Introduce HashMap and HashSet type aliases (apache#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::{