soulsync/tests/exports/test_export_sources.py
BoulderBadgeDad 37c8b06a27 playlist export: resolve IDs from the discovery cache first (#945, increment 6)
Boulder: "all 50 tracks are discovered to Deezer already — it's not using any of that." Right —
the export only checked tracks.deezer_id (library) and ignored the IDs discovery already resolved
and stored in each mirrored track's extra_data. So tracks that were discovered+downloaded but not
separately enriched showed as "not on Deezer" and got dropped.

Adds a per-track waterfall for service export:
- service_id_from_extra_data(track, service): the id discovery already matched, read from
  extra_data.matched_data.id — FREE (no API call) and reliable (it's the same id used to mirror
  the track). Trusted only when discovered ON the target service (provider == service); a
  wing_it_fallback (low-confidence guess) does NOT match here, so it falls through rather than
  risk a wrong track in the export.
- resolve_service_track_ids(tracks, service): cache (extra_data) → library stored id → unmatched.
  Reports from_cache / from_library / unmatched. _run_service_export now uses this instead of the
  artist/title MBID-style resolver.

For Boulder's playlist this means all 50 resolve straight from the cache — full coverage, zero API
calls. (A live confident-search backfill for the genuinely-missing remainder is the optional next
step, gated + thresholded.)

9 new tests: extra_data id only when provider matches + wing_it excluded + bad-json/not-discovered
guards, the cache→library→unmatched waterfall with stat tallies, and _run_service_export resolving
straight from the cache end-to-end. 49 export tests green, ruff clean.
2026-06-28 21:39:39 -07:00

171 lines
6.6 KiB
Python

"""Export source wiring (#903): waterfall order + cache write-back.
build_resolve_fn assembles cache -> DB -> file -> MusicBrainz and writes a fresh
(non-cache) hit back to the cache. Pins: a cache hit short-circuits everything and is
NOT re-written; a DB/MB hit IS written back; misses fall through; the resolving label is
returned.
"""
from __future__ import annotations
from core.exports.export_sources import build_resolve_fn
from core.exports.mbid_resolver import SRC_CACHE, SRC_DB, SRC_MUSICBRAINZ
MBID = "e8f9b188-f819-4e43-ab0f-4bd26ce9ff56"
def _wire(db=None, file=None, mb=None, cache=None):
recorded = {}
store = dict(cache or {})
fn = build_resolve_fn(
db_fn=lambda a, t: (db or {}).get((a, t)),
file_fn=lambda a, t: (file or {}).get((a, t)),
mb_fn=lambda a, t: (mb or {}).get((a, t)),
cache_lookup=lambda k: store.get(k),
cache_record=lambda k, m: recorded.__setitem__(k, m) or True,
)
return fn, recorded
def test_cache_hit_short_circuits_and_is_not_rewritten():
from core.exports.mbid_resolver import normalize_key
fn, recorded = _wire(
cache={normalize_key("A", "T"): MBID},
db={("A", "T"): "should-not-reach"},
)
mbid, label = fn("A", "T")
assert (mbid, label) == (MBID, SRC_CACHE)
assert recorded == {} # cache hit -> no write-back
def test_db_hit_is_written_back_to_cache():
from core.exports.mbid_resolver import normalize_key
fn, recorded = _wire(db={("A", "T"): MBID})
mbid, label = fn("A", "T")
assert (mbid, label) == (MBID, SRC_DB)
assert recorded == {normalize_key("A", "T"): MBID} # fresh hit cached for next time
def test_falls_through_to_musicbrainz_and_caches():
fn, recorded = _wire(db={}, file={}, mb={("A", "T"): MBID})
mbid, label = fn("A", "T")
assert (mbid, label) == (MBID, SRC_MUSICBRAINZ)
assert list(recorded.values()) == [MBID]
def test_all_miss_returns_none_and_no_write():
fn, recorded = _wire()
assert fn("A", "T") == (None, None)
assert recorded == {}
# ── service track-id resolver (#945 export to Spotify/Deezer) ──
from core.exports.export_sources import (
db_service_track_id,
build_service_resolve_fn,
_SERVICE_ID_COLUMNS,
)
def test_service_id_column_mapping():
assert _SERVICE_ID_COLUMNS == {'spotify': 'spotify_track_id', 'deezer': 'deezer_id'}
def test_db_service_track_id_unknown_service_is_none():
assert db_service_track_id('A', 'X', 'tidal') is None
assert db_service_track_id('A', 'X', '') is None
def test_db_service_track_id_no_title_is_none():
assert db_service_track_id('A', '', 'spotify') is None
def test_build_service_resolve_fn_returns_id_and_source(monkeypatch):
import core.exports.export_sources as es
monkeypatch.setattr(es, 'db_service_track_id',
lambda a, t, s: 'spid-99' if t == 'Hit' else None)
fn = build_service_resolve_fn('spotify')
assert fn('Artist', 'Hit') == ('spid-99', 'library')
assert fn('Artist', 'Miss') == (None, None)
def test_db_service_track_id_real_sql_executes(tmp_path, monkeypatch):
"""Run the ACTUAL query against a real (temp) tracks/artists schema — the broad
except→None in db_service_track_id would otherwise mask a column/join typo as
'no match' for every track (#945 verification)."""
import sqlite3
import types
import core.exports.export_sources as es
dbfile = tmp_path / "lib.db"
con = sqlite3.connect(str(dbfile))
con.executescript(
"CREATE TABLE artists (id TEXT PRIMARY KEY, name TEXT);"
"CREATE TABLE tracks (id TEXT, artist_id TEXT, title TEXT, "
"spotify_track_id TEXT, deezer_id TEXT);"
"INSERT INTO artists VALUES ('a1','Kendrick Lamar');"
"INSERT INTO tracks VALUES ('t1','a1','Not Like Us','spid-NLU','dz-NLU');"
)
con.commit()
con.close()
# fresh connection per call (db_service_track_id closes it in finally)
fake_db = types.SimpleNamespace(_get_connection=lambda: sqlite3.connect(str(dbfile)))
monkeypatch.setattr("database.music_database.get_database", lambda: fake_db)
assert es.db_service_track_id("Kendrick Lamar", "Not Like Us", "spotify") == "spid-NLU"
assert es.db_service_track_id("kendrick lamar", "not like us", "deezer") == "dz-NLU" # case-insensitive
assert es.db_service_track_id("Kendrick Lamar", "Unknown Song", "spotify") is None
# ── discovery-cache resolution (#945: use the already-discovered IDs, no API call) ──
import json as _json
from core.exports.export_sources import (
service_id_from_extra_data,
resolve_service_track_ids,
)
def _extra(service, tid, discovered=True, provider=None):
return {'extra_data': _json.dumps({'discovered': discovered,
'provider': provider or service,
'matched_data': {'id': tid}})}
def test_extra_data_id_when_discovered_to_that_service():
assert service_id_from_extra_data(_extra('deezer', 111), 'deezer') == '111'
# dict (not str) extra_data also works
raw = {'extra_data': {'discovered': True, 'provider': 'spotify', 'matched_data': {'id': 'spX'}}}
assert service_id_from_extra_data(raw, 'spotify') == 'spX'
def test_extra_data_provider_must_match_service():
# discovered to Spotify, exporting to Deezer → don't reuse the (wrong-service) id
assert service_id_from_extra_data(_extra('spotify', 111), 'deezer') is None
def test_extra_data_wing_it_fallback_is_not_trusted():
track = _extra('deezer', 111, provider='wing_it_fallback')
assert service_id_from_extra_data(track, 'deezer') is None
def test_extra_data_misc_none_cases():
assert service_id_from_extra_data({}, 'deezer') is None # no extra_data
assert service_id_from_extra_data({'extra_data': 'not json{'}, 'deezer') is None # bad json
assert service_id_from_extra_data(_extra('deezer', 111, discovered=False), 'deezer') is None
def test_resolve_waterfall_cache_then_library_then_unmatched():
tracks = [
_extra('deezer', 111) | {'artist_name': 'A', 'track_name': 'Cached'}, # cache hit
{'artist_name': 'A', 'track_name': 'InLib'}, # library hit (db_fn)
{'artist_name': 'A', 'track_name': 'Nowhere'}, # unmatched
]
db_fn = lambda a, t, s: 'lib-222' if t == 'InLib' else None
out = resolve_service_track_ids(tracks, 'deezer', db_fn=db_fn)
ids = [r['service_track_id'] for r in out['resolved']]
assert ids == ['111', 'lib-222', None]
s = out['stats']
assert s == {'total': 3, 'resolved': 2, 'unmatched': 1, 'from_cache': 1, 'from_library': 1}