Como usar Async e Multithreading em C#

// Mindee: invoice with bank details leaves your infrastructure on this line
var response = await _client.ParseAsync<InvoiceV4>(new LocalInputSource("invoice.pdf"));
// IBAN, routing number, EIN, line items — all transmitted toMindeecloud

Imports System.Threading.Tasks

' Mindee: invoice with bank details leaves your infrastructure on this line
Dim response = Await _client.ParseAsync(Of InvoiceV4)(New LocalInputSource("invoice.pdf"))
' IBAN, routing number, EIN, line items — all transmitted to Mindee cloud

// IronOCR: same invoice, same result, zero data transmission
var result = new IronTesseract().Read("invoice.pdf");
// All processing local — bank details never leave your machine

' IronOCR: same invoice, same result, zero data transmission
Dim result = New IronTesseract().Read("invoice.pdf")
' All processing local — bank details never leave your machine

dotnet remove package Mindee

// Before (Mindee)
using Mindee;
using Mindee.Input;
using Mindee.Product.Invoice;
using Mindee.Product.Receipt;
using Mindee.Product.FinancialDocument;

// After (IronOCR)
using IronOcr;

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.Invoice
Imports Mindee.Product.Receipt
Imports Mindee.Product.FinancialDocument

Imports IronOcr

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

using Mindee;
using Mindee.Input;
using Mindee.Product.Invoice;

public class MindeeZoneExtractor
{
    private readonly MindeeClient _client;

    public MindeeZoneExtractor(string apiKey)
    {
        _client = new MindeeClient(apiKey);
    }

    public async Task<(string invoiceNumber, string supplierName, decimal? total)>
        ExtractKeyFieldsAsync(string filePath)
    {
        // Document transmitted toMindee— spatial field detection happens server-side
        var inputSource = new LocalInputSource(filePath);
        var response    = await _client.ParseAsync<InvoiceV4>(inputSource);
        var prediction  = response.Document.Inference.Prediction;

        // Fields arrive pre-parsed; no zone configuration required on your end
        return (
            prediction.InvoiceNumber?.Value,
            prediction.SupplierName?.Value,
            prediction.TotalAmount?.Value
        );
    }
}

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.Invoice
Imports System.Threading.Tasks

Public Class MindeeZoneExtractor
    Private ReadOnly _client As MindeeClient

    Public Sub New(apiKey As String)
        _client = New MindeeClient(apiKey)
    End Sub

    Public Async Function ExtractKeyFieldsAsync(filePath As String) As Task(Of (invoiceNumber As String, supplierName As String, total As Decimal?))
        ' Document transmitted to Mindee— spatial field detection happens server-side
        Dim inputSource = New LocalInputSource(filePath)
        Dim response = Await _client.ParseAsync(Of InvoiceV4)(inputSource)
        Dim prediction = response.Document.Inference.Prediction

        ' Fields arrive pre-parsed; no zone configuration required on your end
        Return (
            prediction.InvoiceNumber?.Value,
            prediction.SupplierName?.Value,
            prediction.TotalAmount?.Value
        )
    End Function
End Class

using IronOcr;
using System.Text.RegularExpressions;

public class IronOcrZoneExtractor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public (string invoiceNumber, string supplierName, string total)
        ExtractKeyFields(string filePath)
    {
        // Zone 1: supplier name — top 12% of document, full width
        var headerRegion = new CropRectangle(0, 0, 850, 120);
        using var headerInput = new OcrInput();
        headerInput.LoadImage(filePath, headerRegion);
        var supplierResult = _ocr.Read(headerInput);

        // Zone 2: invoice number and date — upper-right quadrant
        var metaRegion = new CropRectangle(450, 80, 400, 100);
        using var metaInput = new OcrInput();
        metaInput.LoadImage(filePath, metaRegion);
        var metaResult = _ocr.Read(metaInput);

        // Zone 3: totals block — bottom-right 20%
        var totalsRegion = new CropRectangle(500, 800, 350, 200);
        using var totalsInput = new OcrInput();
        totalsInput.LoadImage(filePath, totalsRegion);
        var totalsResult = _ocr.Read(totalsInput);

        var invoiceNumber = Regex.Match(
            metaResult.Text,
            @"Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)",
            RegexOptions.IgnoreCase).Groups[1].Value;

        var total = Regex.Match(
            totalsResult.Text,
            @"Total\s*(?:Due)?\s*:?\s*\$?([\d,]+\.?\d*)",
            RegexOptions.IgnoreCase).Groups[1].Value;

        // Supplier name is the first substantial text line in the header zone
        var supplierName = supplierResult.Text
            .Split('\n')
            .FirstOrDefault(l => l.Trim().Length > 4)
            ?.Trim();

        return (invoiceNumber, supplierName, total);
    }
}

Imports IronOcr
Imports System.Text.RegularExpressions

Public Class IronOcrZoneExtractor
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ExtractKeyFields(filePath As String) As (invoiceNumber As String, supplierName As String, total As String)
        ' Zone 1: supplier name — top 12% of document, full width
        Dim headerRegion As New CropRectangle(0, 0, 850, 120)
        Using headerInput As New OcrInput()
            headerInput.LoadImage(filePath, headerRegion)
            Dim supplierResult = _ocr.Read(headerInput)

            ' Zone 2: invoice number and date — upper-right quadrant
            Dim metaRegion As New CropRectangle(450, 80, 400, 100)
            Using metaInput As New OcrInput()
                metaInput.LoadImage(filePath, metaRegion)
                Dim metaResult = _ocr.Read(metaInput)

                ' Zone 3: totals block — bottom-right 20%
                Dim totalsRegion As New CropRectangle(500, 800, 350, 200)
                Using totalsInput As New OcrInput()
                    totalsInput.LoadImage(filePath, totalsRegion)
                    Dim totalsResult = _ocr.Read(totalsInput)

                    Dim invoiceNumber = Regex.Match(metaResult.Text, "Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)", RegexOptions.IgnoreCase).Groups(1).Value
                    Dim total = Regex.Match(totalsResult.Text, "Total\s*(?:Due)?\s*:?\s*\$?([\d,]+\.?\d*)", RegexOptions.IgnoreCase).Groups(1).Value

                    ' Supplier name is the first substantial text line in the header zone
                    Dim supplierName = supplierResult.Text.Split(vbLf).FirstOrDefault(Function(l) l.Trim().Length > 4)?.Trim()

                    Return (invoiceNumber, supplierName, total)
                End Using
            End Using
        End Using
    End Function
End Class

using Mindee;
using Mindee.Input;
using Mindee.Product.Receipt;

public class MindeeExpenseReportProcessor
{
    private readonly MindeeClient _client;

    public MindeeExpenseReportProcessor(string apiKey)
    {
        _client = new MindeeClient(apiKey);
    }

    public async Task<List<ExpenseSummary>> ProcessExpenseReportAsync(string pdfPath)
    {
        var summaries = new List<ExpenseSummary>();

        //Mindeeprocesses per-document; each page of a PDF is a separate upload
        // For a 10-page expense report: 10 API calls, 10 pages billed
        var inputSource = new LocalInputSource(pdfPath);
        var response    = await _client.ParseAsync<ReceiptV5>(inputSource);

        var prediction = response.Document.Inference.Prediction;

        summaries.Add(new ExpenseSummary
        {
            MerchantName  = prediction.SupplierName?.Value,
            Date          = prediction.Date?.Value?.ToString(),
            TotalAmount   = prediction.TotalAmount?.Value ?? 0m,
            Category      = prediction.Category?.Value
        });

        return summaries;
    }
}

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.Receipt
Imports System.Threading.Tasks

Public Class MindeeExpenseReportProcessor
    Private ReadOnly _client As MindeeClient

    Public Sub New(apiKey As String)
        _client = New MindeeClient(apiKey)
    End Sub

    Public Async Function ProcessExpenseReportAsync(pdfPath As String) As Task(Of List(Of ExpenseSummary))
        Dim summaries As New List(Of ExpenseSummary)()

        ' Mindee processes per-document; each page of a PDF is a separate upload
        ' For a 10-page expense report: 10 API calls, 10 pages billed
        Dim inputSource As New LocalInputSource(pdfPath)
        Dim response = Await _client.ParseAsync(Of ReceiptV5)(inputSource)

        Dim prediction = response.Document.Inference.Prediction

        summaries.Add(New ExpenseSummary With {
            .MerchantName = prediction.SupplierName?.Value,
            .Date = prediction.Date?.Value?.ToString(),
            .TotalAmount = If(prediction.TotalAmount?.Value, 0D),
            .Category = prediction.Category?.Value
        })

        Return summaries
    End Function
End Class

using IronOcr;
using System.Text.RegularExpressions;

public class IronOcrExpenseReportProcessor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public List<ExpenseSummary> ProcessExpenseReport(string pdfPath)
    {
        // Load entire multi-page PDF in one call — no per-page upload
        using var input = new OcrInput();
        input.LoadPdf(pdfPath);    // all pages loaded locally

        var result    = _ocr.Read(input);
        var summaries = new List<ExpenseSummary>();

        // Each page maps to one receipt in the expense report
        foreach (var page in result.Pages)
        {
            var pageText = page.Text;

            // Skip pages without receipt content
            if (!pageText.Contains("Total", StringComparison.OrdinalIgnoreCase))
                continue;

            var merchantName = page.Lines
                .FirstOrDefault(l => l.Text.Trim().Length > 4)
                ?.Text.Trim();

            var totalMatch = Regex.Match(
                pageText,
                @"(?:Total|Amount\s+Due|Grand\s+Total)\s*:?\s*\$?([\d,]+\.\d{2})",
                RegexOptions.IgnoreCase);

            var dateMatch = Regex.Match(
                pageText,
                @"\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b");

            var categoryMatch = Regex.Match(
                pageText,
                @"(?:Category|Dept|Department)\s*:?\s*(.+)",
                RegexOptions.IgnoreCase);

            summaries.Add(new ExpenseSummary
            {
                PageNumber   = page.PageNumber,
                MerchantName = merchantName,
                Date         = dateMatch.Success ? dateMatch.Value : null,
                TotalAmount  = totalMatch.Success
                    ? decimal.Parse(totalMatch.Groups[1].Value.Replace(",", ""))
                    : 0m,
                Category     = categoryMatch.Success
                    ? categoryMatch.Groups[1].Value.Trim()
                    : null,
                Confidence   = page.Words.Any()
                    ? page.Words.Average(w => (double)w.Confidence)
                    : 0
            });
        }

        return summaries;
    }
}

public class ExpenseSummary
{
    public int    PageNumber   { get; set; }
    public string MerchantName { get; set; }
    public string Date         { get; set; }
    public decimal TotalAmount { get; set; }
    public string Category     { get; set; }
    public double Confidence   { get; set; }
}

Imports IronOcr
Imports System.Text.RegularExpressions

Public Class IronOcrExpenseReportProcessor
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ProcessExpenseReport(pdfPath As String) As List(Of ExpenseSummary)
        ' Load entire multi-page PDF in one call — no per-page upload
        Using input As New OcrInput()
            input.LoadPdf(pdfPath) ' all pages loaded locally

            Dim result = _ocr.Read(input)
            Dim summaries As New List(Of ExpenseSummary)()

            ' Each page maps to one receipt in the expense report
            For Each page In result.Pages
                Dim pageText = page.Text

                ' Skip pages without receipt content
                If Not pageText.Contains("Total", StringComparison.OrdinalIgnoreCase) Then
                    Continue For
                End If

                Dim merchantName = page.Lines _
                    .FirstOrDefault(Function(l) l.Text.Trim().Length > 4) _
                    ?.Text.Trim()

                Dim totalMatch = Regex.Match(
                    pageText,
                    "(?:Total|Amount\s+Due|Grand\s+Total)\s*:?\s*\$?([\d,]+\.\d{2})",
                    RegexOptions.IgnoreCase)

                Dim dateMatch = Regex.Match(
                    pageText,
                    "\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b")

                Dim categoryMatch = Regex.Match(
                    pageText,
                    "(?:Category|Dept|Department)\s*:?\s*(.+)",
                    RegexOptions.IgnoreCase)

                summaries.Add(New ExpenseSummary With {
                    .PageNumber = page.PageNumber,
                    .MerchantName = merchantName,
                    .Date = If(dateMatch.Success, dateMatch.Value, Nothing),
                    .TotalAmount = If(totalMatch.Success, Decimal.Parse(totalMatch.Groups(1).Value.Replace(",", "")), 0D),
                    .Category = If(categoryMatch.Success, categoryMatch.Groups(1).Value.Trim(), Nothing),
                    .Confidence = If(page.Words.Any(), page.Words.Average(Function(w) CDbl(w.Confidence)), 0)
                })
            Next

            Return summaries
        End Using
    End Function
End Class

Public Class ExpenseSummary
    Public Property PageNumber As Integer
    Public Property MerchantName As String
    Public Property Date As String
    Public Property TotalAmount As Decimal
    Public Property Category As String
    Public Property Confidence As Double
End Class

using Mindee;
using Mindee.Input;
using Mindee.Product.Invoice;

public class MindeeScanProcessor
{
    private readonly MindeeClient _client;

    public MindeeScanProcessor(string apiKey)
    {
        _client = new MindeeClient(apiKey);
    }

    public async Task<ScanResult> ProcessScannedInvoiceAsync(string scanPath)
    {
        //Mindeeapplies internal normalization — no developer control over preprocessing
        var inputSource = new LocalInputSource(scanPath);
        var response    = await _client.ParseAsync<InvoiceV4>(inputSource);
        var prediction  = response.Document.Inference.Prediction;

        return new ScanResult
        {
            InvoiceNumber = prediction.InvoiceNumber?.Value,
            Total         = prediction.TotalAmount?.Value,
            // Per-field confidence: only proxy for scan quality
            InvoiceNumberConfidence = prediction.InvoiceNumber?.Confidence,
            TotalConfidence         = prediction.TotalAmount?.Confidence
        };
    }
}

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.Invoice
Imports System.Threading.Tasks

Public Class MindeeScanProcessor
    Private ReadOnly _client As MindeeClient

    Public Sub New(apiKey As String)
        _client = New MindeeClient(apiKey)
    End Sub

    Public Async Function ProcessScannedInvoiceAsync(scanPath As String) As Task(Of ScanResult)
        ' Mindee applies internal normalization — no developer control over preprocessing
        Dim inputSource = New LocalInputSource(scanPath)
        Dim response = Await _client.ParseAsync(Of InvoiceV4)(inputSource)
        Dim prediction = response.Document.Inference.Prediction

        Return New ScanResult With {
            .InvoiceNumber = prediction.InvoiceNumber?.Value,
            .Total = prediction.TotalAmount?.Value,
            ' Per-field confidence: only proxy for scan quality
            .InvoiceNumberConfidence = prediction.InvoiceNumber?.Confidence,
            .TotalConfidence = prediction.TotalAmount?.Confidence
        }
    End Function
End Class

using IronOcr;
using System.Text.RegularExpressions;

public class IronOcrScanProcessor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public ScanResult ProcessScannedInvoice(string scanPath)
    {
        // First pass: read without preprocessing
        var quickResult = _ocr.Read(scanPath);

        OcrResult result;

        if (quickResult.Confidence < 75)
        {
            // Low confidence — apply full preprocessing pipeline
            using var input = new OcrInput();
            input.LoadImage(scanPath);
            input.Deskew();       // correct page rotation up to ±45 degrees
            input.DeNoise();      // remove scanner artifacts and speckle
            input.Contrast();     // normalize contrast for faded or overexposed scans
            input.Sharpen();      // sharpen blurred text edges

            result = _ocr.Read(input);
        }
        else
        {
            result = quickResult;
        }

        var invoiceNumber = Regex.Match(
            result.Text,
            @"Invoice\s*(?:Number|#|No\.?)?\s*:?\s*([A-Z0-9\-]+)",
            RegexOptions.IgnoreCase).Groups[1].Value;

        var total = Regex.Match(
            result.Text,
            @"(?:Total|Amount\s+Due)\s*:?\s*\$?([\d,]+\.\d{2})",
            RegexOptions.IgnoreCase).Groups[1].Value;

        return new ScanResult
        {
            InvoiceNumber    = invoiceNumber,
            Total            = total,
            DocumentConfidence = result.Confidence,
            PreprocessingApplied = quickResult.Confidence < 75
        };
    }
}

public class ScanResult
{
    public string InvoiceNumber        { get; set; }
    public string Total                { get; set; }
    public double DocumentConfidence   { get; set; }
    public bool   PreprocessingApplied { get; set; }
}

Imports IronOcr
Imports System.Text.RegularExpressions

Public Class IronOcrScanProcessor
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ProcessScannedInvoice(scanPath As String) As ScanResult
        ' First pass: read without preprocessing
        Dim quickResult = _ocr.Read(scanPath)

        Dim result As OcrResult

        If quickResult.Confidence < 75 Then
            ' Low confidence — apply full preprocessing pipeline
            Using input As New OcrInput()
                input.LoadImage(scanPath)
                input.Deskew()       ' correct page rotation up to ±45 degrees
                input.DeNoise()      ' remove scanner artifacts and speckle
                input.Contrast()     ' normalize contrast for faded or overexposed scans
                input.Sharpen()      ' sharpen blurred text edges

                result = _ocr.Read(input)
            End Using
        Else
            result = quickResult
        End If

        Dim invoiceNumber = Regex.Match(
            result.Text,
            "Invoice\s*(?:Number|#|No\.?)?\s*:?\s*([A-Z0-9\-]+)",
            RegexOptions.IgnoreCase).Groups(1).Value

        Dim total = Regex.Match(
            result.Text,
            "(?:Total|Amount\s+Due)\s*:?\s*\$?([\d,]+\.\d{2})",
            RegexOptions.IgnoreCase).Groups(1).Value

        Return New ScanResult With {
            .InvoiceNumber = invoiceNumber,
            .Total = total,
            .DocumentConfidence = result.Confidence,
            .PreprocessingApplied = quickResult.Confidence < 75
        }
    End Function
End Class

Public Class ScanResult
    Public Property InvoiceNumber As String
    Public Property Total As String
    Public Property DocumentConfidence As Double
    Public Property PreprocessingApplied As Boolean
End Class

using Mindee;
using Mindee.Input;
using Mindee.Product.Invoice;

public class MindeeArchiveProcessor
{
    private readonly MindeeClient _client;

    public MindeeArchiveProcessor(string apiKey)
    {
        _client = new MindeeClient(apiKey);
    }

    public async Task ArchiveInvoiceAsync(string scanPath, string archivePath)
    {
        // Extract fields viaMindee(document transmitted to cloud)
        var inputSource = new LocalInputSource(scanPath);
        var response    = await _client.ParseAsync<InvoiceV4>(inputSource);
        var prediction  = response.Document.Inference.Prediction;

        //Mindeereturns no PDF output — searchable PDF requires a separate library
        // (e.g., iTextSharp, PdfSharp, or a separate OCR library)
        // The scan at scanPath is the only PDF available for archiving;
        // it remains image-only with no embedded text layer
        Console.WriteLine($"Fields extracted. Searchable PDF: not available from Mindee.");
        Console.WriteLine($"Invoice: {prediction.InvoiceNumber?.Value}");
    }
}

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.Invoice
Imports System.Threading.Tasks

Public Class MindeeArchiveProcessor
    Private ReadOnly _client As MindeeClient

    Public Sub New(apiKey As String)
        _client = New MindeeClient(apiKey)
    End Sub

    Public Async Function ArchiveInvoiceAsync(scanPath As String, archivePath As String) As Task
        ' Extract fields via Mindee (document transmitted to cloud)
        Dim inputSource = New LocalInputSource(scanPath)
        Dim response = Await _client.ParseAsync(Of InvoiceV4)(inputSource)
        Dim prediction = response.Document.Inference.Prediction

        ' Mindee returns no PDF output — searchable PDF requires a separate library
        ' (e.g., iTextSharp, PdfSharp, or a separate OCR library)
        ' The scan at scanPath is the only PDF available for archiving;
        ' it remains image-only with no embedded text layer
        Console.WriteLine($"Fields extracted. Searchable PDF: not available from Mindee.")
        Console.WriteLine($"Invoice: {prediction.InvoiceNumber?.Value}")
    End Function
End Class

using IronOcr;
using System.Text.RegularExpressions;

public class IronOcrArchiveProcessor
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public ArchiveResult ArchiveInvoice(string scanPath, string archiveOutputPath)
    {
        // Apply preprocessing before recognition and archiving
        using var input = new OcrInput();
        input.LoadPdf(scanPath);   // works with both PDF scans and image files
        input.Deskew();
        input.DeNoise();

        var result = _ocr.Read(input);

        // Extract fields from the same recognition pass
        var invoiceNumber = Regex.Match(
            result.Text,
            @"Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)",
            RegexOptions.IgnoreCase).Groups[1].Value;

        var vendor = result.Pages.FirstOrDefault()?.Lines
            .FirstOrDefault(l => l.Text.Trim().Length > 4)
            ?.Text.Trim();

        var totalMatch = Regex.Match(
            result.Text,
            @"Total\s*(?:Due)?\s*:?\s*\$?([\d,]+\.\d{2})",
            RegexOptions.IgnoreCase);

        // Write searchable PDF to archive in one call — no separate library needed
        result.SaveAsSearchablePdf(archiveOutputPath);

        return new ArchiveResult
        {
            InvoiceNumber    = invoiceNumber,
            VendorName       = vendor,
            Total            = totalMatch.Success ? totalMatch.Groups[1].Value : null,
            ArchivePath      = archiveOutputPath,
            DocumentConfidence = result.Confidence,
            PageCount        = result.Pages.Count()
        };
    }
}

public class ArchiveResult
{
    public string InvoiceNumber      { get; set; }
    public string VendorName         { get; set; }
    public string Total              { get; set; }
    public string ArchivePath        { get; set; }
    public double DocumentConfidence { get; set; }
    public int    PageCount          { get; set; }
}

Imports IronOcr
Imports System.Text.RegularExpressions
Imports System.Linq

Public Class IronOcrArchiveProcessor
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ArchiveInvoice(scanPath As String, archiveOutputPath As String) As ArchiveResult
        ' Apply preprocessing before recognition and archiving
        Using input As New OcrInput()
            input.LoadPdf(scanPath) ' works with both PDF scans and image files
            input.Deskew()
            input.DeNoise()

            Dim result = _ocr.Read(input)

            ' Extract fields from the same recognition pass
            Dim invoiceNumber = Regex.Match(result.Text, "Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)", RegexOptions.IgnoreCase).Groups(1).Value

            Dim vendor = result.Pages.FirstOrDefault()?.Lines.FirstOrDefault(Function(l) l.Text.Trim().Length > 4)?.Text.Trim()

            Dim totalMatch = Regex.Match(result.Text, "Total\s*(?:Due)?\s*:?\s*\$?([\d,]+\.\d{2})", RegexOptions.IgnoreCase)

            ' Write searchable PDF to archive in one call — no separate library needed
            result.SaveAsSearchablePdf(archiveOutputPath)

            Return New ArchiveResult With {
                .InvoiceNumber = invoiceNumber,
                .VendorName = vendor,
                .Total = If(totalMatch.Success, totalMatch.Groups(1).Value, Nothing),
                .ArchivePath = archiveOutputPath,
                .DocumentConfidence = result.Confidence,
                .PageCount = result.Pages.Count()
            }
        End Using
    End Function
End Class

Public Class ArchiveResult
    Public Property InvoiceNumber As String
    Public Property VendorName As String
    Public Property Total As String
    Public Property ArchivePath As String
    Public Property DocumentConfidence As Double
    Public Property PageCount As Integer
End Class

using Mindee;
using Mindee.Input;
using Mindee.Product.FinancialDocument;

public class MindeeFinancialRouter
{
    private readonly MindeeClient _client;

    public MindeeFinancialRouter(string apiKey)
    {
        _client = new MindeeClient(apiKey);
    }

    public async Task<FinancialSummary> ProcessFinancialDocumentAsync(string filePath)
    {
        // All financial documents uploaded for auto-detection and parsing
        var inputSource = new LocalInputSource(filePath);
        var response    = await _client.ParseAsync<FinancialDocumentV1>(inputSource);
        var prediction  = response.Document.Inference.Prediction;

        return new FinancialSummary
        {
            DocumentType  = prediction.DocumentType?.Value,  // "INVOICE" or "RECEIPT"
            InvoiceNumber = prediction.InvoiceNumber?.Value,
            Date          = prediction.Date?.Value?.ToString(),
            TotalAmount   = prediction.TotalAmount?.Value,
            SupplierName  = prediction.SupplierName?.Value,
            CustomerName  = prediction.CustomerName?.Value
        };
    }
}

Imports Mindee
Imports Mindee.Input
Imports Mindee.Product.FinancialDocument
Imports System.Threading.Tasks

Public Class MindeeFinancialRouter
    Private ReadOnly _client As MindeeClient

    Public Sub New(apiKey As String)
        _client = New MindeeClient(apiKey)
    End Sub

    Public Async Function ProcessFinancialDocumentAsync(filePath As String) As Task(Of FinancialSummary)
        ' All financial documents uploaded for auto-detection and parsing
        Dim inputSource = New LocalInputSource(filePath)
        Dim response = Await _client.ParseAsync(Of FinancialDocumentV1)(inputSource)
        Dim prediction = response.Document.Inference.Prediction

        Return New FinancialSummary With {
            .DocumentType = prediction.DocumentType?.Value,  ' "INVOICE" or "RECEIPT"
            .InvoiceNumber = prediction.InvoiceNumber?.Value,
            .Date = prediction.Date?.Value?.ToString(),
            .TotalAmount = prediction.TotalAmount?.Value,
            .SupplierName = prediction.SupplierName?.Value,
            .CustomerName = prediction.CustomerName?.Value
        }
    End Function
End Class

using IronOcr;
using System.Text.RegularExpressions;

public class IronOcrFinancialRouter
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public FinancialSummary ProcessFinancialDocument(string filePath)
    {
        var result = _ocr.Read(filePath);
        var text   = result.Text;

        // Detect document type using structural keywords from word data
        var isInvoice = DetectInvoice(result);

        if (isInvoice)
        {
            return new FinancialSummary
            {
                DocumentType  = "INVOICE",
                InvoiceNumber = Regex.Match(text,
                    @"Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)",
                    RegexOptions.IgnoreCase).Groups[1].Value,
                Date          = Regex.Match(text,
                    @"(?:Invoice\s+)?Date\s*:?\s*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})",
                    RegexOptions.IgnoreCase).Groups[1].Value,
                TotalAmount   = ParseAmount(text,
                    @"Total\s*(?:Due|Amount)?\s*:?\s*\$?([\d,]+\.\d{2})"),
                SupplierName  = ExtractTopLine(result),
                CustomerName  = Regex.Match(text,
                    @"Bill\s+To\s*:?\s*\n?(.+)",
                    RegexOptions.IgnoreCase).Groups[1].Value.Trim()
            };
        }
        else
        {
            // Receipt structure: merchant at top, no "Bill To" section
            return new FinancialSummary
            {
                DocumentType = "RECEIPT",
                Date         = Regex.Match(text,
                    @"\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b").Value,
                TotalAmount  = ParseAmount(text,
                    @"(?:Total|Amount\s+Due|Grand\s+Total)\s*:?\s*\$?([\d,]+\.\d{2})"),
                SupplierName = ExtractTopLine(result)
            };
        }
    }

    private bool DetectInvoice(OcrResult result)
    {
        // Invoice indicators: "Invoice", "Bill To", "Due Date", line items with quantities
        var text = result.Text;
        var invoiceSignals = new[] { "Invoice", "Bill To", "Due Date", "Purchase Order" };
        return invoiceSignals.Any(s =>
            text.IndexOf(s, StringComparison.OrdinalIgnoreCase) >= 0);
    }

    private string ExtractTopLine(OcrResult result)
    {
        return result.Pages
            .FirstOrDefault()
            ?.Lines
            .FirstOrDefault(l => l.Text.Trim().Length > 4)
            ?.Text.Trim();
    }

    private decimal? ParseAmount(string text, string pattern)
    {
        var match = Regex.Match(text, pattern, RegexOptions.IgnoreCase);
        if (match.Success &&
            decimal.TryParse(match.Groups[1].Value.Replace(",", ""), out var val))
            return val;
        return null;
    }
}

public class FinancialSummary
{
    public string   DocumentType  { get; set; }
    public string   InvoiceNumber { get; set; }
    public string   Date          { get; set; }
    public decimal? TotalAmount   { get; set; }
    public string   SupplierName  { get; set; }
    public string   CustomerName  { get; set; }
}

Imports IronOcr
Imports System.Text.RegularExpressions

Public Class IronOcrFinancialRouter
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ProcessFinancialDocument(filePath As String) As FinancialSummary
        Dim result = _ocr.Read(filePath)
        Dim text = result.Text

        ' Detect document type using structural keywords from word data
        Dim isInvoice = DetectInvoice(result)

        If isInvoice Then
            Return New FinancialSummary With {
                .DocumentType = "INVOICE",
                .InvoiceNumber = Regex.Match(text,
                    "Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)",
                    RegexOptions.IgnoreCase).Groups(1).Value,
                .Date = Regex.Match(text,
                    "(?:Invoice\s+)?Date\s*:?\s*(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})",
                    RegexOptions.IgnoreCase).Groups(1).Value,
                .TotalAmount = ParseAmount(text,
                    "Total\s*(?:Due|Amount)?\s*:?\s*\$?([\d,]+\.\d{2})"),
                .SupplierName = ExtractTopLine(result),
                .CustomerName = Regex.Match(text,
                    "Bill\s+To\s*:?\s*\n?(.+)",
                    RegexOptions.IgnoreCase).Groups(1).Value.Trim()
            }
        Else
            ' Receipt structure: merchant at top, no "Bill To" section
            Return New FinancialSummary With {
                .DocumentType = "RECEIPT",
                .Date = Regex.Match(text,
                    "\b(\d{1,2}[/-]\d{1,2}[/-]\d{2,4})\b").Value,
                .TotalAmount = ParseAmount(text,
                    "(?:Total|Amount\s+Due|Grand\s+Total)\s*:?\s*\$?([\d,]+\.\d{2})"),
                .SupplierName = ExtractTopLine(result)
            }
        End If
    End Function

    Private Function DetectInvoice(result As OcrResult) As Boolean
        ' Invoice indicators: "Invoice", "Bill To", "Due Date", line items with quantities
        Dim text = result.Text
        Dim invoiceSignals = {"Invoice", "Bill To", "Due Date", "Purchase Order"}
        Return invoiceSignals.Any(Function(s) text.IndexOf(s, StringComparison.OrdinalIgnoreCase) >= 0)
    End Function

    Private Function ExtractTopLine(result As OcrResult) As String
        Return result.Pages _
            .FirstOrDefault() _
            ?.Lines _
            .FirstOrDefault(Function(l) l.Text.Trim().Length > 4) _
            ?.Text.Trim()
    End Function

    Private Function ParseAmount(text As String, pattern As String) As Decimal?
        Dim match = Regex.Match(text, pattern, RegexOptions.IgnoreCase)
        If match.Success AndAlso
            Decimal.TryParse(match.Groups(1).Value.Replace(",", ""), val) Then
            Return val
        End If
        Return Nothing
    End Function
End Class

Public Class FinancialSummary
    Public Property DocumentType As String
    Public Property InvoiceNumber As String
    Public Property Date As String
    Public Property TotalAmount As Decimal?
    Public Property SupplierName As String
    Public Property CustomerName As String
End Class

var result  = _ocr.Read("invoice.jpg");
var allWords = result.Pages.First().Words;

// Find the word "Total" and read the region 50px to its right
var totalLabel = allWords.FirstOrDefault(w =>
    w.Text.Equals("Total", StringComparison.OrdinalIgnoreCase));

if (totalLabel != null)
{
    var valueRegion = new CropRectangle(
        totalLabel.X + totalLabel.Width + 5,
        totalLabel.Y - 5,
        200,
        totalLabel.Height + 10);

    using var valueInput = new OcrInput();
    valueInput.LoadImage("invoice.jpg", valueRegion);
    var valueResult = _ocr.Read(valueInput);
    Console.WriteLine($"Total: {valueResult.Text.Trim()}");
}

Imports System
Imports System.Linq

Dim result = _ocr.Read("invoice.jpg")
Dim allWords = result.Pages.First().Words

' Find the word "Total" and read the region 50px to its right
Dim totalLabel = allWords.FirstOrDefault(Function(w) w.Text.Equals("Total", StringComparison.OrdinalIgnoreCase))

If totalLabel IsNot Nothing Then
    Dim valueRegion = New CropRectangle(totalLabel.X + totalLabel.Width + 5, totalLabel.Y - 5, 200, totalLabel.Height + 10)

    Using valueInput As New OcrInput()
        valueInput.LoadImage("invoice.jpg", valueRegion)
        Dim valueResult = _ocr.Read(valueInput)
        Console.WriteLine($"Total: {valueResult.Text.Trim()}")
    End Using
End If

// Existing async signature preserved for callers
public async Task<string> ExtractInvoiceNumberAsync(string filePath)
{
    return await Task.Run(() =>
    {
        var result = new IronTesseract().Read(filePath);
        return Regex.Match(result.Text,
            @"Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)",
            RegexOptions.IgnoreCase).Groups[1].Value;
    });
}

Imports System.Text.RegularExpressions
Imports System.Threading.Tasks

' Existing async signature preserved for callers
Public Async Function ExtractInvoiceNumberAsync(filePath As String) As Task(Of String)
    Return Await Task.Run(Function()
                              Dim result = New IronTesseract().Read(filePath)
                              Return Regex.Match(result.Text, 
                                                 "Invoice\s*#?\s*:?\s*([A-Z0-9\-]+)", 
                                                 RegexOptions.IgnoreCase).Groups(1).Value
                          End Function)
End Function

using var input = new OcrInput();
input.LoadImage("faded-invoice.jpg");
input.Deskew();
input.DeNoise();
input.Contrast();    // for faded or low-contrast thermal paper receipts
input.Binarize();    // convert to clean black-and-white before recognition
var result = new IronTesseract().Read(input);

Imports IronOcr

Using input As New OcrInput()
    input.LoadImage("faded-invoice.jpg")
    input.Deskew()
    input.DeNoise()
    input.Contrast() ' for faded or low-contrast thermal paper receipts
    input.Binarize() ' convert to clean black-and-white before recognition
    Dim result = New IronTesseract().Read(input)
End Using

// appsettings.json: remove "Mindee:ApiKey"
// Firewall: revoke egress rule for api.mindee.net
// Startup.cs or Program.cs:
IronOcr.License.LicenseKey = Configuration["IronOcr:LicenseKey"];
// Não rotation schedule, no secure storage beyond standard config secret management

' appsettings.json: remove "Mindee:ApiKey"
' Firewall: revoke egress rule for api.mindee.net
' Startup.vb or Program.vb:
IronOcr.License.LicenseKey = Configuration("IronOcr:LicenseKey")
' Não rotation schedule, no secure storage beyond standard config secret management

using var input = new OcrInput();
input.LoadPdf("vendor-statement.pdf");   // 12 pages — no billing unit increment
var result = new IronTesseract().Read(input);

foreach (var page in result.Pages)
    Console.WriteLine($"Page {page.PageNumber}: {page.Text.Length} characters recognized");

Imports IronOcr

Using input As New OcrInput()
    input.LoadPdf("vendor-statement.pdf") ' 12 pages — no billing unit increment
    Dim result = New IronTesseract().Read(input)

    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}: {page.Text.Length} characters recognized")
    Next
End Using

var result  = _ocr.Read(filePath);
var summary = result.Text.IndexOf("Invoice", StringComparison.OrdinalIgnoreCase) >= 0
    ? ExtractInvoiceFields(result)
    : ExtractReceiptFields(result);

Dim result = _ocr.Read(filePath)
Dim summary = If(result.Text.IndexOf("Invoice", StringComparison.OrdinalIgnoreCase) >= 0, ExtractInvoiceFields(result), ExtractReceiptFields(result))

grep -r "using Mindee" --include="*.cs" .
grep -r "MindeeClient\|ParseAsync\|InvoiceV4\|ReceiptV5\|PassportV1\|FinancialDocumentV1" --include="*.cs" .
grep -r "LocalInputSource\|MindeeException" --include="*.cs" .
grep -r "Mindee:ApiKey\|mindee_api_key\|MINDEE_API_KEY" --include="*.json" --include="*.env" --include="*.yml" .