Lordworms commented on code in PR #10842:
URL: https://github.com/apache/datafusion/pull/10842#discussion_r1633633345
##########
datafusion/substrait/src/logical_plan/consumer.rs:
##########
@@ -569,7 +571,80 @@ pub async fn from_substrait_rel(
Ok(LogicalPlan::Values(Values { schema, values }))
}
- _ => not_impl_err!("Only NamedTable and VirtualTable reads are
supported"),
+ Some(ReadType::LocalFiles(lf)) => {
+ fn extract_filename(name: &str) -> Option<String> {
+ let corrected_url =
+ if name.starts_with("file://") &&
!name.starts_with("file:///") {
+ name.replacen("file://", "file:///", 1)
+ } else {
+ name.to_string()
+ };
+
+ Url::parse(&corrected_url).ok().and_then(|url| {
+ let path = url.path();
+ std::path::Path::new(path)
+ .file_name()
+ .map(|filename|
filename.to_string_lossy().to_string())
+ })
+ }
+
+ // we could use the file name to check the original table
provider
+ // TODO: currently does not support multiple local files
+ let filename: Option<String> =
+ lf.items.first().and_then(|x| match x.path_type.as_ref() {
+ Some(UriFile(name)) => extract_filename(name),
+ _ => None,
+ });
+
+ if lf.items.len() > 1 || filename.is_none() {
+ return not_impl_err!(
+ "Only NamedTable and VirtualTable reads are supported"
+ );
+ }
+ let name = filename.unwrap();
+ // directly use unwrap here since we could determine it is a
valid one
+ let table_reference = TableReference::Bare { table:
name.into() };
+ let t = ctx.table(table_reference).await?;
+ let t = t.into_optimized_plan()?;
+ match &read.projection {
Review Comment:
Sure
##########
datafusion/substrait/src/logical_plan/consumer.rs:
##########
@@ -569,7 +571,80 @@ pub async fn from_substrait_rel(
Ok(LogicalPlan::Values(Values { schema, values }))
}
- _ => not_impl_err!("Only NamedTable and VirtualTable reads are
supported"),
+ Some(ReadType::LocalFiles(lf)) => {
+ fn extract_filename(name: &str) -> Option<String> {
+ let corrected_url =
+ if name.starts_with("file://") &&
!name.starts_with("file:///") {
+ name.replacen("file://", "file:///", 1)
+ } else {
+ name.to_string()
+ };
+
+ Url::parse(&corrected_url).ok().and_then(|url| {
+ let path = url.path();
+ std::path::Path::new(path)
+ .file_name()
+ .map(|filename|
filename.to_string_lossy().to_string())
+ })
+ }
+
+ // we could use the file name to check the original table
provider
+ // TODO: currently does not support multiple local files
+ let filename: Option<String> =
+ lf.items.first().and_then(|x| match x.path_type.as_ref() {
+ Some(UriFile(name)) => extract_filename(name),
+ _ => None,
+ });
+
+ if lf.items.len() > 1 || filename.is_none() {
+ return not_impl_err!(
+ "Only NamedTable and VirtualTable reads are supported"
+ );
+ }
+ let name = filename.unwrap();
+ // directly use unwrap here since we could determine it is a
valid one
+ let table_reference = TableReference::Bare { table:
name.into() };
+ let t = ctx.table(table_reference).await?;
+ let t = t.into_optimized_plan()?;
+ match &read.projection {
+ Some(MaskExpression { select, .. }) => match
&select.as_ref() {
+ Some(projection) => {
+ let column_indices: Vec<usize> = projection
+ .struct_items
+ .iter()
+ .map(|item| item.field as usize)
+ .collect();
+ match &t {
+ LogicalPlan::TableScan(scan) => {
+ let fields = column_indices
+ .iter()
+ .map(|i| {
+
scan.projected_schema.qualified_field(*i)
+ })
+ .map(|(qualifier, field)| {
+ (qualifier.cloned(),
Arc::new(field.clone()))
+ })
+ .collect();
+ let mut scan = scan.clone();
+ scan.projection = Some(column_indices);
+ scan.projected_schema =
+
DFSchemaRef::new(DFSchema::new_with_metadata(
+ fields,
+ HashMap::new(),
+ )?);
+ Ok(LogicalPlan::TableScan(scan))
+ }
+ _ => plan_err!("unexpected plan for table"),
+ }
+ }
+ _ => Ok(t),
+ },
+ _ => Ok(t),
+ }
+ }
+ _ => {
+ not_impl_err!("Only NamedTable and VirtualTable reads are
supported")
+ }
Review Comment:
got it
--
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
