Merge branch 'main' into fix/binary-map-initial-map-size

Author: yashrb24

datafusion/expr/src/logical_plan/builder.rs

@@ -1931,10 +1931,12 @@ fn project_with_validation(
     expr: impl IntoIterator<Item = (impl Into<SelectExpr>, bool)>,
 ) -> Result<LogicalPlan> {
     let mut projected_expr = vec![];
+    let mut has_wildcard = false;
     for (e, validate) in expr {
         let e = e.into();
         match e {
             SelectExpr::Wildcard(opt) => {
+                has_wildcard = true;
                 let expanded = expand_wildcard(plan.schema(), &plan, Some(&opt))?;
 
                 // If there is a REPLACE statement, replace that column with the given
@@ -1955,6 +1957,7 @@ fn project_with_validation(
                 }
             }
             SelectExpr::QualifiedWildcard(table_ref, opt) => {
+                has_wildcard = true;
                 let expanded =
                     expand_qualified_wildcard(&table_ref, plan.schema(), Some(&opt))?;
 
@@ -1984,6 +1987,12 @@ fn project_with_validation(
             }
         }
     }
+    if has_wildcard && projected_expr.is_empty() && !plan.schema().fields().is_empty() {
+        return plan_err!(
+            "SELECT list is empty after resolving * expressions, \
+             the wildcard expanded to zero columns"
+        );
+    }
     validate_unique_names("Projections", projected_expr.iter())?;
 
     Projection::try_new(projected_expr, Arc::new(plan)).map(LogicalPlan::Projection)

datafusion/functions/src/core/named_struct.rs

@@ -27,7 +27,9 @@ use std::sync::Arc;
 
 #[user_doc(
     doc_section(label = "Struct Functions"),
-    description = "Returns an Arrow struct using the specified name and input expressions pairs.",
+    description = "Returns an Arrow struct using the specified name and input expressions pairs.
+For information on comparing and ordering struct values (including `NULL` handling),
+see [Comparison and Ordering](struct_coercion.md#comparison-and-ordering).",
     syntax_example = "named_struct(expression1_name, expression1_input[, ..., expression_n_name, expression_n_input])",
     sql_example = r#"
 For example, this query converts two columns `a` and `b` to a single column with

datafusion/functions/src/core/struct.rs

@@ -27,7 +27,9 @@ use std::sync::Arc;
     doc_section(label = "Struct Functions"),
     description = "Returns an Arrow struct using the specified input expressions optionally named.
 Fields in the returned struct use the optional name or the `cN` naming convention.
-For example: `c0`, `c1`, `c2`, etc.",
+For example: `c0`, `c1`, `c2`, etc.
+For information on comparing and ordering struct values (including `NULL` handling),
+see [Comparison and Ordering](struct_coercion.md#comparison-and-ordering).",
     syntax_example = "struct(expression1[, ..., expression_n])",
     sql_example = r#"For example, this query converts two columns `a` and `b` to a single column with
 a struct type of fields `field_a` and `c1`:

datafusion/sqllogictest/test_files/select.slt

@@ -1318,25 +1318,25 @@ statement error
 SELECT * EXCLUDE(a, a)
 FROM table1
 
-# if EXCEPT all the columns, query should still succeed but return empty
-statement ok
+# if EXCEPT all the columns, query should return an error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT(a, b, c, d)
 FROM table1
 
-# try zero column with LIMIT, 1 row but empty
-statement ok
+# try zero column with LIMIT, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT (a, b, c, d)
 FROM table1
 LIMIT 1
 
-# try zero column with GROUP BY, 2 row but empty
-statement ok
+# try zero column with GROUP BY, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT (a, b, c, d)
 FROM table1
 GROUP BY a
 
-# try zero column with WHERE, 1 row but empty
-statement ok
+# try zero column with WHERE, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT (a, b, c, d)
 FROM table1
 WHERE a = 1
@@ -1352,15 +1352,15 @@ CREATE TABLE table2 (
   (1, 10, 100, 1000),
   (2, 20, 200, 2000);
 
-# try zero column with inner JOIN, 2 row but empty
-statement ok
+# try zero column with inner JOIN, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 WITH t1 AS (SELECT a AS t1_a FROM table1), t2 AS (SELECT a AS t2_a FROM table2)
 SELECT * EXCEPT (t1_a, t2_a)
 FROM t1
 JOIN t2 ON (t1_a = t2_a)
 
-# try zero column with more JOIN, 2 row but empty
-statement ok
+# try zero column with more JOIN, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT (b1, b2)
 FROM (
   SELECT b AS b1 FROM table1
@@ -1369,8 +1369,8 @@ JOIN (
   SELECT b AS b2 FROM table2
 ) ON b1 = b2
 
-# try zero column with Window, 2 row but empty
-statement ok
+# try zero column with Window, should error
+statement error DataFusion error: Error during planning: SELECT list is empty after resolving \* expressions, the wildcard expanded to zero columns
 SELECT * EXCEPT (a, b, row_num)
 FROM (
     SELECT

docs/source/user-guide/sql/scalar_functions.md

@@ -4709,6 +4709,8 @@ _Alias of [string_to_array](#string_to_array)._
 ### `named_struct`
 
 Returns an Arrow struct using the specified name and input expressions pairs.
+For information on comparing and ordering struct values (including `NULL` handling),
+see [Comparison and Ordering](struct_coercion.md#comparison-and-ordering).
 
 ```sql
 named_struct(expression1_name, expression1_input[, ..., expression_n_name, expression_n_input])
@@ -4750,6 +4752,8 @@ _Alias of [struct](#struct)._
 Returns an Arrow struct using the specified input expressions optionally named.
 Fields in the returned struct use the optional name or the `cN` naming convention.
 For example: `c0`, `c1`, `c2`, etc.
+For information on comparing and ordering struct values (including `NULL` handling),
+see [Comparison and Ordering](struct_coercion.md#comparison-and-ordering).
 
 ```sql
 struct(expression1[, ..., expression_n])

docs/source/user-guide/sql/struct_coercion.md

@@ -208,6 +208,26 @@ SELECT [
 ] FROM t_left JOIN t_right;
 ```
 
+## Comparison and Ordering
+
+DataFusion supports comparing `STRUCT` values with standard comparison operators
+(`=`, `!=`, `<`, `<=`, `>`, `>=`). Ordering comparisons are lexicographical and
+follow DataFusion's default ascending comparison behavior, where `NULL` sorts
+before non-`NULL` values.
+
+### Examples
+
+```sql
+SELECT {x: 1, y: 2} < {x: 1, y: 3};
+-- true
+
+SELECT {x: 1, y: NULL} < {x: 1, y: 2};
+-- true
+
+SELECT {x: 1, y: NULL} = {x: 1, y: NULL};
+--true
+```
+
 ## Migration Guide: From Positional to Name-Based Matching
 
 If you have existing code that relied on **positional** struct field matching, you may need to update it.

docs/source/user-guide/sql/subqueries.md

@@ -102,6 +102,18 @@ SELECT * FROM x WHERE column_1 NOT IN (1,3);
 +----------+----------+
 ```
 
+#### `IN` with tuple-like values and `NULL`
+
+For tuple-like values, `IN` uses DataFusion's struct equality semantics:
+
+```sql
+SELECT (1, 1) IN ((1, NULL));
+-- false
+
+SELECT (1, NULL) IN ((1, NULL));
+-- true
+```
+
 ## SELECT clause subqueries
 
 `SELECT` clause subqueries use values returned from the inner query as part