| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 1 | package de.ids_mannheim.korap.index; |
| 2 | |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 3 | import static de.ids_mannheim.korap.TestSimple.getJsonQuery; |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 4 | import static org.junit.Assert.assertEquals; |
| 5 | |
| 6 | import java.io.IOException; |
| 7 | |
| 8 | import org.apache.lucene.index.Term; |
| 9 | import org.apache.lucene.search.spans.SpanQuery; |
| 10 | import org.apache.lucene.search.spans.SpanTermQuery; |
| 11 | import org.junit.Test; |
| 12 | |
| 13 | import de.ids_mannheim.korap.KrillIndex; |
| margaretha | f09fdd4 | 2017-12-19 17:47:50 +0100 | [diff] [blame] | 14 | import de.ids_mannheim.korap.constants.RelationDirection; |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 15 | import de.ids_mannheim.korap.query.DistanceConstraint; |
| 16 | import de.ids_mannheim.korap.query.SpanClassQuery; |
| 17 | import de.ids_mannheim.korap.query.SpanDistanceQuery; |
| 18 | import de.ids_mannheim.korap.query.SpanElementQuery; |
| 19 | import de.ids_mannheim.korap.query.SpanFocusQuery; |
| 20 | import de.ids_mannheim.korap.query.SpanNextQuery; |
| 21 | import de.ids_mannheim.korap.query.SpanReferenceQuery; |
| 22 | import de.ids_mannheim.korap.query.SpanRelationMatchQuery; |
| 23 | import de.ids_mannheim.korap.query.SpanRelationQuery; |
| 24 | import de.ids_mannheim.korap.query.wrap.SpanQueryWrapper; |
| 25 | import de.ids_mannheim.korap.response.Result; |
| 26 | import de.ids_mannheim.korap.util.QueryException; |
| 27 | |
| 28 | public class TestReferenceIndex { |
| 29 | private KrillIndex ki; |
| 30 | private Result kr; |
| 31 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 32 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 33 | @Test |
| 34 | public void testCase1 () throws IOException { |
| 35 | ki = new KrillIndex(); |
| 36 | ki.addDoc(TestRelationIndex.createFieldDoc2()); |
| 37 | ki.commit(); |
| 38 | |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 39 | SpanTermQuery stq = new SpanTermQuery(new Term("base", "pos:V")); |
| 40 | SpanElementQuery seq = new SpanElementQuery("base", "np"); |
| 41 | SpanClassQuery scq1 = new SpanClassQuery(stq, (byte) 1); |
| 42 | SpanClassQuery scq2 = new SpanClassQuery(seq, (byte) 2); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 43 | SpanNextQuery snq1 = new SpanNextQuery(scq1, scq2); |
| 44 | |
| 45 | SpanFocusQuery sfq1 = new SpanFocusQuery(snq1, (byte) 2); |
| 46 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 47 | SpanRelationQuery srq = new SpanRelationQuery( |
| margaretha | f09fdd4 | 2017-12-19 17:47:50 +0100 | [diff] [blame] | 48 | new SpanTermQuery(new Term("base", "<:child-of")), true, |
| 49 | RelationDirection.LEFT); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 50 | |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 51 | SpanElementQuery seq2 = new SpanElementQuery("base", "pp"); |
| 52 | SpanClassQuery scq3 = new SpanClassQuery(seq2, (byte) 3); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 53 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 54 | SpanRelationMatchQuery rq = new SpanRelationMatchQuery(srq, sfq1, scq3, |
| 55 | true); |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 56 | |
| 57 | // focus on np |
| 58 | SpanFocusQuery sfq2 = new SpanFocusQuery(rq, (byte) 1); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 59 | |
| 60 | DistanceConstraint constraint = new DistanceConstraint(3, 3, true, |
| 61 | false); |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 62 | SpanDistanceQuery sdq = new SpanDistanceQuery(sfq2, scq3, constraint, |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 63 | true); |
| 64 | |
| 65 | SpanReferenceQuery ref = new SpanReferenceQuery(sdq, (byte) 3, true); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 66 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 67 | kr = ki.search(ref, (short) 10); |
| Akron | 499c94c | 2016-02-04 13:13:43 +0100 | [diff] [blame] | 68 | /* |
| margaretha | 32d2bee | 2016-04-22 16:06:53 +0200 | [diff] [blame] | 69 | * for (Match km : kr.getMatches()) { |
| 70 | * |
| 71 | * System.out.println(km.getStartPos() + "," + km.getEndPos() |
| 72 | * + " " + km.getSnippetBrackets()); } |
| 73 | * System.out.println(kr.getTotalResults()); |
| 74 | */ |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 75 | |
| 76 | // cat=V & cat=np & cat=pp & #1 . #2 & #3 ->child-of #2 & #1 .{3,3} #3 |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 77 | assertEquals( |
| 78 | "spanReference(spanDistance(focus(1: focus(#[1,2]spanSegment(" |
| 79 | + "focus(#1: spanSegment(spanRelation(base:<:child-of), focus(2: spanNext(" |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 80 | + "{1: base:pos:V}, {2: <base:np />})))), {3: <base:pp />}),sorting)), " |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 81 | + "{3: <base:pp />}, [(w[3:3], ordered, notExcluded)]), 3)", |
| 82 | ref.toString()); |
| 83 | |
| 84 | assertEquals(1, kr.getMatch(0).getStartPos()); |
| 85 | assertEquals(7, kr.getMatch(0).getEndPos()); |
| 86 | } |
| 87 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 88 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 89 | @Test |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 90 | // @Ignore |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 91 | public void testCase2 () throws IOException, QueryException { |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 92 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 93 | String filepath = getClass() |
| 94 | .getResource("/queries/reference/distance-reference.jsonld") |
| 95 | .getFile(); |
| Akron | d6f5f59 | 2018-06-19 15:58:16 +0200 | [diff] [blame] | 96 | SpanQueryWrapper sqwi = getJsonQuery(filepath); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 97 | SpanQuery sq = sqwi.toQuery(); |
| 98 | |
| Eliza Margaretha | dc98dc1 | 2016-11-16 14:33:42 +0100 | [diff] [blame] | 99 | // cat="vb" & cat="prp" & cat="nn" & #1 .{0,1} #2 & #1 |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 100 | // .{0,2} #3 & #3 -> #2 |
| 101 | |
| Akron | 13db615 | 2016-02-19 14:08:38 +0100 | [diff] [blame] | 102 | assertEquals( |
| margaretha | 32d2bee | 2016-04-22 16:06:53 +0200 | [diff] [blame] | 103 | "spanReference(focus(#[1,2]spanSegment({2: <tokens:prp />}, focus(#2: " |
| Akron | 13db615 | 2016-02-19 14:08:38 +0100 | [diff] [blame] | 104 | + "spanSegment(spanRelation(tokens:>:stanford/d:tag), " |
| 105 | + "focus(3: spanDistance(focus(1: spanDistance({1: <tokens:vb />}, " |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 106 | + "{2: <tokens:prp />}, [(w[1:2], notOrdered, notExcluded)]),sorting), " |
| 107 | + "{3: <tokens:nn />}, [(w[1:3], notOrdered, notExcluded)]),sorting)),sorting)" |
| 108 | + "),sorting), 2)", |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 109 | sq.toString()); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 110 | |
| 111 | SpanElementQuery seq1 = new SpanElementQuery("tokens", "vb"); |
| 112 | // new SpanTermQuery(new Term("tokens", "c:vb")); |
| 113 | SpanElementQuery seq2 = new SpanElementQuery("tokens", "prp"); |
| 114 | // new SpanTermQuery(new Term("tokens", "c:prp")); |
| 115 | SpanElementQuery seq3 = new SpanElementQuery("tokens", "nn"); |
| 116 | // new SpanTermQuery(new Term("tokens", "c:nn")); |
| 117 | SpanClassQuery scq1 = new SpanClassQuery(seq1, (byte) 1); |
| 118 | SpanClassQuery scq2 = new SpanClassQuery(seq2, (byte) 2); |
| 119 | SpanClassQuery scq3 = new SpanClassQuery(seq3, (byte) 3); |
| 120 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 121 | SpanDistanceQuery sdq1 = new SpanDistanceQuery(scq1, scq2, |
| Akron | 13db615 | 2016-02-19 14:08:38 +0100 | [diff] [blame] | 122 | new DistanceConstraint(1, 2, false, false), true); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 123 | SpanFocusQuery sfq1 = new SpanFocusQuery(sdq1, (byte) 1); |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 124 | sfq1.setSorted(false); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 125 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 126 | SpanDistanceQuery sdq2 = new SpanDistanceQuery(sfq1, scq3, |
| Akron | 13db615 | 2016-02-19 14:08:38 +0100 | [diff] [blame] | 127 | new DistanceConstraint(1, 3, false, false), true); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 128 | SpanFocusQuery sfq2 = new SpanFocusQuery(sdq2, (byte) 3); |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 129 | sfq2.setSorted(false); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 130 | |
| 131 | // nn -> prp |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 132 | SpanRelationQuery srq = new SpanRelationQuery( |
| 133 | new SpanTermQuery(new Term("tokens", ">:stanford/d:tag")), |
| margaretha | f09fdd4 | 2017-12-19 17:47:50 +0100 | [diff] [blame] | 134 | true, RelationDirection.RIGHT); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 135 | SpanRelationMatchQuery rq = new SpanRelationMatchQuery(srq, sfq2, scq2, |
| 136 | true); |
| 137 | |
| 138 | SpanReferenceQuery ref = new SpanReferenceQuery(rq, (byte) 2, true); |
| 139 | |
| 140 | ki = new KrillIndex(); |
| 141 | ki.addDoc(createFieldDoc0()); |
| 142 | ki.commit(); |
| 143 | |
| 144 | kr = ki.search(ref, (short) 10); |
| 145 | // for (Match km : kr.getMatches()) { |
| 146 | // System.out.println(km.getStartPos() + "," + km.getEndPos() |
| 147 | // + " " |
| 148 | // + km.getSnippetBrackets()); |
| 149 | // } |
| 150 | |
| 151 | assertEquals(sq.toString(), ref.toString()); |
| 152 | assertEquals(2, kr.getMatch(0).getStartPos()); |
| 153 | assertEquals(4, kr.getMatch(0).getEndPos()); |
| 154 | assertEquals(5, kr.getMatch(1).getStartPos()); |
| 155 | assertEquals(9, kr.getMatch(1).getEndPos()); |
| 156 | assertEquals(11, kr.getMatch(2).getStartPos()); |
| 157 | assertEquals(13, kr.getMatch(2).getEndPos()); |
| 158 | |
| 159 | // multiple references |
| 160 | |
| 161 | SpanFocusQuery sfq3 = new SpanFocusQuery(ref, (byte) 1); |
| 162 | // vp -> nn |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 163 | SpanRelationMatchQuery rq2 = new SpanRelationMatchQuery(srq, sfq3, scq3, |
| 164 | true); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 165 | |
| 166 | SpanReferenceQuery ref2 = new SpanReferenceQuery(rq2, (byte) 3, true); |
| 167 | |
| 168 | kr = ki.search(ref2, (short) 10); |
| 169 | assertEquals(1, kr.getMatch(0).getStartPos()); |
| 170 | assertEquals(4, kr.getMatch(0).getEndPos()); |
| 171 | assertEquals(10, kr.getMatch(1).getStartPos()); |
| 172 | assertEquals(13, kr.getMatch(1).getEndPos()); |
| 173 | |
| 174 | // for (Match km : kr.getMatches()) { |
| 175 | // System.out.println(km.getStartPos() + "," + km.getEndPos() |
| 176 | // + " " |
| 177 | // + km.getSnippetBrackets()); |
| 178 | // } |
| 179 | } |
| 180 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 181 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 182 | // multiple references |
| 183 | @Test |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 184 | public void testCase3 () throws IOException, QueryException { |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 185 | ki = new KrillIndex(); |
| 186 | ki.addDoc(createFieldDoc0()); |
| 187 | ki.commit(); |
| 188 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 189 | String filepath = getClass() |
| 190 | .getResource( |
| 191 | "/queries/reference/distance-multiple-references.jsonld") |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 192 | .getFile(); |
| Akron | d6f5f59 | 2018-06-19 15:58:16 +0200 | [diff] [blame] | 193 | SpanQueryWrapper sqwi = getJsonQuery(filepath); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 194 | SpanQuery sq = sqwi.toQuery(); |
| 195 | |
| 196 | // 'cat="vb" & cat="prp" & cat="nn" & #1 .{0,1} #2 & #1 .{0,2} |
| 197 | // #3 & #3 ->stanford/d #2 & #1 ->stanford #3' annis |
| 198 | // without layer=c and + relation key |
| 199 | assertEquals( |
| margaretha | 32d2bee | 2016-04-22 16:06:53 +0200 | [diff] [blame] | 200 | "spanReference(focus(#[1,2]spanSegment({3: <tokens:nn />}, " |
| 201 | + "focus(#2: spanSegment(spanRelation(tokens:>:stanford/d:tag), " |
| 202 | + "focus(1: spanReference(focus(#[1,2]spanSegment({2: <tokens:prp />}, " |
| 203 | + "focus(#2: spanSegment(spanRelation(tokens:>:stanford/d:tag), " |
| 204 | + "focus(3: spanDistance(focus(1: spanDistance({1: <tokens:vb />}, " |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 205 | + "{2: <tokens:prp />}, [(w[1:2], notOrdered, notExcluded)]),sorting), " |
| 206 | + "{3: <tokens:nn />}, [(w[1:3], notOrdered, notExcluded)]),sorting)),sorting)),sorting), 2),sorting)),sorting)),sorting), 3)", |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 207 | sq.toString()); |
| 208 | kr = ki.search(sq, (short) 10); |
| 209 | // for (Match km : kr.getMatches()) { |
| 210 | // System.out.println(km.getStartPos() + "," + km.getEndPos() |
| 211 | // + " " |
| 212 | // + km.getSnippetBrackets()); |
| 213 | // } |
| 214 | assertEquals(1, kr.getMatch(0).getStartPos()); |
| 215 | assertEquals(4, kr.getMatch(0).getEndPos()); |
| 216 | assertEquals(10, kr.getMatch(1).getStartPos()); |
| 217 | assertEquals(13, kr.getMatch(1).getEndPos()); |
| 218 | } |
| 219 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 220 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 221 | // multiple document |
| 222 | @Test |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 223 | public void testCase4 () throws Exception { |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 224 | ki = new KrillIndex(); |
| 225 | ki.addDoc(createFieldDoc0()); |
| 226 | ki.addDoc(createFieldDoc1()); |
| 227 | ki.commit(); |
| 228 | |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 229 | String filepath = getClass() |
| 230 | .getResource("/queries/reference/distance-reference.jsonld") |
| 231 | .getFile(); |
| Akron | d6f5f59 | 2018-06-19 15:58:16 +0200 | [diff] [blame] | 232 | SpanQueryWrapper sqwi = getJsonQuery(filepath); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 233 | SpanQuery sq = sqwi.toQuery(); |
| 234 | |
| 235 | kr = ki.search(sq, (short) 10); |
| 236 | |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 237 | /* |
| 238 | for (Match km : kr.getMatches()) { |
| 239 | System.out.println(km.getDocID() + ":" + km.getStartPos() + "," + km.getEndPos() |
| 240 | + " " |
| 241 | + km.getSnippetBrackets()); |
| 242 | } |
| 243 | */ |
| 244 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 245 | assertEquals(4, kr.getTotalResults()); |
| 246 | assertEquals("doc-1", kr.getMatch(3).getDocID()); |
| Akron | a26184e | 2018-12-05 15:37:34 +0100 | [diff] [blame] | 247 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 248 | assertEquals(2, kr.getMatch(3).getStartPos()); |
| 249 | assertEquals(4, kr.getMatch(3).getEndPos()); |
| 250 | } |
| 251 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 252 | |
| 253 | public static FieldDocument createFieldDoc1 () { |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 254 | FieldDocument fd = new FieldDocument(); |
| 255 | fd.addString("ID", "doc-1"); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 256 | fd.addTV("tokens", |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 257 | "Frankenstein, treat my daughter well. She is the one that saved your master who you hold so dear.", |
| 258 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 259 | "[(0-12)s:Frankenstein|_0$<i>0<i>12|" |
| 260 | + "<>:nn$<b>64<i>0<i>12<i>1<b>0<s>3|" |
| 261 | + "<>:np$<b>64<i>0<i>13<i>1<b>0<s>2|" |
| 262 | + "<>:s$<b>64<i>0<i>37<i>4<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 263 | + "<:stanford/d:tag$<b>32<i>1<s>3<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 264 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 265 | + "[(14-19)s:treat|_1$<i>14<i>19|" |
| 266 | + "<>:vb$<b>64<i>14<i>19<i>2<b>0<s>1|" |
| margaretha | 10da63e | 2015-12-18 15:42:52 +0100 | [diff] [blame] | 267 | + "<>:vp$<b>64<i>14<i>36<i>4<b>0<s>2|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 268 | + ">:stanford/d:tag$<b>32<i>0<s>1<s>3<s>0|" |
| 269 | + ">:stanford/d:tag$<b>32<i>3<s>1<s>1<s>0|" |
| 270 | + ">:stanford/d:tag$<b>32<i>4<s>1<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 271 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 272 | + "[(20-22)s:my|_2$<i>20<i>22|" |
| 273 | + "<>:prp$<b>64<i>20<i>22<i>3<b>0<s>1|" |
| 274 | + "<>:np$<b>64<i>20<i>31<i>3<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 275 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 276 | + "[(23-31)s:daughter|_3$<i>23<i>31|" |
| 277 | + "<>:nn$<b>64<i>23<i>31<i>4<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 278 | + ">:stanford/d:tag$<b>32<i>2<s>1<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 279 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 280 | + "[(32-36)s:well|_4$<i>32<i>36|" |
| 281 | + "<>:rb$<b>64<i>32<i>36<i>5<b>0<s>1|" |
| 282 | + "<>:advp$<b>64<i>32<i>36<i>4<b>0<s>2]"); |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 283 | return fd; |
| 284 | } |
| 285 | |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 286 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 287 | public static FieldDocument createFieldDoc0 () { |
| 288 | FieldDocument fd = new FieldDocument(); |
| 289 | fd.addString("ID", "doc-0"); |
| Eliza Margaretha | 6f98920 | 2016-10-14 21:48:29 +0200 | [diff] [blame] | 290 | fd.addTV("tokens", |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 291 | "Frankenstein, treat my daughter well. She is the one that saved your master who you hold so dear.", |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 292 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 293 | "[(0-12)s:Frankenstein|_0$<i>0<i>12|" |
| 294 | + "<>:nn$<b>64<i>0<i>12<i>1<b>0<s>3|" |
| 295 | + "<>:np$<b>64<i>0<i>13<i>1<b>0<s>2|" |
| margaretha | 4f99558 | 2015-12-14 14:14:34 +0100 | [diff] [blame] | 296 | + "<>:s$<b>64<i>0<i>37<i>5<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 297 | + "<:stanford/d:tag$<b>32<i>1<s>3<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 298 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 299 | + "[(14-19)s:treat|_1$<i>14<i>19|" |
| 300 | + "<>:vb$<b>64<i>14<i>19<i>2<b>0<s>1|" |
| 301 | + "<>:vp$<b>64<i>14<i>36<i>5<b>0<s>2|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 302 | + ">:stanford/d:tag$<b>32<i>0<s>1<s>2<s>0|" |
| 303 | + ">:stanford/d:tag$<b>32<i>3<s>1<s>1<s>0|" |
| 304 | + ">:stanford/d:tag$<b>32<i>4<s>1<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 305 | |
| margaretha | 7ee6595 | 2015-12-14 15:39:12 +0100 | [diff] [blame] | 306 | + "[(20-22)s:my|_2$<i>20<i>22|" |
| margaretha | 10da63e | 2015-12-18 15:42:52 +0100 | [diff] [blame] | 307 | + "<>:prp$<b>64<i>20<i>22<i>3<b>0<s>1|" |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 308 | + "<>:np$<b>64<i>20<i>31<i>4<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 309 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 310 | + "[(23-31)s:daughter|_3$<i>23<i>31|" |
| 311 | + "<>:nn$<b>64<i>23<i>31<i>4<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 312 | + ">:stanford/d:tag$<b>32<i>2<s>21<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 313 | |
| margaretha | 7ee6595 | 2015-12-14 15:39:12 +0100 | [diff] [blame] | 314 | + "[(32-36)s:well|_4$<i>32<i>36|" |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 315 | + "<>:rb$<b>64<i>32<i>36<i>5<b>0<s>1|" |
| 316 | + "<>:advp$<b>64<i>32<i>36<i>5<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 317 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 318 | + "[(38-41)s:She|_5$<i>38<i>41|" |
| 319 | + "<>:prp$<b>64<i>38<i>41<i>6<b>0<s>3|" |
| 320 | + "<>:np$<b>64<i>38<i>41<i>6<b>0<s>2|" |
| 321 | + "<>:s$<b>64<i>38<i>97<i>18<b>0<s>1]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 322 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 323 | + "[(42-44)s:is|_6$<i>42<i>44|" |
| 324 | + "<>:vb$<b>64<i>42<i>44<i>7<b>0<s>1|" |
| 325 | + "<>:vp$<b>64<i>42<i>96<i>18<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 326 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 327 | + "[(45-48)s:the|_7$<i>45<i>48|" |
| 328 | + "<>:dt$<b>64<i>45<i>48<i>8<b>0<s>3|" |
| 329 | + "<>:np$<b>64<i>45<i>52<i>9<b>0<s>2|" |
| 330 | + "<>:np$<b>64<i>45<i>96<i>18<b>0<s>1]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 331 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 332 | + "[(49-52)s:one|_8$<i>49<i>52|" |
| 333 | + "<>:nn$<b>64<i>49<i>52<i>9<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 334 | + ">:stanford/d:tag$<b>32<i>5<s>1<s>3<s>0|" |
| 335 | + ">:stanford/d:tag$<b>32<i>6<s>1<s>1<s>0|" |
| 336 | + ">:stanford/d:tag$<b>32<i>7<s>1<s>3<s>0|" |
| 337 | + ">:stanford/d:tag$<b>32<i>10<s>1<s>1<s>0]" |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 338 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 339 | + "[(53-57)s:that|_9$<i>53<i>57|" |
| 340 | + "<>:rp$<b>64<i>53<i>57<i>10<b>0<s>1|" |
| 341 | + "<>:sb$<b>64<i>53<i>96<i>18<b>0<s>2]" |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 342 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 343 | + "[(58-63)s:saved|_10$<i>58<i>63|" |
| 344 | + "<>:vb$<b>64<i>58<i>63<i>11<b>0<s>1|" |
| 345 | + "<>:s$<b>64<i>58<i>96<i>18<b>0<s>2|" |
| 346 | + "<>:vp$<b>64<i>58<i>96<i>18<b>0<s>3|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 347 | + ">:stanford/d:tag$<b>32<i>9<s>1<s>1<s>0|" |
| 348 | + ">:stanford/d:tag$<b>32<i>12<s>1<s>1<s>0|" |
| 349 | + ">:stanford/d:tag$<b>32<i>15<s>1<s>33<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 350 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 351 | + "[(64-68)s:your|_11$<i>64<i>68|" |
| 352 | + "<>:prp$<b>64<i>64<i>68<i>12<b>0<s>1|" |
| 353 | + "<>:np$<b>64<i>64<i>75<i>13<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 354 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 355 | + "[(69-75)s:master|_12$<i>69<i>75|" |
| 356 | + "<>:nn$<b>64<i>69<i>75<i>13<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 357 | + ">:stanford/d:tag$<b>32<i>11<s>1<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 358 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 359 | + "[(76-79)s:who|_13$<i>76<i>79|" |
| 360 | + "<>:rp$<b>64<i>76<i>79<i>14<b>0<s>1|" |
| 361 | + "<>:sb$<b>64<i>76<i>96<i>18<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 362 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 363 | + "[(80-83)s:you|_14$<i>80<i>83|" |
| 364 | + "<>:prp$<b>64<i>80<i>83<i>15<b>0<s>3|" |
| 365 | + "<>:np$<b>64<i>80<i>83<i>15<b>0<s>2|" |
| 366 | + "<>:s$<b>64<i>80<i>96<i>18<b>0<s>1]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 367 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 368 | + "[(84-88)s:hold|_15$<i>84<i>88|" |
| 369 | + "<>:vb$<b>64<i>84<i>88<i>16<b>0<s>2|" |
| 370 | + "<>:vp$<b>64<i>84<i>96<i>18<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 371 | + ">:stanford/d:tag$<b>32<i>13<s>2<s>1<s>0|" |
| 372 | + ">:stanford/d:tag$<b>32<i>14<s>2<s>3<s>0|" |
| 373 | + ">:stanford/d:tag$<b>32<i>17<s>2<s>1<s>0]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 374 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 375 | + "[(89-91)s:so|_16$<i>89<i>91|" |
| 376 | + "<>:rb$<b>64<i>89<i>91<i>17<b>0<s>1|" |
| 377 | + "<>:adjp$<b>64<i>89<i>96<i>18<b>0<s>2]" |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 378 | |
| Akron | 4299355 | 2016-02-04 13:24:24 +0100 | [diff] [blame] | 379 | + "[(92-96)s:dear|_17$<i>92<i>96|" |
| 380 | + "<>:jj$<b>64<i>92<i>96<i>18<b>0<s>1|" |
| margaretha | 29a3911 | 2016-04-04 12:10:11 +0200 | [diff] [blame] | 381 | + ">:stanford/d:tag$<b>32<i>16<s>1<s>1<s>0]"); |
| Akron | bb5d173 | 2015-06-22 01:22:40 +0200 | [diff] [blame] | 382 | |
| margaretha | 61eb20e | 2015-05-07 11:53:01 +0200 | [diff] [blame] | 383 | return fd; |
| 384 | } |
| 385 | } |