ewoodbury commented on code in PR #3255:
URL: https://github.com/apache/iceberg-rust/pull/3255#discussion_r4235385077
##########
crates/iceberg/src/arrow/record_batch_transformer.rs:
##########
@@ -193,6 +195,284 @@ pub(crate) enum ColumnSource {
// post-processing step by using the projection mask.
}
+/// Reconciles a source array to the target type by matching nested fields on
+/// field id rather than position, mirroring iceberg-java's nested readers.
+///
+/// The plan is resolved once per file, when the `BatchTransform` is built, so
+/// applying it per batch is just index lookups and array assembly.
+#[derive(Debug)]
+pub(crate) enum PromotePlan {
+ PassThrough,
+ Cast(DataType),
+ Struct {
+ fields: Fields,
+ children: Vec<ChildPlan>,
+ },
+ List {
+ field: FieldRef,
+ element: Box<PromotePlan>,
+ },
+ Map {
+ field: FieldRef,
+ entry_fields: Fields,
+ entries: Vec<ChildPlan>,
+ sorted: bool,
+ },
+}
+
+#[derive(Debug)]
+pub(crate) enum ChildPlan {
+ FromSource {
+ source_index: usize,
+ plan: PromotePlan,
+ },
+ Add {
+ target_type: DataType,
+ value: Option<PrimitiveLiteral>,
+ },
+}
+
+impl PromotePlan {
+ fn build(
+ source: &DataType,
+ target: &DataType,
+ snapshot_schema: &IcebergSchema,
+ constant_fields: &HashMap<i32, ColumnConstant>,
+ ) -> Result<Self> {
+ if source == target {
+ return Ok(PromotePlan::PassThrough);
+ }
+ match (source, target) {
+ (DataType::Struct(source_fields), DataType::Struct(target_fields))
=> {
+ Ok(PromotePlan::Struct {
+ children: Self::build_struct_children(
+ source_fields,
+ target_fields,
+ snapshot_schema,
+ constant_fields,
+ )?,
+ fields: target_fields.clone(),
+ })
+ }
+ // A file's Arrow schema hint can give either offset width;
`apply` converts it.
+ // Table schemas are always `List`
(`ToArrowSchemaConverter::list`).
+ (
+ DataType::List(source_field) |
DataType::LargeList(source_field),
+ DataType::List(target_field),
+ ) => Ok(PromotePlan::List {
+ element: Box::new(Self::build(
+ source_field.data_type(),
+ target_field.data_type(),
+ snapshot_schema,
+ constant_fields,
+ )?),
+ field: target_field.clone(),
+ }),
+ (DataType::Map(source_entries, _), DataType::Map(target_entries,
sorted)) => {
+ match (source_entries.data_type(), target_entries.data_type())
{
+ (DataType::Struct(source_fields),
DataType::Struct(target_fields)) => {
+ Ok(PromotePlan::Map {
+ entries: Self::build_struct_children(
+ source_fields,
+ target_fields,
+ snapshot_schema,
+ constant_fields,
+ )?,
+ entry_fields: target_fields.clone(),
+ field: target_entries.clone(),
+ sorted: *sorted,
+ })
+ }
+ _ => Err(Error::new(
+ ErrorKind::Unexpected,
+ format!(
+ "expected struct-typed map entries, got
{source_entries:?} and {target_entries:?}"
+ ),
+ )),
+ }
+ }
+ (_, DataType::Struct(_) | DataType::List(_) |
DataType::LargeList(_))
+ | (_, DataType::Map(_, _)) => {
+ Err(invalid_data!("cannot promote {source:?} to {target:?}"))
+ }
+ _ => Ok(PromotePlan::Cast(target.clone())),
+ }
+ }
+
+ fn build_struct_children(
+ source_fields: &Fields,
+ target_fields: &Fields,
+ snapshot_schema: &IcebergSchema,
+ constant_fields: &HashMap<i32, ColumnConstant>,
+ ) -> Result<Vec<ChildPlan>> {
+ let mut source_by_id = HashMap::with_capacity(source_fields.len());
+ for (idx, field) in source_fields.iter().enumerate() {
+ if let Some(id) = try_get_field_id_from_metadata(field)? {
+ source_by_id.insert(id, idx);
+ }
+ }
+ // Name mapping only assigns top-level ids (#1845). Fully id-less
children
+ // match by position when the counts line up, and `build` checks each
pair.
+ // A same-type reorder cannot be detected without ids. Any missing id
+ // errors instead of nulling that child.
+ if source_by_id.len() != source_fields.len() {
+ if source_by_id.is_empty() && source_fields.len() ==
target_fields.len() {
Review Comment:
Makes sense - decided to pin it so
`promote_idless_same_type_reorder_stays_positional` locks in the current
behavior, and the comment now calls it a compatibility fallback until #1845. I
held off on the name check: it would make renamed children in files without
nested ids fail, and a reorder keeps the same names, so it wouldn't catch this
case anyway, and #1845 is the real fix.
--
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]
