Python课程作业三——文件读取时间

题目要求

下载 参考资料–》课上代码–〉make_sentence.py，该文件的功能是可以生成一个句子，把该文件作为一个模块引入到你的程序中。

程序功能如下：

1、调用make_sentence.py模块，把生成的句子写到一个文本文件中，写100000000次，得到大约2G的一个文件

2、分别通过以下三种方式访问生成的文件，要求从文件中统计cat出现的次数。

1）磁盘文件检索方式

2）按行读取文件，一行一行读入内存处理

3）一次性读入内存处理

3、对上面的三种形式通过装饰器计算每种方式的运行时间。

代码

	import makesentence as ms
import time

def generate():
    return " ".join(ms.sentence())
#装饰器
def timer(func):
    # 传入了参数
    def count_time(*args):
        print("文件开始读取，计时开始")
        start = time.time()
        # 调用原函数
        func(*args)
        end = time.time()
        print("文件结束读取，计时结束")
        print("函数 {name} 的用时为 {time:.6f} 秒(s)".format(name = func.__name__,time = end-start))
    return count_time

#以1e8次生成句子
def get_sentences(name):
    file = open(name,'w')
    for i in range(0,int(1e8)):
        print(i)
        file.write(generate()+'\n')
    file.close()
#生成样例
def generate_samples(num,name,tmp_name):
    new_file = open(tmp_name,'w')
    file = open(name,'r')
    time = 0
    # 从源文件中读取样例
    for line in file:
        if time<num :
            new_file.write(line)
            time+=1
        else :break
    new_file.close()
    file.close()

@timer
def count_cat_os(name):
    cat = 0
    try:
        file = open(name,'r')
        # 直接从file中检索，磁盘文件检索方法
        for line in file:
            words = line.split(" ")
            for word in words:
                if "cat" in word:cat+=1
        file.close()
        print("文件中共有：\t", cat, "个cat")
    # 对FileNotFoundError单独处理
    except FileNotFoundError:
        print("文件名错误，请重新输入")
    except:
        print("出现异常，请重试")

@timer
def count_cat_line(name):
    cat = 0
    try:
        file = open(name,'r')
        while True:
            # 读取每行
            line = file.readline()
            if not line: break
            words = line.split(" ")
            for word in words:
                if "cat" in word: cat += 1
        file.close()
        print("文件中共有：\t", cat, "个cat")
    except FileNotFoundError:
        print("文件名错误，请重新输入")
    except:
        print("出现异常，请重试")

# @timer
# def count_cat_3(name):
#     cat = 0
#     try:
#         file = open(name,'r')
#         chars = file.read()
#         words = chars.split()
#         for each in words:
#             if "cat" in each: cat += 1
#         file.close()
#         print("文件中共有：\t", cat, "个cat")
#     except FileNotFoundError:
#         print("文件名错误，请重新输入")

# 按字符处理
@timer
def count_cat_mem(name):
    cat = 0
    try:
        file = open(name,'r')
        # 一次性读到内存中
        chars = file.read()
        word = ""
        for each in chars:
            if each == ' ' or each == '\n':
                if "cat" in word: cat += 1
                word = ""
            else :word += each
        file.close()
        print("文件中共有：\t", cat, "个cat")
    except FileNotFoundError:
        print("文件名错误，请重新输入")
    # 由于需要一次性读到内存，对内存有要求，因此设置MemoryError处理
    except MemoryError:
        print("内存溢出！请选择其他方法或扩大文件存储")
    except:
        print("出现异常，请重试")

if __name__ == "__main__":
    # 生成句子
    # get_sentences("sentences.txt")
    # 生成sample用来测试
    # generate_samples(10000,"sentences.txt","s.txt")
    count_cat_os("sentences.txt")
    count_cat_line("sentences.txt")
    count_cat_mem("sentences.txt")

    '''
    文件开始读取，计时开始
    文件中共有：	 48485821 个cat
    文件结束读取，计时结束
    函数 count_cat_1 的用时为 68.235201 秒(s)
    文件开始读取，计时开始
    文件中共有：	 48485821 个cat
    文件结束读取，计时结束
    函数 count_cat_2 的用时为 80.687801 秒(s)
    文件开始读取，计时开始
    文件中共有：	 48485821 个cat
    文件结束读取，计时结束
    函数 count_cat_3 的用时为 229.200805 秒(s)
    '''

附：makesentence.py

#### 生成复合英文语法的单词序列

from random import choice, seed, randrange

articles = ("a", "the","1","2","3","4","5","6","7","8","9","10")
nouns = ("cat", "dog", "sheep", "rabbit", "tiger", "chicken",
         "fish", "grass", "seed", "carrot", "apple")
verbs = ("eats", "catches", "finds")

def sentence():
    return noun_phrase() + verb_phrase()

def noun_phrase():
    return [choice(articles), choice(nouns)]

def verb_phrase():
    vp = [choice(verbs)]
    if randrange(3) > 0:
        vp.extend(noun_phrase())
    return vp
    
if __name__ == "__main__":
    seed()
    for i in range(10):
        print(" ".join(sentence()))