Example usage for org.apache.lucene.analysis.standard StandardTokenizer StandardTokenizer

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.standard StandardTokenizer StandardTokenizer.

Prototype

public StandardTokenizer()

Source Link

Document

Creates a new instance of the org.apache.lucene.analysis.standard.StandardTokenizer .

Usage

From source file:org.nlp4l.framework.builtin.kea.KEAStandardAnalyzer.java

License:Apache License

@Override
protected TokenStreamComponents createComponents(String fieldName) {
    Tokenizer source = new StandardTokenizer();
    TokenStream lcf = new LowerCaseFilter(source);
    if (n == 1) {
        TokenStream stf = new KEAStopFilter(lcf, n, stopWords, beginStopWords, endStopWords);
        return new TokenStreamComponents(source, stf);
    } else {/*from  w w w .  j  av a 2s.  c  om*/
        assert n >= 2;
        ShingleFilter shf = new ShingleFilter(lcf, n, n);
        shf.setOutputUnigrams(false);
        KEAStopFilter keasf = new KEAStopFilter(shf, n, stopWords, beginStopWords, endStopWords);
        return new TokenStreamComponents(source, keasf);
    }
}

From source file:org.silverpeas.core.index.indexing.model.WAAnalyzer.java

License:Open Source License

/**
 * Returns a tokens stream built on top of the given reader.
 *
 *///from w w  w.ja v a 2s  .co  m
@Override
protected TokenStreamComponents createComponents(final String s) {
    final Tokenizer source = new StandardTokenizer();
    // remove 's and . from token
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    // remove some unexplicit terms
    result = new StopFilter(result, FrenchAnalyzer.getDefaultStopSet());
    // remove [cdjlmnst-qu]' from token
    result = new ElisionFilter(result, FrenchAnalyzer.DEFAULT_ARTICLES);
    if (snowballUsed) {
        // Important! Strings given to Snowball filter must contains accents
        // so accents must be removed after stemmer have done the job
        // ignoring singular/plural, male/female and conjugated forms
        result = new SnowballFilter(result, stemmer);
    }
    // remove accents
    result = new ASCIIFoldingFilter(result);
    return new TokenStreamComponents(source, result);
}

From source file:org.tallison.lucene.search.concordance.ConcordanceTestBase.java

License:Apache License

public static Analyzer getCJKBigramAnalyzer(final boolean outputUnigrams) {
    return new Analyzer() {

        @Override/*from  w ww .  ja v  a2  s .co m*/
        public TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new StandardTokenizer();
            TokenFilter filter = new CJKBigramFilter(tokenizer, 15, outputUnigrams);
            return new TokenStreamComponents(tokenizer, filter);
        }

        @Override
        public int getPositionIncrementGap(String fieldName) {
            return 10;
        }

        @Override
        public int getOffsetGap(String fieldName) {
            return 10;
        }
    };
}

From source file:org.wltea.analyzer.sample.LuceneTokenizerDemo.java

License:Apache License

/**
 * ?StandardTokenizer/*  w w w .  ja  v a  2s  . c  o  m*/
 */
public void testST() {
    Tokenizer tokenizer = new StandardTokenizer();
    try {
        tokenizer.setReader(new StringReader(
                "?????IKAnalyer can analysis english text too"));
    } catch (IOException e) {
        throw new RuntimeException();
    }
    TokenStreamComponents tsc = new TokenStreamComponents(tokenizer);
    TokenStream ts = tsc.getTokenStream();
    OffsetAttribute offset = ts.addAttribute(OffsetAttribute.class);
    CharTermAttribute term = ts.addAttribute(CharTermAttribute.class);
    TypeAttribute type = ts.addAttribute(TypeAttribute.class);
    try {
        ts.reset();
        while (ts.incrementToken()) {
            System.out.println(term.toString() + "->" + offset.startOffset() + "-" + offset.endOffset() + "->"
                    + type.type());
        }
        ts.end();
    } catch (IOException e) {
        throw new RuntimeException();
    }
}

From source file:ri.AnalyzerNuevo.java

@Override
protected TokenStreamComponents createComponents(String string) {

    //To change body of generated methods, choose Tools | Templates.
    final Tokenizer source = new StandardTokenizer();

    Reader reader = new StringReader(string);

    source.setReader(reader);/*w w w  . ja va2 s.  c o  m*/

    //SynonymMap.Builder builder = new SynonymMap.Builder(true);
    //builder.add(new CharsRef("text"), new CharsRef("documento"), true);

    //SynonymMap synonymMap;

    TokenStream pipeline = source;
    pipeline = new StandardFilter(pipeline);

    pipeline = new EnglishPossessiveFilter(pipeline);
    /*try {
    synonymMap = builder.build();
    pipeline = new SynonymFilter(pipeline,synonymMap,true);
    } catch (IOException ex) {
       Logger.getLogger(AnalyzerNuevo.class.getName()).log(Level.SEVERE, null, ex);
    }*/

    pipeline = new ASCIIFoldingFilter(pipeline);
    pipeline = new LowerCaseFilter(pipeline);
    pipeline = new StopFilter(pipeline, new CharArraySet(stopwords, true));
    pipeline = new PorterStemFilter(pipeline);

    return new TokenStreamComponents(source, pipeline);
}