You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ds...@apache.org on 2016/09/09 14:06:56 UTC
lucene-solr:master: LUCENE-7417: Highlighter WSTE didn't handle
single-term MultiPhraseQuery. Also updated to Java 5 for-each in this method.
Repository: lucene-solr
Updated Branches:
refs/heads/master 003a346d5 -> 3966f9982
LUCENE-7417: Highlighter WSTE didn't handle single-term MultiPhraseQuery.
Also updated to Java 5 for-each in this method.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/3966f998
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/3966f998
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/3966f998
Branch: refs/heads/master
Commit: 3966f998214e8d34593ccde2db70c5cc49966443
Parents: 003a346
Author: David Smiley <ds...@apache.org>
Authored: Fri Sep 9 10:06:39 2016 -0400
Committer: David Smiley <ds...@apache.org>
Committed: Fri Sep 9 10:06:39 2016 -0400
----------------------------------------------------------------------
lucene/CHANGES.txt | 16 ++++++++++-
.../highlight/WeightedSpanTermExtractor.java | 26 +++++++++--------
.../search/highlight/HighlighterTest.java | 30 +++++++++++++-------
3 files changed, 48 insertions(+), 24 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/3966f998/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 1387d25..9603ea5 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -36,7 +36,21 @@ Other
======================= Lucene 6.3.0 =======================
-(No changes)
+API Changes
+
+New Features
+
+Bug Fixes
+
+* LUCENE-7417: The standard Highlighter could throw an IllegalArgumentException when
+ trying to highlight a query containing a degenerate case of a MultiPhraseQuery with one
+ term. (Thomas Kappler via David Smiley)
+
+Improvements
+
+Optimizations
+
+Other
======================= Lucene 6.2.0 =======================
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/3966f998/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 837201e..7f79809 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
@@ -118,8 +118,7 @@ public class WeightedSpanTermExtractor {
Term[] phraseQueryTerms = phraseQuery.getTerms();
if (phraseQueryTerms.length == 1) {
extractWeightedSpanTerms(terms, new SpanTermQuery(phraseQueryTerms[0]), boost);
- }
- else {
+ } else {
SpanQuery[] clauses = new SpanQuery[phraseQueryTerms.length];
for (int i = 0; i < phraseQueryTerms.length; i++) {
clauses[i] = new SpanTermQuery(phraseQueryTerms[i]);
@@ -153,8 +152,8 @@ public class WeightedSpanTermExtractor {
// this query is TermContext sensitive.
extractWeightedTerms(terms, query, boost);
} else if (query instanceof DisjunctionMaxQuery) {
- for (Iterator<Query> iterator = ((DisjunctionMaxQuery) query).iterator(); iterator.hasNext();) {
- extract(iterator.next(), boost, terms);
+ for (Query clause : ((DisjunctionMaxQuery) query)) {
+ extract(clause, boost, terms);
}
} else if (query instanceof ToParentBlockJoinQuery) {
extract(((ToParentBlockJoinQuery) query).getChildQuery(), boost, terms);
@@ -184,16 +183,15 @@ public class WeightedSpanTermExtractor {
disjuncts = (disjunctLists[positions[i]] = new ArrayList<>(termArray.length));
++distinctPositions;
}
- for (int j = 0; j < termArray.length; ++j) {
- disjuncts.add(new SpanTermQuery(termArray[j]));
+ for (Term aTermArray : termArray) {
+ disjuncts.add(new SpanTermQuery(aTermArray));
}
}
int positionGaps = 0;
int position = 0;
final SpanQuery[] clauses = new SpanQuery[distinctPositions];
- for (int i = 0; i < disjunctLists.length; ++i) {
- List<SpanQuery> disjuncts = disjunctLists[i];
+ for (List<SpanQuery> disjuncts : disjunctLists) {
if (disjuncts != null) {
clauses[position++] = new SpanOrQuery(disjuncts
.toArray(new SpanQuery[disjuncts.size()]));
@@ -202,11 +200,15 @@ public class WeightedSpanTermExtractor {
}
}
- final int slop = mpq.getSlop();
- final boolean inorder = (slop == 0);
+ if (clauses.length == 1) {
+ extractWeightedSpanTerms(terms, clauses[0], boost);
+ } else {
+ final int slop = mpq.getSlop();
+ final boolean inorder = (slop == 0);
- SpanNearQuery sp = new SpanNearQuery(clauses, slop + positionGaps, inorder);
- extractWeightedSpanTerms(terms, sp, boost);
+ SpanNearQuery sp = new SpanNearQuery(clauses, slop + positionGaps, inorder);
+ extractWeightedSpanTerms(terms, sp, boost);
+ }
}
} else if (query instanceof MatchAllDocsQuery) {
//nothing
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/3966f998/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 cf727d7..fc402ba 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
@@ -94,7 +94,6 @@ import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.automaton.Automata;
import org.apache.lucene.util.automaton.CharacterRunAutomaton;
import org.apache.lucene.util.automaton.RegExp;
-import org.junit.Test;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
@@ -1580,30 +1579,39 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
helper.start();
}
- @Test
public void testHighlighterWithPhraseQuery() throws IOException, InvalidTokenOffsetsException {
+ final String fieldName = "substring";
+
+ final PhraseQuery query = new PhraseQuery(fieldName, new BytesRef[] { new BytesRef("uchu") });
+
+ assertHighlighting(query, new SimpleHTMLFormatter("<b>", "</b>"), "Buchung", "B<b>uchu</b>ng", fieldName);
+ }
+
+ public void testHighlighterWithMultiPhraseQuery() throws IOException, InvalidTokenOffsetsException {
+ final String fieldName = "substring";
+
+ final MultiPhraseQuery mpq = new MultiPhraseQuery.Builder()
+ .add(new Term(fieldName, "uchu")).build();
+ assertHighlighting(mpq, new SimpleHTMLFormatter("<b>", "</b>"), "Buchung", "B<b>uchu</b>ng", fieldName);
+ }
+
+ private void assertHighlighting(Query query, Formatter formatter, String text, String expected, String fieldName)
+ throws IOException, InvalidTokenOffsetsException {
final Analyzer analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
return new TokenStreamComponents(new NGramTokenizer(4, 4));
}
};
- final String fieldName = "substring";
-
- final List<BytesRef> list = new ArrayList<>();
- list.add(new BytesRef("uchu"));
- final PhraseQuery query = new PhraseQuery(fieldName, list.toArray(new BytesRef[list.size()]));
final QueryScorer fragmentScorer = new QueryScorer(query, fieldName);
- final SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<b>", "</b>");
final Highlighter highlighter = new Highlighter(formatter, fragmentScorer);
highlighter.setTextFragmenter(new SimpleFragmenter(100));
- final String fragment = highlighter.getBestFragment(analyzer, fieldName, "Buchung");
-
- assertEquals("B<b>uchu</b>ng",fragment);
+ final String fragment = highlighter.getBestFragment(analyzer, fieldName, text);
+ assertEquals(expected, fragment);
}
public void testUnRewrittenQuery() throws Exception {