alamb commented on a change in pull request #8870:
URL: https://github.com/apache/arrow/pull/8870#discussion_r541180190
##########
File path: rust/datafusion/src/logical_plan/builder.rs
##########
@@ -71,37 +98,44 @@ impl LogicalPlanBuilder {
};
let projected_schema = projection
- .clone()
.map(|p| Schema::new(p.iter().map(|i|
schema.field(*i).clone()).collect()))
- .or(Some(schema.clone()))
+ .or(Some(schema))
.unwrap();
+ let projected_schema =
DFSchemaRef::new(DFSchema::from(&projected_schema)?);
- Ok(Self::from(&LogicalPlan::CsvScan {
- path: path.to_owned(),
- schema: SchemaRef::new(schema),
- has_header,
- delimiter: Some(delimiter),
- projection,
- projected_schema:
DFSchemaRef::new(DFSchema::from(&projected_schema)?),
- }))
+ let provider = Arc::new(CsvFile::try_new(path, options)?);
+ let schema = provider.schema();
+
+ let table_scan = LogicalPlan::TableScan {
+ schema_name: "".to_string(),
+ source: TableSource::FromProvider(provider),
+ table_schema: schema,
+ projected_schema,
+ projection: None,
+ };
+
+ Ok(Self::from(&table_scan))
}
/// Scan a Parquet data source
pub fn scan_parquet(path: &str, projection: Option<Vec<usize>>) ->
Result<Self> {
- let p = ParquetTable::try_new(path)?;
- let schema = p.schema();
+ let provider = Arc::new(ParquetTable::try_new(path)?);
+ let schema = provider.schema();
let projected_schema = projection
- .clone()
.map(|p| Schema::new(p.iter().map(|i|
schema.field(*i).clone()).collect()));
let projected_schema = projected_schema.map_or(schema.clone(),
SchemaRef::new);
+ let projected_schema =
DFSchemaRef::new(DFSchema::from(&projected_schema)?);
Review comment:
https://github.com/apache/arrow/pull/8888 for the record
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
