Introduce HashMap and HashSet type aliases (#13236)

* Unite all references to hashbrown::HashMap by using a common type definition

* Replace some use of std::collections::HashMap with hashbrown::HashMap

* Replace some use of std::collections::HashMap with hashbrown::HashMap

* Replace some use of std::collections::HashMap with hashbrown::HashMap

* Unite all references to hashbrown::HashSet by using a common type definition

* Replace some use of std::collections::HashSet with hashbrown::HashSet

Author: drauschenbach

datafusion/common/src/functional_dependencies.rs

@@ -18,13 +18,12 @@
 //! FunctionalDependencies keeps track of functional dependencies
 //! inside DFSchema.
 
-use std::collections::HashSet;
 use std::fmt::{Display, Formatter};
 use std::ops::Deref;
 use std::vec::IntoIter;
 
 use crate::utils::{merge_and_order_indices, set_difference};
-use crate::{DFSchema, JoinType};
+use crate::{DFSchema, HashSet, JoinType};
 
 /// This object defines a constraint on a table.
 #[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Hash)]

datafusion/common/src/lib.rs

@@ -66,6 +66,7 @@ pub use functional_dependencies::{
     get_target_functional_dependencies, Constraint, Constraints, Dependency,
     FunctionalDependence, FunctionalDependencies,
 };
+use hashbrown::hash_map::DefaultHashBuilder;
 pub use join_type::{JoinConstraint, JoinSide, JoinType};
 pub use param_value::ParamValues;
 pub use scalar::{ScalarType, ScalarValue};
@@ -87,6 +88,10 @@ pub use error::{
     _substrait_datafusion_err,
 };
 
+// The HashMap and HashSet implementations that should be used as the uniform defaults
+pub type HashMap<K, V, S = DefaultHashBuilder> = hashbrown::HashMap<K, V, S>;
+pub type HashSet<T, S = DefaultHashBuilder> = hashbrown::HashSet<T, S>;
+
 /// Downcast an Arrow Array to a concrete type, return an `DataFusionError::Internal` if the cast is
 /// not possible. In normal usage of DataFusion the downcast should always succeed.
 ///

datafusion/core/src/bin/print_functions_docs.rs

@@ -16,12 +16,11 @@
 // under the License.
 
 use datafusion::execution::SessionStateDefaults;
-use datafusion_common::{not_impl_err, Result};
+use datafusion_common::{not_impl_err, HashSet, Result};
 use datafusion_expr::{
     aggregate_doc_sections, scalar_doc_sections, window_doc_sections, AggregateUDF,
     DocSection, Documentation, ScalarUDF, WindowUDF,
 };
-use hashbrown::HashSet;
 use itertools::Itertools;
 use std::env::args;
 use std::fmt::Write as _;

datafusion/core/src/catalog_common/listing_schema.rs

@@ -18,14 +18,16 @@
 //! [`ListingSchemaProvider`]: [`SchemaProvider`] that scans ObjectStores for tables automatically
 
 use std::any::Any;
-use std::collections::{HashMap, HashSet};
+use std::collections::HashSet;
 use std::path::Path;
 use std::sync::{Arc, Mutex};
 
 use crate::catalog::{SchemaProvider, TableProvider, TableProviderFactory};
 use crate::execution::context::SessionState;
 
-use datafusion_common::{Constraints, DFSchema, DataFusionError, TableReference};
+use datafusion_common::{
+    Constraints, DFSchema, DataFusionError, HashMap, TableReference,
+};
 use datafusion_expr::CreateExternalTable;
 
 use async_trait::async_trait;

datafusion/core/src/datasource/file_format/parquet.rs

@@ -63,7 +63,7 @@ use datafusion_physical_plan::metrics::MetricsSet;
 
 use async_trait::async_trait;
 use bytes::Bytes;
-use hashbrown::HashMap;
+use datafusion_common::HashMap;
 use log::debug;
 use object_store::buffered::BufWriter;
 use parquet::arrow::arrow_writer::{

datafusion/core/src/datasource/listing/helpers.rs

@@ -17,15 +17,14 @@
 
 //! Helper functions for the table implementation
 
-use std::collections::HashMap;
 use std::mem;
 use std::sync::Arc;
 
 use super::ListingTableUrl;
 use super::PartitionedFile;
 use crate::execution::context::SessionState;
 use datafusion_common::internal_err;
-use datafusion_common::{Result, ScalarValue};
+use datafusion_common::{HashMap, Result, ScalarValue};
 use datafusion_expr::{BinaryExpr, Operator};
 
 use arrow::{

datafusion/core/src/physical_optimizer/sort_pushdown.rs

@@ -32,7 +32,7 @@ use crate::physical_plan::{ExecutionPlan, ExecutionPlanProperties};
 use datafusion_common::tree_node::{
     ConcreteTreeNode, Transformed, TreeNode, TreeNodeRecursion,
 };
-use datafusion_common::{plan_err, JoinSide, Result};
+use datafusion_common::{plan_err, HashSet, JoinSide, Result};
 use datafusion_expr::JoinType;
 use datafusion_physical_expr::expressions::Column;
 use datafusion_physical_expr::utils::collect_columns;
@@ -41,8 +41,6 @@ use datafusion_physical_expr_common::sort_expr::{
     LexOrdering, LexOrderingRef, LexRequirement,
 };
 
-use hashbrown::HashSet;
-
 /// This is a "data class" we use within the [`EnforceSorting`] rule to push
 /// down [`SortExec`] in the plan. In some cases, we can reduce the total
 /// computational cost by pushing down `SortExec`s through some executors. The

datafusion/core/tests/fuzz_cases/aggregate_fuzz.rs

@@ -42,8 +42,8 @@ use test_utils::{add_empty_batches, StringBatchGenerator};
 use crate::fuzz_cases::aggregation_fuzzer::{
     AggregationFuzzerBuilder, ColumnDescr, DatasetGeneratorConfig, QueryBuilder,
 };
+use datafusion_common::HashMap;
 use datafusion_physical_expr_common::sort_expr::LexOrdering;
-use hashbrown::HashMap;
 use rand::rngs::StdRng;
 use rand::{Rng, SeedableRng};
 use tokio::task::JoinSet;

datafusion/core/tests/fuzz_cases/window_fuzz.rs

@@ -45,10 +45,10 @@ use datafusion_physical_expr::{PhysicalExpr, PhysicalSortExpr};
 use test_utils::add_empty_batches;
 
 use datafusion::functions_window::row_number::row_number_udwf;
+use datafusion_common::HashMap;
 use datafusion_functions_window::lead_lag::{lag_udwf, lead_udwf};
 use datafusion_functions_window::rank::{dense_rank_udwf, rank_udwf};
 use datafusion_physical_expr_common::sort_expr::LexOrdering;
-use hashbrown::HashMap;
 use rand::distributions::Alphanumeric;
 use rand::rngs::StdRng;
 use rand::{Rng, SeedableRng};

datafusion/core/tests/user_defined/user_defined_scalar_functions.rs

@@ -16,7 +16,6 @@
 // under the License.
 
 use std::any::Any;
-use std::collections::HashMap;
 use std::hash::{DefaultHasher, Hash, Hasher};
 use std::sync::Arc;
 
@@ -39,7 +38,8 @@ use datafusion_common::cast::{as_float64_array, as_int32_array};
 use datafusion_common::tree_node::{Transformed, TreeNode};
 use datafusion_common::{
     assert_batches_eq, assert_batches_sorted_eq, assert_contains, exec_err, internal_err,
-    not_impl_err, plan_err, DFSchema, DataFusionError, ExprSchema, Result, ScalarValue,
+    not_impl_err, plan_err, DFSchema, DataFusionError, ExprSchema, HashMap, Result,
+    ScalarValue,
 };
 use datafusion_expr::simplify::{ExprSimplifyResult, SimplifyInfo};
 use datafusion_expr::{

datafusion/execution/src/memory_pool/pool.rs

@@ -16,8 +16,8 @@
 // under the License.
 
 use crate::memory_pool::{MemoryConsumer, MemoryPool, MemoryReservation};
+use datafusion_common::HashMap;
 use datafusion_common::{resources_datafusion_err, DataFusionError, Result};
-use hashbrown::HashMap;
 use log::debug;
 use parking_lot::Mutex;
 use std::{

datafusion/expr/src/conditional_expressions.rs

@@ -19,8 +19,7 @@
 use crate::expr::Case;
 use crate::{expr_schema::ExprSchemable, Expr};
 use arrow::datatypes::DataType;
-use datafusion_common::{plan_err, DFSchema, Result};
-use std::collections::HashSet;
+use datafusion_common::{plan_err, DFSchema, HashSet, Result};
 
 /// Helper struct for building [Expr::Case]
 pub struct CaseBuilder {

datafusion/expr/src/execution_props.rs

@@ -18,7 +18,7 @@
 use crate::var_provider::{VarProvider, VarType};
 use chrono::{DateTime, TimeZone, Utc};
 use datafusion_common::alias::AliasGenerator;
-use std::collections::HashMap;
+use datafusion_common::HashMap;
 use std::sync::Arc;
 
 /// Holds per-query execution properties and data (such as statement

datafusion/expr/src/expr.rs

@@ -17,7 +17,7 @@
 
 //! Logical Expressions: [`Expr`]
 
-use std::collections::{HashMap, HashSet};
+use std::collections::HashSet;
 use std::fmt::{self, Display, Formatter, Write};
 use std::hash::{Hash, Hasher};
 use std::mem;
@@ -39,7 +39,7 @@ use datafusion_common::tree_node::{
     Transformed, TransformedResult, TreeNode, TreeNodeRecursion,
 };
 use datafusion_common::{
-    plan_err, Column, DFSchema, Result, ScalarValue, TableReference,
+    plan_err, Column, DFSchema, HashMap, Result, ScalarValue, TableReference,
 };
 use datafusion_functions_window_common::field::WindowUDFFieldArgs;
 use sqlparser::ast::{

datafusion/expr/src/registry.rs

@@ -20,8 +20,8 @@
 use crate::expr_rewriter::FunctionRewrite;
 use crate::planner::ExprPlanner;
 use crate::{AggregateUDF, ScalarUDF, UserDefinedLogicalNode, WindowUDF};
-use datafusion_common::{not_impl_err, plan_datafusion_err, Result};
-use std::collections::{HashMap, HashSet};
+use datafusion_common::{not_impl_err, plan_datafusion_err, HashMap, Result};
+use std::collections::HashSet;
 use std::fmt::Debug;
 use std::sync::Arc;
 

datafusion/expr/src/utils.rs

@@ -18,7 +18,7 @@
 //! Expression utilities
 
 use std::cmp::Ordering;
-use std::collections::{HashMap, HashSet};
+use std::collections::HashSet;
 use std::ops::Deref;
 use std::sync::Arc;
 
@@ -36,7 +36,7 @@ use datafusion_common::tree_node::{
 use datafusion_common::utils::get_at_indices;
 use datafusion_common::{
     internal_err, plan_datafusion_err, plan_err, Column, DFSchema, DFSchemaRef,
-    DataFusionError, Result, TableReference,
+    DataFusionError, HashMap, Result, TableReference,
 };
 
 use indexmap::IndexSet;

datafusion/functions-aggregate/src/median.rs

@@ -15,7 +15,6 @@
 // specific language governing permissions and limitations
 // under the License.
 
-use std::collections::HashSet;
 use std::fmt::{Debug, Formatter};
 use std::mem::{size_of, size_of_val};
 use std::sync::{Arc, OnceLock};
@@ -33,7 +32,7 @@ use arrow::array::Array;
 use arrow::array::ArrowNativeTypeOp;
 use arrow::datatypes::ArrowNativeType;
 
-use datafusion_common::{DataFusionError, Result, ScalarValue};
+use datafusion_common::{DataFusionError, HashSet, Result, ScalarValue};
 use datafusion_expr::aggregate_doc_sections::DOC_SECTION_GENERAL;
 use datafusion_expr::function::StateFieldsArgs;
 use datafusion_expr::{

datafusion/functions-aggregate/src/regr.rs

@@ -24,8 +24,10 @@ use arrow::{
     datatypes::DataType,
     datatypes::Field,
 };
-use datafusion_common::{downcast_value, plan_err, unwrap_or_internal_err, ScalarValue};
-use datafusion_common::{DataFusionError, Result};
+use datafusion_common::{
+    downcast_value, plan_err, unwrap_or_internal_err, DataFusionError, HashMap, Result,
+    ScalarValue,
+};
 use datafusion_expr::aggregate_doc_sections::DOC_SECTION_STATISTICAL;
 use datafusion_expr::function::{AccumulatorArgs, StateFieldsArgs};
 use datafusion_expr::type_coercion::aggregates::NUMERICS;
@@ -34,7 +36,6 @@ use datafusion_expr::{
     Accumulator, AggregateUDFImpl, Documentation, Signature, Volatility,
 };
 use std::any::Any;
-use std::collections::HashMap;
 use std::fmt::Debug;
 use std::mem::size_of_val;
 use std::sync::OnceLock;

datafusion/functions-nested/src/except.rs

@@ -23,13 +23,12 @@ use arrow_array::cast::AsArray;
 use arrow_array::{Array, ArrayRef, GenericListArray, OffsetSizeTrait};
 use arrow_buffer::OffsetBuffer;
 use arrow_schema::{DataType, FieldRef};
-use datafusion_common::{exec_err, internal_err, Result};
+use datafusion_common::{exec_err, internal_err, HashSet, Result};
 use datafusion_expr::scalar_doc_sections::DOC_SECTION_ARRAY;
 use datafusion_expr::{
     ColumnarValue, Documentation, ScalarUDFImpl, Signature, Volatility,
 };
 use std::any::Any;
-use std::collections::HashSet;
 use std::sync::{Arc, OnceLock};
 
 make_udf_expr_and_func!(

datafusion/functions-nested/src/map.rs

@@ -16,7 +16,7 @@
 // under the License.
 
 use std::any::Any;
-use std::collections::{HashSet, VecDeque};
+use std::collections::VecDeque;
 use std::sync::{Arc, OnceLock};
 
 use arrow::array::ArrayData;
@@ -25,7 +25,7 @@ use arrow_buffer::{Buffer, ToByteSlice};
 use arrow_schema::{DataType, Field, SchemaBuilder};
 
 use datafusion_common::utils::{fixed_size_list_to_arrays, list_to_arrays};
-use datafusion_common::{exec_err, Result, ScalarValue};
+use datafusion_common::{exec_err, HashSet, Result, ScalarValue};
 use datafusion_expr::expr::ScalarFunction;
 use datafusion_expr::scalar_doc_sections::DOC_SECTION_MAP;
 use datafusion_expr::{

datafusion/functions/src/core/named_struct.rs

@@ -17,11 +17,10 @@
 
 use arrow::array::StructArray;
 use arrow::datatypes::{DataType, Field, Fields};
-use datafusion_common::{exec_err, internal_err, Result, ScalarValue};
+use datafusion_common::{exec_err, internal_err, HashSet, Result, ScalarValue};
 use datafusion_expr::scalar_doc_sections::DOC_SECTION_STRUCT;
 use datafusion_expr::{ColumnarValue, Documentation, Expr, ExprSchemable};
 use datafusion_expr::{ScalarUDFImpl, Signature, Volatility};
-use hashbrown::HashSet;
 use std::any::Any;
 use std::sync::{Arc, OnceLock};
 

datafusion/functions/src/unicode/translate.rs

@@ -22,7 +22,7 @@ use arrow::array::{
     ArrayAccessor, ArrayIter, ArrayRef, AsArray, GenericStringArray, OffsetSizeTrait,
 };
 use arrow::datatypes::DataType;
-use hashbrown::HashMap;
+use datafusion_common::HashMap;
 use unicode_segmentation::UnicodeSegmentation;
 
 use crate::utils::{make_scalar_function, utf8_to_str_type};

datafusion/optimizer/src/decorrelate.rs

@@ -17,7 +17,7 @@
 
 //! [`PullUpCorrelatedExpr`] converts correlated subqueries to `Joins`
 
-use std::collections::{BTreeSet, HashMap};
+use std::collections::BTreeSet;
 use std::ops::Deref;
 use std::sync::Arc;
 
@@ -27,7 +27,7 @@ use crate::utils::collect_subquery_cols;
 use datafusion_common::tree_node::{
     Transformed, TransformedResult, TreeNode, TreeNodeRecursion, TreeNodeRewriter,
 };
-use datafusion_common::{plan_err, Column, DFSchemaRef, Result, ScalarValue};
+use datafusion_common::{plan_err, Column, DFSchemaRef, HashMap, Result, ScalarValue};
 use datafusion_expr::expr::Alias;
 use datafusion_expr::simplify::SimplifyContext;
 use datafusion_expr::utils::{conjunction, find_join_exprs, split_conjunction};

datafusion/optimizer/src/optimize_projections/mod.rs

@@ -19,15 +19,15 @@
 
 mod required_indices;
 
-use std::collections::{HashMap, HashSet};
+use std::collections::HashSet;
 use std::sync::Arc;
 
 use crate::optimizer::ApplyOrder;
 use crate::{OptimizerConfig, OptimizerRule};
 
 use datafusion_common::{
     get_required_group_by_exprs_indices, internal_datafusion_err, internal_err, Column,
-    JoinType, Result,
+    HashMap, JoinType, Result,
 };
 use datafusion_expr::expr::Alias;
 use datafusion_expr::Unnest;

datafusion/optimizer/src/optimizer.rs

@@ -17,7 +17,6 @@
 
 //! [`Optimizer`] and [`OptimizerRule`]
 
-use std::collections::HashSet;
 use std::fmt::Debug;
 use std::sync::Arc;
 
@@ -29,7 +28,7 @@ use datafusion_common::alias::AliasGenerator;
 use datafusion_common::config::ConfigOptions;
 use datafusion_common::instant::Instant;
 use datafusion_common::tree_node::{Transformed, TreeNodeRewriter};
-use datafusion_common::{internal_err, DFSchema, DataFusionError, Result};
+use datafusion_common::{internal_err, DFSchema, DataFusionError, HashSet, Result};
 use datafusion_expr::logical_plan::LogicalPlan;
 
 use crate::common_subexpr_eliminate::CommonSubexprEliminate;

datafusion/optimizer/src/single_distinct_to_groupby.rs

@@ -22,7 +22,9 @@ use std::sync::Arc;
 use crate::optimizer::ApplyOrder;
 use crate::{OptimizerConfig, OptimizerRule};
 
-use datafusion_common::{internal_err, tree_node::Transformed, DataFusionError, Result};
+use datafusion_common::{
+    internal_err, tree_node::Transformed, DataFusionError, HashSet, Result,
+};
 use datafusion_expr::builder::project;
 use datafusion_expr::{
     col,
@@ -31,8 +33,6 @@ use datafusion_expr::{
     Expr,
 };
 
-use hashbrown::HashSet;
-
 /// single distinct to group by optimizer rule
 ///  ```text
 ///    Before: