pinyin4j的使用

转自：  http://lavasoft.blog.51cto.com/62575/178320

pinyin4j是一个功能强悍的汉语拼音工具包，主要是从汉语获取各种格式和需求的拼音，功能强悍，下面看看如何使用pinyin4j。 

本人以前用AscII编码提取工具，效果不理想，现在用pinyin4j简单实现了一个。功能还不是很完美，陆续再改进吧。

 

import net.sourceforge.pinyin4j.PinyinHelper; 
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType; 
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; 
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType; 
import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination; 

import java.io.UnsupportedEncodingException; 

/** 
* 拼音工具 
* 
* @author leizhimin 2009-7-15 15:26:21 
*/ 
public  class PinyinToolkit { 

         /** 
         * 获取汉字串拼音首字母，英文字符不变 
         * 
         * @param chinese 汉字串 
         * @return 汉语拼音首字母 
         */ 
         public  static String cn2FirstSpell(String chinese) { 
                StringBuffer pybf =  new StringBuffer(); 
                 char[] arr = chinese.toCharArray(); 
                HanyuPinyinOutputFormat defaultFormat =  new HanyuPinyinOutputFormat(); 
                defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); 
                defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); 
                 for ( int i = 0; i < arr.length; i++) { 
                         if (arr[i] > 128) { 
                                 try { 
                                        String[] _t = PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat); 
                                         if (_t !=  null) { 
                                                pybf.append(_t[0].charAt(0)); 
                                        } 
                                }  catch (BadHanyuPinyinOutputFormatCombination e) { 
                                        e.printStackTrace(); 
                                } 
                        }  else { 
                                pybf.append(arr[i]); 
                        } 
                } 
                 return pybf.toString().replaceAll( "\\W", "").trim(); 
        } 

         /** 
         * 获取汉字串拼音，英文字符不变 
         * 
         * @param chinese 汉字串 
         * @return 汉语拼音 
         */ 
         public  static String cn2Spell(String chinese) { 
                StringBuffer pybf =  new StringBuffer(); 
                 char[] arr = chinese.toCharArray(); 
                HanyuPinyinOutputFormat defaultFormat =  new HanyuPinyinOutputFormat(); 
                defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); 
                defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); 
                 for ( int i = 0; i < arr.length; i++) { 
                         if (arr[i] > 128) { 
                                 try { 
                                        pybf.append(PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat)[0]); 
                                }  catch (BadHanyuPinyinOutputFormatCombination e) { 
                                        e.printStackTrace(); 
                                } 
                        }  else { 
                                pybf.append(arr[i]); 
                        } 
                } 
                 return pybf.toString(); 
        } 

         public  static  void main(String[] args)  throws UnsupportedEncodingException { 
                String x =  "嘅囧誰說壞學生來勼髮視頻裆児"; 
                System.out.println(cn2FirstSpell(x)); 
                System.out.println(cn2Spell(x)); 
        } 
}

 

运行结果：

kjsshxsljfspde 
kaijiongshuishuohuaixueshenglaijiufashipindanger 

Process finished with exit code 0