Skip to content

Fix panic when hashing empty FixedSizeList Array #13533

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
merged 2 commits into from
Nov 24, 2024
Merged

Fix panic when hashing empty FixedSizeList Array #13533

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28e3b99
Fix panic when hashing empty FixedSizeList Array
findepi Nov 22, 2024
4b46b8a
simplify code
findepi Nov 23, 2024
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
18 changes: 14 additions & 4 deletions datafusion/common/src/hash_utils.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -321,16 +321,16 @@ fn hash_fixed_list_array(
hashes_buffer: &mut [u64],
) -> Result<()> {
let values = Arc::clone(array.values());
let value_len = array.value_length();
let offset_size = value_len as usize / array.len();
let value_length = array.value_length() as usize;
let nulls = array.nulls();
let mut values_hashes = vec![0u64; values.len()];
create_hashes(&[values], random_state, &mut values_hashes)?;
if let Some(nulls) = nulls {
for i in 0..array.len() {
if nulls.is_valid(i) {
let hash = &mut hashes_buffer[i];
for values_hash in &values_hashes[i * offset_size..(i + 1) * offset_size]
for values_hash in
&values_hashes[i * value_length..(i + 1) * value_length]
{
*hash = combine_hashes(*hash, *values_hash);
}
Expand All @@ -339,7 +339,7 @@ fn hash_fixed_list_array(
} else {
for i in 0..array.len() {
let hash = &mut hashes_buffer[i];
for values_hash in &values_hashes[i * offset_size..(i + 1) * offset_size] {
for values_hash in &values_hashes[i * value_length..(i + 1) * value_length] {
*hash = combine_hashes(*hash, *values_hash);
}
}
Expand Down Expand Up @@ -454,6 +454,16 @@ mod tests {
Ok(())
}

#[test]
fn create_hashes_for_empty_fixed_size_lit() -> Result<()> {
let empty_array = FixedSizeListBuilder::new(StringBuilder::new(), 1).finish();
let random_state = RandomState::with_seeds(0, 0, 0, 0);
let hashes_buff = &mut vec![0; 0];
let hashes = create_hashes(&[Arc::new(empty_array)], &random_state, hashes_buff)?;
assert_eq!(hashes, &Vec::<u64>::new());
Ok(())
}

#[test]
fn create_hashes_for_float_arrays() -> Result<()> {
let f32_arr = Arc::new(Float32Array::from(vec![0.12, 0.5, 1f32, 444.7]));
Expand Down