Package org.apache.lucene.analysis.core

Examples of org.apache.lucene.analysis.core.WhitespaceTokenizer
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
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            {
                TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_default");
                String source = "the quick brown is a fox Or noT";
                String[] expected = new String[] { "the", "quick", "brown", "is", "a", "fox", "Or", "noT" };
                Tokenizer tokenizer = new WhitespaceTokenizer();
                tokenizer.setReader(new StringReader(source));
                assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
            }
        }

        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_default.type", "common_grams")
                     .put("index.analysis.filter.common_grams_default.query_mode", false)
                     .putArray("index.analysis.filter.common_grams_default.common_words", "chromosome", "protein")
                     .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            {
                TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_default");
                String source = "the quick brown is a fox Or noT";
                String[] expected = new String[] { "the", "quick", "brown", "is", "a", "fox", "Or", "noT" };
                Tokenizer tokenizer = new WhitespaceTokenizer();
                tokenizer.setReader(new StringReader(source));
                assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
            }
        }
    }
View Full Code Here
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
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_1");
            String source = "the quick brown is a fox or noT";
            String[] expected = new String[] { "the", "the_quick", "quick", "brown", "brown_is", "is", "is_a", "a", "a_fox", "fox", "fox_or", "or", "or_noT", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_2.type", "common_grams")
                    .put("index.analysis.filter.common_grams_2.ignore_case", false)
                    .putArray("index.analysis.filter.common_grams_2.common_words", "the", "Or", "noT", "a", "is", "an", "they", "are")
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_2");
            String source = "the quick brown is a fox or why noT";
            String[] expected = new String[] { "the", "the_quick", "quick", "brown", "brown_is", "is", "is_a", "a", "a_fox", "fox", "or", "why", "why_noT", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_3.type", "common_grams")
                    .putArray("index.analysis.filter.common_grams_3.common_words", "the", "or", "not", "a", "is", "an", "they", "are")
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_3");
            String source = "the quick brown is a fox Or noT";
            String[] expected = new String[] { "the", "the_quick", "quick", "brown", "brown_is", "is", "is_a", "a", "a_fox", "fox", "Or", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_1");
            String source = "the quick brown is a fox or noT";
            String[] expected = new String[] { "the_quick", "quick", "brown_is", "is_a", "a_fox", "fox_or", "or_noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_2.type", "common_grams")
                    .put("index.analysis.filter.common_grams_2.query_mode", true)
                    .putArray("index.analysis.filter.common_grams_2.common_words", "the", "Or", "noT", "a", "is", "an", "they", "are")
                    .put("index.analysis.filter.common_grams_2.ignore_case", false)
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_2");
            String source = "the quick brown is a fox or why noT";
            String[] expected = new String[] { "the_quick", "quick", "brown_is", "is_a", "a_fox", "fox", "or", "why_noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_3.type", "common_grams")
                    .put("index.analysis.filter.common_grams_3.query_mode", true)
                    .putArray("index.analysis.filter.common_grams_3.common_words", "the", "Or", "noT", "a", "is", "an", "they", "are")
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_3");
            String source = "the quick brown is a fox or why noT";
            String[] expected = new String[] { "the_quick", "quick", "brown_is", "is_a", "a_fox", "fox", "or", "why_noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.common_grams_4.type", "common_grams")
                    .put("index.analysis.filter.common_grams_4.query_mode", true)
                    .putArray("index.analysis.filter.common_grams_4.common_words", "the", "or", "not", "a", "is", "an", "they", "are")
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("common_grams_4");
            String source = "the quick brown is a fox Or noT";
            String[] expected = new String[] { "the_quick", "quick", "brown_is", "is_a", "a_fox", "fox", "Or", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
        AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
        {
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("limit_default");
            String source = "the quick brown fox";
            String[] expected = new String[] { "the" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("limit");
            String source = "the quick brown fox";
            String[] expected = new String[] { "the" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
View Full Code Here
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
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("limit_1");
            String source = "the quick brown fox";
            String[] expected = new String[] { "the", "quick", "brown" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.limit_1.type", "limit")
                    .put("index.analysis.filter.limit_1.max_token_count", 3).put("index.analysis.filter.limit_1.consume_all_tokens", false)
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("limit_1");
            String source = "the quick brown fox";
            String[] expected = new String[] { "the", "quick", "brown" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }

        {
            Settings settings = ImmutableSettings.settingsBuilder().put("index.analysis.filter.limit_1.type", "limit")
                    .put("index.analysis.filter.limit_1.max_token_count", 17).put("index.analysis.filter.limit_1.consume_all_tokens", true)
                    .build();
            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("limit_1");
            String source = "the quick brown fox";
            String[] expected = new String[] { "the", "quick", "brown", "fox" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
View Full Code Here
36
37
38
39
40
41
42
43
44
                .put("index.analysis.filter.my_ascii_folding.type", "asciifolding")
                .build());
        TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_ascii_folding");
        String source = "Ansprüche";
        String[] expected = new String[]{"Anspruche"};
        Tokenizer tokenizer = new WhitespaceTokenizer();
        tokenizer.setReader(new StringReader(source));
        assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
    }
View Full Code Here
50
51
52
53
54
55
56
57
58
                .put("index.analysis.filter.my_ascii_folding.preserve_original", true)
                .build());
        TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_ascii_folding");
        String source = "Ansprüche";
        String[] expected = new String[]{"Anspruche", "Ansprüche"};
        Tokenizer tokenizer = new WhitespaceTokenizer();
        tokenizer.setReader(new StringReader(source));
        assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
    }
View Full Code Here
93
94
95
96
97
98
99
100
101
        AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromClassPath(RESOURCE);
        TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_keep_filter");
        assertThat(tokenFilter, instanceOf(KeepWordFilterFactory.class));
        String source = "hello small world";
        String[] expected = new String[]{"hello", "world"};
        Tokenizer tokenizer = new WhitespaceTokenizer();
        tokenizer.setReader(new StringReader(source));
        assertTokenStreamContents(tokenFilter.create(tokenizer), expected, new int[]{1, 2});
    }
View Full Code Here
105
106
107
108
109
110
111
112
113
        AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromClassPath(RESOURCE);
        TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_case_sensitive_keep_filter");
        assertThat(tokenFilter, instanceOf(KeepWordFilterFactory.class));
        String source = "Hello small world";
        String[] expected = new String[]{"Hello"};
        Tokenizer tokenizer = new WhitespaceTokenizer();
        tokenizer.setReader(new StringReader(source));
        assertTokenStreamContents(tokenFilter.create(tokenizer), expected, new int[]{1});
    }
View Full Code Here
37
38
39
40
41
42
43
44
45
                .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);
    }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.core.WhitespaceTokenizer

  • cc.twittertools.index.TweetAnalyzer
  • cc.twittertools.search.indexing.TweetAnalyzer
  • cc.twittertools.udf.LuceneTokenizer
  • de.arago.lucene.util.LowCaseAnalyzer
  • org.apache.jackrabbit.oak.plugins.index.lucene.OakAnalyzer
  • org.apache.lucene.analysis.cn.smart.TestSmartChineseFactories
  • org.apache.lucene.analysis.cn.TestChineseTokenizer$JustChineseFilterAnalyzer
  • org.apache.lucene.analysis.commongrams.CommonGramsFilterTest
  • org.apache.lucene.analysis.compound.TestCompoundWordTokenFilter
  • org.apache.lucene.analysis.core.WhitespaceTokenizerFactory
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.