哈夫曼编码/译码器数据结构课程设计

以下是哈夫曼编码/译码器的数据结构课程设计：

1. 数据结构设计

（1）哈夫曼树节点的数据结构

typedef struct HuffmanNode {
    char data; // 节点存储的字符
    int weight; // 节点的权重
    int parent; // 节点的父节点下标
    int lchild; // 节点的左孩子下标
    int rchild; // 节点的右孩子下标
} HuffmanNode;

（2）哈夫曼编码的数据结构

typedef struct HuffmanCode {
    char data; // 字符
    char *code; // 编码
} HuffmanCode;

2. 哈夫曼编码/译码器的实现

（1）统计文本文件中每个字符出现的次数，生成哈夫曼树

void createHuffmanTree(HuffmanNode *huffmanTree, int n) {
    int i, j, min1, min2;
    for (i = 0; i < 2 * n - 1; i++) {
        huffmanTree[i].parent = -1;
        huffmanTree[i].lchild = -1;
        huffmanTree[i].rchild = -1;
    }
    for (i = 0; i < n; i++) {
        printf("请输入第%d个字符及其权重：", i + 1);
        scanf("%s%d", &huffmanTree[i].data, &huffmanTree[i].weight);
    }
    for (i = 0; i < n - 1; i++) {
        min1 = min2 = -1;
        for (j = 0; j < n + i; j++) {
            if (huffmanTree[j].parent == -1) {
                if (min1 == -1) {
                    min1 = j;
                } else if (min2 == -1) {
                    min2 = j;
                } else {
                    if (huffmanTree[j].weight < huffmanTree[min1].weight) {
                        min2 = min1;
                        min1 = j;
                    } else if (huffmanTree[j].weight < huffmanTree[min2].weight) {
                        min2 = j;
                    }
                }
            }
        }
        huffmanTree[min1].parent = n + i;
        huffmanTree[min2].parent = n + i;
        huffmanTree[n + i].lchild = min1;
        huffmanTree[n + i].rchild = min2;
        huffmanTree[n + i].weight = huffmanTree[min1].weight + huffmanTree[min2].weight;
    }
}

（2）生成哈夫曼编码

void createHuffmanCode(HuffmanNode *huffmanTree, HuffmanCode *huffmanCode, int n) {
    char *code = (char *) malloc(n * sizeof(char));
    int i, j, parent, current;
    code[n - 1] = '\0';
    for (i = 0; i < n; i++) {
        huffmanCode[i].data = huffmanTree[i].data;
        current = i;
        parent = huffmanTree[current].parent;
        while (parent != -1) {
            if (huffmanTree[parent].lchild == current) {
                code[--n] = '0';
            } else {
                code[--n] = '1';
            }
            current = parent;
            parent = huffmanTree[current].parent;
        }
        huffmanCode[i].code = (char *) malloc((strlen(&code[n]) + 1) * sizeof(char));
        strcpy(huffmanCode[i].code, &code[n]);
    }
    free(code);
}

（3）编码文本文件

void encodeFile(char *fileName, HuffmanCode *huffmanCode, int n) {
    FILE *fp1, *fp2;
    char ch;
    int i, j;
    if ((fp1 = fopen(fileName, "r")) == NULL) {
        printf("文件打开失败！\n");
        exit(0);
    }
    if ((fp2 = fopen(strcat(fileName, ".cod"), "w")) == NULL) {
        printf("文件打开失败！\n");
        exit(0);
    }
    while ((ch = fgetc(fp1)) != EOF) {
        for (i = 0; i < n; i++) {
            if (huffmanCode[i].data == ch) {
                fprintf(fp2, "%s", huffmanCode[i].code);
                break;
            }
        }
    }
    fclose(fp1);
    fclose(fp2);
}

（4）译码编码文件

void decodeFile(char *fileName, HuffmanNode *huffmanTree, int n) {
    FILE *fp1, *fp2;
    char ch;
    int i, j, current = 2 * n - 2;
    if ((fp1 = fopen(fileName, "r")) == NULL) {
        printf("文件打开失败！\n");
        exit(0);
    }
    fileName[strlen(fileName) - 4] = '\0';
    if ((fp2 = fopen(fileName, "w")) == NULL) {
        printf("文件打开失败！\n");
        exit(0);
    }
    while ((ch = fgetc(fp1)) != EOF) {
        if (ch == '0') {
            current = huffmanTree[current].lchild;
        } else {
            current = huffmanTree[current].rchild;
        }
        if (huffmanTree[current].lchild == -1 && huffmanTree[current].rchild == -1) {
            fprintf(fp2, "%c", huffmanTree[current].data);
            current = 2 * n - 2;
        }
    }
    fclose(fp1);
    fclose(fp2);
}