Merge branch 'master' of jamie.stanford.edu:/u/nlp/git/javanlp

itest/src/edu/stanford/nlp/pipeline/ProtobufAnnotationSerializerSlowITest.java

@@ -63,7 +63,7 @@ protected Annotation mkLargeAnnotation() {
     return ann;
   }
 
-  @SuppressWarnings("unchecked")
+  @SuppressWarnings({"unchecked", "ConstantConditions"})
   public static void sameAsRead(Annotation doc, Annotation readDoc) {
     // Run the original document through the number normalizer
     if (doc.containsKey(CoreAnnotations.SentencesAnnotation.class)) {

src/edu/stanford/nlp/classify/NaiveBayesClassifierFactory.java

@@ -53,7 +53,7 @@
 public class NaiveBayesClassifierFactory<L, F> implements ClassifierFactory<L, F, NaiveBayesClassifier<L, F>>  {
 
   /** A logger for this class */
-  private static Redwood.RedwoodChannels log = Redwood.channels(NaiveBayesClassifierFactory.class);
+  private static final Redwood.RedwoodChannels logger = Redwood.channels(NaiveBayesClassifierFactory.class);
 
   private static final long serialVersionUID = -8164165428834534041L;
   public static final int JL = 0;
@@ -67,8 +67,6 @@ public class NaiveBayesClassifierFactory<L, F> implements ClassifierFactory<L, F
   private Index<L> labelIndex;
   private Index<F> featureIndex;
 
-  final static Redwood.RedwoodChannels logger = Redwood.channels(NaiveBayesClassifierFactory.class);
-
   public NaiveBayesClassifierFactory() {
   }
 

src/edu/stanford/nlp/coref/data/DocumentMaker.java

@@ -56,7 +56,8 @@ private static DocReader getDocumentReader(Properties props) {
     if (!PropertiesUtils.getBool(props,"coref.printConLLLoadingMessage",true))
       options.printConLLLoadingMessage = false;
     options.annotateTokenCoref = false;
-    options.setFilter(".*_auto_conll$");
+    String conllFileFilter = props.getProperty("coref.conllFileFilter", ".*_auto_conll$");
+    options.setFilter(conllFileFilter);
     options.lang = CorefProperties.getLanguage(props);
     return new CoNLLDocumentReader(corpusPath, options);
   }

src/edu/stanford/nlp/ie/ChineseQuantifiableEntityNormalizer.java

@@ -920,7 +920,8 @@ public static <E extends CoreMap> String singleEntityToString(List<E> l) {
     StringBuilder sb = new StringBuilder();
     for (E w : l) {
       if(!w.get(CoreAnnotations.NamedEntityTagAnnotation.class).equals(entityType)) {
-        log.fatal("Incontinuous NER tags detected in entity: " + l);
+        log.error("differing NER tags detected in entity: " + l);
+        throw new Error("Error with entity construction, two tokens had inconsistent NER tags");
       }
       sb.append(w.get(CoreAnnotations.TextAnnotation.class));
     }

src/edu/stanford/nlp/ie/NERClassifierCombiner.java

@@ -192,7 +192,6 @@ public NERClassifierCombiner(ObjectInputStream ois, Properties props) throws IOE
       this.gazetteMapping = readRegexnerGazette(DefaultPaths.DEFAULT_NER_GAZETTE_MAPPING);
     } else {
       this.gazetteMapping = Collections.emptyMap();
-      log.fatal("Property ner.language not recognized: " + nerLanguage);
     }
   }
 

src/edu/stanford/nlp/ie/regexp/ChineseNumberSequenceClassifier.java

@@ -200,7 +200,8 @@ private static boolean rightScanFindsMoneyWord(List<CoreLabel> pl, int i) {
   @Override
   public List<CoreLabel> classifyWithGlobalInformation(List<CoreLabel> tokenSequence, CoreMap document, CoreMap sentence) {
     if(useSUTime) {
-      log.fatal("ChineseNumberSequenceClassifier does not have SUTime implementation.");
+      log.error("ChineseNumberSequenceClassifier does not have SUTime implementation.");
+      throw new Error("Error: no SUTime implementation for ChineseNumberSequenceClassifier");
     }
     return classify(tokenSequence);
   }

src/edu/stanford/nlp/naturalli/NaturalLogicAnnotations.java

@@ -46,6 +46,17 @@ public Class<Collection<SentenceFragment>> getType() {
     }
   }
 
+  /**
+   * A set of clauses contained in and entailed by this sentence.
+   */
+  public static final class EntailedClausesAnnotation implements CoreAnnotation<Collection<SentenceFragment>> {
+    @SuppressWarnings("unchecked")
+    @Override
+    public Class<Collection<SentenceFragment>> getType() {
+      return (Class<Collection<SentenceFragment>>) ((Object) Collection.class);
+    }
+  }
+
   /**
    * The set of relation triples extracted from this sentence.
    */

src/edu/stanford/nlp/naturalli/OpenIE.java

@@ -494,6 +494,7 @@ public void annotateSentence(CoreMap sentence, Map<CoreLabel, List<CoreLabel>> c
       extractions.addAll(relationsInFragments(fragments, sentence));
 
       // Set the annotations
+      sentence.set(NaturalLogicAnnotations.EntailedClausesAnnotation.class, new HashSet<>(clauses));
       sentence.set(NaturalLogicAnnotations.EntailedSentencesAnnotation.class, fragments);
       sentence.set(NaturalLogicAnnotations.RelationTriplesAnnotation.class,
           new ArrayList<>(new HashSet<>(extractions)));  // uniq the extractions

src/edu/stanford/nlp/pipeline/CoreNLP.proto

@@ -75,6 +75,7 @@ message Sentence {
   repeated RelationTriple   openieTriple                        = 14;   // The OpenIE triples in the sentence
   repeated RelationTriple   kbpTriple                           = 16;   // The KBP triples in this sentence
   repeated SentenceFragment entailedSentence                    = 15;   // The entailed sentences, by natural logic
+  repeated SentenceFragment entailedClause                      = 35;   // The entailed clauses, by natural logic
   optional DependencyGraph  enhancedDependencies                = 17;
   optional DependencyGraph  enhancedPlusPlusDependencies        = 18;
   repeated Token            character                           = 19;