From 26458a4017dc05ae61afd7bcc0214656329efe50 Mon Sep 17 00:00:00 2001
From: TekH <h.tek@digitaldata.works>
Date: Tue, 21 Jul 2026 09:26:18 +0200
Subject: [PATCH] feat: Implement
 DevExpressPdfProcessor.ExtractAttachmentsAsync with ZIP packaging

---
 .../PdfProcessing/DevExpressPdfProcessor.cs   | 62 +++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/DocumentOperator.Infrastructure/Services/PdfProcessing/DevExpressPdfProcessor.cs b/DocumentOperator.Infrastructure/Services/PdfProcessing/DevExpressPdfProcessor.cs
index 6a6d380..ed4118a 100644
--- a/DocumentOperator.Infrastructure/Services/PdfProcessing/DevExpressPdfProcessor.cs
+++ b/DocumentOperator.Infrastructure/Services/PdfProcessing/DevExpressPdfProcessor.cs
@@ -234,6 +234,68 @@ public class DevExpressPdfProcessor : IPdfProcessor
         );
     }
 
+    /// <summary>
+    /// Extracts all embedded files from a PDF document and returns them as a ZIP archive.
+    /// Uses DevExpress PdfDocument.FileAttachments to retrieve attachment data.
+    /// </summary>
+    /// <param name="pdfStream">PDF content as stream (caller is responsible for disposal)</param>
+    /// <returns>ZIP archive byte array containing all extracted attachments</returns>
+    /// <exception cref="BadRequestException">Thrown when stream is empty</exception>
+    /// <exception cref="NotFoundException">Thrown when PDF contains no attachments</exception>
+    public async Task<byte[]> ExtractAttachmentsAsync(Stream pdfStream)
+    {
+        // 1. Input Validation
+        ArgumentNullException.ThrowIfNull(pdfStream, nameof(pdfStream));
+        
+        if (pdfStream.Length == 0)
+        {
+            throw new BadRequestException("PDF stream cannot be empty");
+        }
+
+        // Defensive validation: Seekable streams must be at Position = 0
+        if (pdfStream.CanSeek && pdfStream.Position != 0)
+        {
+            throw new BadRequestException("PDF stream must be positioned at the beginning (Position = 0).");
+        }
+
+        // 2. Load PDF with DevExpress Document API
+        using var processor = new PdfDocumentProcessor();
+        processor.LoadDocument(pdfStream);
+
+        var document = processor.Document;
+
+        // 3. Extract attachment data using DevExpress FileAttachments collection
+        var fileAttachments = document.FileAttachments;
+
+        // 4. No attachments case
+        if (fileAttachments == null || !fileAttachments.Any())
+        {
+            throw new NotFoundException("PDF does not contain any attachments");
+        }
+
+        // 5. Create ZIP archive in memory
+        using var zipStream = new MemoryStream();
+        using (var zipArchive = new System.IO.Compression.ZipArchive(zipStream, System.IO.Compression.ZipArchiveMode.Create, leaveOpen: true))
+        {
+            foreach (var attachment in fileAttachments)
+            {
+                // Get attachment metadata
+                string fileName = attachment.FileName ?? "unnamed";
+                byte[] fileData = attachment.Data;
+
+                // Create entry in ZIP
+                var entry = zipArchive.CreateEntry(fileName, System.IO.Compression.CompressionLevel.Optimal);
+                
+                // Write attachment data to ZIP entry
+                using var entryStream = entry.Open();
+                await entryStream.WriteAsync(fileData, 0, fileData.Length);
+            }
+        }
+
+        // 6. Return ZIP byte array
+        return zipStream.ToArray();
+    }
+
     #endregion
 
     #region Private Helpers