Skip to content

fix: Add overflow checks to SparkDateAdd/Sub to avoid panics #18013

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
alamb merged 8 commits into from
Oct 10, 2025
Merged

fix: Add overflow checks to SparkDateAdd/Sub to avoid panics #18013

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
c3a60bc
fix
andygrove Oct 10, 2025
0871386
fix
andygrove Oct 10, 2025
fd1807d
fix
andygrove Oct 10, 2025
93fe20b
fix
andygrove Oct 10, 2025
57a6c12
fix
andygrove Oct 10, 2025
dbba50c
add negative overflow test
andygrove Oct 10, 2025
f3a754a
remove unrelated test
andygrove Oct 10, 2025
51f896d
update test
andygrove Oct 10, 2025
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
25 changes: 19 additions & 6 deletions datafusion/spark/src/function/datetime/date_add.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ use std::sync::Arc;
use arrow::array::ArrayRef;
use arrow::compute;
use arrow::datatypes::{DataType, Date32Type};
use arrow::error::ArrowError;
use datafusion_common::cast::{
as_date32_array, as_int16_array, as_int32_array, as_int8_array,
};
Expand Down Expand Up @@ -96,26 +97,38 @@ fn spark_date_add(args: &[ArrayRef]) -> Result<ArrayRef> {
let result = match days_arg.data_type() {
DataType::Int8 => {
let days_array = as_int8_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date + days as i32,
|date, days| {
date.checked_add(days as i32).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_add".to_string())
})
},
)?
}
DataType::Int16 => {
let days_array = as_int16_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date + days as i32,
|date, days| {
date.checked_add(days as i32).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_add".to_string())
})
},
)?
}
DataType::Int32 => {
let days_array = as_int32_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date + days,
|date, days| {
date.checked_add(days).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_add".to_string())
})
},
)?
}
_ => {
Expand Down
25 changes: 19 additions & 6 deletions datafusion/spark/src/function/datetime/date_sub.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ use std::sync::Arc;
use arrow::array::ArrayRef;
use arrow::compute;
use arrow::datatypes::{DataType, Date32Type};
use arrow::error::ArrowError;
use datafusion_common::cast::{
as_date32_array, as_int16_array, as_int32_array, as_int8_array,
};
Expand Down Expand Up @@ -90,26 +91,38 @@ fn spark_date_sub(args: &[ArrayRef]) -> Result<ArrayRef> {
let result = match days_arg.data_type() {
DataType::Int8 => {
let days_array = as_int8_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date - days as i32,
|date, days| {
date.checked_sub(days as i32).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_sub".to_string())
})
},
)?
}
DataType::Int16 => {
let days_array = as_int16_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date - days as i32,
|date, days| {
date.checked_sub(days as i32).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_sub".to_string())
})
},
)?
}
DataType::Int32 => {
let days_array = as_int32_array(days_arg)?;
compute::binary::<_, _, _, Date32Type>(
compute::try_binary::<_, _, _, Date32Type>(
date_array,
days_array,
|date, days| date - days,
|date, days| {
date.checked_sub(days).ok_or_else(|| {
ArrowError::ArithmeticOverflow("date_sub".to_string())
})
},
)?
}
_ => {
Expand Down
18 changes: 18 additions & 0 deletions datafusion/sqllogictest/test_files/spark/datetime/date_add.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,24 @@ SELECT date_sub('2016-07-30'::date, 0::int);
----
2016-07-30

query error DataFusion error: Arrow error: Arithmetic overflow:
SELECT date_add('2016-07-30'::date, 2147483647::int);

query D
SELECT date_sub('2016-07-30'::date, 2147483647::int);
----
ERROR: Cast error: Failed to convert -2147466635 to temporal for Date32

@comphead comphead Oct 10, 2025

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.

ERROR: Cast error: Failed to convert -2147466635 to temporal for Date32 is it a result returned by date_sub 🤔 ?

@andygrove andygrove Oct 10, 2025

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

No. This error is unrelated to the changes in this PR, but I thought it was good to add the test.

I was expecting to see an overflow though. I will try and track down the root cause.

@andygrove andygrove Oct 10, 2025

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

I added a test to show negative overflow


query D
SELECT date_add('2016-07-30'::date, 100000::int);
----
2290-05-15

query D
SELECT date_sub('2016-07-30'::date, 100000::int);
----
1742-10-15

# Test with negative day values (should subtract days)
query D
SELECT date_add('2016-07-30'::date, -5::int);
Expand Down