def deal_Redundantwords(string):string = string.replace('\n', ' ').replace(',', ' ')s1 = list(string)num = len(s1)s1.append(' ')for i in range(num): if s1[i] in '."?\')-(;#$%&*!': #isalnum检测字符串是否有数组组成 if str(s1[i - 1].isalnum()) == 'True' and (str(s1[i + 1].isalnum()) == 'True'): pass else: s1[i] = ' ' for i in range(num): if s1[i] in ':': if s1[i + 1] == '/': pass else: s1[i] = ' ' #join连接字符数组 s = ''.join(s1) # print(s) return s

list1 = text.replace('\n', ' ').lower().split()  # 保存原始数据list2 = list(set(list1))  # 去重之后的数据if (flag == 0):print("total  " + str(len(list2)))  # 小文本统计词汇量（功能1不输出words）else:print("total  " + str(len(list2)) + "  words")  # 统计词汇量print("\n")dir_a = {}  # 计算频数for str1 in list1:if str1 != ' ':if str1 in dir_a.keys(): dir_a[str1] = dir_a[str1] + 1 else: dir_a[str1] = 1 dir_b = sorted((dir_a).items(), key=lambda x: x[1], reverse=True) # 按照频数排序

  try:with open(filename, 'r', encoding='UTF-8') as f_obj:content = f_obj.read()countNumber(content, flag)except FileNotFoundError:msg = "sorry,the file " + filename + " does not exist."print(msg)

path = os.listdir(os.getcwd())  # 获取当前目录下所有文件folderList = []for p in path:if os.path.isdir(p):  # 找到所有文件夹

for folder in folderList:if textFolder == folder:path1 = os.listdir(folder)  # 该文件夹下所有文件建成列表for i in path1:if os.path.splitext(i)[1] == '.txt':fileNameList.append(os.path.splitext(i)[0])

    elif sys.argv[1] == "-s":if (len(sys.argv) == 3):# print(sys.argv)flag = 0countFileWords(sys.argv[2], flag)else:# print(sys.argv) #重定向获取文件名redirect_words = sys.stdin.read()  # 存储文件名调用方法即可flag = 0 countNumber(redirect_words, flag)