Java數據結構——哈夫曼編碼（數據解壓）

import java.util.*;

public class Main {
    public static void main(String[] args) {
        String str = "This is the test data";
        byte[] bytes = str.getBytes();
        byte[] huffmanCodesBytes = huffmanZip(bytes);
        System.out.println("原數據爲：");
        System.out.println(str);
        System.out.println("壓縮後的數據爲：");
        System.out.println(Arrays.toString(huffmanCodesBytes));
        System.out.println("解壓後的字符串爲：");
        System.out.println(new String(decode(huffmanCodes, huffmanCodesBytes)));

    }

//    完成數據的解壓
//   1.將字節型數組轉換爲二進制字符串
//   2.將二進制字符串轉爲字符串
    //將byte轉爲二進制字符串,flag表示是否需要補高位
    private static String byeToBitString(boolean flag, byte b){
        int temp = b; // 字節型轉換爲整型
        if(flag){
            temp |= 256; // 當字節型轉二進制時，二進制數不滿足8位，則需要補位。b = 1, temp = 1 | 100000000 = 100000001
        }
        String str = Integer.toBinaryString(temp); // 返回爲二進制補碼
        if(flag || temp < 0){
            return str.substring(str.length() - 8);
        }else{
            return str;
        }

    }

//    對壓縮數據進行解碼
    private static byte[] decode(Map<Byte, String> huffmanCodes, byte[] huffmanBytes){
//        1.獲得二進制字符串
        StringBuilder stringBuilder = new StringBuilder();
//        將數組轉爲二進制字符串
        for(int i = 0; i < huffmanBytes.length; i++){
            byte b = huffmanBytes[i];
            boolean flag = (i == huffmanBytes.length - 1); // 當i爲數字最後一個字節時，flag爲true
            stringBuilder.append(byeToBitString(!flag, b));
        }
//        把字符串按哈夫曼編碼進行解碼
//        調轉哈夫曼編碼表，即a->001
        Map<String, Byte> map = new HashMap<String, Byte>();
        for(Map.Entry<Byte, String> entry : huffmanCodes.entrySet()){
            map.put(entry.getValue(), entry.getKey());
        }
//        創建集合，存放byte
        List<Byte> list = new ArrayList<Byte>();
        for(int i = 0; i < stringBuilder.length(); ){
            int count = 1;
            boolean flag = true;
            Byte b = null;
            while (flag){
                String key = stringBuilder.substring(i, i + count);
                b = map.get(key);
                //判斷key是否爲哈夫曼編碼，b爲null代表不是哈夫曼編碼，需要再加一位二進制數，否則找到，退出循環
                if(b == null){
                    count++;
                }else{
                    flag = false;
                }
            }
            list.add(b);
            i += count;
        }
        byte[] b = new byte[list.size()];
        for(int i = 0; i < b.length; i++){
            b[i] = list.get(i);
        }
        return b;
    }

    //將前面方法全部封裝
    public static byte[] huffmanZip(byte[] bytes) {
        List<Node> nodes = getNodes(bytes);
        Node root = createHuffmanTree(nodes);
        Map<Byte, String> map = getCodes(root);
        return zip(bytes, map);
    }

    //將字符串對應的byte[]數組，壓縮
    public static byte[] zip(byte[] bytes, Map<Byte, String> huffmanCodes) {
        //bytes數組中的字符串爲二進制編碼，對字符串進行壓縮
        //將字符串每8位進行分割，再將其轉換爲byte類型。
        //例如：10101000，轉換後爲11011000,即轉換之前爲二進制補碼，要將其轉換爲原碼
        StringBuilder stringbuilder = new StringBuilder();
        for (byte b : bytes) {
            stringbuilder.append(huffmanCodes.get(b));
        }
        //統計轉換後的字符串長度
        int len;
        //字符串長度可能爲8的整數，也可能不是
        len = (stringbuilder.length() + 7) / 8;
        byte[] huffmanCodesBytes = new byte[len];
        int index = 0;
        for (int i = 0; i < stringbuilder.length(); i += 8) {
            String str;
            //如果字符串不滿足8位
            if (i + 8 > stringbuilder.length()) {
                str = stringbuilder.substring(i);
            } else {
                str = stringbuilder.substring(i, i + 8);
            }
            huffmanCodesBytes[index++] = (byte) Integer.parseInt(str, 2);
        }
        return huffmanCodesBytes;
    }

    //實現哈夫曼樹轉化爲哈夫曼編碼
    //使用哈希表來存放哈夫曼編碼，形式爲：97(a) - 001
    public static Map<Byte, String> huffmanCodes = new HashMap<>();
    //使用StringBuilder來存儲哈夫曼編碼
    public static StringBuilder stringbuilder = new StringBuilder();

    //對getCodes函數進行重載
    public static Map<Byte, String> getCodes(Node node) {
        if (node == null) {
            return null;
        }
        getCodes(node.left, "0", stringbuilder);
        getCodes(node.right, "1", stringbuilder);
        return huffmanCodes;
    }

    //獲取傳入的節點node的哈夫曼編碼，保存在stringbuilder中
    public static void getCodes(Node node, String code, StringBuilder stringbuilder) {
        StringBuilder stringbuilder2 = new StringBuilder(stringbuilder);
        stringbuilder2.append(code);
        if (node != null) {
            //當該節點爲非葉子節點
            if (node.data == null) {
                //向左遞歸
                getCodes(node.left, "0", stringbuilder2);
                //向右遞歸
                getCodes(node.right, "1", stringbuilder2);
            } else {
                //該節點爲葉子結點
                huffmanCodes.put(node.data, stringbuilder2.toString());
            }
        }
    }

    //將字符串轉換爲字節型
    public static List<Node> getNodes(byte[] bytes) {
        ArrayList<Node> nodes = new ArrayList<Node>();
        //遍歷bytes,獲得每個字節出現的次數
        //使用map來存儲每個字節與字節出現的次數
        Map<Byte, Integer> map = new HashMap<>();
        for (byte b : bytes) {
            Integer count = map.get(b);
            //當該字節第一次出現
            if (count == null) {
                map.put(b, 1);
            } else {
                //當該字節不是第一次出現
                map.put(b, count + 1);
            }
        }
        //把HashMap中每一個鍵值對轉爲Node對象
        for (Map.Entry<Byte, Integer> entry : map.entrySet()) {
            nodes.add(new Node(entry.getKey(), entry.getValue()));
        }
        return nodes;
    }

    //哈夫曼樹方法
    public static Node createHuffmanTree(List<Node> nodes) {
        while (nodes.size() > 1) {
            //從小到大排序
            Collections.sort(nodes);
            //取出節點權值最小的兩個節點構成二叉樹
            Node leftNode = nodes.get(0);
            Node rightNode = nodes.get(1);
            //重新構建新的二叉樹，以之前兩個節點爲左右子節點
            Node parent = new Node(null, leftNode.value + rightNode.value);
            parent.left = leftNode;
            parent.right = rightNode;
            //刪除兩個子節點，並將父節點放入順序表中
            nodes.remove(leftNode);
            nodes.remove(rightNode);
            nodes.add(parent);
        }
        return nodes.get(0);
    }

    //實現前序遍歷
    public static void preOrder(Node root) {
        if (root != null) {
            root.preOrder();
        } else {
            System.out.println("該二叉樹爲空");
        }
    }
}

//實現Comparable接口
class Node implements Comparable<Node> {
    Byte data; //存放字符本身
    int value; //權值大小
    Node left;
    Node right;

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

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

    //實現從小到大排序
    @Override
    public int compareTo(Node o) {
        return this.value - o.value;
    }

    //前序遍歷
    public void preOrder() {
        System.out.println(this);
        if (this.left != null) {
            this.left.preOrder();
        }
        if (this.right != null) {
            this.right.preOrder();
        }
    }
}

原數據爲：
This is the test data
壓縮後的數據爲：
[-124, -18, 119, 116, 119, 55, -23, 28, 0]
解壓後的字符串爲：
This is the test data