import re
from collections import Counter
from cppy.cp_util import *

# 缓存系统，使用字典来存储文件路径和对应的词频结果; 可以存到本地磁盘，就可重复利用计算结果
word_freq_cache = {}

def calculate_word_frequency(file_path):
    # 如果文件路径已经在缓存中，直接返回缓存的结果
    if file_path in word_freq_cache:
        return word_freq_cache[file_path]

    # 计算词频
    words = extract_file_words(file_path)
    word_counts = Counter(words)

    # 将结果存储到缓存中
    word_freq_cache[file_path] = word_counts.most_common(10)

    return word_freq_cache[file_path]

# 测试函数
top_10_words = calculate_word_frequency(testfilepath)
for word, freq in top_10_words:
    print(f"{word}: {freq}")