Remove tests from sql_integration that were ported to sqllogictest (apache#4836)

* delete tests duplicated between sqllogictests and aggregates / arrow_typeof

* recomment failing test

* remove typo

* add back in test that's broken in sqllogictest

* remove arrow module

Co-authored-by: Matt <[email protected]>

Author: matthewwillian

datafusion/core/tests/sql/aggregates.rs

@@ -20,24 +20,6 @@ use datafusion::scalar::ScalarValue;
 use datafusion::test_util::scan_empty;
 use datafusion_common::cast::as_float64_array;
 
-#[tokio::test]
-async fn csv_query_avg_multi_batch() -> Result<()> {
-    let ctx = SessionContext::new();
-    register_aggregate_csv(&ctx).await?;
-    let sql = "SELECT avg(c12) FROM aggregate_test_100";
-    let dataframe = ctx.sql(sql).await.unwrap();
-    let results = dataframe.collect().await.unwrap();
-    let batch = &results[0];
-    let column = batch.column(0);
-    let array = as_float64_array(column)?;
-    let actual = array.value(0);
-    let expected = 0.5089725;
-    // Due to float number's accuracy, different batch size will lead to different
-    // answers.
-    assert!((expected - actual).abs() < 0.01);
-    Ok(())
-}
-
 #[tokio::test]
 #[ignore] // https://github.com/apache/arrow-datafusion/issues/3353
 async fn csv_query_approx_count() -> Result<()> {
@@ -120,60 +102,6 @@ async fn csv_query_approx_percentile_cont_with_histogram_bins() -> Result<()> {
     Ok(())
 }
 
-#[tokio::test]
-async fn csv_query_array_agg() -> Result<()> {
-    let ctx = SessionContext::new();
-    register_aggregate_csv(&ctx).await?;
-    let sql =
-        "SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test";
-    let actual = execute_to_batches(&ctx, sql).await;
-    let expected = vec![
-        "+------------------------------------------------------------------+",
-        "| ARRAYAGG(test.c13)                                               |",
-        "+------------------------------------------------------------------+",
-        "| [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm, 0keZ5G8BffGwgF2RwQD59TFzMStxCB] |",
-        "+------------------------------------------------------------------+",
-    ];
-    assert_batches_eq!(expected, &actual);
-    Ok(())
-}
-
-#[tokio::test]
-async fn csv_query_array_agg_empty() -> Result<()> {
-    let ctx = SessionContext::new();
-    register_aggregate_csv(&ctx).await?;
-    let sql =
-        "SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 LIMIT 0) test";
-    let actual = execute_to_batches(&ctx, sql).await;
-    let expected = vec![
-        "+--------------------+",
-        "| ARRAYAGG(test.c13) |",
-        "+--------------------+",
-        "| []                 |",
-        "+--------------------+",
-    ];
-    assert_batches_eq!(expected, &actual);
-    Ok(())
-}
-
-#[tokio::test]
-async fn csv_query_array_agg_one() -> Result<()> {
-    let ctx = SessionContext::new();
-    register_aggregate_csv(&ctx).await?;
-    let sql =
-        "SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 1) test";
-    let actual = execute_to_batches(&ctx, sql).await;
-    let expected = vec![
-        "+----------------------------------+",
-        "| ARRAYAGG(test.c13)               |",
-        "+----------------------------------+",
-        "| [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm] |",
-        "+----------------------------------+",
-    ];
-    assert_batches_eq!(expected, &actual);
-    Ok(())
-}
-
 #[tokio::test]
 async fn csv_query_array_agg_unsupported() -> Result<()> {
     let ctx = SessionContext::new();

datafusion/core/tests/sql/arrow_typeof.rs

@@ -104,7 +104,6 @@ pub mod union;
 pub mod wildcard;
 pub mod window;
 
-pub mod arrow_typeof;
 pub mod decimal;
 pub mod explain;
 pub mod idenfifers;

datafusion/core/tests/sql/mod.rs

@@ -846,26 +846,23 @@ SELECT count(1 + 1)
 ----
 1
 
-# FIX: "CSV Writer does not support List(Field { name: \"item\", data_type: Utf8, nullable: true, dict_id: 0, dict_is_ordered: false, metadata: None }) data type")
 # csv_query_array_agg
-# query T
-# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test
-# ----
-# [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm0keZ5G8BffGwgF2RwQD59TFzMStxCB]
+query T
+SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test
+----
+[0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm, 0keZ5G8BffGwgF2RwQD59TFzMStxCB]
 
-# FIX: see above
 # csv_query_array_agg_empty
-# query I
-# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 LIMIT 0) test
-# ----
-# []
+query I
+SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 LIMIT 0) test
+----
+[]
 
-# FIX: see above
 # csv_query_array_agg_one
-# query I
-# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 1) test
-# ----
-# [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm]
+query I
+SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 1) test
+----
+[0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm]
 
 # csv_query_array_agg_with_overflow
 query IIRIII
@@ -976,6 +973,7 @@ select max(c1) from d_table
 ----
 110.009
 
+# FIX: doesn't check datatype
 # aggregate_decimal_sum
 query R
 select sum(c1) from d_table