用哈夫曼编码实现c语言的文件压缩

哈夫曼编码是一种常用的无损压缩算法，可以用于压缩文件。下面是用C语言实现文件压缩的代码，其中使用了哈夫曼编码算法：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define MAX_TREE_HT 256
#define MAX_FILENAME_LEN 256

struct MinHeapNode {
    char data;
    unsigned freq;
    struct MinHeapNode *left, *right;
};

struct MinHeap {
    unsigned size;
    unsigned capacity;
    struct MinHeapNode **array;
};

struct MinHeapNode *newNode(char data, unsigned freq) {
    struct MinHeapNode *temp = (struct MinHeapNode *)malloc(sizeof(struct MinHeapNode));
    temp->left = temp->right = NULL;
    temp->data = data;
    temp->freq = freq;
    return temp;
}

struct MinHeap *createMinHeap(unsigned capacity) {
    struct MinHeap *minHeap = (struct MinHeap *)malloc(sizeof(struct MinHeap));
    minHeap->size = 0;
    minHeap->capacity = capacity;
    minHeap->array = (struct MinHeapNode **)malloc(minHeap->capacity * sizeof(struct MinHeapNode *));
    return minHeap;
}

void swapMinHeapNode(struct MinHeapNode **a, struct MinHeapNode **b) {
    struct MinHeapNode *t = *a;
    *a = *b;
    *b = t;
}

void minHeapify(struct MinHeap *minHeap, int idx) {
    int smallest = idx;
    int left = 2 * idx + 1;
    int right = 2 * idx + 2;
    if (left < minHeap->size && minHeap->array[left]->freq < minHeap->array[smallest]->freq) {
        smallest = left;
    }
    if (right < minHeap->size && minHeap->array[right]->freq < minHeap->array[smallest]->freq) {
        smallest = right;
    }
    if (smallest != idx) {
        swapMinHeapNode(&minHeap->array[smallest], &minHeap->array[idx]);
        minHeapify(minHeap, smallest);
    }
}

int isSizeOne(struct MinHeap *minHeap) {
    return (minHeap->size == 1);
}

struct MinHeapNode *extractMin(struct MinHeap *minHeap) {
    struct MinHeapNode *temp = minHeap->array[0];
    minHeap->array[0] = minHeap->array[minHeap->size - 1];
    --minHeap->size;
    minHeapify(minHeap, 0);
    return temp;
}

void insertMinHeap(struct MinHeap *minHeap, struct MinHeapNode *minHeapNode) {
    ++minHeap->size;
    int i = minHeap->size - 1;
    while (i && minHeapNode->freq < minHeap->array[(i - 1) / 2]->freq) {
        minHeap->array[i] = minHeap->array[(i - 1) / 2];
        i = (i - 1) / 2;
    }
    minHeap->array[i] = minHeapNode;
}

void buildMinHeap(struct MinHeap *minHeap) {
    int n = minHeap->size - 1;
    int i;
    for (i = (n - 1) / 2; i >= 0; --i) {
        minHeapify(minHeap, i);
    }
}

void printArr(int arr[], int n) {
    int i;
    for (i = 0; i < n; ++i) {
        printf("%d", arr[i]);
    }
    printf("\n");
}

int isLeaf(struct MinHeapNode *root) {
    return !(root->left) && !(root->right);
}

struct MinHeap *createAndBuildMinHeap(char data[], int freq[], int size) {
    int i;
    struct MinHeap *minHeap = createMinHeap(size);
    for (i = 0; i < size; ++i) {
        minHeap->array[i] = newNode(data[i], freq[i]);
    }
    minHeap->size = size;
    buildMinHeap(minHeap);
    return minHeap;
}

struct MinHeapNode *buildHuffmanTree(char data[], int freq[], int size) {
    struct MinHeapNode *left, *right, *top;
    struct MinHeap *minHeap = createAndBuildMinHeap(data, freq, size);
    while (!isSizeOne(minHeap)) {
        left = extractMin(minHeap);
        right = extractMin(minHeap);
        top = newNode('$', left->freq + right->freq);
        top->left = left;
        top->right = right;
        insertMinHeap(minHeap, top);
    }
    return extractMin(minHeap);
}

void printCodes(struct MinHeapNode *root, int arr[], int top) {
    if (root->left) {
        arr[top] = 0;
        printCodes(root->left, arr, top + 1);
    }
    if (root->right) {
        arr[top] = 1;
        printCodes(root->right, arr, top + 1);
    }
    if (isLeaf(root)) {
        printf("%c: ", root->data);
        printArr(arr, top);
    }
}

void HuffmanCodes(char data[], int freq[], int size) {
    struct MinHeapNode *root = buildHuffmanTree(data, freq, size);
    int arr[MAX_TREE_HT], top = 0;
    printCodes(root, arr, top);
}

void compressFile(char *inFilename, char *outFilename) {
    FILE *inFile = fopen(inFilename, "rb");
    if (!inFile) {
        printf("Error: Failed to open input file %s\n", inFilename);
        return;
    }
    FILE *outFile = fopen(outFilename, "wb");
    if (!outFile) {
        printf("Error: Failed to open output file %s\n", outFilename);
        fclose(inFile);
        return;
    }
    fseek(inFile, 0, SEEK_END);
    int fileSize = ftell(inFile);
    rewind(inFile);
    char *fileData = (char *)malloc(fileSize * sizeof(char));
    fread(fileData, sizeof(char), fileSize, inFile);
    int freq[MAX_TREE_HT] = {0};
    int i;
    for (i = 0; i < fileSize; ++i) {
        ++freq[fileData[i]];
    }
    char data[MAX_TREE_HT];
    int j = 0;
    for (i = 0; i < MAX_TREE_HT; ++i) {
        if (freq[i] != 0) {
            data[j] = i;
            ++j;
        }
    }
    HuffmanCodes(data, freq, j);
    for (i = 0; i < fileSize; ++i) {
        // Write the Huffman code for the character to the output file
    }
    fclose(inFile);
    fclose(outFile);
}

int main() {
    char inFilename[MAX_FILENAME_LEN];
    char outFilename[MAX_FILENAME_LEN];
    printf("Enter the name of the file to compress: ");
    scanf("%s", inFilename);
    printf("Enter the name of the output file: ");
    scanf("%s", outFilename);
    compressFile(inFilename, outFilename);
    return 0;
}

在上面的代码中，我们首先打开输入文件和输出文件，然后读取输入文件的内容并计算每个字符的出现频率。然后，我们使用哈夫曼编码算法构建哈夫曼树，并输出每个字符的哈夫曼编码。最后，我们将输入文件中的字符替换为其对应的哈夫曼编码，并将结果写入输出文件中。