文本文件单词的检索与计数（Java代码实现）

谁借莪１个温暖的怀抱￠ 2023-10-04 08:07 4阅读 0赞

### 文章目录 ###

*   *  一、文本文件单词匹配算法类（algorithm包）
     *   *  1.BFAlgorithm类（朴素模式匹配算法）
         *  2.代码如下
         *  3.KMPAlgorithm类（KMP匹配算法）
         *  4.代码如下
     *  二、文本文件数据类和文档交互类（data包）
     *   *  1.Reader类
         *  2.代码如下
         *  3.Database类
         *  4.代码如下
     *  三、文本文件数据访问对象类（dao包）
     *   *  1.wordDao类
     *  四、文本文件信息类（pojo包）
     *   *  1.sentence类
         *  2.代码如下
     *  五、文本文档服务端类（Service包）
     *   *  1.searchService类
         *  2.代码如下
     *  六、文本文档主类（main包）
     *   *  1.main类
         *  2.代码如下
     *  七、文本文档信息存储展示
     *  八、文本代码运行结果展示

## 一、文本文件单词匹配算法类（algorithm包） ##

### 1.BFAlgorithm类（朴素模式匹配算法） ###

### 2.代码如下 ###

package algorithm;
    
    public class BFAlgorithm {
        public int bf(String str1, String match1) {
            int length1 = str1.length();
            int length2 = match1.length();
            int i = 0;
            int j = 0;
            int k = 0;
            char [] str = str1.toCharArray();
            char [] match = match1.toCharArray();
            while(i < length1 && j < length2) {
                if(str[i] == match[j]) {
                    i++;
                    j++;
                }else {
                    k++;
                    j = 0;
                    i = k;
                }
            }
            if(j == length2) {
                return k;
            }else {
                return -1;
            }
        }
    
    }

### 3.KMPAlgorithm类（KMP匹配算法） ###

### 4.代码如下 ###

package algorithm;
    
    public class KMPAlgorithm {
        public static int[] getNextArray(char[] t) {
            int[] next = new int[t.length];
            next[0] = -1;
            next[1] = 0;
            int k;
            for (int j = 2; j < t.length; j++) {
                k=next[j-1];
                while (k!=-1) {
                    if (t[j - 1] == t[k]) {
                        next[j] = k + 1;
                        break;
                    }
                    else {
                        k = next[k];
                    }
                    next[j] = 0;
                }
            }
            return next;
        }
    
    
        public int kmpMatch(String s, String t){
            char[] s_arr = s.toCharArray();
            char[] t_arr = t.toCharArray();
            int[] next = getNextArray(t_arr);
            int i = 0, j = 0;
            while (i<s_arr.length && j<t_arr.length){
                if(j == -1 || s_arr[i]==t_arr[j]){
                    i++;
                    j++;
                }
                else
                    j = next[j];
            }
            if(j == t_arr.length)
                return i-j;
            else
                return -1;
        }
    }

## 二、文本文件数据类和文档交互类（data包） ##

### 1.Reader类 ###

### 2.代码如下 ###

package data;
    
    import java.io.*;
    import java.util.ArrayList;
    
    public class Reader {
        private BufferedReader br;
        private File file = new File("E:\\javaText\\javaOne\\JavaSE\\document.txt");
    
        public Reader() {
        }
    
        public ArrayList<String> reader() {
            ArrayList<String> list = new ArrayList<>();
            //创建字符缓冲输入流
            try {
                br = new BufferedReader(
                        new InputStreamReader(new FileInputStream(file)));
                String line = null;
                while ((line = br.readLine()) != null) {
                    list.add(line);
                }
                br.close();
            } catch (Exception e) {
                e.printStackTrace();
            }
            return list;
        }
    
    }

### 3.Database类 ###

### 4.代码如下 ###

package data;
    import pojo.sentence;
    
    import java.util.ArrayList;
    
    
    public class Database {
        private Reader reader = new Reader();
        private sentence word = new sentence();
        private ArrayList<sentence> list = new ArrayList<>();
    
        public Database() {
            ArrayList<String> list1 = reader.reader();
            ArrayList<String> list2 = new ArrayList<>();
            for (String s : list1) {
                String student[] = s.split(" ");
                for (int i = 0; i < student.length; i++) {
                    list2.add(student[i]);
                }
                ArrayList<String> list3 = new ArrayList<>();
                for (String s1 : list2) {
                    list3.add(s1);
                }
                list2.clear();
                list.add(new sentence(list3));
            }
        }
    
        public ArrayList<sentence> getList() {
            return list;
        }
    }

## 三、文本文件数据访问对象类（dao包） ##

### 1.wordDao类 ###

package dao;
    import data.Database;
    
    public class wordDao {
        private Database database;
    
        public wordDao(Database database) {
            this.database = database;
        }
    
        public Database getDatabase() {
            return database;
        }
    }

## 四、文本文件信息类（pojo包） ##

### 1.sentence类 ###

### 2.代码如下 ###

package pojo;
    
    import java.util.ArrayList;
    
    public class sentence {
        private ArrayList<String> list = new ArrayList<>();
    
        public sentence() {
        }
    
        public sentence(ArrayList<String> list) {
            this.list = list;
        }
    
        public ArrayList<String> getList() {
            return list;
        }
    
        public void setList(ArrayList<String> list) {
            this.list = list;
        }
    }

## 五、文本文档服务端类（Service包） ##

### 1.searchService类 ###

### 2.代码如下 ###

package service;
    
    import algorithm.BFAlgorithm;
    import algorithm.KMPAlgorithm;
    import dao.wordDao;
    import data.Database;
    import pojo.sentence;
    
    import java.util.ArrayList;
    import java.util.Scanner;
    
    public class searchService {
        private Scanner key = new Scanner(System.in);
        private wordDao wordDao;
        private KMPAlgorithm kmp_algorithm = new KMPAlgorithm();
        private BFAlgorithm bf_algorithm = new BFAlgorithm();
    
        public searchService(Database database) {
            wordDao = new wordDao(database);
        }
    
        /**
         * 主菜单
         */
        public void start() {
            System.out.println("::::::主菜单::::::");
            System.out.println("****请您按需查找:****");
            System.out.println("1.#进行单词的查找#");
            System.out.println("2.#进行子串的查询#");
            System.out.println("3.#退出系统######");
            String choice = key.next();
            switch (choice) {
                case "1":
                    searchWord();
                    break;
                case "2":
                    substring();
                    break;
                case "3":
                    System.out.println("已退出，欢迎下次使用！");
                    break;
                default:
                    System.out.println("输入有误，请重新输入");
                    start();
            }
        }
    
        /**
         * 单个单词查找
         */
        public void searchWord() {
            int array[] = new int[2];
            ArrayList<int[]> list = new ArrayList<>();
            System.out.println("请输入您要查找的单词：");
            String s = key.next();
            for (sentence word : wordDao.getDatabase().getList()) {
                for (int i = 0; i < word.getList().size(); i++) {
                    if (word.getList().get(i).equals(s)) {
                        array = new int[]{wordDao.getDatabase().getList().indexOf(word) + 1, i + 1};
                        list.add(array);
                    }
                }
            }
            System.out.println("总共找到该单词" + s + " " + list.size() + "次");
            for (int i = 0; i < list.size(); i++) {
                System.out.println("第" + (i + 1) + "次：第" + list.get(i)[0] + "行第" + list.get(i)[1] + "个单词");
            }
            System.out.println("输入数字回到主菜单");
            String s1 = key.next();
            System.out.println("已为您返回主菜单");
            start();
        }
    
        /**
         * 字符串子串查询
         */
        public void substring() {
            String[] array = new String[3];
            ArrayList<String[]> list = new ArrayList<>();
            System.out.println("请输入你要查找的字符串子串：");
            String s = key.next();
            for (sentence word : wordDao.getDatabase().getList()) {
                for (int i = 0; i < word.getList().size(); i++) {
                    //int n=kmp_algorithm.kmpMatch(s,word.getList().get(i));
                    int n = bf_algorithm.bf(s, word.getList().get(i));
                    if (n != -1) {
                        array = new String[]{word.getList().get(i),
                                String.valueOf(wordDao.getDatabase().getList().indexOf(word) + 1),
                                String.valueOf(i + 1)};
                        list.add(array);
                    }
                }
            }
            System.out.println("总共找到该字符串" + s + "的子串" + list.size() + "次");
            for (int i = 0; i < list.size() - 1; i++) {
                System.out.println("第" + (i + 1) + "个字串" + list.get(i)[0] + ":第" + list.get(i)[1] + "行第" + list.get(i)[2] + "个单词");
            }
            System.out.println("输入数字回到主菜单");
            String s1 = key.next();
            System.out.println("已为您返回主菜单");
            start();
        }
    }

## 六、文本文档主类（main包） ##

### 1.main类 ###

### 2.代码如下 ###

package main;
    
    import data.Database;
    import service.searchService;
    
    public class main {
        public static void main(String[] args) {
            Database database = new Database();
            searchService wordServer = new searchService(database);
            wordServer.start();
        }
    }

## 七、文本文档信息存储展示 ##

![在这里插入图片描述][20210312013633755.png]

## 八、文本代码运行结果展示 ##

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1_size_16_color_FFFFFF_t_70]  
![在这里插入图片描述][20210312014317117.png]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1_size_16_color_FFFFFF_t_70 1]

[20210312013633755.png]: https://img-blog.csdnimg.cn/20210312013633755.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20210312014245894.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1,size_16,color_FFFFFF,t_70
[20210312014317117.png]: https://img-blog.csdnimg.cn/20210312014317117.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20210312014404740.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L20wXzQ4MTcwMjY1,size_16,color_FFFFFF,t_70