/**
* Copyright 2014 National University of Ireland, Galway.
*
* This file is part of the SIREn project. Project and contact information:
*
* https://github.com/rdelbru/SIREn
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.sindice.siren.analysis;
import java.io.Reader;
import java.util.Map.Entry;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.CharArrayMap;
import org.apache.lucene.util.Version;
import org.sindice.siren.analysis.filter.DatatypeAnalyzerFilter;
import org.sindice.siren.analysis.filter.PositionAttributeFilter;
import org.sindice.siren.analysis.filter.SirenPayloadFilter;
import org.sindice.siren.util.JSONDatatype;
import org.sindice.siren.util.XSDDatatype;
/**
* The JsonAnalyzer is especially designed to process JSON data.
*/
public class JsonAnalyzer extends Analyzer {
private Analyzer valueAnalyzer;
private Analyzer fieldAnalyzer;
private final Version matchVersion;
private final CharArrayMap<Analyzer> regAnalyzers;
/**
* Create a {@link JsonAnalyzer} with the specified {@link Analyzer}s for
* field names and values.
* <p>
* The default analyzer for field names will be associated with the datatype
* {@link JSONDatatype#JSON_FIELD}. The default analyzer for values will be
* associated with the datatype {@link XSDDatatype#XSD_STRING}.
*
* @param fieldAnalyzer Default {@link Analyzer} for the field names
* @param valueAnalyzer Default {@link Analyzer} for the values
*/
public JsonAnalyzer(final Version version, final Analyzer fieldAnalyzer,
final Analyzer valueAnalyzer) {
matchVersion = version;
this.valueAnalyzer = valueAnalyzer;
this.fieldAnalyzer = fieldAnalyzer;
regAnalyzers = new CharArrayMap<Analyzer>(version, 64, false);
}
public void setValueAnalyzer(final Analyzer analyzer) {
valueAnalyzer = analyzer;
}
public void setFieldAnalyzer(final Analyzer analyzer) {
fieldAnalyzer = analyzer;
}
/**
* Assign an {@link Analyzer} to be used with that key. That analyzer is used
* to process tokens generated by the {@link JsonTokenizer}.
*
* @param datatype The datatype key
* @param a the associated {@link Analyzer}
*/
public void registerDatatype(final char[] datatype, final Analyzer a) {
if (!regAnalyzers.containsKey(datatype)) {
regAnalyzers.put(datatype, a);
}
}
/**
* Remove all registered Datatype {@link Analyzer}s.
*/
public void clearDatatypes() {
regAnalyzers.clear();
}
@Override
protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
final JsonTokenizer source = new JsonTokenizer(reader);
final DatatypeAnalyzerFilter tt = new DatatypeAnalyzerFilter(matchVersion, source, fieldAnalyzer, valueAnalyzer);
for (final Entry<Object, Analyzer> e : regAnalyzers.entrySet()) {
tt.register((char[]) e.getKey(), e.getValue());
}
TokenStream sink = new PositionAttributeFilter(tt);
sink = new SirenPayloadFilter(sink);
return new TokenStreamComponents(source, sink);
}
}