NaviWatcher/internal/musicbrainz/sync.go

package musicbrainz

import (
	"context"
	"database/sql"
	"fmt"
	"strings"
	"time"

	"naviwatcher/internal/database"
)

// SyncArtistDiscography synchronizes an artist's discography from MusicBrainz
// into the local external_releases table. It follows this flow:
//  1. Check if cached data exists and is within TTL.
//  2. If cache hit, return the cached releases immediately.
//  3. If cache miss or expired, fetch release groups from MusicBrainz API.
//  4. Apply status and type filtering.
//  5. Within a transaction: delete old entries, then upsert each filtered release group.
//  6. Return the list of external releases.
//
// artistID is the canonical artist key from artist_settings (the Navidrome
// artist ID). It is stored as external_releases.artist_id so that the foreign
// key to artist_settings and the scanner's join on ArtistID resolve correctly.
// artistMBID is the MusicBrainz ID used only to query the MusicBrainz API.
//
// Context cancellation is checked before the API call and between each upsert
// to allow graceful interruption.
func SyncArtistDiscography(
	ctx context.Context,
	client *MusicBrainzClient,
	db *database.DB,
	artistID string,
	artistMBID string,
	ttl time.Duration,
) ([]database.ExternalRelease, error) {
	// Check context before starting.
	if err := ctx.Err(); err != nil {
		return nil, fmt.Errorf("sync artist discography: %w", err)
	}

	// Step 1: Check cache freshness. A genuine hit means the artist was synced
	// within the TTL — even when it has zero release groups. We must not gate on
	// row count, or artists with an empty MusicBrainz discography would be
	// re-fetched on every sync (defeating the TTL and wasting the 1 req/s budget).
	cachedReleases, err := database.GetExternalReleasesByArtistWithCache(db, artistID, ttl)
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: cache check failed: %w", err)
	}
	fresh, err := database.ArtistCacheFresh(db, artistID, ttl)
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: cache freshness check failed: %w", err)
	}

	// Step 2: If we have a fresh cache, return the cached data. Re-apply the
	// per-artist type toggles even on a cache hit so user changes to
	// ignore_singles / ignore_compilations take effect without waiting for cache
	// expiry. (Status/type inclusion was already applied when the rows were first
	// synced and stored, so only the toggles can change.)
	//
	// The MusicBrainz sync path applies filtering at store-time (when caching
	// release groups from the API), while the scanner path applies filtering at
	// read-time (when retrieving cached data). This dual-path approach ensures:
	// 1. Storage efficiency: filtered results are stored, reducing database size
	// 2. Real-time responsiveness: changes to ignore_singles/ignore_compilations
	//    take effect immediately without waiting for cache expiry
	// 3. Consistency: both paths use the same filtering logic via
	//    musicbrainz.ApplyTypeToggles
	if fresh {
		if err := ctx.Err(); err != nil {
			return nil, fmt.Errorf("sync artist discography: %w", err)
		}
		opts, err := getArtistFilterOptions(db, artistID)
		if err != nil {
			return nil, fmt.Errorf("sync artist discography: read artist filter options: %w", err)
		}
		filtered := ApplyTypeToggles(cachedReleases, opts)
		return filtered, nil
	}

	// Step 3: Cache miss — fetch from MusicBrainz API.
	groups, err := client.GetArtistReleaseGroups(ctx, artistMBID)
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: fetch release groups for artist %s: %w", artistMBID, err)
	}

	// Step 4: Apply filtering with per-artist type preferences.
	opts, err := getArtistFilterOptions(db, artistID)
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: read artist filter options: %w", err)
	}
	filtered := FilterReleaseGroups(groups, opts)

	// Step 5: Upsert within a transaction — delete old entries first, then insert new ones.
	now := time.Now().UTC()
	tx, err := db.Begin()
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: begin transaction: %w", err)
	}
	defer tx.Rollback()

	// Read existing ignore states before deleting to preserve user-set flags.
	ignoredMap := map[string]bool{}
	rows, err := tx.Query("SELECT rgid, is_ignored FROM external_releases WHERE artist_id = ?", artistID)
	if err != nil {
		return nil, fmt.Errorf("sync artist discography: query existing releases: %w", err)
	}
	for rows.Next() {
		var rgid string
		var ignored bool
		if err := rows.Scan(&rgid, &ignored); err != nil {
			rows.Close()
			return nil, fmt.Errorf("sync artist discography: scan existing release: %w", err)
		}
		ignoredMap[rgid] = ignored
	}
	if err := rows.Err(); err != nil {
		rows.Close()
		return nil, fmt.Errorf("sync artist discography: iterate existing releases: %w", err)
	}
	rows.Close()

	// Build the set of RGIDs present in this sync so we can drop only the rows
	// that disappeared, leaving the rest (and their notification markers) intact.
	synced := make([]string, 0, len(filtered))
	for _, rg := range filtered {
		synced = append(synced, rg.ID)
	}

	// Drop notification markers for releases that are gone. This runs before the
	// external_releases delete so the FK on notifications_sent.rgid stays valid
	// (we only ever delete from notifications_sent here).
	// Process in chunks to avoid SQLite parameter limits (default limit is 999).
	if len(synced) > 0 {
		const chunkSize = 500
		for i := 0; i < len(synced); i += chunkSize {
			end := i + chunkSize
			if end > len(synced) {
				end = len(synced)
			}
			chunk := synced[i:end]

			placeholders := strings.Repeat("?,", len(chunk))
			placeholders = placeholders[:len(placeholders)-1]
			query := fmt.Sprintf(
				"DELETE FROM notifications_sent WHERE rgid IN (SELECT rgid FROM external_releases WHERE artist_id = ? AND rgid NOT IN (%s))",
				placeholders,
			)
			args := make([]any, 1+len(chunk))
			args[0] = artistID
			for i, v := range chunk {
				args[i+1] = v
			}
			if _, err := tx.Exec(query, args...); err != nil {
				return nil, fmt.Errorf("sync artist discography: prune stale notifications (chunk %d-%d): %w", i, end, err)
			}
		}

		// Remove external_release rows that are no longer part of the discography.
		// Process in chunks to avoid SQLite parameter limits.
		for i := 0; i < len(synced); i += chunkSize {
			end := i + chunkSize
			if end > len(synced) {
				end = len(synced)
			}
			chunk := synced[i:end]

			placeholders := strings.Repeat("?,", len(chunk))
			placeholders = placeholders[:len(placeholders)-1]
			delQuery := fmt.Sprintf(
				"DELETE FROM external_releases WHERE artist_id = ? AND rgid NOT IN (%s)",
				placeholders,
			)
			args := make([]any, 1+len(chunk))
			args[0] = artistID
			for i, v := range chunk {
				args[i+1] = v
			}
			if _, err := tx.Exec(delQuery, args...); err != nil {
				return nil, fmt.Errorf("sync artist discography: delete stale releases (chunk %d-%d): %w", i, end, err)
			}
		}
	} else {
		// No releases this sync: the artist may have an empty discography. Drop
		// everything we previously cached for them.
		if _, err := tx.Exec("DELETE FROM notifications_sent WHERE rgid IN (SELECT rgid FROM external_releases WHERE artist_id = ?)", artistID); err != nil {
			return nil, fmt.Errorf("sync artist discography: delete notifications: %w", err)
		}
		if _, err := tx.Exec("DELETE FROM external_releases WHERE artist_id = ?", artistID); err != nil {
			return nil, fmt.Errorf("sync artist discography: delete old releases: %w", err)
		}
	}

	var releases []database.ExternalRelease
	for _, rg := range filtered {
		// Check context cancellation between each upsert.
		if err := ctx.Err(); err != nil {
			return nil, fmt.Errorf("sync artist discography: %w", err)
		}

		ext := rg.ToExternalRelease(artistID)
		ext.CachedAt = now
		// Preserve user-set ignore flag from previous sync.
		if ignored, ok := ignoredMap[ext.RGID]; ok {
			ext.IsIgnored = ignored
		}

		if _, err := tx.Exec(
			"INSERT OR REPLACE INTO external_releases (rgid, artist_id, title, type, release_date, is_ignored, cached_at, secondary_types) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
			ext.RGID, ext.ArtistID, ext.Title, ext.Type, ext.ReleaseDate, ext.IsIgnored, database.FormatCachedAt(ext.CachedAt), database.JoinSecondaryTypes(ext.SecondaryTypes),
		); err != nil {
			return nil, fmt.Errorf("sync artist discography: insert release %s: %w", rg.ID, err)
		}

		releases = append(releases, *ext)
	}

	// Mark the artist as synced (even when it has zero release groups) so the
	// cache TTL honours empty discographies and they are not re-fetched every
	// cycle.
	if err := database.TouchArtistSynced(tx, artistID, now); err != nil {
		return nil, fmt.Errorf("sync artist discography: touch last_synced: %w", err)
	}

	if err := tx.Commit(); err != nil {
		return nil, fmt.Errorf("sync artist discography: commit transaction: %w", err)
	}

	return releases, nil
}

// getArtistFilterOptions reads per-artist type filtering preferences.
// Defaults to no filtering if artist_settings row doesn't exist.
// artistID is the Navidrome artist ID (artist_settings.id), not the MusicBrainz ID.
func getArtistFilterOptions(db *database.DB, artistID string) (FilterOptions, error) {
	var opts FilterOptions
	err := db.Conn().QueryRow(
		"SELECT COALESCE(ignore_singles, 0), COALESCE(ignore_compilations, 0) FROM artist_settings WHERE id = ?",
		artistID,
	).Scan(&opts.IgnoreSingles, &opts.IgnoreCompilations)
	if err == sql.ErrNoRows {
		return opts, nil
	}
	if err != nil {
		return opts, fmt.Errorf("query artist filter options: %w", err)
	}
	return opts, nil
}