2、哈夫曼編碼演算法

輸入：字元及其權值，待譯碼字串，待解碼字串

功能要求：輸出各字元的哈夫曼編碼，輸出譯碼字串，輸出解碼字串

原始碼：

  1 class Node:
  2     def __init__(self, name, weight):
  3         self.name = name
  4         self.weight = weight
  5         self.left = None
  6         self.right = None
  7         self.father = None
  8 
  9     def is_left_child(self):
 
 10         return self.father.left == self
 11 
 12 
 13 def create_prim_nodes(data_set, labels):
 14     if len(data_set) != len(labels):
 15         raise Exception('資料和標籤不匹配!')
 16     nodes = []
 17     for i in range(len(labels)):
 18         nodes.append(Node(labels[i], data_set[i]))
 19     return
 
 nodes
 20 
 21 
 22 def create_HF_tree(nodes):
 23     tree_nodes = nodes.copy()
 24     while len(tree_nodes) > 1:
 25         tree_nodes.sort(key=lambda node: node.weight)
 26         new_left = tree_nodes.pop(0)
 27         new_right = tree_nodes.pop(0)
 28         new_node = Node(None, (new_left.weight + new_right.weight))
 
 29         new_node.left = new_left
 30         new_node.right = new_right
 31         new_left.father = new_right.father = new_node
 32         tree_nodes.append(new_node)
 33     tree_nodes[0].father = None
 34     return tree_nodes[0]
 35 
 36 
 37 def get_huffman_code(nodes):
 38     codes = {}
 39     for node in nodes:
 40         code = ''
 41         name = node.name
 42         while node.father != None:
 43             if node.is_left_child():
 44                 code = '0' + code
 45             else:
 46                 code = '1' + code
 47             node = node.father
 48         codes[name] = code
 49     return codes
 50 
 51 
 52 def encode_huffman(codes, str_encoding):
 53     after_encoding = ''
 54     for char in str_encoding:
 55         flag = 0
 56         for key in codes.keys():
 57             if char == key:
 58                 after_encoding += codes[key]
 59                 flag = 1
 60                 break
 61         if flag == 0:
 62             print('字串中包含未知字元!')
 63             break
 64     return after_encoding
 65 
 66 
 67 def decode_huffman(codes, str_decoding):
 68     after_decoding = ''
 69     temp = ''
 70     for char in str_decoding:
 71         temp += char
 72         if temp == str_decoding:
 73             print("編碼存在錯誤！")
 74             break
 75         for key in codes.keys():
 76             if codes[key] == temp:
 77                 after_decoding += key
 78                 temp = ''
 79     return after_decoding
 80 
 81 
 82 if __name__ == '__main__':
 83     # labels = ['a', 'b', 'c', 'd', 'e', 'f']
 84     # data_set = [9, 12, 6, 3, 5, 15]
 85     str_labels = input('請輸入字元（用空格分隔）：')
 86     str_data = input('請輸入權值（用空格分隔）：')
 87     str_labels = str_labels.replace(' ', '')
 88     list_data = str_data.split(' ')
 89     labels = []
 90     data_set = []
 91     for char in str_labels:
 92         labels.append(char)
 93     for list in list_data:
 94         data_set.append(int(list))
 95 
 96     # str_encoding = 'abbcefd'
 97     # str_decoding = '0001011001011111010'
 98     str_encoding = input('請輸入譯碼字串：')
 99     str_decoding = input('請輸入解碼字串：')
100     nodes = create_prim_nodes(data_set, labels)
101     root = create_HF_tree(nodes)
102     codes = get_huffman_code(nodes)
103     print('各字元的哈夫曼編碼：')
104     for key in codes.keys():
105         print(key, ': ', codes[key])
106 
107     print('譯碼字串：', encode_huffman(codes, str_encoding))
108     print('解碼字串：', decode_huffman(codes, str_decoding))