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
This commit is contained in:
Michael McGuinness
2025-04-02 18:50:03 +00:00
parent e6a4cb3990
commit 81e7223560
226 changed files with 17283 additions and 2744 deletions
@@ -0,0 +1,70 @@
//go:build aws
//go:generate go run -tags=aws ./textdetection.go
package main
import (
"context"
"encoding/json"
"fmt"
"log/slog"
"os"
"queryorchestration/internal/serviceconfig/aws"
"queryorchestration/internal/serviceconfig/textract"
awstextract "github.com/aws/aws-sdk-go-v2/service/textract"
"github.com/aws/aws-sdk-go-v2/service/textract/types"
)
func main() {
ctx := context.Background()
cfg := &textract.TextractConfig{}
profile := aws.Profile(os.Getenv("AWS_PROFILE"))
if profile == "" {
slog.Error("profile not available")
os.Exit(1)
}
err := cfg.SetTextractClientWithProfile(ctx, profile)
if err != nil {
slog.Error("error creating client", "error", err)
os.Exit(1)
}
base := "../../assets/sampleGeneration"
name := "helloWorld"
filename := fmt.Sprintf("%s/%s.pdf", base, name)
content, err := os.ReadFile(filename)
if err != nil {
slog.Error("error writing file", "error", err)
os.Exit(1)
}
slog.Info("detecting text", "filename", filename)
res, err := cfg.GetTextractClient().DetectDocumentText(ctx, &awstextract.DetectDocumentTextInput{
Document: &types.Document{
Bytes: content,
},
})
if err != nil {
slog.Error("error detecting text", "error", err)
os.Exit(1)
}
jsonContent, err := json.MarshalIndent(res, "", "\t")
if err != nil {
slog.Error("error marshaling json", "error", err)
os.Exit(1)
}
outputFilename := fmt.Sprintf("%s/generated/%s.gen", base, name)
err = os.WriteFile(outputFilename, jsonContent, 0600)
if err != nil {
slog.Error("error writing file", "error", err)
os.Exit(1)
}
fmt.Println("Successfully generated " + outputFilename)
}