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

LUCENE-8040: optimize IndexSearcher.collectionStatistics

This commit is contained in:
David Smiley 2017-11-15 08:57:47 -05:00
parent 183571c085
commit af2b903f65
2 changed files with 19 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lucene/CHANGES.txt
View File

@ -41,6 +41,12 @@ Improvements
Add missing range checks for similarity parameters.
Improve BM25 and ClassicSimilarity's explanations. (Robert Muir)
Optimizations
* LUCENE-8040: Optimize IndexSearcher.collectionStatistics, avoiding MultiFields/MultiTerms
(David Smiley, Robert Muir)
======================= Lucene 7.2.0 =======================
API Changes

26
lucene/core/src/java/org/apache/lucene/search/IndexSearcher.java
View File

@ -37,7 +37,6 @@ import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexReaderContext;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.index.ReaderUtil;
import org.apache.lucene.index.StoredFieldVisitor;
import org.apache.lucene.index.Term;
@ -778,21 +777,22 @@ public class IndexSearcher {
* @lucene.experimental
*/
public CollectionStatistics collectionStatistics(String field) throws IOException {
final int docCount;
final long sumTotalTermFreq;
final long sumDocFreq;
assert field != null;
Terms terms = MultiFields.getTerms(reader, field);
if (terms == null) {
long docCount = 0;
long sumTotalTermFreq = 0;
long sumDocFreq = 0;
for (LeafReaderContext leaf : reader.leaves()) {
final Terms terms = leaf.reader().terms(field);
if (terms == null) {
continue;
}
docCount += terms.getDocCount();
sumTotalTermFreq += terms.getSumTotalTermFreq();
sumDocFreq += terms.getSumDocFreq();
}
if (docCount == 0) {
return null;
}
docCount = terms.getDocCount();
sumTotalTermFreq = terms.getSumTotalTermFreq();
sumDocFreq = terms.getSumDocFreq();
return new CollectionStatistics(field, reader.maxDoc(), docCount, sumTotalTermFreq, sumDocFreq);
}
}