Skip to content

fix: prevent repeat from attempting impossible LargeUtf8 allocations #27010

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

Closed
huong8373tt-beep wants to merge 1 commit into from
Closed

fix: prevent repeat from attempting impossible LargeUtf8 allocations #27010

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
37 changes: 33 additions & 4 deletions datafusion/functions/src/string/repeat.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ use datafusion_expr_common::signature::{Coercion, TypeSignatureClass};
use datafusion_expr_common::sort_properties::ExprProperties;
use datafusion_macros::user_doc;

const MAX_REPEAT_SIZE: usize = i32::MAX as usize;

#[user_doc(
doc_section(label = "String Functions"),
description = "Returns a string with an input string repeated a specified number.",
Expand Down Expand Up @@ -119,13 +121,13 @@ impl ScalarUDFImpl for RepeatFunc {

let result = match string_scalar {
ScalarValue::Utf8View(Some(s)) => ScalarValue::Utf8View(Some(
compute_repeat(s, count, i32::MAX as usize)?,
compute_repeat(s, count, MAX_REPEAT_SIZE)?,
)),
ScalarValue::Utf8(Some(s)) => ScalarValue::Utf8(Some(
compute_repeat(s, count, i32::MAX as usize)?,
compute_repeat(s, count, MAX_REPEAT_SIZE)?,
)),
ScalarValue::LargeUtf8(Some(s)) => ScalarValue::LargeUtf8(Some(
compute_repeat(s, count, i64::MAX as usize)?,
compute_repeat(s, count, MAX_REPEAT_SIZE)?,
)),
_ => {
return internal_err!(
Expand Down Expand Up @@ -225,7 +227,7 @@ fn repeat(string_array: &ArrayRef, count_array: &ArrayRef) -> Result<ArrayRef> {
LargeUtf8 => {
let string_arr = string_array.as_string::<i64>();
let (total_capacity, max_item_capacity) =
calculate_capacities(&string_arr, number_array, i64::MAX as usize)?;
calculate_capacities(&string_arr, number_array, MAX_REPEAT_SIZE)?;
let builder = GenericStringArrayBuilder::<i64>::with_capacity(
string_array.len(),
total_capacity,
Expand Down Expand Up @@ -454,6 +456,21 @@ mod tests {
Utf8,
StringArray
);
test_function!(
RepeatFunc::new(),
vec![
ColumnarValue::Scalar(ScalarValue::LargeUtf8(Some(String::from("Pg")))),
ColumnarValue::Scalar(ScalarValue::Int64(Some(1i64 << 60))),
],
exec_err!(
"string size overflow on repeat, max size is {}, but got {}",
i32::MAX,
2usize * (1usize << 60)
),
&str,
LargeUtf8,
LargeStringArray
);

Ok(())
}
Expand Down Expand Up @@ -519,6 +536,18 @@ mod tests {
);
}

#[test]
fn test_repeat_large_string_array_overflow() {
let strings: ArrayRef = Arc::new(LargeStringArray::from(vec![Some("abc")]));
let counts: ArrayRef = Arc::new(Int64Array::from(vec![Some(1i64 << 60)]));

let err = super::repeat(&strings, &counts).unwrap_err().to_string();
assert!(
err.contains("string size overflow on repeat"),
"unexpected error: {err}"
);
}

#[test]
fn test_repeat_sliced_large_string_with_null_offset() {
let (strings, counts) =
Expand Down