pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / icu / src / test / org / apache / lucene / analysis / icu / TestICUNormalizer2Filter.java

diff --git a/lucene-java-3.5.0/lucene/contrib/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2Filter.java b/lucene-java-3.5.0/lucene/contrib/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2Filter.java
new file mode 100644 (file)
index 0000000..c8d00cd
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2Filter.java
@@ -0,0 +1,82 @@
+package org.apache.lucene.analysis.icu;
+
+/**
+ * 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.Reader;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.WhitespaceTokenizer;
+
+import com.ibm.icu.text.Normalizer2;
+
+/**
+ * Tests the ICUNormalizer2Filter
+ */
+public class TestICUNormalizer2Filter extends BaseTokenStreamTestCase {
+  Analyzer a = new Analyzer() {
+    @Override
+    public TokenStream tokenStream(String fieldName, Reader reader) {
+      return new ICUNormalizer2Filter(
+          new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader));
+    }
+  };
+
+  public void testDefaults() throws IOException {
+    // case folding
+    assertAnalyzesTo(a, "This is a test", new String[] { "this", "is", "a", "test" });
+
+    // case folding
+    assertAnalyzesTo(a, "Ruß", new String[] { "russ" });
+    
+    // case folding
+    assertAnalyzesTo(a, "ΜΆΪΟΣ", new String[] { "μάϊοσ" });
+    assertAnalyzesTo(a, "Μάϊος", new String[] { "μάϊοσ" });
+
+    // supplementary case folding
+    assertAnalyzesTo(a, "𐐖", new String[] { "𐐾" });
+    
+    // normalization
+    assertAnalyzesTo(a, "ﴳﴺﰧ", new String[] { "طمطمطم" });
+
+    // removal of default ignorables
+    assertAnalyzesTo(a, "क्‍ष", new String[] { "क्ष" });
+  }
+  
+  public void testAlternate() throws IOException {
+    Analyzer a = new Analyzer() {
+      @Override
+      public TokenStream tokenStream(String fieldName, Reader reader) {
+        return new ICUNormalizer2Filter(
+            new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader),
+            /* specify nfc with decompose to get nfd */
+            Normalizer2.getInstance(null, "nfc", Normalizer2.Mode.DECOMPOSE));
+      }
+    };
+    
+    // decompose EAcute into E + combining Acute
+    assertAnalyzesTo(a, "\u00E9", new String[] { "\u0065\u0301" });
+  }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+  }
+}