数据结构之哈夫曼树及编码的实现（java）

package com.haiyang.datastructure.huffmancode;

import java.util.*;

/**
 * @author haiYang
 * @create 2022-01-19 15:31
 */
public class HuffmanCode {
    public static void main(String[] args) {
        String content = "The most heated arguments often occur between people on opposite ends of the spectrum";
        //对应的字节数组为[84, 104, 101, 32, 109, 111, 115, 116, 32, 104, 101, 97, 116, 101, 100, 32, 97, 114, 103, 117, 109, 101, 110, 116, 115, 32, 111, 102, 116, 101, 110, 32, 111, 99, 99, 117, 114, 32, 98, 101, 116, 119, 101, 101, 110, 32, 112, 101, 111, 112, 108, 101, 32, 111, 110, 32, 111, 112, 112, 111, 115, 105, 116, 101, 32, 101, 110, 100, 115, 32, 111, 102, 32, 116, 104, 101, 32, 115, 112, 101, 99, 116, 114, 117, 109]
        byte[] contentBytes = content.getBytes();//将给定的字符串转化为字节数组
        System.out.println(Arrays.toString(contentBytes));
        System.out.println(contentBytes.length);

        List<Node> nodes = getNodes(contentBytes);//调用getCodes方法将字节数组转化为结点类型
        System.out.println("nodes=" + nodes);
        //nodes=[Node{data=32, weight=13}, Node{data=97, weight=2}, Node{data=98, weight=1}, Node{data=99, weight=3}, Node{data=100, weight=2}, Node{data=101, weight=14}, Node{data=102, weight=2}, Node{data=103, weight=1}, Node{data=104, weight=3}, Node{data=105, weight=1}, Node{data=108, weight=1}, Node{data=109, weight=3}, Node{data=110, weight=5}, Node{data=111, weight=8}, Node{data=112, weight=5}, Node{data=114, weight=3}, Node{data=115, weight=5}, Node{data=84, weight=1}, Node{data=116, weight=8}, Node{data=117, weight=3}, Node{data=119, weight=1}]
        System.out.println("创建哈夫曼树");
        Node huffmanTree = createHuffmanTree(nodes);
        System.out.println("先序遍历");
        huffmanTree.preOrder();

        Map<Byte, String> codes = getCodes(huffmanTree);//获取哈夫曼编码
        System.out.println(codes);


    }
    //用于存储哈夫曼编码
    static Map<Byte, String> huffmanCodes = new HashMap<Byte, String>();
    //用于拼接哈夫曼编码
    static StringBuilder stringBuilder = new StringBuilder();

    /**
     * 获取哈夫曼编码
     * @param node 根结点
     * @param code 编码 左0右1
     * @param stringBuilder 用于拼接哈夫曼编码
     */
    public static void getCodes(Node node, String code, StringBuilder stringBuilder) {
        StringBuilder stringBuilder1 = new StringBuilder(stringBuilder);
        stringBuilder1.append(code);
        if(node != null){
            if(node.data == null){ //代表非叶子结点
                getCodes(node.left,"0",stringBuilder1);
                getCodes(node.right,"1",stringBuilder1);
            }else{
                //如果是叶子结点，代表该字节的编码已拼接完成，加入到Map中
                huffmanCodes.put(node.data,stringBuilder1.toString());
            }
        }
    }

    /**
     * 方法重载
     * 将字节编码存储到Map中
     * @param root
     * @return
     */
    public static Map<Byte,String> getCodes(Node root){
        if(root ==null){
            return null;
        }
        getCodes(root.left,"0",stringBuilder);
        getCodes(root.right,"1",stringBuilder);
        return huffmanCodes;
    }

    public static void preOrder(Node root) {
        if (root != null) {
            root.preOrder();
        } else {
            System.out.println("树为空，无法遍历");
        }
    }

    //将字节数组转化为结点类型
    public static List<Node> getNodes(byte[] bytes) {
        ArrayList<Node> nodes = new ArrayList<>();//储存结点
        HashMap<Byte, Integer> map = new HashMap<>();//储存每种字节出现的次数
        for (byte b : bytes) {
            //遍历数组记录每种字节出现的次数
            Integer count = map.get(b);
            if (count == null) {
                map.put(b, 1);
            } else {
                map.put(b, count + 1);
            }
        }

        for (Map.Entry<Byte, Integer> entry : map.entrySet()) {
            //遍历Map将每种字节及其出现的次数转化为结点
            nodes.add(new Node(entry.getKey(), entry.getValue()));
        }
        return nodes;
    }

    /**
     * 创建哈夫曼树
     * 1、首先将结点列表nodes按weight升序排序
     * 2、从结点列表nodes中选取两个最小的结点构建一棵树，其根节点的weight为两个最小结点的和
     * 3、将结点列表中的已选取两个最小的结点移除，并将新构建的树的根节点加入到结点列表中
     * 4、重复1 2 3 步骤，直到剩一个结点，此节点为已构建好的哈夫曼树的根节点
     * @param nodes
     * @return
     */
    public static Node createHuffmanTree(List<Node> nodes) {
        while (nodes.size() > 1) {
            //按weight升序排序
            Collections.sort(nodes);
            //从结点列表nodes中选取两个最小的结点
            Node leftNode = nodes.get(0);
            Node rightNode = nodes.get(1);
            //通过选取的结点构建一棵树,其根节点的weight为两个最小结点的和
            Node parent = new Node(null, leftNode.weight + rightNode.weight);
            parent.left = leftNode;
            parent.right = rightNode;
            //将结点列表中的已选取两个最小的结点移除，并将新构建的树的根节点加入到结点列表中
            nodes.remove(leftNode);
            nodes.remove(rightNode);
            nodes.add(parent);
        }
        return nodes.get(0);
    }
}

class Node implements Comparable<Node> {
    //在给定的序列中，每种字节是一个data，weight代表每种字节出现的次数
    Byte data;
    int weight;
    Node left;
    Node right;

    public Node(Byte data, int weight) {
        this.data = data;
        this.weight = weight;
    }

    @Override
    public String toString() {
        return "Node{" +
                "data=" + data +
                ", weight=" + weight +
                '}';
    }

    //自定义比较器，通过weight进行升序排序
    @Override
    public int compareTo(Node o) {
        return this.weight - o.weight;
    }

    //先序遍历 用于查看构建的大顶堆是否正确
    public void preOrder() {
        System.out.println(this);
        if (this.left != null) {
            this.left.preOrder();
        }
        if (this.right != null) {
            this.right.preOrder();
        }
    }
}