Package org.elasticsearch.index.analysis

Examples of org.elasticsearch.index.analysis.TokenFilterFactory.create()

74
75
76
77
78
79
80
81
82
83
84
            "gekosten"
        };

        Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_36, new StringReader(source));

        assertSimpleTSOutput(tokenFilter.create(tokenizer), expected);

    }

    public AnalysisService createAnalysisService() {
        Settings settings = ImmutableSettings.settingsBuilder().loadFromClasspath("org/xbib/elasticsearch/index/analysis/decompound_analysis.json").build();
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
            "Strassenecke"
        };

        Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_36, new StringReader(source));

        assertSimpleTSOutput(tokenFilter.create(tokenizer), expected);

    }

    public AnalysisService createAnalysisService() {
        Settings settings = ImmutableSettings.settingsBuilder().loadFromClasspath("org/xbib/elasticsearch/index/analysis/german_normalization_analysis.json").build();
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
                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")
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
                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);
            }
        }
    }

    @Test
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
            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")
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
            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();
View Full Code Here
120
121
122
123
124
125
126
127
128
129
130
            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);
        }
    }

    @Test
    public void testCommonGramsAnalysis() throws IOException {
View Full Code Here
157
158
159
160
161
162
163
164
165
166
167
            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")
View Full Code Here
171
172
173
174
175
176
177
178
179
180
181
            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")
View Full Code Here
184
185
186
187
188
189
190
191
192
193
194
            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")
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.