具体代码
package huffmancode;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
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(StandardCharsets.UTF_8);
System.out.println(contentBytes.length);//40
//测试一把
List nodes = getNodes(contentBytes);
System.out.println("nodes"+nodes);
}
public static List getNodes(byte[] bytes){
//1创建一个ArrayList
ArrayList nodes = new ArrayList<>();
//遍历bytes，统计每一个byte出现的次数-->map[key,value]
Map counts = new HashMap<>();
for (byte b : bytes) {
Integer count = counts.get(b);
if (count==null){ //Map还没有这个字符数据，第一次
counts.put(b,1);
}else {
counts.put(b,count+1);
}
}
// 每个键值对转成node对象 并加入nodes
// 遍历map
for (Map.Entry entry:counts.entrySet()){
nodes.add(new Node(entry.getKey(),entry.getValue()));
}
return nodes;
}
}
// 创建node ,带数据和权值
class Node implements Comparable{
Byte data; // 存放数据(字符)本身 比如'a' => 97 ' '=> 32
int weight; // 权值 表示数据(字符) 出现的次数
Node left;
Node right;
public Node(Byte data, int weight) {
this.data = data;
this.weight = weight;
}
@Override
public int compareTo(Node o) {
// weight 升序排列，从小到大排序
return this.weight - o.weight;
}
@Override
public String toString() {
return "Node [data = "+data+"weight="+weight+"]";
}
// 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();
}
}
}
测试输出结果
新增创建哈夫曼树的方法并测试
package huffmancode;
import java.nio.charset.StandardCharsets;
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(StandardCharsets.UTF_8);
System.out.println(contentBytes.length);//40
//测试一把
List nodes = getNodes(contentBytes);
System.out.println("nodes"+nodes);
//测试一把，创建的二叉树
System.out.println("哈夫曼树");
Node huffmanTreeRoot = createHuffmanTree(nodes);
System.out.println("前序遍历");
huffmanTreeRoot.preOrder();
}
public static List getNodes(byte[] bytes){
//1创建一个ArrayList
ArrayList nodes = new ArrayList<>();
//遍历bytes，统计每一个byte出现的次数-->map[key,value]
Map counts = new HashMap<>();
for (byte b : bytes) {
Integer count = counts.get(b);
if (count==null){ //Map还没有这个字符数据，第一次
counts.put(b,1);
}else {
counts.put(b,count+1);
}
}
// 每个键值对转成node对象 并加入nodes
// 遍历map
for (Map.Entry entry:counts.entrySet()){
nodes.add(new Node(entry.getKey(),entry.getValue()));
}
return nodes;
}
//可以通过List 创建对应的赫夫曼树
private static Node createHuffmanTree(List nodes){
while (nodes.size()>1){
//排序，从小到大
Collections.sort(nodes);
//取出最小的二叉树
Node leftNode = nodes.get(0);
//取出第二颗最小的二叉树
Node rightNode = nodes.get(1);
//创建一颗新的二叉树
Node parent = new Node(null, leftNode.weight + rightNode.weight);
parent.left=leftNode;
parent.right=rightNode;
//将已经处理的二叉树从nodes删除
nodes.remove(leftNode);
nodes.remove(rightNode);
//将新的二叉树，加到nodes中
nodes.add(parent);
}
//nodes 最后的节点，也就是哈夫曼树的根节点
return nodes.get(0);
}
//前序遍历的方法
private static void preOrder(Node root){
if (root==null){
System.out.println("哈夫曼树为空");
}else {
root.preOrder();
}
}
}
// 创建node ,带数据和权值
class Node implements Comparable{
Byte data; // 存放数据(字符)本身 比如'a' => 97 ' '=> 32
int weight; // 权值 表示数据(字符) 出现的次数
Node left;
Node right;
public Node(Byte data, int weight) {
this.data = data;
this.weight = weight;
}
@Override
public int compareTo(Node o) {
// weight 升序排列，从小到大排序
return this.weight - o.weight;
}
@Override
public String toString() {
return "Node [data = "+data+ " weight= "+weight+"]";
}
// 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();
}
}
}
对应预期
生成哈夫曼编码表以及测试
package huffmancode;
import java.nio.charset.StandardCharsets;
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(StandardCharsets.UTF_8);
System.out.println(contentBytes.length);//40
//测试一把
List nodes = getNodes(contentBytes);
System.out.println("nodes"+nodes);
//测试一把，创建的二叉树
System.out.println("哈夫曼树");
Node huffmanTreeRoot = createHuffmanTree(nodes);
System.out.println("前序遍历");
huffmanTreeRoot.preOrder();
//测试一把 是否生成了哈夫曼编码
getCodes(huffmanTreeRoot);
System.out.println("生成的哈夫曼编码表"+huffmanCode);
}
public static List getNodes(byte[] bytes){
//1创建一个ArrayList
ArrayList nodes = new ArrayList<>();
//遍历bytes，统计每一个byte出现的次数-->map[key,value]
Map counts = new HashMap<>();
for (byte b : bytes) {
Integer count = counts.get(b);
if (count==null){ //Map还没有这个字符数据，第一次
counts.put(b,1);
}else {
counts.put(b,count+1);
}
}
// 每个键值对转成node对象 并加入nodes
// 遍历map
for (Map.Entry entry:counts.entrySet()){
nodes.add(new Node(entry.getKey(),entry.getValue()));
}
return nodes;
}
//可以通过List 创建对应的赫夫曼树
private static Node createHuffmanTree(List nodes){
while (nodes.size()>1){
//排序，从小到大
Collections.sort(nodes);
//取出最小的二叉树
Node leftNode = nodes.get(0);
//取出第二颗最小的二叉树
Node rightNode = nodes.get(1);
//创建一颗新的二叉树
Node parent = new Node(null, leftNode.weight + rightNode.weight);
parent.left=leftNode;
parent.right=rightNode;
//将已经处理的二叉树从nodes删除
nodes.remove(leftNode);
nodes.remove(rightNode);
//将新的二叉树，加到nodes中
nodes.add(parent);
}
//nodes 最后的节点，也就是哈夫曼树的根节点
return nodes.get(0);
}
// 生成哈夫曼对应的哈夫曼编码
// 1 将哈夫曼树放在Map 形式大概为 a->100 d->11000 u->11001 e->1110 v->11011 i->101 y->11010 j->0010 k->1111 l->000 o->0011
// 2 在生成哈夫曼编码表时 需要拼接路径 定义一个stringBuilder 存储某个叶子节点的路径
static Map huffmanCode = new HashMap<>();
static StringBuilder stringBuilder = new StringBuilder();
//为了调用方便。我们重载geyCodes
private static Map getCodes(Node root){
if (root==null){
return null;
}
//处理左子树
getCodes(root.left,"0",stringBuilder);
//处理右子树
getCodes(root.right,"1",stringBuilder);
return huffmanCode;
}
private static void getCodes(Node node, String code, StringBuilder stringBuilder){
StringBuilder stringBuilder2 = new StringBuilder(stringBuilder);
//将code 加入到stringBuilder2
stringBuilder2.append(code);
if (node != null){
//判断是叶子节点还是非叶子节点
if (node.data == null){ // 非叶子节点
//递归处理
//像左递归
getCodes(node.left,"0",stringBuilder2);
//像右递归
getCodes(node.right,"1",stringBuilder2);
}else {//说明是叶子节点
//就表示找到某个叶子节点的最后
huffmanCode.put(node.data, stringBuilder2.toString());
}
}
}
//前序遍历的方法
private static void preOrder(Node root){
if (root==null){
System.out.println("哈夫曼树为空");
}else {
root.preOrder();
}
}
}
// 创建node ,带数据和权值
class Node implements Comparable{
Byte data; // 存放数据(字符)本身 比如'a' => 97 ' '=> 32
int weight; // 权值 表示数据(字符) 出现的次数
Node left;
Node right;
public Node(Byte data, int weight) {
this.data = data;
this.weight = weight;
}
@Override
public int compareTo(Node o) {
// weight 升序排列，从小到大排序
return this.weight - o.weight;
}
@Override
public String toString() {
return "Node [data = "+data+ " weight= "+weight+"]";
}
// 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();
}
}
}
上图是测试结果！
数据压缩-哈夫曼编码字节数组package huffmancode;
import java.nio.charset.StandardCharsets;
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(StandardCharsets.UTF_8);
System.out.println(contentBytes.length);//40
//测试一把
List nodes = getNodes(contentBytes);
System.out.println("nodes"+nodes);
//测试一把，创建的二叉树
System.out.println("哈夫曼树");
Node huffmanTreeRoot = createHuffmanTree(nodes);
System.out.println("前序遍历");
huffmanTreeRoot.preOrder();
//测试一把 是否生成了哈夫曼编码
Map huffmanCodes = getCodes(huffmanTreeRoot);
System.out.println("生成的哈夫曼编码表"+huffmanCodes);
//测试
byte[] huffmanCodeBytes = zip(contentBytes, huffmanCodes);
System.out.println("huffmanCodeBytes="+Arrays.toString(huffmanCodeBytes));//17个
//发送huffmanCodeBytes 数组
}
public static List getNodes(byte[] bytes){
//1创建一个ArrayList
ArrayList nodes = new ArrayList<>();
//遍历bytes，统计每一个byte出现的次数-->map[key,value]
Map counts = new HashMap<>();
for (byte b : bytes) {
Integer count = counts.get(b);
if (count==null){ //Map还没有这个字符数据，第一次
counts.put(b,1);
}else {
counts.put(b,count+1);
}
}
// 每个键值对转成node对象 并加入nodes
// 遍历map
for (Map.Entry entry:counts.entrySet()){
nodes.add(new Node(entry.getKey(),entry.getValue()));
}
return nodes;
}
//可以通过List 创建对应的赫夫曼树
private static Node createHuffmanTree(List nodes){
while (nodes.size()>1){
//排序，从小到大
Collections.sort(nodes);
//取出最小的二叉树
Node leftNode = nodes.get(0);
//取出第二颗最小的二叉树
Node rightNode = nodes.get(1);
//创建一颗新的二叉树
Node parent = new Node(null, leftNode.weight + rightNode.weight);
parent.left=leftNode;
parent.right=rightNode;
//将已经处理的二叉树从nodes删除
nodes.remove(leftNode);
nodes.remove(rightNode);
//将新的二叉树，加到nodes中
nodes.add(parent);
}
//nodes 最后的节点，也就是哈夫曼树的根节点
return nodes.get(0);
}
private static byte[] zip(byte[] bytes, Map huffmanCode){
// 1 先用Huffman编码表 将bytes 转成 Huffman编码对应的字符串
StringBuilder stringBuilder = new StringBuilder();
// 遍历byte数组
for(byte b : bytes){
stringBuilder.append(huffmanCode.get(b));
}
//System.out.println(stringBuilder.toString());
//将101010001011111...转成bute[]
//统计返回byte[]huffmanCodeBytes 长度
int len;
if (stringBuilder.length()%8==0){
len=stringBuilder.length()/8;
}else {
len=stringBuilder.length()/8+1;
}
// 创建 一个存储压缩后的byte数组
byte[] huffmanCodeBytes = new byte[len];
int index = 0; // 第几个byte
for (int i = 0; i < stringBuilder.length(); i+=8){// 步长为8
String strByte;
if(i + 8 > stringBuilder.length()) {// 不够8位
strByte = stringBuilder.substring(i); // i-结束
}else {
strByte = stringBuilder.substring(i, i + 8);
}
huffmanCodeBytes[index++] = (byte) Integer.parseInt(strByte,2); // 二进制
}
return huffmanCodeBytes;
}
// 生成哈夫曼对应的哈夫曼编码
// 1 将哈夫曼树放在Map 形式大概为 a->100 d->11000 u->11001 e->1110 v->11011 i->101 y->11010 j->0010 k->1111 l->000 o->0011
// 2 在生成哈夫曼编码表时 需要拼接路径 定义一个stringBuilder 存储某个叶子节点的路径
static Map huffmanCode = new HashMap<>();
static StringBuilder stringBuilder = new StringBuilder();
//为了调用方便。我们重载geyCodes
private static Map getCodes(Node root){
if (root==null){
return null;
}
//处理左子树
getCodes(root.left,"0",stringBuilder);
//处理右子树
getCodes(root.right,"1",stringBuilder);
return huffmanCode;
}
private static void getCodes(Node node, String code, StringBuilder stringBuilder){
StringBuilder stringBuilder2 = new StringBuilder(stringBuilder);
//将code 加入到stringBuilder2
stringBuilder2.append(code);
if (node != null){
//判断是叶子节点还是非叶子节点
if (node.data == null){ // 非叶子节点
//递归处理
//像左递归
getCodes(node.left,"0",stringBuilder2);
//像右递归
getCodes(node.right,"1",stringBuilder2);
}else {//说明是叶子节点
//就表示找到某个叶子节点的最后
huffmanCode.put(node.data, stringBuilder2.toString());
}
}
}
//前序遍历的方法
private static void preOrder(Node root){
if (root==null){
System.out.println("哈夫曼树为空");
}else {
root.preOrder();
}
}
}
// 创建node ,带数据和权值
class Node implements Comparable{
Byte data; // 存放数据(字符)本身 比如'a' => 97 ' '=> 32
int weight; // 权值 表示数据(字符) 出现的次数
Node left;
Node right;
public Node(Byte data, int weight) {
this.data = data;
this.weight = weight;
}
@Override
public int compareTo(Node o) {
// weight 升序排列，从小到大排序
return this.weight - o.weight;
}
@Override
public String toString() {
return "Node [data = "+data+ " weight= "+weight+"]";
}
// 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();
}
}
}
输出：
封装方法
package huffmancode;
import java.nio.charset.StandardCharsets;
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(StandardCharsets.UTF_8);
System.out.println(contentBytes.length);//40
byte[] huffmanCodesBytes = huffmanZip(contentBytes);
System.out.println("压缩后的结果是:"+Arrays.toString(huffmanCodesBytes)+"长度="+huffmanCodesBytes.length);
}
// 使用一个方法 将前面的方法封装起来 ,便于调用
private static byte[] huffmanZip(byte[] bytes) {
List nodes = getNodes(bytes);
// 根据node创建哈夫曼树
Node huffmanTreeRoot = createHuffmanTree(nodes);
// 根据哈夫曼树生成对应的哈夫曼编码
Map huffmanCodes = getCodes(huffmanTreeRoot);
// 根据生成的哈夫曼编码 压缩得到压缩后的哈夫曼编码字节数组
byte[] huffmanCodeBytes = zip(bytes, huffmanCodes);
return huffmanCodeBytes;
}
public static List getNodes(byte[] bytes){
//1创建一个ArrayList
ArrayList nodes = new ArrayList<>();
//遍历bytes，统计每一个byte出现的次数-->map[key,value]
Map counts = new HashMap<>();
for (byte b : bytes) {
Integer count = counts.get(b);
if (count==null){ //Map还没有这个字符数据，第一次
counts.put(b,1);
}else {
counts.put(b,count+1);
}
}
// 每个键值对转成node对象 并加入nodes
// 遍历map
for (Map.Entry entry:counts.entrySet()){
nodes.add(new Node(entry.getKey(),entry.getValue()));
}
return nodes;
}
//可以通过List 创建对应的赫夫曼树
private static Node createHuffmanTree(List nodes){
while (nodes.size()>1){
//排序，从小到大
Collections.sort(nodes);
//取出最小的二叉树
Node leftNode = nodes.get(0);
//取出第二颗最小的二叉树
Node rightNode = nodes.get(1);
//创建一颗新的二叉树
Node parent = new Node(null, leftNode.weight + rightNode.weight);
parent.left=leftNode;
parent.right=rightNode;
//将已经处理的二叉树从nodes删除
nodes.remove(leftNode);
nodes.remove(rightNode);
//将新的二叉树，加到nodes中
nodes.add(parent);
}
//nodes 最后的节点，也就是哈夫曼树的根节点
return nodes.get(0);
}
private static byte[] zip(byte[] bytes, Map huffmanCode){
// 1 先用Huffman编码表 将bytes 转成 Huffman编码对应的字符串
StringBuilder stringBuilder = new StringBuilder();
// 遍历byte数组
for(byte b : bytes){
stringBuilder.append(huffmanCode.get(b));
}
//System.out.println(stringBuilder.toString());
//将101010001011111...转成bute[]
//统计返回byte[]huffmanCodeBytes 长度
int len;
if (stringBuilder.length()%8==0){
len=stringBuilder.length()/8;
}else {
len=stringBuilder.length()/8+1;
}
// 创建 一个存储压缩后的byte数组
byte[] huffmanCodeBytes = new byte[len];
int index = 0; // 第几个byte
for (int i = 0; i < stringBuilder.length(); i+=8){// 步长为8
String strByte;
if(i + 8 > stringBuilder.length()) {// 不够8位
strByte = stringBuilder.substring(i); // i-结束
}else {
strByte = stringBuilder.substring(i, i + 8);
}
huffmanCodeBytes[index++] = (byte) Integer.parseInt(strByte,2); // 二进制
}
return huffmanCodeBytes;
}
// 生成哈夫曼对应的哈夫曼编码
// 1 将哈夫曼树放在Map 形式大概为 a->100 d->11000 u->11001 e->1110 v->11011 i->101 y->11010 j->0010 k->1111 l->000 o->0011
// 2 在生成哈夫曼编码表时 需要拼接路径 定义一个stringBuilder 存储某个叶子节点的路径
static Map huffmanCode = new HashMap<>();
static StringBuilder stringBuilder = new StringBuilder();
//为了调用方便。我们重载geyCodes
private static Map getCodes(Node root){
if (root==null){
return null;
}
//处理左子树
getCodes(root.left,"0",stringBuilder);
//处理右子树
getCodes(root.right,"1",stringBuilder);
return huffmanCode;
}
private static void getCodes(Node node, String code, StringBuilder stringBuilder){
StringBuilder stringBuilder2 = new StringBuilder(stringBuilder);
//将code 加入到stringBuilder2
stringBuilder2.append(code);
if (node != null){
//判断是叶子节点还是非叶子节点
if (node.data == null){ // 非叶子节点
//递归处理
//像左递归
getCodes(node.left,"0",stringBuilder2);
//像右递归
getCodes(node.right,"1",stringBuilder2);
}else {//说明是叶子节点
//就表示找到某个叶子节点的最后
huffmanCode.put(node.data, stringBuilder2.toString());
}
}
}
//前序遍历的方法
private static void preOrder(Node root){
if (root==null){
System.out.println("哈夫曼树为空");
}else {
root.preOrder();
}
}
}
// 创建node ,带数据和权值
class Node implements Comparable{
Byte data; // 存放数据(字符)本身 比如'a' => 97 ' '=> 32
int weight; // 权值 表示数据(字符) 出现的次数
Node left;
Node right;
public Node(Byte data, int weight) {
this.data = data;
this.weight = weight;
}
@Override
public int compareTo(Node o) {
// weight 升序排列，从小到大排序
return this.weight - o.weight;
}
@Override
public String toString() {
return "Node [data = "+data+ " weight= "+weight+"]";
}
// 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();
}
}
}
测试输出
