Skip to content

Spark 4.2: Set Iceberg field IDs as Spark column IDs for DSv2 validation #17958

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rahulsmahadev wants to merge 2 commits into
base: main
Choose a base branch
from
+33 −1
Open

Spark 4.2: Set Iceberg field IDs as Spark column IDs for DSv2 validation #17958

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f9d1338
Spark 4.2: Set Iceberg field IDs as Spark column IDs for DSv2 validation
rahulsmahadev Sep 4, 2026
d348513
Merge remote-tracking branch 'databricks/main' into spark-4.2-column-…
rahulsmahadev Sep 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion spark/v4.2/spark/src/main/java/org/apache/iceberg/spark/TypeToSparkType.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,9 @@ public DataType struct(Types.StructType struct, List<DataType> fieldResults) {
Types.NestedField field = fields.get(i);
DataType type = fieldResults.get(i);
Metadata metadata = fieldMetadata(field.fieldId());
StructField sparkField = StructField.apply(field.name(), type, field.isOptional(), metadata);
StructField sparkField =
StructField.apply(field.name(), type, field.isOptional(), metadata)
.withId(Integer.toString(field.fieldId()));
if (field.doc() != null) {
sparkField = sparkField.withComment(field.doc());
}
Expand Down
30 changes: 30 additions & 0 deletions spark/v4.2/spark/src/test/java/org/apache/iceberg/spark/TestSparkSchemaUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,8 @@
import org.apache.spark.sql.catalyst.expressions.MetadataAttribute;
import org.apache.spark.sql.catalyst.types.DataTypeUtils;
import org.apache.spark.sql.catalyst.util.ResolveDefaultColumnsUtils$;
import org.apache.spark.sql.connector.catalog.CatalogV2Util;
import org.apache.spark.sql.connector.catalog.Column;
import org.apache.spark.sql.types.DataType;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.GeographyType;
Expand Down Expand Up @@ -101,6 +103,34 @@ public void testSchemaConversionWithMetaDataColumnSchema() {
}
}

@Test
public void testFieldIDsInSparkColumns() {
Schema schema =
new Schema(
optional(
10,
"location",
Types.StructType.of(
optional(11, "latitude", Types.DoubleType.get()),
optional(12, "longitude", Types.DoubleType.get()))));

StructType sparkSchema = SparkSchemaUtil.convert(schema);
StructField location = sparkSchema.apply("location");
StructType locationType = (StructType) location.dataType();

assertThat(location.id().get()).isEqualTo("10");
assertThat(locationType.apply("latitude").id().get()).isEqualTo("11");
assertThat(locationType.apply("longitude").id().get()).isEqualTo("12");

Column[] columns = CatalogV2Util.structTypeToV2Columns(sparkSchema, true);
assertThat(columns).hasSize(1);
assertThat(columns[0].id()).isEqualTo("10");

StructType columnType = (StructType) columns[0].dataType();
assertThat(columnType.apply("latitude").id().get()).isEqualTo("11");
assertThat(columnType.apply("longitude").id().get()).isEqualTo("12");
}

@Test
public void testGeospatialTypeConversion() {
// a default-CRS geometry round-trips through the null <-> OGC:CRS84 normalization
Expand Down
Loading