tustvold commented on code in PR #4057:
URL: https://github.com/apache/arrow-datafusion/pull/4057#discussion_r1010213649
##########
datafusion/physical-expr/src/expressions/in_list.rs:
##########
@@ -17,50 +17,37 @@
//! InList expression
+use ahash::RandomState;
use std::any::Any;
-use std::collections::HashSet;
use std::fmt::Debug;
use std::sync::Arc;
-use arrow::array::GenericStringArray;
-use arrow::array::{
- ArrayRef, BooleanArray, Float32Array, Float64Array, Int16Array, Int32Array,
- Int64Array, Int8Array, OffsetSizeTrait, TimestampMicrosecondArray,
- TimestampMillisecondArray, TimestampNanosecondArray, TimestampSecondArray,
- UInt16Array, UInt32Array, UInt64Array, UInt8Array,
-};
-use arrow::{
- datatypes::{DataType, Schema},
- record_batch::RecordBatch,
-};
-
+use crate::hash_utils::HashValue;
use crate::physical_expr::down_cast_any_ref;
use crate::utils::expr_list_eq_any_order;
use crate::PhysicalExpr;
use arrow::array::*;
-use arrow::datatypes::TimeUnit;
-use datafusion_common::cast::as_date32_array;
-use datafusion_common::ScalarValue;
-use datafusion_common::ScalarValue::{
- Binary, Boolean, Date32, Date64, Decimal128, Int16, Int32, Int64, Int8,
LargeBinary,
- LargeUtf8, TimestampMicrosecond, TimestampMillisecond, TimestampNanosecond,
- TimestampSecond, UInt16, UInt32, UInt64, UInt8, Utf8,
-};
-use datafusion_common::{DataFusionError, Result};
+use arrow::datatypes::*;
+use arrow::downcast_primitive_array;
+use arrow::record_batch::RecordBatch;
+use arrow::util::bit_iterator::BitIndexIterator;
+use datafusion_common::{DataFusionError, Result, ScalarValue};
use datafusion_expr::ColumnarValue;
+use hashbrown::hash_map::RawEntryMut;
+use hashbrown::HashMap;
/// Size at which to use a Set rather than Vec for `IN` / `NOT IN`
/// Value chosen by the benchmark at
/// https://github.com/apache/arrow-datafusion/pull/2156#discussion_r845198369
/// TODO: add switch codeGen in In_List
-static OPTIMIZER_INSET_THRESHOLD: usize = 30;
+static OPTIMIZER_INSET_THRESHOLD: usize = 10;
Review Comment:
I need to double-check whether we even need this anymore
--
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]
