Examples of org.sindice.siren.analysis.AnyURIAnalyzer

org.sindice.siren.analysis.AnyURIAnalyzer
Analyzer designed to deal with any kind of URIs and perform some post-processing on URIs.
The URI normalisation can be configured using {@link #setUriNormalisation(URINormalisation)}. You can disable it, activate it only on URI local name, or on the full URI. However, URI normalisation on the full URI is costly in term of CPU at indexing time, and can double the size of the index, since each URI is duplicated by n tokens. By default, the URI normalisation is disabled. @see URINormalisationFilter @see URILocalnameFilter


  @Override
  protected void configure() throws IOException {
    this.setAnalyzer(AnalyzerType.TUPLE);
    // TODO: remove when TupleAnalyzer is no more used
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    uriAnalyzer.setUriNormalisation(URINormalisation.FULL);
    ((TupleAnalyzer) analyzer).registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);
  }

View Full Code Here


public class TestNodeTermRangeQuery extends BasicSirenTestCase {


  @Override
  protected void configure() throws IOException {
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    final TupleAnalyzer tupleAnalyzer = new TupleAnalyzer(TEST_VERSION_CURRENT,
      new WhitespaceAnalyzer(TEST_VERSION_CURRENT), uriAnalyzer);
    tupleAnalyzer.registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setAnalyzer(tupleAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);

View Full Code Here


  @Override
  protected void configure() throws IOException {
    this.setAnalyzer(AnalyzerType.TUPLE);
    // TODO: remove when TupleAnalyzer is no more used
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    uriAnalyzer.setUriNormalisation(URINormalisation.FULL);
    ((TupleAnalyzer) analyzer).registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);
  }

View Full Code Here

public class TestTupleQuery extends AbstractTestSirenScorer {


  @Override
  protected void configure() throws IOException {
    this.setAnalyzer(AnalyzerType.TUPLE);
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    ((TupleAnalyzer) analyzer).registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);
  }

View Full Code Here

public class TestBooleanQuery extends BasicSirenTestCase {


  @Override
  protected void configure() throws IOException {
    this.setAnalyzer(AnalyzerType.TUPLE);
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    ((TupleAnalyzer) analyzer).registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);
  }

View Full Code Here

  @Override
  protected void configure() throws IOException {
    this.setAnalyzer(
      new TupleAnalyzer(TEST_VERSION_CURRENT,
        new WhitespaceAnalyzer(TEST_VERSION_CURRENT),
        new AnyURIAnalyzer(TEST_VERSION_CURRENT))
    );
    this.setPostingsFormat(PostingsFormatType.RANDOM);
  }

View Full Code Here


  private static void init(final Index index)
  throws IOException {
    final RandomSirenCodec codec = new RandomSirenCodec(random(), PostingsFormatType.RANDOM);
    final TupleAnalyzer tupleAnalyzer = (TupleAnalyzer) SirenTestCase.newTupleAnalyzer();
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    tupleAnalyzer.registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);


    // Set the SIREn fields
    codec.addSirenFields("field8", "field6", "field4", "field2", "field" + Integer.MAX_VALUE,
      "ascfield8", "ascfield6", "ascfield4", "ascfield2",

View Full Code Here

 */
public class TestNodeFuzzyQuery extends BasicSirenTestCase {


  @Override
  protected void configure() throws IOException {
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    final TupleAnalyzer tupleAnalyzer = new TupleAnalyzer(TEST_VERSION_CURRENT,
      new WhitespaceAnalyzer(TEST_VERSION_CURRENT), uriAnalyzer);
    tupleAnalyzer.registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setAnalyzer(tupleAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);

View Full Code Here


  private static void init(final Index index)
  throws IOException {
    final RandomSirenCodec codec = new RandomSirenCodec(random(), PostingsFormatType.RANDOM);
    final TupleAnalyzer tupleAnalyzer = (TupleAnalyzer) SirenTestCase.newTupleAnalyzer();
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    tupleAnalyzer.registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);


    // Set the SIREn fields
    codec.addSirenFields("field8", "field4", "field2", "field" + Integer.MAX_VALUE,
      "ascfield8", "ascfield4", "ascfield2",

View Full Code Here

 */
public class TestNodePrefixQuery extends BasicSirenTestCase {


  @Override
  protected void configure() throws IOException {
    final AnyURIAnalyzer uriAnalyzer = new AnyURIAnalyzer(TEST_VERSION_CURRENT);
    final TupleAnalyzer tupleAnalyzer = new TupleAnalyzer(TEST_VERSION_CURRENT,
      new WhitespaceAnalyzer(TEST_VERSION_CURRENT), uriAnalyzer);
    tupleAnalyzer.registerDatatype(XSDDatatype.XSD_ANY_URI.toCharArray(), uriAnalyzer);
    this.setAnalyzer(tupleAnalyzer);
    this.setPostingsFormat(PostingsFormatType.RANDOM);

View Full Code Here

0 1 2

TOP

Related Classes of org.sindice.siren.analysis.AnyURIAnalyzer

org.apache.lucene.analysis.core.LowerCaseFilter

org.apache.lucene.analysis.core.StopFilter

org.apache.lucene.analysis.core.WhitespaceTokenizer

org.apache.lucene.analysis.miscellaneous.LengthFilter

org.apache.lucene.analysis.TokenStream

org.sindice.siren.analysis.filter.MailtoFilter

org.sindice.siren.analysis.filter.URIDecodingFilter

org.sindice.siren.analysis.filter.URILocalnameFilter

org.sindice.siren.analysis.filter.URINormalisationFilter

org.sindice.siren.analysis.filter.URITrailingSlashFilter

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.