LUCENE-6385: add null check to WeightedSpanTermExtractor

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1671064 13f79535-47bb-0310-9956-ffa450edef68

lucene/CHANGES.txt

@@ -40,10 +40,10 @@ API Changes
 
 New Features
 
-* LUCENE-6308: Span queries now share document conjunction/intersection
+* LUCENE-6308, LUCENE-6385: Span queries now share document conjunction/intersection
   code with boolean queries, and use two-phased iterators for
   faster intersection by avoiding loading positions in certain cases.
-  (Paul Elschot, Robert Muir via Mike McCandless)
+  (Paul Elschot, Terry Smith, Robert Muir via Mike McCandless)
 
 * LUCENE-6352: Added a new query time join to the join module that uses
   global ordinals, which is faster for subsequent joins between reopens.

lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java

@@ -306,6 +306,9 @@ public class WeightedSpanTermExtractor {
       }
       Bits acceptDocs = context.reader().getLiveDocs();
       final Spans spans = q.getSpans(context, acceptDocs, termContexts);
+      if (spans == null) {
+        return;
+      }
 
       // collect span positions
       while (spans.nextDoc() != Spans.NO_MORE_DOCS) {

lucene/highlighter/src/test/org/apache/lucene/search/highlight/MissesTest.java

@@ -0,0 +1,82 @@
+package org.apache.lucene.search.highlight;
+
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.search.BooleanClause.Occur;
+import org.apache.lucene.search.BooleanQuery;
+import org.apache.lucene.search.PhraseQuery;
+import org.apache.lucene.search.Query;
+import org.apache.lucene.search.TermQuery;
+import org.apache.lucene.search.spans.SpanNearQuery;
+import org.apache.lucene.search.spans.SpanQuery;
+import org.apache.lucene.search.spans.SpanTermQuery;
+import org.apache.lucene.util.LuceneTestCase;
+
+public class MissesTest extends LuceneTestCase {
+  public void testTermQuery() throws IOException, InvalidTokenOffsetsException {
+    try (Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false)) {
+      final Query query = new TermQuery(new Term("test", "foo"));
+      final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(query));
+      assertEquals("this is a <B>foo</B> bar example",
+          highlighter.getBestFragment(analyzer, "test", "this is a foo bar example"));
+      assertNull(highlighter.getBestFragment(analyzer, "test", "this does not match"));
+    }
+  }
+
+  public void testBooleanQuery() throws IOException, InvalidTokenOffsetsException {
+    try (Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false)) {
+      final BooleanQuery query = new BooleanQuery();
+      query.add(new TermQuery(new Term("test", "foo")), Occur.MUST);
+      query.add(new TermQuery(new Term("test", "bar")), Occur.MUST);
+      final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(query));
+      assertEquals("this is a <B>foo</B> <B>bar</B> example",
+          highlighter.getBestFragment(analyzer, "test", "this is a foo bar example"));
+      assertNull(highlighter.getBestFragment(analyzer, "test", "this does not match"));
+    }
+  }
+
+  public void testPhraseQuery() throws IOException, InvalidTokenOffsetsException {
+    try (Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false)) {
+      final PhraseQuery query = new PhraseQuery();
+      query.add(new Term("test", "foo"));
+      query.add(new Term("test", "bar"));
+      final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(query));
+      assertEquals("this is a <B>foo</B> <B>bar</B> example",
+          highlighter.getBestFragment(analyzer, "test", "this is a foo bar example"));
+      assertNull(highlighter.getBestFragment(analyzer, "test", "this does not match"));
+    }
+  }
+
+  public void testSpanNearQuery() throws IOException, InvalidTokenOffsetsException {
+    try (Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false)) {
+      final Query query = new SpanNearQuery(new SpanQuery[] {
+          new SpanTermQuery(new Term("test", "foo")),
+          new SpanTermQuery(new Term("test", "bar"))}, 0, true);
+      final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(query));
+      assertEquals("this is a <B>foo</B> <B>bar</B> example",
+          highlighter.getBestFragment(analyzer, "test", "this is a foo bar example"));
+      assertNull(highlighter.getBestFragment(analyzer, "test", "this does not match"));
+    }
+  }
+}