Support for Latvian stemming: `latvian` analyzer and `latvian` language for stemmer filter, closes #1842.

src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java

@@ -498,6 +498,7 @@ public class AnalysisModule extends AbstractModule {
             analyzersBindings.processAnalyzer("hungarian", HungarianAnalyzerProvider.class);
             analyzersBindings.processAnalyzer("indonesian", IndonesianAnalyzerProvider.class);
             analyzersBindings.processAnalyzer("italian", ItalianAnalyzerProvider.class);
+            analyzersBindings.processAnalyzer("latvian", LatvianAnalyzerProvider.class);
             analyzersBindings.processAnalyzer("norwegian", NorwegianAnalyzerProvider.class);
             analyzersBindings.processAnalyzer("persian", PersianAnalyzerProvider.class);
             analyzersBindings.processAnalyzer("portuguese", PortugueseAnalyzerProvider.class);

src/main/java/org/elasticsearch/index/analysis/LatvianAnalyzerProvider.java

@@ -0,0 +1,50 @@
+/*
+ * 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.CharArraySet;
+import org.apache.lucene.analysis.lv.LatvianAnalyzer;
+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;
+
+/**
+ *
+ */
+public class LatvianAnalyzerProvider extends AbstractIndexAnalyzerProvider<LatvianAnalyzer> {
+
+    private final LatvianAnalyzer analyzer;
+
+    @Inject
+    public LatvianAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name, settings);
+        analyzer = new LatvianAnalyzer(version,
+                Analysis.parseStopWords(env, settings, LatvianAnalyzer.getDefaultStopSet(), version),
+                Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET));
+    }
+
+    @Override
+    public LatvianAnalyzer get() {
+        return this.analyzer;
+    }
+}

src/main/java/org/elasticsearch/index/analysis/StemmerTokenFilterFactory.java

@@ -38,6 +38,7 @@ import org.apache.lucene.analysis.hi.HindiStemFilter;
 import org.apache.lucene.analysis.hu.HungarianLightStemFilter;
 import org.apache.lucene.analysis.id.IndonesianStemFilter;
 import org.apache.lucene.analysis.it.ItalianLightStemFilter;
+import org.apache.lucene.analysis.lv.LatvianStemFilter;
 import org.apache.lucene.analysis.pt.PortugueseLightStemFilter;
 import org.apache.lucene.analysis.pt.PortugueseMinimalStemFilter;
 import org.apache.lucene.analysis.pt.PortugueseStemFilter;
@@ -102,6 +103,8 @@ public class StemmerTokenFilterFactory extends AbstractTokenFilterFactory {
             return new KStemFilter(tokenStream);
         } else if ("lovins".equalsIgnoreCase(language)) {
             return new SnowballFilter(tokenStream, new LovinsStemmer());
+        } else if ("latvian".equalsIgnoreCase(language)) {
+            return new LatvianStemFilter(tokenStream);
         } else if ("norwegian".equalsIgnoreCase(language)) {
             return new SnowballFilter(tokenStream, new NorwegianStemmer());
         } else if ("porter".equalsIgnoreCase(language)) {

src/main/java/org/elasticsearch/indices/analysis/IndicesAnalysisService.java

@@ -49,6 +49,7 @@ import org.apache.lucene.analysis.hu.HungarianAnalyzer;
 import org.apache.lucene.analysis.hy.ArmenianAnalyzer;
 import org.apache.lucene.analysis.id.IndonesianAnalyzer;
 import org.apache.lucene.analysis.it.ItalianAnalyzer;
+import org.apache.lucene.analysis.lv.LatvianAnalyzer;
 import org.apache.lucene.analysis.miscellaneous.*;
 import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
 import org.apache.lucene.analysis.ngram.EdgeNGramTokenizer;
@@ -141,6 +142,7 @@ public class IndicesAnalysisService extends AbstractComponent {
         analyzerProviderFactories.put("hungarian", new PreBuiltAnalyzerProviderFactory("hungarian", AnalyzerScope.INDICES, new HungarianAnalyzer(Lucene.ANALYZER_VERSION)));
         analyzerProviderFactories.put("indonesian", new PreBuiltAnalyzerProviderFactory("indonesian", AnalyzerScope.INDICES, new IndonesianAnalyzer(Lucene.ANALYZER_VERSION)));
         analyzerProviderFactories.put("italian", new PreBuiltAnalyzerProviderFactory("italian", AnalyzerScope.INDICES, new ItalianAnalyzer(Lucene.ANALYZER_VERSION)));
+        analyzerProviderFactories.put("latvian", new PreBuiltAnalyzerProviderFactory("latvian", AnalyzerScope.INDICES, new LatvianAnalyzer(Lucene.ANALYZER_VERSION)));
         analyzerProviderFactories.put("norwegian", new PreBuiltAnalyzerProviderFactory("norwegian", AnalyzerScope.INDICES, new NorwegianAnalyzer(Lucene.ANALYZER_VERSION)));
         analyzerProviderFactories.put("persian", new PreBuiltAnalyzerProviderFactory("persian", AnalyzerScope.INDICES, new PersianAnalyzer(Lucene.ANALYZER_VERSION)));
         analyzerProviderFactories.put("portuguese", new PreBuiltAnalyzerProviderFactory("portuguese", AnalyzerScope.INDICES, new PortugueseAnalyzer(Lucene.ANALYZER_VERSION)));