赫夫曼树压缩文件c语言

以下是使用赫夫曼树进行文件压缩的 C 语言示例代码：

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

#define MAX_TREE_HT 100

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

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

typedef struct HuffmanNode {
    char data;
    char *code;
    struct HuffmanNode *left, *right;
} HuffmanNode;

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

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

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

void minHeapify(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(MinHeap* minHeap) {
    return (minHeap->size == 1);
}

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

void insertMinHeap(MinHeap* minHeap, 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(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(MinHeapNode* root) {
    return !(root->left) && !(root->right);
}

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

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

void printCodes(MinHeapNode* root, int arr[], int top, HuffmanNode **huffmanTable) {
    if (root->left) {
        arr[top] = 0;
        printCodes(root->left, arr, top + 1, huffmanTable);
    }
    if (root->right) {
        arr[top] = 1;
        printCodes(root->right, arr, top + 1, huffmanTable);
    }
    if (isLeaf(root)) {
        HuffmanNode *node = (HuffmanNode*) malloc(sizeof(HuffmanNode));
        node->data = root->data;
        node->code = (char*) malloc((top+1) * sizeof(char));
        memcpy(node->code, arr, (top+1) * sizeof(char));
        huffmanTable[node->data] = node;
    }
}

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

void compressFile(char *inputFile, char *outputFile, HuffmanNode **huffmanTable) {
    FILE *inFile = fopen(inputFile, "r");
    FILE *outFile = fopen(outputFile, "wb");
    char c, byte = 0;
    int bitCount = 0;
    while ((c = fgetc(inFile)) != EOF) {
        HuffmanNode *node = huffmanTable[c];
        for (int i = 0; i < strlen(node->code); i++) {
            byte <<= 1;
            byte |= node->code[i] - '0';
            bitCount++;
            if (bitCount == 8) {
                fwrite(&byte, 1, 1, outFile);
                byte = 0;
                bitCount = 0;
            }
        }
    }
    if (bitCount > 0) {
        byte <<= (8 - bitCount);
        fwrite(&byte, 1, 1, outFile);
    }
    fclose(inFile);
    fclose(outFile);
}

int main() {
    char data[] = {'A', 'B', 'C', 'D', 'E', 'F'};
    int freq[] = {5, 9, 12, 13, 16, 45};
    int size = sizeof(data) / sizeof(data[0]);
    HuffmanNode *huffmanTable[256] = {NULL};
    HuffmanCodes(data, freq, size, huffmanTable);
    char *inputFile = "input.txt";
    char *outputFile = "output.bin";
    compressFile(inputFile, outputFile, huffmanTable);
    return 0;
}

这个示例代码是以字符为单位进行压缩的，可以根据实际需要进行修改和扩展。