blackmwk commented on code in PR #3091:
URL: https://github.com/apache/iceberg-rust/pull/3091#discussion_r3891493941
##########
crates/iceberg/src/scan/task.rs:
##########
@@ -282,3 +246,150 @@ pub struct FileScanTaskDeleteFile {
#[builder(default)]
pub key_metadata: Option<Box<[u8]>>,
}
+
+mod _serde {
+ use serde_derive::{Deserialize as DeserializeDerive, Serialize as
SerializeDerive};
+
+ use super::*;
+ use crate::{Error, ErrorKind};
+
+ // Container-level `into` conversion is infallible. Keep a failed typed
conversion here so
+ // serialization can return that error instead of panicking or changing
the wire format.
+ struct PartitionSerde(Result<RawLiteral>);
+
+ impl Serialize for PartitionSerde {
+ fn serialize<S>(&self, serializer: S) -> std::result::Result<S::Ok,
S::Error>
+ where S: serde::Serializer {
+ self.0
+ .as_ref()
+ .map_err(serde::ser::Error::custom)?
+ .serialize(serializer)
+ }
+ }
+
+ impl<'de> Deserialize<'de> for PartitionSerde {
+ fn deserialize<D>(deserializer: D) -> std::result::Result<Self,
D::Error>
+ where D: serde::Deserializer<'de> {
+ Ok(Self(Ok(RawLiteral::deserialize(deserializer)?)))
+ }
+ }
+
+ #[derive(SerializeDerive, DeserializeDerive)]
+ pub(super) struct FileScanTaskSerde {
+ file_size_in_bytes: u64,
+ start: u64,
+ length: u64,
+ record_count: Option<u64>,
+ #[serde(skip_serializing_if = "Option::is_none")]
+ first_row_id: Option<i64>,
+ #[serde(skip_serializing_if = "Option::is_none")]
+ data_sequence_number: Option<i64>,
+ data_file_path: String,
+ data_file_format: DataFileFormat,
+ schema: SchemaRef,
+ project_field_ids: Vec<i32>,
+ #[serde(skip_serializing_if = "Option::is_none")]
+ predicate: Option<BoundPredicate>,
+ deletes: Vec<FileScanTaskDeleteFile>,
+ #[serde(default)]
+ #[serde(skip_serializing_if = "Option::is_none")]
+ partition: Option<PartitionSerde>,
+ #[serde(default)]
+ #[serde(skip_serializing_if = "Option::is_none")]
+ partition_spec: Option<Arc<PartitionSpec>>,
+ #[serde(default)]
+ #[serde(skip_serializing_if = "Option::is_none")]
+ name_mapping: Option<Arc<NameMapping>>,
+ #[serde(default)]
+ #[serde(skip_serializing_if = "Option::is_none")]
+ unified_partition_type: Option<Arc<StructType>>,
+ case_sensitive: bool,
+ #[serde(default)]
+ #[serde(skip_serializing_if = "Option::is_none")]
+ key_metadata: Option<Box<[u8]>>,
+ }
+
+ fn partition_type(schema: &Schema, partition_spec: Option<&PartitionSpec>)
-> Result<Type> {
+ let partition_spec = partition_spec.ok_or_else(|| {
+ Error::new(
+ ErrorKind::DataInvalid,
+ "FileScanTask partition requires a partition spec",
+ )
+ })?;
+ Ok(Type::Struct(partition_spec.partition_type(schema)?))
+ }
+
+ impl From<FileScanTask> for FileScanTaskSerde {
+ fn from(value: FileScanTask) -> Self {
+ let partition = value.partition.map(|partition| {
Review Comment:
Updated partition type resolution so a missing partition spec uses an empty
StructType, and added a round-trip regression case with Struct::empty() and no
partition spec.
--
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]
