数据压缩的操作步骤:
1、首先将原数据转为字节型数据;
2、将字节型数据转化为哈夫曼编码。使用Map方法将每一个字符按照<Byte, String>的方式存储起来,其中String就代表该字节的哈夫曼编码;
3、再将哈夫曼编码进行数据压缩,按照8位压缩为数字。
import java.util.*;
public class Main {
public static void main(String[] args) {
String str = "This is test data.";
byte[] bytes = str.getBytes();
byte[] huffmanCodesBytes = huffmanZip(bytes);
System.out.println("原数据为:");
System.out.println(str);
System.out.println("压缩后的数据为:");
System.out.println(Arrays.toString(huffmanCodesBytes));
}
//将前面方法全部封装
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);
}
//将字符串对应的byte[]数组,压缩
public static byte[] zip(byte[] bytes, Map<Byte, String> huffmanCodes) {
//bytes数组中的字符串为二进制编码,对字符串进行压缩
//将字符串每8位进行分割,再将其转换为byte类型。
//例如:10101000,转换后为11011000,即转换之前为二进制补码,要将其转换为原码
StringBuilder stringbuilder = new StringBuilder();
for (byte b : bytes) {
stringbuilder.append(huffmanCodes.get(b));
}
//统计转换后的字符串长度
int len;
//字符串长度可能为8的整数,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;
//如果字符串不满足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;
}
//实现哈夫曼树转化为哈夫曼编码
//使用哈希表来存放哈夫曼编码,形式为:97(a) - 001
public static Map<Byte, String> huffmanCodes = new HashMap<>();
//使用StringBuilder来存储哈夫曼编码
public static StringBuilder stringbuilder = new StringBuilder();
//对getCodes函数进行重载
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;
}
//获取传入的节点node的哈夫曼编码,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) {
//当该节点为非叶子节点
if (node.data == null) {
//向左递归
getCodes(node.left, "0", stringbuilder2);
//向右递归
getCodes(node.right, "1", stringbuilder2);
} else {
//该节点为叶子结点
huffmanCodes.put(node.data, stringbuilder2.toString());
}
}
}
//将字符串转换为字节型
public static List<Node> getNodes(byte[] bytes) {
ArrayList<Node> nodes = new ArrayList<Node>();
//遍历bytes,获得每个字节出现的次数
//使用map来存储每个字节与字节出现的次数
Map<Byte, Integer> map = new HashMap<>();
for (byte b : bytes) {
Integer count = map.get(b);
//当该字节第一次出现
if (count == null) {
map.put(b, 1);
} else {
//当该字节不是第一次出现
map.put(b, count + 1);
}
}
//把HashMap中每一个键值对转为Node对象
for (Map.Entry<Byte, Integer> entry : map.entrySet()) {
nodes.add(new Node(entry.getKey(), entry.getValue()));
}
return nodes;
}
//哈夫曼树方法
public static Node createHuffmanTree(List<Node> nodes) {
while (nodes.size() > 1) {
//从小到大排序
Collections.sort(nodes);
//取出节点权值最小的两个节点构成二叉树
Node leftNode = nodes.get(0);
Node rightNode = nodes.get(1);
//重新构建新的二叉树,以之前两个节点为左右子节点
Node parent = new Node(null, leftNode.value + rightNode.value);
parent.left = leftNode;
parent.right = rightNode;
//删除两个子节点,并将父节点放入顺序表中
nodes.remove(leftNode);
nodes.remove(rightNode);
nodes.add(parent);
}
return nodes.get(0);
}
//实现前序遍历
public static void preOrder(Node root) {
if (root != null) {
root.preOrder();
} else {
System.out.println("该二叉树为空");
}
}
}
//实现Comparable接口
class Node implements Comparable<Node> {
Byte data; //存放字符本身
int value; //权值大小
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 +
'}';
}
//实现从小到大排序
@Override
public int compareTo(Node o) {
return this.value - o.value;
}
//前序遍历
public void preOrder() {
System.out.println(this);
if (this.left != null) {
this.left.preOrder();
}
if (this.right != null) {
this.right.preOrder();
}
}
}
原数据为:
This is test data.
压缩后的数据为:
[105, 90, -83, 124, 111, 92, -14, 0]