pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiNormalizer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiNormalizer.java
new file mode 100644 (file)
index 0000000..8948729
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiNormalizer.java
@@ -0,0 +1,66 @@
+package org.apache.lucene.analysis.hi;
+
+/**
+ * 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 HindiNormalizer
+ */
+public class TestHindiNormalizer extends BaseTokenStreamTestCase {
+  /**
+   * Test some basic normalization, with an example from the paper.
+   */
+  public void testBasics() throws IOException {
+    check("अँगरेज़ी", "अंगरेजि");
+    check("अँगरेजी", "अंगरेजि");
+    check("अँग्रेज़ी", "अंगरेजि");
+    check("अँग्रेजी", "अंगरेजि");
+    check("अंगरेज़ी", "अंगरेजि");
+    check("अंगरेजी", "अंगरेजि");
+    check("अंग्रेज़ी", "अंगरेजि");
+    check("अंग्रेजी", "अंगरेजि");
+  }
+  
+  public void testDecompositions() throws IOException {
+    // removing nukta dot
+    check("क़िताब", "किताब");
+    check("फ़र्ज़", "फरज");
+    check("क़र्ज़", "करज");
+    // some other composed nukta forms
+    check("ऱऴख़ग़ड़ढ़य़", "रळखगडढय");
+    // removal of format (ZWJ/ZWNJ)
+    check("शार्‍मा", "शारमा");
+    check("शार्‌मा", "शारमा");
+    // removal of chandra
+    check("ॅॆॉॊऍऎऑऒ\u0972", "ेेोोएएओओअ");
+    // vowel shortening
+    check("आईऊॠॡऐऔीूॄॣैौ", "अइउऋऌएओिुृॢेो");
+  }
+  private void check(String input, String output) throws IOException {
+    Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
+    TokenFilter tf = new HindiNormalizationFilter(tokenizer);
+    assertTokenStreamContents(tf, new String[] { output });
+  }
+}