Python数据结构之霍夫曼压缩

前言

  无损压缩领域最为常见的算法当属霍夫曼压缩算法了。其主要思想是放弃文本文件的传统保存方式，不再使用八位二进制数表示每一个字符，而是用较少的比特表示出现频率较高的字符，用较多的比特表示出现频率较低的字符。
在图像数据压缩时，游程编码和霍夫曼编码也是十分常用的。

变长前缀码

  和每个字符所相关的编码都是一个比特字符串，就好像有一个以字符为键、比特字符串为值得符号表一样。我们可以试着将最短得比特字符赋予最常用的字符，将A编码为0、B编码为1、R编码为00。这样一来问题就出现了，A的编码是0，R的编码是00，那么当0出现的时候，我们应该认为其是A还是R的前缀呢？如果你不想引入分隔符的话，这个时候就需要引入变长前缀码。
  在变长前缀码中，所有字符编码都不会成为其它字符编码的前缀，那么如此就不需要分隔符了。

前缀码的实现

  前缀码的实现采用了单词查找树。

自制Huffman压缩和解压工具

  网址如下，点击此处跳转

https://download.csdn.net/download/m0_37772174/11965071

  自制工具是exe文件
压缩命令 ：SZip A inputfilename outputfilename
解压缩命令：SZip X inputfilename outputfilename

Python 代码

'''
@file huffman.py
'''
import heapq
import os
from functools import total_ordering


@total_ordering
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


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

	# functions for compression:

	def make_frequency_dict(self, text):
		frequency = {}
		for character in text:
			if not character in frequency:
				frequency[character] = 0
			frequency[character] += 1
		return frequency

	def make_heap(self, frequency):
		for key in frequency:
			node = 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 = 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 + ".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.make_heap(frequency)
			self.merge_nodes()
			self.make_codes()

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

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

		print("Compressed")
		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 = ""
		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)

			decompressed_text = self.decode_text(encoded_text)
			
			output.write(decompressed_text)

		print("Decompressed")
		return output_path

#@file main.py
from huffman import HuffmanCoding


path = "test.txt"

h = HuffmanCoding(path)

output_path = h.compress()
print("Compressed file path: " + output_path)

decom_path = h.decompress(output_path)
print("Decompressed file path: " + decom_path)