This commit is contained in:
Džubara 2025-01-19 21:51:45 +01:00
parent 790aa2149c
commit ee7833a8f1

View File

@ -123,7 +123,7 @@ void write_bits(FILE* file, const char* bits, unsigned char* buffer, int* bit_po
(*bit_pos)++; (*bit_pos)++;
if (*bit_pos % 8 == 0) { if (*bit_pos % 8 == 0) {
fwrite(buffer, 1, 1, file); fwrite(buffer, 1, 1, file);
buffer[*bit_pos / 8 - 1] = 0; // Clear the written byte buffer[*bit_pos / 8 - 1] = 0;
} }
} }
} }
@ -142,14 +142,14 @@ HuffmanNode* deserialize_tree(FILE* file) {
if (marker == EOF) return NULL; if (marker == EOF) return NULL;
if (marker == '1') { if (marker == '1') {
// Leaf node: Read the symbol
HuffmanNode* node = (HuffmanNode*)malloc(sizeof(HuffmanNode)); HuffmanNode* node = (HuffmanNode*)malloc(sizeof(HuffmanNode));
node->symbol = fgetc(file); node->symbol = fgetc(file);
node->left = node->right = NULL; node->left = node->right = NULL;
return node; return node;
} }
// Internal node: Create a new node and deserialize children
HuffmanNode* node = (HuffmanNode*)malloc(sizeof(HuffmanNode)); HuffmanNode* node = (HuffmanNode*)malloc(sizeof(HuffmanNode));
node->left = deserialize_tree(file); node->left = deserialize_tree(file);
node->right = deserialize_tree(file); node->right = deserialize_tree(file);
@ -162,19 +162,17 @@ int compress_1(const char* input_file_name, const char* output_file_name) {
unsigned char* data = read_file(input_file_name, &size); unsigned char* data = read_file(input_file_name, &size);
if (!data) return -1; if (!data) return -1;
// Build Huffman tree
HuffmanNode* root = build_huffman_tree(data, size); HuffmanNode* root = build_huffman_tree(data, size);
if (!root) { if (!root) {
free(data); free(data);
return -1; return -1;
} }
// Generate Huffman codes
char* codes[256] = {0}; char* codes[256] = {0};
char buffer[256]; char buffer[256];
generate_huffman_codes(root, codes, buffer, 0); generate_huffman_codes(root, codes, buffer, 0);
// Open output file
FILE* output_file = fopen(output_file_name, "wb"); FILE* output_file = fopen(output_file_name, "wb");
if (!output_file) { if (!output_file) {
perror("Error opening output file"); perror("Error opening output file");
@ -183,7 +181,7 @@ int compress_1(const char* input_file_name, const char* output_file_name) {
return -1; return -1;
} }
// Compress data
unsigned char bit_buffer[1] = {0}; unsigned char bit_buffer[1] = {0};
int bit_pos = 0; int bit_pos = 0;
@ -191,7 +189,6 @@ int compress_1(const char* input_file_name, const char* output_file_name) {
write_bits(output_file, codes[data[i]], bit_buffer, &bit_pos); write_bits(output_file, codes[data[i]], bit_buffer, &bit_pos);
} }
// Flush remaining bits
if (bit_pos % 8 != 0) { if (bit_pos % 8 != 0) {
fwrite(bit_buffer, 1, 1, output_file); fwrite(bit_buffer, 1, 1, output_file);
} }
@ -200,7 +197,7 @@ int compress_1(const char* input_file_name, const char* output_file_name) {
printf("Compressing using Huffman coding...\n"); printf("Compressing using Huffman coding...\n");
// Clean up
for (int i = 0; i < 256; i++) { for (int i = 0; i < 256; i++) {
if (codes[i]) free(codes[i]); if (codes[i]) free(codes[i]);
} }
@ -273,15 +270,14 @@ int compress_2(const char* input_file_name, const char* output_file_name) {
return -1; return -1;
} }
size_t search_buffer_size = 1024; // Veľkosť search bufferu size_t search_buffer_size = 1024;
size_t lookahead_buffer_size = 16; // Veľkosť lookahead bufferu size_t lookahead_buffer_size = 16;
size_t pos = 0; size_t pos = 0;
while (pos < size) { while (pos < size) {
size_t best_match_offset = 0; size_t best_match_offset = 0;
size_t best_match_length = 0; size_t best_match_length = 0;
// Vyhľadaj najlepšiu zhodu v search bufferi
for (size_t i = (pos > search_buffer_size ? pos - search_buffer_size : 0); i < pos; i++) { for (size_t i = (pos > search_buffer_size ? pos - search_buffer_size : 0); i < pos; i++) {
size_t match_length = 0; size_t match_length = 0;
while (match_length < lookahead_buffer_size && while (match_length < lookahead_buffer_size &&
@ -295,7 +291,6 @@ int compress_2(const char* input_file_name, const char* output_file_name) {
} }
} }
// Ulož trojicu (offset, length, next_symbol)
unsigned char offset_high = (best_match_offset >> 8) & 0xFF; unsigned char offset_high = (best_match_offset >> 8) & 0xFF;
unsigned char offset_low = best_match_offset & 0xFF; unsigned char offset_low = best_match_offset & 0xFF;
unsigned char length = best_match_length; unsigned char length = best_match_length;
@ -306,7 +301,6 @@ int compress_2(const char* input_file_name, const char* output_file_name) {
fputc(length, output_file); fputc(length, output_file);
fputc(next_symbol, output_file); fputc(next_symbol, output_file);
// Posuň pozíciu v dátach
pos += best_match_length + 1; pos += best_match_length + 1;
} }
@ -351,13 +345,13 @@ int decompress_2(const char* input_file_name, const char* output_file_name) {
size_t offset = (offset_high << 8) | offset_low; size_t offset = (offset_high << 8) | offset_low;
// Skopíruj zhodu z histórie
for (size_t i = 0; i < length; i++) { for (size_t i = 0; i < length; i++) {
output_buffer[pos] = output_buffer[pos - offset]; output_buffer[pos] = output_buffer[pos - offset];
pos++; pos++;
} }
// Pridaj ďalší symbol
output_buffer[pos++] = next_symbol; output_buffer[pos++] = next_symbol;
} }