Add unused_qualifications with deny level to linter. Fix unused_qualifications violations." (#13086)

Author: dhegberg

Cargo.toml

@@ -169,3 +169,4 @@ large_futures = "warn"
 
 [workspace.lints.rust]
 unexpected_cfgs = { level = "warn", check-cfg = ["cfg(tarpaulin)"] }
+unused_qualifications = "deny"

datafusion-examples/examples/advanced_udaf.rs

@@ -193,7 +193,7 @@ impl Accumulator for GeometricMean {
     }
 
     fn size(&self) -> usize {
-        std::mem::size_of_val(self)
+        size_of_val(self)
     }
 }
 
@@ -394,8 +394,8 @@ impl GroupsAccumulator for GeometricMeanGroupsAccumulator {
     }
 
     fn size(&self) -> usize {
-        self.counts.capacity() * std::mem::size_of::<u32>()
-            + self.prods.capacity() * std::mem::size_of::<Float64Type>()
+        self.counts.capacity() * size_of::<u32>()
+            + self.prods.capacity() * size_of::<Float64Type>()
     }
 }
 

datafusion-examples/examples/custom_datasource.rs

@@ -110,7 +110,7 @@ struct CustomDataSourceInner {
 }
 
 impl Debug for CustomDataSource {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
         f.write_str("custom_db")
     }
 }
@@ -220,7 +220,7 @@ impl CustomExec {
 }
 
 impl DisplayAs for CustomExec {
-    fn fmt_as(&self, _t: DisplayFormatType, f: &mut fmt::Formatter) -> std::fmt::Result {
+    fn fmt_as(&self, _t: DisplayFormatType, f: &mut Formatter) -> fmt::Result {
         write!(f, "CustomExec")
     }
 }

datafusion-examples/examples/custom_file_format.rs

@@ -74,10 +74,7 @@ impl FileFormat for TSVFileFormat {
         "tsv".to_string()
     }
 
-    fn get_ext_with_compression(
-        &self,
-        c: &FileCompressionType,
-    ) -> datafusion::error::Result<String> {
+    fn get_ext_with_compression(&self, c: &FileCompressionType) -> Result<String> {
         if c == &FileCompressionType::UNCOMPRESSED {
             Ok("tsv".to_string())
         } else {

datafusion-examples/examples/flight/flight_server.rs

@@ -105,7 +105,7 @@ impl FlightService for FlightServiceImpl {
                 }
 
                 // add an initial FlightData message that sends schema
-                let options = datafusion::arrow::ipc::writer::IpcWriteOptions::default();
+                let options = arrow::ipc::writer::IpcWriteOptions::default();
                 let schema_flight_data = SchemaAsIpc::new(&schema, &options);
 
                 let mut flights = vec![FlightData::from(schema_flight_data)];

datafusion-examples/examples/function_factory.rs

@@ -121,7 +121,7 @@ impl ScalarUDFImpl for ScalarFunctionWrapper {
         &self.name
     }
 
-    fn signature(&self) -> &datafusion_expr::Signature {
+    fn signature(&self) -> &Signature {
         &self.signature
     }
 

datafusion-examples/examples/simple_udaf.rs

@@ -131,7 +131,7 @@ impl Accumulator for GeometricMean {
     }
 
     fn size(&self) -> usize {
-        std::mem::size_of_val(self)
+        size_of_val(self)
     }
 }
 

datafusion-examples/examples/simplify_udaf_expression.rs

@@ -70,7 +70,7 @@ impl AggregateUDFImpl for BetterAvgUdaf {
         unimplemented!("should not be invoked")
     }
 
-    fn state_fields(&self, _args: StateFieldsArgs) -> Result<Vec<arrow_schema::Field>> {
+    fn state_fields(&self, _args: StateFieldsArgs) -> Result<Vec<Field>> {
         unimplemented!("should not be invoked")
     }
 
@@ -90,8 +90,7 @@ impl AggregateUDFImpl for BetterAvgUdaf {
     fn simplify(&self) -> Option<AggregateFunctionSimplification> {
         // as an example for this functionality we replace UDF function
         // with build-in aggregate function to illustrate the use
-        let simplify = |aggregate_function: datafusion_expr::expr::AggregateFunction,
-                        _: &dyn SimplifyInfo| {
+        let simplify = |aggregate_function: AggregateFunction, _: &dyn SimplifyInfo| {
             Ok(Expr::AggregateFunction(AggregateFunction::new_udf(
                 avg_udaf(),
                 // yes it is the same Avg, `BetterAvgUdaf` was just a

datafusion-examples/examples/simplify_udwf_expression.rs

@@ -70,8 +70,7 @@ impl WindowUDFImpl for SimplifySmoothItUdf {
 
     /// this function will simplify `SimplifySmoothItUdf` to `SmoothItUdf`.
     fn simplify(&self) -> Option<WindowFunctionSimplification> {
-        let simplify = |window_function: datafusion_expr::expr::WindowFunction,
-                        _: &dyn SimplifyInfo| {
+        let simplify = |window_function: WindowFunction, _: &dyn SimplifyInfo| {
             Ok(Expr::WindowFunction(WindowFunction {
                 fun: datafusion_expr::WindowFunctionDefinition::AggregateUDF(avg_udaf()),
                 args: window_function.args,

datafusion/common/src/config.rs

@@ -876,7 +876,7 @@ pub trait ConfigExtension: ExtensionOptions {
 }
 
 /// An object-safe API for storing arbitrary configuration
-pub trait ExtensionOptions: Send + Sync + std::fmt::Debug + 'static {
+pub trait ExtensionOptions: Send + Sync + fmt::Debug + 'static {
     /// Return `self` as [`Any`]
     ///
     /// This is needed until trait upcasting is stabilised

datafusion/common/src/join_type.rs

@@ -97,7 +97,7 @@ pub enum JoinConstraint {
 }
 
 impl Display for JoinSide {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+    fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
         match self {
             JoinSide::Left => write!(f, "left"),
             JoinSide::Right => write!(f, "right"),

datafusion/common/src/parsers.rs

@@ -18,7 +18,6 @@
 //! Interval parsing logic
 
 use std::fmt::Display;
-use std::result;
 use std::str::FromStr;
 
 use sqlparser::parser::ParserError;
@@ -41,7 +40,7 @@ pub enum CompressionTypeVariant {
 impl FromStr for CompressionTypeVariant {
     type Err = ParserError;
 
-    fn from_str(s: &str) -> result::Result<Self, ParserError> {
+    fn from_str(s: &str) -> Result<Self, ParserError> {
         let s = s.to_uppercase();
         match s.as_str() {
             "GZIP" | "GZ" => Ok(Self::GZIP),

datafusion/common/src/pyarrow.rs

@@ -34,7 +34,7 @@ impl From<DataFusionError> for PyErr {
 }
 
 impl FromPyArrow for ScalarValue {
-    fn from_pyarrow_bound(value: &pyo3::Bound<'_, pyo3::PyAny>) -> PyResult<Self> {
+    fn from_pyarrow_bound(value: &Bound<'_, PyAny>) -> PyResult<Self> {
         let py = value.py();
         let typ = value.getattr("type")?;
         let val = value.call_method0("as_py")?;

datafusion/common/src/scalar/mod.rs

@@ -28,6 +28,7 @@ use std::fmt;
 use std::hash::Hash;
 use std::hash::Hasher;
 use std::iter::repeat;
+use std::mem::{size_of, size_of_val};
 use std::str::FromStr;
 use std::sync::Arc;
 
@@ -691,8 +692,8 @@ hash_float_value!((f64, u64), (f32, u32));
 // # Panics
 //
 // Panics if there is an error when creating hash values for rows
-impl std::hash::Hash for ScalarValue {
-    fn hash<H: std::hash::Hasher>(&self, state: &mut H) {
+impl Hash for ScalarValue {
+    fn hash<H: Hasher>(&self, state: &mut H) {
         use ScalarValue::*;
         match self {
             Decimal128(v, p, s) => {
@@ -768,7 +769,7 @@ impl std::hash::Hash for ScalarValue {
     }
 }
 
-fn hash_nested_array<H: std::hash::Hasher>(arr: ArrayRef, state: &mut H) {
+fn hash_nested_array<H: Hasher>(arr: ArrayRef, state: &mut H) {
     let arrays = vec![arr.to_owned()];
     let hashes_buffer = &mut vec![0; arr.len()];
     let random_state = ahash::RandomState::with_seeds(0, 0, 0, 0);
@@ -802,7 +803,7 @@ fn dict_from_scalar<K: ArrowDictionaryKeyType>(
     let values_array = value.to_array_of_size(1)?;
 
     // Create a key array with `size` elements, each of 0
-    let key_array: PrimitiveArray<K> = std::iter::repeat(if value.is_null() {
+    let key_array: PrimitiveArray<K> = repeat(if value.is_null() {
         None
     } else {
         Some(K::default_value())
@@ -2043,7 +2044,7 @@ impl ScalarValue {
         scale: i8,
         size: usize,
     ) -> Result<Decimal256Array> {
-        Ok(std::iter::repeat(value)
+        Ok(repeat(value)
             .take(size)
             .collect::<Decimal256Array>()
             .with_precision_and_scale(precision, scale)?)
@@ -2512,7 +2513,7 @@ impl ScalarValue {
     }
 
     fn list_to_array_of_size(arr: &dyn Array, size: usize) -> Result<ArrayRef> {
-        let arrays = std::iter::repeat(arr).take(size).collect::<Vec<_>>();
+        let arrays = repeat(arr).take(size).collect::<Vec<_>>();
         let ret = match !arrays.is_empty() {
             true => arrow::compute::concat(arrays.as_slice())?,
             false => arr.slice(0, 0),
@@ -3083,7 +3084,7 @@ impl ScalarValue {
     /// Estimate size if bytes including `Self`. For values with internal containers such as `String`
     /// includes the allocated size (`capacity`) rather than the current length (`len`)
     pub fn size(&self) -> usize {
-        std::mem::size_of_val(self)
+        size_of_val(self)
             + match self {
                 ScalarValue::Null
                 | ScalarValue::Boolean(_)
@@ -3137,12 +3138,12 @@ impl ScalarValue {
                 ScalarValue::Map(arr) => arr.get_array_memory_size(),
                 ScalarValue::Union(vals, fields, _mode) => {
                     vals.as_ref()
-                        .map(|(_id, sv)| sv.size() - std::mem::size_of_val(sv))
+                        .map(|(_id, sv)| sv.size() - size_of_val(sv))
                         .unwrap_or_default()
                         // `fields` is boxed, so it is NOT already included in `self`
-                        + std::mem::size_of_val(fields)
-                        + (std::mem::size_of::<Field>() * fields.len())
-                        + fields.iter().map(|(_idx, field)| field.size() - std::mem::size_of_val(field)).sum::<usize>()
+                        + size_of_val(fields)
+                        + (size_of::<Field>() * fields.len())
+                        + fields.iter().map(|(_idx, field)| field.size() - size_of_val(field)).sum::<usize>()
                 }
                 ScalarValue::Dictionary(dt, sv) => {
                     // `dt` and `sv` are boxed, so they are NOT already included in `self`
@@ -3155,35 +3156,35 @@ impl ScalarValue {
     ///
     /// Includes the size of the [`Vec`] container itself.
     pub fn size_of_vec(vec: &Vec<Self>) -> usize {
-        std::mem::size_of_val(vec)
-            + (std::mem::size_of::<ScalarValue>() * vec.capacity())
+        size_of_val(vec)
+            + (size_of::<ScalarValue>() * vec.capacity())
             + vec
                 .iter()
-                .map(|sv| sv.size() - std::mem::size_of_val(sv))
+                .map(|sv| sv.size() - size_of_val(sv))
                 .sum::<usize>()
     }
 
     /// Estimates [size](Self::size) of [`VecDeque`] in bytes.
     ///
     /// Includes the size of the [`VecDeque`] container itself.
     pub fn size_of_vec_deque(vec_deque: &VecDeque<Self>) -> usize {
-        std::mem::size_of_val(vec_deque)
-            + (std::mem::size_of::<ScalarValue>() * vec_deque.capacity())
+        size_of_val(vec_deque)
+            + (size_of::<ScalarValue>() * vec_deque.capacity())
             + vec_deque
                 .iter()
-                .map(|sv| sv.size() - std::mem::size_of_val(sv))
+                .map(|sv| sv.size() - size_of_val(sv))
                 .sum::<usize>()
     }
 
     /// Estimates [size](Self::size) of [`HashSet`] in bytes.
     ///
     /// Includes the size of the [`HashSet`] container itself.
     pub fn size_of_hashset<S>(set: &HashSet<Self, S>) -> usize {
-        std::mem::size_of_val(set)
-            + (std::mem::size_of::<ScalarValue>() * set.capacity())
+        size_of_val(set)
+            + (size_of::<ScalarValue>() * set.capacity())
             + set
                 .iter()
-                .map(|sv| sv.size() - std::mem::size_of_val(sv))
+                .map(|sv| sv.size() - size_of_val(sv))
                 .sum::<usize>()
     }
 }
@@ -4445,7 +4446,7 @@ mod tests {
         let right_array = right.to_array().expect("Failed to convert to array");
         let arrow_left_array = left_array.as_primitive::<T>();
         let arrow_right_array = right_array.as_primitive::<T>();
-        let arrow_result = kernels::numeric::add(arrow_left_array, arrow_right_array);
+        let arrow_result = add(arrow_left_array, arrow_right_array);
 
         assert_eq!(scalar_result.is_ok(), arrow_result.is_ok());
     }
@@ -5060,13 +5061,13 @@ mod tests {
         // thus the size of the enum appears to as well
 
         // The value may also change depending on rust version
-        assert_eq!(std::mem::size_of::<ScalarValue>(), 64);
+        assert_eq!(size_of::<ScalarValue>(), 64);
     }
 
     #[test]
     fn memory_size() {
         let sv = ScalarValue::Binary(Some(Vec::with_capacity(10)));
-        assert_eq!(sv.size(), std::mem::size_of::<ScalarValue>() + 10,);
+        assert_eq!(sv.size(), size_of::<ScalarValue>() + 10,);
         let sv_size = sv.size();
 
         let mut v = Vec::with_capacity(10);
@@ -5075,9 +5076,7 @@ mod tests {
         assert_eq!(v.capacity(), 10);
         assert_eq!(
             ScalarValue::size_of_vec(&v),
-            std::mem::size_of::<Vec<ScalarValue>>()
-                + (9 * std::mem::size_of::<ScalarValue>())
-                + sv_size,
+            size_of::<Vec<ScalarValue>>() + (9 * size_of::<ScalarValue>()) + sv_size,
         );
 
         let mut s = HashSet::with_capacity(0);
@@ -5087,8 +5086,8 @@ mod tests {
         let s_capacity = s.capacity();
         assert_eq!(
             ScalarValue::size_of_hashset(&s),
-            std::mem::size_of::<HashSet<ScalarValue>>()
-                + ((s_capacity - 1) * std::mem::size_of::<ScalarValue>())
+            size_of::<HashSet<ScalarValue>>()
+                + ((s_capacity - 1) * size_of::<ScalarValue>())
                 + sv_size,
         );
     }

datafusion/common/src/stats.rs

@@ -190,7 +190,7 @@ impl Precision<ScalarValue> {
     }
 }
 
-impl<T: fmt::Debug + Clone + PartialEq + Eq + PartialOrd> Debug for Precision<T> {
+impl<T: Debug + Clone + PartialEq + Eq + PartialOrd> Debug for Precision<T> {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
             Precision::Exact(inner) => write!(f, "Exact({:?})", inner),
@@ -200,7 +200,7 @@ impl<T: fmt::Debug + Clone + PartialEq + Eq + PartialOrd> Debug for Precision<T>
     }
 }
 
-impl<T: fmt::Debug + Clone + PartialEq + Eq + PartialOrd> Display for Precision<T> {
+impl<T: Debug + Clone + PartialEq + Eq + PartialOrd> Display for Precision<T> {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         match self {
             Precision::Exact(inner) => write!(f, "Exact({:?})", inner),
@@ -341,7 +341,7 @@ fn check_num_rows(value: Option<usize>, is_exact: bool) -> Precision<usize> {
 }
 
 impl Display for Statistics {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         // string of column statistics
         let column_stats = self
             .column_statistics

datafusion/common/src/utils/memory.rs

@@ -18,6 +18,7 @@
 //! This module provides a function to estimate the memory size of a HashTable prior to alloaction
 
 use crate::{DataFusionError, Result};
+use std::mem::size_of;
 
 /// Estimates the memory size required for a hash table prior to allocation.
 ///
@@ -87,7 +88,7 @@ pub fn estimate_memory_size<T>(num_elements: usize, fixed_size: usize) -> Result
             // + size of entry * number of buckets
             // + 1 byte for each bucket
             // + fixed size of collection (HashSet/HashTable)
-            std::mem::size_of::<T>()
+            size_of::<T>()
                 .checked_mul(estimated_buckets)?
                 .checked_add(estimated_buckets)?
                 .checked_add(fixed_size)
@@ -108,7 +109,7 @@ mod tests {
     #[test]
     fn test_estimate_memory() {
         // size (bytes): 48
-        let fixed_size = std::mem::size_of::<HashSet<u32>>();
+        let fixed_size = size_of::<HashSet<u32>>();
 
         // estimated buckets: 16 = (8 * 8 / 7).next_power_of_two()
         let num_elements = 8;
@@ -126,7 +127,7 @@ mod tests {
     #[test]
     fn test_estimate_memory_overflow() {
         let num_elements = usize::MAX;
-        let fixed_size = std::mem::size_of::<HashSet<u32>>();
+        let fixed_size = size_of::<HashSet<u32>>();
         let estimated = estimate_memory_size::<u32>(num_elements, fixed_size);
 
         assert!(estimated.is_err());