// Textract: five environment variables, an IAM role, and an S3 bucket
// — all required before the first OCR call

// Environment must have:
//   AWS_ACCESS_KEY_ID=AKIA...
//   AWS_SECRET_ACCESS_KEY=...
//   AWS_DEFAULT_REGION=us-east-1
//   IAM role: textract:DetectDocumentText, textract:AnalyzeDocument
//   IAM role: s3:PutObject, s3:DeleteObject (for any PDF processing)
//   S3 bucket: my-textract-staging-bucket (with lifecycle policy to prevent cost accumulation)

public class TextractOcrService
{
    private readonly AmazonTextractClient _textractClient;
    private readonly AmazonS3Client _s3Client; // required for PDFs

    public TextractOcrService()
    {
        // Fails with AmazonClientException if credentials not found in chain
        _textractClient = new AmazonTextractClient(Amazon.RegionEndpoint.USEast1);
        _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.USEast1);
    }
}

// Textract: five environment variables, an IAM role, and an S3 bucket
// — all required before the first OCR call

// Environment must have:
//   AWS_ACCESS_KEY_ID=AKIA...
//   AWS_SECRET_ACCESS_KEY=...
//   AWS_DEFAULT_REGION=us-east-1
//   IAM role: textract:DetectDocumentText, textract:AnalyzeDocument
//   IAM role: s3:PutObject, s3:DeleteObject (for any PDF processing)
//   S3 bucket: my-textract-staging-bucket (with lifecycle policy to prevent cost accumulation)

public class TextractOcrService
{
    private readonly AmazonTextractClient _textractClient;
    private readonly AmazonS3Client _s3Client; // required for PDFs

    public TextractOcrService()
    {
        // Fails with AmazonClientException if credentials not found in chain
        _textractClient = new AmazonTextractClient(Amazon.RegionEndpoint.USEast1);
        _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.USEast1);
    }
}

// IronOCR: one line, one string, done
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Or from environment (no IAM, no rotation, no S3)
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

// IronOCR: one line, one string, done
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Or from environment (no IAM, no rotation, no S3)
IronOcr.License.LicenseKey = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");

dotnet remove package AWSSDK.Textract
dotnet remove package AWSSDK.S3
dotnet remove package AWSSDK.Core

dotnet remove package AWSSDK.Textract
dotnet remove package AWSSDK.S3
dotnet remove package AWSSDK.Core

// Before (AWS Textract)
using Amazon.Textract;
using Amazon.Textract.Model;
using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Runtime;

// After (IronOCR)
using IronOcr;

// Before (AWS Textract)
using Amazon.Textract;
using Amazon.Textract.Model;
using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Runtime;

// After (IronOCR)
using IronOcr;

// Remove from startup:
//   AWS_ACCESS_KEY_ID environment variable
//   AWS_SECRET_ACCESS_KEY environment variable
//   AWS_DEFAULT_REGION environment variable
//   ~/.aws/credentials file entries
//   IAM role bindings on the execution context

// Add instead:
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Remove from startup:
//   AWS_ACCESS_KEY_ID environment variable
//   AWS_SECRET_ACCESS_KEY environment variable
//   AWS_DEFAULT_REGION environment variable
//   ~/.aws/credentials file entries
//   IAM role bindings on the execution context

// Add instead:
IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY";

// Requires: NuGet AWSSDK.Textract, AWSSDK.S3
// Requires: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION in environment
// Requires: IAM policy with textract:* and s3:PutObject, s3:DeleteObject

using Amazon.S3;
using Amazon.Textract;

public class DocumentOcrService
{
    private readonly AmazonTextractClient _textractClient;
    private readonly AmazonS3Client _s3Client;
    private readonly string _stagingBucket;

    public DocumentOcrService(IConfiguration config)
    {
        // Credential chain: environment → ~/.aws/credentials → EC2 instance profile
        // Fails if none found — runtime exception, not compile-time
        _textractClient = new AmazonTextractClient(Amazon.RegionEndpoint.USEast1);
        _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.USEast1);
        _stagingBucket = config["Textract:StagingBucket"]; // bucket must exist and have permissions
    }

    public async Task<string> ReadImageAsync(string imagePath)
    {
        var bytes = File.ReadAllBytes(imagePath);
        var response = await _textractClient.DetectDocumentTextAsync(
            new DetectDocumentTextRequest
            {
                Document = new Document { Bytes = new MemoryStream(bytes) }
            });

        return string.Join("\n", response.Blocks
            .Where(b => b.BlockType == BlockType.LINE)
            .Select(b => b.Text));
    }
}

// Requires: NuGet AWSSDK.Textract, AWSSDK.S3
// Requires: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION in environment
// Requires: IAM policy with textract:* and s3:PutObject, s3:DeleteObject

using Amazon.S3;
using Amazon.Textract;

public class DocumentOcrService
{
    private readonly AmazonTextractClient _textractClient;
    private readonly AmazonS3Client _s3Client;
    private readonly string _stagingBucket;

    public DocumentOcrService(IConfiguration config)
    {
        // Credential chain: environment → ~/.aws/credentials → EC2 instance profile
        // Fails if none found — runtime exception, not compile-time
        _textractClient = new AmazonTextractClient(Amazon.RegionEndpoint.USEast1);
        _s3Client = new AmazonS3Client(Amazon.RegionEndpoint.USEast1);
        _stagingBucket = config["Textract:StagingBucket"]; // bucket must exist and have permissions
    }

    public async Task<string> ReadImageAsync(string imagePath)
    {
        var bytes = File.ReadAllBytes(imagePath);
        var response = await _textractClient.DetectDocumentTextAsync(
            new DetectDocumentTextRequest
            {
                Document = new Document { Bytes = new MemoryStream(bytes) }
            });

        return string.Join("\n", response.Blocks
            .Where(b => b.BlockType == BlockType.LINE)
            .Select(b => b.Text));
    }
}

// Requires: NuGet IronOcr
// Requires: one license key string — nothing else

using IronOcr;

public class DocumentOcrService
{
    private readonly IronTesseract _ocr;

    public DocumentOcrService()
    {
        IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"; // or set at Program.cs startup
        _ocr = new IronTesseract();
    }

    public string ReadImage(string imagePath)
    {
        // No credential chain, no region, no bucket — just read
        return _ocr.Read(imagePath).Text;
    }
}

// Requires: NuGet IronOcr
// Requires: one license key string — nothing else

using IronOcr;

public class DocumentOcrService
{
    private readonly IronTesseract _ocr;

    public DocumentOcrService()
    {
        IronOcr.License.LicenseKey = "YOUR-LICENSE-KEY"; // or set at Program.cs startup
        _ocr = new IronTesseract();
    }

    public string ReadImage(string imagePath)
    {
        // No credential chain, no region, no bucket — just read
        return _ocr.Read(imagePath).Text;
    }
}

// Textract cannot accept TIFF directly — requires PDF conversion + S3 + async job
// This shows the conversion overhead plus the minimum async pipeline

using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<string> ProcessScannedTiffAsync(string tiffPath, string s3Bucket)
{
    // Step 0: Convert TIFF to PDF first (Textract does not accept TIFF for async jobs)
    // Requires a separate PDF conversion library — not shown here
    var pdfPath = Path.ChangeExtension(tiffPath, ".pdf");
    ConvertTiffToPdf(tiffPath, pdfPath); // external dependency required

    // Step 1: Upload converted PDF to S3
    var s3Key = $"staging/{Guid.NewGuid()}.pdf";
    using (var stream = File.OpenRead(pdfPath))
    {
        await _s3Client.PutObjectAsync(new PutObjectRequest
        {
            BucketName = s3Bucket,
            Key = s3Key,
            InputStream = stream
        });
    }

    try
    {
        // Step 2: Start async detection job
        var startResp = await _textractClient.StartDocumentTextDetectionAsync(
            new StartDocumentTextDetectionRequest
            {
                DocumentLocation = new DocumentLocation
                {
                    S3Object = new S3Object { Bucket = s3Bucket, Name = s3Key }
                }
            });

        // Step 3: Poll every 5 seconds — can block for 30–120 seconds on large files
        GetDocumentTextDetectionResponse pollResp;
        do
        {
            await Task.Delay(5000);
            pollResp = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest { JobId = startResp.JobId });
        } while (pollResp.JobStatus == JobStatus.IN_PROGRESS);

        if (pollResp.JobStatus != JobStatus.SUCCEEDED)
            throw new Exception($"Job failed: {pollResp.StatusMessage}");

        // Step 4: Collect paginated results
        var text = new StringBuilder();
        string token = null;
        do
        {
            var page = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest
                {
                    JobId = startResp.JobId,
                    NextToken = token
                });
            foreach (var block in page.Blocks.Where(b => b.BlockType == BlockType.LINE))
                text.AppendLine(block.Text);
            token = page.NextToken;
        } while (token != null);

        return text.ToString();
    }
    finally
    {
        // Step 5: Clean up S3 — orphaned objects accumulate storage costs
        await _s3Client.DeleteObjectAsync(s3Bucket, s3Key);
        File.Delete(pdfPath); // clean up intermediate PDF
    }
}

// Textract cannot accept TIFF directly — requires PDF conversion + S3 + async job
// This shows the conversion overhead plus the minimum async pipeline

using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<string> ProcessScannedTiffAsync(string tiffPath, string s3Bucket)
{
    // Step 0: Convert TIFF to PDF first (Textract does not accept TIFF for async jobs)
    // Requires a separate PDF conversion library — not shown here
    var pdfPath = Path.ChangeExtension(tiffPath, ".pdf");
    ConvertTiffToPdf(tiffPath, pdfPath); // external dependency required

    // Step 1: Upload converted PDF to S3
    var s3Key = $"staging/{Guid.NewGuid()}.pdf";
    using (var stream = File.OpenRead(pdfPath))
    {
        await _s3Client.PutObjectAsync(new PutObjectRequest
        {
            BucketName = s3Bucket,
            Key = s3Key,
            InputStream = stream
        });
    }

    try
    {
        // Step 2: Start async detection job
        var startResp = await _textractClient.StartDocumentTextDetectionAsync(
            new StartDocumentTextDetectionRequest
            {
                DocumentLocation = new DocumentLocation
                {
                    S3Object = new S3Object { Bucket = s3Bucket, Name = s3Key }
                }
            });

        // Step 3: Poll every 5 seconds — can block for 30–120 seconds on large files
        GetDocumentTextDetectionResponse pollResp;
        do
        {
            await Task.Delay(5000);
            pollResp = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest { JobId = startResp.JobId });
        } while (pollResp.JobStatus == JobStatus.IN_PROGRESS);

        if (pollResp.JobStatus != JobStatus.SUCCEEDED)
            throw new Exception($"Job failed: {pollResp.StatusMessage}");

        // Step 4: Collect paginated results
        var text = new StringBuilder();
        string token = null;
        do
        {
            var page = await _textractClient.GetDocumentTextDetectionAsync(
                new GetDocumentTextDetectionRequest
                {
                    JobId = startResp.JobId,
                    NextToken = token
                });
            foreach (var block in page.Blocks.Where(b => b.BlockType == BlockType.LINE))
                text.AppendLine(block.Text);
            token = page.NextToken;
        } while (token != null);

        return text.ToString();
    }
    finally
    {
        // Step 5: Clean up S3 — orphaned objects accumulate storage costs
        await _s3Client.DeleteObjectAsync(s3Bucket, s3Key);
        File.Delete(pdfPath); // clean up intermediate PDF
    }
}

//IronOCR reads multi-frame TIFF directly — no conversion, no S3, no polling

using IronOcr;

public string ProcessScannedTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath); // reads all frames natively

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

    // Access per-page results if needed
    foreach (var page in result.Pages)
        Console.WriteLine($"Page {page.PageNumber}: {page.Words.Length} words detected");

    return result.Text;
}

//IronOCR reads multi-frame TIFF directly — no conversion, no S3, no polling

using IronOcr;

public string ProcessScannedTiff(string tiffPath)
{
    using var input = new OcrInput();
    input.LoadImageFrames(tiffPath); // reads all frames natively

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

    // Access per-page results if needed
    foreach (var page in result.Pages)
        Console.WriteLine($"Page {page.PageNumber}: {page.Words.Length} words detected");

    return result.Text;
}

// Textract extracts text but cannot produce searchable PDFs
// Requires: S3 upload + async job + separate PDF library to embed the text layer

using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<string> ExtractTextForSearchableLayerAsync(
    string scannedPdfPath,
    string s3Bucket)
{
    // Must upload to S3 — cannot pass PDF bytes directly for async jobs
    var key = $"ocr-input/{Guid.NewGuid()}.pdf";

    await using (var fs = File.OpenRead(scannedPdfPath))
    {
        await _s3Client.PutObjectAsync(new PutObjectRequest
        {
            BucketName = s3Bucket,
            Key = key,
            InputStream = fs,
            ContentType = "application/pdf"
        });
    }

    string jobId;
    try
    {
        var startResp = await _textractClient.StartDocumentTextDetectionAsync(
            new StartDocumentTextDetectionRequest
            {
                DocumentLocation = new DocumentLocation
                {
                    S3Object = new S3Object { Bucket = s3Bucket, Name = key }
                }
            });
        jobId = startResp.JobId;
    }
    catch
    {
        await _s3Client.DeleteObjectAsync(s3Bucket, key);
        throw;
    }

    // Poll — minimum 5s wait; typical 15–60s for a 10-page PDF
    GetDocumentTextDetectionResponse pollResp;
    int pollAttempts = 0;
    const int maxAttempts = 120; // 10 minute timeout

    do
    {
        await Task.Delay(5000);
        pollResp = await _textractClient.GetDocumentTextDetectionAsync(
            new GetDocumentTextDetectionRequest { JobId = jobId });

        if (++pollAttempts >= maxAttempts)
            throw new TimeoutException("Textract job timed out after 10 minutes");

    } while (pollResp.JobStatus == JobStatus.IN_PROGRESS);

    await _s3Client.DeleteObjectAsync(s3Bucket, key); // cleanup regardless of outcome

    if (pollResp.JobStatus != JobStatus.SUCCEEDED)
        throw new Exception($"Textract job status: {pollResp.JobStatus} — {pollResp.StatusMessage}");

    // Return extracted text — caller must use a separate library to produce searchable PDF
    return string.Join("\n", pollResp.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .Select(b => b.Text));

    // Caller still needs: iTextSharp, PdfSharp, or similar to embed text layer
}

// Textract extracts text but cannot produce searchable PDFs
// Requires: S3 upload + async job + separate PDF library to embed the text layer

using Amazon.S3;
using Amazon.S3.Model;
using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<string> ExtractTextForSearchableLayerAsync(
    string scannedPdfPath,
    string s3Bucket)
{
    // Must upload to S3 — cannot pass PDF bytes directly for async jobs
    var key = $"ocr-input/{Guid.NewGuid()}.pdf";

    await using (var fs = File.OpenRead(scannedPdfPath))
    {
        await _s3Client.PutObjectAsync(new PutObjectRequest
        {
            BucketName = s3Bucket,
            Key = key,
            InputStream = fs,
            ContentType = "application/pdf"
        });
    }

    string jobId;
    try
    {
        var startResp = await _textractClient.StartDocumentTextDetectionAsync(
            new StartDocumentTextDetectionRequest
            {
                DocumentLocation = new DocumentLocation
                {
                    S3Object = new S3Object { Bucket = s3Bucket, Name = key }
                }
            });
        jobId = startResp.JobId;
    }
    catch
    {
        await _s3Client.DeleteObjectAsync(s3Bucket, key);
        throw;
    }

    // Poll — minimum 5s wait; typical 15–60s for a 10-page PDF
    GetDocumentTextDetectionResponse pollResp;
    int pollAttempts = 0;
    const int maxAttempts = 120; // 10 minute timeout

    do
    {
        await Task.Delay(5000);
        pollResp = await _textractClient.GetDocumentTextDetectionAsync(
            new GetDocumentTextDetectionRequest { JobId = jobId });

        if (++pollAttempts >= maxAttempts)
            throw new TimeoutException("Textract job timed out after 10 minutes");

    } while (pollResp.JobStatus == JobStatus.IN_PROGRESS);

    await _s3Client.DeleteObjectAsync(s3Bucket, key); // cleanup regardless of outcome

    if (pollResp.JobStatus != JobStatus.SUCCEEDED)
        throw new Exception($"Textract job status: {pollResp.JobStatus} — {pollResp.StatusMessage}");

    // Return extracted text — caller must use a separate library to produce searchable PDF
    return string.Join("\n", pollResp.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .Select(b => b.Text));

    // Caller still needs: iTextSharp, PdfSharp, or similar to embed text layer
}

//IronOCR reads the PDF and produces a searchable PDF output directly
// No S3, no polling, no external PDF library needed

using IronOcr;

public void ConvertToSearchablePdf(string scannedPdfPath, string outputPath)
{
    var ocr = new IronTesseract();

    using var input = new OcrInput();
    input.LoadPdf(scannedPdfPath);

    var result = ocr.Read(input);

    // Embed extracted text as searchable layer in one call
    result.SaveAsSearchablePdf(outputPath);

    Console.WriteLine($"Pages processed: {result.Pages.Length}");
    Console.WriteLine($"Overall confidence: {result.Confidence:F1}%");
}

//IronOCR reads the PDF and produces a searchable PDF output directly
// No S3, no polling, no external PDF library needed

using IronOcr;

public void ConvertToSearchablePdf(string scannedPdfPath, string outputPath)
{
    var ocr = new IronTesseract();

    using var input = new OcrInput();
    input.LoadPdf(scannedPdfPath);

    var result = ocr.Read(input);

    // Embed extracted text as searchable layer in one call
    result.SaveAsSearchablePdf(outputPath);

    Console.WriteLine($"Pages processed: {result.Pages.Length}");
    Console.WriteLine($"Overall confidence: {result.Confidence:F1}%");
}

// AnalyzeDocument with TABLES returns blocks that must be graph-traversed
// to determine which words belong to which paragraphs

using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<List<DocumentSection>> ExtractDocumentStructureAsync(string imagePath)
{
    var bytes = File.ReadAllBytes(imagePath);

    var response = await _textractClient.AnalyzeDocumentAsync(
        new AnalyzeDocumentRequest
        {
            Document = new Document { Bytes = new MemoryStream(bytes) },
            FeatureTypes = new List<string> { "TABLES", "FORMS" }
            // Note: AnalyzeDocument (TABLES) costs $0.015/page — 10x DetectDocumentText
        });

    var sections = new List<DocumentSection>();

    // Filter LINE blocks for paragraph reconstruction
    // LINE blocks are not grouped into paragraphs — must infer from Y proximity
    var lineBlocks = response.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .OrderBy(b => b.Geometry?.BoundingBox?.Top ?? 0)
        .ToList();

    // Group lines into pseudo-paragraphs by vertical gap heuristic
    var currentParagraph = new List<Block>();
    float? lastBottom = null;
    const float paragraphGapThreshold = 0.02f; // 2% of page height

    foreach (var line in lineBlocks)
    {
        var top = line.Geometry?.BoundingBox?.Top ?? 0;
        var height = line.Geometry?.BoundingBox?.Height ?? 0;

        if (lastBottom.HasValue && (top - lastBottom.Value) > paragraphGapThreshold)
        {
            if (currentParagraph.Any())
            {
                sections.Add(new DocumentSection
                {
                    Text = string.Join(" ", currentParagraph.Select(b => b.Text)),
                    LineCount = currentParagraph.Count,
                    // Confidence: average of all LINE block confidence values
                    Confidence = (float)currentParagraph.Average(b => b.Confidence ?? 0)
                });
                currentParagraph.Clear();
            }
        }

        currentParagraph.Add(line);
        lastBottom = top + height;
    }

    if (currentParagraph.Any())
        sections.Add(new DocumentSection
        {
            Text = string.Join(" ", currentParagraph.Select(b => b.Text)),
            LineCount = currentParagraph.Count,
            Confidence = (float)currentParagraph.Average(b => b.Confidence ?? 0)
        });

    return sections;
}

public class DocumentSection
{
    public string Text { get; set; }
    public int LineCount { get; set; }
    public float Confidence { get; set; }
}

// AnalyzeDocument with TABLES returns blocks that must be graph-traversed
// to determine which words belong to which paragraphs

using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<List<DocumentSection>> ExtractDocumentStructureAsync(string imagePath)
{
    var bytes = File.ReadAllBytes(imagePath);

    var response = await _textractClient.AnalyzeDocumentAsync(
        new AnalyzeDocumentRequest
        {
            Document = new Document { Bytes = new MemoryStream(bytes) },
            FeatureTypes = new List<string> { "TABLES", "FORMS" }
            // Note: AnalyzeDocument (TABLES) costs $0.015/page — 10x DetectDocumentText
        });

    var sections = new List<DocumentSection>();

    // Filter LINE blocks for paragraph reconstruction
    // LINE blocks are not grouped into paragraphs — must infer from Y proximity
    var lineBlocks = response.Blocks
        .Where(b => b.BlockType == BlockType.LINE)
        .OrderBy(b => b.Geometry?.BoundingBox?.Top ?? 0)
        .ToList();

    // Group lines into pseudo-paragraphs by vertical gap heuristic
    var currentParagraph = new List<Block>();
    float? lastBottom = null;
    const float paragraphGapThreshold = 0.02f; // 2% of page height

    foreach (var line in lineBlocks)
    {
        var top = line.Geometry?.BoundingBox?.Top ?? 0;
        var height = line.Geometry?.BoundingBox?.Height ?? 0;

        if (lastBottom.HasValue && (top - lastBottom.Value) > paragraphGapThreshold)
        {
            if (currentParagraph.Any())
            {
                sections.Add(new DocumentSection
                {
                    Text = string.Join(" ", currentParagraph.Select(b => b.Text)),
                    LineCount = currentParagraph.Count,
                    // Confidence: average of all LINE block confidence values
                    Confidence = (float)currentParagraph.Average(b => b.Confidence ?? 0)
                });
                currentParagraph.Clear();
            }
        }

        currentParagraph.Add(line);
        lastBottom = top + height;
    }

    if (currentParagraph.Any())
        sections.Add(new DocumentSection
        {
            Text = string.Join(" ", currentParagraph.Select(b => b.Text)),
            LineCount = currentParagraph.Count,
            Confidence = (float)currentParagraph.Average(b => b.Confidence ?? 0)
        });

    return sections;
}

public class DocumentSection
{
    public string Text { get; set; }
    public int LineCount { get; set; }
    public float Confidence { get; set; }
}

//IronOCR returns a typed hierarchy — paragraphs are first-class objects
// No block graph, no heuristic gap detection, no confidence averaging

using IronOcr;

public List<DocumentSection> ExtractDocumentStructure(string imagePath)
{
    var ocr = new IronTesseract();
    var result = ocr.Read(imagePath);

    var sections = new List<DocumentSection>();

    foreach (var page in result.Pages)
    {
        foreach (var paragraph in page.Paragraphs)
        {
            sections.Add(new DocumentSection
            {
                Text = paragraph.Text,
                LineCount = paragraph.Lines.Length,
                // Coordinate access: exact pixel position on the page
                LocationX = paragraph.X,
                LocationY = paragraph.Y,
                Width = paragraph.Width,
                Height = paragraph.Height,
                Confidence = paragraph.Confidence
            });
        }
    }

    return sections;
}

public class DocumentSection
{
    public string Text { get; set; }
    public int LineCount { get; set; }
    public int LocationX { get; set; }
    public int LocationY { get; set; }
    public int Width { get; set; }
    public int Height { get; set; }
    public double Confidence { get; set; }
}

//IronOCR returns a typed hierarchy — paragraphs are first-class objects
// No block graph, no heuristic gap detection, no confidence averaging

using IronOcr;

public List<DocumentSection> ExtractDocumentStructure(string imagePath)
{
    var ocr = new IronTesseract();
    var result = ocr.Read(imagePath);

    var sections = new List<DocumentSection>();

    foreach (var page in result.Pages)
    {
        foreach (var paragraph in page.Paragraphs)
        {
            sections.Add(new DocumentSection
            {
                Text = paragraph.Text,
                LineCount = paragraph.Lines.Length,
                // Coordinate access: exact pixel position on the page
                LocationX = paragraph.X,
                LocationY = paragraph.Y,
                Width = paragraph.Width,
                Height = paragraph.Height,
                Confidence = paragraph.Confidence
            });
        }
    }

    return sections;
}

public class DocumentSection
{
    public string Text { get; set; }
    public int LineCount { get; set; }
    public int LocationX { get; set; }
    public int LocationY { get; set; }
    public int Width { get; set; }
    public int Height { get; set; }
    public double Confidence { get; set; }
}

// Batch processing requires SemaphoreSlim throttle + retry on rate limit exceeded

using Amazon.Textract;
using Amazon.Textract.Model;
using System.Collections.Concurrent;

public async Task<Dictionary<string, string>> ProcessImageBatchAsync(
    IReadOnlyList<string> imagePaths,
    IProgress<(int Completed, int Total)> progress = null)
{
    var results = new ConcurrentDictionary<string, string>();
    var semaphore = new SemaphoreSlim(5); // 5 concurrent — Textract default TPS limit
    var tasks = new List<Task>();
    int completed = 0;

    foreach (var path in imagePaths)
    {
        await semaphore.WaitAsync();

        tasks.Add(Task.Run(async () =>
        {
            try
            {
                string text = null;
                int retryCount = 0;

                while (text == null && retryCount < 3)
                {
                    try
                    {
                        var bytes = await File.ReadAllBytesAsync(path);
                        var response = await _textractClient.DetectDocumentTextAsync(
                            new DetectDocumentTextRequest
                            {
                                Document = new Document { Bytes = new MemoryStream(bytes) }
                            });

                        text = string.Join("\n", response.Blocks
                            .Where(b => b.BlockType == BlockType.LINE)
                            .Select(b => b.Text));
                    }
                    catch (AmazonTextractException ex)
                        when (ex.ErrorCode == "ProvisionedThroughputExceededException")
                    {
                        // Exponential backoff on rate limit — blocks the entire thread
                        await Task.Delay(TimeSpan.FromSeconds(Math.Pow(2, retryCount)));
                        retryCount++;
                    }
                }

                results[path] = text ?? string.Empty;
                var done = Interlocked.Increment(ref completed);
                progress?.Report((done, imagePaths.Count));
            }
            finally
            {
                semaphore.Release();
            }
        }));
    }

    await Task.WhenAll(tasks);
    return results.ToDictionary(x => x.Key, x => x.Value);
}

// Batch processing requires SemaphoreSlim throttle + retry on rate limit exceeded

using Amazon.Textract;
using Amazon.Textract.Model;
using System.Collections.Concurrent;

public async Task<Dictionary<string, string>> ProcessImageBatchAsync(
    IReadOnlyList<string> imagePaths,
    IProgress<(int Completed, int Total)> progress = null)
{
    var results = new ConcurrentDictionary<string, string>();
    var semaphore = new SemaphoreSlim(5); // 5 concurrent — Textract default TPS limit
    var tasks = new List<Task>();
    int completed = 0;

    foreach (var path in imagePaths)
    {
        await semaphore.WaitAsync();

        tasks.Add(Task.Run(async () =>
        {
            try
            {
                string text = null;
                int retryCount = 0;

                while (text == null && retryCount < 3)
                {
                    try
                    {
                        var bytes = await File.ReadAllBytesAsync(path);
                        var response = await _textractClient.DetectDocumentTextAsync(
                            new DetectDocumentTextRequest
                            {
                                Document = new Document { Bytes = new MemoryStream(bytes) }
                            });

                        text = string.Join("\n", response.Blocks
                            .Where(b => b.BlockType == BlockType.LINE)
                            .Select(b => b.Text));
                    }
                    catch (AmazonTextractException ex)
                        when (ex.ErrorCode == "ProvisionedThroughputExceededException")
                    {
                        // Exponential backoff on rate limit — blocks the entire thread
                        await Task.Delay(TimeSpan.FromSeconds(Math.Pow(2, retryCount)));
                        retryCount++;
                    }
                }

                results[path] = text ?? string.Empty;
                var done = Interlocked.Increment(ref completed);
                progress?.Report((done, imagePaths.Count));
            }
            finally
            {
                semaphore.Release();
            }
        }));
    }

    await Task.WhenAll(tasks);
    return results.ToDictionary(x => x.Key, x => x.Value);
}

// No rate limits, no semaphore, no retry logic — Parallel.ForEach saturates all cores

using IronOcr;
using System.Collections.Concurrent;

public Dictionary<string, string> ProcessImageBatch(
    IReadOnlyList<string> imagePaths,
    IProgress<(int Completed, int Total)> progress = null)
{
    var ocr = new IronTesseract();
    var results = new ConcurrentDictionary<string, string>();
    int completed = 0;

    Parallel.ForEach(imagePaths, path =>
    {
        var result = ocr.Read(path);
        results[path] = result.Text;

        var done = Interlocked.Increment(ref completed);
        progress?.Report((done, imagePaths.Count));
    });

    return results.ToDictionary(x => x.Key, x => x.Value);
}

// No rate limits, no semaphore, no retry logic — Parallel.ForEach saturates all cores

using IronOcr;
using System.Collections.Concurrent;

public Dictionary<string, string> ProcessImageBatch(
    IReadOnlyList<string> imagePaths,
    IProgress<(int Completed, int Total)> progress = null)
{
    var ocr = new IronTesseract();
    var results = new ConcurrentDictionary<string, string>();
    int completed = 0;

    Parallel.ForEach(imagePaths, path =>
    {
        var result = ocr.Read(path);
        results[path] = result.Text;

        var done = Interlocked.Increment(ref completed);
        progress?.Report((done, imagePaths.Count));
    });

    return results.ToDictionary(x => x.Key, x => x.Value);
}

// FORMS mode costs $0.05/page — the most expensive Textract tier
// Relationship graph traversal required to reconstruct key-value pairs

using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<Dictionary<string, string>> ExtractInvoiceFieldsAsync(string imagePath)
{
    var bytes = File.ReadAllBytes(imagePath);

    // $0.05/page for FORMS analysis
    var response = await _textractClient.AnalyzeDocumentAsync(
        new AnalyzeDocumentRequest
        {
            Document = new Document { Bytes = new MemoryStream(bytes) },
            FeatureTypes = new List<string> { "FORMS" }
        });

    var allBlocks = response.Blocks;
    var fields = new Dictionary<string, string>();

    // Find KEY blocks only
    var keyBlocks = allBlocks.Where(b =>
        b.BlockType == BlockType.KEY_VALUE_SET &&
        b.EntityTypes?.Contains("KEY") == true);

    foreach (var keyBlock in keyBlocks)
    {
        // Assemble key text from CHILD WORD blocks
        var keyText = GetTextFromBlock(allBlocks, keyBlock);

        // Find associated VALUE block via VALUE relationship
        var valueBlockId = keyBlock.Relationships?
            .FirstOrDefault(r => r.Type == RelationshipType.VALUE)?
            .Ids.FirstOrDefault();

        if (valueBlockId == null) continue;

        var valueBlock = allBlocks.FirstOrDefault(b => b.Id == valueBlockId);
        if (valueBlock == null) continue;

        var valueText = GetTextFromBlock(allBlocks, valueBlock);
        fields[keyText.TrimEnd(':')] = valueText;
    }

    return fields;
}

private string GetTextFromBlock(IList<Block> allBlocks, Block block)
{
    if (block.Relationships == null) return string.Empty;

    var childWordIds = block.Relationships
        .Where(r => r.Type == RelationshipType.CHILD)
        .SelectMany(r => r.Ids);

    return string.Join(" ", allBlocks
        .Where(b => b.BlockType == BlockType.WORD && childWordIds.Contains(b.Id))
        .Select(b => b.Text));
}

// FORMS mode costs $0.05/page — the most expensive Textract tier
// Relationship graph traversal required to reconstruct key-value pairs

using Amazon.Textract;
using Amazon.Textract.Model;

public async Task<Dictionary<string, string>> ExtractInvoiceFieldsAsync(string imagePath)
{
    var bytes = File.ReadAllBytes(imagePath);

    // $0.05/page for FORMS analysis
    var response = await _textractClient.AnalyzeDocumentAsync(
        new AnalyzeDocumentRequest
        {
            Document = new Document { Bytes = new MemoryStream(bytes) },
            FeatureTypes = new List<string> { "FORMS" }
        });

    var allBlocks = response.Blocks;
    var fields = new Dictionary<string, string>();

    // Find KEY blocks only
    var keyBlocks = allBlocks.Where(b =>
        b.BlockType == BlockType.KEY_VALUE_SET &&
        b.EntityTypes?.Contains("KEY") == true);

    foreach (var keyBlock in keyBlocks)
    {
        // Assemble key text from CHILD WORD blocks
        var keyText = GetTextFromBlock(allBlocks, keyBlock);

        // Find associated VALUE block via VALUE relationship
        var valueBlockId = keyBlock.Relationships?
            .FirstOrDefault(r => r.Type == RelationshipType.VALUE)?
            .Ids.FirstOrDefault();

        if (valueBlockId == null) continue;

        var valueBlock = allBlocks.FirstOrDefault(b => b.Id == valueBlockId);
        if (valueBlock == null) continue;

        var valueText = GetTextFromBlock(allBlocks, valueBlock);
        fields[keyText.TrimEnd(':')] = valueText;
    }

    return fields;
}

private string GetTextFromBlock(IList<Block> allBlocks, Block block)
{
    if (block.Relationships == null) return string.Empty;

    var childWordIds = block.Relationships
        .Where(r => r.Type == RelationshipType.CHILD)
        .SelectMany(r => r.Ids);

    return string.Join(" ", allBlocks
        .Where(b => b.BlockType == BlockType.WORD && childWordIds.Contains(b.Id))
        .Select(b => b.Text));
}

// CropRectangle extracts each field zone directly — no relationship graph
// Works for any fixed-format form where field positions are known

using IronOcr;

// Define the field zones for your form template once
private static readonly Dictionary<string, CropRectangle> InvoiceFieldZones =
    new Dictionary<string, CropRectangle>
    {
        { "InvoiceNumber", new CropRectangle(450, 80,  300, 35) },
        { "InvoiceDate",   new CropRectangle(450, 120, 300, 35) },
        { "VendorName",    new CropRectangle(50,  160, 400, 35) },
        { "TotalAmount",   new CropRectangle(450, 680, 200, 35) },
        { "DueDate",       new CropRectangle(450, 720, 200, 35) }
    };

public Dictionary<string, string> ExtractInvoiceFields(string imagePath)
{
    var ocr = new IronTesseract();
    var fields = new Dictionary<string, string>();

    foreach (var zone in InvoiceFieldZones)
    {
        using var input = new OcrInput();
        input.LoadImage(imagePath, zone.Value); // load only the defined region

        var result = ocr.Read(input);
        fields[zone.Key] = result.Text.Trim();
    }

    return fields;
}

// CropRectangle extracts each field zone directly — no relationship graph
// Works for any fixed-format form where field positions are known

using IronOcr;

// Define the field zones for your form template once
private static readonly Dictionary<string, CropRectangle> InvoiceFieldZones =
    new Dictionary<string, CropRectangle>
    {
        { "InvoiceNumber", new CropRectangle(450, 80,  300, 35) },
        { "InvoiceDate",   new CropRectangle(450, 120, 300, 35) },
        { "VendorName",    new CropRectangle(50,  160, 400, 35) },
        { "TotalAmount",   new CropRectangle(450, 680, 200, 35) },
        { "DueDate",       new CropRectangle(450, 720, 200, 35) }
    };

public Dictionary<string, string> ExtractInvoiceFields(string imagePath)
{
    var ocr = new IronTesseract();
    var fields = new Dictionary<string, string>();

    foreach (var zone in InvoiceFieldZones)
    {
        using var input = new OcrInput();
        input.LoadImage(imagePath, zone.Value); // load only the defined region

        var result = ocr.Read(input);
        fields[zone.Key] = result.Text.Trim();
    }

    return fields;
}

// Single environment variable — no IAM, no rotation, no chain resolution
var key = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");
if (string.IsNullOrEmpty(key))
    throw new InvalidOperationException("IRONOCR_LICENSE environment variable is not set");

IronOcr.License.LicenseKey = key;

// Single environment variable — no IAM, no rotation, no chain resolution
var key = Environment.GetEnvironmentVariable("IRONOCR_LICENSE");
if (string.IsNullOrEmpty(key))
    throw new InvalidOperationException("IRONOCR_LICENSE environment variable is not set");

IronOcr.License.LicenseKey = key;

// If the call site must remain async (e.g., an ASP.NET controller action):
public async Task<IActionResult> ProcessUpload(IFormFile file)
{
    using var ms = new MemoryStream();
    await file.CopyToAsync(ms);

    // Offload synchronous OCR to thread pool — keeps controller non-blocking
    var text = await Task.Run(() =>
    {
        var ocr = new IronTesseract();
        using var input = new OcrInput();
        input.LoadImage(ms.ToArray());
        return ocr.Read(input).Text;
    });

    return Ok(text);
}

// If the call site must remain async (e.g., an ASP.NET controller action):
public async Task<IActionResult> ProcessUpload(IFormFile file)
{
    using var ms = new MemoryStream();
    await file.CopyToAsync(ms);

    // Offload synchronous OCR to thread pool — keeps controller non-blocking
    var text = await Task.Run(() =>
    {
        var ocr = new IronTesseract();
        using var input = new OcrInput();
        input.LoadImage(ms.ToArray());
        return ocr.Read(input).Text;
    });

    return Ok(text);
}

// Before: upload → job → poll → extract → cleanup (50+ lines)
// After: two lines, no cleanup required

using var input = new OcrInput();
input.LoadPdf(localPdfPath);
var text = new IronTesseract().Read(input).Text;

// Before: upload → job → poll → extract → cleanup (50+ lines)
// After: two lines, no cleanup required

using var input = new OcrInput();
input.LoadPdf(localPdfPath);
var text = new IronTesseract().Read(input).Text;

// Before: filter by BlockType + traverse relationship IDs
var paragraphText = string.Join(" ", allBlocks
    .Where(b => b.BlockType == BlockType.WORD &&
                childIds.Contains(b.Id))
    .Select(b => b.Text));

// After: direct paragraph text (no filtering, no relationship lookup)
foreach (var page in result.Pages)
    foreach (var para in page.Paragraphs)
        Console.WriteLine(para.Text); // already assembled

// Before: filter by BlockType + traverse relationship IDs
var paragraphText = string.Join(" ", allBlocks
    .Where(b => b.BlockType == BlockType.WORD &&
                childIds.Contains(b.Id))
    .Select(b => b.Text));

// After: direct paragraph text (no filtering, no relationship lookup)
foreach (var page in result.Pages)
    foreach (var para in page.Paragraphs)
        Console.WriteLine(para.Text); // already assembled

// Delete: SemaphoreSlim, retry loops, ProvisionedThroughputExceededException handlers
// Replace with:
Parallel.ForEach(imagePaths, path =>
{
    var result = new IronTesseract().Read(path);
    results[path] = result.Text;
});

// Delete: SemaphoreSlim, retry loops, ProvisionedThroughputExceededException handlers
// Replace with:
Parallel.ForEach(imagePaths, path =>
{
    var result = new IronTesseract().Read(path);
    results[path] = result.Text;
});

grep -rn "Amazon.Textract\|AmazonTextractClient\|DetectDocumentText" --include="*.cs" .
grep -rn "StartDocumentTextDetection\|GetDocumentTextDetection\|JobStatus" --include="*.cs" .
grep -rn "AmazonS3Client\|PutObjectRequest\|DeleteObjectAsync" --include="*.cs" .
grep -rn "BlockType\|RelationshipType\|KEY_VALUE_SET" --include="*.cs" .
grep -rn "ProvisionedThroughputExceededException\|AmazonTextractException" --include="*.cs" .
grep -rn "AWSSDK\|Amazon.RegionEndpoint" --include="*.csproj" .

grep -rn "Amazon.Textract\|AmazonTextractClient\|DetectDocumentText" --include="*.cs" .
grep -rn "StartDocumentTextDetection\|GetDocumentTextDetection\|JobStatus" --include="*.cs" .
grep -rn "AmazonS3Client\|PutObjectRequest\|DeleteObjectAsync" --include="*.cs" .
grep -rn "BlockType\|RelationshipType\|KEY_VALUE_SET" --include="*.cs" .
grep -rn "ProvisionedThroughputExceededException\|AmazonTextractException" --include="*.cs" .
grep -rn "AWSSDK\|Amazon.RegionEndpoint" --include="*.csproj" .