zTools2/app/controllers/file_admin_controller.py

"""文件管理接口（Basic Auth，鉴权同 docs）。

与公开的 /api/files 区分：本路由面向「文件浏览页」，提供列表 / 查询 / 下载 / 删除，
均需 docs 凭据。公开路由（user.py 依赖的查重、查询、下载）保留不变。

硬删除策略：删 DB 行 + 删磁盘文件（unlink missing_ok），列表只展示仍存在的行。
"""

from __future__ import annotations

from fastapi import APIRouter, Depends, HTTPException, Query
from fastapi.responses import FileResponse
from pydantic import BaseModel, Field
from sqlalchemy.orm import Session

from ..database import get_db
from ..dao.pdf_job_dao import PdfJobDAO
from ..dao.uploaded_file_dao import UploadedFileDAO
from ..schemas.file import (
    FileListResponse,
    FileWithPdfListResponse,
    PdfJobBrief,
    UploadedFileOut,
    UploadedFileWithPdfOut,
)
from ..security import require_docs_auth
from ..services.upload_service import UploadService

router = APIRouter(prefix="/api/admin/files", tags=["files-admin"])


def _service(db: Session = Depends(get_db)) -> UploadService:
    return UploadService(UploadedFileDAO(db))


class DeleteResult(BaseModel):
    deleted: bool


class BatchDeleteRequest(BaseModel):
    ids: list[int] = Field(..., description="要删除的文件 id 列表")


class BatchDeleteResult(BaseModel):
    deleted: int = Field(..., description="实际删除的条数")
    not_found: list[int] = Field(default_factory=list, description="未找到的 id")


@router.get(
    "",
    response_model=FileListResponse,
    summary="列出已上传文件（需鉴权）",
    description="供文件浏览页使用；字段同公开 /api/files，但要求 docs Basic Auth。支持分页。"
    "返回前会触发磁盘扫描（频率限制 3s），把 SFTP 上传但未入库的文件补录进来。",
)
def list_files(
    limit: int = Query(100, ge=1, le=10000, description="每页条数，1-10000"),
    offset: int = Query(0, ge=0, description="偏移量"),
    service: UploadService = Depends(_service),
    _: str = Depends(require_docs_auth),
) -> FileListResponse:
    service.scan_sftp_files()  # 频率限制内置：3s 内重复只返回 DB 缓存
    total, items = service.list_files(limit=limit, offset=offset)
    return FileListResponse(total=total, items=items)


@router.get(
    "/with-pdf",
    response_model=FileWithPdfListResponse,
    summary="列出已上传文件并附带 PDF 转换任务关联（需鉴权）",
    description=(
        "合并管理页使用：以 uploaded_files 为基础分页拉取，再内存匹配 pdf_jobs，"
        "为每个文件附带它作为 PDF 任务「源文件(epub)」或「产物(PDF)」时的状态、"
        "进度与用户软删标记。匹配键为 pdf_job.source_file_id / output_file_id -> uploaded_file.id。"
        "返回前会触发磁盘扫描（频率限制 3s），把 SFTP 上传但未入库的文件补录进来。"
    ),
)
def list_files_with_pdf(
    limit: int = Query(100, ge=1, le=10000, description="每页条数，1-10000"),
    offset: int = Query(0, ge=0, description="偏移量"),
    service: UploadService = Depends(_service),
    db: Session = Depends(get_db),
    _: str = Depends(require_docs_auth),
) -> FileWithPdfListResponse:
    service.scan_sftp_files()  # 频率限制内置：3s 内重复只返回 DB 缓存
    total, items = service.list_files(limit=limit, offset=offset)

    # 拉全部 pdf_jobs（数据量小，不分页），建反查 map
    jobs = PdfJobDAO(db).list_all(limit=10000, offset=0)
    by_source: dict[int, list] = {}
    by_output: dict[int, list] = {}
    for j in jobs:
        by_source.setdefault(j.source_file_id, []).append(j)
        if j.output_file_id is not None:
            by_output.setdefault(j.output_file_id, []).append(j)

    out_items: list[UploadedFileWithPdfOut] = []
    for f in items:
        briefs: list[PdfJobBrief] = []
        for j in by_source.get(f.id, []):
            briefs.append(PdfJobBrief(
                job_id=j.id, role="source", status=j.status,
                progress=j.progress, user_deleted=j.user_deleted, deleted_at=j.deleted_at,
            ))
        for j in by_output.get(f.id, []):
            briefs.append(PdfJobBrief(
                job_id=j.id, role="output", status=j.status,
                progress=j.progress, user_deleted=j.user_deleted, deleted_at=j.deleted_at,
            ))
        out_items.append(UploadedFileWithPdfOut(**f.model_dump(), pdf_jobs=briefs))
    return FileWithPdfListResponse(total=total, items=out_items)


@router.post(
    "/batch-delete",
    response_model=BatchDeleteResult,
    summary="批量硬删除文件（需鉴权）",
    description="一次删除多个文件；返回实际删除条数与未命中的 id 列表。",
)
def batch_delete_files(
    body: BatchDeleteRequest,
    service: UploadService = Depends(_service),
    _: str = Depends(require_docs_auth),
) -> BatchDeleteResult:
    if not body.ids:
        raise HTTPException(400, "ids 不能为空")
    deleted = 0
    not_found: list[int] = []
    for fid in body.ids:
        ok = service.delete_file(fid)
        if ok:
            deleted += 1
        else:
            not_found.append(fid)
    return BatchDeleteResult(deleted=deleted, not_found=not_found)


@router.get(
    "/{file_id}",
    response_model=UploadedFileOut,
    summary="查询单个文件元数据（需鉴权）",
)
def get_file(
    file_id: int,
    service: UploadService = Depends(_service),
    _: str = Depends(require_docs_auth),
) -> UploadedFileOut:
    out = service.get_out(file_id)
    if out is None:
        raise HTTPException(404, "文件不存在")
    return out


@router.get(
    "/{file_id}/download",
    summary="下载文件（需鉴权，校验磁盘存在）",
    description="文件实体不在磁盘上时返回 410 Gone。",
)
def download_file(
    file_id: int,
    service: UploadService = Depends(_service),
    _: str = Depends(require_docs_auth),
) -> FileResponse:
    out, path = service.get_out_with_disk_path(file_id)
    if out is None:
        raise HTTPException(404, "文件不存在")
    if path is None or not path.exists():
        raise HTTPException(410, "文件实体已不在磁盘上")
    return FileResponse(
        path=str(path),
        media_type=out.content_type or "application/octet-stream",
        filename=out.original_filename,
    )


@router.delete(
    "/{file_id}",
    response_model=DeleteResult,
    summary="硬删除文件（需鉴权）",
    description="删除 DB 行与磁盘文件实体；不可恢复。列表随后不再显示。",
)
def delete_file(
    file_id: int,
    service: UploadService = Depends(_service),
    _: str = Depends(require_docs_auth),
) -> DeleteResult:
    return DeleteResult(deleted=service.delete_file(file_id))