Huffman树实现编码译码--数据结构实验

Posted 2021-09-14 Prince_H_23

#define _CRT_SECURE_NO_WARNINGS
#include<iostream>
#include<vector>
#include<algorithm>
#include<map>
#include <string>
using namespace std;

typedef struct {
    int val;
    int weight;
    int parent, lchild, rchild;
}HuffmanNode;
static bool cmp(vector<int> a, vector<int> b) {
    return a[1] > b[1];
}
void calculate(vector<vector<int>>& check) {
    FILE* file;
    file = fopen("a.txt", "r");
    char c;
    while ((c = fgetc(file)) != EOF) {
        if (c >= \'a\' && c <= \'z\') {
            check[c - \'a\'][1]++;
        }
        else if (c >= \'A\' && c <= \'Z\') {
            check[c - \'A\' + 26][1]++;
        }
        else if (c == \' \') {
            check[52][1]++;
        }
        else if (c == \',\') {
            check[53][1]++;
        }
        else if (c == \'.\') {
            check[54][1]++;
        }
    }
    sort(check.begin(), check.end(), cmp);
}//统计出现字母的频率
void initHuffmanTree(HuffmanNode* HT, int n, int m, vector<vector<int>>& check) {
    int j = 1;
    for (int i = n - 1; i >= 0; i--) {
        HT[j++] = {check[i][0], check[i][1],0,0,0};
    }
    for (; j <= m; j++) {
        HT[j] = { 0,0,0,0,0 };
    }
}//初始化哈夫曼树
void select(HuffmanNode* HT,int endLoc, int& node1, int& node2) {
    int min1 = INT_MAX - 1, min2 = INT_MAX;
    for (int i = 1; i <= endLoc; i++) {
        if (HT[i].parent == 0) {
            if (HT[i].weight < min1) {
                min1 = HT[i].weight;
                node1 = i;
            }
            else if (HT[i].weight < min2) {
                min2 = HT[i].weight;
                node2 = i;
            }
        }
    }
}//选出两个最小的节点
void createHuffmanTree(HuffmanNode* HT, int n, int m) {
    int loc;
    int node1, node2;
    for (int i = n + 1; i <= m; i++) {
        select(HT, i - 1, node1, node2);
        HT[i].lchild = node2;
        HT[i].rchild = node1;
        HT[i].weight = HT[node1].weight + HT[node2].weight;
        HT[node1].parent = HT[node2].parent = i;
    }
}//建立哈夫曼树
void encode(HuffmanNode* HT, int n, map<int, string>& huffmanCode) {
    int par; //父节点
    int son; //子节点位置
    for (int i = 1; i <= n; i++) {
        son = i;
        par = HT[i].parent;
        string code = "";
        while (par != 0) {
            if (HT[par].lchild == son) {
                code.insert(code.begin(), \'0\');
            }
            if (HT[par].rchild == son) {
                code.insert(code.begin(), \'1\');
            }
            son = par;
            par = HT[par].parent;
        }//向上找，直到没有parent
        huffmanCode[HT[i].val] = code;
    }
    

}//生成哈夫曼码
void encodeTxtToHuffmanCode(map<int, string>& huffmanCode) {
    FILE* readFile = fopen("a.txt", "r");
    FILE* writeFile = fopen("b.txt", "w");
    char c = fgetc(readFile);
    while (c != EOF) {
        int i;
        if (c >= \'a\' && c <= \'z\') {
            i = c - \'a\';
        }
        else if (c >= \'A\' && c <= \'Z\') {
            i = c - \'A\' + 26;
        }
        else if (c == \' \') {
            i = 52;
        }
        else if (c == \',\') {
            i = 53;
        }
        else if (c == \'.\') {
            i = 54;
        }
        for (int j = 0; j < huffmanCode[i].size(); j++) {
            fputc(huffmanCode[i][j], writeFile);
        }
        
        c = fgetc(readFile);
    }
    fclose(readFile);
    fclose(writeFile);
}
void decode(HuffmanNode* HT, int n) {
    FILE* readFile = fopen("b.txt", "r");
    FILE* writeFile = fopen("c.txt", "w");
    char c = fgetc(readFile);
    int i = 2 * n - 1;
    while (c != EOF) {
        if (c == \'0\') {
            i = HT[i].lchild;
        }
        else if (c == \'1\') {
            i = HT[i].rchild;
        }
        if (HT[i].lchild == 0 || HT[i].rchild == 0) {
            char c;
            if (HT[i].val >= 0 && HT[i].val <= 25) {
                c = \'a\' + HT[i].val;
            }
            else if (HT[i].val >= 26 && HT[i].val <= 51) {
                c = \'A\' + HT[i].val - 26;
            }
            else if (HT[i].val == 52) {
                c = \' \';
            }
            else if (HT[i].val == 53) {
                c = \',\';
            }
            else if (HT[i].val == 54) {
                c = \'.\';
            }
            fputc(c, writeFile);
            i = 2 * n - 1;
        }
        c = fgetc(readFile);
    }
    fclose(readFile);
    fclose(writeFile);
}//哈夫曼码翻译成文章
int main() {

    //统计字符出现的频率
    vector<vector<int>> check(55,vector<int>(2,0));
    for (int i = 0; i < check.size(); i++) {
        check[i][0] = i;
    }
    calculate(check);

    //叶子个数（出现的字母个数）
    int n = 0; 
    for (int i = 0; i < check.size(); i++) {
        if (check[i][1] != 0) n++;
    }

    //Huffman树的节点个数
    int m = 2 * n - 1; 
    HuffmanNode* HT;
    HT = (HuffmanNode*)malloc((m + 1) * sizeof(HuffmanNode)); //第0个节点不用

    //初始化Huffman树
    initHuffmanTree(HT, n, m, check);

    //根据字符频率创建Huffman树
    createHuffmanTree(HT, n, m);

    //根据Huffman树给每个字符编码
    map<int, string> huffmanCode;
    encode(HT, n, huffmanCode);

    //根据编码进行文章翻译
    encodeTxtToHuffmanCode(huffmanCode);
    
    //将Huffman编码翻译成文字
    decode(HT, n);
}