private static void DoImageToPdfOcr(AbstractTesseract4OcrEngine tesseractReader, IList <FileInfo> imageFiles
)
{
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader);
ocrPdfCreator.CreatePdf(imageFiles, new PdfWriter(new MemoryStream()));
}
/// <summary>Parse text from image and compare with expected.</summary>
private void TestImageOcrText(AbstractTesseract4OcrEngine tesseractReader, String path, String expectedOutput
)
{
FileInfo ex1 = new FileInfo(path);
String realOutputHocr = GetTextUsingTesseractFromImage(tesseractReader, ex1);
NUnit.Framework.Assert.IsTrue(realOutputHocr.Contains(expectedOutput));
}
/// <summary>Do OCR for given image and compare result text file with expected one.</summary>
private bool DoOcrAndCompareTxtFiles(AbstractTesseract4OcrEngine tesseractReader, String imgPath, String expectedPath
, IList <String> languages)
{
String resultTxtFile = GetTargetDirectory() + GetImageName(imgPath, languages) + ".txt";
DoOcrAndSaveToTextFile(tesseractReader, imgPath, resultTxtFile, languages);
return(CompareTxtFiles(expectedPath, resultTxtFile));
}
internal DoImageOcrRunnable(AbstractTesseract4OcrEngine tesseractReader, IMetaInfo metaInfo, FileInfo imgFile
, FileInfo outputFile, bool createPdf)
{
this.tesseractReader = tesseractReader;
this.metaInfo = metaInfo;
this.imgFile = imgFile;
this.outputFile = outputFile;
this.createPdf = createPdf;
}
public EventCountingTest(IntegrationTestHelper.ReaderType type)
{
isExecutableReaderType = type.Equals(IntegrationTestHelper.ReaderType.EXECUTABLE);
if (isExecutableReaderType)
{
testFileTypeName = "executable";
}
else
{
testFileTypeName = "lib";
}
tesseractReader = GetTesseractReader(type);
}
/// <summary>Retrieve text from specified page from given PDF document.</summary>
protected internal virtual String GetTextFromPdf(AbstractTesseract4OcrEngine tesseractReader, FileInfo file
, int page, IList <String> languages, IList <String> fonts)
{
String result = null;
String pdfPath = null;
try {
pdfPath = GetTargetDirectory() + GetImageName(file.FullName, languages) + ".pdf";
DoOcrAndSavePdfToPath(tesseractReader, file.FullName, pdfPath, languages, fonts);
result = GetTextFromPdfLayer(pdfPath, null, page);
}
catch (System.IO.IOException e) {
LOGGER.Error(e.Message);
}
return(result);
}
/// <summary>
/// Perform OCR using provided path to image (imgPath),
/// save to file and get text from file.
/// </summary>
protected internal virtual String GetRecognizedTextFromTextFile(AbstractTesseract4OcrEngine tesseractReader
, String input, IList <String> languages)
{
String result = null;
String txtPath = null;
try {
txtPath = GetTargetDirectory() + GetImageName(input, languages) + ".txt";
DoOcrAndSaveToTextFile(tesseractReader, input, txtPath, languages);
result = GetTextFromTextFile(new FileInfo(txtPath));
}
catch (Exception e) {
LOGGER.Error(e.Message);
}
return(result);
}
/// <summary>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// </summary>
/// <remarks>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// (Method is used for compare tool)
/// </remarks>
protected internal virtual void DoOcrAndSavePdfToPath(AbstractTesseract4OcrEngine tesseractReader, String
imgPath, String pdfPath, IList <String> languages, IList <String> fonts, Color color)
{
if (languages != null)
{
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetLanguages(languages);
tesseractReader.SetTesseract4OcrEngineProperties(properties);
}
OcrPdfCreatorProperties properties_1 = new OcrPdfCreatorProperties();
properties_1.SetPdfLang("en-US");
properties_1.SetTitle("");
if (fonts != null && fonts.Count > 0)
{
FontProvider fontProvider = new FontProvider();
foreach (String fontPath in fonts)
{
String name = FONT_PATH_TO_FONT_NAME_MAP.Get(fontPath);
fontProvider.GetFontSet().AddFont(fontPath, PdfEncodings.IDENTITY_H, name);
}
properties_1.SetFontProvider(fontProvider);
}
if (color != null)
{
properties_1.SetTextColor(color);
}
if (languages != null)
{
NUnit.Framework.Assert.AreEqual(languages.Count, tesseractReader.GetTesseract4OcrEngineProperties().GetLanguages
().Count);
}
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader, properties_1);
try {
using (PdfWriter pdfWriter = GetPdfWriter(pdfPath)) {
PdfDocument doc = ocrPdfCreator.CreatePdf(JavaCollectionsUtil.SingletonList <FileInfo>(new FileInfo(imgPath
)), pdfWriter);
NUnit.Framework.Assert.IsNotNull(doc);
doc.Close();
}
}
catch (System.IO.IOException e) {
LOGGER.Error(e.Message);
}
}
/// <summary>
/// Perform OCR using provided path to image (imgPath)
/// and save result to text file.
/// </summary>
protected internal virtual void DoOcrAndSaveToTextFile(AbstractTesseract4OcrEngine tesseractReader, String
imgPath, String txtPath, IList <String> languages)
{
if (languages != null)
{
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetLanguages(languages);
tesseractReader.SetTesseract4OcrEngineProperties(properties);
}
tesseractReader.CreateTxtFile(JavaCollectionsUtil.SingletonList <FileInfo>(new FileInfo(imgPath)), new FileInfo
(txtPath));
if (languages != null)
{
NUnit.Framework.Assert.AreEqual(languages.Count, tesseractReader.GetTesseract4OcrEngineProperties().GetLanguages
().Count);
}
}
private static void DoImageToPdfAOcr(AbstractTesseract4OcrEngine tesseractReader, IList <FileInfo> imageFiles
)
{
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader, new OcrPdfCreatorProperties().SetPdfLang(
"en-US"));
Stream @is = null;
try {
@is = new FileStream(PROFILE_FOLDER + "sRGB_CS_profile.icm", FileMode.Open, FileAccess.Read);
}
catch (FileNotFoundException) {
}
// No expected
PdfOutputIntent outputIntent = new PdfOutputIntent("Custom", "", "http://www.color.org", "sRGB IEC61966-2.1"
, @is);
ocrPdfCreator.CreatePdfA(imageFiles, new PdfWriter(new MemoryStream()), outputIntent);
}
/// <summary>Retrieve text from specified page from given PDF document.</summary>
protected internal virtual String GetTextFromPdf(AbstractTesseract4OcrEngine tesseractReader, FileInfo file
, int page, IList <String> languages, String fontPath)
{
return(GetTextFromPdf(tesseractReader, file, page, languages, JavaCollectionsUtil.SingletonList <String>(fontPath
)));
}
private static void DoImageOcr(AbstractTesseract4OcrEngine tesseractReader, FileInfo imageFile)
{
tesseractReader.DoImageOcr(imageFile);
}
public ImageFormatIntegrationTest(IntegrationTestHelper.ReaderType type)
{
tesseractReader = GetTesseractReader(type);
this.testType = type.ToString().ToLowerInvariant();
}
public MultiThreadingTest(IntegrationTestHelper.ReaderType type)
{
tesseractReader = GetTesseractReader(type);
}
/// <summary>Retrieve text from the first page of given PDF document setting font.</summary>
protected internal virtual String GetTextFromPdf(AbstractTesseract4OcrEngine tesseractReader, FileInfo file
, IList <String> languages, String fontPath)
{
return(GetTextFromPdf(tesseractReader, file, 1, languages, fontPath));
}
/// <summary>
/// Perform OCR using provided path to image (imgPath),
/// save to file and get text from file.
/// </summary>
protected internal virtual String GetRecognizedTextFromTextFile(AbstractTesseract4OcrEngine tesseractReader
, String input)
{
return(GetRecognizedTextFromTextFile(tesseractReader, input, null));
}
/// <summary>Retrieve text from the first page of given PDF document.</summary>
protected internal virtual String GetTextFromPdf(AbstractTesseract4OcrEngine tesseractReader, FileInfo file
)
{
return(GetTextFromPdf(tesseractReader, file, 1, null, new List <String>()));
}
/// <summary>Retrieve text from the required page of given PDF document.</summary>
protected internal virtual String GetTextFromPdf(AbstractTesseract4OcrEngine tesseractReader, FileInfo file
, int page, IList <String> languages)
{
return(GetTextFromPdf(tesseractReader, file, page, languages, new List <String>()));
}
public BasicTesseractIntegrationTest(IntegrationTestHelper.ReaderType type)
{
tesseractReader = GetTesseractReader(type);
}
/// <summary>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// </summary>
/// <remarks>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// (Text will be invisible)
/// </remarks>
protected internal virtual void DoOcrAndSavePdfToPath(AbstractTesseract4OcrEngine tesseractReader, String
imgPath, String pdfPath, IList <String> languages, IList <String> fonts)
{
DoOcrAndSavePdfToPath(tesseractReader, imgPath, pdfPath, languages, fonts, null);
}
public PdfA3UIntegrationTest(IntegrationTestHelper.ReaderType type)
{
tesseractReader = GetTesseractReader(type);
}
/// <summary>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// </summary>
/// <remarks>
/// Perform OCR using provided path to image (imgPath)
/// and save result PDF document to "pdfPath".
/// (Method is used for compare tool)
/// </remarks>
protected internal virtual void DoOcrAndSavePdfToPath(AbstractTesseract4OcrEngine tesseractReader, String
imgPath, String pdfPath)
{
DoOcrAndSavePdfToPath(tesseractReader, imgPath, pdfPath, null, null, null);
}
