mbutrovich commented on code in PR #3255:
URL: https://github.com/apache/iceberg-rust/pull/3255#discussion_r4138836439
##########
crates/iceberg/src/arrow/record_batch_transformer.rs:
##########
@@ -1144,19 +1424,591 @@ mod test {
use std::collections::HashMap;
use std::sync::Arc;
+ use arrow_array::cast::AsArray;
+ use arrow_array::types::{Int32Type, Int64Type};
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;
use crate::arrow::build_partition_constant;
use crate::arrow::record_batch_transformer::{
- RecordBatchTransformer, RecordBatchTransformerBuilder,
+ PromotePlan, RecordBatchTransformer, RecordBatchTransformerBuilder,
};
- use crate::spec::{Literal, NestedField, PrimitiveType, Schema, Struct,
Type};
+ use crate::spec::{
+ 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)?.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 assert_existing_field_kept(s: &StructArray, expected_existing: &[i32]) {
+ assert_eq!(
+ s.column(0).as_primitive::<Int32Type>().values(),
+ expected_existing
+ );
+ }
+
+ fn assert_added_field_null(s: &StructArray) {
+ assert_eq!(s.column(1).null_count(), s.len());
+ }
+
+ 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_middle_field_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 target = DataType::Struct(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),
+ ]));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let s = out.as_struct();
+ assert_eq!(s.num_columns(), 3);
+ assert_eq!(s.column(0).as_primitive::<Int32Type>().values(), &[1, 2]);
+ assert_eq!(s.column(1).null_count(), 2);
+ let cc = s.column(2).as_string::<i32>();
+ assert_eq!((cc.value(0), cc.value(1)), ("x", "y"));
+ }
+
+ #[test]
+ fn promote_struct_fills_appended_field_by_id() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![
+ field_with_id("a", DataType::Int32, true, 1),
+ field_with_id("b", DataType::Utf8, true, 2),
+ ]),
+ vec![
+ Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef,
+ Arc::new(StringArray::from(vec!["x", "y"])) as ArrayRef,
+ ],
+ None,
+ )) as ArrayRef;
+ let target = DataType::Struct(Fields::from(vec![
+ field_with_id("a", DataType::Int32, true, 1),
+ field_with_id("b", DataType::Utf8, true, 2),
+ field_with_id("c", DataType::Int32, true, 3),
+ ]));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let s = out.as_struct();
+ assert_eq!(s.num_columns(), 3);
+ assert_eq!(s.column(0).as_primitive::<Int32Type>().values(), &[1, 2]);
+ let bb = s.column(1).as_string::<i32>();
+ assert_eq!((bb.value(0), bb.value(1)), ("x", "y"));
+ assert_eq!(s.column(2).null_count(), 2);
+ }
+
+ #[test]
+ fn promote_struct_missing_field_before_nested_list_struct() {
+ let elem_field = Arc::new(field_with_id("element",
unevolved_struct_type(), true, 4));
+ let list = Arc::new(ListArray::new(
+ elem_field.clone(),
+ OffsetBuffer::new(vec![0, 1, 2].into()),
+ unevolved_struct_data(vec![10, 20]),
+ None,
+ )) as ArrayRef;
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![
+ field_with_id("s", DataType::Utf8, true, 1),
+ field_with_id("ev", DataType::List(elem_field.clone()), true,
3),
+ ]),
+ vec![
+ Arc::new(StringArray::from(vec!["a", "b"])) as ArrayRef,
+ list,
+ ],
+ None,
+ )) as ArrayRef;
+ let target = DataType::Struct(Fields::from(vec![
+ field_with_id("s", DataType::Utf8, true, 1),
+ field_with_id("gap", DataType::Int32, true, 2),
+ field_with_id("ev", DataType::List(elem_field), true, 3),
+ ]));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let st = out.as_struct();
+ assert_eq!(st.num_columns(), 3);
+ assert_eq!(st.column(1).null_count(), 2);
+ let ev = st.column(2).as_list::<i32>();
+ assert_eq!(ev.len(), 2);
+ assert_eq!(
+ ev.value(0)
+ .as_struct()
+ .column(0)
+ .as_primitive::<Int32Type>()
+ .value(0),
+ 10
+ );
+ }
+
+ #[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 lst = out.as_list::<i32>();
+ assert_eq!(lst.len(), 2);
+ let elements = lst.values().as_struct();
+ assert_existing_field_kept(elements, &[10, 20]);
+ assert_added_field_null(elements);
+ }
+
+ #[test]
+ fn promote_map_value_struct_fills_added_field_by_id() {
+ let entries = StructArray::new(
+ Fields::from(vec![
+ field_with_id("key", DataType::Utf8, false, 7),
+ field_with_id("value", unevolved_struct_type(), true, 8),
+ ]),
+ vec![
+ Arc::new(StringArray::from(vec!["k1", "k2"])) as ArrayRef,
+ unevolved_struct_data(vec![100, 200]),
+ ],
+ None,
+ );
+ let source = Arc::new(MapArray::new(
+ Arc::new(Field::new("entries", entries.data_type().clone(),
false)),
+ OffsetBuffer::new(vec![0, 1, 2].into()),
+ entries,
+ None,
+ false,
+ )) as ArrayRef;
+ let target_entries = DataType::Struct(Fields::from(vec![
+ field_with_id("key", DataType::Utf8, false, 7),
+ field_with_id("value", evolved_struct_type(), true, 8),
+ ]));
+ let target = DataType::Map(
+ Arc::new(Field::new("entries", target_entries, false)),
+ false,
+ );
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let m = out.as_map();
+ assert_eq!(m.len(), 2);
+ let entries = m.entries();
+ let ks = entries.column(0).as_string::<i32>();
+ assert_eq!((ks.value(0), ks.value(1)), ("k1", "k2"));
+ let values = entries.column(1).as_struct();
+ assert_existing_field_kept(values, &[100, 200]);
+ assert_added_field_null(values);
+ }
+
+ #[test]
+ fn promote_large_list_element_struct_fills_added_field_by_id() {
+ let source = Arc::new(LargeListArray::new(
+ Arc::new(field_with_id("element", unevolved_struct_type(), true,
4)),
+ OffsetBuffer::new(vec![0i64, 1, 2].into()),
+ unevolved_struct_data(vec![7, 8]),
+ None,
+ )) as ArrayRef;
+ let target = DataType::LargeList(Arc::new(field_with_id(
+ "element",
+ evolved_struct_type(),
+ true,
+ 4,
+ )));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let lst = out.as_list::<i64>();
+ assert_eq!(lst.len(), 2);
+ let elements = lst.values().as_struct();
+ assert_existing_field_kept(elements, &[7, 8]);
+ assert_added_field_null(elements);
+ }
+
+ #[test]
+ fn promote_struct_renames_field_by_id() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![field_with_id("x_old", DataType::Int32, true,
5)]),
+ vec![Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef],
+ None,
+ )) as ArrayRef;
+ let target = DataType::Struct(Fields::from(vec![field_with_id(
+ "x",
+ DataType::Int32,
+ true,
+ 5,
+ )]));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let s = out.as_struct();
+ assert_eq!(s.fields()[0].name(), "x");
+ assert_eq!(s.column(0).as_primitive::<Int32Type>().values(), &[1, 2]);
+ }
+
+ #[test]
+ fn promote_struct_dropped_and_readded_same_name_nulls_by_id() {
+ let file = StructArray::new(
+ Fields::from(vec![field_with_id("x", DataType::Int32, true, 5)]),
+ vec![Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef],
+ None,
+ );
+ let out = transform_top_level(
+ NestedField::optional(
+ 2,
+ "s",
+ Type::Struct(StructType::new(vec![
+ NestedField::optional(6, "x",
Type::Primitive(PrimitiveType::Int)).into(),
+ ])),
+ ),
+ Arc::new(file),
+ )
+ .unwrap();
+ assert_eq!(out.as_struct().column(0).null_count(), 2);
+ }
+
+ #[test]
+ fn promote_struct_promotes_child_primitive() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![field_with_id("x", DataType::Int32, true, 5)]),
+ vec![Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef],
+ None,
+ )) as ArrayRef;
+ let target = DataType::Struct(Fields::from(vec![field_with_id(
+ "x",
+ DataType::Int64,
+ true,
+ 5,
+ )]));
+
+ let out = promote(&source, &target, &empty_schema()).unwrap();
+ let s = out.as_struct();
+ assert_eq!(s.column(0).as_primitive::<Int64Type>().values(), &[1, 2]);
+ }
+
+ #[test]
+ fn promote_struct_preserves_null_parent_rows() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![field_with_id("x", DataType::Int32, true, 5)]),
+ vec![Arc::new(Int32Array::from(vec![10, 20])) as ArrayRef],
+ Some(NullBuffer::from(vec![true, false])),
+ )) as ArrayRef;
+
+ let out = promote(&source, &evolved_struct_type(),
&empty_schema()).unwrap();
+ let s = out.as_struct();
+ assert!(!s.is_null(0));
+ assert!(s.is_null(1));
+ assert_eq!(s.column(0).as_primitive::<Int32Type>().value(0), 10);
+ assert_added_field_null(s);
+ }
+
+ #[test]
+ fn promote_struct_without_source_field_ids_errors() {
+ let source = Arc::new(StructArray::new(
+ Fields::from(vec![Field::new("x", DataType::Int32, true)]),
+ vec![Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef],
+ None,
+ )) as ArrayRef;
+
+ let err = promote(&source, &evolved_struct_type(),
&empty_schema()).unwrap_err();
+ assert!(err.to_string().contains("do not all have field ids"));
+ }
+
+ #[test]
+ fn promote_required_nested_field_absent_without_default_errors() {
+ let schema = Schema::builder()
+ .with_fields(vec![
+ NestedField::required(6, "y",
Type::Primitive(PrimitiveType::Int)).into(),
+ ])
+ .build()
+ .unwrap();
+ let source = unevolved_struct_data(vec![1, 2]) as ArrayRef;
+
+ let err = promote(&source, &evolved_struct_type(),
&schema).unwrap_err();
+ assert!(err.to_string().contains("required nested field"));
+ }
+
+ #[test]
+ fn promote_nested_field_with_initial_default_errors() {
+ let schema = Schema::builder()
+ .with_fields(vec![
+ NestedField::optional(6, "y",
Type::Primitive(PrimitiveType::Int))
+ .with_initial_default(Literal::int(42))
+ .into(),
+ ])
+ .build()
+ .unwrap();
+ let source = unevolved_struct_data(vec![1, 2]) as ArrayRef;
+
+ let err = promote(&source, &evolved_struct_type(),
&schema).unwrap_err();
+ assert!(err.to_string().contains("initial-default"));
+ }
+
+ #[test]
+ fn promote_struct_reorders_children_by_id_via_process_record_batch() {
+ let file = StructArray::new(
+ Fields::from(vec![
+ field_with_id("a", DataType::Int32, true, 5),
+ field_with_id("b", DataType::Int32, true, 6),
+ ]),
+ vec![
+ Arc::new(Int32Array::from(vec![1, 2])) as ArrayRef,
+ Arc::new(Int32Array::from(vec![100, 200])) as ArrayRef,
+ ],
+ None,
+ );
+ let out = transform_top_level(
+ NestedField::optional(
+ 2,
+ "s",
+ Type::Struct(StructType::new(vec![
+ NestedField::optional(6, "b",
Type::Primitive(PrimitiveType::Int)).into(),
+ NestedField::optional(5, "a",
Type::Primitive(PrimitiveType::Int)).into(),
+ ])),
+ ),
+ Arc::new(file),
+ )
+ .unwrap();
+ let s = out.as_struct();
+ assert_eq!(s.fields()[0].name(), "b");
+ assert_eq!(s.fields()[1].name(), "a");
+ assert_eq!(s.column(0).as_primitive::<Int32Type>().values(), &[
+ 100, 200
+ ]);
+ assert_eq!(s.column(1).as_primitive::<Int32Type>().values(), &[1, 2]);
Review Comment:
> Updated tests for rename, id-less nested struct, and evolved-struct to
compare the whole struct too.
Could the tests that came over from #2647 build the expected array too?
`promote_struct_fills_added_middle_field_by_id`,
`promote_struct_fills_appended_field_by_id`,
`promote_struct_missing_field_before_nested_list_struct`,
`promote_list_element_struct_fills_added_field_by_id`,
`promote_map_value_struct_fills_added_field_by_id`,
`promote_large_list_element_struct_fills_added_field_by_id`,
`promote_struct_promotes_child_primitive`, and
`promote_struct_preserves_null_parent_rows` still check values one column at a
time. Most of them null-fill a child without checking its name or field id, and
those come from the by-id matching this PR adds. With whole-array comparisons,
`assert_existing_field_kept` and `assert_added_field_null` can go away too.
--
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]
