From a1f3cebe5013878cfc7b3a6bd13402750a8a87d5 Mon Sep 17 00:00:00 2001
From: Tommaso Teofili <tommaso@apache.org>
Date: Wed, 12 Nov 2014 08:38:53 +0000
Subject: [PATCH] LUCENE-5736 - adding test for caching nb classifier

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1638717 13f79535-47bb-0310-9956-ffa450edef68
---
 .../CachingNaiveBayesClassifierTest.java      | 65 +++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 lucene/classification/src/test/org/apache/lucene/classification/CachingNaiveBayesClassifierTest.java

diff --git a/lucene/classification/src/test/org/apache/lucene/classification/CachingNaiveBayesClassifierTest.java b/lucene/classification/src/test/org/apache/lucene/classification/CachingNaiveBayesClassifierTest.java
new file mode 100644
index 00000000000..ef58d7c5a20
--- /dev/null
+++ b/lucene/classification/src/test/org/apache/lucene/classification/CachingNaiveBayesClassifierTest.java
@@ -0,0 +1,65 @@
+package org.apache.lucene.classification;
+
+/*
+ * 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 org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.core.KeywordTokenizer;
+import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
+import org.apache.lucene.analysis.reverse.ReverseStringFilter;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.util.BytesRef;
+import org.junit.Test;
+
+/**
+ * Testcase for {@link org.apache.lucene.classification.CachingNaiveBayesClassifier
+ */
+public class CachingNaiveBayesClassifierTest extends ClassificationTestBase<BytesRef> {
+
+  @Test
+  public void testBasicUsage() throws Exception {
+    checkCorrectClassification(new CachingNaiveBayesClassifier(), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT, new MockAnalyzer(random()), textFieldName, categoryFieldName);
+    checkCorrectClassification(new CachingNaiveBayesClassifier(), POLITICS_INPUT, POLITICS_RESULT, new MockAnalyzer(random()), textFieldName, categoryFieldName);
+  }
+
+  @Test
+  public void testBasicUsageWithQuery() throws Exception {
+    checkCorrectClassification(new CachingNaiveBayesClassifier(), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT, new MockAnalyzer(random()), textFieldName, categoryFieldName, new TermQuery(new Term(textFieldName, "it")));
+  }
+
+  @Test
+  public void testNGramUsage() throws Exception {
+    checkCorrectClassification(new CachingNaiveBayesClassifier(), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT, new NGramAnalyzer(), textFieldName, categoryFieldName);
+  }
+
+  private class NGramAnalyzer extends Analyzer {
+    @Override
+    protected TokenStreamComponents createComponents(String fieldName) {
+      final Tokenizer tokenizer = new KeywordTokenizer();
+      return new TokenStreamComponents(tokenizer, new ReverseStringFilter(new EdgeNGramTokenFilter(new ReverseStringFilter(tokenizer), 10, 20)));
+    }
+  }
+
+  @Test
+  public void testPerformance() throws Exception {
+    checkPerformance(new CachingNaiveBayesClassifier(), new MockAnalyzer(random()), categoryFieldName);
+  }
+
+}