Files
DocumentService/DocumentService.Application/ExtractZugferd/ExtractZugferdCommand.cs
TekH 207c778f3a Refactor: Rename DocumentOperator to DocumentService
Updated project and solution files to rename and restructure
`DocumentOperator` to `DocumentService`. Modified project
references in `DocumentService.API.csproj`, `DocumentService.Application.csproj`,
and `DocumentService.Infrastructure.csproj` to reflect the new
naming convention. Updated `DocumentService.sln` to remove
old project references, add new ones, and adjust configuration
and nested project mappings accordingly. This change aligns
the project structure with the new naming convention.
2026-08-30 21:33:25 +02:00

114 lines
3.7 KiB
C#

using DocumentService.Application.Common.Configuration;
using DocumentService.Application.Common.Interfaces;
using DocumentService.Domain.Common.Exceptions;
using FluentValidation;
using MediatR;
using Microsoft.Extensions.Options;
namespace DocumentService.Application.ExtractZugferd;
/// <summary>
/// Command to extract ZUGFeRD XML from a PDF document
/// </summary>
public record ExtractZugferdCommand : IRequest<ZugferdExtractionResult>
{
/// <summary>
/// PDF document stream. Must be positioned at the beginning (Position = 0).
/// </summary>
public required Stream PdfStream { get; init; }
}
/// <summary>
/// Handler for ExtractZugferdCommand.
/// Extracts ZUGFeRD XML from PDF and returns XML content
/// </summary>
public class ExtractZugferdCommandHandler(
IPdfProcessor pdfProcessor,
IOptions<ZugferdSettings> settings)
: IRequestHandler<ExtractZugferdCommand, ZugferdExtractionResult>
{
private readonly ZugferdSettings _settings = settings.Value;
public async Task<ZugferdExtractionResult> Handle(ExtractZugferdCommand request, CancellationToken cancellationToken)
{
// Get all attachments
var attachmentInfo = await pdfProcessor.CheckAttachmentsAsync(request.PdfStream);
// Find ZUGFeRD XML file using configured names and patterns
var zugferdAttachment = attachmentInfo.Attachments.FirstOrDefault(a =>
_settings.ZugferdFileNames.Any(name =>
a.FileName.Equals(name, StringComparison.OrdinalIgnoreCase)) ||
_settings.ZugferdFileNamePatterns.Any(pattern =>
a.FileName.Contains(pattern, StringComparison.OrdinalIgnoreCase)));
if (zugferdAttachment == null)
{
throw new NotFoundException("ZUGFeRD XML not found in PDF attachments");
}
// Reset stream position for extraction
request.PdfStream.Position = 0;
// Extract all attachments as ZIP
byte[] zipBytes = await pdfProcessor.ExtractAttachmentsAsync(request.PdfStream);
// Find ZUGFeRD XML in ZIP
using var zipStream = new MemoryStream(zipBytes);
using var zipArchive = new System.IO.Compression.ZipArchive(zipStream, System.IO.Compression.ZipArchiveMode.Read);
var zugferdEntry = zipArchive.Entries.FirstOrDefault(e =>
e.Name.Equals(zugferdAttachment.FileName, StringComparison.OrdinalIgnoreCase));
if (zugferdEntry == null)
{
throw new NotFoundException($"ZUGFeRD XML '{zugferdAttachment.FileName}' not found in extracted attachments");
}
// Read XML content
using var entryStream = zugferdEntry.Open();
using var reader = new StreamReader(entryStream);
string xmlContent = await reader.ReadToEndAsync(cancellationToken);
return new ZugferdExtractionResult
{
FileName = zugferdAttachment.FileName,
XmlContent = xmlContent,
FileSize = zugferdAttachment.SizeBytes
};
}
}
/// <summary>
/// Validator for ExtractZugferdCommand.
/// </summary>
public class ExtractZugferdCommandValidator : AbstractValidator<ExtractZugferdCommand>
{
public ExtractZugferdCommandValidator()
{
RuleFor(x => x.PdfStream)
.NotNull()
.WithMessage("PDF stream is required");
}
}
/// <summary>
/// Result DTO for ZUGFeRD extraction
/// </summary>
public record ZugferdExtractionResult
{
/// <summary>
/// ZUGFeRD XML file name
/// </summary>
public required string FileName { get; init; }
/// <summary>
/// ZUGFeRD XML content as string
/// </summary>
public required string XmlContent { get; init; }
/// <summary>
/// File size in bytes
/// </summary>
public long FileSize { get; init; }
}