TestIndicTokenizer.java

package org.apache.lucene.analysis.in;

/**
 * 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.StringReader;

import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;

/**
 * Test IndicTokenizer
 */
public class TestIndicTokenizer extends BaseTokenStreamTestCase {
  /** Test tokenizing Indic vowels, signs, and punctuation */
  public void testBasics() throws IOException {
    TokenStream ts = new IndicTokenizer(TEST_VERSION_CURRENT,
        new StringReader("मुझे हिंदी का और अभ्यास करना होगा ।"));
    assertTokenStreamContents(ts,
        new String[] { "मुझे", "हिंदी", "का", "और", "अभ्यास", "करना", "होगा" });
  }
  
  /** Test that words with format chars such as ZWJ are kept */
  public void testFormat() throws Exception {
    TokenStream ts = new IndicTokenizer(TEST_VERSION_CURRENT,
        new StringReader("शार्‍मा शार्‍मा"));
    assertTokenStreamContents(ts, new String[] { "शार्‍मा", "शार्‍मा" });
  }
}