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

plugin.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"embed"
 	"errors"
+	"fmt"
 	"io/fs"
 	"time"
 
@@ -11,6 +12,7 @@ import (
 	"git.golem15.com/golem15/summercms/modules/bonfire"
 	"git.golem15.com/golem15/summercms/modules/conga"
 	"git.golem15.com/golem15/summercms/modules/lagoon"
+	"git.golem15.com/golem15/summercms/modules/lagoon/attach"
 	"git.golem15.com/golem15/summercms/modules/lighthouse"
 	"git.golem15.com/golem15/summercms/modules/lighthouse/centrifugo"
 	"git.golem15.com/golem15/summercms/modules/pact"
@@ -19,6 +21,7 @@ import (
 	"git.golem15.com/jakub/sm-bm-plugin/console"
 	"git.golem15.com/jakub/sm-bm-plugin/controllers"
 	"github.com/go-gormigrate/gormigrate/v2"
+	"gocloud.dev/blob"
 	"gorm.io/gorm"
 )
 
@@ -131,7 +134,7 @@ func (p *Plugin) Commands() []bonfire.Command {
 	cmds = append(cmds, console.ChatSyncCommand(p.withDB, func() (string, string) {
 		return p.chatGroup(), p.chatModeratorGroup()
 	}))
-	cmds = append(cmds, console.MaterialsReindexCommand(console.MaterialsReindexDeps{DB: p.publishedDB, Index: p.materialIndex}))
+	cmds = append(cmds, console.MaterialsReindexCommand(console.MaterialsReindexDeps{DB: p.publishedDB, Index: p.materialIndex, Backfill: p.backfillFileTexts}))
 	return append(cmds, centrifugo.Commands(p.app)...)
 }
 
@@ -222,6 +225,42 @@ func (p *Plugin) publishedDB(ctx context.Context) (*gorm.DB, func(), error) {
 	return gdb, func() { _ = sqlDB.Close() }, nil
 }
 
+// backfillFileTexts extracts the text of material id's PDFs that have none
+// yet, for bm:materials-reindex (D-04: PDFs attached before file search).
+func (p *Plugin) backfillFileTexts(ctx context.Context, db *gorm.DB, id uint) error {
+	bucket, err := p.uploadsBucket(ctx)
+	if err != nil {
+		return err
+	}
+	_, err = classes.EnsureFileTexts(ctx, db, bucket, classes.DefaultPDFText(), id)
+	return err
+}
+
+// uploadsBucket returns the uploads bucket published on the app: the one
+// serve published or, when a console command runs, one opened from
+// storage.uploads.bucket_url and published. It is an error when no bucket
+// is configured.
+func (p *Plugin) uploadsBucket(ctx context.Context) (*blob.Bucket, error) {
+	if p.app == nil {
+		return nil, errors.New("jz.bm: app is nil")
+	}
+	if b, ok := p.app.Lookup[*blob.Bucket](); ok && b != nil {
+		return b, nil
+	}
+	b, err := attach.OpenBucket(ctx, p.app.Config)
+	if err != nil {
+		return nil, fmt.Errorf("jz.bm: the uploads bucket is not configured: %w", err)
+	}
+	if err := attach.Publish(p.app, b); err != nil {
+		_ = b.Close()
+		if pub, ok := p.app.Lookup[*blob.Bucket](); ok && pub != nil {
+			return pub, nil
+		}
+		return nil, err
+	}
+	return b, nil
+}
+
 func init() {
 	party.Register(&Plugin{})
 }