1 package org.apache.lucene.analysis.icu;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
21 import java.io.Reader;
22 import java.io.StringReader;
24 import org.apache.lucene.analysis.Analyzer;
25 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
26 import org.apache.lucene.analysis.Tokenizer;
27 import org.apache.lucene.analysis.KeywordTokenizer;
28 import org.apache.lucene.analysis.WhitespaceTokenizer;
29 import org.apache.lucene.analysis.ReusableAnalyzerBase;
30 import org.apache.lucene.analysis.TokenStream;
32 import com.ibm.icu.text.Transliterator;
33 import com.ibm.icu.text.UnicodeSet;
37 * Test the ICUTransformFilter with some basic examples.
39 public class TestICUTransformFilter extends BaseTokenStreamTestCase {
41 public void testBasicFunctionality() throws Exception {
42 checkToken(Transliterator.getInstance("Traditional-Simplified"),
44 checkToken(Transliterator.getInstance("Katakana-Hiragana"),
46 checkToken(Transliterator.getInstance("Fullwidth-Halfwidth"),
48 checkToken(Transliterator.getInstance("Any-Latin"),
49 "Αλφαβητικός Κατάλογος", "Alphabētikós Katálogos");
50 checkToken(Transliterator.getInstance("NFD; [:Nonspacing Mark:] Remove"),
51 "Alphabētikós Katálogos", "Alphabetikos Katalogos");
52 checkToken(Transliterator.getInstance("Han-Latin"),
56 public void testCustomFunctionality() throws Exception {
57 String rules = "a > b; b > c;"; // convert a's to b's and b's to c's
58 checkToken(Transliterator.createFromRules("test", rules, Transliterator.FORWARD), "abacadaba", "bcbcbdbcb");
61 public void testCustomFunctionality2() throws Exception {
62 String rules = "c { a > b; a > d;"; // convert a's to b's and b's to c's
63 checkToken(Transliterator.createFromRules("test", rules, Transliterator.FORWARD), "caa", "cbd");
66 public void testOptimizer() throws Exception {
67 String rules = "a > b; b > c;"; // convert a's to b's and b's to c's
68 Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
69 assertTrue(custom.getFilter() == null);
70 new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
71 assertTrue(custom.getFilter().equals(new UnicodeSet("[ab]")));
74 public void testOptimizer2() throws Exception {
75 checkToken(Transliterator.getInstance("Traditional-Simplified; CaseFold"),
79 public void testOptimizerSurrogate() throws Exception {
80 String rules = "\\U00020087 > x;"; // convert CJK UNIFIED IDEOGRAPH-20087 to an x
81 Transliterator custom = Transliterator.createFromRules("test", rules, Transliterator.FORWARD);
82 assertTrue(custom.getFilter() == null);
83 new ICUTransformFilter(new KeywordTokenizer(new StringReader("")), custom);
84 assertTrue(custom.getFilter().equals(new UnicodeSet("[\\U00020087]")));
87 private void checkToken(Transliterator transform, String input, String expected) throws IOException {
88 TokenStream ts = new ICUTransformFilter(new KeywordTokenizer((new StringReader(input))), transform);
89 assertTokenStreamContents(ts, new String[] { expected });
92 /** blast some random strings through the analyzer */
93 public void testRandomStrings() throws Exception {
94 final Transliterator transform = Transliterator.getInstance("Any-Latin");
95 Analyzer a = new ReusableAnalyzerBase() {
97 protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
98 Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, reader);
99 return new TokenStreamComponents(tokenizer, new ICUTransformFilter(tokenizer, transform));
102 checkRandomData(random, a, 1000*RANDOM_MULTIPLIER);