Examples of org.apache.lucene.analysis.Token.startOffset()

org.apache.lucene.analysis.Token.startOffset()
Returns this Token's starting offset, the position of the first character corresponding to this token in the source text. Note that the difference between endOffset() and startOffset() may not be equal to {@link #termLength}, as the term text may have been altered by a stemmer or some other filter.

      public boolean incrementToken() throws IOException {
        if(iter.hasNext()) {
          Token token = (Token) iter.next();
          termAtt.setTermBuffer(token.term());
          posIncrAtt.setPositionIncrement(token.getPositionIncrement());
          offsetAtt.setOffset(token.startOffset(), token.endOffset());
          return true;
        }
        return false;
      }
    };

View Full Code Here

      }
      Token prototype = (Token) iterator.next();
      termAtt.setTermBuffer(prototype.termBuffer(), 0, prototype.termLength());
      posIncrAtt.setPositionIncrement(prototype.getPositionIncrement());
      flagsAtt.setFlags(prototype.getFlags());
      offsetAtt.setOffset(prototype.startOffset(), prototype.endOffset());
      typeAtt.setType(prototype.type());
      payloadAtt.setPayload(prototype.getPayload());


      return true;
    }

View Full Code Here

    public final boolean incrementToken() throws IOException {
      clearAttributes();
      if (index < testToken.length) {
        Token t = testToken[index++];
        termAtt.setTermBuffer(t.termBuffer(), 0, t.termLength());
        offsetAtt.setOffset(t.startOffset(), t.endOffset());
        posIncrAtt.setPositionIncrement(t.getPositionIncrement());
        typeAtt.setType(TypeAttributeImpl.DEFAULT_TYPE);
        return true;
      } else {
        return false;

View Full Code Here

            if (currentToken >= tokens.length) {
              return false;
            }
            Token token = tokens[currentToken++];
            termAtt.setTermBuffer(token.term());
            offsetAtt.setOffset(token.startOffset(), token.endOffset());
            return true;
          }
        }      
        //code to reconstruct the original sequence of Tokens
        String[] terms=tpv.getTerms();

View Full Code Here

                {
                    Token t1=(Token) o1;
                    Token t2=(Token) o2;
                    if(t1.startOffset()>t2.endOffset())
                        return 1;
                    if(t1.startOffset()<t2.startOffset())
                        return -1;
                    return 0;
                }});
        }
        return new StoredTokenStream(tokensInOriginalOrder);

View Full Code Here

          termDocumentInformationFactory.payloads.add(null);
        }


        if (eField_Tokens.getKey().isStoreOffsetWithTermVector()) {


          termDocumentInformationFactory.termOffsets.add(new TermVectorOffsetInfo(fieldSetting.offset + token.startOffset(), fieldSetting.offset + token.endOffset()));
          lastOffset = fieldSetting.offset + token.endOffset();
        }




      }

View Full Code Here

            if (currentToken >= tokens.length) {
              return false;
            }
            Token token = tokens[currentToken++];
            termAtt.setTermBuffer(token.term());
            offsetAtt.setOffset(token.startOffset(), token.endOffset());
            return true;
          }
        }      
        //code to reconstruct the original sequence of Tokens
        String[] terms=tpv.getTerms();

View Full Code Here

        return reusableToken;
      } else
        while ((token = this.input.next(reusableToken)) != null) {
          if (token.term().equals("phrase")) {
            inPhrase = true;
            savedStart = token.startOffset();
            savedEnd = token.endOffset();
            token.setTermBuffer("phrase1");
            token.setStartOffset(savedStart);
            token.setEndOffset(savedEnd);
            return token;

View Full Code Here


        Token token = null;


        while ((token = ts.next()) != null) {
            System.out.println("ReTokenizeFile.reTokenize(File): " + token.termText() + " " +
                token.startOffset() + " " + token.endOffset() + " " + token.type());
        }


        return file.getAbsolutePath();
    }

View Full Code Here

            {
               TermVectorOffsetInfo[] tmp = info;
               info = new TermVectorOffsetInfo[tmp.length + 1];
               System.arraycopy(tmp, 0, info, 0, tmp.length);
            }
            info[info.length - 1] = new TermVectorOffsetInfo(t.startOffset(), t.endOffset());
            termMap.put(termText, info);
         }
      }
      catch (IOException e)
      {

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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.