kosiew commented on code in PR #20808:
URL: https://github.com/apache/datafusion/pull/20808#discussion_r2999210852


##########
datafusion/spark/src/function/datetime/quarter.rs:
##########
@@ -0,0 +1,102 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use arrow::array::{Array, ArrayRef};
+use arrow::compute::{CastOptions, DatePart, cast_with_options, date_part};
+use arrow::datatypes::{DataType, Field, FieldRef, TimeUnit};
+use datafusion::logical_expr::{ColumnarValue, Signature, TypeSignature, 
Volatility};
+use datafusion_common::utils::take_function_args;
+use datafusion_common::{Result, internal_err};
+use datafusion_expr::{ReturnFieldArgs, ScalarFunctionArgs, ScalarUDFImpl};
+use datafusion_functions::utils::make_scalar_function;
+use std::sync::Arc;
+
+#[derive(Debug, PartialEq, Eq, Hash)]
+pub struct SparkQuarter {
+    signature: Signature,
+}
+
+impl Default for SparkQuarter {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl SparkQuarter {
+    pub fn new() -> Self {
+        Self {
+            signature: Signature::one_of(
+                vec![
+                    TypeSignature::Exact(vec![DataType::Utf8]),
+                    TypeSignature::Exact(vec![DataType::Utf8View]),
+                    TypeSignature::Exact(vec![DataType::LargeUtf8]),
+                    TypeSignature::Exact(vec![DataType::Date32]),
+                    TypeSignature::Exact(vec![DataType::Timestamp(

Review Comment:
   I think there is still one important gap here.
   
   `quarter` is still declared with an exact `Timestamp(Millisecond, None)` 
signature, while Spark's `date_part` wrapper already uses the broader coercible 
timestamp path. 
   Because of that, timestamp inputs with other units or timezones can still 
get rejected during planning, even though the implementation below handles 
`DataType::Timestamp(_, _)` once execution starts.
   
   Could we align this with the existing Spark datetime coercion model so 
`quarter` behaves consistently with the rest of that path?



##########
datafusion/sqllogictest/test_files/spark/datetime/quarter.slt:
##########
@@ -15,13 +15,57 @@
 # specific language governing permissions and limitations
 # under the License.
 
-# This file was originally created by a porting script from:
-#   
https://github.com/lakehq/sail/tree/43b6ed8221de5c4c4adbedbb267ae1351158b43c/crates/sail-spark-connect/tests/gold_data/function
-# This file is part of the implementation of the datafusion-spark function 
library.
-# For more information, please see:
-#   https://github.com/apache/datafusion/issues/15914
-
-## Original Query: SELECT quarter('2016-08-31');
-## PySpark 3.5.5 Result: {'quarter(2016-08-31)': 3, 
'typeof(quarter(2016-08-31))': 'int', 'typeof(2016-08-31)': 'string'}
-#query
-#SELECT quarter('2016-08-31'::string);
+query I
+SELECT quarter('2009-01-12'::date);
+----
+1
+
+query I
+SELECT quarter('1970-01-01'::date);
+----
+1
+
+query I
+SELECT quarter('1870-01-01'::date);
+----
+1
+
+query I
+SELECT quarter('2011-04-21'::date);
+----
+2
+
+query I
+SELECT quarter('2024-08-14'::date);
+----
+3
+
+query I
+SELECT quarter('2016-12-12'::date);
+----
+4
+
+query I
+SELECT quarter(NULL::date);
+----
+NULL
+
+query I
+SELECT quarter('2009-01-12 10:00:00'::timestamp);
+----
+1
+
+query I
+SELECT quarter('2009-01-12'::string);

Review Comment:
   Nice to see the string coverage added here. 
   
   I think we still need the specific regression case from Spark's documented 
uncasted form.
   
   Right now this file checks `quarter('2009-01-12'::string)`, but it does not 
restore a plain string literal query like `quarter('2016-08-31')`. 
   
   Since preserving that call shape was the reason for broadening the 
signature, could we add that case back as well?



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to