advancedxy commented on code in PR #179: URL: https://github.com/apache/arrow-datafusion-comet/pull/179#discussion_r1522630698
########## core/src/execution/datafusion/expressions/bloom_filter_might_contain.rs: ########## @@ -0,0 +1,163 @@ +// 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 crate::{ + execution::datafusion::util::spark_bloom_filter::SparkBloomFilter, parquet::data_type::AsBytes, +}; +use arrow::record_batch::RecordBatch; +use arrow_array::{BooleanArray, Int64Array}; +use arrow_schema::DataType; +use datafusion::{common::Result, physical_plan::ColumnarValue}; +use datafusion_common::{internal_err, DataFusionError, Result as DataFusionResult, ScalarValue}; +use datafusion_physical_expr::{aggregate::utils::down_cast_any_ref, PhysicalExpr}; +use once_cell::sync::OnceCell; +use std::{ + any::Any, + fmt::Display, + hash::{Hash, Hasher}, + sync::Arc, +}; + +#[derive(Debug)] +pub struct BloomFilterMightContain { + pub bloom_filter_expr: Arc<dyn PhysicalExpr>, + pub value_expr: Arc<dyn PhysicalExpr>, + bloom_filter: OnceCell<Option<SparkBloomFilter>>, +} + +impl Display for BloomFilterMightContain { + fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result { + write!( + f, + "BloomFilterMightContain [bloom_filter_expr: {}, value_expr: {}]", + self.bloom_filter_expr, self.value_expr + ) + } +} + +impl PartialEq<dyn Any> for BloomFilterMightContain { + fn eq(&self, _other: &dyn Any) -> bool { + down_cast_any_ref(_other) + .downcast_ref::<Self>() + .map(|other| { + self.bloom_filter_expr.eq(&other.bloom_filter_expr) + && self.value_expr.eq(&other.value_expr) + }) + .unwrap_or(false) + } +} + +impl BloomFilterMightContain { + pub fn new( + bloom_filter_expr: Arc<dyn PhysicalExpr>, + value_expr: Arc<dyn PhysicalExpr>, + ) -> Self { + Self { + bloom_filter_expr, + value_expr, + bloom_filter: Default::default(), + } + } +} + +impl PhysicalExpr for BloomFilterMightContain { + fn as_any(&self) -> &dyn Any { + self + } + + fn data_type(&self, _input_schema: &arrow_schema::Schema) -> Result<DataType> { + Ok(DataType::Boolean) + } + + fn nullable(&self, _input_schema: &arrow_schema::Schema) -> Result<bool> { + Ok(true) + } + + fn evaluate(&self, batch: &RecordBatch) -> DataFusionResult<ColumnarValue> { + // lazily get the spark bloom filter + if self.bloom_filter.get().is_none() { Review Comment: The bloom filter's binary is either a literal type or from ScalarSubquery, so I took the approach the lazily initialize that. But maybe we can simply evaluate it before constructing the expression just like how `in_list` is constructed, let me address it in the new commit. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
