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

LUCENE-7286: Added support for highlighting SynonymQuery.

This commit is contained in:
Adrien Grand 2016-06-10 09:11:15 +02:00
parent 74d94ec265
commit ef707f05ae
3 changed files with 24 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lucene/CHANGES.txt
View File

@ -126,6 +126,8 @@ Bug Fixes
other ranges had more than one clause matching (Ahmet Arslan,
hossman, Mike McCandless)
* LUCENE-7286: Added support for highlighting SynonymQuery. (Adrien Grand)
Other
* LUCENE-7295: TermAutomatonQuery.hashCode calculates Automaton.toDot().hash,

3
lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
View File

@ -53,6 +53,7 @@ import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.join.ToChildBlockJoinQuery;
import org.apache.lucene.search.join.ToParentBlockJoinQuery;
@ -138,7 +139,7 @@ public class WeightedSpanTermExtractor {
SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
} else if (query instanceof TermQuery) {
} else if (query instanceof TermQuery || query instanceof SynonymQuery) {
extractWeightedTerms(terms, query, boost);
} else if (query instanceof SpanQuery) {
extractWeightedSpanTerms(terms, (SpanQuery) query, boost);

21
lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
View File

@ -71,6 +71,7 @@ import org.apache.lucene.search.PhraseQuery.Builder;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
@ -223,6 +224,24 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
assertEquals("This piece of text refers to Kennedy at the beginning then has a longer piece of text that is <B>very</B>", fragment);
}
public void testHighlightingSynonymQuery() throws Exception {
searcher = newSearcher(reader);
Query query = new SynonymQuery(new Term(FIELD_NAME, "jfk"), new Term(FIELD_NAME, "kennedy"));
QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
Highlighter highlighter = new Highlighter(scorer);
TokenStream stream = getAnyTokenStream(FIELD_NAME, 2);
Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
highlighter.setTextFragmenter(fragmenter);
String storedField = searcher.doc(2).get(FIELD_NAME);
String fragment = highlighter.getBestFragment(stream, storedField);
assertEquals("<B>JFK</B> has been shot", fragment);
stream = getAnyTokenStream(FIELD_NAME, 3);
storedField = searcher.doc(3).get(FIELD_NAME);
fragment = highlighter.getBestFragment(stream, storedField);
assertEquals("John <B>Kennedy</B> has been shot", fragment);
}
public void testHighlightUnknownQueryAfterRewrite() throws IOException, InvalidTokenOffsetsException {
Query query = new Query() {
@ -2093,7 +2112,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, MockTokenFilter.ENGLISH_STOPSET);
ramDir = newDirectory();
fieldType = random().nextBoolean() ? FIELD_TYPE_TV : TextField.TYPE_STORED;
IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer));
IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer).setMergePolicy(newLogMergePolicy()));
for (String text : texts) {
writer.addDocument(doc(FIELD_NAME, text));