如何在 AWS Lambda 上進行 OCR 文件識別

var awsTmpPath = @"/tmp/";
IronOcr.Installation.InstallationPath = awsTmpPath;
IronOcr.Installation.LogFilePath = awsTmpPath;

Dim awsTmpPath = "/tmp/"
IronOcr.Installation.InstallationPath = awsTmpPath
IronOcr.Installation.LogFilePath = awsTmpPath

using Amazon.Lambda.Core;
using Amazon.S3;
using Amazon.S3.Model;
using IronOcr;

// Assembly attribute to enable the Lambda function's JSON input to be converted into a .NET class.
[assembly: LambdaSerializer(typeof(Amazon.Lambda.Serialization.SystemTextJson.DefaultLambdaJsonSerializer))]

namespace IronOcrZipAwsLambda;

public class Function
{
    private static readonly IAmazonS3 _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.APSoutheast1);

    /// <param name="context">The ILambdaContext that provides methods for logging and describing the Lambda environment.</param>
    /// <returns></returns>
    public async Task FunctionHandler(ILambdaContext context)
    {
        // Set temp file
        var awsTmpPath = @"/tmp/";
        IronOcr.Installation.InstallationPath = awsTmpPath;
        IronOcr.Installation.LogFilePath = awsTmpPath;

        IronOcr.License.LicenseKey = "IRONOCR-MYLICENSE-KEY-1EF01";

        string bucketName = "deploymenttestbucket"; // Your bucket name
        string pdfName = "sample";
        string objectKey = $"IronPdfZip/{pdfName}.pdf";
        string objectKeyForSearchablePdf = $"IronPdfZip/{pdfName}-SearchablePdf.pdf";

        try
        {
            // Retrieve the PDF file from S3
            var pdfData = await GetPdfFromS3Async(bucketName, objectKey);

            IronTesseract ironTesseract = new IronTesseract();
            OcrInput ocrInput = new OcrInput();
            ocrInput.LoadPdf(pdfData);
            OcrResult result = ironTesseract.Read(ocrInput);

            // Use pdfData (byte array) as needed
            context.Logger.LogLine($"OCR result: {result.Text}");

            // Upload the PDF to S3
            await UploadPdfToS3Async(bucketName, objectKeyForSearchablePdf, result.SaveAsSearchablePdfBytes());

            context.Logger.LogLine($"PDF uploaded successfully to {bucketName}/{objectKeyForSearchablePdf}");
        }
        catch (Exception e)
        {
            context.Logger.LogLine($"[ERROR] FunctionHandler: {e.Message}");
        }
    }
    private async Task<byte[]> GetPdfFromS3Async(string bucketName, string objectKey)
    {
        var request = new GetObjectRequest
        {
            BucketName = bucketName,
            Key = objectKey
        };

        using (var response = await _s3Client.GetObjectAsync(request))
        using (var memoryStream = new MemoryStream())
        {
            await response.ResponseStream.CopyToAsync(memoryStream);
            return memoryStream.ToArray();
        }
    }

    // Function to upload the PDF file to S3
    private async Task UploadPdfToS3Async(string bucketName, string objectKey, byte[] pdfBytes)
    {
        using (var memoryStream = new MemoryStream(pdfBytes))
        {
            var request = new PutObjectRequest
            {
                BucketName = bucketName,
                Key = objectKey,
                InputStream = memoryStream,
                ContentType = "application/pdf",
            };

            await _s3Client.PutObjectAsync(request);
        }
    }
}

Imports Amazon.Lambda.Core
Imports Amazon.S3
Imports Amazon.S3.Model
Imports IronOcr

' Assembly attribute to enable the Lambda function's JSON input to be converted into a .NET class.
<Assembly: LambdaSerializer(GetType(Amazon.Lambda.Serialization.SystemTextJson.DefaultLambdaJsonSerializer))>

Namespace IronOcrZipAwsLambda

	Public Class [Function]
		Private Shared ReadOnly _s3Client As IAmazonS3 = New AmazonS3Client(Amazon.RegionEndpoint.APSoutheast1)

		''' <param name="context">The ILambdaContext that provides methods for logging and describing the Lambda environment.</param>
		''' <returns></returns>
		Public Async Function FunctionHandler(ByVal context As ILambdaContext) As Task
			' Set temp file
			Dim awsTmpPath = "/tmp/"
			IronOcr.Installation.InstallationPath = awsTmpPath
			IronOcr.Installation.LogFilePath = awsTmpPath

			IronOcr.License.LicenseKey = "IRONOCR-MYLICENSE-KEY-1EF01"

			Dim bucketName As String = "deploymenttestbucket" ' Your bucket name
			Dim pdfName As String = "sample"
			Dim objectKey As String = $"IronPdfZip/{pdfName}.pdf"
			Dim objectKeyForSearchablePdf As String = $"IronPdfZip/{pdfName}-SearchablePdf.pdf"

			Try
				' Retrieve the PDF file from S3
				Dim pdfData = Await GetPdfFromS3Async(bucketName, objectKey)

				Dim ironTesseract As New IronTesseract()
				Dim ocrInput As New OcrInput()
				ocrInput.LoadPdf(pdfData)
				Dim result As OcrResult = ironTesseract.Read(ocrInput)

				' Use pdfData (byte array) as needed
				context.Logger.LogLine($"OCR result: {result.Text}")

				' Upload the PDF to S3
				Await UploadPdfToS3Async(bucketName, objectKeyForSearchablePdf, result.SaveAsSearchablePdfBytes())

				context.Logger.LogLine($"PDF uploaded successfully to {bucketName}/{objectKeyForSearchablePdf}")
			Catch e As Exception
				context.Logger.LogLine($"[ERROR] FunctionHandler: {e.Message}")
			End Try
		End Function
		Private Async Function GetPdfFromS3Async(ByVal bucketName As String, ByVal objectKey As String) As Task(Of Byte())
			Dim request = New GetObjectRequest With {
				.BucketName = bucketName,
				.Key = objectKey
			}

			Using response = Await _s3Client.GetObjectAsync(request)
			Using memoryStream As New MemoryStream()
				Await response.ResponseStream.CopyToAsync(memoryStream)
				Return memoryStream.ToArray()
			End Using
			End Using
		End Function

		' Function to upload the PDF file to S3
		Private Async Function UploadPdfToS3Async(ByVal bucketName As String, ByVal objectKey As String, ByVal pdfBytes() As Byte) As Task
			Using memoryStream As New MemoryStream(pdfBytes)
				Dim request = New PutObjectRequest With {
					.BucketName = bucketName,
					.Key = objectKey,
					.InputStream = memoryStream,
					.ContentType = "application/pdf"
				}

				Await _s3Client.PutObjectAsync(request)
			End Using
		End Function
	End Class
End Namespace