Skip to content

Apache DataFusion SQL Query Engine

chore: enforce clippy::allow_attributes for datasource crates (#19068)

Chakkk71fdad0801f2
diff --git a/datafusion/datasource-arrow/src/mod.rs b/datafusion/datasource-arrow/src/mod.rs
index 4816a45942..cbfd788709 100644
--- a/datafusion/datasource-arrow/src/mod.rs
+++ b/datafusion/datasource-arrow/src/mod.rs
@@ -19,6 +19,7 @@
// Make sure fast / cheap clones on Arc are explicit:
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
+#![deny(clippy::allow_attributes)]
//! [`ArrowFormat`]: Apache Arrow file format abstractions
diff --git a/datafusion/datasource-avro/src/mod.rs b/datafusion/datasource-avro/src/mod.rs
index 5ad209591e..22c40e203a 100644
--- a/datafusion/datasource-avro/src/mod.rs
+++ b/datafusion/datasource-avro/src/mod.rs
@@ -24,6 +24,7 @@
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
+#![deny(clippy::allow_attributes)]
//! An [Avro](https://avro.apache.org/) based [`FileSource`](datafusion_datasource::file::FileSource) implementation and related functionality.
diff --git a/datafusion/datasource-csv/src/mod.rs b/datafusion/datasource-csv/src/mod.rs
index fdfee05d86..d58ce11885 100644
--- a/datafusion/datasource-csv/src/mod.rs
+++ b/datafusion/datasource-csv/src/mod.rs
@@ -19,6 +19,7 @@
// Make sure fast / cheap clones on Arc are explicit:
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
+#![deny(clippy::allow_attributes)]
pub mod file_format;
pub mod source;
diff --git a/datafusion/datasource-json/src/mod.rs b/datafusion/datasource-json/src/mod.rs
index c39ee2cd93..3d27d4cc5e 100644
--- a/datafusion/datasource-json/src/mod.rs
+++ b/datafusion/datasource-json/src/mod.rs
@@ -19,6 +19,7 @@
// Make sure fast / cheap clones on Arc are explicit:
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
+#![deny(clippy::allow_attributes)]
pub mod file_format;
pub mod source;
diff --git a/datafusion/datasource-parquet/src/mod.rs b/datafusion/datasource-parquet/src/mod.rs
index eedda03c89..53ee597bd1 100644
--- a/datafusion/datasource-parquet/src/mod.rs
+++ b/datafusion/datasource-parquet/src/mod.rs
@@ -19,6 +19,7 @@
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
+#![deny(clippy::allow_attributes)]
pub mod access_plan;
pub mod file_format;
diff --git a/datafusion/datasource-parquet/src/opener.rs b/datafusion/datasource-parquet/src/opener.rs
index 83235dafda..fd2907b86b 100644
--- a/datafusion/datasource-parquet/src/opener.rs
+++ b/datafusion/datasource-parquet/src/opener.rs
@@ -584,7 +584,6 @@ where
}
#[derive(Default)]
-#[cfg_attr(not(feature = "parquet_encryption"), allow(dead_code))]
struct EncryptionContext {
#[cfg(feature = "parquet_encryption")]
file_decryption_properties: Option<Arc<FileDecryptionProperties>>,
@@ -626,7 +625,7 @@ impl EncryptionContext {
}
#[cfg(not(feature = "parquet_encryption"))]
-#[allow(dead_code)]
+#[expect(dead_code)]
impl EncryptionContext {
async fn get_file_decryption_properties(
&self,
@@ -646,7 +645,7 @@ impl ParquetOpener {
}
#[cfg(not(feature = "parquet_encryption"))]
- #[allow(dead_code)]
+ #[expect(dead_code)]
fn get_encryption_context(&self) -> EncryptionContext {
EncryptionContext::default()
}
diff --git a/datafusion/datasource-parquet/src/reader.rs b/datafusion/datasource-parquet/src/reader.rs
index 59a5da7b9d..0d27d18d88 100644
--- a/datafusion/datasource-parquet/src/reader.rs
+++ b/datafusion/datasource-parquet/src/reader.rs
@@ -289,7 +289,8 @@ impl AsyncFileReader for CachedParquetFileReader {
fn get_metadata<'a>(
&'a mut self,
- #[allow(unused_variables)] options: Option<&'a ArrowReaderOptions>,
+ #[cfg_attr(not(feature = "parquet_encryption"), expect(unused_variables))]
+ options: Option<&'a ArrowReaderOptions>,
) -> BoxFuture<'a, parquet::errors::Result<Arc<ParquetMetaData>>> {
let object_meta = self.partitioned_file.object_meta.clone();
let metadata_cache = Arc::clone(&self.metadata_cache);
diff --git a/datafusion/datasource-parquet/src/source.rs b/datafusion/datasource-parquet/src/source.rs
index d84ddf5993..940cf32901 100644
--- a/datafusion/datasource-parquet/src/source.rs
+++ b/datafusion/datasource-parquet/src/source.rs
@@ -803,7 +803,7 @@ mod tests {
use datafusion_physical_expr::expressions::lit;
#[test]
- #[allow(deprecated)]
+ #[expect(deprecated)]
fn test_parquet_source_predicate_same_as_filter() {
let predicate = lit(true);
diff --git a/datafusion/datasource/src/file_scan_config.rs b/datafusion/datasource/src/file_scan_config.rs
index 12654ee5b6..925caee162 100644
--- a/datafusion/datasource/src/file_scan_config.rs
+++ b/datafusion/datasource/src/file_scan_config.rs
@@ -19,8 +19,6 @@
//! file sources.
use crate::file_groups::FileGroup;
-#[allow(unused_imports)]
-use crate::schema_adapter::SchemaAdapterFactory;
use crate::{
display::FileGroupsDisplay, file::FileSource,
file_compression_type::FileCompressionType, file_stream::FileStream,
diff --git a/datafusion/datasource/src/file_stream.rs b/datafusion/datasource/src/file_stream.rs
index 7b24b71348..3ac70a5f75 100644
--- a/datafusion/datasource/src/file_stream.rs
+++ b/datafusion/datasource/src/file_stream.rs
@@ -354,7 +354,6 @@ impl StartableTime {
}
}
-#[allow(rustdoc::broken_intra_doc_links)]
/// Metrics for [`FileStream`]
///
/// Note that all of these metrics are in terms of wall clock time
diff --git a/datafusion/datasource/src/mod.rs b/datafusion/datasource/src/mod.rs
index ae7fd905d0..d02166b92d 100644
--- a/datafusion/datasource/src/mod.rs
+++ b/datafusion/datasource/src/mod.rs
@@ -24,6 +24,7 @@
// https://github.com/apache/datafusion/issues/11143
#![cfg_attr(not(test), deny(clippy::clone_on_ref_ptr))]
#![cfg_attr(test, allow(clippy::needless_pass_by_value))]
+#![deny(clippy::allow_attributes)]
//! A table that uses the `ObjectStore` listing capability
//! to get the list of files to process.
@@ -62,7 +63,7 @@ use object_store::{path::Path, ObjectMeta};
use object_store::{GetOptions, GetRange, ObjectStore};
pub use table_schema::TableSchema;
// Remove when add_row_stats is remove
-#[allow(deprecated)]
+#[expect(deprecated)]
pub use statistics::add_row_stats;
pub use statistics::compute_all_files_statistics;
use std::ops::Range;
diff --git a/datafusion/datasource/src/statistics.rs b/datafusion/datasource/src/statistics.rs
index 980677e488..17a6775526 100644
--- a/datafusion/datasource/src/statistics.rs
+++ b/datafusion/datasource/src/statistics.rs
@@ -50,13 +50,13 @@ pub(crate) struct MinMaxStatistics {
impl MinMaxStatistics {
/// Sort order used to sort the statistics
- #[allow(unused)]
+ #[expect(unused)]
pub fn sort_order(&self) -> &LexOrdering {
&self.sort_order
}
/// Min value at index
- #[allow(unused)]
+ #[expect(unused)]
pub fn min(&'_ self, idx: usize) -> Row<'_> {
self.min_by_sort_order.row(idx)
}
@@ -292,7 +292,7 @@ fn sort_columns_from_physical_sort_exprs(
since = "47.0.0",
note = "Please use `get_files_with_limit` and `compute_all_files_statistics` instead"
)]
-#[allow(unused)]
+#[expect(unused)]
pub async fn get_statistics_with_limit(
all_files: impl Stream<Item = Result<(PartitionedFile, Arc<Statistics>)>>,
file_schema: SchemaRef,
diff --git a/datafusion/doc/src/lib.rs b/datafusion/doc/src/lib.rs
index 88156eeb5b..591a5a62f3 100644
--- a/datafusion/doc/src/lib.rs
+++ b/datafusion/doc/src/lib.rs
@@ -30,15 +30,13 @@ pub use udaf::aggregate_doc_sections;
pub use udf::scalar_doc_sections;
pub use udwf::window_doc_sections;
-#[allow(rustdoc::broken_intra_doc_links)]
-/// Documentation for use by [`ScalarUDFImpl`](ScalarUDFImpl),
-/// [`AggregateUDFImpl`](AggregateUDFImpl) and [`WindowUDFImpl`](WindowUDFImpl) functions.
+/// Documentation for use by `ScalarUDFImpl`, `AggregateUDFImpl` and `WindowUDFImpl` functions.
///
/// See the [`DocumentationBuilder`] to create a new [`Documentation`] struct.
///
/// The DataFusion [SQL function documentation] is automatically generated from these structs.
-/// The name of the udf will be pulled from the [`ScalarUDFImpl::name`](ScalarUDFImpl::name),
-/// [`AggregateUDFImpl::name`](AggregateUDFImpl::name) or [`WindowUDFImpl::name`](WindowUDFImpl::name)
+/// The name of the udf will be pulled from the `ScalarUDFImpl::name`,
+/// `AggregateUDFImpl::name` or `WindowUDFImpl::name`
/// function as appropriate.
///
/// All strings in the documentation are required to be