-
Notifications
You must be signed in to change notification settings - Fork 24.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Use preconfigured filters correctly in Analyze API (#43568)
When a named token filter or char filter is passed as part of an Analyze API request with no index, we currently try and build the relevant filter using no index settings. However, this can miss cases where there is a pre-configured filter defined in the analysis registry. One example here is the elision filter, which has a pre-configured version built with the french elision set; when used as part of normal analysis, this preconfigured set is used, but when used as part of the Analyze API we end up with NPEs because it tries to instantiate the filter with no index settings. This commit changes the Analyze API to check for pre-configured filters in the case that the request has no index defined, and is using a name rather than a custom definition for a filter. It also changes the pre-configured `word_delimiter_graph` filter and `edge_ngram` tokenizer to make their settings consistent with the defaults used when creating them with no settings Closes #43002 Closes #43621 Closes #43582
- Loading branch information
1 parent
d2c696d
commit fbefb46
Showing
5 changed files
with
208 additions
and
37 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
98 changes: 98 additions & 0 deletions
98
...lysis-common/src/test/java/org/elasticsearch/analysis/common/EdgeNGramTokenizerTests.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,98 @@ | ||
| /* | ||
| * 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.elasticsearch.Version; | ||
| import org.elasticsearch.cluster.metadata.IndexMetaData; | ||
| import org.elasticsearch.common.settings.Settings; | ||
| import org.elasticsearch.env.Environment; | ||
| import org.elasticsearch.env.TestEnvironment; | ||
| import org.elasticsearch.index.IndexSettings; | ||
| import org.elasticsearch.index.analysis.IndexAnalyzers; | ||
| import org.elasticsearch.index.analysis.NamedAnalyzer; | ||
| import org.elasticsearch.indices.analysis.AnalysisModule; | ||
| import org.elasticsearch.test.ESTokenStreamTestCase; | ||
| import org.elasticsearch.test.IndexSettingsModule; | ||
| import org.elasticsearch.test.VersionUtils; | ||
|
|
||
| import java.io.IOException; | ||
| import java.util.Collections; | ||
|
|
||
| public class EdgeNGramTokenizerTests extends ESTokenStreamTestCase { | ||
|
|
||
| private IndexAnalyzers buildAnalyzers(Version version, String tokenizer) throws IOException { | ||
| Settings settings = Settings.builder() | ||
| .put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString()) | ||
| .build(); | ||
| Settings indexSettings = Settings.builder() | ||
| .put(IndexMetaData.SETTING_VERSION_CREATED, version) | ||
| .put("index.analysis.analyzer.my_analyzer.tokenizer", tokenizer) | ||
| .build(); | ||
| IndexSettings idxSettings = IndexSettingsModule.newIndexSettings("index", indexSettings); | ||
| return new AnalysisModule(TestEnvironment.newEnvironment(settings), | ||
| Collections.singletonList(new CommonAnalysisPlugin())).getAnalysisRegistry().build(idxSettings); | ||
| } | ||
|
|
||
| public void testPreConfiguredTokenizer() throws IOException { | ||
|
|
||
| // Before 7.3 we return ngrams of length 1 only | ||
| { | ||
| Version version = VersionUtils.randomVersionBetween(random(), Version.V_7_0_0, | ||
| VersionUtils.getPreviousVersion(Version.V_7_3_0)); | ||
| try (IndexAnalyzers indexAnalyzers = buildAnalyzers(version, "edge_ngram")) { | ||
| NamedAnalyzer analyzer = indexAnalyzers.get("my_analyzer"); | ||
| assertNotNull(analyzer); | ||
| assertAnalyzesTo(analyzer, "test", new String[]{"t"}); | ||
| } | ||
| } | ||
|
|
||
| // Check deprecated name as well | ||
| { | ||
| Version version = VersionUtils.randomVersionBetween(random(), Version.V_7_0_0, | ||
| VersionUtils.getPreviousVersion(Version.V_7_3_0)); | ||
| try (IndexAnalyzers indexAnalyzers = buildAnalyzers(version, "edgeNGram")) { | ||
| NamedAnalyzer analyzer = indexAnalyzers.get("my_analyzer"); | ||
| assertNotNull(analyzer); | ||
| assertAnalyzesTo(analyzer, "test", new String[]{"t"}); | ||
| } | ||
| } | ||
|
|
||
| // Afterwards, we return ngrams of length 1 and 2, to match the default factory settings | ||
| { | ||
| try (IndexAnalyzers indexAnalyzers = buildAnalyzers(Version.CURRENT, "edge_ngram")) { | ||
| NamedAnalyzer analyzer = indexAnalyzers.get("my_analyzer"); | ||
| assertNotNull(analyzer); | ||
| assertAnalyzesTo(analyzer, "test", new String[]{"t", "te"}); | ||
| } | ||
| } | ||
|
|
||
| // Check deprecated name as well | ||
| { | ||
| try (IndexAnalyzers indexAnalyzers = buildAnalyzers(Version.CURRENT, "edgeNGram")) { | ||
| NamedAnalyzer analyzer = indexAnalyzers.get("my_analyzer"); | ||
| assertNotNull(analyzer); | ||
| assertAnalyzesTo(analyzer, "test", new String[]{"t", "te"}); | ||
|
|
||
| } | ||
| } | ||
|
|
||
| } | ||
|
|
||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.