<?php
/**
*
* 漢字轉(zhuǎn)拼音類
* @Author : Kin
* @Date : 2014-03-16
* @Email : Mr.kin@foxmail.com
*
*/
namespace Org\Util;
define('PINYIN_ROOT', dirname(__FILE__));
class ChinesePinyin{
//utf-8中國漢字集合
private $ChineseCharacters;
//編碼
private $charset = 'utf-8';
public function __construct(){
if( empty($this->ChineseCharacters) ){
$this->ChineseCharacters = file_get_contents(PINYIN_ROOT.'/Pinyin/ChineseCharacters.dat');
}
}
/*
* 轉(zhuǎn)成帶有聲調(diào)的漢語拼音
* param $input_char String 需要轉(zhuǎn)換的漢字
* param $delimiter String 轉(zhuǎn)換之后拼音之間分隔符
* param $outside_ignore Boolean 是否忽略非漢字內(nèi)容
*/
public function TransformWithTone($input_char,$delimiter=' ',$outside_ignore=false){
$input_len = mb_strlen($input_char,$this->charset);
$output_char = '';
for($i=0;$i<$input_len;$i++){
$word = mb_substr($input_char,$i,1,$this->charset);
if(preg_match('/^[\x{4e00}-\x{9fa5}]$/u',$word) && preg_match('/\,'.preg_quote($word).'(.*?)\,/',$this->ChineseCharacters,$matches) ){
$output_char.=$matches[1].$delimiter;
}else if(!$outside_ignore){
$output_char.=$word;
}
}
return $output_char;
}
/*
* 轉(zhuǎn)成帶無聲調(diào)的漢語拼音
* param $input_char String 需要轉(zhuǎn)換的漢字
* param $delimiter String 轉(zhuǎn)換之后拼音之間分隔符
* param $outside_ignore Boolean 是否忽略非漢字內(nèi)容
*/
public function TransformWithoutTone($input_char,$delimiter='',$outside_ignore=true){
$char_with_tone = $this->TransformWithTone($input_char,$delimiter,$outside_ignore);
$char_without_tone = str_replace(array('ā','á','ǎ','à','ō','ó','ǒ','ò','ē','é','ě','è','ī','í','ǐ','ì','ū','ú','ǔ','ù','ǖ','ǘ','ǚ','ǜ','ü'),
array('a','a','a','a','o','o','o','o','e','e','e','e','i','i','i','i','u','u','u','u','v','v','v','v','v')
,$char_with_tone );
return $char_without_tone;
}
/*
* 轉(zhuǎn)成漢語拼音首字母,只包括漢字
* param $input_char String 需要轉(zhuǎn)換的漢字
* param $delimiter String 轉(zhuǎn)換之后拼音之間分隔符
*/
public function TransformUcwordsOnlyChar($input_char,$delimiter=''){
$char_without_tone = ucwords($this->TransformWithoutTone($input_char,' ',true));
$ucwords = preg_replace('/[^A-Z]/','',$char_without_tone);
if(!empty($delimiter)){
$ucwords = implode($delimiter,str_split($ucwords));
}
return $ucwords;
}
/*
* 轉(zhuǎn)成漢語拼音首字母,包含非漢字內(nèi)容
* param $input_char String 需要轉(zhuǎn)換的漢字
* param $delimiter String 轉(zhuǎn)換之后拼音之間分隔符
*/
public function TransformUcwords($input_char,$delimiter=' ',$outside_ignore=false){
$input_len = mb_strlen($input_char,$this->charset);
$output_char = '';
for($i=0;$i<$input_len;$i++){
$word = mb_substr($input_char,$i,1,$this->charset);
if(preg_match('/^[\x{4e00}-\x{9fa5}]$/u',$word) && preg_match('/\,'.preg_quote($word).'(.*?)\,/',$this->ChineseCharacters,$matches) ){
$output_char.=$matches[1].$delimiter;
}else if(!$outside_ignore){
$output_char.= $delimiter.$word.$delimiter;
}
}
$output_char = str_replace(array('ā','á','ǎ','à','ō','ó','ǒ','ò','ē','é','ě','è','ī','í','ǐ','ì','ū','ú','ǔ','ù','ǖ','ǘ','ǚ','ǜ','ü'),
array('a','a','a','a','o','o','o','o','e','e','e','e','i','i','i','i','u','u','u','u','v','v','v','v','v')
,$output_char );
$array = explode($delimiter,$output_char);
$array = array_filter($array);
$res = '';
foreach($array as $list){
$res .= substr($list,0,1);
}
return $res;
}
}
