This is an automated email from the ASF dual-hosted git repository.
dheres pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion.git
The following commit(s) were added to refs/heads/master by this push:
new e1e7b86 Address clippy warnings (#1553)
e1e7b86 is described below
commit e1e7b8651f0aedc93fbf830daef82457f32bf0c2
Author: Sergey Melnychuk <[email protected]>
AuthorDate: Wed Jan 12 21:39:34 2022 +0100
Address clippy warnings (#1553)
* Fix 'new_without_default' clippy warnings
* Fix 'from_over_into' clippy warnings
* Push 'allow(module_inception)' down from lib.rs
* Fix 'complex_type' clippy warning with type alias
* Remove unused yet allowed clippy warnings
* Fix 'new_without_default' clippy warnings for tests
---
datafusion/src/catalog/catalog.rs | 12 +++++++
datafusion/src/catalog/mod.rs | 1 +
datafusion/src/catalog/schema.rs | 6 ++++
datafusion/src/datasource/mod.rs | 1 +
datafusion/src/datasource/object_store/mod.rs | 6 ++++
datafusion/src/execution/context.rs | 42 +++++++++++++++-------
datafusion/src/execution/options.rs | 6 ++++
datafusion/src/lib.rs | 9 -----
datafusion/src/logical_plan/dfschema.rs | 23 ++++++------
.../src/optimizer/common_subexpr_eliminate.rs | 6 ++++
datafusion/src/optimizer/eliminate_limit.rs | 1 +
datafusion/src/optimizer/filter_push_down.rs | 1 +
datafusion/src/optimizer/limit_push_down.rs | 1 +
datafusion/src/optimizer/mod.rs | 1 +
datafusion/src/optimizer/projection_push_down.rs | 1 +
datafusion/src/optimizer/simplify_expressions.rs | 1 +
.../src/optimizer/single_distinct_to_groupby.rs | 1 +
.../src/physical_optimizer/aggregate_statistics.rs | 1 +
.../src/physical_optimizer/coalesce_batches.rs | 1 +
.../physical_optimizer/hash_build_probe_order.rs | 1 +
datafusion/src/physical_optimizer/merge_exec.rs | 1 +
datafusion/src/physical_optimizer/repartition.rs | 1 +
datafusion/src/physical_plan/expressions/case.rs | 10 +++---
datafusion/src/physical_plan/metrics/value.rs | 18 ++++++++++
datafusion/src/test/exec.rs | 7 ++++
datafusion/src/test/variable.rs | 2 ++
26 files changed, 125 insertions(+), 36 deletions(-)
diff --git a/datafusion/src/catalog/catalog.rs
b/datafusion/src/catalog/catalog.rs
index 30fea1f..7dbfa5a 100644
--- a/datafusion/src/catalog/catalog.rs
+++ b/datafusion/src/catalog/catalog.rs
@@ -59,6 +59,12 @@ impl MemoryCatalogList {
}
}
+impl Default for MemoryCatalogList {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl CatalogList for MemoryCatalogList {
fn as_any(&self) -> &dyn Any {
self
@@ -84,6 +90,12 @@ impl CatalogList for MemoryCatalogList {
}
}
+impl Default for MemoryCatalogProvider {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
/// Represents a catalog, comprising a number of named schemas.
pub trait CatalogProvider: Sync + Send {
/// Returns the catalog provider as [`Any`](std::any::Any)
diff --git a/datafusion/src/catalog/mod.rs b/datafusion/src/catalog/mod.rs
index 10591f0..478cdef 100644
--- a/datafusion/src/catalog/mod.rs
+++ b/datafusion/src/catalog/mod.rs
@@ -18,6 +18,7 @@
//! This module contains interfaces and default implementations
//! of table namespacing concepts, including catalogs and schemas.
+#![allow(clippy::module_inception)]
pub mod catalog;
pub mod information_schema;
pub mod schema;
diff --git a/datafusion/src/catalog/schema.rs b/datafusion/src/catalog/schema.rs
index cf754f6..08707ea 100644
--- a/datafusion/src/catalog/schema.rs
+++ b/datafusion/src/catalog/schema.rs
@@ -79,6 +79,12 @@ impl MemorySchemaProvider {
}
}
+impl Default for MemorySchemaProvider {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl SchemaProvider for MemorySchemaProvider {
fn as_any(&self) -> &dyn Any {
self
diff --git a/datafusion/src/datasource/mod.rs b/datafusion/src/datasource/mod.rs
index 9f4f77f..6e119f0 100644
--- a/datafusion/src/datasource/mod.rs
+++ b/datafusion/src/datasource/mod.rs
@@ -17,6 +17,7 @@
//! DataFusion data sources
+#![allow(clippy::module_inception)]
pub mod datasource;
pub mod empty;
pub mod file_format;
diff --git a/datafusion/src/datasource/object_store/mod.rs
b/datafusion/src/datasource/object_store/mod.rs
index 59e1841..aece82a 100644
--- a/datafusion/src/datasource/object_store/mod.rs
+++ b/datafusion/src/datasource/object_store/mod.rs
@@ -186,6 +186,12 @@ impl fmt::Debug for ObjectStoreRegistry {
}
}
+impl Default for ObjectStoreRegistry {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl ObjectStoreRegistry {
/// Create the registry that object stores can registered into.
/// ['LocalFileSystem'] store is registered in by default to support read
local files natively.
diff --git a/datafusion/src/execution/context.rs
b/datafusion/src/execution/context.rs
index 8c3df46..944284b 100644
--- a/datafusion/src/execution/context.rs
+++ b/datafusion/src/execution/context.rs
@@ -141,6 +141,12 @@ pub struct ExecutionContext {
pub state: Arc<Mutex<ExecutionContextState>>,
}
+impl Default for ExecutionContext {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl ExecutionContext {
/// Creates a new execution context using a default configuration.
pub fn new() -> Self {
@@ -1049,6 +1055,27 @@ pub struct ExecutionProps {
pub(crate) query_execution_start_time: DateTime<Utc>,
}
+impl Default for ExecutionProps {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
+impl ExecutionProps {
+ /// Creates a new execution props
+ pub fn new() -> Self {
+ ExecutionProps {
+ query_execution_start_time: chrono::Utc::now(),
+ }
+ }
+
+ /// Marks the execution of query started timestamp
+ pub fn start_execution(&mut self) -> &Self {
+ self.query_execution_start_time = chrono::Utc::now();
+ &*self
+ }
+}
+
/// Execution context for registering data sources and executing queries
#[derive(Clone)]
pub struct ExecutionContextState {
@@ -1068,18 +1095,9 @@ pub struct ExecutionContextState {
pub object_store_registry: Arc<ObjectStoreRegistry>,
}
-impl ExecutionProps {
- /// Creates a new execution props
- pub fn new() -> Self {
- ExecutionProps {
- query_execution_start_time: chrono::Utc::now(),
- }
- }
-
- /// Marks the execution of query started timestamp
- pub fn start_execution(&mut self) -> &Self {
- self.query_execution_start_time = chrono::Utc::now();
- &*self
+impl Default for ExecutionContextState {
+ fn default() -> Self {
+ Self::new()
}
}
diff --git a/datafusion/src/execution/options.rs
b/datafusion/src/execution/options.rs
index c6b5ff6..219e2fd 100644
--- a/datafusion/src/execution/options.rs
+++ b/datafusion/src/execution/options.rs
@@ -46,6 +46,12 @@ pub struct CsvReadOptions<'a> {
pub file_extension: &'a str,
}
+impl<'a> Default for CsvReadOptions<'a> {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl<'a> CsvReadOptions<'a> {
/// Create a CSV read option with default presets
pub fn new() -> Self {
diff --git a/datafusion/src/lib.rs b/datafusion/src/lib.rs
index df9efaf..26d55bc 100644
--- a/datafusion/src/lib.rs
+++ b/datafusion/src/lib.rs
@@ -15,15 +15,6 @@
// specific language governing permissions and limitations
// under the License.
#![warn(missing_docs, clippy::needless_borrow)]
-// Clippy lints, some should be disabled incrementally
-#![allow(
- clippy::float_cmp,
- clippy::from_over_into,
- clippy::module_inception,
- clippy::new_without_default,
- clippy::type_complexity,
- clippy::upper_case_acronyms
-)]
//! [DataFusion](https://github.com/apache/arrow-datafusion)
//! is an extensible query execution framework that uses
diff --git a/datafusion/src/logical_plan/dfschema.rs
b/datafusion/src/logical_plan/dfschema.rs
index 31143c4..9db720e 100644
--- a/datafusion/src/logical_plan/dfschema.rs
+++ b/datafusion/src/logical_plan/dfschema.rs
@@ -297,11 +297,12 @@ impl DFSchema {
}
}
-impl Into<Schema> for DFSchema {
- /// Convert a schema into a DFSchema
- fn into(self) -> Schema {
+impl From<DFSchema> for Schema {
+ /// Convert DFSchema into a Schema
+ fn from(df_schema: DFSchema) -> Self {
Schema::new(
- self.fields
+ df_schema
+ .fields
.into_iter()
.map(|f| {
if f.qualifier().is_some() {
@@ -319,10 +320,10 @@ impl Into<Schema> for DFSchema {
}
}
-impl Into<Schema> for &DFSchema {
- /// Convert a schema into a DFSchema
- fn into(self) -> Schema {
- Schema::new(self.fields.iter().map(|f| f.field.clone()).collect())
+impl From<&DFSchema> for Schema {
+ /// Convert DFSchema reference into a Schema
+ fn from(df_schema: &DFSchema) -> Self {
+ Schema::new(df_schema.fields.iter().map(|f| f.field.clone()).collect())
}
}
@@ -340,9 +341,9 @@ impl TryFrom<Schema> for DFSchema {
}
}
-impl Into<SchemaRef> for DFSchema {
- fn into(self) -> SchemaRef {
- SchemaRef::new(self.into())
+impl From<DFSchema> for SchemaRef {
+ fn from(df_schema: DFSchema) -> Self {
+ SchemaRef::new(df_schema.into())
}
}
diff --git a/datafusion/src/optimizer/common_subexpr_eliminate.rs
b/datafusion/src/optimizer/common_subexpr_eliminate.rs
index 233d112..9470734 100644
--- a/datafusion/src/optimizer/common_subexpr_eliminate.rs
+++ b/datafusion/src/optimizer/common_subexpr_eliminate.rs
@@ -69,6 +69,12 @@ impl OptimizerRule for CommonSubexprEliminate {
}
}
+impl Default for CommonSubexprEliminate {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl CommonSubexprEliminate {
#[allow(missing_docs)]
pub fn new() -> Self {
diff --git a/datafusion/src/optimizer/eliminate_limit.rs
b/datafusion/src/optimizer/eliminate_limit.rs
index 1f74ae2..c1fc206 100644
--- a/datafusion/src/optimizer/eliminate_limit.rs
+++ b/datafusion/src/optimizer/eliminate_limit.rs
@@ -25,6 +25,7 @@ use super::utils;
use crate::execution::context::ExecutionProps;
/// Optimization rule that replaces LIMIT 0 with an
[LogicalPlan::EmptyRelation]
+#[derive(Default)]
pub struct EliminateLimit;
impl EliminateLimit {
diff --git a/datafusion/src/optimizer/filter_push_down.rs
b/datafusion/src/optimizer/filter_push_down.rs
index c55a5cd..c721712 100644
--- a/datafusion/src/optimizer/filter_push_down.rs
+++ b/datafusion/src/optimizer/filter_push_down.rs
@@ -54,6 +54,7 @@ use std::{
/// and when it reaches a node that does not commute with it, it adds the
filter to that place.
/// When it passes through a projection, it re-writes the filter's expression
taking into accoun that projection.
/// When multiple filters would have been written, it `AND` their expressions
into a single expression.
+#[derive(Default)]
pub struct FilterPushDown {}
#[derive(Debug, Clone, Default)]
diff --git a/datafusion/src/optimizer/limit_push_down.rs
b/datafusion/src/optimizer/limit_push_down.rs
index 15d5093..4fa6e27 100644
--- a/datafusion/src/optimizer/limit_push_down.rs
+++ b/datafusion/src/optimizer/limit_push_down.rs
@@ -28,6 +28,7 @@ use std::sync::Arc;
/// Optimization rule that tries pushes down LIMIT n
/// where applicable to reduce the amount of scanned / processed data
+#[derive(Default)]
pub struct LimitPushDown {}
impl LimitPushDown {
diff --git a/datafusion/src/optimizer/mod.rs b/datafusion/src/optimizer/mod.rs
index c5cab97..984cbee 100644
--- a/datafusion/src/optimizer/mod.rs
+++ b/datafusion/src/optimizer/mod.rs
@@ -18,6 +18,7 @@
//! This module contains a query optimizer that operates against a logical
plan and applies
//! some simple rules to a logical plan, such as "Projection Push Down" and
"Type Coercion".
+#![allow(clippy::module_inception)]
pub mod common_subexpr_eliminate;
pub mod eliminate_limit;
pub mod filter_push_down;
diff --git a/datafusion/src/optimizer/projection_push_down.rs
b/datafusion/src/optimizer/projection_push_down.rs
index f92ab65..fb45e98 100644
--- a/datafusion/src/optimizer/projection_push_down.rs
+++ b/datafusion/src/optimizer/projection_push_down.rs
@@ -39,6 +39,7 @@ use std::{
/// Optimizer that removes unused projections and aggregations from plans
/// This reduces both scans and
+#[derive(Default)]
pub struct ProjectionPushDown {}
impl OptimizerRule for ProjectionPushDown {
diff --git a/datafusion/src/optimizer/simplify_expressions.rs
b/datafusion/src/optimizer/simplify_expressions.rs
index 7445c90..653c613 100644
--- a/datafusion/src/optimizer/simplify_expressions.rs
+++ b/datafusion/src/optimizer/simplify_expressions.rs
@@ -43,6 +43,7 @@ use crate::{error::Result, logical_plan::Operator};
/// is optimized to
/// `Filter: b > 2`
///
+#[derive(Default)]
pub struct SimplifyExpressions {}
/// returns true if `needle` is found in a chain of search_op
diff --git a/datafusion/src/optimizer/single_distinct_to_groupby.rs
b/datafusion/src/optimizer/single_distinct_to_groupby.rs
index 9bddec9..02a24e2 100644
--- a/datafusion/src/optimizer/single_distinct_to_groupby.rs
+++ b/datafusion/src/optimizer/single_distinct_to_groupby.rs
@@ -40,6 +40,7 @@ use std::sync::Arc;
/// )
/// GROUP BY k
/// ```
+#[derive(Default)]
pub struct SingleDistinctToGroupBy {}
const SINGLE_DISTINCT_ALIAS: &str = "alias1";
diff --git a/datafusion/src/physical_optimizer/aggregate_statistics.rs
b/datafusion/src/physical_optimizer/aggregate_statistics.rs
index 2732777..515f732 100644
--- a/datafusion/src/physical_optimizer/aggregate_statistics.rs
+++ b/datafusion/src/physical_optimizer/aggregate_statistics.rs
@@ -34,6 +34,7 @@ use super::utils::optimize_children;
use crate::error::Result;
/// Optimizer that uses available statistics for aggregate functions
+#[derive(Default)]
pub struct AggregateStatistics {}
impl AggregateStatistics {
diff --git a/datafusion/src/physical_optimizer/coalesce_batches.rs
b/datafusion/src/physical_optimizer/coalesce_batches.rs
index 9af8911..14616a7 100644
--- a/datafusion/src/physical_optimizer/coalesce_batches.rs
+++ b/datafusion/src/physical_optimizer/coalesce_batches.rs
@@ -29,6 +29,7 @@ use crate::{
use std::sync::Arc;
/// Optimizer that introduces CoalesceBatchesExec to avoid overhead with small
batches
+#[derive(Default)]
pub struct CoalesceBatches {}
impl CoalesceBatches {
diff --git a/datafusion/src/physical_optimizer/hash_build_probe_order.rs
b/datafusion/src/physical_optimizer/hash_build_probe_order.rs
index 0d1c39f..1184751 100644
--- a/datafusion/src/physical_optimizer/hash_build_probe_order.rs
+++ b/datafusion/src/physical_optimizer/hash_build_probe_order.rs
@@ -38,6 +38,7 @@ use crate::error::Result;
/// is the smallest.
/// If the information is not available, the order stays the same,
/// so that it could be optimized manually in a query.
+#[derive(Default)]
pub struct HashBuildProbeOrder {}
impl HashBuildProbeOrder {
diff --git a/datafusion/src/physical_optimizer/merge_exec.rs
b/datafusion/src/physical_optimizer/merge_exec.rs
index 0127313..58823a6 100644
--- a/datafusion/src/physical_optimizer/merge_exec.rs
+++ b/datafusion/src/physical_optimizer/merge_exec.rs
@@ -26,6 +26,7 @@ use crate::{
use std::sync::Arc;
/// Introduces CoalescePartitionsExec
+#[derive(Default)]
pub struct AddCoalescePartitionsExec {}
impl AddCoalescePartitionsExec {
diff --git a/datafusion/src/physical_optimizer/repartition.rs
b/datafusion/src/physical_optimizer/repartition.rs
index 8ac9dad..26f77ef 100644
--- a/datafusion/src/physical_optimizer/repartition.rs
+++ b/datafusion/src/physical_optimizer/repartition.rs
@@ -26,6 +26,7 @@ use crate::physical_plan::{Distribution, Partitioning::*};
use crate::{error::Result, execution::context::ExecutionConfig};
/// Optimizer that introduces repartition to introduce more parallelism in the
plan
+#[derive(Default)]
pub struct Repartition {}
impl Repartition {
diff --git a/datafusion/src/physical_plan/expressions/case.rs
b/datafusion/src/physical_plan/expressions/case.rs
index f577d6c..551d87a 100644
--- a/datafusion/src/physical_plan/expressions/case.rs
+++ b/datafusion/src/physical_plan/expressions/case.rs
@@ -24,6 +24,8 @@ use arrow::compute::{eq, eq_utf8};
use arrow::datatypes::{DataType, Schema};
use arrow::record_batch::RecordBatch;
+type WhenThen = (Arc<dyn PhysicalExpr>, Arc<dyn PhysicalExpr>);
+
/// The CASE expression is similar to a series of nested if/else and there are
two forms that
/// can be used. The first form consists of a series of boolean "when"
expressions with
/// corresponding "then" expressions, and an optional "else" expression.
@@ -46,7 +48,7 @@ pub struct CaseExpr {
/// Optional base expression that can be compared to literal values in the
"when" expressions
expr: Option<Arc<dyn PhysicalExpr>>,
/// One or more when/then expressions
- when_then_expr: Vec<(Arc<dyn PhysicalExpr>, Arc<dyn PhysicalExpr>)>,
+ when_then_expr: Vec<WhenThen>,
/// Optional "else" expression
else_expr: Option<Arc<dyn PhysicalExpr>>,
}
@@ -71,7 +73,7 @@ impl CaseExpr {
/// Create a new CASE WHEN expression
pub fn try_new(
expr: Option<Arc<dyn PhysicalExpr>>,
- when_then_expr: &[(Arc<dyn PhysicalExpr>, Arc<dyn PhysicalExpr>)],
+ when_then_expr: &[WhenThen],
else_expr: Option<Arc<dyn PhysicalExpr>>,
) -> Result<Self> {
if when_then_expr.is_empty() {
@@ -93,7 +95,7 @@ impl CaseExpr {
}
/// One or more when/then expressions
- pub fn when_then_expr(&self) -> &[(Arc<dyn PhysicalExpr>, Arc<dyn
PhysicalExpr>)] {
+ pub fn when_then_expr(&self) -> &[WhenThen] {
&self.when_then_expr
}
@@ -437,7 +439,7 @@ impl PhysicalExpr for CaseExpr {
/// Create a CASE expression
pub fn case(
expr: Option<Arc<dyn PhysicalExpr>>,
- when_thens: &[(Arc<dyn PhysicalExpr>, Arc<dyn PhysicalExpr>)],
+ when_thens: &[WhenThen],
else_expr: Option<Arc<dyn PhysicalExpr>>,
) -> Result<Arc<dyn PhysicalExpr>> {
Ok(Arc::new(CaseExpr::try_new(expr, when_thens, else_expr)?))
diff --git a/datafusion/src/physical_plan/metrics/value.rs
b/datafusion/src/physical_plan/metrics/value.rs
index 6f63583..1caf13e 100644
--- a/datafusion/src/physical_plan/metrics/value.rs
+++ b/datafusion/src/physical_plan/metrics/value.rs
@@ -50,6 +50,12 @@ impl Display for Count {
}
}
+impl Default for Count {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl Count {
/// create a new counter
pub fn new() -> Self {
@@ -78,6 +84,12 @@ pub struct Time {
nanos: Arc<AtomicUsize>,
}
+impl Default for Time {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl PartialEq for Time {
fn eq(&self, other: &Self) -> bool {
self.value().eq(&other.value())
@@ -140,6 +152,12 @@ pub struct Timestamp {
timestamp: Arc<Mutex<Option<DateTime<Utc>>>>,
}
+impl Default for Timestamp {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl Timestamp {
/// Create a new timestamp and sets its value to 0
pub fn new() -> Self {
diff --git a/datafusion/src/test/exec.rs b/datafusion/src/test/exec.rs
index 4a9534f..8351c9b 100644
--- a/datafusion/src/test/exec.rs
+++ b/datafusion/src/test/exec.rs
@@ -342,6 +342,13 @@ impl ExecutionPlan for BarrierExec {
pub struct ErrorExec {
schema: SchemaRef,
}
+
+impl Default for ErrorExec {
+ fn default() -> Self {
+ Self::new()
+ }
+}
+
impl ErrorExec {
pub fn new() -> Self {
let schema = Arc::new(Schema::new(vec![Field::new(
diff --git a/datafusion/src/test/variable.rs b/datafusion/src/test/variable.rs
index 47d1370..fcde0e9 100644
--- a/datafusion/src/test/variable.rs
+++ b/datafusion/src/test/variable.rs
@@ -22,6 +22,7 @@ use crate::scalar::ScalarValue;
use crate::variable::VarProvider;
/// System variable
+#[derive(Default)]
pub struct SystemVar {}
impl SystemVar {
@@ -40,6 +41,7 @@ impl VarProvider for SystemVar {
}
/// user defined variable
+#[derive(Default)]
pub struct UserDefinedVar {}
impl UserDefinedVar {
