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
169
170
171
172
173
174
175
176
177
178
|
/*
* 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.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter;
import org.apache.lucene.analysis.ngram.Lucene43EdgeNGramTokenFilter;
import org.apache.lucene.analysis.reverse.ReverseStringFilter;
import org.elasticsearch.Version;
import org.elasticsearch.cluster.metadata.IndexMetaData;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.settings.Settings.Builder;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.test.ESTokenStreamTestCase;
import org.elasticsearch.test.IndexSettingsModule;
import java.io.IOException;
import java.io.StringReader;
import java.lang.reflect.Field;
import java.lang.reflect.Modifier;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Random;
import static com.carrotsearch.randomizedtesting.RandomizedTest.scaledRandomIntBetween;
import static org.hamcrest.Matchers.instanceOf;
public class NGramTokenizerFactoryTests extends ESTokenStreamTestCase {
public void testParseTokenChars() {
final Index index = new Index("test");
final String name = "ngr";
final Settings indexSettings = newAnalysisSettingsBuilder().build();
IndexSettings indexProperties = IndexSettingsModule.newIndexSettings(index, indexSettings);
for (String tokenChars : Arrays.asList("letters", "number", "DIRECTIONALITY_UNDEFINED")) {
final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", tokenChars).build();
try {
new NGramTokenizerFactory(indexProperties, null, name, settings).create();
fail();
} catch (IllegalArgumentException expected) {
// OK
}
}
for (String tokenChars : Arrays.asList("letter", " digit ", "punctuation", "DIGIT", "CoNtRoL", "dash_punctuation")) {
final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", tokenChars).build();
indexProperties = IndexSettingsModule.newIndexSettings(index, indexSettings);
new NGramTokenizerFactory(indexProperties, null, name, settings).create();
// no exception
}
}
public void testNoTokenChars() throws IOException {
final Index index = new Index("test");
final String name = "ngr";
final Settings indexSettings = newAnalysisSettingsBuilder().build();
final Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 4).putArray("token_chars", new String[0]).build();
Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
tokenizer.setReader(new StringReader("1.34"));
assertTokenStreamContents(tokenizer, new String[] {"1.", "1.3", "1.34", ".3", ".34", "34"});
}
public void testPreTokenization() throws IOException {
// Make sure that pretokenization works well and that it can be used even with token chars which are supplementary characters
final Index index = new Index("test");
final String name = "ngr";
final Settings indexSettings = newAnalysisSettingsBuilder().build();
Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit").build();
Tokenizer tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
tokenizer.setReader(new StringReader("Åbc déf g\uD801\uDC00f "));
assertTokenStreamContents(tokenizer,
new String[] {"Åb", "Åbc", "bc", "dé", "déf", "éf", "g\uD801\uDC00", "g\uD801\uDC00f", "\uD801\uDC00f"});
settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
tokenizer = new NGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
tokenizer.setReader(new StringReader(" a!$ 9"));
assertTokenStreamContents(tokenizer,
new String[] {" a", " a!", "a!", "a!$", "!$", "!$ ", "$ ", "$ 9", " 9"});
}
public void testPreTokenizationEdge() throws IOException {
// Make sure that pretokenization works well and that it can be used even with token chars which are supplementary characters
final Index index = new Index("test");
final String name = "ngr";
final Settings indexSettings = newAnalysisSettingsBuilder().build();
Settings settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit").build();
Tokenizer tokenizer = new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
tokenizer.setReader(new StringReader("Åbc déf g\uD801\uDC00f "));
assertTokenStreamContents(tokenizer,
new String[] {"Åb", "Åbc", "dé", "déf", "g\uD801\uDC00", "g\uD801\uDC00f"});
settings = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3).put("token_chars", "letter,digit,punctuation,whitespace,symbol").build();
tokenizer = new EdgeNGramTokenizerFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create();
tokenizer.setReader(new StringReader(" a!$ 9"));
assertTokenStreamContents(tokenizer,
new String[] {" a", " a!"});
}
public void testBackwardsCompatibilityEdgeNgramTokenFilter() throws Exception {
int iters = scaledRandomIntBetween(20, 100);
for (int i = 0; i < iters; i++) {
final Index index = new Index("test");
final String name = "ngr";
Version v = randomVersion(random());
if (v.onOrAfter(Version.V_0_90_2)) {
Builder builder = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3);
boolean compatVersion = false;
if ((compatVersion = random().nextBoolean())) {
builder.put("version", "4." + random().nextInt(3));
}
boolean reverse = random().nextBoolean();
if (reverse) {
builder.put("side", "back");
}
Settings settings = builder.build();
Settings indexSettings = newAnalysisSettingsBuilder().put(IndexMetaData.SETTING_VERSION_CREATED, v.id).build();
Tokenizer tokenizer = new MockTokenizer();
tokenizer.setReader(new StringReader("foo bar"));
TokenStream edgeNGramTokenFilter = new EdgeNGramTokenFilterFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create(tokenizer);
if (reverse) {
assertThat(edgeNGramTokenFilter, instanceOf(ReverseStringFilter.class));
} else if (compatVersion) {
assertThat(edgeNGramTokenFilter, instanceOf(Lucene43EdgeNGramTokenFilter.class));
} else {
assertThat(edgeNGramTokenFilter, instanceOf(EdgeNGramTokenFilter.class));
}
} else {
Builder builder = newAnalysisSettingsBuilder().put("min_gram", 2).put("max_gram", 3);
boolean reverse = random().nextBoolean();
if (reverse) {
builder.put("side", "back");
}
Settings settings = builder.build();
Settings indexSettings = newAnalysisSettingsBuilder().put(IndexMetaData.SETTING_VERSION_CREATED, v.id).build();
Tokenizer tokenizer = new MockTokenizer();
tokenizer.setReader(new StringReader("foo bar"));
TokenStream edgeNGramTokenFilter = new EdgeNGramTokenFilterFactory(IndexSettingsModule.newIndexSettings(index, indexSettings), null, name, settings).create(tokenizer);
if (reverse) {
assertThat(edgeNGramTokenFilter, instanceOf(ReverseStringFilter.class));
} else {
assertThat(edgeNGramTokenFilter, instanceOf(Lucene43EdgeNGramTokenFilter.class));
}
}
}
}
private Version randomVersion(Random random) throws IllegalArgumentException, IllegalAccessException {
Field[] declaredFields = Version.class.getFields();
List<Field> versionFields = new ArrayList<>();
for (Field field : declaredFields) {
if ((field.getModifiers() & Modifier.STATIC) != 0 && field.getName().startsWith("V_") && field.getType() == Version.class) {
versionFields.add(field);
}
}
return (Version) versionFields.get(random.nextInt(versionFields.size())).get(Version.class);
}
}
|
