利用Java如何實(shí)現(xiàn)讀取文章中重復(fù)的中文

import java.io.*;
import java.util.*;
/**
 * Created by chunmiao on 17-3-20.
 */
public class ReadArticle {
 //讀取文件名稱
 private String filename;
 //讀取段落
 private ArrayList<String> result = new ArrayList<>();
 //最小字長（兩個(gè)字以上進(jìn)行匹配）
 private final int MINSIZE = 2;
 //重復(fù)詞儲(chǔ)存
 HashSet<String> set;
 public ReadArticle(String filename, HashSet<String> set) {
 this.filename = filename;
 this.set = set;
 }
 public void createData() throws IOException {
 String r;
 //讀取文章內(nèi)容
 BufferedReader in = new BufferedReader(new FileReader(new File(filename).getAbsoluteFile()));
 try {
  while ((r = in.readLine()) != null) {
  //消除不必要的標(biāo)點(diǎn)符號(hào)
  r = r.replaceAll("\\s+ |“|\\[|‘|《|　*|", "").trim();
  //留下” ， 。 ?！?”。 ”， ？ 》 -等作為劃分句子的分割符標(biāo)示
  Collections.addAll(result, r.split("，|(?！眧”(。|，)|。)|(\\])|”|'|？|:|》|-"));
  }
 }finally {
  in.close();
 }
 //對(duì)文章內(nèi)容進(jìn)行遍歷找出重讀出現(xiàn)的句子或者是詞語
 for (int i = 0 ; i < result.size() - 1; i ++){
  for (int j = 0 ; j < result.size() - i - 1; j ++) {
  //將重復(fù)出現(xiàn)的詞語保存到set集合里面
  set.addAll(getSameCharacter(result.get(i), result.get(j + i + 1)));
  }
 }
 }
 private ArrayList<String> getSameCharacter(String a1, String a2){
 String maxS;
 String minS;
 //短句遍歷開始處
 int start = 0;
 //詞的長度最短為兩個(gè)字長
 int range =2;
 //設(shè)定短句和長句s,使得遍歷更加快捷
 if (a1.length() <= a2.length()){
  maxS = a2;
  minS = a1;
 }else {
  maxS = a1;
  minS = a2;
 }
 String result = "";
 ArrayList<String> list = new ArrayList<String>();
 //防止substring時(shí)超出范圍
 while (start + range <= minS.length()) {
  //如果句子或詞在對(duì)象里面，則找出相應(yīng)的句子或詞保存在list里面
  if (maxS.indexOf(minS.substring(start, start + range)) != -1) {
  //獲取最長句子,刪除短句子
  list.remove(result);
  list.add(minS.substring(start, start + range));
  result = minS.substring(start, start + range);
  range++;
  continue;
  }
  range = MINSIZE;
  start++;
 }
 return list;
 }
}

import java.io.IOException;
import java.util.HashSet;
public class Main {
 public static void main(String[] args) throws IOException {
 String filename = "test.txt";
 HashSet<String> result = new HashSet<String>();
 ReadArticle read = new ReadArticle(filename,result);
 read.createData();
 System.out.println("這篇文章中的重復(fù)出現(xiàn)的詞或句子有以下幾個(gè)詞或句子:\n");
 for (String s : result){
  System.out.println(s);
 }
 }
}