More doxygen fixes

cpp/include/cudf/contiguous_split.hpp

@@ -25,7 +25,7 @@
 namespace cudf {
 
 /**
- * @addtogroup column_copy
+ * @addtogroup copy_split
  * @{
  * @file
  * @brief Table APIs for contiguous_split, pack, unpack, and metadata
@@ -34,8 +34,6 @@ namespace cudf {
 /**
  * @brief Column data in a serialized format
  *
- * @ingroup copy_split
- *
  * Contains data from an array of columns in two contiguous buffers: one on host, which contains
  * table metadata and one on device which contains the table data.
  */
@@ -65,8 +63,6 @@ struct packed_columns {
 /**
  * @brief The result(s) of a cudf::contiguous_split
  *
- * @ingroup copy_split
- *
  * Each table_view resulting from a split operation performed by contiguous_split,
  * will be returned wrapped in a `packed_table`. The table_view and internal
  * column_views in this struct are not owned by a top level cudf::table or cudf::column.
@@ -85,8 +81,6 @@ struct packed_table {
  * @brief Performs a deep-copy split of a `table_view` into a vector of `packed_table` where each
  * `packed_table` is using a single contiguous block of memory for all of the split's column data.
  *
- * @ingroup copy_split
- *
  * The memory for the output views is allocated in a single contiguous `rmm::device_buffer` returned
  * in the `packed_table`. There is no top-level owning table.
  *

cpp/include/cudf/fixed_point/fixed_point.hpp

@@ -31,6 +31,13 @@
 /// `fixed_point` and supporting types
 namespace numeric {
 
+/**
+ * @addtogroup fixed_point_classes
+ * @{
+ * @file
+ * @brief Class definition for fixed point data type
+ */
+
 /// The scale type for fixed_point
 enum scale_type : int32_t {};
 
@@ -71,6 +78,8 @@ constexpr inline auto is_supported_construction_value_type()
   return cuda::std::is_integral<T>() || cuda::std::is_floating_point_v<T>;
 }
 
+/** @} */  // end of group
+
 // Helper functions for `fixed_point` type
 namespace detail {
 /**

cpp/include/cudf/io/orc_metadata.hpp

@@ -30,6 +30,11 @@
 
 namespace cudf {
 namespace io {
+/**
+ * @addtogroup io_types
+ * @{
+ * @file
+ */
 
 /**
  * @brief Holds column names and buffers containing raw file-level and stripe-level statistics.
@@ -147,6 +152,7 @@ struct timestamp_statistics : minmax_statistics<int64_t> {
   std::optional<uint32_t> maximum_nanos;  ///< nanoseconds part of the maximum
 };
 
+//! Orc I/O interfaces
 namespace orc {
 // forward declare the type that ProtobufReader uses. The `cudf::io::column_statistics` objects,
 // returned from `read_parsed_orc_statistics`, are constructed from
@@ -367,5 +373,6 @@ class orc_metadata {
  */
 orc_metadata read_orc_metadata(source_info const& src_info);
 
+/** @} */  // end of group
 }  // namespace io
 }  // namespace cudf

cpp/include/cudf/io/orc_types.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2023, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -19,7 +19,15 @@
 #include <cstdint>
 
 namespace cudf::io::orc {
+/**
+ * @addtogroup io_types
+ * @{
+ * @file
+ */
 
+/**
+ * @brief Identifies a compression algorithm
+ */
 enum CompressionKind : uint8_t {
   NONE   = 0,
   ZLIB   = 1,
@@ -29,6 +37,9 @@ enum CompressionKind : uint8_t {
   ZSTD   = 5,
 };
 
+/**
+ * @brief Identifies a data type in an orc file
+ */
 enum TypeKind : int8_t {
   INVALID_TYPE_KIND = -1,
   BOOLEAN           = 0,
@@ -51,6 +62,9 @@ enum TypeKind : int8_t {
   CHAR              = 17,
 };
 
+/**
+ * @brief Identifies the type of data stream
+ */
 enum StreamKind : int8_t {
   INVALID_STREAM_KIND = -1,
   PRESENT             = 0,  // boolean stream of whether the next value is non-null
@@ -64,6 +78,9 @@ enum StreamKind : int8_t {
   BLOOM_FILTER_UTF8   = 8,  // bloom filters that consistently use utf8
 };
 
+/**
+ * @brief Identifies the encoding of columns
+ */
 enum ColumnEncodingKind : int8_t {
   INVALID_ENCODING_KIND = -1,
   DIRECT                = 0,  // the encoding is mapped directly to the stream using RLE v1
@@ -72,6 +89,9 @@ enum ColumnEncodingKind : int8_t {
   DICTIONARY_V2         = 3,  // the encoding is dictionary-based using RLE v2
 };
 
+/**
+ * @brief Identifies the type of encoding in a protocol buffer
+ */
 enum ProtofType : uint8_t {
   VARINT      = 0,
   FIXED64     = 1,
@@ -83,4 +103,5 @@ enum ProtofType : uint8_t {
   INVALID_7   = 7,
 };
 
+/** @} */  // end of group
 }  // namespace cudf::io::orc

cpp/include/cudf/io/parquet_metadata.hpp

@@ -30,7 +30,13 @@
 
 namespace cudf {
 namespace io {
+/**
+ * @addtogroup io_types
+ * @{
+ * @file
+ */
 
+//! Parquet I/O interfaces
 namespace parquet {
 /**
  * @brief Basic data types in Parquet, determines how data is physically stored
@@ -227,5 +233,6 @@ class parquet_metadata {
  */
 parquet_metadata read_parquet_metadata(source_info const& src_info);
 
+/** @} */  // end of group
 }  // namespace io
 }  // namespace cudf

cpp/include/cudf/io/types.hpp

@@ -729,8 +729,8 @@ class column_in_metadata {
   /**
    * @brief Gets the explicitly set nullability for this column.
    *
-   * @throws If nullability is not explicitly defined for this column.
-   *         Check using `is_nullability_defined()` first.
+   * @throws std::bad_optional_access If nullability is not explicitly defined
+   *         for this column. Check using `is_nullability_defined()` first.
    * @return Boolean indicating whether this column is nullable
    */
   [[nodiscard]] bool nullable() const { return _nullable.value(); }
@@ -763,8 +763,8 @@ class column_in_metadata {
   /**
    * @brief Get the decimal precision that was set for this column.
    *
-   * @throws If decimal precision was not set for this column.
-   *         Check using `is_decimal_precision_set()` first.
+   * @throws std::bad_optional_access If decimal precision was not set for this
+   *         column. Check using `is_decimal_precision_set()` first.
    * @return The decimal precision that was set for this column
    */
   [[nodiscard]] uint8_t get_decimal_precision() const { return _decimal_precision.value(); }
@@ -782,8 +782,8 @@ class column_in_metadata {
   /**
    * @brief Get the parquet field id that was set for this column.
    *
-   * @throws If parquet field id was not set for this column.
-   *         Check using `is_parquet_field_id_set()` first.
+   * @throws std::bad_optional_access If parquet field id was not set for this
+   *         column. Check using `is_parquet_field_id_set()` first.
    * @return The parquet field id that was set for this column
    */
   [[nodiscard]] int32_t get_parquet_field_id() const { return _parquet_field_id.value(); }

cpp/include/cudf/rolling/range_window_bounds.hpp

@@ -19,6 +19,11 @@
 #include <cudf/scalar/scalar.hpp>
 
 namespace cudf {
+/**
+ * @addtogroup aggregation_rolling
+ * @{
+ * @file
+ */
 
 /**
  * @brief Abstraction for window boundary sizes, to be used with
@@ -105,4 +110,5 @@ struct range_window_bounds {
   range_window_bounds(extent_type extent_, std::unique_ptr<scalar> range_scalar_);
 };
 
+/** @} */  // end of group
 }  // namespace cudf

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

@@ -143,7 +143,7 @@ std::unique_ptr<table> rsplit(
  *
  * A null string element will result in a null list item for that row.
  *
- * @throw cudf:logic_error if `delimiter` is invalid.
+ * @throw cudf::logic_error if `delimiter` is invalid.
  *
  * @param strings A column of string elements to be split
  * @param delimiter The string to identify split points in each string;
@@ -222,7 +222,7 @@ std::unique_ptr<column> split_record(
  *
  * A null string element will result in a null list item for that row.
  *
- * @throw cudf:logic_error if `delimiter` is invalid.
+ * @throw cudf::logic_error if `delimiter` is invalid.
  *
  * @param strings A column of string elements to be split
  * @param delimiter The string to identify split points in each string;

cpp/include/cudf/tdigest/tdigest_column_view.hpp

@@ -19,7 +19,14 @@
 #include <cudf/lists/lists_column_view.hpp>
 
 namespace cudf {
+//! Tdigest interfaces
 namespace tdigest {
+/**
+ * @addtogroup tdigest
+ * @{
+ * @file
+ * @brief tdigest data APIs
+ */
 
 /**
  * @brief Given a column_view containing tdigest data, an instance of this class
@@ -123,5 +130,6 @@ class tdigest_column_view : private column_view {
   [[nodiscard]] double const* max_begin() const;
 };
 
+/** @} */  // end of group
 }  // namespace tdigest
 }  // namespace cudf

cpp/include/cudf/utilities/span.hpp

@@ -30,10 +30,17 @@
 #include <type_traits>
 
 namespace cudf {
+/**
+ * @addtogroup utility_span
+ * @{
+ * @file
+ * @brief APIs for spans
+ */
 
 /// A constant used to differentiate std::span of static and dynamic extent
 constexpr std::size_t dynamic_extent = std::numeric_limits<std::size_t>::max();
 
+/** @} */  // end of group
 namespace detail {
 
 /**
@@ -189,7 +196,7 @@ class span_base {
  * @addtogroup utility_span
  * @{
  * @file
- * @brief APIs for labeling values by bin.
+ * @brief APIs for spans
  */
 
 // ===== host_span =================================================================================

cpp/include/doxygen_groups.h

@@ -141,6 +141,7 @@
  * @}
  * @defgroup io_apis IO
  * @{
+ *   @defgroup io_types IO Types
  *   @defgroup io_readers Readers
  *   @defgroup io_writers Writers
  *   @defgroup io_datasources Data Sources
@@ -187,4 +188,5 @@
  *   @defgroup label_bins Bin Labeling
  * @}
  * @defgroup expressions Expression Evaluation
+ * @defgroup tdigest tdigest APIs
  */