使用PinYin4j.jar将汉字转换为拼音使用实例

package com.wlh.lucene.test2;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

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.HanyuPinyinVCharType;

public class Test { 
	//源文件与目标文件的全路径名
	private static final String READ_FILE="E:/workspace65/paoding-analysis_test/src/com/wlh/lucene/test2/txt.txt";
	private static final String WRITE_FILE="E:/workspace65/paoding-analysis_test/src/com/wlh/lucene/test2/txt1.txt";
	private static HanyuPinyinOutputFormat spellFormat = new HanyuPinyinOutputFormat();  
	private static BufferedWriter writer = null;
	private static BufferedReader reader = null;
	//初始化信息
	public static void init() throws IOException{
		writer = new BufferedWriter(new FileWriter(new File(WRITE_FILE),false));
		reader = new BufferedReader(new FileReader(new File(READ_FILE)));  
		spellFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);  
		spellFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);  
		spellFormat.setVCharType(HanyuPinyinVCharType.WITH_V); 
	}
    // 判断字符串是否包含有中文 
    public static boolean isChinese(String str) {  
        String regex = "[\\u4e00-\\u9fa5]";  
        Pattern pattern = Pattern.compile(regex);  
        Matcher matcher = pattern.matcher(str);  
        return matcher.find();  
    }  
	//使用PinYin4j.jar将汉字转换为拼音
	public static String chineneToSpell(String chineseStr){
		return PinyinHelper.toHanyuPinyinString(chineseStr , spellFormat ,"");
	}
	//将转换后的字符串写入目标文件
	public static void writeToFile(String spellStr) throws IOException{
		writer.write(spellStr);
	}
	//从源文件读取按行数据
	public static void readFromFile() throws IOException{
		String line = null;
		 while ((line = reader.readLine()) != null) {  
             line = line.trim();  
             //是中文
             if(isChinese(line)){
            	 line = chineneToSpell(line);
             }
             writeToFile(line + "\n");
         }  
	}
	//关闭文件流
	public static void destory() throws IOException{
		reader.close();
		writer.close();
	}
	public static void main(String[] args) throws IOException {
		init();
		readFromFile();
		destory();
	}
}

评论

1 楼 pop1030123 2013-09-22  

没发现转不了吗?汉字还是汉字