基于Huffman编码的压缩软件的Python实现

scuess

哈夫曼编码是利用贪心算法进行文本压缩的算法，其算法思想是首先统计文件中各字符出现的次数，保存到数组中，然后将各字符按照次数升序排序，挑选次数最小的两个元素进行连结形成子树，子树的次数等于两节点的次数之和，接着把两个元素从数组删除，将子树放入数组，重新排序，重复以上步骤。为了解压，在压缩时首先往文件中填入huffman编码的映射表的长度，该表的序列化字符串，编码字符串分组后最后一组的长度（编码后字符串长度模上分组长度），最后再填充编码后的字符串。本算法中以一个字节，8位作为分组长度，将编码后二进制字符串一一分组。代码如下：



__author__ = 'linfuyuan'
import struct
import pickle
type = int(raw_input('please input the type number(0 for compress, 1 for decompress):'))
file = raw_input('please input the filepath:')

class Node:
def __init__(self):
self.value = ''
self.left = None
self.right = None
self.frequency = 0
self.code = ''

# let the unique value be the key in the map
def change_value_to_key(huffmap):
map = {}
for (key, value) in huffmap.items():
map[value] = key
return map

if type == 0:
origindata = ''
# count the frequency of each letter
lettermap = {}
def give_code(node):
if node.left:
node.left.code = '%s%s' % (node.code, '0')
give_code(node.left)
if node.right:
node.right.code = '%s%s' % (node.code, '1')
give_code(node.right)

def print_code(node):
if not node.left and not node.right:
print "%s %s" % (node.value, node.code)
if node.left:
print_code(node.left)
if node.right:
print_code(node.right)

def save_code(map, node):
if not node.left and not node.right:
map[node.value] = node.code
if node.left:
save_code(map, node.left)
if node.right:
save_code(map, node.right)

with open(file)as f:
for line in f.readlines():
origindata += line
for j in line:
if lettermap.get(j):
lettermap[j] += 1
else:
lettermap[j] = 1
nodelist = []
for (key, value) in lettermap.items():
node = Node()
node.value = key
node.frequency = value
nodelist.append(node)
nodelist.sort(cmp=lambda n1, n2: cmp(n1.frequency, n2.frequency))
for i in range(len(nodelist) - 1):
node1 = nodelist[0]
node2 = nodelist[1]
node = Node()
node.left = node1
node.right = node2
node.frequency = node1.frequency + node2.frequency
nodelist[0] = node
nodelist.pop(1)
nodelist.sort(cmp=lambda n1, n2: cmp(n1.frequency, n2.frequency))
# give the code
root = nodelist[0]
give_code(root)
huffman_map = {}
# save the node code to a map
save_code(huffman_map, root)
code_data = ''
for letter in origindata:
code_data += huffman_map[letter]
output_data = ''
f = open('%s_compress' % file, 'wb')
huffman_map_bytes = pickle.dumps(huffman_map)
f.write(struct.pack('I', len(huffman_map_bytes)))
f.write(struct.pack('%ds' % len(huffman_map_bytes), huffman_map_bytes))
f.write(struct.pack('B', len(code_data) % 8))
for i in range(0, len(code_data), 8):
if i + 8 < len(code_data):
f.write(struct.pack('B', int(code_data[i:i + 8], 2)))
else:
# padding
f.write(struct.pack('B', int(code_data[i:], 2)))
f.close()
print 'finished compressing'
if type == 1:
f = open(file, 'rb')
size = struct.unpack('I', f.read(4))[0]
huffman_map = pickle.loads(f.read(size))
left = struct.unpack('B', f.read(1))[0]
data = f.read(1)
datalist = []
while not data == '':
bdata = bin(struct.unpack('B', data)[0])[2:]
datalist.append(bdata)
data = f.read(1)
f.close()
for i in range(len(datalist) - 1):
datalist = '%s%s' % ('0' * (8 - len(datalist)), datalist)
datalist[-1] = '%s%s' % ('0' * (left - len(datalist[-1])), datalist[-1])
encode_data = ''.join(datalist)
current_code = ''
huffman_map = change_value_to_key(huffman_map)
f = open('%s_origin' % file, 'w')
for letter in encode_data:
current_code += letter
if huffman_map.get(current_code):
f.write(huffman_map[current_code])
current_code = ''
f.close()
print 'finished decompressing'
raw_input('please press any key to quit')



　　代码中有用到pickle模块进行对象序列化，还有struct模块进行读写二进制文件。
　　
由于算法中运算量最⼤的地⽅在于循环⾥嵌套了排序,故算法的时间复杂度是O(n2logn)。

经过压缩后,文件大⼩小分别为110KB和931KB。原来⼤⼩为190KB和
2.1MB,压缩效果明显。
　　希望对大家有用。