Skip to content
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.

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

Re-implement cardinality() on arrays, replacing the one from Datafusion. #69

Merged
merged 1 commit into from
Jul 31, 2024
Merged
Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion assets/trino/functions.sdf.yml
Original file line number Diff line number Diff line change
Expand Up @@ -1432,7 +1432,7 @@ function:
optional-parameters: []
returns:
datatype: bigint
implemented-by: !datafusion
implemented-by: !rust
section: array
cross-link: https://trino.io/docs/current/functions/array.html#cardinality
description: >
Expand Down
38 changes: 25 additions & 13 deletions src/trino/cardinality_impl.rs
Original file line number Diff line number Diff line change
Expand Up @@ -16,27 +16,39 @@
// under the License.

#![allow(non_camel_case_types)]
use arrow::array::{ArrayRef, UInt64Array};
use arrow::datatypes::DataType;
use datafusion::common::cast::as_list_array;
use datafusion::common::Result;
use datafusion::error::DataFusionError;
use datafusion::logical_expr::simplify::{ExprSimplifyResult, SimplifyInfo};
use datafusion::logical_expr::{ColumnarValue, Expr, ScalarUDFImpl, Signature, Volatility};
use std::any::Any;

fn cardinality_array_3_invoke(_args: &[ColumnarValue]) -> Result<ColumnarValue> {
Err(DataFusionError::NotImplemented(format!(
"Not implemented {}:{}",
file!(),
line!()
)))
use std::sync::Arc;

use crate::utils::apply_unary_kernel;

fn cardinality_array_3_invoke(args: &[ColumnarValue]) -> Result<ColumnarValue> {
apply_unary_kernel(&args[0], move |array: &ArrayRef| {
let list_array = as_list_array(array)?;
let result = list_array
.iter()
.map(|item| match item {
Some(arr) => Some(arr.len() as u64),
None => None, // NULL
})
.collect::<UInt64Array>();
Ok(Arc::new(result) as ArrayRef)
})
}

fn cardinality_array_3_return_type(_arg_types: &[DataType]) -> Result<DataType> {
Err(DataFusionError::NotImplemented(format!(
"Not implemented {}:{}",
file!(),
line!()
)))
fn cardinality_array_3_return_type(arg_types: &[DataType]) -> Result<DataType> {
match arg_types[0] {
DataType::List(_) => Ok(DataType::UInt64),
_ => Err(DataFusionError::Plan(format!(
"The cardinality function only accepts List."
))),
}
}

fn cardinality_array_3_simplify(
Expand Down
4 changes: 3 additions & 1 deletion src/utils.rs
Original file line number Diff line number Diff line change
Expand Up @@ -106,6 +106,8 @@ pub(super) fn apply_datepart_kernel(arg: &ColumnarValue, part: DatePart) -> Resu
})
}

/// Use Arrow `date_part` kernel to compute day of week,
/// with Monday being 1 through Sunday being 7, per Trino convention..
pub(super) fn apply_dow_kernel(arg: &ColumnarValue) -> Result<ColumnarValue> {
apply_unary_kernel(arg, move |arr| {
let monday0 = date_part(arr, DatePart::DayOfWeekMonday0)?;
Expand All @@ -132,7 +134,7 @@ pub(super) fn array_to_columnar(array: ArrayRef) -> ColumnarValue {
if array.len() == 1 {
match ScalarValue::try_from_array(&array, 0) {
Ok(scalar) => ColumnarValue::Scalar(scalar),
Err(_) => ColumnarValue::Array(array),
Err(_) => ColumnarValue::Array(array), // Should not happen; can just panic instead
}
} else {
ColumnarValue::Array(array)
Expand Down