LUCENE-7769: UnifiedHighlighter wasn't seeing inside BoostQuery or SpanBoostQuery

lucene/CHANGES.txt

@@ -131,6 +131,9 @@ Bug Fixes
 * LUCENE-7749: Made LRUQueryCache delegate the scoreSupplier method.
   (Martin Amirault via Adrien Grand)
 
+* LUCENE-7769: The UnifiedHighligter wasn't highlighting portions of the query
+  wrapped in BoostQuery or SpanBoostQuery. (David Smiley, Dmitry Malinin)
+
 Other
 
 * LUCENE-7763: Remove outdated comment in IndexWriterConfig.setIndexSort javadocs.

lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java

@@ -28,12 +28,14 @@ import org.apache.lucene.index.Term;
 import org.apache.lucene.search.AutomatonQuery;
 import org.apache.lucene.search.BooleanClause;
 import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.BoostQuery;
 import org.apache.lucene.search.ConstantScoreQuery;
 import org.apache.lucene.search.DisjunctionMaxQuery;
 import org.apache.lucene.search.FuzzyQuery;
 import org.apache.lucene.search.PrefixQuery;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.search.TermRangeQuery;
+import org.apache.lucene.search.spans.SpanBoostQuery;
 import org.apache.lucene.search.spans.SpanMultiTermQueryWrapper;
 import org.apache.lucene.search.spans.SpanNearQuery;
 import org.apache.lucene.search.spans.SpanNotQuery;
@@ -64,6 +66,8 @@ class MultiTermHighlighting {
                                                         Predicate<String> fieldMatcher,
                                                         boolean lookInSpan,
                                                         Function<Query, Collection<Query>> preRewriteFunc) {
+    // TODO Lucene needs a Query visitor API!  LUCENE-3041
+
     List<CharacterRunAutomaton> list = new ArrayList<>();
     Collection<Query> customSubQueries = preRewriteFunc.apply(query);
     if (customSubQueries != null) {
@@ -79,6 +83,9 @@ class MultiTermHighlighting {
     } else if (query instanceof ConstantScoreQuery) {
       list.addAll(Arrays.asList(extractAutomata(((ConstantScoreQuery) query).getQuery(), fieldMatcher, lookInSpan,
           preRewriteFunc)));
+    } else if (query instanceof BoostQuery) {
+      list.addAll(Arrays.asList(extractAutomata(((BoostQuery)query).getQuery(), fieldMatcher, lookInSpan,
+          preRewriteFunc)));
     } else if (query instanceof DisjunctionMaxQuery) {
       for (Query sub : ((DisjunctionMaxQuery) query).getDisjuncts()) {
         list.addAll(Arrays.asList(extractAutomata(sub, fieldMatcher, lookInSpan, preRewriteFunc)));
@@ -97,6 +104,9 @@ class MultiTermHighlighting {
     } else if (lookInSpan && query instanceof SpanPositionCheckQuery) {
       list.addAll(Arrays.asList(extractAutomata(((SpanPositionCheckQuery) query).getMatch(), fieldMatcher, lookInSpan,
           preRewriteFunc)));
+    } else if (lookInSpan && query instanceof SpanBoostQuery) {
+      list.addAll(Arrays.asList(extractAutomata(((SpanBoostQuery) query).getQuery(), fieldMatcher, lookInSpan,
+          preRewriteFunc)));
     } else if (lookInSpan && query instanceof SpanMultiTermQueryWrapper) {
       list.addAll(Arrays.asList(extractAutomata(((SpanMultiTermQueryWrapper<?>) query).getWrappedQuery(),
           fieldMatcher, lookInSpan, preRewriteFunc)));

lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java

@@ -38,6 +38,7 @@ import org.apache.lucene.index.RandomIndexWriter;
 import org.apache.lucene.index.Term;
 import org.apache.lucene.search.BooleanClause;
 import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.BoostQuery;
 import org.apache.lucene.search.ConstantScoreQuery;
 import org.apache.lucene.search.DisjunctionMaxQuery;
 import org.apache.lucene.search.FuzzyQuery;
@@ -52,6 +53,7 @@ import org.apache.lucene.search.TermQuery;
 import org.apache.lucene.search.TermRangeQuery;
 import org.apache.lucene.search.TopDocs;
 import org.apache.lucene.search.WildcardQuery;
+import org.apache.lucene.search.spans.SpanBoostQuery;
 import org.apache.lucene.search.spans.SpanFirstQuery;
 import org.apache.lucene.search.spans.SpanMultiTermQueryWrapper;
 import org.apache.lucene.search.spans.SpanNearQuery;
@@ -163,7 +165,8 @@ public class TestUnifiedHighlighterMTQ extends LuceneTestCase {
 
     IndexSearcher searcher = newSearcher(ir);
     UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
-    Query query = new PrefixQuery(new Term("body", "te"));
+    // wrap in a BoostQuery to also show we see inside it
+    Query query = new BoostQuery(new PrefixQuery(new Term("body", "te")), 2.0f);
     TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
     assertEquals(2, topDocs.totalHits);
     String snippets[] = highlighter.highlight("body", query, topDocs);
@@ -522,7 +525,9 @@ public class TestUnifiedHighlighterMTQ extends LuceneTestCase {
 
     IndexSearcher searcher = newSearcher(ir);
     UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
-    Query query = new SpanMultiTermQueryWrapper<>(new WildcardQuery(new Term("body", "te*")));
+    // wrap in a SpanBoostQuery to also show we see inside it
+    Query query = new SpanBoostQuery(
+        new SpanMultiTermQueryWrapper<>(new WildcardQuery(new Term("body", "te*"))), 2.0f);
     TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
     assertEquals(2, topDocs.totalHits);
     String snippets[] = highlighter.highlight("body", query, topDocs);