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 4ff867b507 chore: update workspace Rust toolchain to 1.96.1 (#10257)
4ff867b507 is described below
commit 4ff867b50778241c02fe0d8cc03f13c49277acdd
Author: Andrew Lamb <[email protected]>
AuthorDate: Thu Jul 2 06:38:09 2026 -0400
chore: update workspace Rust toolchain to 1.96.1 (#10257)
# Which issue does this PR close?
N/A
# Rationale for this change
The repository toolchain pin was still on Rust 1.91, while the current
stable toolchain is Rust 1.96.1.
Changes to `rust-toolchain.toml` also affect the full workspace, but the
path-filtered crate workflows did not run for toolchain-only PRs. Those
workflow filters should treat toolchain changes as broad CI-impacting
changes.
# What changes are included in this PR?
Updates `rust-toolchain.toml` from `1.91` to `1.96.1`.
Adds `rust-toolchain.toml` to the `pull_request.paths` filters for the
crate and audit workflows so toolchain updates trigger the full suite
instead of only the unfiltered workflows.
Addresses Clippy lints surfaced by Rust 1.96.1.
# Are these changes tested?
No tests added; this updates CI metadata and the pinned Rust toolchain.
# Are there any user-facing changes?
No runtime or API behavior changes.
---
.github/workflows/arrow.yml | 1 +
.github/workflows/arrow_flight.yml | 1 +
.github/workflows/audit.yml | 1 +
.github/workflows/integration.yml | 1 +
.github/workflows/miri.yaml | 1 +
.github/workflows/parquet-geospatial.yml | 1 +
.github/workflows/parquet-variant.yml | 1 +
.github/workflows/parquet.yml | 1 +
.github/workflows/parquet_derive.yml | 1 +
arrow-array/src/array/run_array.rs | 2 +-
arrow-avro/src/reader/mod.rs | 20 +++------
arrow-flight/src/sql/metadata/mod.rs | 2 +-
arrow-json/src/reader/tape.rs | 2 +-
arrow-ord/src/sort.rs | 1 -
arrow/benches/lexsort.rs | 2 +-
.../arrow/array_reader/byte_array_dictionary.rs | 2 +-
parquet/src/arrow/arrow_writer/mod.rs | 12 ++---
parquet/src/arrow/in_memory_row_group.rs | 2 +-
parquet/src/encryption/decrypt.rs | 2 +-
parquet/src/file/page_index/column_index.rs | 52 +++++++---------------
parquet/src/util/push_buffers.rs | 2 +-
parquet/tests/encryption/encryption.rs | 4 +-
rust-toolchain.toml | 2 +-
23 files changed, 50 insertions(+), 66 deletions(-)
diff --git a/.github/workflows/arrow.yml b/.github/workflows/arrow.yml
index cb9a6efcab..fd70152134 100644
--- a/.github/workflows/arrow.yml
+++ b/.github/workflows/arrow.yml
@@ -30,6 +30,7 @@ on:
pull_request:
paths:
- .github/**
+ - rust-toolchain.toml
- arrow-arith/**
- arrow-array/**
- arrow-buffer/**
diff --git a/.github/workflows/arrow_flight.yml
b/.github/workflows/arrow_flight.yml
index fd8bd2dadd..a0c417e46f 100644
--- a/.github/workflows/arrow_flight.yml
+++ b/.github/workflows/arrow_flight.yml
@@ -30,6 +30,7 @@ on:
- main
pull_request:
paths:
+ - rust-toolchain.toml
- arrow-array/**
- arrow-buffer/**
- arrow-cast/**
diff --git a/.github/workflows/audit.yml b/.github/workflows/audit.yml
index a206c350ea..6d90dddf3b 100644
--- a/.github/workflows/audit.yml
+++ b/.github/workflows/audit.yml
@@ -30,6 +30,7 @@ on:
paths:
- '**/Cargo.toml'
- '**/Cargo.lock'
+ - rust-toolchain.toml
jobs:
cargo-audit:
diff --git a/.github/workflows/integration.yml
b/.github/workflows/integration.yml
index 4065ed0b06..68d9b46e29 100644
--- a/.github/workflows/integration.yml
+++ b/.github/workflows/integration.yml
@@ -29,6 +29,7 @@ on:
pull_request:
paths:
- .github/**
+ - rust-toolchain.toml
- arrow-array/**
- arrow-buffer/**
- arrow-cast/**
diff --git a/.github/workflows/miri.yaml b/.github/workflows/miri.yaml
index 36285bc2fa..aa3b22ce0d 100644
--- a/.github/workflows/miri.yaml
+++ b/.github/workflows/miri.yaml
@@ -29,6 +29,7 @@ on:
pull_request:
paths:
- .github/**
+ - rust-toolchain.toml
- arrow-array/**
- arrow-buffer/**
- arrow-cast/**
diff --git a/.github/workflows/parquet-geospatial.yml
b/.github/workflows/parquet-geospatial.yml
index 201790339e..89cf63f535 100644
--- a/.github/workflows/parquet-geospatial.yml
+++ b/.github/workflows/parquet-geospatial.yml
@@ -31,6 +31,7 @@ on:
pull_request:
paths:
- parquet-geospatial/**
+ - rust-toolchain.toml
- .github/**
jobs:
diff --git a/.github/workflows/parquet-variant.yml
b/.github/workflows/parquet-variant.yml
index 51858f0898..5dca4cca5b 100644
--- a/.github/workflows/parquet-variant.yml
+++ b/.github/workflows/parquet-variant.yml
@@ -33,6 +33,7 @@ on:
- parquet-variant/**
- parquet-variant-json/**
- parquet-variant-compute/**
+ - rust-toolchain.toml
- .github/**
jobs:
diff --git a/.github/workflows/parquet.yml b/.github/workflows/parquet.yml
index 03d7e599fe..dcc78f8be6 100644
--- a/.github/workflows/parquet.yml
+++ b/.github/workflows/parquet.yml
@@ -30,6 +30,7 @@ on:
- main
pull_request:
paths:
+ - rust-toolchain.toml
- arrow/**
- arrow-array/**
- arrow-buffer/**
diff --git a/.github/workflows/parquet_derive.yml
b/.github/workflows/parquet_derive.yml
index c2b3083f6f..28ed4a1ebb 100644
--- a/.github/workflows/parquet_derive.yml
+++ b/.github/workflows/parquet_derive.yml
@@ -33,6 +33,7 @@ on:
- parquet/**
- parquet_derive/**
- parquet_derive_test/**
+ - rust-toolchain.toml
- .github/**
jobs:
diff --git a/arrow-array/src/array/run_array.rs
b/arrow-array/src/array/run_array.rs
index 09fb2998a2..9a56b01fca 100644
--- a/arrow-array/src/array/run_array.rs
+++ b/arrow-array/src/array/run_array.rs
@@ -1183,7 +1183,7 @@ mod tests {
// create run array using input_array
let mut builder = PrimitiveRunBuilder::<Int32Type,
Int32Type>::new();
- builder.extend(input_array.clone().into_iter());
+ builder.extend(input_array.clone());
let run_array = builder.finish();
let physical_values_array =
run_array.values().as_primitive::<Int32Type>();
diff --git a/arrow-avro/src/reader/mod.rs b/arrow-avro/src/reader/mod.rs
index 6dbf5b1553..c837398164 100644
--- a/arrow-avro/src/reader/mod.rs
+++ b/arrow-avro/src/reader/mod.rs
@@ -6808,14 +6808,8 @@ mod test {
.unwrap();
// First row should be "ACTIVE", second row should be "PENDING"
- assert_eq!(
- status_values.value(status_col.key(0).unwrap() as usize),
- "ACTIVE"
- );
- assert_eq!(
- status_values.value(status_col.key(1).unwrap() as usize),
- "PENDING"
- );
+ assert_eq!(status_values.value(status_col.key(0).unwrap()), "ACTIVE");
+ assert_eq!(status_values.value(status_col.key(1).unwrap()), "PENDING");
// Get backupStatus enum values (same as status)
let backup_status_col = batch
@@ -6831,11 +6825,11 @@ mod test {
// First row should be "INACTIVE", second row should be "ACTIVE"
assert_eq!(
- backup_status_values.value(backup_status_col.key(0).unwrap() as
usize),
+ backup_status_values.value(backup_status_col.key(0).unwrap()),
"INACTIVE"
);
assert_eq!(
- backup_status_values.value(backup_status_col.key(1).unwrap() as
usize),
+ backup_status_values.value(backup_status_col.key(1).unwrap()),
"ACTIVE"
);
@@ -6862,15 +6856,15 @@ mod test {
// First row: ["PENDING", "ACTIVE", "INACTIVE"]
assert_eq!(first_array_dict_array.len(), 3);
assert_eq!(
- first_array_values.value(first_array_dict_array.key(0).unwrap() as
usize),
+ first_array_values.value(first_array_dict_array.key(0).unwrap()),
"PENDING"
);
assert_eq!(
- first_array_values.value(first_array_dict_array.key(1).unwrap() as
usize),
+ first_array_values.value(first_array_dict_array.key(1).unwrap()),
"ACTIVE"
);
assert_eq!(
- first_array_values.value(first_array_dict_array.key(2).unwrap() as
usize),
+ first_array_values.value(first_array_dict_array.key(2).unwrap()),
"INACTIVE"
);
}
diff --git a/arrow-flight/src/sql/metadata/mod.rs
b/arrow-flight/src/sql/metadata/mod.rs
index 66c12fce9a..b914cd3823 100644
--- a/arrow-flight/src/sql/metadata/mod.rs
+++ b/arrow-flight/src/sql/metadata/mod.rs
@@ -57,7 +57,7 @@ fn lexsort_to_indices(arrays: &[ArrayRef]) -> UInt32Array {
let converter = RowConverter::new(fields).unwrap();
let rows = converter.convert_columns(arrays).unwrap();
let mut sort: Vec<_> = rows.iter().enumerate().collect();
- sort.sort_unstable_by(|(_, a), (_, b)| a.cmp(b));
+ sort.sort_unstable_by_key(|(_, a)| *a);
UInt32Array::from_iter_values(sort.iter().map(|(i, _)| *i as u32))
}
diff --git a/arrow-json/src/reader/tape.rs b/arrow-json/src/reader/tape.rs
index 89ee3f7787..d332951349 100644
--- a/arrow-json/src/reader/tape.rs
+++ b/arrow-json/src/reader/tape.rs
@@ -691,7 +691,7 @@ impl Iterator for BufIter<'_> {
}
fn size_hint(&self) -> (usize, Option<usize>) {
- let s = self.buf.len().checked_sub(self.pos).unwrap_or_default();
+ let s = self.buf.len().saturating_sub(self.pos);
(s, Some(s))
}
}
diff --git a/arrow-ord/src/sort.rs b/arrow-ord/src/sort.rs
index 3156063480..55e517c54e 100644
--- a/arrow-ord/src/sort.rs
+++ b/arrow-ord/src/sort.rs
@@ -5292,7 +5292,6 @@ mod tests {
let remaining = length - current_len;
for _ in 0..remaining {
result.push(rng.random_range('a'..='z'));
- current_len += 1;
}
break;
}
diff --git a/arrow/benches/lexsort.rs b/arrow/benches/lexsort.rs
index 16a2606b91..7061973fae 100644
--- a/arrow/benches/lexsort.rs
+++ b/arrow/benches/lexsort.rs
@@ -141,7 +141,7 @@ fn do_bench(c: &mut Criterion, columns: &[Column], len:
usize) {
let converter = RowConverter::new(fields).unwrap();
let rows = converter.convert_columns(&arrays).unwrap();
let mut sort: Vec<_> = rows.iter().enumerate().collect();
- sort.sort_unstable_by(|(_, a), (_, b)| a.cmp(b));
+ sort.sort_unstable_by_key(|(_, a)| *a);
UInt32Array::from_iter_values(sort.iter().map(|(i, _)| *i as
u32))
})
})
diff --git a/parquet/src/arrow/array_reader/byte_array_dictionary.rs
b/parquet/src/arrow/array_reader/byte_array_dictionary.rs
index dfd44a8efa..65f2d9cb0a 100644
--- a/parquet/src/arrow/array_reader/byte_array_dictionary.rs
+++ b/parquet/src/arrow/array_reader/byte_array_dictionary.rs
@@ -43,7 +43,7 @@ macro_rules! make_reader {
$(($key_arrow:pat, $value_arrow:pat) => ($key_type:ty,
$value_type:ty),)+
}
) => {
- match (($k, $v)) {
+ match ($k, $v) {
$(
($key_arrow, $value_arrow) => {
let mut reader = GenericRecordReader::new($column_desc,
$batch_size);
diff --git a/parquet/src/arrow/arrow_writer/mod.rs
b/parquet/src/arrow/arrow_writer/mod.rs
index 063d5abcf1..e985c183ed 100644
--- a/parquet/src/arrow/arrow_writer/mod.rs
+++ b/parquet/src/arrow/arrow_writer/mod.rs
@@ -389,11 +389,13 @@ impl<W: Write + Send> ArrowWriter<W> {
return self.write(batch);
}
- let avg_row_bytes = current_bytes / in_progress.buffered_rows;
- if avg_row_bytes > 0 {
+ if let Some(avg_row_bytes) = current_bytes
+ .checked_div(in_progress.buffered_rows)
+ .filter(|avg_row_bytes| *avg_row_bytes > 0)
+ {
// At this point, `current_bytes < max_bytes` (checked
above)
let remaining_bytes = max_bytes - current_bytes;
- let rows_that_fit = remaining_bytes / avg_row_bytes;
+ let rows_that_fit =
remaining_bytes.checked_div(avg_row_bytes).unwrap_or(0);
if batch.num_rows() > rows_that_fit {
if rows_that_fit > 0 {
@@ -4356,7 +4358,7 @@ mod tests {
// check values roundtrip through parquet
let src = [
u32::MIN,
- u32::MIN + 1,
+ 1,
(i32::MAX as u32) - 1,
i32::MAX as u32,
(i32::MAX as u32) + 1,
@@ -4402,7 +4404,7 @@ mod tests {
// check values roundtrip through parquet
let src = [
u64::MIN,
- u64::MIN + 1,
+ 1,
(i64::MAX as u64) - 1,
i64::MAX as u64,
(i64::MAX as u64) + 1,
diff --git a/parquet/src/arrow/in_memory_row_group.rs
b/parquet/src/arrow/in_memory_row_group.rs
index 4baa8cf9de..6c5f013159 100644
--- a/parquet/src/arrow/in_memory_row_group.rs
+++ b/parquet/src/arrow/in_memory_row_group.rs
@@ -165,7 +165,7 @@ impl InMemoryRowGroup<'_> {
data: offsets
.into_iter()
.map(|x| x as usize)
- .zip(chunks.into_iter())
+ .zip(chunks)
.collect(),
}))
}
diff --git a/parquet/src/encryption/decrypt.rs
b/parquet/src/encryption/decrypt.rs
index bfa5872779..3e42664d58 100644
--- a/parquet/src/encryption/decrypt.rs
+++ b/parquet/src/encryption/decrypt.rs
@@ -507,7 +507,7 @@ impl DecryptionPropertiesBuilder {
keys.len()
));
}
- for (column_name, key) in
column_names.into_iter().zip(keys.into_iter()) {
+ for (column_name, key) in column_names.into_iter().zip(keys) {
self.column_keys.insert(column_name.to_string(), key);
}
Ok(self)
diff --git a/parquet/src/file/page_index/column_index.rs
b/parquet/src/file/page_index/column_index.rs
index 9613292825..2f90b3d8e5 100644
--- a/parquet/src/file/page_index/column_index.rs
+++ b/parquet/src/file/page_index/column_index.rs
@@ -278,25 +278,15 @@ impl<T: ParquetValueType> WriteThrift for
PrimitiveColumnIndex<T> {
max.write_thrift(writer)?;
}
let mut last_field_id = self.boundary_order.write_thrift_field(writer,
4, 3)?;
- if self.null_counts.is_some() {
+ if let Some(null_counts) = &self.null_counts {
+ last_field_id = null_counts.write_thrift_field(writer, 5,
last_field_id)?;
+ }
+ if let Some(repetition_level_histograms) =
&self.repetition_level_histograms {
last_field_id =
- self.null_counts
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 5, last_field_id)?;
- }
- if self.repetition_level_histograms.is_some() {
- last_field_id = self
- .repetition_level_histograms
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 6, last_field_id)?;
- }
- if self.definition_level_histograms.is_some() {
- self.definition_level_histograms
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 7, last_field_id)?;
+ repetition_level_histograms.write_thrift_field(writer, 6,
last_field_id)?;
+ }
+ if let Some(definition_level_histograms) =
&self.definition_level_histograms {
+ definition_level_histograms.write_thrift_field(writer, 7,
last_field_id)?;
}
writer.write_struct_end()
}
@@ -487,25 +477,15 @@ impl WriteThrift for ByteArrayColumnIndex {
max.write_thrift(writer)?;
}
let mut last_field_id = self.boundary_order.write_thrift_field(writer,
4, 3)?;
- if self.null_counts.is_some() {
+ if let Some(null_counts) = &self.null_counts {
+ last_field_id = null_counts.write_thrift_field(writer, 5,
last_field_id)?;
+ }
+ if let Some(repetition_level_histograms) =
&self.repetition_level_histograms {
last_field_id =
- self.null_counts
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 5, last_field_id)?;
- }
- if self.repetition_level_histograms.is_some() {
- last_field_id = self
- .repetition_level_histograms
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 6, last_field_id)?;
- }
- if self.definition_level_histograms.is_some() {
- self.definition_level_histograms
- .as_ref()
- .unwrap()
- .write_thrift_field(writer, 7, last_field_id)?;
+ repetition_level_histograms.write_thrift_field(writer, 6,
last_field_id)?;
+ }
+ if let Some(definition_level_histograms) =
&self.definition_level_histograms {
+ definition_level_histograms.write_thrift_field(writer, 7,
last_field_id)?;
}
writer.write_struct_end()
}
diff --git a/parquet/src/util/push_buffers.rs b/parquet/src/util/push_buffers.rs
index be245b3359..32c9ba8304 100644
--- a/parquet/src/util/push_buffers.rs
+++ b/parquet/src/util/push_buffers.rs
@@ -99,7 +99,7 @@ impl PushBuffers {
buffers.len(),
"Number of ranges must match number of buffers"
);
- for (range, buffer) in ranges.into_iter().zip(buffers.into_iter()) {
+ for (range, buffer) in ranges.into_iter().zip(buffers) {
self.push_range(range, buffer);
}
}
diff --git a/parquet/tests/encryption/encryption.rs
b/parquet/tests/encryption/encryption.rs
index 2ac94b8c37..2b4a438b61 100644
--- a/parquet/tests/encryption/encryption.rs
+++ b/parquet/tests/encryption/encryption.rs
@@ -594,7 +594,7 @@ fn uniform_encryption_roundtrip(
let mut writer = ArrowWriter::try_new(file.try_clone()?, schema.clone(),
Some(props))?;
- for (x0, x1) in x0_arrays.into_iter().zip(x1_arrays.into_iter()) {
+ for (x0, x1) in x0_arrays.into_iter().zip(x1_arrays) {
let batch = RecordBatch::try_new(schema.clone(), vec![Arc::new(x0),
Arc::new(x1)])?;
writer.write(&batch)?;
}
@@ -698,7 +698,7 @@ fn uniform_encryption_page_skipping(page_index: bool) ->
parquet::errors::Result
let mut writer = ArrowWriter::try_new(file.try_clone()?, schema.clone(),
Some(props))?;
- for (x0, x1) in x0_arrays.into_iter().zip(x1_arrays.into_iter()) {
+ for (x0, x1) in x0_arrays.into_iter().zip(x1_arrays) {
let batch = RecordBatch::try_new(schema.clone(), vec![Arc::new(x0),
Arc::new(x1)])?;
writer.write(&batch)?;
}
diff --git a/rust-toolchain.toml b/rust-toolchain.toml
index 6d6e1bfb10..a6ca9ead37 100644
--- a/rust-toolchain.toml
+++ b/rust-toolchain.toml
@@ -16,5 +16,5 @@
# under the License.
[toolchain]
-channel = "1.91"
+channel = "1.96.1"
components = ["rustfmt", "clippy"]
