Add BytesRefIterator to TermInSetQuery (#13806)

TermInSetQuery used to have an accessor to its terms that was removed in #12173
to protect leaking internal encoding details. This introduces an accessor to the
term data in the query that doesn't expose internals but merely allows iterating
over the decoded BytesRef, making inspection of the querys content possible again.

Closes #13804

lucene/CHANGES.txt

@@ -8,6 +8,8 @@ http://s.apache.org/luceneversions
 API Changes
 ---------------------
 
+* GITHUB#13806: Add TermInSetQuery#getBytesRefIterator to be able to iterate over query terms. (Christoph Büscher)
+
 * GITHUB#13469: Expose FlatVectorsFormat as a first-class format; can be configured using a custom Codec. (Michael Sokolov)
 
 * GITHUB#13612: Hunspell: add Suggester#proceedPastRep to avoid losing relevant suggestions. (Peter Gromov)

lucene/core/src/java/org/apache/lucene/search/TermInSetQuery.java

@@ -28,13 +28,7 @@
 import org.apache.lucene.index.Term;
 import org.apache.lucene.index.Terms;
 import org.apache.lucene.index.TermsEnum;
-import org.apache.lucene.util.Accountable;
-import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.BytesRef;
-import org.apache.lucene.util.BytesRefBuilder;
-import org.apache.lucene.util.BytesRefComparator;
-import org.apache.lucene.util.RamUsageEstimator;
-import org.apache.lucene.util.StringSorter;
+import org.apache.lucene.util.*;
 import org.apache.lucene.util.automaton.Automata;
 import org.apache.lucene.util.automaton.Automaton;
 import org.apache.lucene.util.automaton.ByteRunAutomaton;
@@ -161,6 +155,16 @@ public long getTermsCount() throws IOException {
     return termData.size();
   }
 
+  /**
+   * Get an iterator over the encoded terms for query inspection.
+   *
+   * @lucene.experimental
+   */
+  public BytesRefIterator getBytesRefIterator() {
+    final TermIterator iterator = this.termData.iterator();
+    return () -> iterator.next();
+  }
+
   @Override
   public void visit(QueryVisitor visitor) {
     if (visitor.acceptField(field) == false) {
@@ -207,7 +211,8 @@ public int hashCode() {
    * Returns the terms wrapped in a PrefixCodedTerms.
    *
    * @deprecated the encoded terms will no longer be exposed in a future major version; this is an
-   *     implementation detail that could change at some point and shouldn't be relied on directly
+   *     implementation detail that could change at some point and shouldn't be relied on directly.
+   *     Call {@link #getBytesRefIterator()} instead to retrieve over the terms.
    */
   @Deprecated
   public PrefixCodedTerms getTermData() {

lucene/core/src/test/org/apache/lucene/search/TestTermInSetQuery.java

@@ -51,6 +51,7 @@
 import org.apache.lucene.tests.util.RamUsageTester;
 import org.apache.lucene.tests.util.TestUtil;
 import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.BytesRefIterator;
 import org.apache.lucene.util.IOUtils;
 import org.apache.lucene.util.automaton.ByteRunAutomaton;
 
@@ -474,4 +475,19 @@ public void consumeTermsMatching(
           }
         });
   }
+
+  public void testTermsIterator() throws IOException {
+    TermInSetQuery empty = new TermInSetQuery("field", Collections.emptyList());
+    BytesRefIterator it = empty.getBytesRefIterator();
+    assertNull(it.next());
+
+    TermInSetQuery query =
+        new TermInSetQuery(
+            "field", List.of(newBytesRef("term1"), newBytesRef("term2"), newBytesRef("term3")));
+    it = query.getBytesRefIterator();
+    assertEquals(newBytesRef("term1"), it.next());
+    assertEquals(newBytesRef("term2"), it.next());
+    assertEquals(newBytesRef("term3"), it.next());
+    assertNull(it.next());
+  }
 }