[BugFix] Fix eval overwrites MAP root field when assigning multiple dotted-path names (#5185)

Signed-off-by: Songkan Tang <songkant@amazon.com>

Author: songkant-aws

core/src/main/java/org/opensearch/sql/calcite/CalciteRelNodeVisitor.java

@@ -1295,7 +1295,7 @@ private void projectPlusOverriding(
     List<String> originalFieldNames = context.relBuilder.peek().getRowType().getFieldNames();
     List<RexNode> toOverrideList =
         originalFieldNames.stream()
-            .filter(originalName -> shouldOverrideField(originalName, newNames))
+            .filter(originalName -> shouldOverrideField(originalName, newNames, originalFieldNames))
             .map(a -> (RexNode) context.relBuilder.field(a))
             .toList();
     // 1. add the new fields, For example "age0, country0"
@@ -1315,15 +1315,31 @@ private void projectPlusOverriding(
     context.relBuilder.rename(expectedRenameFields);
   }
 
-  private boolean shouldOverrideField(String originalName, List<String> newNames) {
+  private boolean shouldOverrideField(
+      String originalName, List<String> newNames, List<String> allFieldNames) {
     return newNames.stream()
         .anyMatch(
             newName ->
                 // Match exact field names (e.g., "age" == "age") for flat fields
                 newName.equals(originalName)
                     // OR match nested paths (e.g., "resource.attributes..." starts with
-                    // "resource.")
-                    || newName.startsWith(originalName + "."));
+                    // "resource."), but only when the schema already contains sub-fields of
+                    // originalName. This distinguishes real struct parents (which have flattened
+                    // sub-field columns) from MAP columns produced by spath where dotted names
+                    // are just flat column names, not nested sub-fields.
+                    || (newName.startsWith(originalName + ".")
+                        && hasSubFields(originalName, allFieldNames)));
+  }
+
+  /**
+   * Checks whether the schema contains any field whose name starts with {@code parentName + "."}.
+   * This indicates that {@code parentName} is a real struct parent with flattened sub-field
+   * columns, as opposed to a standalone MAP column (e.g., from spath) that has no sub-fields in the
+   * schema.
+   */
+  private boolean hasSubFields(String parentName, List<String> allFieldNames) {
+    String prefix = parentName + ".";
+    return allFieldNames.stream().anyMatch(name -> name.startsWith(prefix));
   }
 
   private List<List<RexInputRef>> extractInputRefList(List<RelBuilder.AggCall> aggCalls) {

integ-test/src/test/java/org/opensearch/sql/calcite/remote/CalcitePPLSpathCommandIT.java

@@ -216,4 +216,27 @@ public void testSpathAutoExtractWithSort() throws IOException {
     verifySchema(result, schema("doc.user.name", "string"));
     verifyDataRowsInOrder(result, rows("Alice"), rows("John"));
   }
+
+  @Test
+  public void testSpathAutoExtractWithMultiFieldEval() throws IOException {
+    JSONObject result =
+        executeQuery(
+            "source=test_spath_cmd | spath input=doc"
+                + " | eval doc.user.name=doc.user.name, doc.user.age=doc.user.age"
+                + " | fields doc.user.name, doc.user.age");
+    verifySchema(result, schema("doc.user.name", "string"), schema("doc.user.age", "string"));
+    verifyDataRows(result, rows("Alice", "25"), rows("John", "30"));
+  }
+
+  @Test
+  public void testSpathAutoExtractWithSeparateEvalCommands() throws IOException {
+    JSONObject result =
+        executeQuery(
+            "source=test_spath_cmd | spath input=doc"
+                + " | eval doc.user.name=doc.user.name"
+                + " | eval doc.user.age=doc.user.age"
+                + " | fields doc.user.name, doc.user.age");
+    verifySchema(result, schema("doc.user.name", "string"), schema("doc.user.age", "string"));
+    verifyDataRows(result, rows("Alice", "25"), rows("John", "30"));
+  }
 }

integ-test/src/yamlRestTest/resources/rest-api-spec/test/issues/5185.yml

@@ -0,0 +1,69 @@
+setup:
+  - do:
+      query.settings:
+        body:
+          transient:
+            plugins.calcite.enabled: true
+  - do:
+      indices.create:
+        index: issue5185
+        body:
+          settings:
+            number_of_shards: 1
+            number_of_replicas: 0
+          mappings:
+            properties:
+              doc:
+                type: text
+  - do:
+      bulk:
+        refresh: true
+        body:
+          - '{"index": {"_index": "issue5185", "_id": "1"}}'
+          - '{"doc": "{\"user\":{\"name\":\"John\",\"age\":30}}"}'
+          - '{"index": {"_index": "issue5185", "_id": "2"}}'
+          - '{"doc": "{\"user\":{\"name\":\"Alice\",\"age\":25}}"}'
+
+---
+teardown:
+  - do:
+      indices.delete:
+        index: issue5185
+        ignore_unavailable: true
+  - do:
+      query.settings:
+        body:
+          transient:
+            plugins.calcite.enabled: false
+
+---
+"Issue 5185: eval with multiple dotted-path assignments from MAP column":
+  - skip:
+      features:
+        - headers
+        - allowed_warnings
+  - do:
+      headers:
+        Content-Type: 'application/json'
+      ppl:
+        body:
+          query: "source=issue5185 | spath input=doc | eval doc.user.name=doc.user.name, doc.user.age=doc.user.age | fields doc.user.name, doc.user.age"
+
+  - match: { total: 2 }
+  - length: { datarows: 2 }
+
+---
+"Issue 5185: separate eval commands with dotted-path from MAP column":
+  - skip:
+      features:
+        - headers
+        - allowed_warnings
+  - do:
+      headers:
+        Content-Type: 'application/json'
+      ppl:
+        body:
+          query: "source=issue5185 | spath input=doc | eval doc.user.name=doc.user.name | eval doc.user.age=doc.user.age | fields doc.user.name, doc.user.age"
+
+  - match: { total: 2 }
+  - length: { datarows: 2 }

ppl/src/test/java/org/opensearch/sql/ppl/calcite/CalcitePPLSpathTest.java

@@ -123,6 +123,34 @@ public void testSpathAutoExtractModeWithFields() {
                 + "FROM `scott`.`EMP`");
   }
 
+  @Test
+  public void testSpathAutoExtractWithMultiFieldEval() {
+    // Issue #5185: eval with multiple dotted-path assignments from MAP column
+    // should not remove the MAP root field
+    withPPLQuery(
+            "source=EMP | spath input=ENAME"
+                + " | eval ENAME.user.name=ENAME.user.name, ENAME.user.age=ENAME.user.age"
+                + " | fields ENAME.user.name, ENAME.user.age")
+        .expectLogical(
+            "LogicalProject(ENAME.user.name=[ITEM(JSON_EXTRACT_ALL($1), 'user.name')],"
+                + " ENAME.user.age=[ITEM(JSON_EXTRACT_ALL($1), 'user.age')])\n"
+                + "  LogicalTableScan(table=[[scott, EMP]])\n");
+  }
+
+  @Test
+  public void testSpathAutoExtractWithSeparateEvalCommands() {
+    // Issue #5185: separate eval commands with dotted-path assignments from MAP column
+    withPPLQuery(
+            "source=EMP | spath input=ENAME"
+                + " | eval ENAME.user.name=ENAME.user.name"
+                + " | eval ENAME.user.age=ENAME.user.age"
+                + " | fields ENAME.user.name, ENAME.user.age")
+        .expectLogical(
+            "LogicalProject(ENAME.user.name=[ITEM(JSON_EXTRACT_ALL($1), 'user.name')],"
+                + " ENAME.user.age=[ITEM(JSON_EXTRACT_ALL($1), 'user.age')])\n"
+                + "  LogicalTableScan(table=[[scott, EMP]])\n");
+  }
+
   @Test
   public void testSpathAutoExtractModeWithSort() {
     withPPLQuery("source=EMP | spath input=ENAME output=result" + " | sort result.user.name")