Package org.apache.lucene.analysis.shingle

Examples of org.apache.lucene.analysis.shingle.ShingleFilter.incrementToken()


        count++;
        ngrams.adjustOrPutValue(term, 1, 1);
      } else if (emitUnigrams && term.length() > 0) { // unigram
        unigrams.adjustOrPutValue(term, 1, 1);
      }
    } while (sf.incrementToken());
   
    try {
      final GramKey gramKey = new GramKey();
     
      ngrams.forEachPair(new ObjectIntProcedure<String>() {
View Full Code Here


            continue;
          }
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      } while (sf.incrementToken());
     
      sf.end();
      sf.close();
    } else {
      for (String term : value.getEntries()) {
View Full Code Here

            wordList.put(term, 1 + wordList.get(term));
          } else {
            wordList.put(term, 1);
          }
        }
      } while (sf.incrementToken());
    } else {
      for (String term : tokens) {
        if (wordList.containsKey(term)) {
          wordList.put(term, 1 + wordList.get(term));
        } else {
View Full Code Here

        count++;
        ngrams.adjustOrPutValue(term, 1, 1);
      } else if (emitUnigrams && term.length() > 0) { // unigram
        unigrams.adjustOrPutValue(term, 1, 1);
      }
    } while (sf.incrementToken());

    try {
      final GramKey gramKey = new GramKey();

      ngrams.forEachPair(new ObjectIntProcedure<String>() {
View Full Code Here

        String term = (sf.getAttribute(TermAttribute.class)).term();
        if (term.length() > 0 && dictionary.containsKey(term)) { // ngram
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      } while (sf.incrementToken());

      sf.end();
      sf.close();
    } else {
      for (String term : value.getEntries()) {
View Full Code Here

            wordList.put(term, 1 + wordList.get(term));
          } else {
            wordList.put(term, 1);
          }
        }
      } while (sf.incrementToken());
    } else {
      for (String term : tokens) {
        if (wordList.containsKey(term)) {
          wordList.put(term, 1 + wordList.get(term));
        } else {
View Full Code Here

            wordList.put(term, 1 + wordList.get(term));
          } else {
            wordList.put(term, 1);
          }
        }
      } while (sf.incrementToken());
    } else {
      for (String term : tokens) {
        if (wordList.containsKey(term)) {
          wordList.put(term, 1 + wordList.get(term));
        } else {
View Full Code Here

          String term = sf.getAttribute(CharTermAttribute.class).toString();
          if (!term.isEmpty() && dictionary.containsKey(term)) { // ngram
            int termId = dictionary.get(term);
            vector.setQuick(termId, vector.getQuick(termId) + 1);
          }
        } while (sf.incrementToken());

        sf.end();
      } finally {
        Closeables.close(sf, true);
      }
View Full Code Here

          count++;
          ngrams.adjustOrPutValue(term, 1, 1);
        } else if (emitUnigrams && !term.isEmpty()) { // unigram
          unigrams.adjustOrPutValue(term, 1, 1);
        }
      } while (sf.incrementToken());

      final GramKey gramKey = new GramKey();

      ngrams.forEachPair(new ObjectIntProcedure<String>() {
        @Override
View Full Code Here

            wordList.put(term, 1 + wordList.get(term));
          } else {
            wordList.put(term, 1);
          }
        }
      } while (sf.incrementToken());
    } else {
      for (String term : tokens) {
        if (wordList.containsKey(term)) {
          wordList.put(term, 1 + wordList.get(term));
        } else {
View Full Code Here

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.