Analysis: Add keep_types for filtering by token type

This commit is contained in:
Robert Muir 2014-08-15 09:28:12 -04:00
parent f4d75f0212
commit 5c7cefa292
6 changed files with 162 additions and 2 deletions

View File

@ -79,6 +79,8 @@ include::tokenfilters/delimited-payload-tokenfilter.asciidoc[]
include::tokenfilters/keep-words-tokenfilter.asciidoc[]
include::tokenfilters/keep-types-tokenfilter.asciidoc[]
include::tokenfilters/classic-tokenfilter.asciidoc[]
include::tokenfilters/apostrophe-tokenfilter.asciidoc[]

View File

@ -0,0 +1,39 @@
[[analysis-keep-types-tokenfilter]]
=== Keep Types Token Filter
coming[1.4.0]
A token filter of type `keep_types` that only keeps tokens with a token type
contained in a predefined set.
[float]
=== Options
[horizontal]
types:: a list of types to keep
[float]
=== Settings example
[source,js]
--------------------------------------------------
{
"index" : {
"analysis" : {
"analyzer" : {
"my_analyzer" : {
"tokenizer" : "standard",
"filter" : ["standard", "lowercase", "extract_numbers"]
},
},
"filter" : {
"extract_numbers" : {
"type" : "keep_types",
"types" : [ "<NUM>" ]
},
}
}
}
}
--------------------------------------------------

View File

@ -485,6 +485,7 @@ public class AnalysisModule extends AbstractModule {
tokenFiltersBindings.processTokenFilter("synonym", SynonymTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("elision", ElisionTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("keep", KeepWordFilterFactory.class);
tokenFiltersBindings.processTokenFilter("keep_types", KeepTypesFilterFactory.class);
tokenFiltersBindings.processTokenFilter("pattern_capture", PatternCaptureGroupTokenFilterFactory.class);
tokenFiltersBindings.processTokenFilter("pattern_replace", PatternReplaceTokenFilterFactory.class);

View File

@ -0,0 +1,69 @@
/*
* 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.TypeTokenFilter;
import org.elasticsearch.ElasticsearchIllegalArgumentException;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
import java.util.Arrays;
import java.util.HashSet;
import java.util.Set;
/**
* A {@link TokenFilterFactory} for {@link TypeFilter}. This filter only
* keep tokens that are contained in the set configured via
* {@value #KEEP_TYPES_KEY} setting.
* <p/>
* Configuration options:
* <p/>
* <ul>
* <li>{@value #KEEP_TYPES_KEY} the array of words / tokens to keep.</li>
* </ul>
*/
@AnalysisSettingsRequired
public class KeepTypesFilterFactory extends AbstractTokenFilterFactory {
private final Set<String> keepTypes;
private static final String KEEP_TYPES_KEY = "types";
@Inject
public KeepTypesFilterFactory(Index index, @IndexSettings Settings indexSettings,
Environment env, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
final String[] arrayKeepTypes = settings.getAsArray(KEEP_TYPES_KEY, null);
if ((arrayKeepTypes == null)) {
throw new ElasticsearchIllegalArgumentException("keep_types requires `" + KEEP_TYPES_KEY + "` to be configured");
}
this.keepTypes = new HashSet<>(Arrays.asList(arrayKeepTypes));
}
@Override
public TokenStream create(TokenStream tokenStream) {
return new TypeTokenFilter(version, tokenStream, keepTypes, true);
}
}

View File

@ -147,6 +147,7 @@ public class AnalysisFactoryTests extends ElasticsearchTestCase {
put("trim", TrimTokenFilterFactory.class);
put("truncate", TruncateTokenFilterFactory.class);
put("turkishlowercase", LowerCaseTokenFilterFactory.class);
put("type", KeepTypesFilterFactory.class);
put("uppercase", UpperCaseTokenFilterFactory.class);
put("worddelimiter", WordDelimiterTokenFilterFactory.class);
@ -168,8 +169,6 @@ public class AnalysisFactoryTests extends ElasticsearchTestCase {
put("removeduplicates", Void.class);
// ???
put("tokenoffsetpayload", Void.class);
// like a stop filter but by token-type
put("type", Void.class);
// puts the type into the payload
put("typeaspayload", Void.class);
}};

View File

@ -0,0 +1,50 @@
/*
* 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.Tokenizer;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.elasticsearch.common.settings.ImmutableSettings;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.test.ElasticsearchTokenStreamTestCase;
import org.junit.Test;
import java.io.IOException;
import java.io.StringReader;
import static org.hamcrest.Matchers.instanceOf;
public class KeepTypesFilterFactoryTests extends ElasticsearchTokenStreamTestCase {
@Test
public void testKeepTypes() throws IOException {
Settings settings = ImmutableSettings.settingsBuilder()
.put("index.analysis.filter.keep_numbers.type", "keep_types")
.putArray("index.analysis.filter.keep_numbers.types", new String[] {"<NUM>", "<SOMETHINGELSE>"})
.build();
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
TokenFilterFactory tokenFilter = analysisService.tokenFilter("keep_numbers");
assertThat(tokenFilter, instanceOf(KeepTypesFilterFactory.class));
String source = "Hello 123 world";
String[] expected = new String[]{"123"};
Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected, new int[]{2});
}
}