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

Expose FlattenGraphTokenFilter (#22643) 

FlattenGraphTokenFilter is necessary for using graph-based token streams (e.g. the new SynonymGraphFilter) during indexing.
This commit is contained in:
Michael McCandless 2017-01-16 16:53:32 -05:00 committed by GitHub
parent d80e3eea6c
commit ebd38e2a6a
3 changed files with 113 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
core/src/main/java/org/elasticsearch/index/analysis/FlattenGraphTokenFilterFactory.java Normal file
View File

@ -0,0 +1,38 @@
/*
* 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.synonym.FlattenGraphFilter;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
public class FlattenGraphTokenFilterFactory extends AbstractTokenFilterFactory {
public FlattenGraphTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
super(indexSettings, name, settings);
}
@Override
public TokenStream create(TokenStream tokenStream) {
return new FlattenGraphFilter(tokenStream);
}
}

73
core/src/test/java/org/elasticsearch/index/analysis/FlattenGraphTokenFilterFactoryTests.java Normal file
View File

@ -0,0 +1,73 @@
/*
* 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 java.io.IOException;
import org.apache.lucene.analysis.CannedTokenStream;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.test.ESTokenStreamTestCase;
import org.elasticsearch.test.IndexSettingsModule;
public class FlattenGraphTokenFilterFactoryTests extends ESTokenStreamTestCase {
public void testBasic() throws IOException {
Index index = new Index("test", "_na_");
String name = "ngr";
Settings indexSettings = newAnalysisSettingsBuilder().build();
IndexSettings indexProperties = IndexSettingsModule.newIndexSettings(index, indexSettings);
Settings settings = newAnalysisSettingsBuilder().build();
// "wow that's funny" and "what the fudge" are separate side paths, in parallel with "wtf", on input:
TokenStream in = new CannedTokenStream(0, 12, new Token[] {
token("wtf", 1, 5, 0, 3),
token("what", 0, 1, 0, 3),
token("wow", 0, 3, 0, 3),
token("the", 1, 1, 0, 3),
token("fudge", 1, 3, 0, 3),
token("that's", 1, 1, 0, 3),
token("funny", 1, 1, 0, 3),
token("happened", 1, 1, 4, 12)
});
TokenStream tokens = new FlattenGraphTokenFilterFactory(indexProperties, null, name, settings).create(in);
// ... but on output, it's flattened to wtf/what/wow that's/the fudge/funny happened:
assertTokenStreamContents(tokens,
new String[] {"wtf", "what", "wow", "the", "that's", "fudge", "funny", "happened"},
new int[] {0, 0, 0, 0, 0, 0, 0, 4},
new int[] {3, 3, 3, 3, 3, 3, 3, 12},
new int[] {1, 0, 0, 1, 0, 1, 0, 1},
new int[] {3, 1, 1, 1, 1, 1, 1, 1},
12);
}
private static Token token(String term, int posInc, int posLength, int startOffset, int endOffset) {
final Token t = new Token(term, startOffset, endOffset);
t.setPositionIncrement(posInc);
t.setPositionLength(posLength);
return t;
}
}

4
test/framework/src/main/java/org/elasticsearch/AnalysisFactoryTestCase.java
View File

@ -42,6 +42,7 @@ import org.elasticsearch.index.analysis.DelimitedPayloadTokenFilterFactory;
import org.elasticsearch.index.analysis.EdgeNGramTokenFilterFactory;
import org.elasticsearch.index.analysis.EdgeNGramTokenizerFactory;
import org.elasticsearch.index.analysis.ElisionTokenFilterFactory;
import org.elasticsearch.index.analysis.FlattenGraphTokenFilterFactory;
import org.elasticsearch.index.analysis.GermanNormalizationFilterFactory;
import org.elasticsearch.index.analysis.GermanStemTokenFilterFactory;
import org.elasticsearch.index.analysis.HindiNormalizationFilterFactory;
@ -248,6 +249,7 @@ public class AnalysisFactoryTestCase extends ESTestCase {
.put("type", KeepTypesFilterFactory.class)
.put("uppercase", UpperCaseTokenFilterFactory.class)
.put("worddelimiter", WordDelimiterTokenFilterFactory.class)
.put("flattengraph", FlattenGraphTokenFilterFactory.class)
// TODO: these tokenfilters are not yet exposed: useful?
@ -277,8 +279,6 @@ public class AnalysisFactoryTestCase extends ESTestCase {
.put("fingerprint", Void.class)
// for tee-sinks
.put("daterecognizer", Void.class)
// to flatten graphs created by the synonym graph filter
.put("flattengraph", Void.class)
.immutableMap();