記事内で繰り返される中国語文字列を読み取るためのサンプルコード分析の Java 実装

import java.io.*;
import java.util.*;
/**
 * Created by chunmiao on 17-3-20.
 */
public class ReadArticle {
 //读取文件名称
 private String filename;
 //读取段落
 private ArrayList<String> result = new ArrayList<>();
 //最小字长（两个字以上进行匹配）
 private final int MINSIZE = 2;
 //重复词储存
 HashSet<String> set;
 public ReadArticle(String filename, HashSet<String> set) {
 this.filename = filename;
 this.set = set;
 }
 public void createData() throws IOException {
 String r;
 //读取文章内容
 BufferedReader in = new BufferedReader(new FileReader(new File(filename).getAbsoluteFile()));
 try {
  while ((r = in.readLine()) != null) {
  //消除不必要的标点符号
  r = r.replaceAll("\\s+ |“|\\[|‘|《|　*|", "").trim();
  //留下” ， 。 。” ”。 ”， ？ 》 -等作为划分句子的分割符标示
  Collections.addAll(result, r.split("，|(。”|”(。|，)|。)|(\\])|”|&#39;|？|:|》|-"));
  }
 }finally {
  in.close();
 }
 //对文章内容进行遍历找出重读出现的句子或者是词语
 for (int i = 0 ; i < result.size() - 1; i ++){
  for (int j = 0 ; j < result.size() - i - 1; j ++) {
  //将重复出现的词语保存到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;
 //短句遍历开始处
 int start = 0;
 //词的长度最短为两个字长
 int range =2;
 //设定短句和长句s,使得遍历更加快捷
 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时超出范围
 while (start + range <= minS.length()) {
  //如果句子或词在对象里面，则找出相应的句子或词保存在list里面
  if (maxS.indexOf(minS.substring(start, start + range)) != -1) {
  //获取最长句子,删除短句子
  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("这篇文章中的重复出现的词或句子有以下几个词或句子:\n");
 for (String s : result){
  System.out.println(s);
 }
 }
}