1 package org.apache.lucene.analysis;
3 import java.io.StringReader;
6 * Licensed to the Apache Software Foundation (ASF) under one or more
7 * contributor license agreements. See the NOTICE file distributed with
8 * this work for additional information regarding copyright ownership.
9 * The ASF licenses this file to You under the Apache License, Version 2.0
10 * (the "License"); you may not use this file except in compliance with
11 * the License. You may obtain a copy of the License at
13 * http://www.apache.org/licenses/LICENSE-2.0
15 * Unless required by applicable law or agreed to in writing, software
16 * distributed under the License is distributed on an "AS IS" BASIS,
17 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
18 * See the License for the specific language governing permissions and
19 * limitations under the License.
22 public class TestMockAnalyzer extends BaseTokenStreamTestCase {
24 /** Test a configuration that behaves a lot like WhitespaceAnalyzer */
25 public void testWhitespace() throws Exception {
26 Analyzer a = new MockAnalyzer(random);
27 assertAnalyzesTo(a, "A bc defg hiJklmn opqrstuv wxy z ",
28 new String[] { "a", "bc", "defg", "hijklmn", "opqrstuv", "wxy", "z" });
29 assertAnalyzesToReuse(a, "aba cadaba shazam",
30 new String[] { "aba", "cadaba", "shazam" });
31 assertAnalyzesToReuse(a, "break on whitespace",
32 new String[] { "break", "on", "whitespace" });
35 /** Test a configuration that behaves a lot like SimpleAnalyzer */
36 public void testSimple() throws Exception {
37 Analyzer a = new MockAnalyzer(random, MockTokenizer.SIMPLE, true);
38 assertAnalyzesTo(a, "a-bc123 defg+hijklmn567opqrstuv78wxy_z ",
39 new String[] { "a", "bc", "defg", "hijklmn", "opqrstuv", "wxy", "z" });
40 assertAnalyzesToReuse(a, "aba4cadaba-Shazam",
41 new String[] { "aba", "cadaba", "shazam" });
42 assertAnalyzesToReuse(a, "break+on/Letters",
43 new String[] { "break", "on", "letters" });
46 /** Test a configuration that behaves a lot like KeywordAnalyzer */
47 public void testKeyword() throws Exception {
48 Analyzer a = new MockAnalyzer(random, MockTokenizer.KEYWORD, false);
49 assertAnalyzesTo(a, "a-bc123 defg+hijklmn567opqrstuv78wxy_z ",
50 new String[] { "a-bc123 defg+hijklmn567opqrstuv78wxy_z " });
51 assertAnalyzesToReuse(a, "aba4cadaba-Shazam",
52 new String[] { "aba4cadaba-Shazam" });
53 assertAnalyzesToReuse(a, "break+on/Nothing",
54 new String[] { "break+on/Nothing" });
57 /** Test a configuration that behaves a lot like StopAnalyzer */
58 public void testStop() throws Exception {
59 Analyzer a = new MockAnalyzer(random, MockTokenizer.SIMPLE, true, (CharArraySet) StopAnalyzer.ENGLISH_STOP_WORDS_SET, true);
60 assertAnalyzesTo(a, "the quick brown a fox",
61 new String[] { "quick", "brown", "fox" },
62 new int[] { 2, 1, 2 });
65 a = new MockAnalyzer(random, MockTokenizer.SIMPLE, true, (CharArraySet) StopAnalyzer.ENGLISH_STOP_WORDS_SET, false);
66 assertAnalyzesTo(a, "the quick brown a fox",
67 new String[] { "quick", "brown", "fox" },
68 new int[] { 1, 1, 1 });
71 public void testLUCENE_3042() throws Exception {
72 String testString = "t";
74 Analyzer analyzer = new MockAnalyzer(random);
75 TokenStream stream = analyzer.reusableTokenStream("dummy", new StringReader(testString));
77 while (stream.incrementToken()) {
83 assertAnalyzesToReuse(analyzer, testString, new String[] { "t" });
86 /** blast some random strings through the analyzer */
87 public void testRandomStrings() throws Exception {
88 checkRandomData(random, new MockAnalyzer(random), atLeast(1000));