QMDSearch/tests/test_ingest_task_api.py

"""入库异步任务 API 测试（TestClient + FakeManager，不真实联网）"""

from collections.abc import Iterator
from typing import Any

import pytest
from fastapi.testclient import TestClient

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


class FakeManager:
    """假入库任务管理器：记录 submit 调用，按 task_id 返回预置任务"""

    def __init__(self, tasks: dict[str, dict[str, Any]] | None = None, task_id: str = "task-1") -> None:
        self.tasks = tasks or {}
        self.task_id = task_id
        self.submitted: list[DocumentInput] = []

    async def submit(self, doc: DocumentInput) -> str:
        self.submitted.append(doc)
        return self.task_id

    async def get(self, task_id: str) -> dict[str, Any] | None:
        return self.tasks.get(task_id)


def _task(task_id: str, status: str, **extra: Any) -> dict[str, Any]:
    """构造一条任务记录（时间字段为固定 ISO8601 字符串）"""
    record: dict[str, Any] = {
        "task_id": task_id,
        "status": status,
        "created_at": "2026-07-29T08:00:00+00:00",
        "updated_at": "2026-07-29T08:00:01+00:00",
        "result": None,
        "error": None,
    }
    record.update(extra)
    return record


@pytest.fixture
def client(monkeypatch: pytest.MonkeyPatch, admin_headers: dict[str, str]) -> Iterator[TestClient]:
    """TestClient，lifespan 中的 Qdrant 集合初始化替换为空操作；默认携带 admin 认证头"""

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

    monkeypatch.setattr(QdrantService, "ensure_collections", _noop_ensure_collections)
    with TestClient(app) as test_client:
        test_client.headers.update(admin_headers)
        yield test_client


def _inject_manager(monkeypatch: pytest.MonkeyPatch, manager: FakeManager) -> None:
    """将 FakeManager 注入路由的 _get_task_manager"""
    monkeypatch.setattr(document_module, "_get_task_manager", lambda: manager)


def test_post_documents_returns_202(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """POST /documents：HTTP 202，data.task_id 非空且 status=pending，文档已提交给管理器"""
    manager = FakeManager(task_id="abc123")
    _inject_manager(monkeypatch, manager)

    resp = client.post("/api/v1/documents", json={"text": "正文内容", "title": "标题"})

    assert resp.status_code == 202
    body = resp.json()
    assert body["code"] == 0
    assert body["data"]["task_id"] == "abc123"
    assert body["data"]["status"] == "pending"
    assert len(manager.submitted) == 1


def test_get_task_pending(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """GET tasks/{id}：进行中任务 → code=0，含 status/created_at/updated_at"""
    manager = FakeManager(tasks={"t-pending": _task("t-pending", "summarizing")})
    _inject_manager(monkeypatch, manager)

    resp = client.get("/api/v1/documents/tasks/t-pending")

    body = resp.json()
    assert body["code"] == 0
    data = body["data"]
    assert data["task_id"] == "t-pending"
    assert data["status"] == "summarizing"
    assert data["created_at"]
    assert data["updated_at"]
    assert data["result"] is None
    assert data["error"] is None


def test_get_task_done(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """GET tasks/{id}：done 任务 → data.result 含 document_id"""
    result = {
        "document_id": "doc-1",
        "summary": {"l1_summary": "一句话", "l2_outline": None, "l3_content_outline": "大纲", "level": "L3"},
        "category": "技术文档",
        "collection": "四层集合",
        "chunks_count": 3,
        "tags": ["API"],
        "category_confidence": 0.9,
    }
    manager = FakeManager(tasks={"t-done": _task("t-done", "done", result=result)})
    _inject_manager(monkeypatch, manager)

    resp = client.get("/api/v1/documents/tasks/t-done")

    body = resp.json()
    assert body["code"] == 0
    data = body["data"]
    assert data["status"] == "done"
    assert data["result"]["document_id"] == "doc-1"
    assert data["result"]["chunks_count"] == 3
    assert data["error"] is None


def test_get_task_failed(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """GET tasks/{id}：failed 任务 → data.error 含 stage/message/partial_summary"""
    partial = {"l1_summary": "L1", "l2_outline": None, "l3_content_outline": "L3", "level": "L3"}
    error = {"stage": "embed", "message": "向量化失败: boom", "partial_summary": partial}
    manager = FakeManager(tasks={"t-failed": _task("t-failed", "failed", error=error)})
    _inject_manager(monkeypatch, manager)

    resp = client.get("/api/v1/documents/tasks/t-failed")

    body = resp.json()
    assert body["code"] == 0
    data = body["data"]
    assert data["status"] == "failed"
    assert data["error"]["stage"] == "embed"
    assert "boom" in data["error"]["message"]
    assert data["error"]["partial_summary"] == partial
    assert data["result"] is None


def test_get_task_not_found(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """GET tasks/{id}：不存在的 task_id → code=1004"""
    _inject_manager(monkeypatch, FakeManager())

    resp = client.get("/api/v1/documents/tasks/不存在")

    body = resp.json()
    assert body["code"] == 1004
    assert body["message"] == "任务不存在"
    assert body["data"] is None


def test_post_empty_text_creates_no_task(client: TestClient, monkeypatch: pytest.MonkeyPatch) -> None:
    """POST 空文本：code=1001，且不产生任务（submit 未被调用）"""
    manager = FakeManager()
    _inject_manager(monkeypatch, manager)

    resp = client.post("/api/v1/documents", json={"text": "   "})

    body = resp.json()
    assert body["code"] == 1001
    assert manager.submitted == []