[lucene] branch branch_9x updated: No need to rewrite queries in unified highlighter (#11807)

[ro...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

romseygeek pushed a commit to branch branch_9x
in repository https://gitbox.apache.org/repos/asf/lucene.git


The following commit(s) were added to refs/heads/branch_9x by this push:
     new b3541204da1 No need to rewrite queries in unified highlighter (#11807)
b3541204da1 is described below

commit b3541204da11e2ee0d7c93f21138cd8481bee89b
Author: Alan Woodward <ro...@apache.org>
AuthorDate: Mon Oct 3 10:15:40 2022 +0100

    No need to rewrite queries in unified highlighter (#11807)
    
    Since QueryVisitor added the ability to signal multi-term queries, the query rewrite
    call in UnifiedHighlighter has been essentially useless, and with more aggressive
    rewriting this is now causing bugs like #11490. We can safely remove this call.
    
    Fixes #11490
---
 lucene/CHANGES.txt                                    |  3 +++
 .../lucene/search/uhighlight/UnifiedHighlighter.java  | 19 +++----------------
 2 files changed, 6 insertions(+), 16 deletions(-)

diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 5dd8547bf58..f1259e33196 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -141,6 +141,9 @@ Bug Fixes
 * GITHUB#12072: Fix exponential runtime for nested BooleanQuery#rewrite when a
   BooleanClause is non-scoring. (Ben Trent)
 
+* GITHUB#11807: Don't rewrite queries in unified highlighter. (Alan Woodward)
+
+
 Optimizations
 ---------------------
 * GITHUB#11738: Optimize MultiTermQueryConstantScoreWrapper when a term is present that matches all
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/UnifiedHighlighter.java b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/UnifiedHighlighter.java
index 8f8e3e3c762..0dee795ebc2 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/UnifiedHighlighter.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/UnifiedHighlighter.java
@@ -44,7 +44,6 @@ import org.apache.lucene.index.IndexOptions;
 import org.apache.lucene.index.IndexReader;
 import org.apache.lucene.index.LeafReader;
 import org.apache.lucene.index.LeafReaderContext;
-import org.apache.lucene.index.MultiReader;
 import org.apache.lucene.index.ReaderUtil;
 import org.apache.lucene.index.StoredFieldVisitor;
 import org.apache.lucene.index.StoredFields;
@@ -100,18 +99,6 @@ public class UnifiedHighlighter {
 
   public static final int DEFAULT_CACHE_CHARS_THRESHOLD = 524288; // ~ 1 MB (2 byte chars)
 
-  static final IndexSearcher EMPTY_INDEXSEARCHER;
-
-  static {
-    try {
-      IndexReader emptyReader = new MultiReader();
-      EMPTY_INDEXSEARCHER = new IndexSearcher(emptyReader);
-      EMPTY_INDEXSEARCHER.setQueryCache(null);
-    } catch (IOException bogus) {
-      throw new RuntimeException(bogus);
-    }
-  }
-
   protected static final LabelledCharArrayMatcher[] ZERO_LEN_AUTOMATA_ARRAY =
       new LabelledCharArrayMatcher[0];
 
@@ -455,10 +442,10 @@ public class UnifiedHighlighter {
     this.cacheFieldValCharsThreshold = builder.cacheFieldValCharsThreshold;
   }
 
-  /** Extracts matching terms after rewriting against an empty index */
-  protected static Set<Term> extractTerms(Query query) throws IOException {
+  /** Extracts matching terms */
+  protected static Set<Term> extractTerms(Query query) {
     Set<Term> queryTerms = new HashSet<>();
-    EMPTY_INDEXSEARCHER.rewrite(query).visit(QueryVisitor.termCollector(queryTerms));
+    query.visit(QueryVisitor.termCollector(queryTerms));
     return queryTerms;
   }