Example usage for org.apache.lucene.analysis WordlistLoader getWordSet

List of usage examples for org.apache.lucene.analysis WordlistLoader getWordSet

Introduction

In this page you can find the example usage for org.apache.lucene.analysis WordlistLoader getWordSet.

Prototype

public static CharArraySet getWordSet(Reader reader, String comment) throws IOException 

Source Link

Document

Reads lines from a Reader and adds every non-comment line as an entry to a CharArraySet (omitting leading and trailing whitespace).

Usage

From source file:dk.defxws.fgslucene.PhaidraAnalyzer.java

License:Apache License

/** Builds an analyzer with the stop words from the given file.
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion Lucene version to match See {@link
 * <a href="#version">above</a>}
 * @param stopwords File to read stop words from */
public PhaidraAnalyzer(Version matchVersion, File stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords, IOUtils.CHARSET_UTF_8),
            matchVersion));/*  w  ww .java 2  s.  c o  m*/
}

From source file:dk.defxws.fgslucene.PhaidraAnalyzer.java

License:Apache License

/** Builds an analyzer with the stop words from the given reader.
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion Lucene version to match See {@link
 * <a href="#version">above</a>}
 * @param stopwords Reader to read stop words from */
public PhaidraAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion));
}

From source file:edu.ur.lucene.analysis.StandardWithACIIFoldingFilter.java

License:Apache License

/** Builds an analyzer with the stop words from the given file.
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion Lucene version to match See {@link
 * <a href="#version">above</a>}
 * @param stopwords File to read stop words from */
public StandardWithACIIFoldingFilter(Version matchVersion, File stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords, IOUtils.CHARSET_UTF_8),
            matchVersion));/*from  w  w w  .  ja  va2  s. c  o  m*/
}

From source file:edu.ur.lucene.analysis.StandardWithACIIFoldingFilter.java

License:Apache License

/** Builds an analyzer with the stop words from the given reader.
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion Lucene version to match See {@link
 * <a href="#version">above</a>}
 * @param stopwords Reader to read stop words from */
public StandardWithACIIFoldingFilter(Version matchVersion, Reader stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion));
}

From source file:mj.ocraptor.database.StandardAnalyzer.java

License:Apache License

/**
 * Builds an analyzer with the stop words from the given file.
 *
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion//  w  ww  .  java 2  s.  com
 *          Lucene version to match See {@link <a href="#version">above</a>}
 * @param stopwords
 *          File to read stop words from
 * @deprecated Use {@link #StandardAnalyzer(Version, Reader)} instead.
 */
@Deprecated
public StandardAnalyzer(Version matchVersion, File stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(IOUtils.getDecodingReader(stopwords, IOUtils.CHARSET_UTF_8),
            matchVersion));
}

From source file:mj.ocraptor.database.StandardAnalyzer.java

License:Apache License

/**
 * Builds an analyzer with the stop words from the given reader.
 *
 * @see WordlistLoader#getWordSet(Reader, Version)
 * @param matchVersion/*from w  w  w.  j  av a2  s .c  o m*/
 *          Lucene version to match See {@link <a href="#version">above</a>}
 * @param stopwords
 *          Reader to read stop words from
 */
public StandardAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
    this(matchVersion, WordlistLoader.getWordSet(stopwords, matchVersion));
}

From source file:org.sindice.siren.analysis.AnyURIAnalyzer.java

License:Open Source License

public AnyURIAnalyzer(Version version, final Reader stopWords) throws IOException {
    stopSet = WordlistLoader.getWordSet(stopWords, version);
    matchVersion = version;
}

From source file:org.sindice.siren.analysis.bench.NoDeltaTupleAnalyzer.java

License:Open Source License

/**
 * Builds an analyzer with the stop words from the given file.
 *
 * @see WordlistLoader#getWordSet(File)// w  ww  . j  a  v  a  2  s  .c  o  m
 */
public NoDeltaTupleAnalyzer(final Analyzer stringAnalyzer, final Analyzer anyURIAnalyzer, final File stopwords)
        throws IOException {
    this.stringAnalyzer = stringAnalyzer;
    this.anyURIAnalyzer = anyURIAnalyzer;
    stopSet = WordlistLoader.getWordSet(new FileReader(stopwords), matchVersion);
}

From source file:org.sindice.siren.analysis.bench.NoDeltaTupleAnalyzer.java

License:Open Source License

/**
 * Builds an analyzer with the stop words from the given reader.
 *
 * @see WordlistLoader#getWordSet(Reader)
 *///from   www  .  j a va  2  s  . com
public NoDeltaTupleAnalyzer(final Analyzer stringAnalyzer, final Analyzer anyURIAnalyzer,
        final Reader stopwords) throws IOException {
    this.stringAnalyzer = stringAnalyzer;
    this.anyURIAnalyzer = anyURIAnalyzer;
    stopSet = WordlistLoader.getWordSet(stopwords, matchVersion);
}

From source file:org.sindice.siren.analysis.WhitespaceAnyURIAnalyzer.java

License:Open Source License

public WhitespaceAnyURIAnalyzer(Version version, final Reader stopWords) throws IOException {
    stopSet = WordlistLoader.getWordSet(stopWords, version);
    matchVersion = version;/*from   w  ww  .j av a  2s. c o m*/
}