Search in sources :

Example 1 with CommonGramsFilterFactory

use of org.apache.lucene.analysis.commongrams.CommonGramsFilterFactory in project lucene-solr by apache.

the class SolrStopwordsCarrot2LexicalDataFactory method getSolrStopWordsForField.

/**
   * Obtains stop words for a field from the associated
   * {@link StopFilterFactory}, if any.
   */
private List<CharArraySet> getSolrStopWordsForField(String fieldName) {
    // of this class are not used by multiple threads at a time.
    synchronized (solrStopWords) {
        if (!solrStopWords.containsKey(fieldName)) {
            solrStopWords.put(fieldName, new ArrayList<>());
            IndexSchema schema = core.getLatestSchema();
            final Analyzer fieldAnalyzer = schema.getFieldType(fieldName).getIndexAnalyzer();
            if (fieldAnalyzer instanceof TokenizerChain) {
                final TokenFilterFactory[] filterFactories = ((TokenizerChain) fieldAnalyzer).getTokenFilterFactories();
                for (TokenFilterFactory factory : filterFactories) {
                    if (factory instanceof StopFilterFactory) {
                        // StopFilterFactory holds the stop words in a CharArraySet
                        CharArraySet stopWords = ((StopFilterFactory) factory).getStopWords();
                        solrStopWords.get(fieldName).add(stopWords);
                    }
                    if (factory instanceof CommonGramsFilterFactory) {
                        CharArraySet commonWords = ((CommonGramsFilterFactory) factory).getCommonWords();
                        solrStopWords.get(fieldName).add(commonWords);
                    }
                }
            }
        }
        return solrStopWords.get(fieldName);
    }
}
Also used : CharArraySet(org.apache.lucene.analysis.CharArraySet) StopFilterFactory(org.apache.lucene.analysis.core.StopFilterFactory) TokenizerChain(org.apache.solr.analysis.TokenizerChain) CommonGramsFilterFactory(org.apache.lucene.analysis.commongrams.CommonGramsFilterFactory) IndexSchema(org.apache.solr.schema.IndexSchema) Analyzer(org.apache.lucene.analysis.Analyzer) TokenFilterFactory(org.apache.lucene.analysis.util.TokenFilterFactory)

Aggregations

Analyzer (org.apache.lucene.analysis.Analyzer)1 CharArraySet (org.apache.lucene.analysis.CharArraySet)1 CommonGramsFilterFactory (org.apache.lucene.analysis.commongrams.CommonGramsFilterFactory)1 StopFilterFactory (org.apache.lucene.analysis.core.StopFilterFactory)1 TokenFilterFactory (org.apache.lucene.analysis.util.TokenFilterFactory)1 TokenizerChain (org.apache.solr.analysis.TokenizerChain)1 IndexSchema (org.apache.solr.schema.IndexSchema)1