3 import java.io.IOException;
4 import java.util.ArrayList;
6 import java.util.logging.Logger;
8 import edu.stanford.nlp.ie.crf.CRFClassifier;
9 import edu.stanford.nlp.util.CoreMap;
10 import edu.stanford.nlp.util.Triple;
12 /** https://stanfordnlp.github.io/CoreNLP/api.html */
14 private static final String CLASS_NAME = NER.class.getName();
15 private static final Logger LOG = Logger.getLogger(CLASS_NAME);
16 private static final CRFClassifier<CoreMap> classifier = CRFClassifier.getDefaultClassifier();
18 public static List<String> classify(String str, List<String> entities) throws ClassCastException, ClassNotFoundException, IOException {
20 List<Triple<String, Integer, Integer>> triples;
22 final String FUNCTION_NAME = "classify";
24 LOG.entering(CLASS_NAME, FUNCTION_NAME, str);
26 OpenNLP.classify(str, entities);
28 synchronized (classifier) {
29 triples = classifier.classifyToCharacterOffsets(str);
32 for (Triple<String, Integer, Integer> t: triples) {
33 w = str.substring(t.second, t.third);
34 if (!entities.contains(w))
38 entities.remove("CNET");
39 entities.remove("Read More");
40 entities.remove("New");
41 entities.remove("App");
42 entities.remove("Digital Trends");
44 LOG.exiting(CLASS_NAME, FUNCTION_NAME, entities);
49 public static void main(String[] args) throws Exception {
52 lst = classify("I live in Washington and New York in United States.", new ArrayList<>());
54 System.out.println(str);