Apply clippy fixes for Rust 1.83 (#13596)

* Apply clippy fixes

`dev/rust_lint.sh` no longer passes for me, maybe because of `rustup
update`. This is first portion of fixes suggested by clippy.

* Fix typo

Co-authored-by: Oleks V <comphead@users.noreply.github.com>

* Suppress missing docs clippy check in test code

* Revert "Temporarily pin toolchain version to avoid clippy (#13598)"

This reverts commit 2b37018.
Toolchain pinning is no longer needed.

---------

Co-authored-by: Daniël Heres <danielheres@gmail.com>
Co-authored-by: Oleks V <comphead@users.noreply.github.com>

Author: 3 people

datafusion/catalog/src/catalog.rs

@@ -101,7 +101,6 @@ use datafusion_common::Result;
 /// [`UnityCatalogProvider`]: https://github.com/delta-io/delta-rs/blob/951436ecec476ce65b5ed3b58b50fb0846ca7b91/crates/deltalake-core/src/data_catalog/unity/datafusion.rs#L111-L123
 ///
 /// [`TableProvider`]: crate::TableProvider
-
 pub trait CatalogProvider: Debug + Sync + Send {
     /// Returns the catalog provider as [`Any`]
     /// so that it can be downcast to a specific implementation.

datafusion/common/src/column.rs

@@ -109,21 +109,23 @@ impl Column {
     /// where `"foo.BAR"` would be parsed to a reference to column named `foo.BAR`
     pub fn from_qualified_name(flat_name: impl Into<String>) -> Self {
         let flat_name = flat_name.into();
-        Self::from_idents(&mut parse_identifiers_normalized(&flat_name, false))
-            .unwrap_or_else(|| Self {
+        Self::from_idents(&mut parse_identifiers_normalized(&flat_name, false)).unwrap_or(
+            Self {
                 relation: None,
                 name: flat_name,
-            })
+            },
+        )
     }
 
     /// Deserialize a fully qualified name string into a column preserving column text case
     pub fn from_qualified_name_ignore_case(flat_name: impl Into<String>) -> Self {
         let flat_name = flat_name.into();
-        Self::from_idents(&mut parse_identifiers_normalized(&flat_name, true))
-            .unwrap_or_else(|| Self {
+        Self::from_idents(&mut parse_identifiers_normalized(&flat_name, true)).unwrap_or(
+            Self {
                 relation: None,
                 name: flat_name,
-            })
+            },
+        )
     }
 
     /// return the column's name.

datafusion/common/src/hash_utils.rs

@@ -63,7 +63,7 @@ pub trait HashValue {
     fn hash_one(&self, state: &RandomState) -> u64;
 }
 
-impl<'a, T: HashValue + ?Sized> HashValue for &'a T {
+impl<T: HashValue + ?Sized> HashValue for &T {
     fn hash_one(&self, state: &RandomState) -> u64 {
         T::hash_one(self, state)
     }

datafusion/common/src/utils/mod.rs

@@ -319,17 +319,13 @@ pub fn longest_consecutive_prefix<T: Borrow<usize>>(
     count
 }
 
-/// Array Utils
-
 /// Wrap an array into a single element `ListArray`.
 /// For example `[1, 2, 3]` would be converted into `[[1, 2, 3]]`
 /// The field in the list array is nullable.
 pub fn array_into_list_array_nullable(arr: ArrayRef) -> ListArray {
     array_into_list_array(arr, true)
 }
 
-/// Array Utils
-
 /// Wrap an array into a single element `ListArray`.
 /// For example `[1, 2, 3]` would be converted into `[[1, 2, 3]]`
 pub fn array_into_list_array(arr: ArrayRef, nullable: bool) -> ListArray {
@@ -569,7 +565,7 @@ pub mod datafusion_strsim {
 
     struct StringWrapper<'a>(&'a str);
 
-    impl<'a, 'b> IntoIterator for &'a StringWrapper<'b> {
+    impl<'b> IntoIterator for &StringWrapper<'b> {
         type Item = char;
         type IntoIter = Chars<'b>;
 

datafusion/core/src/datasource/avro_to_arrow/arrow_array_reader.rs

@@ -60,7 +60,7 @@ pub struct AvroArrowArrayReader<'a, R: Read> {
     schema_lookup: BTreeMap<String, usize>,
 }
 
-impl<'a, R: Read> AvroArrowArrayReader<'a, R> {
+impl<R: Read> AvroArrowArrayReader<'_, R> {
     pub fn try_new(
         reader: R,
         schema: SchemaRef,

datafusion/core/src/datasource/avro_to_arrow/reader.rs

@@ -128,7 +128,7 @@ pub struct Reader<'a, R: Read> {
     batch_size: usize,
 }
 
-impl<'a, R: Read> Reader<'a, R> {
+impl<R: Read> Reader<'_, R> {
     /// Create a new Avro Reader from any value that implements the `Read` trait.
     ///
     /// If reading a `File`, you can customise the Reader, such as to enable schema
@@ -157,7 +157,7 @@ impl<'a, R: Read> Reader<'a, R> {
     }
 }
 
-impl<'a, R: Read> Iterator for Reader<'a, R> {
+impl<R: Read> Iterator for Reader<'_, R> {
     type Item = ArrowResult<RecordBatch>;
 
     /// Returns the next batch of results (defined by `self.batch_size`), or `None` if there

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

@@ -89,7 +89,7 @@ pub struct CsvReadOptions<'a> {
     pub file_sort_order: Vec<Vec<SortExpr>>,
 }
 
-impl<'a> Default for CsvReadOptions<'a> {
+impl Default for CsvReadOptions<'_> {
     fn default() -> Self {
         Self::new()
     }
@@ -243,7 +243,7 @@ pub struct ParquetReadOptions<'a> {
     pub file_sort_order: Vec<Vec<SortExpr>>,
 }
 
-impl<'a> Default for ParquetReadOptions<'a> {
+impl Default for ParquetReadOptions<'_> {
     fn default() -> Self {
         Self {
             file_extension: DEFAULT_PARQUET_EXTENSION,
@@ -323,7 +323,7 @@ pub struct ArrowReadOptions<'a> {
     pub table_partition_cols: Vec<(String, DataType)>,
 }
 
-impl<'a> Default for ArrowReadOptions<'a> {
+impl Default for ArrowReadOptions<'_> {
     fn default() -> Self {
         Self {
             schema: None,
@@ -368,7 +368,7 @@ pub struct AvroReadOptions<'a> {
     pub table_partition_cols: Vec<(String, DataType)>,
 }
 
-impl<'a> Default for AvroReadOptions<'a> {
+impl Default for AvroReadOptions<'_> {
     fn default() -> Self {
         Self {
             schema: None,
@@ -420,7 +420,7 @@ pub struct NdJsonReadOptions<'a> {
     pub file_sort_order: Vec<Vec<SortExpr>>,
 }
 
-impl<'a> Default for NdJsonReadOptions<'a> {
+impl Default for NdJsonReadOptions<'_> {
     fn default() -> Self {
         Self {
             schema: None,

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

@@ -477,7 +477,7 @@ impl<'a> ObjectStoreFetch<'a> {
     }
 }
 
-impl<'a> MetadataFetch for ObjectStoreFetch<'a> {
+impl MetadataFetch for ObjectStoreFetch<'_> {
     fn fetch(
         &mut self,
         range: Range<usize>,

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

@@ -135,7 +135,7 @@ pub fn split_files(
     partitioned_files.sort_by(|a, b| a.path().cmp(b.path()));
 
     // effectively this is div with rounding up instead of truncating
-    let chunk_size = (partitioned_files.len() + n - 1) / n;
+    let chunk_size = partitioned_files.len().div_ceil(n);
     let mut chunks = Vec::with_capacity(n);
     let mut current_chunk = Vec::with_capacity(chunk_size);
     for file in partitioned_files.drain(..) {

datafusion/core/src/datasource/physical_plan/file_groups.rs

@@ -217,8 +217,7 @@ impl FileGroupPartitioner {
             return None;
         }
 
-        let target_partition_size =
-            (total_size as usize + (target_partitions) - 1) / (target_partitions);
+        let target_partition_size = (total_size as usize).div_ceil(target_partitions);
 
         let current_partition_index: usize = 0;
         let current_partition_size: usize = 0;