From a7c16ff951862cccdfa1d348c86b9cf0bb0df280 Mon Sep 17 00:00:00 2001 From: geographybuff Date: Wed, 9 Sep 2026 01:18:15 +0000 Subject: [PATCH 1/2] chore: Fix duplicated word typos in comments and docs Removes thirteen accidentally doubled words across eleven Rust files and one Markdown file: "run-encoded encoded", "and and an offset", "typed typed on", "must must enable", "2. the the null count", "Note this this", "are used used", "of the the column metadata", "to the the histogram's", "to be be calculated", "required required for", "to pass to to" and "from from an iterator". Comment and prose text only, with no code changes. The `PageHeader` case is a transcription slip rather than a faithful copy: upstream parquet-format's parquet.thrift reads "to be calculated". These survive CI because the typos checker matches misspelled words and does not detect a correctly spelled word repeated twice in a row. Co-Authored-By: Claude Opus 5 (1M context) --- arrow-array/src/array/run_array.rs | 2 +- arrow-buffer/src/lib.rs | 2 +- arrow-buffer/src/util/bit_chunk_iterator.rs | 2 +- arrow-data/src/data.rs | 2 +- arrow-data/src/transform/mod.rs | 2 +- parquet/src/arrow/arrow_reader/mod.rs | 2 +- parquet/src/arrow/arrow_reader/statistics.rs | 2 +- parquet/src/arrow/mod.rs | 2 +- parquet/src/file/metadata/mod.rs | 4 ++-- parquet/src/file/metadata/thrift/mod.rs | 2 +- parquet/src/file/properties.rs | 2 +- parquet_derive/README.md | 2 +- 12 files changed, 13 insertions(+), 13 deletions(-) diff --git a/arrow-array/src/array/run_array.rs b/arrow-array/src/array/run_array.rs index 7255eb50d373..ca5155569f2a 100644 --- a/arrow-array/src/array/run_array.rs +++ b/arrow-array/src/array/run_array.rs @@ -670,7 +670,7 @@ pub type Int32RunArray = RunArray; /// ``` pub type Int64RunArray = RunArray; -/// A [`RunArray`] typed typed on its child values array +/// A [`RunArray`] typed on its child values array /// /// Implements [`ArrayAccessor`] and [`IntoIterator`] allowing fast access to its elements /// diff --git a/arrow-buffer/src/lib.rs b/arrow-buffer/src/lib.rs index 3e4fc828f63c..cd4d662dbb75 100644 --- a/arrow-buffer/src/lib.rs +++ b/arrow-buffer/src/lib.rs @@ -30,7 +30,7 @@ //! - [`NullBuffer`][]: Arrow null (validity) bitmaps ([`BooleanBuffer`] with extra utilities) //! - [`ScalarBuffer`][]: Typed buffer for primitive types (e.g., `i32`, `f64`) //! - [`OffsetBuffer`][]: Offsets used in variable-length types (e.g., strings, lists) -//! - [`RunEndBuffer`][]: Run-ends used in run-encoded encoded data +//! - [`RunEndBuffer`][]: Run-ends used in run-encoded data #![doc( html_logo_url = "https://arrow.apache.org/img/arrow-logo_chevrons_black-txt_white-bg.svg", diff --git a/arrow-buffer/src/util/bit_chunk_iterator.rs b/arrow-buffer/src/util/bit_chunk_iterator.rs index 73b849d9a7d4..0607f2a04eef 100644 --- a/arrow-buffer/src/util/bit_chunk_iterator.rs +++ b/arrow-buffer/src/util/bit_chunk_iterator.rs @@ -38,7 +38,7 @@ pub struct UnalignedBitChunk<'a> { } impl<'a> UnalignedBitChunk<'a> { - /// Create a from a byte array, and and an offset and length in bits + /// Create a from a byte array, and an offset and length in bits pub fn new(buffer: &'a [u8], offset: usize, len: usize) -> Self { if len == 0 { return Self { diff --git a/arrow-data/src/data.rs b/arrow-data/src/data.rs index 5f68e6548f8e..b9114165062c 100644 --- a/arrow-data/src/data.rs +++ b/arrow-data/src/data.rs @@ -1494,7 +1494,7 @@ impl ArrayData { /// /// Does not (yet) check /// 1. Union type_ids are valid see [#85](https://github.com/apache/arrow-rs/issues/85) - /// 2. the the null count is correct and that any + /// 2. the null count is correct and that any /// 3. nullability requirements of its children are correct /// /// [#85]: https://github.com/apache/arrow-rs/issues/85 diff --git a/arrow-data/src/transform/mod.rs b/arrow-data/src/transform/mod.rs index 989e502e093a..2db03a42aa9b 100644 --- a/arrow-data/src/transform/mod.rs +++ b/arrow-data/src/transform/mod.rs @@ -156,7 +156,7 @@ pub struct MutableArrayData<'a> { /// Variadic data buffers referenced by views. /// - /// Note this this is not stored in `_MutableArrayData` because these values + /// Note this is not stored in `_MutableArrayData` because these values /// are constant and only needed at the end, when freezing /// [_MutableArrayData] variadic_data_buffers: Vec, diff --git a/parquet/src/arrow/arrow_reader/mod.rs b/parquet/src/arrow/arrow_reader/mod.rs index 056bc97a09e5..1e482bbe51a5 100644 --- a/parquet/src/arrow/arrow_reader/mod.rs +++ b/parquet/src/arrow/arrow_reader/mod.rs @@ -3375,7 +3375,7 @@ pub(crate) mod tests { /// `ParquetFileArrowReader` using a standard set of parameters /// `opts`. /// - /// `rand_max` represents the maximum size of value to pass to to + /// `rand_max` represents the maximum size of value to pass to /// value generator fn run_single_column_reader_tests( rand_max: i32, diff --git a/parquet/src/arrow/arrow_reader/statistics.rs b/parquet/src/arrow/arrow_reader/statistics.rs index 8ef4cc4544c4..486e937a79de 100644 --- a/parquet/src/arrow/arrow_reader/statistics.rs +++ b/parquet/src/arrow/arrow_reader/statistics.rs @@ -231,7 +231,7 @@ make_stats_iterator!( [u8] ); -/// Special iterator adapter for extracting i128 values from from an iterator of +/// Special iterator adapter for extracting i128 values from an iterator of /// `ParquetStatistics` /// /// Handles checking if the statistics are present and valid with the correct type. diff --git a/parquet/src/arrow/mod.rs b/parquet/src/arrow/mod.rs index 8309a35e9b1d..e2ea1b4ca0bf 100644 --- a/parquet/src/arrow/mod.rs +++ b/parquet/src/arrow/mod.rs @@ -149,7 +149,7 @@ //! # //! let file = File::open(path).unwrap(); //! -//! // Define the AES encryption keys required required for decrypting the footer metadata +//! // Define the AES encryption keys required for decrypting the footer metadata //! // and column-specific data. If only a footer key is used then it is assumed that the //! // file uses uniform encryption and all columns are encrypted with the footer key. //! // If any column keys are specified, other columns without a key provided are assumed diff --git a/parquet/src/file/metadata/mod.rs b/parquet/src/file/metadata/mod.rs index 0520db7b057d..166a7eb7ab6a 100644 --- a/parquet/src/file/metadata/mod.rs +++ b/parquet/src/file/metadata/mod.rs @@ -726,7 +726,7 @@ impl RowGroupMetaDataBuilder { self } - /// Takes ownership of the the column metadata in this builder, and clears + /// Takes ownership of the column metadata in this builder, and clears /// the list of columns. /// /// This can be used for more efficient creation of a new RowGroupMetaData @@ -843,7 +843,7 @@ impl LevelHistogram { None } } - /// Returns a reference to the the histogram's values. + /// Returns a reference to the histogram's values. pub fn values(&self) -> &[i64] { &self.inner } diff --git a/parquet/src/file/metadata/thrift/mod.rs b/parquet/src/file/metadata/thrift/mod.rs index 8d590079cc03..8bc0cbbd0b67 100644 --- a/parquet/src/file/metadata/thrift/mod.rs +++ b/parquet/src/file/metadata/thrift/mod.rs @@ -1178,7 +1178,7 @@ pub(crate) struct PageHeader { /// Compressed (and potentially encrypted) page size in bytes, not including this header 3: required i32 compressed_page_size - /// The 32-bit CRC checksum for the page, to be be calculated as follows: + /// The 32-bit CRC checksum for the page, to be calculated as follows: 4: optional i32 crc // Headers for page specific data. One only will be set. diff --git a/parquet/src/file/properties.rs b/parquet/src/file/properties.rs index a03fb0d9cca0..b831cbc3b05d 100644 --- a/parquet/src/file/properties.rs +++ b/parquet/src/file/properties.rs @@ -1161,7 +1161,7 @@ impl WriterPropertiesBuilder { /// * If the bloom filter is enabled previously then it is a no-op. /// /// * If the bloom filter is not enabled, default values for ndv and fpp - /// value are used used. See [`set_bloom_filter_max_ndv`] and + /// value are used. See [`set_bloom_filter_max_ndv`] and /// [`set_bloom_filter_fpp`] to further adjust the ndv and fpp. /// /// [`set_bloom_filter_max_ndv`]: Self::set_bloom_filter_max_ndv diff --git a/parquet_derive/README.md b/parquet_derive/README.md index 6423fa5a51d3..e17c5bd8e51a 100644 --- a/parquet_derive/README.md +++ b/parquet_derive/README.md @@ -24,7 +24,7 @@ generate readers or writers for arbitrarily nested structures. It only works for generic structures and various levels of reference. Please see features checklist for what is currently supported. -Derive also has some support for the chrono time library. You must must enable the `chrono` feature to get this support. +Derive also has some support for the chrono time library. You must enable the `chrono` feature to get this support. ## Usage From 4f2efde75c6dc8bbc6a80f156f0684beb5c02b1a Mon Sep 17 00:00:00 2001 From: geographybuff <31372572+geographybuff@users.noreply.github.com> Date: Wed, 9 Sep 2026 08:13:19 -0300 Subject: [PATCH 2/2] Update arrow-buffer/src/util/bit_chunk_iterator.rs Co-authored-by: Jeffrey Vo --- arrow-buffer/src/util/bit_chunk_iterator.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arrow-buffer/src/util/bit_chunk_iterator.rs b/arrow-buffer/src/util/bit_chunk_iterator.rs index 0607f2a04eef..77c98000cb08 100644 --- a/arrow-buffer/src/util/bit_chunk_iterator.rs +++ b/arrow-buffer/src/util/bit_chunk_iterator.rs @@ -38,7 +38,7 @@ pub struct UnalignedBitChunk<'a> { } impl<'a> UnalignedBitChunk<'a> { - /// Create a from a byte array, and an offset and length in bits + /// Create from a byte array, offset and length in bits pub fn new(buffer: &'a [u8], offset: usize, len: usize) -> Self { if len == 0 { return Self {