diff --git a/core/library.go b/core/library.go index 0bf3be9fa..365dcbd4c 100644 --- a/core/library.go +++ b/core/library.go @@ -253,7 +253,11 @@ func (r *libraryRepositoryWrapper) Delete(id string) error { return r.mapError(err) } - err = r.LibraryRepository.Delete(libID) + // Run the deletion in a transaction so the cascade delete and the orphaned-artist + // reconciliation it triggers (see libraryRepository.Delete) commit atomically. + err = r.ds.WithTx(func(tx model.DataStore) error { + return tx.Library(r.ctx).Delete(libID) + }, "delete library") if err != nil { return r.mapError(err) } diff --git a/persistence/artist_repository.go b/persistence/artist_repository.go index aa3bc0776..56843b911 100644 --- a/persistence/artist_repository.go +++ b/persistence/artist_repository.go @@ -353,6 +353,19 @@ func (r *artistRepository) purgeEmpty() error { return nil } +// markOrphansMissing flags as missing any non-missing artist with no library_artist row, keeping the +// search fast-path's `missing = false` filter correct (see searchCfg). Called wherever such a row can +// be dropped: RefreshStats cleanup and library deletion cascade. +func (r *artistRepository) markOrphansMissing() error { + _, err := r.executeSQL(Expr( + "update artist set missing = true where missing = false " + + "and not exists (select 1 from library_artist where library_artist.artist_id = artist.id)")) + if err != nil { + return fmt.Errorf("marking orphaned artists missing: %w", err) + } + return nil +} + // markMissing marks artists as missing if all their albums are missing. func (r *artistRepository) markMissing() error { q := Expr(` @@ -527,57 +540,156 @@ func (r *artistRepository) RefreshStats(allArtists bool) (int64, error) { totalRowsAffected += rowsAffected } - // // Remove library_artist entries for artists that no longer have any content in any library + // Remove library_artist entries for artists that no longer have any content in a library. cleanupSQL := Delete("library_artist").Where("stats = '{}'") cleanupRows, err := r.executeSQL(cleanupSQL) if err != nil { - log.Warn(r.ctx, "Failed to cleanup empty library_artist entries", "error", err) - } else if cleanupRows > 0 { - log.Debug(r.ctx, "Cleaned up empty library_artist entries", "rowsDeleted", cleanupRows) + log.Warn(r.ctx, "Failed to cleanup empty library_artist entries", err) + } else { + if cleanupRows > 0 { + log.Debug(r.ctx, "Cleaned up empty library_artist entries", "rowsDeleted", cleanupRows) + } + // Reconcile orphans whenever the cleanup removed rows, and on a full refresh so a full scan + // also heals any left by older versions. + if cleanupRows > 0 || allArtists { + if err := r.markOrphansMissing(); err != nil { + log.Warn(r.ctx, "Failed to mark orphaned artists missing after library_artist cleanup", err) + } + } } log.Debug(r.ctx, "RefreshStats: Successfully updated stats.", "totalArtistsProcessed", len(allTouchedArtistIDs), "totalDBRowsAffected", totalRowsAffected) return totalRowsAffected, nil } -// applyLibraryFilterToSearchQuery is applyLibraryFilterToArtistQuery with the join order -// pinned via CROSS JOIN (SQLite's explicit join-order override): the search Phase 1 paginates -// rowids by artist.id, and when the planner drives from library_artist it must sort every -// junction row on every page (temp b-tree over the whole table). Keeping artist as the outer -// table streams rows in artist.id order from its primary key index, so LIMIT/OFFSET -// short-circuits. Search-only: other artist queries keep the planner's freedom. -func (r *artistRepository) applyLibraryFilterToSearchQuery(query SelectBuilder) SelectBuilder { - user := loggedUser(r.ctx) - query = query.CrossJoin("library_artist on library_artist.artist_id = artist.id") - if user.ID != invalidUserId && !user.IsAdmin { - query = query.Join("user_library on user_library.library_id = library_artist.library_id AND user_library.user_id = ?", user.ID) - } - return query -} - -func (r *artistRepository) searchCfg() searchConfig { +// searchCfg builds the per-search config. scope is the set of library IDs the rowid Phase 1 must +// restrict artists to, or nil to skip the filter (fast-path). See [artistRepository.searchScope]. +func (r *artistRepository) searchCfg(scope []int) searchConfig { return searchConfig{ // Natural order for artists is more performant by ID, due to GROUP BY clause in selectArtist - NaturalOrder: "artist.id", - OrderBy: []string{"sum(json_extract(stats, '$.total.m')) desc", "name"}, - MBIDFields: []string{"mbz_artist_id"}, - LibraryFilter: r.applyLibraryFilterToSearchQuery, + NaturalOrder: "artist.id", + OrderBy: []string{"sum(json_extract(stats, '$.total.m')) desc", "name"}, + MBIDFields: []string{"mbz_artist_id"}, + // scope==nil is the fast-path: no filter (and orphans must not exist — see markOrphansMissing). + // Otherwise the join-free [artistLibraryFilter]. + LibraryFilter: func(query SelectBuilder) SelectBuilder { + if scope == nil { + return query + } + return query.Where(artistLibraryFilter(scope)) + }, } } +// artistLibraryFilter restricts artists to the given libraries via a correlated EXISTS over the +// library_artist junction, staying join-free so it can scope the join-free search Phase 1 (a JOIN +// would fan out rowids and corrupt offset pagination). The inner LIMIT 1 is load-bearing: it stops +// SQLite from flattening the EXISTS back into a fan-out join, while still using the +// (library_id, artist_id) UNIQUE autoindex. +func artistLibraryFilter(libraryIDs []int) Sqlizer { + if len(libraryIDs) == 0 { + return Eq{"1": 2} // match nothing, without a degenerate `IN ()` subquery + } + sub, args, _ := Select("1").From("library_artist"). + Where(And{ + Expr("library_artist.artist_id = artist.id"), + Eq{"library_artist.library_id": libraryIDs}, + }).Limit(1).ToSql() + return Expr("EXISTS ("+sub+")", args...) +} + func (r *artistRepository) Search(q string, options ...model.QueryOptions) (model.Artists, error) { var opts model.QueryOptions if len(options) > 0 { opts = options[0] } + // Artists have no library_id column, so the library_id filter callers pass (same as albums/songs) + // can't be applied directly: consume it and realize it as a join-free Phase-1 scope (searchCfg). + scope := r.searchScope(opts.Filters) + if isLibraryIDFilter(opts.Filters) { + opts.Filters = nil + } var res dbArtists - err := r.doSearch(r.selectArtist(options...), q, &res, r.searchCfg(), opts) + err := r.doSearch(r.selectArtist(opts), q, &res, r.searchCfg(scope), opts) if err != nil { return nil, fmt.Errorf("searching artist %q: %w", q, err) } return res.toModels(), nil } +// searchScope returns the library IDs the search must be restricted to, or nil to skip the filter +// entirely (the fast-path: the user sees everything the search could return, so a filter would be +// pure O(offset) overhead). It intersects the requested libraries with what the user can see. +func (r *artistRepository) searchScope(filter Sqlizer) []int { + visible, err := r.visibleLibraryIDs() + if err != nil { + return r.requestedLibraryIDs(filter) // fail safe: narrow to the request rather than widen + } + requested := r.requestedLibraryIDs(filter) + if requested == nil { + // No explicit request: scope to the visible set, unless the user sees everything. + if r.userSeesAllLibraries(visible) { + return nil + } + return visible + } + // Narrow unless the request already covers everything the user can see. Compare by membership, + // not length: the requested IDs may contain duplicates. + requestedSet := slice.ToSet(requested) + if slices.ContainsFunc(visible, func(id int) bool { _, ok := requestedSet[id]; return !ok }) { + return requested + } + return nil +} + +// requestedLibraryIDs extracts the []int from an Eq{"library_id": ids} filter, or nil if filter is +// not that shape. +func (r *artistRepository) requestedLibraryIDs(filter Sqlizer) []int { + eq, ok := filter.(Eq) + if !ok { + return nil + } + ids, _ := eq["library_id"].([]int) + return ids +} + +// isLibraryIDFilter reports whether the filter is an Eq carrying a library_id key, so Search can +// consume it before it reaches the bare artist table (which has no library_id column). +func isLibraryIDFilter(filter Sqlizer) bool { + eq, ok := filter.(Eq) + if !ok { + return false + } + _, ok = eq["library_id"] + return ok +} + +// userSeesAllLibraries reports whether the visible set already covers every library, so a search +// needs no library filter at all. +func (r *artistRepository) userSeesAllLibraries(visible []int) bool { + user := loggedUser(r.ctx) + if user.IsAdmin || user.ID == invalidUserId { + return true // visible is the whole library table + } + total, err := NewLibraryRepository(r.ctx, r.db).CountAll() + if err != nil || total == 0 { + return false + } + return int64(len(visible)) >= total +} + +// visibleLibraryIDs returns the libraries the current user can see: all libraries for admin and +// headless processes, otherwise the user's granted libraries. +func (r *artistRepository) visibleLibraryIDs() ([]int, error) { + user := loggedUser(r.ctx) + if user.IsAdmin || user.ID == invalidUserId { + var ids []int + err := r.queryAllSlice(Select("id").From("library"), &ids) + return ids, err + } + return slice.Map(user.Libraries, func(lib model.Library) int { return lib.ID }), nil +} + func (r *artistRepository) Count(options ...rest.QueryOptions) (int64, error) { return r.CountAll(r.parseRestOptions(r.ctx, options...)) } diff --git a/persistence/artist_repository_test.go b/persistence/artist_repository_test.go index 7003efec3..603c5dd5e 100644 --- a/persistence/artist_repository_test.go +++ b/persistence/artist_repository_test.go @@ -111,6 +111,80 @@ var _ = Describe("ArtistRepository", func() { }) }) + Describe("searchScope", func() { + // Resolves the library IDs a search must be restricted to (nil = fast-path / no filter), + // the way Search() does, for a repo whose context carries the given user. + scope := func(user model.User, filter squirrel.Sqlizer) []int { + ctx := request.WithUser(GinkgoT().Context(), user) + r := NewArtistRepository(ctx, GetDBXBuilder()).(*artistRepository) + return r.searchScope(filter) + } + subsetUser := model.User{ID: "u", Libraries: model.Libraries{{ID: 1}, {ID: 2}, {ID: 3}}} + + It("scopes to a strict subset of the user's libraries", func() { + Expect(scope(subsetUser, squirrel.Eq{"library_id": []int{1, 2}})).To(Equal([]int{1, 2})) + }) + + It("treats duplicate IDs as a set so a real subset still narrows", func() { + // {1,1,2} has 3 entries but is a strict subset of the user's 3 libraries. + Expect(scope(subsetUser, squirrel.Eq{"library_id": []int{1, 1, 2}})).To(Equal([]int{1, 1, 2})) + }) + + It("returns nil (fast-path) when the request covers all the user's libraries", func() { + Expect(scope(subsetUser, squirrel.Eq{"library_id": []int{1, 2, 3}})).To(BeNil()) + }) + + It("scopes to the user's libraries when no library filter is given", func() { + // A restricted user (strictly fewer libs than exist) with no musicFolderId is still + // confined to their granted libs. Build the user with total-1 libraries derived from + // the real DB total, so the "sees all" fast-path can't kick in regardless of count. + total, err := NewLibraryRepository(GinkgoT().Context(), GetDBXBuilder()).CountAll() + Expect(err).ToNot(HaveOccurred()) + Expect(total).To(BeNumerically(">", 0)) + libs := make(model.Libraries, 0, total-1) + for i := int64(1); i < total; i++ { // total-1 distinct libraries → a strict subset + libs = append(libs, model.Library{ID: int(i)}) + } + restricted := model.User{ID: "r", Libraries: libs} + got := scope(restricted, nil) + Expect(got).To(HaveLen(int(total) - 1)) + }) + + It("returns nil (fast-path) for an admin requesting all existing libraries", func() { + // Admins see every library, so the visible set is the whole library table — derive + // it from the DB rather than assuming a count. + var allLibs []int + Expect(NewLibraryRepository(GinkgoT().Context(), GetDBXBuilder()).(*libraryRepository). + queryAllSlice(squirrel.Select("id").From("library"), &allLibs)).To(Succeed()) + admin := model.User{ID: "a", IsAdmin: true} + Expect(scope(admin, squirrel.Eq{"library_id": allLibs})).To(BeNil()) + Expect(scope(admin, nil)).To(BeNil()) + }) + + It("narrows for an admin explicitly requesting a subset via musicFolderId", func() { + // An admin scoping to a single, non-existent-as-the-whole-set library must still be + // narrowed (regression: search3?musicFolderId=lib2 was leaking lib1 content). + admin := model.User{ID: "a", IsAdmin: true} + Expect(scope(admin, squirrel.Eq{"library_id": []int{-1}})).To(Equal([]int{-1})) + }) + + It("returns nil for a non-library_id filter (no library scoping requested)", func() { + // Such a filter carries no library intent; for this fully-granted-style user the + // search needs no extra library restriction. + allUser := model.User{ID: "u2", IsAdmin: true} + Expect(scope(allUser, squirrel.Eq{"name": "x"})).To(BeNil()) + }) + + It("falls back to the visible scope for a malformed library_id value (no crash)", func() { + // A library_id filter whose value isn't []int is still recognized as a library + // filter (so Search consumes it and it never reaches the bare artist table), and + // searchScope falls back to exactly the no-filter behavior rather than crashing. + malformed := squirrel.Eq{"library_id": "not-a-slice"} + Expect(isLibraryIDFilter(malformed)).To(BeTrue()) + Expect(scope(subsetUser, malformed)).To(Equal(scope(subsetUser, nil))) + }) + }) + Describe("dbArtist mapping", func() { var ( artist *model.Artist @@ -653,6 +727,38 @@ var _ = Describe("ArtistRepository", func() { _, _ = raw.executeSQL(squirrel.Delete(raw.tableName).Where(squirrel.Eq{"id": lib2Artist.ID})) } }) + + It("paginates a restricted user's visible artists without gaps", func() { + // ID "25" sorts between base fixtures "2" and "3", so this lib2-only artist lands + // inside the restricted user's visible range — exercising the no-gap guarantee. + lib2Artist := model.Artist{ID: "25", Name: "Restricted Lib2 Artist"} + Expect(repo.Put(&lib2Artist)).To(Succeed()) + Expect(lr.AddArtist(lib2.ID, lib2Artist.ID)).To(Succeed()) + DeferCleanup(func() { + if raw, ok := repo.(*artistRepository); ok { + _, _ = raw.executeSQL(squirrel.Delete(raw.tableName).Where(squirrel.Eq{"id": lib2Artist.ID})) + } + }) + + all, err := restrictedRepo.Search("", model.QueryOptions{Max: 1000}) + Expect(err).ToNot(HaveOccurred()) + Expect(len(all)).To(BeNumerically(">", 1)) + for _, a := range all { + Expect(a.ID).ToNot(Equal(lib2Artist.ID)) + } + + var paged model.Artists + for offset := range len(all) { + page, err := restrictedRepo.Search("", model.QueryOptions{Max: 1, Offset: offset}) + Expect(err).ToNot(HaveOccurred()) + Expect(page).To(HaveLen(1), fmt.Sprintf("page at offset %d should be full", offset)) + paged = append(paged, page...) + } + Expect(paged).To(HaveLen(len(all))) + for i := range all { + Expect(paged[i].ID).To(Equal(all[i].ID)) + } + }) }) Context("Headless Processes (No User Context)", func() { @@ -891,6 +997,45 @@ var _ = Describe("ArtistRepository", func() { Expect(err).ToNot(HaveOccurred()) Expect(idx).To(HaveLen(0)) }) + + It("takes the unfiltered fast-path when the user can access every library", func() { + // The fixture DB has a single library and the user was granted it, so it has access + // to all libraries: search results must match what an admin sees. + adminRepo := NewArtistRepository(request.WithUser(GinkgoT().Context(), adminUser), GetDBXBuilder()) + adminAll, err := adminRepo.Search("", model.QueryOptions{Max: 1000}) + Expect(err).ToNot(HaveOccurred()) + + userAll, err := restrictedRepo.Search("", model.QueryOptions{Max: 1000}) + Expect(err).ToNot(HaveOccurred()) + + ids := func(artists model.Artists) []string { + out := make([]string, len(artists)) + for i, a := range artists { + out[i] = a.ID + } + return out + } + Expect(ids(userAll)).To(Equal(ids(adminAll))) + Expect(userAll).ToNot(BeEmpty()) + }) + + It("detects all-library access regardless of result equivalence", func() { + // userSeesAllLibraries drives the search fast-path for a non-admin: true when the + // visible-library count reaches the DB total. Derive the total from the DB so the + // assertion doesn't depend on how many libraries other specs left behind. + raw := restrictedRepo.(*artistRepository) // context carries a non-admin user + total, err := NewLibraryRepository(GinkgoT().Context(), GetDBXBuilder()).CountAll() + Expect(err).ToNot(HaveOccurred()) + Expect(total).To(BeNumerically(">", 0)) + + allLibs := make([]int, total) + for i := range allLibs { + allLibs[i] = i + 1 + } + Expect(raw.userSeesAllLibraries(allLibs)).To(BeTrue()) + Expect(raw.userSeesAllLibraries(allLibs[:total-1])).To(BeFalse()) + Expect(raw.userSeesAllLibraries([]int{})).To(BeFalse()) + }) }) }) @@ -976,6 +1121,66 @@ var _ = Describe("ArtistRepository", func() { Expect(err).ToNot(HaveOccurred()) }) }) + + Describe("RefreshStats", func() { + var repo *artistRepository + + missing := func(id string) bool { + var vals []bool + Expect(repo.queryAllSlice(squirrel.Select("missing").From("artist").Where(squirrel.Eq{"id": id}), &vals)).To(Succeed()) + Expect(vals).To(HaveLen(1)) + return vals[0] + } + + BeforeEach(func() { + ctx := request.WithUser(GinkgoT().Context(), adminUser) + repo = NewArtistRepository(ctx, GetDBXBuilder()).(*artistRepository) + }) + + It("marks artists missing when the empty-stats cleanup drops their last library_artist row", func() { + // A library_artist row with stats '{}' (no content) gets deleted by the cleanup, + // which would orphan this non-missing artist. + emptyArtist := model.Artist{ID: "refresh-empty", Name: "No Content Artist"} + Expect(repo.Put(&emptyArtist)).To(Succeed()) + _, err := repo.executeSQL(squirrel.Insert("library_artist"). + SetMap(map[string]any{"library_id": 1, "artist_id": emptyArtist.ID, "stats": "{}"})) + Expect(err).ToNot(HaveOccurred()) + DeferCleanup(func() { + _, _ = repo.executeSQL(squirrel.Delete("library_artist").Where(squirrel.Eq{"artist_id": emptyArtist.ID})) + _ = repo.delete(squirrel.Eq{"id": emptyArtist.ID}) + }) + + Expect(missing(emptyArtist.ID)).To(BeFalse()) + + _, err = repo.RefreshStats(true) + Expect(err).ToNot(HaveOccurred()) + + Expect(missing(emptyArtist.ID)).To(BeTrue()) + var orphanIDs []string + Expect(repo.queryAllSlice(squirrel.Select("id").From("artist"). + Where("missing = false"). + Where("id not in (select artist_id from library_artist)"), &orphanIDs)).To(Succeed()) + Expect(orphanIDs).ToNot(ContainElement(emptyArtist.ID)) + }) + + It("heals a pre-existing orphan (no library_artist row) on a full refresh", func() { + // A legacy orphan left by an older version: non-missing, with no library_artist row at + // all. The cleanup deletes nothing for it, so a full refresh (allArtists) must still + // reconcile it. + legacyOrphan := model.Artist{ID: "refresh-legacy-orphan", Name: "Legacy Orphan"} + Expect(repo.Put(&legacyOrphan)).To(Succeed()) + DeferCleanup(func() { + _ = repo.delete(squirrel.Eq{"id": legacyOrphan.ID}) + }) + + Expect(missing(legacyOrphan.ID)).To(BeFalse()) + + _, err := repo.RefreshStats(true) + Expect(err).ToNot(HaveOccurred()) + + Expect(missing(legacyOrphan.ID)).To(BeTrue()) + }) + }) }) // Helper function to create an artist with proper library association. diff --git a/persistence/library_repository.go b/persistence/library_repository.go index 1d8e6f35e..3789a71c9 100644 --- a/persistence/library_repository.go +++ b/persistence/library_repository.go @@ -261,6 +261,11 @@ func (r *libraryRepository) Delete(id int) error { return err } + // The cascade above can drop an artist's last library_artist row; reconcile any such orphans. + if err := NewArtistRepository(r.ctx, r.db).(*artistRepository).markOrphansMissing(); err != nil { + return fmt.Errorf("marking orphaned artists missing after deleting library %d: %w", id, err) + } + // Clear cache entry for this library only if DB operation was successful libLock.Lock() defer libLock.Unlock() diff --git a/persistence/library_repository_test.go b/persistence/library_repository_test.go index de7161643..1743df209 100644 --- a/persistence/library_repository_test.go +++ b/persistence/library_repository_test.go @@ -4,6 +4,7 @@ import ( "context" "time" + "github.com/Masterminds/squirrel" "github.com/navidrome/navidrome/log" "github.com/navidrome/navidrome/model" "github.com/navidrome/navidrome/model/request" @@ -206,4 +207,49 @@ var _ = Describe("LibraryRepository", func() { }) }) }) + + Describe("Delete", func() { + var adminRepo model.LibraryRepository + var artistRepo model.ArtistRepository + + artistMissing := func(id string) bool { + var missing bool + err := conn.NewQuery("SELECT missing FROM artist WHERE id = {:id}"). + Bind(dbx.Params{"id": id}).Row(&missing) + Expect(err).ToNot(HaveOccurred()) + return missing + } + + BeforeEach(func() { + adminCtx := request.WithUser(log.NewContext(context.TODO()), adminUser) + adminRepo = NewLibraryRepository(adminCtx, conn) + artistRepo = NewArtistRepository(adminCtx, conn) + }) + + It("marks artists orphaned by the delete as missing", func() { + lib := model.Library{Name: "Doomed Library", Path: "/doomed"} + Expect(adminRepo.Put(&lib)).To(Succeed()) + + orphanArtist := model.Artist{ID: "delete-orphan", Name: "Orphan To Be"} + sharedArtist := model.Artist{ID: "delete-shared", Name: "Shared Artist"} + Expect(artistRepo.Put(&orphanArtist)).To(Succeed()) + Expect(artistRepo.Put(&sharedArtist)).To(Succeed()) + Expect(adminRepo.AddArtist(lib.ID, orphanArtist.ID)).To(Succeed()) + Expect(adminRepo.AddArtist(lib.ID, sharedArtist.ID)).To(Succeed()) + Expect(adminRepo.AddArtist(1, sharedArtist.ID)).To(Succeed()) + DeferCleanup(func() { + if raw, ok := artistRepo.(*artistRepository); ok { + _, _ = raw.executeSQL(squirrel.Delete("artist"). + Where(squirrel.Eq{"id": []string{orphanArtist.ID, sharedArtist.ID}})) + } + }) + + Expect(artistMissing(orphanArtist.ID)).To(BeFalse()) + + Expect(adminRepo.Delete(lib.ID)).To(Succeed()) + + Expect(artistMissing(orphanArtist.ID)).To(BeTrue(), "orphaned artist should be marked missing") + Expect(artistMissing(sharedArtist.ID)).To(BeFalse(), "artist still in another library must stay visible") + }) + }) }) diff --git a/persistence/sql_search.go b/persistence/sql_search.go index 19cbaf24f..3049baae7 100644 --- a/persistence/sql_search.go +++ b/persistence/sql_search.go @@ -21,10 +21,9 @@ type searchConfig struct { NaturalOrder string // ORDER BY for empty-query results (e.g. "album.rowid") OrderBy []string // ORDER BY for text search results (e.g. ["name"]) MBIDFields []string // columns to match when query is a UUID - // LibraryFilter overrides the default applyLibraryFilter for the rowid Phase 1 of - // two-phase searches (FTS and empty-query). Needed when library access goes through a - // junction table (e.g. artist → library_artist), whose JOIN can fan out rowids for - // entities in multiple libraries — Phase 1 dedups whenever this is set. + // LibraryFilter overrides the default applyLibraryFilter for the rowid Phase 1, for entities whose + // library access goes through a junction table (e.g. artist → library_artist). It MUST be join-free + // (Phase 1 has no DISTINCT, so a fan-out JOIN would corrupt offset pagination). See [artistLibraryFilter]. LibraryFilter func(sq SelectBuilder) SelectBuilder } @@ -102,10 +101,7 @@ func (r sqlRepository) executeTwoPhase(sq SelectBuilder, results any, rowidCore rowidQuery = rowidQuery.Offset(uint64(options.Offset)) } if cfg.LibraryFilter != nil { - // Junction-table library filters can repeat rowids for entities in multiple - // libraries, which would corrupt offset-based pagination — dedup before paginating. - // (DISTINCT, not GROUP BY: bm25() can't be evaluated in a grouped query.) - rowidQuery = cfg.LibraryFilter(rowidQuery).Distinct() + rowidQuery = cfg.LibraryFilter(rowidQuery) } else { rowidQuery = r.applyLibraryFilter(rowidQuery) } diff --git a/scanner/scanner_test.go b/scanner/scanner_test.go index 7bf91d64f..cc3732bc3 100644 --- a/scanner/scanner_test.go +++ b/scanner/scanner_test.go @@ -2,6 +2,7 @@ package scanner_test import ( "context" + "database/sql" "errors" "path/filepath" "testing/fstest" @@ -531,6 +532,69 @@ var _ = Describe("Scanner", Ordered, func() { })).To(Equal(int64(2))) }) + It("leaves no non-missing orphan artist after purging an artist's only content", func() { + // Guards the orphan case: with PurgeMissing on, removing an artist's last file hard-deletes + // its media_file_artists rows, RefreshStats recomputes its stats to '{}', and the cleanup + // drops its last library_artist row — leaving the artist row alive but orphaned. RefreshStats + // must then mark it missing (see markOrphansMissing). + DeferCleanup(configtest.SetupConfig()) + conf.Server.Scanner.PurgeMissing = consts.PurgeMissingAlways + + By("Starting from a library where Pink Floyd has its own single album") + floyd := template(_t{"artist": "Pink Floyd", "album": "The Wall", "year": 1979}) + fsys = createFS(fstest.MapFS{ + "The Beatles/Help!/01 - Help!.mp3": help(track(1, "Help!")), + "The Beatles/Help!/02 - The Night Before.mp3": help(track(2, "The Night Before")), + "The Beatles/Revolver/01 - Taxman.mp3": revolver(track(1, "Taxman")), + "The Beatles/Revolver/02 - Eleanor Rigby.mp3": revolver(track(2, "Eleanor Rigby")), + "Pink Floyd/The Wall/01 - Another Brick.mp3": floyd(track(1, "Another Brick in the Wall")), + }) + Expect(runScanner(ctx, true)).To(Succeed()) + + nonMissingArtists := func() []string { + aa, err := ds.Artist(ctx).GetAll(model.QueryOptions{Filters: squirrel.Eq{"missing": false}}) + Expect(err).ToNot(HaveOccurred()) + return slice.Map(aa, func(a model.Artist) string { return a.Name }) + } + orphanCount := func() int64 { + var n int64 + Expect(db.Db().QueryRowContext(ctx, + "SELECT count(*) FROM artist WHERE missing = false "+ + "AND id NOT IN (SELECT artist_id FROM library_artist)").Scan(&n)).To(Succeed()) + return n + } + // Read the artist row directly: selectArtist inner-joins library_artist, so an orphan never + // surfaces through the repository. Returns a descriptive string for clear test failures. + floydState := func() string { + var m bool + err := db.Db().QueryRowContext(ctx, + "SELECT missing FROM artist WHERE name = 'Pink Floyd'").Scan(&m) + if errors.Is(err, sql.ErrNoRows) { + return "NOT_FOUND" + } + Expect(err).ToNot(HaveOccurred()) + if m { + return "MISSING" + } + return "PRESENT" + } + + By("Confirming Pink Floyd is visible after the import, with no orphan") + Expect(nonMissingArtists()).To(ContainElement("Pink Floyd")) + Expect(floydState()).To(Equal("PRESENT")) + Expect(orphanCount()).To(BeZero()) + + By("Removing all of Pink Floyd's files and rescanning") + fsys.Remove("Pink Floyd/The Wall/01 - Another Brick.mp3") + Expect(runScanner(ctx, true)).To(Succeed()) + + By("Checking Pink Floyd's row survives but is marked missing, leaving no orphan") + Expect(floydState()).To(Equal("MISSING")) + Expect(orphanCount()).To(BeZero()) + // The Beatles keep their content, so the fix must not over-mark them. + Expect(nonMissingArtists()).To(ContainElement("The Beatles")) + }) + It("does not override artist fields when importing an undertagged file", func() { By("Making sure artist in the DB contains MBID and sort name") aa, err := ds.Artist(ctx).GetAll(model.QueryOptions{ diff --git a/server/subsonic/searching.go b/server/subsonic/searching.go index fd7e29587..5d4989ae5 100644 --- a/server/subsonic/searching.go +++ b/server/subsonic/searching.go @@ -74,7 +74,7 @@ func (api *Router) searchAll(ctx context.Context, sp *searchParams, musicFolderI if len(musicFolderIds) > 0 { songOpts.Filters = Eq{"library_id": musicFolderIds} albumOpts.Filters = Eq{"library_id": musicFolderIds} - artistOpts.Filters = Eq{"library_artist.library_id": musicFolderIds} + artistOpts.Filters = Eq{"library_id": musicFolderIds} } // Run searches in parallel diff --git a/server/subsonic/searching_test.go b/server/subsonic/searching_test.go index 9a9c6af6f..4e72bd2e6 100644 --- a/server/subsonic/searching_test.go +++ b/server/subsonic/searching_test.go @@ -39,12 +39,17 @@ var _ = Describe("Search", func() { } Describe("Search2", func() { - It("should accept musicFolderId parameter", func() { + It("scopes all entity types to the requested libraries", func() { + // The subsonic layer passes the same library_id filter to all three repos; the + // artist repository translates it to the join-free library_artist predicate itself. r := newGetRequest("query=test", "musicFolderId=1") ctx := request.WithUser(r.Context(), model.User{ - ID: "user1", - UserName: "testuser", - Libraries: []model.Library{{ID: 1, Name: "Library 1"}}, + ID: "user1", + UserName: "testuser", + Libraries: []model.Library{ + {ID: 1, Name: "Library 1"}, + {ID: 2, Name: "Library 2"}, + }, }) r = r.WithContext(ctx) @@ -54,14 +59,13 @@ var _ = Describe("Search", func() { Expect(resp).ToNot(BeNil()) Expect(resp.SearchResult2).ToNot(BeNil()) - // Verify that library filter was applied to all repositories assertQueryOptions(mockAlbumRepo.Options.Filters, "library_id IN (?)", 1) - assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?)", 1) assertQueryOptions(mockMediaFileRepo.Options.Filters, "library_id IN (?)", 1) + assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?)", 1) }) - It("should return results from all accessible libraries when musicFolderId is not provided", func() { - r := newGetRequest("query=test") + It("applies no library filter when musicFolderId is not provided", func() { + r := newGetRequest("query=test") // no musicFolderId → all accessible libraries ctx := request.WithUser(r.Context(), model.User{ ID: "user1", UserName: "testuser", @@ -79,10 +83,9 @@ var _ = Describe("Search", func() { Expect(resp).ToNot(BeNil()) Expect(resp.SearchResult2).ToNot(BeNil()) - // Verify that library filter was applied to all repositories with all accessible libraries assertQueryOptions(mockAlbumRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) - assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) assertQueryOptions(mockMediaFileRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) + assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) }) It("should return empty results when user has no accessible libraries", func() { @@ -122,12 +125,15 @@ var _ = Describe("Search", func() { }) Describe("Search3", func() { - It("should accept musicFolderId parameter", func() { + It("scopes all entity types to the requested libraries", func() { r := newGetRequest("query=test", "musicFolderId=1") ctx := request.WithUser(r.Context(), model.User{ - ID: "user1", - UserName: "testuser", - Libraries: []model.Library{{ID: 1, Name: "Library 1"}}, + ID: "user1", + UserName: "testuser", + Libraries: []model.Library{ + {ID: 1, Name: "Library 1"}, + {ID: 2, Name: "Library 2"}, + }, }) r = r.WithContext(ctx) @@ -137,14 +143,13 @@ var _ = Describe("Search", func() { Expect(resp).ToNot(BeNil()) Expect(resp.SearchResult3).ToNot(BeNil()) - // Verify that library filter was applied to all repositories assertQueryOptions(mockAlbumRepo.Options.Filters, "library_id IN (?)", 1) - assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?)", 1) assertQueryOptions(mockMediaFileRepo.Options.Filters, "library_id IN (?)", 1) + assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?)", 1) }) - It("should return results from all accessible libraries when musicFolderId is not provided", func() { - r := newGetRequest("query=test") + It("applies no library filter when musicFolderId is not provided", func() { + r := newGetRequest("query=test") // no musicFolderId → all accessible libraries ctx := request.WithUser(r.Context(), model.User{ ID: "user1", UserName: "testuser", @@ -162,10 +167,9 @@ var _ = Describe("Search", func() { Expect(resp).ToNot(BeNil()) Expect(resp.SearchResult3).ToNot(BeNil()) - // Verify that library filter was applied to all repositories with all accessible libraries assertQueryOptions(mockAlbumRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) - assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) assertQueryOptions(mockMediaFileRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) + assertQueryOptions(mockArtistRepo.Options.Filters, "library_id IN (?,?,?)", 1, 2, 3) }) It("should return empty results when user has no accessible libraries", func() { diff --git a/utils/slice/slice.go b/utils/slice/slice.go index e87ac5388..73537c8f8 100644 --- a/utils/slice/slice.go +++ b/utils/slice/slice.go @@ -42,6 +42,16 @@ func ToMap[T any, K comparable, V any](s []T, transformFunc func(T) (K, V)) map[ return m } +// ToSet builds a set (a map keyed by the slice's elements) for O(1) membership tests. Duplicate +// elements collapse to a single key. +func ToSet[T comparable](s []T) map[T]struct{} { + m := make(map[T]struct{}, len(s)) + for _, item := range s { + m[item] = struct{}{} + } + return m +} + func CompactByFrequency[T comparable](list []T) []T { counters := make(map[T]int) for _, item := range list { diff --git a/utils/slice/slice_test.go b/utils/slice/slice_test.go index 64cb89d53..27548d693 100644 --- a/utils/slice/slice_test.go +++ b/utils/slice/slice_test.go @@ -81,6 +81,20 @@ var _ = Describe("Slice Utils", func() { }) }) + Describe("ToSet", func() { + It("returns empty set for an empty input", func() { + Expect(slice.ToSet([]int{})).To(BeEmpty()) + }) + + It("builds a set with one key per distinct element", func() { + result := slice.ToSet([]int{1, 2, 2, 3, 3, 3}) + Expect(result).To(HaveLen(3)) + Expect(result).To(HaveKey(1)) + Expect(result).To(HaveKey(2)) + Expect(result).To(HaveKey(3)) + }) + }) + Describe("CompactByFrequency", func() { It("returns empty slice for an empty input", func() { Expect(slice.CompactByFrequency([]int{})).To(BeEmpty())