| Eliza Margaretha | 0192918 | 2014-02-19 11:48:59 +0000 | [diff] [blame] | 1 | package de.ids_mannheim.korap.index; |
| 2 | |
| Nils Diewald | f399a67 | 2013-11-18 17:55:22 +0000 | [diff] [blame] | 3 | import java.util.*; |
| 4 | import java.io.*; |
| 5 | |
| 6 | import static org.junit.Assert.*; |
| 7 | import org.junit.Test; |
| 8 | import org.junit.Ignore; |
| 9 | import org.junit.runner.RunWith; |
| 10 | import org.junit.runners.JUnit4; |
| 11 | |
| 12 | import de.ids_mannheim.korap.KorapIndex; |
| 13 | import de.ids_mannheim.korap.KorapQuery; |
| 14 | import de.ids_mannheim.korap.KorapResult; |
| 15 | import de.ids_mannheim.korap.query.SpanElementQuery; |
| 16 | import de.ids_mannheim.korap.query.SpanWithinQuery; |
| 17 | import de.ids_mannheim.korap.query.SpanNextQuery; |
| 18 | import de.ids_mannheim.korap.query.SpanClassQuery; |
| 19 | import de.ids_mannheim.korap.index.FieldDocument; |
| 20 | import de.ids_mannheim.korap.analysis.MultiTermTokenStream; |
| 21 | import de.ids_mannheim.korap.index.PositionsToOffset; |
| 22 | |
| 23 | import org.apache.lucene.index.AtomicReaderContext; |
| 24 | import org.apache.lucene.search.spans.SpanQuery; |
| 25 | import org.apache.lucene.search.spans.SpanTermQuery; |
| 26 | import org.apache.lucene.index.TermContext; |
| 27 | import org.apache.lucene.util.OpenBitSet; |
| 28 | import org.apache.lucene.search.DocIdSet; |
| 29 | import org.apache.lucene.util.DocIdBitSet; |
| 30 | import org.apache.lucene.util.Bits; |
| 31 | |
| 32 | import java.nio.ByteBuffer; |
| 33 | |
| 34 | |
| 35 | @RunWith(JUnit4.class) |
| 36 | public class TestPosToOffset { |
| 37 | |
| 38 | @Test |
| 39 | public void indexExample1 () throws IOException { |
| 40 | KorapIndex ki = new KorapIndex(); |
| 41 | |
| 42 | FieldDocument fd = new FieldDocument(); |
| 43 | fd.addTV("base", |
| 44 | "a b c", |
| 45 | "[(0-1)s:a|i:a|_0#0-1|-:t$<i>3]" + |
| 46 | "[(2-3)s:b|i:b|_1#2-3]" + |
| 47 | "[(4-5)s:c|i:c|_2#4-5]"); |
| 48 | ki.addDoc(fd); |
| 49 | |
| 50 | fd = new FieldDocument(); |
| 51 | fd.addTV("base", |
| 52 | "x y z", |
| 53 | "[(0-1)s:x|i:x|_0#0-2|-:t$<i>3]" + |
| 54 | "[(3-4)s:y|i:y|_1#3-4]" + |
| 55 | "[(6-7)s:z|i:z|_2#6-7]"); // 3 |
| 56 | ki.addDoc(fd); |
| 57 | |
| 58 | ki.commit(); |
| 59 | |
| 60 | String field = "base"; |
| 61 | |
| 62 | for (AtomicReaderContext atomic : ki.reader().leaves()) { |
| 63 | PositionsToOffset pto = new PositionsToOffset(atomic, field); |
| 64 | |
| 65 | pto.add(0,1); |
| 66 | pto.add(0,2); |
| 67 | pto.add(1,2); |
| 68 | pto.add(1,1); |
| 69 | pto.add(1,20); |
| 70 | |
| 71 | assertEquals("Start 0,1", pto.start(0,1), 2); |
| 72 | assertEquals("End 0,1", pto.end(0,1), 3); |
| 73 | |
| 74 | assertEquals("Start 0,2", pto.start(0,2), 4); |
| 75 | assertEquals("End 0,2", pto.end(0,2), 5); |
| 76 | |
| 77 | assertEquals("Start 1,2", pto.start(1,2), 6); |
| 78 | assertEquals("End 1,2", pto.end(1,2), 7); |
| 79 | |
| 80 | assertEquals("Start 1,1", pto.start(1,1), 3); |
| 81 | assertEquals("End 1,1", pto.end(1,1), 4); |
| 82 | |
| 83 | assertEquals("Start 1,20", pto.start(1,20), 0); |
| 84 | assertEquals("End 1,20", pto.end(1,20), -1); |
| 85 | }; |
| 86 | }; |
| 87 | }; |