Examples of org.apache.lucene.analysis.TokenStream.incrementToken()

Class org.apache.lucene.analysis.TokenStream

Examples of org.apache.lucene.analysis.TokenStream.incrementToken()

org.apache.lucene.analysis.TokenStream.incrementToken()
Consumers (i.e., {@link IndexWriter}) use this method to advance the stream to the next token. Implementing classes must implement this method and update the appropriate {@link AttributeImpl}s with the attributes of the next token.
The producer must make no assumptions about the attributes after the method has been returned: the caller may arbitrarily change it. If the producer needs to preserve the state for subsequent calls, it can use {@link #captureState} to create a copy of the current attribute state.
This method is called for every token of a document, so an efficient implementation is crucial for good performance. To avoid calls to {@link #addAttribute(Class)} and {@link #getAttribute(Class)}, references to all {@link AttributeImpl}s that this stream uses should be retrieved during instantiation.
To ensure that filters and consumers know which attributes are available, the attributes must be added during instantiation. Filters and consumers are not required to check for availability of attributes in {@link #incrementToken()}. @return false for end of stream; true otherwise

    ts1.reset();
    ts2.reset();
    TermToBytesRefAttribute termAtt1 = ts1.addAttribute(TermToBytesRefAttribute.class);
    TermToBytesRefAttribute termAtt2 = ts2.addAttribute(TermToBytesRefAttribute.class);
    assertTrue(ts1.incrementToken());
    assertTrue(ts2.incrementToken());
    BytesRef bytes1 = termAtt1.getBytesRef();
    BytesRef bytes2 = termAtt2.getBytesRef();
    termAtt1.fillBytesRef();
    termAtt2.fillBytesRef();
    assertEquals(bytes1, bytes2);

View Full Code Here

    BytesRef bytes2 = termAtt2.getBytesRef();
    termAtt1.fillBytesRef();
    termAtt2.fillBytesRef();
    assertEquals(bytes1, bytes2);
    assertFalse(ts1.incrementToken());
    assertFalse(ts2.incrementToken());
    ts1.close();
    ts2.close();
  }
  
  private String[] getCollatorConfig(String localeParam,

View Full Code Here

    try {
      ts.reset();


      MorphosyntacticTagsAttribute attribute = ts.getAttribute(MorphosyntacticTagsAttribute.class);
      CharTermAttribute charTerm = ts.getAttribute(CharTermAttribute.class);
      while (ts.incrementToken()) {
        System.out.println(charTerm.toString() + " => " + attribute.getTags());
      }
      ts.end();
    } finally {
      IOUtils.closeWhileHandlingException(ts);

View Full Code Here

    Analyzer a = getTestAnalyzer();
    TokenStream ts_1 = a.tokenStream("dummy", "liście");
    try {
      CharTermAttribute termAtt_1 = ts_1.getAttribute(CharTermAttribute.class);
      ts_1.reset();
      ts_1.incrementToken();
      assertEquals("first stream", "liście", termAtt_1.toString());
      ts_1.end();
    } finally {
      IOUtils.closeWhileHandlingException(ts_1);
    }

View Full Code Here


    TokenStream ts_2 = a.tokenStream("dummy", "danych");
    try {
      CharTermAttribute termAtt_2 = ts_2.getAttribute(CharTermAttribute.class);
      ts_2.reset();
      ts_2.incrementToken();
      assertEquals("second stream", "dany", termAtt_2.toString());
      ts_2.end();
    } finally {
      IOUtils.closeWhileHandlingException(ts_2);
    }

View Full Code Here

    final CharTermAttribute termAtt = tk.addAttribute(CharTermAttribute.class);
    final OffsetAttribute offsetAtt = tk.addAttribute(OffsetAttribute.class);
    tk.reset();
    for (int start = 0; start < codePointCount; ++start) {
      for (int end = start + minGram; end <= Math.min(codePointCount, start + maxGram); ++end) {
        assertTrue(tk.incrementToken());
        assertEquals(0, offsetAtt.startOffset());
        assertEquals(s.length(), offsetAtt.endOffset());
        final int startIndex = Character.offsetByCodePoints(s, 0, start);
        final int endIndex = Character.offsetByCodePoints(s, 0, end);
        assertEquals(s.substring(startIndex, endIndex), termAtt.toString());

View Full Code Here

        final int startIndex = Character.offsetByCodePoints(s, 0, start);
        final int endIndex = Character.offsetByCodePoints(s, 0, end);
        assertEquals(s.substring(startIndex, endIndex), termAtt.toString());
      }
    }
    assertFalse(tk.incrementToken());
  }


}

View Full Code Here

        for (int j = start; j < end; ++j) {
          if (!isTokenChar(nonTokenChars, codePoints[j])) {
            continue nextGram;
          }
        }
        assertTrue(grams.incrementToken());
        assertArrayEquals(Arrays.copyOfRange(codePoints, start, end), toCodePoints(termAtt));
        assertEquals(1, posIncAtt.getPositionIncrement());
        assertEquals(1, posLenAtt.getPositionLength());
        assertEquals(offsets[start], offsetAtt.startOffset());
        assertEquals(offsets[end], offsetAtt.endOffset());

View Full Code Here

        assertEquals(1, posLenAtt.getPositionLength());
        assertEquals(offsets[start], offsetAtt.startOffset());
        assertEquals(offsets[end], offsetAtt.endOffset());
      }
    }
    assertFalse(grams.incrementToken());
    grams.end();
    assertEquals(s.length(), offsetAtt.startOffset());
    assertEquals(s.length(), offsetAtt.endOffset());
  }

View Full Code Here

      String s = _TestUtil.randomUnicodeString(random());
      TokenStream ts = analyzer.tokenStream("foo", s);
      try {
        ts.reset();
        OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
        while (ts.incrementToken()) {
          String highlightedText = s.substring(offsetAtt.startOffset(), offsetAtt.endOffset());
          for (int j = 0, cp = 0; j < highlightedText.length(); j += Character.charCount(cp)) {
            cp = highlightedText.codePointAt(j);
            assertTrue("non-letter:" + Integer.toHexString(cp), Character.isLetter(cp));
          }

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.