Python文本语言评估性能优化：使用正则表达式加速词汇匹配

import re
from collections import Counter

class LanguageEvaluator:
    def __init__(self, english_words_file='words.txt', min_word_len=4, min_non_english_count=4):
        self.min_word_len = min_word_len
        self.file_path = english_words_file
        self.min_non_english_count = min_non_english_count
        self.english_words = set()

    async def load_english_words(self):
        """异步加载英文词汇表"""
        if not self.english_words:
            with open(self.file_path, 'r', encoding='utf-8') as file:
                self.english_words = {word.strip().lower() for word in file}
        return self.english_words

    async def preprocess_text(self, text):
        """预处理文本，提取符合条件的单词"""
        words = re.findall(r'\b\w+\b', text.lower())
        return [word for word in words if len(word) >= self.min_word_len and not word.startswith('@') and not re.match(r'^https?://', word)]

    async def count_non_english_words(self, words):
        """统计非英文单词数量（原始实现）"""
        english_words = await self.load_english_words()
        # 性能瓶颈所在：对于每个输入单词，遍历整个英文词汇表进行前缀匹配
        return sum(1 for word in words if not any(english_word.startswith(word) for english_word in english_words))

    async def is_english_custom(self, text):
        """判断文本是否为英文"""
        words_in_text = await self.preprocess_text(text)
        non_english_count = await self.count_non_english_words(words_in_text)
        print(f"Non-English words count: {non_english_count}")
        return non_english_count <= self.min_non_english_count

    async def count_duplicate_words(self, text):
        """统计重复单词数量"""
        words = await self.preprocess_text(text)
        word_counts = Counter(words)
        duplicate_count = sum(
            count - 1 for count in word_counts.values() if count > 1)
        return duplicate_count

import re
from collections import Counter

class LanguageEvaluatorOptimized:
    def __init__(self, english_words_file='words.txt', min_word_len=4, min_non_english_count=4):
        self.min_word_len = min_word_len
        self.file_path = english_words_file
        self.min_non_english_count = min_non_english_count
        self.english_words = set()
        self.english_prefix_regexp = None # 用于存储编译后的正则表达式

    async def load_english_words(self):
        """异步加载英文词汇表并编译正则表达式"""
        if not self.english_words:
            with open(self.file_path, 'r', encoding='utf-8') as file:
                self.english_words = {word.strip().lower() for word in file}
            # 构建并编译正则表达式
            # re.escape() 用于转义词汇中可能存在的正则表达式特殊字符
            # '^(' + ... + ')' 确保匹配从单词开头进行
            self.english_prefix_regexp = re.compile('^(' + '|'.join(re.escape(w) for w in self.english_words) + ')')
        return self.english_words

    def is_english_word(self, word):
        """使用正则表达式判断单词是否以英文词汇开头"""
        if self.english_prefix_regexp is None:
            # 确保正则表达式已加载，实际使用中应先调用 load_english_words
            raise RuntimeError("English words and regex not loaded. Call load_english_words first.")
        return self.english_prefix_regexp.search(word) is not None

    async def preprocess_text(self, text):
        """预处理文本，提取符合条件的单词"""
        words = re.findall(r'\b\w+\b', text.lower())
        return [word for word in words if len(word) >= self.min_word_len and not word.startswith('@') and not re.match(r'^https?://', word)]

    async def count_non_english_words(self, words):
        """统计非英文单词数量（优化后）"""
        await self.load_english_words() # 确保词汇表和正则表达式已加载
        # 对于每个输入单词，使用编译好的正则表达式进行匹配
        return sum(not self.is_english_word(word) for word in words)

    async def is_english_custom(self, text):
        """判断文本是否为英文"""
        words_in_text = await self.preprocess_text(text)
        non_english_count = await self.count_non_english_words(words_in_text)
        print(f"Non-English words count: {non_english_count}")
        return non_english_count <= self.min_non_english_count

    async def count_duplicate_words(self, text):
        """统计重复单词数量"""
        words = await self.preprocess_text(text)
        word_counts = Counter(words)
        duplicate_count = sum(
            count - 1 for count in word_counts.values() if count > 1)
        return duplicate_count