软工作业3：Python词频统计

def process_file(dst):     # 读文件到缓冲区
    try:     # 打开文件
        file=open(dst,"r")
    except IOError as s:
        print(s)
        return None
    try:     # 读文件到缓冲区
        bvffer=file.read()
    except:
        print("Read File Error!")
        return None
    file.close()
    return bvffer

def process_buffer(bvffer):
    if bvffer:
        word_freq = {}
        # 下面添加处理缓冲区 bvffer代码，统计每个单词的频率，存放在字典word_freq
        for i in ‘!"#$%&()*+-,-./:;<=>?@“”[\\]^_{|}~‘:
            bvffer = bvffer.replace(i, " ")  # 替换特殊字符
        bvffer = bvffer.lower()  # 把大写字母转换为小写
        words = bvffer.split()  # 分割字符串
        for word in words:
            word_freq[word] = word_freq.get(word, 0)+1
        return word_freq

def output_result(word_freq):
    if word_freq:
        sorted_word_freq = sorted(word_freq.items(), key=lambda v: v[1], reverse=True)
        for item in sorted_word_freq[:10]:  # 输出 Top 10 的单词
            print(item)

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument(‘dst‘)
    args = parser.parse_args()
    dst = args.dstdst = "Gone_with_the_wind.txt"
    bvffer = process_file(dst)
    word_freq = process_buffer(bvffer)
    output_result(word_freq)

if __name__ == "__main__":
    import cProfile
    import pstats
    import argparse
    cProfile.run("main()", "result")
    # 直接把分析结果打印到控制台
    p = pstats.Stats("result")  # 创建Stats对象
    p.sort_stats(‘calls‘).print_stats(10)
    # 按照调用次数排序，打印前10函数的信息
    p.strip_dirs().sort_stats("cumulative", "name").print_stats(10)
    p.print_callers(0.5, "process_file")  # 得知哪些函数调用了process_file
    p.print_callers(0.5, "process_buffer")  
    p.print_callers(0.5, "output_result")

if bvffer:
        word_freq = {}

for i in ‘!"#$%&()*+-,-./:;<=>?@“”[\\]^_{|}~‘:
            bvffer = bvffer.replace(i, " ")  # 替换特殊字符

for i in ‘!"()+-,-./:;<=>?“”^~‘:
            bvffer = bvffer.replace(i, " ")  # 替换特殊字符