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

classes/material_index_test.go

@@ -1,15 +1,20 @@
 package classes_test
 
 import (
+	"bytes"
 	"context"
 	"errors"
+	"log/slog"
 	"net/http"
 	"slices"
 	"strings"
 	"testing"
 
+	"git.golem15.com/golem15/summercms/modules/pact"
 	"git.golem15.com/jakub/sm-bm-plugin/classes"
 	"git.golem15.com/jakub/sm-bm-plugin/internal/searchtest"
+	"git.golem15.com/jakub/sm-bm-plugin/jobs"
+	"gorm.io/gorm"
 )
 
 func TestMaterialSearchGate(t *testing.T) {
@@ -119,3 +124,60 @@ func materialSearchUnavailable(t *testing.T) {
 	none.Sync(context.Background(), nil, 1)
 	none.RemoveAfterCommit(context.Background(), nil, 1)
 }
+
+func TestMaterialQueueExtract(t *testing.T) {
+	ctx := context.Background()
+
+	// A nil indexer, or one without Enqueue, is a no-op.
+	var none *classes.MaterialIndexer
+	none.QueueExtract(ctx, nil, 3)
+	(&classes.MaterialIndexer{}).QueueExtract(ctx, nil, 3)
+
+	var logs bytes.Buffer
+	var got []pact.JobArgs
+	var txs []*gorm.DB
+	ix := &classes.MaterialIndexer{
+		Log: slog.New(slog.NewTextHandler(&logs, nil)),
+		Enqueue: func(_ context.Context, tx *gorm.DB, args pact.JobArgs) error {
+			got = append(got, args)
+			txs = append(txs, tx)
+			return nil
+		},
+	}
+	tx := &gorm.DB{}
+	ix.QueueExtract(ctx, tx, 12)
+	ix.QueueExtract(ctx, tx, 0)
+	if len(got) != 1 {
+		t.Fatalf("enqueued %d jobs, want 1 (id 0 queues nothing)", len(got))
+	}
+	args, ok := got[0].(jobs.ExtractMaterialTextArgs)
+	if !ok || args.MaterialID != 12 || args.Kind() != "jz.bm.extract_material_text" {
+		t.Errorf("args = %#v, want ExtractMaterialTextArgs{12} of kind jz.bm.extract_material_text", got[0])
+	}
+	if txs[0] != tx {
+		t.Error("the job was not enqueued in the given transaction")
+	}
+	if logs.Len() != 0 {
+		t.Errorf("a successful enqueue logged %q", logs.String())
+	}
+
+	// A failing Enqueue is logged with the material id and not returned.
+	ix.Enqueue = func(context.Context, *gorm.DB, pact.JobArgs) error { return errors.New("river is down") }
+	ix.QueueExtract(ctx, tx, 12)
+	if out := logs.String(); !strings.Contains(out, "could not queue the file text job") || !strings.Contains(out, "material_id=12") || !strings.Contains(out, "river is down") {
+		t.Errorf("log = %q, want the failure with the material id", out)
+	}
+
+	// The indexer of an app resolves conga at call time; without an app the
+	// enqueue fails and is only logged.
+	logs.Reset()
+	app := classes.NewMaterialIndexer(nil)
+	if app.Enqueue == nil {
+		t.Fatal("NewMaterialIndexer left Enqueue nil")
+	}
+	app.Log = slog.New(slog.NewTextHandler(&logs, nil))
+	app.QueueExtract(ctx, nil, 5)
+	if !strings.Contains(logs.String(), "material_id=5") {
+		t.Errorf("log = %q, want the failed enqueue logged", logs.String())
+	}
+}