OPENNLP-1532 Conduct cleanup in existing test code

Author: mawiesne

opennlp-tools/src/test/java/opennlp/tools/chunker/ChunkerFactoryTest.java

@@ -57,8 +57,8 @@ void testDefaultFactory() throws IOException {
     ChunkerModel model = trainModel(ModelType.MAXENT, new ChunkerFactory());
 
     ChunkerFactory factory = model.getFactory();
-    Assertions.assertTrue(factory.getContextGenerator() instanceof DefaultChunkerContextGenerator);
-    Assertions.assertTrue(factory.getSequenceValidator() instanceof DefaultChunkerSequenceValidator);
+    Assertions.assertInstanceOf(DefaultChunkerContextGenerator.class, factory.getContextGenerator());
+    Assertions.assertInstanceOf(DefaultChunkerSequenceValidator.class, factory.getSequenceValidator());
 
     ByteArrayOutputStream out = new ByteArrayOutputStream();
     model.serialize(out);
@@ -67,8 +67,8 @@ void testDefaultFactory() throws IOException {
     ChunkerModel fromSerialized = new ChunkerModel(in);
 
     factory = fromSerialized.getFactory();
-    Assertions.assertTrue(factory.getContextGenerator() instanceof DefaultChunkerContextGenerator);
-    Assertions.assertTrue(factory.getSequenceValidator() instanceof DefaultChunkerSequenceValidator);
+    Assertions.assertInstanceOf(DefaultChunkerContextGenerator.class, factory.getContextGenerator());
+    Assertions.assertInstanceOf(DefaultChunkerSequenceValidator.class, factory.getSequenceValidator());
   }
 
 
@@ -78,10 +78,10 @@ void testDummyFactory() throws IOException {
     ChunkerModel model = trainModel(ModelType.MAXENT, new DummyChunkerFactory());
 
     DummyChunkerFactory factory = (DummyChunkerFactory) model.getFactory();
-    Assertions.assertTrue(factory.getContextGenerator()
-        instanceof DummyChunkerFactory.DummyContextGenerator);
-    Assertions.assertTrue(factory.getSequenceValidator()
-        instanceof DummyChunkerFactory.DummySequenceValidator);
+    Assertions.assertInstanceOf(DummyChunkerFactory.DummyContextGenerator.class,
+            factory.getContextGenerator());
+    Assertions.assertInstanceOf(DummyChunkerFactory.DummySequenceValidator.class,
+            factory.getSequenceValidator());
 
 
     ByteArrayOutputStream out = new ByteArrayOutputStream();
@@ -91,10 +91,8 @@ void testDummyFactory() throws IOException {
     ChunkerModel fromSerialized = new ChunkerModel(in);
 
     factory = (DummyChunkerFactory) fromSerialized.getFactory();
-    Assertions.assertTrue(factory.getContextGenerator()
-        instanceof DefaultChunkerContextGenerator);
-    Assertions.assertTrue(factory.getSequenceValidator()
-        instanceof DefaultChunkerSequenceValidator);
+    Assertions.assertInstanceOf(DefaultChunkerContextGenerator.class, factory.getContextGenerator());
+    Assertions.assertInstanceOf(DefaultChunkerSequenceValidator.class, factory.getSequenceValidator());
 
 
     ChunkerME chunker = new ChunkerME(model);

opennlp-tools/src/test/java/opennlp/tools/chunker/DummyChunkSampleStream.java

@@ -74,7 +74,7 @@ public ChunkSample read() throws IOException {
       count++;
     }
 
-    if (toks.size() > 0) {
+    if (!toks.isEmpty()) {
       if (mIsPredicted) {
         return new ChunkSample(toks.toArray(new String[0]),
             posTags.toArray(new String[0]),

opennlp-tools/src/test/java/opennlp/tools/cmdline/TokenNameFinderToolTest.java

@@ -69,10 +69,10 @@ void run() throws IOException {
     TokenNameFinderTool tool = new TokenNameFinderTool();
     tool.run(args);
 
-    final String content = new String(baos.toByteArray(), StandardCharsets.UTF_8);
+    final String content = baos.toString(StandardCharsets.UTF_8);
     Assertions.assertTrue(content.contains("It is <START:person> Stefanie Schmidt. <END>"));
 
-    model1.delete();
+    Assertions.assertTrue(model1.delete());
   }
 
   @Test
@@ -106,7 +106,7 @@ void usage() {
     TokenNameFinderTool tool = new TokenNameFinderTool();
     tool.run(args);
 
-    final String content = new String(baos.toByteArray(), StandardCharsets.UTF_8);
+    final String content = baos.toString(StandardCharsets.UTF_8);
     Assertions.assertEquals(tool.getHelp(), content.trim());
 
   }

opennlp-tools/src/test/java/opennlp/tools/cmdline/tokenizer/TokenizerTrainerToolTest.java

@@ -96,7 +96,7 @@ public void testTestRunHappyCase() throws IOException {
 
     final String content = baos.toString(StandardCharsets.UTF_8);
     Assertions.assertTrue(content.contains("Number of Event Tokens: 171"));
-    model.delete();
+    Assertions.assertTrue(model.delete());
   }
 
   //TODO OPENNLP-1447

opennlp-tools/src/test/java/opennlp/tools/eval/AbstractEvalTest.java

@@ -26,7 +26,6 @@
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.security.MessageDigest;
-import java.util.Collections;
 import java.util.List;
 import java.util.stream.Collectors;
 
@@ -81,13 +80,11 @@ public static void verifyDirectoryChecksum(Path path, String extension, BigInteg
     MessageDigest digest = MessageDigest.getInstance(HASH_ALGORITHM);
 
     final List<Path> paths = Files.walk(path)
-        .filter(Files::isRegularFile)
-        .filter(p -> p.toString().endsWith(extension))
-        .collect(Collectors.toList());
+            .filter(Files::isRegularFile)
+            .filter(p -> p.toString().endsWith(extension)).sorted().collect(Collectors.toList());
 
     // Ensure the paths are in a consistent order when
     // verifying the file checksums.
-    Collections.sort(paths);
 
     for (Path p : paths) {
       try (InputStream in = new BufferedInputStream(Files.newInputStream(p))) {

opennlp-tools/src/test/java/opennlp/tools/eval/SourceForgeModelEval.java

@@ -24,7 +24,6 @@
 import java.security.MessageDigest;
 import java.util.ArrayList;
 import java.util.Arrays;
-import java.util.Collections;
 import java.util.List;
 import java.util.Objects;
 
@@ -92,7 +91,7 @@ private static class LeipzigTestSample {
 
     private LeipzigTestSample(String[] text) {
       Objects.requireNonNull(text, "text must not be null");
-      this.text = Collections.unmodifiableList(new ArrayList<>(Arrays.asList(text)));
+      this.text = List.of(text);
     }
 
     public String[] getText() {
@@ -110,7 +109,7 @@ public String toString() {
         sampleString.append(s).append(' ');
       }
 
-      if (sampleString.length() > 0) {
+      if (!sampleString.isEmpty()) {
         // remove last space
         sampleString.setLength(sampleString.length() - 1);
       }
@@ -151,7 +150,7 @@ public LeipzigTestSample read() throws IOException {
         count++;
       }
 
-      if (tokensList.size() > 0) {
+      if (!tokensList.isEmpty()) {
         return new LeipzigTestSample(tokensList.toArray(new String[0]));
       }
 

opennlp-tools/src/test/java/opennlp/tools/formats/brat/BratDocumentTest.java

@@ -54,7 +54,7 @@ void testDocumentWithEntitiesParsing() throws IOException {
   }
 
   private void checkNote(BratAnnotation annotation, String expectedCoveredText, String expectedNote) {
-    Assertions.assertTrue(annotation instanceof SpanAnnotation);
+    Assertions.assertInstanceOf(SpanAnnotation.class, annotation);
     SpanAnnotation spanAnn = (SpanAnnotation) annotation;
     Assertions.assertEquals(expectedCoveredText, spanAnn.getCoveredText());
     Assertions.assertEquals(expectedNote, spanAnn.getNote());

opennlp-tools/src/test/java/opennlp/tools/formats/masc/MascPOSSampleStreamTest.java

@@ -109,11 +109,10 @@ void train() {
       ObjectStream<POSSample> trainPOS = new MascPOSSampleStream(
           new MascDocumentStream(directory, true, fileFilter));
 
-      POSModel model = null;
       TrainingParameters trainingParameters = new TrainingParameters();
       trainingParameters.put(TrainingParameters.ITERATIONS_PARAM, 20);
 
-      model = POSTaggerME.train("en", trainPOS,
+      POSModel model = POSTaggerME.train("en", trainPOS,
           trainingParameters, new POSTaggerFactory());
 
       ObjectStream<POSSample> testPOS = new MascPOSSampleStream(

opennlp-tools/src/test/java/opennlp/tools/formats/masc/MascSentenceSampleStreamTest.java

@@ -126,11 +126,10 @@ void train() {
           new MascDocumentStream(directory,
               true, fileFilter), 1);
 
-      SentenceModel model = null;
       TrainingParameters trainingParameters = new TrainingParameters();
       trainingParameters.put(TrainingParameters.ITERATIONS_PARAM, 20);
 
-      model = SentenceDetectorME.train("en", trainSentences,
+      SentenceModel model = SentenceDetectorME.train("en", trainSentences,
           new SentenceDetectorFactory(), trainingParameters);
 
       ObjectStream<SentenceSample> testPOS = new MascSentenceSampleStream(

opennlp-tools/src/test/java/opennlp/tools/formats/masc/MascTokenSampleStreamTest.java

@@ -129,12 +129,11 @@ void train() {
       ObjectStream<TokenSample> trainTokens = new MascTokenSampleStream(
           new MascDocumentStream(directory, true, fileFilter));
 
-      TokenizerModel model = null;
       TrainingParameters trainingParameters = new TrainingParameters();
       trainingParameters.put(TrainingParameters.ITERATIONS_PARAM, 20);
 
-      model = TokenizerME.train(trainTokens, new TokenizerFactory("en", null, false, null),
-          trainingParameters);
+      TokenizerModel model = TokenizerME.train(trainTokens, new TokenizerFactory(
+              "en", null, false, null), trainingParameters);
 
       ObjectStream<TokenSample> testTokens = new MascTokenSampleStream(
           new MascDocumentStream(directory, true, fileFilter));

opennlp-tools/src/test/java/opennlp/tools/langdetect/DummyFactory.java

@@ -81,7 +81,7 @@ public String[] getContext(CharSequence document) {
 
         for (StringList tokenList : tokenNgramModel) {
           if (tokenList.size() > 0) {
-            context.add("tg=" + tokenList.toString());
+            context.add("tg=" + tokenList);
           }
         }
       }

opennlp-tools/src/test/java/opennlp/tools/langdetect/LanguageDetectorFactoryTest.java

@@ -62,14 +62,14 @@ static void train() throws Exception {
   void testCorrectFactory() throws IOException {
     LanguageDetectorModel myModel = new LanguageDetectorModel(new ByteArrayInputStream(serialized));
     Assertions.assertNotNull(myModel.getFactory());
-    Assertions.assertTrue(myModel.getFactory() instanceof LanguageDetectorFactory);
+    Assertions.assertInstanceOf(LanguageDetectorFactory.class, myModel.getFactory());
   }
 
   @Test
   void testDummyFactory() throws IOException {
     LanguageDetectorModel myModel = new LanguageDetectorModel(new ByteArrayInputStream(serialized));
     Assertions.assertNotNull(myModel.getFactory());
-    Assertions.assertTrue(myModel.getFactory() instanceof DummyFactory);
+    Assertions.assertInstanceOf(DummyFactory.class, myModel.getFactory());
   }
 
   @Test

opennlp-tools/src/test/java/opennlp/tools/languagemodel/NgramLanguageModelTest.java

@@ -23,7 +23,6 @@
 import java.nio.charset.StandardCharsets;
 import java.util.Arrays;
 import java.util.List;
-import java.util.stream.Collectors;
 
 import org.junit.jupiter.api.Assertions;
 import org.junit.jupiter.api.Test;
@@ -141,7 +140,7 @@ public void testTrigramLanguageModelCreationFromText() throws Exception {
 
     try (InputStream is = getClass().getResourceAsStream("/opennlp/tools/languagemodel/sentences.txt");
          BufferedReader reader = new BufferedReader(new InputStreamReader(is, StandardCharsets.UTF_8))) {
-      for (String line : reader.lines().collect(Collectors.toList())) {
+      for (String line : reader.lines().toList()) {
         String[] array = line.split(" ");
         List<String> split = Arrays.asList(array);
         List<String> generatedStrings = NGramGenerator.generate(split, ngramSize, " ");

opennlp-tools/src/test/java/opennlp/tools/lemmatizer/DictionaryLemmatizerMultiTest.java

@@ -42,15 +42,7 @@ void testForNullPointerException() {
         "down", "the", "street");
     List<String> sentencePOS = Arrays.asList("DT", "NNS", "VBD", "VBG", "CC", "VBG", "RP", "DT", "NN");
     List<List<String>> expectedLemmas = new ArrayList<>();
-    expectedLemmas.add(Arrays.asList("the"));
-    expectedLemmas.add(Arrays.asList("dog"));
-    expectedLemmas.add(Arrays.asList("is"));
-    expectedLemmas.add(Arrays.asList("run,run"));
-    expectedLemmas.add(Arrays.asList("and"));
-    expectedLemmas.add(Arrays.asList("bark,bark"));
-    expectedLemmas.add(Arrays.asList("down"));
-    expectedLemmas.add(Arrays.asList("the"));
-    expectedLemmas.add(Arrays.asList("street"));
+    expectedLemmas.add(List.of("the", "dog", "is", "run,run", "and", "bark, bark", "down", "the", "street"));
 
     List<List<String>> actualLemmas = dictionaryLemmatizer.lemmatize(sentence, sentencePOS);
 

opennlp-tools/src/test/java/opennlp/tools/lemmatizer/DummyLemmaSampleStream.java

@@ -68,7 +68,7 @@ public LemmaSample read() throws IOException {
       count++;
     }
 
-    if (toks.size() > 0) {
+    if (!toks.isEmpty()) {
       if (mIsPredicted) {
         return new LemmaSample(toks.toArray(new String[0]),
             posTags.toArray(new String[0]),

opennlp-tools/src/test/java/opennlp/tools/ml/naivebayes/NaiveBayesPrepAttachTest.java

@@ -59,7 +59,7 @@ void testNaiveBayesOnPrepAttachData() throws IOException {
     testDataIndexer.index(trainingStream);
 
     MaxentModel model = new NaiveBayesTrainer().trainModel(testDataIndexer);
-    Assertions.assertTrue(model instanceof NaiveBayesModel);
+    Assertions.assertInstanceOf(NaiveBayesModel.class, model);
     PrepAttachDataUtil.testModel(model, 0.7897994553107205);
   }
 
@@ -71,7 +71,7 @@ void testNaiveBayesOnPrepAttachDataUsingTrainUtil() throws IOException {
 
     EventTrainer trainer = TrainerFactory.getEventTrainer(trainParams, null);
     MaxentModel model = trainer.train(trainingStream);
-    Assertions.assertTrue(model instanceof NaiveBayesModel);
+    Assertions.assertInstanceOf(NaiveBayesModel.class, model);
     PrepAttachDataUtil.testModel(model, 0.7897994553107205);
   }
 
@@ -83,7 +83,7 @@ void testNaiveBayesOnPrepAttachDataUsingTrainUtilWithCutoff5() throws IOExceptio
 
     EventTrainer trainer = TrainerFactory.getEventTrainer(trainParams, null);
     MaxentModel model = trainer.train(trainingStream);
-    Assertions.assertTrue(model instanceof NaiveBayesModel);
+    Assertions.assertInstanceOf(NaiveBayesModel.class, model);
     PrepAttachDataUtil.testModel(model, 0.7945035899975241);
   }
 }

opennlp-tools/src/test/java/opennlp/tools/namefind/BilouCodecTest.java

@@ -104,7 +104,7 @@ void testEncodeAdjacentUnitSpans() {
 
   @Test
   void testCreateSequenceValidator() {
-    Assertions.assertTrue(codec.createSequenceValidator() instanceof BilouNameFinderSequenceValidator);
+    Assertions.assertInstanceOf(BilouNameFinderSequenceValidator.class, codec.createSequenceValidator());
   }
 
   @Test

opennlp-tools/src/test/java/opennlp/tools/namefind/BioCodecTest.java

@@ -111,7 +111,7 @@ void testEncodeAdjacentSpans() {
 
   @Test
   void testCreateSequenceValidator() {
-    Assertions.assertTrue(codec.createSequenceValidator() instanceof NameFinderSequenceValidator);
+    Assertions.assertInstanceOf(NameFinderSequenceValidator.class, codec.createSequenceValidator());
   }