add uppercase token filter

closes #5539
This commit is contained in:
Kevin Wang 2014-03-26 12:15:19 +11:00 committed by Martijn van Groningen
parent 2c65711dd9
commit 374b633a4b
5 changed files with 62 additions and 0 deletions

View File

@ -17,6 +17,8 @@ include::tokenfilters/length-tokenfilter.asciidoc[]
include::tokenfilters/lowercase-tokenfilter.asciidoc[]
include::tokenfilters/uppercase-tokenfilter.asciidoc[]
include::tokenfilters/ngram-tokenfilter.asciidoc[]
include::tokenfilters/edgengram-tokenfilter.asciidoc[]

View File

@ -0,0 +1,5 @@
[[analysis-uppercase-tokenfilter]]
=== Uppercase Token Filter
A token filter of type `uppercase` that normalizes token text to upper
case.

View File

@ -426,6 +426,7 @@ public class AnalysisModule extends AbstractModule {
tokenFiltersBindings.processTokenFilter("asciifolding", ASCIIFoldingTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("length", LengthTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("lowercase", LowerCaseTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("uppercase", UpperCaseTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("porter_stem", PorterStemTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("kstem", KStemTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("standard", StandardTokenFilterFactory.class);

View File

@ -0,0 +1,46 @@
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch licenses this file to you 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.elasticsearch.index.analysis;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.UpperCaseFilter;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
/**
*
*/
public class UpperCaseTokenFilterFactory extends AbstractTokenFilterFactory {
@Inject
public UpperCaseTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
}
@Override
public TokenStream create(TokenStream tokenStream) {
return new UpperCaseFilter(version, tokenStream);
}
}

View File

@ -26,6 +26,7 @@ import org.apache.lucene.analysis.commongrams.CommonGramsFilter;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.core.UpperCaseFilter;
import org.apache.lucene.analysis.cz.CzechStemFilter;
import org.apache.lucene.analysis.de.GermanStemFilter;
import org.apache.lucene.analysis.en.KStemFilter;
@ -117,6 +118,13 @@ public enum PreBuiltTokenFilters {
}
},
UPPERCASE(CachingStrategy.LUCENE) {
@Override
public TokenStream create(TokenStream tokenStream, Version version) {
return new UpperCaseFilter(version.luceneVersion, tokenStream);
}
},
KSTEM(CachingStrategy.ONE) {
@Override
public TokenStream create(TokenStream tokenStream, Version version) {