X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/analysis/TestPorterStemFilter.java

diff --git a/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/analysis/TestPorterStemFilter.java b/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/analysis/TestPorterStemFilter.java
new file mode 100644
index 0000000..b0347c8
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/src/test/org/apache/lucene/analysis/TestPorterStemFilter.java
@@ -0,0 +1,65 @@
+package org.apache.lucene.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.io.IOException;
+import java.io.Reader;
+import java.io.StringReader;
+
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+
+import static org.apache.lucene.analysis.VocabularyAssert.*;
+
+/**
+ * Test the PorterStemFilter with Martin Porter's test data.
+ */
+public class TestPorterStemFilter extends BaseTokenStreamTestCase {  
+  Analyzer a = new ReusableAnalyzerBase() {
+    @Override
+    protected TokenStreamComponents createComponents(String fieldName,
+        Reader reader) {
+      Tokenizer t = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
+      return new TokenStreamComponents(t, new PorterStemFilter(t));
+    }
+  };
+
+  /**
+   * Run the stemmer against all strings in voc.txt
+   * The output should be the same as the string in output.txt
+   */
+  public void testPorterStemFilter() throws Exception {
+    assertVocabulary(a, getDataFile("porterTestData.zip"), "voc.txt", "output.txt");
+  }
+  
+  public void testWithKeywordAttribute() throws IOException {
+    CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
+    set.add("yourselves");
+    Tokenizer tokenizer = new MockTokenizer(new StringReader("yourselves yours"), MockTokenizer.WHITESPACE, false);
+    TokenStream filter = new PorterStemFilter(new KeywordMarkerFilter(tokenizer, set));   
+    assertTokenStreamContents(filter, new String[] {"yourselves", "your"});
+  }
+  
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);
+  }
+}