using IronPdf;

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

using IronPdf;

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

using IronPdf;

// Create a PDF document with IronPDF
var renderer = new ChromePdfRenderer();

// Set 300 DPI for OCR accuracy -- higher DPI preserves text sharpness
renderer.RenderingOptions.PaperSize = IronPdf.Rendering.PdfPaperSize.A4;
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.MarginTop = 50;
renderer.RenderingOptions.MarginBottom = 50;

var pdf = renderer.RenderHtmlAsPdf(@"
    <h1>Document Report</h1>
    <p>Scene text integration for computer vision analysis.</p>
    <p>Text detection results for dataset and model analysis.</p>");

// Tag the document with searchable metadata
pdf.MetaData.Author = "OCR Processing Pipeline";
pdf.MetaData.Keywords = "OCR, Text Recognition, Computer Vision";
pdf.MetaData.ModifiedDate = DateTime.Now;

pdf.SaveAs("document-for-ocr.pdf");

// Export pages as PNG images for OCR.net -- 300 DPI is the recommended minimum
pdf.RasterizeToImageFiles("page-*.png", IronPdf.Imaging.ImageType.Png, 300);

using IronPdf;

// Create a PDF document with IronPDF
var renderer = new ChromePdfRenderer();

// Set 300 DPI for OCR accuracy -- higher DPI preserves text sharpness
renderer.RenderingOptions.PaperSize = IronPdf.Rendering.PdfPaperSize.A4;
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.MarginTop = 50;
renderer.RenderingOptions.MarginBottom = 50;

var pdf = renderer.RenderHtmlAsPdf(@"
    <h1>Document Report</h1>
    <p>Scene text integration for computer vision analysis.</p>
    <p>Text detection results for dataset and model analysis.</p>");

// Tag the document with searchable metadata
pdf.MetaData.Author = "OCR Processing Pipeline";
pdf.MetaData.Keywords = "OCR, Text Recognition, Computer Vision";
pdf.MetaData.ModifiedDate = DateTime.Now;

pdf.SaveAs("document-for-ocr.pdf");

// Export pages as PNG images for OCR.net -- 300 DPI is the recommended minimum
pdf.RasterizeToImageFiles("page-*.png", IronPdf.Imaging.ImageType.Png, 300);

using IronPdf;

// Kubernetes-compatible health check endpoint
var builder = WebApplication.CreateBuilder(args);
var app = builder.Build();

app.MapGet("/health/ready", async () =>
{
    try
    {
        var renderer = new ChromePdfRenderer();
        var testPdf = await renderer.RenderHtmlAsPdfAsync("<p>Health check</p>");
        return testPdf.PageCount > 0 ? Results.Ok() : Results.Problem();
    }
    catch
    {
        return Results.Problem("PDF rendering unavailable");
    }
});

await app.RunAsync();

using IronPdf;

// Kubernetes-compatible health check endpoint
var builder = WebApplication.CreateBuilder(args);
var app = builder.Build();

app.MapGet("/health/ready", async () =>
{
    try
    {
        var renderer = new ChromePdfRenderer();
        var testPdf = await renderer.RenderHtmlAsPdfAsync("<p>Health check</p>");
        return testPdf.PageCount > 0 ? Results.Ok() : Results.Problem();
    }
    catch
    {
        return Results.Problem("PDF rendering unavailable");
    }
});

await app.RunAsync();

using System;
using System.Net.Http;
using System.Threading.Tasks;

// Queue-based OCR processing with exponential backoff retry
async Task<string> ProcessOcrWithRetry(string imagePath, int maxRetries = 3)
{
    for (int attempt = 0; attempt < maxRetries; attempt++)
    {
        try
        {
            // Replace with your actual OCR.net API call
            return await CallOcrNetApi(imagePath);
        }
        catch (HttpRequestException ex) when (ex.Message.Contains("429"))
        {
            if (attempt == maxRetries - 1) throw;
            var delay = TimeSpan.FromSeconds(Math.Pow(2, attempt));
            await Task.Delay(delay);
        }
    }
    throw new InvalidOperationException("OCR processing failed after all retries");
}

using System;
using System.Net.Http;
using System.Threading.Tasks;

// Queue-based OCR processing with exponential backoff retry
async Task<string> ProcessOcrWithRetry(string imagePath, int maxRetries = 3)
{
    for (int attempt = 0; attempt < maxRetries; attempt++)
    {
        try
        {
            // Replace with your actual OCR.net API call
            return await CallOcrNetApi(imagePath);
        }
        catch (HttpRequestException ex) when (ex.Message.Contains("429"))
        {
            if (attempt == maxRetries - 1) throw;
            var delay = TimeSpan.FromSeconds(Math.Pow(2, attempt));
            await Task.Delay(delay);
        }
    }
    throw new InvalidOperationException("OCR processing failed after all retries");
}

using IronPdf;
using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

// --- Stage 1: Export PDF pages as images for OCR ---
var scannedPdf = PdfDocument.FromFile("input-document.pdf");
var imageFiles = scannedPdf.RasterizeToImageFiles(
    "scan-page-{0}.png",
    IronPdf.Imaging.ImageType.Png,
    300 // 300 DPI -- minimum for reliable OCR accuracy
);

// --- Stage 2: Process each image through OCR.net ---
var ocrResults = new List<string>();
foreach (var imageFile in imageFiles)
{
    // Replace this placeholder with your actual OCR.net API integration
    string ocrText = await SendImageToOcrNet(imageFile);
    ocrResults.Add(ocrText);
}

// --- Stage 3: Reassemble recognized text as a searchable PDF ---
var htmlBuilder = new StringBuilder();
htmlBuilder.Append(@"<!DOCTYPE html><html><head>
    <style>body{font-family:Arial,sans-serif;margin:40px;}
    .page{page-break-after:always;} pre{white-space:pre-wrap;}</style>
    </head><body>");

for (int i = 0; i < ocrResults.Count; i++)
{
    htmlBuilder.AppendFormat(
        "<div class='page'><h2>Page {0}</h2><pre>{1}</pre></div>",
        i + 1,
        System.Web.HttpUtility.HtmlEncode(ocrResults[i])
    );
}
htmlBuilder.Append("</body></html>");

var renderer = new ChromePdfRenderer();
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.EnableJavaScript = false;

var searchablePdf = await renderer.RenderHtmlAsPdfAsync(htmlBuilder.ToString());
searchablePdf.MetaData.Title = "OCR Processed Document";
searchablePdf.MetaData.Subject = "Searchable PDF from OCR";
searchablePdf.MetaData.CreationDate = DateTime.UtcNow;
searchablePdf.SecuritySettings.AllowUserPrinting = true;
searchablePdf.SecuritySettings.AllowUserCopyPasteContent = true;

searchablePdf.SaveAs("searchable-document.pdf");

using IronPdf;
using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;

// --- Stage 1: Export PDF pages as images for OCR ---
var scannedPdf = PdfDocument.FromFile("input-document.pdf");
var imageFiles = scannedPdf.RasterizeToImageFiles(
    "scan-page-{0}.png",
    IronPdf.Imaging.ImageType.Png,
    300 // 300 DPI -- minimum for reliable OCR accuracy
);

// --- Stage 2: Process each image through OCR.net ---
var ocrResults = new List<string>();
foreach (var imageFile in imageFiles)
{
    // Replace this placeholder with your actual OCR.net API integration
    string ocrText = await SendImageToOcrNet(imageFile);
    ocrResults.Add(ocrText);
}

// --- Stage 3: Reassemble recognized text as a searchable PDF ---
var htmlBuilder = new StringBuilder();
htmlBuilder.Append(@"<!DOCTYPE html><html><head>
    <style>body{font-family:Arial,sans-serif;margin:40px;}
    .page{page-break-after:always;} pre{white-space:pre-wrap;}</style>
    </head><body>");

for (int i = 0; i < ocrResults.Count; i++)
{
    htmlBuilder.AppendFormat(
        "<div class='page'><h2>Page {0}</h2><pre>{1}</pre></div>",
        i + 1,
        System.Web.HttpUtility.HtmlEncode(ocrResults[i])
    );
}
htmlBuilder.Append("</body></html>");

var renderer = new ChromePdfRenderer();
renderer.RenderingOptions.DPI = 300;
renderer.RenderingOptions.EnableJavaScript = false;

var searchablePdf = await renderer.RenderHtmlAsPdfAsync(htmlBuilder.ToString());
searchablePdf.MetaData.Title = "OCR Processed Document";
searchablePdf.MetaData.Subject = "Searchable PDF from OCR";
searchablePdf.MetaData.CreationDate = DateTime.UtcNow;
searchablePdf.SecuritySettings.AllowUserPrinting = true;
searchablePdf.SecuritySettings.AllowUserCopyPasteContent = true;

searchablePdf.SaveAs("searchable-document.pdf");

using Prometheus;
using System;
using System.Threading.Tasks;

// Prometheus metrics for OCR pipeline observability
var ocrRequestsTotal = Metrics
    .CreateCounter("ocr_requests_total", "Total OCR requests processed");

var ocrDuration = Metrics
    .CreateHistogram("ocr_duration_seconds", "OCR processing duration in seconds",
        new HistogramConfiguration
        {
            Buckets = Histogram.LinearBuckets(0.1, 0.1, 10)
        });

var activeOcrJobs = Metrics
    .CreateGauge("ocr_active_jobs", "Currently active OCR jobs");

// Wrapper that tracks every OCR operation automatically
async Task<t> TrackOcrOperation<t>(Func<Task<t>> operation)
{
    using (ocrDuration.NewTimer())
    {
        activeOcrJobs.Inc();
        try
        {
            var result = await operation();
            ocrRequestsTotal.Inc();
            return result;
        }
        finally
        {
            activeOcrJobs.Dec();
        }
    }
}

using Prometheus;
using System;
using System.Threading.Tasks;

// Prometheus metrics for OCR pipeline observability
var ocrRequestsTotal = Metrics
    .CreateCounter("ocr_requests_total", "Total OCR requests processed");

var ocrDuration = Metrics
    .CreateHistogram("ocr_duration_seconds", "OCR processing duration in seconds",
        new HistogramConfiguration
        {
            Buckets = Histogram.LinearBuckets(0.1, 0.1, 10)
        });

var activeOcrJobs = Metrics
    .CreateGauge("ocr_active_jobs", "Currently active OCR jobs");

// Wrapper that tracks every OCR operation automatically
async Task<t> TrackOcrOperation<t>(Func<Task<t>> operation)
{
    using (ocrDuration.NewTimer())
    {
        activeOcrJobs.Inc();
        try
        {
            var result = await operation();
            ocrRequestsTotal.Inc();
            return result;
        }
        finally
        {
            activeOcrJobs.Dec();
        }
    }
}