path: root/packages/meshbay-node/tests/test_enrich_audio.py

"""Tests for indexer/enrich_audio.py — tag/cover extraction and the end-to-end pool."""

import asyncio
import shutil
import subprocess
from pathlib import Path

import pytest
from meshbay_common.protocol import IndexEntry
from meshbay_node.indexer.enrich_audio import (
    AudioEnricher,
    _artist_album_from_ancestors,
    _clean_tag,
    _extract_cover,
    _split_top_level_folder,
)
from meshbay_node.indexer.title_parse import parse_track_filename, strip_track_prefix
from meshbay_node.media_cache import MediaCache

_HAVE_FFMPEG = shutil.which("ffmpeg") and shutil.which("ffprobe")


# ── pure helpers, no ffmpeg/mutagen file needed ──────────────────────────────

def test_parse_track_filename_splits_leading_track_number():
    parsed = parse_track_filename("01 - Venus As A Boy (Edited Lp Version).mp3")
    assert parsed.track_no == 1
    assert parsed.title == "Venus As A Boy (Edited Lp Version)"


def test_parse_track_filename_handles_dot_separated():
    parsed = parse_track_filename("03. Human Behaviour.mp3")
    assert parsed.track_no == 3
    assert parsed.title == "Human Behaviour"


def test_parse_track_filename_handles_underscore_separated():
    parsed = parse_track_filename("12_Some_Title.mp3")
    assert parsed.track_no == 12
    assert parsed.title == "Some Title"


def test_parse_track_filename_no_prefix_leaves_track_no_none():
    parsed = parse_track_filename("Some Title.mp3")
    assert parsed.track_no is None
    assert parsed.title == "Some Title"


def test_parse_track_filename_does_not_mistake_a_leading_year_for_a_track_number():
    parsed = parse_track_filename("1999 - Some Title.mp3")
    assert parsed.track_no is None, "a 4-digit prefix is capped out, not read as track 199"


def test_artist_album_from_ancestors_reads_artist_album_track_layout(tmp_path):
    folder = tmp_path / "Some Artist" / "Some Album"
    folder.mkdir(parents=True)
    track = folder / "01 - A Track.mp3"
    track.touch()

    artist, album = _artist_album_from_ancestors(track, tmp_path)

    assert artist == "Some Artist"
    assert album == "Some Album"


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 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 / "Some Flat Artist"
    folder.mkdir(parents=True)
    track = folder / "A Track.mp3"
    track.touch()

    artist, album = _artist_album_from_ancestors(track, tmp_path)

    assert artist == "Some Flat Artist"
    assert album is None, "no album folder exists — must not invent one, or swap artist/album"


def test_artist_album_from_ancestors_file_directly_in_root_has_no_context(tmp_path):
    track = tmp_path / "loose_track.mp3"
    track.touch()

    artist, album = _artist_album_from_ancestors(track, tmp_path)

    assert (artist, album) == (None, None)


def test_artist_album_from_ancestors_without_a_root_keeps_the_old_two_level_behaviour(tmp_path):
    """No root resolved (should not happen in practice, but must degrade safely)."""
    folder = tmp_path / "Some Artist" / "Some Album"
    folder.mkdir(parents=True)
    track = folder / "01 - A Track.mp3"
    track.touch()

    artist, album = _artist_album_from_ancestors(track, None)

    assert artist == "Some Artist"
    assert album == "Some Album"


def test_split_top_level_folder_splits_artist_dash_album():
    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("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(
        "Some Artist - Some Release [MP3 320kbps Album]")
    assert artist == "Some Artist"
    assert album == "Some Release"


def test_clean_tag_filters_known_placeholders():
    assert _clean_tag("No Artist") is None
    assert _clean_tag("unknown artist") is None
    assert _clean_tag("Nouvel artiste (334)") is None
    assert _clean_tag("Nouveau titre (12)") is None
    assert _clean_tag("") is None
    assert _clean_tag(None) is None


def test_clean_tag_keeps_various_artists_as_a_real_credit():
    """A real, meaningful compilation credit — not a placeholder to blank out."""
    assert _clean_tag("Various Artists") == "Various Artists"


def test_clean_tag_keeps_a_real_value():
    # 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 - Some Track (Edited Version)") == \
        "Some Track (Edited Version)"


def test_strip_track_prefix_is_a_noop_on_a_clean_title():
    assert strip_track_prefix("Some Track") == "Some Track"


# ── end-to-end against a real (tiny, synthetic) MP3 file ────────────────────

pytestmark_ffmpeg = pytest.mark.skipif(not _HAVE_FFMPEG, reason="ffmpeg/ffprobe not installed")


def _make_clip(path: Path, *, title=None, artist=None, album=None, track=None) -> None:
    subprocess.run(
        ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
         "-f", "lavfi", "-i", "sine=frequency=440:duration=1",
         "-c:a", "libmp3lame", "-b:a", "64k",
         *(["-metadata", f"title={title}"] if title else []),
         *(["-metadata", f"artist={artist}"] if artist else []),
         *(["-metadata", f"album={album}"] if album else []),
         *(["-metadata", f"track={track}"] if track else []),
         str(path)],
        check=True, capture_output=True,
    )


@pytest.fixture
async def media_cache(tmp_path):
    c = MediaCache(db_path=tmp_path / "media_cache.db")
    await c.open()
    yield c
    await c.close()


@pytestmark_ffmpeg
@pytest.mark.asyncio
async def test_enricher_prefers_tags_over_filename_parse(tmp_path, media_cache):
    clip = tmp_path / "99 - wrong title.mp3"
    _make_clip(clip, title="Real Title", artist="Real Artist", album="Real Album", track=3)
    entry = IndexEntry(id="fileid1", name=clip.name, path=clip.name,
                        size=clip.stat().st_size, type="audio", added_at=0)

    enricher = AudioEnricher(media_cache)
    done = asyncio.get_event_loop().create_future()

    async def on_done(file_id, fields):
        done.set_result((file_id, fields))

    enricher.spawn(entry, clip, on_done)
    file_id, fields = await asyncio.wait_for(done, timeout=30)

    assert file_id == "fileid1"
    assert fields["display_title"] == "Real Title"
    assert fields["artist"] == "Real Artist"
    assert fields["album"] == "Real Album"
    assert fields["track_no"] == 3
    assert fields["duration"] == 1
    assert fields.get("thumb_hash") is None, "no embedded cover was written in this clip"


@pytestmark_ffmpeg
@pytest.mark.asyncio
async def test_enricher_falls_back_to_filename_and_folder_when_tags_absent(tmp_path, media_cache):
    folder = tmp_path / "Folder Artist" / "Folder Album"
    folder.mkdir(parents=True)
    clip = folder / "05 - Filename Title.mp3"
    _make_clip(clip)   # no metadata tags at all
    entry = IndexEntry(id="fileid2", name=clip.name,
                        path=str(clip.relative_to(tmp_path)),
                        size=clip.stat().st_size, type="audio", added_at=0)

    enricher = AudioEnricher(media_cache)
    done = asyncio.get_event_loop().create_future()

    async def on_done(file_id, fields):
        done.set_result((file_id, fields))

    enricher.spawn(entry, clip, on_done, tmp_path)
    _, fields = await asyncio.wait_for(done, timeout=30)

    assert fields["display_title"] == "Filename Title"
    assert fields["track_no"] == 5
    assert fields["artist"] == "Folder Artist"
    assert fields["album"] == "Folder Album"


@pytestmark_ffmpeg
@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 / "Some Flat Artist"
    folder.mkdir(parents=True)
    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)),
                        size=clip.stat().st_size, type="audio", added_at=0)

    enricher = AudioEnricher(media_cache)
    done = asyncio.get_event_loop().create_future()

    async def on_done(file_id, fields):
        done.set_result((file_id, fields))

    enricher.spawn(entry, clip, on_done, tmp_path)
    _, fields = await asyncio.wait_for(done, timeout=30)

    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"


@pytestmark_ffmpeg
@pytest.mark.asyncio
async def test_enricher_uses_a_sibling_cover_file_when_no_embedded_art(tmp_path, media_cache):
    folder = tmp_path / "Some Artist" / "Some Album"
    folder.mkdir(parents=True)
    clip = folder / "01 - A Track.mp3"
    _make_clip(clip)
    (folder / "Folder.jpg").write_bytes(b"\xff\xd8\xff\xe0fake-jpeg-bytes")
    entry = IndexEntry(id="fileid4", name=clip.name,
                        path=str(clip.relative_to(tmp_path)),
                        size=clip.stat().st_size, type="audio", added_at=0)

    enricher = AudioEnricher(media_cache)
    done = asyncio.get_event_loop().create_future()

    async def on_done(file_id, fields):
        done.set_result((file_id, fields))

    enricher.spawn(entry, clip, on_done, tmp_path)
    _, fields = await asyncio.wait_for(done, timeout=30)

    assert fields.get("thumb_hash"), "a Folder.jpg beside the track must be picked up as its cover"
    stored = await media_cache.get_thumb(fields["thumb_hash"])
    assert stored == b"\xff\xd8\xff\xe0fake-jpeg-bytes"


@pytestmark_ffmpeg
def test_extract_cover_returns_none_when_no_apic_frame(tmp_path):
    from mutagen import File as MutagenFile

    clip = tmp_path / "plain.mp3"
    _make_clip(clip)

    mf = MutagenFile(str(clip))
    assert _extract_cover(mf) is None