Java pinyin4j.jar中文转拼音

 

• 需要引入多音字配置文件及jar

• 配置文件地址：https://download.csdn.net/download/extraordinarylife/10687658

    com.belerweb
	pinyin4j
	2.5.0

 

• java代码部分

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

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;

/**
 * 中文转英文字母
 * @ClassName ChineseUtil
 * @author sw.liu
 * @Date 2018年6月21日 下午3:07:34
 * @version 1.0.0
 */
public class ChineseUtil {

    
         // UPPERCASE：大写  (ZHONG)  
         // LOWERCASE：小写  (zhong)  
//         format.setCaseType(HanyuPinyinCaseType.LOWERCASE);  
           
         // WITHOUT_TONE：无音标  (zhong)  
         // WITH_TONE_NUMBER：1-4数字表示英标  (zhong4)  
         // WITH_TONE_MARK：直接用音标符（必须WITH_U_UNICODE否则异常）  (zhòng)  
        // format.setToneType(HanyuPinyinToneType.WITH_TONE_MARK);  
           
         // WITH_V：用v表示ü  (nv)  
         // WITH_U_AND_COLON：用"u:"表示ü  (nu:)  
         // WITH_U_UNICODE：直接用ü (nü)  
//         format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

    private static Map> pinyinMap = new HashMap>();    
    private static long count = 0;    
    
    public static void main(String[] args) {    
    
        String str = "阿尔法·罗密欧";    
        String py = convertChineseToPinyin(str);    
        System.out.println(str+" = "+py);    
    }    
        
    /**  
     * 将某个字符串的首字母 大写  
     * @param str  
     * @return  
     */    
    public static String convertInitialToUpperCase(String str){    
        if(str==null){    
            return null;    
        }    
        StringBuffer sb = new StringBuffer();    
        char[] arr = str.toCharArray();    
        for(int i=0;i 128) { // 非ASCII码    
                // 取得当前汉字的所有全拼    
                try {    
    
                    String[] results = PinyinHelper.toHanyuPinyinStringArray(    
                            ch, defaultFormat);    
    
                    if (results != null) {  //非中文    
    
    
                        int len = results.length;    
    
                        if (len == 1) { // 不是多音字    
    
//                          pinyin.append(results[0]);    
                            String py = results[0];         
                            if(py.contains("u:")){  //过滤 u:    
                                py = py.replace("u:", "v");    
                                System.out.println("filter u:"+py);    
                            }    
                            pinyin.append(convertInitialToUpperCase(py));    
                                
                        }else if(results[0].equals(results[1])){    //非多音字 有多个音，取第一个    
                                
//                          pinyin.append(results[0]);    
                            pinyin.append(convertInitialToUpperCase(results[0]));    
                                
                        }else { // 多音字    
                                
                            System.out.println("多音字："+ch);    
                                
                            int length = chinese.length();    
                                
                            boolean flag = false;    
                                
                            String s = null;    
                                
                            List keyList =null;    
                                
                            for (int x = 0; x < len; x++) {    
                                    
                                String py = results[x];    
                                    
                                if(py.contains("u:")){  //过滤 u:    
                                    py = py.replace("u:", "v");    
                                    System.out.println("filter u:"+py);    
                                }    
    
                                keyList = pinyinMap.get(py);    
                                    
                                if (i + 3 <= length) {   //后向匹配2个汉字  大西洋     
                                    s = chinese.substring(i, i + 3);    
                                    if (keyList != null && (keyList.contains(s))) {    
//                                  if (value != null && value.contains(s)) {    
    
                                        System.out.println("last 2 > " + py);    
//                                      pinyin.append(results[x]);    
                                        pinyin.append(convertInitialToUpperCase(py));    
                                        flag = true;    
                                        break;    
                                    }    
                                }    
                                    
                                if (i + 2 <= length) {   //后向匹配 1个汉字  大西    
                                    s = chinese.substring(i, i + 2);    
                                    if (keyList != null && (keyList.contains(s))) {    
    
                                        System.out.println("last 1 > " + py);    
//                                      pinyin.append(results[x]);    
                                        pinyin.append(convertInitialToUpperCase(py));    
                                        flag = true;    
                                        break;    
                                    }    
                                }    
                                    
                                if ((i - 2 >= 0) && (i+1<=length)) {  // 前向匹配2个汉字 龙固大    
                                    s = chinese.substring(i - 2, i+1);    
                                    if (keyList != null && (keyList.contains(s))) {    
                                            
                                        System.out.println("before 2 < " + py);    
//                                      pinyin.append(results[x]);    
                                        pinyin.append(convertInitialToUpperCase(py));    
                                        flag = true;    
                                        break;    
                                    }    
                                }    
                                    
                                if ((i - 1 >= 0) && (i+1<=length)) {  // 前向匹配1个汉字   固大    
                                    s = chinese.substring(i - 1, i+1);    
                                    if (keyList != null && (keyList.contains(s))) {    
                                            
                                        System.out.println("before 1 < " + py);    
//                                      pinyin.append(results[x]);    
                                        pinyin.append(convertInitialToUpperCase(py));    
                                        flag = true;    
                                        break;    
                                    }    
                                }    
                                    
                                if ((i - 1 >= 0) && (i+2<=length)) {  //前向1个，后向1个      固大西    
                                    s = chinese.substring(i - 1, i+2);    
                                    if (keyList != null && (keyList.contains(s))) {    
                                            
                                        System.out.println("before last 1 <> " + py);    
//                                      pinyin.append(results[x]);    
                                        pinyin.append(convertInitialToUpperCase(py));    
                                        flag = true;    
                                        break;    
                                    }    
                                }    
                            }    
                                
                            if (!flag) {    //都没有找到，匹配默认的 读音  大     
                                    
                                s = String.valueOf(ch);    
                                    
                                for (int x = 0; x < len; x++) {    
                                        
                                    String py = results[x];    
                                        
                                    if(py.contains("u:")){  //过滤 u:    
                                        py = py.replace("u:", "v");    
                                        System.out.println("filter u:");    
                                    }    
                                        
                                    keyList = pinyinMap.get(py);    
                                        
                                    if (keyList != null && (keyList.contains(s))) {    
                                            
                                        System.out.println("default = " + py);    
//                                      pinyin.append(results[x]);  //如果不需要拼音首字母大写 ，直接返回即可    
                                        pinyin.append(convertInitialToUpperCase(py));//拼音首字母 大写    
                                        break;    
                                    }    
                                }    
                            }    
                        }    
                    }    
    
                } catch (BadHanyuPinyinOutputFormatCombination e) {    
                    e.printStackTrace();    
                }    
            } else {    
                pinyin.append(arr[i]);    
            }    
        }    
        return pinyin.toString();    
    }    
    
    /**  
     * 初始化 所有的多音字词组  
     *   
     * @param fileName  
     */    
    public static void initPinyin(String fileName) {    
        // 读取多音字的全部拼音表;    
        InputStream file = PinyinHelper.class.getResourceAsStream(fileName);    
    
        BufferedReader br = new BufferedReader(new InputStreamReader(file));    
    
        String s = null;    
        try {    
            while ((s = br.readLine()) != null) {    
    
                if (s != null) {    
                    String[] arr = s.split("#");    
                    String pinyin = arr[0];    
                    String chinese = arr[1];    
    
                    if(chinese!=null){    
                        String[] strs = chinese.split(" ");    
                        List list = Arrays.asList(strs);    
                        pinyinMap.put(pinyin, list);    
                    }    
                }    
            }    
    
        } catch (IOException e) {    
            e.printStackTrace();    
        }finally{    
            try {    
                br.close();    
            } catch (IOException e) {    
                e.printStackTrace();    
            }    
        }    
    } 
}