使用Pinyin4j进行拼音分词的方法

使用maven引入相关的jar

 com.belerweb
 pinyin4j
 2.5.1

创建Pinyin4jUtil

package com.os.core.util.solr;
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.util.ArrayList;
import java.util.Hashtable;
import java.util.List;
import java.util.Map;

public class Pinyin4jUtil {
 public static void main(String[] args) {
  String str = "测试";
  String pinyin = Pinyin4jUtil.converterToSpell(str);
  System.out.println(str + " pin yin ：" + pinyin);
  pinyin = Pinyin4jUtil.converterToFirstSpell(str);
  System.out.println(str + " short pin yin ：" + pinyin);
 }
 
 public static String converterToFirstSpell(String chines) {
  StringBuffer pinyinName = new StringBuffer();
  char[] nameChar = chines.toCharArray();
  HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
  defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
  defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
  for (int i = 0; i < nameChar.length; i++) {
   if (nameChar[i] > 128) {
    try {
     // 取得当前汉字的所有全拼
     String[] strs = PinyinHelper.toHanyuPinyinStringArray(
nameChar[i], defaultFormat);
     if (strs != null) {
      for (int j = 0; j < strs.length; j++) {
// 取首字母
pinyinName.append(strs[j].charAt(0));
if (j != strs.length - 1) {
 pinyinName.append(",");
}
      }
     }
     // else {
     // pinyinName.append(nameChar[i]);
     // }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
     e.printStackTrace();
    }
   } else {
    pinyinName.append(nameChar[i]);
   }
   pinyinName.append(" ");
  }
  // return pinyinName.toString();
  return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
 }
 
 public static String converterToSpell(String chines) {
  StringBuffer pinyinName = new StringBuffer();
  char[] nameChar = chines.toCharArray();
  HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
  defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
  defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
  for (int i = 0; i < nameChar.length; i++) {
   if (nameChar[i] > 128) {
    try {
     // 取得当前汉字的所有全拼
     String[] strs = PinyinHelper.toHanyuPinyinStringArray(
nameChar[i], defaultFormat);
     if (strs != null) {
      for (int j = 0; j < strs.length; j++) {
pinyinName.append(strs[j]);
if (j != strs.length - 1) {
 pinyinName.append(",");
}
      }
     }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
     e.printStackTrace();
    }
   } else {
    pinyinName.append(nameChar[i]);
   }
   pinyinName.append(" ");
  }
  // return pinyinName.toString();
  return parseTheChineseByObject(discountTheChinese(pinyinName.toString()));
 }
 
 private static List> discountTheChinese(String theStr) {
  // 去除重复拼音后的拼音列表
  List> mapList = new ArrayList>();
  // 用于处理每个字的多音字，去掉重复
  Map onlyOne = null;
  String[] firsts = theStr.split(" ");
  // 读出每个汉字的拼音
  for (String str : firsts) {
   onlyOne = new Hashtable();
   String[] china = str.split(",");
   // 多音字处理
   for (String s : china) {
    Integer count = onlyOne.get(s);
    if (count == null) {
     onlyOne.put(s, new Integer(1));
    } else {
     onlyOne.remove(s);
     count++;
     onlyOne.put(s, count);
    }
   }
   mapList.add(onlyOne);
  }
  return mapList;
 }
 
 private static String parseTheChineseByObject(
   List> list) {
  Map first = null; // 用于统计每一次,集合组合数据
  // 遍历每一组集合
  for (int i = 0; i < list.size(); i++) {
   // 每一组集合与上一次组合的Map
   Map temp = new Hashtable();
   // 第一次循环，first为空
   if (first != null) {
    // 取出上次组合与此次集合的字符，并保存
    for (String s : first.keySet()) {
     for (String s1 : list.get(i).keySet()) {
      String str = s + s1;
      temp.put(str, 1);
     }
    }
    // 清理上一次组合数据
    if (temp != null && temp.size() > 0) {
     first.clear();
    }
   } else {
    for (String s : list.get(i).keySet()) {
     String str = s;
     temp.put(str, 1);
    }
   }
   // 保存组合数据以便下次循环使用
   if (temp != null && temp.size() > 0) {
    first = temp;
   }
  }
  String returnStr = "";
  if (first != null) {
   // 遍历取出组合字符串
   for (String str : first.keySet()) {
    returnStr += (str + ",");
   }
  }
  if (returnStr.length() > 0) {
   returnStr = returnStr.substring(0, returnStr.length() - 1);
  }
  return returnStr;
 }
}

以上这篇使用Pinyin4j进行拼音分词的方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持考高分网。