alamb commented on code in PR #12816:
URL: https://github.com/apache/datafusion/pull/12816#discussion_r1803746194
##########
benchmarks/src/clickbench.rs:
##########
@@ -115,12 +115,15 @@ impl RunOpt {
None => queries.min_query_id()..=queries.max_query_id(),
};
+ // configure parquet options
let mut config = self.common.config();
- config
- .options_mut()
- .execution
- .parquet
- .schema_force_view_types = self.common.force_view_types;
+ {
+ let parquet_options = &mut config.options_mut().execution.parquet;
+ parquet_options.schema_force_view_types =
self.common.force_view_types;
+ // The hits_partitioned dataset specifies string columns
+ // as binary due to how it was written. Force it to strings
+ parquet_options.binary_as_string = true;
Review Comment:
we will have to mirror these options in the actual clickbench run
##########
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 reduced repetition of this code by encapsulating creating a new `FieldRef`
from an existing `Field` in a function. I also think this will avoid the
potential loss of metadata
--
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
