honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Pre-configured shingle filter should disable graph analysis (#25853) 

This change disables the graph analysis on default `shingle` filter.
The pre-configured shingle filter produces shingles of different size.
Graph analysis on such token stream is useless and dangerous as it may create too many paths.

Fixes #25555
This commit is contained in:
Jim Ferenczi 2017-07-24 18:42:15 +02:00 committed by GitHub
parent 4a9995145c
commit ab3b5c695a
2 changed files with 78 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
modules/analysis-common/src/main/java/org/elasticsearch/analysis/common/CommonAnalysisPlugin.java
View File

@ -46,6 +46,7 @@ import org.apache.lucene.analysis.fr.FrenchAnalyzer;
import org.apache.lucene.analysis.hi.HindiNormalizationFilter;
import org.apache.lucene.analysis.in.IndicNormalizationFilter;
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
import org.apache.lucene.analysis.miscellaneous.DisableGraphAttribute;
import org.apache.lucene.analysis.miscellaneous.KeywordRepeatFilter;
import org.apache.lucene.analysis.miscellaneous.LengthFilter;
import org.apache.lucene.analysis.miscellaneous.LimitTokenCountFilter;
@ -207,7 +208,17 @@ public class CommonAnalysisPlugin extends Plugin implements AnalysisPlugin {
filters.add(PreConfiguredTokenFilter.singleton("russian_stem", false, input -> new SnowballFilter(input, "Russian")));
filters.add(PreConfiguredTokenFilter.singleton("scandinavian_folding", true, ScandinavianFoldingFilter::new));
filters.add(PreConfiguredTokenFilter.singleton("scandinavian_normalization", true, ScandinavianNormalizationFilter::new));
filters.add(PreConfiguredTokenFilter.singleton("shingle", false, ShingleFilter::new));
filters.add(PreConfiguredTokenFilter.singleton("shingle", false, input -> {
TokenStream ts = new ShingleFilter(input);
/**
* We disable the graph analysis on this token stream
* because it produces shingles of different size.
* Graph analysis on such token stream is useless and dangerous as it may create too many paths
* since shingles of different size are not aligned in terms of positions.
*/
ts.addAttribute(DisableGraphAttribute.class);
return ts;
}));
filters.add(PreConfiguredTokenFilter.singleton("snowball", false, input -> new SnowballFilter(input, "English")));
filters.add(PreConfiguredTokenFilter.singleton("sorani_normalization", true, SoraniNormalizationFilter::new));
filters.add(PreConfiguredTokenFilter.singleton("stemmer", false, PorterStemFilter::new));

66
modules/analysis-common/src/test/java/org/elasticsearch/analysis/common/ShingleTokenFilterTests.java Normal file
View File

@ -0,0 +1,66 @@
/*
* 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.analysis.common;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.miscellaneous.DisableGraphAttribute;
import org.elasticsearch.Version;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.cluster.metadata.IndexMetaData;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.analysis.AnalysisTestsHelper;
import org.elasticsearch.index.analysis.IndexAnalyzers;
import org.elasticsearch.index.analysis.NamedAnalyzer;
import org.elasticsearch.index.analysis.TokenFilterFactory;
import org.elasticsearch.index.query.Operator;
import org.elasticsearch.plugins.Plugin;
import org.elasticsearch.test.ESIntegTestCase;
import org.elasticsearch.test.ESTestCase;
import org.elasticsearch.test.ESTokenStreamTestCase;
import org.elasticsearch.test.IndexSettingsModule;
import java.io.StringReader;
import java.util.Arrays;
import java.util.Collection;
import static org.elasticsearch.index.query.QueryBuilders.queryStringQuery;
import static org.elasticsearch.test.ESTestCase.createTestAnalysis;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertHitCount;
public class ShingleTokenFilterTests extends ESTokenStreamTestCase {
public void testPreConfiguredShingleFilterDisableGraphAttribute() throws Exception {
ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(
Settings.builder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_ascii_folding.type", "asciifolding")
.build(),
new CommonAnalysisPlugin());
TokenFilterFactory tokenFilter = analysis.tokenFilter.get("shingle");
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader("this is a test"));
TokenStream tokenStream = tokenFilter.create(tokenizer);
assertTrue(tokenStream.hasAttribute(DisableGraphAttribute.class));
}
}