feat: extract file text on every attach path and backfill on reindex

- inline and signed uploads queue the text job in their transaction
- the admin form queues it in the save transaction
- detach resyncs the material (its text row goes by cascade)
- bm:materials-reindex backfills missing PDF texts before each sync

controllers/api/manage_files.go

@@ -208,7 +208,8 @@ func sizeMB(n int64) string {
 }
 
 // DetachMaterialFile answers DELETE /materials/{id}/files/{file}: the file
-// row goes, then its blob and thumbnails. A file of another material is a
+// row goes (its extracted text with it), the material is resynced, then the
+// blob and thumbnails go. A file of another material is a
 // 404.
 func (h *Handlers) DetachMaterialFile(w http.ResponseWriter, r *http.Request) {
 	db, ok := h.db(w, r)
@@ -242,6 +243,9 @@ func (h *Handlers) DetachMaterialFile(w http.ResponseWriter, r *http.Request) {
 		writeOpaque500(w)
 		return
 	}
+	// The file's text row went with it (foreign-key cascade); the resync
+	// drops the text from the material's document.
+	h.MaterialIndex.Sync(r.Context(), db, m.ID)
 	// The row is gone, so the file is no longer served; a blob left behind
 	// by a failed delete is only disk space.
 	_ = attach.DeleteKeys(r.Context(), bucket, attach.BlobKeys(f))

controllers/api/uploads.go

@@ -134,6 +134,10 @@ func (h *Handlers) AttachMaterialInline(w http.ResponseWriter, r *http.Request)
 	err := lagoon.Transaction(r.Context(), db, func(ctx context.Context, tx *gorm.DB) error {
 		f, why, err := storeMaterialFile(ctx, tx, bucket, m, name, bytes.NewReader(data), lim)
 		stored, refusal = f, why
+		if err == nil && why == "" && f != nil {
+			// The text job joins the transaction and syncs the material.
+			h.MaterialIndex.QueueExtract(ctx, tx, m.ID)
+		}
 		return err
 	})
 	if err != nil || refusal != "" {
@@ -302,6 +306,8 @@ func (h *Handlers) SignedMaterialUpload(w http.ResponseWriter, r *http.Request)
 			refusal = singleFilePart
 			return errUploadRefused
 		}
+		// The text job joins the transaction and syncs the material.
+		h.MaterialIndex.QueueExtract(ctx, tx, m.ID)
 		return nil
 	})
 	if err != nil {

controllers/materials_hooks.go

@@ -18,10 +18,12 @@ var (
 )
 
 // MaterialIndex keeps the materials search index current once a write
-// commits (classes.MaterialIndexer). Its calls never fail the write.
+// commits (classes.MaterialIndexer). QueueExtract enqueues the file text job
+// inside tx. Its calls never fail the write.
 type MaterialIndex interface {
 	SyncAfterCommit(ctx context.Context, tx *gorm.DB, id uint)
 	RemoveAfterCommit(ctx context.Context, tx *gorm.DB, id uint)
+	QueueExtract(ctx context.Context, tx *gorm.DB, id uint)
 }
 
 type materialIndexHolder struct{ ix MaterialIndex }
@@ -40,12 +42,17 @@ func installedMaterialIndex() MaterialIndex {
 	return h.ix
 }
 
-// FormAfterCreate syncs the new material once the save transaction commits.
+// FormAfterCreate queues the file text job in the save transaction (the
+// form's deferred files commit in the same one) and syncs the new material
+// once it commits.
 func (materialsAdmin) FormAfterCreate(ctx context.Context, model any) error {
 	return materialAfterCommit(ctx, model, false)
 }
 
-// FormAfterUpdate syncs the material once the save transaction commits.
+// FormAfterUpdate queues the file text job in the save transaction and
+// syncs the material once it commits. A save that added no file queues a
+// job that finds no new PDF and only resyncs; a file removed in the form
+// leaves the document through the cascade and this sync.
 func (materialsAdmin) FormAfterUpdate(ctx context.Context, model any) error {
 	return materialAfterCommit(ctx, model, false)
 }
@@ -70,8 +77,9 @@ func materialAfterCommit(ctx context.Context, model any, remove bool) error {
 	tx, _ := cabana.TxFromContext(ctx)
 	if remove {
 		ix.RemoveAfterCommit(ctx, tx, m.ID)
-	} else {
-		ix.SyncAfterCommit(ctx, tx, m.ID)
+		return nil
 	}
+	ix.QueueExtract(ctx, tx, m.ID)
+	ix.SyncAfterCommit(ctx, tx, m.ID)
 	return nil
 }

controllers/materials_hooks_test.go

@@ -26,6 +26,11 @@ func (r *recordingIndex) RemoveAfterCommit(_ context.Context, tx *gorm.DB, id ui
 	r.txs = append(r.txs, tx)
 }
 
+func (r *recordingIndex) QueueExtract(_ context.Context, tx *gorm.DB, id uint) {
+	r.calls = append(r.calls, "queue "+itoa(id))
+	r.txs = append(r.txs, tx)
+}
+
 func itoa(id uint) string { return strconv.FormatUint(uint64(id), 10) }
 
 func TestMaterialsAdminHooks(t *testing.T) {
@@ -53,7 +58,9 @@ func TestMaterialsAdminHooks(t *testing.T) {
 	if err := c.FormAfterDelete(ctx, m); err != nil {
 		t.Fatal(err)
 	}
-	if want := []string{"sync 7", "sync 7", "remove 7"}; !slices.Equal(rec.calls, want) {
+	// Create and update queue the file text job (in the save transaction)
+	// before the after-commit sync; delete queues nothing.
+	if want := []string{"queue 7", "sync 7", "queue 7", "sync 7", "remove 7"}; !slices.Equal(rec.calls, want) {
 		t.Errorf("calls = %v, want %v", rec.calls, want)
 	}
 	// Outside a cabana write there is no transaction: the index then runs