usaa24/sk1/compressor.c

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

#define MAX_TREE_NODES 256

// Structure to represent a tree node
typedef struct HuffmanNode {
    unsigned char data;
    unsigned frequency;
    struct HuffmanNode* left;
    struct HuffmanNode* right;
} HuffmanNode;

// A structure to represent the Min Heap (Priority Queue)
typedef struct MinHeap {
    unsigned size;
    unsigned capacity;
    HuffmanNode** array;
} MinHeap;

// Function to create a new node
HuffmanNode* newNode(unsigned char data, unsigned frequency) {
    HuffmanNode* node = (HuffmanNode*)malloc(sizeof(HuffmanNode));
    if (!node) {
        perror("Failed to allocate memory for new node");
        exit(EXIT_FAILURE);
    }
    node->data = data;
    node->frequency = frequency;
    node->left = node->right = NULL;
    return node;
}

// Function to create a MinHeap
MinHeap* createMinHeap(unsigned capacity) {
    MinHeap* minHeap = (MinHeap*)malloc(sizeof(MinHeap));
    if (!minHeap) {
        perror("Failed to allocate memory for MinHeap");
        exit(EXIT_FAILURE);
    }
    minHeap->size = 0;
    minHeap->capacity = capacity;
    minHeap->array = (HuffmanNode**)malloc(capacity * sizeof(HuffmanNode*));
    if (!minHeap->array) {
        perror("Failed to allocate memory for MinHeap array");
        exit(EXIT_FAILURE);
    }
    return minHeap;
}

// Function to swap two min heap nodes
void swapMinHeapNode(HuffmanNode** a, HuffmanNode** b) {
    HuffmanNode* temp = *a;
    *a = *b;
    *b = temp;
}

// Function to min heapify
void minHeapify(MinHeap* minHeap, int idx) {
    int smallest = idx;
    int left = 2 * idx + 1;
    int right = 2 * idx + 2;

    if (left < (int)minHeap->size && minHeap->array[left]->frequency < minHeap->array[smallest]->frequency)
        smallest = left;

    if (right < (int)minHeap->size && minHeap->array[right]->frequency < minHeap->array[smallest]->frequency)
        smallest = right;

    if (smallest != idx) {
        swapMinHeapNode(&minHeap->array[smallest], &minHeap->array[idx]);
        minHeapify(minHeap, smallest);
    }
}

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

// Extract the minimum node from heap
HuffmanNode* extractMin(MinHeap* minHeap) {
    HuffmanNode* 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(MinHeap* minHeap, HuffmanNode* node) {
    ++minHeap->size;
    int i = minHeap->size - 1;
    while (i && node->frequency < minHeap->array[(i - 1) / 2]->frequency) {
        minHeap->array[i] = minHeap->array[(i - 1) / 2];
        i = (i - 1) / 2;
    }
    minHeap->array[i] = node;
}

// Build a min heap of given capacity
void buildMinHeap(MinHeap* minHeap) {
    int n = minHeap->size - 1;
    for (int i = (n - 1) / 2; i >= 0; --i)
        minHeapify(minHeap, i);
}

// Function to build the Huffman tree
HuffmanNode* buildHuffmanTree(unsigned char* data, unsigned* freq, int size) {
    HuffmanNode *left, *right, *top;

    MinHeap* minHeap = createMinHeap(size);

    for (int i = 0; i < size; ++i)
        insertMinHeap(minHeap, newNode(data[i], freq[data[i]]));

    buildMinHeap(minHeap);

    while (!isSizeOne(minHeap)) {
        left = extractMin(minHeap);
        right = extractMin(minHeap);

        top = newNode('$', left->frequency + right->frequency);
        top->left = left;
        top->right = right;

        insertMinHeap(minHeap, top);
    }

    return extractMin(minHeap);
}

// Function to generate the Huffman codes for each character
void generateCodes(HuffmanNode* root, char* arr, int top, char** codes) {
    if (root->left) {
        arr[top] = '0';
        generateCodes(root->left, arr, top + 1, codes);
    }

    if (root->right) {
        arr[top] = '1';
        generateCodes(root->right, arr, top + 1, codes);
    }

    if (!root->left && !root->right) {
        arr[top] = '\0';  // Null terminate the string
        codes[root->data] = strdup(arr);
    }
}
void free_huffman_tree(Node* root) {
    if (!root) return;
    free_huffman_tree(root->left);
    free_huffman_tree(root->right);
    free(root);
}
// Function to compress a file
int compress_1(const char* input_file, const char* output_file) {
    FILE* input = fopen(input_file, "rb");
    FILE* output = fopen(output_file, "wb");
    if (!input || !output) {
        perror("Error opening file");
        return -1;
    }

    unsigned freq[256] = {0};
    unsigned char data;
    while (fread(&data, sizeof(data), 1, input) == 1)
        freq[data]++;

    unsigned char unique_data[256];
    int unique_count = 0;
    for (int i = 0; i < 256; i++) {
        if (freq[i] > 0) {
            unique_data[unique_count++] = i;
        }
    }

    HuffmanNode* root = buildHuffmanTree(unique_data, freq, unique_count);

    char* codes[256] = {0};
    char arr[256];
    generateCodes(root, arr, 0, codes);

    fwrite(&unique_count, sizeof(int), 1, output);
    for (int i = 0; i < unique_count; i++) {
        unsigned char symbol = unique_data[i];
        fwrite(&symbol, sizeof(unsigned char), 1, output);
        fwrite(&freq[symbol], sizeof(unsigned), 1, output);
    }

    fseek(input, 0, SEEK_SET);

    unsigned char buffer = 0;
    int bit_count = 0;
    size_t total_bits = 0;

    while (fread(&data, sizeof(data), 1, input) == 1) {
        char* code = codes[data];
        for (int i = 0; code[i] != '\0'; i++) {
            unsigned char bit = code[i] - '0';
            buffer = (buffer << 1) | bit;
            bit_count++;
            total_bits++;

            if (bit_count == 8) {
                fwrite(&buffer, sizeof(unsigned char), 1, output);
                bit_count = 0;
                buffer = 0;
            }
        }
    }

    if (bit_count > 0) {
        buffer <<= (8 - bit_count);
        fwrite(&buffer, sizeof(unsigned char), 1, output);
    }

    fwrite(&total_bits, sizeof(size_t), 1, output); // Write total bits used

    fclose(input);
    fclose(output);
    free_huffman_tree(root);
    return 0;
}

// Function to decompress the compressed file
int decompress_1(const char* input_file_name, const char* output_file_name) {
    FILE* input = fopen(input_file_name, "rb");
    if (!input) {
        perror("Error opening input file");
        return -1;
    }
    FILE* output = fopen(output_file_name, "wb");
    if (!output) {
        perror("Error opening output file");
        fclose(input);
        return -1;
    }

    int unique_count;
    if (fread(&unique_count, sizeof(int), 1, input) != 1) {
        perror("Error reading from input file");
        fclose(input);
        fclose(output);
        return -1;
    }

    unsigned char unique_data[256];
    unsigned freq[256] = {0};
    for (int i = 0; i < unique_count; i++) {
        if (fread(&unique_data[i], sizeof(unsigned char), 1, input) != 1 ||
            fread(&freq[unique_data[i]], sizeof(unsigned), 1, input) != 1) {
            perror("Error reading from input file");
            fclose(input);
            fclose(output);
            return -1;
        }
    }

    HuffmanNode* root = buildHuffmanTree(unique_data, freq, unique_count);

    size_t total_bits;
    fseek(input, -(long long)sizeof(size_t), SEEK_END);
    fread(&total_bits, sizeof(size_t), 1, input);

    fseek(input, sizeof(int) + unique_count * (sizeof(unsigned char) + sizeof(unsigned)), SEEK_SET);

    HuffmanNode* current = root;
    unsigned char byte;
    size_t bits_read = 0;

    while (bits_read < total_bits && fread(&byte, sizeof(byte), 1, input) == 1) {
        for (int i = 7; i >= 0 && bits_read < total_bits; i--, bits_read++) {
            if (byte & (1 << i)) {
                current = current->right;
            } else {
                current = current->left;
            }

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

    fclose(input);
    fclose(output);
    free_huffman_tree(root);
    return 0;
}