This is an automated email from the ASF dual-hosted git repository.
Jefffrey pushed a change to branch
dependabot/rust_toolchain/rust-toolchain-1.98.0
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
from 7602b1711b fix clippy
add ff4d74f2f2 chore(deps): bump comfy-table from 7.2.2 to 8.0.0 (#10610)
add bab409b82d fix(ffi): report the producer's C stream error message,
don't unwrap it (#10844)
add 0a8fdd505b perf: Write compressed directly to buffer (#10833)
add aa9b9231c2 docs(arrow-data): Document how `ArrayData::offset` applies
to buffers, child_data and nulls (#10838)
add 98deaf182e Replace BufferBuilder with Vec in cast_byte_container
(#10867)
add 579ccf1a49 fix: Avoid spurious assert when Parquet decimal has scale
== precision (#10875)
add 802a7263a2 chore(deps): bump crc32fast from 1.5.0 to 1.5.1 in the
all-other-cargo-deps group across 1 directory (#10858)
add 590116a536 chore(deps): bump taiki-e/install-action from 2.86.5 to
2.86.6 (#10856)
add bb0d497b75 fix: casting Decimal256 to signed integers returned wrong
results (#10857)
add 2ea4a7348d introduce union and REE take benchmarks (#10819)
add 14a5d7b8af docs : add saftey comments to unsafe callsites (#10839)
add b266024a8c feat(parquet): support round-trip of Dictionary(_,
Utf8View/BinaryView) columns (#10831)
add 5d087d0d62 fix: Correctly decode zero-valued Decimal256s in
integration tests (#10873)
add 7e65400964 docs : add safety comments (#10843)
add 1e63aff3fd chore(deps): bump taiki-e/install-action from 2.86.6 to
2.86.7 (#10886)
add 4ae884085e chore(deps): bump syn from 3.0.3 to 3.0.4 in the
all-other-cargo-deps group across 1 directory (#10887)
add 268d9a8081 chore: Forward port `59.3.0` CHANGELOG to main (#10870)
add 0be3a5f636 bench(parquet): add wide-schema writer benchmark with
repeated batches (#10878)
add ddd210b38d Improve arrow-avro decoding for one-record messages (#10713)
add 7c6e3ad80c chore: change gh action dependabot update schedule to
weekly (#10888)
add 4cc296bca1 fix: Avoid incorrect min/max stats for BYTE_ARRAY decimals
of unequal byte lengths (#10861)
add 0b0f7cc05d docs: provide performance guide for primitive (#10895)
add ef94f4fa20 add const generic to take kernel (#10820)
add 9500647b24 fix(variant): accept Dictionary and RunEndEncoded metadata
in VariantArray (#10810)
add e6a059d714 perf : optimize take(fixed_sized_list) (#10441)
add edd277530b fix: Reject decimal arrays with different scales in
`make_comparator` (#10864)
add 27f68b1659 docs: update primitive docs to focus on vec<T> (#10898)
add 2c50074ca7 perf(arrow-array): compile array `Debug` formatting helpers
once, not per primitive type (~2% binary size reduction) (#10890)
add 34b49efced perf: Use interleave for fragmented zip masks (#10368)
add 25adb3be20 perf(take): avoid bounds checks and speed up take on
List<T> (#10812)
add 15449e9447 fix: Correct two bugs when formatting decimal values
(#10869)
add 684d64a580 Add `OffsetBuffer::first`/`last` to always return offset &
remove some `unwrap`s (#10759)
add 4962d38422 chore: ensure miri ignores are properly commented, add
guidelines (#10884)
add 558c5fec9f perf(arrow-array): Reduce binary size 0.5%: do
`PrimitiveArray` → `ArrayData` conversion once, not per type (#10893)
add 0219b5b754 Parquet: Make page index decoders public (#10899)
add 07ec038b6a enable miri workflow for parquet crate (#10803)
add cbbb56bba1 bench: byte view rank collisions (#10772)
add baa4bd3a3b Fix take on zero-width FixedSizeListArray (#10915)
add 70fa5bcf21 Fix FFI import of zero-length `Utf8`/`Binary` arrays at a
non-zero offset (#10916)
add 71cd3239ad dep: update chacha20 to 0.10.2 (#10922)
add 51690ed69d [Variant] Skip UTF-8 revalidation when reading validated
metadata dictionary entries (#10879)
add 5fa7c8cc10 perf(parquet): resolve per-column writer properties once
per column (#10880)
add 8a6ce46c29 parquet: introduce `FILE` logical type (#10109)
add 1c7f002e02 fix(arrow-avro): preserve object_store error source in the
async reader (#10496)
add 0aece99d08 fix(arrow-select): treat null take indices as null for
dense union and REE (#10909)
add 27a6a40879 chore: fix missing code block endings (#10918)
add cbd0e02f96 Return errors instead of panicking in fallible functions
(#10755)
add 59eeb442a6 perf: optimize `rank` for byte views via caching prefix
keys (#10605)
add 65662e2582 chore(deps): bump the all-other-cargo-deps group across 1
directory with 3 updates (#10928)
add c44f8d4c2f fix(arrow-data): don't double-count offset when slicing
struct ArrayData (#10835)
add f0c2de7ede chore(deps): bump taiki-e/install-action from 2.86.7 to
2.87.1 (#10937)
add 000a7fd32e Enable five more clippy lints (#10935)
add 70219af2ff fix: Consolidate string-to-decimal parsing into a single
code path (#10850)
add 8f03078eb6 docs + feature : Introduce schemaBuilder::project + make
better docs (#10924)
add 0dc1e46c1a Benches: introduce null_expand benchmarks (#10942)
add 1c7830d6c8 chore: fix typos in code comments (#10943)
add da1e0bc5fe chore(deps): bump indexmap from 2.14.0 to 2.14.1 in the
all-other-cargo-deps group across 1 directory (#10940)
add e1bdc31e69 chore(deps): bump the codeql-actions group with 2 updates
(#10936)
add bd4d32bbd7 fix(arrow-avro): decode records with no fields (#10771)
add c6f031305b perf: optimize take bool & take null buffers (#10813)
add 2a1ba4107f Add new parquet tests based on updated variant/json files
(#10785)
add 98ad0f31b0 feat(arrow-buffer): add `OverflowError` and fallible offset
constructors (#10736)
add 6e728ced77 Fix pool claim race condition (#10301)
add a381897ff0 arith: fallback to dividing decimals digitwise when regular
scale into div overflows (#10911)
add b84fc5cfa9 Json decoder factory (#10670)
add 027b45f2a9 fix(arrow-data): account for struct parent offsets (#10934)
add 8c49c7132f chore: Fix typos (#10956)
add f12c5045e8 chore: Improve `decimal` benchmark coverage (#10954)
add c134baf8fc Add `ARROW_VERSION` const to arrow-array (#10957)
add 9a8400ea86 fix(arrow-buffer): prevent use-after-free in
Buffer::shrink_to_fit when MemoryReservation::resize panics (#10932)
add 300c77250e fix(arrow-avro): reset union offsets after flush (#10971)
add 0561057333 chore: cut down amount of zip benchmarks (#10919)
add 32ff76c48f Remove `force_validate` feature from `arrow-cast` (#10950)
add 58f818dd6a feature: introduce typo check ci job (#10960)
add ec21627533 perf(arrow-array): speed up `RunArray::try_new` by avoiding
the `ArrayData` roundtrip (#10807)
add 3e89669636 fix(arrow-array): align FFI buffers before validation under
force_validate (#10798)
add bcd963ecdc Merge branch 'main' into
dependabot/rust_toolchain/rust-toolchain-1.98.0
add ed6dd90667 bump to rust 1.98.1
No new revisions were added by this update.
Summary of changes:
.github/ci/scripts/typos_check.sh | 69 ++
.github/dependabot.yml | 2 +-
.github/workflows/audit.yml | 2 +-
.github/workflows/codeql.yml | 4 +-
.github/workflows/dev.yml | 16 +
.github/workflows/miri.sh | 3 +-
.github/workflows/miri.yaml | 8 +-
.github/workflows/rust.yml | 2 +-
CHANGELOG-old.md | 74 ++
CHANGELOG.md | 75 +-
CONTRIBUTING.md | 77 ++
Cargo.lock | 64 +-
Cargo.toml | 5 -
arrow-arith/src/arity.rs | 2 +-
arrow-arith/src/boolean.rs | 1 +
arrow-arith/src/numeric.rs | 167 ++-
arrow-array/Cargo.toml | 2 +-
arrow-array/src/array/boolean_array.rs | 4 +-
arrow-array/src/array/byte_array.rs | 14 +-
arrow-array/src/array/byte_view_array.rs | 9 +-
arrow-array/src/array/fixed_size_binary_array.rs | 9 +-
arrow-array/src/array/fixed_size_list_array.rs | 4 +-
arrow-array/src/array/list_array.rs | 6 +-
arrow-array/src/array/list_view_array.rs | 4 +-
arrow-array/src/array/map_array.rs | 8 +-
arrow-array/src/array/mod.rs | 19 +-
arrow-array/src/array/null_array.rs | 2 +-
arrow-array/src/array/primitive_array.rs | 181 ++--
arrow-array/src/array/run_array.rs | 70 +-
arrow-array/src/array/struct_array.rs | 157 ++-
arrow-array/src/array/union_array.rs | 11 +-
arrow-array/src/builder/boolean_builder.rs | 2 +
arrow-array/src/builder/buffer_builder.rs | 24 +-
.../src/builder/fixed_size_binary_builder.rs | 2 +
.../fixed_size_binary_dictionary_builder.rs | 13 +-
arrow-array/src/builder/generic_bytes_builder.rs | 2 +
.../builder/generic_bytes_dictionary_builder.rs | 13 +-
.../src/builder/generic_bytes_view_builder.rs | 27 +-
.../src/builder/generic_list_view_builder.rs | 2 +-
arrow-array/src/builder/map_builder.rs | 1 +
arrow-array/src/builder/null_builder.rs | 2 +
arrow-array/src/builder/primitive_builder.rs | 60 +-
.../src/builder/primitive_dictionary_builder.rs | 14 +-
arrow-array/src/builder/union_builder.rs | 2 +
arrow-array/src/delta.rs | 6 +-
arrow-array/src/ffi.rs | 156 ++-
arrow-array/src/ffi_stream.rs | 188 +++-
arrow-array/src/lib.rs | 3 +
arrow-array/src/scalar.rs | 3 +-
arrow-array/src/temporal_conversions.rs | 41 +-
arrow-array/src/types.rs | 10 +-
arrow-avro/README.md | 7 +-
arrow-avro/benches/decoder.rs | 37 +
arrow-avro/benches/project_record.rs | 2 +-
arrow-avro/src/errors.rs | 12 +
arrow-avro/src/lib.rs | 46 +-
arrow-avro/src/reader/async_reader/builder.rs | 9 +-
arrow-avro/src/reader/async_reader/store.rs | 57 +-
arrow-avro/src/reader/header.rs | 2 +-
arrow-avro/src/reader/mod.rs | 483 ++++++++-
arrow-avro/src/reader/record.rs | 470 ++++++---
arrow-buffer/src/bigint/mod.rs | 86 +-
arrow-buffer/src/buffer/immutable.rs | 77 +-
arrow-buffer/src/buffer/mutable.rs | 52 +-
arrow-buffer/src/buffer/null.rs | 26 +-
arrow-buffer/src/buffer/offset.rs | 178 +++-
arrow-buffer/src/buffer/run.rs | 20 +-
arrow-buffer/src/builder/boolean.rs | 18 +-
arrow-buffer/src/builder/null.rs | 29 +-
arrow-buffer/src/builder/offset.rs | 76 +-
arrow-buffer/src/bytes.rs | 33 +-
arrow-buffer/src/error.rs | 89 ++
arrow-buffer/src/lib.rs | 3 +
arrow-buffer/src/pool.rs | 138 ++-
arrow-buffer/src/util/bit_chunk_iterator.rs | 9 +-
arrow-buffer/src/util/bit_mask.rs | 4 +
arrow-buffer/src/util/bit_util.rs | 9 +
arrow-cast/Cargo.toml | 4 +-
arrow-cast/benches/parse_decimal.rs | 124 ++-
arrow-cast/src/base64.rs | 21 +-
arrow-cast/src/cast/decimal.rs | 475 ++-------
arrow-cast/src/cast/list.rs | 2 +-
arrow-cast/src/cast/mod.rs | 112 ++-
arrow-cast/src/display.rs | 2 +-
arrow-cast/src/parse.rs | 1049 ++++++++++++++-----
arrow-cast/src/pretty.rs | 9 +-
arrow-cmp/src/lib.rs | 77 ++
arrow-csv/src/reader/mod.rs | 60 +-
arrow-csv/src/writer.rs | 4 +-
arrow-data/src/data.rs | 358 ++++++-
arrow-data/src/decimal.rs | 89 +-
arrow-data/src/equal/boolean.rs | 10 +-
arrow-data/src/equal/structure.rs | 3 +
arrow-data/src/transform/structure.rs | 15 +-
arrow-flight/src/decode.rs | 2 +-
arrow-flight/src/encode.rs | 2 +-
arrow-flight/src/sql/client.rs | 31 +-
arrow-flight/src/sql/metadata/sql_info.rs | 13 +-
arrow-flight/src/sql/metadata/tables.rs | 2 +-
arrow-flight/src/sql/metadata/xdbc_info.rs | 6 +-
arrow-flight/tests/encode_decode.rs | 8 +-
arrow-integration-test/src/datatype.rs | 30 +-
arrow-integration-test/src/field.rs | 6 +-
arrow-integration-test/src/lib.rs | 37 +-
.../src/bin/arrow-json-integration-test.rs | 4 +-
arrow-integration-testing/src/lib.rs | 35 +-
arrow-ipc/src/compression.rs | 11 +-
arrow-ipc/src/convert.rs | 18 +-
arrow-ipc/src/reader.rs | 222 +++-
arrow-ipc/src/writer.rs | 29 +-
arrow-json/benches/json_reader.rs | 25 +
arrow-json/src/lib.rs | 6 +-
arrow-json/src/reader/list_array.rs | 4 +-
arrow-json/src/reader/map_array.rs | 10 +-
arrow-json/src/reader/mod.rs | 515 +++++++++-
arrow-json/src/reader/run_end_array.rs | 2 +-
arrow-json/src/reader/struct_array.rs | 2 +-
arrow-json/src/reader/tape.rs | 11 +
arrow-json/src/writer/encoder.rs | 6 +-
arrow-json/src/writer/mod.rs | 37 +-
arrow-ord/src/rank.rs | 384 ++++++-
arrow-row/src/lib.rs | 12 +-
arrow-schema/src/datatype.rs | 6 +-
arrow-schema/src/extension/mod.rs | 2 +-
arrow-schema/src/ffi.rs | 60 +-
arrow-schema/src/field.rs | 2 +-
arrow-schema/src/metadata.rs | 2 +-
arrow-schema/src/schema.rs | 180 +++-
arrow-select/src/coalesce.rs | 8 +-
arrow-select/src/concat.rs | 10 +-
arrow-select/src/dictionary.rs | 4 +-
arrow-select/src/filter.rs | 4 +-
arrow-select/src/interleave.rs | 2 +-
arrow-select/src/merge.rs | 5 +-
arrow-select/src/take.rs | 1061 +++++++++++++++++---
arrow-select/src/union_extract.rs | 15 +-
arrow-select/src/zip.rs | 131 ++-
arrow-string/src/concat_elements.rs | 20 +-
arrow-string/src/regexp.rs | 10 +-
arrow/benches/boolean_kernels.rs | 32 +-
arrow/benches/csv_reader.rs | 67 +-
arrow/benches/sort_kernel.rs | 43 +
arrow/benches/take_kernels.rs | 140 +++
arrow/benches/zip_kernels.rs | 58 +-
arrow/src/util/test_util.rs | 10 +-
arrow/tests/array_cast.rs | 2 +-
arrow/tests/array_validation.rs | 2 +-
parquet-geospatial/src/interval.rs | 8 +-
parquet-variant-compute/src/arrow_to_variant.rs | 14 +-
parquet-variant-compute/src/cast_to_variant.rs | 2 +-
parquet-variant-compute/src/to_json.rs | 62 +-
parquet-variant-compute/src/type_conversion.rs | 15 +-
parquet-variant-compute/src/variant_array.rs | 147 ++-
parquet-variant-compute/src/variant_get.rs | 4 +-
parquet-variant/benches/variant_validation.rs | 120 ++-
parquet-variant/src/builder/list.rs | 4 +-
parquet-variant/src/builder/object.rs | 2 +-
parquet-variant/src/decoder.rs | 2 +-
parquet-variant/src/path.rs | 1 +
parquet-variant/src/utils.rs | 2 +-
parquet-variant/src/variant.rs | 2 +-
parquet-variant/src/variant/list.rs | 2 +-
parquet-variant/src/variant/metadata.rs | 88 +-
parquet-variant/src/variant/object.rs | 4 +-
parquet-variant/tests/variant_interop.rs | 5 +-
parquet/THRIFT.md | 2 +-
parquet/benches/writer_overhead.rs | 58 +-
parquet/examples/external_metadata.rs | 6 +-
.../arrow/array_reader/byte_array_dictionary.rs | 95 +-
parquet/src/arrow/arrow_reader/mod.rs | 37 +-
parquet/src/arrow/arrow_reader/read_plan.rs | 1 +
.../src/arrow/arrow_reader/selection/algebra.rs | 4 +
.../src/arrow/arrow_reader/selection/boolean.rs | 3 +
.../src/arrow/arrow_reader/selection/selector.rs | 3 +-
parquet/src/arrow/arrow_writer/byte_array.rs | 44 +-
parquet/src/arrow/arrow_writer/levels.rs | 2 +-
parquet/src/arrow/arrow_writer/mod.rs | 116 ++-
parquet/src/arrow/async_reader/mod.rs | 13 +-
parquet/src/arrow/buffer/dictionary_buffer.rs | 14 +-
parquet/src/arrow/in_memory_row_group.rs | 4 +-
parquet/src/arrow/mod.rs | 1 +
parquet/src/arrow/push_decoder/mod.rs | 2 +-
parquet/src/basic.rs | 15 +-
parquet/src/bin/parquet-index.rs | 1 +
parquet/src/bloom_filter/mod.rs | 12 +-
parquet/src/column/chunker/cdc.rs | 16 +
parquet/src/column/reader.rs | 24 +-
parquet/src/column/reader/decoder.rs | 1 +
parquet/src/column/writer/byte_budget_chunker.rs | 8 +-
parquet/src/column/writer/encoder.rs | 40 +-
parquet/src/column/writer/mod.rs | 192 +++-
parquet/src/compression.rs | 15 +-
parquet/src/data_type.rs | 36 +-
parquet/src/encodings/decoding.rs | 3 +
parquet/src/encodings/encoding/mod.rs | 6 +
parquet/src/encodings/rle.rs | 2 +
parquet/src/file/metadata/footer_tail.rs | 2 +-
parquet/src/file/metadata/mod.rs | 20 +-
parquet/src/file/metadata/reader.rs | 23 +-
parquet/src/file/metadata/thrift/encryption.rs | 2 +-
parquet/src/file/metadata/thrift/mod.rs | 2 +-
parquet/src/file/page_index/index_reader.rs | 122 ++-
parquet/src/file/properties.rs | 304 +++++-
parquet/src/file/serialized_reader.rs | 7 +
parquet/src/file/statistics.rs | 58 +-
parquet/src/file/writer.rs | 6 +-
parquet/src/geospatial/accumulator.rs | 9 +-
parquet/src/lib.rs | 2 +-
parquet/src/record/api.rs | 28 +-
parquet/src/record/reader.rs | 2 +
parquet/src/record/record_writer.rs | 2 +-
parquet/src/record/triplet.rs | 4 +
parquet/src/schema/parser.rs | 13 +-
parquet/src/schema/printer.rs | 40 +
parquet/src/schema/types.rs | 286 +++++-
parquet/src/util/bit_util.rs | 3 +-
parquet/src/util/prefix.rs | 2 +
parquet/tests/arrow_reader/bad_data.rs | 9 +-
parquet/tests/arrow_reader/bloom_filter/sync.rs | 1 +
parquet/tests/arrow_reader/io/async_reader.rs | 4 +-
parquet/tests/arrow_reader/parquet_testing.rs | 42 +-
parquet/tests/arrow_reader/statistics.rs | 53 +-
parquet/tests/arrow_writer/layout.rs | 3 +
parquet/tests/arrow_writer/mod.rs | 2 +
parquet/tests/encryption/encryption.rs | 8 +-
parquet/tests/encryption/encryption_async.rs | 54 +-
parquet/tests/ieee754_nan_interop.rs | 3 +-
parquet/tests/variant_integration.rs | 59 ++
rust-toolchain.toml | 2 +-
typos.toml | 55 +
230 files changed, 9382 insertions(+), 2484 deletions(-)
create mode 100755 .github/ci/scripts/typos_check.sh
create mode 100644 arrow-buffer/src/error.rs
create mode 100644 typos.toml
