CloudSearch/cloudsearch_transfer/adapter/aliyun/cleanup.py

"""
阿里云盘回收站清理模块 v1.0.0
将文件移入回收站（非直接删除），支持批量操作。
"""

import logging
from typing import List, Dict

import requests

from .credential import AliyunCredentialManager, API_HOST

logger = logging.getLogger(__name__)

# ─── API 端点 ──────────────────────────────────────────────

# 批量操作（v4）
BATCH_URL = f"{API_HOST}/adrive/v4/batch"

# 默认请求头
DEFAULT_HEADERS = {
    "User-Agent": (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
        "AppleWebKit/537.36 (KHTML, like Gecko) "
        "Chrome/135.0.0.0 Safari/537.36"
    ),
    "Accept": "application/json, text/plain, */*",
    "Content-Type": "application/json",
    "Referer": "https://aliyundrive.com",
}


class AliyunCleanup:
    """
    阿里云盘回收站清理

    将文件移入回收站（放入回收站，非永久删除）。
    使用 v4 批量接口，支持一次清理多个文件。

    用法:
        credential = AliyunCredentialManager(refresh_token="xxx")
        cleanup = AliyunCleanup(credential, drive_id="12345")
        result = cleanup.delete_files(["file_id_1", "file_id_2"])
    """

    def __init__(
        self,
        credential: AliyunCredentialManager,
        drive_id: str = "",
        request_timeout: int = 30,
    ):
        self.credential = credential
        self.drive_id = drive_id or credential.get_drive_id()
        self.request_timeout = request_timeout
        self._session = requests.Session()
        self._session.headers.update(DEFAULT_HEADERS)

    # ─── 公开 API ──────────────────────────────────────────

    def delete_files(self, file_ids: List[str]) -> Dict:
        """
        将指定文件移入回收站（批量）。

        Args:
            file_ids: 要删除的文件 ID 列表

        Returns:
            {
                "success": True/False,
                "deleted_count": 成功删除数量,
                "total_count": 总文件数,
                "failed_ids": 失败的文件 ID 列表,
                "error": None or "错误信息",
            }

        实现:
            POST /adrive/v4/batch
            {
                "requests": [
                    {
                        "url": "/recyclebin/trash",
                        "body": {"file_id": "...", "drive_id": "..."},
                        "headers": {"Content-Type": "application/json"},
                        "id": "...",
                        "method": "POST"
                    }
                ],
                "resource": "file"
            }
        """
        if not file_ids:
            return self._error("文件 ID 列表为空")

        drive_id = self.drive_id
        if not drive_id:
            drive_id = self.credential.get_drive_id()
        if not drive_id:
            return self._error("缺少 drive_id，无法执行删除操作")

        # 构建批量请求体
        requests_list = []
        for fid in file_ids:
            requests_list.append({
                "url": "/recyclebin/trash",
                "body": {
                    "drive_id": drive_id,
                    "file_id": fid,
                },
                "headers": {"Content-Type": "application/json"},
                "id": fid,
                "method": "POST",
            })

        try:
            headers = self.credential.get_headers()

            resp = self._session.post(
                BATCH_URL,
                json={"requests": requests_list, "resource": "file"},
                headers=headers,
                timeout=self.request_timeout,
            )
            data = resp.json()

            if resp.status_code != 200:
                logger.error(
                    f"[AliyunCleanup] 批量删除失败: "
                    f"HTTP {resp.status_code}, {data}"
                )
                return self._error(f"HTTP {resp.status_code}")

            code = data.get("code", "")
            if code:
                logger.error(
                    f"[AliyunCleanup] 批量删除 API 错误: "
                    f"code={code}, message={data.get('message', '')}"
                )
                return self._error(data.get("message", f"API code={code}"))

            # 统计结果
            responses = data.get("responses", [])
            success_ids = []
            failed_ids = []

            for item in responses:
                status = item.get("status", 0)
                fid = item.get("id", "")
                if status in (200, 201, 202):
                    success_ids.append(fid)
                else:
                    logger.warning(
                        f"[AliyunCleanup] 删除文件失败: "
                        f"id={fid}, status={status}, body={item.get('body', {})}"
                    )
                    failed_ids.append(fid)

            logger.info(
                f"[AliyunCleanup] 删除完成: "
                f"成功={len(success_ids)}, 失败={len(failed_ids)}, 总计={len(file_ids)}"
            )

            return {
                "success": len(failed_ids) == 0,
                "deleted_count": len(success_ids),
                "total_count": len(file_ids),
                "success_ids": success_ids,
                "failed_ids": failed_ids,
                "error": None,
            }

        except requests.RequestException as e:
            logger.error(f"[AliyunCleanup] 批量删除网络异常: {e}")
            return self._error(str(e))
        except Exception as e:
            logger.exception(f"[AliyunCleanup] 批量删除异常: {e}")
            return self._error(str(e))

    def empty_recycle_bin(self) -> Dict:
        """
        清空回收站（永久删除回收站中的所有文件）。

        NOTE: 阿里云盘 API 目前不直接支持清空回收站，
        此方法作为占位，需要逐个文件 ID 调用 delete_files。
        实际使用请先 list 回收站内容再调用 delete_files。

        Returns:
            {"success": False, "error": "清空回收站需要通过 list + delete 两步完成"}
        """
        logger.warning("[AliyunCleanup] 清空回收站 API 暂未实现，需要 list+delete 两步")
        return self._error("清空回收站需要通过列出回收站内容 + 逐个删除两步完成，尚未实现")

    # ─── 工具方法 ──────────────────────────────────────────

    def _error(self, message: str) -> Dict:
        """构造错误返回"""
        return {
            "success": False,
            "deleted_count": 0,
            "total_count": 0,
            "success_ids": [],
            "failed_ids": [],
            "error": message,
        }