OPENNLP-1483 Apply Java language migration aids (#524)

- modernizes existing classes and tests towards Java 8+
- adds `final` modifier where applicable
- adjusts broken or non-compliant JavaDoc

opennlp-tools/src/main/java/opennlp/tools/chunker/ChunkerEvaluator.java

@@ -51,7 +51,7 @@ public ChunkerEvaluator(Chunker chunker, ChunkerEvaluationMonitor... listeners)
 
   /**
    * Evaluates the given reference {@link ChunkSample} object.
-   *
+   * <p>
    * This is done by finding the phrases with the {@link Chunker} in the sentence from the reference
    * {@link ChunkSample}. The found phrases are then used to calculate and update the scores.
    *

opennlp-tools/src/main/java/opennlp/tools/cmdline/chunker/ChunkerEvaluatorTool.java

@@ -83,7 +83,7 @@ public void run(String format, String[] args) {
 
     final PerformanceMonitor monitor = new PerformanceMonitor("sent");
 
-    try (ObjectStream<ChunkSample> measuredSampleStream = new ObjectStream<ChunkSample>() {
+    try (ObjectStream<ChunkSample> measuredSampleStream = new ObjectStream<>() {
 
       public ChunkSample read() throws IOException {
         monitor.incrementCounter();

opennlp-tools/src/main/java/opennlp/tools/cmdline/langdetect/LanguageDetectorEvaluatorTool.java

@@ -100,7 +100,7 @@ public void run(String format, String[] args) {
 
     final PerformanceMonitor monitor = new PerformanceMonitor("doc");
 
-    try (ObjectStream<LanguageSample> measuredSampleStream = new ObjectStream<LanguageSample>() {
+    try (ObjectStream<LanguageSample> measuredSampleStream = new ObjectStream<>() {
 
       @Override
       public LanguageSample read() throws IOException {

opennlp-tools/src/main/java/opennlp/tools/cmdline/namefind/TokenNameFinderEvaluatorTool.java

@@ -81,7 +81,7 @@ public void run(String format, String[] args) {
 
     TokenNameFinderModel model = new TokenNameFinderModelLoader().load(params.getModel());
 
-    List<EvaluationMonitor<NameSample>> listeners = new LinkedList<EvaluationMonitor<NameSample>>();
+    List<EvaluationMonitor<NameSample>> listeners = new LinkedList<>();
     if (params.getMisclassified()) {
       listeners.add(new NameEvaluationErrorListener());
     }
@@ -120,7 +120,7 @@ public void run(String format, String[] args) {
 
     final PerformanceMonitor monitor = new PerformanceMonitor("sent");
 
-    try (ObjectStream<NameSample> measuredSampleStream = new ObjectStream<NameSample>() {
+    try (ObjectStream<NameSample> measuredSampleStream = new ObjectStream<>() {
 
       @Override
       public NameSample read() throws IOException {

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

@@ -392,7 +392,7 @@ public String getMorphologicalTag() {
 
     /** Represents the AD node */
     public static class Node extends TreeElement {
-      private List<TreeElement> elems = new ArrayList<>();
+      private final List<TreeElement> elems = new ArrayList<>();
 
       public void addElement(TreeElement element) {
         elems.add(element);

opennlp-tools/src/main/java/opennlp/tools/formats/brat/BratNameSampleStreamFactory.java

@@ -92,6 +92,7 @@ private boolean notNull(Object... objects) {
     return true;
   }
 
+  @Override
   public ObjectStream<NameSample> create(String[] args) {
 
     Parameters params = ArgumentParser.parse(args, Parameters.class);

opennlp-tools/src/main/java/opennlp/tools/formats/brat/SegmenterObjectStream.java

@@ -27,7 +27,7 @@
 
 public abstract class SegmenterObjectStream<S, T> extends FilterObjectStream<S, T> {
 
-  private Iterator<T> sampleIt = Collections.<T>emptySet().iterator();
+  private Iterator<T> sampleIt = Collections.emptyIterator();
 
   public SegmenterObjectStream(ObjectStream<S> in) {
     super(in);

opennlp-tools/src/main/java/opennlp/tools/formats/conllu/ConlluStream.java

@@ -202,7 +202,7 @@ private ConlluWordLine mergeAnnotation(ConlluWordLine contraction,
     String form = contraction.getForm();
     String lemma = expandedParts.stream()
         .filter(p -> !"_".equals(p.getLemma()))
-        .map(p -> p.getLemma())
+        .map(ConlluWordLine::getLemma)
         .collect(Collectors.joining("+"));
 
     String uPosTag = expandedParts.stream()
@@ -217,7 +217,7 @@ private ConlluWordLine mergeAnnotation(ConlluWordLine contraction,
 
     String feats = expandedParts.stream()
         .filter(p -> !"_".equals(p.getFeats()))
-        .map(p -> p.getFeats())
+        .map(ConlluWordLine::getFeats)
         .collect(Collectors.joining("+"));
 
     String head = contraction.getHead();

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

@@ -29,7 +29,7 @@
 
 /**
  * Default factory used by {@link LanguageDetector}.
- *
+ * <p>
  * Extend this class to change the Language Detector behaviour,
  * such as the {@link LanguageDetectorContextGenerator}.
  * The default {@link DefaultLanguageDetectorContextGenerator} will use char n-grams of

opennlp-tools/src/main/java/opennlp/tools/ml/maxent/io/GISModelWriter.java

@@ -168,14 +168,14 @@ protected List<List<ComparablePredicate>> compressOutcomes(ComparablePredicate[]
     if (sorted.length > 0) {
       ComparablePredicate cp = sorted[0];
       List<ComparablePredicate> newGroup = new ArrayList<>();
-      for (int i = 0; i < sorted.length; i++) {
-        if (cp.compareTo(sorted[i]) == 0) {
-          newGroup.add(sorted[i]);
+      for (ComparablePredicate comparablePredicate : sorted) {
+        if (cp.compareTo(comparablePredicate) == 0) {
+          newGroup.add(comparablePredicate);
         } else {
-          cp = sorted[i];
+          cp = comparablePredicate;
           outcomePatterns.add(newGroup);
           newGroup = new ArrayList<>();
-          newGroup.add(sorted[i]);
+          newGroup.add(comparablePredicate);
         }
       }
       outcomePatterns.add(newGroup);

opennlp-tools/src/main/java/opennlp/tools/ml/maxent/io/QNModelWriter.java

@@ -56,8 +56,7 @@ public void persist() throws IOException {
     // the mapping from outcomes to their integer indexes
     writeInt(OUTCOME_LABELS.length);
 
-    for (int i = 0; i < OUTCOME_LABELS.length; i++)
-      writeUTF(OUTCOME_LABELS[i]);
+    for (String outcomeLabel : OUTCOME_LABELS) writeUTF(outcomeLabel);
 
     // the mapping from predicates to the outcomes they contributed to.
     // The sorting is done so that we actually can write this out more
@@ -67,21 +66,19 @@ public void persist() throws IOException {
 
     writeInt(compressed.size());
 
-    for (int i = 0; i < compressed.size(); i++) {
-      List<ComparablePredicate> a = compressed.get(i);
+    for (List<ComparablePredicate> a : compressed) {
       writeUTF(a.size() + a.get(0).toString());
     }
 
     // the mapping from predicate names to their integer indexes
     writeInt(PARAMS.length);
 
-    for (int i = 0; i < sorted.length; i++)
-      writeUTF(sorted[i].name);
+    for (ComparablePredicate predicate : sorted) writeUTF(predicate.name);
 
     // write out the parameters
-    for (int i = 0; i < sorted.length; i++)
-      for (int j = 0; j < sorted[i].params.length; j++)
-        writeDouble(sorted[i].params[j]);
+    for (ComparablePredicate comparablePredicate : sorted)
+      for (int j = 0; j < comparablePredicate.params.length; j++)
+        writeDouble(comparablePredicate.params[j]);
 
     close();
   }

opennlp-tools/src/main/java/opennlp/tools/ml/model/TwoPassDataIndexer.java

@@ -112,7 +112,7 @@ public void index(ObjectStream<Event> eventStream) throws IOException {
    * predicates associated with each event are counted and any which
    * occur at least <tt>cutoff</tt> times are added to the
    * <tt>predicatesInOut</tt> map along with a unique integer index.
-   *
+   * <p>
    * Protocol:
    *  1 - (utf string) - Event outcome
    *  2 - (int) - Event context array length

opennlp-tools/src/main/java/opennlp/tools/ml/naivebayes/NaiveBayesModelWriter.java

@@ -114,14 +114,14 @@ protected List<List<ComparablePredicate>> compressOutcomes(ComparablePredicate[]
     if (sorted.length > 0) {
       ComparablePredicate cp = sorted[0];
       List<ComparablePredicate> newGroup = new ArrayList<>();
-      for (int i = 0; i < sorted.length; i++) {
-        if (cp.compareTo(sorted[i]) == 0) {
-          newGroup.add(sorted[i]);
+      for (ComparablePredicate comparablePredicate : sorted) {
+        if (cp.compareTo(comparablePredicate) == 0) {
+          newGroup.add(comparablePredicate);
         } else {
-          cp = sorted[i];
+          cp = comparablePredicate;
           outcomePatterns.add(newGroup);
           newGroup = new ArrayList<>();
-          newGroup.add(sorted[i]);
+          newGroup.add(comparablePredicate);
         }
       }
       outcomePatterns.add(newGroup);
@@ -198,9 +198,9 @@ public void persist() throws IOException {
     }
 
     // write out the parameters
-    for (int i = 0; i < sorted.length; i++)
-      for (int j = 0; j < sorted[i].params.length; j++)
-        writeDouble(sorted[i].params[j]);
+    for (ComparablePredicate comparablePredicate : sorted)
+      for (int j = 0; j < comparablePredicate.params.length; j++)
+        writeDouble(comparablePredicate.params[j]);
 
     close();
   }

opennlp-tools/src/main/java/opennlp/tools/ml/perceptron/PerceptronModelWriter.java

@@ -189,9 +189,9 @@ public void persist() throws IOException {
     }
 
     // write out the parameters
-    for (int i = 0; i < sorted.length; i++)
-      for (int j = 0; j < sorted[i].params.length; j++)
-        writeDouble(sorted[i].params[j]);
+    for (ComparablePredicate comparablePredicate : sorted)
+      for (int j = 0; j < comparablePredicate.params.length; j++)
+        writeDouble(comparablePredicate.params[j]);
 
     close();
   }

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

@@ -22,7 +22,7 @@
 /**
  * Interface for processing an entire document allowing a {@link TokenNameFinder} to use context
  * from the entire document.
- *
+ * <p>
  * <strong>EXPERIMENTAL</strong>:
  * This interface has been added as part of a work in progress and might change without notice.
  */

opennlp-tools/src/main/java/opennlp/tools/ngram/NGramCharModel.java

@@ -27,13 +27,13 @@
 /**
  * The {@link NGramCharModel} can be used to create character ngrams.
  *
- * @see {@link NGramModel}
+ * @see NGramModel
  */
 public class NGramCharModel implements Iterable<String> {
 
   protected static final String COUNT = "count";
 
-  private Map<String, Integer> mNGrams = new HashMap<>();
+  private final Map<String, Integer> mNGrams = new HashMap<>();
 
   /**
    * Initializes an empty instance.

opennlp-tools/src/main/java/opennlp/tools/ngram/NGramGenerator.java

@@ -21,22 +21,21 @@
 import java.util.List;
 
 /**
- * Generates an nGram, with optional separator, and returns the grams as a list
+ * Generates an nGram, via an optional separator, and returns the grams as a list
  * of strings
  */
 public class NGramGenerator {
 
-
   /**
-   * Creates an ngram separated
-   * by the separator param value i.e. a,b,c,d with n = 3 and separator = "-"
-   * would return a-b-c,b-c-d
+   * Creates nGrams separated
+   * by the separator param value i.e. {@code a,b,c,d} with {@code n = 3} and a
+   * separator as {@code "-"} would return {@code a-b-c,b-c-d}.
    *
    * @param input     the input tokens the output ngrams will be derived from
    * @param n         the number of tokens as the sliding window
    * @param separator each string in each gram will be separated by this value if desired.
    *                  Pass in empty string if no separator is desired
-   * @return
+   * @return The generated list of resulting nGrams.
    */
   public static List<String> generate(List<String> input, int n, String separator) {
 
@@ -57,12 +56,12 @@ public static List<String> generate(List<String> input, int n, String separator)
   }
 
   /**
-   *Generates an nGram based on a char[] input
+   * Generates nGrams based on a {@code char[]} input.
    * @param input the array of chars to convert to nGram
    * @param n The number of grams (chars) that each output gram will consist of
    * @param separator each char in each gram will be separated by this value if desired.
    *                  Pass in empty string if no separator is desired
-   * @return
+   * @return The generated list of resulting nGrams.
    */
   public static List<String> generate(char[] input, int n, String separator) {
 

opennlp-tools/src/main/java/opennlp/tools/ngram/NGramModel.java

@@ -42,7 +42,7 @@ public class NGramModel implements Iterable<StringList> {
 
   protected static final String COUNT = "count";
 
-  private Map<StringList, Integer> mNGrams = new LinkedHashMap<>();
+  private final Map<StringList, Integer> mNGrams = new LinkedHashMap<>();
 
   /**
    * Initializes an empty instance.
@@ -264,9 +264,9 @@ public void cutoff(int cutoffUnder, int cutoffOver) {
   /**
    * Creates a dictionary which contain all {@link StringList} which
    * are in the current {@link NGramModel}.
-   *
+   * <p>
    * Entries which are only different in the case are merged into one.
-   *
+   * <p>
    * Calling this method is the same as calling {@link #toDictionary(boolean)} with true.
    *
    * @return a dictionary of the ngrams
@@ -303,9 +303,8 @@ public Dictionary toDictionary(boolean caseSensitive) {
    * @throws IOException if an I/O Error during writing occurs
    */
   public void serialize(OutputStream out) throws IOException {
-    Iterator<Entry> entryIterator = new Iterator<Entry>()
-    {
-      private Iterator<StringList> mDictionaryIterator = NGramModel.this.iterator();
+    Iterator<Entry> entryIterator = new Iterator<>() {
+      private final Iterator<StringList> mDictionaryIterator = NGramModel.this.iterator();
 
       @Override
       public boolean hasNext() {
@@ -320,7 +319,7 @@ public Entry next() {
         Attributes attributes = new Attributes();
 
         attributes.setValue(COUNT, Integer.toString(getCount(tokens)));
-        
+
         return new Entry(tokens, attributes);
       }
 

opennlp-tools/src/main/java/opennlp/tools/ngram/NGramUtils.java

@@ -143,10 +143,10 @@ public static double calculateTrigramLinearInterpolationProbability(String x0, S
    * @param set      the vocabulary
    * @return the probability
    */
-  public static double calculateMissingNgramProbabilityMass(StringList ngram, Double discount,
+  public static double calculateMissingNgramProbabilityMass(StringList ngram, double discount,
                                                             Iterable<StringList> set) {
-    Double missingMass = 0d;
-    Double countWord = count(ngram, set);
+    double missingMass = 0d;
+    double countWord = count(ngram, set);
     for (String word : flatSet(set)) {
       missingMass += (count(getNPlusOneNgram(ngram, word), set) - discount) / countWord;
     }

opennlp-tools/src/main/java/opennlp/tools/parser/Constituent.java

@@ -27,7 +27,7 @@
 public class Constituent {
 
   private String label;
-  private Span span;
+  private final Span span;
 
   public Constituent(String label, Span span) {
     this.label = label;

opennlp-tools/src/main/java/opennlp/tools/parser/ParserModel.java

@@ -203,8 +203,7 @@ public ParserModel(URL modelURL) throws IOException {
   }
 
   @Override
-  protected void createArtifactSerializers(
-      Map<String, ArtifactSerializer> serializers) {
+  protected void createArtifactSerializers(Map<String, ArtifactSerializer> serializers) {
 
     super.createArtifactSerializers(serializers);
 

opennlp-tools/src/main/java/opennlp/tools/parser/lang/en/HeadRules.java

@@ -181,19 +181,19 @@ else if ((hr = headRules.get(type)) != null) {
       int cl = constituents.length;
       int tl = tags.length;
       if (hr.leftToRight) {
-        for (int ti = 0; ti < tl; ti++) {
-          for (int ci = 0; ci < cl; ci++) {
-            if (constituents[ci].getType().equals(tags[ti])) {
-              return constituents[ci].getHead();
+        for (String tag : tags) {
+          for (Parse constituent : constituents) {
+            if (constituent.getType().equals(tag)) {
+              return constituent.getHead();
             }
           }
         }
         return constituents[0].getHead();
       }
       else {
-        for (int ti = 0; ti < tl; ti++) {
+        for (String tag : tags) {
           for (int ci = cl - 1; ci >= 0; ci--) {
-            if (constituents[ci].getType().equals(tags[ti])) {
+            if (constituents[ci].getType().equals(tag)) {
               return constituents[ci].getHead();
             }
           }