chore: Fix duplicated word typos in comments and docs

arrow-array/src/array/run_array.rs

@@ -670,7 +670,7 @@ pub type Int32RunArray = RunArray<Int32Type>;
 /// ```
 pub type Int64RunArray = RunArray<Int64Type>;
 
-/// 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
 ///

arrow-buffer/src/lib.rs

@@ -30,7 +30,7 @@
 //! - [`NullBuffer`][]: Arrow null (validity) bitmaps ([`BooleanBuffer`] with extra utilities)
 //! - [`ScalarBuffer<T>`][]: Typed buffer for primitive types (e.g., `i32`, `f64`)
 //! - [`OffsetBuffer<O>`][]: Offsets used in variable-length types (e.g., strings, lists)
-//! - [`RunEndBuffer<E>`][]: Run-ends used in run-encoded encoded data
+//! - [`RunEndBuffer<E>`][]: Run-ends used in run-encoded data
 
 #![doc(
     html_logo_url = "https://arrow.apache.org/img/arrow-logo_chevrons_black-txt_white-bg.svg",

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 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 {

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

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<Buffer>,

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<T, F, G>(
         rand_max: i32,

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.

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

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
     }

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.

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

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