How to read from an Amazon S3 Bucket and call AWS services

Question

I am able to call AWS Textract to read an image from my local path. How can I integrate this textract code to read the image uploaded onto a created S3 bucket with the S3 bucket codes.

Working Textract Code to textract images from local path

package aws.cloud.work;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.io.InputStream;

import org.json.simple.JSONArray;
import org.json.simple.JSONObject;

import com.amazonaws.auth.AWSStaticCredentialsProvider;
import com.amazonaws.auth.BasicAWSCredentials;
import com.amazonaws.regions.Regions;
import com.amazonaws.services.textract.AmazonTextract;
import com.amazonaws.services.textract.AmazonTextractClientBuilder;
import com.amazonaws.services.textract.model.DetectDocumentTextRequest;
import com.amazonaws.services.textract.model.DetectDocumentTextResult;
import com.amazonaws.services.textract.model.Document;
import com.amazonaws.util.IOUtils;

public class TextractDemo {

    static AmazonTextractClientBuilder clientBuilder = AmazonTextractClientBuilder.standard()
            .withRegion(Regions.US_EAST_1);

    private static FileWriter file;

    public static void main(String[] args) throws IOException {

//AWS Credentials to access AWS Textract services

        clientBuilder.setCredentials(new AWSStaticCredentialsProvider(
                new BasicAWSCredentials("Access Key", "Secret key")));

//Set the path of the image to be textract. Can be configured to use from S3

      String document="C:\\Users\\image-local-path\\sampleTT.jpg";
      ByteBuffer imageBytes;

//Code to use AWS Textract services

        try (InputStream inputStream = new FileInputStream(new File(document))) {
            imageBytes = ByteBuffer.wrap(IOUtils.toByteArray(inputStream));
        }
        AmazonTextract client = clientBuilder.build();
        DetectDocumentTextRequest request = new DetectDocumentTextRequest()
                .withDocument(new Document().withBytes(imageBytes));

        /*
         * DetectDocumentTextResult result = client.detectDocumentText(request);
         * System.out.println(result); result.getBlocks().forEach(block ->{
         * if(block.getBlockType().equals("LINE")) System.out.println("text is "+
         * block.getText() + " confidence is "+ block.getConfidence());
         */ 

//      
        DetectDocumentTextResult result = client.detectDocumentText(request);
        System.out.println(result);
        JSONObject obj = new JSONObject();
        result.getBlocks().forEach(block -> {
            if (block.getBlockType().equals("LINE"))
                System.out.println("text is " + block.getText() + " confidence is " + block.getConfidence());
            JSONArray fields = new JSONArray();

            fields.add(block.getText() + " , " + block.getConfidence());
            obj.put(block.getText(), fields);

        });

//To import the results into JSON file and output the console output as sample.txt      
        try {
            file = new FileWriter("/Users/output-path/sample.txt");
            file.write(obj.toJSONString());
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                file.flush();
                file.close();
            } catch (IOException e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        }

    }
}

This is an example of the console out where the "text" and corresponding "confidence scores" are returned

S3 bucket code integration I managed to find from the docs:

        String document = "sampleTT.jpg";
        String bucket = "textract-images";

        AmazonS3 s3client = AmazonS3ClientBuilder.standard()
                .withEndpointConfiguration( 
                        new EndpointConfiguration("https://s3.amazonaws.com","us-east-1"))
                .build();
        
               
        // Get the document from S3
        com.amazonaws.services.s3.model.S3Object s3object = s3client.getObject(bucket, document);
        S3ObjectInputStream inputStream = s3object.getObjectContent();
        BufferedImage image = ImageIO.read(inputStream);

---

(Edited) - Thanks @smac2020, I currently have a working Rekognition Code that reads from my AWS console S3 bucket and runs the Rekognition services that I am referencing to. However, I am unable to modify and merge it with the Textract source code

package com.amazonaws.samples;

import com.amazonaws.auth.AWSCredentialsProvider;
import com.amazonaws.auth.AWSStaticCredentialsProvider;
import com.amazonaws.auth.BasicAWSCredentials;
import com.amazonaws.services.rekognition.AmazonRekognition;
import com.amazonaws.services.rekognition.AmazonRekognitionClientBuilder;
import com.amazonaws.services.rekognition.model.AmazonRekognitionException;
import com.amazonaws.services.rekognition.model.DetectLabelsRequest;
import com.amazonaws.services.rekognition.model.DetectLabelsResult;
import com.amazonaws.services.rekognition.model.Image;
import com.amazonaws.services.rekognition.model.Label;
import com.amazonaws.services.rekognition.model.S3Object;
import java.util.List;

public class DetectLabels {

 public static void main(String[] args) throws Exception {

    String photo = "sampleTT.jpg";
    String bucket = "Textract-bucket";

    
    
//    AmazonRekognition rekognitionClient = AmazonRekognitionClientBuilder.standard().withRegion("ap-southeast-1").build();

    AWSCredentialsProvider credentialsProvider = new AWSStaticCredentialsProvider (new BasicAWSCredentials("Access Key", "Secret Key"));
    AmazonRekognition rekognitionClient = AmazonRekognitionClientBuilder.standard().withCredentials(credentialsProvider).withRegion("ap-southeast-1").build();

    
    DetectLabelsRequest request = new DetectLabelsRequest()
         .withImage(new Image()
         .withS3Object(new S3Object()
         .withName(photo).withBucket(bucket)))
         .withMaxLabels(10)
         .withMinConfidence(75F);

    try {
       DetectLabelsResult result = rekognitionClient.detectLabels(request);
       List <Label> labels = result.getLabels();

       System.out.println("Detected labels for " + photo);
       for (Label label: labels) {
          System.out.println(label.getName() + ": " + label.getConfidence().toString());
       }
    } catch(AmazonRekognitionException e) {
       e.printStackTrace();
    }
 }
}

Answer 1

Looks like you are trying to read an Amazon S3 object from a Spring boot app and then pass that byte array to DetectDocumentTextRequest.

There is a tutorial that shows a very similar use case where a Spring BOOT app reads the bytes from an Amazon S3 object and passes it to the Amazon Rekognition service (instead of Textract).

The Java code is:

// Get the byte[] from this AWS S3 object.
public byte[] getObjectBytes (String bucketName, String keyName) {

    s3 = getClient();

    try {
        GetObjectRequest objectRequest = GetObjectRequest
                .builder()
                .key(keyName)
                .bucket(bucketName)
                .build();
        
        ResponseBytes<GetObjectResponse> objectBytes = s3.getObjectAsBytes(objectRequest);
        byte[] data = objectBytes.asByteArray();
        return data;

    } catch (S3Exception e) {
        System.err.println(e.awsErrorDetails().errorMessage());
        System.exit(1);
    }
    return null;
}

See this AWS development article to see how to build a Spring BOOT app that has this functionality.

Creating an example AWS photo analyzer application using the AWS SDK for Java

This example uses the AWS SDK For Java V2. If you are not familiar with working with the latest SDK version, I recommend that you start here:

Get started with the AWS SDK for Java 2.x