Huffuman Coding (哈夫曼编码)

哈夫曼编码(Huffman Coding)，又称霍夫曼编码，是一种编码方式，哈夫曼编码是可变字长编码(VLC)的一种。Huffman于1952年提出一种编码方法，该方法完全依据字符出现概率来构造异字头的平均长度最短的码字，有时称之为最佳编码，一般就叫做Huffman编码（有时也称为霍夫曼编码）。

 #include "stdafx.h"
 #include <iostream>
 #include<queue>
 #include<vector>
 #include <string>

 using namespace std;

 typedef struct
 {
     //内容
     unsigned char    character;
     //频次
     unsigned int    frequency;

 } CharNode;

 struct MinHeapNode
 {
     char data;
     unsigned int freq;
     MinHeapNode *left, *right;
     MinHeapNode(char data, unsigned int freq)
     {
         left = right = NULL;
         this->data = data;
         this->freq = freq;
     }
 };
 typedef struct MinHeapNode MinHeapNode;

 struct compare
 {
     bool operator()(MinHeapNode *a, MinHeapNode *b)
     {
         //"a > b" 表示 数值小 的 优先级高, 排最上面
         //反之 "<" 表示大的优先级高
         return (a->freq > b->freq);
     }
 };

 void get_huffuman_code(MinHeapNode *topNode, string code)
 {
     if (NULL == topNode)
     {
         return;
     }
     //表示已到达最末端，含有左右节点的元素中(由while循环中生成)data必为-1
     if (topNode->data != -)
     {
         cout << topNode->data << " : " << code<<endl;
     }
     get_huffuman_code(topNode->left, code + "");
     get_huffuman_code(topNode->right, code + "");
 }

 int main()
 {
          FILE * inputFile = NULL;
          fopen_s(&inputFile,"input.txt", "rb");
          if (!inputFile)
          {
              cout<< "Error: open file failed !" << endl;
              return -;
          }

          //初始化ASCII码数组
          CharNode nodeArr[] = { {,} };
          while (!feof(inputFile))
          {
               char buf = getc(inputFile);
               cout << buf;
               nodeArr[buf].character = buf;
               nodeArr[buf].frequency++;
          }
          cout << endl;
          //定义一个小顶堆
          priority_queue<MinHeapNode*, vector<MinHeapNode*>, compare > minHeap;
          for (size_t i = ; i < ; i++)
          {
              //将数据堆中，与升序排序效果类似，即堆首为小值，堆尾为大值
              if (nodeArr[i].frequency > )
              {
                  minHeap.push(new MinHeapNode(nodeArr[i].character, nodeArr[i].frequency));
                  cout << "Node " << i << ": [" << nodeArr[i].character << ", " << nodeArr[i].frequency << "]" << endl;
              }
          }

          MinHeapNode *leftNode = NULL, *rightNode = NULL, *topNode = NULL;
          //从堆首中抛出两个较小节点，生成一个新节点放回堆中并进行重新排序，
          //故，每次操作完成后 堆中会减少一个元素, 且堆顶必为权值最小的2个元素
          //直至堆中只剩一个元素时,哈夫曼树生成完毕
          while (minHeap.size() > )
          {
              //较小放左侧
              leftNode = minHeap.top();
              minHeap.pop();
              //较大的放右侧
              rightNode = minHeap.top();
              minHeap.pop();

              topNode = new MinHeapNode(-, leftNode->freq + rightNode->freq);
              topNode->left = leftNode;
              topNode->right = rightNode;
              minHeap.push(topNode);
          }
          get_huffuman_code(topNode, "");
          getchar();
          return ;
 }

对于解码过程，从根节点出发，依次读取文件流的bit 遇到“0”找leftNode，遇到“1”找rightNode，直至 data != -1