Java学习笔记（day29）

一、学习内容

Huffman 编码 (建树)

（1）huffman编码原理
huffman编码是一种无失真编码方式，是可变长（VLC）编码的一种。
huffman编码基于信源的概率统计模型，基本思路是出现概率大的信源符号编长码，出现概率小的符号编短码，从而使平均码长最小。

（2）具体内容：

1、Arrays.fill(charMapping, -1); 这种初始化工作非常重要。

2、171 行将 char 强制转换为 int, 即其在 ASCII 字符集中的位置.。

3、当我们设计完成的实际问题涉及到多个变量，以及这些变量的相关计算时，我们可以通过在变量名前面加上前缀，这样两个变量的相对关系就更明显。

4、最后生成的节点就是根节点。

二、代码编写

package datastructure.tree;

import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.stream.Collectors;

/**
 * Huffman tree, encoding, and decoding. For simplicity, only ASCII characters
 * are supported.
 * 
 * @author Fan Min minfanphd@163.com.
 */
public class Huffman {

	/**
	 * An inner class for Huffman nodes.
	 */
	class HuffmanNode {
		/**
		 * The char. Only valid for leaf nodes.
		 */
		char character;

		/**
		 * Weight. It can also be double.
		 */
		int weight;

		/**
		 * The left child.
		 */
		HuffmanNode leftChild;

		/**
		 * The right child.
		 */
		HuffmanNode rightChild;

		/**
		 * The parent. It helps constructing the Huffman code of each character.
		 */
		HuffmanNode parent;

		/**
		 ******************* 
		 * The first constructor
		 ******************* 
		 */
		public HuffmanNode(char paraCharacter, int paraWeight, HuffmanNode paraLeftChild,
				HuffmanNode paraRightChild, HuffmanNode paraParent) {
			character = paraCharacter;
			weight = paraWeight;
			leftChild = paraLeftChild;
			rightChild = paraRightChild;
			parent = paraParent;
		}// Of HuffmanNode

		/**
		 ******************* 
		 * To string.
		 ******************* 
		 */
		public String toString() {
			String resultString = "(" + character + ", " + weight + ")";

			return resultString;
		}// Of toString

	}// Of class HuffmanNode

	/**
	 * The number of characters. 256 for ASCII.
	 */
	public static final int NUM_CHARS = 256;

	/**
	 * The input text. It is stored in a string for simplicity.
	 */
	String inputText;

	/**
	 * The length of the alphabet, also the number of leaves.
	 */
	int alphabetLength;

	/**
	 * The alphabet.
	 */
	char[] alphabet;

	/**
	 * The count of chars. The length is 2 * alphabetLength - 1 to include
	 * non-leaf nodes.
	 */
	int[] charCounts;

	/**
	 * The mapping of chars to the indices in the alphabet.
	 */
	int[] charMapping;

	/**
	 * Codes for each char in the alphabet. It should have the same length as
	 * alphabet.
	 */
	String[] huffmanCodes;

	/**
	 * All nodes. The last node is the root.
	 */
	HuffmanNode[] nodes;

	/**
	 *********************
	 * The first constructor.
	 * 
	 * @param paraFilename
	 *            The text filename.
	 *********************
	 */
	public Huffman(String paraFilename) {
		charMapping = new int[NUM_CHARS];

		readText(paraFilename);
	}// Of the first constructor

	/**
	 *********************
	 * Read text.
	 * 
	 * @param paraFilename
	 *            The text filename.
	 *********************
	 */
	public void readText(String paraFilename) {
		try {
			inputText = Files.newBufferedReader(Paths.get(paraFilename), StandardCharsets.UTF_8)
					.lines().collect(Collectors.joining("\n"));
		} catch (Exception ee) {
			System.out.println(ee);
			System.exit(0);
		} // Of try

		System.out.println("The text is:\r\n" + inputText);
	}// Of readText

	/**
	 *********************
	 * Construct the alphabet. The results are stored in the member variables 
	 * charMapping and alphabet.
	 *********************
	 */
	public void constructAlphabet() {
		// Initialize.
		Arrays.fill(charMapping, -1);

		// The count for each char. At most NUM_CHARS chars.
		int[] tempCharCounts = new int[NUM_CHARS];

		// The index of the char in the ASCII charset.
		int tempCharIndex;

		// Step 1. Scan the string to obtain the counts.
		char tempChar;
		for (int i = 0; i < inputText.length(); i++) {
			tempChar = inputText.charAt(i);
			tempCharIndex = (int) tempChar;

			System.out.print("" + tempCharIndex + " ");

			tempCharCounts[tempCharIndex]++;
		} // Of for i

		// Step 2. Scan to determine the size of the alphabet.
		alphabetLength = 0;
		for (int i = 0; i < 255; i++) {
			if (tempCharCounts[i] > 0) {
				alphabetLength++;
			} // Of if
		} // Of for i

		// Step 3. Compress to the alphabet
		alphabet = new char[alphabetLength];
		charCounts = new int[2 * alphabetLength - 1];

		int tempCounter = 0;
		for (int i = 0; i < NUM_CHARS; i++) {
			if (tempCharCounts[i] > 0) {
				alphabet[tempCounter] = (char) i;
				charCounts[tempCounter] = tempCharCounts[i];
				charMapping[i] = tempCounter;
				tempCounter++;
			} // Of if
		} // Of for i

		System.out.println("The alphabet is: " + Arrays.toString(alphabet));
		System.out.println("Their counts are: " + Arrays.toString(charCounts));
		System.out.println("The char mappings are: " + Arrays.toString(charMapping));
	}// Of constructAlphabet

	/**
	 *********************
	 * Construct the tree.
	 *********************
	 */
	public void constructTree() {
		// Step 1. Allocate space.
		nodes = new HuffmanNode[alphabetLength * 2 - 1];
		boolean[] tempProcessed = new boolean[alphabetLength * 2 - 1];

		// Step 2. Initialize leaves.
		for (int i = 0; i < alphabetLength; i++) {
			nodes[i] = new HuffmanNode(alphabet[i], charCounts[i], null, null, null);
		} // Of for i

		// Step 3. Construct the tree.
		int tempLeft, tempRight, tempMinimal;
		for (int i = alphabetLength; i < 2 * alphabetLength - 1; i++) {
			// Step 3.1 Select the first minimal as the left child.
			tempLeft = -1;
			tempMinimal = Integer.MAX_VALUE;
			for (int j = 0; j < i; j++) {
				if (tempProcessed[j]) {
					continue;
				} // Of if

				if (tempMinimal > charCounts[j]) {
					tempMinimal = charCounts[j];
					tempLeft = j;
				} // Of if
			} // Of for j
			tempProcessed[tempLeft] = true;

			// Step 3.2 Select the second minimal as the right child.
			tempRight = -1;
			tempMinimal = Integer.MAX_VALUE;
			for (int j = 0; j < i; j++) {
				if (tempProcessed[j]) {
					continue;
				} // Of if

				if (tempMinimal > charCounts[j]) {
					tempMinimal = charCounts[j];
					tempRight = j;
				} // Of if
			} // Of for j
			tempProcessed[tempRight] = true;
			System.out.println("Selecting " + tempLeft + " and " + tempRight);

			// Step 3.3 Construct the new node.
			charCounts[i] = charCounts[tempLeft] + charCounts[tempRight];
			nodes[i] = new HuffmanNode('*', charCounts[i], nodes[tempLeft], nodes[tempRight], null);

			// Step 3.4 Link with children.
			nodes[tempLeft].parent = nodes[i];
			nodes[tempRight].parent = nodes[i];
			System.out.println("The children of " + i + " are " + tempLeft + " and " + tempRight);
		} // Of for i
	}// Of constructTree

	/**
	 *********************
	 * Get the root of the binary tree.
	 * 
	 * @return The root.
	 *********************
	 */
	public HuffmanNode getRoot() {
		return nodes[nodes.length - 1];
	}// Of getRoot

 

三、运行结果