import sqlite3
import json
import os
from collections import defaultdict

def process_daily_summary(log_paths):
    summary = defaultdict(lambda: {
        'total_count': 0,
        'first_hour': None,
        'hourly_counts': {},
        'log_content': None
    })

    # 按文件名排序确保时间顺序
    sorted_files = sorted(log_paths, key=lambda x: os.path.basename(x))

    for file_path in sorted_files:
        # 提取小时部分
        filename = os.path.basename(file_path)
        hour = filename.split('.')[0][-2:]

        try:
            conn = sqlite3.connect(file_path)
            cursor = conn.cursor()
            cursor.execute('SELECT component, level, position, sample as log_content, count FROM log_stats')
            rows = cursor.fetchall()
            conn.close()
        except Exception as e:
            print(f"Error processing {file_path}: {str(e)}")
            continue

        for component, level, position, log_content, count in rows:
            key = (component, level, position)
            entry = summary[key]

            # 首次出现时记录时间和内容
            if not entry['first_hour']:
                entry['first_hour'] = hour
                entry['log_content'] = log_content

            # 累加总数
            entry['total_count'] += count

            # 记录每小时的数量（直接覆盖，保证每个小时只保留最新记录）
            entry['hourly_counts'][hour] = count

    # 计算总数和比例
    total_all = sum(entry['total_count'] for entry in summary.values())
    result = []

    for key in summary:
        component, level, position = key
        entry = summary[key]

        # 找出最大出现次数的小时
        max_count = max(entry['hourly_counts'].values(), default=0)
        max_hours = [h for h, c in entry['hourly_counts'].items() if c == max_count]
        most_frequent_hour = max(max_hours) if max_hours else None

        result.append({
            'component': component,
            'level': level,
            'position': position,
            'total': entry['total_count'],
            'ratio': entry['total_count'] / total_all,
            'first_hour': entry['first_hour'],
            'most_frequent_hour': most_frequent_hour,
            'log_content': entry['log_content']
        })

    return result

def process_eigenvalue(historical_files, today_data):
    # 读取历史数据
    history_totals = defaultdict(int)

    # 处理过去7天文件
    for h_file in historical_files:
        try:
            with open(h_file, 'r') as f:
                data = json.load(f)
                for entry in data:
                    key = (entry["component"], entry["level"], entry["position"])
                    history_totals[key] += entry["total"]
        except Exception as e:
            print(f"Error processing {h_file}: {str(e)}")

    # 添加标记
    for entry in today_data:
        key = (entry["component"], entry["level"], entry["position"])
        total = entry["total"]

        # 初始化标记
        tags = []

        # 标记1：过去7天未出现
        is_new = key not in history_totals
        if is_new:
            tags.append("new")

        # 标记2：超过历史平均值的两倍
        history_sum = history_totals.get(key, 0)
        history_avg = history_sum / 7  # 过去7天平均值
        if total > 2 * history_avg:
            tags.append("surge")

        entry["tags"] = tags

    return today_data