Migration 0050 adds candidate_artist_tags + candidate_artist_tag_state: folksonomy tags for artists NOT in the library, which track_tags cannot hold because it's FK'd to tracks(id) and a Discover candidate has no local row. Slice 6 ranks against these; this slice only fills the cache. The reuse the task claimed is real and verified: MusicBrainz's fetchEntityTags(ctx, "artist", mbid, scale) already existed for the #1519 recording→artist fallback, so FetchArtistTags is a thin wrapper. Two subtleties it does NOT inherit: - Weight scale is 1.0, not artistTagWeightFactor (0.6). That discount exists because FetchTrackTags uses artist tags as a *proxy* for a track's; here the artist IS the subject. Applying it would make these weights incomparable with track_tags — exactly the comparison slice 6 depends on. Pinned by a test. - fetchEntityTags reports existing-but-untagged as (empty, nil) so the track path can fall through. There's no next level here, so empty becomes the terminal ErrNotFound; otherwise the enricher would settle a candidate as "enriched" with zero tags. ArtistTagProvider is the split TrackTagProvider's own doc comment anticipated ("e.g. artist-level tags"). Last.fm gains artist.getTopTags, which returns the same toptags envelope, so the response type and normalizer are reused unchanged. Rather than write the merge-and-classify loop twice, extracted it from EnrichTrack into runChain(). The ErrNotFound-vs-transient split is the load-bearing part — those lead to opposite persistence decisions — so it now has direct unit tests it never had while inlined. Bookkeeping is a separate table, not columns, because the "providers had nothing" outcome must be recordable for a candidate with zero tag rows, and there is no per-candidate row to hang columns off ( artist_similarity_unmatched holds many rows per candidate). Absence of a state row means "never processed", so a transient failure writes nothing and stays eligible. Two capacity realities are designed for, not papered over: - The pool is O(library artists x neighbours) and MusicBrainz allows ~1 req/s, so it can never drain in one pass. The eligibility query returns candidates in descending summed-similarity order, so the ones that can actually reach a deck are enriched first. - candidateBatch (50) is smaller than the track batch (200): tracks are finite and drain to completion, candidates are effectively unbounded and would otherwise starve the track arm forever. GC sweeps both tables — the similarity feed churns, and a candidate that joins the library has its tags in track_tags now. Tags swept before state so a mid-sweep crash leaves a valid state, not a re-fetch loop. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
126 lines
5.1 KiB
Go
126 lines
5.1 KiB
Go
// Package dbtest provides shared helpers for integration tests that need
|
|
// a clean Postgres state without disturbing the operator's admin user.
|
|
//
|
|
// Background: when integration tests run against the same Postgres
|
|
// instance an operator uses for local dev (a common dev-laptop setup),
|
|
// a TRUNCATE that includes the users table wipes the operator's admin
|
|
// login between every test run. To avoid that, tests should:
|
|
//
|
|
// 1. Call ResetDB instead of issuing TRUNCATE statements directly. It
|
|
// truncates every data table EXCEPT users, then deletes only those
|
|
// users whose username starts with TestUserPrefix.
|
|
// 2. Always create test user rows with a username that begins with
|
|
// TestUserPrefix; otherwise those rows survive across runs and
|
|
// leak into other tests.
|
|
//
|
|
// One test legitimately needs to wipe the entire users table:
|
|
// internal/auth/bootstrap_test.go, which exercises first-time admin
|
|
// bootstrap. That file does its own TRUNCATE and does not use this
|
|
// helper.
|
|
package dbtest
|
|
|
|
import (
|
|
"context"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/jackc/pgx/v5/pgxpool"
|
|
)
|
|
|
|
// TestUserPrefix is the required username prefix for any user row
|
|
// created by an integration test. ResetDB removes every user matching
|
|
// this prefix and leaves all others intact.
|
|
const TestUserPrefix = "test-"
|
|
|
|
// dataTables is the union of every non-users table touched by any
|
|
// integration test in the repo. Truncating the union is harmless for
|
|
// callers that only care about a subset; truncating tables that don't
|
|
// exist would error, but every name here corresponds to a migration
|
|
// that has shipped.
|
|
var dataTables = []string{
|
|
"artist_similarity",
|
|
"track_similarity",
|
|
"artist_similarity_unmatched", // M5c
|
|
"scrobble_queue",
|
|
"contextual_likes",
|
|
"general_likes_albums",
|
|
"general_likes_artists",
|
|
"general_likes",
|
|
"play_events",
|
|
"skip_events",
|
|
"play_sessions",
|
|
"sessions",
|
|
"lidarr_quarantine_actions",
|
|
"lidarr_quarantine",
|
|
// #2374. Keyed by (user_id, candidate_mbid) with no FK to artists —
|
|
// candidates are out-of-library — so the CASCADE from artists/users
|
|
// does NOT reach it for a leftover row whose user survived. Truncate
|
|
// explicitly or a stale snooze silently hides a candidate from the
|
|
// next test's suggestion assertions.
|
|
"suggestion_snoozes",
|
|
// #2376. Same reasoning: keyed by candidate MBID with no FK anywhere,
|
|
// so nothing cascades to them. A leftover tag row would make a
|
|
// candidate look enriched to the next test, and a leftover state row
|
|
// would make it look already-settled and thus ineligible.
|
|
"candidate_artist_tags",
|
|
"candidate_artist_tag_state",
|
|
"playlist_tracks",
|
|
"playlists",
|
|
"library_changes", // M7 #357 — must reset to keep cursor isolated per test
|
|
// SettingsService.reconcile() idempotently re-UpsertProviderSettings
|
|
// for every registered provider at boot, so truncating this is the
|
|
// correct per-test reset (clears test-modified enabled/api_key rows).
|
|
// cover_art_sources_meta is NOT truncated — boot only READS it
|
|
// (never recreates the singleton, seeded once by 0018); ResetDB
|
|
// resets its counter via UPDATE below instead.
|
|
"cover_art_provider_settings",
|
|
// Same reasoning for the tag-enrichment settings (#1490): truncate the
|
|
// per-provider rows (reconcile re-seeds registered ones), and reset the
|
|
// tag_sources_meta counter via UPDATE below rather than truncating it.
|
|
"tag_provider_settings",
|
|
// recsettings.New reconciles shipped defaults on every construction
|
|
// (#1250), so truncating gives each test pristine tuning values.
|
|
"recommendation_weight_profiles",
|
|
"taste_tuning",
|
|
"recommendation_tuning_audit",
|
|
"tracks",
|
|
"albums",
|
|
"artists",
|
|
}
|
|
|
|
// ResetDB clears all data tables and removes any user whose username
|
|
// begins with TestUserPrefix. Users without that prefix (notably the
|
|
// operator's admin row) are left alone. Calls t.Fatalf on error.
|
|
func ResetDB(t *testing.T, pool *pgxpool.Pool) {
|
|
t.Helper()
|
|
ctx := context.Background()
|
|
stmt := "TRUNCATE " + strings.Join(dataTables, ", ") + " RESTART IDENTITY CASCADE"
|
|
if _, err := pool.Exec(ctx, stmt); err != nil {
|
|
t.Fatalf("dbtest.ResetDB truncate: %v", err)
|
|
}
|
|
if _, err := pool.Exec(ctx,
|
|
"DELETE FROM users WHERE username LIKE $1",
|
|
TestUserPrefix+"%",
|
|
); err != nil {
|
|
t.Fatalf("dbtest.ResetDB delete test users: %v", err)
|
|
}
|
|
// Reset the monotonic cover-art source-version counter to its
|
|
// post-migration seeded value. Truncating the row would break
|
|
// SettingsService boot, which reads (never recreates) this
|
|
// singleton; an UPDATE keeps the row while clearing cross-test
|
|
// version accumulation (CurrentVersion=4 want 1, key-only-bump).
|
|
if _, err := pool.Exec(ctx,
|
|
"UPDATE cover_art_sources_meta SET current_version = 1",
|
|
); err != nil {
|
|
t.Fatalf("dbtest.ResetDB reset cover-art version: %v", err)
|
|
}
|
|
// Same for the tag-sources counter (#1490) — clears cross-test version
|
|
// accumulation that would spuriously report version_bumped on a
|
|
// key-only change.
|
|
if _, err := pool.Exec(ctx,
|
|
"UPDATE tag_sources_meta SET current_version = 1, last_registered_providers_hash = ''",
|
|
); err != nil {
|
|
t.Fatalf("dbtest.ResetDB reset tag-sources version: %v", err)
|
|
}
|
|
}
|