This is an automated email from the ASF dual-hosted git repository.
Jefffrey pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/main by this push:
new 9225fc5983 Enable `allow_attributes` lint for `parquet` (#10714)
9225fc5983 is described below
commit 9225fc5983a4952871cfbadfa0fbb42139a3fc98
Author: WaterWhisperer <[email protected]>
AuthorDate: Tue Aug 18 09:57:55 2026 +0800
Enable `allow_attributes` lint for `parquet` (#10714)
# Which issue does this PR close?
<!--
We generally require a GitHub issue to be filed for all bug fixes and
enhancements and this helps us generate change logs for our releases.
You can link an issue to this PR using the GitHub syntax.
-->
- Part of #10458.
# Rationale for this change
<!--
Why are you proposing this change? If this is already explained clearly
in the issue then this section is not needed.
Explaining clearly why changes are proposed helps reviewers understand
your changes and offer better suggestions for fixes.
-->
Enable `clippy::allow_attributes` for the `parquet` crate.
# What changes are included in this PR?
<!--
There is no need to duplicate the description in the issue here but it
is sometimes worth providing a summary of the individual changes in this
PR.
-->
- Enable `clippy::allow_attributes` for `parquet`.
- Replace active `allow` attributes with `expect`.
# Are these changes tested?
<!--
We typically require tests for all PRs in order to:
1. Prevent the code from being accidentally broken by subsequent changes
2. Serve as another way to document the expected behavior of the code
If tests are not included in your PR, please explain why (for example,
are they covered by existing tests)?
If this PR claims a performance improvement, please include evidence
such as benchmark results.
-->
Yes.
- `cargo clippy -p parquet --all-targets --all-features -- -D warnings
-D clippy::allow_attributes`
- `cargo clippy --workspace --all-targets --all-features -- -D warnings`
# Are there any user-facing changes?
<!--
If there are user-facing changes then we may require documentation to be
updated before approving the PR.
If there are any breaking changes to public APIs, please call them out.
-->
No.
Co-authored-by: Jeffrey Vo <[email protected]>
---
parquet/benches/arrow_reader_clickbench.rs | 2 +-
parquet/benches/arrow_reader_peak_memory.rs | 2 +-
parquet/src/arrow/array_reader/map_array.rs | 1 -
parquet/src/arrow/array_reader/mod.rs | 5 ++---
parquet/src/arrow/array_reader/primitive_array.rs | 2 +-
parquet/src/arrow/arrow_writer/byte_array.rs | 1 -
parquet/src/arrow/arrow_writer/mod.rs | 6 +++---
parquet/src/arrow/async_reader/mod.rs | 1 -
parquet/src/arrow/async_reader/store.rs | 8 ++++----
parquet/src/arrow/async_writer/mod.rs | 1 -
parquet/src/arrow/async_writer/store.rs | 8 ++++----
parquet/src/arrow/buffer/dictionary_buffer.rs | 2 +-
parquet/src/arrow/record_reader/definition_levels.rs | 2 +-
parquet/src/arrow/record_reader/mod.rs | 2 +-
parquet/src/arrow/schema/complex.rs | 4 ++--
parquet/src/arrow/schema/mod.rs | 2 +-
parquet/src/arrow/schema/primitive.rs | 2 +-
parquet/src/basic.rs | 12 ++++++------
parquet/src/bin/parquet-rewrite.rs | 2 +-
parquet/src/column/chunker/cdc.rs | 1 -
parquet/src/column/reader.rs | 6 +++---
parquet/src/column/reader/decoder.rs | 2 +-
parquet/src/column/writer/mod.rs | 6 +++---
parquet/src/compression.rs | 19 ++++++++++++++++++-
parquet/src/data_type.rs | 3 ---
parquet/src/encodings/decoding.rs | 10 ++--------
parquet/src/encodings/encoding/mod.rs | 2 +-
parquet/src/encodings/levels.rs | 2 +-
parquet/src/encodings/rle.rs | 8 ++++----
parquet/src/file/metadata/mod.rs | 2 +-
parquet/src/file/metadata/reader.rs | 1 -
parquet/src/file/metadata/thrift/mod.rs | 4 ++--
parquet/src/file/page_index/column_index.rs | 6 +++---
parquet/src/file/properties.rs | 4 ++--
parquet/src/file/reader.rs | 2 +-
parquet/src/file/serialized_reader.rs | 2 +-
parquet/src/lib.rs | 1 +
parquet/src/parquet_macros.rs | 17 +++++++++++++++++
parquet/src/record/api.rs | 9 ++++-----
parquet/src/record/triplet.rs | 2 +-
parquet/src/schema/printer.rs | 16 ++++++++--------
parquet/src/schema/types.rs | 2 +-
parquet/src/util/bit_util.rs | 2 +-
parquet/src/util/interner.rs | 2 --
parquet/src/util/test_common/rand_gen.rs | 2 +-
parquet/tests/arrow_reader/io/mod.rs | 4 ++--
parquet/tests/arrow_writer/mod.rs | 2 +-
parquet/tests/variant_integration.rs | 2 +-
48 files changed, 111 insertions(+), 95 deletions(-)
diff --git a/parquet/benches/arrow_reader_clickbench.rs
b/parquet/benches/arrow_reader_clickbench.rs
index f411b9684f..90be040601 100644
--- a/parquet/benches/arrow_reader_clickbench.rs
+++ b/parquet/benches/arrow_reader_clickbench.rs
@@ -654,7 +654,7 @@ impl ClickBenchPredicate {
}
/// Create Predicate: col LIKE '%Google%'
- #[allow(non_snake_case)]
+ #[expect(non_snake_case)]
fn like_Google(column_index: usize) -> Self {
Self::new(column_index, move || {
let google_url = StringViewArray::new_scalar("%Google%");
diff --git a/parquet/benches/arrow_reader_peak_memory.rs
b/parquet/benches/arrow_reader_peak_memory.rs
index 4d5fda1fe8..378bb7ca02 100644
--- a/parquet/benches/arrow_reader_peak_memory.rs
+++ b/parquet/benches/arrow_reader_peak_memory.rs
@@ -84,7 +84,7 @@ fn add_allocated_bytes(size: usize) {
});
}
-#[allow(unsafe_code)]
+#[expect(unsafe_code)]
unsafe impl std::alloc::GlobalAlloc for TrackingAllocator {
unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
let ptr = unsafe { self.inner.alloc(layout) };
diff --git a/parquet/src/arrow/array_reader/map_array.rs
b/parquet/src/arrow/array_reader/map_array.rs
index 117f3b73ba..8bc847b386 100644
--- a/parquet/src/arrow/array_reader/map_array.rs
+++ b/parquet/src/arrow/array_reader/map_array.rs
@@ -29,7 +29,6 @@ pub struct MapArrayReader {
}
impl MapArrayReader {
- #[allow(rustdoc::private_intra_doc_links)]
/// Creates a new [`MapArrayReader`] with a `def_level`, `rep_level` and
`nullable`
/// as defined on [`ParquetField`][crate::arrow::schema::ParquetField]
pub fn new(
diff --git a/parquet/src/arrow/array_reader/mod.rs
b/parquet/src/arrow/array_reader/mod.rs
index 347058329f..32fb90d2e1 100644
--- a/parquet/src/arrow/array_reader/mod.rs
+++ b/parquet/src/arrow/array_reader/mod.rs
@@ -56,9 +56,9 @@ use crate::file::metadata::RowGroupMetaData;
pub use builder::{ArrayReaderBuilder, CacheOptions, CacheOptionsBuilder};
pub use byte_array::make_byte_array_reader;
pub use byte_array_dictionary::make_byte_array_dictionary_reader;
-#[allow(unused_imports)] // Only used for benchmarks
+#[cfg_attr(not(feature = "experimental"), expect(unused_imports))]
pub use byte_view_array::make_byte_view_array_reader;
-#[allow(unused_imports)] // Only used for benchmarks
+#[cfg_attr(not(feature = "experimental"), expect(unused_imports))]
pub use fixed_len_byte_array::make_fixed_len_byte_array_reader;
pub use fixed_size_list_array::FixedSizeListArrayReader;
pub use list_array::ListArrayReader;
@@ -88,7 +88,6 @@ pub use struct_array::StructArrayReader;
pub trait ArrayReader: Send {
// TODO: this function is never used, and the trait is not public. Perhaps
this should be
// removed.
- #[allow(dead_code)]
fn as_any(&self) -> &dyn Any;
/// Returns the arrow type of this array reader.
diff --git a/parquet/src/arrow/array_reader/primitive_array.rs
b/parquet/src/arrow/array_reader/primitive_array.rs
index eb3745c5bb..c468ad6cff 100644
--- a/parquet/src/arrow/array_reader/primitive_array.rs
+++ b/parquet/src/arrow/array_reader/primitive_array.rs
@@ -466,7 +466,7 @@ mod tests {
use rand::distr::uniform::SampleUniform;
use std::collections::VecDeque;
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
fn make_column_chunks<T: DataType>(
column_desc: ColumnDescPtr,
encoding: Encoding,
diff --git a/parquet/src/arrow/arrow_writer/byte_array.rs
b/parquet/src/arrow/arrow_writer/byte_array.rs
index 93a16f7693..14c23f9a8d 100644
--- a/parquet/src/arrow/arrow_writer/byte_array.rs
+++ b/parquet/src/arrow/arrow_writer/byte_array.rs
@@ -323,7 +323,6 @@ impl Storage for ByteArrayStorage {
key as u64
}
- #[allow(dead_code)] // not used in parquet_derive, so is dead there
fn estimated_memory_size(&self) -> usize {
self.page.capacity() * std::mem::size_of::<u8>()
+ self.values.capacity() *
std::mem::size_of::<std::ops::Range<usize>>()
diff --git a/parquet/src/arrow/arrow_writer/mod.rs
b/parquet/src/arrow/arrow_writer/mod.rs
index 71d122b935..8b8b7a9727 100644
--- a/parquet/src/arrow/arrow_writer/mod.rs
+++ b/parquet/src/arrow/arrow_writer/mod.rs
@@ -4057,7 +4057,7 @@ mod tests {
#[test]
fn arrow_writer_string_dictionary() {
// define schema
- #[allow(deprecated)]
+ #[expect(deprecated)]
let schema = Arc::new(Schema::new(vec![Field::new_dict(
"dictionary",
DataType::Dictionary(Box::new(DataType::Int32),
Box::new(DataType::Utf8)),
@@ -4310,7 +4310,7 @@ mod tests {
#[test]
fn arrow_writer_primitive_dictionary() {
// define schema
- #[allow(deprecated)]
+ #[expect(deprecated)]
let schema = Arc::new(Schema::new(vec![Field::new_dict(
"dictionary",
DataType::Dictionary(Box::new(DataType::UInt8),
Box::new(DataType::UInt32)),
@@ -4421,7 +4421,7 @@ mod tests {
#[test]
fn arrow_writer_string_dictionary_unsigned_index() {
// define schema
- #[allow(deprecated)]
+ #[expect(deprecated)]
let schema = Arc::new(Schema::new(vec![Field::new_dict(
"dictionary",
DataType::Dictionary(Box::new(DataType::UInt8),
Box::new(DataType::Utf8)),
diff --git a/parquet/src/arrow/async_reader/mod.rs
b/parquet/src/arrow/async_reader/mod.rs
index d386bec48d..0bff84b3d8 100644
--- a/parquet/src/arrow/async_reader/mod.rs
+++ b/parquet/src/arrow/async_reader/mod.rs
@@ -58,7 +58,6 @@ mod store;
use crate::DecodeResult;
use crate::arrow::push_decoder::{ParquetPushDecoder,
ParquetPushDecoderBuilder, PushDecoderInput};
-#[allow(deprecated)]
#[cfg(feature = "object_store")]
pub use store::*;
diff --git a/parquet/src/arrow/async_reader/store.rs
b/parquet/src/arrow/async_reader/store.rs
index 8d572fe99b..d4f5beb817 100644
--- a/parquet/src/arrow/async_reader/store.rs
+++ b/parquet/src/arrow/async_reader/store.rs
@@ -66,7 +66,7 @@ pub struct ParquetObjectReader {
runtime: Option<Handle>,
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl ParquetObjectReader {
/// Creates a new [`ParquetObjectReader`] for the provided [`ObjectStore`]
and [`Path`].
pub fn new(store: Arc<dyn ObjectStore>, path: Path) -> Self {
@@ -177,7 +177,7 @@ impl ParquetObjectReader {
}
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl MetadataSuffixFetch for &mut ParquetObjectReader {
fn fetch_suffix(&mut self, suffix: usize) -> BoxFuture<'_, Result<Bytes>> {
let options = GetOptions {
@@ -194,7 +194,7 @@ impl MetadataSuffixFetch for &mut ParquetObjectReader {
}
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl AsyncFileReader for ParquetObjectReader {
fn get_bytes(&mut self, range: Range<u64>) -> BoxFuture<'_, Result<Bytes>>
{
self.spawn(|store, path| store.get_range(path, range).boxed())
@@ -257,7 +257,7 @@ impl AsyncFileReader for ParquetObjectReader {
}
#[cfg(test)]
-#[allow(deprecated)]
+#[expect(deprecated)]
mod tests {
use crate::arrow::async_reader::ArrowReaderOptions;
use crate::file::metadata::PageIndexPolicy;
diff --git a/parquet/src/arrow/async_writer/mod.rs
b/parquet/src/arrow/async_writer/mod.rs
index d9124417d5..1755bcfca4 100644
--- a/parquet/src/arrow/async_writer/mod.rs
+++ b/parquet/src/arrow/async_writer/mod.rs
@@ -60,7 +60,6 @@
#[cfg(feature = "object_store")]
mod store;
-#[allow(deprecated)]
#[cfg(feature = "object_store")]
pub use store::*;
diff --git a/parquet/src/arrow/async_writer/store.rs
b/parquet/src/arrow/async_writer/store.rs
index ad674268a3..b5481ef877 100644
--- a/parquet/src/arrow/async_writer/store.rs
+++ b/parquet/src/arrow/async_writer/store.rs
@@ -84,7 +84,7 @@ pub struct ParquetObjectWriter {
w: BufWriter,
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl ParquetObjectWriter {
/// Create a new [`ParquetObjectWriter`] that writes to the specified path
in the given store.
///
@@ -104,7 +104,7 @@ impl ParquetObjectWriter {
}
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl AsyncFileWriter for ParquetObjectWriter {
fn write(&mut self, bs: Bytes) -> BoxFuture<'_, Result<()>> {
Box::pin(async {
@@ -124,14 +124,14 @@ impl AsyncFileWriter for ParquetObjectWriter {
})
}
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl From<BufWriter> for ParquetObjectWriter {
fn from(w: BufWriter) -> Self {
Self::from_buf_writer(w)
}
}
#[cfg(test)]
-#[allow(deprecated)]
+#[expect(deprecated)]
mod tests {
use arrow_array::{ArrayRef, Int64Array, RecordBatch};
use object_store::memory::InMemory;
diff --git a/parquet/src/arrow/buffer/dictionary_buffer.rs
b/parquet/src/arrow/buffer/dictionary_buffer.rs
index 2cfb9b26b8..67396a1ceb 100644
--- a/parquet/src/arrow/buffer/dictionary_buffer.rs
+++ b/parquet/src/arrow/buffer/dictionary_buffer.rs
@@ -39,7 +39,7 @@ pub enum DictionaryBuffer<K: ArrowNativeType, V:
OffsetSizeTrait> {
}
impl<K: ArrowNativeType + Ord, V: OffsetSizeTrait> DictionaryBuffer<K, V> {
- #[allow(unused)]
+ #[cfg_attr(not(test), expect(unused))]
pub fn len(&self) -> usize {
match self {
Self::Dict { keys, .. } => keys.len(),
diff --git a/parquet/src/arrow/record_reader/definition_levels.rs
b/parquet/src/arrow/record_reader/definition_levels.rs
index 37a0dd9918..d151f0d1b5 100644
--- a/parquet/src/arrow/record_reader/definition_levels.rs
+++ b/parquet/src/arrow/record_reader/definition_levels.rs
@@ -385,7 +385,7 @@ impl PackedDecoder {
self.packed_offset = 0;
self.packed_count = match encoding {
Encoding::RLE => 0,
- #[allow(deprecated)]
+ #[expect(deprecated)]
Encoding::BIT_PACKED => data.len() * 8,
_ => unreachable!("invalid level encoding: {}", encoding),
};
diff --git a/parquet/src/arrow/record_reader/mod.rs
b/parquet/src/arrow/record_reader/mod.rs
index d4b2f5cefd..7e568a9d53 100644
--- a/parquet/src/arrow/record_reader/mod.rs
+++ b/parquet/src/arrow/record_reader/mod.rs
@@ -174,7 +174,7 @@ where
}
/// Returns number of records stored in buffer.
- #[allow(unused)]
+ #[cfg_attr(not(test), expect(unused))]
pub fn num_records(&self) -> usize {
self.num_records
}
diff --git a/parquet/src/arrow/schema/complex.rs
b/parquet/src/arrow/schema/complex.rs
index 9277c8e193..e5a80b3b9a 100644
--- a/parquet/src/arrow/schema/complex.rs
+++ b/parquet/src/arrow/schema/complex.rs
@@ -749,11 +749,11 @@ fn convert_field(
match arrow_hint {
Some(hint) => {
// If the inferred type is a dictionary, preserve dictionary
metadata
- #[allow(deprecated)]
+ #[expect(deprecated)]
let field = match (&data_type, hint.dict_id(),
hint.dict_is_ordered()) {
(DataType::Dictionary(_, _), Some(id), Some(ordered)) =>
{
- #[allow(deprecated)]
+ #[expect(deprecated)]
Field::new_dict(name, data_type, nullable, id, ordered)
}
_ => Field::new(name, data_type, nullable),
diff --git a/parquet/src/arrow/schema/mod.rs b/parquet/src/arrow/schema/mod.rs
index 05a6952529..f9acedcbf9 100644
--- a/parquet/src/arrow/schema/mod.rs
+++ b/parquet/src/arrow/schema/mod.rs
@@ -2103,7 +2103,7 @@ mod tests {
// Field::new("c28",
DataType::Duration(TimeUnit::Millisecond), false),
// Field::new("c29",
DataType::Duration(TimeUnit::Microsecond), false),
// Field::new("c30", DataType::Duration(TimeUnit::Nanosecond),
false),
- #[allow(deprecated)]
+ #[expect(deprecated)]
Field::new_dict(
"c31",
DataType::Dictionary(Box::new(DataType::Int32),
Box::new(DataType::Utf8)),
diff --git a/parquet/src/arrow/schema/primitive.rs
b/parquet/src/arrow/schema/primitive.rs
index ea35f68031..6fcf86b662 100644
--- a/parquet/src/arrow/schema/primitive.rs
+++ b/parquet/src/arrow/schema/primitive.rs
@@ -170,7 +170,7 @@ fn decimal_256_type(scale: i32, precision: i32) ->
Result<DataType> {
Ok(DataType::Decimal256(precision, scale))
}
-#[allow(clippy::manual_range_contains)]
+#[expect(clippy::manual_range_contains)]
fn check_decimal_length(type_length: i32) -> Result<()> {
if type_length < 1 || type_length > 32 {
return Err(ParquetError::General(format!(
diff --git a/parquet/src/basic.rs b/parquet/src/basic.rs
index c92b5286ff..aec324e25b 100644
--- a/parquet/src/basic.rs
+++ b/parquet/src/basic.rs
@@ -460,7 +460,7 @@ impl FromStr for Encoding {
"PLAIN" | "plain" => Ok(Encoding::PLAIN),
"PLAIN_DICTIONARY" | "plain_dictionary" =>
Ok(Encoding::PLAIN_DICTIONARY),
"RLE" | "rle" => Ok(Encoding::RLE),
- #[allow(deprecated)]
+ #[expect(deprecated)]
"BIT_PACKED" | "bit_packed" => Ok(Encoding::BIT_PACKED),
"DELTA_BINARY_PACKED" | "delta_binary_packed" =>
Ok(Encoding::DELTA_BINARY_PACKED),
"DELTA_LENGTH_BYTE_ARRAY" | "delta_length_byte_array" => {
@@ -596,7 +596,7 @@ impl<'a, R: ThriftCompactInputProtocol<'a>> ReadThrift<'a,
R> for EncodingMask {
}
}
-#[allow(deprecated)]
+#[expect(deprecated)]
fn i32_to_encoding(val: i32) -> Encoding {
match val {
0 => Encoding::PLAIN,
@@ -658,7 +658,7 @@ enum CompressionCodec {
/// worse compression ratios. However, it is not as widely supported by the
ecosystem, with the
/// Hadoop ecosystem historically favoring the non-standard and now deprecated
[`Compression::LZ4`].
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-#[allow(non_camel_case_types)]
+#[expect(non_camel_case_types)]
pub enum Compression {
/// No compression.
UNCOMPRESSED,
@@ -976,7 +976,7 @@ union BloomFilterCompression {
///
/// See [`ColumnOrder`] for more information.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-#[allow(non_camel_case_types)]
+#[expect(non_camel_case_types)]
pub enum SortOrder {
/// Signed (either value or legacy byte-wise) comparison.
SIGNED,
@@ -1021,7 +1021,7 @@ impl SortOrder {
///
/// [`ColumnOrder`]:
https://github.com/apache/parquet-format/blob/2076361bb64e2de9ca6a8d06eda025a6fa4e9df6/src/main/thrift/parquet.thrift#L1103
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-#[allow(non_camel_case_types)]
+#[expect(non_camel_case_types)]
pub enum ColumnOrder {
/// Column uses the order defined by its logical or physical type
/// (if there is no logical type), parquet-format 2.4.0+.
@@ -1451,7 +1451,7 @@ impl str::FromStr for LogicalType {
}
#[cfg(test)]
-#[allow(deprecated)] // allow BIT_PACKED encoding for the whole test module
+#[expect(deprecated)] // allow BIT_PACKED encoding for the whole test module
mod tests {
use super::*;
use crate::parquet_thrift::{ThriftSliceInputProtocol,
tests::test_roundtrip};
diff --git a/parquet/src/bin/parquet-rewrite.rs
b/parquet/src/bin/parquet-rewrite.rs
index 2428c49141..c10eb26deb 100644
--- a/parquet/src/bin/parquet-rewrite.rs
+++ b/parquet/src/bin/parquet-rewrite.rs
@@ -132,7 +132,7 @@ enum EncodingArgs {
ByteStreamSplit,
}
-#[allow(deprecated)]
+#[expect(deprecated)]
impl From<EncodingArgs> for Encoding {
fn from(value: EncodingArgs) -> Self {
match value {
diff --git a/parquet/src/column/chunker/cdc.rs
b/parquet/src/column/chunker/cdc.rs
index 28a8bb3c06..a0d6899adc 100644
--- a/parquet/src/column/chunker/cdc.rs
+++ b/parquet/src/column/chunker/cdc.rs
@@ -324,7 +324,6 @@ impl ContentDefinedChunker {
// def_levels: [1, 0, 1, 0, 1]
// level: 0 1 2 3 4
// value_offset: 0 1 2 (only increments on def==1)
- #[allow(clippy::needless_range_loop)]
for offset in 0..num_levels {
let def_level = def_levels
.value_at(offset)
diff --git a/parquet/src/column/reader.rs b/parquet/src/column/reader.rs
index 498f73a4a9..61214910e8 100644
--- a/parquet/src/column/reader.rs
+++ b/parquet/src/column/reader.rs
@@ -606,7 +606,7 @@ fn parse_v1_level(
}
Err(general_err!("not enough data to read levels"))
}
- #[allow(deprecated)]
+ #[expect(deprecated)]
Encoding::BIT_PACKED => {
let bit_width = num_required_bits(max_level as u64);
let num_bytes = ceil(num_buffered_values as usize * bit_width as
usize, 8);
@@ -1290,7 +1290,7 @@ mod tests {
// Helper function for the general case of `read_batch()` where
`values`,
// `def_levels` and `rep_levels` are always provided with enough space.
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
fn test_read_batch_general(
&mut self,
desc: ColumnDescPtr,
@@ -1309,7 +1309,7 @@ mod tests {
// Helper function to test `read_batch()` method with custom buffers
for values,
// definition and repetition levels.
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
fn test_read_batch(
&mut self,
desc: ColumnDescPtr,
diff --git a/parquet/src/column/reader/decoder.rs
b/parquet/src/column/reader/decoder.rs
index 4e579f8f0d..ee619ddef8 100644
--- a/parquet/src/column/reader/decoder.rs
+++ b/parquet/src/column/reader/decoder.rs
@@ -273,7 +273,7 @@ impl LevelDecoder {
decoder.set_data(data)?;
Ok(Self::Rle(decoder))
}
- #[allow(deprecated)]
+ #[expect(deprecated)]
Encoding::BIT_PACKED => Ok(Self::Packed(BitReader::new(data),
bit_width)),
_ => unreachable!("invalid level encoding: {}", encoding),
}
diff --git a/parquet/src/column/writer/mod.rs b/parquet/src/column/writer/mod.rs
index 850bcc425b..70cd8acb34 100644
--- a/parquet/src/column/writer/mod.rs
+++ b/parquet/src/column/writer/mod.rs
@@ -539,7 +539,7 @@ impl<'a, E: ColumnValueEncoder> GenericColumnWriter<'a, E> {
}
}
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(crate) fn write_batch_internal(
&mut self,
values: &E::Values,
@@ -830,7 +830,7 @@ impl<'a, E: ColumnValueEncoder> GenericColumnWriter<'a, E> {
/// `#[inline(never)]` keeps this slow path — only reached for
/// variable-width columns whose values need page splitting — out of
/// the hot `write_batch_internal` loop.
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
#[inline(never)]
fn write_granular_chunk(
&mut self,
@@ -1725,7 +1725,7 @@ fn update_max<T: ParquetValueType>(descr:
&ColumnDescriptor, val: &T, max: &mut
}
#[inline]
-#[allow(clippy::eq_op)]
+#[expect(clippy::eq_op)]
fn is_nan<T: ParquetValueType>(basic_type_info: &BasicTypeInfo, val: &T) ->
bool {
match T::PHYSICAL_TYPE {
Type::FLOAT | Type::DOUBLE => val != val,
diff --git a/parquet/src/compression.rs b/parquet/src/compression.rs
index 8d25891e90..e5fe743ec3 100644
--- a/parquet/src/compression.rs
+++ b/parquet/src/compression.rs
@@ -147,7 +147,24 @@ pub(crate) trait CompressionLevel<T: std::fmt::Display +
std::cmp::PartialOrd> {
/// bytes for the compression type.
/// This returns `None` if the codec type is `UNCOMPRESSED`.
pub fn create_codec(codec: CodecType, _options: &CodecOptions) ->
Result<Option<Box<dyn Codec>>> {
- #[allow(unreachable_code, unused_variables)]
+ #[cfg_attr(
+ any(
+ test,
+ feature = "brotli",
+ feature = "flate2",
+ feature = "lz4",
+ feature = "snap",
+ feature = "zstd"
+ ),
+ expect(unreachable_code)
+ )]
+ #[cfg_attr(
+ all(
+ not(test),
+ not(all(feature = "brotli", feature = "flate2", feature = "zstd"))
+ ),
+ expect(unused_variables)
+ )]
match codec {
CodecType::BROTLI(level) => {
#[cfg(any(feature = "brotli", test))]
diff --git a/parquet/src/data_type.rs b/parquet/src/data_type.rs
index 063caa0dfd..a2c7cc581a 100644
--- a/parquet/src/data_type.rs
+++ b/parquet/src/data_type.rs
@@ -564,7 +564,6 @@ impl AsBytes for [u8] {
macro_rules! gen_as_bytes {
($source_ty:ident) => {
impl AsBytes for $source_ty {
- #[allow(clippy::size_of_in_element_count)]
fn as_bytes(&self) -> &[u8] {
// SAFETY: macro is only used with primitive types that have
no padding, so the
// resulting slice always refers to initialized memory.
@@ -579,7 +578,6 @@ macro_rules! gen_as_bytes {
impl SliceAsBytes for $source_ty {
#[inline]
- #[allow(clippy::size_of_in_element_count)]
fn slice_as_bytes(self_: &[Self]) -> &[u8] {
// SAFETY: macro is only used with primitive types that have
no padding, so the
// resulting slice always refers to initialized memory.
@@ -592,7 +590,6 @@ macro_rules! gen_as_bytes {
}
#[inline]
- #[allow(clippy::size_of_in_element_count)]
unsafe fn slice_as_bytes_mut(self_: &mut [Self]) -> &mut [u8] {
// SAFETY: macro is only used with primitive types that have
no padding, so the
// resulting slice always refers to initialized memory.
Moreover, self has no
diff --git a/parquet/src/encodings/decoding.rs
b/parquet/src/encodings/decoding.rs
index 4d902a96e6..85f3bd495b 100644
--- a/parquet/src/encodings/decoding.rs
+++ b/parquet/src/encodings/decoding.rs
@@ -1327,7 +1327,7 @@ mod tests {
);
// unsupported
- #[allow(deprecated)]
+ #[expect(deprecated)]
create_and_check_decoder::<Int32Type>(
Encoding::BIT_PACKED,
Some(nyi_err!("Encoding BIT_PACKED is not supported")),
@@ -2322,14 +2322,12 @@ mod tests {
/// A util trait to convert slices of different types to byte arrays
trait ToByteArray<T: DataType> {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[T::T]) -> Vec<u8>;
}
macro_rules! to_byte_array_impl {
($ty: ty) => {
impl ToByteArray<$ty> for $ty {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[<$ty as DataType>::T]) -> Vec<u8> {
<$ty as DataType>::T::slice_as_bytes(data).to_vec()
}
@@ -2343,7 +2341,6 @@ mod tests {
to_byte_array_impl!(DoubleType);
impl ToByteArray<BoolType> for BoolType {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[bool]) -> Vec<u8> {
let mut v = vec![];
for (i, item) in data.iter().enumerate() {
@@ -2359,7 +2356,6 @@ mod tests {
}
impl ToByteArray<Int96Type> for Int96Type {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[Int96]) -> Vec<u8> {
let mut v = vec![];
for d in data {
@@ -2370,7 +2366,6 @@ mod tests {
}
impl ToByteArray<ByteArrayType> for ByteArrayType {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[ByteArray]) -> Vec<u8> {
let mut v = vec![];
for d in data {
@@ -2384,7 +2379,6 @@ mod tests {
}
impl ToByteArray<FixedLenByteArrayType> for FixedLenByteArrayType {
- #[allow(clippy::wrong_self_convention)]
fn to_byte_array(data: &[FixedLenByteArray]) -> Vec<u8> {
let mut v = vec![];
for d in data {
@@ -2397,7 +2391,7 @@ mod tests {
#[test]
// Allow initializing a vector and pushing to it for clarity in this test
- #[allow(clippy::vec_init_then_push)]
+ #[expect(clippy::vec_init_then_push)]
fn test_delta_bit_packed_invalid_bit_width() {
// Manually craft a buffer with an invalid bit width
let mut buffer = vec![];
diff --git a/parquet/src/encodings/encoding/mod.rs
b/parquet/src/encodings/encoding/mod.rs
index b5fd5c78f7..6932450bfa 100644
--- a/parquet/src/encodings/encoding/mod.rs
+++ b/parquet/src/encodings/encoding/mod.rs
@@ -796,7 +796,7 @@ mod tests {
);
// unsupported
- #[allow(deprecated)]
+ #[expect(deprecated)]
create_and_check_encoder::<Int32Type>(
0,
Encoding::BIT_PACKED,
diff --git a/parquet/src/encodings/levels.rs b/parquet/src/encodings/levels.rs
index 841afd8b31..425eaec290 100644
--- a/parquet/src/encodings/levels.rs
+++ b/parquet/src/encodings/levels.rs
@@ -126,7 +126,7 @@ impl LevelEncoder {
/// Finalizes level encoder, flush all intermediate buffers and return
resulting
/// encoded buffer. Returned buffer is already truncated to encoded bytes
only.
#[inline]
- #[allow(unused)]
+ #[cfg_attr(all(not(feature = "experimental"), not(test)), expect(unused))]
pub fn consume(self) -> Vec<u8> {
match self {
LevelEncoder::Rle(encoder) => {
diff --git a/parquet/src/encodings/rle.rs b/parquet/src/encodings/rle.rs
index e9f013a69c..a1994a4fe0 100644
--- a/parquet/src/encodings/rle.rs
+++ b/parquet/src/encodings/rle.rs
@@ -82,7 +82,7 @@ pub struct RleEncoder {
}
impl RleEncoder {
- #[allow(unused)]
+ #[cfg_attr(all(not(feature = "experimental"), not(test)), expect(unused))]
pub fn new(bit_width: u8, buffer_len: usize) -> Self {
let buffer = Vec::with_capacity(buffer_len);
RleEncoder::new_from_buf(bit_width, buffer)
@@ -185,7 +185,7 @@ impl RleEncoder {
}
#[inline]
- #[allow(unused)]
+ #[cfg_attr(not(feature = "experimental"), expect(unused))]
pub fn buffer(&self) -> &[u8] {
self.bit_writer.buffer()
}
@@ -195,7 +195,7 @@ impl RleEncoder {
self.bit_writer.bytes_written()
}
- #[allow(unused)]
+ #[cfg_attr(not(feature = "experimental"), expect(unused))]
pub fn is_empty(&self) -> bool {
self.bit_writer.bytes_written() == 0
}
@@ -389,7 +389,7 @@ impl RleDecoder {
// These functions inline badly, they tend to inline and then create very
large loop unrolls
// that damage L1d-cache occupancy. This results in a ~18% performance drop
#[inline(never)]
- #[allow(unused)]
+ #[cfg_attr(all(not(feature = "experimental"), not(test)), expect(unused))]
pub fn get<T: FromBitpacked>(&mut self) -> Result<Option<T>> {
assert!(size_of::<T>() <= size_of::<u64>());
diff --git a/parquet/src/file/metadata/mod.rs b/parquet/src/file/metadata/mod.rs
index 54eee48063..90773439e8 100644
--- a/parquet/src/file/metadata/mod.rs
+++ b/parquet/src/file/metadata/mod.rs
@@ -1757,7 +1757,7 @@ mod tests {
};
#[test]
- #[allow(deprecated)]
+ #[expect(deprecated)]
fn test_level_histogram_update_from_levels_compat() {
let mut histogram = LevelHistogram::try_new(2).unwrap();
histogram.update_from_levels(&[0, 2, 1, 2, 2]);
diff --git a/parquet/src/file/metadata/reader.rs
b/parquet/src/file/metadata/reader.rs
index 43bd339930..a69d3131ed 100644
--- a/parquet/src/file/metadata/reader.rs
+++ b/parquet/src/file/metadata/reader.rs
@@ -804,7 +804,6 @@ impl ParquetMetaDataReader {
/// The bounds needed to read page indexes
// this is an internal enum, so it is ok to allow differences in enum size
-#[allow(clippy::large_enum_variant)]
enum NeedsIndexData {
/// no additional data is needed (e.g. the indexes weren't requested)
No(ParquetMetaData),
diff --git a/parquet/src/file/metadata/thrift/mod.rs
b/parquet/src/file/metadata/thrift/mod.rs
index 3915e96a80..748d3ad3a7 100644
--- a/parquet/src/file/metadata/thrift/mod.rs
+++ b/parquet/src/file/metadata/thrift/mod.rs
@@ -1422,7 +1422,7 @@ impl<'a> WriteThrift for FileMeta<'a> {
const ELEMENT_TYPE: ElementType = ElementType::Struct;
// needed for last_field_id w/o encryption
- #[allow(unused_assignments)]
+ #[cfg_attr(not(feature = "encryption"), expect(unused_assignments))]
fn write_thrift<W: Write>(&self, writer: &mut
ThriftCompactOutputProtocol<W>) -> Result<()> {
writer.set_write_path_in_schema(self.write_path_in_schema);
// only write ordinal if all values will fit in an i16
@@ -1613,7 +1613,7 @@ impl WriteThrift for RowGroupMetaData {
impl WriteThrift for ColumnChunkMetaData {
const ELEMENT_TYPE: ElementType = ElementType::Struct;
- #[allow(unused_assignments)]
+ #[cfg_attr(not(feature = "encryption"), expect(unused_assignments))]
fn write_thrift<W: Write>(&self, writer: &mut
ThriftCompactOutputProtocol<W>) -> Result<()> {
let mut last_field_id = 0i16;
if let Some(file_path) = self.file_path() {
diff --git a/parquet/src/file/page_index/column_index.rs
b/parquet/src/file/page_index/column_index.rs
index b7a77fdc0d..b68e8e811d 100644
--- a/parquet/src/file/page_index/column_index.rs
+++ b/parquet/src/file/page_index/column_index.rs
@@ -103,7 +103,7 @@ pub struct PrimitiveColumnIndex<T> {
}
impl<T: ParquetValueType> PrimitiveColumnIndex<T> {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(crate) fn try_new(
null_pages: Vec<bool>,
boundary_order: BoundaryOrder,
@@ -322,7 +322,7 @@ pub struct ByteArrayColumnIndex {
}
impl ByteArrayColumnIndex {
- #[allow(clippy::too_many_arguments)]
+ #[expect(clippy::too_many_arguments)]
pub(crate) fn try_new(
null_pages: Vec<bool>,
boundary_order: BoundaryOrder,
@@ -564,7 +564,7 @@ macro_rules! colidx_enum_func {
/// [`ParquetColumnIndex`]: crate::file::metadata::ParquetColumnIndex
/// [`ColumnIndex`]:
https://github.com/apache/parquet-format/blob/master/PageIndex.md
#[derive(Debug, Clone, PartialEq)]
-#[allow(non_camel_case_types)]
+#[expect(non_camel_case_types)]
pub enum ColumnIndexMetaData {
/// Sometimes reading page index from parquet file
/// will only return pageLocations without min_max index,
diff --git a/parquet/src/file/properties.rs b/parquet/src/file/properties.rs
index 074f26fef8..174c783377 100644
--- a/parquet/src/file/properties.rs
+++ b/parquet/src/file/properties.rs
@@ -135,7 +135,7 @@ impl Default for CdcOptions {
///
/// Basic constant, which is not part of the Thrift definition.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-#[allow(non_camel_case_types)]
+#[expect(non_camel_case_types)]
pub enum WriterVersion {
/// Parquet format version 1.0
PARQUET_1_0,
@@ -2180,7 +2180,7 @@ mod tests {
}
#[test]
- #[allow(deprecated)]
+ #[expect(deprecated)]
fn test_writer_properties_deprecated_bloom_filter_ndv_setters_still_work()
{
let col = ColumnPath::from("col");
let props = WriterProperties::builder()
diff --git a/parquet/src/file/reader.rs b/parquet/src/file/reader.rs
index 2b3c46f507..b4fbd66aa7 100644
--- a/parquet/src/file/reader.rs
+++ b/parquet/src/file/reader.rs
@@ -39,7 +39,7 @@ use crate::column::reader::ColumnReaderImpl;
/// Length should return the total number of bytes in the input source.
/// It's mainly used to read the metadata, which is at the end of the source.
-#[allow(clippy::len_without_is_empty)]
+#[expect(clippy::len_without_is_empty)]
pub trait Length {
/// Returns the amount of bytes of the inner source.
fn len(&self) -> u64;
diff --git a/parquet/src/file/serialized_reader.rs
b/parquet/src/file/serialized_reader.rs
index 661976c560..93aceedc2e 100644
--- a/parquet/src/file/serialized_reader.rs
+++ b/parquet/src/file/serialized_reader.rs
@@ -1439,7 +1439,7 @@ mod tests {
assert_eq!(num_values, 8);
assert_eq!(encoding, Encoding::PLAIN_DICTIONARY);
assert_eq!(def_level_encoding, Encoding::RLE);
- #[allow(deprecated)]
+ #[expect(deprecated)]
let expected_rep_level_encoding = Encoding::BIT_PACKED;
assert_eq!(rep_level_encoding,
expected_rep_level_encoding);
assert!(statistics.is_none());
diff --git a/parquet/src/lib.rs b/parquet/src/lib.rs
index 3acdb61884..eb5aac0465 100644
--- a/parquet/src/lib.rs
+++ b/parquet/src/lib.rs
@@ -143,6 +143,7 @@
html_favicon_url =
"https://raw.githubusercontent.com/apache/parquet-format/25f05e73d8cd7f5c83532ce51cb4f4de8ba5f2a2/logo/parquet-logos_1.svg";
)]
#![cfg_attr(docsrs, feature(doc_cfg))]
+#![deny(clippy::allow_attributes)]
#![warn(missing_docs)]
/// Defines a an item with an experimental public API
///
diff --git a/parquet/src/parquet_macros.rs b/parquet/src/parquet_macros.rs
index f7ddf57b14..359a0d7b53 100644
--- a/parquet/src/parquet_macros.rs
+++ b/parquet/src/parquet_macros.rs
@@ -31,8 +31,12 @@
//! [Thrift compact]:
https://github.com/apache/thrift/blob/master/doc/specs/thrift-compact-protocol.md#list-and-set
//! [THRIFT.md]: https://github.com/apache/arrow-rs/blob/main/parquet/THRIFT.md
+// These macros generate `allow` attributes for lints that may not fire on
every
+// invocation, so we keep `allow` instead of `expect`.
+
#[doc(hidden)]
#[macro_export]
+#[expect(clippy::allow_attributes)]
#[allow(clippy::crate_in_macro_def)]
/// Macro used to generate rust enums from a Thrift `enum` definition.
///
@@ -43,6 +47,7 @@ macro_rules! thrift_enum {
($(#[$($def_attrs:tt)*])* enum $identifier:ident {
$($(#[$($field_attrs:tt)*])* $field_name:ident = $field_value:literal;)* }) => {
$(#[$($def_attrs)*])*
#[derive(Clone, Copy, Debug, Eq, Hash, Ord, PartialEq, PartialOrd)]
+ #[allow(clippy::allow_attributes)]
#[allow(non_camel_case_types)]
#[allow(missing_docs)]
pub enum $identifier {
@@ -50,6 +55,7 @@ macro_rules! thrift_enum {
}
impl<'a, R: ThriftCompactInputProtocol<'a>> ReadThrift<'a, R> for
$identifier {
+ #[allow(clippy::allow_attributes)]
#[allow(deprecated)]
fn read_thrift(prot: &mut R) -> Result<Self> {
let val = prot.read_i32()?;
@@ -83,6 +89,7 @@ macro_rules! thrift_enum {
}
impl $identifier {
+ #[allow(clippy::allow_attributes)]
#[allow(deprecated)]
#[doc = "Returns a slice containing every variant of this enum."]
#[allow(dead_code)]
@@ -90,6 +97,7 @@ macro_rules! thrift_enum {
$(Self::$field_name),*
];
+ #[allow(clippy::allow_attributes)]
#[allow(deprecated)]
const fn max_discriminant_impl() -> i32 {
let values: &[i32] = &[$($field_value),*];
@@ -105,6 +113,7 @@ macro_rules! thrift_enum {
max
}
+ #[allow(clippy::allow_attributes)]
#[allow(deprecated)]
#[doc = "Returns the largest discriminant value defined for this
enum."]
#[allow(dead_code)]
@@ -127,11 +136,13 @@ macro_rules! thrift_enum {
/// - When utilizing this macro the Thrift serialization traits and structs
need to be in scope.
#[doc(hidden)]
#[macro_export]
+#[expect(clippy::allow_attributes)]
#[allow(clippy::crate_in_macro_def)]
macro_rules! thrift_union_all_empty {
($(#[$($def_attrs:tt)*])* union $identifier:ident {
$($(#[$($field_attrs:tt)*])* $field_id:literal : $field_type:ident $(<
$element_type:ident >)? $field_name:ident $(;)?)* }) => {
$(#[cfg_attr(not(doctest), $($def_attrs)*)])*
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
+ #[allow(clippy::allow_attributes)]
#[allow(non_camel_case_types)]
#[allow(non_snake_case)]
#[allow(missing_docs)]
@@ -201,11 +212,13 @@ macro_rules! thrift_union_all_empty {
/// - When utilizing this macro the Thrift serialization traits and structs
need to be in scope.
#[doc(hidden)]
#[macro_export]
+#[expect(clippy::allow_attributes)]
#[allow(clippy::crate_in_macro_def)]
macro_rules! thrift_union {
($(#[$($def_attrs:tt)*])* union $identifier:ident $(< $lt:lifetime >)? {
$($(#[$($field_attrs:tt)*])* $field_id:literal : $( ( $field_type:ident $(<
$element_type:ident >)? $(< $field_lt:lifetime >)?) )? $field_name:ident
$(;)?)* }) => {
$(#[cfg_attr(not(doctest), $($def_attrs)*)])*
#[derive(Clone, Debug, Eq, PartialEq)]
+ #[allow(clippy::allow_attributes)]
#[allow(non_camel_case_types)]
#[allow(non_snake_case)]
#[allow(missing_docs)]
@@ -273,11 +286,13 @@ macro_rules! thrift_union {
/// When utilizing this macro the Thrift serialization traits and structs need
to be in scope.
#[doc(hidden)]
#[macro_export]
+#[expect(clippy::allow_attributes)]
#[allow(clippy::crate_in_macro_def)]
macro_rules! thrift_union_with_unknown {
($(#[$($def_attrs:tt)*])* union $identifier:ident $(< $lt:lifetime >)? {
$($(#[$($field_attrs:tt)*])* $field_id:literal : $( ( $field_type:ident $(<
$element_type:ident >)? $(< $field_lt:lifetime >)?) )? $field_name:ident
$(;)?)* }) => {
$(#[cfg_attr(not(doctest), $($def_attrs)*)])*
#[derive(Clone, Debug, Eq, PartialEq)]
+ #[allow(clippy::allow_attributes)]
#[allow(non_camel_case_types)]
#[allow(non_snake_case)]
#[allow(missing_docs)]
@@ -353,6 +368,7 @@ macro_rules! thrift_struct {
($(#[$($def_attrs:tt)*])* $vis:vis struct $identifier:ident $(<
$lt:lifetime >)? { $($(#[$($field_attrs:tt)*])* $field_id:literal :
$required_or_optional:ident $field_type:ident $(< $field_lt:lifetime >)? $(<
$element_type:ident >)? $field_name:ident $(= $default_value:literal)? $(;)?)*
}) => {
$(#[cfg_attr(not(doctest), $($def_attrs)*)])*
#[derive(Clone, Debug, Eq, PartialEq)]
+ #[allow(clippy::allow_attributes)]
#[allow(non_camel_case_types)]
#[allow(non_snake_case)]
#[allow(missing_docs)]
@@ -390,6 +406,7 @@ macro_rules! thrift_struct {
impl $(<$lt>)? WriteThrift for $identifier $(<$lt>)? {
const ELEMENT_TYPE: ElementType = ElementType::Struct;
+ #[allow(clippy::allow_attributes)]
#[allow(unused_assignments)]
fn write_thrift<W: Write>(&self, writer: &mut
ThriftCompactOutputProtocol<W>) -> Result<()> {
#[allow(unused_mut, unused_variables)]
diff --git a/parquet/src/record/api.rs b/parquet/src/record/api.rs
index 104a82e64d..3a09f5253c 100644
--- a/parquet/src/record/api.rs
+++ b/parquet/src/record/api.rs
@@ -50,7 +50,7 @@ pub struct Row {
fields: Vec<(String, Field)>,
}
-#[allow(clippy::len_without_is_empty)]
+#[expect(clippy::len_without_is_empty)]
impl Row {
/// Constructs a `Row` from the list of `fields` and returns it.
pub fn new(fields: Vec<(String, Field)>) -> Row {
@@ -326,7 +326,7 @@ pub struct List {
elements: Vec<Field>,
}
-#[allow(clippy::len_without_is_empty)]
+#[expect(clippy::len_without_is_empty)]
impl List {
/// Get the number of fields in this row
pub fn len(&self) -> usize {
@@ -474,7 +474,7 @@ pub struct Map {
entries: Vec<(Field, Field)>,
}
-#[allow(clippy::len_without_is_empty)]
+#[expect(clippy::len_without_is_empty)]
impl Map {
/// Get the number of fields in this row
pub fn len(&self) -> usize {
@@ -1022,7 +1022,7 @@ fn convert_decimal_to_string(decimal: &Decimal) -> String
{
}
#[cfg(test)]
-#[allow(clippy::many_single_char_names)]
+#[expect(clippy::many_single_char_names)]
mod tests {
use super::*;
@@ -2161,7 +2161,6 @@ mod tests {
}
#[cfg(test)]
-#[allow(clippy::many_single_char_names)]
mod api_tests {
use super::{Row, make_list, make_map};
use crate::record::Field;
diff --git a/parquet/src/record/triplet.rs b/parquet/src/record/triplet.rs
index db3088c715..440e765c20 100644
--- a/parquet/src/record/triplet.rs
+++ b/parquet/src/record/triplet.rs
@@ -42,7 +42,7 @@ macro_rules! triplet_enum_func {
/// High level API wrapper on column reader.
/// Provides per-element access for each primitive column.
-#[allow(clippy::enum_variant_names)]
+#[expect(clippy::enum_variant_names)]
pub enum TripletIter {
BoolTripletIter(TypedTripletIter<BoolType>),
Int32TripletIter(TypedTripletIter<Int32Type>),
diff --git a/parquet/src/schema/printer.rs b/parquet/src/schema/printer.rs
index ddb51b20a1..d711bd4419 100644
--- a/parquet/src/schema/printer.rs
+++ b/parquet/src/schema/printer.rs
@@ -53,7 +53,7 @@ use crate::file::metadata::{ColumnChunkMetaData,
FileMetaData, ParquetMetaData,
use crate::schema::types::Type;
/// Prints Parquet metadata [`ParquetMetaData`] information.
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
pub fn print_parquet_metadata(out: &mut dyn io::Write, metadata:
&ParquetMetaData) {
print_file_metadata(out, metadata.file_metadata());
writeln!(out);
@@ -69,7 +69,7 @@ pub fn print_parquet_metadata(out: &mut dyn io::Write,
metadata: &ParquetMetaDat
}
/// Prints file metadata [`FileMetaData`] information.
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
pub fn print_file_metadata(out: &mut dyn io::Write, file_metadata:
&FileMetaData) {
writeln!(out, "version: {}", file_metadata.version());
writeln!(out, "num of rows: {}", file_metadata.num_rows());
@@ -143,7 +143,7 @@ pub fn print_file_metadata(out: &mut dyn io::Write,
file_metadata: &FileMetaData
/// }
/// }
/// ```
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
pub fn print_schema(out: &mut dyn io::Write, tp: &Type) {
// TODO: better if we can pass fmt::Write to Printer.
// But how can we make it to accept both io::Write & fmt::Write?
@@ -155,7 +155,7 @@ pub fn print_schema(out: &mut dyn io::Write, tp: &Type) {
writeln!(out, "{s}");
}
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
fn print_row_group_metadata(out: &mut dyn io::Write, rg_metadata:
&RowGroupMetaData) {
writeln!(out, "total byte size: {}", rg_metadata.total_byte_size());
writeln!(out, "num of rows: {}", rg_metadata.num_rows());
@@ -170,7 +170,7 @@ fn print_row_group_metadata(out: &mut dyn io::Write,
rg_metadata: &RowGroupMetaD
}
}
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
fn print_column_chunk_metadata(out: &mut dyn io::Write, cc_metadata:
&ColumnChunkMetaData) {
writeln!(out, "column type: {}", cc_metadata.column_type());
writeln!(out, "column path: {}", cc_metadata.column_path());
@@ -240,7 +240,7 @@ fn print_column_chunk_metadata(out: &mut dyn io::Write,
cc_metadata: &ColumnChun
writeln!(out);
}
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
fn print_dashes(out: &mut dyn io::Write, num: i32) {
for _ in 0..num {
write!(out, "-");
@@ -256,7 +256,7 @@ struct Printer<'a> {
indent: i32,
}
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
impl<'a> Printer<'a> {
fn new(output: &'a mut dyn fmt::Write) -> Self {
Printer { output, indent: 0 }
@@ -365,7 +365,7 @@ fn print_logical_and_converted(
}
}
-#[allow(unused_must_use)]
+#[expect(unused_must_use)]
impl Printer<'_> {
pub fn print(&mut self, tp: &Type) {
self.print_indent();
diff --git a/parquet/src/schema/types.rs b/parquet/src/schema/types.rs
index 5c906b171d..a5b6c51bf0 100644
--- a/parquet/src/schema/types.rs
+++ b/parquet/src/schema/types.rs
@@ -1255,7 +1255,7 @@ fn count_leaves(tp: &TypePtr, n_leaves: &mut usize) {
}
}
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
fn build_tree<'a>(
tp: &'a TypePtr,
root_idx: usize,
diff --git a/parquet/src/util/bit_util.rs b/parquet/src/util/bit_util.rs
index 468d7895c8..ca61a885fd 100644
--- a/parquet/src/util/bit_util.rs
+++ b/parquet/src/util/bit_util.rs
@@ -954,7 +954,7 @@ impl From<Vec<u8>> for BitReader {
///
/// Replace with `value.compress(mask)` when `uint_gather_scatter_bits`
/// is stabilised: <https://github.com/rust-lang/rust/issues/149069>
-#[allow(dead_code)]
+#[cfg_attr(all(not(feature = "arrow"), not(test)), expect(dead_code))]
#[inline]
pub(crate) fn compress(value: u64, mask: u64) -> u64 {
#[cfg(all(target_arch = "x86_64", target_feature = "bmi2"))]
diff --git a/parquet/src/util/interner.rs b/parquet/src/util/interner.rs
index deae3720d5..f156541c8f 100644
--- a/parquet/src/util/interner.rs
+++ b/parquet/src/util/interner.rs
@@ -33,7 +33,6 @@ pub trait Storage {
fn push(&mut self, value: &Self::Value) -> Self::Key;
/// Return an estimate of the memory used in this storage, in bytes
- #[allow(dead_code)] // not used in parquet_derive, so is dead there
fn estimated_memory_size(&self) -> usize;
}
@@ -75,7 +74,6 @@ impl<S: Storage> Interner<S> {
}
/// Return estimate of the memory used, in bytes
- #[allow(dead_code)] // not used in parquet_derive, so is dead there
pub fn estimated_memory_size(&self) -> usize {
self.storage.estimated_memory_size() + self.dedup.allocation_size()
}
diff --git a/parquet/src/util/test_common/rand_gen.rs
b/parquet/src/util/test_common/rand_gen.rs
index 635edfce0a..d10b10ca2c 100644
--- a/parquet/src/util/test_common/rand_gen.rs
+++ b/parquet/src/util/test_common/rand_gen.rs
@@ -135,7 +135,7 @@ where
}
}
-#[allow(clippy::too_many_arguments)]
+#[expect(clippy::too_many_arguments)]
pub fn make_pages<T: DataType>(
desc: ColumnDescPtr,
encoding: Encoding,
diff --git a/parquet/tests/arrow_reader/io/mod.rs
b/parquet/tests/arrow_reader/io/mod.rs
index 7e50b2c4bd..cab3c24e7a 100644
--- a/parquet/tests/arrow_reader/io/mod.rs
+++ b/parquet/tests/arrow_reader/io/mod.rs
@@ -479,12 +479,12 @@ enum LogEntry {
/// Read the metadata of the parquet file
ReadMetadata(Range<usize>),
/// Access previously parsed metadata
- #[allow(dead_code)]
+ #[cfg_attr(not(feature = "async"), expect(dead_code))]
GetProvidedMetadata,
/// Read a single logical data object
ReadData(ReadInfo),
/// Read one or more logical data objects in a single operation
- #[allow(dead_code)]
+ #[cfg_attr(not(feature = "async"), expect(dead_code))]
ReadMultipleData(Vec<LogEntry>),
/// Not known where the read came from
Unknown(Range<usize>),
diff --git a/parquet/tests/arrow_writer/mod.rs
b/parquet/tests/arrow_writer/mod.rs
index 2ab386f982..2ba2aab6a4 100644
--- a/parquet/tests/arrow_writer/mod.rs
+++ b/parquet/tests/arrow_writer/mod.rs
@@ -112,7 +112,7 @@ fn subtract_live_bytes(size: usize) {
});
}
-#[allow(unsafe_code)]
+#[expect(unsafe_code)]
unsafe impl GlobalAlloc for TrackingAllocator {
unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
let ptr = unsafe { self.inner.alloc(layout) };
diff --git a/parquet/tests/variant_integration.rs
b/parquet/tests/variant_integration.rs
index e06426a7a8..2db56cddb8 100644
--- a/parquet/tests/variant_integration.rs
+++ b/parquet/tests/variant_integration.rs
@@ -236,7 +236,7 @@ variant_test_case!(138);
/// "variant" : "Variant(metadata=VariantMetadata(dict={}),
value=Variant(type=BOOLEAN_FALSE, value=false))"
/// },
/// ```
-#[allow(dead_code)] // some fields are not used except when printing the struct
+#[expect(dead_code)] // some fields are not used except when printing the
struct
#[derive(Debug, Clone, Deserialize)]
struct VariantTestCase {
/// Case number (e.g., 1, 2, 4, etc. - note: case 3 is missing any data)
![https://raw.githubusercontent.com/apache/parquet-format/25f05e73d8cd7f5c83532ce51cb4f4de8ba5f2a2/logo/parquet-logos_1.svg"](https://raw.githubusercontent.com/apache/parquet-format/25f05e73d8cd7f5c83532ce51cb4f4de8ba5f2a2/logo/parquet-logos_1.svg"){kind=link}