You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ro...@apache.org on 2012/11/12 22:39:54 UTC
svn commit: r1408467 [2/2] - in
/lucene/dev/branches/LUCENE-2878/lucene/core/src:
java/org/apache/lucene/search/intervals/
test/org/apache/lucene/search/intervals/
Copied: lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestNestedIntervalFilterQueries.java (from r1405439, lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestIntervalFilterQueries.java)
URL: http://svn.apache.org/viewvc/lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestNestedIntervalFilterQueries.java?p2=lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestNestedIntervalFilterQueries.java&p1=lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestIntervalFilterQueries.java&r1=1405439&r2=1408467&rev=1408467&view=diff
==============================================================================
--- lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestIntervalFilterQueries.java (original)
+++ lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestNestedIntervalFilterQueries.java Mon Nov 12 21:39:45 2012
@@ -17,51 +17,24 @@ package org.apache.lucene.search.interva
* limitations under the License.
*/
-import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.TextField;
-import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.RandomIndexWriter;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.search.*;
-import org.apache.lucene.search.intervals.OrderedNearQuery;
-import org.apache.lucene.search.intervals.UnorderedNearQuery;
-import org.apache.lucene.store.Directory;
-import org.apache.lucene.util.LuceneTestCase;
+import org.apache.lucene.search.BooleanClause;
+import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.Query;
import java.io.IOException;
-public class TestIntervalFilterQueries extends LuceneTestCase {
-
- private IndexSearcher searcher;
- private IndexReader reader;
- private Directory directory;
-
- public static final String field = "field";
+public class TestNestedIntervalFilterQueries extends IntervalTestBase {
@Override
- public void setUp() throws Exception {
- super.setUp();
- directory = newDirectory();
- RandomIndexWriter writer = new RandomIndexWriter(random(), directory,
- newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random()))
- .setMergePolicy(newLogMergePolicy()));
+ protected void addDocs(RandomIndexWriter writer) throws IOException {
for (int i = 0; i < docFields.length; i++) {
Document doc = new Document();
- doc.add(newField(field, docFields[i], TextField.TYPE_STORED));
+ doc.add(newField("field", docFields[i], TextField.TYPE_STORED));
writer.addDocument(doc);
}
- writer.forceMerge(1);
- reader = writer.getReader();
- writer.close();
- searcher = newSearcher(reader);
- }
-
- @Override
- public void tearDown() throws Exception {
- reader.close();
- directory.close();
- super.tearDown();
}
private String[] docFields = {
@@ -71,23 +44,29 @@ public class TestIntervalFilterQueries e
"w1 w3 w2 w4 w5 w6 w7 w8", //3
};
- public TermQuery makeTermQuery(String text) {
- return new TermQuery(new Term(field, text));
- }
-
- private void checkHits(Query query, int[] results) throws IOException {
- CheckHits.checkHits(random(), query, field, searcher, results);
+ public void testOrderedDisjunctionQueries() throws IOException {
+ // Two phrases whose subparts appear in a document, but that do not fulfil the slop
+ // requirements of the parent IntervalFilterQuery
+ Query sentence1 = new OrderedNearQuery(0, makeTermQuery("w1"), makeTermQuery("w8"), makeTermQuery("w4"));
+ Query sentence2 = new OrderedNearQuery(0, makeTermQuery("w3"), makeTermQuery("w7"), makeTermQuery("w6"));
+ BooleanQuery bq = new BooleanQuery();
+ bq.add(sentence1, BooleanClause.Occur.SHOULD);
+ bq.add(sentence2, BooleanClause.Occur.SHOULD);
+ checkIntervals(bq, searcher, new int[][]{});
}
// or(w1 pre/2 w2, w1 pre/3 w10)
public void testOrNearNearQuery() throws IOException {
- Query near1 = new OrderedNearQuery(2, makeTermQuery("w1"), makeTermQuery("w2"));
- Query near2 = new OrderedNearQuery(3, makeTermQuery("w1"), makeTermQuery("w10"));
+ Query near1 = new OrderedNearQuery(2, false, makeTermQuery("w1"), makeTermQuery("w2"));
+ Query near2 = new OrderedNearQuery(3, false, makeTermQuery("w1"), makeTermQuery("w10"));
BooleanQuery bq = new BooleanQuery();
bq.add(near1, BooleanClause.Occur.SHOULD);
bq.add(near2, BooleanClause.Occur.SHOULD);
-
- checkHits(bq, new int[] { 0, 2, 3 });
+ checkIntervals(bq, searcher, new int[][]{
+ { 0, 0, 1, 0, 9 },
+ { 2, 0, 2 },
+ { 3, 0, 2 }
+ });
}
// or(w2 within/2 w1, w10 within/3 w1)
@@ -97,15 +76,20 @@ public class TestIntervalFilterQueries e
BooleanQuery bq = new BooleanQuery();
bq.add(near1, BooleanClause.Occur.SHOULD);
bq.add(near2, BooleanClause.Occur.SHOULD);
-
- checkHits(bq, new int[] { 0, 2, 3 });
+ checkIntervals(bq, searcher, new int[][]{
+ {0, 0, 1},
+ {2, 0, 2},
+ {3, 0, 2}
+ });
}
// (a pre/2 b) pre/6 (c pre/2 d)
public void testNearNearNearQuery() throws IOException {
- Query near1 = new OrderedNearQuery(2, makeTermQuery("w1"), makeTermQuery("w4"));
- Query near2 = new OrderedNearQuery(2, makeTermQuery("w10"), makeTermQuery("w12"));
+ Query near1 = new OrderedNearQuery(2, false, makeTermQuery("w1"), makeTermQuery("w4"));
+ Query near2 = new OrderedNearQuery(2, false, makeTermQuery("w10"), makeTermQuery("w12"));
Query near3 = new OrderedNearQuery(6, near1, near2);
- checkHits(near3, new int[] { 0 });
+ checkIntervals(near3, searcher, new int[][]{
+ { 0, 0, 11, 0, 3, 9, 11 }
+ });
}
}
Modified: lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestPositionsAndOffsets.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestPositionsAndOffsets.java?rev=1408467&r1=1408466&r2=1408467&view=diff
==============================================================================
--- lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestPositionsAndOffsets.java (original)
+++ lucene/dev/branches/LUCENE-2878/lucene/core/src/test/org/apache/lucene/search/intervals/TestPositionsAndOffsets.java Mon Nov 12 21:39:45 2012
@@ -16,57 +16,28 @@ package org.apache.lucene.search.interva
* limitations under the License.
*/
-import java.io.IOException;
-import java.util.List;
-
-import org.apache.lucene.analysis.MockAnalyzer;
-import org.apache.lucene.codecs.Codec;
-import org.apache.lucene.codecs.lucene41.Lucene41PostingsFormat;
-import org.apache.lucene.codecs.memory.MemoryPostingsFormat;
-import org.apache.lucene.codecs.nestedpulsing.NestedPulsingPostingsFormat;
-import org.apache.lucene.codecs.pulsing.Pulsing41PostingsFormat;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.TextField;
-import org.apache.lucene.index.AtomicReaderContext;
import org.apache.lucene.index.FieldInfo;
-import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.index.IndexReaderContext;
-import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.RandomIndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
-import org.apache.lucene.search.IndexSearcher;
-import org.apache.lucene.search.MultiPhraseQuery;
-import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
-import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.TermQuery;
-import org.apache.lucene.search.Weight.PostingFeatures;
-import org.apache.lucene.search.Weight;
-import org.apache.lucene.search.intervals.Interval;
-import org.apache.lucene.search.intervals.IntervalIterator;
-import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
-import org.apache.lucene.util.LuceneTestCase;
-import org.apache.lucene.util._TestUtil;
-
-@SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom"})
-public class TestPositionsAndOffsets extends LuceneTestCase {
-
- // What am I testing here?
- // - can get offsets out of a basic TermQuery, and a more complex BooleanQuery
- // - if offsets are not stored, then we get -1 returned
+import java.io.IOException;
+// We need to store offsets here, so don't use the following Codecs, which don't
+// support them.
+@SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom"})
+public class TestPositionsAndOffsets extends IntervalTestBase {
- private static void addDocs(RandomIndexWriter writer, boolean withOffsets) throws IOException {
- FieldType fieldType = TextField.TYPE_STORED;
- if (withOffsets) {
- fieldType = new FieldType(fieldType);
- fieldType.setIndexOptions(FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
- }
+ protected void addDocs(RandomIndexWriter writer) throws IOException {
+ FieldType fieldType = new FieldType(TextField.TYPE_NOT_STORED);
+ fieldType.setIndexOptions(FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS);
Document doc = new Document();
doc.add(newField(
"field",
@@ -76,103 +47,22 @@ public class TestPositionsAndOffsets ext
writer.addDocument(doc);
}
- private void testQuery(Query query, int[][] expectedOffsets) throws IOException {
- testQuery(query, expectedOffsets, true);
- }
-
- private void testQuery(Query query, int[][] expectedOffsets, boolean needsOffsets) throws IOException {
- Directory directory = newDirectory();
- RandomIndexWriter writer = new RandomIndexWriter(random(), directory, newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random())));
- addDocs(writer, needsOffsets);
-
- IndexReader reader = writer.getReader();
- IndexSearcher searcher = new IndexSearcher(reader);
- writer.close();
-
- Weight weight = query.createWeight(searcher);
- IndexReaderContext topReaderContext = searcher.getTopReaderContext();
- List<AtomicReaderContext> leaves = topReaderContext.leaves();
- assertEquals(1, leaves.size());
- Scorer scorer = weight.scorer(leaves.get(0),
- true, true, PostingFeatures.OFFSETS, leaves.get(0).reader().getLiveDocs());
-
- int nextDoc = scorer.nextDoc();
- assertEquals(0, nextDoc);
- IntervalIterator positions = scorer.intervals(false);
- int startOffsets[] = expectedOffsets[0];
- int endOffsets[] = expectedOffsets[1];
-
- assertEquals(0, positions.scorerAdvanced(nextDoc));
- for (int i = 0; i < startOffsets.length; i++) {
- Interval interval = positions.next();
- assertEquals("i: " + i, startOffsets[i], interval.offsetBegin);
- assertEquals("i: " + i, endOffsets[i], interval.offsetEnd);
- }
-
- assertNull(positions.next());
-
- reader.close();
- directory.close();
- }
-
- public void testTermQueryWithoutOffsets() throws IOException {
+ public void testTermQueryOffsets() throws IOException {
Query query = new TermQuery(new Term("field", "porridge"));
- int[] startOffsets = new int[] { 6, 26, 47, 164, 184 };
- int[] endOffsets = new int[] { 14, 34, 55, 172, 192 };
- testQuery(query, new int[][] { startOffsets, endOffsets });
+ checkIntervalOffsets(query, searcher, new int[][]{
+ { 0, 6, 14, 26, 34, 47, 55, 164, 172, 184, 192 }
+ });
}
- public void testBooleanQueryWithOffsets() throws IOException {
-
+ public void testBooleanQueryOffsets() throws IOException {
BooleanQuery query = new BooleanQuery();
query.add(new BooleanClause(new TermQuery(new Term("field", "porridge")),
BooleanClause.Occur.MUST));
query.add(new BooleanClause(new TermQuery(new Term("field", "nine")),
BooleanClause.Occur.MUST));
- int[] startOffsetsConj = new int[] {47,143};
- int[] endOffsetsConj = new int[] {71, 172};
- testQuery(query, new int[][] {startOffsetsConj, endOffsetsConj});
- }
-
- public void testExactPhraseQuery() throws IOException {
- PhraseQuery query = new PhraseQuery();
- query.add(new Term("field", "pease"));
- query.add(new Term("field", "porridge"));
- query.add(new Term("field", "hot!"));
- int[] startOffsetsBlock = new int[] {0, 158};
- int[] endOffsetsBlock = new int[] {19, 177};
- testQuery(query, new int[][] {startOffsetsBlock, endOffsetsBlock});
- }
-
- public void testSloppyPhraseQuery() throws IOException {
- PhraseQuery query = new PhraseQuery();
- query.add(new Term("field", "pease"));
- query.add(new Term("field", "hot!"));
- query.setSlop(1);
- int[] startOffsetsBlock = new int[] {0, 158};
- int[] endOffsetsBlock = new int[] {19, 177};
- testQuery(query, new int[][] {startOffsetsBlock, endOffsetsBlock});
- }
-
- public void testManyTermSloppyPhraseQuery() throws IOException {
- PhraseQuery query = new PhraseQuery();
- query.add(new Term("field", "pease"));
- query.add(new Term("field", "porridge"));
- query.add(new Term("field", "pot"));
- query.setSlop(2);
- int[] startOffsetsBlock = new int[] {41};
- int[] endOffsetsBlock = new int[] {66};
- testQuery(query, new int[][] {startOffsetsBlock, endOffsetsBlock});
- }
-
- public void testMultiTermPhraseQuery() throws IOException {
- MultiPhraseQuery query = new MultiPhraseQuery();
- query.add(new Term("field", "pease"));
- query.add(new Term("field", "porridge"));
- query
- .add(new Term[] {new Term("field", "hot!"), new Term("field", "cold!")});
- int[] startOffsetsBlock = new int[] {0, 20, 158, 178};
- int[] endOffsetsBlock = new int[] {19, 40, 177, 198};
- testQuery(query, new int[][] {startOffsetsBlock, endOffsetsBlock});
+ checkIntervalOffsets(query, searcher, new int[][]{
+ { 0, 47, 71, 143, 172 }
+ });
}
+
}
\ No newline at end of file