comphead commented on code in PR #3536:
URL: https://github.com/apache/datafusion-comet/pull/3536#discussion_r2819550773
##########
native/core/src/parquet/parquet_exec.rs:
##########
@@ -166,27 +203,24 @@ fn get_options(
(table_parquet_options, spark_parquet_options)
}
-fn get_file_config_builder(
- schema: SchemaRef,
- partition_schema: Option<SchemaRef>,
- file_groups: Vec<FileGroup>,
- object_store_url: ObjectStoreUrl,
- file_source: Arc<dyn FileSource>,
-) -> FileScanConfigBuilder {
- match partition_schema {
- Some(partition_schema) => {
- let partition_fields: Vec<Field> = partition_schema
- .fields()
- .iter()
- .map(|field| {
- Field::new(field.name(), field.data_type().clone(),
field.is_nullable())
- })
- .collect_vec();
- FileScanConfigBuilder::new(object_store_url, Arc::clone(&schema),
file_source)
- .with_file_groups(file_groups)
- .with_table_partition_cols(partition_fields)
+/// Wraps a `SendableRecordBatchStream` to print each batch as it flows
through.
+/// Returns a new `SendableRecordBatchStream` that yields the same batches.
+pub fn dbg_batch_stream(stream: SendableRecordBatchStream) ->
SendableRecordBatchStream {
Review Comment:
Found it useful for outputting a stream, preserving the original stream to
the output. it is not used now, but would be handy for debug purposes.
--
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]
