比较两个文件夹下的代码重复率

最新推荐文章于 2024-08-19 16:01:20 发布

南北念着东西

最新推荐文章于 2024-08-19 16:01:20 发布

阅读量229

点赞数 3

文章标签： java

本文链接：https://blog.csdn.net/qq_41120938/article/details/138512439

版权

指纹比对算法

package com.example.springbootdemo.controller;

import java.io.*;
import java.util.*;

public class CodeDuplicationChecker3 {

    public static void main(String[] args) {
            String dir1 = "E:\\fp\\Folder1";
            String dir2 = "E:\\fp\\Folder2";

        File folder1 = new File(dir1);
        File folder2 = new File(dir2);

        if (!folder1.isDirectory() || !folder2.isDirectory()) {
            System.out.println("Error: Both arguments must be valid directories.");
            return;
        }

        Map<String, Set<String>> wordsMap1 = getFileWordsMap(folder1);
        Map<String, Set<String>> wordsMap2 = getFileWordsMap(folder2);

        Set<String> uniqueWords = new HashSet<>(wordsMap1.keySet());
        uniqueWords.addAll(wordsMap2.keySet());

        int totalUniqueWords = uniqueWords.size();
        List<String> duplicatedWords = findDuplicatedWords(wordsMap1, wordsMap2);

        System.out.println("Total unique words compared: " + totalUniqueWords);
        System.out.println("Duplicated words found: " + duplicatedWords.size());
        double duplicationRate = ((double) duplicatedWords.size() / totalUniqueWords) * 100;
        System.out.println("Code duplication rate: " + duplicationRate + "%");

        for (String word : duplicatedWords) {
            System.out.println("Duplicated word: " + word);
            Set<String> files1 = wordsMap1.getOrDefault(word, new HashSet<>());
            Set<String> files2 = wordsMap2.getOrDefault(word, new HashSet<>());
            System.out.println("Files in folder 1: " + files1);
            System.out.println("Files in folder 2: " + files2);
            System.out.println("---------------------------------------");
        }
    }

    private static Map<String, Set<String>> getFileWordsMap(File folder) {
        Map<String, Set<String>> wordsMap = new HashMap<>();
        addFilesToWordsMap(folder, wordsMap);
        return wordsMap;
    }

    private static void addFilesToWordsMap(File folder, Map<String, Set<String>> wordsMap) {
        File[] files = folder.listFiles();
        if (files != null) {
            for (File file : files) {
                if (file.isDirectory()) {
                    addFilesToWordsMap(file, wordsMap); // Recursive call for subdirectory
                } else if (file.isFile() && file.getName().endsWith(".java")) {
                    try {
                        Set<String> wordsSet = getFileWordsSet(file);
                        for (String word : wordsSet) {
                            Set<String> filesSet = wordsMap.computeIfAbsent(word, k -> new HashSet<>());
                            filesSet.add(file.getAbsolutePath());
                        }
                    } catch (IOException e) {
                        e.printStackTrace();
                    }
                }
            }
        }
    }

    private static Set<String> getFileWordsSet(File file) throws IOException {
        Set<String> wordsSet = new HashSet<>();
        BufferedReader reader = new BufferedReader(new FileReader(file));
        String line;
        while ((line = reader.readLine()) != null) {
            String[] words = line.trim().split("[\\s\\p{Punct}]+"); // Split by whitespace and punctuation
            wordsSet.addAll(Arrays.asList(words));
        }
        reader.close();
        return wordsSet;
    }

    private static List<String> findDuplicatedWords(Map<String, Set<String>> wordsMap1, Map<String, Set<String>> wordsMap2) {
        List<String> duplicatedWords = new ArrayList<>();
        for (String word : wordsMap1.keySet()) {
            if (wordsMap2.containsKey(word)) {
                duplicatedWords.add(word);
            }
        }
        return duplicatedWords;
    }
}