Examples of LowerCaseFilter

org.apache.lucene.analysis.LowerCaseFilter
Normalizes token text to lower case.
org.apache.lucene.analysis.core.LowerCaseFilter
Normalizes token text to lower case.
You must specify the required {@link Version}compatibility when creating LowerCaseFilter:
- As of 3.1, supplementary characters are properly lowercased.

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

        final Version matchVersion = Version.LUCENE_40;
        final JsonTokenizer src = new JsonTokenizer(reader);
        TokenStream tok = new DatatypeAnalyzerFilter(matchVersion, src,
          new StandardAnalyzer(matchVersion),
          new StandardAnalyzer(matchVersion));
        tok = new LowerCaseFilter(matchVersion, tok);
        // The PositionAttributeFilter and SirenPayloadFilter are mandatory
        // and must be always the last filters in your token stream
        tok = new PositionAttributeFilter(tok);
        tok = new SirenPayloadFilter(tok);
        return new TokenStreamComponents(src, tok);

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  @Override
  protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
    final StandardTokenizer src = new StandardTokenizer(matchVersion, reader);
    src.setMaxTokenLength(maxTokenLength);
    TokenStream tok = new StandardFilter(matchVersion, src);
    tok = new LowerCaseFilter(matchVersion, tok);
    tok = new StopFilter(matchVersion, tok, stopwords);
    return new TokenStreamComponents(src, tok) {
      @Override
      protected void setReader(final Reader reader) throws IOException {
        src.setMaxTokenLength(NoStopWordStandardAnalyzer.this.maxTokenLength);

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

    
    Analyzer analyzer = new Analyzer() {
      @Override
      protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
        Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_43, reader) : factory.create(reader);
        TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_43, tokenizer) : tokenizer;
        return new TokenStreamComponents(tokenizer, stream);
      }
    };


    try {

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

    TokenStream stream = new JapaneseBaseFormFilter(tokenizer);
    stream = new JapanesePartOfSpeechStopFilter(matchVersion, stream, stoptags);
    stream = new CJKWidthFilter(stream);
    stream = new StopFilter(matchVersion, stream, stopwords);
    stream = new JapaneseKatakanaStemFilter(stream);
    stream = new LowerCaseFilter(matchVersion, stream);
    return new TokenStreamComponents(tokenizer, stream);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new NorwegianStemmer());
    return new TokenStreamComponents(source, result);

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    if (matchVersion.onOrAfter(Version.LUCENE_31))
      result = new LowerCaseFilter(matchVersion, result);
    result = new ThaiWordFilter(matchVersion, result);
    return new TokenStreamComponents(source, new StopFilter(matchVersion,
        result, stopwords));
  }

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  @Override
  protected TokenStreamComponents createComponents(String fieldName,
      Reader reader) {
    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new SpanishLightStemFilter(result);

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  private boolean hasIllegalOffsets = false; // only if the length changed before this filter


  /** Creates a new ThaiWordFilter with the specified match version. */
  public ThaiWordFilter(Version matchVersion, TokenStream input) {
    super(matchVersion.onOrAfter(Version.LUCENE_31) ?
      input : new LowerCaseFilter(matchVersion, input));
    if (!DBBI_AVAILABLE)
      throw new UnsupportedOperationException("This JRE does not have support for Thai segmentation");
    handlePosIncr = matchVersion.onOrAfter(Version.LUCENE_31);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.core.LowerCaseFilter

  protected TokenStreamComponents createComponents(String fieldName,
      Reader aReader) {
    if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);

View Full Code Here

0 1 2 3 4 5

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.