vortex-array 0.68.0

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: Copyright the Vortex contributors

use vortex_error::VortexResult;

use super::Dict;
use super::DictArray;
use crate::ArrayRef;
use crate::Canonical;
use crate::ExecutionCtx;
use crate::IntoArray;
use crate::array::ArrayView;
use crate::arrays::ConstantArray;
use crate::arrays::dict::DictArrayExt;
use crate::arrays::dict::DictArraySlotsExt;
use crate::builtins::ArrayBuiltins;
use crate::scalar_fn::fns::binary::CompareKernel;
use crate::scalar_fn::fns::operators::CompareOperator;
use crate::scalar_fn::fns::operators::Operator;

impl CompareKernel for Dict {
    fn compare(
        lhs: ArrayView<'_, Dict>,
        rhs: &ArrayRef,
        operator: CompareOperator,
        ctx: &mut ExecutionCtx,
    ) -> VortexResult<Option<ArrayRef>> {
        // if we have more values than codes, it is faster to canonicalise first.
        if lhs.values().len() > lhs.codes().len() {
            return Ok(None);
        }

        // If the RHS is constant, then we just need to compare against our encoded values.
        if let Some(rhs) = rhs.as_constant() {
            let compare_result = lhs.values().clone().binary(
                ConstantArray::new(rhs, lhs.values().len()).into_array(),
                Operator::from(operator),
            )?;

            // SAFETY: values len preserved, codes all still point to valid values
            let result = unsafe {
                DictArray::new_unchecked(lhs.codes().clone(), compare_result)
                    .set_all_values_referenced(lhs.has_all_values_referenced())
                    .into_array()
            };

            // We canonicalize the result because dictionary-encoded bools is dumb.
            return Ok(Some(result.execute::<Canonical>(ctx)?.into_array()));
        }

        // It's a little more complex, but we could perform a comparison against the dictionary
        // values in the future.
        Ok(None)
    }
}