[SPARK-51303] [SQL] [TESTS] Extend ORDER BY testing coverage

sql/core/src/test/resources/sql-tests/analyzer-results/order-by-all.sql.out

@@ -248,3 +248,14 @@ org.apache.spark.sql.catalyst.ExtendedAnalysisException
     "fragment" : "all"
   } ]
 }
+
+
+-- !query
+SELECT all, (SELECT col2 FROM VALUES (2, 2) ORDER BY ALL) FROM VALUES (1) AS t1 (all)
+-- !query analysis
+Project [all#x, scalar-subquery#x [] AS scalarsubquery()#x]
+:  +- Sort [col2#x ASC NULLS FIRST], true
+:     +- Project [col2#x]
+:        +- LocalRelation [col1#x, col2#x]
++- SubqueryAlias t1
+   +- LocalRelation [all#x]

sql/core/src/test/resources/sql-tests/analyzer-results/order-by.sql.out

@@ -0,0 +1,190 @@
+-- Automatically generated by SQLQueryTestSuite
+-- !query
+CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
+(1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2), (null, 1), (3, null), (null, null)
+AS testData(a, b)
+-- !query analysis
+CreateViewCommand `testData`, SELECT * FROM VALUES
+(1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2), (null, 1), (3, null), (null, null)
+AS testData(a, b), false, true, LocalTempView, UNSUPPORTED, true
+   +- Project [a#x, b#x]
+      +- SubqueryAlias testData
+         +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT a FROM testData ORDER BY a
+-- !query analysis
+Sort [a#x ASC NULLS FIRST], true
++- Project [a#x]
+   +- SubqueryAlias testdata
+      +- View (`testData`, [a#x, b#x])
+         +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+            +- Project [a#x, b#x]
+               +- SubqueryAlias testData
+                  +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT a FROM testData GROUP BY a, b ORDER BY a
+-- !query analysis
+Sort [a#x ASC NULLS FIRST], true
++- Aggregate [a#x, b#x], [a#x]
+   +- SubqueryAlias testdata
+      +- View (`testData`, [a#x, b#x])
+         +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+            +- Project [a#x, b#x]
+               +- SubqueryAlias testData
+                  +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT b FROM testData WHERE a > 1 ORDER BY a
+-- !query analysis
+Project [b#x]
++- Sort [a#x ASC NULLS FIRST], true
+   +- Project [b#x, a#x]
+      +- Filter (a#x > 1)
+         +- SubqueryAlias testdata
+            +- View (`testData`, [a#x, b#x])
+               +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+                  +- Project [a#x, b#x]
+                     +- SubqueryAlias testData
+                        +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT b FROM testData GROUP BY a, b ORDER BY a
+-- !query analysis
+Project [b#x]
++- Sort [a#x ASC NULLS FIRST], true
+   +- Aggregate [a#x, b#x], [b#x, a#x]
+      +- SubqueryAlias testdata
+         +- View (`testData`, [a#x, b#x])
+            +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+               +- Project [a#x, b#x]
+                  +- SubqueryAlias testData
+                     +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT col1 FROM VALUES (1, named_struct('f1', 1)) ORDER BY col2.f1
+-- !query analysis
+Project [col1#x]
++- Sort [col2#x.f1 ASC NULLS FIRST], true
+   +- Project [col1#x, col2#x]
+      +- LocalRelation [col1#x, col2#x]
+
+
+-- !query
+SELECT col1 FROM VALUES (1, named_struct('f1', named_struct('f2', 1))) ORDER BY col2.f1.f2
+-- !query analysis
+Project [col1#x]
++- Sort [col2#x.f1.f2 ASC NULLS FIRST], true
+   +- Project [col1#x, col2#x]
+      +- LocalRelation [col1#x, col2#x]
+
+
+-- !query
+SELECT a, (SELECT b FROM testData GROUP BY b HAVING b > 1 ORDER BY a) FROM testData
+-- !query analysis
+org.apache.spark.sql.catalyst.ExtendedAnalysisException
+{
+  "errorClass" : "UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY.CORRELATED_REFERENCE",
+  "sqlState" : "0A000",
+  "messageParameters" : {
+    "sqlExprs" : "\"a ASC NULLS FIRST\""
+  },
+  "queryContext" : [ {
+    "objectType" : "",
+    "objectName" : "",
+    "startIndex" : 59,
+    "stopIndex" : 68,
+    "fragment" : "ORDER BY a"
+  } ]
+}
+
+
+-- !query
+SELECT a, (SELECT b FROM VALUES (1, 2) AS innerTestData (all, b) ORDER BY ALL) FROM testData
+-- !query analysis
+Project [a#x, scalar-subquery#x [] AS scalarsubquery()#x]
+:  +- Project [b#x]
+:     +- Sort [ALL#x ASC NULLS FIRST], true
+:        +- Project [b#x, ALL#x]
+:           +- SubqueryAlias innerTestData
+:              +- LocalRelation [all#x, b#x]
++- SubqueryAlias testdata
+   +- View (`testData`, [a#x, b#x])
+      +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+         +- Project [a#x, b#x]
+            +- SubqueryAlias testData
+               +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT * FROM testData ORDER BY (SELECT a FROM testData ORDER BY b)
+-- !query analysis
+Sort [scalar-subquery#x [] ASC NULLS FIRST], true
+:  +- Project [a#x]
+:     +- Sort [b#x ASC NULLS FIRST], true
+:        +- Project [a#x, b#x]
+:           +- SubqueryAlias testdata
+:              +- View (`testData`, [a#x, b#x])
+:                 +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+:                    +- Project [a#x, b#x]
+:                       +- SubqueryAlias testData
+:                          +- LocalRelation [a#x, b#x]
++- Project [a#x, b#x]
+   +- SubqueryAlias testdata
+      +- View (`testData`, [a#x, b#x])
+         +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]
+            +- Project [a#x, b#x]
+               +- SubqueryAlias testData
+                  +- LocalRelation [a#x, b#x]
+
+
+-- !query
+SELECT * FROM testData ORDER BY (SELECT * FROM testData ORDER BY (SELECT a FROM testData ORDER BY b))
+-- !query analysis
+org.apache.spark.sql.catalyst.ExtendedAnalysisException
+{
+  "errorClass" : "INVALID_SUBQUERY_EXPRESSION.SCALAR_SUBQUERY_RETURN_MORE_THAN_ONE_OUTPUT_COLUMN",
+  "sqlState" : "42823",
+  "messageParameters" : {
+    "number" : "2"
+  },
+  "queryContext" : [ {
+    "objectType" : "",
+    "objectName" : "",
+    "startIndex" : 33,
+    "stopIndex" : 101,
+    "fragment" : "(SELECT * FROM testData ORDER BY (SELECT a FROM testData ORDER BY b))"
+  } ]
+}
+
+
+-- !query
+SELECT * FROM testData ORDER BY (SELECT a FROM VALUES (1))
+-- !query analysis
+org.apache.spark.sql.catalyst.ExtendedAnalysisException
+{
+  "errorClass" : "UNSUPPORTED_SUBQUERY_EXPRESSION_CATEGORY.UNSUPPORTED_CORRELATED_SCALAR_SUBQUERY",
+  "sqlState" : "0A000",
+  "messageParameters" : {
+    "treeNode" : "Sort [scalar-subquery#x [a#x] ASC NULLS FIRST], true\n:  +- Project [outer(a#x)]\n:     +- LocalRelation [col1#x]\n+- Project [a#x, b#x]\n   +- SubqueryAlias testdata\n      +- View (`testData`, [a#x, b#x])\n         +- Project [cast(a#x as int) AS a#x, cast(b#x as int) AS b#x]\n            +- Project [a#x, b#x]\n               +- SubqueryAlias testData\n                  +- LocalRelation [a#x, b#x]\n"
+  },
+  "queryContext" : [ {
+    "objectType" : "",
+    "objectName" : "",
+    "startIndex" : 24,
+    "stopIndex" : 58,
+    "fragment" : "ORDER BY (SELECT a FROM VALUES (1))"
+  } ]
+}
+
+
+-- !query
+DROP VIEW IF EXISTS testData
+-- !query analysis
+DropTempViewCommand testData

sql/core/src/test/resources/sql-tests/inputs/order-by-all.sql

@@ -42,3 +42,6 @@ select * from values("z", 1), ("y", 2), ("x", 3) AS T(col1, all) order by all;
 -- shouldn't work in window functions
 select name, dept, rank() over (partition by dept order by all) as rank
 from values('Lisa', 'Sales', 10000, 35) as T(name, dept, salary, age);
+
+-- ORDER BY column can't reference an outer scope
+SELECT all, (SELECT col2 FROM VALUES (2, 2) ORDER BY ALL) FROM VALUES (1) AS t1 (all)

sql/core/src/test/resources/sql-tests/inputs/order-by.sql

@@ -0,0 +1,34 @@
+-- Test data.
+CREATE OR REPLACE TEMPORARY VIEW testData AS SELECT * FROM VALUES
+(1, 1), (1, 2), (2, 1), (2, 2), (3, 1), (3, 2), (null, 1), (3, null), (null, null)
+AS testData(a, b);
+
+-- ORDER BY a column from a child's output
+SELECT a FROM testData ORDER BY a;
+SELECT a FROM testData GROUP BY a, b ORDER BY a;
+
+-- ORDER BY a column from an output below a child's one
+SELECT b FROM testData WHERE a > 1 ORDER BY a;
+
+-- ORDER BY a column from grouping expressions list
+SELECT b FROM testData GROUP BY a, b ORDER BY a;
+
+-- ORDER BY a nested column from an output below a child's one
+SELECT col1 FROM VALUES (1, named_struct('f1', 1)) ORDER BY col2.f1;
+SELECT col1 FROM VALUES (1, named_struct('f1', named_struct('f2', 1))) ORDER BY col2.f1.f2;
+
+-- ORDER BY column can't reference an outer scope
+SELECT a, (SELECT b FROM testData GROUP BY b HAVING b > 1 ORDER BY a) FROM testData;
+
+-- Column resolution from the child's output takes the precedence over `ORDER BY ALL`
+SELECT a, (SELECT b FROM VALUES (1, 2) AS innerTestData (all, b) ORDER BY ALL) FROM testData;
+
+-- ORDER BY with scalar subqueries
+SELECT * FROM testData ORDER BY (SELECT a FROM testData ORDER BY b);
+SELECT * FROM testData ORDER BY (SELECT * FROM testData ORDER BY (SELECT a FROM testData ORDER BY b));
+
+-- Fails because correlation is not allowed in ORDER BY
+SELECT * FROM testData ORDER BY (SELECT a FROM VALUES (1));
+
+-- Clean up
+DROP VIEW IF EXISTS testData;

sql/core/src/test/resources/sql-tests/results/order-by-all.sql.out

@@ -200,3 +200,11 @@ org.apache.spark.sql.catalyst.ExtendedAnalysisException
     "fragment" : "all"
   } ]
 }
+
+
+-- !query
+SELECT all, (SELECT col2 FROM VALUES (2, 2) ORDER BY ALL) FROM VALUES (1) AS t1 (all)
+-- !query schema
+struct<all:int,scalarsubquery():int>
+-- !query output
+1	2