You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by cp...@apache.org on 2016/10/24 18:32:49 UTC
[45/50] [abbrv] lucene-solr:jira/solr-8542-v2: LUCENE-7520: WSTE
shouldn't expand MTQ if its field doesn't match filter
LUCENE-7520: WSTE shouldn't expand MTQ if its field doesn't match filter
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/e1b06938
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/e1b06938
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/e1b06938
Branch: refs/heads/jira/solr-8542-v2
Commit: e1b06938b4b0442b18878e59fde57e29ca641499
Parents: ef57374
Author: David Smiley <ds...@apache.org>
Authored: Mon Oct 24 09:31:55 2016 -0400
Committer: David Smiley <ds...@apache.org>
Committed: Mon Oct 24 09:31:55 2016 -0400
----------------------------------------------------------------------
lucene/CHANGES.txt | 4 ++++
.../highlight/WeightedSpanTermExtractor.java | 13 +++++--------
.../lucene/search/highlight/HighlighterTest.java | 17 +++++++++++++++++
3 files changed, 26 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e1b06938/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index c4b3521..954137f 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -111,6 +111,10 @@ Improvements
* LUCENE-7496: Better toString for SweetSpotSimilarity (janhoy)
+* LUCENE-7520: Highlighter's WeightedSpanTermExtractor shouldn't attempt to expand a MultiTermQuery
+ when its field doesn't match the field the extraction is scoped to.
+ (Cao Manh Dat via David Smiley)
+
Optimizations
* LUCENE-7501: BKDReader should not store the split dimension explicitly in the
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e1b06938/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
index 1b277f1..0e0093b 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
@@ -217,13 +217,14 @@ public class WeightedSpanTermExtractor {
} else if (isQueryUnsupported(query.getClass())) {
// nothing
} else {
+ if (query instanceof MultiTermQuery &&
+ (!expandMultiTermQuery || !fieldNameComparator(((MultiTermQuery)query).getField()))) {
+ return;
+ }
Query origQuery = query;
final IndexReader reader = getLeafContext().reader();
Query rewritten;
if (query instanceof MultiTermQuery) {
- if (!expandMultiTermQuery) {
- return;
- }
rewritten = MultiTermQuery.SCORING_BOOLEAN_REWRITE.rewrite(reader, (MultiTermQuery) query);
} else {
rewritten = origQuery.rewrite(reader);
@@ -508,11 +509,7 @@ public class WeightedSpanTermExtractor {
*/
public Map<String,WeightedSpanTerm> getWeightedSpanTerms(Query query, float boost, TokenStream tokenStream,
String fieldName) throws IOException {
- if (fieldName != null) {
- this.fieldName = fieldName;
- } else {
- this.fieldName = null;
- }
+ this.fieldName = fieldName;
Map<String,WeightedSpanTerm> terms = new PositionCheckingMap<>();
this.tokenStream = tokenStream;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e1b06938/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
index fc402ba..c37709b 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
@@ -33,6 +33,7 @@ import java.util.StringTokenizer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.CachingTokenFilter;
+import org.apache.lucene.analysis.CannedTokenStream;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.analysis.MockPayloadAnalyzer;
import org.apache.lucene.analysis.MockTokenFilter;
@@ -1339,6 +1340,22 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
}
+ public void testNotRewriteMultiTermQuery() throws IOException {
+ // field "bar": (not the field we ultimately want to extract)
+ MultiTermQuery mtq = new TermRangeQuery("bar", new BytesRef("aa"), new BytesRef("zz"), true, true) ;
+ WeightedSpanTermExtractor extractor = new WeightedSpanTermExtractor() {
+ @Override
+ protected void extract(Query query, float boost, Map<String, WeightedSpanTerm> terms) throws IOException {
+ assertEquals(mtq, query);
+ super.extract(query, boost, terms);
+ }
+ };
+ extractor.setExpandMultiTermQuery(true);
+ extractor.setMaxDocCharsToAnalyze(51200);
+ extractor.getWeightedSpanTerms(
+ mtq, 3, new CannedTokenStream(new Token("aa",0,2), new Token("bb", 2,4)), "foo"); // field "foo"
+ }
+
public void testGetBestSingleFragmentWithWeights() throws Exception {
TestHighlightRunner helper = new TestHighlightRunner() {