Fix issue with case-insensitive + wildcard + aggregration query\n\nSigned-off-by: Isha Gupta <igupta24@apple.com> (#19489)

Signed-off-by: Isha Gupta <igupta24@apple.com>
Signed-off-by: ishag4 <isha26701@gmail.com>
Co-authored-by: Isha Gupta <igupta24@apple.com>

Author: ishag4

CHANGELOG.md

@@ -33,6 +33,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 ### Fixed
 - Fix Allocation and Rebalance Constraints of WeightFunction are incorrectly reset ([#19012](https://github.com/opensearch-project/OpenSearch/pull/19012))
 - Fix flaky test FieldDataLoadingIT.testIndicesFieldDataCacheSizeSetting ([#19571](https://github.com/opensearch-project/OpenSearch/pull/19571))
+- Fix case-insensitive wildcard + aggregation query crash ([#19489](https://github.com/opensearch-project/OpenSearch/pull/19489))
 - Avoid primary shard failure caused by merged segment warmer exceptions ([#19436](https://github.com/opensearch-project/OpenSearch/pull/19436))
 - Fix pull-based ingestion out-of-bounds offset scenarios and remove persisted offsets ([#19607](https://github.com/opensearch-project/OpenSearch/pull/19607))
 - Fix issue with updating core with a patch number other than 0 ([#19377](https://github.com/opensearch-project/OpenSearch/pull/19377))

server/src/main/java/org/opensearch/common/lucene/search/AutomatonQueries.java

@@ -39,6 +39,7 @@
 import org.apache.lucene.util.automaton.Automata;
 import org.apache.lucene.util.automaton.Automaton;
 import org.apache.lucene.util.automaton.Operations;
+import org.apache.lucene.util.automaton.TooComplexToDeterminizeException;
 
 import java.util.ArrayList;
 import java.util.Arrays;
@@ -92,7 +93,14 @@ public static AutomatonQuery caseInsensitiveTermQuery(Term term) {
      * Build an automaton matching a wildcard pattern, ASCII case insensitive, if the method is null, then will use {@link  MultiTermQuery#CONSTANT_SCORE_BLENDED_REWRITE}.
      */
     public static AutomatonQuery caseInsensitiveWildcardQuery(Term wildcardquery, MultiTermQuery.RewriteMethod method) {
-        return createAutomatonQuery(wildcardquery, toCaseInsensitiveWildcardAutomaton(wildcardquery), method);
+        Automaton automaton = toCaseInsensitiveWildcardAutomaton(wildcardquery);
+        try {
+            automaton = Operations.determinize(automaton, Operations.DEFAULT_DETERMINIZE_WORK_LIMIT);
+        } catch (TooComplexToDeterminizeException e) {
+            throw new RuntimeException("Wildcard query too complex to determinize for term: " + wildcardquery, e);
+        }
+        assert automaton.isDeterministic();
+        return createAutomatonQuery(wildcardquery, automaton, method);
     }
 
     /**

server/src/test/java/org/opensearch/index/mapper/TextFieldTypeTests.java

@@ -48,6 +48,7 @@
 import org.apache.lucene.util.automaton.Automata;
 import org.apache.lucene.util.automaton.Automaton;
 import org.apache.lucene.util.automaton.Operations;
+import org.apache.lucene.util.automaton.TooComplexToDeterminizeException;
 import org.opensearch.OpenSearchException;
 import org.opensearch.common.lucene.BytesRefs;
 import org.opensearch.common.lucene.Lucene;
@@ -61,7 +62,9 @@
 import java.util.Collections;
 import java.util.List;
 
+import static org.hamcrest.Matchers.containsString;
 import static org.hamcrest.Matchers.equalTo;
+import static org.hamcrest.Matchers.instanceOf;
 import static org.apache.lucene.search.MultiTermQuery.CONSTANT_SCORE_BLENDED_REWRITE;
 import static org.apache.lucene.search.MultiTermQuery.CONSTANT_SCORE_REWRITE;
 
@@ -231,6 +234,56 @@ public void testIndexPrefixes() {
         assertThat(q, equalTo(expected));
     }
 
+    public void testCaseInsensitiveWildcardQueryDeterminization() {
+        Term wildcardTerm = new Term("field", "test*");
+        Query result = AutomatonQueries.caseInsensitiveWildcardQuery(wildcardTerm, null);
+
+        assertNotNull(result);
+        assertTrue(((AutomatonQuery) result).getAutomaton().isDeterministic());
+    }
+
+    private String createComplexPattern(int repetitions, String basePattern) {
+        StringBuilder pattern = new StringBuilder();
+        for (int i = 0; i < repetitions; i++) {
+            pattern.append(basePattern);
+        }
+        return pattern.toString();
+    }
+
+    private String createExponentialPattern(int depth) {
+        StringBuilder pattern = new StringBuilder();
+        for (int i = 0; i < depth; i++) {
+            pattern.append("(");
+            for (int j = 0; j < 5; j++) {
+                pattern.append((char) ('a' + (i * 5 + j) % 26)).append("*");
+            }
+            pattern.append(")*");
+        }
+        return pattern.toString();
+    }
+
+    public void testCaseInsensitiveWildcardQueryTooComplexToDeterminize() {
+        String[] complexPatterns = {
+            createComplexPattern(200, "a*b*c*d*e*f*g*h*i*j*"),
+            createComplexPattern(150, "*[a-z]*[A-Z]*[0-9]*"),
+            createExponentialPattern(10) };
+
+        for (String pattern : complexPatterns) {
+            Term complexTerm = new Term("field", pattern);
+
+            try {
+                AutomatonQuery result = AutomatonQueries.caseInsensitiveWildcardQuery(complexTerm, null);
+                assertNotNull(result);
+                assertTrue(result.getAutomaton().isDeterministic());
+            } catch (RuntimeException e) {
+                assertThat(e.getCause(), instanceOf(TooComplexToDeterminizeException.class));
+                assertThat(e.getMessage(), containsString("Wildcard query too complex to determinize for term:"));
+                assertThat(e.getMessage(), containsString(complexTerm.toString()));
+                return;
+            }
+        }
+    }
+
     public void testFetchSourceValue() throws IOException {
         TextFieldType fieldType = createFieldType(true);
         fieldType.setIndexAnalyzer(Lucene.STANDARD_ANALYZER);