public virtual void TestFontColorInMultiPagePdf()
{
String testName = "testFontColorInMultiPagePdf";
String path = TEST_IMAGES_DIRECTORY + "multîpage.tiff";
String pdfPath = GetTargetDirectory() + testName + ".pdf";
FileInfo file = new FileInfo(path);
tesseractReader.SetTesseract4OcrEngineProperties(tesseractReader.GetTesseract4OcrEngineProperties().SetPreprocessingImages
(false));
OcrPdfCreatorProperties ocrPdfCreatorProperties = new OcrPdfCreatorProperties();
ocrPdfCreatorProperties.SetTextLayerName("Text1");
Color color = DeviceCmyk.MAGENTA;
ocrPdfCreatorProperties.SetTextColor(color);
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader, ocrPdfCreatorProperties);
PdfDocument doc = ocrPdfCreator.CreatePdf(JavaCollectionsUtil.SingletonList <FileInfo>(file), GetPdfWriter(
pdfPath));
NUnit.Framework.Assert.IsNotNull(doc);
doc.Close();
PdfDocument pdfDocument = new PdfDocument(new PdfReader(pdfPath));
IntegrationTestHelper.ExtractionStrategy strategy = new IntegrationTestHelper.ExtractionStrategy("Text1");
PdfCanvasProcessor processor = new PdfCanvasProcessor(strategy);
processor.ProcessPageContent(pdfDocument.GetPage(1));
Color fillColor = strategy.GetFillColor();
NUnit.Framework.Assert.AreEqual(fillColor, color);
pdfDocument.Close();
}
public virtual void ComparePdfA3uRGBSpanishJPG()
{
String testName = "comparePdfA3uRGBSpanishJPG";
String filename = "spanish_01";
String expectedPdfPath = TEST_DOCUMENTS_DIRECTORY + filename + "_a3u.pdf";
String resultPdfPath = GetTargetDirectory() + filename + "_" + testName + "_a3u.pdf";
Tesseract4OcrEngineProperties properties = new Tesseract4OcrEngineProperties(tesseractReader.GetTesseract4OcrEngineProperties
());
properties.SetPathToTessData(GetTessDataDirectory());
properties.SetLanguages(JavaCollectionsUtil.SingletonList <String>("spa"));
tesseractReader.SetTesseract4OcrEngineProperties(properties);
OcrPdfCreatorProperties ocrPdfCreatorProperties = new OcrPdfCreatorProperties();
ocrPdfCreatorProperties.SetPdfLang("en-US");
ocrPdfCreatorProperties.SetTitle("");
ocrPdfCreatorProperties.SetTextColor(DeviceRgb.BLACK);
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader, ocrPdfCreatorProperties);
PdfDocument doc = ocrPdfCreator.CreatePdfA(JavaCollectionsUtil.SingletonList <FileInfo>(new FileInfo(TEST_IMAGES_DIRECTORY
+ filename + ".jpg")), GetPdfWriter(resultPdfPath), GetRGBPdfOutputIntent());
NUnit.Framework.Assert.IsNotNull(doc);
doc.Close();
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(resultPdfPath, expectedPdfPath, GetTargetDirectory
(), "diff_"));
}
public virtual void TestSpanishPNG()
{
String testName = "compareSpanishPNG";
String filename = "scanned_spa_01";
String expectedText1 = "¿Y SI ENSAYARA COMO ACTUAR?";
String expectedText2 = "¿Y SI ENSAYARA ACTUAR?";
String resultPdfPath = GetTargetDirectory() + filename + "_" + testName + "_" + testFileTypeName + ".pdf";
IList <String> languages = JavaUtil.ArraysAsList("spa", "spa_old");
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
if (isExecutableReaderType)
{
properties.SetPreprocessingImages(false);
}
// locate text by words
properties.SetTextPositioning(TextPositioning.BY_WORDS);
properties.SetLanguages(languages);
tesseractReader.SetTesseract4OcrEngineProperties(properties);
OcrPdfCreatorProperties ocrPdfCreatorProperties = new OcrPdfCreatorProperties();
ocrPdfCreatorProperties.SetTextColor(DeviceCmyk.BLACK);
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader, ocrPdfCreatorProperties);
using (PdfWriter pdfWriter = GetPdfWriter(resultPdfPath)) {
ocrPdfCreator.CreatePdf(JavaCollectionsUtil.SingletonList <FileInfo>(new FileInfo(TEST_IMAGES_DIRECTORY + filename
+ ".png")), pdfWriter).Close();
}
try {
String result = GetTextFromPdfLayer(resultPdfPath, null, 1).Replace("\n", " ");
NUnit.Framework.Assert.IsTrue(result.Contains(expectedText1) || result.Contains(expectedText2));
}
finally {
NUnit.Framework.Assert.AreEqual(TextPositioning.BY_WORDS, tesseractReader.GetTesseract4OcrEngineProperties
().GetTextPositioning());
}
}