JAVA学习—Huffman 编码 (节点定义与文件读取)—2021-06-16

JAVA学习—Huffman 编码 (节点定义与文件读取)—2021-06-16

代码

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 henyuzuo.
 */
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