AWS LambdaでドキュメントのPDFテキスト抽出とOCR処理をする方法

// Set temporary folder path and log file path for IronOCR.
var awsTmpPath = @"/tmp/";
IronOcr.Installation.InstallationPath = awsTmpPath;
IronOcr.Installation.LogFilePath = awsTmpPath;

' Set temporary folder path and log file path for IronOCR.
Dim awsTmpPath = "/tmp/"
IronOcr.Installation.InstallationPath = awsTmpPath
IronOcr.Installation.LogFilePath = awsTmpPath

using Amazon.Lambda.Core;
using Amazon.S3;
using Amazon.S3.Model;
using IronOcr;
using System;
using System.IO;
using System.Threading.Tasks;

// 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
    {
        // Initialize the S3 client with a specific region endpoint
        private static readonly IAmazonS3 _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.APSoutheast1);

        /// <summary>
        /// Function handler to process OCR on the PDF stored in S3.
        /// </summary>
        /// <param name="context">The ILambdaContext that provides methods for logging and describing the Lambda environment.</param>
        public async Task FunctionHandler(ILambdaContext context)
        {
            // Set up necessary paths for IronOCR
            var awsTmpPath = @"/tmp/";
            IronOcr.Installation.InstallationPath = awsTmpPath;
            IronOcr.Installation.LogFilePath = awsTmpPath;

            // Set license key for IronOCR
            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);

                // Initialize IronTesseract for OCR processing
                IronTesseract ironTesseract = new IronTesseract();
                OcrInput ocrInput = new OcrInput();
                ocrInput.LoadPdf(pdfData);
                OcrResult result = ironTesseract.Read(ocrInput);

                // Log the OCR result
                context.Logger.LogLine($"OCR result: {result.Text}");

                // Upload the searchable 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}");
            }
        }

        /// <summary>
        /// Retrieves a PDF from S3 and returns it as a byte array.
        /// </summary>
        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();
            }
        }

        /// <summary>
        /// Uploads the generated searchable PDF back to S3.
        /// </summary>
        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
Imports System
Imports System.IO
Imports System.Threading.Tasks

' 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]
		' Initialize the S3 client with a specific region endpoint
		Private Shared ReadOnly _s3Client As IAmazonS3 = New AmazonS3Client(Amazon.RegionEndpoint.APSoutheast1)

		''' <summary>
		''' Function handler to process OCR on the PDF stored in S3.
		''' </summary>
		''' <param name="context">The ILambdaContext that provides methods for logging and describing the Lambda environment.</param>
		Public Async Function FunctionHandler(ByVal context As ILambdaContext) As Task
			' Set up necessary paths for IronOCR
			Dim awsTmpPath = "/tmp/"
			IronOcr.Installation.InstallationPath = awsTmpPath
			IronOcr.Installation.LogFilePath = awsTmpPath

			' Set license key for IronOCR
			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)

				' Initialize IronTesseract for OCR processing
				Dim ironTesseract As New IronTesseract()
				Dim ocrInput As New OcrInput()
				ocrInput.LoadPdf(pdfData)
				Dim result As OcrResult = ironTesseract.Read(ocrInput)

				' Log the OCR result
				context.Logger.LogLine($"OCR result: {result.Text}")

				' Upload the searchable 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

		''' <summary>
		''' Retrieves a PDF from S3 and returns it as a byte array.
		''' </summary>
		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

		''' <summary>
		''' Uploads the generated searchable PDF back to S3.
		''' </summary>
		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