Support for polish_stem token filter

Added missing token filter support for polish analyzer.
Now it's possible to combine polish_stem token filter with the other token filters available in ES to create custom analyzer.
Closes #3.

README.md

@@ -23,7 +23,7 @@ In order to install the plugin, simply run: `bin/plugin -install elasticsearch/e
     | 1.0.0                         | 0.18             |
     ----------------------------------------------------
 
-The plugin includes the `polish` analyzer.
+The plugin includes the `polish` analyzer and `polish_stem` token filter.
 
 License
 -------

src/main/java/org/elasticsearch/index/analysis/pl/PolishAnalysisBinderProcessor.java

@@ -29,4 +29,8 @@ public class PolishAnalysisBinderProcessor extends AnalysisModule.AnalysisBinder
     public void processAnalyzers(AnalyzersBindings analyzersBindings) {
         analyzersBindings.processAnalyzer("polish", PolishAnalyzerProvider.class);
     }
+    @Override
+    public void processTokenFilters(TokenFiltersBindings tokenFiltersBindings) {
+        tokenFiltersBindings.processTokenFilter("polish_stem", PolishStemTokenFilterFactory.class);
+   }
 }

src/main/java/org/elasticsearch/index/analysis/pl/PolishStemTokenFilterFactory.java

@@ -0,0 +1,56 @@
+/*
+ * 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.pl;
+
+import org.apache.lucene.analysis.pl.PolishAnalyzer;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.stempel.StempelFilter;
+import org.apache.lucene.analysis.stempel.StempelStemmer;
+import org.egothor.stemmer.Trie;
+import org.elasticsearch.common.inject.Inject;
+import org.elasticsearch.common.inject.assistedinject.Assisted;
+import org.elasticsearch.common.settings.Settings;
+import org.elasticsearch.index.Index;
+import org.elasticsearch.index.settings.IndexSettings;
+import org.elasticsearch.index.analysis.AbstractTokenFilterFactory;
+
+import java.io.IOException;
+
+
+
+public class PolishStemTokenFilterFactory extends AbstractTokenFilterFactory {
+
+    private final StempelStemmer stemmer;
+
+    @Inject public PolishStemTokenFilterFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name, settings);
+        Trie tire;
+        try {
+            tire = StempelStemmer.load(PolishAnalyzer.class.getResourceAsStream(PolishAnalyzer.DEFAULT_STEMMER_FILE));
+        } catch (IOException ex) {
+            throw new RuntimeException("Unable to load default stemming tables", ex);
+        }
+        stemmer = new StempelStemmer(tire);
+    }
+
+    @Override public TokenStream create(TokenStream tokenStream) {
+        return new StempelFilter(tokenStream, stemmer);
+    }
+}

src/main/java/org/elasticsearch/indices/analysis/pl/PolishIndicesAnalysis.java

@@ -26,7 +26,16 @@ import org.elasticsearch.common.lucene.Lucene;
 import org.elasticsearch.common.settings.Settings;
 import org.elasticsearch.index.analysis.AnalyzerScope;
 import org.elasticsearch.index.analysis.PreBuiltAnalyzerProviderFactory;
+import org.elasticsearch.index.analysis.PreBuiltTokenFilterFactoryFactory;
 import org.elasticsearch.indices.analysis.IndicesAnalysisService;
+import org.elasticsearch.index.analysis.TokenFilterFactory;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.stempel.StempelFilter;
+import org.apache.lucene.analysis.stempel.StempelStemmer;
+import org.egothor.stemmer.Trie;
+
+import java.io.IOException;
 
 /**
  * Registers indices level analysis components so, if not explicitly configured, will be shared
@@ -38,5 +47,21 @@ public class PolishIndicesAnalysis extends AbstractComponent {
     public PolishIndicesAnalysis(Settings settings, IndicesAnalysisService indicesAnalysisService) {
         super(settings);
         indicesAnalysisService.analyzerProviderFactories().put("default", new PreBuiltAnalyzerProviderFactory("default", AnalyzerScope.INDICES, new PolishAnalyzer(Lucene.ANALYZER_VERSION)));
+
+        indicesAnalysisService.tokenFilterFactories().put("polish_stem", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() {
+            @Override public String name() {
+                return "polish_stem";
+            }
+
+            @Override public TokenStream create(TokenStream tokenStream) {
+                Trie tire;
+                try {
+                    tire = StempelStemmer.load(PolishAnalyzer.class.getResourceAsStream(PolishAnalyzer.DEFAULT_STEMMER_FILE));
+                } catch (IOException ex) {
+                    throw new RuntimeException("Unable to load default stemming tables", ex);
+                }
+                return new StempelFilter(tokenStream, new StempelStemmer(tire));
+            }
+        }));
     }
 }