Imports System.IO
Imports System.Threading.Tasks

' Every call to this method costs money — per page, permanently
Public Async Function DetectTextAsync(imagePath As String) As Task(Of String)
    Dim imageBytes = File.ReadAllBytes(imagePath)  ' Image leaves your network

    Dim request = New DetectDocumentTextRequest With {
        .Document = New Document With {
            .Bytes = New MemoryStream(imageBytes)
        }
    }

    Dim response = Await _client.DetectDocumentTextAsync(request)  ' per-page charge

    Return String.Join(vbLf, response.Blocks _
        .Where(Function(b) b.BlockType = BlockType.LINE) _
        .Select(Function(b) b.Text))
End Function

Imports System.IO
Imports System.Threading.Tasks

' Every call to this method costs money — per page, permanently
Public Async Function DetectTextAsync(imagePath As String) As Task(Of String)
    Dim imageBytes = File.ReadAllBytes(imagePath)  ' Image leaves your network

    Dim request = New DetectDocumentTextRequest With {
        .Document = New Document With {
            .Bytes = New MemoryStream(imageBytes)
        }
    }

    Dim response = Await _client.DetectDocumentTextAsync(request)  ' per-page charge

    Return String.Join(vbLf, response.Blocks _
        .Where(Function(b) b.BlockType = BlockType.LINE) _
        .Select(Function(b) b.Text))
End Function

Imports System.IO
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.Textract.Model

Public Class DocumentProcessor
    Private _client As AmazonTextractClient

    Public Sub New(client As AmazonTextractClient)
        _client = client
    End Sub

    ' This code sends PHI, legal documents, financial records — whatever is in
    ' the file — to Amazon Web Services infrastructure
    Public Async Function ProcessSensitiveDocumentAsync(documentPath As String) As Task(Of String)
        Dim imageBytes = File.ReadAllBytes(documentPath)

        ' Data crosses your security perimeter here
        Dim request As New DetectDocumentTextRequest With {
            .Document = New Document With {
                .Bytes = New MemoryStream(imageBytes)
            }
        }

        ' Amazon processes it; you receive text back
        Dim response = Await _client.DetectDocumentTextAsync(request)

        Return String.Join(vbLf, response.Blocks _
            .Where(Function(b) b.BlockType = BlockType.LINE) _
            .Select(Function(b) b.Text))
    End Function
End Class

Imports System.IO
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.Textract.Model

Public Class DocumentProcessor
    Private _client As AmazonTextractClient

    Public Sub New(client As AmazonTextractClient)
        _client = client
    End Sub

    ' This code sends PHI, legal documents, financial records — whatever is in
    ' the file — to Amazon Web Services infrastructure
    Public Async Function ProcessSensitiveDocumentAsync(documentPath As String) As Task(Of String)
        Dim imageBytes = File.ReadAllBytes(documentPath)

        ' Data crosses your security perimeter here
        Dim request As New DetectDocumentTextRequest With {
            .Document = New Document With {
                .Bytes = New MemoryStream(imageBytes)
            }
        }

        ' Amazon processes it; you receive text back
        Dim response = Await _client.DetectDocumentTextAsync(request)

        Return String.Join(vbLf, response.Blocks _
            .Where(Function(b) b.BlockType = BlockType.LINE) _
            .Select(Function(b) b.Text))
    End Function
End Class

' IronOCR: document bytes never leave this process
Public Function ProcessSensitiveDocument(documentPath As String) As String
    ' Processes entirely on local hardware — no network call
    Dim ocr As New IronTesseract()
    Return ocr.Read(documentPath).Text
End Function

' IronOCR: document bytes never leave this process
Public Function ProcessSensitiveDocument(documentPath As String) As String
    ' Processes entirely on local hardware — no network call
    Dim ocr As New IronTesseract()
    Return ocr.Read(documentPath).Text
End Function

Imports System
Imports System.IO
Imports System.Threading
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.S3
Imports Amazon.Textract.Model

' Full production-grade async processor for Textract PDF handling
Public Class TextractAsyncProcessor
    Private ReadOnly _textractClient As AmazonTextractClient
    Private ReadOnly _s3Client As AmazonS3Client
    Private ReadOnly _bucketName As String
    Private ReadOnly _pollInterval As TimeSpan = TimeSpan.FromSeconds(5)
    Private ReadOnly _maxWaitTime As TimeSpan = TimeSpan.FromMinutes(10)

    Public Async Function ProcessDocumentAsync(localFilePath As String, Optional cancellationToken As CancellationToken = Nothing) As Task(Of DocumentResult)
        Dim s3Key = $"textract-uploads/{Guid.NewGuid()}{Path.GetExtension(localFilePath)}"

        Try
            ' Phase 1: Upload to S3
            Await UploadToS3Async(localFilePath, s3Key, cancellationToken)

            ' Phase 2: Start Textract job
            Dim jobId = Await StartTextractJobAsync(s3Key, cancellationToken)

            ' Phase 3: Poll until complete (up to 10 minutes)
            Dim pollResult = Await PollForCompletionAsync(jobId, cancellationToken)

            If Not pollResult.Success Then
                Throw New Exception($"Textract job failed: {pollResult.ErrorMessage}")
            End If

            ' Phase 4: Retrieve paginated results
            Return Await GetAllResultsAsync(jobId, cancellationToken)
        Finally
            ' Phase 5: S3 cleanup — must succeed or storage costs accumulate
            Await DeleteFromS3Async(s3Key, cancellationToken)
        End Try
    End Function

    Private Async Function PollForCompletionAsync(jobId As String, cancellationToken As CancellationToken) As Task(Of (Success As Boolean, ErrorMessage As String))
        Dim startTime = DateTime.UtcNow
        Dim pollCount As Integer = 0

        While DateTime.UtcNow - startTime < _maxWaitTime
            cancellationToken.ThrowIfCancellationRequested()

            Dim response = Await _textractClient.GetDocumentTextDetectionAsync(New GetDocumentTextDetectionRequest With {.JobId = jobId}, cancellationToken)

            pollCount += 1

            Select Case response.JobStatus
                Case JobStatus.SUCCEEDED
                    Return (True, Nothing)
                Case JobStatus.FAILED
                    Return (False, If(response.StatusMessage, "Unknown error"))
                Case JobStatus.IN_PROGRESS
                    Await Task.Delay(_pollInterval, cancellationToken)
                Case Else
                    Throw New Exception($"Unknown job status: {response.JobStatus}")
            End Select
        End While

        Return (False, "Job timed out")
    End Function
End Class

Imports System
Imports System.IO
Imports System.Threading
Imports System.Threading.Tasks
Imports Amazon.Textract
Imports Amazon.S3
Imports Amazon.Textract.Model

' Full production-grade async processor for Textract PDF handling
Public Class TextractAsyncProcessor
    Private ReadOnly _textractClient As AmazonTextractClient
    Private ReadOnly _s3Client As AmazonS3Client
    Private ReadOnly _bucketName As String
    Private ReadOnly _pollInterval As TimeSpan = TimeSpan.FromSeconds(5)
    Private ReadOnly _maxWaitTime As TimeSpan = TimeSpan.FromMinutes(10)

    Public Async Function ProcessDocumentAsync(localFilePath As String, Optional cancellationToken As CancellationToken = Nothing) As Task(Of DocumentResult)
        Dim s3Key = $"textract-uploads/{Guid.NewGuid()}{Path.GetExtension(localFilePath)}"

        Try
            ' Phase 1: Upload to S3
            Await UploadToS3Async(localFilePath, s3Key, cancellationToken)

            ' Phase 2: Start Textract job
            Dim jobId = Await StartTextractJobAsync(s3Key, cancellationToken)

            ' Phase 3: Poll until complete (up to 10 minutes)
            Dim pollResult = Await PollForCompletionAsync(jobId, cancellationToken)

            If Not pollResult.Success Then
                Throw New Exception($"Textract job failed: {pollResult.ErrorMessage}")
            End If

            ' Phase 4: Retrieve paginated results
            Return Await GetAllResultsAsync(jobId, cancellationToken)
        Finally
            ' Phase 5: S3 cleanup — must succeed or storage costs accumulate
            Await DeleteFromS3Async(s3Key, cancellationToken)
        End Try
    End Function

    Private Async Function PollForCompletionAsync(jobId As String, cancellationToken As CancellationToken) As Task(Of (Success As Boolean, ErrorMessage As String))
        Dim startTime = DateTime.UtcNow
        Dim pollCount As Integer = 0

        While DateTime.UtcNow - startTime < _maxWaitTime
            cancellationToken.ThrowIfCancellationRequested()

            Dim response = Await _textractClient.GetDocumentTextDetectionAsync(New GetDocumentTextDetectionRequest With {.JobId = jobId}, cancellationToken)

            pollCount += 1

            Select Case response.JobStatus
                Case JobStatus.SUCCEEDED
                    Return (True, Nothing)
                Case JobStatus.FAILED
                    Return (False, If(response.StatusMessage, "Unknown error"))
                Case JobStatus.IN_PROGRESS
                    Await Task.Delay(_pollInterval, cancellationToken)
                Case Else
                    Throw New Exception($"Unknown job status: {response.JobStatus}")
            End Select
        End While

        Return (False, "Job timed out")
    End Function
End Class

Imports System.IO

' IronOCR: same synchronous API regardless of document type or size
Public Function ProcessDocument(filePath As String) As String
    Using input As New OcrInput()
        If Path.GetExtension(filePath).Equals(".pdf", StringComparison.OrdinalIgnoreCase) Then
            input.LoadPdf(filePath)
        Else
            input.LoadImage(filePath)
        End If

        Return New IronTesseract().Read(input).Text
    End Using
End Function

Imports System.IO

' IronOCR: same synchronous API regardless of document type or size
Public Function ProcessDocument(filePath As String) As String
    Using input As New OcrInput()
        If Path.GetExtension(filePath).Equals(".pdf", StringComparison.OrdinalIgnoreCase) Then
            input.LoadPdf(filePath)
        Else
            input.LoadImage(filePath)
        End If

        Return New IronTesseract().Read(input).Text
    End Using
End Function

' Every environment needs these configured before this constructor succeeds
Public Sub New()
    ' Reads credentials from environment, ~/.aws/credentials, or IAM role
    _client = New AmazonTextractClient(Amazon.RegionEndpoint.USEast1)
End Sub

' Every environment needs these configured before this constructor succeeds
Public Sub New()
    ' Reads credentials from environment, ~/.aws/credentials, or IAM role
    _client = New AmazonTextractClient(Amazon.RegionEndpoint.USEast1)
End Sub

' One-time setup at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' Or from environment — recommended for deployments
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

' One-time setup at application startup
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' Or from environment — recommended for deployments
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE")

' Textract: filter flat block list by type
Dim lines = response.Blocks.Where(Function(b) b.BlockType = BlockType.LINE)
Dim words = response.Blocks.Where(Function(b) b.BlockType = BlockType.WORD)

' IronOCR: direct access to typed collections
Dim result = ocr.Read(imagePath)
Dim lines = result.Lines   ' IEnumerable(Of OcrResult.OcrResultLine)
Dim words = result.Words   ' IEnumerable(Of OcrResult.OcrResultWord)
For Each word In result.Words
    Console.WriteLine($"'{word.Text}' at ({word.X},{word.Y}) confidence {word.Confidence}%")
Next

' Textract: filter flat block list by type
Dim lines = response.Blocks.Where(Function(b) b.BlockType = BlockType.LINE)
Dim words = response.Blocks.Where(Function(b) b.BlockType = BlockType.WORD)

' IronOCR: direct access to typed collections
Dim result = ocr.Read(imagePath)
Dim lines = result.Lines   ' IEnumerable(Of OcrResult.OcrResultLine)
Dim words = result.Words   ' IEnumerable(Of OcrResult.OcrResultWord)
For Each word In result.Words
    Console.WriteLine($"'{word.Text}' at ({word.X},{word.Y}) confidence {word.Confidence}%")
Next

Imports IronOcr

Public Class PdfProcessor
    ' Textract: upload to S3 → start job → poll → paginate → cleanup (50+ lines)
    ' IronOCR equivalent:
    Public Function ProcessPdf(pdfPath As String) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdf(pdfPath)
            Return ocr.Read(input).Text
        End Using
    End Function

    ' Specific page ranges (no Textract equivalent without async job per range)
    Public Function ProcessPdfPages(pdfPath As String, startPage As Integer, endPage As Integer) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdfPages(pdfPath, startPage, endPage)
            Return ocr.Read(input).Text
        End Using
    End Function
End Class

Imports IronOcr

Public Class PdfProcessor
    ' Textract: upload to S3 → start job → poll → paginate → cleanup (50+ lines)
    ' IronOCR equivalent:
    Public Function ProcessPdf(pdfPath As String) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdf(pdfPath)
            Return ocr.Read(input).Text
        End Using
    End Function

    ' Specific page ranges (no Textract equivalent without async job per range)
    Public Function ProcessPdfPages(pdfPath As String, startPage As Integer, endPage As Integer) As String
        Dim ocr As New IronTesseract()
        Using input As New OcrInput()
            input.LoadPdfPages(pdfPath, startPage, endPage)
            Return ocr.Read(input).Text
        End Using
    End Function
End Class

Imports IronOcr

Dim input As New OcrInput()
input.LoadImage("low-quality-scan.jpg")

input.Deskew()              ' Fix rotation from scanner misalignment
input.DeNoise()             ' Remove scanner noise artifacts
input.Contrast()            ' Boost faint text
input.EnhanceResolution(300) ' Scale to optimal OCR resolution

Dim result = New IronTesseract().Read(input)
Console.WriteLine($"Confidence: {result.Confidence}%")

Imports IronOcr

Dim input As New OcrInput()
input.LoadImage("low-quality-scan.jpg")

input.Deskew()              ' Fix rotation from scanner misalignment
input.DeNoise()             ' Remove scanner noise artifacts
input.Contrast()            ' Boost faint text
input.EnhanceResolution(300) ' Scale to optimal OCR resolution

Dim result = New IronTesseract().Read(input)
Console.WriteLine($"Confidence: {result.Confidence}%")

Imports System.Threading.Tasks

' Preserves async call site for minimal refactoring
Public Async Function ExtractTextAsync(path As String) As Task(Of String)
    Return Await Task.Run(Function() New IronTesseract().Read(path).Text)
End Function

Imports System.Threading.Tasks

' Preserves async call site for minimal refactoring
Public Async Function ExtractTextAsync(path As String) As Task(Of String)
    Return Await Task.Run(Function() New IronTesseract().Read(path).Text)
End Function