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/fi/TestFinnishAnalyzer.java diff --git a/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java new file mode 100644 index 0000000..35b67a2 --- /dev/null +++ b/lucene-java-3.5.0/lucene/contrib/analyzers/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java @@ -0,0 +1,58 @@ +package org.apache.lucene.analysis.fi; + +/** + * 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.util.HashSet; +import java.util.Set; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.BaseTokenStreamTestCase; + +public class TestFinnishAnalyzer extends BaseTokenStreamTestCase { + /** This test fails with NPE when the + * stopwords file is missing in classpath */ + public void testResourcesAvailable() { + new FinnishAnalyzer(TEST_VERSION_CURRENT); + } + + /** test stopwords and stemming */ + public void testBasics() throws IOException { + Analyzer a = new FinnishAnalyzer(TEST_VERSION_CURRENT); + // stemming + checkOneTermReuse(a, "edeltäjiinsä", "edeltäj"); + checkOneTermReuse(a, "edeltäjistään", "edeltäj"); + // stopword + assertAnalyzesTo(a, "olla", new String[] {}); + } + + /** test use of exclusion set */ + public void testExclude() throws IOException { + Set exclusionSet = new HashSet(); + exclusionSet.add("edeltäjistään"); + Analyzer a = new FinnishAnalyzer(TEST_VERSION_CURRENT, + FinnishAnalyzer.getDefaultStopSet(), exclusionSet); + checkOneTermReuse(a, "edeltäjiinsä", "edeltäj"); + checkOneTermReuse(a, "edeltäjistään", "edeltäjistään"); + } + + /** blast some random strings through the analyzer */ + public void testRandomStrings() throws Exception { + checkRandomData(random, new FinnishAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER); + } +}