java实现找出两个文件中相同的单词，具体代码如下所示：
package com.zy.DesignPrinciples.singleresponsibility;
import javax.print.DocFlavor;
import java.io.BufferedReader;
import java.io.FileReader;
import java.util.HashSet;
/**
* @ClassName: ReaderComplete
* @Author: Tiger
* @Title: 找出两个文件中相同的单词
* @Datetime: 2020/8/19 19:49
* @Package: com.zy.DesignPrinciples.singleresponsibility
*/
public class ReaderComplete {
public static void main(String[] args) throws Exception {
String s = loadFile("F:\\.temp\\1.txt");
String s1 = loadFile("F:\\.temp\\2.txt");
String[] words1 = parseWordsFromString(s);
String[] words2 = parseWordsFromString(s1);
String[] words = findTheSameWords(words1, words2);
for (String word : words) {
System.out.println(word);
}
}
//加载文件内容，并将文本内容解析返回出去
public static String loadFile(String path) throws Exception {
FileReader reader = new FileReader(path);
//bufferedReader 一次只能读一行内容
BufferedReader br = new BufferedReader(reader);
String line = null;
StringBuilder sb = new StringBuilder();
while ((line = br.readLine()) != null) {
sb.append(line);
sb.append("\n");
}
br.close();
return sb.toString();
}
//将解析的内容变成数组
public static String[] parseWordsFromString(String string) {
String[] strings = string.split("[^a-zA-Z]+");
return strings;
}
//查询两文件的相同代码
public static String[] findTheSameWords(String[] s1,String[] s2){
HashSet<String> set = new HashSet<>();
for (int i = 0; i < s1.length; i++) {
for (int j = 0; j < s2.length; j++) {
if (s1[i].equals(s2[j])){
set.add(s1[i]);
}
}
}
return set.toArray(new String[] {});
}
}
第二种比较单词的方法：将string【】数组转换成集合，通过集合的retainAll()方法
两个集合取交集
public static String[] findTheSameWords2(String[] s1,String[] s2){
//将字符串数组转换成集合
List<String> list = new ArrayList(Arrays.asList(s1));
List<String> list2 = new ArrayList(Arrays.asList(s2));
//计算交集 并且把计算结果存入到list中而且list2并不会改变
list.retainAll(list2);
HashSet<String> set = new HashSet<>(list);
return set.toArray(new String[] {});
}
PS：java实现获取两个文本共同的词
代码块
public class ComWords {
/**
* @ClassName: ComWords
* @Description: TODO(获取两个文档的共同词)
* @author: Amy_Robot
* @date: 2017年3月24日 下午5:16:48
*/
public static String getFileContent(String path)
{
StringBuffer sb = new StringBuffer();
InputStreamReader isr = null;
BufferedReader bufferedReader = null;
String fileContent="";{
try {
String encoding = "utf-8";
File file = new File(path);
if (file.isFile() && file.exists()) { // 判断文件是否存在
isr = new InputStreamReader(new FileInputStream(file), encoding);// 考虑到编码格式
bufferedReader = new BufferedReader(isr);
String lineTxt = null;
while ((lineTxt = bufferedReader.readLine()) != null) {
//System.out.println(lineTxt);//输出文档内容
sb.append(lineTxt);
}
isr.close();
} else {
System.out.println("找不到指定的文件");
}
} catch (Exception e) {
System.out.println("读取文件内容出错");
e.printStackTrace();
} finally {
try {
if (isr != null) {
isr.close();
isr = null;
}
if (bufferedReader != null) {
bufferedReader.close();
bufferedReader = null;
}
} catch (Exception e) {
e.printStackTrace();
}
}
return sb.toString();}
}
public static void getComWords(String sourcefile1,String sourcefile2,String targetfile) throws IOException{
BufferedWriter F2Writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(targetfile))));
List<String> list1= new ArrayList<String>();
List<String> list2= new ArrayList<String>();
List<String> list3= new ArrayList<String>();
String a[] =getFileContent(sourcefile1).split("\\s");
for (int j = 0; j < a.length; j++) {
list1.add(a[j]);
}
String b[] = getFileContent(sourcefile2).split("\\s");
for (int j = 0; j < b.length; j++) {
list2.add(b[j]);
}
for (String str2 : list2) {
if(list1.contains(str2)){
list3.add(str2);
F2Writer.write(str2+"\r\n");
}
}
for (String str : list3) {
System.out.println(str);
}
F2Writer.close();
}
public static void main(String[] args) throws IOException {
String target="e:\\1.txt";
String path1="D:\\qirui_naf.txt";
String path2="D:\\jianghuai_naf.txt";
getComWords(path1, path2, target);
}
}
