PHP的UTF-8中文转拼音处理类
<?php
/**
* PHP 汉字转拼音
* @author Jerryli(hzjerry@gmail.com)
* @version V0.20140715
* @package SPFW.core.lib.final
* @global SEA_PHP_FW_VAR_ENV
* @example
* echo CUtf8_PY::encode('阿里巴巴科技有限公司'); //编码为拼音首字母
* echo CUtf8_PY::encode('阿里巴巴科技有限公司', 'all'); //编码为全拼音
*/
class CUtf8_PY {
/**
* 拼音字符转换图
* @var array
*/
private static $_aMaps = array(
'a'=>-20319,'ai'=>-20317,'an'=>-20304,'ang'=>-20295,'ao'=>-20292,
'ba'=>-20283,'bai'=>-20265,'ban'=>-20257,'bang'=>-20242,'bao'=>-20230,'bei'=>-20051,'ben'=>-20036,'beng'=>-20032,'bi'=>-20026,'bian'=>-20002,'biao'=>-19990,'bie'=>-19986,'bin'=>-19982,'bing'=>-19976,'bo'=>-19805,'bu'=>-19784,
'ca'=>-19775,'cai'=>-19774,'can'=>-19763,'cang'=>-19756,'cao'=>-19751,'ce'=>-19746,'ceng'=>-19741,'cha'=>-19739,'chai'=>-19728,'chan'=>-19725,'chang'=>-19715,'chao'=>-19540,'che'=>-19531,'chen'=>-19525,'cheng'=>-19515,'chi'=>-19500,'chong'=>-19484,'chou'=>-19479,'chu'=>-19467,'chuai'=>-19289,'chuan'=>-19288,'chuang'=>-19281,'chui'=>-19275,'chun'=>-19270,'chuo'=>-19263,'ci'=>-19261,'cong'=>-19249,'cou'=>-19243,'cu'=>-19242,'cuan'=>-19238,'cui'=>-19235,'cun'=>-19227,'cuo'=>-19224,
'da'=>-19218,'dai'=>-19212,'dan'=>-19038,'dang'=>-19023,'dao'=>-19018,'de'=>-19006,'deng'=>-19003,'di'=>-18996,'dian'=>-18977,'diao'=>-18961,'die'=>-18952,'ding'=>-18783,'diu'=>-18774,'dong'=>-18773,'dou'=>-18763,'du'=>-18756,'duan'=>-18741,'dui'=>-18735,'dun'=>-18731,'duo'=>-18722,
'e'=>-18710,'en'=>-18697,'er'=>-18696,
'fa'=>-18526,'fan'=>-18518,'fang'=>-18501,'fei'=>-18490,'fen'=>-18478,'feng'=>-18463,'fo'=>-18448,'fou'=>-18447,'fu'=>-18446,
'ga'=>-18239,'gai'=>-18237,'gan'=>-18231,'gang'=>-18220,'gao'=>-18211,'ge'=>-18201,'gei'=>-18184,'gen'=>-18183,'geng'=>-18181,'gong'=>-18012,'gou'=>-17997,'gu'=>-17988,'gua'=>-17970,'guai'=>-17964,'guan'=>-17961,'guang'=>-17950,'gui'=>-17947,'gun'=>-17931,'guo'=>-17928,
'ha'=>-17922,'hai'=>-17759,'han'=>-17752,'hang'=>-17733,'hao'=>-17730,'he'=>-17721,'hei'=>-17703,'hen'=>-17701,'heng'=>-17697,'hong'=>-17692,'hou'=>-17683,'hu'=>-17676,'hua'=>-17496,'huai'=>-17487,'huan'=>-17482,'huang'=>-17468,'hui'=>-17454,'hun'=>-17433,'huo'=>-17427,
'ji'=>-17417,'jia'=>-17202,'jian'=>-17185,'jiang'=>-16983,'jiao'=>-16970,'jie'=>-16942,'jin'=>-16915,'jing'=>-16733,'jiong'=>-16708,'jiu'=>-16706,'ju'=>-16689,'juan'=>-16664,'jue'=>-16657,'jun'=>-16647,
'ka'=>-16474,'kai'=>-16470,'kan'=>-16465,'kang'=>-16459,'kao'=>-16452,'ke'=>-16448,'ken'=>-16433,'keng'=>-16429,'kong'=>-16427,'kou'=>-16423,'ku'=>-16419,'kua'=>-16412,'kuai'=>-16407,'kuan'=>-16403,'kuang'=>-16401,'kui'=>-16393,'kun'=>-16220,'kuo'=>-16216,
'la'=>-16212,'lai'=>-16205,'lan'=>-16202,'lang'=>-16187,'lao'=>-16180,'le'=>-16171,'lei'=>-16169,'leng'=>-16158,'li'=>-16155,'lia'=>-15959,'lian'=>-15958,'liang'=>-15944,'liao'=>-15933,'lie'=>-15920,'lin'=>-15915,'ling'=>-15903,'liu'=>-15889,'long'=>-15878,'lou'=>-15707,'lu'=>-15701,'lv'=>-15681,'luan'=>-15667,'lue'=>-15661,'lun'=>-15659,'luo'=>-15652,
'ma'=>-15640,'mai'=>-15631,'man'=>-15625,'mang'=>-15454,'mao'=>-15448,'me'=>-15436,'mei'=>-15435,'men'=>-15419,'meng'=>-15416,'mi'=>-15408,'mian'=>-15394,'miao'=>-15385,'mie'=>-15377,'min'=>-15375,'ming'=>-15369,'miu'=>-15363,'mo'=>-15362,'mou'=>-15183,'mu'=>-15180,
'na'=>-15165,'nai'=>-15158,'nan'=>-15153,'nang'=>-15150,'nao'=>-15149,'ne'=>-15144,'nei'=>-15143,'nen'=>-15141,'neng'=>-15140,'ni'=>-15139,'nian'=>-15128,'niang'=>-15121,'niao'=>-15119,'nie'=>-15117,'nin'=>-15110,'ning'=>-15109,'niu'=>-14941,'nong'=>-14937,'nu'=>-14933,'nv'=>-14930,'nuan'=>-14929,'nue'=>-14928,'nuo'=>-14926,
'o'=>-14922,'ou'=>-14921,
'pa'=>-14914,'pai'=>-14908,'pan'=>-14902,'pang'=>-14894,'pao'=>-14889,'pei'=>-14882,'pen'=>-14873,'peng'=>-14871,'pi'=>-14857,'pian'=>-14678,'piao'=>-14674,'pie'=>-14670,'pin'=>-14668,'ping'=>-14663,'po'=>-14654,'pu'=>-14645,
'qi'=>-14630,'qia'=>-14594,'qian'=>-14429,'qiang'=>-14407,'qiao'=>-14399,'qie'=>-14384,'qin'=>-14379,'qing'=>-14368,'qiong'=>-14355,'qiu'=>-14353,'qu'=>-14345,'quan'=>-14170,'que'=>-14159,'qun'=>-14151,
'ran'=>-14149,'rang'=>-14145,'rao'=>-14140,'re'=>-14137,'ren'=>-14135,'reng'=>-14125,'ri'=>-14123,'rong'=>-14122,'rou'=>-14112,'ru'=>-14109,'ruan'=>-14099,'rui'=>-14097,'run'=>-14094,'ruo'=>-14092,
'sa'=>-14090,'sai'=>-14087,'san'=>-14083,'sang'=>-13917,'sao'=>-13914,'se'=>-13910,'sen'=>-13907,'seng'=>-13906,'sha'=>-13905,'shai'=>-13896,'shan'=>-13894,'shang'=>-13878,'shao'=>-13870,'she'=>-13859,'shen'=>-13847,'sheng'=>-13831,'shi'=>-13658,'shou'=>-13611,'shu'=>-13601,'shua'=>-13406,'shuai'=>-13404,'shuan'=>-13400,'shuang'=>-13398,'shui'=>-13395,'shun'=>-13391,'shuo'=>-13387,'si'=>-13383,'song'=>-13367,'sou'=>-13359,'su'=>-13356,'suan'=>-13343,'sui'=>-13340,'sun'=>-13329,'suo'=>-13326,
'ta'=>-13318,'tai'=>-13147,'tan'=>-13138,'tang'=>-13120,'tao'=>-13107,'te'=>-13096,'teng'=>-13095,'ti'=>-13091,'tian'=>-13076,'tiao'=>-13068,'tie'=>-13063,'ting'=>-13060,'tong'=>-12888,'tou'=>-12875,'tu'=>-12871,'tuan'=>-12860,'tui'=>-12858,'tun'=>-12852,'tuo'=>-12849,
'wa'=>-12838,'wai'=>-12831,'wan'=>-12829,'wang'=>-12812,'wei'=>-12802,'wen'=>-12607,'weng'=>-12597,'wo'=>-12594,'wu'=>-12585,
'xi'=>-12556,'xia'=>-12359,'xian'=>-12346,'xiang'=>-12320,'xiao'=>-12300,'xie'=>-12120,'xin'=>-12099,'xing'=>-12089,'xiong'=>-12074,'xiu'=>-12067,'xu'=>-12058,'xuan'=>-12039,'xue'=>-11867,'xun'=>-11861,
'ya'=>-11847,'yan'=>-11831,'yang'=>-11798,'yao'=>-11781,'ye'=>-11604,'yi'=>-11589,'yin'=>-11536,'ying'=>-11358,'yo'=>-11340,'yong'=>-11339,'you'=>-11324,'yu'=>-11303,'yuan'=>-11097,'yue'=>-11077,'yun'=>-11067,
'za'=>-11055,'zai'=>-11052,'zan'=>-11045,'zang'=>-11041,'zao'=>-11038,'ze'=>-11024,'zei'=>-11020,'zen'=>-11019,'zeng'=>-11018,'zha'=>-11014,'zhai'=>-10838,'zhan'=>-10832,'zhang'=>-10815,'zhao'=>-10800,'zhe'=>-10790,'zhen'=>-10780,'zheng'=>-10764,'zhi'=>-10587,'zhong'=>-10544,'zhou'=>-10533,'zhu'=>-10519,'zhua'=>-10331,'zhuai'=>-10329,'zhuan'=>-10328,'zhuang'=>-10322,'zhui'=>-10315,'zhun'=>-10309,'zhuo'=>-10307,'zi'=>-10296,'zong'=>-10281,'zou'=>-10274,'zu'=>-10270,'zuan'=>-10262,'zui'=>-10260,'zun'=>-10256,'zuo'=>-10254
); /**
* 将中文编码成拼音
* @param string $utf8Data utf8字符集数据
* @param string $sRetFormat 返回格式 [head:首字母|all:全拼音]
* @return string
*/
public static function encode($utf8Data, $sRetFormat='head'){
$sGBK = iconv('UTF-8', 'GBK', $utf8Data);
$aBuf = array();
for ($i=0, $iLoop=strlen($sGBK); $i<$iLoop; $i++) {
$iChr = ord($sGBK{$i});
if ($iChr>160)
$iChr = ($iChr<<8) + ord($sGBK{++$i}) - 65536;
if ('head' === $sRetFormat)
$aBuf[] = substr(self::zh2py($iChr),0,1);
else
$aBuf[] = self::zh2py($iChr);
}
if ('head' === $sRetFormat)
return implode('', $aBuf);
else
return implode(' ', $aBuf);
} /**
* 中文转换到拼音(每次处理一个字符)
* @param number $iWORD 待处理字符双字节
* @return string 拼音
*/
private static function zh2py($iWORD) {
if($iWORD>0 && $iWORD<160 ) {
return chr($iWORD);
} elseif ($iWORD<-20319||$iWORD>-10247) {
return '';
} else {
foreach (self::$_aMaps as $py => $code) {
if($code > $iWORD) break;
$result = $py;
}
return $result;
}
}
} echo CUtf8_PY::encode('青科大博苑大馒头','all');die; ?>
本文转自http://blog.csdn.net/hzbigdog/article/details/37817135
PHP的UTF-8中文转拼音处理类的更多相关文章
- PHP的UTF-8中文转拼音处理类(性能已优化至极致)
<?php /** * PHP 汉字转拼音 * @author Jerryli(hzjerry@gmail.com) * @version V0.20140715 * @package SPFW ...
- PHP如何将中文转换为拼音
用来得到中文的首字母: 这个是将中文转换为拼音的类:charset <?php/*** 汉字转化为拼音,拼音转化为汉字**/ class charset{private $_code=array ...
- 中文转拼音without CJK
Xamarin写Android程序时,通常要使用按中文首字母分组显示(如通讯录) . 于是需要被迫包含CJK,不过包含后包肯定是会变大的,于是....自己写了一个硬枚举的中文转拼音的类. 原理是这样的 ...
- Mono 3.2 测试NPinyin 中文转换拼音代码
C#中文转换为拼音NPinyin代码 在Mono 3.2下运行正常,Spacebuilder 有使用到NPinyin组件,代码兼容性没有问题. using System; using System. ...
- php 获取中文字符拼音首字母
//php获取中文字符拼音首字母 function getFirstCharter($str){ if(empty($str)){return '';} $fchar=ord($str{}); }); ...
- C# 中文转拼音类
using System; using System.Collections.Generic; using System.Linq; using System.Text; namespace SU { ...
- SQL 用中文的拼音和笔画排序
SQL 用中文的拼音和笔画排序 城市按拼音排序: SELECT chineseName FROM [表名] order by chinesename collate Chinese_PRC_CS_ ...
- NPinyin 中文转换拼音代码
Mono 3.2 测试NPinyin 中文转换拼音代码 C#中文转换为拼音NPinyin代码 在Mono 3.2下运行正常,Spacebuilder 有使用到NPinyin组件,代码兼容性没有问 ...
- php获取中文字符拼音首字母
//php获取中文字符拼音首字母 function getFirstCharter($str){ if(empty($str)){ return ''; } $fchar = ord($str{0}) ...
随机推荐
- [TestNG] Eclipse/STS中两种安装TestNG的方法
Two Ways To Install TestNG in Eclipse/STS Today I install the newest Sprint Tool Suite and want to i ...
- 目录命令(cd)
cd 命令: // 描述: (Change Directory) 更改当前目录或显示当前目录的名称. 如果仅使用驱动器号(例如,cd C :),则cd将显示指定驱动器中当前目录的名称. 如果不带参数使 ...
- Oracle使用JDBC进行增删改查 表是否存在
Oracle使用JDBC进行增删改查 数据库和表 table USERS ( USERNAME VARCHAR2(20) not null, PASSWORD VARCHAR2(20) ) a ...
- C#部分试题实例
1.在C#中,下列选项中自定义方法的语句错误的是().(选择一项) 正确答案:AD 解析:本题考查自定义方法的定义及调用.A项void是无返回值类型,D项定义方法的时候没有写返回值类型:故选AD. 2 ...
- 在cmd下可以import cv2,而Pycharm报错:找不到cv2
平台:win10 x64+Pycharm+Anaconda3+opencv 安装教程:参考博客——http://blog.sina.com.cn/s/blog_cca23c300102xiy4.htm ...
- 75.iOS内存管理
堆区和栈区 1.栈区:由编译器自动分配释放,函数的参数值,局部变量等值 2.堆区:一般由开发人员分配释放,若不释放,则可能会引起内存泄漏 NSString *string = @"abcd& ...
- (PMP)第11章-----项目风险管理
11.1 规划风险管理 输入 工具与技术 输出 1.项目章程 2.项目管理计划 (所有组件) 3.项目文件 (相关方登记册) 4.事业环境因素 5.组织过程资产 1.专家判断 2.数据分析 (相关方分 ...
- 转 Master-Worker模式 并行程序设计模式--Master-Worker模式
简介 Master-Worker模式是常用的并行设计模式.它的核心思想是,系统有两个进程协议工作:Master进程和Worker进程.Master进程负责接收和分配任务,Worker进程负责处理子任务 ...
- 分支结构-Switch
/* switch(表达式或变量){ case value1:{ 语句体1; break; } case value2:{ 语句体2; break; } ... default:{ 语句体n+1; b ...
- 中国剩余定理poj1006
中国剩余定理即解一组带余除法的不定方程组(同余式组解法). 例如:求一个最小数x,已知x%3=2且x%5=3且x%7=2. 思路就是: 1.先从(3,5)的公倍数中找一个%7=1的最小公倍数,这里是1 ...