jayzhan211 commented on code in PR #10268:
URL: https://github.com/apache/datafusion/pull/10268#discussion_r1583129464
##########
datafusion/expr/src/type_coercion/binary.rs:
##########
@@ -289,15 +290,164 @@ fn bitwise_coercion(left_type: &DataType, right_type:
&DataType) -> Option<DataT
}
}
+#[derive(Debug, PartialEq, Eq, Hash, Clone)]
+enum TypeCategory {
+ Array,
+ Boolean,
+ Numeric,
+ // String, well-defined type, but are considered as unknown type.
+ DateTime,
+ Composite,
+ Unknown,
+ NotSupported,
+}
+
+fn data_type_category(data_type: &DataType) -> TypeCategory {
+ if data_type.is_numeric() {
+ return TypeCategory::Numeric;
+ }
+
+ if matches!(data_type, DataType::Boolean) {
+ return TypeCategory::Boolean;
+ }
+
+ if matches!(
+ data_type,
+ DataType::List(_) | DataType::FixedSizeList(_, _) |
DataType::LargeList(_)
+ ) {
+ return TypeCategory::Array;
+ }
+
+ // String literal is possible to cast to many other types like numeric or
datetime,
+ // therefore, it is categorized as a unknown type
+ if matches!(
+ data_type,
+ DataType::Utf8 | DataType::LargeUtf8 | DataType::Null
+ ) {
+ return TypeCategory::Unknown;
+ }
+
+ if matches!(
+ data_type,
+ DataType::Date32
+ | DataType::Date64
+ | DataType::Time32(_)
+ | DataType::Time64(_)
+ | DataType::Timestamp(_, _)
+ | DataType::Interval(_)
+ | DataType::Duration(_)
+ ) {
+ return TypeCategory::DateTime;
+ }
+
+ if matches!(
+ data_type,
+ DataType::Dictionary(_, _) | DataType::Struct(_) | DataType::Union(_,
_)
+ ) {
+ return TypeCategory::Composite;
+ }
+
+ TypeCategory::NotSupported
+}
+
+/// Coerce `lhs_type` and `rhs_type` to a common type for the purposes of
constructs including
+/// CASE, ARRAY, VALUES, and the GREATEST and LEAST functions.
+/// See <https://www.postgresql.org/docs/current/typeconv-union-case.html> for
more information.
+/// The actual rules follows the behavior of Postgres and DuckDB
+pub fn type_resolution(data_types: &[DataType]) -> Option<DataType> {
Review Comment:
I think the biggest difference between comparison coercion is that we
categorize types.
--
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]
