CTTY commented on code in PR #1511:
URL: https://github.com/apache/iceberg-rust/pull/1511#discussion_r2241285933
##########
crates/iceberg/src/spec/manifest/mod.rs:
##########
@@ -1056,4 +1089,120 @@ mod tests {
assert!(!partitions[2].clone().contains_null);
assert_eq!(partitions[2].clone().contains_nan, Some(false));
}
+
+ #[test]
+ fn test_data_file_serialization() {
+ // Create a simple schema
+ let schema = Schema::builder()
+ .with_schema_id(1)
+ .with_identifier_field_ids(vec![1])
+ .with_fields(vec![
+ crate::spec::NestedField::required(1, "id",
Type::Primitive(PrimitiveType::Long))
+ .into(),
+ crate::spec::NestedField::required(
+ 2,
+ "name",
+ Type::Primitive(PrimitiveType::String),
+ )
+ .into(),
+ ])
+ .build()
+ .unwrap();
+
+ // Create a partition spec
+ let partition_spec = PartitionSpec::builder(schema.clone())
+ .with_spec_id(1)
+ .add_partition_field("id", "id_partition",
crate::spec::Transform::Identity)
+ .unwrap()
+ .build()
+ .unwrap();
+
+ // Get partition type from the partition spec
+ let partition_type = partition_spec.partition_type(&schema).unwrap();
+
+ // Create a vector of DataFile objects
+ let data_files = vec![
+ DataFileBuilder::default()
+ .content(crate::spec::DataContentType::Data)
+ .file_format(DataFileFormat::Parquet)
+ .file_path("path/to/file1.parquet".to_string())
+ .file_size_in_bytes(1024)
+ .record_count(100)
+ .partition_spec_id(1)
+ .partition(Struct::empty())
+ .column_sizes(HashMap::from([(1, 512), (2, 512)]))
+ .value_counts(HashMap::from([(1, 100), (2, 100)]))
+ .null_value_counts(HashMap::from([(1, 0), (2, 0)]))
+ .build()
+ .unwrap(),
+ DataFileBuilder::default()
+ .content(crate::spec::DataContentType::Data)
+ .file_format(DataFileFormat::Parquet)
+ .file_path("path/to/file2.parquet".to_string())
+ .file_size_in_bytes(2048)
+ .record_count(200)
+ .partition_spec_id(1)
+ .partition(Struct::empty())
+ .column_sizes(HashMap::from([(1, 1024), (2, 1024)]))
+ .value_counts(HashMap::from([(1, 200), (2, 200)]))
+ .null_value_counts(HashMap::from([(1, 10), (2, 5)]))
+ .build()
+ .unwrap(),
+ ];
+
+ // Serialize the DataFile objects
+ let serialized_files = data_files
+ .into_iter()
+ .map(|f| {
+ let json =
+ serialize_data_file_to_json(f, &partition_type,
FormatVersion::V2).unwrap();
+ println!("Test serialized data file: {}", json);
+ json
+ })
+ .collect::<Vec<String>>();
+
+ // Verify we have the expected number of serialized files
+ assert_eq!(serialized_files.len(), 2);
+
+ // Verify each serialized file contains expected data
+ for json in &serialized_files {
+ assert!(json.contains("path/to/file"));
Review Comment:
I've created a new [PR](https://github.com/apache/iceberg-rust/pull/1563) to
address the DataFileSerde-related changes separately
--
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]
