Examples of SplitterFilter


Examples of org.apache.uima.lucas.indexer.analysis.SplitterFilter

    Collection<Token> tokens = new ArrayList<Token>();
    tokens.add(newToken("token1 token2 token3", 0, 6));
    tokens.add(newToken("token4 token5 token6", 7, 13));
   
    TokenStream tokenStream = new CollectionTokenStream(tokens);
    TokenFilter filter = new SplitterFilter(tokenStream, " ");
   
    Token nextToken = new Token();
    filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token1", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(0, nextToken.startOffset());
    assertEquals(6, nextToken.endOffset());
   
    nextToken = filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token2", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(0, nextToken.startOffset());
    assertEquals(6, nextToken.endOffset());
   
    nextToken = filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token3", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(0, nextToken.startOffset());
    assertEquals(6, nextToken.endOffset());

    nextToken = filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token4", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(7, nextToken.startOffset());
    assertEquals(13, nextToken.endOffset());

    nextToken = filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token5", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(7, nextToken.startOffset());
    assertEquals(13, nextToken.endOffset());

    nextToken = filter.next(nextToken);
    assertNotNull(nextToken);
    assertEquals("token6", new String(nextToken.termBuffer(), 0, nextToken.termLength()));
    assertEquals(7, nextToken.startOffset());
    assertEquals(13, nextToken.endOffset());
  }
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.