public virtual void TestIncorrectLanguageForUserWordsAsList()
{
NUnit.Framework.Assert.That(() => {
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetUserWords("eng1", JavaUtil.ArraysAsList("word1", "word2"));
properties.SetLanguages(new List <String>());
}
, NUnit.Framework.Throws.InstanceOf <Tesseract4OcrException>().With.Message.EqualTo(MessageFormatUtil.Format(Tesseract4OcrException.LANGUAGE_IS_NOT_IN_THE_LIST, "eng1")))
;
}
public virtual void TestUserWordsWithLanguageNotInList()
{
NUnit.Framework.Assert.That(() => {
String userWords = TEST_DOCUMENTS_DIRECTORY + "userwords.txt";
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetUserWords("spa", new FileStream(userWords, FileMode.Open, FileAccess.Read));
properties.SetLanguages(new List <String>());
}
, NUnit.Framework.Throws.InstanceOf <Tesseract4OcrException>().With.Message.EqualTo(MessageFormatUtil.Format(Tesseract4OcrException.LANGUAGE_IS_NOT_IN_THE_LIST, "spa")))
;
}
public virtual void TestUserWordsWithDefaultLanguageNotInList()
{
String userWords = TEST_DOCUMENTS_DIRECTORY + "userwords.txt";
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetUserWords("eng", new FileStream(userWords, FileMode.Open, FileAccess.Read));
properties.SetLanguages(new List <String>());
tesseractReader.SetTesseract4OcrEngineProperties(properties);
String imgPath = TEST_IMAGES_DIRECTORY + "numbers_01.jpg";
String expectedOutput = "619121";
String result = GetRecognizedTextFromTextFile(tesseractReader, imgPath);
NUnit.Framework.Assert.IsTrue(result.StartsWith(expectedOutput));
}
public virtual void TestCustomUserWords()
{
String imgPath = TEST_IMAGES_DIRECTORY + "wierdwords.png";
IList <String> userWords = JavaUtil.ArraysAsList("he23llo", "qwetyrtyqpwe-rty");
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetLanguages(JavaUtil.ArraysAsList("fra"));
properties.SetUserWords("fra", userWords);
tesseractReader.SetTesseract4OcrEngineProperties(properties);
String result = GetRecognizedTextFromTextFile(tesseractReader, imgPath);
NUnit.Framework.Assert.IsTrue(result.Contains(userWords[0]) || result.Contains(userWords[1]));
NUnit.Framework.Assert.IsTrue(tesseractReader.GetTesseract4OcrEngineProperties().GetPathToUserWordsFile().
EndsWith(".user-words"));
}
public virtual void TestCustomUserWordsWithListOfLanguages()
{
String imgPath = TEST_IMAGES_DIRECTORY + "bogusText.jpg";
String expectedOutput = "B1adeb1ab1a";
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetLanguages(JavaUtil.ArraysAsList("fra", "eng"));
properties.SetUserWords("eng", JavaUtil.ArraysAsList("b1adeb1ab1a"));
tesseractReader.SetTesseract4OcrEngineProperties(properties);
String result = GetRecognizedTextFromTextFile(tesseractReader, imgPath);
result = result.Replace("\n", "").Replace("\f", "");
result = iText.IO.Util.StringUtil.ReplaceAll(result, "[^\\u0009\\u000A\\u000D\\u0020-\\u007E]", "");
NUnit.Framework.Assert.IsTrue(result.StartsWith(expectedOutput));
NUnit.Framework.Assert.IsTrue(tesseractReader.GetTesseract4OcrEngineProperties().GetPathToUserWordsFile().
EndsWith(".user-words"));
}