QMDSearch/tests/test_document_file_api.py

"""GET /api/v1/documents/{doc_id}/file 文件下载端点测试（TestClient + FakeQdrant，不真实联网）

覆盖分支：成功下载、文档不存在、无关联文件、文件已从磁盘删除、路径越界、免登录访问。
"""

from collections.abc import Iterator
from pathlib import Path

import pytest
from fastapi.testclient import TestClient

from app.api.v1 import document as document_module
from app.main import app
from app.services.qdrant import QdrantService


class FakeQdrant:
    """假 QdrantService：仅实现 get_l1_metadata，按 doc_id 返回固定 metadata 或 None"""

    def __init__(self, meta: dict[str, str] | None = None) -> None:
        self.meta = meta

    async def get_l1_metadata(self, doc_id: str) -> dict[str, str] | None:
        return self.meta


@pytest.fixture
def client(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> Iterator[TestClient]:
    """TestClient，Qdrant 集合初始化空操作；upload_dir 指向临时目录

    不挂 admin_headers：下载端点免登录，验证无 token 可访问。
    """

    async def _noop_ensure_collections(self: QdrantService) -> None:
        return None

    monkeypatch.setattr(QdrantService, "ensure_collections", _noop_ensure_collections)
    monkeypatch.setattr(document_module.settings, "upload_dir", str(tmp_path / "uploads"))
    with TestClient(app) as test_client:
        yield test_client


def _install_fake(monkeypatch: pytest.MonkeyPatch, fake: FakeQdrant) -> None:
    """将 _get_qdrant 单例替换为假服务"""
    monkeypatch.setattr(document_module, "_get_qdrant", lambda: fake)


def test_download_file_success(
    client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """文档存在且有关联文件 → 200 + 文件内容正确 + content-disposition 含文件名"""
    upload_dir = tmp_path / "uploads"
    upload_dir.mkdir(parents=True, exist_ok=True)
    target = upload_dir / "doc-1_notes.txt"
    content = b"hello world file content"
    target.write_bytes(content)

    fake = FakeQdrant(
        meta={
            "raw_file_path": str(target),
            "original_filename": "notes.txt",
            "original_size_bytes": str(len(content)),
        }
    )
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    assert resp.status_code == 200
    assert resp.content == content
    disposition = resp.headers.get("content-disposition", "")
    assert "attachment" in disposition
    assert "notes.txt" in disposition


def test_download_file_doc_not_found(
    client: TestClient, monkeypatch: pytest.MonkeyPatch
) -> None:
    """文档不存在（metadata 为 None）→ 1004"""
    fake = FakeQdrant(meta=None)
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/missing/file")

    body = resp.json()
    assert body["code"] == 1004
    assert "文件" in body["message"]


def test_download_file_no_associated_file(
    client: TestClient, monkeypatch: pytest.MonkeyPatch
) -> None:
    """文档存在但 raw_file_path 为空 → 1004"""
    fake = FakeQdrant(meta={"raw_file_path": "", "original_filename": "x.txt"})
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    body = resp.json()
    assert body["code"] == 1004
    assert "未关联文件" in body["message"]


def test_download_file_missing_on_disk(
    client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """文件已从磁盘删除（path.is_file() False）→ 1004"""
    missing = tmp_path / "uploads" / "gone.txt"
    fake = FakeQdrant(meta={"raw_file_path": str(missing), "original_filename": "gone.txt"})
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    body = resp.json()
    assert body["code"] == 1004
    assert "文件不存在" in body["message"]


def test_download_file_path_traversal_rejected(
    client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """raw_file_path 指向 upload_dir 之外 → 1004（路径越界校验）"""
    outside = tmp_path / "secret.txt"
    outside.write_bytes(b"secret")

    fake = FakeQdrant(meta={"raw_file_path": str(outside), "original_filename": "secret.txt"})
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    body = resp.json()
    assert body["code"] == 1004
    assert "文件不存在" in body["message"]


def test_download_file_no_auth_required(
    client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """免登录：不携带 Authorization 头可正常下载（端点不挂鉴权依赖）"""
    upload_dir = tmp_path / "uploads"
    upload_dir.mkdir(parents=True, exist_ok=True)
    target = upload_dir / "doc-1_open.txt"
    target.write_bytes(b"open content")

    fake = FakeQdrant(meta={"raw_file_path": str(target), "original_filename": "open.txt"})
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    assert resp.status_code == 200
    assert resp.content == b"open content"


def test_download_file_uses_original_filename_when_missing(
    client: TestClient, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
) -> None:
    """metadata 缺少 original_filename 时回退到 path.name 作为下载文件名"""
    upload_dir = tmp_path / "uploads"
    upload_dir.mkdir(parents=True, exist_ok=True)
    target = upload_dir / "fallback_name.txt"
    target.write_bytes(b"fb")

    fake = FakeQdrant(meta={"raw_file_path": str(target)})
    _install_fake(monkeypatch, fake)

    resp = client.get("/api/v1/documents/doc-1/file")

    assert resp.status_code == 200
    assert "fallback_name.txt" in resp.headers.get("content-disposition", "")