Fix clippy errors for Rust 1.80 (#11654)

* Fix some new warnings

Signed-off-by: Nick Cameron <nrc@ncameron.org>

* Fix formatting errors reported by clippy

Newest version of clippy complains when list item continuation is not
indented.

* Remove redundant reference

Reported by clippy

* Suppress non-trivial clippy suggestion

To be revisited

---------

Signed-off-by: Nick Cameron <nrc@ncameron.org>
Co-authored-by: Nick Cameron <nrc@ncameron.org>

Author: findepi

Cargo.toml

@@ -154,4 +154,5 @@ rpath = false
 large_futures = "warn"
 
 [workspace.lints.rust]
+unexpected_cfgs = { level = "warn", check-cfg = ["cfg(tarpaulin)"] }
 unused_imports = "deny"

datafusion/common/Cargo.toml

@@ -39,6 +39,7 @@ path = "src/lib.rs"
 avro = ["apache-avro"]
 backtrace = []
 pyarrow = ["pyo3", "arrow/pyarrow", "parquet"]
+force_hash_collisions = []
 
 [dependencies]
 ahash = { workspace = true }

datafusion/common/src/config.rs

@@ -1207,7 +1207,7 @@ impl ConfigField for TableOptions {
     /// # Parameters
     ///
     /// * `key`: The configuration key specifying which setting to adjust, prefixed with the format (e.g., "format.delimiter")
-    /// for CSV format.
+    ///   for CSV format.
     /// * `value`: The value to set for the specified configuration key.
     ///
     /// # Returns

datafusion/common/src/hash_utils.rs

@@ -17,22 +17,27 @@
 
 //! Functionality used both on logical and physical plans
 
+#[cfg(not(feature = "force_hash_collisions"))]
 use std::sync::Arc;
 
 use ahash::RandomState;
 use arrow::array::*;
 use arrow::datatypes::*;
 use arrow::row::Rows;
+#[cfg(not(feature = "force_hash_collisions"))]
 use arrow::{downcast_dictionary_array, downcast_primitive_array};
 use arrow_buffer::IntervalDayTime;
 use arrow_buffer::IntervalMonthDayNano;
 
+#[cfg(not(feature = "force_hash_collisions"))]
 use crate::cast::{
     as_boolean_array, as_fixed_size_list_array, as_generic_binary_array,
     as_large_list_array, as_list_array, as_map_array, as_primitive_array,
     as_string_array, as_struct_array,
 };
-use crate::error::{Result, _internal_err};
+use crate::error::Result;
+#[cfg(not(feature = "force_hash_collisions"))]
+use crate::error::_internal_err;
 
 // Combines two hashes into one hash
 #[inline]
@@ -41,6 +46,7 @@ pub fn combine_hashes(l: u64, r: u64) -> u64 {
     hash.wrapping_mul(37).wrapping_add(r)
 }
 
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_null(random_state: &RandomState, hashes_buffer: &'_ mut [u64], mul_col: bool) {
     if mul_col {
         hashes_buffer.iter_mut().for_each(|hash| {
@@ -90,6 +96,7 @@ hash_float_value!((half::f16, u16), (f32, u32), (f64, u64));
 /// Builds hash values of PrimitiveArray and writes them into `hashes_buffer`
 /// If `rehash==true` this combines the previous hash value in the buffer
 /// with the new hash using `combine_hashes`
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_array_primitive<T>(
     array: &PrimitiveArray<T>,
     random_state: &RandomState,
@@ -135,6 +142,7 @@ fn hash_array_primitive<T>(
 /// Hashes one array into the `hashes_buffer`
 /// If `rehash==true` this combines the previous hash value in the buffer
 /// with the new hash using `combine_hashes`
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_array<T>(
     array: T,
     random_state: &RandomState,
@@ -180,6 +188,7 @@ fn hash_array<T>(
 }
 
 /// Hash the values in a dictionary array
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_dictionary<K: ArrowDictionaryKeyType>(
     array: &DictionaryArray<K>,
     random_state: &RandomState,
@@ -210,6 +219,7 @@ fn hash_dictionary<K: ArrowDictionaryKeyType>(
     Ok(())
 }
 
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_struct_array(
     array: &StructArray,
     random_state: &RandomState,
@@ -270,6 +280,7 @@ fn hash_map_array(
     Ok(())
 }
 
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_list_array<OffsetSize>(
     array: &GenericListArray<OffsetSize>,
     random_state: &RandomState,
@@ -303,6 +314,7 @@ where
     Ok(())
 }
 
+#[cfg(not(feature = "force_hash_collisions"))]
 fn hash_fixed_list_array(
     array: &FixedSizeListArray,
     random_state: &RandomState,
@@ -488,7 +500,11 @@ pub fn create_row_hashes_v2<'a>(
 
 #[cfg(test)]
 mod tests {
-    use arrow::{array::*, datatypes::*};
+    use std::sync::Arc;
+
+    use arrow::array::*;
+    #[cfg(not(feature = "force_hash_collisions"))]
+    use arrow::datatypes::*;
 
     use super::*;
 

datafusion/common/src/tree_node.rs

@@ -43,14 +43,14 @@ macro_rules! handle_transform_recursion {
 /// There are three categories of TreeNode APIs:
 ///
 /// 1. "Inspecting" APIs to traverse a tree of `&TreeNodes`:
-/// [`apply`], [`visit`], [`exists`].
+///    [`apply`], [`visit`], [`exists`].
 ///
 /// 2. "Transforming" APIs that traverse and consume a tree of `TreeNode`s
-/// producing possibly changed `TreeNode`s: [`transform`], [`transform_up`],
-/// [`transform_down`], [`transform_down_up`], and [`rewrite`].
+///    producing possibly changed `TreeNode`s: [`transform`], [`transform_up`],
+///    [`transform_down`], [`transform_down_up`], and [`rewrite`].
 ///
 /// 3. Internal APIs used to implement the `TreeNode` API: [`apply_children`],
-/// and [`map_children`].
+///    and [`map_children`].
 ///
 /// | Traversal Order | Inspecting | Transforming |
 /// | --- | --- | --- |

datafusion/common/src/utils/memory.rs

@@ -24,7 +24,7 @@ use crate::{DataFusionError, Result};
 /// # Parameters
 /// - `num_elements`: The number of elements expected in the hash table.
 /// - `fixed_size`: A fixed overhead size associated with the collection
-/// (e.g., HashSet or HashTable).
+///    (e.g., HashSet or HashTable).
 /// - `T`: The type of elements stored in the hash table.
 ///
 /// # Details

datafusion/common/src/utils/mod.rs

@@ -335,7 +335,7 @@ pub fn get_at_indices<T: Clone, I: Borrow<usize>>(
 /// This function finds the longest prefix of the form 0, 1, 2, ... within the
 /// collection `sequence`. Examples:
 /// - For 0, 1, 2, 4, 5; we would produce 3, meaning 0, 1, 2 is the longest satisfying
-/// prefix.
+///   prefix.
 /// - For 1, 2, 3, 4; we would produce 0, meaning there is no such prefix.
 pub fn longest_consecutive_prefix<T: Borrow<usize>>(
     sequence: impl IntoIterator<Item = T>,

datafusion/core/Cargo.toml

@@ -62,7 +62,7 @@ default = [
 ]
 encoding_expressions = ["datafusion-functions/encoding_expressions"]
 # Used for testing ONLY: causes all values to hash to the same value (test for collisions)
-force_hash_collisions = []
+force_hash_collisions = ["datafusion-physical-plan/force_hash_collisions", "datafusion-common/force_hash_collisions"]
 math_expressions = ["datafusion-functions/math_expressions"]
 parquet = ["datafusion-common/parquet", "dep:parquet"]
 pyarrow = ["datafusion-common/pyarrow", "parquet"]

datafusion/core/benches/sort.rs

@@ -21,7 +21,7 @@
 //! 1. Creates a list of tuples (sorted if necessary)
 //!
 //! 2. Divides those tuples across some number of streams of [`RecordBatch`]
-//! preserving any ordering
+//!    preserving any ordering
 //!
 //! 3. Times how long it takes for a given sort plan to process the input
 //!

datafusion/core/src/catalog/mod.rs

@@ -141,12 +141,12 @@ pub trait CatalogList: CatalogProviderList {}
 /// Here are some examples of how to implement custom catalogs:
 ///
 /// * [`datafusion-cli`]: [`DynamicFileCatalogProvider`] catalog provider
-/// that treats files and directories on a filesystem as tables.
+///   that treats files and directories on a filesystem as tables.
 ///
 /// * The [`catalog.rs`]:  a simple directory based catalog.
 ///
 ///  * [delta-rs]:  [`UnityCatalogProvider`] implementation that can
-///  read from Delta Lake tables
+///    read from Delta Lake tables
 ///
 /// [`datafusion-cli`]: https://datafusion.apache.org/user-guide/cli/index.html
 /// [`DynamicFileCatalogProvider`]: https://github.com/apache/datafusion/blob/31b9b48b08592b7d293f46e75707aad7dadd7cbc/datafusion-cli/src/catalog.rs#L75