哈夫曼树压缩与解压缩的代码

下面是Python实现哈夫曼树压缩和解压缩的代码：

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

        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

    # 统计字符出现的频率
    def make_frequency_dict(self, text):
        frequency = {}
        for character in text:
            if not character in frequency:
                frequency[character] = 0
            frequency[character] += 1
        return frequency

    # 构建哈夫曼树
    def build_heap(self, frequency):
        for key in frequency:
            node = self.HeapNode(key, frequency[key])
            heapq.heappush(self.heap, node)

    # 合并节点，构建哈夫曼树
    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)

    # 对哈夫曼树进行遍历，生成编码
    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)

    # 将编码后的数据写入输出文件
    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):
        padding_required = 8 - len(encoded_text) % 8
        for i in range(padding_required):
            encoded_text += "0"
        padding_info = "{0:08b}".format(padding_required)
        padded_encoded_text = padding_info + encoded_text
        return padded_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

    # 压缩
    def compress(self):
        filename, file_extension = os.path.splitext(self.path)
        output_path = filename + ".bin"

        with open(self.path, 'r+') as file, open(output_path, 'wb') as output:
            text = file.read()
            text = text.rstrip()

            frequency = self.make_frequency_dict(text)
            self.build_heap(frequency)
            self.merge_nodes()
            self.make_codes()

            encoded_text = self.get_encoded_text(text)
            padded_encoded_text = self.pad_encoded_text(encoded_text)
            byte_array = self.get_byte_array(padded_encoded_text)
            output.write(bytes(byte_array))

        print("Compressed")
        return output_path

    # 解压缩
    def remove_padding(self, padded_encoded_text):
        padding_info = padded_encoded_text[:8]
        padding_required = int(padding_info, 2)

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

        return encoded_text

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

        for bit in encoded_text:
            current_code += bit
            if(current_code in self.reverse_mapping):
                character = self.reverse_mapping[current_code]
                decoded_text += character
                current_code = ""

        return decoded_text

    def decompress(self, input_path):
        filename, file_extension = os.path.splitext(self.path)
        output_path = filename + "_decompressed" + ".txt"

        with open(input_path, 'rb') as file, open(output_path, 'w') 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)
            decoded_text = self.decode_text(encoded_text)
            output.write(decoded_text)

        print("Decompressed")
        return output_path

使用示例：

h = HuffmanCoding("test.txt")
compressed_path = h.compress()
decompressed_path = h.decompress(compressed_path)

其中，`test.txt`是待压缩的文件名，`compressed_path`是压缩后的文件路径，`decompressed_path`是解压缩后的文件路径。