C语言 实现哈夫曼编码

好的，我来给你讲解如何用 C 语言实现哈夫曼编码。

哈夫曼编码是一种用于数据压缩的编码方法，它能够有效地减少数据的大小。哈夫曼编码的基本思想是：给出一个字符串，根据字符串中每个字符的出现频率，构建一棵二叉树，然后为每个字符分配一个二进制编码，使得字符串中出现频率较高的字符的编码较短，这样就能有效地减少数据的大小。

下面是一个简单的 C 语言实现的哈夫曼编码的例子：

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

#define MAX_TREE_SIZE 100

typedef struct {
  // 存储哈夫曼编码的字符数组
  char ch[MAX_TREE_SIZE];
  // 存储哈夫曼编码的权值
  int weight[MAX_TREE_SIZE];
  // 存储哈夫曼编码的左儿子
  int left[MAX_TREE_SIZE];
  // 存储哈夫曼编码的右儿子
  int right[MAX_TREE_SIZE];
  // 哈夫曼编码的节点数
  int n;
} HuffmanTree;

// 哈夫曼树的节点
typedef struct {
  // 节点的权值
  int weight;
  // 左儿子的下标
  int left;
  // 右儿子的下标
  int right;
  // 父亲节点的下标
  int parent;
} HTNode;

相关问题

用C语言实现哈夫曼编码

以下是使用C语言实现哈夫曼编码的基本步骤：

1. 定义结构体来表示每个字符及其对应的频率和编码：

struct node {
    char ch;
    int freq;
    char *code;
};

2. 统计每个字符出现的频率，并将其存储到一个数组中：

int freq[256] = {0};
for (int i = 0; i < strlen(input); i++) {
    freq[input[i]]++;
}

3. 构建哈夫曼树，可以使用优先队列（也称为堆）来实现：

struct node *buildHuffmanTree(int freq[]) {
    priority_queue<struct node*, vector<struct node*>, compare> pq;
    for (int i = 0; i < 256; i++) {
        if (freq[i] > 0) {
            struct node *n = new node;
            n->ch = (char)i;
            n->freq = freq[i];
            n->left = NULL;
            n->right = NULL;
            pq.push(n);
        }
    }
    while (pq.size() > 1) {
        struct node *n1 = pq.top();
        pq.pop();
        struct node *n2 = pq.top();
        pq.pop();
        struct node *n = new node;
        n->freq = n1->freq + n2->freq;
        n->left = n1;
        n->right = n2;
        pq.push(n);
    }
    return pq.top();
}

其中，compare是一个比较函数，用于将节点按照频率从小到大排序。

4. 通过递归遍历哈夫曼树，生成每个字符的编码：

void generateCodes(struct node *root, char *code, int index) {
    if (root->left == NULL && root->right == NULL) {
        code[index] = '\0';
        root->code = strdup(code);
        return;
    }
    code[index] = '0';
    generateCodes(root->left, code, index + 1);
    code[index] = '1';
    generateCodes(root->right, code, index + 1);
}

5. 使用生成的编码对原始数据进行编码：

char *encodeData(char *input, struct node *root) {
    char *output = (char*)malloc(sizeof(char) * strlen(input) * 8);
    int index = 0;
    for (int i = 0; i < strlen(input); i++) {
        struct node *n = findNode(root, input[i]);
        strcat(output, n->code);
    }
    return output;
}

其中，findNode函数用于在哈夫曼树中查找指定字符对应的节点。

6. 使用生成的编码对压缩后的数据进行解码：

char *decodeData(char *input, struct node *root) {
    char *output = (char*)malloc(sizeof(char) * strlen(input));
    int index = 0;
    struct node *n = root;
    for (int i = 0; i < strlen(input); i++) {
        if (input[i] == '0') {
            n = n->left;
        } else {
            n = n->right;
        }
        if (n->left == NULL && n->right == NULL) {
            output[index++] = n->ch;
            n = root;
        }
    }
    output[index] = '\0';
    return output;
}

以上就是使用C语言实现哈夫曼编码的基本步骤。

c语言实现哈夫曼编码压缩

好的，实现哈夫曼编码压缩的步骤如下：

1. 统计字符频率：遍历待压缩的文件，统计每个字符出现的次数，将结果存储在一个频率表中。

2. 构建哈夫曼树：根据字符频率表构建哈夫曼树，构建过程中需要用到最小堆。

3. 生成编码表：根据哈夫曼树，生成每个字符对应的哈夫曼编码，将结果存储在一个编码表中。

4. 压缩文件：遍历待压缩的文件，将每个字符替换为其对应的哈夫曼编码，重新写入一个压缩后的文件中。

下面是一个简单的C语言实现：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define MAX_TREE_HT 100

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)
{
    struct MinHeap* minHeap = createMinHeap(size);

    for (int 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 compress(char* input, char* output)
{
    FILE* fp1 = fopen(input, "r");
    if (fp1 == NULL) {
        printf("File Not Found!\n");
        return;
    }
    FILE* fp2 = fopen(output, "w");

    char ch;
    int freq[256] = { 0 };
    while ((ch = fgetc(fp1)) != EOF) {
        freq[ch]++;
    }

    char data[256] = { 0 };
    int j = 0;
    for (int i = 0; i < 256; i++) {
        if (freq[i] != 0) {
            data[j] = (char)i;
            j++;
        }
    }

    HuffmanCodes(data, freq, j);

    rewind(fp1);
    char buffer = 0, bit_count = 0;
    while ((ch = fgetc(fp1)) != EOF) {
        int len = strlen(codes[ch]);
        for (int i = 0; i < len; i++) {
            buffer = buffer << 1;
            if (codes[ch][i] == '1') {
                buffer = buffer | 1;
            }
            bit_count++;
            if (bit_count == 8) {
                fwrite(&buffer, 1, 1, fp2);
                buffer = 0;
                bit_count = 0;
            }
        }
    }
    if (bit_count != 0) {
        buffer = buffer << (8 - bit_count);
        fwrite(&buffer, 1, 1, fp2);
    }
    fclose(fp1);
    fclose(fp2);
}

int main()
{
    compress("test.txt", "test.huff");
    return 0;
}

其中，compress函数实现了文件压缩的过程。在压缩过程中，先统计字符频率，再根据字符频率构建哈夫曼树，生成每个字符对应的哈夫曼编码，最后将每个字符替换为其对应的哈夫曼编码，写入一个压缩后的文件中。