Standing-Man commented on code in PR #16936: URL: https://github.com/apache/datafusion/pull/16936#discussion_r2249484518
########## datafusion/spark/src/function/array/spark_array.rs: ########## @@ -0,0 +1,273 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +use std::{any::Any, sync::Arc}; + +use arrow::array::{ + make_array, new_null_array, Array, ArrayData, ArrayRef, Capacities, GenericListArray, + MutableArrayData, NullArray, OffsetSizeTrait, +}; +use arrow::buffer::OffsetBuffer; +use arrow::datatypes::{DataType, Field, FieldRef}; +use datafusion_common::utils::SingleRowListArrayBuilder; +use datafusion_common::{plan_datafusion_err, plan_err, Result}; +use datafusion_expr::type_coercion::binary::comparison_coercion; +use datafusion_expr::{ + ColumnarValue, ReturnFieldArgs, ScalarFunctionArgs, ScalarUDFImpl, Signature, + TypeSignature, Volatility, +}; + +use crate::function::functions_nested_utils::make_scalar_function; + +#[derive(Debug)] +pub struct SparkArray { + signature: Signature, + aliases: Vec<String>, +} + +impl Default for SparkArray { + fn default() -> Self { + Self::new() + } +} + +impl SparkArray { + pub fn new() -> Self { + Self { + signature: Signature::one_of( + vec![TypeSignature::UserDefined, TypeSignature::Nullary], + Volatility::Immutable, + ), + aliases: vec![String::from("spark_make_array")], + } + } +} + +impl ScalarUDFImpl for SparkArray { + fn as_any(&self) -> &dyn Any { + self + } + + fn name(&self) -> &str { + "array" + } + + fn signature(&self) -> &Signature { + &self.signature + } + + fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> { + match arg_types.len() { + 0 => Ok(empty_array_type()), + _ => { + let mut expr_type = DataType::Null; + for arg_type in arg_types { + if !arg_type.equals_datatype(&DataType::Null) { + expr_type = arg_type.clone(); + break; + } + } + + if expr_type.is_null() { + expr_type = DataType::Int32; + } + + Ok(DataType::List(Arc::new(Field::new_list_field( + expr_type, true, + )))) + } + } + } + + fn return_field_from_args(&self, args: ReturnFieldArgs) -> Result<FieldRef> { + let data_types = args + .arg_fields + .iter() + .map(|f| f.data_type()) + .cloned() + .collect::<Vec<_>>(); + let return_type = self.return_type(&data_types)?; + Ok(Arc::new(Field::new(self.name(), return_type, false))) + } + + fn invoke_with_args(&self, args: ScalarFunctionArgs) -> Result<ColumnarValue> { + let ScalarFunctionArgs { args, .. } = args; + make_scalar_function(make_array_inner)(args.as_slice()) + } + + fn aliases(&self) -> &[String] { + &self.aliases + } + + fn coerce_types(&self, arg_types: &[DataType]) -> Result<Vec<DataType>> { + let first_type = arg_types.first().ok_or_else(|| { + plan_datafusion_err!("Spark array function requires at least one argument") + })?; + let new_type = + arg_types + .iter() + .skip(1) + .try_fold(first_type.clone(), |acc, x| { + // The coerced types found by `comparison_coercion` are not guaranteed to be + // coercible for the arguments. `comparison_coercion` returns more loose + // types that can be coerced to both `acc` and `x` for comparison purpose. + // See `maybe_data_types` for the actual coercion. + let coerced_type = comparison_coercion(&acc, x); + if let Some(coerced_type) = coerced_type { + Ok(coerced_type) + } else { + plan_err!("Coercion from {acc:?} to {x:?} failed.") + } + })?; + Ok(vec![new_type; arg_types.len()]) + } +} + +// Empty array is a special case that is useful for many other array functions +pub(super) fn empty_array_type() -> DataType { + DataType::List(Arc::new(Field::new_list_field(DataType::Int32, true))) Review Comment: Got it, I’ve hardcoded the field name into the array-related functions. I think we can create an issue to improve this SparkArray problem. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org For additional commands, e-mail: github-h...@datafusion.apache.org
