test: Add PdfAttachmentController extract endpoint integration tests (6 tests)

DocumentOperator.Tests/Integration/API/PdfAttachmentControllerTests.cs

@@ -250,4 +250,134 @@ public class PdfAttachmentControllerTests : IClassFixture<WebApplicationFactory<
     }
 
     #endregion
+
+    #region Extract Attachments Tests (Multipart)
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Multipart_ValidPdfWithAttachments_Returns200WithZip()
+    {
+        // Arrange
+        byte[] pdfBytes = await LoadTestPdfAsync("pdfWithMoreThanOneAttachment.pdf");
+
+        using var content = new MultipartFormDataContent();
+        var fileContent = new ByteArrayContent(pdfBytes);
+        fileContent.Headers.ContentType = new System.Net.Http.Headers.MediaTypeHeaderValue("application/pdf");
+        content.Add(fileContent, "file", "test.pdf");
+
+        // Act
+        var response = await _client.PostAsync("/api/pdf/attachments/extract", content);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.OK);
+        response.Content.Headers.ContentType?.MediaType.Should().Be("application/zip");
+        response.Content.Headers.ContentDisposition?.FileName.Should().Be("attachments.zip");
+
+        byte[] zipBytes = await response.Content.ReadAsByteArrayAsync();
+        zipBytes.Should().NotBeEmpty("ZIP should contain data");
+
+        // Verify ZIP structure
+        using var zipStream = new MemoryStream(zipBytes);
+        using var zipArchive = new System.IO.Compression.ZipArchive(zipStream, System.IO.Compression.ZipArchiveMode.Read);
+        
+        zipArchive.Entries.Should().HaveCount(6, "PDF contains 6 attachments");
+    }
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Multipart_EmptyPdf_Returns400()
+    {
+        // Arrange
+        using var content = new MultipartFormDataContent();
+        var fileContent = new ByteArrayContent(Array.Empty<byte>());
+        fileContent.Headers.ContentType = new System.Net.Http.Headers.MediaTypeHeaderValue("application/pdf");
+        content.Add(fileContent, "file", "empty.pdf");
+
+        // Act
+        var response = await _client.PostAsync("/api/pdf/attachments/extract", content);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.BadRequest);
+    }
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Multipart_CorruptedPdf_Returns500()
+    {
+        // Arrange
+        byte[] corruptedBytes = "This is not a valid PDF content"u8.ToArray();
+
+        using var content = new MultipartFormDataContent();
+        var fileContent = new ByteArrayContent(corruptedBytes);
+        fileContent.Headers.ContentType = new System.Net.Http.Headers.MediaTypeHeaderValue("application/pdf");
+        content.Add(fileContent, "file", "corrupted.pdf");
+
+        // Act
+        var response = await _client.PostAsync("/api/pdf/attachments/extract", content);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.InternalServerError);
+    }
+
+    #endregion
+
+    #region Extract Attachments Tests (Base64)
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Base64_ValidPdfWithAttachments_Returns200WithZip()
+    {
+        // Arrange
+        byte[] pdfBytes = await LoadTestPdfAsync("pdfWithMoreThanOneAttachment.pdf");
+        string base64Pdf = Convert.ToBase64String(pdfBytes);
+        var request = new ExtractPdfAttachmentsRequest { Base64Pdf = base64Pdf };
+
+        // Act
+        var response = await _client.PostAsJsonAsync("/api/pdf/attachments/extract", request);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.OK);
+        response.Content.Headers.ContentType?.MediaType.Should().Be("application/zip");
+        response.Content.Headers.ContentDisposition?.FileName.Should().Be("attachments.zip");
+
+        byte[] zipBytes = await response.Content.ReadAsByteArrayAsync();
+        zipBytes.Should().NotBeEmpty("ZIP should contain data");
+
+        // Verify ZIP structure
+        using var zipStream = new MemoryStream(zipBytes);
+        using var zipArchive = new System.IO.Compression.ZipArchive(zipStream, System.IO.Compression.ZipArchiveMode.Read);
+        
+        zipArchive.Entries.Should().HaveCount(6, "PDF contains 6 attachments");
+    }
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Base64_InvalidBase64_Returns400()
+    {
+        // Arrange
+        var request = new ExtractPdfAttachmentsRequest { Base64Pdf = "invalid-base64!!!" };
+
+        // Act
+        var response = await _client.PostAsJsonAsync("/api/pdf/attachments/extract", request);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.BadRequest);
+
+        var problemDetails = await response.Content.ReadAsStringAsync();
+        // FormatException message contains "Base-64" (with hyphen)
+        problemDetails.Should().MatchRegex("(?i)base.?64", "should contain Base64 validation error");
+    }
+
+    [Fact]
+    public async Task POST_ExtractAttachments_Base64_EmptyPdf_Returns400()
+    {
+        // Arrange
+        var request = new ExtractPdfAttachmentsRequest { Base64Pdf = string.Empty };
+
+        // Act
+        var response = await _client.PostAsJsonAsync("/api/pdf/attachments/extract", request);
+
+        // Assert
+        response.StatusCode.Should().Be(HttpStatusCode.BadRequest);
+
+        var problemDetails = await response.Content.ReadAsStringAsync();
+        problemDetails.Should().MatchRegex("(Base64|empty|stream)", "should contain validation error message");
+    }
+
+    #endregion
 }