alfred/tests/domain/test_subtitle_pattern_detector.py

"""Tests for ``alfred.domain.subtitles.services.pattern_detector.PatternDetector``.

The detector inspects a release folder and returns the best-matching known
pattern + a confidence score.

Coverage:

- ``TestEmbeddedDetection`` — ffprobe is mocked; ``embedded`` pattern wins
  when no external subs and ffprobe reports tracks.
- ``TestAdjacentDetection`` — .srt next to the video → ``adjacent``.
- ``TestFlatSubsFolder`` — ``Subs/*.srt`` → ``subs_flat``.
- ``TestEpisodeSubfolder`` — ``Subs/{ep}/*.srt`` → ``episode_subfolder``.
- ``TestNothingFound`` — empty release returns no pattern.
- ``TestDescribe`` — human-readable description mentions the right cues.

Uses the real ``SubtitleKnowledgeBase`` (loaded from the live builtin
``patterns/`` folder) since rebuilding all four patterns by hand would
just duplicate fixture state.
"""

from __future__ import annotations

from pathlib import Path
from unittest.mock import patch

import pytest

from alfred.infrastructure.knowledge.subtitles.base import SubtitleKnowledgeBase
from alfred.domain.subtitles.services.pattern_detector import PatternDetector


@pytest.fixture(scope="module")
def kb():
    return SubtitleKnowledgeBase()


@pytest.fixture
def detector(kb):
    return PatternDetector(kb)


def _make_video(folder: Path, name: str = "Show.S01E01.mkv") -> Path:
    v = folder / name
    v.write_bytes(b"")
    return v


# --------------------------------------------------------------------------- #
# Embedded                                                                     #
# --------------------------------------------------------------------------- #


class TestEmbeddedDetection:
    def test_embedded_only(self, detector, tmp_path):
        # Folder has video but no external .srt files anywhere.
        video = _make_video(tmp_path)
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=True
        ):
            result = detector.detect(tmp_path, video)
        assert result["detected"] is not None
        assert result["detected"].id == "embedded"
        assert result["confidence"] > 0
        assert "embedded" in result["description"].lower()


# --------------------------------------------------------------------------- #
# Adjacent                                                                     #
# --------------------------------------------------------------------------- #


class TestAdjacentDetection:
    def test_srt_next_to_video(self, detector, tmp_path):
        video = _make_video(tmp_path)
        (tmp_path / "Show.S01E01.English.srt").write_text("")
        (tmp_path / "Show.S01E01.French.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        assert result["detected"] is not None
        assert result["detected"].id == "adjacent"
        assert "adjacent" in result["description"]


# --------------------------------------------------------------------------- #
# Subs flat folder                                                             #
# --------------------------------------------------------------------------- #


class TestFlatSubsFolder:
    def test_flat_subs_folder_adjacent_to_video(self, detector, tmp_path):
        video = _make_video(tmp_path)
        subs = tmp_path / "Subs"
        subs.mkdir()
        (subs / "Show.S01E01.English.srt").write_text("")
        (subs / "Show.S01E01.French.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        assert result["detected"] is not None
        assert result["detected"].id == "subs_flat"
        assert "flat" in result["description"]

    def test_flat_subs_folder_at_release_root(self, detector, tmp_path):
        # Sample video lives one level deep; Subs/ is at the release root.
        season_dir = tmp_path / "Season.01"
        season_dir.mkdir()
        video = _make_video(season_dir)
        subs = tmp_path / "Subs"
        subs.mkdir()
        (subs / "ep01.English.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        assert result["detected"] is not None
        assert result["detected"].id == "subs_flat"


# --------------------------------------------------------------------------- #
# Episode subfolder                                                            #
# --------------------------------------------------------------------------- #


class TestEpisodeSubfolder:
    def test_per_episode_subfolder(self, detector, tmp_path):
        video = _make_video(tmp_path, name="Show.S01E01.mkv")
        subs = tmp_path / "Subs" / "Show.S01E01"
        subs.mkdir(parents=True)
        (subs / "2_English.srt").write_text("")
        (subs / "3_French.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        assert result["detected"] is not None
        assert result["detected"].id == "episode_subfolder"
        desc = result["description"]
        assert "episode_subfolder" in desc
        # Numeric-prefix cue should be reported.
        assert "numeric prefix" in desc


# --------------------------------------------------------------------------- #
# Nothing                                                                      #
# --------------------------------------------------------------------------- #


class TestNothingFound:
    def test_empty_release_no_pattern(self, detector, tmp_path):
        video = _make_video(tmp_path)
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        # No external subs and no embedded → adjacent strategy still scores
        # 0.5 (no Subs folder bonus). Best pattern may exist or not depending
        # on threshold (0.4). Either way the description must reflect emptiness.
        assert "no external subtitle files" in result["description"]


# --------------------------------------------------------------------------- #
# Describe                                                                     #
# --------------------------------------------------------------------------- #


class TestDescribe:
    def test_describe_includes_language_token_cue(self, detector, tmp_path):
        video = _make_video(tmp_path)
        subs = tmp_path / "Subs"
        subs.mkdir()
        (subs / "ep01.English.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=False
        ):
            result = detector.detect(tmp_path, video)
        assert "language tokens" in result["description"]

    def test_describe_combines_external_and_embedded(self, detector, tmp_path):
        video = _make_video(tmp_path)
        (tmp_path / "Show.S01E01.English.srt").write_text("")
        with patch.object(
            PatternDetector, "_has_embedded_subtitles", return_value=True
        ):
            result = detector.detect(tmp_path, video)
        desc = result["description"]
        assert "adjacent" in desc
        assert "embedded" in desc.lower()