FabledScribe/tests/test_rss_service.py

import pytest
from unittest.mock import patch, MagicMock


def test_extract_item_fields():
    """extract_item() should pull title, link, id, summary from a feedparser entry."""
    from fabledassistant.services.rss import extract_item
    entry = MagicMock()
    entry.get = lambda k, d="": {"title": "Test Post", "link": "https://example.com/1",
                                  "id": "guid-1", "summary": "A summary"}.get(k, d)
    entry.published_parsed = None
    item = extract_item(entry)
    assert item["title"] == "Test Post"
    assert item["url"] == "https://example.com/1"
    assert item["guid"] == "guid-1"
    assert item["content"] == "A summary"


def test_extract_item_does_not_truncate_content():
    """extract_item() should store content without truncation."""
    from fabledassistant.services.rss import extract_item
    long_text = "x" * 100_000
    entry = MagicMock()
    entry.get = lambda k, d="": {"summary": long_text, "title": "", "link": "", "id": "g"}.get(k, d)
    entry.content = []
    entry.published_parsed = None
    item = extract_item(entry)
    assert len(item["content"]) == 100_000


def test_extract_item_prefers_content_over_summary():
    """extract_item() should prefer 'content' field over 'summary' when present."""
    from fabledassistant.services.rss import extract_item
    entry = MagicMock()
    content_obj = MagicMock()
    content_obj.value = "Full content here"
    entry.get = lambda k, d="": {
        "title": "T", "link": "http://x.com", "id": "g",
        "summary": "Short summary",
    }.get(k, d)
    entry.content = [content_obj]
    entry.published_parsed = None
    item = extract_item(entry)
    assert item["content"] == "Full content here"


@pytest.mark.asyncio
async def test_classify_items_batch_returns_topic_map():
    """classify_items_batch should return a dict mapping item_id to topic list."""
    from unittest.mock import AsyncMock
    from fabledassistant.services.rss_classifier import classify_items_batch

    fake_response = '{"1": ["technology", "ai"], "2": ["politics"]}'

    with patch(
        "fabledassistant.services.rss_classifier._llm_classify",
        new_callable=AsyncMock,
        return_value=fake_response,
    ):
        items = [
            {"id": 1, "title": "OpenAI releases GPT-5", "content": "..."},
            {"id": 2, "title": "EU passes new law", "content": "..."},
        ]
        result = await classify_items_batch(items, user_include_topics=[])
        assert result[1] == ["technology", "ai"]
        assert result[2] == ["politics"]


@pytest.mark.asyncio
async def test_classify_items_batch_handles_llm_failure():
    """classify_items_batch should return empty dict on LLM error."""
    from unittest.mock import AsyncMock
    from fabledassistant.services.rss_classifier import classify_items_batch

    with patch(
        "fabledassistant.services.rss_classifier._llm_classify",
        new_callable=AsyncMock,
        side_effect=Exception("LLM unavailable"),
    ):
        items = [{"id": 5, "title": "Some news", "content": ""}]
        result = await classify_items_batch(items, user_include_topics=[])
        assert result == {}


def test_score_rss_items_excludes_blacklisted_topics():
    """Items with excluded topics should be removed."""
    from fabledassistant.services.rss_filtering import score_and_filter_items

    items = [
        {"id": 1, "title": "Tech news", "topics": ["technology"], "published_at": "2026-03-25T08:00:00"},
        {"id": 2, "title": "Sports score", "topics": ["sports"], "published_at": "2026-03-25T08:00:00"},
    ]
    result = score_and_filter_items(
        items,
        include_topics=["technology"],
        exclude_topics=["sports"],
        topic_scores={},
        max_items=10,
    )
    ids = [r["id"] for r in result]
    assert 1 in ids
    assert 2 not in ids


def test_score_rss_items_boosts_included_topics():
    """Items matching include_topics should rank higher than neutral items."""
    from fabledassistant.services.rss_filtering import score_and_filter_items

    items = [
        {"id": 1, "title": "Random news", "topics": ["other"], "published_at": "2026-03-25T07:00:00"},
        {"id": 2, "title": "Tech news", "topics": ["technology"], "published_at": "2026-03-25T06:00:00"},
    ]
    result = score_and_filter_items(
        items,
        include_topics=["technology"],
        exclude_topics=[],
        topic_scores={},
        max_items=10,
    )
    assert result[0]["id"] == 2


def test_score_rss_items_no_preferences_returns_all():
    """With no preferences, all items should be returned sorted by recency."""
    from fabledassistant.services.rss_filtering import score_and_filter_items

    items = [
        {"id": 1, "title": "A", "topics": [], "published_at": "2026-03-24T10:00:00"},
        {"id": 2, "title": "B", "topics": [], "published_at": "2026-03-25T10:00:00"},
    ]
    result = score_and_filter_items(items, [], [], {}, max_items=10)
    assert result[0]["id"] == 2  # Newer first