# filename： word_freq.py
# 阅读注释，在所有pass处删除pass，添加代码

from string import punctuation


def process_file(dst):     # 读文件到缓冲区
    try:     # 打开文件

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

    return bvffer


def process_buffer(bvffer):
    if bvffer:
        word_freq = {}
        bvffer = bvffer.lower()     #将文本内容都改为小写
        # 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 ch in '“‘!;,.?”':  # 除去文本中的中英文标点符号
           bvffer = bvffer.replace(ch, " ")
        words = bvffer.strip().split()
        # strip()删除空白符（包括'/n', '/r','/t'）；split()以空格分割字符串
        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)

if __name__ == "__main__":
    import argparse
    parser = argparse.ArgumentParser()
    parser.add_argument('dst')
    args = parser.parse_args()
    dst = args.dst
    bvffer = process_file(dst)
    word_freq = process_buffer(bvffer)
    output_result(word_freq)