Analysis: Unique token filter, closes #1185.

modules/elasticsearch/src/main/java/org/apache/lucene/analysis/miscellaneous/UniqueTokenFilter.java

@@ -0,0 +1,88 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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.apache.lucene.analysis.miscellaneous;
+
+import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.util.Version;
+
+import java.io.IOException;
+
+/**
+ * A token filter that generates unique tokens. Can remove unique tokens only on the same
+ * position increments as well.
+ */
+public class UniqueTokenFilter extends TokenFilter {
+
+    private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class);
+    private final PositionIncrementAttribute posIncAttribute = addAttribute(PositionIncrementAttribute.class);
+
+    // use a fixed version, as we don't care about case sensitivity.
+    private final CharArraySet previous = new CharArraySet(Version.LUCENE_31, 8, false);
+    private final boolean onlyOnSamePosition;
+
+    public UniqueTokenFilter(TokenStream in) {
+        this(in, false);
+    }
+
+    public UniqueTokenFilter(TokenStream in, boolean onlyOnSamePosition) {
+        super(in);
+        this.onlyOnSamePosition = onlyOnSamePosition;
+    }
+
+    @Override public final boolean incrementToken() throws IOException {
+        while (input.incrementToken()) {
+            final char term[] = termAttribute.buffer();
+            final int length = termAttribute.length();
+
+            boolean duplicate;
+            if (onlyOnSamePosition) {
+                final int posIncrement = posIncAttribute.getPositionIncrement();
+                if (posIncrement > 0) {
+                    previous.clear();
+                }
+
+                duplicate = (posIncrement == 0 && previous.contains(term, 0, length));
+            } else {
+                duplicate = previous.contains(term, 0, length);
+            }
+
+            // clone the term, and add to the set of seen terms.
+            char saved[] = new char[length];
+            System.arraycopy(term, 0, saved, 0, length);
+            previous.add(saved);
+
+            if (!duplicate) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    @Override public final void reset() throws IOException {
+        super.reset();
+        previous.clear();
+    }
+}
+
+

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

@@ -337,6 +337,7 @@ public class AnalysisModule extends AbstractModule {
             tokenFiltersBindings.processTokenFilter("edgeNGram", EdgeNGramTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("edge_ngram", EdgeNGramTokenFilterFactory.class);
             tokenFiltersBindings.processTokenFilter("shingle", ShingleTokenFilterFactory.class);
+            tokenFiltersBindings.processTokenFilter("unique", UniqueTokenFilterFactory.class);
         }
 
         @Override public void processTokenizers(TokenizersBindings tokenizersBindings) {

modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/UniqueTokenFilterFactory.java

@@ -0,0 +1,46 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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.miscellaneous.UniqueTokenFilter;
+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;
+
+/**
+ *
+ */
+public class UniqueTokenFilterFactory extends AbstractTokenFilterFactory {
+
+    private final boolean onlyOnSamePosition;
+
+    @Inject public UniqueTokenFilterFactory(Index index, @IndexSettings Settings indexSettings,
+                                            @Assisted String name, @Assisted Settings settings) {
+        super(index, indexSettings, name, settings);
+        this.onlyOnSamePosition = settings.getAsBoolean("only_on_same_position", false);
+    }
+
+    @Override public TokenStream create(TokenStream tokenStream) {
+        return new UniqueTokenFilter(tokenStream, onlyOnSamePosition);
+    }
+}

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

@@ -49,6 +49,7 @@ 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.miscellaneous.PatternAnalyzer;
+import org.apache.lucene.analysis.miscellaneous.UniqueTokenFilter;
 import org.apache.lucene.analysis.miscellaneous.WordDelimiterFilter;
 import org.apache.lucene.analysis.miscellaneous.WordDelimiterIterator;
 import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
@@ -422,6 +423,16 @@ public class IndicesAnalysisService extends AbstractComponent {
             }
         }));
 
+        tokenFilterFactories.put("unique", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() {
+            @Override public String name() {
+                return "unique";
+            }
+
+            @Override public TokenStream create(TokenStream tokenStream) {
+                return new UniqueTokenFilter(tokenStream);
+            }
+        }));
+
         // Extended Token Filters
         tokenFilterFactories.put("snowball", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() {
             @Override public String name() {

modules/elasticsearch/src/test/java/org/apache/lucene/analysis/miscellaneous/UniqueTokenFilterTests.java

@@ -0,0 +1,66 @@
+/*
+ * Licensed to Elastic Search and Shay Banon under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. Elastic Search 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.apache.lucene.analysis.miscellaneous;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.ReusableAnalyzerBase;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.WhitespaceTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.elasticsearch.common.lucene.Lucene;
+import org.testng.annotations.Test;
+
+import java.io.IOException;
+import java.io.Reader;
+import java.io.StringReader;
+
+import static org.hamcrest.MatcherAssert.*;
+import static org.hamcrest.Matchers.*;
+
+/**
+ */
+@Test
+public class UniqueTokenFilterTests {
+
+    @Test public void simpleTest() throws IOException {
+        Analyzer analyzer = new ReusableAnalyzerBase() {
+            @Override
+            protected TokenStreamComponents createComponents(String fieldName,
+                                                             Reader reader) {
+                Tokenizer t = new WhitespaceTokenizer(Lucene.VERSION, reader);
+                return new TokenStreamComponents(t, new UniqueTokenFilter(t));
+            }
+        };
+
+        TokenStream test = analyzer.reusableTokenStream("test", new StringReader("this test with test"));
+        CharTermAttribute termAttribute = test.addAttribute(CharTermAttribute.class);
+        assertThat(test.incrementToken(), equalTo(true));
+        assertThat(termAttribute.toString(), equalTo("this"));
+
+        assertThat(test.incrementToken(), equalTo(true));
+        assertThat(termAttribute.toString(), equalTo("test"));
+
+        assertThat(test.incrementToken(), equalTo(true));
+        assertThat(termAttribute.toString(), equalTo("with"));
+
+        assertThat(test.incrementToken(), equalTo(false));
+    }
+}