Fix the bug of explicit makeNullLiteral for UDT fields (#4475)

songkant-aws · web-flow · commit 7d6357d820ad · 2025-10-10T12:59:20.000+08:00
Signed-off-by: Songkan Tang &lt;songkant@amazon.com&gt;
diff --git a/core/src/main/java/org/opensearch/sql/calcite/ExtendedRexBuilder.java b/core/src/main/java/org/opensearch/sql/calcite/ExtendedRexBuilder.java
@@ -126,6 +126,9 @@ public RexNode makeCast(
         //            ImmutableList.of(exp, makeZeroLiteral(sourceType)));
       }
     } else if (OpenSearchTypeFactory.isUserDefinedType(type)) {
+      if (RexLiteral.isNullLiteral(exp)) {
+        return super.makeCast(pos, type, exp, matchNullability, safe, format);
+      }
       var udt = ((AbstractExprRelDataType<?>) type).getUdt();
       var argExprType = OpenSearchTypeFactory.convertRelDataTypeToExprType(sourceType);
       return switch (udt) {
diff --git a/integ-test/src/test/java/org/opensearch/sql/calcite/remote/CalcitePPLAppendCommandIT.java b/integ-test/src/test/java/org/opensearch/sql/calcite/remote/CalcitePPLAppendCommandIT.java
@@ -7,6 +7,7 @@
 
 import static org.opensearch.sql.legacy.TestsConstants.TEST_INDEX_ACCOUNT;
 import static org.opensearch.sql.legacy.TestsConstants.TEST_INDEX_BANK;
+import static org.opensearch.sql.legacy.TestsConstants.TEST_INDEX_WEBLOGS;
 import static org.opensearch.sql.util.MatcherUtils.rows;
 import static org.opensearch.sql.util.MatcherUtils.schema;
 import static org.opensearch.sql.util.MatcherUtils.verifyDataRows;
@@ -28,6 +29,7 @@ public void init() throws Exception {
     enableCalcite();
     loadIndex(Index.ACCOUNT);
     loadIndex(Index.BANK);
+    loadIndex(Index.WEBLOG);
   }
 
   @Test
@@ -236,4 +238,39 @@ public void testAppendWithConflictTypeColumn() throws IOException {
         rows(null, null, "NM", 412d),
         rows(null, null, "AZ", 414d));
   }
+
+  @Test
+  public void testAppendSchemaMergeWithTimestampUDT() throws IOException {
+    JSONObject actual =
+        executeQuery(
+            String.format(
+                Locale.ROOT,
+                "source=%s | fields account_number, age | append [ source=%s | fields"
+                    + " account_number, age, birthdate ] | where isnotnull(birthdate) and"
+                    + " account_number > 30",
+                TEST_INDEX_ACCOUNT,
+                TEST_INDEX_BANK));
+    verifySchemaInOrder(
+        actual,
+        schema("account_number", "bigint"),
+        schema("age", "bigint"),
+        schema("age0", "int"),
+        schema("birthdate", "string"));
+    verifyDataRows(actual, rows(32, null, 34, "2018-08-11 00:00:00"));
+  }
+
+  @Test
+  public void testAppendSchemaMergeWithIpUDT() throws IOException {
+    JSONObject actual =
+        executeQuery(
+            String.format(
+                Locale.ROOT,
+                "source=%s | fields account_number, age | append [ source=%s | fields host ] |"
+                    + " where cidrmatch(host, '0.0.0.0/24')",
+                TEST_INDEX_ACCOUNT,
+                TEST_INDEX_WEBLOGS));
+    verifySchemaInOrder(
+        actual, schema("account_number", "bigint"), schema("age", "bigint"), schema("host", "ip"));
+    verifyDataRows(actual, rows(null, null, "0.0.0.2"));
+  }
 }
diff --git a/integ-test/src/yamlRestTest/resources/rest-api-spec/test/issues/4383.yml b/integ-test/src/yamlRestTest/resources/rest-api-spec/test/issues/4383.yml
@@ -0,0 +1,62 @@
+setup:
+  - do:
+      query.settings:
+        body:
+          transient:
+            plugins.calcite.enabled : true
+
+---
+teardown:
+  - do:
+      query.settings:
+        body:
+          transient:
+            plugins.calcite.enabled : false
+
+---
+"Append UDT fields should merge schema successfully":
+  - skip:
+      features:
+        - headers
+        - allowed_warnings
+  - do:
+      indices.create:
+        index: log-test1
+        body:
+          mappings:
+            properties:
+              "timestamp":
+                type: date
+  - do:
+      indices.create:
+        index: log-test2
+        body:
+          mappings:
+            properties:
+              "host":
+                type: ip
+
+  - do:
+      bulk:
+        index: log-test1
+        refresh: true
+        body:
+          - '{"index": {}}'
+          - '{ "timestamp" : "2025-09-04T16:15:00.000Z" }'
+  - do:
+      bulk:
+        index: log-test2
+        refresh: true
+        body:
+          - '{"index": {}}'
+          - '{ "host" : "0.0.0.2" }'
+
+  - do:
+      headers:
+        Content-Type: 'application/json'
+      ppl:
+        body:
+          query: source=log-test1 | append [ source=log-test2 ]
+
+  - match: { total: 2 }
+  - match: { datarows: [["2025-09-04 16:15:00", null], [null, "0.0.0.2"]] }
