| Eliza Margaretha | 0192918 | 2014-02-19 11:48:59 +0000 | [diff] [blame] | 1 | package de.ids_mannheim.korap.index; |
| 2 | |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 3 | import static org.junit.Assert.assertEquals; |
| 4 | import static org.junit.Assert.fail; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 5 | |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 6 | import java.io.IOException; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 7 | |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 8 | import org.apache.lucene.index.Term; |
| 9 | import org.apache.lucene.search.spans.SpanOrQuery; |
| 10 | import org.apache.lucene.search.spans.SpanQuery; |
| 11 | import org.apache.lucene.search.spans.SpanTermQuery; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 12 | import org.junit.Ignore; |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 13 | import org.junit.Test; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 14 | import org.junit.runner.RunWith; |
| 15 | import org.junit.runners.JUnit4; |
| 16 | |
| Nils Diewald | 2d5f810 | 2015-02-26 21:07:54 +0000 | [diff] [blame] | 17 | import de.ids_mannheim.korap.KrillCollection; |
| Akron | 6097169 | 2016-06-08 12:56:21 +0200 | [diff] [blame] | 18 | import de.ids_mannheim.korap.Krill; |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 19 | import de.ids_mannheim.korap.KrillIndex; |
| 20 | import de.ids_mannheim.korap.query.QueryBuilder; |
| 21 | import de.ids_mannheim.korap.query.SpanClassQuery; |
| 22 | import de.ids_mannheim.korap.query.SpanElementQuery; |
| 23 | import de.ids_mannheim.korap.query.SpanFocusQuery; |
| 24 | import de.ids_mannheim.korap.query.SpanNextQuery; |
| 25 | import de.ids_mannheim.korap.query.SpanWithinQuery; |
| Nils Diewald | 392bcf3 | 2015-02-26 20:01:17 +0000 | [diff] [blame] | 26 | import de.ids_mannheim.korap.response.Match; |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 27 | import de.ids_mannheim.korap.response.Result; |
| Akron | 6097169 | 2016-06-08 12:56:21 +0200 | [diff] [blame] | 28 | import de.ids_mannheim.korap.response.SearchContext; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 29 | |
| 30 | // mvn -Dtest=TestWithinIndex#indexExample1 test |
| 31 | |
| Nils Diewald | 85f9c42 | 2015-02-06 21:09:16 +0000 | [diff] [blame] | 32 | // match is focus and split |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 33 | |
| 34 | @RunWith(JUnit4.class) |
| 35 | public class TestMatchIndex { |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 36 | @Test |
| 37 | public void testEmbeddedClassQuery () throws IOException { |
| 38 | KrillIndex ki = new KrillIndex(); |
| 39 | |
| 40 | // abcabcabac |
| 41 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 42 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 43 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 44 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 45 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 46 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 47 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 48 | ki.addDoc(fd); |
| 49 | |
| 50 | ki.commit(); |
| 51 | |
| 52 | SpanQuery sq; |
| 53 | Result kr; |
| 54 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 55 | sq = new SpanFocusQuery( |
| 56 | new SpanClassQuery( |
| 57 | new SpanNextQuery( |
| 58 | new SpanClassQuery( |
| 59 | new SpanTermQuery( |
| 60 | new Term("base", "s:b")), |
| 61 | (byte) 1), |
| 62 | new SpanClassQuery( |
| 63 | new SpanTermQuery( |
| 64 | new Term("base", "s:c")), |
| 65 | (byte) 2)), |
| 66 | (byte) 3), |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 67 | (byte) 3); |
| 68 | |
| 69 | kr = ki.search(sq, (short) 10); |
| 70 | |
| 71 | assertEquals("totalResults", kr.getTotalResults(), 2); |
| 72 | assertEquals("StartPos (0)", 1, kr.getMatch(0).startPos); |
| 73 | assertEquals("EndPos (0)", 3, kr.getMatch(0).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 74 | assertEquals("SnippetBrackets (0)", "a[[{3:{1:b}{2:c}}]]abcaba ...", |
| 75 | kr.getMatch(0).getSnippetBrackets()); |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 76 | assertEquals("StartPos (1)", 4, kr.getMatch(1).startPos); |
| 77 | assertEquals("EndPos (1)", 6, kr.getMatch(1).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 78 | assertEquals("SnippetBrackets (1)", "abca[[{3:{1:b}{2:c}}]]abac", |
| 79 | kr.getMatch(1).getSnippetBrackets()); |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 80 | |
| 81 | assertEquals("Document count", 1, ki.numberOf("base", "documents")); |
| 82 | assertEquals("Token count", 10, ki.numberOf("base", "t")); |
| 83 | |
| 84 | } |
| 85 | |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 86 | |
| 87 | @Test |
| 88 | public void indexExample1 () throws IOException { |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 89 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 90 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 91 | // abcabcabac |
| 92 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 93 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 94 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 95 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 96 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| Akron | 08f4ceb | 2016-08-03 23:53:32 +0200 | [diff] [blame] | 97 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 98 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 99 | ki.addDoc(fd); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 100 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 101 | ki.commit(); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 102 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 103 | SpanQuery sq; |
| 104 | Result kr; |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 105 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 106 | sq = new SpanNextQuery(new SpanTermQuery(new Term("base", "s:b")), |
| 107 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:a")))); |
| 108 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 109 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 110 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| 111 | assertEquals("StartPos (0)", 7, kr.getMatch(0).startPos); |
| 112 | assertEquals("EndPos (0)", 9, kr.getMatch(0).endPos); |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 113 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 114 | assertEquals("SnippetBrackets (0)", "... bcabca[[b{1:a}]]c", |
| 115 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 116 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 117 | assertEquals("Test no 'more' context", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 118 | "<span class=\"context-left\"><span class=\"more\"></span>bcabca</span><span class=\"match\"><mark>b<mark class=\"class-1 level-0\">a</mark></mark></span><span class=\"context-right\">c</span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 119 | kr.getMatch(0).getSnippetHTML()); |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 120 | |
| 121 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 122 | sq = new SpanFocusQuery(new SpanNextQuery( |
| 123 | new SpanTermQuery(new Term("base", "s:b")), new SpanClassQuery( |
| 124 | new SpanTermQuery(new Term("base", "s:a"))))); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 125 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 126 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 127 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| 128 | assertEquals("StartPos (0)", 8, kr.getMatch(0).startPos); |
| 129 | assertEquals("EndPos (0)", 9, kr.getMatch(0).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 130 | assertEquals("SnippetBrackets (0)", "... cabcab[[{1:a}]]c", |
| 131 | kr.getMatch(0).getSnippetBrackets()); |
| 132 | sq = new SpanFocusQuery(new SpanNextQuery( |
| 133 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:a")), |
| 134 | (byte) 2), |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 135 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:b")), |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 136 | (byte) 3)), |
| 137 | (byte) 3); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 138 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 139 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 140 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 141 | assertEquals("totalResults", kr.getTotalResults(), 3); |
| 142 | assertEquals("StartPos (0)", 1, kr.getMatch(0).startPos); |
| 143 | assertEquals("EndPos (0)", 2, kr.getMatch(0).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 144 | assertEquals("SnippetBrackets (0)", "a[[{3:b}]]cabcab ...", |
| 145 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 146 | |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 147 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 148 | assertEquals( |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 149 | "<span class=\"context-left\">a</span><span class=\"match\"><mark><mark class=\"class-3 level-0\">b</mark></mark></span><span class=\"context-right\">cabcab<span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 150 | kr.getMatch(0).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 151 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 152 | assertEquals("StartPos (1)", 4, kr.getMatch(1).startPos); |
| 153 | assertEquals("EndPos (1)", 5, kr.getMatch(1).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 154 | assertEquals("SnippetBrackets (1)", "abca[[{3:b}]]cabac", |
| 155 | kr.getMatch(1).getSnippetBrackets()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 156 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 157 | assertEquals( |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 158 | "<span class=\"context-left\">abca</span><span class=\"match\"><mark><mark class=\"class-3 level-0\">b</mark></mark></span><span class=\"context-right\">cabac</span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 159 | kr.getMatch(1).getSnippetHTML()); |
| 160 | |
| 161 | assertEquals("StartPos (2)", 7, kr.getMatch(2).startPos); |
| 162 | assertEquals("EndPos (2)", 8, kr.getMatch(2).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 163 | assertEquals("SnippetBrackets (2)", "... bcabca[[{3:b}]]ac", |
| 164 | kr.getMatch(2).getSnippetBrackets()); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 165 | |
| 166 | |
| 167 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 168 | // abcabcabac |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 169 | sq = new SpanFocusQuery(new SpanNextQuery( |
| 170 | new SpanTermQuery(new Term("base", "s:a")), |
| 171 | new SpanClassQuery( |
| 172 | new SpanNextQuery(new SpanTermQuery( |
| 173 | new Term("base", "s:b")), |
| 174 | new SpanClassQuery(new SpanTermQuery( |
| 175 | new Term("base", "s:a")))), |
| 176 | (byte) 2)), |
| 177 | (byte) 2); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 178 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 179 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 180 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 181 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 182 | assertEquals("SnippetBrackets (0)", "... bcabca[[{2:b{1:a}}]]c", |
| 183 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 184 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 185 | assertEquals("SnippetHTML (0) 1", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 186 | "<span class=\"context-left\"><span class=\"more\"></span>bcabca</span><span class=\"match\"><mark><mark class=\"class-2 level-0\">b<mark class=\"class-1 level-1\">a</mark></mark></mark></span><span class=\"context-right\">c</span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 187 | kr.getMatch(0).getSnippetHTML()); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 188 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 189 | // Offset tokens |
| 190 | kr = ki.search(sq, 0, (short) 10, true, (short) 2, true, (short) 2); |
| 191 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 192 | assertEquals("SnippetBrackets (0)", "... ca[[{2:b{1:a}}]]c", |
| 193 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 194 | |
| 195 | |
| 196 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 197 | // Offset Characters |
| 198 | kr = ki.search(sq, 0, (short) 10, false, (short) 1, false, (short) 0); |
| 199 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 200 | assertEquals("SnippetBrackets (0)", "... a[[{2:b{1:a}}]] ...", |
| 201 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 202 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 203 | assertEquals("SnippetHTML (0) 2", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 204 | "<span class=\"context-left\"><span class=\"more\"></span>a</span><span class=\"match\"><mark><mark class=\"class-2 level-0\">b<mark class=\"class-1 level-1\">a</mark></mark></mark></span><span class=\"context-right\"><span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 205 | kr.getMatch(0).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 206 | |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 207 | |
| Nils Diewald | 1455e1e | 2014-08-01 16:12:43 +0000 | [diff] [blame] | 208 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 209 | // Don't match the expected class! |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 210 | sq = new SpanFocusQuery(new SpanNextQuery( |
| 211 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:b")), |
| 212 | (byte) 1), |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 213 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:c")), |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 214 | (byte) 2)), |
| 215 | (byte) 3); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 216 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 217 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 218 | |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 219 | assertEquals("totalResults", kr.getTotalResults(), 0); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 220 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 221 | sq = new SpanFocusQuery( |
| 222 | new SpanNextQuery(new SpanTermQuery(new Term("base", "s:a")), |
| 223 | new SpanClassQuery(new SpanNextQuery( |
| 224 | new SpanTermQuery(new Term("base", |
| 225 | "s:b")), |
| 226 | new SpanTermQuery(new Term("base", "s:c")))))); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 227 | |
| 228 | kr = ki.search(sq, (short) 2); |
| 229 | |
| 230 | assertEquals("totalResults", kr.getTotalResults(), 2); |
| 231 | assertEquals("StartPos (0)", 1, kr.getMatch(0).startPos); |
| 232 | assertEquals("EndPos (0)", 3, kr.getMatch(0).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 233 | assertEquals("SnippetBrackets (0)", "a[[{1:bc}]]abcaba ...", |
| 234 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 235 | assertEquals("StartPos (1)", 4, kr.getMatch(1).startPos); |
| 236 | assertEquals("EndPos (1)", 6, kr.getMatch(1).endPos); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 237 | assertEquals("SnippetBrackets (1)", "abca[[{1:bc}]]abac", |
| 238 | kr.getMatch(1).getSnippetBrackets()); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 239 | |
| 240 | assertEquals(1, ki.numberOf("base", "documents")); |
| 241 | assertEquals(10, ki.numberOf("base", "t")); |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 242 | }; |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 243 | |
| 244 | |
| 245 | @Test |
| 246 | public void indexExample2 () throws IOException { |
| Nils Diewald | a14ecd6 | 2015-02-26 21:00:20 +0000 | [diff] [blame] | 247 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 248 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 249 | // abcabcabac |
| 250 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 251 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 252 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 253 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 254 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 255 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 256 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 257 | ki.addDoc(fd); |
| 258 | ki.commit(); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 259 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 260 | SpanQuery sq; |
| Nils Diewald | 884dbcf | 2015-02-27 17:02:28 +0000 | [diff] [blame] | 261 | Result kr; |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 262 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 263 | // No contexts: |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 264 | sq = new SpanOrQuery(new SpanTermQuery(new Term("base", "s:a")), |
| 265 | new SpanTermQuery(new Term("base", "s:c"))); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 266 | kr = ki.search(sq, (short) 20); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 267 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 268 | assertEquals("totalResults", kr.getTotalResults(), 7); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 269 | assertEquals("SnippetBrackets (0)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 270 | "<span class=\"context-left\"></span><span class=\"match\"><mark>a</mark></span><span class=\"context-right\">bcabca<span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 271 | kr.getMatch(0).getSnippetHTML()); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 272 | assertEquals("SnippetBrackets (0)", "[[a]]bcabca ...", |
| 273 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 274 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 275 | assertEquals("SnippetBrackets (1)", "ab[[c]]abcaba ...", |
| 276 | kr.getMatch(1).getSnippetBrackets()); |
| 277 | assertEquals("SnippetBrackets (1)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 278 | "<span class=\"context-left\">ab</span><span class=\"match\"><mark>c</mark></span><span class=\"context-right\">abcaba<span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 279 | kr.getMatch(1).getSnippetHTML()); |
| 280 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 281 | assertEquals("SnippetBrackets (6)", "... abcaba[[c]]", |
| 282 | kr.getMatch(6).getSnippetBrackets()); |
| 283 | assertEquals("SnippetBrackets (6)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 284 | "<span class=\"context-left\"><span class=\"more\"></span>abcaba</span><span class=\"match\"><mark>c</mark></span><span class=\"context-right\"></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 285 | kr.getMatch(6).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 286 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 287 | kr = ki.search(sq, 0, (short) 20, true, (short) 0, true, (short) 0); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 288 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 289 | assertEquals("totalResults", kr.getTotalResults(), 7); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 290 | assertEquals("SnippetBrackets (0)", "[[a]] ...", |
| 291 | kr.getMatch(0).getSnippetBrackets()); |
| 292 | assertEquals("SnippetHTML (0)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 293 | "<span class=\"context-left\"></span><span class=\"match\"><mark>a</mark></span><span class=\"context-right\"><span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 294 | kr.getMatch(0).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 295 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 296 | assertEquals("SnippetBrackets (1)", "... [[c]] ...", |
| 297 | kr.getMatch(1).getSnippetBrackets()); |
| 298 | assertEquals("SnippetHTML (1)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 299 | "<span class=\"context-left\"><span class=\"more\"></span></span><span class=\"match\"><mark>c</mark></span><span class=\"context-right\"><span class=\"more\"></span></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 300 | kr.getMatch(1).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 301 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 302 | assertEquals("SnippetBrackets (6)", "... [[c]]", |
| 303 | kr.getMatch(6).getSnippetBrackets()); |
| 304 | assertEquals("SnippetBrackets (6)", |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 305 | "<span class=\"context-left\"><span class=\"more\"></span></span><span class=\"match\"><mark>c</mark></span><span class=\"context-right\"></span>", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 306 | kr.getMatch(6).getSnippetHTML()); |
| Nils Diewald | f3b30ae | 2013-11-27 17:42:37 +0000 | [diff] [blame] | 307 | }; |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 308 | |
| 309 | |
| 310 | @Test |
| Nils Diewald | be5943e | 2014-10-21 19:35:34 +0000 | [diff] [blame] | 311 | public void indexExample3 () throws Exception { |
| Nils Diewald | a14ecd6 | 2015-02-26 21:00:20 +0000 | [diff] [blame] | 312 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 313 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 314 | // abcabcabac |
| 315 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 316 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 317 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 318 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 319 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 320 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 321 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 322 | ki.addDoc(fd); |
| 323 | ki.commit(); |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 324 | |
| Nils Diewald | 884dbcf | 2015-02-27 17:02:28 +0000 | [diff] [blame] | 325 | Result kr; |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 326 | |
| Nils Diewald | 8904c1d | 2015-02-26 16:13:18 +0000 | [diff] [blame] | 327 | QueryBuilder kq = new QueryBuilder("base"); |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 328 | |
| Akron | 4f52a63 | 2018-02-09 19:02:40 +0100 | [diff] [blame] | 329 | SpanQuery sq = kq.nr(1, kq.seq(kq.seg("s:b")).append(kq.seg("s:a")) |
| 330 | .append(kq.nr(2, kq.seg("s:c")))).toQuery(); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 331 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 332 | kr = ki.search(sq, 0, (short) 20, true, (short) 2, true, (short) 5); |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 333 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 334 | assertEquals("totalResults", kr.getTotalResults(), 1); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 335 | assertEquals("SnippetBrackets (0)", "... ca[[{1:ba{2:c}}]]", |
| 336 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | 3ef9a47 | 2013-12-02 16:06:09 +0000 | [diff] [blame] | 337 | }; |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 338 | |
| 339 | |
| 340 | @Test |
| 341 | public void indexExampleExtend () throws IOException { |
| Nils Diewald | a14ecd6 | 2015-02-26 21:00:20 +0000 | [diff] [blame] | 342 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 343 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 344 | // abcabcabac |
| 345 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 346 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 347 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 348 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 349 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 350 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 351 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 352 | ki.addDoc(fd); |
| 353 | ki.commit(); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 354 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 355 | SpanQuery sq; |
| Nils Diewald | 884dbcf | 2015-02-27 17:02:28 +0000 | [diff] [blame] | 356 | Result kr; |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 357 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 358 | sq = new SpanFocusQuery(new SpanNextQuery( |
| 359 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:a")), |
| 360 | (byte) 2), |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 361 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:b")), |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 362 | (byte) 3)), |
| 363 | (byte) 3); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 364 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 365 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 366 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 367 | assertEquals("totalResults", kr.getTotalResults(), 3); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 368 | |
| Nils Diewald | 392bcf3 | 2015-02-26 20:01:17 +0000 | [diff] [blame] | 369 | Match km = kr.getMatch(0); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 370 | assertEquals("StartPos (0)", 1, km.startPos); |
| 371 | assertEquals("EndPos (0)", 2, km.endPos); |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 372 | assertEquals("SnippetBrackets (0)", "a[[{3:b}]]cabcab ...", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 373 | km.getSnippetBrackets()); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 374 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 375 | sq = new SpanFocusQuery( |
| 376 | new SpanFocusQuery( |
| 377 | new SpanNextQuery( |
| 378 | new SpanClassQuery( |
| 379 | new SpanTermQuery( |
| 380 | new Term("base", "s:a")), |
| 381 | (byte) 2), |
| 382 | new SpanClassQuery( |
| 383 | new SpanTermQuery( |
| 384 | new Term("base", "s:b")), |
| 385 | (byte) 3)), |
| 386 | (byte) 3), |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 387 | (byte) 2); |
| 388 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 389 | kr = ki.search(sq, (short) 10); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 390 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 391 | km = kr.getMatch(0); |
| 392 | assertEquals("StartPos (0)", 0, km.startPos); |
| 393 | assertEquals("EndPos (0)", 1, km.endPos); |
| Akron | f05fde6 | 2016-08-03 23:46:17 +0200 | [diff] [blame] | 394 | assertEquals("SnippetBrackets (0)", "[[{2:a}]]bcabca ...", |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 395 | km.getSnippetBrackets()); |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 396 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 397 | // TODO: Check ID |
| Nils Diewald | d4401ec | 2014-06-16 17:04:02 +0000 | [diff] [blame] | 398 | }; |
| Nils Diewald | 44693e8 | 2014-11-05 18:00:12 +0000 | [diff] [blame] | 399 | |
| 400 | |
| 401 | @Test |
| Nils Diewald | 85f9c42 | 2015-02-06 21:09:16 +0000 | [diff] [blame] | 402 | public void indexExampleFocusWithSpan () throws IOException { |
| Nils Diewald | a14ecd6 | 2015-02-26 21:00:20 +0000 | [diff] [blame] | 403 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 404 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 405 | // abcabcabac |
| 406 | FieldDocument fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 407 | fd.addTV("base", "abcabcabac", "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" |
| 408 | + "[(1-2)s:b|i:b|_1$<i>1<i>2|<>:s$<b>64<i>1<i>5<i>5]" |
| 409 | + "[(2-3)s:c|i:c|_2$<i>2<i>3|<>:s$<b>64<i>2<i>7<i>7]" |
| 410 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 411 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 412 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 413 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 414 | ki.addDoc(fd); |
| 415 | ki.commit(); |
| Nils Diewald | 44693e8 | 2014-11-05 18:00:12 +0000 | [diff] [blame] | 416 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 417 | SpanQuery sq; |
| Nils Diewald | 884dbcf | 2015-02-27 17:02:28 +0000 | [diff] [blame] | 418 | Result kr; |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 419 | |
| margaretha | 50c7633 | 2015-03-19 10:10:39 +0100 | [diff] [blame] | 420 | // sq = new SpanWithinQuery(new SpanClassQuery(new SpanElementQuery( |
| 421 | // "base", "s"), (byte) 2), new SpanClassQuery(new SpanTermQuery( |
| 422 | // new Term("base", "s:b")), (byte) 3)); |
| 423 | // |
| 424 | // kr = ki.search(sq, (short) 10); |
| 425 | // assertEquals(kr.getSerialQuery(), |
| 426 | // "spanContain({2: <base:s />}, {3: base:s:b})"); |
| 427 | // assertEquals(kr.getMatch(0).getSnippetBrackets(), |
| 428 | // "a[{2:{3:b}cab}]cabac"); |
| Nils Diewald | 44693e8 | 2014-11-05 18:00:12 +0000 | [diff] [blame] | 429 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 430 | sq = new SpanFocusQuery(new SpanWithinQuery( |
| 431 | new SpanClassQuery(new SpanElementQuery("base", "s"), (byte) 2), |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 432 | new SpanClassQuery(new SpanTermQuery(new Term("base", "s:b")), |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 433 | (byte) 3)), |
| 434 | (byte) 3); |
| Nils Diewald | 44693e8 | 2014-11-05 18:00:12 +0000 | [diff] [blame] | 435 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 436 | kr = ki.search(sq, (short) 10); |
| Marc Kupietz | 613f432 | 2025-09-24 13:59:24 +0200 | [diff] [blame^] | 437 | assertEquals( |
| 438 | "focus(3: spanContain({2: <base:s />}, {3: base:s:b}))", |
| 439 | kr.getSerialQuery()); |
| Akron | 6cc7b7b | 2016-01-14 21:39:18 +0100 | [diff] [blame] | 440 | |
| Marc Kupietz | 613f432 | 2025-09-24 13:59:24 +0200 | [diff] [blame^] | 441 | assertEquals( |
| 442 | "a[[{3:b}]]cabcab ...", |
| 443 | kr.getMatch(0).getSnippetBrackets()); |
| Nils Diewald | 44693e8 | 2014-11-05 18:00:12 +0000 | [diff] [blame] | 444 | }; |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 445 | |
| 446 | |
| Nils Diewald | f075df0 | 2015-03-03 20:34:00 +0000 | [diff] [blame] | 447 | @Ignore |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 448 | public void indexExampleFocusWithSkip () throws IOException { |
| Nils Diewald | a14ecd6 | 2015-02-26 21:00:20 +0000 | [diff] [blame] | 449 | KrillIndex ki = new KrillIndex(); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 450 | |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 451 | // abcabcabac |
| 452 | FieldDocument fd = new FieldDocument(); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 453 | fd.addTV("base", "abcabcabac", |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 454 | // The payload should be ignored |
| 455 | "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10]" + // |<>:p#0-10<i>9]" + |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 456 | "[(1-2)s:b|i:b|_1$<i>1<i>2|<>:s$<b>64<i>1<i>5<i>5]" |
| 457 | + "[(2-3)s:c|i:c|_2$<i>2<i>3|<>:s$<b>64<i>2<i>7<i>7]" |
| 458 | + "[(3-4)s:a|i:a|_3$<i>3<i>4]" |
| 459 | + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 460 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" |
| 461 | + "[(6-7)s:a|i:a|_6$<i>6<i>7]" |
| 462 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" |
| 463 | + "[(8-9)s:a|i:a|_8$<i>8<i>9]" |
| 464 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 465 | ki.addDoc(fd); |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 466 | fd = new FieldDocument(); |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 467 | fd.addTV("base", "gbcgbcgbgc", |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 468 | "[(0-1)s:g|i:g|_0$<i>0<i>1|-:t$<i>10|<>:p$<b>64<i>0<i>10<i>9]" |
| 469 | + "[(1-2)s:b|i:b|_1$<i>1<i>2|<>:s$<b>64<i>1<i>5<i>5]" |
| 470 | + "[(2-3)s:c|i:c|_2$<i>2<i>3|<>:s$<b>64<i>2<i>7<i>7]" |
| 471 | + "[(3-4)s:g|i:g|_3$<i>3<i>4]" |
| 472 | + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 473 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" |
| 474 | + "[(6-7)s:g|i:g|_6$<i>6<i>7]" |
| 475 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" |
| 476 | + "[(8-9)s:g|i:g|_8$<i>8<i>9]" |
| 477 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 478 | ki.addDoc(fd); |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 479 | fd = new FieldDocument(); |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 480 | fd.addTV("base", "gbcgbcgbgc", "[(0-1)s:g|i:g|_0$<i>0<i>1|-:t$<i>10]" |
| 481 | + "[(1-2)s:b|i:b|_1$<i>1<i>2]" + "[(2-3)s:c|i:c|_2$<i>2<i>3]" |
| 482 | + "[(3-4)s:g|i:g|_3$<i>3<i>4]" + "[(4-5)s:b|i:b|_4$<i>4<i>5]" |
| 483 | + "[(5-6)s:c|i:c|_5$<i>5<i>6]" + "[(6-7)s:g|i:g|_6$<i>6<i>7]" |
| 484 | + "[(7-8)s:b|i:b|_7$<i>7<i>8]" + "[(8-9)s:g|i:g|_8$<i>8<i>9]" |
| 485 | + "[(9-10)s:c|i:c|_9$<i>9<i>10]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 486 | ki.addDoc(fd); |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 487 | fd = new FieldDocument(); |
| 488 | // contains(<p>, focus(3: contains({2:<s>}, {3:a}))) |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 489 | fd.addTV("base", "acabcabac", |
| margaretha | 71c66ee | 2015-12-11 14:39:55 +0100 | [diff] [blame] | 490 | "[(0-1)s:a|i:a|_0$<i>0<i>1|-:t$<i>10|<>:p$<b>64<i>0<i>9<i>8]" |
| 491 | + "[(1-2)s:b|i:b|_1$<i>1<i>2|<>:s$<b>64<i>1<i>5<i>5]" |
| 492 | + "[(2-3)s:a|i:a|_2$<i>2<i>3|<>:s$<b>64<i>2<i>7<i>7]" |
| 493 | + "[(3-4)s:b|i:b|_3$<i>3<i>4]" |
| 494 | + "[(4-5)s:c|i:c|_4$<i>4<i>5]" |
| 495 | + "[(5-6)s:a|i:a|_5$<i>5<i>6]" |
| 496 | + "[(6-7)s:b|i:b|_6$<i>6<i>7]" |
| 497 | + "[(7-8)s:a|i:a|_7$<i>7<i>8]" |
| 498 | + "[(8-9)s:c|i:c|_8$<i>8<i>9]"); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 499 | ki.addDoc(fd); |
| 500 | ki.commit(); |
| 501 | |
| 502 | SpanQuery sq; |
| Nils Diewald | 884dbcf | 2015-02-27 17:02:28 +0000 | [diff] [blame] | 503 | Result kr; |
| Nils Diewald | 2d5f810 | 2015-02-26 21:07:54 +0000 | [diff] [blame] | 504 | KrillCollection kc = new KrillCollection(ki); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 505 | |
| 506 | assertEquals("Documents", 4, kc.numberOf("documents")); |
| 507 | |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 508 | // within(<p>, focus(3:within({2:<s>}, {3:a}))) |
| Nils Diewald | bb33da2 | 2015-03-04 16:24:25 +0000 | [diff] [blame] | 509 | sq = new SpanWithinQuery(new SpanElementQuery("base", "p"), |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 510 | new SpanFocusQuery(new SpanWithinQuery( |
| 511 | new SpanClassQuery(new SpanElementQuery("base", "s"), |
| 512 | (byte) 2), |
| 513 | new SpanClassQuery( |
| 514 | new SpanTermQuery(new Term("base", "s:a")), |
| 515 | (byte) 3)), |
| 516 | (byte) 3)); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 517 | |
| Akron | 6097169 | 2016-06-08 12:56:21 +0200 | [diff] [blame] | 518 | // fail("Skipping may go horribly wrong! (Known issue)"); |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 519 | |
| Akron | 6097169 | 2016-06-08 12:56:21 +0200 | [diff] [blame] | 520 | Krill ks = new Krill(sq); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 521 | ks.getMeta().setStartIndex(0).setCount((short) 20) |
| Akron | 08f4ceb | 2016-08-03 23:53:32 +0200 | [diff] [blame] | 522 | .setContext(new SearchContext(true, (short) 5, true, (short) 5)) |
| 523 | // .setCollection(kc) |
| 524 | ; |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 525 | |
| Akron | 6097169 | 2016-06-08 12:56:21 +0200 | [diff] [blame] | 526 | kr = ks.apply(ki); |
| 527 | // kr = ki.search(kc, sq, 0, (short) 20, true, (short) 5, true, (short) 5); |
| Nils Diewald | cd22686 | 2015-02-11 22:27:45 +0000 | [diff] [blame] | 528 | |
| Marc Kupietz | 613f432 | 2025-09-24 13:59:24 +0200 | [diff] [blame^] | 529 | assertEquals( |
| 530 | "spanContain(<base:p />, focus(3: spanContain({2: <base:s />}, {3: base:s:a})))", |
| 531 | kr.getSerialQuery()); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 532 | assertEquals(12, kr.getTotalResults()); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 533 | assertEquals("[a{2:bc{3:a}b}cabac]", |
| 534 | kr.getMatch(0).getSnippetBrackets()); |
| 535 | assertEquals("[ab{2:c{3:a}bcab}ac]", |
| 536 | kr.getMatch(1).getSnippetBrackets()); |
| 537 | assertEquals("[ab{2:cabc{3:a}}bac]", |
| 538 | kr.getMatch(2).getSnippetBrackets()); |
| Nils Diewald | 5c37570 | 2015-02-09 20:58:24 +0000 | [diff] [blame] | 539 | }; |
| 540 | |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 541 | }; |