feat: major architectural refactor

- Refactor memory system (episodic/STM/LTM with components) - Implement complete subtitle domain (scanner, matcher, placer) - Add YAML workflow infrastructure - Externalize knowledge base (patterns, release groups) - Add comprehensive testing suite - Create manual testing CLIs
2026-05-11 21:33:37 +02:00
parent 62b5d0b998
commit 249c5de76a
103 changed files with 8559 additions and 1346 deletions
@@ -0,0 +1,217 @@
+"""Tests for SubtitleScanner and _classify helper."""
+
+import pytest
+from pathlib import Path
+
+from alfred.domain.subtitles.scanner import (
+    SubtitleCandidate,
+    SubtitleScanner,
+    _classify,
+)
+
+
+# ---------------------------------------------------------------------------
+# _classify — unit tests for the filename parser
+# ---------------------------------------------------------------------------
+
+class TestClassify:
+
+    def test_iso_lang_code(self, tmp_path):
+        p = tmp_path / "fr.srt"
+        p.write_text("")
+        lang, is_sdh, is_forced = _classify(p)
+        assert lang == "fr"
+        assert not is_sdh
+        assert not is_forced
+
+    def test_english_keyword(self, tmp_path):
+        p = tmp_path / "english.srt"
+        p.write_text("")
+        lang, _, _ = _classify(p)
+        assert lang == "en"
+
+    def test_french_keyword(self, tmp_path):
+        p = tmp_path / "Show.S01E01.French.srt"
+        p.write_text("")
+        lang, _, _ = _classify(p)
+        assert lang == "fr"
+
+    def test_vostfr_is_french(self, tmp_path):
+        p = tmp_path / "Show.S01E01.VOSTFR.srt"
+        p.write_text("")
+        lang, _, _ = _classify(p)
+        assert lang == "fr"
+
+    def test_sdh_token(self, tmp_path):
+        p = tmp_path / "fr.sdh.srt"
+        p.write_text("")
+        lang, is_sdh, _ = _classify(p)
+        assert lang == "fr"
+        assert is_sdh
+
+    def test_hi_alias_for_sdh(self, tmp_path):
+        p = tmp_path / "en.hi.srt"
+        p.write_text("")
+        _, is_sdh, _ = _classify(p)
+        assert is_sdh
+
+    def test_forced_token(self, tmp_path):
+        p = tmp_path / "fr.forced.srt"
+        p.write_text("")
+        _, _, is_forced = _classify(p)
+        assert is_forced
+
+    def test_unknown_language_returns_none(self, tmp_path):
+        p = tmp_path / "Show.S01E01.720p.srt"
+        p.write_text("")
+        lang, _, _ = _classify(p)
+        assert lang is None
+
+    def test_dot_separator(self, tmp_path):
+        p = tmp_path / "fr.sdh.srt"
+        p.write_text("")
+        lang, is_sdh, _ = _classify(p)
+        assert lang == "fr"
+        assert is_sdh
+
+    def test_hyphen_separator(self, tmp_path):
+        p = tmp_path / "fr-forced.srt"
+        p.write_text("")
+        lang, _, is_forced = _classify(p)
+        assert lang == "fr"
+        assert is_forced
+
+
+# ---------------------------------------------------------------------------
+# SubtitleCandidate.destination_name
+# ---------------------------------------------------------------------------
+
+class TestSubtitleCandidateDestinationName:
+
+    def _make(self, lang="fr", is_sdh=False, is_forced=False, ext=".srt", path=None):
+        return SubtitleCandidate(
+            source_path=path or Path("/fake/fr.srt"),
+            language=lang,
+            is_sdh=is_sdh,
+            is_forced=is_forced,
+            extension=ext,
+        )
+
+    def test_standard(self):
+        assert self._make().destination_name == "fr.srt"
+
+    def test_sdh(self):
+        assert self._make(is_sdh=True).destination_name == "fr.sdh.srt"
+
+    def test_forced(self):
+        assert self._make(is_forced=True).destination_name == "fr.forced.srt"
+
+    def test_ass_extension(self):
+        assert self._make(ext=".ass").destination_name == "fr.ass"
+
+    def test_english_standard(self):
+        assert self._make(lang="en").destination_name == "en.srt"
+
+
+# ---------------------------------------------------------------------------
+# SubtitleScanner — integration with real filesystem
+# ---------------------------------------------------------------------------
+
+class TestSubtitleScanner:
+
+    def _scanner(self, languages=None, min_size_kb=0, keep_sdh=True, keep_forced=True):
+        return SubtitleScanner(
+            languages=languages or ["fr", "en"],
+            min_size_kb=min_size_kb,
+            keep_sdh=keep_sdh,
+            keep_forced=keep_forced,
+        )
+
+    def _video(self, tmp_path):
+        video = tmp_path / "Movie.mkv"
+        video.write_bytes(b"video")
+        return video
+
+    def test_finds_adjacent_subtitle(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.srt").write_text("subtitle content")
+
+        candidates = self._scanner().scan(video)
+
+        assert len(candidates) == 1
+        assert candidates[0].language == "fr"
+
+    def test_finds_multiple_languages(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.srt").write_text("fr subtitle")
+        (tmp_path / "en.srt").write_text("en subtitle")
+
+        candidates = self._scanner().scan(video)
+        langs = {c.language for c in candidates}
+        assert langs == {"fr", "en"}
+
+    def test_scans_subs_subfolder(self, tmp_path):
+        video = self._video(tmp_path)
+        subs = tmp_path / "Subs"
+        subs.mkdir()
+        (subs / "fr.srt").write_text("subtitle")
+
+        candidates = self._scanner().scan(video)
+        assert any(c.language == "fr" for c in candidates)
+
+    def test_filters_unknown_language(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "unknown.srt").write_text("subtitle")
+
+        candidates = self._scanner().scan(video)
+        assert len(candidates) == 0
+
+    def test_filters_wrong_language(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "de.srt").write_text("german subtitle")
+
+        candidates = self._scanner(languages=["fr"]).scan(video)
+        assert len(candidates) == 0
+
+    def test_filters_too_small_file(self, tmp_path):
+        video = self._video(tmp_path)
+        small = tmp_path / "fr.srt"
+        small.write_bytes(b"x")  # 1 byte, well below any min_size_kb
+
+        candidates = self._scanner(min_size_kb=10).scan(video)
+        assert len(candidates) == 0
+
+    def test_filters_sdh_when_not_wanted(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.sdh.srt").write_text("sdh subtitle")
+
+        candidates = self._scanner(keep_sdh=False).scan(video)
+        assert len(candidates) == 0
+
+    def test_filters_forced_when_not_wanted(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.forced.srt").write_text("forced subtitle")
+
+        candidates = self._scanner(keep_forced=False).scan(video)
+        assert len(candidates) == 0
+
+    def test_keeps_sdh_when_wanted(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.sdh.srt").write_text("sdh subtitle")
+
+        candidates = self._scanner(keep_sdh=True).scan(video)
+        assert len(candidates) == 1
+        assert candidates[0].is_sdh
+
+    def test_ignores_non_subtitle_files(self, tmp_path):
+        video = self._video(tmp_path)
+        (tmp_path / "fr.nfo").write_text("nfo file")
+        (tmp_path / "fr.jpg").write_bytes(b"image")
+
+        candidates = self._scanner().scan(video)
+        assert len(candidates) == 0
+
+    def test_returns_empty_when_no_subtitles(self, tmp_path):
+        video = self._video(tmp_path)
+        candidates = self._scanner().scan(video)
+        assert candidates == []