HIVE-29466: Ambiguous table alias exception when using CTE suggester (#6323)

Author: zabetak

ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/translator/PlanModifierForASTConv.java

@@ -44,6 +44,7 @@
 import org.apache.calcite.rel.core.SetOp;
 import org.apache.calcite.rel.core.Sort;
 import org.apache.calcite.rel.core.Spool;
+import org.apache.calcite.rel.core.TableSpool;
 import org.apache.calcite.rel.core.Window.RexWinAggCall;
 import org.apache.calcite.rel.rules.MultiJoin;
 import org.apache.calcite.rel.type.RelDataType;
@@ -267,6 +268,10 @@ public RelNode visit(final RelNode rel) {
         aliases.add(((HiveTableScan) dq.getTableScan()).getTableAlias().toLowerCase());
         return dq;
       }
+      if (rel instanceof TableSpool spool) {
+        aliases.add(spool.getTable().getQualifiedName().getLast().toLowerCase());
+        return spool;
+      }
       return super.visit(rel);
     }
   }

ql/src/test/queries/clientpositive/cbo_self_join_ambiguous_alias_spool.q

@@ -0,0 +1,10 @@
+create table t1 (key int, value int);
+
+set hive.optimize.cte.materialize.threshold=1;
+set hive.optimize.cte.suggester.class=org.apache.hadoop.hive.ql.optimizer.calcite.CommonTableExpressionIdentitySuggester;
+set hive.optimize.cte.materialize.full.aggregate.only=false;
+
+explain cbo
+select *
+from (select key from t1 where value = 10) a
+join (select key from t1 where value = 10) b;

ql/src/test/results/clientpositive/llap/cbo_self_join_ambiguous_alias_spool.q.out

@@ -0,0 +1,35 @@
+PREHOOK: query: create table t1 (key int, value int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@t1
+POSTHOOK: query: create table t1 (key int, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@t1
+Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, cte_suggestion_0]] in Stage 'Reducer 3' is a cross product
+PREHOOK: query: explain cbo
+select *
+from (select key from t1 where value = 10) a
+join (select key from t1 where value = 10) b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@cte_suggestion_0
+PREHOOK: Input: default@t1
+#### A masked pattern was here ####
+POSTHOOK: query: explain cbo
+select *
+from (select key from t1 where value = 10) a
+join (select key from t1 where value = 10) b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@cte_suggestion_0
+POSTHOOK: Input: default@t1
+#### A masked pattern was here ####
+CBO PLAN:
+HiveProject(a.key=[$0], b.key=[$1])
+  HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available])
+    HiveProject(key=[$0])
+      HiveTableSpool(table=[[cte, cte_suggestion_0]])
+        HiveProject(key=[$0])
+          HiveFilter(condition=[=($1, 10)])
+            HiveTableScan(table=[[default, t1]], table:alias=[t1])
+    HiveTableScan(table=[[cte, cte_suggestion_0]], table:alias=[cte_suggestion_0])
+