t-youtube/backend/tests/test_summarizer.py

"""Tests for summarizer.py — mocks transcript API + DeepSeek API."""
import pytest
import os
import httpx
import aiosqlite
import summarizer
from unittest.mock import patch, MagicMock, AsyncMock


class MockTranscript:
    def fetch(self):
        return [
            {"text": "Welcome to this video tutorial.", "start": 0.0, "duration": 3.0},
            {"text": "Today we are learning about Svelte 5 and runes.", "start": 3.0, "duration": 4.0}
        ]

class MockTranscriptList:
    def __init__(self, transcript):
        self.transcript = transcript

    def find_manually_created_transcript(self, languages):
        return self.transcript

    def find_generated_transcript(self, languages):
        return self.transcript

    def __iter__(self):
        return iter([self.transcript])


def _mock_deepseek_response(content: str) -> MagicMock:
    """Build a DeepSeek/OpenAI-compatible API response."""
    r = MagicMock(spec=httpx.Response)
    r.status_code = 200
    r.json.return_value = {
        "choices": [{"message": {"content": content}}]
    }
    return r


@pytest.mark.asyncio
async def test_download_transcript_success():
    mock_trans = MockTranscript()
    mock_list = MockTranscriptList(mock_trans)

    with patch("youtube_transcript_api.YouTubeTranscriptApi.list", return_value=mock_list):
        text = summarizer.download_transcript("test_vid")
        assert text == "Welcome to this video tutorial. Today we are learning about Svelte 5 and runes."


@pytest.mark.asyncio
async def test_summarize_video_success(test_db):
    await test_db.execute("""
        INSERT INTO videos (video_id, title, url, status)
        VALUES ('summarize_vid', 'Video to Summarize', 'https://www.youtube.com/watch?v=summarize_vid', 'pending')
    """)
    await test_db.commit()

    mock_trans = MockTranscript()
    mock_list = MockTranscriptList(mock_trans)
    mock_response = _mock_deepseek_response("**Mock Core Hook**\n- Takeaway 1\n- Takeaway 2\nVerdict line.")

    with patch("youtube_transcript_api.YouTubeTranscriptApi.list", return_value=mock_list), \
         patch("httpx.AsyncClient.post", new_callable=AsyncMock, return_value=mock_response) as mock_post:

        summary = await summarizer.summarize_video("summarize_vid")

        # Verify API request details
        mock_post.assert_called_once()
        url = mock_post.call_args[0][0]
        assert summarizer.BASE_URL in url

        headers = mock_post.call_args[1]["headers"]
        assert "Authorization" in headers
        assert headers["User-Agent"] is not None

        payload = mock_post.call_args[1]["json"]
        assert payload["model"] == "deepseek-chat"
        assert len(payload["messages"]) == 2  # system + user

        assert summary == "**Mock Core Hook**\n- Takeaway 1\n- Takeaway 2\nVerdict line."

    # Query db to verify transcript & summary were saved
    cursor = await test_db.execute("SELECT * FROM videos WHERE video_id = 'summarize_vid'")
    video = await cursor.fetchone()
    assert video is not None
    assert video["transcript"] == "Welcome to this video tutorial. Today we are learning about Svelte 5 and runes."
    assert video["summary"] == "**Mock Core Hook**\n- Takeaway 1\n- Takeaway 2\nVerdict line."


@pytest.mark.asyncio
async def test_summarize_video_deepseek_error_leaves_null(test_db):
    """When DeepSeek fails, summary should stay NULL for retry."""
    await test_db.execute("""
        INSERT INTO videos (video_id, title, url, status)
        VALUES ('err_vid', 'Error Video', 'https://youtube.com/watch?v=err_vid', 'pending')
    """)
    await test_db.commit()

    mock_trans = MockTranscript()
    mock_list = MockTranscriptList(mock_trans)
    mock_response = MagicMock(spec=httpx.Response)
    mock_response.status_code = 429
    # raise_for_status on 429 should raise HTTPStatusError
    mock_response.raise_for_status.side_effect = httpx.HTTPStatusError(
        "429 Rate Limited", request=MagicMock(), response=mock_response
    )

    with patch("youtube_transcript_api.YouTubeTranscriptApi.list", return_value=mock_list), \
         patch("httpx.AsyncClient.post", new_callable=AsyncMock, return_value=mock_response):

        result = await summarizer.summarize_video("err_vid")

        assert result is None  # Returns None instead of an error string

    # Verify DB — summary should remain NULL
    cursor = await test_db.execute("SELECT summary FROM videos WHERE video_id = 'err_vid'")
    row = await cursor.fetchone()
    assert row["summary"] is None


@pytest.mark.asyncio
async def test_summarize_all_pending(test_db):
    await test_db.execute("""
        INSERT INTO videos (video_id, title, url, summary, status)
        VALUES
        ('pending_vid', 'Pending Video', 'https://youtube.com/watch?v=pending_vid', '', 'pending'),
        ('done_vid', 'Done Video', 'https://youtube.com/watch?v=done_vid', 'Existing summary', 'pending')
    """)
    await test_db.commit()

    mock_trans = MockTranscript()
    mock_list = MockTranscriptList(mock_trans)
    mock_response = _mock_deepseek_response("Fresh summary")

    with patch("youtube_transcript_api.YouTubeTranscriptApi.list", return_value=mock_list), \
         patch("httpx.AsyncClient.post", new_callable=AsyncMock, return_value=mock_response) as mock_post:

        await summarizer.summarize_all_pending()

        # Should only call API once for 'pending_vid' (done_vid already has summary)
        mock_post.assert_called_once()

    # Verify db states
    cursor = await test_db.execute("SELECT video_id, summary FROM videos ORDER BY video_id")
    videos = await cursor.fetchall()
    assert videos[0]["video_id"] == "done_vid"
    assert videos[0]["summary"] == "Existing summary"  # Untouched

    assert videos[1]["video_id"] == "pending_vid"
    assert videos[1]["summary"] == "Fresh summary"  # Updated