public async static void GetTextFromS3(IAmazonTextract textractClient, string bucketName, string keyName)
{
List <Block> result = null;
DetectDocumentTextRequest detectTextRequest = new DetectDocumentTextRequest()
{
Document = new Document {
S3Object = new S3Object {
Bucket = bucketName,
Name = keyName
}
}
};
try
{
Task <DetectDocumentTextResponse> detectTask = textractClient.DetectDocumentTextAsync(detectTextRequest);
DetectDocumentTextResponse detectTextResponse = await detectTask;
result = detectTextResponse.Blocks;
//PrintBlockDetails(result);
}
catch (AmazonTextractException textractException)
{
Console.WriteLine(textractException.Message, textractException.InnerException);
}
}
public async Task <List <Block> > GetTextFromStream(IAmazonTextract textractClient, MemoryStream stream)
{
List <Block> result = null;
DetectDocumentTextRequest detectTextRequest = new DetectDocumentTextRequest()
{
Document = new Document
{
Bytes = stream
}
};
try
{
Task <DetectDocumentTextResponse> detectTask = textractClient.DetectDocumentTextAsync(detectTextRequest);
DetectDocumentTextResponse detectTextResponse = await detectTask;
result = detectTextResponse.Blocks;
//PrintBlockDetails(result);
}
catch (AmazonTextractException textractException)
{
Console.WriteLine(textractException.Message, textractException.InnerException);
}
return(result);
}
public IActionResult Post()
{
AmazonTextractClient objTextExtract = new AmazonTextractClient("AKIA23XZGIB6BEUBA5HM", "ePmW8ZsldWdQP3hmillAOMLu+A5b4ePgeBV3+/O5", Amazon.RegionEndpoint.USEast1);
DetectDocumentTextRequest request = new DetectDocumentTextRequest();
byte[] fileData = null;
using (var ms = new MemoryStream())
{
HttpContext.Request.Form.Files[0].CopyTo(ms);
fileData = ms.ToArray();
string s = Convert.ToBase64String(fileData);
// act on the Base64 data
}
request.Document = new Document
{
Bytes = new MemoryStream(fileData)
};
var task = UploadImageForRekognition(objTextExtract, request);
task.Wait();
var result = task.Result;
return(Ok(result));
}
/// <summary>
/// Detects text in the input document. Amazon Textract can detect lines of text and the
/// words that make up a line of text. The input document must be an image in JPG or PNG
/// format. <code>DetectDocumentText</code> returns the detected text in an array of <a>Block</a>
/// objects.
///
///
/// <para>
/// Each document page has as an associated <code>Block</code> of type PAGE. Each PAGE
/// <code>Block</code> object is the parent of LINE <code>Block</code> objects that represent
/// the lines of detected text on a page. A LINE <code>Block</code> object is a parent
/// for each word that makes up the line. Words are represented by <code>Block</code>
/// objects of type WORD.
/// </para>
///
/// <para>
/// <code>DetectDocumentText</code> is a synchronous operation. To analyze documents
/// asynchronously, use <a>StartDocumentTextDetection</a>.
/// </para>
///
/// <para>
/// For more information, see <a href="https://docs.aws.amazon.com/textract/latest/dg/how-it-works-detecting.html">Document
/// Text Detection</a>.
/// </para>
/// </summary>
/// <param name="request">Container for the necessary parameters to execute the DetectDocumentText service method.</param>
/// <param name="cancellationToken">
/// A cancellation token that can be used by other objects or threads to receive notice of cancellation.
/// </param>
///
/// <returns>The response from the DetectDocumentText service method, as returned by Textract.</returns>
/// <exception cref="Amazon.Textract.Model.AccessDeniedException">
/// You aren't authorized to perform the action.
/// </exception>
/// <exception cref="Amazon.Textract.Model.BadDocumentException">
/// Amazon Textract isn't able to read the document.
/// </exception>
/// <exception cref="Amazon.Textract.Model.DocumentTooLargeException">
/// The document can't be processed because it's too large. The maximum document size
/// for synchronous operations 5 MB. The maximum document size for asynchronous operations
/// is 500 MB for PDF format files.
/// </exception>
/// <exception cref="Amazon.Textract.Model.InternalServerErrorException">
/// Amazon Textract experienced a service issue. Try your call again.
/// </exception>
/// <exception cref="Amazon.Textract.Model.InvalidParameterException">
/// An input parameter violated a constraint. For example, in synchronous operations,
/// an <code>InvalidParameterException</code> exception occurs when neither of the <code>S3Object</code>
/// or <code>Bytes</code> values are supplied in the <code>Document</code> request parameter.
/// Validate your parameter before calling the API operation again.
/// </exception>
/// <exception cref="Amazon.Textract.Model.InvalidS3ObjectException">
/// Amazon Textract is unable to access the S3 object that's specified in the request.
/// </exception>
/// <exception cref="Amazon.Textract.Model.ProvisionedThroughputExceededException">
/// The number of requests exceeded your throughput limit. If you want to increase this
/// limit, contact Amazon Textract.
/// </exception>
/// <exception cref="Amazon.Textract.Model.ThrottlingException">
/// Amazon Textract is temporarily unable to process the request. Try your call again.
/// </exception>
/// <exception cref="Amazon.Textract.Model.UnsupportedDocumentException">
/// The format of the input document isn't supported. Amazon Textract supports documents
/// that are .png or .jpg format.
/// </exception>
/// <seealso href="http://docs.aws.amazon.com/goto/WebAPI/textract-2018-06-27/DetectDocumentText">REST API Reference for DetectDocumentText Operation</seealso>
public virtual Task <DetectDocumentTextResponse> DetectDocumentTextAsync(DetectDocumentTextRequest request, System.Threading.CancellationToken cancellationToken = default(CancellationToken))
{
var options = new InvokeOptions();
options.RequestMarshaller = DetectDocumentTextRequestMarshaller.Instance;
options.ResponseUnmarshaller = DetectDocumentTextResponseUnmarshaller.Instance;
return(InvokeAsync <DetectDocumentTextResponse>(request, options, cancellationToken));
}
internal virtual DetectDocumentTextResponse DetectDocumentText(DetectDocumentTextRequest request)
{
var options = new InvokeOptions();
options.RequestMarshaller = DetectDocumentTextRequestMarshaller.Instance;
options.ResponseUnmarshaller = DetectDocumentTextResponseUnmarshaller.Instance;
return(Invoke <DetectDocumentTextResponse>(request, options));
}
public async Task <DetectDocumentTextResponse> DetectTextS3(string bucketName, string key)
{
var result = new DetectDocumentTextResponse();
var s3Object = new S3Object {
Bucket = bucketName,
Name = key
};
var request = new DetectDocumentTextRequest();
request.Document = new Document {
S3Object = s3Object
};
return(await this.textract.DetectDocumentTextAsync(request));
}
public async Task <DetectDocumentTextResponse> DetectTextLocal(string localPath)
{
var result = new DetectDocumentTextResponse();
if (File.Exists(localPath))
{
var request = new DetectDocumentTextRequest();
request.Document = new Document {
Bytes = new MemoryStream(File.ReadAllBytes(localPath))
};
return(await this.textract.DetectDocumentTextAsync(request));
}
Console.WriteLine("File: " + localPath + " doesn't exist");
return(result);
}
public override async Task RunCommand(object sender)
{
var engine = (IAutomationEngineInstance)sender;
var vAccessKey = (string)await v_AccessKey.EvaluateCode(engine);
var vSecretKey = (string)await v_SecretKey.EvaluateCode(engine);
var ocrRequest = new DetectDocumentTextRequest();
MemoryStream memStream = new MemoryStream();
if (v_ImageType == "Filepath")
{
string vFilePath = (string)await v_FilePath.EvaluateCode(engine);
FileStream image = File.OpenRead(vFilePath);
image.CopyTo(memStream);
}
else
{
Bitmap vBitmap = (Bitmap)await v_Bitmap.EvaluateCode(engine);
vBitmap.Save(memStream, ImageFormat.Jpeg);
}
ocrRequest.Document = new Document();
ocrRequest.Document.Bytes = memStream;
AmazonTextractConfig config = new AmazonTextractConfig();
config.RegionEndpoint = Amazon.RegionEndpoint.GetBySystemName(v_AWSRegion);
AmazonTextractClient client = new AmazonTextractClient(vAccessKey, vSecretKey, config);
DetectDocumentTextResponse results = client.DetectDocumentText(ocrRequest);
string readText = "";
if (results.HttpStatusCode == System.Net.HttpStatusCode.OK)
{
foreach (Block block in results.Blocks)
{
if (block.BlockType.Value == "LINE")
{
readText += block.Text + "\n";
}
}
}
else
{
throw new Exception("Call to AWS textract failed");
}
readText.SetVariableValue(engine, v_OutputUserVariableName);
}
private static async Task <string> ReadText(string textUrl)
{
using var client = new AmazonTextractClient();
var document = new Document
{
S3Object = new Amazon.Textract.Model.S3Object
{
Bucket = S3BucketName,
Name = textUrl
}
};
var request = new DetectDocumentTextRequest
{
Document = document
};
var response = await client.DetectDocumentTextAsync(request);
return(GetTextFromBlocks(response.Blocks));
}
private async Task <DetectDocumentTextResponse> UploadImageForRekognition(AmazonTextractClient objRekClient, DetectDocumentTextRequest objDetectText)
{
return(await objRekClient.DetectDocumentTextAsync(objDetectText));
}
