.NET Example for Amazon Textract

Program.cs

using System;
using System.IO;
using System.Threading.Tasks;
using System.Threading;

using Amazon;

// From the AWSSDK.Textract NuGet package
using Amazon.Textract;
using Amazon.Textract.Model;

// From the AWSSDK.S3 NuGet package
using Amazon.S3;
using Amazon.S3.Model;

namespace AWSTextractSample
{
    class Program
    {
        static async Task Main(string[] args)
        {
            try
            {
                await StartDetectSampleAsync();
                await DetectSampleAsync();
            }
            catch(Exception e)
            {
                Console.WriteLine(e.Message);
            }
        }

        private static async Task DetectSampleAsync()
        {
            using (var textractClient = new AmazonTextractClient(RegionEndpoint.USEast1))
            {
                var bytes = File.ReadAllBytes("example.png");

                Console.WriteLine("Detect Document Text");
                var detectResponse = await textractClient.DetectDocumentTextAsync(new DetectDocumentTextRequest
                {
                    Document = new Document
                    {
                        Bytes = new MemoryStream(bytes)
                    }
                });

                foreach (var block in detectResponse.Blocks)
                {
                    Console.WriteLine($"Type {block.BlockType}, Text: {block.Text}");
                }
            }
        }

        private static async Task StartDetectSampleAsync()
        {
            // Set to a bucket that you actually own
            var s3Bucket = "normj-east1";

            // The file name that will be uploaded to S3 and then sent to Textract
            var localFile = "textract-dg.pdf";

            using (var textractClient = new AmazonTextractClient(RegionEndpoint.USEast1))
            using(var s3Client = new AmazonS3Client(RegionEndpoint.USEast1))
            {
                Console.WriteLine($"Upload {localFile} to {s3Bucket} bucket");
                var putRequest = new PutObjectRequest
                {
                    BucketName = s3Bucket,
                    FilePath = localFile,
                    Key = Path.GetFileName(localFile)
                };
                await s3Client.PutObjectAsync(putRequest); 

                Console.WriteLine("Start document detection job");
                var startResponse = await textractClient.StartDocumentTextDetectionAsync(new StartDocumentTextDetectionRequest
                {
                    DocumentLocation = new DocumentLocation
                    {
                        S3Object = new Amazon.Textract.Model.S3Object
                        {
                            Bucket = s3Bucket,
                            Name = putRequest.Key
                        }
                    }
                });

                Console.WriteLine($"Job ID: {startResponse.JobId}");

                var getDetectionRequest = new GetDocumentTextDetectionRequest
                {
                    JobId = startResponse.JobId
                };

                Console.WriteLine("Poll for detect job to complete");
                // Poll till job is no longer in progress.
                GetDocumentTextDetectionResponse getDetectionResponse = null;
                do
                {
                    Thread.Sleep(1000);
                    getDetectionResponse = await textractClient.GetDocumentTextDetectionAsync(getDetectionRequest);
                } while (getDetectionResponse.JobStatus == JobStatus.IN_PROGRESS);

                Console.WriteLine("Print out results if the job was successful.");
                // If the job was successful loop through the pages of results and print the detected text
                if (getDetectionResponse.JobStatus == JobStatus.SUCCEEDED)
                {
                    do
                    {
                        foreach (var block in getDetectionResponse.Blocks)
                        {
                            Console.WriteLine($"Type {block.BlockType}, Text: {block.Text}");
                        }

                        // Check to see if there are no more pages of data. If no then break.
                        if (string.IsNullOrEmpty(getDetectionResponse.NextToken))
                        {
                            break;
                        }

                        getDetectionRequest.NextToken = getDetectionResponse.NextToken;
                        getDetectionResponse = await textractClient.GetDocumentTextDetectionAsync(getDetectionRequest);

                    } while (!string.IsNullOrEmpty(getDetectionResponse.NextToken));
                }
                else
                {
                    Console.WriteLine($"Job failed with message: {getDetectionResponse.StatusMessage}");
                }
            }
        }
    }
}

I have been using TexTract since it was started but I am a fairly basic programmer (C#). I have never used the ASYNC processing. My programs loop with delay timers waiting for TexTract to complete. I love the simplicity of your example. But I can't figure out how to use it as a namespace with the AWAIT processing. My program runs as an ASHX program on a web server in C# v5. If I take your example how would I use the namespace to get the ASYNC advantages? The code just returns since I am not setting up the call correctly.
AWSTextractSample.Program.StartDetectSampleAsync();

I don't have a lot of experience with ASHX files but I believe to use async/await for an ASHX file you need your class to implement the IHttpAsyncHandler interface instead of IHttpHandler interface.

You have a bug in this example. If there is more than one chunk, it will not read the last chunk of blocks. Line 122, you read in a chunk of blocks. If it's the last chunk, then the NextToken will not be set, but you won't process the chunk.