pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / analyzers / common / src / test / org / apache / lucene / analysis / in / TestIndicNormalizer.java

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/in/TestIndicNormalizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/in/TestIndicNormalizer.java
new file mode 100644 (file)
index 0000000..e26f6e8
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/in/TestIndicNormalizer.java
@@ -0,0 +1,51 @@
+package org.apache.lucene.analysis.in;
+
+/**
+ * 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.io.IOException;
+import java.io.StringReader;
+
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.Tokenizer;
+
+/**
+ * Test IndicNormalizer
+ */
+public class TestIndicNormalizer extends BaseTokenStreamTestCase {
+  /**
+   * Test some basic normalization
+   */
+  public void testBasics() throws IOException {
+    check("अाॅअाॅ", "ऑऑ");
+    check("अाॆअाॆ", "ऒऒ");
+    check("अाेअाे", "ओओ");
+    check("अाैअाै", "औऔ");
+    check("अाअा", "आआ");
+    check("अाैर", "और");
+    // khanda-ta
+    check("ত্‍", "ৎ");
+  }
+  
+  private void check(String input, String output) throws IOException {
+    Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);;
+    TokenFilter tf = new IndicNormalizationFilter(tokenizer);
+    assertTokenStreamContents(tf, new String[] { output });
+  }
+}