Python:如何在文件的字符串中搜索和统计词根出现的次数？

import re
from nltk.stem import PorterStemmer

def read_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        content = file.read()
    return content

def stem_and_count_words(text, stemmer, target_stem):
    # 使用正则表达式分割单词
    words = re.findall(r'\b\w+\b', text)
    
    # 初始化计数器
    count = 0
    
    for word in words:
        stemmed_word = stemmer.stem(word)
        if stemmed_word == target_stem:
            count += 1
    
    return count

# 主程序
if __name__ == "__main__":
    file_path = 'example.txt'  # 替换为你的文件路径
    target_stem = 'run'  # 替换为你想要统计的词根
    
    text = read_file(file_path)
    
    stemmer = PorterStemmer()
    count = stem_and_count_words(text, stemmer, target_stem)
    
    print(f"The stem '{target_stem}' appears {count} times in the file.")