X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java new file mode 100644 index 0000000..343a52b --- /dev/null +++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java @@ -0,0 +1,55 @@ +package org.apache.lucene.analysis.hi; + +import java.util.HashSet; +import java.util.Set; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.BaseTokenStreamTestCase; + +/** + * 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. + */ + +/** + * Tests the HindiAnalyzer + */ +public class TestHindiAnalyzer extends BaseTokenStreamTestCase { + /** This test fails with NPE when the + * stopwords file is missing in classpath */ + public void testResourcesAvailable() { + new HindiAnalyzer(TEST_VERSION_CURRENT); + } + + public void testBasics() throws Exception { + Analyzer a = new HindiAnalyzer(TEST_VERSION_CURRENT); + // two ways to write 'hindi' itself. + checkOneTermReuse(a, "हिन्दी", "हिंद"); + checkOneTermReuse(a, "हिंदी", "हिंद"); + } + + public void testExclusionSet() throws Exception { + Set exclusionSet = new HashSet(); + exclusionSet.add("हिंदी"); + Analyzer a = new HindiAnalyzer(TEST_VERSION_CURRENT, + HindiAnalyzer.getDefaultStopSet(), exclusionSet); + checkOneTermReuse(a, "हिंदी", "हिंदी"); + } + + /** blast some random strings through the analyzer */ + public void testRandomStrings() throws Exception { + checkRandomData(random, new HindiAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER); + } +}