lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicFilters.java

/*
 * 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.
 */
package org.apache.lucene.analysis.ar;

import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.BaseTokenStreamFactoryTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;

/** Simple tests to ensure the Arabic filter Factories are working. */
public class TestArabicFilters extends BaseTokenStreamFactoryTestCase {

  /** Test ArabicNormalizationFilterFactory */
  public void testNormalizer() throws Exception {
    Reader reader = new StringReader("الذين مَلكت أيمانكم");
    Tokenizer tokenizer = whitespaceMockTokenizer(reader);
    TokenStream stream = tokenFilterFactory("ArabicNormalization").create(tokenizer);
    assertTokenStreamContents(stream, new String[] {"الذين", "ملكت", "ايمانكم"});
  }

  /** Test ArabicStemFilterFactory */
  public void testStemmer() throws Exception {
    Reader reader = new StringReader("الذين مَلكت أيمانكم");
    Tokenizer tokenizer = whitespaceMockTokenizer(reader);
    TokenStream stream = tokenFilterFactory("ArabicNormalization").create(tokenizer);
    stream = tokenFilterFactory("ArabicStem").create(stream);
    assertTokenStreamContents(stream, new String[] {"ذين", "ملكت", "ايمانكم"});
  }

  /** Test PersianCharFilterFactory */
  public void testPersianCharFilter() throws Exception {
    Reader reader = charFilterFactory("Persian").create(new StringReader("می‌خورد"));
    Tokenizer tokenizer = whitespaceMockTokenizer(reader);
    assertTokenStreamContents(tokenizer, new String[] {"می", "خورد"});
  }

  /** Test that bogus arguments result in exception */
  public void testBogusArguments() throws Exception {
    IllegalArgumentException expected =
        expectThrows(
            IllegalArgumentException.class,
            () -> {
              tokenFilterFactory("ArabicNormalization", "bogusArg", "bogusValue");
            });
    assertTrue(expected.getMessage().contains("Unknown parameters"));

    expected =
        expectThrows(
            IllegalArgumentException.class,
            () -> {
              tokenFilterFactory("Arabicstem", "bogusArg", "bogusValue");
            });
    assertTrue(expected.getMessage().contains("Unknown parameters"));

    expected =
        expectThrows(
            IllegalArgumentException.class,
            () -> {
              charFilterFactory("Persian", "bogusArg", "bogusValue");
            });
    assertTrue(expected.getMessage().contains("Unknown parameters"));
  }
}