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! ;-)
}
}
private static opennlp.tools.parser.ParserModel OpenJavaModel(string fileName)
{
java.io.FileInputStream inputStream = null;
try {
inputStream = OpenNLP.OpenInputStream(fileName);
return(new opennlp.tools.parser.ParserModel(inputStream));
} finally {
inputStream?.close();
}
}
private static opennlp.tools.chunker.ChunkSampleStream JavaSampleStream()
{
return(new opennlp.tools.chunker.ChunkSampleStream(
// we don't care about warnings on java
#pragma warning disable 612
new opennlp.tools.util.PlainTextByLineStream(
OpenNLP.OpenInputStream("opennlp/tools/chunker/test.txt"), "utf-8")));
#pragma warning restore 612
}
//
// DO NOT USE THIS TESTS AS SAMPLES TO BUILD YOUR STUFF !
//
// I use some things here, that are not needed in a "real" implementation
//
private static opennlp.tools.tokenize.TokenizerModel OpenJavaModel(string fileName)
{
java.io.FileInputStream inputStream = null;
try {
inputStream = OpenNLP.OpenInputStream(fileName);
return(new opennlp.tools.tokenize.TokenizerModel(inputStream));
} finally {
if (inputStream != null)
{
inputStream.close();
}
}
}
public void TestCrossCompatibility()
{
using (var data = Tests.OpenFile("/opennlp/tools/tokenize/token.train")) {
var samples = new TokenSampleStream(new PlainTextByLineStream(data));
var mlParams = new TrainingParameters();
mlParams.Set(Parameters.Iterations, "100");
mlParams.Set(Parameters.Cutoff, "0");
var model = TokenizerME.Train(samples, new TokenizerFactory("en", null, true), mlParams);
var sMe = new TokenizerME(model);
TokenizerMETest.TestTokenizer(sMe);
var sProbs = sMe.TokenProbabilities;
// --- java \/
var sFile = Path.GetTempFileName();
model.Serialize(new FileStream(sFile, FileMode.Create));
var jModel = new opennlp.tools.tokenize.TokenizerModel(
OpenNLP.CreateInputStream(sFile)
);
var jMe = new opennlp.tools.tokenize.TokenizerME(jModel);
TestJavaTokenizer(jMe);
var jProbs = jMe.getTokenProbabilities();
Assert.AreEqual(jProbs.Length, sProbs.Length);
for (int i = 0; i < jProbs.Length; i++)
{
// one difference :(
// -0.00000000000000011102230246251565
//
// but still "insignificant" :)
Assert.AreEqual(jProbs[i], sProbs[i], 0.0000000001d);
}
}
}
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 static JavaModel OpenJavaModel()
{
return(new JavaModel(OpenNLP.OpenInputStream("opennlp/models/en-sent.bin")));
}
private static opennlp.tools.chunker.ChunkSampleStream JavaSampleStream()
{
return(new opennlp.tools.chunker.ChunkSampleStream(
new opennlp.tools.util.PlainTextByLineStream(
OpenNLP.OpenInputStream("opennlp/tools/chunker/test.txt"), "utf-8")));
}
private static JavaModel OpenJavaModel()
{
return(new JavaModel(OpenNLP.OpenInputStream(ModeFile)));
}