b1d48418cf
Replaced `DevExpress.Pdf.Core` with `DevExpress.Document.Processor` in `DocumentOperator.Infrastructure.csproj` to adopt a newer library for PDF processing. Removed the `Services\PdfProcessing\` folder reference. Updated `DevExpressPdfProcessorTests` to reflect changes in the `ValidateAsync` method's behavior. Introduced the `DevExpressPdfProcessor` class, implementing the `IPdfProcessor` interface. This class validates PDF documents and extracts metadata using the `DevExpress.Pdf` library. Added defensive input validation, metadata extraction, and exception handling for domain consistency.
67 lines
2.5 KiB
C#
67 lines
2.5 KiB
C#
using DevExpress.Pdf;
|
|
using DevExpress.Pdf;
|
|
using DocumentOperator.Application.Common.Interfaces;
|
|
using DocumentOperator.Domain.Common.Exceptions;
|
|
|
|
namespace DocumentOperator.Infrastructure.Services.PdfProcessing;
|
|
|
|
/// <summary>
|
|
/// PDF processor implementation using DevExpress.Pdf library.
|
|
/// Handles PDF validation and metadata extraction.
|
|
/// </summary>
|
|
public class DevExpressPdfProcessor : IPdfProcessor
|
|
{
|
|
/// <summary>
|
|
/// Validates a PDF document and returns metadata.
|
|
/// </summary>
|
|
/// <param name="pdfBytes">PDF content as byte array</param>
|
|
/// <returns>PDF metadata (page count, file size, version, etc.)</returns>
|
|
/// <exception cref="PdfProcessingException">Thrown when PDF is invalid or null</exception>
|
|
public async Task<DocumentOperator.Domain.Models.ValueObjects.PdfMetadata> ValidateAsync(byte[] pdfBytes)
|
|
{
|
|
// 1. Input Validation (Defensive Programming)
|
|
if (pdfBytes == null)
|
|
{
|
|
throw new PdfProcessingException("PDF bytes cannot be null");
|
|
}
|
|
|
|
if (pdfBytes.Length == 0)
|
|
{
|
|
throw new PdfProcessingException("PDF bytes cannot be empty");
|
|
}
|
|
|
|
try
|
|
{
|
|
// 2. Load PDF with DevExpress Document API (PdfDocumentProcessor)
|
|
using var processor = new PdfDocumentProcessor();
|
|
processor.LoadDocument(new MemoryStream(pdfBytes));
|
|
|
|
// 3. Extract metadata
|
|
var document = processor.Document;
|
|
|
|
int pageCount = document.Pages.Count;
|
|
string pdfVersion = document.Version.ToString(); // z.B. "1.4", "1.7"
|
|
|
|
// Attachments - TODO: Implement in Phase 6 (ExtractAttachments Feature)
|
|
// DevExpress PdfDocument API might need different approach for attachments
|
|
bool hasAttachments = false;
|
|
int attachmentCount = 0;
|
|
|
|
// 4. Create and return PdfMetadata Value Object (fully qualified name!)
|
|
return new DocumentOperator.Domain.Models.ValueObjects.PdfMetadata(
|
|
pageCount: pageCount,
|
|
fileSizeBytes: pdfBytes.Length,
|
|
pdfVersion: pdfVersion,
|
|
hasAttachments: hasAttachments,
|
|
attachmentCount: attachmentCount
|
|
);
|
|
}
|
|
catch (Exception ex) when (ex is not PdfProcessingException)
|
|
{
|
|
// Wrap DevExpress exceptions in our domain exception
|
|
throw new PdfProcessingException(
|
|
$"Failed to validate PDF: {ex.Message}",
|
|
ex);
|
|
}
|
|
}
|
|
} |