alamb commented on code in PR #8069:
URL: https://github.com/apache/arrow-rs/pull/8069#discussion_r2325097896
##########
parquet/src/arrow/arrow_writer/mod.rs:
##########
@@ -4293,4 +4304,50 @@ mod tests {
assert_eq!(get_dict_page_size(col0_meta), 1024 * 1024);
assert_eq!(get_dict_page_size(col1_meta), 1024 * 1024 * 4);
}
+
+ #[test]
+ fn arrow_writer_run_end_encoded() {
+ // Create a run array of strings
+ let mut builder = StringRunBuilder::<Int16Type>::new();
+ builder.extend(
+ vec![Some("alpha"); 1000]
+ .into_iter()
+ .chain(vec![Some("beta"); 1000]),
+ );
+ let run_array: RunArray<Int16Type> = builder.finish();
+ println!("run_array type: {:?}", run_array.data_type());
+ let schema = Arc::new(Schema::new(vec![Field::new(
+ "ree",
+ run_array.data_type().clone(),
+ run_array.is_nullable(),
+ )]));
+
+ // Write to parquet
+ let mut parquet_bytes: Vec<u8> = Vec::new();
+ let mut writer = ArrowWriter::try_new(&mut parquet_bytes,
schema.clone(), None).unwrap();
+ let batch = RecordBatch::try_new(schema.clone(),
vec![Arc::new(run_array)]).unwrap();
+ writer.write(&batch).unwrap();
+ writer.close().unwrap();
+
+ // Schema of output is plain, not dictionary or REE encoded!!
Review Comment:
Yes, I think that sounds like a very good approach -- especially if we focus
on the tests for reading/writing REE arrays first so when we go to implement
the optimized version we already have good test coverage
--
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]
