from collections import Counter


class DanmukuAnalyzer:
    def __init__(self, danmukus):
        # 初始化弹幕数据：去除空弹幕和前后空格
        self.danmukus = [d.strip() for d in danmukus if d.strip()]
        # 加载停用词表（用于过滤无意义词汇）
        self.stopwords = self._load_stopwords()

    def _load_stopwords(self):
        """加载停用词表，包含默认停用词和自定义停用词（从文件读取）"""
        # 默认停用词集合（常见无实际意义的虚词）
        default_stopwords = {"的", "了", "是", "在", "我", "有", "和", "就", "不", "人", "都"}
        try:
            # 尝试从本地文件读取额外停用词并合并
            with open("stopwords.txt", "r", encoding="utf-8") as f:
                # 读取文件中所有停用词，去除空格后与默认停用词合并
                file_stopwords = {line.strip() for line in f.readlines()}
                return default_stopwords.union(file_stopwords)
        except:
            # 若文件读取失败（如文件不存在），则仅返回默认停用词
            return default_stopwords

    def get_ai_related(self):
        """筛选出与AI相关的弹幕，并统计每条弹幕的出现次数"""
        # 定义与AI相关的关键词集合
        ai_keywords = {"AI", "人工智能", "大模型", "语言模型", "LLM", "训练", "算法", "数据"}
        # 筛选包含任意AI关键词的弹幕
        ai_danmukus = [d for d in self.danmukus if any(k in d for k in ai_keywords)]
        # 使用Counter统计每条AI相关弹幕的出现次数
        return Counter(ai_danmukus)

    def classify_views(self, ai_counter):
        """
        对AI相关弹幕按观点类别进行分类统计
        :param ai_counter: 包含AI相关弹幕及其出现次数的Counter对象
        :return: 各观点类别的总出现次数字典
        """
        # 定义观点分类标准：键为类别名称，值为该类别对应的关键词列表
        categories = {
            "应用成本": [ "收费", "贵", "便宜", 
        "性价比", "会员", "订阅", "费用", "氪金", "省钱", "花钱",
        "成本高", "零成本", "低价", "高价","价格", "免费", "付费"],  # 与成本相关的观点

            "应用领域": ["应用", "场景", "教育", "医疗", "创作","办公", "学习", 
        "编程", "写作", "翻译", "客服", "设计", "科研", "金融",
        "教学", "聊天", "助手", "工具", "领域", "行业"],  # 与应用场景相关的观点

            "不利影响": ["风险", "偏见", "错误", "误导",
        "依赖", "滥用", "漏洞", "安全", "泄露", "失控", "替代",
        "虚假", "弊端", "危害" "伦理", "隐私", "失业"],  # 与负面影响相关的观点

            "积极影响": ["高效", "省力", "智能", 
        "好用", "厉害", "帮助", "提升", "优化", "进步", "解放",
        "神器", "给力", "便捷" "方便", "强大", "有用"],  # 与积极影响相关的观点
            "其他观点": []  # 未匹配到上述类别的观点
        }
        # 初始化各观点类别的计数（初始值为0）
        view_counts = {k: 0 for k in categories}
        
        # 遍历每条AI相关弹幕及其出现次数
        for danmuku, count in ai_counter.items():
            matched = False  # 标记是否匹配到某个观点类别
            # 检查当前弹幕是否属于某个预设类别（跳过"其他观点"）
            for cat, keywords in categories.items():
                if cat == "其他观点":
                    continue
                # 若弹幕包含该类别下的任意关键词，则归为该类别
                if any(k in danmuku for k in keywords):
                    view_counts[cat] += count  # 累加该类别的总次数
                    matched = True
                    break  # 匹配到后跳出循环，避免重复归类
            # 若未匹配到任何预设类别，则归为"其他观点"
            if not matched:
                view_counts["其他观点"] += count
        
        return view_counts