Use latest DF 33 branch

Author: andygrove

Cargo.lock

@@ -37,12 +37,12 @@ substrait = ["dep:datafusion-substrait"]
 tokio = { version = "1.24", features = ["macros", "rt", "rt-multi-thread", "sync"] }
 rand = "0.8"
 pyo3 = { version = "0.20", features = ["extension-module", "abi3", "abi3-py38"] }
-datafusion = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1", features = ["pyarrow", "avro"] }
-datafusion-common = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1", features = ["pyarrow"] }
-datafusion-expr = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1" }
-datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1" }
-datafusion-sql = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1" }
-datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion", rev = "33.0.0-rc1", optional = true }
+datafusion = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33", features = ["pyarrow", "avro"] }
+datafusion-common = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33", features = ["pyarrow"] }
+datafusion-expr = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33" }
+datafusion-optimizer = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33" }
+datafusion-sql = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33" }
+datafusion-substrait = { git = "https://github.com/apache/arrow-datafusion", branch = "branch-33", optional = true }
 prost = "0.12"
 prost-types = "0.12"
 uuid = { version = "1.3", features = ["v4"] }

Cargo.toml

@@ -265,9 +265,7 @@ impl PyExpr {
     pub fn rex_type(&self) -> PyResult<RexType> {
         Ok(match self.expr {
             Expr::Alias(..) => RexType::Alias,
-            Expr::Column(..) | Expr::QualifiedWildcard { .. } | Expr::GetIndexedField { .. } => {
-                RexType::Reference
-            }
+            Expr::Column(..) | Expr::GetIndexedField { .. } => RexType::Reference,
             Expr::ScalarVariable(..) | Expr::Literal(..) => RexType::Literal,
             Expr::BinaryExpr { .. }
             | Expr::Not(..)
@@ -286,7 +284,7 @@ impl PyExpr {
             | Expr::WindowFunction { .. }
             | Expr::AggregateUDF { .. }
             | Expr::InList { .. }
-            | Expr::Wildcard
+            | Expr::Wildcard { .. }
             | Expr::ScalarUDF { .. }
             | Expr::Exists { .. }
             | Expr::InSubquery { .. }
@@ -463,8 +461,7 @@ impl PyExpr {
             // Currently un-support/implemented Expr types for Rex Call operations
             Expr::GroupingSet(..)
             | Expr::OuterReferenceColumn(_, _)
-            | Expr::Wildcard
-            | Expr::QualifiedWildcard { .. }
+            | Expr::Wildcard { .. }
             | Expr::ScalarSubquery(..)
             | Expr::Placeholder { .. }
             | Expr::Exists { .. } => Err(py_runtime_err(format!(
@@ -548,7 +545,7 @@ impl PyExpr {
                 // appear in projections) so we just delegate to the contained expression instead
                 Self::expr_to_field(expr, input_plan)
             }
-            Expr::Wildcard => {
+            Expr::Wildcard { .. } => {
                 // Since * could be any of the valid column names just return the first one
                 Ok(input_plan.schema().field(0).clone())
             }