OPENNLP-1588 Clean out deprecated code marked for removal

- removes deprecated getters in several records
- removes a very long time deprecated constructor of TokenizerME
- removes deprecated field in DefaultNameContextGenerator and adapts tests accordingly
- marks a constructor of ADNameSampleStream as "for removal" to indicate actual removal is more likely in upcoming releases
- marks deprecated 'NameFinderEventStream#generateOutcomes(..)' as "for removal" to indicate actual removal is more likely in upcoming releases
- clears unused code from NameFinderME
- fixes resource leak in TokenNameFinderFactory

opennlp-dl/src/main/java/opennlp/dl/SpanEnd.java

@@ -19,16 +19,6 @@
 
 public record SpanEnd(int index, int characterEnd) {
 
-  @Deprecated(forRemoval = true)
-  public int getIndex() {
-    return index;
-  }
-
-  @Deprecated(forRemoval = true)
-  public int getCharacterEnd() {
-    return characterEnd;
-  }
-
   @Override
   public String toString() {
     return "index: " + index + "; character end: " + characterEnd;

opennlp-dl/src/main/java/opennlp/dl/Tokens.java

@@ -27,23 +27,4 @@
  */
 public record Tokens(String[] tokens, long[] ids, long[] mask, long[] types) {
 
-  @Deprecated(forRemoval = true)
-  public String[] getTokens() {
-    return tokens;
-  }
-
-  @Deprecated(forRemoval = true)
-  public long[] getIds() {
-    return ids;
-  }
-
-  @Deprecated(forRemoval = true)
-  public long[] getMask() {
-    return mask;
-  }
-
-  @Deprecated(forRemoval = true)
-  public long[] getTypes() {
-    return types;
-  }
 }

opennlp-tools/src/main/java/opennlp/tools/dictionary/serializer/Entry.java

@@ -31,13 +31,4 @@
  */
 public record Entry(StringList tokens, Attributes attributes) {
 
-  @Deprecated(forRemoval = true)
-  public StringList getTokens() {
-    return tokens;
-  }
-
-  @Deprecated(forRemoval = true)
-  public Attributes getAttributes() {
-    return attributes;
-  }
 }

opennlp-tools/src/main/java/opennlp/tools/formats/ad/ADNameSampleStream.java

@@ -184,7 +184,7 @@ public ADNameSampleStream(ObjectStream<String> lineStream, boolean splitHyphenat
    * @param splitHyphenatedTokens If {@code true} hyphenated tokens will be separated:
    *                              "carros-monstro" &gt; "carros" "-" "monstro".
    */
-  @Deprecated
+  @Deprecated(forRemoval = true)
   public ADNameSampleStream(InputStreamFactory in, String charsetName,
       boolean splitHyphenatedTokens) throws IOException {
     this(new PlainTextByLineStream(in, charsetName), splitHyphenatedTokens);

opennlp-tools/src/main/java/opennlp/tools/langdetect/LanguageSample.java

@@ -17,6 +17,7 @@
 
 package opennlp.tools.langdetect;
 
+import java.io.Serial;
 import java.io.Serializable;
 import java.util.Objects;
 
@@ -25,23 +26,14 @@
  */
 public record LanguageSample(Language language, CharSequence context) implements Serializable {
 
-  private static final long serialVersionUID = -2222893493240468729L;
+  @Serial
+  private static final long serialVersionUID = -4791295976215940258L;
 
   public LanguageSample(Language language, CharSequence context) {
     this.language = Objects.requireNonNull(language, "language must not be null");
     this.context = Objects.requireNonNull(context, "context must not be null");
   }
 
-  @Deprecated(forRemoval = true)
-  public Language getLanguage() {
-    return language;
-  }
-
-  @Deprecated(forRemoval = true)
-  public CharSequence getContext() {
-    return context;
-  }
-
   @Override
   public String toString() {
     return language.getLang() + '\t' + context;

opennlp-tools/src/main/java/opennlp/tools/langdetect/ProbingLanguageDetectionResult.java

@@ -25,13 +25,4 @@
  */
 public record ProbingLanguageDetectionResult(Language[] languages, int length) {
 
-  @Deprecated(forRemoval = true)
-  public Language[] getLanguages() {
-    return languages;
-  }
-
-  @Deprecated(forRemoval = true)
-  public int getLength() {
-    return length;
-  }
 }

opennlp-tools/src/main/java/opennlp/tools/namefind/DefaultNameContextGenerator.java

@@ -19,16 +19,10 @@
 
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Objects;
 
 import opennlp.tools.util.featuregen.AdaptiveFeatureGenerator;
-import opennlp.tools.util.featuregen.BigramNameFeatureGenerator;
-import opennlp.tools.util.featuregen.CachedFeatureGenerator;
 import opennlp.tools.util.featuregen.FeatureGeneratorUtil;
-import opennlp.tools.util.featuregen.OutcomePriorFeatureGenerator;
-import opennlp.tools.util.featuregen.PreviousMapFeatureGenerator;
-import opennlp.tools.util.featuregen.TokenClassFeatureGenerator;
-import opennlp.tools.util.featuregen.TokenFeatureGenerator;
-import opennlp.tools.util.featuregen.WindowFeatureGenerator;
 
 /**
  * A {@link NameContextGenerator} implementation for determining contextual features
@@ -38,31 +32,15 @@ public class DefaultNameContextGenerator implements NameContextGenerator {
 
   protected AdaptiveFeatureGenerator[] featureGenerators;
 
-  @Deprecated
-  private static final AdaptiveFeatureGenerator WINDOW_FEATURES = new CachedFeatureGenerator(
-      new WindowFeatureGenerator(new TokenFeatureGenerator(), 2, 2),
-      new WindowFeatureGenerator(new TokenClassFeatureGenerator(true), 2, 2),
-      new OutcomePriorFeatureGenerator(),
-      new PreviousMapFeatureGenerator(),
-      new BigramNameFeatureGenerator());
-
   /**
    * Creates a name context generator with the specified
    * {@link AdaptiveFeatureGenerator feature generators}.
    *
    * @param featureGenerators One or more {@link AdaptiveFeatureGenerator feature generators}.
-   *                          If none are provided, a default config ({@link #WINDOW_FEATURES})
-   *                          will be used.
    */
   public DefaultNameContextGenerator(AdaptiveFeatureGenerator... featureGenerators) {
-
-    if (featureGenerators != null) {
-      this.featureGenerators = featureGenerators;
-    }
-    else { // use defaults
-      this.featureGenerators =
-          new AdaptiveFeatureGenerator[]{WINDOW_FEATURES, new PreviousMapFeatureGenerator()};
-    }
+    this.featureGenerators = Objects.requireNonNull(
+            featureGenerators, "Please specify at least one featureGenerator");
   }
 
   @Override

opennlp-tools/src/main/java/opennlp/tools/namefind/NameFinderEventStream.java

@@ -83,7 +83,7 @@ public NameFinderEventStream(ObjectStream<NameSample> dataStream, String type,
    *
    * @deprecated use the {@link BioCodec} implementation of the SequenceValidator instead!
    */
-  @Deprecated
+  @Deprecated(forRemoval = true)
   public static String[] generateOutcomes(Span[] names, String type, int length) {
     String[] outcomes = new String[length];
     Arrays.fill(outcomes, NameFinderME.OTHER);

opennlp-tools/src/main/java/opennlp/tools/namefind/NameFinderME.java

@@ -17,7 +17,6 @@
 
 package opennlp.tools.namefind;
 
-import java.io.ByteArrayInputStream;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Collections;
@@ -44,9 +43,7 @@
 import opennlp.tools.util.SequenceValidator;
 import opennlp.tools.util.Span;
 import opennlp.tools.util.TrainingParameters;
-import opennlp.tools.util.featuregen.AdaptiveFeatureGenerator;
 import opennlp.tools.util.featuregen.AdditionalContextFeatureGenerator;
-import opennlp.tools.util.featuregen.GeneratorFactory;
 import opennlp.tools.util.featuregen.WindowFeatureGenerator;
 
 /**
@@ -92,26 +89,6 @@ public NameFinderME(TokenNameFinderModel model) {
             new WindowFeatureGenerator(additionalContextFeatureGenerator, 8, 8));
   }
 
-  private static AdaptiveFeatureGenerator createFeatureGenerator(
-          byte[] generatorDescriptor, final Map<String, Object> resources)
-          throws IOException {
-    AdaptiveFeatureGenerator featureGenerator;
-
-    if (generatorDescriptor != null) {
-      featureGenerator = GeneratorFactory.create(new ByteArrayInputStream(
-          generatorDescriptor), key -> {
-            if (resources != null) {
-              return resources.get(key);
-            }
-            return null;
-          });
-    } else {
-      featureGenerator = null;
-    }
-
-    return featureGenerator;
-  }
-
   @Override
   public Span[] find(String[] tokens) {
     return find(tokens, EMPTY);

opennlp-tools/src/main/java/opennlp/tools/namefind/TokenNameFinderFactory.java

@@ -248,11 +248,8 @@ public AdaptiveFeatureGenerator createFeatureGenerators() {
       featureGeneratorBytes = loadDefaultFeatureGeneratorBytes();
     }
 
-    InputStream descriptorIn = new ByteArrayInputStream(featureGeneratorBytes);
-
-    AdaptiveFeatureGenerator generator;
-    try {
-      generator = GeneratorFactory.create(descriptorIn, key -> {
+    try (InputStream descriptorIn = new ByteArrayInputStream(featureGeneratorBytes)) {
+      return GeneratorFactory.create(descriptorIn, key -> {
         if (artifactProvider != null) {
           return artifactProvider.getArtifact(key);
         }
@@ -273,11 +270,10 @@ public AdaptiveFeatureGenerator createFeatureGenerators() {
       // throwing a Runtime Exception is reasonable
 
       throw new FeatureGeneratorCreationError(e);
-    } catch (IOException e) {
+    }
+    catch (IOException e) {
       throw new IllegalStateException("Reading from mem cannot result in an I/O error", e);
     }
-
-    return generator;
   }
 
   /**

opennlp-tools/src/main/java/opennlp/tools/tokenize/TokenizerME.java

@@ -19,19 +19,16 @@
 
 import java.io.IOException;
 import java.util.ArrayList;
-import java.util.Collections;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
-import java.util.Set;
 import java.util.regex.Pattern;
 
 import opennlp.tools.dictionary.Dictionary;
 import opennlp.tools.ml.EventTrainer;
 import opennlp.tools.ml.TrainerFactory;
 import opennlp.tools.ml.model.Event;
 import opennlp.tools.ml.model.MaxentModel;
-import opennlp.tools.tokenize.lang.Factory;
 import opennlp.tools.util.DownloadUtil;
 import opennlp.tools.util.ObjectStream;
 import opennlp.tools.util.Span;
@@ -143,33 +140,6 @@ public TokenizerME(TokenizerModel model) {
     tokProbs = new ArrayList<>(50);
   }
 
-  /**
-   * @deprecated use {@link TokenizerFactory} to extend the Tokenizer
-   *             functionality
-   */
-  @Deprecated
-  public TokenizerME(TokenizerModel model, Factory factory) {
-    String languageCode = model.getLanguage();
-
-    this.alphanumeric = factory.getAlphanumeric(languageCode);
-    this.cg = factory.createTokenContextGenerator(languageCode,
-        getAbbreviations(model.getAbbreviations()));
-
-    this.model = model.getMaxentModel();
-    useAlphaNumericOptimization = model.useAlphaNumericOptimization();
-
-    abbDict = model.getAbbreviations();
-    newTokens = new ArrayList<>();
-    tokProbs = new ArrayList<>(50);
-  }
-
-  private static Set<String> getAbbreviations(Dictionary abbreviations) {
-    if (abbreviations == null) {
-      return Collections.emptySet();
-    }
-    return abbreviations.asStringSet();
-  }
-
   /**
    * @return the probabilities associated with the most recent calls to
    *         {@link TokenizerME#tokenize(String)} or {@link TokenizerME#tokenizePos(String)}.

opennlp-tools/src/main/java/opennlp/tools/util/TokenTag.java

@@ -32,21 +32,6 @@ public TokenTag(String token, String tag, String[] additionalData) {
     }
   }
 
-  @Deprecated(forRemoval = true)
-  public String getToken() {
-    return token;
-  }
-
-  @Deprecated(forRemoval = true)
-  public String getTag() {
-    return tag;
-  }
-
-  @Deprecated(forRemoval = true)
-  public String[] getAdditionalData() {
-    return additionalData;
-  }
-
   public static String[] extractTokens(TokenTag[] tuples) {
     String[] tokens = new String[tuples.length];
     for (int i = 0; i < tuples.length; i++) {

opennlp-tools/src/test/java/opennlp/tools/ml/model/TwoPassDataIndexerTest.java

@@ -23,15 +23,14 @@
 import org.junit.jupiter.api.Assertions;
 import org.junit.jupiter.api.Test;
 
-import opennlp.tools.namefind.DefaultNameContextGenerator;
 import opennlp.tools.namefind.NameContextGenerator;
 import opennlp.tools.namefind.NameFinderEventStream;
 import opennlp.tools.namefind.NameSample;
+import opennlp.tools.namefind.TokenNameFinderFactory;
 import opennlp.tools.util.ObjectStream;
 import opennlp.tools.util.ObjectStreamUtils;
 import opennlp.tools.util.Span;
 import opennlp.tools.util.TrainingParameters;
-import opennlp.tools.util.featuregen.AdaptiveFeatureGenerator;
 
 public class TwoPassDataIndexerTest {
 
@@ -74,8 +73,7 @@ void testIndexWithNewline() throws IOException {
 
     String[] sentence = "He belongs to Apache \n Software Foundation .".split(" ");
 
-    NameContextGenerator CG = new DefaultNameContextGenerator(
-        (AdaptiveFeatureGenerator[]) null);
+    NameContextGenerator CG = new TokenNameFinderFactory().createContextGenerator();
 
     NameSample nameSample = new NameSample(sentence,
         new Span[] {new Span(3, 7)}, false);

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

@@ -26,7 +26,6 @@
 import opennlp.tools.util.ObjectStream;
 import opennlp.tools.util.ObjectStreamUtils;
 import opennlp.tools.util.Span;
-import opennlp.tools.util.featuregen.AdaptiveFeatureGenerator;
 
 /**
  * This is the test class for {@link NameFinderEventStream}.
@@ -37,18 +36,14 @@ public class NameFinderEventStreamTest {
       "the", "hint", "and", "enjoyed", "a", "delicious", "traditional", "meal",
       "."};
 
-  private static final NameContextGenerator CG = new DefaultNameContextGenerator(
-      (AdaptiveFeatureGenerator[]) null);
+  private static final NameContextGenerator CG = new TokenNameFinderFactory().createContextGenerator();
 
   /**
    * Tests the correctly generated outcomes for a test sentence.
    */
   @Test
   void testOutcomesForSingleTypeSentence() throws IOException {
 
-    NameContextGenerator CG = new DefaultNameContextGenerator(
-            (AdaptiveFeatureGenerator[]) null);
-
     NameSample nameSample = new NameSample(SENTENCE,
         new Span[] {new Span(0, 2, "person")}, false);