tests/test_ingest.py

"""Tests for ``/ingest`` upload, URL ingest, and collection management."""

import asyncio
from unittest.mock import AsyncMock

from api.routes import ingest as ingest_route
from storage.job_store import create_ingest_job, mark_job_processing


def test_upload_queues_job_success(client, monkeypatch):
    monkeypatch.setattr("api.routes.ingest.create_ingest_job", AsyncMock(return_value="job-123"))
    monkeypatch.setattr("api.routes.ingest.run_ingest_job", AsyncMock(return_value=None))

    response = client.post(
        "/ingest/upload",
        data={"collection_name": "default"},
        files=[("files", ("sample.txt", b"hello world", "text/plain"))],
    )

    assert response.status_code == 200
    body = response.json()
    assert body["status"] == "queued"
    assert body["job_id"] == "job-123"
    assert body["total_files"] == 1
    assert body["filenames"] == ["sample.txt"]
    assert "Poll /jobs/job-123" in body["message"]


def test_upload_rejects_unsupported_extension(client):
    response = client.post(
        "/ingest/upload",
        data={"collection_name": "default"},
        files=[("files", ("sample.csv", b"a,b\n1,2", "text/csv"))],
    )

    assert response.status_code == 400
    assert "Unsupported file type" in response.json()["detail"]


def test_upload_rejects_oversized_file(client):
    oversized = b"x" * (2 * 1024 * 1024)
    response = client.post(
        "/ingest/upload",
        data={"collection_name": "default"},
        files=[("files", ("large.txt", oversized, "text/plain"))],
    )

    assert response.status_code == 413
    assert "too large" in response.json()["detail"].lower()


def test_upload_returns_500_on_job_creation_error(client, monkeypatch):
    monkeypatch.setattr(
        "api.routes.ingest.create_ingest_job",
        AsyncMock(side_effect=RuntimeError("job store unavailable")),
    )
    monkeypatch.setattr("api.routes.ingest.run_ingest_job", AsyncMock(return_value=None))

    response = client.post(
        "/ingest/upload",
        data={"collection_name": "default"},
        files=[("files", ("sample.txt", b"hello", "text/plain"))],
    )

    assert response.status_code == 500
    assert "job store unavailable" in response.json()["detail"]


def test_download_request_headers_sec_compliant():
    headers = ingest_route._download_request_headers("DocuAudit AI test@example.com")
    assert headers["User-Agent"] == "DocuAudit AI test@example.com"
    assert headers["Accept-Encoding"] == "gzip, deflate"
    assert "application/pdf" in headers["Accept"]


def test_ingest_url_rejects_non_http_scheme(client, monkeypatch):
    monkeypatch.setattr(
        "api.routes.ingest._download_url_to_temp",
        AsyncMock(
            side_effect=ingest_route.HTTPException(status_code=400, detail="Only http and https URLs are supported.")
        ),
    )

    response = client.post(
        "/ingest/url",
        json={"urls": ["https://example.com/file.txt"], "collection_name": "default"},
    )

    assert response.status_code == 400
    assert "http and https" in response.json()["detail"]


def test_upload_pdf_queues_job_with_job_id(client, monkeypatch):
    """Spec: single PDF upload returns job_id."""
    monkeypatch.setattr("api.routes.ingest.create_ingest_job", AsyncMock(return_value="pdf-job-99"))
    monkeypatch.setattr("api.routes.ingest.run_ingest_job", AsyncMock(return_value=None))

    response = client.post(
        "/ingest/upload",
        data={"collection_name": "default"},
        files=[("files", ("brief.pdf", b"%PDF-1.4 minimal", "application/pdf"))],
    )

    assert response.status_code == 200
    body = response.json()
    assert body["job_id"] == "pdf-job-99"
    assert body["filenames"] == ["brief.pdf"]


def test_list_collections_backfills_created_at_from_jobs(client, test_settings, monkeypatch):
    monkeypatch.setattr(
        "api.routes.ingest.list_collection_names",
        lambda *_: ["default"],
    )
    monkeypatch.setattr("api.routes.ingest.collection_document_count", lambda *_: 3)
    monkeypatch.setattr("api.routes.ingest.collection_created_at", lambda *_: None)
    monkeypatch.setattr(
        "api.routes.ingest.earliest_job_created_at_for_collection",
        AsyncMock(return_value="2026-05-21 07:05:38"),
    )
    monkeypatch.setattr(
        "api.routes.ingest.ensure_collection_created_at",
        lambda *_a, **_k: "2026-05-21T07:05:38Z",
    )

    response = client.get("/ingest/collections")
    assert response.status_code == 200
    body = response.json()
    assert body["total"] == 1
    assert body["collections"][0]["name"] == "default"
    assert body["collections"][0]["document_count"] == 3
    assert body["collections"][0]["created_at"] is not None


def test_job_status_polling_after_real_job_create(client, test_settings):
    """Spec: job status polling returns correct structure."""
    job_id = asyncio.run(
        create_ingest_job(
            test_settings.jobs_db_path,
            collection_name="default",
            filenames=["sample.txt"],
        )
    )
    asyncio.run(mark_job_processing(test_settings.jobs_db_path, job_id))

    response = client.get(f"/jobs/{job_id}")
    assert response.status_code == 200
    body = response.json()
    assert body["job_id"] == job_id
    assert body["status"] == "processing"
    assert body["total_files"] == 1
    assert "progress_percent" in body
    assert "errors" in body