huffman.py

import heapq
import os

class HuffmanCoding:
    def __init__(self, path):
        self.path = path
        self.heap = []
        self.codes = {}
        self.reverse_mapping = {}

    class HeapNode:
        def __init__(self, char, freq):
            self.char = char
            self.freq = freq
            self.left = None
            self.right = None

        # defining comparators less_than and equals
        def __lt__(self, other):
            return self.freq < other.freq

        def __eq__(self, other):
            if (other == None):
                return False
            if (not isinstance(other, HeapNode)):
                return False
            return self.freq == other.freq

    # functions for compression:
    def make_heap(self, frequency):
        for key in frequency:
            node = self.HeapNode(key, frequency[key])
            heapq.heappush(self.heap, node)

    def merge_nodes(self):
        while (len(self.heap) > 1):
            node1 = heapq.heappop(self.heap)
            node2 = heapq.heappop(self.heap)

            merged = self.HeapNode(None, node1.freq + node2.freq)
            merged.left = node1
            merged.right = node2

            heapq.heappush(self.heap, merged)

    def make_codes_helper(self, root, current_code):
        if (root == None):
            return

        if (root.char != None):
            self.codes[root.char] = current_code
            self.reverse_mapping[current_code] = root.char
            return

        self.make_codes_helper(root.left, current_code + "0")
        self.make_codes_helper(root.right, current_code + "1")

    def make_codes(self):
        root = heapq.heappop(self.heap)
        current_code = ""
        self.make_codes_helper(root, current_code)

    def get_encoded_text(self, text):
        encoded_text = ""
        for character in text:
            encoded_text += self.codes[character]
        return encoded_text

    def pad_encoded_text(self, encoded_text):
        extra_padding = 8 - len(encoded_text) % 8
        for i in range(extra_padding):
            encoded_text += "0"

        padded_info = "{0:08b}".format(extra_padding)
        encoded_text = padded_info + encoded_text
        return encoded_text

    def get_byte_array(self, padded_encoded_text):
        if (len(padded_encoded_text) % 8 != 0):
            print("Encoded text not padded properly")
            exit(0)

        b = bytearray()
        for i in range(0, len(padded_encoded_text), 8):
            byte = padded_encoded_text[i:i + 8]
            b.append(int(byte, 2))
        return b

    def compress(self):
        filename, file_extension = os.path.splitext(self.path)
        output_path = filename + "_compressed" + ".bin"
        # read from binary file(jpg) and write to binary file
        with open(self.path, 'rb') as file, open(output_path, 'wb') as output:

            numlist = []
            byte = file.read(-1)
            frequency = {}

            for i in byte:
                numlist.append(i)
                if not i in frequency:
                    frequency[i] = 0
                frequency[i] += 1

            self.make_heap(frequency)
            self.merge_nodes()
            self.make_codes()

            encoded_text = self.get_encoded_text(numlist)
            padded_encoded_text = self.pad_encoded_text(encoded_text)

            b = self.get_byte_array(padded_encoded_text)
            output.write(bytes(b))

        print("Compressed successfully!")
        return output_path

    # functions for decompression:
    def remove_padding(self, padded_encoded_text):
        padded_info = padded_encoded_text[:8]
        extra_padding = int(padded_info, 2)

        padded_encoded_text = padded_encoded_text[8:]
        encoded_text = padded_encoded_text[:-1 * extra_padding]

        return encoded_text

    def decode_text(self, encoded_text):
        current_code = ""

        byted = bytearray()

        for bit in encoded_text:
            current_code += bit
            if (current_code in self.reverse_mapping):
                character = self.reverse_mapping[current_code]
                byted.append(character)
                current_code = ""
        return byted
    def decompress(self, input_path):
        filename, file_extension = os.path.splitext(self.path)
        output_path = filename + "_decompressed" + ".bin"
        with open(input_path, 'rb') as file, open(output_path, 'wb') as output:
            bit_string = ""
            byte = file.read(1)
            while len(byte) > 0:
                byte = ord(byte)
                bits = bin(byte)[2:].rjust(8, '0')
                bit_string += bits
                byte = file.read(1)

            encoded_text = self.remove_padding(bit_string)
            decompressed_text = self.decode_text(encoded_text)
            output.write(bytes(decompressed_text))
        print("Decompressed succsessfully!")
        return output_path

    #binary file to jpg
    def extract_jpg_image(self, file_name):
        jpg_byte_start = b'\xff\xd8'
        jpg_byte_end = b'\xff\xd9'
        jpg_image = bytearray()

        with open(file_name, 'rb') as f:
            req_data = f.read()

            start = req_data.find(jpg_byte_start)

            if start == -1:
                print('Could not find JPG start of image marker!')
                return

            end = req_data.find(jpg_byte_end, start)
            jpg_image += req_data[start:end + 1]

            print(f'Size: {end - start} bytes')

        with open(f'exracted-img.jpg', 'wb') as f:
            f.write(jpg_image)
            return "exracted-img.jpg"