Free, open-source file converter. Convert 263 formats offline by drag & drop — images, PDF, Word, Excel, PowerPoint, HWP/HWPX, video, audio, e-books and archives. No upload, no Office needed.
C# audio-converteravaloniabatch-conversionconvertercsharpdocument-converterdocx-to-pdfdotnetdrag-and-dropfile-conversionfile-converterheic-converterhwphwpximage-converterlinuxmacospdf-convertervideo-converterwindows
test(ocr): add regression tests for default preset image ocr and temp scan cleanup
smjrifle286a937a3dd6
diff --git a/tests/Filee.Platform.Tests/VisionOcrTests.cs b/tests/Filee.Platform.Tests/VisionOcrTests.csindex 68c7bc4e..2c05a365 100644--- a/tests/Filee.Platform.Tests/VisionOcrTests.cs+++ b/tests/Filee.Platform.Tests/VisionOcrTests.cs@@ -194,6 +194,94 @@ public sealed class VisionOcrTests}}+ [Fact]+ public async Task ImageOcrConverterSucceedsWithDefaultPresetWhenDocumentOcrIsFalse()+ {+ if (!OperatingSystem.IsMacOS())+ {+ Assert.Skip("Requires macOS Vision framework.");+ return;+ }++ var engine = new MacOsVisionOcrEngine();+ OcrEngineRegistry.Register(engine);++ var converter = new ImageOcrConverter();+ var imagePath = Path.Combine(FindRepoRoot(), "docs", "media", "banner-en.jpg");+ var workDir = Path.Combine(Path.GetTempPath(), $"filee-test-default-preset-{Guid.NewGuid():N}");+ Directory.CreateDirectory(workDir);++ try+ {+ var defaultPreset = new Preset();+ Assert.False(defaultPreset.Document.Ocr);++ var txtOut = Path.Combine(workDir, "banner-default.txt");+ var txtStep = new ConversionStep(+ InputPath: imagePath,+ From: "jpg",+ To: "txt",+ Preset: defaultPreset,+ Output: new FixedPath(txtOut),+ WorkDirectory: workDir);++ var outputs = await converter.ConvertAsync(txtStep, null, TestContext.Current.CancellationToken);+ Assert.Single(outputs);+ Assert.True(File.Exists(outputs[0]));+ var txt = await File.ReadAllTextAsync(outputs[0], TestContext.Current.CancellationToken);+ Assert.Contains("Filee", txt, StringComparison.OrdinalIgnoreCase);+ }+ finally+ {+ Directory.Delete(workDir, recursive: true);+ }+ }++ [Fact]+ public void PdfDocumentReaderDeletesTempScanInTextOnlyModeWhenOcrReturnsNoWords()+ {+ var emptyEngine = new EmptyMockEngine();+ var workDir = Path.Combine(Path.GetTempPath(), $"filee-pdf-leak-test-{Guid.NewGuid():N}");+ Directory.CreateDirectory(workDir);++ try+ {+ var pdfPath = Path.Combine(workDir, "blank-scanned.pdf");+ using (var pdfDoc = new PdfSharp.Pdf.PdfDocument())+ {+ var page = pdfDoc.AddPage();+ page.Width = PdfSharp.Drawing.XUnit.FromPoint(200);+ page.Height = PdfSharp.Drawing.XUnit.FromPoint(200);+ using var gfx = PdfSharp.Drawing.XGraphics.FromPdfPage(page);+ gfx.DrawRectangle(PdfSharp.Drawing.XBrushes.White, 0, 0, 200, 200);+ pdfDoc.Save(pdfPath);+ }++ var scanDir = Path.Combine(workDir, "pdf-scans");+ var plainDoc = PdfDocumentReader.ReadText(pdfPath, emptyEngine, enableOcr: true, workDirectory: workDir);++ if (Directory.Exists(scanDir))+ {+ var leftoverFiles = Directory.GetFiles(scanDir, "*.png");+ Assert.Empty(leftoverFiles);+ }+ }+ finally+ {+ Directory.Delete(workDir, recursive: true);+ }+ }++ private sealed class EmptyMockEngine : IOcrEngine+ {+ public string Id => "empty-mock";+ public string DisplayName => "Empty Mock";+ public bool IsAvailable => true;+ public IReadOnlyList<string> SupportedLanguages => ["en"];+ public Task<OcrPageResult> RecognizeAsync(string imagePath, string? language = null, CancellationToken cancellationToken = default) =>+ Task.FromResult(OcrPageResult.Empty(100, 100));+ }+private sealed class FixedPath(string path) : IOutputAllocator{public string? Allocate(string extension, string? suffix = null) => path;