alamb commented on code in PR #13874:
URL: https://github.com/apache/datafusion/pull/13874#discussion_r1894948500
##########
datafusion/core/src/dataframe/mod.rs:
##########
@@ -4057,4 +4094,178 @@ mod tests {
Ok(())
}
+
+ // Test issue: https://github.com/apache/datafusion/issues/13873
+ #[tokio::test]
+ async fn write_parquet_with_order() -> Result<()> {
+ let tmp_dir = TempDir::new()?;
+ let schema = Arc::new(Schema::new(vec![
+ Field::new("a", DataType::Int32, true),
+ Field::new("b", DataType::Int32, true),
+ ]));
+
+ let ctx = SessionContext::new();
+ let write_df = ctx.read_batch(RecordBatch::try_new(
+ schema.clone(),
+ vec![
+ Arc::new(Int32Array::from(vec![1, 5, 7, 3, 2])),
+ Arc::new(Int32Array::from(vec![2, 3, 4, 5, 6])),
+ ],
+ )?)?;
+
+ let test_path = tmp_dir.path().join("test.parquet");
+
+ write_df
+ .clone()
+ .write_parquet(
+ test_path.to_str().unwrap(),
+ DataFrameWriteOptions::new()
+ .with_sort_by(vec![col("a").sort(true, true)]),
+ None,
+ )
+ .await?;
+
+ let ctx = SessionContext::new();
+ ctx.register_parquet(
+ "data",
+ test_path.to_str().unwrap(),
+ ParquetReadOptions::default(),
+ )
+ .await?;
+
+ let df = ctx.sql("SELECT * FROM data").await?;
+ let results = df.collect().await?;
+
+ assert_batches_eq!(
+ &[
+ "+---+---+",
Review Comment:
this is a good test 👍
--
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]
