赫夫曼编码解压缩

赫夫曼编码

基本介绍

1、赫夫曼编码也翻译为哈夫曼编码(Huffman Coding)，又称霍夫曼编码，是一种编码方式, 属于一种程序算法

2、赫夫曼编码是赫哈夫曼树在电讯通信中的经典的应用之一。

3、赫夫曼编码广泛地用于数据文件压缩。其压缩率通常在20%～90%之间

4、赫夫曼码是可变字长编码(VLC)的一种。Huffman于1952年提出一种编码方法，称之为最佳编码

原理

1、构建赫夫曼树
1）i like like like java do you like a java // 共40个字符(包括空格)
2）d:1 y:1 u:1 j:2 v:2 o:2 l:4 k:4 e:4 i:5 a:5 :9 // 各个字符对应的个数
3）按照上面字符出现的次数构建一颗赫夫曼树, 次数作为权值

2、根据赫夫曼树构建编码
//根据赫夫曼树，给各个字符
//规定编码 ， 向左的路径为0
//向右的路径为1 ， 编码如下:

o: 1000 u: 10010 d: 100110 y: 100111 i: 101

a : 110 k: 1110 e: 1111 j: 0000 v: 0001

l: 001 : 01

按照上面的赫夫曼编码，我们的"i like like like java do you like a java" 字符串对应的编码为 (注意这里我们使用的无损压缩)

1010100110111101111010011011110111101001101111011110100001100001110011001111000011001111000100100100110111101111011100100001100001110

长度为 ： 133

说明:

1、原来长度是 359 , 压缩了 (359-133) / 359 = 62.9%

2、此编码满足前缀编码, 即字符的编码都不能是其他字符编码的前缀。不会造成匹配的多义性

结果

代码

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

public class HuffmanCode {
    public static void main(String[] args) {
        String content = "hello world";
        byte[] contentBytes = content.getBytes();
        byte[] huffmanCodeBytes = huffmanZip(contentBytes);
        System.out.println(Arrays.toString(huffmanCodeBytes));
        byte[] sourceBytes = decode(huffmanCodes, huffmanCodeBytes);
        System.out.println(new String(sourceBytes));
        String srcFile = "/Users/ALin/Downloads/like.zip";
        String dstFile = "/Users/ALin/Downloads/like2.doc";
        zipFile(srcFile, dstFile);
        System.out.println("ok");
    }

    // 解压文件
    private static void unZipFile(String zipFile, String dstFile) {
        InputStream is = null;
        ObjectInputStream ois = null;
        OutputStream os = null;
        try {
            is = new FileInputStream(zipFile);
            ois = new ObjectInputStream(is);
            byte[] huffmanBytes = (byte[]) ois.readObject();
            Map<Byte, String> huffmanCodes = (Map<Byte, String>) ois.readObject();
            byte[] bytes = decode(huffmanCodes, huffmanBytes);
            os = new FileOutputStream(dstFile);
            os.write(bytes);
        } catch (Exception e) {
            System.out.println(e.getMessage());
        } finally {
            try {
                os.close();
                ois.close();
                is.close();
            } catch (Exception e) {
                System.out.println(e);
            }

        }
    }

    // 压缩文件
    private static void zipFile(String srcFile, String dstFile) {
        FileInputStream is = null;
        OutputStream os = null;
        ObjectOutputStream oos = null;
        try {
            is = new FileInputStream(srcFile);
            byte[] b = new byte[is.available()];
            is.read(b);
            byte[] huffmanBytes = huffmanZip(b);
            os = new FileOutputStream(dstFile);
            oos = new ObjectOutputStream(os);
            oos.writeObject(huffmanBytes);
            oos.writeObject(huffmanCodes);
        } catch (Exception e) {
            System.out.println(e.getMessage());
        } finally {
            try {
                is.close();
                oos.close();
                os.close();
            } catch (Exception e) {
                System.out.println(e.getMessage());
            }

        }

    }

    // 解压
    private static byte[] decode(Map<Byte, String> huffmanCodes, byte[] huffmanBytes) {
        StringBuilder stringBuilder = new StringBuilder();
        for (int i = 0; i < huffmanBytes.length; i++) {
            boolean flag = (i == huffmanBytes.length - 1);
            stringBuilder.append(byteToBitString(!flag, huffmanBytes[i]));
        }
        Map<String, Byte> map = new HashMap<>();
        for (Map.Entry<Byte, String> entry : huffmanCodes.entrySet()) {
            map.put(entry.getValue(), entry.getKey());
        }
        List<Byte> list = new ArrayList<>();
        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);
                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;
    }
	// 转码
    private static String byteToBitString(boolean flag, byte b) {
        int temp = b;
        if (flag) {
            temp |= 256;
        }
        String str = Integer.toBinaryString(temp);
        if (flag) {
            return str.substring(str.length() - 8);
        } else {
            return str;
        }
    }

    private static byte[] huffmanZip(byte[] bytes) {

        List<Node> nodes = getNodes(bytes);
        Node root = createHuffmanTree(nodes);
        getCodes(root, "", stringBuilder);
        byte[] huffmanCodeBytes = zip(bytes, huffmanCodes);
        return huffmanCodeBytes;
    }
	// 压缩字符串
    private static byte[] zip(byte[] bytes, Map<Byte, String> huffmanCodes) {
        StringBuilder stringBuilder = new StringBuilder();
        for (byte b : bytes) {
            stringBuilder.append(huffmanCodes.get(b));
        }

        int len;
        if (stringBuilder.length() % 8 == 0) {
            len = stringBuilder.length() / 8;
        } else {
            len = stringBuilder.length() / 8 + 1;
        }
        byte[] huffmanCodeBytes = new byte[len];
        int index = 0;
        for (int i = 0; i < stringBuilder.length(); i += 8) {
            String strByte;
            if (i + 8 > stringBuilder.length()) {
                strByte = stringBuilder.substring(i);
            } else {
                strByte = stringBuilder.substring(i, i + 8);
            }
            huffmanCodeBytes[index] = (byte) Integer.parseInt(strByte, 2);
            index++;
        }
        return huffmanCodeBytes;
    }

    static Map<Byte, String> huffmanCodes = new HashMap<>();

    static StringBuilder stringBuilder = new StringBuilder();

    /**
     * @param node          传入结点
     * @param code          路径：左子结点0，右子结点1
     * @param stringBuilder 用于拼接路径
     */
    private static void getCodes(Node node, String code, StringBuilder stringBuilder) {
        StringBuilder stringBuilder2 = new StringBuilder(stringBuilder);
        stringBuilder2.append(code);
        if (node != null) {
            if (node.data == null) {
                getCodes(node.left, "0", stringBuilder2);
                getCodes(node.right, "1", stringBuilder2);
            } else {
                huffmanCodes.put(node.data, stringBuilder2.toString());
            }
        }
    }

    private static List<Node> getNodes(byte[] bytes) {

        ArrayList<Node> nodes = new ArrayList<Node>();
        HashMap<Byte, Integer> counts = new HashMap<>();
        for (byte b : bytes) {
            Integer count = counts.get(b);
            if (count == null) {
                counts.put(b, 1);
            } else {
                counts.put(b, count + 1);
            }
        }

        for (Map.Entry<Byte, Integer> entry : counts.entrySet()) {
            nodes.add(new Node(entry.getKey(), entry.getValue()));
        }
        return nodes;
    }

    private static Node createHuffmanTree(List<Node> nodes) {
        while (nodes.size() > 1) {
            Collections.sort(nodes);
            Node leftNode = nodes.get(0);
            Node rightNode = nodes.get(1);
            Node parent = new Node(null, leftNode.weight + rightNode.weight);
            parent.left = leftNode;
            parent.right = rightNode;
            nodes.remove(leftNode);
            nodes.remove(rightNode);
            nodes.add(parent);
        }
        return nodes.get(0);
    }
}

class Node implements Comparable<Node> {
    Byte data;
    int weight;
    Node left;
    Node right;

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

    @Override
    public int compareTo(Node o) {
        return this.weight - o.weight;
    }

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

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