chore: update datafusion to 50 (#7076)

* chore: update datafusion to 50

Signed-off-by: luofucong <luofc@foxmail.com>

* fix ci

Signed-off-by: luofucong <luofc@foxmail.com>

* fix: update datafusion_pg_catalog import

* chore: fix toml format

* chore: fix toml format again

* fix nextest

Signed-off-by: luofucong <luofc@foxmail.com>

* fix sqlness

Signed-off-by: luofucong <luofc@foxmail.com>

* chore: switch datafusion-orc to upstream tag

* fix sqlness

Signed-off-by: luofucong <luofc@foxmail.com>

* resolve PR comments

Signed-off-by: luofucong <luofc@foxmail.com>

---------

Signed-off-by: luofucong <luofc@foxmail.com>
Co-authored-by: Ning Sun <sunning@greptime.com>

src/common/function/src/aggrs/aggr_wrapper.rs

@@ -22,6 +22,7 @@
 //! `foo_merge`'s input arg is the same as `foo_state`'s output, and its output is the same as `foo`'s input.
 //!
 
+use std::hash::{Hash, Hasher};
 use std::sync::Arc;
 
 use arrow::array::StructArray;
@@ -272,7 +273,7 @@ impl StateMergeHelper {
 }
 
 /// Wrapper to make an aggregate function out of a state function.
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
 pub struct StateWrapper {
     inner: AggregateUDF,
     name: String,
@@ -616,6 +617,20 @@ impl AggregateUDFImpl for MergeWrapper {
     }
 }
 
+impl PartialEq for MergeWrapper {
+    fn eq(&self, other: &Self) -> bool {
+        self.inner == other.inner
+    }
+}
+
+impl Eq for MergeWrapper {}
+
+impl Hash for MergeWrapper {
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        self.inner.hash(state);
+    }
+}
+
 /// The merge accumulator, which modify `update_batch`'s behavior to accept one struct array which
 /// include the state fields of original aggregate function, and merge said states into original accumulator
 /// the output is the same as original aggregate function

src/common/function/src/aggrs/aggr_wrapper/tests.rs

@@ -39,8 +39,7 @@ use datafusion::prelude::SessionContext;
 use datafusion_common::arrow::array::AsArray;
 use datafusion_common::arrow::datatypes::{Float64Type, UInt64Type};
 use datafusion_common::{Column, TableReference};
-use datafusion_expr::expr::AggregateFunction;
-use datafusion_expr::sqlparser::ast::NullTreatment;
+use datafusion_expr::expr::{AggregateFunction, NullTreatment};
 use datafusion_expr::{
     Aggregate, ColumnarValue, Expr, LogicalPlan, ScalarFunctionArgs, SortExpr, TableScan, lit,
 };

src/common/function/src/aggrs/count_hash.rs

@@ -68,7 +68,7 @@ impl CountHash {
     }
 }
 
-#[derive(Debug, Clone)]
+#[derive(Debug, Clone, Eq, PartialEq, Hash)]
 pub struct CountHash {
     signature: Signature,
 }

src/common/function/src/scalars/geo/geohash.rs

@@ -76,7 +76,7 @@ impl Function for GeohashFunction {
     }
 
     fn return_type(&self, _: &[DataType]) -> datafusion_common::Result<DataType> {
-        Ok(DataType::Utf8)
+        Ok(DataType::Utf8View)
     }
 
     fn signature(&self) -> &Signature {
@@ -176,7 +176,7 @@ impl Function for GeohashNeighboursFunction {
         Ok(DataType::List(Arc::new(Field::new(
             "item",
             DataType::Utf8View,
-            false,
+            true,
         ))))
     }
 

src/common/function/src/scalars/geo/h3.rs

@@ -355,9 +355,9 @@ impl Function for H3CellCenterLatLng {
 
     fn return_type(&self, _: &[DataType]) -> datafusion_common::Result<DataType> {
         Ok(DataType::List(Arc::new(Field::new(
-            "x",
+            "item",
             DataType::Float64,
-            false,
+            true,
         ))))
     }
 

src/common/function/src/scalars/udf.rs

@@ -14,6 +14,7 @@
 
 use std::any::Any;
 use std::fmt::{Debug, Formatter};
+use std::hash::{Hash, Hasher};
 
 use datafusion::arrow::datatypes::DataType;
 use datafusion::logical_expr::{ScalarFunctionArgs, ScalarUDFImpl};
@@ -33,6 +34,20 @@ impl Debug for ScalarUdf {
     }
 }
 
+impl PartialEq for ScalarUdf {
+    fn eq(&self, other: &Self) -> bool {
+        self.function.signature() == other.function.signature()
+    }
+}
+
+impl Eq for ScalarUdf {}
+
+impl Hash for ScalarUdf {
+    fn hash<H: Hasher>(&self, state: &mut H) {
+        self.function.signature().hash(state)
+    }
+}
+
 impl ScalarUDFImpl for ScalarUdf {
     fn as_any(&self) -> &dyn Any {
         self