集合和映射(set and map)__JAVA版

集合

1.不支持添加重复元素
2.底层可以采用BST和LinkedList来实现
3.应用: 客户统计 ,词汇量统计

Set<E>接口

public interface Set<E> {
    void add(E e);
    void remove(E e);
    boolean contains(E e);
    int getSize();
    boolean isEmpty();
}

基于二叉搜索树的集合实现

public class BSTSet<E extends Comparable<E>> implements Set<E>{
    
    private BST<E> bst;

    public BSTSet(){
        bst = new BST<>();
    }

    @Override
    public void add(E e) {
        bst.add(e);
    }

    @Override
    public void remove(E e) {
        bst.remove(e);
    }

    @Override
    public boolean contains(E e) {
        return bst.contains(e);
    }

    @Override
    public int getSize() {
        return bst.getSize();
    }

    @Override
    public boolean isEmpty() {
        return bst.isEmpty();
    }
}

读取文本文件

import java.io.FileInputStream;
import java.util.ArrayList;
import java.util.Scanner;
import java.util.Locale;
import java.io.File;
import java.io.BufferedInputStream;
import java.io.IOException;

// 文件相关操作
public class FileOperation {

    // 读取文件名称为filename中的内容,并将其中包含的所有词语放进words中
    public static boolean readFile(String filename, ArrayList<String> words){

        if (filename == null || words == null){
            System.out.println("filename is null or words is null");
            return false;
        }

        // 文件读取
        Scanner scanner;

        try {
            File file = new File(filename);
            if(file.exists()){
                FileInputStream fis = new FileInputStream(file);
                scanner = new Scanner(new BufferedInputStream(fis), "UTF-8");
                scanner.useLocale(Locale.ENGLISH);
            }
            else
                return false;
        }
        catch(IOException ioe){
            System.out.println("Cannot open " + filename);
            return false;
        }

        // 简单分词
        // 这个分词方式相对简陋, 没有考虑很多文本处理中的特殊问题
        // 在这里只做demo展示用
        if (scanner.hasNextLine()) {

            String contents = scanner.useDelimiter("\\A").next();

            int start = firstCharacterIndex(contents, 0);
            for (int i = start + 1; i <= contents.length(); )
                if (i == contents.length() || !Character.isLetter(contents.charAt(i))) {
                    String word = contents.substring(start, i).toLowerCase();
                    words.add(word);
                    start = firstCharacterIndex(contents, i);
                    i = start + 1;
                } else
                    i++;
        }

        return true;
    }

    // 寻找字符串s中,从start的位置开始的第一个字母字符的位置
    private static int firstCharacterIndex(String s, int start){

        for( int i = start ; i < s.length() ; i ++ )
            if( Character.isLetter(s.charAt(i)) )
                return i;
        return s.length();
    }
}

测试Main

检测文本中多少个不同的单词

public class Main {

    public static void main(String[] args) {

        System.out.println("Pride and Prejudice");

        ArrayList<String> words1 = new ArrayList<>();
        if(FileOperation.readFile("/Users/apple/Desktop/AL/Set/src/pride-and-prejudice.txt", words1)) {
            System.out.println("Total words: " + words1.size());

            BSTSet<String> set1 = new BSTSet<>();
            for (String word : words1)
                set1.add(word);
            System.out.println("Total different words: " + set1.getSize());
        }

        System.out.println();


        System.out.println("A Tale of Two Cities");

        ArrayList<String> words2 = new ArrayList<>();
        if(FileOperation.readFile("/Users/apple/Desktop/AL/Set/src/a-tale-of-two-cities.txt", words2)){
            System.out.println("Total words: " + words2.size());

            BSTSet<String> set2 = new BSTSet<>();
            for(String word: words2)
                set2.add(word);
            System.out.println("Total different words: " + set2.getSize());
        }
    }
}

基于链表的集合实现

处理速度比bst实现的要慢很多

import java.util.ArrayList;

public class LinkedListSet<E> implements Set<E> {

    private LinkedList<E> list ;

    public LinkedListSet(){
        list = new LinkedList<>();
    }

    @Override
    public void add(E e) {
        if (!list.contains(e))
            list.addFirst(e);

    }

    @Override
    public void remove(E e) {
        list.removeElement(e);
    }

    @Override
    public boolean contains(E e) {
        return list.contains(e);
    }

    @Override
    public int getSize() {
        return list.getSize();
    }

    @Override
    public boolean isEmpty() {
        return list.isEmpty();
    }

    public static void main(String[] args) {

        System.out.println("Pride and Prejudice");

        ArrayList<String> words1 = new ArrayList<>();
        if(FileOperation.readFile("/Users/apple/Desktop/AL/Set/src/pride-and-prejudice.txt", words1)) {
            System.out.println("Total words: " + words1.size());

            LinkedListSet<String> set1 = new LinkedListSet<>();
            for (String word : words1)
                set1.add(word);
            System.out.println("Total different words: " + set1.getSize());
        }

        System.out.println();


        System.out.println("A Tale of Two Cities");

        ArrayList<String> words2 = new ArrayList<>();
        if(FileOperation.readFile("/Users/apple/Desktop/AL/Set/src/a-tale-of-two-cities.txt", words2)){
            System.out.println("Total words: " + words2.size());

            LinkedListSet<String> set2 = new LinkedListSet<>();
            for(String word: words2)
                set2.add(word);
            System.out.println("Total different words: " + set2.getSize());
        }
    }
}

69b97ad8b0ec808f6073082cb01a9a5e.png

有序集合与无序集合

基于搜索树实现的集合是有序集合
基于hash实现的集合是无序集合,速度上更快

映射Map

支持重复元素
底层可以用BST和LinkedList来实现
应用: 统计词频 , 统计每个人总得分等

Map<K,V>接口

public interface Map<K,V> {
    void add(K key, V value);
    V remove(K key);
    boolean contains(K key);
    V get(K key);
    void set(K key,V newValue);
    int getSize();
    boolean isEmpty();
}

基于LinkedList的Map实现

public class LinkedListMap<K, V> implements Map<K, V> {


    private class Node{
        public K key;
        public V value;
        public Node next;

        public Node(K key,V value,Node next){
            this.key = key;
            this.value = value;
            this.next = next;
        }

        public Node(K key){
            this(key,null,null);
        }

        public Node(){
            this(null,null,null);
        }

        @Override
        public String toString() {
            return key.toString()+" : " + value.toString();
        }
    }

    private Node dummyHead;
    private int size;


    public LinkedListMap(){
        dummyHead = new Node();
        size = 0;
    }

    private Node getNode(K key){
        Node res = dummyHead.next;
        while (res!=null){
            if (res.key.equals(key))
                return res;
            res = res.next;
        }
        return null;
    }
    @Override
    public void add(K key, V value) {
        Node node = getNode(key);
        if (node == null){
            dummyHead.next = new Node(key, value, dummyHead.next);
            size++;
        }
        else {
            node.value = value;
        }
    }

    @Override
    public V remove(K key) {
        Node prev = dummyHead;
        while (prev.next != null){
            if (prev.next.key.equals(key))
                break;
            prev = prev.next;
        }

        if (prev.next != null){
            Node delNode = prev.next;
            prev.next = prev.next.next;
            delNode.next = null;
            size--;
            return delNode.value;
        }

        return null;
    }

    @Override
    public boolean contains(K key) {

        return getNode(key) != null;
    }

    @Override
    public V get(K key) {
        Node node = getNode(key);
        return getNode(key) == null ? null : node.value;
    }

    @Override
    public void set(K key, V newValue) {
        Node node = getNode(key);
        if (node != null)
            node.value = newValue;
        else
            throw new IllegalArgumentException("key no extens");
    }

    @Override
    public int getSize() {
        return size;
    }

    @Override
    public boolean isEmpty() {
        return size==0;
    }
}

基于BST实现的映射

import java.util.ArrayList;

public class BSTMap<K extends Comparable<K>, V> implements Map<K, V> {

    private class Node{
        public K key;
        public V value;
        public Node left, right;

        public Node(K key, V value){
            this.key = key;
            this.value = value;
            left = null;
            right = null;
        }
    }

    private Node root;
    private int size;

    public BSTMap(){
        root = null;
        size = 0;
    }

    @Override
    public int getSize(){
        return size;
    }

    @Override
    public boolean isEmpty(){
        return size == 0;
    }

    // 向二分搜索树中添加新的元素(key, value)
    @Override
    public void add(K key, V value){
        root = add(root, key, value);
    }

    // 向以node为根的二分搜索树中插入元素(key, value),递归算法
    // 返回插入新节点后二分搜索树的根
    private Node add(Node node, K key, V value){

        if(node == null){
            size ++;
            return new Node(key, value);
        }

        if(key.compareTo(node.key) < 0)
            node.left = add(node.left, key, value);
        else if(key.compareTo(node.key) > 0)
            node.right = add(node.right, key, value);
        else // key.compareTo(node.key) == 0
            node.value = value;

        return node;
    }

    // 返回以node为根节点的二分搜索树中,key所在的节点
    private Node getNode(Node node, K key){

        if(node == null)
            return null;

        if(key.equals(node.key))
            return node;
        else if(key.compareTo(node.key) < 0)
            return getNode(node.left, key);
        else // if(key.compareTo(node.key) > 0)
            return getNode(node.right, key);
    }

    @Override
    public boolean contains(K key){
        return getNode(root, key) != null;
    }

    @Override
    public V get(K key){

        Node node = getNode(root, key);
        return node == null ? null : node.value;
    }

    @Override
    public void set(K key, V newValue){
        Node node = getNode(root, key);
        if(node == null)
            throw new IllegalArgumentException(key + " doesn't exist!");

        node.value = newValue;
    }

    // 返回以node为根的二分搜索树的最小值所在的节点
    private Node minimum(Node node){
        if(node.left == null)
            return node;
        return minimum(node.left);
    }

    // 删除掉以node为根的二分搜索树中的最小节点
    // 返回删除节点后新的二分搜索树的根
    private Node removeMin(Node node){

        if(node.left == null){
            Node rightNode = node.right;
            node.right = null;
            size --;
            return rightNode;
        }

        node.left = removeMin(node.left);
        return node;
    }

    // 从二分搜索树中删除键为key的节点
    @Override
    public V remove(K key){

        Node node = getNode(root, key);
        if(node != null){
            root = remove(root, key);
            return node.value;
        }
        return null;
    }

    private Node remove(Node node, K key){

        if( node == null )
            return null;

        if( key.compareTo(node.key) < 0 ){
            node.left = remove(node.left , key);
            return node;
        }
        else if(key.compareTo(node.key) > 0 ){
            node.right = remove(node.right, key);
            return node;
        }
        else{   // key.compareTo(node.key) == 0

            // 待删除节点左子树为空的情况
            if(node.left == null){
                Node rightNode = node.right;
                node.right = null;
                size --;
                return rightNode;
            }

            // 待删除节点右子树为空的情况
            if(node.right == null){
                Node leftNode = node.left;
                node.left = null;
                size --;
                return leftNode;
            }

            // 待删除节点左右子树均不为空的情况

            // 找到比待删除节点大的最小节点, 即待删除节点右子树的最小节点
            // 用这个节点顶替待删除节点的位置
            Node successor = minimum(node.right);
            successor.right = removeMin(node.right);
            successor.left = node.left;

            node.left = node.right = null;

            return successor;
        }
    }

    public static void main(String[] args){

        System.out.println("Pride and Prejudice");

        ArrayList<String> words = new ArrayList<>();
        if(FileOperation.readFile("pride-and-prejudice.txt", words)) {
            System.out.println("Total words: " + words.size());

            BSTMap<String, Integer> map = new BSTMap<>();
            for (String word : words) {
                if (map.contains(word))
                    map.set(word, map.get(word) + 1);
                else
                    map.add(word, 1);
            }

            System.out.println("Total different words: " + map.getSize());
            System.out.println("Frequency of PRIDE: " + map.get("pride"));
            System.out.println("Frequency of PREJUDICE: " + map.get("prejudice"));
        }

        System.out.println();
    }
}
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值