Merge pull request #5155 from karthikeyann/doc-spell-check

[REVIEW] cudf documentation spell check fix

CHANGELOG.md

@@ -176,6 +176,7 @@
 - PR #5159 Add `make_meta_object` in `dask_cudf` backend and add `str.split` test
 - PR #5198 Add detail headers for strings converter functions
 - PR #5199 Add index support in `DataFrame.query`
+- PR #5155 Fix cudf documentation misspellings
 
 ## Bug Fixes
 

cpp/include/cudf/aggregation.hpp

@@ -194,7 +194,7 @@ std::unique_ptr<aggregation> make_nth_element_aggregation(
 std::unique_ptr<aggregation> make_row_number_aggregation();
 
 /**
- * @brief Factory to create a aggregation base on UDF for PTX or CUDA
+ * @brief Factory to create an aggregation base on UDF for PTX or CUDA
  *
  * @param[in] type: either udf_type::PTX or udf_type::CUDA
  * @param[in] user_defined_aggregator A string containing the aggregator code

cpp/include/cudf/binaryop.hpp

@@ -59,7 +59,7 @@ enum class binary_operator : int32_t {
                    ///< ptx code
   SHIFT_LEFT,      ///< operator <<
   SHIFT_RIGHT,     ///< operator >>
-  // Logical right shift. Casts to an unsigned value before shifing.
+  // Logical right shift. Casts to an unsigned value before shifting.
   // approximates >>> from Java.
   SHIFT_RIGHT_UNSIGNED,  ///< operator >>>
   LOG_BASE,              ///< logarithm to the base

cpp/include/cudf/column/column_device_view.cuh

@@ -383,7 +383,7 @@ class alignas(16) column_device_view : public detail::column_device_view_base {
   /**
    * @brief Destroy the `column_device_view` object.
    *
-   * @note Does not free the column data, simply free's the device memory
+   * @note Does not free the column data, simply frees the device memory
    * allocated to hold the child views.
    */
   void destroy();
@@ -453,7 +453,7 @@ class alignas(16) mutable_column_device_view : public detail::column_device_view
   /**
    * @brief Factory to construct a column view that is usable in device memory.
    *
-   * Allocates and copies views of `soure_view`'s children to device memory to
+   * Allocates and copies views of `source_view`'s children to device memory to
    * make them accessible in device code.
    *
    * If `source_view.num_children() == 0`, then no device memory is allocated.
@@ -642,7 +642,7 @@ class alignas(16) mutable_column_device_view : public detail::column_device_view
   /**
    * @brief Destroy the `mutable_column_device_view` object.
    *
-   * @note Does not free the column data, simply free's the device memory
+   * @note Does not free the column data, simply frees the device memory
    * allocated to hold the child views.
    */
   void destroy();

cpp/include/cudf/column/column_view.hpp

@@ -32,7 +32,7 @@ namespace detail {
  * Specification: https://arrow.apache.org/docs/memory_layout.html
  *
  * Because `column_view_base` is non-owning, no device memory is allocated nor
- *free'd when `column_view_base` objects are created or destroyed.
+ *freed when `column_view_base` objects are created or destroyed.
  *
  * To enable zero-copy slicing, a `column_view_base` has an `offset` that
  *indicates the index of the first element in the column relative to the base
@@ -150,7 +150,7 @@ class column_view_base {
    * `begin > end`, `begin >= size()`, or `end > size()`).
    *
    * @param[in] begin The starting index of the range (inclusive).
-   * @param[in] end The index of the last element in the range (exlusive).
+   * @param[in] end The index of the last element in the range (exclusive).
    **/
   size_type null_count(size_type begin, size_type end) const;
 
@@ -171,7 +171,7 @@ class column_view_base {
    * `begin > end`, `begin >= size()`, or `end > size()`).
    *
    * @param begin The starting index of the range (inclusive).
-   * @param end The index of the last element in the range (exlusive).
+   * @param end The index of the last element in the range (exclusive).
    * @return true One or more elements are null in the range [begin, end)
    * @return false All elements are valid in the range [begin, end)
    */
@@ -267,7 +267,7 @@ class mutable_column_view_base : public column_view_base {
  * bitmask is expected to adhere to the Arrow Physical Memory Layout
  * Specification: https://arrow.apache.org/docs/memory_layout.html
  *
- * Because `column_view` is non-owning, no device memory is allocated nor free'd
+ * Because `column_view` is non-owning, no device memory is allocated nor freed
  * when `column_view` objects are created or destroyed.
  *
  * To enable zero-copy slicing, a `column_view` has an `offset` that indicates
@@ -354,7 +354,7 @@ class column_view : public detail::column_view_base {
  * Specification: https://arrow.apache.org/docs/memory_layout.html
  *
  * Because `mutable_column_view` is non-owning, no device memory is allocated
- * nor free'd when `mutable_column_view` objects are created or destroyed.
+ * nor freed when `mutable_column_view` objects are created or destroyed.
  *
  * To enable zero-copy slicing, a `mutable_column_view` has an `offset` that
  * indicates the index of the first element in the column relative to the base

cpp/include/cudf/detail/merge.cuh

@@ -35,7 +35,7 @@ using index_type = thrust::tuple<side, cudf::size_type>;
 
 /**
  * @brief tagged_element_relational_comparator uses element_relational_comparator to provide
- * "tagged-index" comparation logic.
+ * "tagged-index" comparison logic.
  *
  * Special treatment is necessary in several thrust algorithms (e.g., merge()) where
  * the index affinity to the side is not guaranteed; i.e., the algorithms rely on

cpp/include/cudf/detail/reduction_operators.cuh

@@ -111,7 +111,7 @@ struct simple_op {
 };
 
 // `sum`, `product`, `sum_of_squares`, `min`, `max` are used at simple_reduction
-// inferface is defined by CRTP calss simple_op
+// interface is defined by CRTP class simple_op
 
 // operator for `sum`
 struct sum : public simple_op<sum> {
@@ -172,7 +172,7 @@ struct compound_op : public simple_op<Derived> {
    * @param count validity count
    * @param ddof  `ddof` parameter used by variance and standard deviation
    *
-   * @return transformed output result of compount operator
+   * @return transformed output result of compound operator
    */
   template <typename ResultType, typename IntermediateType>
   CUDA_HOST_DEVICE_CALLABLE static ResultType compute_result(const IntermediateType& input,
@@ -190,7 +190,7 @@ struct compound_op : public simple_op<Derived> {
 // structure type of a single reduction call, it is also used as OutputType of
 // cudf::reduction::detail::reduce at compound_reduction. compute_result
 // computes the final ResultType from the IntermediateType.
-// intemediate::compute_result method is enforced by CRTP base class compound_op
+// intermediate::compute_result method is enforced by CRTP base class compound_op
 
 // operator for `mean`
 struct mean : public compound_op<mean> {

cpp/include/cudf/detail/repeat.hpp

@@ -49,7 +49,7 @@ namespace detail {
  * has negative values or the sum of @p count elements overflows.
  *
  * @param input_table Input table
- * @param count Non-nullable column of a integral type
+ * @param count Non-nullable column of an integral type
  * @param check_count Whether to check count (negative values and overflow)
  * @param mr Memory resource to allocate the result output table
  * @param stream CUDA stream to run this function
@@ -77,7 +77,7 @@ std::unique_ptr<table> repeat(table_view const& input_table,
  * size_type.
  *
  * @param input_table Input table
- * @param count Non-null scalar of a integral type
+ * @param count Non-null scalar of an integral type
  * @param mr Memory resource to allocate the result output table
  * @param stream CUDA stream to run this function
  * @return std::unique_ptr<table> The result table containing the repetitions

cpp/include/cudf/detail/valid_if.cuh

@@ -136,7 +136,7 @@ std::pair<rmm::device_buffer, size_type> valid_if(
  *
  * @note If any mask in `masks` is `nullptr`, that mask will be ignored.
  *
- * @param begin1        LHS arguments to binary predicte. ex: column/mask idx
+ * @param begin1        LHS arguments to binary predicate. ex: column/mask idx
  * @param begin2        RHS arguments to binary predicate. ex: row/bit idx
  * @param p             Predicate: `bit = p(begin1 + mask_idx, begin2 + bit_idx)`
  * @param masks         Masks for which bits will be obtained and assigned.

cpp/include/cudf/filling.hpp

@@ -111,7 +111,7 @@ std::unique_ptr<column> fill(column_view const& input,
  * has negative values or the sum of @p count elements overflows.
  *
  * @param input_table Input table
- * @param count Non-nullable column of a integral type
+ * @param count Non-nullable column of an integral type
  * @param check_count Whether to check count (negative values and overflow)
  * @param mr Memory resource to allocate the result output table
  * @return std::unique_ptr<table> The result table containing the repetitions
@@ -138,7 +138,7 @@ std::unique_ptr<table> repeat(
  * size_type.
  *
  * @param input_table Input table
- * @param count Non-null scalar of a integral type
+ * @param count Non-null scalar of an integral type
  * @param mr Memory resource to allocate the result output table
  * @return std::unique_ptr<table> The result table containing the repetitions
  */

cpp/include/cudf/partitioning.hpp

@@ -224,7 +224,7 @@ std::pair<std::unique_ptr<experimental::table>, std::vector<size_type>> hash_par
  * @param[in] start_partition Index of the 1st partition
  * @param[in] mr Device memory allocator
  *
- * @return A std::pair consisting of an unique_ptr to the partitioned table
+ * @return A std::pair consisting of a unique_ptr to the partitioned table
  * and the partition offsets for each partition within the table.
  */
 std::pair<std::unique_ptr<cudf::experimental::table>, std::vector<cudf::size_type>>

cpp/include/cudf/strings/convert/convert_ipv4.hpp

@@ -41,7 +41,7 @@ namespace strings {
  * integer is undefined.
  *
  * The resulting 32-bit integer is placed in an int64_t to avoid setting the sign-bit
- * in a int32_t type. This could be changed if cudf supported a UINT32 type in the future.
+ * in an int32_t type. This could be changed if cudf supported a UINT32 type in the future.
  *
  * Any null entries will result in corresponding null entries in the output column.
  *

cpp/include/cudf/strings/convert/convert_urls.hpp

@@ -31,7 +31,7 @@ namespace strings {
  * Converts mostly non-ascii characters and control characters into UTF-8 hex code-points
  * prefixed with '%'. For example, the space character must be converted to characters '%20' where
  * the '20' indicates the hex value for space in UTF-8. Likewise, multi-byte characters are
- * converted to multiple hex charactes. For example, the é character is converted to characters
+ * converted to multiple hex characters. For example, the é character is converted to characters
  * '%C3%A9' where 'C3A9' is the UTF-8 bytes 0xC3A9 for this character.
  *
  * Any null entries will result in corresponding null entries in the output column.

cpp/include/cudf/strings/copying.hpp

@@ -24,7 +24,7 @@ namespace detail {
 /**
  * @brief Returns a new strings column created from a subset of
  * of the strings column. The subset of strings selected is between
- * start (inclusive) and end (exclusive) with incrememnts of step.
+ * start (inclusive) and end (exclusive) with increments of step.
  *
  * @code{.pseudo}
  * Example:

cpp/include/cudf/strings/split/partition.hpp

@@ -48,7 +48,7 @@ namespace strings {
  * @endcode
  *
  * @param strings Strings instance for this operation.
- * @param delimiter UTF-8 encoded string indentifying where to split each string.
+ * @param delimiter UTF-8 encoded string indicating where to split each string.
  *        Default of empty string indicates split on whitespace.
  * @param mr Resource for allocating device memory.
  * @return New table of strings columns.
@@ -80,7 +80,7 @@ std::unique_ptr<experimental::table> partition(
  * @endcode
  *
  * @param strings Strings instance for this operation.
- * @param delimiter UTF-8 encoded string indentifying where to split each string.
+ * @param delimiter UTF-8 encoded string indicating where to split each string.
  *        Default of empty string indicates split on whitespace.
  * @param mr Resource for allocating device memory.
  * @return New strings columns.

cpp/include/cudf/strings/split/split.hpp

@@ -41,7 +41,7 @@ namespace strings {
  * Any null string entries return corresponding null output columns.
  *
  * @param strings_column Strings instance for this operation.
- * @param delimiter UTF-8 encoded string indentifying the split points in each string.
+ * @param delimiter UTF-8 encoded string indicating the split points in each string.
  *        Default of empty string indicates split on whitespace.
  * @param maxsplit Maximum number of splits to perform.
  *        Default of -1 indicates all possible splits on each string.
@@ -69,7 +69,7 @@ std::unique_ptr<experimental::table> split(
  * Any null string entries return corresponding null output columns.
  *
  * @param strings_column Strings instance for this operation.
- * @param delimiter UTF-8 encoded string indentifying the split points in each string.
+ * @param delimiter UTF-8 encoded string indicating the split points in each string.
  *        Default of empty string indicates split on whitespace.
  * @param maxsplit Maximum number of splits to perform.
  *        Default of -1 indicates all possible splits on each string.
@@ -115,7 +115,7 @@ struct contiguous_split_record_result {
  * @throws cudf:logic_error if `delimiter` is invalid.
  *
  * @param strings A column of string elements to be splitted.
- * @param delimiter UTF-8 encoded string indentifying the split points in each
+ * @param delimiter UTF-8 encoded string indicating the split points in each
  *        string.
  *        Default of empty string indicates split on whitespace.
  * @param maxsplit Maximum number of splits to perform.
@@ -147,7 +147,7 @@ contiguous_split_record_result contiguous_split_record(
  * @throws cudf:logic_error if `delimiter` is invalid.
  *
  * @param strings A column of string elements to be splitted.
- * @param delimiter UTF-8 encoded string indentifying the split points in each
+ * @param delimiter UTF-8 encoded string indicating the split points in each
  *        string.
  *        Default of empty string indicates split on whitespace.
  * @param maxsplit Maximum number of splits to perform.

cpp/include/cudf/strings/wrap.hpp

@@ -55,7 +55,7 @@ namespace strings {
  * ```
  *
  * @param[in] strings String column.
- * @param[in] width Maximum chararacter width of a line within each string.
+ * @param[in] width Maximum character width of a line within each string.
  * @param[in] mr Resource for allocating device memory.
  * @return Column of wrapped strings.
  */

cpp/include/cudf/table/row_operators.cuh

@@ -68,7 +68,7 @@ __device__ weak_ordering compare_elements(Element lhs, Element rhs)
 }  // namespace detail
 
 /*
- * @brief A specialization for floating-point `Element` type rerlational comparison
+ * @brief A specialization for floating-point `Element` type relational comparison
  * to derive the order of the elements with respect to `lhs`. Specialization is to
  * handle `nan` in the order shown below.
  * `[-Inf, -ve, 0, -0, +ve, +Inf, NaN, NaN, null] (for null_order::AFTER)`
@@ -152,7 +152,7 @@ class element_equality_comparator {
    * @note `lhs` and `rhs` may be the same.
    *
    * @param lhs The column containing the first element
-   * @param rhs The column containg the second element (may be the same as lhs)
+   * @param rhs The column containing the second element (may be the same as lhs)
    * @param nulls_are_equal Indicates if two null elements are treated as equivalent
    **/
   __host__ __device__ element_equality_comparator(column_device_view lhs,
@@ -235,7 +235,7 @@ class element_relational_comparator {
    * @note `lhs` and `rhs` may be the same.
    *
    * @param lhs The column containing the first element
-   * @param rhs The column containg the second element (may be the same as lhs)
+   * @param rhs The column containing the second element (may be the same as lhs)
    * @param null_precedence Indicates how null values are ordered with other
    * values
    **/

cpp/include/cudf/types.h

@@ -44,7 +44,7 @@ typedef enum {
  */
 typedef enum {
   GDF_SUCCESS = 0,
-  GDF_CUDA_ERROR,             ///< Error occured in a CUDA call
+  GDF_CUDA_ERROR,             ///< Error occurred in a CUDA call
   GDF_UNSUPPORTED_DTYPE,      ///< The datatype of the gdf_column is unsupported
   GDF_COLUMN_SIZE_MISMATCH,   ///< Two columns that should be the same size aren't the same size
   GDF_COLUMN_SIZE_TOO_BIG,    ///< Size of column is larger than the max supported size
@@ -66,7 +66,7 @@ typedef enum {
   GDF_HASH_TABLE_INSERT_FAILURE,  ///< Failed to insert to hash table, likely because its full
   GDF_UNSUPPORTED_JOIN_TYPE,      ///< The type of join requested is unsupported
   GDF_C_ERROR,                    ///< C error not related to CUDA
-  GDF_FILE_ERROR,                 ///< error processing sepcified file
+  GDF_FILE_ERROR,                 ///< error processing specified file
   GDF_MEMORYMANAGER_ERROR,        ///< Memory manager error (see memory.h)
   GDF_UNDEFINED_NVTX_COLOR,  ///< The requested color used to define an NVTX range is not defined
   GDF_NULL_NVTX_NAME,        ///< The requested name for an NVTX range cannot be nullptr
@@ -83,7 +83,7 @@ typedef enum {
 } gdf_hash_func;
 
 /**
- * @brief Defines the unit of time that an algoithm or structure is storing.
+ * @brief Defines the unit of time that an algorithm or structure is storing.
  *
  * There are time types in cudf. Those time types can have different resolutions.
  * The types included are nanosecond, microsecond, millisecond, and second.
@@ -171,7 +171,7 @@ typedef enum {
   GDF_MIN,             ///< Computes minimum value in the aggregation column
   GDF_MAX,             ///< Computes maximum value in the aggregation column
   GDF_AVG,             ///< Computes arithmetic mean of all values in the aggregation column
-  GDF_COUNT,           ///< Computes histogram of the occurance of each key in the GroupBy Columns
+  GDF_COUNT,           ///< Computes histogram of the occurrence of each key in the GroupBy Columns
   GDF_COUNT_DISTINCT,  ///< Counts the number of distinct keys in the GroupBy columns
   GDF_NUMBA_GENERIC_AGG_OPS,  ///< Perform a generic aggregation operation detailed in a PTX code
                               ///< generated by `numba`

cpp/include/cudf/unary.hpp

@@ -37,7 +37,7 @@ enum class unary_op : int32_t {
   COSH,        // < Hyperbolic cosine
   TANH,        // < Hyperbolic tangent
   ARCSINH,     // < Hyperbolic sine inverse
-  ARCCOSH,     // < Hperbolic cosine inverse
+  ARCCOSH,     // < Hyperbolic cosine inverse
   ARCTANH,     // < Hyperbolic tangent inverse
   EXP,         // < Exponential (base e, Euler number)
   LOG,         // < Natural Logarithm (base e)
@@ -72,7 +72,7 @@ std::unique_ptr<cudf::column> unary_operation(
  * @param input A `column_view` as input
  * @param mr Optional, The resource to use for all allocations
  *
- * @returns std::unique_ptr<cudf::column> A non-nulalble column of `BOOL8` elements with `true`
+ * @returns std::unique_ptr<cudf::column> A non-nullable column of `BOOL8` elements with `true`
  * representing `null` values.
  */
 std::unique_ptr<cudf::column> is_null(
@@ -86,7 +86,7 @@ std::unique_ptr<cudf::column> is_null(
  * @param input A `column_view` as input
  * @param mr Optional, The resource to use for all allocations
  *
- * @returns std::unique_ptr<cudf::column> A non-nulalble column of `BOOL8` elements with `false`
+ * @returns std::unique_ptr<cudf::column> A non-nullable column of `BOOL8` elements with `false`
  * representing `null` values.
  */
 std::unique_ptr<cudf::column> is_valid(
@@ -118,7 +118,7 @@ std::unique_ptr<column> cast(column_view const& input,
  * @param input A column of floating-point elements
  * @param mr Optional, The resource to use for allocating the device memory in the returned column.
  *
- * @returns unique_ptr<column> A non-nulalble column of `BOOL8` elements with `true`
+ * @returns unique_ptr<column> A non-nullable column of `BOOL8` elements with `true`
  * representing `NAN` values
  */
 std::unique_ptr<column> is_nan(
@@ -135,7 +135,7 @@ std::unique_ptr<column> is_nan(
  * @param input A column of floating-point elements
  * @param mr Optional, The resource to use for allocating the device memory in the returned column.
  *
- * @returns unique_ptr<column> A non-nulalble column of `BOOL8` elements with `false`
+ * @returns unique_ptr<column> A non-nullable column of `BOOL8` elements with `false`
  * representing `NAN` values
  */
 std::unique_ptr<column> is_not_nan(

cpp/src/bitmask/null_mask.cu

@@ -523,7 +523,7 @@ std::vector<size_type> segmented_count_set_bits(bitmask_type const *bitmask,
 
   CHECK_CUDA(stream);
 
-  // third adjust counts in segement boundaries (if segments are not
+  // third, adjust counts in segment boundaries (if segments are not
   // word-aligned)
 
   constexpr size_type block_size{256};