赫夫曼编码用于数据文件的压缩，压缩率在20%~90%之间，称之为最佳编码
将原始数据转换为ASCII编码后再转二进制属于定长编码
同样数据使用变长编码，按照各个字符出现次数进行编码，出现次数越多则编码越小（字符的编码都不能是其他字符编码的前缀，这样的编码叫做前缀编码），从而实现数据的压缩
步骤：和创建赫夫曼树一样，其数据重复出现的次数作为权值，向左的路径为0，向右的路径为1，采取不一样的排序方式，编码也是不一样的，但是最后WPL是相同的，都是最小
理论上来说赫夫曼编码的压缩率重复数据出现的越多压缩率则越高，相反次之
import java.io.*;
import java.util.*;
public class HuffmanCode {
public static void main(String[] args) {
String content = "i like like like java do you like a java";
byte[] contentBytes = content.getBytes();
byte[] huffmanCodesBytes = huffmanZip(contentBytes);
// System.out.println(Arrays.toString(huffmanCodesBytes) + " " + huffmanCodesBytes.length);
byte[] sourceBytes = decode(huffmanCodes, huffmanCodesBytes);
// System.out.println(new String(sourceBytes));
zipFile("d://msdia80.dll", "d://123.zip");
// unZipFile("d://dsp.zip","d://dsp.png");
}
//封装
private static byte[] huffmanZip(byte[] bytes) {
List<Node> nodes = getNodes(bytes);
//根据node创建赫夫曼树
Node HuffmanTreeRoot = createHuffmanTree(nodes);
//根据赫夫曼树创建对应的赫夫曼编码
Map<Byte, String> huffmanCodes = getCodes(HuffmanTreeRoot);
//根据赫夫曼编码压缩得到压缩后的赫夫曼编码字节数组
byte[] huffmanCodeBytes = zip(bytes, huffmanCodes);
return huffmanCodeBytes;
}
private static List<Node> getNodes(byte[] bytes) {
ArrayList<Node> nodes = new ArrayList<>();
Map<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);
}
//返回根节点
return nodes.get(0);
}
private static void preOrder(Node root) {
if (root != null) {
root.preOrder();
}
}
//生成赫夫曼树对应的赫夫曼编码
static Map<Byte, String> huffmanCodes = new HashMap<>();
static StringBuilder stringBuilder = new StringBuilder();
private static Map<Byte, String> getCodes(Node root) {
if (root == null) {
return null;
}
getCodes(root.left, "0", stringBuilder);
getCodes(root.right, "1", stringBuilder);
return huffmanCodes;
}
/**
* 将传入的node节点的所有叶子节点的赫夫曼编码得到 并放入HuffmanCoeds集合
*
* @param node 根节点
* @param code 路径 左0 右1
* @param stringBuilder 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());
}
}
}
/**
* 推导 返回字符串 前8位 10101000(补码) -1=> 10100111(反码) 首位符号不变其它取反=> 11011000(原码)
*
* @param bytes
* @param huffmanCodes
* @return
*/
private static byte[] zip(byte[] bytes, Map<Byte, String> huffmanCodes) {
StringBuilder stringBuilder = new StringBuilder();
for (byte b : bytes) {
stringBuilder.append(huffmanCodes.get(b));
}
//将 字符串 转 byte[]
//简单写法 int len = (stringBuilder.length() + 7) / 8;
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;
}
/**
* 解压 字符转二进制字符串
*
* @param flag
* @param b
* @return
*/
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;
}
}
/**
* 解码
*
* @param huffmanCodes 赫夫曼编码表 map
* @param huffmanBytes 赫夫曼编码得到的字节数组
* @return
*/
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;
}
//文件压缩
public static void zipFile(String srcFile, String dsFile) {
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(dsFile);
oos = new ObjectOutputStream(os);
oos.writeObject(huffmanBytes);
oos.writeObject(huffmanCodes);
} catch (Exception e) {
System.out.println(e.getMessage());
} finally {
try {
is.close();
os.close();
oos.close();
} catch (Exception e) {
System.out.println(e.getMessage());
}
}
}
//文件解压
public 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 {
is.close();
ois.close();
os.close();
} catch (Exception e) {
System.out.println(e.getMessage());
}
}
}
}
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();
}
}
}
来源：https://www.cnblogs.com/bingbug/p/12298570.html