";
137 if($asc>=-20283 and $asc<=-19776)return "B";
138 if($asc>=-19775 and $asc<=-19219)return "C";
139 if($asc>=-19218 and $asc<=-18711)return "D";
140 if($asc>=-18710 and $asc<=-18527)return "E";
141 if($asc>=-18526 and $asc<=-18240)return "F";
142 if($asc>=-18239 and $asc<=-17923)return "G";
143 if($asc>=-17922 and $asc<=-17418)return "H";
144 if($asc>=-17417 and $asc<=-16475)return "J";
145 if($asc>=-16474 and $asc<=-16213)return "K";
146 if($asc>=-16212 and $asc<=-15641)return "L";
147 if($asc>=-15640 and $asc<=-15166)return "M";
148 if($asc>=-15165 and $asc<=-14923)return "N";
149 if($asc>=-14922 and $asc<=-14915)return "O";
150 if($asc>=-14914 and $asc<=-14631)return "P";
151 if($asc>=-14630 and $asc<=-14150)return "Q";
152 if($asc>=-14149 and $asc<=-14091)return "R";
153 if($asc>=-14090 and $asc<=-13319)return "S";
154 if($asc>=-13318 and $asc<=-12839)return "T";
155 if($asc>=-12838 and $asc<=-12557)return "W";
156 if($asc>=-12556 and $asc<=-11848)return "X";
157 if($asc>=-11847 and $asc<=-11056)return "Y";
158 if($asc>=-11055 and $asc<=-10247)return "Z";
159 return "V";
160
161
162 }
163
164 }
165
166
167
168
169 ?>

Copyright © 2024 bingfeng
Powered by .NET 8.0 on Kubernetes