alamb commented on code in PR #12816:
URL: https://github.com/apache/datafusion/pull/12816#discussion_r1807808549
##########
datafusion/core/src/datasource/file_format/mod.rs:
##########
@@ -235,20 +235,26 @@ pub fn file_type_to_format(
}
}
+/// Create a new field with the specified data type, copying the other
+/// properties from the input field
+fn field_with_new_type(field: &FieldRef, new_type: DataType) -> FieldRef {
+ Arc::new(field.as_ref().clone().with_data_type(new_type))
+}
+
/// Transform a schema to use view types for Utf8 and Binary
+///
+/// See [parquet::ParquetFormat::force_view_types] for details
pub fn transform_schema_to_view(schema: &Schema) -> Schema {
let transformed_fields: Vec<Arc<Field>> = schema
.fields
.iter()
.map(|field| match field.data_type() {
- DataType::Utf8 | DataType::LargeUtf8 => Arc::new(
- Field::new(field.name(), DataType::Utf8View,
field.is_nullable())
- .with_metadata(field.metadata().to_owned()),
- ),
- DataType::Binary | DataType::LargeBinary => Arc::new(
- Field::new(field.name(), DataType::BinaryView,
field.is_nullable())
- .with_metadata(field.metadata().to_owned()),
- ),
+ DataType::Utf8 | DataType::LargeUtf8 => {
Review Comment:
I plan to try and accelerate this PR along with a new arrow-rs release:
https://github.com/apache/arrow-rs/issues/6341
--
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: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
