public void A_valid_file_is_happily_converted()
{
var metadataFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK\header\metadata.xml");
var rootFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK");
var paket = (PaketDIP)Paket.LoadFromFile(metadataFile);
var settings = new ScansZusammenfassenSettings {
GroesseInProzent = 100, DefaultAufloesungInDpi = 300, JpegQualitaetInProzent = 80
};
var processor = new ScanProcessor(new FileResolution(settings), settings);
// Act
processor.ConvertSingleJpeg2000ScansToPdfDocuments(paket, rootFolder);
// Assert
// Every Dokument and Umschlag got converted
var contentFolder = paket.Inhaltsverzeichnis.Ordner[0];
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000001")?.Datei.Count.Should().Be(1); // Just the pdf
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000002")?.Datei.Count.Should().Be(1); // Just the pdf
contentFolder.Ordner.FirstOrDefault(o => o.Name == "U_m_s_c_h_l_a_g_0000001")?.Datei.Count.Should().Be(1); // Just the pdf
// Premis Dateien gelöscht?
var dokument1 = new DirectoryInfo(Path.Combine(rootFolder, "content", "D_o_k_u_m_e_n_t_0000001"));
var dokument2 = new DirectoryInfo(Path.Combine(rootFolder, "content", "D_o_k_u_m_e_n_t_0000002"));
var umschlagDirectory = new DirectoryInfo(Path.Combine(rootFolder, "content", "U_m_s_c_h_l_a_g_0000001"));
umschlagDirectory.GetFiles("*.xml").Length.Should().Be(0);
dokument1.GetFiles("*.xml").Length.Should().Be(0);
dokument2.GetFiles("*.xml").Length.Should().Be(0);
}
public void A_messed_up_metadata_file_results_in_unchanged_document_1_and_2()
{
// This metadata file has data that has wrongly named jp2/premis pairs, so it does not line up
var metadataFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_NOK\header\metadata.xml");
var rootFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_NOK");
var paket = (PaketDIP)Paket.LoadFromFile(metadataFile);
var settings = new ScansZusammenfassenSettings {
GroesseInProzent = 100, DefaultAufloesungInDpi = 300, JpegQualitaetInProzent = 80
};
var processor = new ScanProcessor(new FileResolution(settings), settings);
// Act
processor.ConvertSingleJpeg2000ScansToPdfDocuments(paket, rootFolder);
// Assert
// Document 1 and 2 are the same
// Umschlag 1 got converted to pdf
var contentFolder = paket.Inhaltsverzeichnis.Ordner[0];
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000001")?.Datei.Count.Should().Be(8); // The original jp2 and premis
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000002")?.Datei.Count.Should().Be(8); // The original jp2 and premis
contentFolder.Ordner.FirstOrDefault(o => o.Name == "U_m_s_c_h_l_a_g_0000001")?.Datei.Count.Should().Be(1); // Just the pdf
// Premis Dateien gelöscht?
var umschlagDirectory = new DirectoryInfo(Path.Combine(rootFolder, "content", "U_m_s_c_h_l_a_g_0000001"));
umschlagDirectory.GetFiles("*.xml").Length.Should().Be(0);
}
public ScanProcessor(FileResolution fileResolution, ScansZusammenfassenSettings settings)
{
// ReSharper disable once RedundantNameQualifier
var licensePdf = new License();
licensePdf.SetLicense("Aspose.Total.lic");
var licenseImaging = new Aspose.Imaging.License();
licenseImaging.SetLicense("Aspose.Total.lic");
this.fileResolution = fileResolution;
this.settings = settings;
}
private static void Main(string[] args)
{
ConfigureLogging();
Log.Information("CMI.Manager.Asset.TransformJp2ToPdfTester starting");
if (args.Length == 0 || !Directory.Exists(args[0]))
{
Console.WriteLine(
"You need to provide a directory with a sample DIP package to process as an argument. As a second argument the JPEG quality can be provided. A third parameter sets the new size in percent of the original image");
Console.ReadLine();
return;
}
// Read source folder
var sourceFolder = args[0];
var jpegQuality = 80; // Default
if (args.Length == 2 && int.TryParse(args[1], out var quality))
{
jpegQuality = quality;
}
var sizeInPercent = 100; // Default
if (args.Length == 3 && int.TryParse(args[2], out var size))
{
sizeInPercent = size;
}
try
{
var transformEngine = new TransformEngine(new Xsl2Processor());
ConvertAreldaMetadataXml(sourceFolder, transformEngine);
var metadataFile = Path.Combine(sourceFolder, "header", "metadata.xml");
var paket = (PaketDIP)Paket.LoadFromFile(metadataFile);
var settings = new ScansZusammenfassenSettings {
DefaultAufloesungInDpi = 300, GroesseInProzent = sizeInPercent, JpegQualitaetInProzent = jpegQuality
};
var scanProcessor = new ScanProcessor(new FileResolution(settings), settings);
// Create pdf documents from scanned jpeg 2000 scans.
scanProcessor.ConvertSingleJpeg2000ScansToPdfDocuments(paket, sourceFolder);
}
catch (Exception ex)
{
Log.Error(ex, $"Unexpected error. {ex.Message}");
}
}
public void File_not_found_in_content_structure_results_in_exception()
{
// Arrange
var metadataFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK\header\metadata.xml");
var rootFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK");
var paket = (PaketDIP)Paket.LoadFromFile(metadataFile);
// Make the file invalid to trigger the exception by removing one file reference in the first folder.
paket.Inhaltsverzeichnis.Ordner[0].Ordner[0].Datei.RemoveAt(0);
var settings = new ScansZusammenfassenSettings();
var processor = new ScanProcessor(new FileResolution(settings), settings);
// Act(ion)
Action action = () => processor.ConvertSingleJpeg2000ScansToPdfDocuments(paket, rootFolder);
// Asert
action.Should().Throw <InvalidOperationException>();
}
/// <summary>
/// <para>
/// Converts single page jpeg2000 Scans found within the package into (multi-paged) pdf document.
/// Per document or dossier (with direct dateiRef's) one pdf is created. The metadata information in the package is
/// updated to reflect the changes made.
/// </para>
/// <para>The following assumptions are made:</para>
/// <list type="bullet">
/// <item>JPEG 2000 Files have the extension .jp2</item>
/// <item>The .jp2 may be accompanied by a premis xml file. The premis filename is "[jpeg200Filename]_premis.xml</item>
/// <item>
/// Within one document or (dossier with dateiRef) only .jp2 files are allowed.
/// If other file types are mixed in, (except for the premis files) the conversion silently fails for that
/// document.
/// </item>
/// <item>The premis files are removed after the pdf creation took place.</item>
/// </list>
/// </summary>
/// <param name="paket">The package to be converted</param>
/// <param name="folder">The root folder where the files can be found.</param>
/// <param name="settings">The conversion settings</param>
public void ConvertSingleJpeg2000ScansToPdfDocuments(PaketDIP paket, string folder, ScansZusammenfassenSettings settings)
{
conversionSettings = settings;
rootFolder = folder;
paketToConvert = paket;
// Default settings for Image conversion
encoderParameters = new EncoderParameters(1);
var encoderParameter = new EncoderParameter(Encoder.Quality, conversionSettings.JpegQualitaetInProzent);
encoderParameters.Param[0] = encoderParameter;
BitmapImageCreator.Register();
foreach (var ordnungssystemposition in paket.Ablieferung.Ordnungssystem.Ordnungssystemposition)
{
ProcessOrdnungssystemPosition(ordnungssystemposition);
}
}
public void Files_linked_to_document_that_are_not_jp2_files_and_not_premis_result_in_unchanged_package()
{
var metadataFile = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK\header\metadata.xml");
var rootFolder = Path.Combine(TestContext.CurrentContext.TestDirectory, @"TestDataCopy\jp2_OK");
var paket = (PaketDIP)Paket.LoadFromFile(metadataFile);
var settings = new ScansZusammenfassenSettings {
GroesseInProzent = 100, DefaultAufloesungInDpi = 300, JpegQualitaetInProzent = 80
};
var processor = new ScanProcessor(new FileResolution(settings), settings);
// Add some weird files to the package
AddFileToPackage("test01.txt", "D_o_k_u_m_e_n_t_0000001", paket, rootFolder);
AddFileToPackage("test02.txt", "D_o_k_u_m_e_n_t_0000002", paket, rootFolder);
AddFileToPackage("test03.txt", "U_m_s_c_h_l_a_g_0000001", paket, rootFolder);
// Act
processor.ConvertSingleJpeg2000ScansToPdfDocuments(paket, rootFolder);
// Assert
// Nothing should be changed
var contentFolder = paket.Inhaltsverzeichnis.Ordner[0];
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000001")?.Datei.Count.Should().Be(9);
contentFolder.Ordner.FirstOrDefault(o => o.Name == "D_o_k_u_m_e_n_t_0000002")?.Datei.Count.Should().Be(9);
contentFolder.Ordner.FirstOrDefault(o => o.Name == "U_m_s_c_h_l_a_g_0000001")?.Datei.Count.Should().Be(5);
// Alle Dateien vorhanden?
var dokument1 = new DirectoryInfo(Path.Combine(rootFolder, "content", "D_o_k_u_m_e_n_t_0000001"));
var dokument2 = new DirectoryInfo(Path.Combine(rootFolder, "content", "D_o_k_u_m_e_n_t_0000002"));
var umschlagDirectory = new DirectoryInfo(Path.Combine(rootFolder, "content", "U_m_s_c_h_l_a_g_0000001"));
umschlagDirectory.GetFiles("*.xml").Length.Should().Be(2);
umschlagDirectory.GetFiles("*.jp2").Length.Should().Be(2);
dokument1.GetFiles("*.xml").Length.Should().Be(4);
dokument1.GetFiles("*.jp2").Length.Should().Be(4);
dokument2.GetFiles("*.xml").Length.Should().Be(4);
dokument2.GetFiles("*.jp2").Length.Should().Be(4);
}
public FileResolution(ScansZusammenfassenSettings settings)
{
this.settings = settings;
}
