Files
DocumentService/DocumentOperator.Application/Common/Interfaces/IPdfProcessor.cs
TekH 522de8a863 feat: Add IPdfProcessor.MergePdfsAsync interface
- Add MergePdfsAsync method to IPdfProcessor interface
- Parameters: IReadOnlyList<Stream> pdfStreams, IReadOnlyList<string?>? pageRanges
- Returns: Task<byte[]> (merged PDF)
- Validates: Minimum 2 PDFs, stream Position = 0, page ranges count matches PDF count
- Supports optional page ranges (e.g., '1-3,5' or null for all pages)
2026-07-21 10:20:18 +02:00

79 lines
3.8 KiB
C#

using DocumentOperator.Application.Common.DTOs;
namespace DocumentOperator.Application.Common.Interfaces;
public interface IPdfProcessor
{
/// <summary>
/// Validates a PDF and extracts metadata.
/// </summary>
/// <param name="pdfStream">
/// PDF document stream. Must be readable and positioned at the beginning (Position = 0).
/// Non-seekable streams are supported. Caller is responsible for disposal.
/// </param>
/// <returns>PDF metadata (page count, size, version, attachments)</returns>
/// <exception cref="Domain.Common.Exceptions.BadRequestException">
/// Thrown when stream is empty, invalid, or not positioned at the beginning
/// </exception>
Task<PdfMetadata> ValidateAsync(Stream pdfStream);
/// <summary>
/// Validates a PDF/A document and checks conformance level.
/// </summary>
/// <param name="pdfStream">
/// PDF document stream. Must be readable and positioned at the beginning (Position = 0).
/// Non-seekable streams are supported. Caller is responsible for disposal.
/// </param>
/// <returns>PDF/A metadata including conformance level and validation errors/warnings</returns>
/// <exception cref="Domain.Common.Exceptions.BadRequestException">
/// Thrown when stream is empty, invalid, or not positioned at the beginning
/// </exception>
Task<PdfAMetadata> ValidatePdfAAsync(Stream pdfStream);
/// <summary>
/// Checks for embedded files (attachments) in a PDF document and returns detailed metadata.
/// </summary>
/// <param name="pdfStream">
/// PDF document stream. Must be readable and positioned at the beginning (Position = 0).
/// Non-seekable streams are supported. Caller is responsible for disposal.
/// </param>
/// <returns>Attachment information (count, file names, MIME types, sizes)</returns>
/// <exception cref="Domain.Common.Exceptions.BadRequestException">
/// Thrown when stream is empty, invalid, or not positioned at the beginning
/// </exception>
Task<AttachmentInfo> CheckAttachmentsAsync(Stream pdfStream);
/// <summary>
/// Extracts all embedded files from a PDF document and returns them as a ZIP archive.
/// </summary>
/// <param name="pdfStream">
/// PDF document stream. Must be readable and positioned at the beginning (Position = 0).
/// Non-seekable streams are supported. Caller is responsible for disposal.
/// </param>
/// <returns>ZIP archive containing all extracted attachments as byte array</returns>
/// <exception cref="Domain.Common.Exceptions.BadRequestException">
/// Thrown when stream is empty, invalid, or not positioned at the beginning
/// </exception>
/// <exception cref="Domain.Common.Exceptions.NotFoundException">
/// Thrown when PDF contains no attachments
/// </exception>
Task<byte[]> ExtractAttachmentsAsync(Stream pdfStream);
/// <summary>
/// Merges multiple PDF documents into a single PDF.
/// </summary>
/// <param name="pdfStreams">
/// PDF streams to merge (minimum 2 required). Each stream must be readable and positioned
/// at the beginning (Position = 0). Caller is responsible for disposal.
/// </param>
/// <param name="pageRanges">
/// Optional page ranges per PDF (null = all pages). Format: "1-3,5" means pages 1, 2, 3, and 5.
/// If null or empty for a PDF, all pages are included. Array length must match pdfStreams length if provided.
/// </param>
/// <returns>Merged PDF as byte array</returns>
/// <exception cref="Domain.Common.Exceptions.BadRequestException">
/// Thrown when fewer than 2 PDFs provided, any stream is empty/invalid/not at Position=0,
/// or page range format is invalid
/// </exception>
Task<byte[]> MergePdfsAsync(IReadOnlyList<Stream> pdfStreams, IReadOnlyList<string?>? pageRanges = null);
}