planet/backend/tests/test_tv_catalog.py

from datetime import UTC, datetime
from unittest.mock import AsyncMock

import pytest
from sqlalchemy import create_engine, event
from sqlalchemy.orm import Session

from app.db.session import Base
from app.models.collected_data import CollectedData
from app.models.data_snapshot import DataSnapshot
from app.models.system_setting import SystemSetting
from app.models.task import CollectionTask
from app.services.collectors.news_live_streams import NewsLiveStreamsCollector
from app.services.tv_catalog import get_tv_catalog_page
from app.services.tv_streams import normalize_tv_settings


class CatalogSession:
    """Execute the real catalog queries against an isolated SQLite database."""

    def __init__(self, session):
        self.session = session

    async def execute(self, query):
        return self.session.execute(query)

    async def scalar(self, query):
        return self.session.scalar(query)

    async def scalars(self, query):
        return self.session.scalars(query)


@pytest.fixture
def catalog_db():
    engine = create_engine("sqlite:///:memory:")

    @event.listens_for(engine, "connect")
    def register_functions(connection, _record):
        connection.create_function(
            "concat_ws",
            -1,
            lambda sep, *args: sep.join(str(arg) for arg in args if arg is not None),
        )

    Base.metadata.create_all(
        engine,
        tables=[
            CollectionTask.__table__,
            DataSnapshot.__table__,
            CollectedData.__table__,
            SystemSetting.__table__,
        ],
    )
    with Session(engine) as session:
        for index in range(135):
            session.add(
                CollectedData(
                    source="news_live_streams",
                    source_id=f"channel-{index:03}",
                    data_type="news_live_stream",
                    name=f"Channel {index:03}",
                    collected_at=datetime(2026, 9, 13, tzinfo=UTC),
                    is_current=True,
                    is_valid=1,
                    extra_data={
                        "stream_url": "https://example.invalid/live.m3u8",
                        "region": "Canada",
                    },
                )
            )
        session.flush()
        yield CatalogSession(session)
    engine.dispose()


@pytest.mark.asyncio
async def test_pages_include_entire_catalog_without_overlap(catalog_db):
    first = await get_tv_catalog_page(catalog_db, limit=50)
    second = await get_tv_catalog_page(catalog_db, offset=first["next_offset"], limit=50)
    third = await get_tv_catalog_page(catalog_db, offset=second["next_offset"], limit=50)
    ids = [source["id"] for page in (first, second, third) for source in page["sources"]]
    assert [len(page["sources"]) for page in (first, second, third)] == [50, 50, 45]
    assert len(set(ids)) == first["source_count"] == 145
    assert ids[-1] == "channel-134"
    assert third["next_offset"] is None and not third["has_more"]
    beyond = await get_tv_catalog_page(catalog_db, offset=200)
    assert beyond["sources"] == [] and not beyond["has_more"]


@pytest.mark.asyncio
async def test_search_finds_later_pages_and_treats_wildcards_literally(catalog_db):
    payload = await get_tv_catalog_page(catalog_db, q="CANADA 134")
    assert [source["id"] for source in payload["sources"]] == ["channel-134"]
    assert payload["total"] == 1 and payload["source_count"] == 145
    assert (await get_tv_catalog_page(catalog_db, q="%"))["total"] == 0


@pytest.mark.asyncio
async def test_selection_survives_refresh_when_outside_first_page(catalog_db):
    payload = await get_tv_catalog_page(catalog_db, selected_id="channel-134")
    assert payload["selected_source"]["id"] == "channel-134"
    assert "channel-134" not in [source["id"] for source in payload["sources"]]
    assert payload["default_source_id"] == "aljazeera-mubasher"
    default = (await get_tv_catalog_page(catalog_db, selected_id="removed"))["selected_source"]
    assert default["id"] == "aljazeera-mubasher" and default["source_type"] == "hls"


@pytest.mark.asyncio
async def test_catalog_hides_inactive_records_and_deduplicates_ids(catalog_db):
    for name, values in [
        ("Disabled", {"extra_data": {"is_enabled": False}}),
        ("Historical", {"is_current": False}),
        ("Invalid", {"is_valid": 0}),
        ("Deleted", {"deleted_at": datetime.now(UTC)}),
        ("Replacement", {"source_id": "channel-134"}),
    ]:
        record = dict(
            source="news_live_streams",
            source_id=name,
            name=name,
            data_type="news_live_stream",
            is_current=True,
            is_valid=1,
        )
        catalog_db.session.add(CollectedData(**{**record, **values}))
    catalog_db.session.flush()
    payload = await get_tv_catalog_page(catalog_db, q="replacement")
    assert payload["source_count"] == 145
    assert [source["id"] for source in payload["sources"]] == ["channel-134"]


def test_missing_builtin_default_adds_aljazeera_without_losing_custom_source():
    settings = normalize_tv_settings({"sources": [{"id": "custom", "name": "Custom"}]})
    assert settings["default_source_id"] == "aljazeera-mubasher"
    assert {source["id"] for source in settings["sources"]} == {"custom", "aljazeera-mubasher"}


@pytest.mark.asyncio
@pytest.mark.parametrize(
    "config, expected", [({}, 135), ({"max_sources": 0}, 135), ({"max_sources": 7}, 7)]
)
async def test_collector_keeps_all_matching_channels_unless_explicitly_limited(
    monkeypatch, config, expected
):
    collector = NewsLiveStreamsCollector()
    channels = [
        {"id": f"channel-{i}", "name": f"Channel {i}", "categories": ["news"]} for i in range(135)
    ]
    channels.append({"id": "sport", "name": "Sports", "categories": ["sports"]})
    streams = [
        {"channel": channel["id"], "url": "https://example.invalid/live.m3u8"}
        for channel in channels
    ]
    monkeypatch.setattr(
        collector, "_gather_iptv_org_payloads", AsyncMock(return_value=(channels, streams, []))
    )
    records = await collector._fetch_iptv_org("https://example.invalid/channels.json", config)
    assert len(records) == expected
    assert all(record["source_id"] != "sport" for record in records)