Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
/*
* Licensed to ElasticSearch and Shay Banon 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.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.synonym.SolrSynonymParser;
import org.apache.lucene.analysis.synonym.SynonymFilter;
import org.apache.lucene.analysis.synonym.SynonymMap;
import org.apache.lucene.analysis.synonym.WordnetSynonymParser;
import org.elasticsearch.ElasticSearchIllegalArgumentException;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.io.FastStringReader;
import org.elasticsearch.common.lucene.Lucene;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
import org.elasticsearch.indices.analysis.IndicesAnalysisService;
import java.io.Reader;
import java.util.List;
import java.util.Map;
@AnalysisSettingsRequired
public class SynonymTokenFilterFactory extends AbstractTokenFilterFactory {
private final SynonymMap synonymMap;
private final boolean ignoreCase;
@Inject
public SynonymTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, Environment env, IndicesAnalysisService indicesAnalysisService, Map tokenizerFactories,
@Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name, settings);
Reader rulesReader = null;
if (settings.getAsArray("synonyms", null) != null) {
List rules = Analysis.getWordList(env, settings, "synonyms");
StringBuilder sb = new StringBuilder();
for (String line : rules) {
sb.append(line).append(System.getProperty("line.separator"));
}
rulesReader = new FastStringReader(sb.toString());
} else if (settings.get("synonyms_path") != null) {
rulesReader = Analysis.getReaderFromFile(env, settings, "synonyms_path");
} else {
throw new ElasticSearchIllegalArgumentException("synonym requires either `synonyms` or `synonyms_path` to be configured");
}
this.ignoreCase = settings.getAsBoolean("ignore_case", false);
boolean expand = settings.getAsBoolean("expand", true);
String tokenizerName = settings.get("tokenizer", "whitespace");
TokenizerFactoryFactory tokenizerFactoryFactory = tokenizerFactories.get(tokenizerName);
if (tokenizerFactoryFactory == null) {
tokenizerFactoryFactory = indicesAnalysisService.tokenizerFactoryFactory(tokenizerName);
}
if (tokenizerFactoryFactory == null) {
throw new ElasticSearchIllegalArgumentException("failed to find tokenizer [" + tokenizerName + "] for synonym token filter");
}
final TokenizerFactory tokenizerFactory = tokenizerFactoryFactory.create(tokenizerName, settings);
Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
Tokenizer tokenizer = tokenizerFactory == null ? new WhitespaceTokenizer(Lucene.ANALYZER_VERSION, reader) : tokenizerFactory.create(reader);
TokenStream stream = ignoreCase ? new LowerCaseFilter(Lucene.ANALYZER_VERSION, tokenizer) : tokenizer;
return new TokenStreamComponents(tokenizer, stream);
}
};
try {
SynonymMap.Builder parser = null;
if ("wordnet".equalsIgnoreCase(settings.get("format"))) {
parser = new WordnetSynonymParser(true, expand, analyzer);
((WordnetSynonymParser) parser).add(rulesReader);
} else {
parser = new SolrSynonymParser(true, expand, analyzer);
((SolrSynonymParser) parser).add(rulesReader);
}
synonymMap = parser.build();
} catch (Exception e) {
throw new ElasticSearchIllegalArgumentException("failed to build synonyms", e);
}
}
@Override
public TokenStream create(TokenStream tokenStream) {
// fst is null means no synonyms
return synonymMap.fst == null ? tokenStream : new SynonymFilter(tokenStream, synonymMap, ignoreCase);
}
}