Function concat_elements_bytes

arrow-string/src/concat_elements.rs:31–73

Returns the elementwise concatenation of a [`GenericByteArray`].

(
    left: &GenericByteArray<T>,
    right: &GenericByteArray<T>,
)

/// Returns the elementwise concatenation of a [`GenericByteArray`].
pub fn concat_elements_bytes<T: ByteArrayType>(
    left: &GenericByteArray<T>,
    right: &GenericByteArray<T>,
) -> Result<GenericByteArray<T>, ArrowError> {
    if left.len() != right.len() {
        return Err(ArrowError::ComputeError(format!(
            "Arrays must have the same length: {} != {}",
            left.len(),
            right.len()
        )));
    }

    let nulls = NullBuffer::union(left.nulls(), right.nulls());

    let left_offsets = left.value_offsets();
    let right_offsets = right.value_offsets();

    let left_values = left.value_data();
    let right_values = right.value_data();

    let mut output_values = BufferBuilder::<u8>::new(
        left_values.len() + right_values.len()
            - left_offsets[0].as_usize()
            - right_offsets[0].as_usize(),
    );

    let mut output_offsets = BufferBuilder::<T::Offset>::new(left_offsets.len());
    output_offsets.append(T::Offset::usize_as(0));
    for (left_idx, right_idx) in left_offsets.windows(2).zip(right_offsets.windows(2)) {
        output_values.append_slice(&left_values[left_idx[0].as_usize()..left_idx[1].as_usize()]);
        output_values.append_slice(&right_values[right_idx[0].as_usize()..right_idx[1].as_usize()]);
        output_offsets.append(T::Offset::from_usize(output_values.len()).unwrap());
    }

    let builder = ArrayDataBuilder::new(T::DATA_TYPE)
        .len(left.len())
        .add_buffer(output_offsets.finish())
        .add_buffer(output_values.finish())
        .nulls(nulls);

    // SAFETY - offsets valid by construction
    Ok(unsafe { builder.build_unchecked() }.into())
}

/// Returns the elementwise concatenation of a [`GenericStringArray`].
///