Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix"); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms"); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links"); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default"); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers"); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + '
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode"); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })();
Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
115 changes: 115 additions & 0 deletions rust/datafusion/src/execution/context.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -1403,6 +1403,121 @@ mod tests {
Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_sum() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT sum(nanos), sum(micros), sum(millis), sum(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_count() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT count(nanos), count(micros), count(millis), count(secs) FROM t",
)
.await
.unwrap();

let expected = vec![

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Testing string formatting seems kinda yucky and prone to fail when the formatting changes. Is there a better way to test the output here?

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks @velvia --In general I agree that checking string representations in tests is brittle when formatting changes.

In the case of sql / tabular output, I think it is the best alternative I have seen because:

  1. The output formatting does not change often
  2. Updating these tests are easy (simply copy/paste the output of the test failure into the test after verifying it)
  3. These tests follow the same pattern as the rest of the tests in this module

"+--------------+---------------+---------------+-------------+",
"| COUNT(nanos) | COUNT(micros) | COUNT(millis) | COUNT(secs) |",
"+--------------+---------------+---------------+-------------+",
"| 3 | 3 | 3 | 3 |",
"+--------------+---------------+---------------+-------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_min() -> Result<()> {

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Min and max definitely makes sense.

let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT min(nanos), min(micros), min(millis), min(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| MIN(nanos) | MIN(micros) | MIN(millis) | MIN(secs) |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
"| 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123450 | 2011-12-13 11:13:10.123 | 2011-12-13 11:13:10 |",
"+----------------------------+----------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_max() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT max(nanos), max(micros), max(millis), max(secs) FROM t",
)
.await
.unwrap();

let expected = vec![
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| MAX(nanos) | MAX(micros) | MAX(millis) | MAX(secs) |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
"| 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10.432 | 2021-01-01 05:11:10 |",
"+-------------------------+-------------------------+-------------------------+---------------------+",
];
assert_batches_sorted_eq!(expected, &results);

Ok(())
}

#[tokio::test]
async fn aggregate_timestamps_avg() -> Result<()> {
let tmp_dir = TempDir::new()?;
let mut ctx = create_ctx(&tmp_dir, 1)?;
ctx.register_table("t", test::table_with_timestamps())
.unwrap();

let results = plan_and_collect(
&mut ctx,
"SELECT avg(nanos), avg(micros), avg(millis), avg(secs) FROM t",
)
.await
.unwrap_err();

assert_eq!(results.to_string(), "Error during planning: Coercion from [Timestamp(Nanosecond, None)] to the signature Uniform(1, [Int8, Int16, Int32, Int64, UInt8, UInt16, UInt32, UInt64, Float32, Float64]) failed.");

Copy link
Copy Markdown
ContributorAuthor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This error message is pretty horrible. I filed https://issues.apache.org/jira/browse/ARROW-12319 to track improving it

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed, thanks for filing a ticket!

Ok(())
}

#[tokio::test]
async fn join_partitioned() -> Result<()> {
// self join on partition id (workaround for duplicate column name)
Expand Down
19 changes: 16 additions & 3 deletions rust/datafusion/src/physical_plan/aggregates.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -34,7 +34,7 @@ use super::{
use crate::error::{DataFusionError, Result};
use crate::physical_plan::distinct_expressions;
use crate::physical_plan::expressions;
use arrow::datatypes::{DataType, Schema};
use arrow::datatypes::{DataType, Schema, TimeUnit};
use expressions::{avg_return_type, sum_return_type};
use std::{fmt, str::FromStr, sync::Arc};

Expand DownExpand Up@@ -160,6 +160,8 @@ pub fn create_aggregate_expr(
})
}

static STRINGS: &[DataType] = &[DataType::Utf8, DataType::LargeUtf8];

static NUMERICS: &[DataType] = &[
DataType::Int8,
DataType::Int16,
Expand All@@ -173,14 +175,25 @@ static NUMERICS: &[DataType] = &[
DataType::Float64,
];

static TIMESTAMPS: &[DataType] = &[
DataType::Timestamp(TimeUnit::Second, None),
DataType::Timestamp(TimeUnit::Millisecond, None),
DataType::Timestamp(TimeUnit::Microsecond, None),
DataType::Timestamp(TimeUnit::Nanosecond, None),
];

/// the signatures supported by the function `fun`.
fn signature(fun: &AggregateFunction) -> Signature {
// note: the physical expression must accept the type returned by this function or the execution panics.
match fun {
AggregateFunction::Count => Signature::Any(1),
AggregateFunction::Min | AggregateFunction::Max => {
let mut valid = vec![DataType::Utf8, DataType::LargeUtf8];
valid.extend_from_slice(NUMERICS);
let valid = STRINGS
.iter()
.chain(NUMERICS.iter())
.chain(TIMESTAMPS.iter())
.cloned()
.collect::<Vec<_>>();
Signature::Uniform(1, valid)
}
AggregateFunction::Avg | AggregateFunction::Sum => {
Expand Down
4 changes: 2 additions & 2 deletions rust/datafusion/src/physical_plan/datetime_expressions.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -324,8 +324,8 @@ pub fn date_trunc(args: &[ColumnarValue]) -> Result<ColumnarValue> {

Ok(match array {
ColumnarValue::Scalar(scalar) => {
if let ScalarValue::TimeNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimeNanosecond((f)(*v)?))
if let ScalarValue::TimestampNanosecond(v) = scalar {
ColumnarValue::Scalar(ScalarValue::TimestampNanosecond((f)(*v)?))
} else {
return Err(DataFusionError::Execution(
"array of `date_trunc` must be non-null scalar Utf8".to_string(),
Expand Down
49 changes: 46 additions & 3 deletions rust/datafusion/src/physical_plan/expressions/min_max.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -25,12 +25,13 @@ use crate::error::{DataFusionError, Result};
use crate::physical_plan::{Accumulator, AggregateExpr, PhysicalExpr};
use crate::scalar::ScalarValue;
use arrow::compute;
use arrow::datatypes::DataType;
use arrow::datatypes::{DataType, TimeUnit};
use arrow::{
array::{
ArrayRef, Float32Array, Float64Array, Int16Array, Int32Array, Int64Array,
Int8Array, LargeStringArray, StringArray, UInt16Array, UInt32Array, UInt64Array,
UInt8Array,
Int8Array, LargeStringArray, StringArray, TimestampMicrosecondArray,
TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
UInt16Array, UInt32Array, UInt64Array, UInt8Array,
},
datatypes::Field,
};
Expand DownExpand Up@@ -128,6 +129,27 @@ macro_rules! min_max_batch {
DataType::UInt32 => typed_min_max_batch!($VALUES, UInt32Array, UInt32, $OP),
DataType::UInt16 => typed_min_max_batch!($VALUES, UInt16Array, UInt16, $OP),
DataType::UInt8 => typed_min_max_batch!($VALUES, UInt8Array, UInt8, $OP),
DataType::Timestamp(TimeUnit::Second, _) => {
typed_min_max_batch!($VALUES, TimestampSecondArray, TimestampSecond, $OP)
}
DataType::Timestamp(TimeUnit::Millisecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMillisecondArray,
TimestampMillisecond,
$OP
),
DataType::Timestamp(TimeUnit::Microsecond, _) => typed_min_max_batch!(
$VALUES,
TimestampMicrosecondArray,
TimestampMicrosecond,
$OP
),
DataType::Timestamp(TimeUnit::Nanosecond, _) => typed_min_max_batch!(
$VALUES,
TimestampNanosecondArray,
TimestampNanosecond,
$OP
),
other => {
// This should have been handled before
return Err(DataFusionError::Internal(format!(
Expand DownExpand Up@@ -229,6 +251,27 @@ macro_rules! min_max {
(ScalarValue::LargeUtf8(lhs), ScalarValue::LargeUtf8(rhs)) => {
typed_min_max_string!(lhs, rhs, LargeUtf8, $OP)
}
(ScalarValue::TimestampSecond(lhs), ScalarValue::TimestampSecond(rhs)) => {
typed_min_max!(lhs, rhs, TimestampSecond, $OP)
}
(
ScalarValue::TimestampMillisecond(lhs),
ScalarValue::TimestampMillisecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMillisecond, $OP)
}
(
ScalarValue::TimestampMicrosecond(lhs),
ScalarValue::TimestampMicrosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampMicrosecond, $OP)
}
(
ScalarValue::TimestampNanosecond(lhs),
ScalarValue::TimestampNanosecond(rhs),
) => {
typed_min_max!(lhs, rhs, TimestampNanosecond, $OP)
}
e => {
return Err(DataFusionError::Internal(format!(
"MIN/MAX is not expected to receive a scalar {:?}",
Expand Down
24 changes: 18 additions & 6 deletions rust/datafusion/src/physical_plan/group_scalar.rs
Original file line numberDiff line numberDiff line change
Expand Up@@ -64,9 +64,15 @@ impl TryFrom<&ScalarValue> for GroupByScalar {
ScalarValue::UInt16(Some(v)) => GroupByScalar::UInt16(*v),
ScalarValue::UInt32(Some(v)) => GroupByScalar::UInt32(*v),
ScalarValue::UInt64(Some(v)) => GroupByScalar::UInt64(*v),
ScalarValue::TimeMillisecond(Some(v)) => GroupByScalar::TimeMillisecond(*v),
ScalarValue::TimeMicrosecond(Some(v)) => GroupByScalar::TimeMicrosecond(*v),
ScalarValue::TimeNanosecond(Some(v)) => GroupByScalar::TimeNanosecond(*v),
ScalarValue::TimestampMillisecond(Some(v)) => {
GroupByScalar::TimeMillisecond(*v)
}
ScalarValue::TimestampMicrosecond(Some(v)) => {
GroupByScalar::TimeMicrosecond(*v)
}
ScalarValue::TimestampNanosecond(Some(v)) => {
GroupByScalar::TimeNanosecond(*v)
}
ScalarValue::Utf8(Some(v)) => GroupByScalar::Utf8(Box::new(v.clone())),
ScalarValue::Float32(None)
| ScalarValue::Float64(None)
Expand DownExpand Up@@ -110,9 +116,15 @@ impl From<&GroupByScalar> for ScalarValue {
GroupByScalar::UInt32(v) => ScalarValue::UInt32(Some(*v)),
GroupByScalar::UInt64(v) => ScalarValue::UInt64(Some(*v)),
GroupByScalar::Utf8(v) => ScalarValue::Utf8(Some(v.to_string())),
GroupByScalar::TimeMillisecond(v) => ScalarValue::TimeMillisecond(Some(*v)),
GroupByScalar::TimeMicrosecond(v) => ScalarValue::TimeMicrosecond(Some(*v)),
GroupByScalar::TimeNanosecond(v) => ScalarValue::TimeNanosecond(Some(*v)),
GroupByScalar::TimeMillisecond(v) => {
ScalarValue::TimestampMillisecond(Some(*v))
}
GroupByScalar::TimeMicrosecond(v) => {
ScalarValue::TimestampMicrosecond(Some(*v))
}
GroupByScalar::TimeNanosecond(v) => {
ScalarValue::TimestampNanosecond(Some(*v))
}
GroupByScalar::Date32(v) => ScalarValue::Date32(Some(*v)),
}
}
Expand Down
Loading