1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
|
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch 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.elasticsearch.index.analysis;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.elasticsearch.env.Environment;
import org.elasticsearch.test.ESTokenStreamTestCase;
import java.io.IOException;
import java.io.StringReader;
import static org.elasticsearch.common.settings.Settings.settingsBuilder;
public class WordDelimiterTokenFilterFactoryTests extends ESTokenStreamTestCase {
public void testDefault() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"Power", "Shot", "500", "42", "wi", "fi", "wi", "fi", "4000", "j", "2", "se", "O", "Neil"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testCatenateWords() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.catenate_words", "true")
.put("index.analysis.filter.my_word_delimiter.generate_word_parts", "false")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"PowerShot", "500", "42", "wifi", "wifi", "4000", "j", "2", "se", "ONeil"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testCatenateNumbers() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.generate_number_parts", "false")
.put("index.analysis.filter.my_word_delimiter.catenate_numbers", "true")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"Power", "Shot", "50042", "wi", "fi", "wi", "fi", "4000", "j", "2", "se", "O", "Neil"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testCatenateAll() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.generate_word_parts", "false")
.put("index.analysis.filter.my_word_delimiter.generate_number_parts", "false")
.put("index.analysis.filter.my_word_delimiter.catenate_all", "true")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"PowerShot", "50042", "wifi", "wifi4000", "j2se", "ONeil"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testSplitOnCaseChange() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.split_on_case_change", "false")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot";
String[] expected = new String[]{"PowerShot"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testPreserveOriginal() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.preserve_original", "true")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"PowerShot", "Power", "Shot", "500-42", "500", "42", "wi-fi", "wi", "fi", "wi-fi-4000", "wi", "fi", "4000", "j2se", "j", "2", "se", "O'Neil's", "O", "Neil"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
public void testStemEnglishPossessive() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.stem_english_possessive", "false")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot 500-42 wi-fi wi-fi-4000 j2se O'Neil's";
String[] expected = new String[]{"Power", "Shot", "500", "42", "wi", "fi", "wi", "fi", "4000", "j", "2", "se", "O", "Neil", "s"};
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
/** Correct offset order when doing both parts and concatenation: PowerShot is a synonym of Power */
public void testPartsAndCatenate() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.catenate_words", "true")
.put("index.analysis.filter.my_word_delimiter.generate_word_parts", "true")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot";
String[] expected = new String[]{"Power", "PowerShot", "Shot" };
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
/** Back compat:
* old offset order when doing both parts and concatenation: PowerShot is a synonym of Shot */
public void testDeprecatedPartsAndCatenate() throws IOException {
AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settingsBuilder()
.put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString())
.put("index.analysis.filter.my_word_delimiter.type", "word_delimiter")
.put("index.analysis.filter.my_word_delimiter.catenate_words", "true")
.put("index.analysis.filter.my_word_delimiter.generate_word_parts", "true")
.put("index.analysis.filter.my_word_delimiter.version", "4.7")
.build());
TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_word_delimiter");
String source = "PowerShot";
String[] expected = new String[]{"Power", "Shot", "PowerShot" };
Tokenizer tokenizer = new WhitespaceTokenizer();
tokenizer.setReader(new StringReader(source));
assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
}
}
|
