- SOLR-307: Added Factories for NGram Filters.

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@557622 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -103,7 +103,10 @@ New Features
 17. SOLR-248: Added CapitalizationFilterFactory that creates tokens with 
     normalized capitalization.  This filter is useful for facet display,
     but will not work with a prefix query.  (ryan)
-    
+
+18. SOLR-307: Added NGramFilterFactory and EdgeNGramFilterFactory.
+    (Thomas Peuss via Otis Gospodnetic)
+
 Changes in runtime behavior
 
 Optimizations

src/java/org/apache/solr/analysis/EdgeNGramFilterFactory.java

@@ -0,0 +1,55 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF 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.
+ */
+
+import java.util.Map;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
+
+/**
+ * Creates new instances of {@link EdgeNGramTokenFilter}.
+ */
+public class EdgeNGramFilterFactory extends BaseTokenFilterFactory {
+  private int maxGramSize = 0;
+
+  private int minGramSize = 0;
+
+  private String side;
+
+  @Override
+  public void init(Map<String, String> args) {
+    super.init(args);
+    String maxArg = args.get("maxGramSize");
+    maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
+        : EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
+
+    String minArg = args.get("minGramSize");
+    minGramSize = (minArg != null ? Integer.parseInt(minArg)
+        : EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE);
+
+    side = args.get("side");
+    if (side == null) {
+      side = EdgeNGramTokenFilter.Side.FRONT.getLabel();
+    }
+  }
+
+  public TokenStream create(TokenStream input) {
+    return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
+  }
+}

src/java/org/apache/solr/analysis/NGramFilterFactory.java

@@ -0,0 +1,49 @@
+package org.apache.solr.analysis;
+
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF 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.
+ */
+
+import java.util.Map;
+
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.ngram.NGramTokenFilter;
+
+/**
+ * Creates new instances of {@link NGramTokenFilter}.
+ */
+public class NGramFilterFactory extends BaseTokenFilterFactory {
+  private int maxGramSize = 0;
+
+  private int minGramSize = 0;
+
+  /** Initializes the n-gram min and max sizes and the side from which one should start tokenizing. */
+  @Override
+  public void init(Map<String, String> args) {
+    super.init(args);
+    String maxArg = args.get("maxGramSize");
+    maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
+        : NGramTokenFilter.DEFAULT_MAX_NGRAM_SIZE);
+
+    String minArg = args.get("minGramSize");
+    minGramSize = (minArg != null ? Integer.parseInt(minArg)
+        : NGramTokenFilter.DEFAULT_MIN_NGRAM_SIZE);
+  }
+
+  public TokenStream create(TokenStream input) {
+    return new NGramTokenFilter(input, minGramSize, maxGramSize);
+  }
+}