def main():
while (1):
print("1.Compress\n2.Decompress\n3.Exit")
choice = int(input("Enter Choice :"))
if choice == 1:
fileName = input("Enter file Name: ")
print("Encoding : ", fileName)
frequencyObject = Frequency(fileName)
frequencyTable = frequencyObject.frequencyTable()
huffmanObject = Huffman(frequencyTable)
huffmanCodes = huffmanObject.huffman()
encodeObject = Encode(huffmanCodes, fileName)
encodeObject.encode()
print("File Encoded as:" + fileName + ".bv\n\n")
elif choice == 2:
fileName = input("Enter file Name: ")
print("decoding : ", fileName)
decodeObject = Decode(fileName)
decodeObject.decode()
print("\nDecoded as " + fileName + "_new.txt")
elif choice == 3:
print("Bye\n")
return
else:
print("Invalid Choice\n")
def __init__(self, N):
self.frequency = Frequency()
self.noOfDocs = N
# -*- coding:utf-8 -*-
__author__ = 'Kusamura'
from Data import Data
from InvertedIndex import InvertedIndex
from Search import Search
from Frequency import Frequency
if __name__ == '__main__':
fileList = [] #章の一覧
for line in open('chaps/chap_title.tsv', 'r'): #chaps_titleから章の一覧を生成
fileList.append(line[:-1].split('\t')[0][2:])
dataList = [] #Dataクラス(ファイルから読み込んだデータ)のリスト
for fileName in fileList:
dataList.append(Data(fileName))
index = InvertedIndex(dataList) #転置インデックスを作成
# module = Search(index) #検索モジュール
# keys = ['retrieval', 'half-a-trillion', 'thus', 'layer', 'test', 'hoge', 'hogehoge']
# for key in keys:
# module.do(key)
# print index.countKeys() #辞書内の語数をカウント
# print Frequency().docFrequency(index) #辞書頻度
print Frequency().termFrequency(dataList) #単語頻度
