Example usage for org.apache.lucene.analysis.cjk CJKBigramFilter HAN

List of usage examples for org.apache.lucene.analysis.cjk CJKBigramFilter HAN

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.cjk CJKBigramFilter HAN.

Prototype

int HAN

To view the source code for org.apache.lucene.analysis.cjk CJKBigramFilter HAN.

Click Source Link

Document

bigram flag for Han Ideographs

Usage

From source file:org.apache.solr.analysis.CJKBigramFilterFactory.java

License:Apache License

@Override
public void init(Map<String, String> args) {
    super.init(args);
    flags = 0;/*from   w w w. j  a  v  a2s .  co m*/
    if (getBoolean("han", true)) {
        flags |= CJKBigramFilter.HAN;
    }
    if (getBoolean("hiragana", true)) {
        flags |= CJKBigramFilter.HIRAGANA;
    }
    if (getBoolean("katakana", true)) {
        flags |= CJKBigramFilter.KATAKANA;
    }
    if (getBoolean("hangul", true)) {
        flags |= CJKBigramFilter.HANGUL;
    }
}

From source file:org.elasticsearch.analysis.common.CJKBigramFilterFactory.java

License:Apache License

CJKBigramFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
    super(indexSettings, name, settings);
    outputUnigrams = settings.getAsBoolean("output_unigrams", false);
    final List<String> asArray = settings.getAsList("ignored_scripts");
    Set<String> scripts = new HashSet<>(Arrays.asList("han", "hiragana", "katakana", "hangul"));
    if (asArray != null) {
        scripts.removeAll(asArray);/*w  ww  .j av a 2 s  . co  m*/
    }
    int flags = 0;
    for (String script : scripts) {
        if ("han".equals(script)) {
            flags |= CJKBigramFilter.HAN;
        } else if ("hiragana".equals(script)) {
            flags |= CJKBigramFilter.HIRAGANA;
        } else if ("katakana".equals(script)) {
            flags |= CJKBigramFilter.KATAKANA;
        } else if ("hangul".equals(script)) {
            flags |= CJKBigramFilter.HANGUL;
        }
    }
    this.flags = flags;
}

From source file:org.elasticsearch.index.analysis.CJKBigramFilterFactory.java

License:Apache License

@Inject
public CJKBigramFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name,
        @Assisted Settings settings) {/*from  w  ww .  jav  a 2 s .c om*/
    super(index, indexSettings, name, settings);
    outputUnigrams = settings.getAsBoolean("output_unigrams", false);
    final String[] asArray = settings.getAsArray("ignored_scripts");
    Set<String> scripts = new HashSet<String>(Arrays.asList("han", "hiragana", "katakana", "hangul"));
    if (asArray != null) {
        scripts.removeAll(Arrays.asList(asArray));
    }
    int flags = 0;
    for (String script : scripts) {
        if ("han".equals(script)) {
            flags |= CJKBigramFilter.HAN;
        } else if ("hiragana".equals(script)) {
            flags |= CJKBigramFilter.HIRAGANA;
        } else if ("katakana".equals(script)) {
            flags |= CJKBigramFilter.KATAKANA;
        } else if ("hangul".equals(script)) {
            flags |= CJKBigramFilter.HANGUL;
        }
    }
    this.flags = flags;
}