我已经尝试过使用 struct 模块的方法,如我的代码中注释掉的行所示,但没有成功。基本上我有两个选择:我可以逐个编写二进制数据代码(我的代码是长度从 3 位到 13 位不等的位序列),或者转换整个 n 个字符的字符串(在这种情况下,n=25000+)为二进制数据。但我不知道如何实现这两种方法。代码:
import heapq
import binascii
import struct
def createFrequencyTupleList(inputFile):
frequencyDic = {}
intputFile = open(inputFile, 'r')
for line in intputFile:
for char in line:
if char in frequencyDic.keys():
frequencyDic[char] += 1
else:
frequencyDic[char] = 1
intputFile.close()
tupleList = []
for myKey in frequencyDic:
tupleList.append((frequencyDic[myKey],myKey))
return tupleList
def createHuffmanTree(frequencyList):
heapq.heapify(frequencyList)
n = len(frequencyList)
for i in range(1,n):
left = heapq.heappop(frequencyList)
right = heapq.heappop(frequencyList)
newNode = (left[0] + right[0], left, right)
heapq.heappush(frequencyList, newNode)
return frequencyList[0]
def printHuffmanTree(myTree, someCode,prefix=''):
if len(myTree) == 2:
someCode.append((myTree[1] + "@" + prefix))
else:
printHuffmanTree(myTree[1], someCode,prefix + '0')
printHuffmanTree(myTree[2], someCode,prefix + '1')
def parseCode(char, myCode):
for k in myCode:
if char == k[0]:
return k[2:]
if __name__ == '__main__':
myList = createFrequencyTupleList('input')
myHTree = createHuffmanTree(myList)
myCode = []
printHuffmanTree(myHTree, myCode)
inputFile = open('input', 'r')
outputFile = open('encoded_file2', "w+b")
asciiString = ''
n=0
for line in inputFile:
for char in line:
#outputFile.write(parseCode(char, myCode))
asciiString += parseCode(char, myCode)
n += len(parseCode(char, myCode))
#values = asciiString
#print n
#s = struct.Struct('25216s')
#packed_data = s.pack(values)
#print packed_data
inputFile.close()
#outputFile.write(packed_data)
outputFile.close()