refactor(infrastructure): implement Stream-based PDF processing

DevExpressPdfProcessor:
- ValidateAsync, ValidatePdfAAsync, CheckAttachmentsAsync: Stream parameters
- Defensive Position=0 validation (BadRequestException for seekable streams not at beginning)
- Remove unsafe Position reset (non-seekable stream compatibility)
- Remove PdfProcessingException wrapping (let DevExpress exceptions propagate naturally)

DevExpressSwissQrCodeProcessor:
- ExtractSwissQrCodeAsync: Stream parameter
- Defensive Position=0 validation
- Remove unsafe Position reset

Memory optimization: MemoryStream.TryGetBuffer fast path for byte[] extraction
This commit is contained in:
2026-07-20 16:31:47 +02:00
parent 5dc2e38507
commit 1af158840e
2 changed files with 46 additions and 11 deletions

View File

@@ -28,6 +28,12 @@ public class DevExpressPdfProcessor : IPdfProcessor
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. Read stream to byte array for raw data analysis
// (DevExpress needs byte[] for some operations like attachment detection)
byte[] pdfBytes;
@@ -39,14 +45,18 @@ public class DevExpressPdfProcessor : IPdfProcessor
else
{
// Slow path: copy stream to byte array
pdfStream.Position = 0;
using var memoryStream = new MemoryStream();
await pdfStream.CopyToAsync(memoryStream);
pdfBytes = memoryStream.ToArray();
}
// 3. Load PDF with DevExpress Document API
pdfStream.Position = 0;
// Reset position for DevExpress (seekable streams only)
if (pdfStream.CanSeek)
{
pdfStream.Position = 0;
}
using var processor = new PdfDocumentProcessor();
processor.LoadDocument(pdfStream);
@@ -87,6 +97,12 @@ public class DevExpressPdfProcessor : IPdfProcessor
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. Read stream to byte array for raw data analysis
byte[] pdfBytes;
if (pdfStream is MemoryStream ms && ms.TryGetBuffer(out var buffer))
@@ -95,14 +111,18 @@ public class DevExpressPdfProcessor : IPdfProcessor
}
else
{
pdfStream.Position = 0;
using var memoryStream = new MemoryStream();
await pdfStream.CopyToAsync(memoryStream);
pdfBytes = memoryStream.ToArray();
}
// 3. Load PDF with DevExpress Document API
pdfStream.Position = 0;
// Reset position for DevExpress (seekable streams only)
if (pdfStream.CanSeek)
{
pdfStream.Position = 0;
}
using var processor = new PdfDocumentProcessor();
processor.LoadDocument(pdfStream);
@@ -175,8 +195,15 @@ public class DevExpressPdfProcessor : IPdfProcessor
throw new BadRequestException("PDF stream cannot be empty");
}
// 2. Load PDF with DevExpress Document API (exceptions propagate naturally)
pdfStream.Position = 0;
// 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
// DevExpress LoadDocument may throw exceptions for corrupted PDFs - let them propagate naturally
// Middleware will catch and convert to 500 Internal Server Error
using var processor = new PdfDocumentProcessor();
processor.LoadDocument(pdfStream);