Merge branch 'branch-24.12' into pylibcudf/strings/wrap

cpp/.clang-tidy

@@ -3,7 +3,8 @@ Checks:
       'modernize-*,
        -modernize-use-equals-default,
        -modernize-concat-nested-namespaces,
-       -modernize-use-trailing-return-type'
+       -modernize-use-trailing-return-type,
+       -modernize-use-bool-literals'
 
       # -modernize-use-equals-default        # auto-fix is broken (doesn't insert =default correctly)
       # -modernize-concat-nested-namespaces  # auto-fix is broken (can delete code)

cpp/include/cudf/column/column_device_view.cuh

@@ -1425,13 +1425,13 @@ struct pair_rep_accessor {
 
  private:
   template <typename R, std::enable_if_t<std::is_same_v<R, rep_type>, void>* = nullptr>
-  __device__ inline auto get_rep(cudf::size_type i) const
+  __device__ [[nodiscard]] inline auto get_rep(cudf::size_type i) const
   {
     return col.element<R>(i);
   }
 
   template <typename R, std::enable_if_t<not std::is_same_v<R, rep_type>, void>* = nullptr>
-  __device__ inline auto get_rep(cudf::size_type i) const
+  __device__ [[nodiscard]] inline auto get_rep(cudf::size_type i) const
   {
     return col.element<R>(i).value();
   }

cpp/include/cudf/column/column_view.hpp

@@ -235,7 +235,7 @@ class column_view_base {
    *
    * @return Typed pointer to underlying data
    */
-  virtual void const* get_data() const noexcept { return _data; }
+  [[nodiscard]] virtual void const* get_data() const noexcept { return _data; }
 
   data_type _type{type_id::EMPTY};   ///< Element type
   size_type _size{};                 ///< Number of elements
@@ -695,7 +695,7 @@ class mutable_column_view : public detail::column_view_base {
    *
    * @return Typed pointer to underlying data
    */
-  void const* get_data() const noexcept override;
+  [[nodiscard]] void const* get_data() const noexcept override;
 
  private:
   friend mutable_column_view bit_cast(mutable_column_view const& input, data_type type);

cpp/include/cudf/detail/aggregation/aggregation.hpp

@@ -683,7 +683,7 @@ class ewma_aggregation final : public scan_aggregation {
   {
   }
 
-  std::unique_ptr<aggregation> clone() const override
+  [[nodiscard]] std::unique_ptr<aggregation> clone() const override
   {
     return std::make_unique<ewma_aggregation>(*this);
   }
@@ -694,7 +694,7 @@ class ewma_aggregation final : public scan_aggregation {
     return collector.visit(col_type, *this);
   }
 
-  bool is_equal(aggregation const& _other) const override
+  [[nodiscard]] bool is_equal(aggregation const& _other) const override
   {
     if (!this->aggregation::is_equal(_other)) { return false; }
     auto const& other = dynamic_cast<ewma_aggregation const&>(_other);

cpp/include/cudf/detail/groupby/sort_helper.hpp

@@ -211,7 +211,6 @@ struct sort_groupby_helper {
    */
   column_view keys_bitmask_column(rmm::cuda_stream_view stream);
 
- private:
   column_ptr _key_sorted_order;      ///< Indices to produce _keys in sorted order
   column_ptr _unsorted_keys_labels;  ///< Group labels for unsorted _keys
   column_ptr _keys_bitmask_column;   ///< Column representing rows with one or more nulls values

cpp/include/cudf/detail/utilities/host_vector.hpp

@@ -183,7 +183,7 @@ class rmm_host_allocator {
    */
   inline bool operator!=(rmm_host_allocator const& x) const { return !operator==(x); }
 
-  bool is_device_accessible() const { return _is_device_accessible; }
+  [[nodiscard]] bool is_device_accessible() const { return _is_device_accessible; }
 
  private:
   rmm::host_async_resource_ref mr;

cpp/include/cudf/dictionary/dictionary_column_view.hpp

@@ -47,7 +47,7 @@ class dictionary_column_view : private column_view {
   dictionary_column_view(column_view const& dictionary_column);
   dictionary_column_view(dictionary_column_view&&)      = default;  ///< Move constructor
   dictionary_column_view(dictionary_column_view const&) = default;  ///< Copy constructor
-  ~dictionary_column_view()                             = default;
+  ~dictionary_column_view() override                    = default;
 
   /**
    * @brief Move assignment operator

cpp/include/cudf/groupby.hpp

@@ -36,7 +36,7 @@ namespace CUDF_EXPORT cudf {
 namespace groupby {
 namespace detail {
 namespace sort {
-class sort_groupby_helper;
+struct sort_groupby_helper;
 
 }  // namespace sort
 }  // namespace detail

cpp/include/cudf/io/json.hpp

@@ -116,9 +116,6 @@ class json_reader_options {
   // Whether to parse dates as DD/MM versus MM/DD
   bool _dayfirst = false;
 
-  // Whether to use the legacy reader
-  bool _legacy = false;
-
   // Whether to keep the quote characters of string values
   bool _keep_quotes = false;
 

cpp/include/cudf/io/parquet.hpp

@@ -1200,7 +1200,7 @@ class parquet_writer_options : public parquet_writer_options_base {
    * @param sink The sink used for writer output
    * @param table Table to be written to output
    */
-  explicit parquet_writer_options(sink_info const& sink, table_view const& table);
+  explicit parquet_writer_options(sink_info const& sink, table_view table);
 
  public:
   /**

cpp/include/cudf/lists/lists_column_view.hpp

@@ -48,7 +48,7 @@ class lists_column_view : private column_view {
   lists_column_view(column_view const& lists_column);
   lists_column_view(lists_column_view&&)      = default;  ///< Move constructor
   lists_column_view(lists_column_view const&) = default;  ///< Copy constructor
-  ~lists_column_view()                        = default;
+  ~lists_column_view() override               = default;
   /**
    * @brief Copy assignment operator
    *

cpp/include/cudf/scalar/scalar.hpp

@@ -47,6 +47,7 @@ namespace CUDF_EXPORT cudf {
  */
 class scalar {
  public:
+  scalar()                               = delete;
   virtual ~scalar()                      = default;
   scalar& operator=(scalar const& other) = delete;
   scalar& operator=(scalar&& other)      = delete;
@@ -96,8 +97,6 @@ class scalar {
   data_type _type{type_id::EMPTY};     ///< Logical type of value in the scalar
   rmm::device_scalar<bool> _is_valid;  ///< Device bool signifying validity
 
-  scalar() = delete;
-
   /**
    * @brief Move constructor for scalar.
    * @param other The other scalar to move from.
@@ -145,6 +144,7 @@ class fixed_width_scalar : public scalar {
  public:
   using value_type = T;  ///< Type of the value held by the scalar.
 
+  fixed_width_scalar()           = delete;
   ~fixed_width_scalar() override = default;
 
   /**
@@ -203,8 +203,6 @@ class fixed_width_scalar : public scalar {
  protected:
   rmm::device_scalar<T> _data;  ///< device memory containing the value
 
-  fixed_width_scalar() = delete;
-
   /**
    * @brief Construct a new fixed width scalar object.
    *

cpp/include/cudf/strings/detail/char_tables.hpp

@@ -74,9 +74,9 @@ character_cases_table_type const* get_character_cases_table();
  */
 struct special_case_mapping {
   uint16_t num_upper_chars;
-  uint16_t upper[3];
+  uint16_t upper[3];  // NOLINT
   uint16_t num_lower_chars;
-  uint16_t lower[3];
+  uint16_t lower[3];  // NOLINT
 };
 
 /**

cpp/include/cudf/strings/regex/regex_program.hpp

@@ -54,6 +54,8 @@ struct regex_program {
                                                regex_flags flags      = regex_flags::DEFAULT,
                                                capture_groups capture = capture_groups::EXTRACT);
 
+  regex_program() = delete;
+
   /**
    * @brief Move constructor
    *
@@ -115,8 +117,6 @@ struct regex_program {
   ~regex_program();
 
  private:
-  regex_program() = delete;
-
   std::string _pattern;
   regex_flags _flags;
   capture_groups _capture;

cpp/include/cudf/strings/string_view.cuh

@@ -99,7 +99,7 @@ __device__ inline std::pair<size_type, size_type> bytes_to_character_position(st
  * values. Also, this char pointer serves as valid device pointer of identity
  * value for minimum operator on string values.
  */
-static __constant__ char max_string_sentinel[5]{"\xF7\xBF\xBF\xBF"};
+static __constant__ char max_string_sentinel[5]{"\xF7\xBF\xBF\xBF"};  // NOLINT
 }  // namespace detail
 }  // namespace strings
 
@@ -283,14 +283,11 @@ __device__ inline size_type string_view::const_iterator::position() const { retu
 
 __device__ inline size_type string_view::const_iterator::byte_offset() const { return byte_pos; }
 
-__device__ inline string_view::const_iterator string_view::begin() const
-{
-  return const_iterator(*this, 0, 0);
-}
+__device__ inline string_view::const_iterator string_view::begin() const { return {*this, 0, 0}; }
 
 __device__ inline string_view::const_iterator string_view::end() const
 {
-  return const_iterator(*this, length(), size_bytes());
+  return {*this, length(), size_bytes()};
 }
 // @endcond
 
@@ -411,7 +408,7 @@ __device__ inline size_type string_view::find(char const* str,
 
 __device__ inline size_type string_view::find(char_utf8 chr, size_type pos, size_type count) const
 {
-  char str[sizeof(char_utf8)];
+  char str[sizeof(char_utf8)];  // NOLINT
   size_type chwidth = strings::detail::from_char_utf8(chr, str);
   return find(str, chwidth, pos, count);
 }
@@ -433,7 +430,7 @@ __device__ inline size_type string_view::rfind(char const* str,
 
 __device__ inline size_type string_view::rfind(char_utf8 chr, size_type pos, size_type count) const
 {
-  char str[sizeof(char_utf8)];
+  char str[sizeof(char_utf8)];  // NOLINT
   size_type chwidth = strings::detail::from_char_utf8(chr, str);
   return rfind(str, chwidth, pos, count);
 }

cpp/include/cudf/strings/strings_column_view.hpp

@@ -45,7 +45,7 @@ class strings_column_view : private column_view {
   strings_column_view(column_view strings_column);
   strings_column_view(strings_column_view&&)      = default;  ///< Move constructor
   strings_column_view(strings_column_view const&) = default;  ///< Copy constructor
-  ~strings_column_view()                          = default;
+  ~strings_column_view() override                 = default;
   /**
    * @brief Copy assignment operator
    *

cpp/include/cudf/structs/structs_column_view.hpp

@@ -42,7 +42,7 @@ class structs_column_view : public column_view {
   // Foundation members:
   structs_column_view(structs_column_view const&) = default;  ///< Copy constructor
   structs_column_view(structs_column_view&&)      = default;  ///< Move constructor
-  ~structs_column_view()                          = default;
+  ~structs_column_view() override                 = default;
   /**
    * @brief Copy assignment operator
    *

cpp/include/cudf/tdigest/tdigest_column_view.hpp

@@ -59,7 +59,7 @@ class tdigest_column_view : private column_view {
   tdigest_column_view(column_view const&);  ///< Construct tdigest_column_view from a column_view
   tdigest_column_view(tdigest_column_view&&)      = default;  ///< Move constructor
   tdigest_column_view(tdigest_column_view const&) = default;  ///< Copy constructor
-  ~tdigest_column_view()                          = default;
+  ~tdigest_column_view() override                 = default;
   /**
    * @brief Copy assignment operator
    *

cpp/include/cudf/utilities/span.hpp

@@ -236,26 +236,26 @@ struct host_span : public cudf::detail::span_base<T, Extent, host_span<T, Extent
 
   /// Constructor from container
   /// @param in The container to construct the span from
-  template <
-    typename C,
-    // Only supported containers of types convertible to T
-    std::enable_if_t<is_host_span_supported_container<C>::value &&
-                     std::is_convertible_v<std::remove_pointer_t<decltype(thrust::raw_pointer_cast(
-                                             std::declval<C&>().data()))> (*)[],
-                                           T (*)[]>>* = nullptr>
+  template <typename C,
+            // Only supported containers of types convertible to T
+            std::enable_if_t<is_host_span_supported_container<C>::value &&
+                             std::is_convertible_v<
+                               std::remove_pointer_t<decltype(thrust::raw_pointer_cast(  // NOLINT
+                                 std::declval<C&>().data()))> (*)[],
+                               T (*)[]>>* = nullptr>  // NOLINT
   constexpr host_span(C& in) : base(thrust::raw_pointer_cast(in.data()), in.size())
   {
   }
 
   /// Constructor from const container
   /// @param in The container to construct the span from
-  template <
-    typename C,
-    // Only supported containers of types convertible to T
-    std::enable_if_t<is_host_span_supported_container<C>::value &&
-                     std::is_convertible_v<std::remove_pointer_t<decltype(thrust::raw_pointer_cast(
-                                             std::declval<C&>().data()))> (*)[],
-                                           T (*)[]>>* = nullptr>
+  template <typename C,
+            // Only supported containers of types convertible to T
+            std::enable_if_t<is_host_span_supported_container<C>::value &&
+                             std::is_convertible_v<
+                               std::remove_pointer_t<decltype(thrust::raw_pointer_cast(  // NOLINT
+                                 std::declval<C&>().data()))> (*)[],
+                               T (*)[]>>* = nullptr>  // NOLINT
   constexpr host_span(C const& in) : base(thrust::raw_pointer_cast(in.data()), in.size())
   {
   }
@@ -264,7 +264,7 @@ struct host_span : public cudf::detail::span_base<T, Extent, host_span<T, Extent
   /// @param in The host_vector to construct the span from
   template <typename OtherT,
             // Only supported containers of types convertible to T
-            std::enable_if_t<std::is_convertible_v<OtherT (*)[], T (*)[]>>* = nullptr>
+            std::enable_if_t<std::is_convertible_v<OtherT (*)[], T (*)[]>>* = nullptr>  // NOLINT
   constexpr host_span(cudf::detail::host_vector<OtherT>& in)
     : base(in.data(), in.size()), _is_device_accessible{in.get_allocator().is_device_accessible()}
   {
@@ -274,7 +274,7 @@ struct host_span : public cudf::detail::span_base<T, Extent, host_span<T, Extent
   /// @param in The host_vector to construct the span from
   template <typename OtherT,
             // Only supported containers of types convertible to T
-            std::enable_if_t<std::is_convertible_v<OtherT (*)[], T (*)[]>>* = nullptr>
+            std::enable_if_t<std::is_convertible_v<OtherT (*)[], T (*)[]>>* = nullptr>  // NOLINT
   constexpr host_span(cudf::detail::host_vector<OtherT> const& in)
     : base(in.data(), in.size()), _is_device_accessible{in.get_allocator().is_device_accessible()}
   {
@@ -285,7 +285,7 @@ struct host_span : public cudf::detail::span_base<T, Extent, host_span<T, Extent
   template <typename OtherT,
             std::size_t OtherExtent,
             std::enable_if_t<(Extent == OtherExtent || Extent == dynamic_extent) &&
-                               std::is_convertible_v<OtherT (*)[], T (*)[]>,
+                               std::is_convertible_v<OtherT (*)[], T (*)[]>,  // NOLINT
                              void>* = nullptr>
   constexpr host_span(host_span<OtherT, OtherExtent> const& other) noexcept
     : base(other.data(), other.size())
@@ -333,26 +333,26 @@ struct device_span : public cudf::detail::span_base<T, Extent, device_span<T, Ex
 
   /// Constructor from container
   /// @param in The container to construct the span from
-  template <
-    typename C,
-    // Only supported containers of types convertible to T
-    std::enable_if_t<is_device_span_supported_container<C>::value &&
-                     std::is_convertible_v<std::remove_pointer_t<decltype(thrust::raw_pointer_cast(
-                                             std::declval<C&>().data()))> (*)[],
-                                           T (*)[]>>* = nullptr>
+  template <typename C,
+            // Only supported containers of types convertible to T
+            std::enable_if_t<is_device_span_supported_container<C>::value &&
+                             std::is_convertible_v<
+                               std::remove_pointer_t<decltype(thrust::raw_pointer_cast(  // NOLINT
+                                 std::declval<C&>().data()))> (*)[],
+                               T (*)[]>>* = nullptr>  // NOLINT
   constexpr device_span(C& in) : base(thrust::raw_pointer_cast(in.data()), in.size())
   {
   }
 
   /// Constructor from const container
   /// @param in The container to construct the span from
-  template <
-    typename C,
-    // Only supported containers of types convertible to T
-    std::enable_if_t<is_device_span_supported_container<C>::value &&
-                     std::is_convertible_v<std::remove_pointer_t<decltype(thrust::raw_pointer_cast(
-                                             std::declval<C&>().data()))> (*)[],
-                                           T (*)[]>>* = nullptr>
+  template <typename C,
+            // Only supported containers of types convertible to T
+            std::enable_if_t<is_device_span_supported_container<C>::value &&
+                             std::is_convertible_v<
+                               std::remove_pointer_t<decltype(thrust::raw_pointer_cast(  // NOLINT
+                                 std::declval<C&>().data()))> (*)[],
+                               T (*)[]>>* = nullptr>  // NOLINT
   constexpr device_span(C const& in) : base(thrust::raw_pointer_cast(in.data()), in.size())
   {
   }
@@ -362,7 +362,7 @@ struct device_span : public cudf::detail::span_base<T, Extent, device_span<T, Ex
   template <typename OtherT,
             std::size_t OtherExtent,
             std::enable_if_t<(Extent == OtherExtent || Extent == dynamic_extent) &&
-                               std::is_convertible_v<OtherT (*)[], T (*)[]>,
+                               std::is_convertible_v<OtherT (*)[], T (*)[]>,  // NOLINT
                              void>* = nullptr>
   constexpr device_span(device_span<OtherT, OtherExtent> const& other) noexcept
     : base(other.data(), other.size())

cpp/include/cudf_test/type_list_utilities.hpp

@@ -414,9 +414,8 @@ struct RemoveIfImpl<PRED, Types<>> {
 
 template <class PRED, class HEAD, class... TAIL>
 struct RemoveIfImpl<PRED, Types<HEAD, TAIL...>> {
-  using type =
-    Concat<typename std::conditional<PRED::template Call<HEAD>::value, Types<>, Types<HEAD>>::type,
-           typename RemoveIfImpl<PRED, Types<TAIL...>>::type>;
+  using type = Concat<std::conditional_t<PRED::template Call<HEAD>::value, Types<>, Types<HEAD>>,
+                      typename RemoveIfImpl<PRED, Types<TAIL...>>::type>;
 };
 // @endcond
 

cpp/src/datetime/timezone.cpp

@@ -38,7 +38,7 @@ std::string const tzif_system_directory = "/usr/share/zoneinfo/";
 struct timezone_file_header {
   uint32_t magic;          ///< "TZif"
   uint8_t version;         ///< 0:version1, '2':version2, '3':version3
-  uint8_t reserved15[15];  ///< unused, reserved for future use
+  uint8_t reserved15[15];  ///< unused, reserved for future use // NOLINT
   uint32_t isutccnt;       ///< number of UTC/local indicators contained in the body
   uint32_t isstdcnt;       ///< number of standard/wall indicators contained in the body
   uint32_t leapcnt;        ///< number of leap second records contained in the body