ewoodbury commented on code in PR #3255:
URL: https://github.com/apache/iceberg-rust/pull/3255#discussion_r4235424296
##########
crates/iceberg/src/arrow/record_batch_transformer.rs:
##########
@@ -1147,22 +1422,546 @@ mod test {
use std::collections::HashMap;
use std::sync::Arc;
+ use arrow_array::cast::AsArray;
+ use arrow_array::types::Int32Type;
use arrow_array::{
- Array, Date32Array, Float32Array, Float64Array, Int32Array,
Int64Array, RecordBatch,
- StringArray,
+ Array, ArrayRef, Date32Array, Float32Array, Float64Array, Int32Array,
Int64Array,
+ LargeListArray, ListArray, MapArray, RecordBatch, StringArray,
StructArray,
};
+ use arrow_buffer::{NullBuffer, OffsetBuffer};
use arrow_cast::cast;
- use arrow_schema::{DataType, Field, Schema as ArrowSchema};
+ use arrow_schema::{DataType, Field, Fields, Schema as ArrowSchema};
use super::{field_with_id, schema_to_arrow_schema};
- use crate::arrow::build_partition_constant;
+ use crate::ErrorKind;
use crate::arrow::record_batch_transformer::{
- RecordBatchTransformer, RecordBatchTransformerBuilder,
+ PromotePlan, RecordBatchTransformer, RecordBatchTransformerBuilder,
};
+ use crate::arrow::{DEFAULT_MAP_FIELD_NAME, build_partition_constant};
use crate::spec::{
- ListType, Literal, MapType, NestedField, PrimitiveType, Schema,
Struct, Type,
+ ListType, Literal, MapType, NestedField, PrimitiveType, Schema,
Struct, StructType, Type,
};
+ fn promote(source: &ArrayRef, target: &DataType, schema: &Schema) ->
crate::Result<ArrayRef> {
+ PromotePlan::build(source.data_type(), target, schema,
&HashMap::new())?.apply(source)
+ }
+
+ fn empty_schema() -> Schema {
+ Schema::builder().build().unwrap()
+ }
+
+ fn unevolved_struct_type() -> DataType {
+ DataType::Struct(Fields::from(vec![field_with_id(
+ "x",
+ DataType::Int32,
+ true,
+ 5,
+ )]))
+ }
+
+ fn evolved_struct_type() -> DataType {
+ DataType::Struct(Fields::from(vec![
+ field_with_id("x", DataType::Int32, true, 5),
+ field_with_id("y", DataType::Int32, true, 6),
+ ]))
+ }
+
+ fn unevolved_struct_data(x_values: Vec<i32>) -> Arc<StructArray> {
+ Arc::new(StructArray::new(
+ Fields::from(vec![field_with_id("x", DataType::Int32, true, 5)]),
+ vec![Arc::new(Int32Array::from(x_values)) as ArrayRef],
+ None,
+ ))
+ }
+
+ fn transform_top_level(column: NestedField, file_column: ArrayRef) ->
crate::Result<ArrayRef> {
+ let name = column.name.clone();
+ let snapshot_schema = Arc::new(
+ Schema::builder()
+ .with_schema_id(1)
+ .with_fields(vec![
+ NestedField::required(1, "id",
Type::Primitive(PrimitiveType::Int)).into(),
+ column.into(),
+ ])
+ .build()
+ .unwrap(),
+ );
+ let mut transformer =
RecordBatchTransformerBuilder::new(snapshot_schema, &[1, 2]).build();
+ let file_schema = Arc::new(ArrowSchema::new(vec![
+ field_with_id("id", DataType::Int32, false, 1),
+ field_with_id(name, file_column.data_type().clone(), true, 2),
+ ]));
+ let batch = RecordBatch::try_new(file_schema, vec![
+ Arc::new(Int32Array::from(vec![1; file_column.len()])) as ArrayRef,
+ file_column,
+ ])
+ .unwrap();
+ Ok(transformer.process_record_batch(batch)?.column(1).clone())
+ }
+
+ #[test]
+ fn promote_struct_fills_added_fields_by_id() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![
+ field_with_id("a", DataType::Int32, true, 1),
+ field_with_id("c", DataType::Utf8, true, 3),
+ ]),
+ vec![
+ Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef,
+ Arc::new(StringArray::from(vec!["x", "y"])) as ArrayRef,
+ ],
+ None,
+ )) as ArrayRef;
+ let fields = Fields::from(vec![
+ field_with_id("a", DataType::Int32, true, 1),
+ field_with_id("b", DataType::Int32, true, 2),
+ field_with_id("c", DataType::Utf8, true, 3),
+ field_with_id("d", DataType::Int32, true, 4),
+ ]);
+ let target = DataType::Struct(fields.clone());
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let expected = StructArray::new(
+ fields,
+ vec![
+ Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef,
+ Arc::new(Int32Array::from(vec![None, None])) as ArrayRef,
+ Arc::new(StringArray::from(vec!["x", "y"])) as ArrayRef,
+ Arc::new(Int32Array::from(vec![None, None])) as ArrayRef,
+ ],
+ None,
+ );
+ assert_eq!(out.as_struct(), &expected);
+ }
+
+ #[test]
+ fn promote_list_element_struct_fills_added_field_by_id() {
+ let source = Arc::new(ListArray::new(
+ Arc::new(field_with_id("element", unevolved_struct_type(), true,
4)),
+ OffsetBuffer::new(vec![0, 1, 2].into()),
+ unevolved_struct_data(vec![10, 20]),
+ None,
+ )) as ArrayRef;
+ let target = DataType::List(Arc::new(field_with_id(
+ "element",
+ evolved_struct_type(),
+ true,
+ 4,
+ )));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let values = StructArray::new(
+ Fields::from(vec![
+ field_with_id("x", DataType::Int32, true, 5),
+ field_with_id("y", DataType::Int32, true, 6),
+ ]),
+ vec![
+ Arc::new(Int32Array::from(vec![10, 20])) as ArrayRef,
+ Arc::new(Int32Array::from(vec![None, None])) as ArrayRef,
+ ],
+ None,
+ );
+ let expected = ListArray::new(
+ Arc::new(field_with_id("element", evolved_struct_type(), true, 4)),
+ OffsetBuffer::new(vec![0, 1, 2].into()),
+ Arc::new(values),
+ None,
+ );
+ assert_eq!(out.as_list::<i32>(), &expected);
Review Comment:
Checked this one against arrow-data. `ListArray` equality compares the full
element `Field`, including name and `PARQUET:field_id`: changing either in
expected fails the existing assert.
Checked and agree on maps though, arrow skips the entries field name there;
updated so both map tests now also assert `out.data_type() ==
expected.data_type()`
--
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]
