Merged in feature/textextraction (pull request #110)

Text Extraction

* bases

* go

* splitting

* structure

* movetoasync

* movetoasync

* settinguptrigger

* reorder

* storevent

* standardisepollingvalidation

* unittests

* fixlint

* fixlint

* awscfg

* generatesample

* followthrough

* tests

* clena

* store

* externalidcleanup

* clientid

* local

* baseunittests

* putobjecttests

* tests

cmd/docTextRunner/main.go

@@ -2,9 +2,9 @@
 //
 // **Action**.
 //
-// If the document text is not already extracted according to the collector standards, the text is extracted.
+// If the document text is not already extracted according to the collector standards, trigger the textract job for text detection.
 //
-// An event with the document id is pushed to the QUERYSYNC queue.
+// Otherwise, add an event to the QUERYSYNC queue.
 package main
 
 import (
@@ -15,24 +15,26 @@ import (
 	doctextrunner "queryorchestration/api/docTextRunner"
 	documenttext "queryorchestration/internal/document/text"
 	"queryorchestration/internal/server/runner"
+	"queryorchestration/internal/serviceconfig/objectstore"
 	"queryorchestration/internal/serviceconfig/queue/querysync"
 	"queryorchestration/internal/serviceconfig/textract"
 
 	_ "github.com/lib/pq"
 )
 
-type DocTextConfig struct {
-	runner.BaseConfig
-	querysync.QuerySyncConfig
+type DocTextTriggerConfig struct {
+	runner.BaseConfig[doctextrunner.Body]
 	textract.TextractConfig
+	querysync.QuerySyncConfig
+	objectstore.ObjectStoreConfig
 }
 
 func main() {
 	ctx := context.Background()
 
-	cfg := &DocTextConfig{}
+	cfg := &DocTextTriggerConfig{}
 
-	cfg.ControllerFunc = func() runner.Controller {
+	cfg.ControllerFunc = func() runner.Controller[doctextrunner.Body] {
 		text := documenttext.New(cfg)
 
 		return doctextrunner.New(cfg.GetValidator(), &doctextrunner.Services{
@@ -46,5 +48,11 @@ func main() {
 		os.Exit(1)
 	}
 
+	err = cfg.SetTextractClient(ctx)
+	if err != nil {
+		slog.Error(err.Error())
+		os.Exit(1)
+	}
+
 	server.Listen(ctx)
 }