alamb commented on code in PR #8341:
URL: https://github.com/apache/arrow-rs/pull/8341#discussion_r2356492974
##########
parquet/src/parquet_thrift.rs:
##########
@@ -428,122 +388,176 @@ impl<'b, 'a: 'b> ThriftCompactInputProtocol<'a> {
}
match field_type {
- FieldType::BooleanFalse | FieldType::BooleanTrue =>
self.read_bool().map(|_| ()),
+ // boolean field has no data
+ FieldType::BooleanFalse | FieldType::BooleanTrue => Ok(()),
FieldType::Byte => self.read_i8().map(|_| ()),
FieldType::I16 => self.skip_vlq().map(|_| ()),
FieldType::I32 => self.skip_vlq().map(|_| ()),
FieldType::I64 => self.skip_vlq().map(|_| ()),
FieldType::Double => self.skip_bytes(8).map(|_| ()),
FieldType::Binary => self.skip_binary().map(|_| ()),
FieldType::Struct => {
- self.read_struct_begin()?;
+ let mut last_field_id = 0i16;
loop {
- let field_ident = self.read_field_begin()?;
+ let field_ident = self.read_field_begin(last_field_id)?;
if field_ident.field_type == FieldType::Stop {
break;
}
self.skip_till_depth(field_ident.field_type, depth - 1)?;
+ last_field_id = field_ident.id;
}
- self.read_struct_end()
+ Ok(())
}
FieldType::List => {
let list_ident = self.read_list_begin()?;
for _ in 0..list_ident.size {
let element_type =
FieldType::try_from(list_ident.element_type)?;
self.skip_till_depth(element_type, depth - 1)?;
}
- self.read_list_end()
+ Ok(())
}
// no list or map types in parquet format
u => Err(general_err!(format!("cannot skip field type {:?}", &u))),
}
}
}
+/// A high performance Thrift reader that reads from a slice of bytes.
Review Comment:
🚀
--
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]