Skip to content
Merged
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
35 changes: 30 additions & 5 deletions arrow-array/src/builder/generic_bytes_view_builder.rs
Original file line number Diff line number Diff line change
Expand Up @@ -306,15 +306,30 @@ impl<T: ByteViewType + ?Sized> GenericByteViewBuilder<T> {
/// - String length exceeds `u32::MAX`
#[inline]
pub fn append_value(&mut self, value: impl AsRef<T::Native>) {
self.try_append_value(value).unwrap()
}

/// Appends a value into the builder
///
/// # Errors
///
/// Returns an error if:
/// - String buffer count exceeds `u32::MAX`
/// - String length exceeds `u32::MAX`
#[inline]
pub fn try_append_value(&mut self, value: impl AsRef<T::Native>) -> Result<(), ArrowError> {
let v: &[u8] = value.as_ref().as_ref();
let length: u32 = v.len().try_into().unwrap();
let length: u32 = v.len().try_into().map_err(|_| {
ArrowError::InvalidArgumentError(format!("String length {} exceeds u32::MAX", v.len()))
})?;

if length <= MAX_INLINE_VIEW_LEN {
let mut view_buffer = [0; 16];
view_buffer[0..4].copy_from_slice(&length.to_le_bytes());
view_buffer[4..4 + v.len()].copy_from_slice(v);
self.views_buffer.push(u128::from_le_bytes(view_buffer));
self.null_buffer_builder.append_non_null();
return;
return Ok(());
}

// Deduplication if:
Expand All @@ -339,7 +354,7 @@ impl<T: ByteViewType + ?Sized> GenericByteViewBuilder<T> {
self.views_buffer.push(self.views_buffer[*idx]);
self.null_buffer_builder.append_non_null();
self.string_tracker = Some((ht, hasher));
return;
return Ok(());
}
Entry::Vacant(vacant) => {
// o.w. we insert the (string hash -> view index)
Expand All @@ -356,17 +371,28 @@ impl<T: ByteViewType + ?Sized> GenericByteViewBuilder<T> {
let to_reserve = v.len().max(self.block_size.next_size() as usize);
self.in_progress.reserve(to_reserve);
};

let offset = self.in_progress.len() as u32;
self.in_progress.extend_from_slice(v);

let buffer_index: u32 = self.completed.len().try_into().map_err(|_| {
ArrowError::InvalidArgumentError(format!(
"Buffer count {} exceeds u32::MAX",
self.completed.len()
))
})?;

let view = ByteView {
length,
// This won't panic as we checked the length of prefix earlier.
prefix: u32::from_le_bytes(v[0..4].try_into().unwrap()),
buffer_index: self.completed.len() as u32,
buffer_index,
offset,
};
self.views_buffer.push(view.into());
self.null_buffer_builder.append_non_null();

Ok(())
}

/// Append an `Option` value into the builder
Expand Down Expand Up @@ -581,7 +607,6 @@ mod tests {
use core::str;

use super::*;
use crate::Array;

#[test]
fn test_string_view_deduplicate() {
Expand Down
Loading