Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-5969: add changes and test 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene5969@1629408 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2014-10-04 16:27:03 +00:00
parent 206fb874bc
commit f97e873d8b
2 changed files with 46 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
lucene/CHANGES.txt
View File

@ -73,6 +73,10 @@ New Features
* LUCENE-5911: Add MemoryIndex.freeze() to allow thread-safe searching over a
MemoryIndex. (Alan Woodward)
* LUCENE-5969: Lucene 5.0 has a new index format with mismatched file detection,
improved exception handling, and indirect norms encoding for sparse fields.
(Mike McCandless, Robert Muir)
API Changes
* LUCENE-5900: Deprecated more constructors taking Version in *InfixSuggester and
@ -142,6 +146,11 @@ API Changes
* LUCENE-5924: Rename CheckIndex -fix option to -exorcise. This option does not
actually fix the index, it just drops data. (Robert Muir)
* LUCENE-5969: Add Codec.compoundFormat, which handles the encoding of compound
files. Add getMergeInstance() to codec producer APIs, which can be overridden
to return an instance optimized for merging instead of searching.
(Mike McCandless, Robert Muir)
Bug Fixes
* LUCENE-5650: Enforce read-only access to any path outside the temporary
@ -193,6 +202,10 @@ Optimizations
queries that match few documents by using a sparse bit set implementation.
(Adrien Grand)
* LUCENE-5969: Refactor merging to be more efficient, checksum calculation is
per-segment/per-producer, and norms and doc values merging no longer cause
RAM spikes for latent fields. (Mike McCandless, Robert Muir)
Build
* LUCENE-5909: Smoke tester now has better command line parsing and

33
lucene/core/src/test/org/apache/lucene/codecs/lucene41/TestBlockPostingsFormat.java
View File

@ -17,8 +17,17 @@ package org.apache.lucene.codecs.lucene41;
* limitations under the License.
*/
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.codecs.Codec;
import org.apache.lucene.codecs.blocktree.FieldReader;
import org.apache.lucene.codecs.blocktree.Stats;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.BasePostingsFormatTestCase;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.TestUtil;
/**
@ -31,4 +40,28 @@ public class TestBlockPostingsFormat extends BasePostingsFormatTestCase {
protected Codec getCodec() {
return codec;
}
/** Make sure the final sub-block(s) are not skipped. */
public void testFinalBlock() throws Exception {
Directory d = newDirectory();
IndexWriter w = new IndexWriter(d, new IndexWriterConfig(new MockAnalyzer(random())));
for(int i=0;i<25;i++) {
Document doc = new Document();
doc.add(newStringField("field", Character.toString((char) (97+i)), Field.Store.NO));
doc.add(newStringField("field", "z" + Character.toString((char) (97+i)), Field.Store.NO));
w.addDocument(doc);
}
w.forceMerge(1);
DirectoryReader r = DirectoryReader.open(w, true);
assertEquals(1, r.leaves().size());
FieldReader field = (FieldReader) r.leaves().get(0).reader().fields().terms("field");
// We should see exactly two blocks: one root block (prefix empty string) and one block for z* terms (prefix z):
Stats stats = field.computeStats();
assertEquals(0, stats.floorBlockCount);
assertEquals(2, stats.nonFloorBlockCount);
r.close();
w.close();
d.close();
}
}