chrysopedia/backend/tests/test_search.py

"""Integration tests for the /api/v1/search endpoint.

Tests run against a real PostgreSQL test database via httpx.AsyncClient.
SearchService is mocked at the router dependency level so we can test
endpoint behavior without requiring external embedding API or Qdrant.
"""

from __future__ import annotations

import uuid
from unittest.mock import AsyncMock, MagicMock, patch

import pytest
import pytest_asyncio
from httpx import AsyncClient
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker

from models import (
    ContentType,
    Creator,
    KeyMoment,
    KeyMomentContentType,
    ProcessingStatus,
    SourceVideo,
    TechniquePage,
)
from search_service import SearchService

SEARCH_URL = "/api/v1/search"


# ── Seed helpers ─────────────────────────────────────────────────────────────


async def _seed_search_data(db_engine) -> dict:
    """Seed 2 creators, 3 technique pages, and 5 key moments for search tests.

    Returns a dict with creator/technique IDs and metadata for assertions.
    """
    session_factory = async_sessionmaker(
        db_engine, class_=AsyncSession, expire_on_commit=False
    )
    async with session_factory() as session:
        # Creators
        creator1 = Creator(
            name="Mr. Bill",
            slug="mr-bill",
            genres=["Bass music", "Glitch"],
            folder_name="MrBill",
        )
        creator2 = Creator(
            name="KOAN Sound",
            slug="koan-sound",
            genres=["Drum & bass", "Neuro"],
            folder_name="KOANSound",
        )
        session.add_all([creator1, creator2])
        await session.flush()

        # Videos (needed for key moments FK)
        video1 = SourceVideo(
            creator_id=creator1.id,
            filename="bass-design-101.mp4",
            file_path="MrBill/bass-design-101.mp4",
            duration_seconds=600,
            content_type=ContentType.tutorial,
            processing_status=ProcessingStatus.complete,
        )
        video2 = SourceVideo(
            creator_id=creator2.id,
            filename="reese-bass-deep-dive.mp4",
            file_path="KOANSound/reese-bass-deep-dive.mp4",
            duration_seconds=900,
            content_type=ContentType.tutorial,
            processing_status=ProcessingStatus.complete,
        )
        session.add_all([video1, video2])
        await session.flush()

        # Technique pages
        tp1 = TechniquePage(
            creator_id=creator1.id,
            title="Reese Bass Design",
            slug="reese-bass-design",
            topic_category="Sound design",
            topic_tags=["bass", "textures"],
            summary="How to create a classic reese bass",
        )
        tp2 = TechniquePage(
            creator_id=creator2.id,
            title="Granular Pad Textures",
            slug="granular-pad-textures",
            topic_category="Synthesis",
            topic_tags=["granular", "pads"],
            summary="Creating pad textures with granular synthesis",
        )
        tp3 = TechniquePage(
            creator_id=creator1.id,
            title="FM Bass Layering",
            slug="fm-bass-layering",
            topic_category="Synthesis",
            topic_tags=["fm", "bass"],
            summary="FM synthesis techniques for bass layering",
        )
        session.add_all([tp1, tp2, tp3])
        await session.flush()

        # Key moments
        km1 = KeyMoment(
            source_video_id=video1.id,
            technique_page_id=tp1.id,
            title="Setting up the Reese oscillator",
            summary="Initial oscillator setup for reese bass",
            start_time=10.0,
            end_time=60.0,
            content_type=KeyMomentContentType.technique,
        )
        km2 = KeyMoment(
            source_video_id=video1.id,
            technique_page_id=tp1.id,
            title="Adding distortion to the Reese",
            summary="Distortion processing chain for reese bass",
            start_time=60.0,
            end_time=120.0,
            content_type=KeyMomentContentType.technique,
        )
        km3 = KeyMoment(
            source_video_id=video2.id,
            technique_page_id=tp2.id,
            title="Granular engine settings",
            summary="Dialing in granular engine parameters",
            start_time=20.0,
            end_time=80.0,
            content_type=KeyMomentContentType.settings,
        )
        km4 = KeyMoment(
            source_video_id=video1.id,
            technique_page_id=tp3.id,
            title="FM ratio selection",
            summary="Choosing FM ratios for bass tones",
            start_time=5.0,
            end_time=45.0,
            content_type=KeyMomentContentType.technique,
        )
        km5 = KeyMoment(
            source_video_id=video2.id,
            title="Outro and credits",
            summary="End of the video",
            start_time=800.0,
            end_time=900.0,
            content_type=KeyMomentContentType.workflow,
        )
        session.add_all([km1, km2, km3, km4, km5])
        await session.commit()

        return {
            "creator1_id": str(creator1.id),
            "creator1_name": creator1.name,
            "creator1_slug": creator1.slug,
            "creator2_id": str(creator2.id),
            "creator2_name": creator2.name,
            "tp1_slug": tp1.slug,
            "tp1_title": tp1.title,
            "tp2_slug": tp2.slug,
            "tp3_slug": tp3.slug,
        }


# ── Tests ────────────────────────────────────────────────────────────────────


@pytest.mark.asyncio
async def test_search_happy_path_with_mocked_service(client, db_engine):
    """Search endpoint returns mocked results with correct response shape."""
    seed = await _seed_search_data(db_engine)

    # Mock the SearchService.search method to return canned results
    mock_result = {
        "items": [
            {
                "type": "technique_page",
                "title": "Reese Bass Design",
                "slug": "reese-bass-design",
                "summary": "How to create a classic reese bass",
                "topic_category": "Sound design",
                "topic_tags": ["bass", "textures"],
                "creator_name": "Mr. Bill",
                "creator_slug": "mr-bill",
                "score": 0.95,
            }
        ],
        "total": 1,
        "query": "reese bass",
        "fallback_used": False,
    }

    with patch("routers.search.SearchService") as MockSvc:
        instance = MockSvc.return_value
        instance.search = AsyncMock(return_value=mock_result)

        resp = await client.get(SEARCH_URL, params={"q": "reese bass"})

    assert resp.status_code == 200
    data = resp.json()
    assert data["query"] == "reese bass"
    assert data["total"] == 1
    assert data["fallback_used"] is False
    assert len(data["items"]) == 1

    item = data["items"][0]
    assert item["title"] == "Reese Bass Design"
    assert item["slug"] == "reese-bass-design"
    assert "score" in item


@pytest.mark.asyncio
async def test_search_empty_query_returns_empty(client, db_engine):
    """Empty search query returns empty results without hitting SearchService."""
    await _seed_search_data(db_engine)

    # With empty query, the search service returns empty results directly
    mock_result = {
        "items": [],
        "total": 0,
        "query": "",
        "fallback_used": False,
    }

    with patch("routers.search.SearchService") as MockSvc:
        instance = MockSvc.return_value
        instance.search = AsyncMock(return_value=mock_result)

        resp = await client.get(SEARCH_URL, params={"q": ""})

    assert resp.status_code == 200
    data = resp.json()
    assert data["items"] == []
    assert data["total"] == 0
    assert data["query"] == ""
    assert data["fallback_used"] is False


@pytest.mark.asyncio
async def test_search_keyword_fallback(client, db_engine):
    """When embedding fails, search uses keyword fallback and sets fallback_used=true."""
    seed = await _seed_search_data(db_engine)

    mock_result = {
        "items": [
            {
                "type": "technique_page",
                "title": "Reese Bass Design",
                "slug": "reese-bass-design",
                "summary": "How to create a classic reese bass",
                "topic_category": "Sound design",
                "topic_tags": ["bass", "textures"],
                "creator_name": "",
                "creator_slug": "",
                "score": 0.0,
            }
        ],
        "total": 1,
        "query": "reese",
        "fallback_used": True,
    }

    with patch("routers.search.SearchService") as MockSvc:
        instance = MockSvc.return_value
        instance.search = AsyncMock(return_value=mock_result)

        resp = await client.get(SEARCH_URL, params={"q": "reese"})

    assert resp.status_code == 200
    data = resp.json()
    assert data["fallback_used"] is True
    assert data["total"] >= 1
    assert data["items"][0]["title"] == "Reese Bass Design"


@pytest.mark.asyncio
async def test_search_scope_filter(client, db_engine):
    """Search with scope=topics returns only technique_page type results."""
    await _seed_search_data(db_engine)

    mock_result = {
        "items": [
            {
                "type": "technique_page",
                "title": "FM Bass Layering",
                "slug": "fm-bass-layering",
                "summary": "FM synthesis techniques for bass layering",
                "topic_category": "Synthesis",
                "topic_tags": ["fm", "bass"],
                "creator_name": "Mr. Bill",
                "creator_slug": "mr-bill",
                "score": 0.88,
            }
        ],
        "total": 1,
        "query": "bass",
        "fallback_used": False,
    }

    with patch("routers.search.SearchService") as MockSvc:
        instance = MockSvc.return_value
        instance.search = AsyncMock(return_value=mock_result)

        resp = await client.get(SEARCH_URL, params={"q": "bass", "scope": "topics"})

    assert resp.status_code == 200
    data = resp.json()
    # All items should be technique_page type when scope=topics
    for item in data["items"]:
        assert item["type"] == "technique_page"

    # Verify the service was called with scope=topics
    call_kwargs = instance.search.call_args
    assert call_kwargs.kwargs.get("scope") == "topics" or call_kwargs[1].get("scope") == "topics"


@pytest.mark.asyncio
async def test_search_no_matching_results(client, db_engine):
    """Search with no matching results returns empty items list."""
    await _seed_search_data(db_engine)

    mock_result = {
        "items": [],
        "total": 0,
        "query": "zzzznonexistent",
        "fallback_used": True,
    }

    with patch("routers.search.SearchService") as MockSvc:
        instance = MockSvc.return_value
        instance.search = AsyncMock(return_value=mock_result)

        resp = await client.get(SEARCH_URL, params={"q": "zzzznonexistent"})

    assert resp.status_code == 200
    data = resp.json()
    assert data["items"] == []
    assert data["total"] == 0


# ── SearchService.keyword_search integration tests ──────────────────────────


@pytest.mark.asyncio
async def test_keyword_search_technique_page_has_technique_page_slug(db_engine):
    """Keyword search for technique pages includes technique_page_slug matching its own slug."""
    seed = await _seed_search_data(db_engine)

    session_factory = async_sessionmaker(
        db_engine, class_=AsyncSession, expire_on_commit=False
    )
    async with session_factory() as session:
        from config import Settings
        svc = SearchService(settings=Settings())
        results = await svc.keyword_search("Reese Bass", "topics", 10, session)

    assert len(results) >= 1
    tp_result = next(r for r in results if r["type"] == "technique_page")
    assert tp_result["technique_page_slug"] == "reese-bass-design"
    assert tp_result["slug"] == "reese-bass-design"
    # technique_page_slug == slug for technique pages (they ARE the parent)
    assert tp_result["technique_page_slug"] == tp_result["slug"]


@pytest.mark.asyncio
async def test_keyword_search_key_moment_has_parent_technique_page_slug(db_engine):
    """Keyword search for key moments returns the parent technique page slug."""
    seed = await _seed_search_data(db_engine)

    session_factory = async_sessionmaker(
        db_engine, class_=AsyncSession, expire_on_commit=False
    )
    async with session_factory() as session:
        from config import Settings
        svc = SearchService(settings=Settings())
        results = await svc.keyword_search("Reese", "all", 20, session)

    km_results = [r for r in results if r["type"] == "key_moment"]
    assert len(km_results) >= 1
    for km in km_results:
        assert "technique_page_slug" in km
        # Both Reese-related key moments belong to tp1 (reese-bass-design)
        assert km["technique_page_slug"] == "reese-bass-design"


@pytest.mark.asyncio
async def test_keyword_search_key_moment_without_technique_page(db_engine):
    """Key moments without a technique_page_id get empty technique_page_slug."""
    seed = await _seed_search_data(db_engine)

    session_factory = async_sessionmaker(
        db_engine, class_=AsyncSession, expire_on_commit=False
    )
    async with session_factory() as session:
        from config import Settings
        svc = SearchService(settings=Settings())
        results = await svc.keyword_search("Outro", "all", 20, session)

    km_results = [r for r in results if r["type"] == "key_moment"]
    assert len(km_results) == 1
    assert km_results[0]["technique_page_slug"] == ""


# ── Suggestions endpoint tests ───────────────────────────────────────────────

SUGGESTIONS_URL = "/api/v1/search/suggestions"


@pytest.mark.asyncio
async def test_suggestions_returns_correct_shape(client, db_engine):
    """Suggestions endpoint returns items with text and type fields."""
    await _seed_search_data(db_engine)

    resp = await client.get(SUGGESTIONS_URL)
    assert resp.status_code == 200

    data = resp.json()
    assert "suggestions" in data
    assert isinstance(data["suggestions"], list)
    assert len(data["suggestions"]) > 0

    for item in data["suggestions"]:
        assert "text" in item
        assert "type" in item
        assert item["type"] in ("topic", "technique", "creator")
        assert len(item["text"]) > 0


@pytest.mark.asyncio
async def test_suggestions_includes_all_types(client, db_engine):
    """Suggestions should include technique, topic, and creator types."""
    await _seed_search_data(db_engine)

    resp = await client.get(SUGGESTIONS_URL)
    assert resp.status_code == 200

    data = resp.json()
    types_present = {item["type"] for item in data["suggestions"]}
    assert "technique" in types_present, "Expected technique suggestions"
    assert "topic" in types_present, "Expected topic suggestions"
    assert "creator" in types_present, "Expected creator suggestions"


@pytest.mark.asyncio
async def test_suggestions_no_duplicates(client, db_engine):
    """Suggestions should not contain duplicate texts (case-insensitive)."""
    await _seed_search_data(db_engine)

    resp = await client.get(SUGGESTIONS_URL)
    assert resp.status_code == 200

    data = resp.json()
    texts_lower = [item["text"].lower() for item in data["suggestions"]]
    assert len(texts_lower) == len(set(texts_lower)), "Duplicate suggestions found"


@pytest.mark.asyncio
async def test_suggestions_empty_db(client, db_engine):
    """Suggestions endpoint returns empty list on empty database."""
    resp = await client.get(SUGGESTIONS_URL)
    assert resp.status_code == 200

    data = resp.json()
    assert data["suggestions"] == []


@pytest.mark.asyncio
async def test_suggestions_respects_view_count_ordering(client, db_engine):
    """Higher view_count technique pages should appear first among techniques."""
    session_factory = async_sessionmaker(
        db_engine, class_=AsyncSession, expire_on_commit=False
    )
    async with session_factory() as session:
        creator = Creator(
            name="Test Creator",
            slug="test-creator",
            genres=["Electronic"],
            folder_name="TestCreator",
            view_count=10,
        )
        session.add(creator)
        await session.flush()

        tp_low = TechniquePage(
            creator_id=creator.id,
            title="Low Views Page",
            slug="low-views-page",
            topic_category="Sound design",
            topic_tags=["bass"],
            view_count=5,
        )
        tp_high = TechniquePage(
            creator_id=creator.id,
            title="High Views Page",
            slug="high-views-page",
            topic_category="Synthesis",
            topic_tags=["pads"],
            view_count=100,
        )
        session.add_all([tp_low, tp_high])
        await session.commit()

    resp = await client.get(SUGGESTIONS_URL)
    assert resp.status_code == 200

    data = resp.json()
    technique_items = [
        item for item in data["suggestions"] if item["type"] == "technique"
    ]
    assert len(technique_items) >= 2
    # High Views Page should come before Low Views Page
    titles = [item["text"] for item in technique_items]
    assert titles.index("High Views Page") < titles.index("Low Views Page")