This is an automated email from the ASF dual-hosted git repository.
alamb 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 f28db3e5b4 Introduce workspace lints (#10533)
f28db3e5b4 is described below
commit f28db3e5b4da944a1a21a69c3451ee2895e356e5
Author: Emil Ernerfeldt <[email protected]>
AuthorDate: Tue Aug 4 11:10:10 2026 -0700
Introduce workspace lints (#10533)
# Which issue does this PR close?
No issue in particular
- Related to #10458
- Sibling PR: https://github.com/apache/datafusion/pull/24076
# Rationale for this change
Lint configuration is currently repeated per crate in `lib.rs`. A
`[workspace.lints]` table lets us configure lints once, for every crate,
and makes rolling out new lints a one-line change.
Enabling more lints can also help keeping a higher code quality,
reducing bugs.
# What changes are included in this PR?
Modeled on [egui's
`Cargo.toml`](https://github.com/emilk/egui/blob/main/Cargo.toml). I
started small. We can enable more lints in later PRs.
# Are these changes tested?
Yes, by existing CI: `cargo clippy --workspace --all-targets
--all-features -- -D warnings` and the docs job
(`RUSTDOCFLAGS=-Dwarnings`) both pass. Two previously-dead doc examples
now actually compile and run.
# Are there any user-facing changes?
`parquet_variant_compute::VariantArrayIter` is now exported. It was
already returned by the public `VariantArray::iter`, but was not
nameable. No other API changes.
---------
Co-authored-by: Claude Opus 5 (1M context) <[email protected]>
Co-authored-by: Andrew Lamb <[email protected]>
---
CONTRIBUTING.md | 11 ++++
Cargo.toml | 65 ++++++++++++++++++++++
arrow-arith/Cargo.toml | 3 +
arrow-array/Cargo.toml | 3 +
arrow-array/src/array/boolean_array.rs | 4 ++
arrow-array/src/array/union_array.rs | 4 +-
arrow-array/src/builder/primitive_run_builder.rs | 2 +-
arrow-array/src/ffi_stream.rs | 10 ++--
arrow-array/src/record_batch.rs | 2 +-
arrow-avro/Cargo.toml | 3 +
arrow-avro/src/codec.rs | 2 +-
arrow-avro/src/schema.rs | 8 +--
arrow-avro/src/writer/encoder.rs | 2 +-
arrow-buffer/Cargo.toml | 3 +
arrow-buffer/src/bigint/mod.rs | 2 +-
arrow-buffer/src/buffer/immutable.rs | 4 +-
arrow-buffer/src/util/bit_iterator.rs | 4 +-
arrow-cast/Cargo.toml | 3 +
arrow-cast/src/cast/mod.rs | 4 +-
arrow-csv/Cargo.toml | 3 +
arrow-data/Cargo.toml | 3 +
arrow-data/src/decimal.rs | 2 +-
arrow-data/src/ffi.rs | 2 +-
arrow-flight/Cargo.toml | 3 +
arrow-flight/gen/Cargo.toml | 3 +
arrow-flight/gen/src/main.rs | 2 +
arrow-flight/src/bin/flight_sql_client.rs | 4 +-
arrow-flight/src/encode.rs | 6 +-
arrow-flight/src/sql/metadata/tables.rs | 2 +-
arrow-flight/tests/flight_sql_client.rs | 16 ++----
arrow-integration-test/Cargo.toml | 3 +
arrow-integration-testing/Cargo.toml | 3 +
.../src/bin/arrow-file-to-stream.rs | 2 +
.../src/bin/arrow-json-integration-test.rs | 2 +
.../src/bin/arrow-stream-to-file.rs | 2 +
.../src/bin/flight-test-integration-client.rs | 2 +
.../src/bin/flight-test-integration-server.rs | 2 +
arrow-ipc/Cargo.toml | 3 +
arrow-ipc/src/convert.rs | 2 +-
arrow-ipc/src/reader.rs | 2 +-
arrow-json/Cargo.toml | 3 +
arrow-json/src/writer/encoder.rs | 2 +-
arrow-ord/Cargo.toml | 3 +
arrow-ord/src/sort.rs | 10 ++--
arrow-pyarrow/Cargo.toml | 3 +
arrow-row/Cargo.toml | 3 +
arrow-row/src/lib.rs | 2 +-
arrow-schema/Cargo.toml | 3 +
arrow-schema/src/fields.rs | 16 ++----
arrow-select/Cargo.toml | 3 +
arrow-select/src/filter.rs | 6 +-
arrow-select/src/merge.rs | 5 +-
arrow-string/Cargo.toml | 3 +
arrow/Cargo.toml | 3 +
arrow/src/util/test_util.rs | 9 +--
arrow/tests/shrink_to_fit.rs | 1 -
parquet-geospatial/Cargo.toml | 3 +
parquet-geospatial/src/bounding.rs | 2 +-
parquet-variant-compute/Cargo.toml | 3 +
parquet-variant-compute/src/lib.rs | 2 +-
parquet-variant-compute/src/variant_get.rs | 2 +-
parquet-variant-json/Cargo.toml | 3 +
parquet-variant/Cargo.toml | 3 +
parquet-variant/src/builder/list.rs | 2 +-
parquet-variant/src/utils.rs | 4 +-
parquet/Cargo.toml | 3 +
parquet/benches/metadata.rs | 3 +-
parquet/examples/write_parquet.rs | 2 +-
parquet/src/arrow/arrow_reader/mod.rs | 4 +-
parquet/src/arrow/arrow_reader/statistics.rs | 2 +-
parquet/src/arrow/arrow_writer/levels.rs | 4 +-
parquet/src/arrow/push_decoder/mod.rs | 2 +-
parquet/src/arrow/schema/mod.rs | 2 +-
parquet/src/arrow/schema/primitive.rs | 2 +-
parquet/src/bin/parquet-fromcsv.rs | 9 +--
parquet/src/column/chunker/cdc.rs | 4 +-
parquet/src/column/writer/encoder.rs | 2 +-
parquet/src/column/writer/mod.rs | 2 +-
parquet/src/compression.rs | 4 +-
parquet/src/errors.rs | 26 +++++++++
parquet/src/file/metadata/push_decoder.rs | 2 +-
parquet/src/file/metadata/reader.rs | 3 +-
parquet/src/file/writer.rs | 6 +-
parquet/src/parquet_thrift.rs | 2 +-
parquet/src/util/test_common/file_util.rs | 6 +-
parquet/tests/arrow_reader/row_filter/async.rs | 2 +-
parquet_derive/Cargo.toml | 3 +
parquet_derive_test/Cargo.toml | 3 +
parquet_derive_test/src/lib.rs | 11 ++--
89 files changed, 297 insertions(+), 119 deletions(-)
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index c2d57f20ca..5ff7cc98ab 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -190,6 +190,17 @@ cargo clippy --workspace --all-targets --all-features --
-D warnings
If you use Visual Studio Code with the `rust-analyzer` plugin, you can enable
`clippy` to run each time you save a file. See
https://users.rust-lang.org/t/how-to-use-clippy-in-vs-code-with-rust-analyzer/41881.
+In addition to the lints that `clippy` enables by default, we enable a few
extra ones in
+`[workspace.lints]` in the root `Cargo.toml`. Every crate in the workspace
opts in to those with:
+
+```toml
+[lints]
+workspace = true
+```
+
+New crates should include that section, and new lints should be added to
`[workspace.lints]`
+rather than to individual crates, so that they apply everywhere.
+
One of the concerns with `clippy` is that it often produces a lot of false
positives, or that some recommendations may hurt readability. We do not have a
policy of which lints are ignored, but if you disagree with a `clippy` lint,
you may disable the lint and briefly justify it.
Search for `allow(clippy::` in the codebase to identify lints that are
ignored/allowed. We currently prefer ignoring lints on the lowest unit possible.
diff --git a/Cargo.toml b/Cargo.toml
index e68517ee68..f317703955 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -112,6 +112,71 @@ object_store = { version = "0.14.1", default-features =
false }
simdutf8 = { version = "0.1.5", default-features = false }
+# Lints that are shared by every crate in the workspace.
+#
+# Each member crate opts in with:
+#
+# [lints]
+# workspace = true
+#
+# Only lints that are `allow` by default are worth listing here; the lints
that clippy
+# enables by default are already enforced by CI (`cargo clippy ... -- -D
warnings`).
+#
+# Keep the lists sorted.
+[workspace.lints.rust]
+future_incompatible = { level = "warn", priority = -1 }
+nonstandard_style = { level = "warn", priority = -1 }
+rust_2018_idioms = { level = "warn", priority = -1 }
+rust_2021_prelude_collisions = "warn"
+semicolon_in_expressions_from_macros = "warn"
+unsafe_op_in_unsafe_fn = "warn"
+unused_import_braces = "warn"
+
+# TODO: fix the violations and enable these too. They are all part of
`rust_2018_idioms`,
+# and each has far too many violations to fix in one go:
+elided_lifetimes_in_paths = "allow" # ~1200 violations
+explicit_outlives_requirements = "allow" # ~80 violations
+unused_extern_crates = "allow" # ~60 violations
+
+[workspace.lints.rustdoc]
+all = { level = "warn", priority = -1 }
+broken_intra_doc_links = "warn"
+missing_crate_level_docs = "warn"
+
+[workspace.lints.clippy]
+bool_to_int_with_if = "warn"
+dbg_macro = "warn"
+debug_assert_with_mut_call = "warn"
+doc_comment_double_space_linebreaks = "warn"
+doc_include_without_cfg = "warn"
+flat_map_option = "warn"
+format_push_string = "warn"
+invalid_upcast_comparisons = "warn"
+iter_filter_is_some = "warn"
+iter_with_drain = "warn"
+literal_string_with_formatting_args = "warn"
+manual_instant_elapsed = "warn"
+match_wild_err_arm = "warn"
+mut_mut = "warn"
+mutex_integer = "warn"
+option_as_ref_cloned = "warn"
+path_buf_push_overwrite = "warn"
+pathbuf_init_then_push = "warn"
+ptr_offset_by_literal = "warn"
+rc_mutex = "warn"
+ref_binding_to_reference = "warn"
+same_length_and_capacity = "warn"
+should_panic_without_expect = "warn"
+single_char_pattern = "warn"
+stable_sort_primitive = "warn"
+trailing_empty_array = "warn"
+trait_duplication_in_bounds = "warn"
+unnecessary_box_returns = "warn"
+unnecessary_self_imports = "warn"
+unnecessary_struct_initialization = "warn"
+unused_peekable = "warn"
+zero_sized_map_values = "warn"
+
# release inherited profile keeping debug information and symbols
# for mem/cpu profiling
[profile.profiling]
diff --git a/arrow-arith/Cargo.toml b/arrow-arith/Cargo.toml
index c3222eccf2..b5e1fcc257 100644
--- a/arrow-arith/Cargo.toml
+++ b/arrow-arith/Cargo.toml
@@ -49,3 +49,6 @@ criterion = { workspace = true }
[[bench]]
name = "decimal_arithmetic"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-array/Cargo.toml b/arrow-array/Cargo.toml
index c59c4fe4f2..126996ee64 100644
--- a/arrow-array/Cargo.toml
+++ b/arrow-array/Cargo.toml
@@ -108,3 +108,6 @@ harness = false
[[bench]]
name = "boolean_array"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-array/src/array/boolean_array.rs
b/arrow-array/src/array/boolean_array.rs
index fee4e5b419..18b8fec448 100644
--- a/arrow-array/src/array/boolean_array.rs
+++ b/arrow-array/src/array/boolean_array.rs
@@ -1086,6 +1086,10 @@ mod tests {
fn test_boolean_array_from_iter_with_larger_upper_bound() {
// See https://github.com/apache/arrow-rs/issues/8505
// This returns an upper size hint of 4
+ #[expect(
+ clippy::iter_filter_is_some,
+ reason = "the point of the test is the size hint of `filter`,
which `flatten` does not have"
+ )]
let iterator = vec![Some(true), None, Some(false), None]
.into_iter()
.filter(Option::is_some);
diff --git a/arrow-array/src/array/union_array.rs
b/arrow-array/src/array/union_array.rs
index 5ba7b947c7..4f96ba49d8 100644
--- a/arrow-array/src/array/union_array.rs
+++ b/arrow-array/src/array/union_array.rs
@@ -928,7 +928,7 @@ unsafe impl Array for UnionArray {
}
self.fields
.iter()
- .flat_map(|x| x.as_ref().map(|x| x.get_buffer_memory_size()))
+ .filter_map(|x| x.as_ref().map(|x| x.get_buffer_memory_size()))
.sum::<usize>()
+ sum
}
@@ -942,7 +942,7 @@ unsafe impl Array for UnionArray {
+ self
.fields
.iter()
- .flat_map(|x| x.as_ref().map(|x| x.get_array_memory_size()))
+ .filter_map(|x| x.as_ref().map(|x| x.get_array_memory_size()))
.sum::<usize>()
+ sum
}
diff --git a/arrow-array/src/builder/primitive_run_builder.rs
b/arrow-array/src/builder/primitive_run_builder.rs
index c1dc0d8d7d..8febc29294 100644
--- a/arrow-array/src/builder/primitive_run_builder.rs
+++ b/arrow-array/src/builder/primitive_run_builder.rs
@@ -328,7 +328,7 @@ mod tests {
}
#[test]
- #[should_panic]
+ #[should_panic(expected = "incompatible data type for builder")]
fn test_override_data_type_invalid() {
PrimitiveRunBuilder::<Int16Type,
UInt32Type>::new().with_data_type(DataType::UInt64);
}
diff --git a/arrow-array/src/ffi_stream.rs b/arrow-array/src/ffi_stream.rs
index 9a09c3753d..011f3a8b0f 100644
--- a/arrow-array/src/ffi_stream.rs
+++ b/arrow-array/src/ffi_stream.rs
@@ -417,8 +417,8 @@ mod tests {
pub fn new(
schema: SchemaRef,
iter: Box<dyn Iterator<Item = Result<RecordBatch>> + Send>,
- ) -> Box<TestRecordBatchReader> {
- Box::new(TestRecordBatchReader { schema, iter })
+ ) -> TestRecordBatchReader {
+ TestRecordBatchReader { schema, iter }
}
}
@@ -439,7 +439,7 @@ mod tests {
fn _test_round_trip_export(batch: RecordBatch, schema: Arc<Schema>) ->
Result<()> {
let iter = Box::new(vec![batch.clone(),
batch.clone()].into_iter().map(Ok)) as _;
- let reader = TestRecordBatchReader::new(schema.clone(), iter);
+ let reader = Box::new(TestRecordBatchReader::new(schema.clone(),
iter));
// Export a `RecordBatchReader` through `FFI_ArrowArrayStream`
let mut ffi_stream = FFI_ArrowArrayStream::new(reader);
@@ -484,7 +484,7 @@ mod tests {
fn _test_round_trip_import(batch: RecordBatch, schema: Arc<Schema>) ->
Result<()> {
let iter = Box::new(vec![batch.clone(),
batch.clone()].into_iter().map(Ok)) as _;
- let reader = TestRecordBatchReader::new(schema.clone(), iter);
+ let reader = Box::new(TestRecordBatchReader::new(schema.clone(),
iter));
// Import through `FFI_ArrowArrayStream` as `ArrowArrayStreamReader`
let stream = FFI_ArrowArrayStream::new(reader);
@@ -546,7 +546,7 @@ mod tests {
let iter =
Box::new(vec![Err(ArrowError::MemoryError("".to_string()))].into_iter());
- let reader = TestRecordBatchReader::new(schema.clone(), iter);
+ let reader = Box::new(TestRecordBatchReader::new(schema.clone(),
iter));
// Import through `FFI_ArrowArrayStream` as `ArrowArrayStreamReader`
let stream = FFI_ArrowArrayStream::new(reader);
diff --git a/arrow-array/src/record_batch.rs b/arrow-array/src/record_batch.rs
index 911604cd0b..78177a4d42 100644
--- a/arrow-array/src/record_batch.rs
+++ b/arrow-array/src/record_batch.rs
@@ -644,7 +644,7 @@ impl RecordBatch {
///
/// # Panics
///
- /// Panics if `index`` out of bounds.
+ /// Panics if `index` is out of bounds.
///
/// # Example
///
diff --git a/arrow-avro/Cargo.toml b/arrow-avro/Cargo.toml
index a4c20f0553..ce210cf0e3 100644
--- a/arrow-avro/Cargo.toml
+++ b/arrow-avro/Cargo.toml
@@ -125,3 +125,6 @@ harness = false
[[bench]]
name = "project_record"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-avro/src/codec.rs b/arrow-avro/src/codec.rs
index e21d4df5c3..c4df569ba0 100644
--- a/arrow-avro/src/codec.rs
+++ b/arrow-avro/src/codec.rs
@@ -1198,7 +1198,7 @@ impl From<&Codec> for UnionFieldKind {
fn union_branch_name(dt: &AvroDataType) -> String {
if let Some(name) = dt.metadata.get(AVRO_NAME_METADATA_KEY) {
- if name.contains(".") {
+ if name.contains('.') {
// Full name
return name.to_string();
}
diff --git a/arrow-avro/src/schema.rs b/arrow-avro/src/schema.rs
index ece56c6e71..a22373ac6c 100644
--- a/arrow-avro/src/schema.rs
+++ b/arrow-avro/src/schema.rs
@@ -4011,7 +4011,7 @@ mod tests {
let err = schema.project(&[5]).unwrap_err();
let msg = err.to_string();
assert!(
- msg.contains("out of bounds") && msg.contains("5") &&
msg.contains("2"),
+ msg.contains("out of bounds") && msg.contains('5') &&
msg.contains('2'),
"Expected out of bounds error, got: {msg}"
);
}
@@ -4030,7 +4030,7 @@ mod tests {
let err = schema.project(&[1]).unwrap_err();
let msg = err.to_string();
assert!(
- msg.contains("out of bounds") && msg.contains("1"),
+ msg.contains("out of bounds") && msg.contains('1'),
"Expected out of bounds error for edge case, got: {msg}"
);
}
@@ -4050,7 +4050,7 @@ mod tests {
let err = schema.project(&[0, 1, 0]).unwrap_err();
let msg = err.to_string();
assert!(
- msg.contains("Duplicate projection index") && msg.contains("0"),
+ msg.contains("Duplicate projection index") && msg.contains('0'),
"Expected duplicate index error, got: {msg}"
);
}
@@ -4069,7 +4069,7 @@ mod tests {
let err = schema.project(&[1, 1]).unwrap_err();
let msg = err.to_string();
assert!(
- msg.contains("Duplicate projection index") && msg.contains("1"),
+ msg.contains("Duplicate projection index") && msg.contains('1'),
"Expected duplicate index error for consecutive duplicates, got:
{msg}"
);
}
diff --git a/arrow-avro/src/writer/encoder.rs b/arrow-avro/src/writer/encoder.rs
index 23ace7d049..e88337cd6d 100644
--- a/arrow-avro/src/writer/encoder.rs
+++ b/arrow-avro/src/writer/encoder.rs
@@ -100,7 +100,7 @@ fn write_len_prefixed<W: Write + ?Sized>(out: &mut W,
bytes: &[u8]) -> Result<()
#[inline]
fn write_bool<W: Write + ?Sized>(out: &mut W, v: bool) -> Result<(),
AvroError> {
- out.write_all(&[if v { 1 } else { 0 }])
+ out.write_all(&[u8::from(v)])
.map_err(|e| AvroError::IoError(format!("write bool: {e}"), e))
}
diff --git a/arrow-buffer/Cargo.toml b/arrow-buffer/Cargo.toml
index 86813e6141..6f36d9a0fa 100644
--- a/arrow-buffer/Cargo.toml
+++ b/arrow-buffer/Cargo.toml
@@ -64,3 +64,6 @@ harness = false
[[bench]]
name = "mutable_buffer_repeat_slice"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-buffer/src/bigint/mod.rs b/arrow-buffer/src/bigint/mod.rs
index dc61a5d0f0..81392c3c3a 100644
--- a/arrow-buffer/src/bigint/mod.rs
+++ b/arrow-buffer/src/bigint/mod.rs
@@ -1948,7 +1948,7 @@ mod tests {
assert_eq!(!i256::ONE, i256::from_parts(u128::MAX - 1, -1));
}
- #[should_panic]
+ #[should_panic(expected = "rhs overflow for shift")]
#[test]
fn test_shl_panic_on_arg_overflow() {
let value = i256::from(123);
diff --git a/arrow-buffer/src/buffer/immutable.rs
b/arrow-buffer/src/buffer/immutable.rs
index bfccdf5538..c3821164e4 100644
--- a/arrow-buffer/src/buffer/immutable.rs
+++ b/arrow-buffer/src/buffer/immutable.rs
@@ -692,12 +692,12 @@ mod tests {
assert_eq!([6, 8, 10], buf2.as_slice());
assert_eq!(3, buf2.len());
- assert_eq!(unsafe { buf.as_ptr().offset(2) }, buf2.as_ptr());
+ assert_eq!(unsafe { buf.as_ptr().add(2) }, buf2.as_ptr());
let buf3 = buf2.slice_with_length(1, 2);
assert_eq!([8, 10], buf3.as_slice());
assert_eq!(2, buf3.len());
- assert_eq!(unsafe { buf.as_ptr().offset(3) }, buf3.as_ptr());
+ assert_eq!(unsafe { buf.as_ptr().add(3) }, buf3.as_ptr());
let buf4 = buf.slice(5);
let empty_slice: [u8; 0] = [];
diff --git a/arrow-buffer/src/util/bit_iterator.rs
b/arrow-buffer/src/util/bit_iterator.rs
index a1b2fec6ea..840a2c2df1 100644
--- a/arrow-buffer/src/util/bit_iterator.rs
+++ b/arrow-buffer/src/util/bit_iterator.rs
@@ -555,7 +555,7 @@ mod tests {
#[test]
fn test_bit_index_u32_long_all_set() {
let len = 200;
- let num_bytes = len / 8 + if len % 8 != 0 { 1 } else { 0 };
+ let num_bytes = len / 8 + usize::from(len % 8 != 0);
let bytes = vec![0xFFu8; num_bytes];
let result: Vec<u32> = BitIndexU32Iterator::new(&bytes, 0,
len).collect();
@@ -568,7 +568,7 @@ mod tests {
#[test]
fn test_bit_index_u32_none_set() {
let len = 50;
- let num_bytes = len / 8 + if len % 8 != 0 { 1 } else { 0 };
+ let num_bytes = len / 8 + usize::from(len % 8 != 0);
let bytes = vec![0u8; num_bytes];
let result: Vec<u32> = BitIndexU32Iterator::new(&bytes, 0,
len).collect();
diff --git a/arrow-cast/Cargo.toml b/arrow-cast/Cargo.toml
index 65646bfc2f..d3257f5894 100644
--- a/arrow-cast/Cargo.toml
+++ b/arrow-cast/Cargo.toml
@@ -76,3 +76,6 @@ harness = false
[[bench]]
name = "parse_decimal"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-cast/src/cast/mod.rs b/arrow-cast/src/cast/mod.rs
index 35dce48e68..d88fd2847b 100644
--- a/arrow-cast/src/cast/mod.rs
+++ b/arrow-cast/src/cast/mod.rs
@@ -646,7 +646,7 @@ fn timestamp_to_date32<T: ArrowTimestampType>(
/// has the wrong length it will be replaced with NULL, otherwise an error
will be returned
/// * Primitive to `List`: a list array with 1 value per slot is created
/// * `Date32` and `Date64`: precision lost when going to higher interval
-/// * `Time32 and `Time64`: precision lost when going to higher interval
+/// * `Time32` and `Time64`: precision lost when going to higher interval
/// * `Timestamp` and `Date{32|64}`: precision lost when going to higher
interval
/// * Temporal to/from backing Primitive: zero-copy with data type change
/// * `Float16/Float32/Float64` to `Decimal(precision, scale)` rounds to the
`scale` decimals
@@ -2616,7 +2616,7 @@ where
fn numeric_to_bool_cast<T>(from: &PrimitiveArray<T>) -> Result<BooleanArray,
ArrowError>
where
- T: ArrowPrimitiveType + ArrowPrimitiveType,
+ T: ArrowPrimitiveType,
{
let mut b = BooleanBuilder::with_capacity(from.len());
diff --git a/arrow-csv/Cargo.toml b/arrow-csv/Cargo.toml
index 689acf7b06..aa1cbc21f6 100644
--- a/arrow-csv/Cargo.toml
+++ b/arrow-csv/Cargo.toml
@@ -51,3 +51,6 @@ futures = "0.3"
tokio = { version = "1.27", default-features = false, features = ["io-util"] }
bytes = "1.4"
half = { version = "2.1", default-features = false }
+
+[lints]
+workspace = true
diff --git a/arrow-data/Cargo.toml b/arrow-data/Cargo.toml
index 9f1b50ed14..3c51213474 100644
--- a/arrow-data/Cargo.toml
+++ b/arrow-data/Cargo.toml
@@ -57,3 +57,6 @@ half = { version = "2.1", default-features = false }
[dev-dependencies]
[build-dependencies]
+
+[lints]
+workspace = true
diff --git a/arrow-data/src/decimal.rs b/arrow-data/src/decimal.rs
index a5986755ad..8dc4328102 100644
--- a/arrow-data/src/decimal.rs
+++ b/arrow-data/src/decimal.rs
@@ -896,7 +896,7 @@ pub const MAX_DECIMAL32_FOR_EACH_PRECISION: [i32; 10] = [
9, 99, 999, 9999, 99999, 999999, 9999999, 99999999, 999999999,
];
-/// `MIN_DECIMAL32_FOR_EACH_PRECISION[p]` holds the minimum `ialue that can
+/// `MIN_DECIMAL32_FOR_EACH_PRECISION[p]` holds the minimum value that can
/// be stored in a [`Decimal32`] value of precision `p`.
///
/// # Notes
diff --git a/arrow-data/src/ffi.rs b/arrow-data/src/ffi.rs
index 80ccee6c8a..29107641c1 100644
--- a/arrow-data/src/ffi.rs
+++ b/arrow-data/src/ffi.rs
@@ -166,7 +166,7 @@ impl FFI_ArrowArray {
let buffers_ptr = buffers
.iter()
- .flat_map(|maybe_buffer| match maybe_buffer {
+ .filter_map(|maybe_buffer| match maybe_buffer {
Some(b) => Some(b.as_ptr() as *const c_void),
// This is for null buffer. We only put a null pointer for
// null buffer if by spec it can contain null mask.
diff --git a/arrow-flight/Cargo.toml b/arrow-flight/Cargo.toml
index 0356219079..8062d0fa09 100644
--- a/arrow-flight/Cargo.toml
+++ b/arrow-flight/Cargo.toml
@@ -110,3 +110,6 @@ required-features = ["cli", "flight-sql", "tls-ring"]
name = "flight"
path = "benches/flight.rs"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-flight/gen/Cargo.toml b/arrow-flight/gen/Cargo.toml
index 2ce3f814d8..da766e75e0 100644
--- a/arrow-flight/gen/Cargo.toml
+++ b/arrow-flight/gen/Cargo.toml
@@ -34,3 +34,6 @@ publish = false
# (and checked in) arrow.flight.protocol.rs from changing
prost-build = { version = "0.14.1", default-features = false }
tonic-prost-build = { version = "0.14.1", default-features = false }
+
+[lints]
+workspace = true
diff --git a/arrow-flight/gen/src/main.rs b/arrow-flight/gen/src/main.rs
index 6db70dc109..cd50214f1c 100644
--- a/arrow-flight/gen/src/main.rs
+++ b/arrow-flight/gen/src/main.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! Generates the Rust bindings for the Arrow Flight protobuf definitions.
+
use std::{
fs::OpenOptions,
io::{Read, Write},
diff --git a/arrow-flight/src/bin/flight_sql_client.rs
b/arrow-flight/src/bin/flight_sql_client.rs
index 554c6339aa..c08d945b66 100644
--- a/arrow-flight/src/bin/flight_sql_client.rs
+++ b/arrow-flight/src/bin/flight_sql_client.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! A command line client for Arrow Flight SQL.
+
use std::{sync::Arc, time::Duration};
use anyhow::{Context, Result, bail};
@@ -138,7 +140,7 @@ struct ClientArgs {
/// Since the client needs to decide on the compression before sending the
request, there is no client<->server
/// negotiation. If the server does NOT support the chosen compression, it
will respond with an error a la:
///
- /// ```
+ /// ```text
/// Ipc error: Status {
/// code: Unimplemented,
/// message: "Content is compressed with `zstd` which isn't supported",
diff --git a/arrow-flight/src/encode.rs b/arrow-flight/src/encode.rs
index 810d416d9a..95fde96e37 100644
--- a/arrow-flight/src/encode.rs
+++ b/arrow-flight/src/encode.rs
@@ -463,7 +463,7 @@ impl Stream for FlightDataEncoder {
///
/// For clients which may not support `DictionaryEncoding`, the
`DictionaryHandling::Hydrate` method will bypass the process defined above
/// and "hydrate" any `DictionaryArray` in the batch to their underlying value
type (e.g. `TypedDictionaryArray<'_, UInt32Type, Utf8Type>` will
-/// be sent as a `StringArray`). With this method all data will be sent in
``MessageHeader::RecordBatch` messages and the batch schema
+/// be sent as a `StringArray`). With this method all data will be sent in
`MessageHeader::RecordBatch` messages and the batch schema
/// will be adjusted so that all dictionary encoded fields are changed to
fields of the dictionary value type.
#[derive(Debug, PartialEq)]
pub enum DictionaryHandling {
@@ -1793,7 +1793,7 @@ mod tests {
/// Encode `batches` through a [`FlightDataEncoderBuilder`] using
`options`, decode them
/// again, and assert the decoded batches match the originals.
async fn verify_flight_round_trip_with_options(
- mut batches: Vec<RecordBatch>,
+ batches: Vec<RecordBatch>,
options: IpcWriteOptions,
) {
let expected_schema = batches.first().unwrap().schema();
@@ -1803,7 +1803,7 @@ mod tests {
.with_dictionary_handling(DictionaryHandling::Resend)
.build(futures::stream::iter(batches.clone().into_iter().map(Ok)));
- let mut expected_batches = batches.drain(..);
+ let mut expected_batches = batches.into_iter();
let mut decoder = FlightDataDecoder::new(encoder);
while let Some(decoded) = decoder.next().await {
diff --git a/arrow-flight/src/sql/metadata/tables.rs
b/arrow-flight/src/sql/metadata/tables.rs
index 2cd16fdc23..eedc2bcd2a 100644
--- a/arrow-flight/src/sql/metadata/tables.rs
+++ b/arrow-flight/src/sql/metadata/tables.rs
@@ -267,7 +267,7 @@ impl GetTablesBuilder {
/// Return the schema of the RecordBatch that will be returned from
[`CommandGetTables`]
///
- /// Note the schema differs based on the values of `include_schema
+ /// Note the schema differs based on the values of `include_schema`
///
/// [`CommandGetTables`]: crate::sql::CommandGetTables
pub fn schema(&self) -> SchemaRef {
diff --git a/arrow-flight/tests/flight_sql_client.rs
b/arrow-flight/tests/flight_sql_client.rs
index 97687c3dea..508a80898d 100644
--- a/arrow-flight/tests/flight_sql_client.rs
+++ b/arrow-flight/tests/flight_sql_client.rs
@@ -35,7 +35,7 @@ use arrow_flight::sql::{
use arrow_flight::{Action, FlightData, FlightDescriptor};
use futures::{StreamExt, TryStreamExt};
use prost::Message;
-use std::collections::HashMap;
+use std::collections::{HashMap, HashSet};
use std::sync::Arc;
use tokio::sync::Mutex;
use tonic::{IntoStreamingRequest, Request, Status};
@@ -223,14 +223,14 @@ fn make_ingest_command() -> CommandStatementIngest {
#[derive(Clone)]
pub struct FlightSqlServiceImpl {
- transactions: Arc<Mutex<HashMap<String, ()>>>,
+ transactions: Arc<Mutex<HashSet<String>>>,
ingested_batches: Arc<Mutex<Vec<RecordBatch>>>,
}
impl FlightSqlServiceImpl {
pub fn new() -> Self {
Self {
- transactions: Arc::new(Mutex::new(HashMap::new())),
+ transactions: Arc::new(Mutex::new(HashSet::new())),
ingested_batches: Arc::new(Mutex::new(Vec::new())),
}
}
@@ -262,7 +262,7 @@ impl FlightSqlService for FlightSqlServiceImpl {
self.transactions
.lock()
.await
- .insert(transaction_id.clone(), ());
+ .insert(transaction_id.clone());
Ok(ActionBeginTransactionResult {
transaction_id: transaction_id.as_bytes().to_vec().into(),
})
@@ -275,13 +275,7 @@ impl FlightSqlService for FlightSqlServiceImpl {
) -> Result<(), Status> {
let transaction_id = String::from_utf8(query.transaction_id.to_vec())
.map_err(|_| Status::invalid_argument("Invalid transaction id"))?;
- if self
- .transactions
- .lock()
- .await
- .remove(&transaction_id)
- .is_none()
- {
+ if !self.transactions.lock().await.remove(&transaction_id) {
return Err(Status::invalid_argument("Transaction id not found"));
}
Ok(())
diff --git a/arrow-integration-test/Cargo.toml
b/arrow-integration-test/Cargo.toml
index 807a385744..10fa57d744 100644
--- a/arrow-integration-test/Cargo.toml
+++ b/arrow-integration-test/Cargo.toml
@@ -43,3 +43,6 @@ num-bigint = { version = "0.5", default-features = false }
num-traits = { version = "0.2.19", default-features = false, features =
["std"] }
serde = { version = "1.0", default-features = false, features = ["rc",
"derive"] }
serde_json = { version = "1.0", default-features = false, features = ["std"] }
+
+[lints]
+workspace = true
diff --git a/arrow-integration-testing/Cargo.toml
b/arrow-integration-testing/Cargo.toml
index cb488f5ff7..2a95cefe6a 100644
--- a/arrow-integration-testing/Cargo.toml
+++ b/arrow-integration-testing/Cargo.toml
@@ -50,3 +50,6 @@ flate2 = { version = "1", default-features = false, features
= ["rust_backend"]
[dev-dependencies]
arrow-buffer = { path = "../arrow-buffer", default-features = false }
tempfile = { version = "3", default-features = false }
+
+[lints]
+workspace = true
diff --git a/arrow-integration-testing/src/bin/arrow-file-to-stream.rs
b/arrow-integration-testing/src/bin/arrow-file-to-stream.rs
index 661f0a047d..ca1e25ce98 100644
--- a/arrow-integration-testing/src/bin/arrow-file-to-stream.rs
+++ b/arrow-integration-testing/src/bin/arrow-file-to-stream.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! Converts an Arrow IPC file to an Arrow IPC stream.
+
// The unused_crate_dependencies lint does not work well for crates defining
additional examples/bin targets
#![allow(unused_crate_dependencies)]
diff --git a/arrow-integration-testing/src/bin/arrow-json-integration-test.rs
b/arrow-integration-testing/src/bin/arrow-json-integration-test.rs
index 6a901cc63b..a71ba166ca 100644
--- a/arrow-integration-testing/src/bin/arrow-json-integration-test.rs
+++ b/arrow-integration-testing/src/bin/arrow-json-integration-test.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! Converts between the Arrow IPC file format and the integration test JSON
format.
+
// The unused_crate_dependencies lint does not work well for crates defining
additional examples/bin targets
#![allow(unused_crate_dependencies)]
diff --git a/arrow-integration-testing/src/bin/arrow-stream-to-file.rs
b/arrow-integration-testing/src/bin/arrow-stream-to-file.rs
index 8b4bb33278..ed4c289ca9 100644
--- a/arrow-integration-testing/src/bin/arrow-stream-to-file.rs
+++ b/arrow-integration-testing/src/bin/arrow-stream-to-file.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! Converts an Arrow IPC stream to an Arrow IPC file.
+
// The unused_crate_dependencies lint does not work well for crates defining
additional examples/bin targets
#![allow(unused_crate_dependencies)]
diff --git
a/arrow-integration-testing/src/bin/flight-test-integration-client.rs
b/arrow-integration-testing/src/bin/flight-test-integration-client.rs
index 0d16fe3b40..c23595be3b 100644
--- a/arrow-integration-testing/src/bin/flight-test-integration-client.rs
+++ b/arrow-integration-testing/src/bin/flight-test-integration-client.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! The client side of the Arrow Flight integration tests.
+
// The unused_crate_dependencies lint does not work well for crates defining
additional examples/bin targets
#![allow(unused_crate_dependencies)]
diff --git
a/arrow-integration-testing/src/bin/flight-test-integration-server.rs
b/arrow-integration-testing/src/bin/flight-test-integration-server.rs
index 94be713097..87d1847afd 100644
--- a/arrow-integration-testing/src/bin/flight-test-integration-server.rs
+++ b/arrow-integration-testing/src/bin/flight-test-integration-server.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! The server side of the Arrow Flight integration tests.
+
// The unused_crate_dependencies lint does not work well for crates defining
additional examples/bin targets
#![allow(unused_crate_dependencies)]
diff --git a/arrow-ipc/Cargo.toml b/arrow-ipc/Cargo.toml
index e8c821145b..239e8e139d 100644
--- a/arrow-ipc/Cargo.toml
+++ b/arrow-ipc/Cargo.toml
@@ -64,3 +64,6 @@ harness = false
[[bench]]
name = "ipc_reader"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-ipc/src/convert.rs b/arrow-ipc/src/convert.rs
index 391e73418d..6429f76f8a 100644
--- a/arrow-ipc/src/convert.rs
+++ b/arrow-ipc/src/convert.rs
@@ -190,7 +190,7 @@ impl From<crate::Field<'_>> for Field {
}
}
-/// Deserialize an ipc [crate::Schema`] from flat buffers to an arrow [Schema].
+/// Deserialize an ipc [`crate::Schema`] from flat buffers to an arrow
[Schema].
pub fn fb_to_schema(fb: crate::Schema) -> Schema {
let mut fields: Vec<Field> = vec![];
let c_fields = fb.fields().unwrap();
diff --git a/arrow-ipc/src/reader.rs b/arrow-ipc/src/reader.rs
index 05db7a8ad5..3cd11adda0 100644
--- a/arrow-ipc/src/reader.rs
+++ b/arrow-ipc/src/reader.rs
@@ -43,7 +43,7 @@ use arrow_data::{ArrayData, ArrayDataBuilder, UnsafeFlag};
use arrow_schema::*;
use crate::compression::{CompressionCodec, DecompressionContext};
-use crate::r#gen::Message::{self};
+use crate::r#gen::Message;
use crate::{Block, CONTINUATION_MARKER, FieldNode, MetadataVersion};
use DataType::*;
diff --git a/arrow-json/Cargo.toml b/arrow-json/Cargo.toml
index 4f147f572b..c740450d61 100644
--- a/arrow-json/Cargo.toml
+++ b/arrow-json/Cargo.toml
@@ -75,3 +75,6 @@ harness = false
[[bench]]
name = "json_writer"
harness = false
+
+[lints]
+workspace = true
diff --git a/arrow-json/src/writer/encoder.rs b/arrow-json/src/writer/encoder.rs
index e715ca4b4e..f70f484612 100644
--- a/arrow-json/src/writer/encoder.rs
+++ b/arrow-json/src/writer/encoder.rs
@@ -242,7 +242,7 @@ pub trait EncoderFactory: std::fmt::Debug + Send + Sync {
/// Note that the type of the field may not match the type of the array:
for dictionary arrays unless the top-level dictionary is handled this
/// will be called again for the keys and values of the dictionary, at
which point the field type will still be the outer dictionary type but the
/// array will have a different type.
- /// For example, `field`` might have the type `Dictionary(i32, Utf8)` but
`array` will be `Utf8`.
+ /// For example, `field` might have the type `Dictionary(i32, Utf8)` but
`array` will be `Utf8`.
fn make_default_encoder<'a>(
&self,
_field: &'a FieldRef,
diff --git a/arrow-ord/Cargo.toml b/arrow-ord/Cargo.toml
index 5c4a30994b..fa351f32d8 100644
--- a/arrow-ord/Cargo.toml
+++ b/arrow-ord/Cargo.toml
@@ -45,3 +45,6 @@ arrow-select = { workspace = true }
[dev-dependencies]
half = { version = "2.1", default-features = false, features = ["num-traits"] }
rand = { version = "0.10", default-features = false, features = ["std",
"std_rng"] }
+
+[lints]
+workspace = true
diff --git a/arrow-ord/src/sort.rs b/arrow-ord/src/sort.rs
index fbafcb6732..0c6720e8f2 100644
--- a/arrow-ord/src/sort.rs
+++ b/arrow-ord/src/sort.rs
@@ -5137,7 +5137,7 @@ mod tests {
// Use standard library sort as reference
let mut expected = test_cases.clone();
- expected.sort();
+ expected.sort_unstable();
// Use our sorting algorithm
let string_array = StringArray::from(test_cases.clone());
@@ -5185,7 +5185,7 @@ mod tests {
let strings: Vec<&str> = test_cases.iter().map(|(s, _)| *s).collect();
let mut expected = strings.clone();
- expected.sort();
+ expected.sort_unstable();
let string_array = StringArray::from(strings.clone());
let indices: Vec<u32> = (0..strings.len() as u32).collect();
@@ -5218,7 +5218,7 @@ mod tests {
];
let mut expected = test_cases.clone();
- expected.sort();
+ expected.sort_unstable();
let string_array = StringArray::from(test_cases.clone());
let indices: Vec<u32> = (0..test_cases.len() as u32).collect();
@@ -5336,7 +5336,7 @@ mod tests {
let test_cases = vec!["a", "ab", "ba", "baa", "abba", "abbc", "abc",
"cda"];
let mut expected = test_cases.clone();
- expected.sort();
+ expected.sort_unstable();
expected.reverse(); // Descending order
let string_array = StringArray::from(test_cases.clone());
@@ -5395,7 +5395,7 @@ mod tests {
let limit = 3;
let mut expected = test_cases.clone();
- expected.sort();
+ expected.sort_unstable();
expected.truncate(limit);
let string_array = StringArray::from(test_cases.clone());
diff --git a/arrow-pyarrow/Cargo.toml b/arrow-pyarrow/Cargo.toml
index 9f21a9dcb0..0051de8743 100644
--- a/arrow-pyarrow/Cargo.toml
+++ b/arrow-pyarrow/Cargo.toml
@@ -40,3 +40,6 @@ arrow-array = { workspace = true, features = ["ffi"] }
arrow-data = { workspace = true }
arrow-schema = { workspace = true }
pyo3 = { version = "0.29.0", default-features = false }
+
+[lints]
+workspace = true
diff --git a/arrow-row/Cargo.toml b/arrow-row/Cargo.toml
index 8293093ce4..990ae90371 100644
--- a/arrow-row/Cargo.toml
+++ b/arrow-row/Cargo.toml
@@ -48,3 +48,6 @@ arrow-cast = { workspace = true }
arrow-ord = { workspace = true }
arrow-select = { workspace = true }
rand = { version = "0.9", default-features = false, features = ["std",
"std_rng", "thread_rng"] }
+
+[lints]
+workspace = true
diff --git a/arrow-row/src/lib.rs b/arrow-row/src/lib.rs
index 05d8194932..a48f6a7bc7 100644
--- a/arrow-row/src/lib.rs
+++ b/arrow-row/src/lib.rs
@@ -4897,7 +4897,7 @@ mod tests {
let keys_arrow_row_converter =
RowConverter::new(vec![SortField::new(array.key_type().clone())]).unwrap();
- array.iter().enumerate().flat_map(|(index, entry)| entry.map(|entry|
(index, Arc::clone(entry.column(0))))).for_each(|(entry_index, keys)| {
+ array.iter().enumerate().filter_map(|(index, entry)| entry.map(|entry|
(index, Arc::clone(entry.column(0))))).for_each(|(entry_index, keys)| {
let keys_as_rows =
keys_arrow_row_converter.convert_columns(&[Arc::clone(&keys)]).expect("should
be able to convert keys");
for i in 0..keys_as_rows.num_rows() {
diff --git a/arrow-schema/Cargo.toml b/arrow-schema/Cargo.toml
index 2991e2aa46..e85f8850d3 100644
--- a/arrow-schema/Cargo.toml
+++ b/arrow-schema/Cargo.toml
@@ -61,3 +61,6 @@ postcard = { version = "1.0.10", default-features = false,
features = ["use-std"
name = "ffi"
harness = false
required-features = ["ffi"]
+
+[lints]
+workspace = true
diff --git a/arrow-schema/src/fields.rs b/arrow-schema/src/fields.rs
index f06d5631ed..7f6bc21172 100644
--- a/arrow-schema/src/fields.rs
+++ b/arrow-schema/src/fields.rs
@@ -196,10 +196,7 @@ impl Fields {
Struct(fields) => {
let filtered: Result<Vec<_>, _> =
fields.iter().map(|f| filter_field(f,
filter)).collect();
- let filtered: Fields = filtered?
- .iter()
- .filter_map(|f| f.as_ref().cloned())
- .collect();
+ let filtered: Fields = filtered?.iter().filter_map(|f|
f.clone()).collect();
if filtered.is_empty() {
return Ok(None);
@@ -212,10 +209,8 @@ impl Fields {
.iter()
.map(|(id, f)| filter_field(f, filter).map(|f|
f.map(|f| (id, f))))
.collect();
- let filtered: UnionFields = filtered?
- .iter()
- .filter_map(|f| f.as_ref().cloned())
- .collect();
+ let filtered: UnionFields =
+ filtered?.iter().filter_map(|f| f.clone()).collect();
if filtered.is_empty() {
return Ok(None);
@@ -250,10 +245,7 @@ impl Fields {
.iter()
.map(|f| filter_field(f, &mut filter))
.collect();
- let filtered = filtered?
- .iter()
- .filter_map(|f| f.as_ref().cloned())
- .collect();
+ let filtered = filtered?.iter().filter_map(|f| f.clone()).collect();
Ok(filtered)
}
}
diff --git a/arrow-select/Cargo.toml b/arrow-select/Cargo.toml
index a8d8056647..d6b0a7ee81 100644
--- a/arrow-select/Cargo.toml
+++ b/arrow-select/Cargo.toml
@@ -45,3 +45,6 @@ ahash = { version = "0.8", default-features = false}
[dev-dependencies]
rand = { version = "0.10", default-features = false, features = ["std",
"std_rng", "thread_rng"] }
+
+[lints]
+workspace = true
diff --git a/arrow-select/src/filter.rs b/arrow-select/src/filter.rs
index e3ef6daa96..1c49826fe3 100644
--- a/arrow-select/src/filter.rs
+++ b/arrow-select/src/filter.rs
@@ -1806,7 +1806,7 @@ mod tests {
.skip(offset)
.take(truncated_length)
.enumerate()
- .flat_map(|(idx, v)| v.then(|| idx))
+ .filter_map(|(idx, v)| v.then_some(idx))
.collect();
assert_eq!(slice_bits, expected_bits);
@@ -2373,7 +2373,7 @@ mod tests {
}
#[test]
- #[should_panic]
+ #[should_panic(expected = "buffer.len() >= predicate.filter.len()")]
fn test_filter_bits_too_large() {
let buffer = BooleanBuffer::from(vec![false; 8]);
let predicate = BooleanArray::from(vec![true; 9]);
@@ -2382,7 +2382,7 @@ mod tests {
}
#[test]
- #[should_panic]
+ #[should_panic(expected = "values.len() >= predicate.filter.len()")]
fn test_filter_native_too_large() {
let values = vec![1; 8];
let predicate = BooleanArray::from(vec![false; 9]);
diff --git a/arrow-select/src/merge.rs b/arrow-select/src/merge.rs
index 76958e658f..2198194380 100644
--- a/arrow-select/src/merge.rs
+++ b/arrow-select/src/merge.rs
@@ -564,7 +564,10 @@ mod tests {
}
#[test]
- #[should_panic]
+ // The message differs between debug and release: in release the
+ // `cfg(debug_assertions)` bounds check in `merge_n` is compiled out and
the
+ // slice index panics instead.
+ #[should_panic(expected = "out of bounds")]
fn test_merge_n_invalid_indices() {
let a1 = StringArray::from(vec![Some("A")]);
diff --git a/arrow-string/Cargo.toml b/arrow-string/Cargo.toml
index 3045c355e4..7d0b20edf5 100644
--- a/arrow-string/Cargo.toml
+++ b/arrow-string/Cargo.toml
@@ -45,3 +45,6 @@ regex = { version = "1.7.0", default-features = false,
features = ["std", "unico
regex-syntax = { version = "0.8.0", default-features = false, features =
["unicode"] }
num-traits = { version = "0.2.19", default-features = false, features =
["std"] }
memchr = "2.7.4"
+
+[lints]
+workspace = true
diff --git a/arrow/Cargo.toml b/arrow/Cargo.toml
index 2be4cfd1f1..9dbc59fe5d 100644
--- a/arrow/Cargo.toml
+++ b/arrow/Cargo.toml
@@ -338,3 +338,6 @@ required-features = ["chrono-tz"]
[[test]]
name = "arithmetic"
required-features = ["chrono-tz"]
+
+[lints]
+workspace = true
diff --git a/arrow/src/util/test_util.rs b/arrow/src/util/test_util.rs
index dbcea03ee7..aec867bb27 100644
--- a/arrow/src/util/test_util.rs
+++ b/arrow/src/util/test_util.rs
@@ -40,12 +40,9 @@ pub fn seedable_rng() -> StdRng {
/// TODO: Originates from `parquet` utils, can be merged in [ARROW-4064]
pub fn get_temp_file(file_name: &str, content: &[u8]) -> fs::File {
// build tmp path to a file in "target/debug/testdata"
- let mut path_buf = env::current_dir().unwrap();
- path_buf.push("target");
- path_buf.push("debug");
- path_buf.push("testdata");
- fs::create_dir_all(&path_buf).unwrap();
- path_buf.push(file_name);
+ let dir = env::current_dir().unwrap().join("target/debug/testdata");
+ fs::create_dir_all(&dir).unwrap();
+ let path_buf = dir.join(file_name);
// write file content
let mut tmp_file = fs::File::create(path_buf.as_path()).unwrap();
diff --git a/arrow/tests/shrink_to_fit.rs b/arrow/tests/shrink_to_fit.rs
index 1613fefeda..564c134006 100644
--- a/arrow/tests/shrink_to_fit.rs
+++ b/arrow/tests/shrink_to_fit.rs
@@ -45,7 +45,6 @@ fn test_shrink_to_fit_after_concat() {
memory_use(|| {
let mut concatenated = concatenate(num_concats,
list_array.clone());
concatenated.shrink_to_fit(); // This is what we're testing!
- dbg!(concatenated.data_type());
concatenated
});
let expected_len = num_concats * array_len;
diff --git a/parquet-geospatial/Cargo.toml b/parquet-geospatial/Cargo.toml
index 471b355dc6..08d74ed7e9 100644
--- a/parquet-geospatial/Cargo.toml
+++ b/parquet-geospatial/Cargo.toml
@@ -41,3 +41,6 @@ wkt = { version = "0.14" }
[lib]
name = "parquet_geospatial"
bench = false
+
+[lints]
+workspace = true
diff --git a/parquet-geospatial/src/bounding.rs
b/parquet-geospatial/src/bounding.rs
index 9726c16ba4..6e59c4a953 100644
--- a/parquet-geospatial/src/bounding.rs
+++ b/parquet-geospatial/src/bounding.rs
@@ -146,7 +146,7 @@ impl GeometryBounder {
/// for PointZ). The output is always returned sorted.
pub fn geometry_types(&self) -> Vec<i32> {
let mut out = self.geometry_types.iter().copied().collect::<Vec<_>>();
- out.sort();
+ out.sort_unstable();
out
}
diff --git a/parquet-variant-compute/Cargo.toml
b/parquet-variant-compute/Cargo.toml
index bcfb36b871..7b58fae5a2 100644
--- a/parquet-variant-compute/Cargo.toml
+++ b/parquet-variant-compute/Cargo.toml
@@ -54,3 +54,6 @@ arrow = { workspace = true, features = ["test_utils"] }
[[bench]]
name = "variant_kernels"
harness = false
+
+[lints]
+workspace = true
diff --git a/parquet-variant-compute/src/lib.rs
b/parquet-variant-compute/src/lib.rs
index 066fe15b7c..f1e87661c8 100644
--- a/parquet-variant-compute/src/lib.rs
+++ b/parquet-variant-compute/src/lib.rs
@@ -51,7 +51,7 @@ mod variant_array_builder;
mod variant_get;
mod variant_to_arrow;
-pub use variant_array::{ShreddingState, VariantArray, VariantType};
+pub use variant_array::{ShreddingState, VariantArray, VariantArrayIter,
VariantType};
pub use variant_array_builder::{VariantArrayBuilder, VariantValueArrayBuilder};
pub use cast_to_variant::{cast_to_variant, cast_to_variant_with_options};
diff --git a/parquet-variant-compute/src/variant_get.rs
b/parquet-variant-compute/src/variant_get.rs
index 35d94b70f4..04a2690b1e 100644
--- a/parquet-variant-compute/src/variant_get.rs
+++ b/parquet-variant-compute/src/variant_get.rs
@@ -2328,7 +2328,7 @@ mod test {
println!("Depth 1 (shredded) passed");
}
- /// Test depth 2: Double nested field access "a.b.x" with Int32 conversion
+ /// Test depth 2: Double nested field access "a.b.x" with Int32 conversion
/// Covers shredded vs non-shredded VariantArrays for deeply nested field
access
#[test]
fn test_depth_2_int32_conversion() {
diff --git a/parquet-variant-json/Cargo.toml b/parquet-variant-json/Cargo.toml
index 6ae6222da0..706446da0a 100644
--- a/parquet-variant-json/Cargo.toml
+++ b/parquet-variant-json/Cargo.toml
@@ -45,3 +45,6 @@ name = "parquet_variant_json"
bench = false
[dev-dependencies]
+
+[lints]
+workspace = true
diff --git a/parquet-variant/Cargo.toml b/parquet-variant/Cargo.toml
index c42a060794..ceb4cf2e5e 100644
--- a/parquet-variant/Cargo.toml
+++ b/parquet-variant/Cargo.toml
@@ -66,3 +66,6 @@ harness = false
[[bench]]
name = "variant_validation"
harness = false
+
+[lints]
+workspace = true
diff --git a/parquet-variant/src/builder/list.rs
b/parquet-variant/src/builder/list.rs
index 5064904ca7..4cbce2a093 100644
--- a/parquet-variant/src/builder/list.rs
+++ b/parquet-variant/src/builder/list.rs
@@ -24,7 +24,7 @@ use crate::{
use arrow_schema::ArrowError;
fn array_header(large: bool, offset_size: u8) -> u8 {
- let large_bit = if large { 1 } else { 0 };
+ let large_bit = u8::from(large);
(large_bit << (BASIC_TYPE_BITS + 2))
| ((offset_size - 1) << BASIC_TYPE_BITS)
| VariantBasicType::Array as u8
diff --git a/parquet-variant/src/utils.rs b/parquet-variant/src/utils.rs
index 61ae443d3f..33f65c4e2b 100644
--- a/parquet-variant/src/utils.rs
+++ b/parquet-variant/src/utils.rs
@@ -177,7 +177,7 @@ pub(crate) const fn expect_size_of<T>(expected: usize) {
/// - Trailing `.` (e.g., `"foo."`)
/// - Unclosed '[' (e.g., `"foo[1"`)
/// - Unexpected ']' (e.g., `"foo]"`)
-/// - Trailing '`' inside bracket (treated as unclosed bracket)
+/// - Trailing `\` inside bracket (treated as unclosed bracket)
#[inline]
pub(crate) fn parse_path(s: &str) -> Result<Vec<VariantPathElement<'_>>,
ArrowError> {
let scan_field = |start: usize| {
@@ -234,7 +234,7 @@ fn parse_in_bracket(s: &str, i: usize) ->
Result<(VariantPathElement<'_>, usize)
let start = i + 1; // skip '['
let mut unescaped = String::new();
- let mut chars = s[start..].char_indices().peekable();
+ let mut chars = s[start..].char_indices();
let mut end = None;
while let Some((offset, c)) = chars.next() {
diff --git a/parquet/Cargo.toml b/parquet/Cargo.toml
index d34fbb5e52..4e209b52ec 100644
--- a/parquet/Cargo.toml
+++ b/parquet/Cargo.toml
@@ -319,3 +319,6 @@ harness = false
[lib]
bench = false
+
+[lints]
+workspace = true
diff --git a/parquet/benches/metadata.rs b/parquet/benches/metadata.rs
index 24ac685131..8bbc017f71 100644
--- a/parquet/benches/metadata.rs
+++ b/parquet/benches/metadata.rs
@@ -15,6 +15,7 @@
// specific language governing permissions and limitations
// under the License.
+use std::fmt::Write as _;
use std::hint::black_box;
use std::sync::Arc;
@@ -47,7 +48,7 @@ fn encoded_meta(is_nullable: bool, has_lists: bool,
write_path_in_schema: bool)
let mut column_desc_ptrs: Vec<ColumnDescPtr> =
Vec::with_capacity(NUM_COLUMNS);
let mut message_type = "message test_schema {".to_string();
for i in 0..NUM_COLUMNS {
- message_type.push_str(&format!("REQUIRED FLOAT {};", i));
+ write!(message_type, "REQUIRED FLOAT {i};").ok();
column_desc_ptrs.push(ColumnDescPtr::new(ColumnDescriptor::new(
Arc::new(
SchemaType::primitive_type_builder(&i.to_string(),
PhysicalType::FLOAT)
diff --git a/parquet/examples/write_parquet.rs
b/parquet/examples/write_parquet.rs
index ebdd9527b6..803f29da38 100644
--- a/parquet/examples/write_parquet.rs
+++ b/parquet/examples/write_parquet.rs
@@ -109,7 +109,7 @@ fn main() -> Result<()> {
let mut array_builder = UInt64Builder::new();
let mut last_log = Instant::now();
for i in 0..args.iterations {
- if Instant::now() - last_log > Duration::new(10, 0) {
+ if last_log.elapsed() > Duration::new(10, 0) {
last_log = Instant::now();
eprintln!(
"{} Iteration {}/{}. RSS = {}",
diff --git a/parquet/src/arrow/arrow_reader/mod.rs
b/parquet/src/arrow/arrow_reader/mod.rs
index b41fdd111c..29ba9a4ab3 100644
--- a/parquet/src/arrow/arrow_reader/mod.rs
+++ b/parquet/src/arrow/arrow_reader/mod.rs
@@ -3693,9 +3693,7 @@ pub(crate) mod tests {
}
fn get_test_file(file_name: &str) -> File {
- let mut path = PathBuf::new();
- path.push(arrow::util::test_util::arrow_test_data());
- path.push(file_name);
+ let path =
PathBuf::from(arrow::util::test_util::arrow_test_data()).join(file_name);
File::open(path.as_path()).expect("File not found!")
}
diff --git a/parquet/src/arrow/arrow_reader/statistics.rs
b/parquet/src/arrow/arrow_reader/statistics.rs
index 66d437243f..755d7831ca 100644
--- a/parquet/src/arrow/arrow_reader/statistics.rs
+++ b/parquet/src/arrow/arrow_reader/statistics.rs
@@ -98,7 +98,7 @@ pub(crate) fn from_bytes_to_f16(b: &[u8]) -> Option<f16> {
macro_rules! make_stats_iterator {
($iterator_type:ident, $func:ident, $parquet_statistics_type:path,
$stat_value_type:ty) => {
/// Maps an iterator of `ParquetStatistics` into an iterator of
- /// `&$stat_value_type``
+ /// `&$stat_value_type`
///
/// Yielded elements:
/// * Some(stats) if valid
diff --git a/parquet/src/arrow/arrow_writer/levels.rs
b/parquet/src/arrow/arrow_writer/levels.rs
index efd77036a5..ead1ba0d9a 100644
--- a/parquet/src/arrow/arrow_writer/levels.rs
+++ b/parquet/src/arrow/arrow_writer/levels.rs
@@ -615,8 +615,8 @@ impl LevelInfoBuilder {
nulls: Option<&NullBuffer>,
range: Range<usize>,
) {
- let offsets = &offsets[range.start..range.end];
- let sizes = &sizes[range.start..range.end];
+ let offsets = &offsets[range.clone()];
+ let sizes = &sizes[range.clone()];
let write_non_null_slice =
|child: &mut LevelInfoBuilder, start_idx: usize, end_idx: usize| {
diff --git a/parquet/src/arrow/push_decoder/mod.rs
b/parquet/src/arrow/push_decoder/mod.rs
index ba075b4c08..93994071fc 100644
--- a/parquet/src/arrow/push_decoder/mod.rs
+++ b/parquet/src/arrow/push_decoder/mod.rs
@@ -2396,7 +2396,7 @@ mod test {
fn expect_needs_data<T: Debug>(
result: Result<DecodeResult<T>, ParquetError>,
) -> Vec<Range<u64>> {
- match result.expect("Expected Ok(DecodeResult::NeedsData{ranges})") {
+ match result.expect("Expected Ok(DecodeResult::NeedsData(ranges))") {
DecodeResult::NeedsData(ranges) => ranges,
result => panic!("Expected DecodeResult::NeedsData, got
{result:?}"),
}
diff --git a/parquet/src/arrow/schema/mod.rs b/parquet/src/arrow/schema/mod.rs
index f1d7ea7e88..500745c6e7 100644
--- a/parquet/src/arrow/schema/mod.rs
+++ b/parquet/src/arrow/schema/mod.rs
@@ -420,7 +420,7 @@ pub struct ArrowSchemaConverter<'a> {
schema_root: &'a str,
/// Should we coerce Arrow types to compatible Parquet types?
///
- /// See docs on [Self::with_coerce_types]`
+ /// See docs on [`Self::with_coerce_types`]
coerce_types: bool,
}
diff --git a/parquet/src/arrow/schema/primitive.rs
b/parquet/src/arrow/schema/primitive.rs
index c70885355d..2ca9b9b35e 100644
--- a/parquet/src/arrow/schema/primitive.rs
+++ b/parquet/src/arrow/schema/primitive.rs
@@ -183,7 +183,7 @@ fn check_decimal_length(type_length: i32) -> Result<()> {
fn from_int32(info: &BasicTypeInfo, scale: i32, precision: i32) ->
Result<DataType> {
match (info.logical_type_ref(), info.converted_type()) {
(None, ConvertedType::NONE) => Ok(DataType::Int32),
- (Some(ref t @ LogicalType::Integer(int)), _) => match (int.bit_width,
int.is_signed) {
+ (Some(t @ LogicalType::Integer(int)), _) => match (int.bit_width,
int.is_signed) {
(8, true) => Ok(DataType::Int8),
(16, true) => Ok(DataType::Int16),
(32, true) => Ok(DataType::Int32),
diff --git a/parquet/src/bin/parquet-fromcsv.rs
b/parquet/src/bin/parquet-fromcsv.rs
index f2d9d24d69..37a45cf03f 100644
--- a/parquet/src/bin/parquet-fromcsv.rs
+++ b/parquet/src/bin/parquet-fromcsv.rs
@@ -41,7 +41,7 @@
//! # Options
//!
//! ```text
-#![doc = include_str!("./parquet-fromcsv-help.txt")] // Update for this file :
Run test test_command_help
+#![cfg_attr(doc, doc = include_str!("./parquet-fromcsv-help.txt"))] // Update
for this file : Run test test_command_help
//! ```
//!
//! ## Parquet file options
@@ -434,10 +434,7 @@ mod tests {
fn test_command_help() {
let mut cmd = Args::command();
let dir = std::env::var("CARGO_MANIFEST_DIR").unwrap();
- let mut path_buf = PathBuf::from(dir);
- path_buf.push("src");
- path_buf.push("bin");
- path_buf.push("parquet-fromcsv-help.txt");
+ let path_buf =
PathBuf::from(dir).join("src/bin/parquet-fromcsv-help.txt");
let expected = std::fs::read_to_string(path_buf).unwrap();
let mut buffer_vec = Vec::new();
let mut buffer = std::io::Cursor::new(&mut buffer_vec);
@@ -522,7 +519,7 @@ mod tests {
}
#[test]
- #[should_panic]
+ #[should_panic(expected = "CommandLineParseError")]
fn test_parse_arg_format_error() {
parse_args(vec!["--input-format", "excel"]).unwrap();
}
diff --git a/parquet/src/column/chunker/cdc.rs
b/parquet/src/column/chunker/cdc.rs
index 3f5b6afece..2627d8921b 100644
--- a/parquet/src/column/chunker/cdc.rs
+++ b/parquet/src/column/chunker/cdc.rs
@@ -715,9 +715,7 @@ mod tests {
let num_levels = 20;
// def_level=1 means non-null, def_level=0 means null
// Pattern: null at indices 0, 3, 6, 9, 12, 15, 18 → 7 nulls, 13
non-null
- let def_levels: Vec<i16> = (0..num_levels)
- .map(|i| if i % 3 == 0 { 0 } else { 1 })
- .collect();
+ let def_levels: Vec<i16> = (0..num_levels).map(|i| i16::from(i % 3 !=
0)).collect();
let expected_non_null: usize = def_levels.iter().filter(|&&d| d ==
1).count();
let chunks = chunker.calculate(
diff --git a/parquet/src/column/writer/encoder.rs
b/parquet/src/column/writer/encoder.rs
index 094c7c26a0..9420aa40f7 100644
--- a/parquet/src/column/writer/encoder.rs
+++ b/parquet/src/column/writer/encoder.rs
@@ -69,7 +69,7 @@ pub struct DataPageValues<T> {
}
/// A generic encoder of [`ColumnValues`] to data and dictionary pages used by
-/// [super::GenericColumnWriter`]
+/// [`super::GenericColumnWriter`]
pub trait ColumnValueEncoder {
/// The underlying value type of [`Self::Values`]
///
diff --git a/parquet/src/column/writer/mod.rs b/parquet/src/column/writer/mod.rs
index d0a092a9c5..eb27af2cfb 100644
--- a/parquet/src/column/writer/mod.rs
+++ b/parquet/src/column/writer/mod.rs
@@ -4771,7 +4771,7 @@ mod tests {
let values =
page.iter().filter_map(Clone::clone).collect::<Vec<_>>();
let def_levels = page
.iter()
- .map(|maybe_value| if maybe_value.is_some() { 1 } else { 0 })
+ .map(|maybe_value| i16::from(maybe_value.is_some()))
.collect::<Vec<_>>();
writer.write_batch(&values, Some(&def_levels), None)?;
writer.flush_data_pages()?;
diff --git a/parquet/src/compression.rs b/parquet/src/compression.rs
index 6f3a18fe60..45b2b7edf9 100644
--- a/parquet/src/compression.rs
+++ b/parquet/src/compression.rs
@@ -20,7 +20,9 @@
//! See [`Compression`](crate::basic::Compression) enum for all available
compression
//! algorithms.
//!
-#[cfg_attr(
+// NOTE: this must be an inner attribute so that the example is attached to
the module (and
+// therefore actually run as a doc test) rather than to the `use` statement
below.
+#![cfg_attr(
feature = "experimental",
doc = r##"
# Example
diff --git a/parquet/src/errors.rs b/parquet/src/errors.rs
index 73b4d76de5..9064ff9cf4 100644
--- a/parquet/src/errors.rs
+++ b/parquet/src/errors.rs
@@ -163,6 +163,7 @@ impl From<ParquetError> for io::Error {
// Convenient macros for different errors
macro_rules! general_err {
+ ($fmt:literal) => (ParquetError::General(format!($fmt)));
($fmt:expr) => (ParquetError::General($fmt.to_owned()));
($fmt:expr, $($args:expr),*) => (ParquetError::General(format!($fmt,
$($args),*)));
($e:expr, $fmt:expr) => (ParquetError::General($fmt.to_owned(), $e));
@@ -171,17 +172,20 @@ macro_rules! general_err {
}
macro_rules! nyi_err {
+ ($fmt:literal) => (ParquetError::NYI(format!($fmt)));
($fmt:expr) => (ParquetError::NYI($fmt.to_owned()));
($fmt:expr, $($args:expr),*) => (ParquetError::NYI(format!($fmt,
$($args),*)));
}
macro_rules! eof_err {
+ ($fmt:literal) => (ParquetError::EOF(format!($fmt)));
($fmt:expr) => (ParquetError::EOF($fmt.to_owned()));
($fmt:expr, $($args:expr),*) => (ParquetError::EOF(format!($fmt,
$($args),*)));
}
#[cfg(feature = "arrow")]
macro_rules! arrow_err {
+ ($fmt:literal) => (ParquetError::ArrowError(format!($fmt)));
($fmt:expr) => (ParquetError::ArrowError($fmt.to_owned()));
($fmt:expr, $($args:expr),*) => (ParquetError::ArrowError(format!($fmt,
$($args),*)));
($e:expr, $fmt:expr) => (ParquetError::ArrowError($fmt.to_owned(), $e));
@@ -198,3 +202,25 @@ impl From<ParquetError> for ArrowError {
Self::ParquetError(format!("{p}"))
}
}
+
+#[cfg(test)]
+mod tests {
+ use super::*;
+
+ /// The single-argument arms of the error macros must format their
argument, so that
+ /// inline format arguments are not silently emitted as literal text.
+ #[test]
+ fn error_macros_format_inline_args() {
+ let expected = 1;
+ let actual = 2;
+ assert_eq!(
+ general_err!("expected {expected}, got {actual}").to_string(),
+ "Parquet error: expected 1, got 2"
+ );
+ assert_eq!(
+ nyi_err!("not yet: {expected}").to_string(),
+ "NYI: not yet: 1"
+ );
+ assert_eq!(eof_err!("eof at {actual}").to_string(), "EOF: eof at 2");
+ }
+}
diff --git a/parquet/src/file/metadata/push_decoder.rs
b/parquet/src/file/metadata/push_decoder.rs
index 7e4beb5ad9..de812b3e87 100644
--- a/parquet/src/file/metadata/push_decoder.rs
+++ b/parquet/src/file/metadata/push_decoder.rs
@@ -733,7 +733,7 @@ mod tests {
/// Expect that the [`DecodeResult`] is a [`DecodeResult::NeedsData`] and
return the corresponding ranges
fn expect_needs_data<T: Debug>(result: Result<DecodeResult<T>>) ->
Vec<Range<u64>> {
- match result.expect("Expected Ok(DecodeResult::NeedsData{ranges})") {
+ match result.expect("Expected Ok(DecodeResult::NeedsData(ranges))") {
DecodeResult::NeedsData(ranges) => ranges,
result => panic!("Expected DecodeResult::NeedsData, got
{result:?}"),
}
diff --git a/parquet/src/file/metadata/reader.rs
b/parquet/src/file/metadata/reader.rs
index d695610f20..3f0c2abeab 100644
--- a/parquet/src/file/metadata/reader.rs
+++ b/parquet/src/file/metadata/reader.rs
@@ -513,7 +513,7 @@ impl ParquetMetaDataReader {
remainder.slice(offset..end)
}
// Note: this will potentially fetch data already in remainder,
this keeps things simple
- _ => fetch.fetch(range.start..range.end).await?,
+ _ => fetch.fetch(range.clone()).await?,
};
// Sanity check
@@ -1209,7 +1209,6 @@ mod async_tests {
assert_eq!(fetch_count.load(Ordering::SeqCst), 0);
assert_eq!(suffix_fetch_count.load(Ordering::SeqCst), 2);
- dbg!("test");
// Metadata hint too large
fetch_count.store(0, Ordering::SeqCst);
suffix_fetch_count.store(0, Ordering::SeqCst);
diff --git a/parquet/src/file/writer.rs b/parquet/src/file/writer.rs
index 19de205be5..ddec0fdf21 100644
--- a/parquet/src/file/writer.rs
+++ b/parquet/src/file/writer.rs
@@ -1067,8 +1067,8 @@ impl<'a, W: Write> SerializedPageWriter<'a, W> {
fn page_encryptor_and_sink_mut(
&mut self,
- ) -> Option<(&mut PageEncryptor, &mut &'a mut TrackedWrite<W>)> {
- self.page_encryptor.as_mut().map(|pe| (pe, &mut self.sink))
+ ) -> Option<(&mut PageEncryptor, &mut TrackedWrite<W>)> {
+ self.page_encryptor.as_mut().map(|pe| (pe, &mut *self.sink))
}
}
@@ -1080,7 +1080,7 @@ impl<'a, W: Write> SerializedPageWriter<'a, W> {
fn page_encryptor_and_sink_mut(
&mut self,
- ) -> Option<(&mut PageEncryptor, &mut &'a mut TrackedWrite<W>)> {
+ ) -> Option<(&mut PageEncryptor, &mut TrackedWrite<W>)> {
None
}
}
diff --git a/parquet/src/parquet_thrift.rs b/parquet/src/parquet_thrift.rs
index 218194e0da..b8463ccc65 100644
--- a/parquet/src/parquet_thrift.rs
+++ b/parquet/src/parquet_thrift.rs
@@ -1024,7 +1024,7 @@ impl WriteThrift for String {
/// ```
///
/// which becomes in Rust
-/// ```no_run
+/// ```ignore
/// # struct OtherStruct {}
/// struct MyStruct {
/// field1: i32,
diff --git a/parquet/src/util/test_common/file_util.rs
b/parquet/src/util/test_common/file_util.rs
index 6c031358e7..30664d6338 100644
--- a/parquet/src/util/test_common/file_util.rs
+++ b/parquet/src/util/test_common/file_util.rs
@@ -15,13 +15,11 @@
// specific language governing permissions and limitations
// under the License.
-use std::{fs, path::PathBuf, str::FromStr};
+use std::{fs, path::PathBuf};
/// Returns path to the test parquet file in 'data' directory
pub fn get_test_path(file_name: &str) -> PathBuf {
- let mut pathbuf =
PathBuf::from_str(&arrow::util::test_util::parquet_test_data()).unwrap();
- pathbuf.push(file_name);
- pathbuf
+ PathBuf::from(arrow::util::test_util::parquet_test_data()).join(file_name)
}
/// Returns file handle for a test parquet file from 'data' directory
diff --git a/parquet/tests/arrow_reader/row_filter/async.rs
b/parquet/tests/arrow_reader/row_filter/async.rs
index fe16e426ea..059755cb7b 100644
--- a/parquet/tests/arrow_reader/row_filter/async.rs
+++ b/parquet/tests/arrow_reader/row_filter/async.rs
@@ -804,7 +804,7 @@ async fn test_multi_predicate_auto_mask_with_sparse_pages()
{
// filter_col: 0 for first and last 100 rows, 1 for middle 100 rows
// value_col: just row index
let filter_values: Vec<i32> = (0..num_rows as i32)
- .map(|i| if (100..200).contains(&i) { 1 } else { 0 })
+ .map(|i| i32::from((100..200).contains(&i)))
.collect();
let value_values: Vec<i32> = (0..num_rows as i32).collect();
diff --git a/parquet_derive/Cargo.toml b/parquet_derive/Cargo.toml
index 81565a4d6d..0855720628 100644
--- a/parquet_derive/Cargo.toml
+++ b/parquet_derive/Cargo.toml
@@ -41,3 +41,6 @@ parquet = { workspace = true }
[package.metadata.docs.rs]
all-features = true
+
+[lints]
+workspace = true
diff --git a/parquet_derive_test/Cargo.toml b/parquet_derive_test/Cargo.toml
index 168d10891d..b7d10ab398 100644
--- a/parquet_derive_test/Cargo.toml
+++ b/parquet_derive_test/Cargo.toml
@@ -36,3 +36,6 @@ uuid = { version = "1", features = ["v4"] }
[package.metadata.docs.rs]
all-features = true
+
+[lints]
+workspace = true
diff --git a/parquet_derive_test/src/lib.rs b/parquet_derive_test/src/lib.rs
index e8462874f3..c18b1c1c49 100644
--- a/parquet_derive_test/src/lib.rs
+++ b/parquet_derive_test/src/lib.rs
@@ -15,6 +15,8 @@
// specific language governing permissions and limitations
// under the License.
+//! Tests for the `parquet_derive` procedural macros.
+
#![doc(
html_logo_url =
"https://raw.githubusercontent.com/apache/parquet-format/25f05e73d8cd7f5c83532ce51cb4f4de8ba5f2a2/logo/parquet-logos_1.svg";,
html_favicon_url =
"https://raw.githubusercontent.com/apache/parquet-format/25f05e73d8cd7f5c83532ce51cb4f4de8ba5f2a2/logo/parquet-logos_1.svg";
@@ -446,12 +448,9 @@ mod tests {
/// Returns file handle for a temp file in 'target' directory with a
provided content
pub fn get_temp_file(file_name: &str, content: &[u8]) -> fs::File {
// build tmp path to a file in "target/debug/testdata"
- let mut path_buf = env::current_dir().unwrap();
- path_buf.push("target");
- path_buf.push("debug");
- path_buf.push("testdata");
- fs::create_dir_all(&path_buf).unwrap();
- path_buf.push(file_name);
+ let dir = env::current_dir().unwrap().join("target/debug/testdata");
+ fs::create_dir_all(&dir).unwrap();
+ let path_buf = dir.join(file_name);
// write file content
let mut tmp_file = fs::File::create(path_buf.as_path()).unwrap();
![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}