PHP 之中文转为拼音
/**
* Created by PhpStorm.
* User: Administrator
* Date: 2019/1/2 0002
* Time: 下午 1:01
*/
class PinYin
{ private $dict_list = 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
); /**
* 获取全部拼音,返回拼音的数组,如 '张三丰' ==> ['zhang','san','feng']
* @param $chinese
* @param string $charset
* @return array
*/
public function get_all_py($chinese, $charset = 'utf-8')
{
if ($charset != 'gb2312') $chinese = $this->_U2_Utf8_Gb($chinese);
$py = $this->zh_to_pys($chinese); return $py;
} /**
* 获取拼音首字母,如['zhang','san','feng'] ==> zsf
* @param $all_pys
* @return string
*/
public function get_first_py($all_pys)
{
if (count($all_pys) <= 0) {
return '';
} $result = [];
foreach ($all_pys as $one) {
if (is_null($one) || strlen($one) <= 0) {
continue;
}
$result[] = substr($one, 0, 1);
} return join('', $result);
} /**
* 获取拼音首字母,如['zhang','san','feng'] ==> z
* @param $all_pys
* @return string
*/
public function get_first_letter($all_pys)
{
if (count($all_pys) <= 0) {
return '';
} foreach ($all_pys as $one) {
if (is_null($one) || strlen($one) <= 0) {
continue;
}
return substr($one, 0, 1);
} return '';
} private 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', $_String);
} private function zh_to_py($num, $blank = '')
{
if ($num > 0 && $num < 160) {
return chr($num);
} elseif ($num < -20319 || $num > -10247) {
return $blank;
} else {
foreach ($this->dict_list as $py => $code) {
if ($code > $num) break;
$result = $py;
}
return $result;
}
} private function zh_to_pys($chinese)
{
$result = array();
for ($i = 0; $i < strlen($chinese); $i++) {
$p = ord(substr($chinese, $i, 1));
if ($p > 160) {
$q = ord(substr($chinese, ++$i, 1));
$p = $p * 256 + $q - 65536;
}
$result[] = $this->zh_to_py($p);
}
return $result;
}
}
PHP 之中文转为拼音的更多相关文章
- Python中文转为拼音
# -*- coding: utf-8 -*-import sys def openTable(): f = open('gb-pinyin.table', 'r') table = f.read() ...
- java实现汉字转为拼音
java实现汉字转为拼音: 1.需要导入pinyin4j.jar package com.loo.pinyin; import net.sourceforge.pinyin4j.PinyinHelpe ...
- PHP中文转拼音扩展
Pinyin 基于 CC-CEDICT 词典的中文转拼音工具,更准确的支持多音字的汉字转拼音解决方案. 安装 使用 Composer 安装: $ composer require "over ...
- 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 $_code=array ...
- java实现将汉字转为拼音
有时候为了方便操作程序的开发,需要将汉字转为拼音等操作.下面这个是自己结合网上的资料,加上自己在公司项目中的亲自实践.完整的实现了将汉字转为拼音的操作.这个Demo只是负责将其转换,在main方法中测 ...
- php 获取中文字符拼音首字母
//php获取中文字符拼音首字母 function getFirstCharter($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_ ...
随机推荐
- Performance Tunning - OCP
This artical is forcused on Oracle 11g Release 2. It is an summary from the OCP documentation. The ...
- [Vue-rx] Pass Template Data Through domStreams in Vue.js and RxJS
domStreams enable you to pass additional data along the stream that can be provided by the template ...
- POJ 1260-Pearls(DP)
Pearls Time Limit: 1000MS Memory Limit: 10000K Total Submissions: 7465 Accepted: 3695 Descriptio ...
- 模块化开发(三)---通过node.js学习模块化开发
由于改文章有点大,部分代码格式有点问题,编辑之后博客园莫名其妙推出,有问题可以留言沟通. 什么是Node? 它是一个在浏览器之外可以解析和执行javascript代码的运行环 境,或者说是一个运行 ...
- const与static类成员
const成员函数作用1. 不能修改类的成员变量,同时不能调用类的非const成员函数.(const成员函数中,this的类型是一个指向const类类型对象的const指针,const成员函数返回*t ...
- BestCoder Round #60.1003.GT and set/HDU5506 dfs
GT and set Accepts: 35 Submissions: 194 Time Limit: 2000/1000 MS (Java/Others) Memory Limit: 655 ...
- ASP.NET SignalR Hubs API Guide - JavaScript Client
https://docs.microsoft.com/en-us/aspnet/signalr/overview/guide-to-the-api/hubs-api-guide-javascript- ...
- 让DIV在屏幕上下左右居中
转自:http://blog.sina.com.cn/s/blog_65d41dff0100v0iz.html 其实解决的思路是这样的:首们需要position:absolute;绝对定位.而层的定位 ...
- 湖南集训day6
难度:☆☆☆☆☆☆☆☆ /* 对于第一问:f[i][j]表示前i个数,当前黑板上的数为j的概率 当前有三种情况 1.当前数不是j的倍数—>黑板上的数字改变. 2.当前数是j的倍数且当前数在前i个 ...
- skiing 暴力搜索 + 动态规划
我的代码上去就是 直接纯粹的 暴力 . 居然没有超时 200ms 可能数据比较小 一会在优化 #include<stdio.h> #include<string.h ...