Jak zaimplementować OCR w języku C# przy użyciu bibliotek open source

// Klippa: 15+ lines of HTTP plumbing before you read a single character
var content = new MultipartFormDataContent();
content.Add(new ByteArrayContent(File.ReadAllBytes(imagePath)), "document", "receipt.jpg");
_client.DefaultRequestHeaders.Add("X-Auth-Key", _apiKey); // auth header — rotates, breaks, leaks

var response = await _client.PostAsync(
    "https://custom-ocr.klippa.com/api/v1/parseDocument", content);
response.EnsureSuccessStatusCode(); // throws on 4xx/5xx — no retry, document lost

var json = await response.Content.ReadAsStringAsync();
var parsed = JsonSerializer.Deserialize<KlippaResponse>(json); // your schema, your maintenance
var text = parsed?.Data?.ParsedDocument?.Text; // nullable chain — breaks when schema changes

Imports System.Net.Http
Imports System.IO
Imports System.Text.Json
Imports System.Threading.Tasks

' Klippa: 15+ lines of HTTP plumbing before you read a single character
Dim content As New MultipartFormDataContent()
content.Add(New ByteArrayContent(File.ReadAllBytes(imagePath)), "document", "receipt.jpg")
_client.DefaultRequestHeaders.Add("X-Auth-Key", _apiKey) ' auth header — rotates, breaks, leaks

Dim response As HttpResponseMessage = Await _client.PostAsync("https://custom-ocr.klippa.com/api/v1/parseDocument", content)
response.EnsureSuccessStatusCode() ' throws on 4xx/5xx — no retry, document lost

Dim json As String = Await response.Content.ReadAsStringAsync()
Dim parsed As KlippaResponse = JsonSerializer.Deserialize(Of KlippaResponse)(json) ' your schema, your maintenance
Dim text As String = parsed?.Data?.ParsedDocument?.Text ' nullable chain — breaks when schema changes

// IronOCR: no HTTP, no auth headers, no JSON — just text
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
var text = new IronTesseract().Read(imagePath).Text;

' IronOCR: no HTTP, no auth headers, no JSON — just text
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
Dim text = New IronTesseract().Read(imagePath).Text

# Remove Klippa-related packages (if installed for REST support)
dotnet remove package Newtonsoft.Json
dotnet remove package System.Net.Http.Json

// Before (Klippa integration)
using System.Net.Http;
using System.Net.Http.Headers;
using System.Text.Json;
using System.Text.Json.Serialization;

// After (IronOCR)
using IronOcr;

Imports System.Net.Http
Imports System.Net.Http.Headers
Imports System.Text.Json
Imports System.Text.Json.Serialization

Imports IronOcr

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

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

// Klippa: entire service class just to send one HTTP request
public class KlippaOcrService : IDisposable
{
    private readonly HttpClient _httpClient;
    private readonly string _baseUrl = "https://custom-ocr.klippa.com/api/v1";

    public KlippaOcrService(string apiKey)
    {
        _httpClient = new HttpClient();
        _httpClient.DefaultRequestHeaders.Add("X-Auth-Key", apiKey);
        _httpClient.Timeout = TimeSpan.FromSeconds(30); // network timeout required
    }

    public async Task<string> ReadDocumentTextAsync(string filePath)
    {
        using var form = new MultipartFormDataContent();
        var fileBytes = await File.ReadAllBytesAsync(filePath);
        form.Add(new ByteArrayContent(fileBytes), "document", Path.GetFileName(filePath));

        var response = await _httpClient.PostAsync($"{_baseUrl}/parseDocument", form);
        response.EnsureSuccessStatusCode();

        var json = await response.Content.ReadAsStringAsync();
        using var doc = JsonDocument.Parse(json);
        // navigate Klippa's nested JSON schema
        return doc.RootElement
            .GetProperty("data")
            .GetProperty("parsed_document")
            .GetProperty("text")
            .GetString() ?? string.Empty;
    }

    public void Dispose() => _httpClient.Dispose();
}

Imports System
Imports System.IO
Imports System.Net.Http
Imports System.Threading.Tasks
Imports System.Text.Json

' Klippa: entire service class just to send one HTTP request
Public Class KlippaOcrService
    Implements IDisposable

    Private ReadOnly _httpClient As HttpClient
    Private ReadOnly _baseUrl As String = "https://custom-ocr.klippa.com/api/v1"

    Public Sub New(apiKey As String)
        _httpClient = New HttpClient()
        _httpClient.DefaultRequestHeaders.Add("X-Auth-Key", apiKey)
        _httpClient.Timeout = TimeSpan.FromSeconds(30) ' network timeout required
    End Sub

    Public Async Function ReadDocumentTextAsync(filePath As String) As Task(Of String)
        Using form As New MultipartFormDataContent()
            Dim fileBytes = Await File.ReadAllBytesAsync(filePath)
            form.Add(New ByteArrayContent(fileBytes), "document", Path.GetFileName(filePath))

            Dim response = Await _httpClient.PostAsync($"{_baseUrl}/parseDocument", form)
            response.EnsureSuccessStatusCode()

            Dim json = Await response.Content.ReadAsStringAsync()
            Using doc = JsonDocument.Parse(json)
                ' navigate Klippa's nested JSON schema
                Return doc.RootElement _
                    .GetProperty("data") _
                    .GetProperty("parsed_document") _
                    .GetProperty("text") _
                    .GetString() OrElse String.Empty
            End Using
        End Using
    End Function

    Public Sub Dispose() Implements IDisposable.Dispose
        _httpClient.Dispose()
    End Sub
End Class

// IronOCR: no HTTP, no JSON navigation, no Dispose plumbing
public class OcrService
{
    private readonly IronTesseract _ocr = new IronTesseract();

    public string ReadDocumentText(string filePath)
    {
        return _ocr.Read(filePath).Text;
    }
}

// At startup:
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Usage — identical call site, different internals:
var service = new OcrService();
var text = service.ReadDocumentText("invoice.jpg"); // local, synchronous, zero network

Imports IronOcr

Public Class OcrService
    Private ReadOnly _ocr As New IronTesseract()

    Public Function ReadDocumentText(filePath As String) As String
        Return _ocr.Read(filePath).Text
    End Function
End Class

' At startup:
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' Usage — identical call site, different internals:
Dim service As New OcrService()
Dim text As String = service.ReadDocumentText("invoice.jpg") ' local, synchronous, zero network

// Klippa: multipart upload — every document is an HTTP form POST
public async Task<KlippaResult> UploadAndParseAsync(
    string filePath, string documentType = "financial")
{
    using var form = new MultipartFormDataContent();

    // read file into memory — entire document in RAM before upload
    var fileBytes = await File.ReadAllBytesAsync(filePath);
    var byteContent = new ByteArrayContent(fileBytes);
    byteContent.Headers.ContentType =
        new System.Net.Http.Headers.MediaTypeHeaderValue("image/jpeg");

    form.Add(byteContent, "document", Path.GetFileName(filePath));
    form.Add(new StringContent(documentType), "DocumentType");

    // document leaves your server here
    var response = await _httpClient.PostAsync(
        "https://custom-ocr.klippa.com/api/v1/parseDocument", form);

    if (!response.IsSuccessStatusCode)
    {
        var error = await response.Content.ReadAsStringAsync();
        throw new InvalidOperationException($"Klippa API error: {response.StatusCode} — {error}");
    }

    var json = await response.Content.ReadAsStringAsync();
    return JsonSerializer.Deserialize<KlippaResult>(json,
        new JsonSerializerOptions { PropertyNameCaseInsensitive = true });
}

Imports System.IO
Imports System.Net.Http
Imports System.Text.Json
Imports System.Threading.Tasks

Public Class KlippaUploader
    Private ReadOnly _httpClient As HttpClient

    Public Sub New(httpClient As HttpClient)
        _httpClient = httpClient
    End Sub

    Public Async Function UploadAndParseAsync(filePath As String, Optional documentType As String = "financial") As Task(Of KlippaResult)
        Using form As New MultipartFormDataContent()
            ' read file into memory — entire document in RAM before upload
            Dim fileBytes = Await File.ReadAllBytesAsync(filePath)
            Dim byteContent = New ByteArrayContent(fileBytes)
            byteContent.Headers.ContentType = New System.Net.Http.Headers.MediaTypeHeaderValue("image/jpeg")

            form.Add(byteContent, "document", Path.GetFileName(filePath))
            form.Add(New StringContent(documentType), "DocumentType")

            ' document leaves your server here
            Dim response = Await _httpClient.PostAsync("https://custom-ocr.klippa.com/api/v1/parseDocument", form)

            If Not response.IsSuccessStatusCode Then
                Dim error = Await response.Content.ReadAsStringAsync()
                Throw New InvalidOperationException($"Klippa API error: {response.StatusCode} — {error}")
            End If

            Dim json = Await response.Content.ReadAsStringAsync()
            Return JsonSerializer.Deserialize(Of KlippaResult)(json, New JsonSerializerOptions With {.PropertyNameCaseInsensitive = True})
        End Using
    End Function
End Class

// IronOCR: load from file path, byte array, or stream — no upload, no form
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// From file path
using var input = new OcrInput();
input.LoadImage("invoice.jpg");
var result = new IronTesseract().Read(input);

// From byte array (same bytes Klippa was uploading)
byte[] fileBytes = await File.ReadAllBytesAsync("invoice.jpg");
using var inputFromBytes = new OcrInput();
inputFromBytes.LoadImage(fileBytes);
var resultFromBytes = new IronTesseract().Read(inputFromBytes);

Console.WriteLine(result.Text);

Imports IronOcr
Imports System.IO

' IronOCR: load from file path, byte array, or stream — no upload, no form
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

' From file path
Using input As New OcrInput()
    input.LoadImage("invoice.jpg")
    Dim result = New IronTesseract().Read(input)

    ' From byte array (same bytes Klippa was uploading)
    Dim fileBytes As Byte() = Await File.ReadAllBytesAsync("invoice.jpg")
    Using inputFromBytes As New OcrInput()
        inputFromBytes.LoadImage(fileBytes)
        Dim resultFromBytes = New IronTesseract().Read(inputFromBytes)

        Console.WriteLine(result.Text)
    End Using
End Using

// Klippa: deserialization model — breaks when API schema changes
public class KlippaResponse
{
    [JsonPropertyName("data")]
    public KlippaData Data { get; set; }
}

public class KlippaData
{
    [JsonPropertyName("parsed_document")]
    public KlippaParsedDocument ParsedDocument { get; set; }
}

public class KlippaParsedDocument
{
    [JsonPropertyName("text")]
    public string Text { get; set; }

    [JsonPropertyName("amount")]
    public decimal? Amount { get; set; }

    [JsonPropertyName("merchant")]
    public string Merchant { get; set; }

    [JsonPropertyName("date")]
    public string Date { get; set; }
}

// Usage: navigate the nullable chain every time
public async Task<string> GetExtractedTextAsync(string imagePath)
{
    var klippaResult = await UploadAndParseAsync(imagePath);
    // every property access is nullable — schema drift breaks this silently
    return klippaResult?.Data?.ParsedDocument?.Text ?? string.Empty;
}

Imports System.Text.Json.Serialization

' Klippa: deserialization model — breaks when API schema changes
Public Class KlippaResponse
    <JsonPropertyName("data")>
    Public Property Data As KlippaData
End Class

Public Class KlippaData
    <JsonPropertyName("parsed_document")>
    Public Property ParsedDocument As KlippaParsedDocument
End Class

Public Class KlippaParsedDocument
    <JsonPropertyName("text")>
    Public Property Text As String

    <JsonPropertyName("amount")>
    Public Property Amount As Decimal?

    <JsonPropertyName("merchant")>
    Public Property Merchant As String

    <JsonPropertyName("date")>
    Public Property Date As String
End Class

' Usage: navigate the nullable chain every time
Public Async Function GetExtractedTextAsync(imagePath As String) As Task(Of String)
    Dim klippaResult = Await UploadAndParseAsync(imagePath)
    ' every property access is nullable — schema drift breaks this silently
    Return If(klippaResult?.Data?.ParsedDocument?.Text, String.Empty)
End Function

// IronOCR: typed result object — no JSON schema, no nullable chains
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

var ocr = new IronTesseract();
var result = ocr.Read("invoice.jpg");

// Direct property access — no deserialization, no nullable navigation
string fullText   = result.Text;
double confidence = result.Confidence;
int pageCount     = result.Pages.Count();

// Structured data: lines and words with coordinates
foreach (var page in result.Pages)
{
    foreach (var line in page.Lines)
    {
        Console.WriteLine($"Line: '{line.Text}' at Y={line.Y}");
    }
}

Imports IronOcr

' IronOCR: typed result object — no JSON schema, no nullable chains
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Dim ocr As New IronTesseract()
Dim result = ocr.Read("invoice.jpg")

' Direct property access — no deserialization, no nullable navigation
Dim fullText As String = result.Text
Dim confidence As Double = result.Confidence
Dim pageCount As Integer = result.Pages.Count()

' Structured data: lines and words with coordinates
For Each page In result.Pages
    For Each line In page.Lines
        Console.WriteLine($"Line: '{line.Text}' at Y={line.Y}")
    Next
Next

// Klippa: retry policy required — cloud calls fail unpredictably
public async Task<string> ReadWithRetryAsync(string filePath, int maxRetries = 3)
{
    var delay = TimeSpan.FromSeconds(1);

    for (int attempt = 1; attempt <= maxRetries; attempt++)
    {
        try
        {
            using var form = new MultipartFormDataContent();
            form.Add(
                new ByteArrayContent(await File.ReadAllBytesAsync(filePath)),
                "document",
                Path.GetFileName(filePath));

            using var cts = new CancellationTokenSource(TimeSpan.FromSeconds(30));
            var response = await _httpClient.PostAsync(
                "https://custom-ocr.klippa.com/api/v1/parseDocument", form, cts.Token);

            if (response.StatusCode == System.Net.HttpStatusCode.TooManyRequests)
            {
                // rate limited — back off and retry
                await Task.Delay(delay * attempt);
                continue;
            }

            response.EnsureSuccessStatusCode();
            var json = await response.Content.ReadAsStringAsync(cts.Token);
            var parsed = JsonSerializer.Deserialize<KlippaResponse>(json);
            return parsed?.Data?.ParsedDocument?.Text ?? string.Empty;
        }
        catch (HttpRequestException) when (attempt < maxRetries)
        {
            await Task.Delay(delay * attempt); // exponential backoff
        }
        catch (TaskCanceledException) when (attempt < maxRetries)
        {
            await Task.Delay(delay * attempt); // timeout — retry
        }
    }

    throw new InvalidOperationException($"Klippa API failed after {maxRetries} attempts");
}

Imports System
Imports System.IO
Imports System.Net.Http
Imports System.Text.Json
Imports System.Threading
Imports System.Threading.Tasks

Public Class KlippaService
    Private ReadOnly _httpClient As HttpClient

    Public Sub New(httpClient As HttpClient)
        _httpClient = httpClient
    End Sub

    ' Klippa: retry policy required — cloud calls fail unpredictably
    Public Async Function ReadWithRetryAsync(filePath As String, Optional maxRetries As Integer = 3) As Task(Of String)
        Dim delay As TimeSpan = TimeSpan.FromSeconds(1)

        For attempt As Integer = 1 To maxRetries
            Try
                Using form As New MultipartFormDataContent()
                    form.Add(New ByteArrayContent(Await File.ReadAllBytesAsync(filePath)), "document", Path.GetFileName(filePath))

                    Using cts As New CancellationTokenSource(TimeSpan.FromSeconds(30))
                        Dim response As HttpResponseMessage = Await _httpClient.PostAsync("https://custom-ocr.klippa.com/api/v1/parseDocument", form, cts.Token)

                        If response.StatusCode = System.Net.HttpStatusCode.TooManyRequests Then
                            ' rate limited — back off and retry
                            Await Task.Delay(delay * attempt)
                            Continue For
                        End If

                        response.EnsureSuccessStatusCode()
                        Dim json As String = Await response.Content.ReadAsStringAsync(cts.Token)
                        Dim parsed As KlippaResponse = JsonSerializer.Deserialize(Of KlippaResponse)(json)
                        Return If(parsed?.Data?.ParsedDocument?.Text, String.Empty)
                    End Using
                End Using
            Catch ex As HttpRequestException When attempt < maxRetries
                Await Task.Delay(delay * attempt) ' exponential backoff
            Catch ex As TaskCanceledException When attempt < maxRetries
                Await Task.Delay(delay * attempt) ' timeout — retry
            End Try
        Next

        Throw New InvalidOperationException($"Klippa API failed after {maxRetries} attempts")
    End Function
End Class

Public Class KlippaResponse
    Public Property Data As KlippaData
End Class

Public Class KlippaData
    Public Property ParsedDocument As ParsedDocument
End Class

Public Class ParsedDocument
    Public Property Text As String
End Class

// IronOCR: no network, no retry policy needed — local call either works or throws once
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

public string ReadDocument(string filePath)
{
    // Nie retry loop. Nie CancellationTokenSource. Nie HTTP status checks.
    // Nie rate limit handling. Nie partial-JSON guards.
    var result = new IronTesseract().Read(filePath);
    return result.Text;
}

' IronOCR: no network, no retry policy needed — local call either works or throws once
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Public Function ReadDocument(filePath As String) As String
    ' Nie retry loop. Nie CancellationTokenSource. Nie HTTP status checks.
    ' Nie rate limit handling. Nie partial-JSON guards.
    Dim result = New IronTesseract().Read(filePath)
    Return result.Text
End Function

// Klippa: PDF upload — entire document transmitted, results depend on cloud availability
public async Task<List<string>> ExtractPdfPagesAsync(string pdfPath)
{
    var pages = new List<string>();

    // Klippa parses the entire PDF server-side and returns combined results
    // You cannot control per-page processing or access raw page text
    using var form = new MultipartFormDataContent();
    form.Add(
        new ByteArrayContent(await File.ReadAllBytesAsync(pdfPath)),
        "document",
        Path.GetFileName(pdfPath));

    var response = await _httpClient.PostAsync(
        "https://custom-ocr.klippa.com/api/v1/parseDocument", form);
    response.EnsureSuccessStatusCode();

    var json = await response.Content.ReadAsStringAsync();
    var result = JsonSerializer.Deserialize<KlippaResponse>(json);
    // Klippa returns the combined parsed text — no per-page breakdown in basic API
    pages.Add(result?.Data?.ParsedDocument?.Text ?? string.Empty);

    return pages;
}

Imports System.IO
Imports System.Net.Http
Imports System.Text.Json
Imports System.Threading.Tasks

Public Class PdfExtractor
    Private ReadOnly _httpClient As HttpClient

    Public Sub New(httpClient As HttpClient)
        _httpClient = httpClient
    End Sub

    ' Klippa: PDF upload — entire document transmitted, results depend on cloud availability
    Public Async Function ExtractPdfPagesAsync(pdfPath As String) As Task(Of List(Of String))
        Dim pages As New List(Of String)()

        ' Klippa parses the entire PDF server-side and returns combined results
        ' You cannot control per-page processing or access raw page text
        Using form As New MultipartFormDataContent()
            form.Add(New ByteArrayContent(Await File.ReadAllBytesAsync(pdfPath)), "document", Path.GetFileName(pdfPath))

            Dim response = Await _httpClient.PostAsync("https://custom-ocr.klippa.com/api/v1/parseDocument", form)
            response.EnsureSuccessStatusCode()

            Dim json = Await response.Content.ReadAsStringAsync()
            Dim result = JsonSerializer.Deserialize(Of KlippaResponse)(json)
            ' Klippa returns the combined parsed text — no per-page breakdown in basic API
            pages.Add(If(result?.Data?.ParsedDocument?.Text, String.Empty))
        End Using

        Return pages
    End Function
End Class

Public Class KlippaResponse
    Public Property Data As KlippaData
End Class

Public Class KlippaData
    Public Property ParsedDocument As ParsedDocument
End Class

Public Class ParsedDocument
    Public Property Text As String
End Class

// IronOCR: native PDF OCR with per-page structured access — no upload
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

using var input = new OcrInput();
input.LoadPdf("multi-page-invoice.pdf"); // reads locally — no HTTP

var ocr = new IronTesseract();
var result = ocr.Read(input);

// Per-page access — not available from Klippa's combined response
foreach (var page in result.Pages)
{
    Console.WriteLine($"Page {page.PageNumber}: {page.Lines.Count()} lines");
    Console.WriteLine(page.Text);
}

// Or produce a searchable PDF from the scanned original
result.SaveAsSearchablePdf("searchable-output.pdf");

Imports IronOcr

' IronOCR: native PDF OCR with per-page structured access — no upload
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"

Using input As New OcrInput()
    input.LoadPdf("multi-page-invoice.pdf") ' reads locally — no HTTP

    Dim ocr As New IronTesseract()
    Dim result = ocr.Read(input)

    ' Per-page access — not available from Klippa's combined response
    For Each page In result.Pages
        Console.WriteLine($"Page {page.PageNumber}: {page.Lines.Count()} lines")
        Console.WriteLine(page.Text)
    Next

    ' Or produce a searchable PDF from the scanned original
    result.SaveAsSearchablePdf("searchable-output.pdf")
End Using

// Keep async method signatures — switch the implementation
public async Task<string> ProcessDocumentAsync(
    string filePath, CancellationToken cancellationToken = default)
{
    // Previously: await _httpClient.PostAsync(...)
    // Now: local call, same awaitable pattern
    var ocr = new IronTesseract();
    var result = await ocr.ReadAsync(filePath);
    return result.Text;
}

Imports System.Threading
Imports System.Threading.Tasks

Public Class DocumentProcessor
    Public Async Function ProcessDocumentAsync(filePath As String, Optional cancellationToken As CancellationToken = Nothing) As Task(Of String)
        Dim ocr As New IronTesseract()
        Dim result = Await ocr.ReadAsync(filePath)
        Return result.Text
    End Function
End Class

// In Program.cs or Startup.cs
builder.Services.AddSingleton<IronTesseract>();

// Or wrap for interface compatibility
builder.Services.AddSingleton<IOcrService, IronOcrService>();

public class IronOcrService : IOcrService
{
    private readonly IronTesseract _ocr;
    public IronOcrService(IronTesseract ocr) => _ocr = ocr;

    public string ReadDocument(string path) => _ocr.Read(path).Text;
}

Imports Microsoft.Extensions.DependencyInjection

' In Program.vb or Startup.vb
builder.Services.AddSingleton(Of IronTesseract)()

' Or wrap for interface compatibility
builder.Services.AddSingleton(Of IOcrService, IronOcrService)()

Public Class IronOcrService
    Implements IOcrService

    Private ReadOnly _ocr As IronTesseract

    Public Sub New(ocr As IronTesseract)
        _ocr = ocr
    End Sub

    Public Function ReadDocument(path As String) As String Implements IOcrService.ReadDocument
        Return _ocr.Read(path).Text
    End Function
End Class

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

// Target specific layout regions instead of relying on pre-parsed cloud fields
var totalRegion   = new CropRectangle(350, 580, 250, 50); // bottom-right total area
var merchantRegion = new CropRectangle(50, 30, 400, 60);  // top header area

using var merchantInput = new OcrInput();
merchantInput.LoadImage("receipt.jpg", merchantRegion);
var merchantName = new IronTesseract().Read(merchantInput).Text.Trim();

using var totalInput = new OcrInput();
totalInput.LoadImage("receipt.jpg", totalRegion);
var totalText = new IronTesseract().Read(totalInput).Text.Trim();

Imports IronOcr

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

' Target specific layout regions instead of relying on pre-parsed cloud fields
Dim totalRegion As New CropRectangle(350, 580, 250, 50) ' bottom-right total area
Dim merchantRegion As New CropRectangle(50, 30, 400, 60) ' top header area

Using merchantInput As New OcrInput()
    merchantInput.LoadImage("receipt.jpg", merchantRegion)
    Dim merchantName As String = New IronTesseract().Read(merchantInput).Text.Trim()
End Using

Using totalInput As New OcrInput()
    totalInput.LoadImage("receipt.jpg", totalRegion)
    Dim totalText As String = New IronTesseract().Read(totalInput).Text.Trim()
End Using

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

// Stream from S3, Azure Blob, or any upstream source
public async Task<string> ProcessDocumentStreamAsync(Stream documentStream)
{
    using var input = new OcrInput();
    input.LoadImage(documentStream); // accepts Stream directly

    var ocr = new IronTesseract();
    var result = ocr.Read(input);
    return result.Text;
}

Imports System.IO
Imports System.Threading.Tasks
Imports IronOcr

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

Public Async Function ProcessDocumentStreamAsync(documentStream As Stream) As Task(Of String)
    Using input As New OcrInput()
        input.LoadImage(documentStream) ' accepts Stream directly

        Dim ocr As New IronTesseract()
        Dim result = ocr.Read(input)
        Return result.Text
    End Using
End Function

[Fact]
public void ReadDocument_ReturnsExpectedText()
{
    IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";
    var ocr = new IronTesseract();

    // Use a real test fixture — no HTTP mocking, runs fully offline
    var result = ocr.Read("test-fixtures/sample-invoice.jpg");

    Assert.Contains("Invoice", result.Text, StringComparison.OrdinalIgnoreCase);
    Assert.True(result.Confidence > 70);
}

<Fact>
Public Sub ReadDocument_ReturnsExpectedText()
    IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"
    Dim ocr = New IronTesseract()

    ' Use a real test fixture — no HTTP mocking, runs fully offline
    Dim result = ocr.Read("test-fixtures/sample-invoice.jpg")

    Assert.Contains("Invoice", result.Text, StringComparison.OrdinalIgnoreCase)
    Assert.True(result.Confidence > 70)
End Sub

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

using var input = new OcrInput();
input.LoadImage("low-quality-scan.jpg");
input.Deskew();    // fix rotation from camera or scanner
input.DeNoise();   // remove compression noise
input.Contrast();  // boost faded ink
input.Binarize();  // clean background for clearer character edges

var result = new IronTesseract().Read(input);
Console.WriteLine($"Confidence: {result.Confidence}%");

Imports IronOcr

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

Using input As New OcrInput()
    input.LoadImage("low-quality-scan.jpg")
    input.Deskew()    ' fix rotation from camera or scanner
    input.DeNoise()   ' remove compression noise
    input.Contrast()  ' boost faded ink
    input.Binarize()  ' clean background for clearer character edges

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

# Find all files containing Klippa HTTP integration code
grep -r "X-Auth-Key" --include="*.cs" .
grep -r "klippa.com" --include="*.cs" .
grep -r "KlippaService\|KlippaResponse\|KlippaResult\|KlippaData" --include="*.cs" .

# Find all files with MultipartFormDataContent (likely Klippa upload code)
grep -r "MultipartFormDataContent" --include="*.cs" .

# Find all JSON deserialization models that map to Klippa response fields
grep -r "parsed_document\|vat_amount\|merchant\|X-Auth-Key" --include="*.cs" .

# Find all async methods that wrap Klippa calls
grep -r "ParseDocumentAsync\|ProcessReceiptAsync\|UploadAndParseAsync" --include="*.cs" .

# Find test files with HTTP mocks for Klippa
grep -r "MockHttp\|WireMock\|klippa" --include="*.cs" .