001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018package org.apache.commons.codec.language.bm;
019
020import static org.junit.Assert.assertTrue;
021
022import java.util.Arrays;
023import java.util.List;
024
025import org.junit.Test;
026import org.junit.runner.RunWith;
027import org.junit.runners.Parameterized;
028
029/**
030 * Tests guessLanguages API.
031 *
032 * @since 1.6
033 */
034@RunWith(Parameterized.class)
035public class LanguageGuessingTest {
036
037    private static String EXACT = "exact";
038    private static String ONE_OF = "one of";
039
040    @Parameterized.Parameters
041    public static List<Object[]> data() {
042        return Arrays.asList(new Object[][] {
043                { "Renault", "french", EXACT },
044                { "Mickiewicz", "polish", EXACT },
045                { "Thompson", "english", ONE_OF }, // this also hits german and greeklatin
046                { "Nu\u00f1ez", "spanish", EXACT }, // Nu�ez
047                { "Carvalho", "portuguese", EXACT },
048                { "\u010capek", "czech", EXACT }, // ?apek
049                { "Sjneijder", "dutch", EXACT },
050                { "Klausewitz", "german", EXACT },
051                { "K\u00fc\u00e7\u00fck", "turkish", EXACT }, // K���k
052                { "Giacometti", "italian", EXACT },
053                { "Nagy", "hungarian", EXACT },
054                { "Ceau\u015fescu", "romanian", EXACT }, // Ceau?escu
055                { "Angelopoulos", "greeklatin", EXACT },
056                { "\u0391\u03b3\u03b3\u03b5\u03bb\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2", "greek", EXACT }, // ????????????
057                { "\u041f\u0443\u0448\u043a\u0438\u043d", "cyrillic", EXACT }, // ??????
058                { "\u05db\u05d4\u05df", "hebrew", EXACT }, // ???
059                { "\u00e1cz", "any", EXACT }, // �cz
060                { "\u00e1tz", "any", EXACT } }); // �tz
061    }
062
063    private final String exactness;
064
065    private final Lang lang = Lang.instance(NameType.GENERIC);
066    private final String language;
067    private final String name;
068
069    public LanguageGuessingTest(final String name, final String language, final String exactness) {
070        this.name = name;
071        this.language = language;
072        this.exactness = exactness;
073    }
074
075    @Test
076    public void testLanguageGuessing() {
077        final Languages.LanguageSet guesses = this.lang.guessLanguages(this.name);
078
079        assertTrue("language predicted for name '" + this.name + "' is wrong: " + guesses + " should contain '" + this.language + "'",
080                guesses.contains(this.language));
081
082    }
083}