Example usage for org.apache.lucene.analysis.pattern PatternCaptureGroupTokenFilter PatternCaptureGroupTokenFilter

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.pattern PatternCaptureGroupTokenFilter PatternCaptureGroupTokenFilter.

Prototype

public PatternCaptureGroupTokenFilter(TokenStream input, boolean preserveOriginal, Pattern... patterns) 

Source Link

Usage

From source file:org.apache.jackrabbit.oak.plugins.index.solr.configuration.DefaultAnalyzersConfigurationTest.java

License:Apache License

@Before
public void setUp() throws Exception {
    this.exactPathAnalyzer = new Analyzer() {
        @Override//from   ww w  .  j  a  v  a  2  s .c o  m
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            return new TokenStreamComponents(source);
        }
    };
    this.parentPathIndexingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            return new TokenStreamComponents(source);
        }
    };
    this.parentPathSearchingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            TokenStream filter = new ReverseStringFilter(Version.LUCENE_47, source);
            filter = new PatternReplaceFilter(filter, Pattern.compile("[^\\/]+\\/"), "", false);
            filter = new ReverseStringFilter(Version.LUCENE_47, filter);
            return new TokenStreamComponents(source, filter);
        }
    };

    this.directChildrenPathIndexingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            TokenStream filter = new ReverseStringFilter(Version.LUCENE_47, source);
            filter = new LengthFilter(Version.LUCENE_47, filter, 2, Integer.MAX_VALUE);
            filter = new PatternReplaceFilter(filter, Pattern.compile("([^\\/]+)(\\/)"), "$2", false);
            filter = new PatternReplaceFilter(filter, Pattern.compile("(\\/)(.+)"), "$2", false);
            filter = new ReverseStringFilter(Version.LUCENE_47, filter);
            return new TokenStreamComponents(source, filter);
        }
    };
    this.directChildrenPathSearchingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            return new TokenStreamComponents(source);
        }
    };

    this.allChildrenPathIndexingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new PathHierarchyTokenizer(reader);
            TokenStream filter = new PatternCaptureGroupTokenFilter(source, false,
                    Pattern.compile("((\\/).*)"));
            filter = new RemoveDuplicatesTokenFilter(filter);
            return new TokenStreamComponents(source, filter);
        }
    };
    this.allChildrenPathSearchingAnalyzer = new Analyzer() {
        @Override
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer source = new KeywordTokenizer(reader);
            return new TokenStreamComponents(source);
        }
    };
}

---

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

License:Apache License

@Override
public TokenFilter create(TokenStream tokenStream) {
    return new PatternCaptureGroupTokenFilter(tokenStream, preserveOriginal, patterns);
}

---