public void TestEverything()
{
using (var file = Tests.OpenFile("/opennlp/tools/sentdetect/Sentences.txt")) {
var mlParams = new TrainingParameters();
mlParams.Set(Parameters.Iterations, "100");
mlParams.Set(Parameters.Cutoff, "0");
var sdFactory = new SentenceDetectorFactory("en", true, null, null);
var stream = new SentenceSampleStream(new PlainTextByLineStream(file));
var model = SentenceDetectorME.Train("en", stream, sdFactory, mlParams);
Assert.AreEqual("en", model.Language);
Assert.AreEqual(model.UseTokenEnd, true);
var sMe = new SentenceDetectorME(model);
// test the SharpNL sentences
SentenceDetectorMETest.EvalSentences(sMe);
var sFile = Path.GetTempFileName();
model.Serialize(new FileStream(sFile, FileMode.Create));
var jModel2 = new JavaModel(OpenNLP.CreateInputStream(sFile));
var jMe = new JavaSDME(jModel2);
// test the Java OpenNLP sentences.
JavaEvalSentences(jMe);
// first try?! Yes! ;-)
}
}
public void SentenceDetection()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-sent.bin"));
var model = new opennlp.tools.sentdetect.SentenceModel(modelIn);
var sentenceDetector = new opennlp.tools.sentdetect.SentenceDetectorME(model);
var sentences = sentenceDetector.sentDetect(" First sentence. Second sentence. ");
System.Console.WriteLine(string.Join(";", sentences));
Assert.AreEqual(2, sentences.Length);
}
public void TestCrossCompatibility()
{
var jModel = OpenJavaModel();
var sModel = OpenSharpModel();
var jFile = Path.GetTempFileName();
var sFile = Path.GetTempFileName();
var jFileStream = OpenNLP.CreateOutputStream(jFile);
jModel.serialize(jFileStream);
jFileStream.close();
sModel.Serialize(new FileStream(sFile, FileMode.Create));
// now java opens the csharp model and vice versa :)
var jModel2 = new JavaModel(OpenNLP.CreateInputStream(sFile));
var sModel2 = new SharpModel(jFile);
Assert.Null(jModel2.getAbbreviations());
Assert.Null(sModel2.Abbreviations);
Assert.Null(jModel2.getEosCharacters());
Assert.Null(sModel2.EosCharacters);
Assert.AreEqual(jModel2.useTokenEnd(), sModel2.UseTokenEnd);
var jFactory2 = jModel2.getFactory();
var sFactory2 = sModel2.Factory;
Assert.AreEqual(jFactory2.isUseTokenEnd(), sFactory2.UseTokenEnd);
Assert.AreEqual(jFactory2.getLanguageCode(), sFactory2.LanguageCode);
Assert.True(true);
}
public void TestEverything() {
using (var file = Tests.OpenFile("/opennlp/tools/sentdetect/Sentences.txt")) {
var mlParams = new TrainingParameters();
mlParams.Set(Parameters.Iterations, "100");
mlParams.Set(Parameters.Cutoff, "0");
var sdFactory = new SentenceDetectorFactory("en", true, null, null);
var stream = new SentenceSampleStream(new PlainTextByLineStream(file));
var model = SentenceDetectorME.Train("en", stream, sdFactory, mlParams);
Assert.AreEqual("en", model.Language);
Assert.AreEqual(model.UseTokenEnd, true);
var sMe = new SentenceDetectorME(model);
// test the SharpNL sentences
SentenceDetectorMETest.EvalSentences(sMe);
var sFile = Path.GetTempFileName();
model.Serialize(new FileStream(sFile, FileMode.Create));
var jModel2 = new JavaModel(OpenNLP.CreateInputStream(sFile));
var jMe = new JavaSDME(jModel2);
// test the Java OpenNLP sentences.
JavaEvalSentences(jMe);
// first try?! Yes! ;-)
}
}
public void TestCrossCompatibility() {
var jModel = OpenJavaModel();
var sModel = OpenSharpModel();
var jFile = Path.GetTempFileName();
var sFile = Path.GetTempFileName();
var jFileStream = OpenNLP.CreateOutputStream(jFile);
jModel.serialize(jFileStream);
jFileStream.close();
sModel.Serialize(new FileStream(sFile, FileMode.Create));
// now java opens the csharp model and vice versa :)
var jModel2 = new JavaModel(OpenNLP.CreateInputStream(sFile));
var sModel2 = new SharpModel(jFile);
Assert.Null(jModel2.getAbbreviations());
Assert.Null(sModel2.Abbreviations);
Assert.Null(jModel2.getEosCharacters());
Assert.Null(sModel2.EosCharacters);
Assert.AreEqual(jModel2.useTokenEnd(), sModel2.UseTokenEnd);
var jFactory2 = jModel2.getFactory();
var sFactory2 = sModel2.Factory;
Assert.AreEqual(jFactory2.isUseTokenEnd(), sFactory2.UseTokenEnd);
Assert.AreEqual(jFactory2.getLanguageCode(), sFactory2.LanguageCode);
Assert.True(true);
}
private opennlp.tools.sentdetect.SentenceDetectorME prepareSentenceDetector()
{
java.io.FileInputStream sentModelStream = new java.io.FileInputStream(sentenceModelPath); //load the sentence model into a stream
opennlp.tools.sentdetect.SentenceModel sentModel = new opennlp.tools.sentdetect.SentenceModel(sentModelStream);// load the model
return new opennlp.tools.sentdetect.SentenceDetectorME(sentModel); //create sentence detector
}
