From a47e7d9b79f8bb1df054fcb432bf7be4c1762054 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 16:21:46 -0500
Subject: [PATCH 01/19] sqllogictests v0

---
 tests/sqllogictests/.gitignore                |   1 +
 tests/sqllogictests/Cargo.toml                |  12 +
 tests/sqllogictests/README.md                 |  45 +
 tests/sqllogictests/src/main.rs               |  95 ++
 tests/sqllogictests/src/setup.rs              | 184 ++++
 tests/sqllogictests/src/utils.rs              |  23 +
 tests/sqllogictests/test_files/aggregate.slt  | 868 ++++++++++++++++++
 .../sqllogictests/test_files/arrow_typeof.slt |  65 ++
 8 files changed, 1293 insertions(+)
 create mode 100644 tests/sqllogictests/.gitignore
 create mode 100644 tests/sqllogictests/Cargo.toml
 create mode 100644 tests/sqllogictests/README.md
 create mode 100644 tests/sqllogictests/src/main.rs
 create mode 100644 tests/sqllogictests/src/setup.rs
 create mode 100644 tests/sqllogictests/src/utils.rs
 create mode 100644 tests/sqllogictests/test_files/aggregate.slt
 create mode 100644 tests/sqllogictests/test_files/arrow_typeof.slt

diff --git a/tests/sqllogictests/.gitignore b/tests/sqllogictests/.gitignore
new file mode 100644
index 0000000000000..8e5bbf044f1e0
--- /dev/null
+++ b/tests/sqllogictests/.gitignore
@@ -0,0 +1 @@
+*.py
\ No newline at end of file
diff --git a/tests/sqllogictests/Cargo.toml b/tests/sqllogictests/Cargo.toml
new file mode 100644
index 0000000000000..7bdfb9c503456
--- /dev/null
+++ b/tests/sqllogictests/Cargo.toml
@@ -0,0 +1,12 @@
+[package]
+name = "datafusion-sqllogictests"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
+datafusion = { path = "../../datafusion/core" }
+sqllogictest = { git = "https://github.com/risinglightdb/sqllogictest-rs.git", rev = "282a6008f9b2d0b4e9c498fb637c4c03e92ecf43" }
+async-trait = "0.1.58"
diff --git a/tests/sqllogictests/README.md b/tests/sqllogictests/README.md
new file mode 100644
index 0000000000000..7792ddde87b83
--- /dev/null
+++ b/tests/sqllogictests/README.md
@@ -0,0 +1,45 @@
+#### Overview
+
+This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki). We use [sqllogictest-rs](https://github.com/risinglightdb/sqllogictest-rs) as a parser/runner of `.slt` files in `test_files`.
+
+#### Running tests
+
+`cargo run -p datafusion-sqllogictests`
+
+#### Setup
+
+
+#### sqllogictests
+
+> :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki
+
+sqllogictest is a program originally written for SQLite to verify the correctness of SQL queries against the SQLLite engine. The program is engine-agnostic and can parse sqllogictest files (`.slt`), runs queries against an SQL engine and compare the output to the expected output.
+
+Tests in the `.slt` file are a sequence of query record generally starting with `CREATE` statements to populate tables and then further queries to test the populated data (arrow-datafusion exception).
+
+Query records follow the format:
+```sql
+# <test_name>
+query <type_string> <sort_mode> <label>
+<sql_query>
+----
+<expected_result>
+```
+
+- `test_name`: Uniquely identify the test name (arrow-datafusion only)
+- `type_string`: A short string that specifies the number of result columns and the expected datatype of each result column. There is one character in the <type_string> for each result column. The characters codes are "T" for a text result, "I" for an integer result, and "R" for a floating-point result.
+- (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output. 
+- `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@". 
+
+##### Example
+
+```sql
+# group_by_distinct
+query TTI
+SELECT a, b, COUNT(DISTINCT c) FROM my_table GROUP BY a, b ORDER BY a, b
+----
+foo bar 10
+foo baz 5
+foo     4
+        3
+```
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
new file mode 100644
index 0000000000000..3365a043f8a92
--- /dev/null
+++ b/tests/sqllogictests/src/main.rs
@@ -0,0 +1,95 @@
+use async_trait::async_trait;
+use datafusion::arrow::csv::WriterBuilder;
+use datafusion::arrow::record_batch::RecordBatch;
+use datafusion::prelude::SessionContext;
+use std::path::PathBuf;
+
+use sqllogictest::TestError;
+pub type Result<T> = std::result::Result<T, TestError>;
+
+mod setup;
+mod utils;
+
+const TEST_DIRECTORY: &str = "tests/sqllogictests/test_files";
+const TEST_CATEGORIES: [TestCategory; 2] = [TestCategory::Aggregate, TestCategory::ArrowTypeOf];
+
+pub enum TestCategory {
+    Aggregate,
+    ArrowTypeOf,
+}
+
+impl TestCategory {
+    fn as_str(&self) -> &'static str {
+        match self {
+            TestCategory::Aggregate => "Aggregate",
+            TestCategory::ArrowTypeOf => "ArrowTypeOf",
+        }
+    }
+
+    fn test_filename(&self) -> &'static str {
+        match self {
+            TestCategory::Aggregate => "aggregate.slt",
+            TestCategory::ArrowTypeOf => "arrow_typeof.slt"
+        }
+    }
+
+    async fn register_test_tables(&self, ctx: &SessionContext) {
+        println!("[{}] Registering tables", self.as_str());
+        match self {
+            TestCategory::Aggregate => setup::register_aggregate_tables(&ctx).await,
+            TestCategory::ArrowTypeOf => (),
+        }
+    }
+}
+
+pub struct DataFusion {
+    ctx: SessionContext,
+    test_category: TestCategory,
+}
+
+#[async_trait]
+impl sqllogictest::AsyncDB for DataFusion {
+    type Error = TestError;
+
+    async fn run(&mut self, sql: &str) -> Result<String> {
+        println!("[{}] Running query: \"{}\"", self.test_category.as_str(), sql);
+        let result = run_query(&self.ctx, sql).await?;
+        Ok(result)
+    }
+}
+
+#[tokio::main]
+pub async fn main() -> Result<()> {
+
+    for test_category in TEST_CATEGORIES {
+        let filename = PathBuf::from(format!("{}/{}", TEST_DIRECTORY, test_category.test_filename()));
+        let ctx = SessionContext::new();
+        test_category.register_test_tables(&ctx).await;
+
+        let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
+        // TODO: use tester.run_parallel_async()
+        tester.run_file_async(filename).await.unwrap(); 
+    }
+
+    Ok(())
+}
+
+fn format_batches(batches: &[RecordBatch]) -> Result<String> {
+    let mut bytes = vec![];
+    {
+        let builder = WriterBuilder::new().has_headers(false).with_delimiter(b',');
+        let mut writer = builder.build(&mut bytes);
+        for batch in batches {
+            writer.write(batch).unwrap();
+        }
+    }
+
+    let formatted = String::from_utf8(bytes).unwrap().replace(",", " ");
+    Ok(formatted)
+}
+
+async fn run_query(ctx: &SessionContext, sql: impl Into<String>) -> Result<String> {
+    let df = ctx.sql(&sql.into()).await.unwrap();
+    let results: Vec<RecordBatch> = df.collect().await.unwrap();
+    Ok(format_batches(&results)?)
+}
diff --git a/tests/sqllogictests/src/setup.rs b/tests/sqllogictests/src/setup.rs
new file mode 100644
index 0000000000000..2a69853f8661a
--- /dev/null
+++ b/tests/sqllogictests/src/setup.rs
@@ -0,0 +1,184 @@
+use datafusion::{
+    arrow::{
+        array::{
+            ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
+            Int8Array, UInt16Array, UInt32Array, UInt64Array, UInt8Array,
+        },
+        datatypes::{DataType, Field, Schema},
+        record_batch::RecordBatch,
+    },
+    datasource::MemTable,
+    prelude::{CsvReadOptions, SessionContext},
+    test_util,
+};
+use std::sync::Arc;
+
+use crate::utils;
+
+pub async fn register_aggregate_tables(ctx: &SessionContext) {
+    register_aggregate_csv_by_sql(&ctx).await;
+    register_aggregate_test_100(&ctx).await;
+    register_decimal_table(&ctx);
+    register_median_test_tables(&ctx);
+    register_test_data(&ctx);
+}
+
+fn register_median_test_tables(ctx: &SessionContext) {
+    // Register median tables
+    let items: Vec<(&str, DataType, ArrayRef)> = vec![
+        (
+            "i8",
+            DataType::Int8,
+            Arc::new(Int8Array::from(vec![i8::MIN, i8::MIN, 100, i8::MAX])),
+        ),
+        (
+            "i16",
+            DataType::Int16,
+            Arc::new(Int16Array::from(vec![i16::MIN, i16::MIN, 100, i16::MAX])),
+        ),
+        (
+            "i32",
+            DataType::Int32,
+            Arc::new(Int32Array::from(vec![i32::MIN, i32::MIN, 100, i32::MAX])),
+        ),
+        (
+            "i64",
+            DataType::Int64,
+            Arc::new(Int64Array::from(vec![i64::MIN, i64::MIN, 100, i64::MAX])),
+        ),
+        (
+            "u8",
+            DataType::UInt8,
+            Arc::new(UInt8Array::from(vec![u8::MIN, u8::MIN, 100, u8::MAX])),
+        ),
+        (
+            "u16",
+            DataType::UInt16,
+            Arc::new(UInt16Array::from(vec![u16::MIN, u16::MIN, 100, u16::MAX])),
+        ),
+        (
+            "u32",
+            DataType::UInt32,
+            Arc::new(UInt32Array::from(vec![u32::MIN, u32::MIN, 100, u32::MAX])),
+        ),
+        (
+            "u64",
+            DataType::UInt64,
+            Arc::new(UInt64Array::from(vec![u64::MIN, u64::MIN, 100, u64::MAX])),
+        ),
+        (
+            "f32",
+            DataType::Float32,
+            Arc::new(Float32Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
+        ),
+        (
+            "f64",
+            DataType::Float64,
+            Arc::new(Float64Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
+        ),
+        (
+            "f64_nan",
+            DataType::Float64,
+            Arc::new(Float64Array::from(vec![1.1, f64::NAN, f64::NAN, f64::NAN])),
+        ),
+    ];
+
+    for (name, data_type, values) in items {
+        let batch = RecordBatch::try_new(
+            Arc::new(Schema::new(vec![Field::new("a", data_type, false)])),
+            vec![values],
+        )
+        .unwrap();
+        let table_name = &format!("median_{}", name);
+        ctx.register_batch(table_name, batch).unwrap();
+    }
+}
+
+async fn register_aggregate_csv_by_sql(ctx: &SessionContext) {
+    let test_data = datafusion::test_util::arrow_test_data();
+
+    let df = ctx
+        .sql(&format!(
+            "
+    CREATE EXTERNAL TABLE aggregate_test_100_by_sql (
+        c1  VARCHAR NOT NULL,
+        c2  TINYINT NOT NULL,
+        c3  SMALLINT NOT NULL,
+        c4  SMALLINT NOT NULL,
+        c5  INTEGER NOT NULL,
+        c6  BIGINT NOT NULL,
+        c7  SMALLINT NOT NULL,
+        c8  INT NOT NULL,
+        c9  INT UNSIGNED NOT NULL,
+        c10 BIGINT UNSIGNED NOT NULL,
+        c11 FLOAT NOT NULL,
+        c12 DOUBLE NOT NULL,
+        c13 VARCHAR NOT NULL
+    )
+    STORED AS CSV
+    WITH HEADER ROW
+    LOCATION '{}/csv/aggregate_test_100.csv'
+    ",
+            test_data
+        ))
+        .await
+        .expect("Creating dataframe for CREATE EXTERNAL TABLE");
+
+    // Mimic the CLI and execute the resulting plan -- even though it
+    // is effectively a no-op (returns zero rows)
+    let results = df.collect().await.expect("Executing CREATE EXTERNAL TABLE");
+    assert!(
+        results.is_empty(),
+        "Expected no rows from executing CREATE EXTERNAL TABLE"
+    );
+}
+
+fn register_test_data(ctx: &SessionContext) {
+    let schema = Arc::new(Schema::new(vec![
+        Field::new("c1", DataType::Int64, true),
+        Field::new("c2", DataType::Int64, true),
+    ]));
+
+    let data = RecordBatch::try_new(
+        schema.clone(),
+        vec![
+            Arc::new(Int64Array::from(vec![
+                Some(0),
+                Some(1),
+                None,
+                Some(3),
+                Some(3),
+            ])),
+            Arc::new(Int64Array::from(vec![
+                None,
+                Some(1),
+                Some(1),
+                Some(2),
+                Some(2),
+            ])),
+        ],
+    )
+    .unwrap();
+
+    ctx.register_batch("test", data).unwrap();
+}
+
+fn register_decimal_table(ctx: &SessionContext) {
+    let batch_decimal = utils::make_decimal();
+    let schema = batch_decimal.schema();
+    let partitions = vec![vec![batch_decimal]];
+    let provider = Arc::new(MemTable::try_new(schema, partitions).unwrap());
+    ctx.register_table("d_table", provider).unwrap();
+}
+
+async fn register_aggregate_test_100(ctx: &SessionContext) {
+    let test_data = datafusion::test_util::arrow_test_data();
+    let schema = test_util::aggr_test_schema();
+    ctx.register_csv(
+        "aggregate_test_100",
+        &format!("{}/csv/aggregate_test_100.csv", test_data),
+        CsvReadOptions::new().schema(&schema),
+    )
+    .await
+    .unwrap();
+}
diff --git a/tests/sqllogictests/src/utils.rs b/tests/sqllogictests/src/utils.rs
new file mode 100644
index 0000000000000..9e3cd786e60d1
--- /dev/null
+++ b/tests/sqllogictests/src/utils.rs
@@ -0,0 +1,23 @@
+use datafusion::arrow::{
+    array::{Array, Decimal128Builder},
+    datatypes::{Field, Schema},
+    record_batch::RecordBatch,
+};
+use std::sync::Arc;
+
+// TODO: move this to datafusion::test_utils?
+pub fn make_decimal() -> RecordBatch {
+    let mut decimal_builder = Decimal128Builder::with_capacity(20);
+    for i in 110000..110010 {
+        decimal_builder.append_value(i as i128);
+    }
+    for i in 100000..100010 {
+        decimal_builder.append_value(-i as i128);
+    }
+    let array = decimal_builder
+        .finish()
+        .with_precision_and_scale(10, 3)
+        .unwrap();
+    let schema = Schema::new(vec![Field::new("c1", array.data_type().clone(), true)]);
+    RecordBatch::try_new(Arc::new(schema), vec![Arc::new(array)]).unwrap()
+}
diff --git a/tests/sqllogictests/test_files/aggregate.slt b/tests/sqllogictests/test_files/aggregate.slt
new file mode 100644
index 0000000000000..8cb82923a5810
--- /dev/null
+++ b/tests/sqllogictests/test_files/aggregate.slt
@@ -0,0 +1,868 @@
+# FIX: custom absolute values
+# csv_query_avg_multi_batch
+
+# csv_query_avg
+query R
+SELECT avg(c12) FROM aggregate_test_100
+----
+0.5089725099127211
+
+# csv_query_covariance_1
+query R
+SELECT covar_pop(c2, c12) FROM aggregate_test_100
+----
+-0.07916932235380847
+
+# csv_query_covariance_2
+query R
+SELECT covar(c2, c12) FROM aggregate_test_100
+----
+-0.07996901247859442
+
+# csv_query_correlation
+query R
+SELECT corr(c2, c12) FROM aggregate_test_100
+----
+-0.19064544190576607
+
+# csv_query_variance_1
+query R
+SELECT var_pop(c2) FROM aggregate_test_100
+----
+1.8675
+
+# original: 26156334342021890000000000000000000000
+# csv_query_variance_2
+query R
+SELECT var_pop(c6) FROM aggregate_test_100
+----
+2.615633434202189e37
+
+# csv_query_variance_3
+query R
+SELECT var_pop(c12) FROM aggregate_test_100
+----
+0.09234223721582163
+
+# csv_query_variance_4
+query R
+SELECT var(c2) FROM aggregate_test_100
+----
+1.8863636363636365
+
+# csv_query_variance_5
+query R
+SELECT var_samp(c2) FROM aggregate_test_100
+----
+1.8863636363636365
+
+# csv_query_stddev_1
+query R
+SELECT stddev_pop(c2) FROM aggregate_test_100
+----
+1.3665650368716449
+
+# original: 5114326382039172000
+# csv_query_stddev_2
+query R 
+SELECT stddev_pop(c6) FROM aggregate_test_100
+----
+5.114326382039172e18
+
+# csv_query_stddev_3
+query R
+SELECT stddev_pop(c12) FROM aggregate_test_100
+----
+0.30387865541334363
+
+# csv_query_stddev_4
+query R
+SELECT stddev(c12) FROM aggregate_test_100
+----
+0.3054095399405338
+
+# csv_query_stddev_5
+query R
+SELECT stddev_samp(c12) FROM aggregate_test_100
+----
+0.3054095399405338
+
+# csv_query_stddev_6
+query R
+select stddev(sq.column1) from (values (1.1), (2.0), (3.0)) as sq
+----
+0.9504384952922168
+
+# csv_query_approx_median_1
+query I
+SELECT approx_median(c2) FROM aggregate_test_100
+----
+3
+
+# csv_query_approx_median_2
+query I
+SELECT approx_median(c6) FROM aggregate_test_100
+----
+1146409980542786560
+
+# csv_query_approx_median_3
+query R
+SELECT approx_median(c12) FROM aggregate_test_100
+----
+0.5550065410522981
+
+# csv_query_median_1
+query I
+SELECT median(c2) FROM aggregate_test_100
+----
+3
+
+# csv_query_median_2
+query I
+SELECT median(c6) FROM aggregate_test_100
+----
+1125553990140691277
+
+# csv_query_median_3
+query R
+SELECT median(c12) FROM aggregate_test_100
+----
+0.5513900544385053
+
+# median_i8
+query I
+SELECT median(a) FROM median_i8
+----
+-14
+
+# median_i16
+query I
+SELECT median(a) FROM median_i16
+----
+-16334
+
+# median_i32
+query I
+SELECT median(a) FROM median_i32
+----
+-1073741774
+
+# TODO: FIX - numbers are off?
+# median_i64
+# query I
+# SELECT median(a) FROM median_i64
+# ----
+# -4611686018427388000
+
+# median_u8
+query I
+SELECT median(a) FROM median_u8
+----
+50
+
+# median_u16
+query I
+SELECT median(a) FROM median_u16
+----
+50
+
+# median_u32
+query I
+SELECT median(a) FROM median_u32
+----
+50
+
+# median_u64
+query I
+SELECT median(a) FROM median_u64
+----
+50
+
+# median_f32
+query R
+SELECT median(a) FROM median_f32
+----
+3.3
+
+# median_f64
+query R
+SELECT median(a) FROM median_f64
+----
+3.3
+
+# median_f64_nan
+query T
+SELECT median(a) FROM median_f64_nan
+----
+NaN
+
+# approx_median_f64_nan
+query T
+SELECT approx_median(a) FROM median_f64_nan
+----
+NaN
+
+# csv_query_external_table_count
+query I
+SELECT COUNT(c12) FROM aggregate_test_100
+----
+100
+
+# csv_query_external_table_sum
+query II
+SELECT SUM(CAST(c7 AS BIGINT)), SUM(CAST(c8 AS BIGINT)) FROM aggregate_test_100
+----
+13060 3017641
+
+# csv_query_count
+query I
+SELECT count(c12) FROM aggregate_test_100
+----
+100
+
+# csv_query_count_distinct
+query I
+SELECT count(distinct c2) FROM aggregate_test_100
+----
+5
+
+# csv_query_count_distinct_expr
+query I
+SELECT count(distinct c2 % 2) FROM aggregate_test_100
+----
+2
+
+# csv_query_count_star
+query I
+SELECT COUNT(*) FROM aggregate_test_100
+----
+100
+
+# csv_query_count_literal
+query I
+SELECT COUNT(2) FROM aggregate_test_100
+----
+100
+
+# csv_query_approx_count
+# FIX: https://github.com/apache/arrow-datafusion/issues/3353
+# query II
+# SELECT approx_distinct(c9) AS count_c9, approx_distinct(cast(c9 as varchar)) count_c9_str FROM aggregate_test_100
+# ----
+# 100 99
+
+# csv_query_approx_count_dupe_expr_aliased
+query II
+SELECT approx_distinct(c9) AS a, approx_distinct(c9) AS b FROM aggregate_test_100
+----
+100 100
+
+# TODO: csv_query_approx_percentile_cont
+
+# TODO: fix decimal places
+# csv_query_cube_avg
+# query TIR
+# SELECT c1, c2, AVG(c3) FROM aggregate_test_100_by_sql GROUP BY CUBE (c1, c2) ORDER BY c1, c2
+# ----
+# a 1 -17.6
+# a 2 -15.333333333333334
+# a 3 -4.5
+# a 4 -32
+# a 5 -32
+# a  -18.333333333333332
+# b 1 31.666666666666668
+# b 2 25.5
+# b 3 -42
+# b 4 -44.6
+# b 5 -0.2
+# b  -5.842105263157895
+# c 1 47.5
+# c 2 -55.57142857142857
+# c 3 47.5
+# c 4 -10.75
+# c 5 12
+# c  -1.3333333333333333
+# d 1 -8.142857142857142
+# d 2 109.33333333333333
+# d 3 41.333333333333336
+# d 4 54
+# d 5 -49.5
+# d  25.444444444444443
+# e 1 75.66666666666667
+# e 2 37.8
+# e 3 48
+# e 4 37.285714285714285
+# e 5 -11
+# e  40.333333333333336
+#  1 16.681818181818183
+#  2 8.363636363636363
+#  3 20.789473684210527
+#  4 1.2608695652173914
+#  5 -13.857142857142858
+#    7.81
+
+# TODO: fix decimal places
+# csv_query_rollup_avg
+# query IIII
+# SELECT c1, c2, c3, AVG(c4) FROM aggregate_test_100_by_sql GROUP BY ROLLUP (c1, c2, c3) ORDER BY c1, c2, c3
+# ----
+# a 1 -85 -15154
+# a 1 -56 8692
+# a 1 -25 15295
+# a 1 -5 12636
+# a 1 83 -14704
+# a 1  1353
+# a 2 -48 -18025
+# a 2 -43 13080
+# a 2 45 15673
+# a 2  3576
+# a 3 -72 -11122
+# a 3 -12 -9168
+# a 3 13 22338.5
+# a 3 14 28162
+# a 3 17 -22796
+# a 3  4958.833333333333
+# a 4 -101 11640
+# a 4 -54 -2376
+# a 4 -38 20744
+# a 4 65 -28462
+# a 4  386.5
+# a 5 -101 -12484
+# a 5 -31 -12907
+# a 5 36 -16974
+# a 5  -14121.666666666666
+# a   306.04761904761904
+# b 1 12 7652
+# b 1 29 -18218
+# b 1 54 -18410
+# b 1  -9658.666666666666
+# b 2 -60 -21739
+# b 2 31 23127
+# b 2 63 21456
+# b 2 68 15874
+# b 2  9679.5
+# b 3 -101 -13217
+# b 3 17 14457
+# b 3  620
+# b 4 -117 19316
+# b 4 -111 -1967
+# b 4 -59 25286
+# b 4 17 -28070
+# b 4 47 20690
+# b 4  7051
+# b 5 -82 22080
+# b 5 -44 15788
+# b 5 -5 24896
+# b 5 62 16337
+# b 5 68 21576
+# b 5  20135.4
+# b   7732.315789473684
+# c 1 -24 -24085
+# c 1 41 -4667
+# c 1 70 27752
+# c 1 103 -22186
+# c 1  -5796.5
+# c 2 -117 -30187
+# c 2 -107 -2904
+# c 2 -106 -1114
+# c 2 -60 -16312
+# c 2 -29 25305
+# c 2 1 18109
+# c 2 29 -3855
+# c 2  -1565.4285714285713
+# c 3 -2 -18655
+# c 3 22 13741
+# c 3 73 -9565
+# c 3 97 29106
+# c 3  3656.75
+# c 4 -90 -2935
+# c 4 -79 5281
+# c 4 3 -30508
+# c 4 123 16620
+# c 4  -2885.5
+# c 5 -94 -15880
+# c 5 118 19208
+# c 5  1664
+# c   -1320.5238095238096
+# d 1 -99 5613
+# d 1 -98 13630
+# d 1 -72 25590
+# d 1 -8 27138
+# d 1 38 18384
+# d 1 57 28781
+# d 1 125 31106
+# d 1  21463.14285714286
+# d 2 93 -12642
+# d 2 113 3917
+# d 2 122 10130
+# d 2  468.3333333333333
+# d 3 -76 8809
+# d 3 77 15091
+# d 3 123 29533
+# d 3  17811
+# d 4 5 -7688
+# d 4 55 -1471
+# d 4 102 -24558
+# d 4  -11239
+# d 5 -59 2045
+# d 5 -40 22614
+# d 5  12329.5
+# d   10890.111111111111
+# e 1 36 -21481
+# e 1 71 -5479
+# e 1 120 10837
+# e 1  -5374.333333333333
+# e 2 -61 -2888
+# e 2 49 24495
+# e 2 52 5666
+# e 2 97 18167
+# e 2  10221.2
+# e 3 -95 13611
+# e 3 71 194
+# e 3 104 -25136
+# e 3 112 -6823
+# e 3  -4538.5
+# e 4 -56 -31500
+# e 4 -53 13788
+# e 4 30 -16110
+# e 4 73 -22501
+# e 4 74 -12612
+# e 4 96 -30336
+# e 4 97 -13181
+# e 4  -16064.57142857143
+# e 5 -86 32514
+# e 5 64 -26526
+# e 5  2994
+# e   -4268.333333333333
+#    2319.97
+
+# csv_query_approx_percentile_cont_with_weight
+query II
+SELECT c1, approx_percentile_cont(c3, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_approx_percentile_cont_with_weight (2)
+query II
+SELECT c1, approx_percentile_cont_with_weight(c3, 1, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_approx_percentile_cont_with_histogram_bins
+query II
+SELECT c1, approx_percentile_cont(c3, 0.95, 200) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY a.c1, b.c1 ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+
+# csv_query_cube_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY CUBE (a.c1, b.c1) ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+a   6000
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+b   6200
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+c   5600
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+d   4400
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+e   6300
+  a 5985
+  b 5415
+  c 5985
+  d 5130
+  e 5985
+    28500
+
+# csv_query_cube_distinct_count
+query III
+SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY CUBE (c1,c2) ORDER BY c1,c2
+----
+a 1 5
+a 2 3
+a 3 5
+a 4 4
+a 5 3
+a   19
+b 1 3
+b 2 4
+b 3 2
+b 4 5
+b 5 5
+b   17
+c 1 4
+c 2 7
+c 3 4
+c 4 4
+c 5 2
+c   21
+d 1 7
+d 2 3
+d 3 3
+d 4 3
+d 5 2
+d   18
+e 1 3
+e 2 4
+e 3 4
+e 4 7
+e 5 2
+e   18
+  1 22
+  2 20
+  3 17
+  4 23
+  5 14
+    80
+
+# csv_query_rollup_distinct_count
+query III
+SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY ROLLUP (c1,c2) ORDER BY c1,c2
+----
+a 1 5
+a 2 3
+a 3 5
+a 4 4
+a 5 3
+a   19
+b 1 3
+b 2 4
+b 3 2
+b 4 5
+b 5 5
+b   17
+c 1 4
+c 2 7
+c 3 4
+c 4 4
+c 5 2
+c   21
+d 1 7
+d 2 3
+d 3 3
+d 4 3
+d 5 2
+d   18
+e 1 3
+e 2 4
+e 3 4
+e 4 7
+e 5 2
+e  18
+   80
+
+# csv_query_rollup_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY ROLLUP (a.c1, b.c1) ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+a   6000
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+b   6200
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+c   5600
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+d   4400
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+e   6300
+    28500
+
+# query_count_without_from
+query I
+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 I
+# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test
+# ----
+# [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm0keZ5G8BffGwgF2RwQD59TFzMStxCB]
+
+# FIX: see above
+# csv_query_array_agg_empty
+# 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]
+
+# FIX: Decimal error
+# csv_query_array_agg_with_overflow
+# query IIIIII
+# select c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by c2 order by c2
+# ----
+# 1 367 16.681818181818183 125 -99 22
+# 2 184 8.363636363636363 122 -117 22
+# 3 395 20.789473684210527 123 -101 19
+# 4 29 1.2608695652173914 123 -117 23
+# 5 -194 -13.857142857142858 118 -101 14
+
+# TODO: csv_query_array_agg_unsupported
+
+# FIX: Decimal error
+# csv_query_array_cube_agg_with_overflow
+# query IIIIIII
+# select c1, c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by CUBE (c1,c2) order by c1, c2
+# ----
+# a 1 -88 -17.6 83 -85 5
+# a 2 -46 -15.333333333333334 45 -48 3
+# a 3 -27 -4.5 17 -72 6
+# a 4 -128 -32 65 -101 4
+# a 5 -96 -32 36 -101 3
+# a  -385 -18.333333333333332 83 -101 21
+# b 1 95 31.666666666666668 54 12 3
+# b 2 102 25.5 68 -60 4
+# b 3 -84 -42 17 -101 2
+# b 4 -223 -44.6 47 -117 5
+# b 5 -1 -0.2 68 -82 5
+# b  -111 -5.842105263157895 68 -117 19
+# c 1 190 47.5 103 -24 4
+# c 2 -389 -55.57142857142857 29 -117 7
+# c 3 190 47.5 97 -2 4
+# c 4 -43 -10.75 123 -90 4
+# c 5 24 12 118 -94 2
+# c  -28 -1.3333333333333333 123 -117 21
+# d 1 -57 -8.142857142857142 125 -99 7
+# d 2 328 109.33333333333333 122 93 3
+# d 3 124 41.333333333333336 123 -76 3
+# d 4 162 54 102 5 3
+# d 5 -99 -49.5 -40 -59 2
+# d  458 25.444444444444443 125 -99 18
+# e 1 227 75.66666666666667 120 36 3
+# e 2 189 37.8 97 -61 5
+# e 3 192 48 112 -95 4
+# e 4 261 37.285714285714285 97 -56 7
+# e 5 -22 -11 64 -86 2
+# e  847 40.333333333333336 120 -95 21
+#  1 367 16.681818181818183 125 -99 22
+#  2 184 8.363636363636363 122 -117 22
+#  3 395 20.789473684210527 123 -101 19
+#  4 29 1.2608695652173914 123 -117 23
+#  5 -194 -13.857142857142858 118 -101 14
+#   781 7.81 125 -117 100
+
+# TODO: csv_query_array_agg_distinct
+
+# TODO: aggregate_timestamps_sum
+
+# TODO: aggregate_timestamps_count
+
+# TODO: aggregate_timestamps_min
+
+# TODO: aggregate_timestamps_max
+
+# TODO: aggregate_times_sum
+
+# TODO: aggregate_times_count
+
+# TODO: aggregate_times_min
+
+# TODO: aggregate_times_max
+
+# TODO: aggregate_timestamps_avg
+
+# aggregate_time_min_and_max
+query II
+select min(t), max(t) from  (select '00:00:00' as t union select '00:00:01' union select '00:00:02')
+----
+00:00:00 00:00:02
+
+# aggregate_decimal_min
+query I
+select min(c1) from d_table
+----
+-100.009
+
+# aggregate_decimal_max
+query I
+select max(c1) from d_table
+----
+110.009
+
+query I
+select sum(c1) from d_table
+----
+100.000
+
+# FIX: doesn't check datatype
+# aggregate_decimal_avg
+query I
+select avg(c1) from d_table
+----
+5.0000000
+
+# FIX: different test table
+# aggregate
+# query I
+# SELECT SUM(c1), SUM(c2) FROM test
+# ----
+# 60 220
+
+# TODO: aggregate_empty
+
+# TODO: aggregate_avg
+
+# TODO: aggregate_max
+
+# TODO: aggregate_min
+
+# TODO: aggregate_grouped
+
+# TODO: aggregate_grouped_avg
+
+# TODO: aggregate_grouped_empty
+
+# TODO: aggregate_grouped_max
+
+# TODO: aggregate_grouped_min
+
+# TODO: aggregate_avg_add
+
+# TODO: case_sensitive_identifiers_aggregates
+
+# TODO: count_basic
+
+# TODO: count_partitioned
+
+# TODO: count_aggregated
+
+# TODO: count_aggregated_cube
+
+# TODO: simple_avg
+
+# TODO: simple_mean
+
+# TOOD: bottom 2 require pre-populated data
+# query_sum_distinct
+query II
+SELECT AVG(c1), SUM(DISTINCT c2) FROM test
+----
+1.75 3
+
+# # query_count_distinct
+query I
+SELECT COUNT(DISTINCT c1) FROM test
+----
+3
+
+# TODO: count_distinct_integers_aggregated_single_partition
+
+# TODO: count_distinct_integers_aggregated_multiple_partitions
+
+# TODO: aggregate_with_alias
+
+
+# FIX: CSV Writer error
+# array_agg_zero
+# query I
+# SELECT ARRAY_AGG([])
+# ----
+# []
+
+# FIX: CSV Writer error
+# array_agg_one
+# query I
+# SELECT ARRAY_AGG([1])
+# ----
+# [[1]]
+
+# test_approx_percentile_cont_decimal_support
+query II
+SELECT c1, approx_percentile_cont(c2, cast(0.85 as decimal(10,2))) apc FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 4
+b 5
+c 4
+d 4
+e 4
\ No newline at end of file
diff --git a/tests/sqllogictests/test_files/arrow_typeof.slt b/tests/sqllogictests/test_files/arrow_typeof.slt
new file mode 100644
index 0000000000000..f8baaff18dc86
--- /dev/null
+++ b/tests/sqllogictests/test_files/arrow_typeof.slt
@@ -0,0 +1,65 @@
+# arrow_typeof_null
+query T
+SELECT arrow_typeof(null)
+----
+Null
+
+# arrow_typeof_boolean
+query T
+SELECT arrow_typeof(true)
+----
+Boolean
+
+# arrow_typeof_i64
+query T
+SELECT arrow_typeof(1)
+----
+Int64
+
+# arrow_typeof_i32
+query T
+SELECT arrow_typeof(1::int)
+----
+Int32
+
+# arrow_typeof_f64
+query T
+SELECT arrow_typeof(1.0)
+----
+Float64
+
+# arrow_typeof_f32
+query T
+SELECT arrow_typeof(1.0::float)
+----
+Float32
+
+# arrow_typeof_decimal
+# query T
+# SELECT arrow_typeof(1::Decimal)
+# ----
+# Decimal128(38, 10)
+
+# # arrow_typeof_timestamp
+# query T
+# SELECT arrow_typeof(now()::timestamp)
+# ----
+# Timestamp(Nanosecond, None)
+
+# # arrow_typeof_timestamp_utc
+# query T
+# SELECT arrow_typeof(now())
+# ----
+# Timestamp(Nanosecond, Some(\"+00:00\"))
+
+# # arrow_typeof_timestamp_date32(
+# query T
+# SELECT arrow_typeof(now()::date)
+# ----
+# Date32
+
+# # arrow_typeof_utf8
+# query T
+# SELECT arrow_typeof('1')
+# ----
+# Utf8

From e01653e6259710245ac0ec75404694cd2cba29ce Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 16:30:32 -0500
Subject: [PATCH 02/19] Add CI workflow

---
 .github/workflows/rust.yml      | 28 ++++++++++++++++++++++++++++
 Cargo.toml                      |  1 +
 tests/sqllogictests/src/main.rs | 20 ++++++++++++++------
 3 files changed, 43 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index cdde8aa64c8da..f5e84f3bcf065 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -517,3 +517,31 @@ jobs:
           # If you encounter an error, run './dev/update_config_docs.sh' and commit
           ./dev/update_config_docs.sh
           git diff --exit-code
+
+  # Run sqllogictests
+  sql-logic-tests:
+    name: run sqllogictests
+    needs: [linux-build-lib]
+    runs-on: ubuntu-latest
+    container:
+      image: amd64/rust
+      env:
+        # Disable full debug symbol generation to speed up CI build and keep memory down
+        # "1" means line tables only, which is useful for panic tracebacks.
+        RUSTFLAGS: "-C debuginfo=1"
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          submodules: true
+      - name: Cache Cargo
+        uses: actions/cache@v3
+        with:
+          path: /github/home/.cargo
+          # this key equals the ones on `linux-build-lib` for re-use
+          key: cargo-cache-
+      - name: Setup Rust toolchain
+        uses: ./.github/actions/setup-builder
+        with:
+          rust-version: stable
+      - name: Run sqllogictests
+        run: cargo run -p datafusion-sqllogictests
\ No newline at end of file
diff --git a/Cargo.toml b/Cargo.toml
index 1ab431ea316a9..f39152db232ca 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -31,6 +31,7 @@ members = [
     "test-utils",
     "parquet-test-utils",
     "benchmarks",
+    "tests/sqllogictests",
 ]
 
 [profile.release]
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
index 3365a043f8a92..61f20c64a6231 100644
--- a/tests/sqllogictests/src/main.rs
+++ b/tests/sqllogictests/src/main.rs
@@ -11,7 +11,8 @@ mod setup;
 mod utils;
 
 const TEST_DIRECTORY: &str = "tests/sqllogictests/test_files";
-const TEST_CATEGORIES: [TestCategory; 2] = [TestCategory::Aggregate, TestCategory::ArrowTypeOf];
+const TEST_CATEGORIES: [TestCategory; 2] =
+    [TestCategory::Aggregate, TestCategory::ArrowTypeOf];
 
 pub enum TestCategory {
     Aggregate,
@@ -29,7 +30,7 @@ impl TestCategory {
     fn test_filename(&self) -> &'static str {
         match self {
             TestCategory::Aggregate => "aggregate.slt",
-            TestCategory::ArrowTypeOf => "arrow_typeof.slt"
+            TestCategory::ArrowTypeOf => "arrow_typeof.slt",
         }
     }
 
@@ -52,7 +53,11 @@ impl sqllogictest::AsyncDB for DataFusion {
     type Error = TestError;
 
     async fn run(&mut self, sql: &str) -> Result<String> {
-        println!("[{}] Running query: \"{}\"", self.test_category.as_str(), sql);
+        println!(
+            "[{}] Running query: \"{}\"",
+            self.test_category.as_str(),
+            sql
+        );
         let result = run_query(&self.ctx, sql).await?;
         Ok(result)
     }
@@ -60,15 +65,18 @@ impl sqllogictest::AsyncDB for DataFusion {
 
 #[tokio::main]
 pub async fn main() -> Result<()> {
-
     for test_category in TEST_CATEGORIES {
-        let filename = PathBuf::from(format!("{}/{}", TEST_DIRECTORY, test_category.test_filename()));
+        let filename = PathBuf::from(format!(
+            "{}/{}",
+            TEST_DIRECTORY,
+            test_category.test_filename()
+        ));
         let ctx = SessionContext::new();
         test_category.register_test_tables(&ctx).await;
 
         let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
         // TODO: use tester.run_parallel_async()
-        tester.run_file_async(filename).await.unwrap(); 
+        tester.run_file_async(filename).await.unwrap();
     }
 
     Ok(())

From 3d654b01262e722a49bc99212abcfefb9d70196f Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 16:32:58 -0500
Subject: [PATCH 03/19] Add license

---
 tests/sqllogictests/Cargo.toml   | 21 +++++++++++++++++++--
 tests/sqllogictests/src/main.rs  | 17 +++++++++++++++++
 tests/sqllogictests/src/setup.rs | 17 +++++++++++++++++
 tests/sqllogictests/src/utils.rs | 17 +++++++++++++++++
 4 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/tests/sqllogictests/Cargo.toml b/tests/sqllogictests/Cargo.toml
index 7bdfb9c503456..19bd68cf879be 100644
--- a/tests/sqllogictests/Cargo.toml
+++ b/tests/sqllogictests/Cargo.toml
@@ -1,12 +1,29 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http:#www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
 [package]
 name = "datafusion-sqllogictests"
 version = "0.1.0"
 edition = "2021"
 
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+# See more keys and their definitions at https:#doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
 tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
 datafusion = { path = "../../datafusion/core" }
-sqllogictest = { git = "https://github.com/risinglightdb/sqllogictest-rs.git", rev = "282a6008f9b2d0b4e9c498fb637c4c03e92ecf43" }
 async-trait = "0.1.58"
+sqllogictest = "0.8.0"
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
index 61f20c64a6231..3e43cc13c53bc 100644
--- a/tests/sqllogictests/src/main.rs
+++ b/tests/sqllogictests/src/main.rs
@@ -1,3 +1,20 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
 use async_trait::async_trait;
 use datafusion::arrow::csv::WriterBuilder;
 use datafusion::arrow::record_batch::RecordBatch;
diff --git a/tests/sqllogictests/src/setup.rs b/tests/sqllogictests/src/setup.rs
index 2a69853f8661a..8c90c519e8bb9 100644
--- a/tests/sqllogictests/src/setup.rs
+++ b/tests/sqllogictests/src/setup.rs
@@ -1,3 +1,20 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
 use datafusion::{
     arrow::{
         array::{
diff --git a/tests/sqllogictests/src/utils.rs b/tests/sqllogictests/src/utils.rs
index 9e3cd786e60d1..4d064a76e2ad2 100644
--- a/tests/sqllogictests/src/utils.rs
+++ b/tests/sqllogictests/src/utils.rs
@@ -1,3 +1,20 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
 use datafusion::arrow::{
     array::{Array, Decimal128Builder},
     datatypes::{Field, Schema},

From 1c01f92db168a98894a0e057c37872c0ce9defca Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 16:37:42 -0500
Subject: [PATCH 04/19] Run linter + remove submodule requirement in CI

---
 .github/workflows/rust.yml       |  2 --
 tests/sqllogictests/Cargo.toml   |  4 ++--
 tests/sqllogictests/src/main.rs  |  7 ++++---
 tests/sqllogictests/src/setup.rs | 12 ++++++------
 4 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index f5e84f3bcf065..7d2d308dbbb7d 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -531,8 +531,6 @@ jobs:
         RUSTFLAGS: "-C debuginfo=1"
     steps:
       - uses: actions/checkout@v3
-        with:
-          submodules: true
       - name: Cache Cargo
         uses: actions/cache@v3
         with:
diff --git a/tests/sqllogictests/Cargo.toml b/tests/sqllogictests/Cargo.toml
index 19bd68cf879be..f4777147ea123 100644
--- a/tests/sqllogictests/Cargo.toml
+++ b/tests/sqllogictests/Cargo.toml
@@ -23,7 +23,7 @@ edition = "2021"
 # See more keys and their definitions at https:#doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
-datafusion = { path = "../../datafusion/core" }
 async-trait = "0.1.58"
+datafusion = { path = "../../datafusion/core" }
 sqllogictest = "0.8.0"
+tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
index 3e43cc13c53bc..928905876d3be 100644
--- a/tests/sqllogictests/src/main.rs
+++ b/tests/sqllogictests/src/main.rs
@@ -54,7 +54,7 @@ impl TestCategory {
     async fn register_test_tables(&self, ctx: &SessionContext) {
         println!("[{}] Registering tables", self.as_str());
         match self {
-            TestCategory::Aggregate => setup::register_aggregate_tables(&ctx).await,
+            TestCategory::Aggregate => setup::register_aggregate_tables(ctx).await,
             TestCategory::ArrowTypeOf => (),
         }
     }
@@ -109,12 +109,13 @@ fn format_batches(batches: &[RecordBatch]) -> Result<String> {
         }
     }
 
-    let formatted = String::from_utf8(bytes).unwrap().replace(",", " ");
+    let formatted = String::from_utf8(bytes).unwrap().replace(',', " ");
     Ok(formatted)
 }
 
 async fn run_query(ctx: &SessionContext, sql: impl Into<String>) -> Result<String> {
     let df = ctx.sql(&sql.into()).await.unwrap();
     let results: Vec<RecordBatch> = df.collect().await.unwrap();
-    Ok(format_batches(&results)?)
+    let formatted_batches = format_batches(&results)?;
+    Ok(formatted_batches)
 }
diff --git a/tests/sqllogictests/src/setup.rs b/tests/sqllogictests/src/setup.rs
index 8c90c519e8bb9..1e38d48608eb0 100644
--- a/tests/sqllogictests/src/setup.rs
+++ b/tests/sqllogictests/src/setup.rs
@@ -33,11 +33,11 @@ use std::sync::Arc;
 use crate::utils;
 
 pub async fn register_aggregate_tables(ctx: &SessionContext) {
-    register_aggregate_csv_by_sql(&ctx).await;
-    register_aggregate_test_100(&ctx).await;
-    register_decimal_table(&ctx);
-    register_median_test_tables(&ctx);
-    register_test_data(&ctx);
+    register_aggregate_csv_by_sql(ctx).await;
+    register_aggregate_test_100(ctx).await;
+    register_decimal_table(ctx);
+    register_median_test_tables(ctx);
+    register_test_data(ctx);
 }
 
 fn register_median_test_tables(ctx: &SessionContext) {
@@ -157,7 +157,7 @@ fn register_test_data(ctx: &SessionContext) {
     ]));
 
     let data = RecordBatch::try_new(
-        schema.clone(),
+        schema,
         vec![
             Arc::new(Int64Array::from(vec![
                 Some(0),

From a737c2fffa91fa40e60208510f2f0032bd3cf647 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 16:59:02 -0500
Subject: [PATCH 05/19] Add submodules back

---
 .github/workflows/rust.yml |  2 ++
 filtered_rat.txt           |  0
 rat.txt                    | 44 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 46 insertions(+)
 create mode 100644 filtered_rat.txt
 create mode 100644 rat.txt

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index 7d2d308dbbb7d..f5e84f3bcf065 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -531,6 +531,8 @@ jobs:
         RUSTFLAGS: "-C debuginfo=1"
     steps:
       - uses: actions/checkout@v3
+        with:
+          submodules: true
       - name: Cache Cargo
         uses: actions/cache@v3
         with:
diff --git a/filtered_rat.txt b/filtered_rat.txt
new file mode 100644
index 0000000000000..e69de29bb2d1d
diff --git a/rat.txt b/rat.txt
new file mode 100644
index 0000000000000..277ef6426afbe
--- /dev/null
+++ b/rat.txt
@@ -0,0 +1,44 @@
+usage: java rat.report [options] [DIR|TARBALL]
+Options
+ -a,--addLicence                Add the default license header to any file
+                                with an unknown license that is not in the
+                                exclusion list. By default new files will
+                                be created with the license header, to
+                                force the modification of existing files
+                                use the --force option.
+ -A,--addLicense                Add the default license header to any file
+                                with an unknown license that is not in the
+                                exclusion list. By default new files will
+                                be created with the license header, to
+                                force the modification of existing files
+                                use the --force option.
+ -c,--copyright <arg>           The copyright message to use in the
+                                license headers, usually in the form of
+                                "Copyright 2008 Foo"
+ -d,--dir                       Used to indicate source when using
+                                --exclude
+ -e,--exclude <expression>      Excludes files matching wildcard
+                                <expression>. Note that --dir is required
+                                when using this parameter. Allows multiple
+                                arguments.
+ -E,--exclude-file <fileName>   Excludes files matching regular expression
+                                in <file> Note that --dir is required when
+                                using this parameter.
+ -f,--force                     Forces any changes in files to be written
+                                directly to the source files (i.e. new
+                                files are not created)
+ -h,--help                      Print help for the Rat command line
+                                interface and exit
+ -s,--stylesheet <arg>          XSLT stylesheet to use when creating the
+                                report.  Not compatible with -x
+ -x,--xml                       Output the report in raw XML format.  Not
+                                compatible with -s
+
+NOTE:
+Rat is really little more than a grep ATM
+Rat is also rather memory hungry ATM
+Rat is very basic ATM
+Rat highlights possible issues
+Rat reports require interpretation
+Rat often requires some tuning before it runs well against a project
+Rat relies on heuristics: it may miss issues

From 96bd42e0d5879470dc71281c297eb103115ca300 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Sun, 27 Nov 2022 17:01:12 -0500
Subject: [PATCH 06/19] Remove files

---
 filtered_rat.txt |  0
 rat.txt          | 44 --------------------------------------------
 2 files changed, 44 deletions(-)
 delete mode 100644 filtered_rat.txt
 delete mode 100644 rat.txt

diff --git a/filtered_rat.txt b/filtered_rat.txt
deleted file mode 100644
index e69de29bb2d1d..0000000000000
diff --git a/rat.txt b/rat.txt
deleted file mode 100644
index 277ef6426afbe..0000000000000
--- a/rat.txt
+++ /dev/null
@@ -1,44 +0,0 @@
-usage: java rat.report [options] [DIR|TARBALL]
-Options
- -a,--addLicence                Add the default license header to any file
-                                with an unknown license that is not in the
-                                exclusion list. By default new files will
-                                be created with the license header, to
-                                force the modification of existing files
-                                use the --force option.
- -A,--addLicense                Add the default license header to any file
-                                with an unknown license that is not in the
-                                exclusion list. By default new files will
-                                be created with the license header, to
-                                force the modification of existing files
-                                use the --force option.
- -c,--copyright <arg>           The copyright message to use in the
-                                license headers, usually in the form of
-                                "Copyright 2008 Foo"
- -d,--dir                       Used to indicate source when using
-                                --exclude
- -e,--exclude <expression>      Excludes files matching wildcard
-                                <expression>. Note that --dir is required
-                                when using this parameter. Allows multiple
-                                arguments.
- -E,--exclude-file <fileName>   Excludes files matching regular expression
-                                in <file> Note that --dir is required when
-                                using this parameter.
- -f,--force                     Forces any changes in files to be written
-                                directly to the source files (i.e. new
-                                files are not created)
- -h,--help                      Print help for the Rat command line
-                                interface and exit
- -s,--stylesheet <arg>          XSLT stylesheet to use when creating the
-                                report.  Not compatible with -x
- -x,--xml                       Output the report in raw XML format.  Not
-                                compatible with -s
-
-NOTE:
-Rat is really little more than a grep ATM
-Rat is also rather memory hungry ATM
-Rat is very basic ATM
-Rat highlights possible issues
-Rat reports require interpretation
-Rat often requires some tuning before it runs well against a project
-Rat relies on heuristics: it may miss issues

From f0d7fef894f2c200360a50f3ff700ab091bd2009 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 18:53:25 -0500
Subject: [PATCH 07/19] Address comments:

---
 tests/sqllogictests/README.md   |  4 +++-
 tests/sqllogictests/src/main.rs | 23 ++++++++++++++++++-----
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/tests/sqllogictests/README.md b/tests/sqllogictests/README.md
index 7792ddde87b83..06f739d5be142 100644
--- a/tests/sqllogictests/README.md
+++ b/tests/sqllogictests/README.md
@@ -13,7 +13,7 @@ This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/s
 
 > :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki
 
-sqllogictest is a program originally written for SQLite to verify the correctness of SQL queries against the SQLLite engine. The program is engine-agnostic and can parse sqllogictest files (`.slt`), runs queries against an SQL engine and compare the output to the expected output.
+sqllogictest is a program originally written for SQLite to verify the correctness of SQL queries against the SQLite engine. The program is engine-agnostic and can parse sqllogictest files (`.slt`), runs queries against an SQL engine and compare the output to the expected output.
 
 Tests in the `.slt` file are a sequence of query record generally starting with `CREATE` statements to populate tables and then further queries to test the populated data (arrow-datafusion exception).
 
@@ -30,6 +30,8 @@ query <type_string> <sort_mode> <label>
 - `type_string`: A short string that specifies the number of result columns and the expected datatype of each result column. There is one character in the <type_string> for each result column. The characters codes are "T" for a text result, "I" for an integer result, and "R" for a floating-point result.
 - (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output. 
 - `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@". 
+- `sort_mode`: If included, it must be one of "nosort", "rowsort", or "valuesort". The default is "nosort". In nosort mode, the results appear in exactly the order in which they were received from the database engine. The nosort mode should only be used on queries that have an ORDER BY clause or which only have a single row of result, since otherwise the order of results is undefined and might vary from one database engine to another. The "rowsort" mode gathers all output from the database engine then sorts it by rows on the client side. Sort comparisons use strcmp() on the rendered ASCII text representation of the values. Hence, "9" sorts after "10", not before. The "valuesort" mode works like rowsort except that it does not honor row groupings. Each individual result value is sorted on its own.
+
 
 ##### Example
 
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
index 928905876d3be..cd0529c1234e8 100644
--- a/tests/sqllogictests/src/main.rs
+++ b/tests/sqllogictests/src/main.rs
@@ -20,6 +20,7 @@ use datafusion::arrow::csv::WriterBuilder;
 use datafusion::arrow::record_batch::RecordBatch;
 use datafusion::prelude::SessionContext;
 use std::path::PathBuf;
+use std::time::Duration;
 
 use sqllogictest::TestError;
 pub type Result<T> = std::result::Result<T, TestError>;
@@ -78,6 +79,20 @@ impl sqllogictest::AsyncDB for DataFusion {
         let result = run_query(&self.ctx, sql).await?;
         Ok(result)
     }
+
+    /// Engine name of current database.
+    fn engine_name(&self) -> &str {
+        "DataFusion"
+    }
+    
+    /// [`Runner`] calls this function to perform sleep.
+    ///
+    /// The default implementation is `std::thread::sleep`, which is universial to any async runtime
+    /// but would block the current thread. If you are running in tokio runtime, you should override
+    /// this by `tokio::time::sleep`.
+    async fn sleep(dur: Duration) {
+       tokio::time::sleep(dur).await;
+    }
 }
 
 #[tokio::main]
@@ -93,7 +108,7 @@ pub async fn main() -> Result<()> {
 
         let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
         // TODO: use tester.run_parallel_async()
-        tester.run_file_async(filename).await.unwrap();
+        tester.run_file_async(filename).await?;
     }
 
     Ok(())
@@ -102,15 +117,13 @@ pub async fn main() -> Result<()> {
 fn format_batches(batches: &[RecordBatch]) -> Result<String> {
     let mut bytes = vec![];
     {
-        let builder = WriterBuilder::new().has_headers(false).with_delimiter(b',');
+        let builder = WriterBuilder::new().has_headers(false).with_delimiter(b' ');
         let mut writer = builder.build(&mut bytes);
         for batch in batches {
             writer.write(batch).unwrap();
         }
     }
-
-    let formatted = String::from_utf8(bytes).unwrap().replace(',', " ");
-    Ok(formatted)
+    Ok(String::from_utf8(bytes).unwrap())
 }
 
 async fn run_query(ctx: &SessionContext, sql: impl Into<String>) -> Result<String> {

From 7265e46d66b933be3477b638eb50228712420363 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:19:25 -0500
Subject: [PATCH 08/19] Move sqllogic tests in datafusion/core/tests

---
 .../core/tests/sqllogictests/.gitignore       |   1 +
 datafusion/core/tests/sqllogictests/README.md |  47 +
 .../core/tests/sqllogictests/src/main.rs      | 134 +++
 .../core/tests/sqllogictests/src/setup.rs     | 201 ++++
 .../core/tests/sqllogictests/src/utils.rs     |  40 +
 .../sqllogictests/test_files/aggregate.slt    | 868 ++++++++++++++++++
 .../sqllogictests/test_files/arrow_typeof.slt |  65 ++
 7 files changed, 1356 insertions(+)
 create mode 100644 datafusion/core/tests/sqllogictests/.gitignore
 create mode 100644 datafusion/core/tests/sqllogictests/README.md
 create mode 100644 datafusion/core/tests/sqllogictests/src/main.rs
 create mode 100644 datafusion/core/tests/sqllogictests/src/setup.rs
 create mode 100644 datafusion/core/tests/sqllogictests/src/utils.rs
 create mode 100644 datafusion/core/tests/sqllogictests/test_files/aggregate.slt
 create mode 100644 datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt

diff --git a/datafusion/core/tests/sqllogictests/.gitignore b/datafusion/core/tests/sqllogictests/.gitignore
new file mode 100644
index 0000000000000..8e5bbf044f1e0
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/.gitignore
@@ -0,0 +1 @@
+*.py
\ No newline at end of file
diff --git a/datafusion/core/tests/sqllogictests/README.md b/datafusion/core/tests/sqllogictests/README.md
new file mode 100644
index 0000000000000..06f739d5be142
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/README.md
@@ -0,0 +1,47 @@
+#### Overview
+
+This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki). We use [sqllogictest-rs](https://github.com/risinglightdb/sqllogictest-rs) as a parser/runner of `.slt` files in `test_files`.
+
+#### Running tests
+
+`cargo run -p datafusion-sqllogictests`
+
+#### Setup
+
+
+#### sqllogictests
+
+> :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki
+
+sqllogictest is a program originally written for SQLite to verify the correctness of SQL queries against the SQLite engine. The program is engine-agnostic and can parse sqllogictest files (`.slt`), runs queries against an SQL engine and compare the output to the expected output.
+
+Tests in the `.slt` file are a sequence of query record generally starting with `CREATE` statements to populate tables and then further queries to test the populated data (arrow-datafusion exception).
+
+Query records follow the format:
+```sql
+# <test_name>
+query <type_string> <sort_mode> <label>
+<sql_query>
+----
+<expected_result>
+```
+
+- `test_name`: Uniquely identify the test name (arrow-datafusion only)
+- `type_string`: A short string that specifies the number of result columns and the expected datatype of each result column. There is one character in the <type_string> for each result column. The characters codes are "T" for a text result, "I" for an integer result, and "R" for a floating-point result.
+- (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output. 
+- `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@". 
+- `sort_mode`: If included, it must be one of "nosort", "rowsort", or "valuesort". The default is "nosort". In nosort mode, the results appear in exactly the order in which they were received from the database engine. The nosort mode should only be used on queries that have an ORDER BY clause or which only have a single row of result, since otherwise the order of results is undefined and might vary from one database engine to another. The "rowsort" mode gathers all output from the database engine then sorts it by rows on the client side. Sort comparisons use strcmp() on the rendered ASCII text representation of the values. Hence, "9" sorts after "10", not before. The "valuesort" mode works like rowsort except that it does not honor row groupings. Each individual result value is sorted on its own.
+
+
+##### Example
+
+```sql
+# group_by_distinct
+query TTI
+SELECT a, b, COUNT(DISTINCT c) FROM my_table GROUP BY a, b ORDER BY a, b
+----
+foo bar 10
+foo baz 5
+foo     4
+        3
+```
diff --git a/datafusion/core/tests/sqllogictests/src/main.rs b/datafusion/core/tests/sqllogictests/src/main.rs
new file mode 100644
index 0000000000000..cd0529c1234e8
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/src/main.rs
@@ -0,0 +1,134 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use async_trait::async_trait;
+use datafusion::arrow::csv::WriterBuilder;
+use datafusion::arrow::record_batch::RecordBatch;
+use datafusion::prelude::SessionContext;
+use std::path::PathBuf;
+use std::time::Duration;
+
+use sqllogictest::TestError;
+pub type Result<T> = std::result::Result<T, TestError>;
+
+mod setup;
+mod utils;
+
+const TEST_DIRECTORY: &str = "tests/sqllogictests/test_files";
+const TEST_CATEGORIES: [TestCategory; 2] =
+    [TestCategory::Aggregate, TestCategory::ArrowTypeOf];
+
+pub enum TestCategory {
+    Aggregate,
+    ArrowTypeOf,
+}
+
+impl TestCategory {
+    fn as_str(&self) -> &'static str {
+        match self {
+            TestCategory::Aggregate => "Aggregate",
+            TestCategory::ArrowTypeOf => "ArrowTypeOf",
+        }
+    }
+
+    fn test_filename(&self) -> &'static str {
+        match self {
+            TestCategory::Aggregate => "aggregate.slt",
+            TestCategory::ArrowTypeOf => "arrow_typeof.slt",
+        }
+    }
+
+    async fn register_test_tables(&self, ctx: &SessionContext) {
+        println!("[{}] Registering tables", self.as_str());
+        match self {
+            TestCategory::Aggregate => setup::register_aggregate_tables(ctx).await,
+            TestCategory::ArrowTypeOf => (),
+        }
+    }
+}
+
+pub struct DataFusion {
+    ctx: SessionContext,
+    test_category: TestCategory,
+}
+
+#[async_trait]
+impl sqllogictest::AsyncDB for DataFusion {
+    type Error = TestError;
+
+    async fn run(&mut self, sql: &str) -> Result<String> {
+        println!(
+            "[{}] Running query: \"{}\"",
+            self.test_category.as_str(),
+            sql
+        );
+        let result = run_query(&self.ctx, sql).await?;
+        Ok(result)
+    }
+
+    /// Engine name of current database.
+    fn engine_name(&self) -> &str {
+        "DataFusion"
+    }
+    
+    /// [`Runner`] calls this function to perform sleep.
+    ///
+    /// The default implementation is `std::thread::sleep`, which is universial to any async runtime
+    /// but would block the current thread. If you are running in tokio runtime, you should override
+    /// this by `tokio::time::sleep`.
+    async fn sleep(dur: Duration) {
+       tokio::time::sleep(dur).await;
+    }
+}
+
+#[tokio::main]
+pub async fn main() -> Result<()> {
+    for test_category in TEST_CATEGORIES {
+        let filename = PathBuf::from(format!(
+            "{}/{}",
+            TEST_DIRECTORY,
+            test_category.test_filename()
+        ));
+        let ctx = SessionContext::new();
+        test_category.register_test_tables(&ctx).await;
+
+        let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
+        // TODO: use tester.run_parallel_async()
+        tester.run_file_async(filename).await?;
+    }
+
+    Ok(())
+}
+
+fn format_batches(batches: &[RecordBatch]) -> Result<String> {
+    let mut bytes = vec![];
+    {
+        let builder = WriterBuilder::new().has_headers(false).with_delimiter(b' ');
+        let mut writer = builder.build(&mut bytes);
+        for batch in batches {
+            writer.write(batch).unwrap();
+        }
+    }
+    Ok(String::from_utf8(bytes).unwrap())
+}
+
+async fn run_query(ctx: &SessionContext, sql: impl Into<String>) -> Result<String> {
+    let df = ctx.sql(&sql.into()).await.unwrap();
+    let results: Vec<RecordBatch> = df.collect().await.unwrap();
+    let formatted_batches = format_batches(&results)?;
+    Ok(formatted_batches)
+}
diff --git a/datafusion/core/tests/sqllogictests/src/setup.rs b/datafusion/core/tests/sqllogictests/src/setup.rs
new file mode 100644
index 0000000000000..1e38d48608eb0
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/src/setup.rs
@@ -0,0 +1,201 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use datafusion::{
+    arrow::{
+        array::{
+            ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
+            Int8Array, UInt16Array, UInt32Array, UInt64Array, UInt8Array,
+        },
+        datatypes::{DataType, Field, Schema},
+        record_batch::RecordBatch,
+    },
+    datasource::MemTable,
+    prelude::{CsvReadOptions, SessionContext},
+    test_util,
+};
+use std::sync::Arc;
+
+use crate::utils;
+
+pub async fn register_aggregate_tables(ctx: &SessionContext) {
+    register_aggregate_csv_by_sql(ctx).await;
+    register_aggregate_test_100(ctx).await;
+    register_decimal_table(ctx);
+    register_median_test_tables(ctx);
+    register_test_data(ctx);
+}
+
+fn register_median_test_tables(ctx: &SessionContext) {
+    // Register median tables
+    let items: Vec<(&str, DataType, ArrayRef)> = vec![
+        (
+            "i8",
+            DataType::Int8,
+            Arc::new(Int8Array::from(vec![i8::MIN, i8::MIN, 100, i8::MAX])),
+        ),
+        (
+            "i16",
+            DataType::Int16,
+            Arc::new(Int16Array::from(vec![i16::MIN, i16::MIN, 100, i16::MAX])),
+        ),
+        (
+            "i32",
+            DataType::Int32,
+            Arc::new(Int32Array::from(vec![i32::MIN, i32::MIN, 100, i32::MAX])),
+        ),
+        (
+            "i64",
+            DataType::Int64,
+            Arc::new(Int64Array::from(vec![i64::MIN, i64::MIN, 100, i64::MAX])),
+        ),
+        (
+            "u8",
+            DataType::UInt8,
+            Arc::new(UInt8Array::from(vec![u8::MIN, u8::MIN, 100, u8::MAX])),
+        ),
+        (
+            "u16",
+            DataType::UInt16,
+            Arc::new(UInt16Array::from(vec![u16::MIN, u16::MIN, 100, u16::MAX])),
+        ),
+        (
+            "u32",
+            DataType::UInt32,
+            Arc::new(UInt32Array::from(vec![u32::MIN, u32::MIN, 100, u32::MAX])),
+        ),
+        (
+            "u64",
+            DataType::UInt64,
+            Arc::new(UInt64Array::from(vec![u64::MIN, u64::MIN, 100, u64::MAX])),
+        ),
+        (
+            "f32",
+            DataType::Float32,
+            Arc::new(Float32Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
+        ),
+        (
+            "f64",
+            DataType::Float64,
+            Arc::new(Float64Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
+        ),
+        (
+            "f64_nan",
+            DataType::Float64,
+            Arc::new(Float64Array::from(vec![1.1, f64::NAN, f64::NAN, f64::NAN])),
+        ),
+    ];
+
+    for (name, data_type, values) in items {
+        let batch = RecordBatch::try_new(
+            Arc::new(Schema::new(vec![Field::new("a", data_type, false)])),
+            vec![values],
+        )
+        .unwrap();
+        let table_name = &format!("median_{}", name);
+        ctx.register_batch(table_name, batch).unwrap();
+    }
+}
+
+async fn register_aggregate_csv_by_sql(ctx: &SessionContext) {
+    let test_data = datafusion::test_util::arrow_test_data();
+
+    let df = ctx
+        .sql(&format!(
+            "
+    CREATE EXTERNAL TABLE aggregate_test_100_by_sql (
+        c1  VARCHAR NOT NULL,
+        c2  TINYINT NOT NULL,
+        c3  SMALLINT NOT NULL,
+        c4  SMALLINT NOT NULL,
+        c5  INTEGER NOT NULL,
+        c6  BIGINT NOT NULL,
+        c7  SMALLINT NOT NULL,
+        c8  INT NOT NULL,
+        c9  INT UNSIGNED NOT NULL,
+        c10 BIGINT UNSIGNED NOT NULL,
+        c11 FLOAT NOT NULL,
+        c12 DOUBLE NOT NULL,
+        c13 VARCHAR NOT NULL
+    )
+    STORED AS CSV
+    WITH HEADER ROW
+    LOCATION '{}/csv/aggregate_test_100.csv'
+    ",
+            test_data
+        ))
+        .await
+        .expect("Creating dataframe for CREATE EXTERNAL TABLE");
+
+    // Mimic the CLI and execute the resulting plan -- even though it
+    // is effectively a no-op (returns zero rows)
+    let results = df.collect().await.expect("Executing CREATE EXTERNAL TABLE");
+    assert!(
+        results.is_empty(),
+        "Expected no rows from executing CREATE EXTERNAL TABLE"
+    );
+}
+
+fn register_test_data(ctx: &SessionContext) {
+    let schema = Arc::new(Schema::new(vec![
+        Field::new("c1", DataType::Int64, true),
+        Field::new("c2", DataType::Int64, true),
+    ]));
+
+    let data = RecordBatch::try_new(
+        schema,
+        vec![
+            Arc::new(Int64Array::from(vec![
+                Some(0),
+                Some(1),
+                None,
+                Some(3),
+                Some(3),
+            ])),
+            Arc::new(Int64Array::from(vec![
+                None,
+                Some(1),
+                Some(1),
+                Some(2),
+                Some(2),
+            ])),
+        ],
+    )
+    .unwrap();
+
+    ctx.register_batch("test", data).unwrap();
+}
+
+fn register_decimal_table(ctx: &SessionContext) {
+    let batch_decimal = utils::make_decimal();
+    let schema = batch_decimal.schema();
+    let partitions = vec![vec![batch_decimal]];
+    let provider = Arc::new(MemTable::try_new(schema, partitions).unwrap());
+    ctx.register_table("d_table", provider).unwrap();
+}
+
+async fn register_aggregate_test_100(ctx: &SessionContext) {
+    let test_data = datafusion::test_util::arrow_test_data();
+    let schema = test_util::aggr_test_schema();
+    ctx.register_csv(
+        "aggregate_test_100",
+        &format!("{}/csv/aggregate_test_100.csv", test_data),
+        CsvReadOptions::new().schema(&schema),
+    )
+    .await
+    .unwrap();
+}
diff --git a/datafusion/core/tests/sqllogictests/src/utils.rs b/datafusion/core/tests/sqllogictests/src/utils.rs
new file mode 100644
index 0000000000000..4d064a76e2ad2
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/src/utils.rs
@@ -0,0 +1,40 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use datafusion::arrow::{
+    array::{Array, Decimal128Builder},
+    datatypes::{Field, Schema},
+    record_batch::RecordBatch,
+};
+use std::sync::Arc;
+
+// TODO: move this to datafusion::test_utils?
+pub fn make_decimal() -> RecordBatch {
+    let mut decimal_builder = Decimal128Builder::with_capacity(20);
+    for i in 110000..110010 {
+        decimal_builder.append_value(i as i128);
+    }
+    for i in 100000..100010 {
+        decimal_builder.append_value(-i as i128);
+    }
+    let array = decimal_builder
+        .finish()
+        .with_precision_and_scale(10, 3)
+        .unwrap();
+    let schema = Schema::new(vec![Field::new("c1", array.data_type().clone(), true)]);
+    RecordBatch::try_new(Arc::new(schema), vec![Arc::new(array)]).unwrap()
+}
diff --git a/datafusion/core/tests/sqllogictests/test_files/aggregate.slt b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
new file mode 100644
index 0000000000000..8cb82923a5810
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
@@ -0,0 +1,868 @@
+# FIX: custom absolute values
+# csv_query_avg_multi_batch
+
+# csv_query_avg
+query R
+SELECT avg(c12) FROM aggregate_test_100
+----
+0.5089725099127211
+
+# csv_query_covariance_1
+query R
+SELECT covar_pop(c2, c12) FROM aggregate_test_100
+----
+-0.07916932235380847
+
+# csv_query_covariance_2
+query R
+SELECT covar(c2, c12) FROM aggregate_test_100
+----
+-0.07996901247859442
+
+# csv_query_correlation
+query R
+SELECT corr(c2, c12) FROM aggregate_test_100
+----
+-0.19064544190576607
+
+# csv_query_variance_1
+query R
+SELECT var_pop(c2) FROM aggregate_test_100
+----
+1.8675
+
+# original: 26156334342021890000000000000000000000
+# csv_query_variance_2
+query R
+SELECT var_pop(c6) FROM aggregate_test_100
+----
+2.615633434202189e37
+
+# csv_query_variance_3
+query R
+SELECT var_pop(c12) FROM aggregate_test_100
+----
+0.09234223721582163
+
+# csv_query_variance_4
+query R
+SELECT var(c2) FROM aggregate_test_100
+----
+1.8863636363636365
+
+# csv_query_variance_5
+query R
+SELECT var_samp(c2) FROM aggregate_test_100
+----
+1.8863636363636365
+
+# csv_query_stddev_1
+query R
+SELECT stddev_pop(c2) FROM aggregate_test_100
+----
+1.3665650368716449
+
+# original: 5114326382039172000
+# csv_query_stddev_2
+query R 
+SELECT stddev_pop(c6) FROM aggregate_test_100
+----
+5.114326382039172e18
+
+# csv_query_stddev_3
+query R
+SELECT stddev_pop(c12) FROM aggregate_test_100
+----
+0.30387865541334363
+
+# csv_query_stddev_4
+query R
+SELECT stddev(c12) FROM aggregate_test_100
+----
+0.3054095399405338
+
+# csv_query_stddev_5
+query R
+SELECT stddev_samp(c12) FROM aggregate_test_100
+----
+0.3054095399405338
+
+# csv_query_stddev_6
+query R
+select stddev(sq.column1) from (values (1.1), (2.0), (3.0)) as sq
+----
+0.9504384952922168
+
+# csv_query_approx_median_1
+query I
+SELECT approx_median(c2) FROM aggregate_test_100
+----
+3
+
+# csv_query_approx_median_2
+query I
+SELECT approx_median(c6) FROM aggregate_test_100
+----
+1146409980542786560
+
+# csv_query_approx_median_3
+query R
+SELECT approx_median(c12) FROM aggregate_test_100
+----
+0.5550065410522981
+
+# csv_query_median_1
+query I
+SELECT median(c2) FROM aggregate_test_100
+----
+3
+
+# csv_query_median_2
+query I
+SELECT median(c6) FROM aggregate_test_100
+----
+1125553990140691277
+
+# csv_query_median_3
+query R
+SELECT median(c12) FROM aggregate_test_100
+----
+0.5513900544385053
+
+# median_i8
+query I
+SELECT median(a) FROM median_i8
+----
+-14
+
+# median_i16
+query I
+SELECT median(a) FROM median_i16
+----
+-16334
+
+# median_i32
+query I
+SELECT median(a) FROM median_i32
+----
+-1073741774
+
+# TODO: FIX - numbers are off?
+# median_i64
+# query I
+# SELECT median(a) FROM median_i64
+# ----
+# -4611686018427388000
+
+# median_u8
+query I
+SELECT median(a) FROM median_u8
+----
+50
+
+# median_u16
+query I
+SELECT median(a) FROM median_u16
+----
+50
+
+# median_u32
+query I
+SELECT median(a) FROM median_u32
+----
+50
+
+# median_u64
+query I
+SELECT median(a) FROM median_u64
+----
+50
+
+# median_f32
+query R
+SELECT median(a) FROM median_f32
+----
+3.3
+
+# median_f64
+query R
+SELECT median(a) FROM median_f64
+----
+3.3
+
+# median_f64_nan
+query T
+SELECT median(a) FROM median_f64_nan
+----
+NaN
+
+# approx_median_f64_nan
+query T
+SELECT approx_median(a) FROM median_f64_nan
+----
+NaN
+
+# csv_query_external_table_count
+query I
+SELECT COUNT(c12) FROM aggregate_test_100
+----
+100
+
+# csv_query_external_table_sum
+query II
+SELECT SUM(CAST(c7 AS BIGINT)), SUM(CAST(c8 AS BIGINT)) FROM aggregate_test_100
+----
+13060 3017641
+
+# csv_query_count
+query I
+SELECT count(c12) FROM aggregate_test_100
+----
+100
+
+# csv_query_count_distinct
+query I
+SELECT count(distinct c2) FROM aggregate_test_100
+----
+5
+
+# csv_query_count_distinct_expr
+query I
+SELECT count(distinct c2 % 2) FROM aggregate_test_100
+----
+2
+
+# csv_query_count_star
+query I
+SELECT COUNT(*) FROM aggregate_test_100
+----
+100
+
+# csv_query_count_literal
+query I
+SELECT COUNT(2) FROM aggregate_test_100
+----
+100
+
+# csv_query_approx_count
+# FIX: https://github.com/apache/arrow-datafusion/issues/3353
+# query II
+# SELECT approx_distinct(c9) AS count_c9, approx_distinct(cast(c9 as varchar)) count_c9_str FROM aggregate_test_100
+# ----
+# 100 99
+
+# csv_query_approx_count_dupe_expr_aliased
+query II
+SELECT approx_distinct(c9) AS a, approx_distinct(c9) AS b FROM aggregate_test_100
+----
+100 100
+
+# TODO: csv_query_approx_percentile_cont
+
+# TODO: fix decimal places
+# csv_query_cube_avg
+# query TIR
+# SELECT c1, c2, AVG(c3) FROM aggregate_test_100_by_sql GROUP BY CUBE (c1, c2) ORDER BY c1, c2
+# ----
+# a 1 -17.6
+# a 2 -15.333333333333334
+# a 3 -4.5
+# a 4 -32
+# a 5 -32
+# a  -18.333333333333332
+# b 1 31.666666666666668
+# b 2 25.5
+# b 3 -42
+# b 4 -44.6
+# b 5 -0.2
+# b  -5.842105263157895
+# c 1 47.5
+# c 2 -55.57142857142857
+# c 3 47.5
+# c 4 -10.75
+# c 5 12
+# c  -1.3333333333333333
+# d 1 -8.142857142857142
+# d 2 109.33333333333333
+# d 3 41.333333333333336
+# d 4 54
+# d 5 -49.5
+# d  25.444444444444443
+# e 1 75.66666666666667
+# e 2 37.8
+# e 3 48
+# e 4 37.285714285714285
+# e 5 -11
+# e  40.333333333333336
+#  1 16.681818181818183
+#  2 8.363636363636363
+#  3 20.789473684210527
+#  4 1.2608695652173914
+#  5 -13.857142857142858
+#    7.81
+
+# TODO: fix decimal places
+# csv_query_rollup_avg
+# query IIII
+# SELECT c1, c2, c3, AVG(c4) FROM aggregate_test_100_by_sql GROUP BY ROLLUP (c1, c2, c3) ORDER BY c1, c2, c3
+# ----
+# a 1 -85 -15154
+# a 1 -56 8692
+# a 1 -25 15295
+# a 1 -5 12636
+# a 1 83 -14704
+# a 1  1353
+# a 2 -48 -18025
+# a 2 -43 13080
+# a 2 45 15673
+# a 2  3576
+# a 3 -72 -11122
+# a 3 -12 -9168
+# a 3 13 22338.5
+# a 3 14 28162
+# a 3 17 -22796
+# a 3  4958.833333333333
+# a 4 -101 11640
+# a 4 -54 -2376
+# a 4 -38 20744
+# a 4 65 -28462
+# a 4  386.5
+# a 5 -101 -12484
+# a 5 -31 -12907
+# a 5 36 -16974
+# a 5  -14121.666666666666
+# a   306.04761904761904
+# b 1 12 7652
+# b 1 29 -18218
+# b 1 54 -18410
+# b 1  -9658.666666666666
+# b 2 -60 -21739
+# b 2 31 23127
+# b 2 63 21456
+# b 2 68 15874
+# b 2  9679.5
+# b 3 -101 -13217
+# b 3 17 14457
+# b 3  620
+# b 4 -117 19316
+# b 4 -111 -1967
+# b 4 -59 25286
+# b 4 17 -28070
+# b 4 47 20690
+# b 4  7051
+# b 5 -82 22080
+# b 5 -44 15788
+# b 5 -5 24896
+# b 5 62 16337
+# b 5 68 21576
+# b 5  20135.4
+# b   7732.315789473684
+# c 1 -24 -24085
+# c 1 41 -4667
+# c 1 70 27752
+# c 1 103 -22186
+# c 1  -5796.5
+# c 2 -117 -30187
+# c 2 -107 -2904
+# c 2 -106 -1114
+# c 2 -60 -16312
+# c 2 -29 25305
+# c 2 1 18109
+# c 2 29 -3855
+# c 2  -1565.4285714285713
+# c 3 -2 -18655
+# c 3 22 13741
+# c 3 73 -9565
+# c 3 97 29106
+# c 3  3656.75
+# c 4 -90 -2935
+# c 4 -79 5281
+# c 4 3 -30508
+# c 4 123 16620
+# c 4  -2885.5
+# c 5 -94 -15880
+# c 5 118 19208
+# c 5  1664
+# c   -1320.5238095238096
+# d 1 -99 5613
+# d 1 -98 13630
+# d 1 -72 25590
+# d 1 -8 27138
+# d 1 38 18384
+# d 1 57 28781
+# d 1 125 31106
+# d 1  21463.14285714286
+# d 2 93 -12642
+# d 2 113 3917
+# d 2 122 10130
+# d 2  468.3333333333333
+# d 3 -76 8809
+# d 3 77 15091
+# d 3 123 29533
+# d 3  17811
+# d 4 5 -7688
+# d 4 55 -1471
+# d 4 102 -24558
+# d 4  -11239
+# d 5 -59 2045
+# d 5 -40 22614
+# d 5  12329.5
+# d   10890.111111111111
+# e 1 36 -21481
+# e 1 71 -5479
+# e 1 120 10837
+# e 1  -5374.333333333333
+# e 2 -61 -2888
+# e 2 49 24495
+# e 2 52 5666
+# e 2 97 18167
+# e 2  10221.2
+# e 3 -95 13611
+# e 3 71 194
+# e 3 104 -25136
+# e 3 112 -6823
+# e 3  -4538.5
+# e 4 -56 -31500
+# e 4 -53 13788
+# e 4 30 -16110
+# e 4 73 -22501
+# e 4 74 -12612
+# e 4 96 -30336
+# e 4 97 -13181
+# e 4  -16064.57142857143
+# e 5 -86 32514
+# e 5 64 -26526
+# e 5  2994
+# e   -4268.333333333333
+#    2319.97
+
+# csv_query_approx_percentile_cont_with_weight
+query II
+SELECT c1, approx_percentile_cont(c3, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_approx_percentile_cont_with_weight (2)
+query II
+SELECT c1, approx_percentile_cont_with_weight(c3, 1, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_approx_percentile_cont_with_histogram_bins
+query II
+SELECT c1, approx_percentile_cont(c3, 0.95, 200) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 73
+b 68
+c 122
+d 124
+e 115
+
+# csv_query_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY a.c1, b.c1 ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+
+# csv_query_cube_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY CUBE (a.c1, b.c1) ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+a   6000
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+b   6200
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+c   5600
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+d   4400
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+e   6300
+  a 5985
+  b 5415
+  c 5985
+  d 5130
+  e 5985
+    28500
+
+# csv_query_cube_distinct_count
+query III
+SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY CUBE (c1,c2) ORDER BY c1,c2
+----
+a 1 5
+a 2 3
+a 3 5
+a 4 4
+a 5 3
+a   19
+b 1 3
+b 2 4
+b 3 2
+b 4 5
+b 5 5
+b   17
+c 1 4
+c 2 7
+c 3 4
+c 4 4
+c 5 2
+c   21
+d 1 7
+d 2 3
+d 3 3
+d 4 3
+d 5 2
+d   18
+e 1 3
+e 2 4
+e 3 4
+e 4 7
+e 5 2
+e   18
+  1 22
+  2 20
+  3 17
+  4 23
+  5 14
+    80
+
+# csv_query_rollup_distinct_count
+query III
+SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY ROLLUP (c1,c2) ORDER BY c1,c2
+----
+a 1 5
+a 2 3
+a 3 5
+a 4 4
+a 5 3
+a   19
+b 1 3
+b 2 4
+b 3 2
+b 4 5
+b 5 5
+b   17
+c 1 4
+c 2 7
+c 3 4
+c 4 4
+c 5 2
+c   21
+d 1 7
+d 2 3
+d 3 3
+d 4 3
+d 5 2
+d   18
+e 1 3
+e 2 4
+e 3 4
+e 4 7
+e 5 2
+e  18
+   80
+
+# csv_query_rollup_sum_crossjoin
+query III
+SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY ROLLUP (a.c1, b.c1) ORDER BY a.c1, b.c1
+----
+a a 1260
+a b 1140
+a c 1260
+a d 1080
+a e 1260
+a   6000
+b a 1302
+b b 1178
+b c 1302
+b d 1116
+b e 1302
+b   6200
+c a 1176
+c b 1064
+c c 1176
+c d 1008
+c e 1176
+c   5600
+d a 924
+d b 836
+d c 924
+d d 792
+d e 924
+d   4400
+e a 1323
+e b 1197
+e c 1323
+e d 1134
+e e 1323
+e   6300
+    28500
+
+# query_count_without_from
+query I
+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 I
+# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test
+# ----
+# [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm0keZ5G8BffGwgF2RwQD59TFzMStxCB]
+
+# FIX: see above
+# csv_query_array_agg_empty
+# 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]
+
+# FIX: Decimal error
+# csv_query_array_agg_with_overflow
+# query IIIIII
+# select c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by c2 order by c2
+# ----
+# 1 367 16.681818181818183 125 -99 22
+# 2 184 8.363636363636363 122 -117 22
+# 3 395 20.789473684210527 123 -101 19
+# 4 29 1.2608695652173914 123 -117 23
+# 5 -194 -13.857142857142858 118 -101 14
+
+# TODO: csv_query_array_agg_unsupported
+
+# FIX: Decimal error
+# csv_query_array_cube_agg_with_overflow
+# query IIIIIII
+# select c1, c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by CUBE (c1,c2) order by c1, c2
+# ----
+# a 1 -88 -17.6 83 -85 5
+# a 2 -46 -15.333333333333334 45 -48 3
+# a 3 -27 -4.5 17 -72 6
+# a 4 -128 -32 65 -101 4
+# a 5 -96 -32 36 -101 3
+# a  -385 -18.333333333333332 83 -101 21
+# b 1 95 31.666666666666668 54 12 3
+# b 2 102 25.5 68 -60 4
+# b 3 -84 -42 17 -101 2
+# b 4 -223 -44.6 47 -117 5
+# b 5 -1 -0.2 68 -82 5
+# b  -111 -5.842105263157895 68 -117 19
+# c 1 190 47.5 103 -24 4
+# c 2 -389 -55.57142857142857 29 -117 7
+# c 3 190 47.5 97 -2 4
+# c 4 -43 -10.75 123 -90 4
+# c 5 24 12 118 -94 2
+# c  -28 -1.3333333333333333 123 -117 21
+# d 1 -57 -8.142857142857142 125 -99 7
+# d 2 328 109.33333333333333 122 93 3
+# d 3 124 41.333333333333336 123 -76 3
+# d 4 162 54 102 5 3
+# d 5 -99 -49.5 -40 -59 2
+# d  458 25.444444444444443 125 -99 18
+# e 1 227 75.66666666666667 120 36 3
+# e 2 189 37.8 97 -61 5
+# e 3 192 48 112 -95 4
+# e 4 261 37.285714285714285 97 -56 7
+# e 5 -22 -11 64 -86 2
+# e  847 40.333333333333336 120 -95 21
+#  1 367 16.681818181818183 125 -99 22
+#  2 184 8.363636363636363 122 -117 22
+#  3 395 20.789473684210527 123 -101 19
+#  4 29 1.2608695652173914 123 -117 23
+#  5 -194 -13.857142857142858 118 -101 14
+#   781 7.81 125 -117 100
+
+# TODO: csv_query_array_agg_distinct
+
+# TODO: aggregate_timestamps_sum
+
+# TODO: aggregate_timestamps_count
+
+# TODO: aggregate_timestamps_min
+
+# TODO: aggregate_timestamps_max
+
+# TODO: aggregate_times_sum
+
+# TODO: aggregate_times_count
+
+# TODO: aggregate_times_min
+
+# TODO: aggregate_times_max
+
+# TODO: aggregate_timestamps_avg
+
+# aggregate_time_min_and_max
+query II
+select min(t), max(t) from  (select '00:00:00' as t union select '00:00:01' union select '00:00:02')
+----
+00:00:00 00:00:02
+
+# aggregate_decimal_min
+query I
+select min(c1) from d_table
+----
+-100.009
+
+# aggregate_decimal_max
+query I
+select max(c1) from d_table
+----
+110.009
+
+query I
+select sum(c1) from d_table
+----
+100.000
+
+# FIX: doesn't check datatype
+# aggregate_decimal_avg
+query I
+select avg(c1) from d_table
+----
+5.0000000
+
+# FIX: different test table
+# aggregate
+# query I
+# SELECT SUM(c1), SUM(c2) FROM test
+# ----
+# 60 220
+
+# TODO: aggregate_empty
+
+# TODO: aggregate_avg
+
+# TODO: aggregate_max
+
+# TODO: aggregate_min
+
+# TODO: aggregate_grouped
+
+# TODO: aggregate_grouped_avg
+
+# TODO: aggregate_grouped_empty
+
+# TODO: aggregate_grouped_max
+
+# TODO: aggregate_grouped_min
+
+# TODO: aggregate_avg_add
+
+# TODO: case_sensitive_identifiers_aggregates
+
+# TODO: count_basic
+
+# TODO: count_partitioned
+
+# TODO: count_aggregated
+
+# TODO: count_aggregated_cube
+
+# TODO: simple_avg
+
+# TODO: simple_mean
+
+# TOOD: bottom 2 require pre-populated data
+# query_sum_distinct
+query II
+SELECT AVG(c1), SUM(DISTINCT c2) FROM test
+----
+1.75 3
+
+# # query_count_distinct
+query I
+SELECT COUNT(DISTINCT c1) FROM test
+----
+3
+
+# TODO: count_distinct_integers_aggregated_single_partition
+
+# TODO: count_distinct_integers_aggregated_multiple_partitions
+
+# TODO: aggregate_with_alias
+
+
+# FIX: CSV Writer error
+# array_agg_zero
+# query I
+# SELECT ARRAY_AGG([])
+# ----
+# []
+
+# FIX: CSV Writer error
+# array_agg_one
+# query I
+# SELECT ARRAY_AGG([1])
+# ----
+# [[1]]
+
+# test_approx_percentile_cont_decimal_support
+query II
+SELECT c1, approx_percentile_cont(c2, cast(0.85 as decimal(10,2))) apc FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
+----
+a 4
+b 5
+c 4
+d 4
+e 4
\ No newline at end of file
diff --git a/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt b/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt
new file mode 100644
index 0000000000000..f8baaff18dc86
--- /dev/null
+++ b/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt
@@ -0,0 +1,65 @@
+# arrow_typeof_null
+query T
+SELECT arrow_typeof(null)
+----
+Null
+
+# arrow_typeof_boolean
+query T
+SELECT arrow_typeof(true)
+----
+Boolean
+
+# arrow_typeof_i64
+query T
+SELECT arrow_typeof(1)
+----
+Int64
+
+# arrow_typeof_i32
+query T
+SELECT arrow_typeof(1::int)
+----
+Int32
+
+# arrow_typeof_f64
+query T
+SELECT arrow_typeof(1.0)
+----
+Float64
+
+# arrow_typeof_f32
+query T
+SELECT arrow_typeof(1.0::float)
+----
+Float32
+
+# arrow_typeof_decimal
+# query T
+# SELECT arrow_typeof(1::Decimal)
+# ----
+# Decimal128(38, 10)
+
+# # arrow_typeof_timestamp
+# query T
+# SELECT arrow_typeof(now()::timestamp)
+# ----
+# Timestamp(Nanosecond, None)
+
+# # arrow_typeof_timestamp_utc
+# query T
+# SELECT arrow_typeof(now())
+# ----
+# Timestamp(Nanosecond, Some(\"+00:00\"))
+
+# # arrow_typeof_timestamp_date32(
+# query T
+# SELECT arrow_typeof(now()::date)
+# ----
+# Date32
+
+# # arrow_typeof_utf8
+# query T
+# SELECT arrow_typeof('1')
+# ----
+# Utf8

From 77429bbf7679ade5f1e9592582ee366e944fc567 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:21:11 -0500
Subject: [PATCH 09/19] Update README

---
 Cargo.toml                                    |   1 -
 datafusion/core/Cargo.toml                    |   6 +
 datafusion/core/tests/sqllogictests/README.md |   2 +-
 tests/sqllogictests/.gitignore                |   1 -
 tests/sqllogictests/Cargo.toml                |  29 -
 tests/sqllogictests/README.md                 |  47 -
 tests/sqllogictests/src/main.rs               | 134 ---
 tests/sqllogictests/src/setup.rs              | 201 ----
 tests/sqllogictests/src/utils.rs              |  40 -
 tests/sqllogictests/test_files/aggregate.slt  | 868 ------------------
 .../sqllogictests/test_files/arrow_typeof.slt |  65 --
 11 files changed, 7 insertions(+), 1387 deletions(-)
 delete mode 100644 tests/sqllogictests/.gitignore
 delete mode 100644 tests/sqllogictests/Cargo.toml
 delete mode 100644 tests/sqllogictests/README.md
 delete mode 100644 tests/sqllogictests/src/main.rs
 delete mode 100644 tests/sqllogictests/src/setup.rs
 delete mode 100644 tests/sqllogictests/src/utils.rs
 delete mode 100644 tests/sqllogictests/test_files/aggregate.slt
 delete mode 100644 tests/sqllogictests/test_files/arrow_typeof.slt

diff --git a/Cargo.toml b/Cargo.toml
index f39152db232ca..1ab431ea316a9 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -31,7 +31,6 @@ members = [
     "test-utils",
     "parquet-test-utils",
     "benchmarks",
-    "tests/sqllogictests",
 ]
 
 [profile.release]
diff --git a/datafusion/core/Cargo.toml b/datafusion/core/Cargo.toml
index 37629643529e6..af62f155922c1 100644
--- a/datafusion/core/Cargo.toml
+++ b/datafusion/core/Cargo.toml
@@ -89,6 +89,7 @@ pyo3 = { version = "0.17.1", optional = true }
 rand = "0.8"
 rayon = { version = "1.5", optional = true }
 smallvec = { version = "1.6", features = ["union"] }
+sqllogictest = "0.8.0"
 sqlparser = "0.27"
 tempfile = "3"
 tokio = { version = "1.0", features = ["macros", "rt", "rt-multi-thread", "sync", "fs", "parking_lot"] }
@@ -154,3 +155,8 @@ required-features = ["jit"]
 [[bench]]
 harness = false
 name = "merge"
+
+[[test]]
+name = "sqllogictests"
+path = "tests/sqllogictests/src/main.rs"
+harness = false
diff --git a/datafusion/core/tests/sqllogictests/README.md b/datafusion/core/tests/sqllogictests/README.md
index 06f739d5be142..7f584543c3b82 100644
--- a/datafusion/core/tests/sqllogictests/README.md
+++ b/datafusion/core/tests/sqllogictests/README.md
@@ -4,7 +4,7 @@ This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/s
 
 #### Running tests
 
-`cargo run -p datafusion-sqllogictests`
+`cargo test -p datafusion --test sqllogictests`
 
 #### Setup
 
diff --git a/tests/sqllogictests/.gitignore b/tests/sqllogictests/.gitignore
deleted file mode 100644
index 8e5bbf044f1e0..0000000000000
--- a/tests/sqllogictests/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-*.py
\ No newline at end of file
diff --git a/tests/sqllogictests/Cargo.toml b/tests/sqllogictests/Cargo.toml
deleted file mode 100644
index f4777147ea123..0000000000000
--- a/tests/sqllogictests/Cargo.toml
+++ /dev/null
@@ -1,29 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements.  See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership.  The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License.  You may obtain a copy of the License at
-#
-#   http:#www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied.  See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-[package]
-name = "datafusion-sqllogictests"
-version = "0.1.0"
-edition = "2021"
-
-# See more keys and their definitions at https:#doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-async-trait = "0.1.58"
-datafusion = { path = "../../datafusion/core" }
-sqllogictest = "0.8.0"
-tokio = { version = "1.0", features = ["macros", "rt-multi-thread"] }
diff --git a/tests/sqllogictests/README.md b/tests/sqllogictests/README.md
deleted file mode 100644
index 06f739d5be142..0000000000000
--- a/tests/sqllogictests/README.md
+++ /dev/null
@@ -1,47 +0,0 @@
-#### Overview
-
-This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki). We use [sqllogictest-rs](https://github.com/risinglightdb/sqllogictest-rs) as a parser/runner of `.slt` files in `test_files`.
-
-#### Running tests
-
-`cargo run -p datafusion-sqllogictests`
-
-#### Setup
-
-
-#### sqllogictests
-
-> :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki
-
-sqllogictest is a program originally written for SQLite to verify the correctness of SQL queries against the SQLite engine. The program is engine-agnostic and can parse sqllogictest files (`.slt`), runs queries against an SQL engine and compare the output to the expected output.
-
-Tests in the `.slt` file are a sequence of query record generally starting with `CREATE` statements to populate tables and then further queries to test the populated data (arrow-datafusion exception).
-
-Query records follow the format:
-```sql
-# <test_name>
-query <type_string> <sort_mode> <label>
-<sql_query>
-----
-<expected_result>
-```
-
-- `test_name`: Uniquely identify the test name (arrow-datafusion only)
-- `type_string`: A short string that specifies the number of result columns and the expected datatype of each result column. There is one character in the <type_string> for each result column. The characters codes are "T" for a text result, "I" for an integer result, and "R" for a floating-point result.
-- (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output. 
-- `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@". 
-- `sort_mode`: If included, it must be one of "nosort", "rowsort", or "valuesort". The default is "nosort". In nosort mode, the results appear in exactly the order in which they were received from the database engine. The nosort mode should only be used on queries that have an ORDER BY clause or which only have a single row of result, since otherwise the order of results is undefined and might vary from one database engine to another. The "rowsort" mode gathers all output from the database engine then sorts it by rows on the client side. Sort comparisons use strcmp() on the rendered ASCII text representation of the values. Hence, "9" sorts after "10", not before. The "valuesort" mode works like rowsort except that it does not honor row groupings. Each individual result value is sorted on its own.
-
-
-##### Example
-
-```sql
-# group_by_distinct
-query TTI
-SELECT a, b, COUNT(DISTINCT c) FROM my_table GROUP BY a, b ORDER BY a, b
-----
-foo bar 10
-foo baz 5
-foo     4
-        3
-```
diff --git a/tests/sqllogictests/src/main.rs b/tests/sqllogictests/src/main.rs
deleted file mode 100644
index cd0529c1234e8..0000000000000
--- a/tests/sqllogictests/src/main.rs
+++ /dev/null
@@ -1,134 +0,0 @@
-// Licensed to the Apache Software Foundation (ASF) under one
-// or more contributor license agreements.  See the NOTICE file
-// distributed with this work for additional information
-// regarding copyright ownership.  The ASF licenses this file
-// to you under the Apache License, Version 2.0 (the
-// "License"); you may not use this file except in compliance
-// with the License.  You may obtain a copy of the License at
-//
-//   http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing,
-// software distributed under the License is distributed on an
-// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-// KIND, either express or implied.  See the License for the
-// specific language governing permissions and limitations
-// under the License.
-
-use async_trait::async_trait;
-use datafusion::arrow::csv::WriterBuilder;
-use datafusion::arrow::record_batch::RecordBatch;
-use datafusion::prelude::SessionContext;
-use std::path::PathBuf;
-use std::time::Duration;
-
-use sqllogictest::TestError;
-pub type Result<T> = std::result::Result<T, TestError>;
-
-mod setup;
-mod utils;
-
-const TEST_DIRECTORY: &str = "tests/sqllogictests/test_files";
-const TEST_CATEGORIES: [TestCategory; 2] =
-    [TestCategory::Aggregate, TestCategory::ArrowTypeOf];
-
-pub enum TestCategory {
-    Aggregate,
-    ArrowTypeOf,
-}
-
-impl TestCategory {
-    fn as_str(&self) -> &'static str {
-        match self {
-            TestCategory::Aggregate => "Aggregate",
-            TestCategory::ArrowTypeOf => "ArrowTypeOf",
-        }
-    }
-
-    fn test_filename(&self) -> &'static str {
-        match self {
-            TestCategory::Aggregate => "aggregate.slt",
-            TestCategory::ArrowTypeOf => "arrow_typeof.slt",
-        }
-    }
-
-    async fn register_test_tables(&self, ctx: &SessionContext) {
-        println!("[{}] Registering tables", self.as_str());
-        match self {
-            TestCategory::Aggregate => setup::register_aggregate_tables(ctx).await,
-            TestCategory::ArrowTypeOf => (),
-        }
-    }
-}
-
-pub struct DataFusion {
-    ctx: SessionContext,
-    test_category: TestCategory,
-}
-
-#[async_trait]
-impl sqllogictest::AsyncDB for DataFusion {
-    type Error = TestError;
-
-    async fn run(&mut self, sql: &str) -> Result<String> {
-        println!(
-            "[{}] Running query: \"{}\"",
-            self.test_category.as_str(),
-            sql
-        );
-        let result = run_query(&self.ctx, sql).await?;
-        Ok(result)
-    }
-
-    /// Engine name of current database.
-    fn engine_name(&self) -> &str {
-        "DataFusion"
-    }
-    
-    /// [`Runner`] calls this function to perform sleep.
-    ///
-    /// The default implementation is `std::thread::sleep`, which is universial to any async runtime
-    /// but would block the current thread. If you are running in tokio runtime, you should override
-    /// this by `tokio::time::sleep`.
-    async fn sleep(dur: Duration) {
-       tokio::time::sleep(dur).await;
-    }
-}
-
-#[tokio::main]
-pub async fn main() -> Result<()> {
-    for test_category in TEST_CATEGORIES {
-        let filename = PathBuf::from(format!(
-            "{}/{}",
-            TEST_DIRECTORY,
-            test_category.test_filename()
-        ));
-        let ctx = SessionContext::new();
-        test_category.register_test_tables(&ctx).await;
-
-        let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
-        // TODO: use tester.run_parallel_async()
-        tester.run_file_async(filename).await?;
-    }
-
-    Ok(())
-}
-
-fn format_batches(batches: &[RecordBatch]) -> Result<String> {
-    let mut bytes = vec![];
-    {
-        let builder = WriterBuilder::new().has_headers(false).with_delimiter(b' ');
-        let mut writer = builder.build(&mut bytes);
-        for batch in batches {
-            writer.write(batch).unwrap();
-        }
-    }
-    Ok(String::from_utf8(bytes).unwrap())
-}
-
-async fn run_query(ctx: &SessionContext, sql: impl Into<String>) -> Result<String> {
-    let df = ctx.sql(&sql.into()).await.unwrap();
-    let results: Vec<RecordBatch> = df.collect().await.unwrap();
-    let formatted_batches = format_batches(&results)?;
-    Ok(formatted_batches)
-}
diff --git a/tests/sqllogictests/src/setup.rs b/tests/sqllogictests/src/setup.rs
deleted file mode 100644
index 1e38d48608eb0..0000000000000
--- a/tests/sqllogictests/src/setup.rs
+++ /dev/null
@@ -1,201 +0,0 @@
-// Licensed to the Apache Software Foundation (ASF) under one
-// or more contributor license agreements.  See the NOTICE file
-// distributed with this work for additional information
-// regarding copyright ownership.  The ASF licenses this file
-// to you under the Apache License, Version 2.0 (the
-// "License"); you may not use this file except in compliance
-// with the License.  You may obtain a copy of the License at
-//
-//   http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing,
-// software distributed under the License is distributed on an
-// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-// KIND, either express or implied.  See the License for the
-// specific language governing permissions and limitations
-// under the License.
-
-use datafusion::{
-    arrow::{
-        array::{
-            ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
-            Int8Array, UInt16Array, UInt32Array, UInt64Array, UInt8Array,
-        },
-        datatypes::{DataType, Field, Schema},
-        record_batch::RecordBatch,
-    },
-    datasource::MemTable,
-    prelude::{CsvReadOptions, SessionContext},
-    test_util,
-};
-use std::sync::Arc;
-
-use crate::utils;
-
-pub async fn register_aggregate_tables(ctx: &SessionContext) {
-    register_aggregate_csv_by_sql(ctx).await;
-    register_aggregate_test_100(ctx).await;
-    register_decimal_table(ctx);
-    register_median_test_tables(ctx);
-    register_test_data(ctx);
-}
-
-fn register_median_test_tables(ctx: &SessionContext) {
-    // Register median tables
-    let items: Vec<(&str, DataType, ArrayRef)> = vec![
-        (
-            "i8",
-            DataType::Int8,
-            Arc::new(Int8Array::from(vec![i8::MIN, i8::MIN, 100, i8::MAX])),
-        ),
-        (
-            "i16",
-            DataType::Int16,
-            Arc::new(Int16Array::from(vec![i16::MIN, i16::MIN, 100, i16::MAX])),
-        ),
-        (
-            "i32",
-            DataType::Int32,
-            Arc::new(Int32Array::from(vec![i32::MIN, i32::MIN, 100, i32::MAX])),
-        ),
-        (
-            "i64",
-            DataType::Int64,
-            Arc::new(Int64Array::from(vec![i64::MIN, i64::MIN, 100, i64::MAX])),
-        ),
-        (
-            "u8",
-            DataType::UInt8,
-            Arc::new(UInt8Array::from(vec![u8::MIN, u8::MIN, 100, u8::MAX])),
-        ),
-        (
-            "u16",
-            DataType::UInt16,
-            Arc::new(UInt16Array::from(vec![u16::MIN, u16::MIN, 100, u16::MAX])),
-        ),
-        (
-            "u32",
-            DataType::UInt32,
-            Arc::new(UInt32Array::from(vec![u32::MIN, u32::MIN, 100, u32::MAX])),
-        ),
-        (
-            "u64",
-            DataType::UInt64,
-            Arc::new(UInt64Array::from(vec![u64::MIN, u64::MIN, 100, u64::MAX])),
-        ),
-        (
-            "f32",
-            DataType::Float32,
-            Arc::new(Float32Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
-        ),
-        (
-            "f64",
-            DataType::Float64,
-            Arc::new(Float64Array::from(vec![1.1, 4.4, 5.5, 3.3, 2.2])),
-        ),
-        (
-            "f64_nan",
-            DataType::Float64,
-            Arc::new(Float64Array::from(vec![1.1, f64::NAN, f64::NAN, f64::NAN])),
-        ),
-    ];
-
-    for (name, data_type, values) in items {
-        let batch = RecordBatch::try_new(
-            Arc::new(Schema::new(vec![Field::new("a", data_type, false)])),
-            vec![values],
-        )
-        .unwrap();
-        let table_name = &format!("median_{}", name);
-        ctx.register_batch(table_name, batch).unwrap();
-    }
-}
-
-async fn register_aggregate_csv_by_sql(ctx: &SessionContext) {
-    let test_data = datafusion::test_util::arrow_test_data();
-
-    let df = ctx
-        .sql(&format!(
-            "
-    CREATE EXTERNAL TABLE aggregate_test_100_by_sql (
-        c1  VARCHAR NOT NULL,
-        c2  TINYINT NOT NULL,
-        c3  SMALLINT NOT NULL,
-        c4  SMALLINT NOT NULL,
-        c5  INTEGER NOT NULL,
-        c6  BIGINT NOT NULL,
-        c7  SMALLINT NOT NULL,
-        c8  INT NOT NULL,
-        c9  INT UNSIGNED NOT NULL,
-        c10 BIGINT UNSIGNED NOT NULL,
-        c11 FLOAT NOT NULL,
-        c12 DOUBLE NOT NULL,
-        c13 VARCHAR NOT NULL
-    )
-    STORED AS CSV
-    WITH HEADER ROW
-    LOCATION '{}/csv/aggregate_test_100.csv'
-    ",
-            test_data
-        ))
-        .await
-        .expect("Creating dataframe for CREATE EXTERNAL TABLE");
-
-    // Mimic the CLI and execute the resulting plan -- even though it
-    // is effectively a no-op (returns zero rows)
-    let results = df.collect().await.expect("Executing CREATE EXTERNAL TABLE");
-    assert!(
-        results.is_empty(),
-        "Expected no rows from executing CREATE EXTERNAL TABLE"
-    );
-}
-
-fn register_test_data(ctx: &SessionContext) {
-    let schema = Arc::new(Schema::new(vec![
-        Field::new("c1", DataType::Int64, true),
-        Field::new("c2", DataType::Int64, true),
-    ]));
-
-    let data = RecordBatch::try_new(
-        schema,
-        vec![
-            Arc::new(Int64Array::from(vec![
-                Some(0),
-                Some(1),
-                None,
-                Some(3),
-                Some(3),
-            ])),
-            Arc::new(Int64Array::from(vec![
-                None,
-                Some(1),
-                Some(1),
-                Some(2),
-                Some(2),
-            ])),
-        ],
-    )
-    .unwrap();
-
-    ctx.register_batch("test", data).unwrap();
-}
-
-fn register_decimal_table(ctx: &SessionContext) {
-    let batch_decimal = utils::make_decimal();
-    let schema = batch_decimal.schema();
-    let partitions = vec![vec![batch_decimal]];
-    let provider = Arc::new(MemTable::try_new(schema, partitions).unwrap());
-    ctx.register_table("d_table", provider).unwrap();
-}
-
-async fn register_aggregate_test_100(ctx: &SessionContext) {
-    let test_data = datafusion::test_util::arrow_test_data();
-    let schema = test_util::aggr_test_schema();
-    ctx.register_csv(
-        "aggregate_test_100",
-        &format!("{}/csv/aggregate_test_100.csv", test_data),
-        CsvReadOptions::new().schema(&schema),
-    )
-    .await
-    .unwrap();
-}
diff --git a/tests/sqllogictests/src/utils.rs b/tests/sqllogictests/src/utils.rs
deleted file mode 100644
index 4d064a76e2ad2..0000000000000
--- a/tests/sqllogictests/src/utils.rs
+++ /dev/null
@@ -1,40 +0,0 @@
-// Licensed to the Apache Software Foundation (ASF) under one
-// or more contributor license agreements.  See the NOTICE file
-// distributed with this work for additional information
-// regarding copyright ownership.  The ASF licenses this file
-// to you under the Apache License, Version 2.0 (the
-// "License"); you may not use this file except in compliance
-// with the License.  You may obtain a copy of the License at
-//
-//   http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing,
-// software distributed under the License is distributed on an
-// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-// KIND, either express or implied.  See the License for the
-// specific language governing permissions and limitations
-// under the License.
-
-use datafusion::arrow::{
-    array::{Array, Decimal128Builder},
-    datatypes::{Field, Schema},
-    record_batch::RecordBatch,
-};
-use std::sync::Arc;
-
-// TODO: move this to datafusion::test_utils?
-pub fn make_decimal() -> RecordBatch {
-    let mut decimal_builder = Decimal128Builder::with_capacity(20);
-    for i in 110000..110010 {
-        decimal_builder.append_value(i as i128);
-    }
-    for i in 100000..100010 {
-        decimal_builder.append_value(-i as i128);
-    }
-    let array = decimal_builder
-        .finish()
-        .with_precision_and_scale(10, 3)
-        .unwrap();
-    let schema = Schema::new(vec![Field::new("c1", array.data_type().clone(), true)]);
-    RecordBatch::try_new(Arc::new(schema), vec![Arc::new(array)]).unwrap()
-}
diff --git a/tests/sqllogictests/test_files/aggregate.slt b/tests/sqllogictests/test_files/aggregate.slt
deleted file mode 100644
index 8cb82923a5810..0000000000000
--- a/tests/sqllogictests/test_files/aggregate.slt
+++ /dev/null
@@ -1,868 +0,0 @@
-# FIX: custom absolute values
-# csv_query_avg_multi_batch
-
-# csv_query_avg
-query R
-SELECT avg(c12) FROM aggregate_test_100
-----
-0.5089725099127211
-
-# csv_query_covariance_1
-query R
-SELECT covar_pop(c2, c12) FROM aggregate_test_100
-----
--0.07916932235380847
-
-# csv_query_covariance_2
-query R
-SELECT covar(c2, c12) FROM aggregate_test_100
-----
--0.07996901247859442
-
-# csv_query_correlation
-query R
-SELECT corr(c2, c12) FROM aggregate_test_100
-----
--0.19064544190576607
-
-# csv_query_variance_1
-query R
-SELECT var_pop(c2) FROM aggregate_test_100
-----
-1.8675
-
-# original: 26156334342021890000000000000000000000
-# csv_query_variance_2
-query R
-SELECT var_pop(c6) FROM aggregate_test_100
-----
-2.615633434202189e37
-
-# csv_query_variance_3
-query R
-SELECT var_pop(c12) FROM aggregate_test_100
-----
-0.09234223721582163
-
-# csv_query_variance_4
-query R
-SELECT var(c2) FROM aggregate_test_100
-----
-1.8863636363636365
-
-# csv_query_variance_5
-query R
-SELECT var_samp(c2) FROM aggregate_test_100
-----
-1.8863636363636365
-
-# csv_query_stddev_1
-query R
-SELECT stddev_pop(c2) FROM aggregate_test_100
-----
-1.3665650368716449
-
-# original: 5114326382039172000
-# csv_query_stddev_2
-query R 
-SELECT stddev_pop(c6) FROM aggregate_test_100
-----
-5.114326382039172e18
-
-# csv_query_stddev_3
-query R
-SELECT stddev_pop(c12) FROM aggregate_test_100
-----
-0.30387865541334363
-
-# csv_query_stddev_4
-query R
-SELECT stddev(c12) FROM aggregate_test_100
-----
-0.3054095399405338
-
-# csv_query_stddev_5
-query R
-SELECT stddev_samp(c12) FROM aggregate_test_100
-----
-0.3054095399405338
-
-# csv_query_stddev_6
-query R
-select stddev(sq.column1) from (values (1.1), (2.0), (3.0)) as sq
-----
-0.9504384952922168
-
-# csv_query_approx_median_1
-query I
-SELECT approx_median(c2) FROM aggregate_test_100
-----
-3
-
-# csv_query_approx_median_2
-query I
-SELECT approx_median(c6) FROM aggregate_test_100
-----
-1146409980542786560
-
-# csv_query_approx_median_3
-query R
-SELECT approx_median(c12) FROM aggregate_test_100
-----
-0.5550065410522981
-
-# csv_query_median_1
-query I
-SELECT median(c2) FROM aggregate_test_100
-----
-3
-
-# csv_query_median_2
-query I
-SELECT median(c6) FROM aggregate_test_100
-----
-1125553990140691277
-
-# csv_query_median_3
-query R
-SELECT median(c12) FROM aggregate_test_100
-----
-0.5513900544385053
-
-# median_i8
-query I
-SELECT median(a) FROM median_i8
-----
--14
-
-# median_i16
-query I
-SELECT median(a) FROM median_i16
-----
--16334
-
-# median_i32
-query I
-SELECT median(a) FROM median_i32
-----
--1073741774
-
-# TODO: FIX - numbers are off?
-# median_i64
-# query I
-# SELECT median(a) FROM median_i64
-# ----
-# -4611686018427388000
-
-# median_u8
-query I
-SELECT median(a) FROM median_u8
-----
-50
-
-# median_u16
-query I
-SELECT median(a) FROM median_u16
-----
-50
-
-# median_u32
-query I
-SELECT median(a) FROM median_u32
-----
-50
-
-# median_u64
-query I
-SELECT median(a) FROM median_u64
-----
-50
-
-# median_f32
-query R
-SELECT median(a) FROM median_f32
-----
-3.3
-
-# median_f64
-query R
-SELECT median(a) FROM median_f64
-----
-3.3
-
-# median_f64_nan
-query T
-SELECT median(a) FROM median_f64_nan
-----
-NaN
-
-# approx_median_f64_nan
-query T
-SELECT approx_median(a) FROM median_f64_nan
-----
-NaN
-
-# csv_query_external_table_count
-query I
-SELECT COUNT(c12) FROM aggregate_test_100
-----
-100
-
-# csv_query_external_table_sum
-query II
-SELECT SUM(CAST(c7 AS BIGINT)), SUM(CAST(c8 AS BIGINT)) FROM aggregate_test_100
-----
-13060 3017641
-
-# csv_query_count
-query I
-SELECT count(c12) FROM aggregate_test_100
-----
-100
-
-# csv_query_count_distinct
-query I
-SELECT count(distinct c2) FROM aggregate_test_100
-----
-5
-
-# csv_query_count_distinct_expr
-query I
-SELECT count(distinct c2 % 2) FROM aggregate_test_100
-----
-2
-
-# csv_query_count_star
-query I
-SELECT COUNT(*) FROM aggregate_test_100
-----
-100
-
-# csv_query_count_literal
-query I
-SELECT COUNT(2) FROM aggregate_test_100
-----
-100
-
-# csv_query_approx_count
-# FIX: https://github.com/apache/arrow-datafusion/issues/3353
-# query II
-# SELECT approx_distinct(c9) AS count_c9, approx_distinct(cast(c9 as varchar)) count_c9_str FROM aggregate_test_100
-# ----
-# 100 99
-
-# csv_query_approx_count_dupe_expr_aliased
-query II
-SELECT approx_distinct(c9) AS a, approx_distinct(c9) AS b FROM aggregate_test_100
-----
-100 100
-
-# TODO: csv_query_approx_percentile_cont
-
-# TODO: fix decimal places
-# csv_query_cube_avg
-# query TIR
-# SELECT c1, c2, AVG(c3) FROM aggregate_test_100_by_sql GROUP BY CUBE (c1, c2) ORDER BY c1, c2
-# ----
-# a 1 -17.6
-# a 2 -15.333333333333334
-# a 3 -4.5
-# a 4 -32
-# a 5 -32
-# a  -18.333333333333332
-# b 1 31.666666666666668
-# b 2 25.5
-# b 3 -42
-# b 4 -44.6
-# b 5 -0.2
-# b  -5.842105263157895
-# c 1 47.5
-# c 2 -55.57142857142857
-# c 3 47.5
-# c 4 -10.75
-# c 5 12
-# c  -1.3333333333333333
-# d 1 -8.142857142857142
-# d 2 109.33333333333333
-# d 3 41.333333333333336
-# d 4 54
-# d 5 -49.5
-# d  25.444444444444443
-# e 1 75.66666666666667
-# e 2 37.8
-# e 3 48
-# e 4 37.285714285714285
-# e 5 -11
-# e  40.333333333333336
-#  1 16.681818181818183
-#  2 8.363636363636363
-#  3 20.789473684210527
-#  4 1.2608695652173914
-#  5 -13.857142857142858
-#    7.81
-
-# TODO: fix decimal places
-# csv_query_rollup_avg
-# query IIII
-# SELECT c1, c2, c3, AVG(c4) FROM aggregate_test_100_by_sql GROUP BY ROLLUP (c1, c2, c3) ORDER BY c1, c2, c3
-# ----
-# a 1 -85 -15154
-# a 1 -56 8692
-# a 1 -25 15295
-# a 1 -5 12636
-# a 1 83 -14704
-# a 1  1353
-# a 2 -48 -18025
-# a 2 -43 13080
-# a 2 45 15673
-# a 2  3576
-# a 3 -72 -11122
-# a 3 -12 -9168
-# a 3 13 22338.5
-# a 3 14 28162
-# a 3 17 -22796
-# a 3  4958.833333333333
-# a 4 -101 11640
-# a 4 -54 -2376
-# a 4 -38 20744
-# a 4 65 -28462
-# a 4  386.5
-# a 5 -101 -12484
-# a 5 -31 -12907
-# a 5 36 -16974
-# a 5  -14121.666666666666
-# a   306.04761904761904
-# b 1 12 7652
-# b 1 29 -18218
-# b 1 54 -18410
-# b 1  -9658.666666666666
-# b 2 -60 -21739
-# b 2 31 23127
-# b 2 63 21456
-# b 2 68 15874
-# b 2  9679.5
-# b 3 -101 -13217
-# b 3 17 14457
-# b 3  620
-# b 4 -117 19316
-# b 4 -111 -1967
-# b 4 -59 25286
-# b 4 17 -28070
-# b 4 47 20690
-# b 4  7051
-# b 5 -82 22080
-# b 5 -44 15788
-# b 5 -5 24896
-# b 5 62 16337
-# b 5 68 21576
-# b 5  20135.4
-# b   7732.315789473684
-# c 1 -24 -24085
-# c 1 41 -4667
-# c 1 70 27752
-# c 1 103 -22186
-# c 1  -5796.5
-# c 2 -117 -30187
-# c 2 -107 -2904
-# c 2 -106 -1114
-# c 2 -60 -16312
-# c 2 -29 25305
-# c 2 1 18109
-# c 2 29 -3855
-# c 2  -1565.4285714285713
-# c 3 -2 -18655
-# c 3 22 13741
-# c 3 73 -9565
-# c 3 97 29106
-# c 3  3656.75
-# c 4 -90 -2935
-# c 4 -79 5281
-# c 4 3 -30508
-# c 4 123 16620
-# c 4  -2885.5
-# c 5 -94 -15880
-# c 5 118 19208
-# c 5  1664
-# c   -1320.5238095238096
-# d 1 -99 5613
-# d 1 -98 13630
-# d 1 -72 25590
-# d 1 -8 27138
-# d 1 38 18384
-# d 1 57 28781
-# d 1 125 31106
-# d 1  21463.14285714286
-# d 2 93 -12642
-# d 2 113 3917
-# d 2 122 10130
-# d 2  468.3333333333333
-# d 3 -76 8809
-# d 3 77 15091
-# d 3 123 29533
-# d 3  17811
-# d 4 5 -7688
-# d 4 55 -1471
-# d 4 102 -24558
-# d 4  -11239
-# d 5 -59 2045
-# d 5 -40 22614
-# d 5  12329.5
-# d   10890.111111111111
-# e 1 36 -21481
-# e 1 71 -5479
-# e 1 120 10837
-# e 1  -5374.333333333333
-# e 2 -61 -2888
-# e 2 49 24495
-# e 2 52 5666
-# e 2 97 18167
-# e 2  10221.2
-# e 3 -95 13611
-# e 3 71 194
-# e 3 104 -25136
-# e 3 112 -6823
-# e 3  -4538.5
-# e 4 -56 -31500
-# e 4 -53 13788
-# e 4 30 -16110
-# e 4 73 -22501
-# e 4 74 -12612
-# e 4 96 -30336
-# e 4 97 -13181
-# e 4  -16064.57142857143
-# e 5 -86 32514
-# e 5 64 -26526
-# e 5  2994
-# e   -4268.333333333333
-#    2319.97
-
-# csv_query_approx_percentile_cont_with_weight
-query II
-SELECT c1, approx_percentile_cont(c3, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
-----
-a 73
-b 68
-c 122
-d 124
-e 115
-
-# csv_query_approx_percentile_cont_with_weight (2)
-query II
-SELECT c1, approx_percentile_cont_with_weight(c3, 1, 0.95) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
-----
-a 73
-b 68
-c 122
-d 124
-e 115
-
-# csv_query_approx_percentile_cont_with_histogram_bins
-query II
-SELECT c1, approx_percentile_cont(c3, 0.95, 200) AS c3_p95 FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
-----
-a 73
-b 68
-c 122
-d 124
-e 115
-
-# csv_query_sum_crossjoin
-query III
-SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY a.c1, b.c1 ORDER BY a.c1, b.c1
-----
-a a 1260
-a b 1140
-a c 1260
-a d 1080
-a e 1260
-b a 1302
-b b 1178
-b c 1302
-b d 1116
-b e 1302
-c a 1176
-c b 1064
-c c 1176
-c d 1008
-c e 1176
-d a 924
-d b 836
-d c 924
-d d 792
-d e 924
-e a 1323
-e b 1197
-e c 1323
-e d 1134
-e e 1323
-
-# csv_query_cube_sum_crossjoin
-query III
-SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY CUBE (a.c1, b.c1) ORDER BY a.c1, b.c1
-----
-a a 1260
-a b 1140
-a c 1260
-a d 1080
-a e 1260
-a   6000
-b a 1302
-b b 1178
-b c 1302
-b d 1116
-b e 1302
-b   6200
-c a 1176
-c b 1064
-c c 1176
-c d 1008
-c e 1176
-c   5600
-d a 924
-d b 836
-d c 924
-d d 792
-d e 924
-d   4400
-e a 1323
-e b 1197
-e c 1323
-e d 1134
-e e 1323
-e   6300
-  a 5985
-  b 5415
-  c 5985
-  d 5130
-  e 5985
-    28500
-
-# csv_query_cube_distinct_count
-query III
-SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY CUBE (c1,c2) ORDER BY c1,c2
-----
-a 1 5
-a 2 3
-a 3 5
-a 4 4
-a 5 3
-a   19
-b 1 3
-b 2 4
-b 3 2
-b 4 5
-b 5 5
-b   17
-c 1 4
-c 2 7
-c 3 4
-c 4 4
-c 5 2
-c   21
-d 1 7
-d 2 3
-d 3 3
-d 4 3
-d 5 2
-d   18
-e 1 3
-e 2 4
-e 3 4
-e 4 7
-e 5 2
-e   18
-  1 22
-  2 20
-  3 17
-  4 23
-  5 14
-    80
-
-# csv_query_rollup_distinct_count
-query III
-SELECT c1, c2, COUNT(DISTINCT c3) FROM aggregate_test_100 GROUP BY ROLLUP (c1,c2) ORDER BY c1,c2
-----
-a 1 5
-a 2 3
-a 3 5
-a 4 4
-a 5 3
-a   19
-b 1 3
-b 2 4
-b 3 2
-b 4 5
-b 5 5
-b   17
-c 1 4
-c 2 7
-c 3 4
-c 4 4
-c 5 2
-c   21
-d 1 7
-d 2 3
-d 3 3
-d 4 3
-d 5 2
-d   18
-e 1 3
-e 2 4
-e 3 4
-e 4 7
-e 5 2
-e  18
-   80
-
-# csv_query_rollup_sum_crossjoin
-query III
-SELECT a.c1, b.c1, SUM(a.c2) FROM aggregate_test_100 as a CROSS JOIN aggregate_test_100 as b GROUP BY ROLLUP (a.c1, b.c1) ORDER BY a.c1, b.c1
-----
-a a 1260
-a b 1140
-a c 1260
-a d 1080
-a e 1260
-a   6000
-b a 1302
-b b 1178
-b c 1302
-b d 1116
-b e 1302
-b   6200
-c a 1176
-c b 1064
-c c 1176
-c d 1008
-c e 1176
-c   5600
-d a 924
-d b 836
-d c 924
-d d 792
-d e 924
-d   4400
-e a 1323
-e b 1197
-e c 1323
-e d 1134
-e e 1323
-e   6300
-    28500
-
-# query_count_without_from
-query I
-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 I
-# SELECT array_agg(c13) FROM (SELECT * FROM aggregate_test_100 ORDER BY c13 LIMIT 2) test
-# ----
-# [0VVIHzxWtNOFLtnhjHEKjXaJOSLJfm0keZ5G8BffGwgF2RwQD59TFzMStxCB]
-
-# FIX: see above
-# csv_query_array_agg_empty
-# 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]
-
-# FIX: Decimal error
-# csv_query_array_agg_with_overflow
-# query IIIIII
-# select c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by c2 order by c2
-# ----
-# 1 367 16.681818181818183 125 -99 22
-# 2 184 8.363636363636363 122 -117 22
-# 3 395 20.789473684210527 123 -101 19
-# 4 29 1.2608695652173914 123 -117 23
-# 5 -194 -13.857142857142858 118 -101 14
-
-# TODO: csv_query_array_agg_unsupported
-
-# FIX: Decimal error
-# csv_query_array_cube_agg_with_overflow
-# query IIIIIII
-# select c1, c2, sum(c3) sum_c3, avg(c3) avg_c3, max(c3) max_c3, min(c3) min_c3, count(c3) count_c3 from aggregate_test_100 group by CUBE (c1,c2) order by c1, c2
-# ----
-# a 1 -88 -17.6 83 -85 5
-# a 2 -46 -15.333333333333334 45 -48 3
-# a 3 -27 -4.5 17 -72 6
-# a 4 -128 -32 65 -101 4
-# a 5 -96 -32 36 -101 3
-# a  -385 -18.333333333333332 83 -101 21
-# b 1 95 31.666666666666668 54 12 3
-# b 2 102 25.5 68 -60 4
-# b 3 -84 -42 17 -101 2
-# b 4 -223 -44.6 47 -117 5
-# b 5 -1 -0.2 68 -82 5
-# b  -111 -5.842105263157895 68 -117 19
-# c 1 190 47.5 103 -24 4
-# c 2 -389 -55.57142857142857 29 -117 7
-# c 3 190 47.5 97 -2 4
-# c 4 -43 -10.75 123 -90 4
-# c 5 24 12 118 -94 2
-# c  -28 -1.3333333333333333 123 -117 21
-# d 1 -57 -8.142857142857142 125 -99 7
-# d 2 328 109.33333333333333 122 93 3
-# d 3 124 41.333333333333336 123 -76 3
-# d 4 162 54 102 5 3
-# d 5 -99 -49.5 -40 -59 2
-# d  458 25.444444444444443 125 -99 18
-# e 1 227 75.66666666666667 120 36 3
-# e 2 189 37.8 97 -61 5
-# e 3 192 48 112 -95 4
-# e 4 261 37.285714285714285 97 -56 7
-# e 5 -22 -11 64 -86 2
-# e  847 40.333333333333336 120 -95 21
-#  1 367 16.681818181818183 125 -99 22
-#  2 184 8.363636363636363 122 -117 22
-#  3 395 20.789473684210527 123 -101 19
-#  4 29 1.2608695652173914 123 -117 23
-#  5 -194 -13.857142857142858 118 -101 14
-#   781 7.81 125 -117 100
-
-# TODO: csv_query_array_agg_distinct
-
-# TODO: aggregate_timestamps_sum
-
-# TODO: aggregate_timestamps_count
-
-# TODO: aggregate_timestamps_min
-
-# TODO: aggregate_timestamps_max
-
-# TODO: aggregate_times_sum
-
-# TODO: aggregate_times_count
-
-# TODO: aggregate_times_min
-
-# TODO: aggregate_times_max
-
-# TODO: aggregate_timestamps_avg
-
-# aggregate_time_min_and_max
-query II
-select min(t), max(t) from  (select '00:00:00' as t union select '00:00:01' union select '00:00:02')
-----
-00:00:00 00:00:02
-
-# aggregate_decimal_min
-query I
-select min(c1) from d_table
-----
--100.009
-
-# aggregate_decimal_max
-query I
-select max(c1) from d_table
-----
-110.009
-
-query I
-select sum(c1) from d_table
-----
-100.000
-
-# FIX: doesn't check datatype
-# aggregate_decimal_avg
-query I
-select avg(c1) from d_table
-----
-5.0000000
-
-# FIX: different test table
-# aggregate
-# query I
-# SELECT SUM(c1), SUM(c2) FROM test
-# ----
-# 60 220
-
-# TODO: aggregate_empty
-
-# TODO: aggregate_avg
-
-# TODO: aggregate_max
-
-# TODO: aggregate_min
-
-# TODO: aggregate_grouped
-
-# TODO: aggregate_grouped_avg
-
-# TODO: aggregate_grouped_empty
-
-# TODO: aggregate_grouped_max
-
-# TODO: aggregate_grouped_min
-
-# TODO: aggregate_avg_add
-
-# TODO: case_sensitive_identifiers_aggregates
-
-# TODO: count_basic
-
-# TODO: count_partitioned
-
-# TODO: count_aggregated
-
-# TODO: count_aggregated_cube
-
-# TODO: simple_avg
-
-# TODO: simple_mean
-
-# TOOD: bottom 2 require pre-populated data
-# query_sum_distinct
-query II
-SELECT AVG(c1), SUM(DISTINCT c2) FROM test
-----
-1.75 3
-
-# # query_count_distinct
-query I
-SELECT COUNT(DISTINCT c1) FROM test
-----
-3
-
-# TODO: count_distinct_integers_aggregated_single_partition
-
-# TODO: count_distinct_integers_aggregated_multiple_partitions
-
-# TODO: aggregate_with_alias
-
-
-# FIX: CSV Writer error
-# array_agg_zero
-# query I
-# SELECT ARRAY_AGG([])
-# ----
-# []
-
-# FIX: CSV Writer error
-# array_agg_one
-# query I
-# SELECT ARRAY_AGG([1])
-# ----
-# [[1]]
-
-# test_approx_percentile_cont_decimal_support
-query II
-SELECT c1, approx_percentile_cont(c2, cast(0.85 as decimal(10,2))) apc FROM aggregate_test_100 GROUP BY 1 ORDER BY 1
-----
-a 4
-b 5
-c 4
-d 4
-e 4
\ No newline at end of file
diff --git a/tests/sqllogictests/test_files/arrow_typeof.slt b/tests/sqllogictests/test_files/arrow_typeof.slt
deleted file mode 100644
index f8baaff18dc86..0000000000000
--- a/tests/sqllogictests/test_files/arrow_typeof.slt
+++ /dev/null
@@ -1,65 +0,0 @@
-# arrow_typeof_null
-query T
-SELECT arrow_typeof(null)
-----
-Null
-
-# arrow_typeof_boolean
-query T
-SELECT arrow_typeof(true)
-----
-Boolean
-
-# arrow_typeof_i64
-query T
-SELECT arrow_typeof(1)
-----
-Int64
-
-# arrow_typeof_i32
-query T
-SELECT arrow_typeof(1::int)
-----
-Int32
-
-# arrow_typeof_f64
-query T
-SELECT arrow_typeof(1.0)
-----
-Float64
-
-# arrow_typeof_f32
-query T
-SELECT arrow_typeof(1.0::float)
-----
-Float32
-
-# arrow_typeof_decimal
-# query T
-# SELECT arrow_typeof(1::Decimal)
-# ----
-# Decimal128(38, 10)
-
-# # arrow_typeof_timestamp
-# query T
-# SELECT arrow_typeof(now()::timestamp)
-# ----
-# Timestamp(Nanosecond, None)
-
-# # arrow_typeof_timestamp_utc
-# query T
-# SELECT arrow_typeof(now())
-# ----
-# Timestamp(Nanosecond, Some(\"+00:00\"))
-
-# # arrow_typeof_timestamp_date32(
-# query T
-# SELECT arrow_typeof(now()::date)
-# ----
-# Date32
-
-# # arrow_typeof_utf8
-# query T
-# SELECT arrow_typeof('1')
-# ----
-# Utf8

From 7c93b38ae5ef40f39eb3efce2b1c7ef92b253a9f Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:25:51 -0500
Subject: [PATCH 10/19] Add licences

---
 LICENSE.txt                                   | 212 ------------------
 NOTICE.txt                                    |  84 -------
 datafusion/core/tests/sqllogictests/README.md |  19 ++
 .../sqllogictests/test_files/aggregate.slt    |  17 ++
 .../sqllogictests/test_files/arrow_typeof.slt |  17 ++
 5 files changed, 53 insertions(+), 296 deletions(-)
 delete mode 100644 LICENSE.txt
 delete mode 100644 NOTICE.txt

diff --git a/LICENSE.txt b/LICENSE.txt
deleted file mode 100644
index d74c6b599d2ae..0000000000000
--- a/LICENSE.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
-
-
-This project includes code from Apache Aurora.
-
-* dev/release/{release,changelog,release-candidate} are based on the scripts from
-  Apache Aurora
-
-Copyright: 2016 The Apache Software Foundation.
-Home page: https://aurora.apache.org/
-License: http://www.apache.org/licenses/LICENSE-2.0
diff --git a/NOTICE.txt b/NOTICE.txt
deleted file mode 100644
index a609791374c28..0000000000000
--- a/NOTICE.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-Apache Arrow
-Copyright 2016-2019 The Apache Software Foundation
-
-This product includes software developed at
-The Apache Software Foundation (http://www.apache.org/).
-
-This product includes software from the SFrame project (BSD, 3-clause).
-* Copyright (C) 2015 Dato, Inc.
-* Copyright (c) 2009 Carnegie Mellon University.
-
-This product includes software from the Feather project (Apache 2.0)
-https://github.com/wesm/feather
-
-This product includes software from the DyND project (BSD 2-clause)
-https://github.com/libdynd
-
-This product includes software from the LLVM project
- * distributed under the University of Illinois Open Source
-
-This product includes software from the google-lint project
- * Copyright (c) 2009 Google Inc. All rights reserved.
-
-This product includes software from the mman-win32 project
- * Copyright https://code.google.com/p/mman-win32/
- * Licensed under the MIT License;
-
-This product includes software from the LevelDB project
- * Copyright (c) 2011 The LevelDB Authors. All rights reserved.
- * Use of this source code is governed by a BSD-style license that can be
- * Moved from Kudu http://github.com/cloudera/kudu
-
-This product includes software from the CMake project
- * Copyright 2001-2009 Kitware, Inc.
- * Copyright 2012-2014 Continuum Analytics, Inc.
- * All rights reserved.
-
-This product includes software from https://github.com/matthew-brett/multibuild (BSD 2-clause)
- * Copyright (c) 2013-2016, Matt Terry and Matthew Brett; all rights reserved.
-
-This product includes software from the Ibis project (Apache 2.0)
- * Copyright (c) 2015 Cloudera, Inc.
- * https://github.com/cloudera/ibis
-
-This product includes software from Dremio (Apache 2.0)
-  * Copyright (C) 2017-2018 Dremio Corporation
-  * https://github.com/dremio/dremio-oss
-
-This product includes software from Google Guava (Apache 2.0)
-  * Copyright (C) 2007 The Guava Authors
-  * https://github.com/google/guava
-
-This product include software from CMake (BSD 3-Clause)
-  * CMake - Cross Platform Makefile Generator
-  * Copyright 2000-2019 Kitware, Inc. and Contributors
-
-The web site includes files generated by Jekyll.
-
---------------------------------------------------------------------------------
-
-This product includes code from Apache Kudu, which includes the following in
-its NOTICE file:
-
-  Apache Kudu
-  Copyright 2016 The Apache Software Foundation
-
-  This product includes software developed at
-  The Apache Software Foundation (http://www.apache.org/).
-
-  Portions of this software were developed at
-  Cloudera, Inc (http://www.cloudera.com/).
-
---------------------------------------------------------------------------------
-
-This product includes code from Apache ORC, which includes the following in
-its NOTICE file:
-
-  Apache ORC
-  Copyright 2013-2019 The Apache Software Foundation
-
-  This product includes software developed by The Apache Software
-  Foundation (http://www.apache.org/).
-
-  This product includes software developed by Hewlett-Packard:
-  (c) Copyright [2014-2015] Hewlett-Packard Development Company, L.P
diff --git a/datafusion/core/tests/sqllogictests/README.md b/datafusion/core/tests/sqllogictests/README.md
index 7f584543c3b82..3a5b49a754329 100644
--- a/datafusion/core/tests/sqllogictests/README.md
+++ b/datafusion/core/tests/sqllogictests/README.md
@@ -1,3 +1,22 @@
+<!---
+  Licensed to the Apache Software Foundation (ASF) under one
+  or more contributor license agreements.  See the NOTICE file
+  distributed with this work for additional information
+  regarding copyright ownership.  The ASF licenses this file
+  to you under the Apache License, Version 2.0 (the
+  "License"); you may not use this file except in compliance
+  with the License.  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing,
+  software distributed under the License is distributed on an
+  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+  KIND, either express or implied.  See the License for the
+  specific language governing permissions and limitations
+  under the License.
+-->
+
 #### Overview
 
 This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki). We use [sqllogictest-rs](https://github.com/risinglightdb/sqllogictest-rs) as a parser/runner of `.slt` files in `test_files`.
diff --git a/datafusion/core/tests/sqllogictests/test_files/aggregate.slt b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
index 8cb82923a5810..ca1b58732c08b 100644
--- a/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
+++ b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
@@ -1,3 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+
+#   http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
 # FIX: custom absolute values
 # csv_query_avg_multi_batch
 
diff --git a/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt b/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt
index f8baaff18dc86..8f1c006510f68 100644
--- a/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt
+++ b/datafusion/core/tests/sqllogictests/test_files/arrow_typeof.slt
@@ -1,3 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+
+# http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
 # arrow_typeof_null
 query T
 SELECT arrow_typeof(null)

From 67f9ed4d5d43ec446711888d6407a383875234de Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:26:44 -0500
Subject: [PATCH 11/19] Update CI check

---
 .github/workflows/rust.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index f5e84f3bcf065..86c22f7633b5e 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -544,4 +544,4 @@ jobs:
         with:
           rust-version: stable
       - name: Run sqllogictests
-        run: cargo run -p datafusion-sqllogictests
\ No newline at end of file
+        run: cargo test -p datafusion --test sqllogictests
\ No newline at end of file

From 6a682aaf6c4e82d707d3dde9ea519c8bc5b4a235 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:29:22 -0500
Subject: [PATCH 12/19] rust_lint.sh

---
 datafusion/core/Cargo.toml                      | 2 +-
 datafusion/core/tests/sqllogictests/src/main.rs | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/datafusion/core/Cargo.toml b/datafusion/core/Cargo.toml
index af62f155922c1..97bbfc1fd7af5 100644
--- a/datafusion/core/Cargo.toml
+++ b/datafusion/core/Cargo.toml
@@ -157,6 +157,6 @@ harness = false
 name = "merge"
 
 [[test]]
+harness = false
 name = "sqllogictests"
 path = "tests/sqllogictests/src/main.rs"
-harness = false
diff --git a/datafusion/core/tests/sqllogictests/src/main.rs b/datafusion/core/tests/sqllogictests/src/main.rs
index cd0529c1234e8..3d06c9e32fc8b 100644
--- a/datafusion/core/tests/sqllogictests/src/main.rs
+++ b/datafusion/core/tests/sqllogictests/src/main.rs
@@ -84,14 +84,14 @@ impl sqllogictest::AsyncDB for DataFusion {
     fn engine_name(&self) -> &str {
         "DataFusion"
     }
-    
+
     /// [`Runner`] calls this function to perform sleep.
     ///
     /// The default implementation is `std::thread::sleep`, which is universial to any async runtime
     /// but would block the current thread. If you are running in tokio runtime, you should override
     /// this by `tokio::time::sleep`.
     async fn sleep(dur: Duration) {
-       tokio::time::sleep(dur).await;
+        tokio::time::sleep(dur).await;
     }
 }
 

From d04e9b147206eb64f2828fc7bcda6690615a515c Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 19:33:07 -0500
Subject: [PATCH 13/19] Run prettier on readme

---
 datafusion/core/tests/sqllogictests/README.md | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/datafusion/core/tests/sqllogictests/README.md b/datafusion/core/tests/sqllogictests/README.md
index 3a5b49a754329..7f597ee4d4359 100644
--- a/datafusion/core/tests/sqllogictests/README.md
+++ b/datafusion/core/tests/sqllogictests/README.md
@@ -27,7 +27,6 @@ This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/s
 
 #### Setup
 
-
 #### sqllogictests
 
 > :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki
@@ -37,6 +36,7 @@ sqllogictest is a program originally written for SQLite to verify the correctnes
 Tests in the `.slt` file are a sequence of query record generally starting with `CREATE` statements to populate tables and then further queries to test the populated data (arrow-datafusion exception).
 
 Query records follow the format:
+
 ```sql
 # <test_name>
 query <type_string> <sort_mode> <label>
@@ -47,11 +47,10 @@ query <type_string> <sort_mode> <label>
 
 - `test_name`: Uniquely identify the test name (arrow-datafusion only)
 - `type_string`: A short string that specifies the number of result columns and the expected datatype of each result column. There is one character in the <type_string> for each result column. The characters codes are "T" for a text result, "I" for an integer result, and "R" for a floating-point result.
-- (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output. 
-- `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@". 
+- (Optional) `label`: sqllogictest stores a hash of the results of this query under the given label. If the label is reused, then sqllogictest verifies that the results are the same. This can be used to verify that two or more queries in the same test script that are logically equivalent always generate the same output.
+- `expected_result`: In the results section, integer values are rendered as if by printf("%d"). Floating point values are rendered as if by printf("%.3f"). NULL values are rendered as "NULL". Empty strings are rendered as "(empty)". Within non-empty strings, all control characters and unprintable characters are rendered as "@".
 - `sort_mode`: If included, it must be one of "nosort", "rowsort", or "valuesort". The default is "nosort". In nosort mode, the results appear in exactly the order in which they were received from the database engine. The nosort mode should only be used on queries that have an ORDER BY clause or which only have a single row of result, since otherwise the order of results is undefined and might vary from one database engine to another. The "rowsort" mode gathers all output from the database engine then sorts it by rows on the client side. Sort comparisons use strcmp() on the rendered ASCII text representation of the values. Hence, "9" sorts after "10", not before. The "valuesort" mode works like rowsort except that it does not honor row groupings. Each individual result value is sorted on its own.
 
-
 ##### Example
 
 ```sql

From fc131022883cbd71daaca251306b90ade40a2a83 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 21:04:18 -0500
Subject: [PATCH 14/19] Fix checks

---
 datafusion-cli/Cargo.lock | 218 ++++++++++++++++++++++++++++----------
 1 file changed, 161 insertions(+), 57 deletions(-)

diff --git a/datafusion-cli/Cargo.lock b/datafusion-cli/Cargo.lock
index 3eff2be29b4ed..718d56d96e9d4 100644
--- a/datafusion-cli/Cargo.lock
+++ b/datafusion-cli/Cargo.lock
@@ -23,9 +23,9 @@ dependencies = [
 
 [[package]]
 name = "aho-corasick"
-version = "0.7.19"
+version = "0.7.20"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4f55bd91a0978cbfd91c457a164bab8b4001c833b7f323132c0a4e1922dd44e"
+checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
 dependencies = [
  "memchr",
 ]
@@ -232,9 +232,9 @@ dependencies = [
 
 [[package]]
 name = "async-trait"
-version = "0.1.58"
+version = "0.1.59"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1e805d94e6b5001b651426cf4cd446b1ab5f319d27bab5c644f61de0a804360c"
+checksum = "31e6e93155431f3931513b243d371981bb2770112b370c82745a1d19d2f99364"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -247,7 +247,7 @@ version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
 dependencies = [
- "hermit-abi",
+ "hermit-abi 0.1.19",
  "libc",
  "winapi",
 ]
@@ -281,9 +281,9 @@ dependencies = [
 
 [[package]]
 name = "blake3"
-version = "1.3.1"
+version = "1.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a08e53fc5a564bb15bfe6fae56bd71522205f1f91893f9c0116edad6496c183f"
+checksum = "42ae2468a89544a466886840aa467a25b766499f4f04bf7d9fcd10ecee9fccef"
 dependencies = [
  "arrayref",
  "arrayvec",
@@ -349,9 +349,9 @@ checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
 
 [[package]]
 name = "bytes"
-version = "1.2.1"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec8a7b6a70fde80372154c65702f00a0f56f3e1c36abbc6c440484be248856db"
+checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c"
 
 [[package]]
 name = "bzip2"
@@ -376,9 +376,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.0.76"
+version = "1.0.77"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "76a284da2e6fe2092f2353e51713435363112dfd60030e22add80be333fb928f"
+checksum = "e9f73505338f7d905b19d18738976aae232eb46b8efc15554ffc56deb5d9ebe4"
 dependencies = [
  "jobserver",
 ]
@@ -410,8 +410,8 @@ checksum = "71655c45cb9845d3270c9d6df84ebe72b4dad3c2ba3f7023ad47c144e4e473a5"
 dependencies = [
  "atty",
  "bitflags",
- "clap_derive",
- "clap_lex",
+ "clap_derive 3.2.18",
+ "clap_lex 0.2.4",
  "indexmap",
  "once_cell",
  "strsim",
@@ -419,6 +419,21 @@ dependencies = [
  "textwrap",
 ]
 
+[[package]]
+name = "clap"
+version = "4.0.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4d63b9e9c07271b9957ad22c173bae2a4d9a81127680962039296abcd2f8251d"
+dependencies = [
+ "bitflags",
+ "clap_derive 4.0.21",
+ "clap_lex 0.3.0",
+ "is-terminal",
+ "once_cell",
+ "strsim",
+ "termcolor",
+]
+
 [[package]]
 name = "clap_derive"
 version = "3.2.18"
@@ -432,6 +447,19 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "clap_derive"
+version = "4.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0177313f9f02afc995627906bbd8967e2be069f5261954222dac78290c2b9014"
+dependencies = [
+ "heck",
+ "proc-macro-error",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "clap_lex"
 version = "0.2.4"
@@ -441,6 +469,15 @@ dependencies = [
  "os_str_bytes",
 ]
 
+[[package]]
+name = "clap_lex"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d4198f73e42b4936b35b5bb248d81d2b595ecb170da0bac7655c54eedfa8da8"
+dependencies = [
+ "os_str_bytes",
+]
+
 [[package]]
 name = "clipboard-win"
 version = "4.4.2"
@@ -464,9 +501,9 @@ dependencies = [
 
 [[package]]
 name = "comfy-table"
-version = "6.1.2"
+version = "6.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1090f39f45786ec6dc6286f8ea9c75d0a7ef0a0d3cda674cef0c3af7b307fbc2"
+checksum = "e621e7e86c46fd8a14c32c6ae3cb95656621b4743a27d0cffedb831d46e7ad21"
 dependencies = [
  "strum",
  "strum_macros",
@@ -497,9 +534,9 @@ dependencies = [
 
 [[package]]
 name = "constant_time_eq"
-version = "0.1.5"
+version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "245097e9a4535ee1e3e3931fcfcd55a796a44c643e8596ff6566d68f09b87bbc"
+checksum = "f3ad85c1f65dc7b37604eb0e89748faf0b9653065f2a8ef69f96a687ec1e9279"
 
 [[package]]
 name = "core-foundation-sys"
@@ -565,9 +602,9 @@ dependencies = [
 
 [[package]]
 name = "cxx"
-version = "1.0.81"
+version = "1.0.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "97abf9f0eca9e52b7f81b945524e76710e6cb2366aead23b7d4fbf72e281f888"
+checksum = "d4a41a86530d0fe7f5d9ea779916b7cadd2d4f9add748b99c2c029cbbdfaf453"
 dependencies = [
  "cc",
  "cxxbridge-flags",
@@ -577,9 +614,9 @@ dependencies = [
 
 [[package]]
 name = "cxx-build"
-version = "1.0.81"
+version = "1.0.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7cc32cc5fea1d894b77d269ddb9f192110069a8a9c1f1d441195fba90553dea3"
+checksum = "06416d667ff3e3ad2df1cd8cd8afae5da26cf9cec4d0825040f88b5ca659a2f0"
 dependencies = [
  "cc",
  "codespan-reporting",
@@ -592,15 +629,15 @@ dependencies = [
 
 [[package]]
 name = "cxxbridge-flags"
-version = "1.0.81"
+version = "1.0.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8ca220e4794c934dc6b1207c3b42856ad4c302f2df1712e9f8d2eec5afaacf1f"
+checksum = "820a9a2af1669deeef27cb271f476ffd196a2c4b6731336011e0ba63e2c7cf71"
 
 [[package]]
 name = "cxxbridge-macro"
-version = "1.0.81"
+version = "1.0.82"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b846f081361125bfc8dc9d3940c84e1fd83ba54bbca7b17cd29483c828be0704"
+checksum = "a08a6e2fcc370a089ad3b4aaf54db3b1b4cee38ddabce5896b33eb693275f470"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -654,6 +691,7 @@ dependencies = [
  "pin-project-lite",
  "rand",
  "smallvec",
+ "sqllogictest",
  "sqlparser",
  "tempfile",
  "tokio",
@@ -668,7 +706,7 @@ name = "datafusion-cli"
 version = "14.0.0"
 dependencies = [
  "arrow",
- "clap",
+ "clap 3.2.23",
  "datafusion",
  "dirs",
  "env_logger",
@@ -763,6 +801,12 @@ dependencies = [
  "sqlparser",
 ]
 
+[[package]]
+name = "difference"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "524cbf6897b527295dff137cec09ecf3a05f4fddffd7dfcd1585403449e74198"
+
 [[package]]
 name = "digest"
 version = "0.10.6"
@@ -918,9 +962,9 @@ dependencies = [
 
 [[package]]
 name = "flate2"
-version = "1.0.24"
+version = "1.0.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f82b0f4c27ad9f8bfd1f3208d882da2b09c301bc1c828fd3a00d0216d2fbbff6"
+checksum = "a8a2db397cb1c8772f31494cb8917e48cd1e64f0fa7efac59fbd741a0a8ce841"
 dependencies = [
  "crc32fast",
  "miniz_oxide",
@@ -1116,6 +1160,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "hermit-abi"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ee512640fe35acbfb4bb779db6f0d80704c2cacfa2e39b601ef3e3f47d1ae4c7"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "http"
 version = "0.2.8"
@@ -1229,9 +1282,9 @@ dependencies = [
 
 [[package]]
 name = "indexmap"
-version = "1.9.1"
+version = "1.9.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "10a35a97730320ffe8e2d410b5d3b69279b98d2c14bdb8b70ea89ecf7888d41e"
+checksum = "1885e79c1fc4b10f0e172c475f458b7f7b93061064d98c3293e98c5ba0c8b399"
 dependencies = [
  "autocfg",
  "hashbrown 0.12.3",
@@ -1254,9 +1307,9 @@ checksum = "8bb03732005da905c88227371639bf1ad885cc712789c011c31c5fb3ab3ccf02"
 
 [[package]]
 name = "io-lifetimes"
-version = "1.0.1"
+version = "1.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7d367024b3f3414d8e01f437f704f41a9f64ab36f9067fa73e526ad4c763c87"
+checksum = "46112a93252b123d31a119a8d1a1ac19deac4fac6e0e8b0df58f0d4e5870e63c"
 dependencies = [
  "libc",
  "windows-sys",
@@ -1268,6 +1321,18 @@ version = "2.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f88c5561171189e69df9d98bcf18fd5f9558300f7ea7b801eb8a0fd748bd8745"
 
+[[package]]
+name = "is-terminal"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "927609f78c2913a6f6ac3c27a4fe87f43e2a35367c0c4b0f8265e8f49a104330"
+dependencies = [
+ "hermit-abi 0.2.6",
+ "io-lifetimes",
+ "rustix",
+ "windows-sys",
+]
+
 [[package]]
 name = "itertools"
 version = "0.10.5"
@@ -1399,6 +1464,17 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "libtest-mimic"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7b603516767d1ab23d0de09d023e62966c3322f7148297c35cf3d97aa8b37fa"
+dependencies = [
+ "clap 4.0.29",
+ "termcolor",
+ "threadpool",
+]
+
 [[package]]
 name = "link-cplusplus"
 version = "1.0.7"
@@ -1410,9 +1486,9 @@ dependencies = [
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.1.2"
+version = "0.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bb68f22743a3fb35785f1e7f844ca5a3de2dde5bd0c0ef5b372065814699b121"
+checksum = "8f9f08d8963a6c613f4b1a78f4f4a4dbfadf8e6545b2d72861731e4858b8b47f"
 
 [[package]]
 name = "lock_api"
@@ -1485,9 +1561,9 @@ checksum = "2a60c7ce501c71e03a9c9c0d35b861413ae925bd979cc7a4e30d060069aaac8d"
 
 [[package]]
 name = "miniz_oxide"
-version = "0.5.4"
+version = "0.6.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "96590ba8f175222643a85693f33d26e9c8a015f599c216509b1a6894af675d34"
+checksum = "b275950c28b37e794e8c55d88aeb5e139d0ce23fdbbeda68f8d7174abdf9e8fa"
 dependencies = [
  "adler",
 ]
@@ -1627,7 +1703,7 @@ version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f6058e64324c71e02bc2b150e4f3bc8286db6c83092132ffa3f6b1eab0f9def5"
 dependencies = [
- "hermit-abi",
+ "hermit-abi 0.1.19",
  "libc",
 ]
 
@@ -1676,9 +1752,9 @@ dependencies = [
 
 [[package]]
 name = "os_str_bytes"
-version = "6.4.0"
+version = "6.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b5bf27447411e9ee3ff51186bf7a08e16c341efdde93f4d823e8844429bed7e"
+checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee"
 
 [[package]]
 name = "parking_lot"
@@ -1692,9 +1768,9 @@ dependencies = [
 
 [[package]]
 name = "parking_lot_core"
-version = "0.9.4"
+version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4dc9e0dc2adc1c69d09143aff38d3d30c5c3f0df0dad82e6d25547af174ebec0"
+checksum = "7ff9f3fef3968a3ec5945535ed654cb38ff72d7495a25619e2247fb15a2ed9ba"
 dependencies = [
  "cfg-if",
  "libc",
@@ -1977,9 +2053,9 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "0.36.1"
+version = "0.36.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "812a2ec2043c4d6bc6482f5be2ab8244613cac2493d128d36c0759e52a626ab3"
+checksum = "cb93e85278e08bb5788653183213d3a60fc242b10cb9be96586f5a73dcb67c23"
 dependencies = [
  "bitflags",
  "errno",
@@ -2084,18 +2160,18 @@ checksum = "0772c5c30e1a0d91f6834f8e545c69281c099dfa9a3ac58d96a9fd629c8d4898"
 
 [[package]]
 name = "serde"
-version = "1.0.147"
+version = "1.0.148"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d193d69bae983fc11a79df82342761dfbf28a99fc8d203dca4c3c1b590948965"
+checksum = "e53f64bb4ba0191d6d0676e1b141ca55047d83b74f5607e6d8eb88126c52c2dc"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.147"
+version = "1.0.148"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f1d362ca8fc9c3e3a7484440752472d68a6caa98f1ab81d99b5dfe517cec852"
+checksum = "a55492425aa53521babf6137309e7d34c20bbfbbfcfe2c7f3a047fd1f6b92c0c"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2104,9 +2180,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.87"
+version = "1.0.89"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6ce777b7b150d76b9cf60d28b55f5847135a003f7d7350c6be7a773508ce7d45"
+checksum = "020ff22c755c2ed3f8cf162dbb41a7268d934702f3ed3631656ea597e08fc3db"
 dependencies = [
  "itoa 1.0.4",
  "ryu",
@@ -2175,9 +2251,9 @@ dependencies = [
 
 [[package]]
 name = "snap"
-version = "1.0.5"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "45456094d1983e2ee2a18fdfebce3189fa451699d0502cb8e3b49dba5ba41451"
+checksum = "5e9f0ab6ef7eb7353d9119c170a436d1bf248eea575ac42d19d12f4e34130831"
 
 [[package]]
 name = "socket2"
@@ -2195,6 +2271,25 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6e63cff320ae2c57904679ba7cb63280a3dc4613885beafb148ee7bf9aa9042d"
 
+[[package]]
+name = "sqllogictest"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba41e01d229d7725401de371e323851f82d839d68732a06162405362b60852fe"
+dependencies = [
+ "async-trait",
+ "difference",
+ "futures",
+ "glob",
+ "humantime",
+ "itertools",
+ "libtest-mimic",
+ "regex",
+ "tempfile",
+ "thiserror",
+ "tracing",
+]
+
 [[package]]
 name = "sqlparser"
 version = "0.27.0"
@@ -2249,9 +2344,9 @@ checksum = "6bdef32e8150c2a081110b42772ffe7d7c9032b606bc226c8260fd97e0976601"
 
 [[package]]
 name = "syn"
-version = "1.0.103"
+version = "1.0.104"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a864042229133ada95abf3b54fdc62ef5ccabe9515b64717bcb9a1919e59445d"
+checksum = "4ae548ec36cf198c0ef7710d3c230987c2d6d7bd98ad6edc0274462724c585ce"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -2307,6 +2402,15 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "threadpool"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d050e60b33d41c19108b32cea32164033a9013fe3b46cbd4457559bfbf77afaa"
+dependencies = [
+ "num_cpus",
+]
+
 [[package]]
 name = "thrift"
 version = "0.16.0"
@@ -2344,9 +2448,9 @@ checksum = "cda74da7e1a664f795bb1f8a87ec406fb89a02522cf6e50620d016add6dbbf5c"
 
 [[package]]
 name = "tokio"
-version = "1.21.2"
+version = "1.22.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9e03c497dc955702ba729190dc4aac6f2a0ce97f913e5b1b5912fc5039d9099"
+checksum = "d76ce4a75fb488c605c54bf610f221cea8b0dafb53333c1a67e8ee199dcd2ae3"
 dependencies = [
  "autocfg",
  "bytes",
@@ -2769,9 +2873,9 @@ dependencies = [
 
 [[package]]
 name = "zstd-sys"
-version = "2.0.1+zstd.1.5.2"
+version = "2.0.4+zstd.1.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9fd07cbbc53846d9145dbffdf6dd09a7a0aa52be46741825f5c97bdd4f73f12b"
+checksum = "4fa202f2ef00074143e219d15b62ffc317d17cc33909feac471c044087cad7b0"
 dependencies = [
  "cc",
  "libc",

From 941c55be4666f4ba470beb0960250e8f0f028d6f Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Tue, 29 Nov 2022 21:07:56 -0500
Subject: [PATCH 15/19] New line (windows)

---
 datafusion/core/tests/sqllogictests/test_files/aggregate.slt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datafusion/core/tests/sqllogictests/test_files/aggregate.slt b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
index ca1b58732c08b..11030446dc2fb 100644
--- a/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
+++ b/datafusion/core/tests/sqllogictests/test_files/aggregate.slt
@@ -882,4 +882,4 @@ a 4
 b 5
 c 4
 d 4
-e 4
\ No newline at end of file
+e 4

From aee6c626ab16c886c789e29788c9474614ea6fc7 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Wed, 30 Nov 2022 18:32:40 -0500
Subject: [PATCH 16/19] sqllogictests don't parse correctly on windows - ignore
 windows

---
 datafusion/core/tests/sqllogictests/src/main.rs | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/datafusion/core/tests/sqllogictests/src/main.rs b/datafusion/core/tests/sqllogictests/src/main.rs
index 3d06c9e32fc8b..4d2f54222bf0d 100644
--- a/datafusion/core/tests/sqllogictests/src/main.rs
+++ b/datafusion/core/tests/sqllogictests/src/main.rs
@@ -106,9 +106,11 @@ pub async fn main() -> Result<()> {
         let ctx = SessionContext::new();
         test_category.register_test_tables(&ctx).await;
 
-        let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
-        // TODO: use tester.run_parallel_async()
-        tester.run_file_async(filename).await?;
+        if !cfg!(target_os = "windows") {
+            let mut tester = sqllogictest::Runner::new(DataFusion { ctx, test_category });
+            // TODO: use tester.run_parallel_async()
+            tester.run_file_async(filename).await?;
+        }
     }
 
     Ok(())

From 3e7db70c889f032fb8de2b9667ca65eed8ceb810 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Wed, 30 Nov 2022 19:16:59 -0500
Subject: [PATCH 17/19] empty commit - rerun CI

---
 datafusion/core/tests/sqllogictests/README.md | 2 --
 1 file changed, 2 deletions(-)

diff --git a/datafusion/core/tests/sqllogictests/README.md b/datafusion/core/tests/sqllogictests/README.md
index 7f597ee4d4359..550e4a558eb54 100644
--- a/datafusion/core/tests/sqllogictests/README.md
+++ b/datafusion/core/tests/sqllogictests/README.md
@@ -25,8 +25,6 @@ This is the Datafusion implementation of [sqllogictest](https://www.sqlite.org/s
 
 `cargo test -p datafusion --test sqllogictests`
 
-#### Setup
-
 #### sqllogictests
 
 > :warning: **Warning**:Datafusion's sqllogictest implementation and migration is still in progress. Definitions taken from https://www.sqlite.org/sqllogictest/doc/trunk/about.wiki

From 93e58c664798589362d933a8aeab214044969e56 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Wed, 30 Nov 2022 19:22:30 -0500
Subject: [PATCH 18/19] Add LICENSE.txt and NOTICE.txt back:

---
 LICENSE.txt | 212 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 NOTICE.txt  |  84 +++++++++++++++++++++
 2 files changed, 296 insertions(+)
 create mode 100644 LICENSE.txt
 create mode 100644 NOTICE.txt

diff --git a/LICENSE.txt b/LICENSE.txt
new file mode 100644
index 0000000000000..d74c6b599d2ae
--- /dev/null
+++ b/LICENSE.txt
@@ -0,0 +1,212 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+
+This project includes code from Apache Aurora.
+
+* dev/release/{release,changelog,release-candidate} are based on the scripts from
+  Apache Aurora
+
+Copyright: 2016 The Apache Software Foundation.
+Home page: https://aurora.apache.org/
+License: http://www.apache.org/licenses/LICENSE-2.0
diff --git a/NOTICE.txt b/NOTICE.txt
new file mode 100644
index 0000000000000..a609791374c28
--- /dev/null
+++ b/NOTICE.txt
@@ -0,0 +1,84 @@
+Apache Arrow
+Copyright 2016-2019 The Apache Software Foundation
+
+This product includes software developed at
+The Apache Software Foundation (http://www.apache.org/).
+
+This product includes software from the SFrame project (BSD, 3-clause).
+* Copyright (C) 2015 Dato, Inc.
+* Copyright (c) 2009 Carnegie Mellon University.
+
+This product includes software from the Feather project (Apache 2.0)
+https://github.com/wesm/feather
+
+This product includes software from the DyND project (BSD 2-clause)
+https://github.com/libdynd
+
+This product includes software from the LLVM project
+ * distributed under the University of Illinois Open Source
+
+This product includes software from the google-lint project
+ * Copyright (c) 2009 Google Inc. All rights reserved.
+
+This product includes software from the mman-win32 project
+ * Copyright https://code.google.com/p/mman-win32/
+ * Licensed under the MIT License;
+
+This product includes software from the LevelDB project
+ * Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+ * Use of this source code is governed by a BSD-style license that can be
+ * Moved from Kudu http://github.com/cloudera/kudu
+
+This product includes software from the CMake project
+ * Copyright 2001-2009 Kitware, Inc.
+ * Copyright 2012-2014 Continuum Analytics, Inc.
+ * All rights reserved.
+
+This product includes software from https://github.com/matthew-brett/multibuild (BSD 2-clause)
+ * Copyright (c) 2013-2016, Matt Terry and Matthew Brett; all rights reserved.
+
+This product includes software from the Ibis project (Apache 2.0)
+ * Copyright (c) 2015 Cloudera, Inc.
+ * https://github.com/cloudera/ibis
+
+This product includes software from Dremio (Apache 2.0)
+  * Copyright (C) 2017-2018 Dremio Corporation
+  * https://github.com/dremio/dremio-oss
+
+This product includes software from Google Guava (Apache 2.0)
+  * Copyright (C) 2007 The Guava Authors
+  * https://github.com/google/guava
+
+This product include software from CMake (BSD 3-Clause)
+  * CMake - Cross Platform Makefile Generator
+  * Copyright 2000-2019 Kitware, Inc. and Contributors
+
+The web site includes files generated by Jekyll.
+
+--------------------------------------------------------------------------------
+
+This product includes code from Apache Kudu, which includes the following in
+its NOTICE file:
+
+  Apache Kudu
+  Copyright 2016 The Apache Software Foundation
+
+  This product includes software developed at
+  The Apache Software Foundation (http://www.apache.org/).
+
+  Portions of this software were developed at
+  Cloudera, Inc (http://www.cloudera.com/).
+
+--------------------------------------------------------------------------------
+
+This product includes code from Apache ORC, which includes the following in
+its NOTICE file:
+
+  Apache ORC
+  Copyright 2013-2019 The Apache Software Foundation
+
+  This product includes software developed by The Apache Software
+  Foundation (http://www.apache.org/).
+
+  This product includes software developed by Hewlett-Packard:
+  (c) Copyright [2014-2015] Hewlett-Packard Development Company, L.P

From 71578f2124fff6d6c58a17ebf4fc83e645293082 Mon Sep 17 00:00:00 2001
From: Matthew Van Schellebeeck <mvanschellebeeck@gmail.com>
Date: Wed, 30 Nov 2022 20:38:16 -0500
Subject: [PATCH 19/19] Fix ubuntu version

---
 .github/workflows/rust.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index 86c22f7633b5e..e74d87e609c7e 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -296,7 +296,7 @@ jobs:
   test-datafusion-pyarrow:
     name: cargo test pyarrow (amd64)
     needs: [linux-build-lib]
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-20.04
     container:
       image: amd64/rust
       env: