diff options
Diffstat (limited to 'packages/meshbay-node')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/indexer/enrich_audio.py | 15 | ||||
| -rw-r--r-- | packages/meshbay-node/tests/test_enrich_audio.py | 39 |
2 files changed, 27 insertions, 27 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/indexer/enrich_audio.py b/packages/meshbay-node/src/meshbay_node/indexer/enrich_audio.py index 9ecf1b9..5225d4f 100644 --- a/packages/meshbay-node/src/meshbay_node/indexer/enrich_audio.py +++ b/packages/meshbay-node/src/meshbay_node/indexer/enrich_audio.py @@ -198,8 +198,8 @@ def _read_tags_and_cover(path: Path) -> tuple[dict, float | None, bytes | None]: # A folder name used as a last-resort artist/album, cleaned of the # punctuation-as-separator and release-tag noise this era of rip is full of -# ("L_Oeuf_Raide_-_Berlin_Eggsile", "Sinsemilia - Premiere Recolte [MP3 -# 320kbps Album]"). Same spirit as title_parse.naive_title for video, kept +# (underscores standing in for spaces, a bitrate/quality tag still attached +# to the name). Same spirit as title_parse.naive_title for video, kept # separate because the junk vocabulary differs (bitrates and rip tags, not # edition/language tags). # A whole bracketed/parenthesized group is dropped if it contains any rip-tag @@ -228,12 +228,11 @@ def _split_top_level_folder(name: str) -> tuple[str, str | None]: directly under the group's root (§ below) — there is no further ancestor to call "artist" without leaving the root entirely. The common convention for a single-release folder at that level is - "Artist - Album ...junk..." ("GHOST DOG - Soundtrack", - "cypress_hill_-los_grandes__xitos_en_espa_ol"); split on the first - " - " when the cleaned name has one. Otherwise the whole (cleaned) name - becomes the artist alone, which is the *more* common real shape here — - a flat per-artist folder with no album subfolder at all ("Ben Harper", - "bob_marley", "Renaud"). + "Artist - Album ...junk..." (e.g. a soundtrack folder named after the + film, or a release folder with the ripper's tags still attached); split + on the first " - " when the cleaned name has one. Otherwise the whole + (cleaned) name becomes the artist alone, which is the *more* common real + shape here — a flat per-artist folder with no album subfolder at all. """ cleaned = _clean_folder_name(name) m = re.match(r"^(.{2,60}?)\s*-\s*(.{2,80})$", cleaned) diff --git a/packages/meshbay-node/tests/test_enrich_audio.py b/packages/meshbay-node/tests/test_enrich_audio.py index 221f1c6..0fd8e17 100644 --- a/packages/meshbay-node/tests/test_enrich_audio.py +++ b/packages/meshbay-node/tests/test_enrich_audio.py @@ -68,18 +68,18 @@ def test_artist_album_from_ancestors_refuses_to_name_the_root_as_artist(tmp_path The regression this whole revision exists for: a flat `Artist/track.mp3` layout (no album subfolder) used to read the *root's own directory name* as the artist, because the walk always climbed two levels with no - idea where the root was. Measured live: 289 tracks across 41 real, - unrelated artists collapsed into one fake "artist" this way — the + idea where the root was. Measured live against a real library: dozens + of unrelated artists collapsed into one fake "artist" this way — the single biggest bucket in the whole library. """ - folder = tmp_path / "Ben Harper" + folder = tmp_path / "Some Flat Artist" folder.mkdir(parents=True) - track = folder / "Ashes.mp3" + track = folder / "A Track.mp3" track.touch() artist, album = _artist_album_from_ancestors(track, tmp_path) - assert artist == "Ben Harper" + assert artist == "Some Flat Artist" assert album is None, "no album folder exists — must not invent one, or swap artist/album" @@ -106,22 +106,22 @@ def test_artist_album_from_ancestors_without_a_root_keeps_the_old_two_level_beha def test_split_top_level_folder_splits_artist_dash_album(): - artist, album = _split_top_level_folder("GHOST DOG - Soundtrack") - assert artist == "GHOST DOG" + artist, album = _split_top_level_folder("Some Movie - Soundtrack") + assert artist == "Some Movie" assert album == "Soundtrack" def test_split_top_level_folder_with_no_separator_is_artist_only(): - artist, album = _split_top_level_folder("Ben Harper") - assert artist == "Ben Harper" + artist, album = _split_top_level_folder("Some Flat Artist") + assert artist == "Some Flat Artist" assert album is None def test_split_top_level_folder_cleans_rip_tag_noise(): artist, album = _split_top_level_folder( - "Sinsemilia - Premiere Recolte [MP3 320kbps Album]") - assert artist == "Sinsemilia" - assert album == "Premiere Recolte" + "Some Artist - Some Release [MP3 320kbps Album]") + assert artist == "Some Artist" + assert album == "Some Release" def test_clean_tag_filters_known_placeholders(): @@ -139,16 +139,17 @@ def test_clean_tag_keeps_various_artists_as_a_real_credit(): def test_clean_tag_keeps_a_real_value(): - assert _clean_tag("Björk") == "Björk" + # Non-ASCII must not be mistaken for a placeholder pattern. + assert _clean_tag("Ünïqùé Ärtïst") == "Ünïqùé Ärtïst" def test_strip_track_prefix_removes_a_leaked_filename_number(): - assert strip_track_prefix("01 - Venus As A Boy (Edited Lp Version)") == \ - "Venus As A Boy (Edited Lp Version)" + assert strip_track_prefix("01 - Some Track (Edited Version)") == \ + "Some Track (Edited Version)" def test_strip_track_prefix_is_a_noop_on_a_clean_title(): - assert strip_track_prefix("Venus As A Boy") == "Venus As A Boy" + assert strip_track_prefix("Some Track") == "Some Track" # ── end-to-end against a real (tiny, synthetic) MP3 file ──────────────────── @@ -234,9 +235,9 @@ async def test_enricher_falls_back_to_filename_and_folder_when_tags_absent(tmp_p @pytest.mark.asyncio async def test_enricher_falls_back_to_artist_only_for_a_flat_top_level_dir(tmp_path, media_cache): """The real-world regression case, end to end through the whole pool.""" - folder = tmp_path / "Ben Harper" + folder = tmp_path / "Some Flat Artist" folder.mkdir(parents=True) - clip = folder / "Ashes.mp3" + clip = folder / "A Track.mp3" _make_clip(clip) # no metadata tags at all entry = IndexEntry(id="fileid3", name=clip.name, path=str(clip.relative_to(tmp_path)), @@ -251,7 +252,7 @@ async def test_enricher_falls_back_to_artist_only_for_a_flat_top_level_dir(tmp_p enricher.spawn(entry, clip, on_done, tmp_path) _, fields = await asyncio.wait_for(done, timeout=30) - assert fields["artist"] == "Ben Harper" + assert fields["artist"] == "Some Flat Artist" assert fields["album"] is None assert fields["artist"] != tmp_path.name, \ "must never fall back to the shared root's own directory name" |