etseidl commented on code in PR #9974:
URL: https://github.com/apache/arrow-rs/pull/9974#discussion_r3243139912
##########
parquet/src/parquet_thrift.rs:
##########
@@ -507,26 +512,38 @@ pub(crate) trait ThriftCompactInputProtocol<'a> {
FieldType::Double => self.skip_bytes(8).map(|_| ()),
FieldType::Binary => self.skip_binary().map(|_| ()),
FieldType::Struct => {
- let mut last_field_id = 0i16;
loop {
- let field_ident = self.read_field_begin(last_field_id)?;
+ let field_ident = self.read_field_begin(0)?;
if field_ident.field_type == FieldType::Stop {
break;
}
self.skip_till_depth(field_ident.field_type, depth - 1)?;
- last_field_id = field_ident.id;
}
Ok(())
}
- FieldType::List => {
+ // lists and sets are encoded the same
+ FieldType::List | FieldType::Set => {
let list_ident = self.read_list_begin()?;
+ let element_type = FieldType::from(list_ident.element_type);
for _ in 0..list_ident.size {
- let element_type =
FieldType::try_from(list_ident.element_type)?;
self.skip_till_depth(element_type, depth - 1)?;
}
Ok(())
}
- // no list or map types in parquet format
+ FieldType::Map => {
Review Comment:
A map begins with a varint `size`. If `size` is `0` it's empty. Otherwise,
the next byte encodes the key and value types with 4 bits each, and then
encodes `size` key/value pairs.
--
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]
