Lucene example source code file (TestThaiAnalyzer.java)

This example Lucene source code file (TestThaiAnalyzer.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" ^TM.

Java - Lucene tags/keywords

alphanum, alphanum, breakiterator, deprecated, exception, exception, io, jre, southeast_asian, string, string, thai, thaianalyzer, thaianalyzer, xy

The Lucene TestThaiAnalyzer.java source code

package org.apache.lucene.analysis.th;

/**
 * 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.StringReader;

import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.FlagsAttribute;
import org.apache.lucene.util.Version;

/**
 * Test case for ThaiAnalyzer, modified from TestFrenchAnalyzer
 *
 * @version   0.1
 */

public class TestThaiAnalyzer extends BaseTokenStreamTestCase {
	
	/* 
	 * testcase for offsets
	 */
	public void testOffsets() throws Exception {
	  assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
		assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องแสดงว่างานดี", 
		    new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
				new int[] { 0, 3, 6, 9, 13, 17, 20, 23 },
				new int[] { 3, 6, 9, 13, 17, 20, 23, 25 });
	}
	
	public void testTokenType() throws Exception {
	    assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
      assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องแสดงว่างานดี ๑๒๓", 
                       new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี", "๑๒๓" },
                       new String[] { "<SOUTHEAST_ASIAN>", "", 
                                      "<SOUTHEAST_ASIAN>", "", 
                                      "<SOUTHEAST_ASIAN>", "",
                                      "<SOUTHEAST_ASIAN>", "",
                                      "<NUM>" });
	}

	/**
	 * Thai numeric tokens were typed as <ALPHANUM> instead of .
	 * @deprecated testing backwards behavior
 	 */
	@Deprecated
	public void testBuggyTokenType30() throws Exception {
	  assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
		assertAnalyzesTo(new ThaiAnalyzer(Version.LUCENE_30), "การที่ได้ต้องแสดงว่างานดี ๑๒๓", 
                         new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี", "๑๒๓" },
                         new String[] { "<ALPHANUM>", "", "", 
                                        "<ALPHANUM>", "", "", 
                                        "<ALPHANUM>", "", "" });
	}
	
	/** @deprecated testing backwards behavior */
	@Deprecated
    public void testAnalyzer30() throws Exception {
	  assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
        ThaiAnalyzer analyzer = new ThaiAnalyzer(Version.LUCENE_30);
	
		assertAnalyzesTo(analyzer, "", new String[] {});

		assertAnalyzesTo(
			analyzer,
			"การที่ได้ต้องแสดงว่างานดี",
			new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี"});

		assertAnalyzesTo(
			analyzer,
			"บริษัทชื่อ XY&Z - คุยกับ xyz@demo.com",
			new String[] { "บริษัท", "ชื่อ", "xy&z", "คุย", "กับ", "xyz@demo.com" });

    // English stop words
		assertAnalyzesTo(
			analyzer,
			"ประโยคว่า The quick brown fox jumped over the lazy dogs",
			new String[] { "ประโยค", "ว่า", "quick", "brown", "fox", "jumped", "over", "lazy", "dogs" });
	}
	
	/*
	 * Test that position increments are adjusted correctly for stopwords.
	 */
	public void testPositionIncrements() throws Exception {
	  assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
	  ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT);

    assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้อง the แสดงว่างานดี", 
        new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
        new int[] { 0, 3, 6, 9, 18, 22, 25, 28 },
        new int[] { 3, 6, 9, 13, 22, 25, 28, 30 },
        new int[] { 1, 1, 1, 1, 2, 1, 1, 1 });
	 
	  // case that a stopword is adjacent to thai text, with no whitespace
    assertAnalyzesTo(new ThaiAnalyzer(TEST_VERSION_CURRENT), "การที่ได้ต้องthe แสดงว่างานดี", 
        new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี" },
        new int[] { 0, 3, 6, 9, 17, 21, 24, 27 },
        new int[] { 3, 6, 9, 13, 21, 24, 27, 29 },
        new int[] { 1, 1, 1, 1, 2, 1, 1, 1 });
	}
	
	public void testReusableTokenStream() throws Exception {
	  assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
	  ThaiAnalyzer analyzer = new ThaiAnalyzer(TEST_VERSION_CURRENT);
	  assertAnalyzesToReuse(analyzer, "", new String[] {});

      assertAnalyzesToReuse(
          analyzer,
          "การที่ได้ต้องแสดงว่างานดี",
          new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี"});

      assertAnalyzesToReuse(
          analyzer,
          "บริษัทชื่อ XY&Z - คุยกับ xyz@demo.com",
          new String[] { "บริษัท", "ชื่อ", "xy", "z", "คุย", "กับ", "xyz", "demo.com" });
	}
	
	/** @deprecated, for version back compat */
	@Deprecated
	public void testReusableTokenStream30() throws Exception {
	    assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
	    ThaiAnalyzer analyzer = new ThaiAnalyzer(Version.LUCENE_30);
	    assertAnalyzesToReuse(analyzer, "", new String[] {});

	    assertAnalyzesToReuse(
            analyzer,
            "การที่ได้ต้องแสดงว่างานดี",
            new String[] { "การ", "ที่", "ได้", "ต้อง", "แสดง", "ว่า", "งาน", "ดี"});

	    assertAnalyzesToReuse(
            analyzer,
            "บริษัทชื่อ XY&Z - คุยกับ xyz@demo.com",
            new String[] { "บริษัท", "ชื่อ", "xy&z", "คุย", "กับ", "xyz@demo.com" });
  }
	
  /** blast some random strings through the analyzer */
  public void testRandomStrings() throws Exception {
    checkRandomData(random, new ThaiAnalyzer(TEST_VERSION_CURRENT), 10000*RANDOM_MULTIPLIER);
  }
  
  // LUCENE-3044
  public void testAttributeReuse() throws Exception {
    assumeTrue("JRE does not support Thai dictionary-based BreakIterator", ThaiWordFilter.DBBI_AVAILABLE);
    ThaiAnalyzer analyzer = new ThaiAnalyzer(Version.LUCENE_30);
    // just consume
    TokenStream ts = analyzer.reusableTokenStream("dummy", new StringReader("ภาษาไทย"));
    assertTokenStreamContents(ts, new String[] { "ภาษา", "ไทย" });
    // this consumer adds flagsAtt, which this analyzer does not use. 
    ts = analyzer.reusableTokenStream("dummy", new StringReader("ภาษาไทย"));
    ts.addAttribute(FlagsAttribute.class);
    assertTokenStreamContents(ts, new String[] { "ภาษา", "ไทย" });
  }
}