ylt_diy/lib/api/download_api.py

"""
文件下载 API
"""
import os
import zipfile
from datetime import datetime
from flask import request, jsonify, send_from_directory
from lib.db import execute_query
from lib.logger import log_info, log_error, log_warning
from . import download_bp


def get_reports_dir():
    """获取报表文件目录"""
    return os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))), 'public', 'reports')


def get_temp_dir():
    """获取临时zip文件目录"""
    temp_dir = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))), 'public', 'temp_zip')
    os.makedirs(temp_dir, exist_ok=True)
    return temp_dir


def cleanup_old_temp_zips():
    """清理1小时前的临时zip文件"""
    try:
        temp_dir = get_temp_dir()
        now = datetime.now().timestamp()
        count = 0
        for filename in os.listdir(temp_dir):
            if filename.endswith('.zip'):
                filepath = os.path.join(temp_dir, filename)
                if now - os.path.getmtime(filepath) > 3600:  # 1小时前的
                    os.remove(filepath)
                    count += 1
        if count > 0:
            log_info(f'[下载API] 清理了 {count} 个过期临时zip文件', 'download')
    except Exception as e:
        log_error(f'[下载API] 清理临时文件失败: {e}', 'download')


@download_bp.route('/download', methods=['GET'])
def download_file():
    """下载文件
    支持两种方式：
    1. path: 直接传文件路径
    2. id: 传历史记录ID，从数据库查询文件路径
    """
    try:
        file_path = request.args.get('path')
        history_id = request.args.get('id')
        
        log_info(f'[下载API] 请求，path={file_path}, id={history_id}', 'download')
        
        # 如果传了id，从历史记录表查询文件路径
        if history_id:
            result = execute_query(
                'SELECT file_path, status FROM t_daily_report_history WHERE id = %s LIMIT 1',
                (history_id,)
            )
            if not result:
                log_error(f'[下载API] 历史记录不存在，id={history_id}', 'download')
                return jsonify({'success': False, 'message': '历史记录不存在'}), 404
            
            history = result[0]
            if history.get('status') != 1:
                log_error(f'[下载API] 生成失败的记录无法下载，id={history_id}', 'download')
                return jsonify({'success': False, 'message': '该记录生成失败，无法下载'}), 400
            
            file_path = history.get('file_path')
            if not file_path:
                log_error(f'[下载API] 文件路径为空，id={history_id}', 'download')
                return jsonify({'success': False, 'message': '文件路径不能为空'}), 400
            
            log_info(f'[下载API] 从历史记录查询到文件路径: {file_path}', 'download')
        
        if not file_path:
            return jsonify({'success': False, 'message': '文件路径不能为空'}), 400
        
        # 安全检查：确保路径在 public/reports 目录下
        if not file_path.startswith('/reports/') and not file_path.startswith('/public/reports/'):
            return jsonify({'success': False, 'message': '无效的文件路径'}), 400
        
        # 提取文件名
        if file_path.startswith('/public/reports/'):
            filename = file_path.replace('/public/reports/', '')
        else:
            filename = file_path.replace('/reports/', '')
        
        reports_dir = get_reports_dir()
        full_path = os.path.join(reports_dir, filename)
        if not os.path.exists(full_path):
            log_error(f'[下载API] 文件不存在: {full_path}', 'download')
            return jsonify({'success': False, 'message': '文件不存在'}), 404
        
        log_info(f'[下载API] 下载文件: {filename}', 'download')
        return send_from_directory(reports_dir, filename, as_attachment=True)
    except Exception as e:
        log_error(f'[下载API] 错误: {e}', 'download')
        import traceback
        traceback.print_exc()
        return jsonify({'success': False, 'message': str(e)}), 500


@download_bp.route('/download/batch', methods=['POST'])
def batch_download():
    """批量打包下载
    接收 ids 数组，将对应的报表文件打包成zip后下载
    """
    try:
        data = request.get_json(silent=True) or {}
        ids = data.get('ids', [])
        
        log_info(f'[下载API] 批量下载，数量: {len(ids)}', 'download')
        
        if not ids or len(ids) == 0:
            return jsonify({'success': False, 'message': '请选择要下载的记录'}), 400
        
        # 清理旧的临时文件
        cleanup_old_temp_zips()
        
        # 查询所有成功的历史记录（附带筛选条件以增强安全性）
        placeholders = ', '.join(['%s'] * len(ids))
        result = execute_query(
            f'SELECT id, file_path, config_name, report_date, status, split_name FROM t_daily_report_history WHERE id IN ({placeholders})',
            tuple(ids)
        )
        
        if not result:
            return jsonify({'success': False, 'message': '未找到对应的历史记录'}), 404
        
        total_matched = len(result)
        success_records = [r for r in result if r.get('status') == 1]
        skipped_failed = total_matched - len(success_records)
        
        reports_dir = get_reports_dir()
        temp_dir = get_temp_dir()
        
        # 收集要打包的文件
        files_to_zip = []
        failed_names = []
        used_names = set()  # 检测 zip 内文件名冲突
        
        for item in success_records:
            file_path = item.get('file_path')
            if not file_path:
                failed_names.append(f"{item.get('config_name', '未知')} (无文件路径)")
                continue
            
            # 提取文件名
            if file_path.startswith('/public/reports/'):
                filename = file_path.replace('/public/reports/', '')
            elif file_path.startswith('/reports/'):
                filename = file_path.replace('/reports/', '')
            else:
                filename = os.path.basename(file_path)
            
            full_path = os.path.join(reports_dir, filename)
            if not os.path.exists(full_path):
                failed_names.append(f"{item.get('config_name', '未知')}_{item.get('report_date', '')} (文件不存在)")
                continue
            
            # 使用配置名+报表日期+拆分值作为zip内的文件名，避免重名
            config_name = item.get('config_name', '未知')
            report_date = item.get('report_date', '')
            split_name = item.get('split_name', '')
            ext = os.path.splitext(filename)[1] or '.xlsx'
            
            base_parts = [config_name]
            if report_date:
                base_parts.append(str(report_date))
            if split_name:
                base_parts.append(str(split_name))
            base_name = '_'.join(base_parts)
            zip_inner_name = f"{base_name}{ext}"
            
            # 处理文件名冲突：如果同名，追加记录ID
            if zip_inner_name in used_names:
                zip_inner_name = f"{base_name}_{item.get('id', '')}{ext}"
            used_names.add(zip_inner_name)
            
            files_to_zip.append({
                'full_path': full_path,
                'inner_name': zip_inner_name
            })
        
        if len(files_to_zip) == 0:
            return jsonify({'success': False, 'message': '没有可下载的文件'}), 400
        
        # 生成zip文件名
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        zip_filename = f'批量下载_{timestamp}.zip'
        zip_path = os.path.join(temp_dir, zip_filename)
        
        # 打包
        with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zf:
            for file_info in files_to_zip:
                zf.write(file_info['full_path'], file_info['inner_name'])
        
        log_info(f'[下载API] 批量打包完成，共 {len(files_to_zip)} 个文件，失败 {len(failed_names)} 个，跳过 {skipped_failed} 个失败记录', 'download')
        if failed_names:
            log_warning(f'[下载API] 缺失/无效文件列表: {failed_names[:20]}', 'download')
        
        # 返回zip文件，通过响应头返回统计信息
        from flask import send_file
        response = send_file(
            zip_path,
            as_attachment=True,
            download_name=zip_filename,
            mimetype='application/zip'
        )
        response.headers['X-Total-Matched'] = str(total_matched)
        response.headers['X-Files-Zipped'] = str(len(files_to_zip))
        response.headers['X-Files-Missing'] = str(len(failed_names))
        response.headers['X-Skipped-Failed'] = str(skipped_failed)
        return response
    except Exception as e:
        log_error(f'[下载API] 批量下载错误: {e}', 'download')
        import traceback
        traceback.print_exc()
        return jsonify({'success': False, 'message': str(e)}), 500


@download_bp.route('/download/batch-filter', methods=['POST'])
def batch_download_by_filter():
    """按筛选条件批量打包下载
    接收筛选条件（config_name, start_date, end_date, status），
    将所有匹配的成功记录的报表文件打包成zip后下载。
    与历史记录列表的搜索条件保持同步。
    """
    try:
        data = request.get_json(silent=True) or {}
        config_name = data.get('config_name', '').strip()
        start_date = data.get('start_date', '').strip()
        end_date = data.get('end_date', '').strip()
        status = data.get('status', '')
        
        log_info(f'[下载API] 按筛选批量下载，配置名称: {config_name or "全部"}，日期范围: {start_date or "开始"} ~ {end_date or "结束"}，状态: {status or "全部"}', 'download')
        
        # 清理旧的临时文件
        cleanup_old_temp_zips()
        
        # 构建查询条件（与历史记录列表查询条件完全一致）
        where_clauses = ['status = 1']  # 只下载成功的记录
        params = []
        
        if start_date:
            where_clauses.append('DATE(start_time) >= %s')
            params.append(start_date)
        
        if end_date:
            where_clauses.append('DATE(end_time) <= %s')
            params.append(end_date)
        
        # 注意：批量导出只导出成功记录（status=1），忽略用户传入的 status 筛选
        # 因为失败的记录没有文件可下载
        
        if config_name:
            where_clauses.append('config_name LIKE %s')
            params.append(f'%{config_name}%')
        
        where_sql = ' AND '.join(where_clauses)
        
        # 先查询总数，用于日志记录
        count_result = execute_query(
            f'SELECT COUNT(*) as total FROM t_daily_report_history WHERE {where_sql}',
            tuple(params)
        )
        total_matched = count_result[0]['total'] if count_result else 0
        log_info(f'[下载API] 按筛选匹配到 {total_matched} 条成功记录', 'download')
        
        # 查询所有匹配的成功记录（按报表日期正序排列，方便用户查看）
        result = execute_query(
            f'SELECT id, file_path, config_name, report_date, status, split_name FROM t_daily_report_history WHERE {where_sql} ORDER BY report_date ASC, config_name ASC, id ASC',
            tuple(params)
        )
        
        if not result:
            return jsonify({'success': False, 'message': '未找到符合条件的历史记录'}), 404
        
        reports_dir = get_reports_dir()
        temp_dir = get_temp_dir()
        
        # 收集要打包的文件
        files_to_zip = []
        failed_names = []
        used_names = set()  # 用于检测 zip 内文件名冲突
        
        for item in result:
            file_path = item.get('file_path')
            if not file_path:
                failed_names.append(f"{item.get('config_name', '未知')}_{item.get('report_date', '')} (无文件路径)")
                continue
            
            # 提取文件名
            if file_path.startswith('/public/reports/'):
                filename = file_path.replace('/public/reports/', '')
            elif file_path.startswith('/reports/'):
                filename = file_path.replace('/reports/', '')
            else:
                filename = os.path.basename(file_path)
            
            full_path = os.path.join(reports_dir, filename)
            if not os.path.exists(full_path):
                failed_names.append(f"{item.get('config_name', '未知')}_{item.get('report_date', '')} (文件不存在)")
                continue
            
            # 构建 zip 内文件名：配置名_报表日期（避免重名）
            config_name_val = item.get('config_name', '未知')
            report_date = item.get('report_date', '')
            split_name = item.get('split_name', '')
            ext = os.path.splitext(filename)[1] or '.xlsx'
            
            # 基础名称：配置名_报表日期
            base_parts = [config_name_val]
            if report_date:
                base_parts.append(str(report_date))
            if split_name:
                base_parts.append(str(split_name))
            base_name = '_'.join(base_parts)
            zip_inner_name = f"{base_name}{ext}"
            
            # 处理文件名冲突：如果同名，追加记录ID
            if zip_inner_name in used_names:
                zip_inner_name = f"{base_name}_{item.get('id', '')}{ext}"
            used_names.add(zip_inner_name)
            
            files_to_zip.append({
                'full_path': full_path,
                'inner_name': zip_inner_name
            })
        
        log_info(f'[下载API] 匹配 {total_matched} 条记录，成功打包 {len(files_to_zip)} 个文件，缺失 {len(failed_names)} 个文件', 'download')
        if failed_names:
            log_warning(f'[下载API] 缺失的文件列表: {failed_names[:20]}', 'download')
        
        if len(files_to_zip) == 0:
            return jsonify({'success': False, 'message': '没有可下载的文件（匹配的记录文件均不存在）'}), 400
        
        # 生成zip文件名
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        zip_filename = f'批量导出_{timestamp}.zip'
        zip_path = os.path.join(temp_dir, zip_filename)
        
        # 打包
        with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zf:
            for file_info in files_to_zip:
                zf.write(file_info['full_path'], file_info['inner_name'])
        
        log_info(f'[下载API] 按筛选批量打包完成，共 {len(files_to_zip)} 个文件，失败 {len(failed_names)} 个', 'download')
        
        # 返回zip文件，通过自定义头部返回统计信息
        from flask import send_file
        response = send_file(
            zip_path,
            as_attachment=True,
            download_name=zip_filename,
            mimetype='application/zip'
        )
        # 通过响应头返回统计信息，便于前端诊断
        response.headers['X-Total-Matched'] = str(total_matched)
        response.headers['X-Files-Zipped'] = str(len(files_to_zip))
        response.headers['X-Files-Missing'] = str(len(failed_names))
        return response
    except Exception as e:
        log_error(f'[下载API] 按筛选批量下载错误: {e}', 'download')
        import traceback
        traceback.print_exc()
        return jsonify({'success': False, 'message': str(e)}), 500


@download_bp.route('/download/batch-filter-count', methods=['POST'])
def batch_download_filter_count():
    """按筛选条件统计可导出的记录数
    在批量导出前调用，让用户确认导出范围。
    """
    try:
        data = request.get_json(silent=True) or {}
        config_name = data.get('config_name', '').strip()
        start_date = data.get('start_date', '').strip()
        end_date = data.get('end_date', '').strip()
        
        # 构建查询条件（与批量导出完全一致，只统计成功记录）
        where_clauses = ['status = 1']
        params = []
        
        if start_date:
            where_clauses.append('DATE(start_time) >= %s')
            params.append(start_date)
        
        if end_date:
            where_clauses.append('DATE(end_time) <= %s')
            params.append(end_date)
        
        if config_name:
            where_clauses.append('config_name LIKE %s')
            params.append(f'%{config_name}%')
        
        where_sql = ' AND '.join(where_clauses)
        
        # 统计总记录数
        count_result = execute_query(
            f'SELECT COUNT(*) as total FROM t_daily_report_history WHERE {where_sql}',
            tuple(params)
        )
        total = count_result[0]['total'] if count_result else 0
        
        # 统计日期范围
        date_range = execute_query(
            f'SELECT MIN(report_date) as min_date, MAX(report_date) as max_date FROM t_daily_report_history WHERE {where_sql}',
            tuple(params)
        )
        min_date = date_range[0]['min_date'] if date_range else None
        max_date = date_range[0]['max_date'] if date_range else None
        
        return jsonify({
            'success': True,
            'data': {
                'total': total,
                'min_date': str(min_date) if min_date else '',
                'max_date': str(max_date) if max_date else ''
            }
        })
    except Exception as e:
        log_error(f'[下载API] 统计可导出记录数错误: {e}', 'download')
        return jsonify({'success': False, 'message': str(e)}), 500