usaa24/sk1/compressor.c

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

#define MAX_TREE_HT 256

// A Huffman tree node
struct MinHeapNode {
    unsigned char data;
    unsigned freq;
    struct MinHeapNode *left, *right;
};

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

// Function to create a new node
struct MinHeapNode* createNode(unsigned char data, unsigned freq) {
    struct MinHeapNode* temp = (struct MinHeapNode*)malloc(sizeof(struct MinHeapNode));
    temp->data = data;
    temp->freq = freq;
    temp->left = temp->right = NULL;
    return temp;
}

// Function to create a MinHeap
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;
}

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

// MinHeapify function
void minHeapify(struct MinHeap* minHeap, unsigned idx) {
    unsigned smallest = idx;  // Changed to unsigned
    unsigned left = 2 * idx + 1;  // Changed to unsigned
    unsigned right = 2 * idx + 2;  // Changed to unsigned

    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);
    }
}

// Extract minimum value node from heap
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;
}

// Insert a new node to MinHeap
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;
}

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

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

// Create and build a MinHeap
struct MinHeap* createAndBuildMinHeap(unsigned char data[], int freq[], int size) {
    struct MinHeap* minHeap = createMinHeap(size);
    for (int i = 0; i < size; ++i)
        minHeap->array[i] = createNode(data[i], freq[i]);
    minHeap->size = size;
    buildMinHeap(minHeap);
    return minHeap;
}
void freeMinHeap(struct MinHeap* minHeap) {
    for (int i = 0; i < minHeap->size; ++i) {
        free(minHeap->array[i]);
    }
    free(minHeap->array);
    free(minHeap);
}

void freeHuffmanCodes(char* codes[256]) {
    for (int i = 0; i < 256; ++i) {
        if (codes[i]) {
            free(codes[i]);
        }
    }
}
// Build Huffman Tree
struct MinHeapNode* buildHuffmanTree(unsigned 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 = createNode('$', left->freq + right->freq);
        top->left = left;
        top->right = right;

        insertMinHeap(minHeap, top);
    }
    return extractMin(minHeap);
}

// Print Huffman Codes to a map
void storeCodes(struct MinHeapNode* root, char** codes, char* currentCode, int top) {
    if (!root) return;

    if (root->left) {
        currentCode[top] = '0';
        storeCodes(root->left, codes, currentCode, top + 1);
    }
    if (root->right) {
        currentCode[top] = '1';
        storeCodes(root->right, codes, currentCode, top + 1);
    }
    if (!(root->left) && !(root->right)) {
        currentCode[top] = '\0';
        codes[root->data] = strdup(currentCode); // Ensure memory is allocated
    }
}

// Updated compressFile function
void storeCodes(struct MinHeapNode* root, char** codes, char* currentCode, int top) {
    if (!root) return;

    if (root->left) {
        currentCode[top] = '0';
        storeCodes(root->left, codes, currentCode, top + 1);
    }
    if (root->right) {
        currentCode[top] = '1';
        storeCodes(root->right, codes, currentCode, top + 1);
    }
    if (!(root->left) && !(root->right)) {
        currentCode[top] = '\0';
        codes[root->data] = (char*)malloc(strlen(currentCode) + 1);  // Use malloc instead of strdup
        strcpy(codes[root->data], currentCode); // Copy the string
    }
}

// Исправление для minHeap в compressFile
int compressFile(const char* input_file_name, const char* output_file_name) {
    FILE* inputFile = fopen(input_file_name, "rb");
    if (!inputFile) {
        perror("Error opening input file");
        return -1;
    }

    int freq[256] = {0};
    unsigned char buffer;

    // Count frequency of each byte
    while (fread(&buffer, sizeof(unsigned char), 1, inputFile)) {
        freq[buffer]++;
    }
    rewind(inputFile);

    unsigned char data[256];
    int frequencies[256], size = 0;
    for (int i = 0; i < 256; i++) {
        if (freq[i] > 0) {
            data[size] = (unsigned char)i;
            frequencies[size] = freq[i];
            size++;
        }
    }

    struct MinHeap* minHeap = createAndBuildMinHeap(data, frequencies, size);  // Создаем кучу
    struct MinHeapNode* root = buildHuffmanTree(data, frequencies, size);
    char* codes[256] = {0};
    char currentCode[MAX_TREE_HT] = {0}; // Initialize to avoid garbage values
    storeCodes(root, codes, currentCode, 0);

    FILE* outputFile = fopen(output_file_name, "wb");
    if (!outputFile) {
        perror("Error opening output file");
        fclose(inputFile);
        return -1;
    }

    // Write codes to output file
    fwrite(freq, sizeof(int), 256, outputFile);

    unsigned char byte = 0;
    int bitCount = 0;
    while (fread(&buffer, sizeof(unsigned char), 1, inputFile)) {
        char* code = codes[buffer];
        if (!code) {
            fprintf(stderr, "Error: Undefined code for byte %u\n", buffer);
            fclose(inputFile);
            fclose(outputFile);
            return -1;
        }
        for (int i = 0; code[i] != '\0'; i++) {
            byte = (byte << 1) | (code[i] - '0');
            bitCount++;
            if (bitCount == 8) {
                fwrite(&byte, sizeof(unsigned char), 1, outputFile);
                byte = 0;
                bitCount = 0;
            }
        }
    }
    if (bitCount > 0) {
        byte <<= (8 - bitCount);
        fwrite(&byte, sizeof(unsigned char), 1, outputFile);
    }

    fclose(inputFile);
    fclose(outputFile);

    freeMinHeap(minHeap);  // Free the min heap memory
    freeHuffmanCodes(codes);  // Free Huffman codes
    return 0;
}


// Decompress the file
int decompressFile(const char* input_file_name, const char* output_file_name) {
    FILE* inputFile = fopen(input_file_name, "rb");
    if (!inputFile) {
        perror("Error opening input file");
        return -1;
    }

    int freq[256];
    fread(freq, sizeof(int), 256, inputFile);

    unsigned char data[256];
    int frequencies[256], size = 0;
    for (int i = 0; i < 256; i++) {
        if (freq[i] > 0) {
            data[size] = (unsigned char)i;
            frequencies[size] = freq[i];
            size++;
        }
    }

    struct MinHeapNode* root = buildHuffmanTree(data, frequencies, size);

    FILE* outputFile = fopen(output_file_name, "wb");
    if (!outputFile) {
        perror("Error opening output file");
        fclose(inputFile);
        return -1;
    }

    struct MinHeapNode* current = root;
    unsigned char buffer;
    int bitCount = 0;
    while (fread(&buffer, sizeof(unsigned char), 1, inputFile)) {
        for (int i = 7; i >= 0; i--) {
            int bit = (buffer >> i) & 1;
            if (bit == 0)
                current = current->left;
            else
                current = current->right;

            if (!(current->left) && !(current->right)) {
                fwrite(&current->data, sizeof(unsigned char), 1, outputFile);
                current = root;
            }
        }
    }

    fclose(inputFile);
    fclose(outputFile);
    return 0;
}



int compress_1(const char* input_file_name, const char* output_file_name){
	if(compressFile(input_file_name, output_file_name) == 0){
		printf("Succsses!");
	}
	return 0;
}

int decompress_1(const char* input_file_name, const char* output_file_name){
	if(decompressFile(input_file_name, output_file_name) == 0){
                printf("Succsses!");
        }
        return 0;

}
int compress_2(const char* input_file_name, const char* output_file_name);
int decompress_2(const char* input_file_name, const char* output_file_name);