sparrow::dense_union_array Class Reference

Dense union array implementation with offset buffer. More...

#include <union_array.hpp>

Inheritance diagram for sparrow::dense_union_array:

Collaboration diagram for sparrow::dense_union_array:

Public Types
using	base_type = union_array_crtp_base<dense_union_array>
using	offset_buffer_type = u8_buffer<std::uint32_t>
using	type_id_buffer_type = typename base_type::type_id_buffer_type
Public Types inherited from sparrow::union_array_crtp_base< dense_union_array >
using	self_type
using	derived_type
using	inner_value_type
using	value_type
using	const_reference
using	functor_type
using	const_functor_type
using	iterator
using	const_iterator
using	const_reverse_iterator
using	size_type
using	type_id_buffer_type

Public Member Functions
template<class... Args> requires (mpl::excludes_copy_and_move_ctor_v<dense_union_array, Args...>)
	dense_union_array (Args &&... args)
	Generic constructor for creating dense union arrays.
SPARROW_API	dense_union_array (arrow_proxy proxy)
	Constructs dense union array from Arrow proxy.
SPARROW_API	dense_union_array (const dense_union_array &rhs)
	Copy constructor.
SPARROW_API dense_union_array &	operator= (const dense_union_array &rhs)
	Copy assignment operator.
	dense_union_array (dense_union_array &&rhs)=default
dense_union_array &	operator= (dense_union_array &&rhs)=default
template<input_metadata_container METADATA_RANGE>
auto	create_proxy_impl (std::vector< array > &&children, type_id_buffer_type &&element_type, offset_buffer_type &&offsets, std::string &&format, std::optional< std::string_view > name, std::optional< METADATA_RANGE > metadata) -> arrow_proxy
Public Member Functions inherited from sparrow::union_array_crtp_base< dense_union_array >
constexpr std::optional< std::string_view >	name () const
	Gets the optional name of the union array.
SPARROW_CONSTEXPR_CLANG std::optional< key_value_view >	metadata () const
	Gets the metadata associated with the union array.
SPARROW_CONSTEXPR_CLANG value_type	at (size_type i) const
	Gets element at specified position with bounds checking.
SPARROW_CONSTEXPR_CLANG value_type	operator[] (size_type i) const
	Gets element at specified position without bounds checking.
SPARROW_CONSTEXPR_CLANG value_type	operator[] (size_type i)
	Gets mutable element at specified position.
SPARROW_CONSTEXPR_CLANG value_type	front () const
	Gets reference to the first element.
SPARROW_CONSTEXPR_CLANG value_type	back () const
	Gets reference to the last element.
constexpr bool	empty () const
	Checks if the union array is empty.
constexpr size_type	size () const
	Gets the number of elements in the union array.
constexpr iterator	begin ()
	Gets iterator to the beginning of the array.
constexpr iterator	end ()
	Gets iterator to the end of the array.
constexpr const_iterator	begin () const
	Gets const iterator to the beginning of the array.
constexpr const_iterator	end () const
	Gets const iterator to the end of the array.
constexpr const_iterator	cbegin () const
	Gets const iterator to the beginning of the array.
constexpr const_iterator	cend () const
	Gets const iterator to the end of the array.
constexpr const_reverse_iterator	rbegin () const
	Gets reverse iterator to the beginning of reversed array.
constexpr const_reverse_iterator	rend () const
	Gets reverse iterator to the end of reversed array.
constexpr const_reverse_iterator	crbegin () const
	Gets const reverse iterator to the beginning of reversed array.
constexpr const_reverse_iterator	crend () const
	Gets const reverse iterator to the end of reversed array.
constexpr void	zero_null_values (const inner_value_type &value)
	Sets all null values to the specified value.
constexpr auto	type_id_map_from_child_to_type_id (const std::optional< R > &child_index_to_type_id) -> type_id_map
constexpr std::optional< std::string_view >	name () const
	Gets the optional name of the union array.
SPARROW_CONSTEXPR_CLANG std::optional< key_value_view >	metadata () const
	Gets the metadata associated with the union array.
SPARROW_CONSTEXPR_CLANG value_type	at (size_type i) const
	Gets element at specified position with bounds checking.
SPARROW_CONSTEXPR_CLANG value_type	operator[] (size_type i) const
	Gets element at specified position without bounds checking.
SPARROW_CONSTEXPR_CLANG value_type	operator[] (size_type i)
	Gets mutable element at specified position.
SPARROW_CONSTEXPR_CLANG value_type	front () const
	Gets reference to the first element.
SPARROW_CONSTEXPR_CLANG value_type	back () const
	Gets reference to the last element.
constexpr bool	empty () const
	Checks if the union array is empty.
constexpr size_type	size () const
	Gets the number of elements in the union array.
constexpr iterator	begin ()
	Gets iterator to the beginning of the array.
constexpr const_iterator	begin () const
	Gets const iterator to the beginning of the array.
constexpr iterator	end ()
	Gets iterator to the end of the array.
constexpr const_iterator	end () const
	Gets const iterator to the end of the array.
constexpr const_iterator	cbegin () const
	Gets const iterator to the beginning of the array.
constexpr const_iterator	cend () const
	Gets const iterator to the end of the array.
constexpr const_reverse_iterator	rbegin () const
	Gets reverse iterator to the beginning of reversed array.
constexpr const_reverse_iterator	rend () const
	Gets reverse iterator to the end of reversed array.
constexpr const_reverse_iterator	crbegin () const
	Gets const reverse iterator to the beginning of reversed array.
constexpr const_reverse_iterator	crend () const
	Gets const reverse iterator to the end of reversed array.
constexpr void	zero_null_values (const inner_value_type &value)
	Sets all null values to the specified value.
constexpr auto	type_id_map_from_child_to_type_id (const std::optional< R > &child_index_to_type_id) -> type_id_map

Friends
class	union_array_crtp_base< dense_union_array >

Additional Inherited Members
Protected Types inherited from sparrow::union_array_crtp_base< dense_union_array >
using	type_id_map
using	children_type
Protected Types inherited from sparrow::crtp_base< D >
using	derived_type = D
Protected Member Functions inherited from sparrow::union_array_crtp_base< dense_union_array >
constexpr children_type	make_children (arrow_proxy &proxy)
	Creates child array wrappers from Arrow proxy.
	union_array_crtp_base (arrow_proxy proxy)
	Protected constructor from Arrow proxy.
constexpr	union_array_crtp_base (const self_type &rhs)
	Copy constructor.
constexpr self_type &	operator= (const self_type &rhs)
	Copy assignment operator.
constexpr	union_array_crtp_base (self_type &&rhs)=default
constexpr self_type &	operator= (self_type &&rhs)=default
constexpr arrow_proxy &	get_arrow_proxy ()
	Gets mutable reference to the Arrow proxy.
constexpr const arrow_proxy &	get_arrow_proxy () const
	Gets const reference to the Arrow proxy.
constexpr children_type	make_children (arrow_proxy &proxy)
	Creates child array wrappers from Arrow proxy.
	union_array_crtp_base (arrow_proxy proxy)
	Protected constructor from Arrow proxy.
constexpr	union_array_crtp_base (const self_type &rhs)
	Copy constructor.
constexpr	union_array_crtp_base (self_type &&rhs)=default
constexpr self_type &	operator= (const self_type &rhs)
	Copy assignment operator.
constexpr self_type &	operator= (self_type &&rhs)=default
constexpr arrow_proxy &	get_arrow_proxy ()
	Gets mutable reference to the Arrow proxy.
constexpr const arrow_proxy &	get_arrow_proxy () const
	Gets const reference to the Arrow proxy.
Protected Member Functions inherited from sparrow::crtp_base< D >
constexpr derived_type &	derived_cast ()
constexpr const derived_type &	derived_cast () const
Static Protected Member Functions inherited from sparrow::union_array_crtp_base< dense_union_array >
static constexpr type_id_map	parse_type_id_map (std::string_view format_string)
	Parses type ID mapping from Arrow format string.
static constexpr type_id_map	type_id_map_from_child_to_type_id (const std::optional< R > &child_index_to_type_id)
	Creates type ID mapping from child index to type ID mapping.
static constexpr std::string	make_format_string (bool dense, std::size_t n, const std::optional< R > &child_index_to_type_id)
	Creates Arrow format string for union arrays.
static constexpr type_id_map	parse_type_id_map (std::string_view format_string)
	Parses type ID mapping from Arrow format string.
static constexpr type_id_map	type_id_map_from_child_to_type_id (const std::optional< R > &child_index_to_type_id)
	Creates type ID mapping from child index to type ID mapping.
static constexpr std::string	make_format_string (bool dense, std::size_t n, const std::optional< R > &child_index_to_type_id)
	Creates Arrow format string for union arrays.
Protected Attributes inherited from sparrow::union_array_crtp_base< dense_union_array >
arrow_proxy	m_proxy
	Internal Arrow proxy.
const std::uint8_t *	p_type_ids
	Pointer to type ID buffer.
children_type	m_children
	Child array wrappers.
std::array< std::uint8_t, TYPE_ID_MAP_SIZE >	m_type_id_map
	Type ID to child index mapping.
arrow_proxy	m_proxy
	Internal Arrow proxy.
const std::uint8_t *	p_type_ids
	Pointer to type ID buffer.
children_type	m_children
	Child array wrappers.
std::array< std::uint8_t, TYPE_ID_MAP_SIZE >	m_type_id_map
	Type ID to child index mapping.
Static Protected Attributes inherited from sparrow::union_array_crtp_base< dense_union_array >
static constexpr size_t	TYPE_ID_MAP_SIZE
static constexpr size_t	TYPE_ID_MAP_SIZE

Detailed Description

Dense union array implementation with offset buffer.

Dense union arrays store an additional offset buffer that maps each element to its position within the corresponding child array. This allows child arrays to be densely packed (only containing values that are actually used), making them more memory efficient when union elements are sparse.

Memory layout:

• Type ID buffer: Maps each element to child array type
• Offset buffer: Maps each element to position in child array
• Child arrays: Contain only the values actually used

Related Apache Arrow specification: https://arrow.apache.org/docs/dev/format/Columnar.html#dense-union

Postcondition

Maintains Arrow dense union format compatibility ("+ud:")

Child arrays can be shorter than the union array length

Provides memory-efficient storage for sparse union data

//Create dense union with int and string children
std::vector<array> children = {int_array, string_array};
type_id_buffer_type type_ids = {0, 1, 0, 1};        // alternating types
offset_buffer_type offsets = {0, 0, 1, 1};          // positions in child arrays
 
dense_union_array union_arr(std::move(children),
                         std::move(type_ids),
                         std::move(offsets));

Definition at line 542 of file union_array.hpp.

Member Typedef Documentation

base_type

using sparrow::dense_union_array::base_type = union_array_crtp_base<dense_union_array>

Definition at line 546 of file union_array.hpp.

offset_buffer_type

using sparrow::dense_union_array::offset_buffer_type = u8_buffer<std::uint32_t>

Definition at line 547 of file union_array.hpp.

type_id_buffer_type

using sparrow::dense_union_array::type_id_buffer_type = typename base_type::type_id_buffer_type

Definition at line 548 of file union_array.hpp.

Constructor & Destructor Documentation

dense_union_array() [1/4]

template<class... Args>
requires (mpl::excludes_copy_and_move_ctor_v<dense_union_array, Args...>)

sparrow::dense_union_array::dense_union_array ( Args &&... args )

inlineexplicit

Generic constructor for creating dense union arrays.

Creates a dense union array from various input combinations including child arrays, type IDs, offsets, and optional type mapping.

Template Parameters

Args	Parameter pack for constructor arguments

Parameters

args	Constructor arguments (children, type_ids, offsets, etc.)

Precondition

Args must match one of the create_proxy() overload signatures

Args must exclude copy and move constructor signatures

Children, type IDs, and offsets must have consistent sizes

Postcondition

Array is created with the specified children and configuration

Definition at line 566 of file union_array.hpp.

Here is the caller graph for this function:

dense_union_array() [2/4]

SPARROW_API sparrow::dense_union_array::dense_union_array ( arrow_proxy proxy )

explicit

Constructs dense union array from Arrow proxy.

Parameters

proxy

Arrow proxy containing dense union array data and schema

Precondition

proxy must contain valid Arrow dense union array and schema

proxy format must be "+ud:..."

proxy must have type ID buffer and offset buffer

Postcondition

Array is initialized with data from proxy

Offset buffer pointer is cached for efficient access

dense_union_array() [3/4]

SPARROW_API sparrow::dense_union_array::dense_union_array

(

const dense_union_array &

rhs

)

Copy constructor.

Parameters

rhs	Source dense union array to copy from

Precondition

rhs must be in a valid state

Postcondition

This array contains a copy of rhs data

Offset buffer pointer is properly set

Here is the call graph for this function:

dense_union_array() [4/4]

sparrow::dense_union_array::dense_union_array ( dense_union_array && rhs )

default

Here is the call graph for this function:

Member Function Documentation

create_proxy_impl()

template<input_metadata_container METADATA_RANGE>

auto sparrow::dense_union_array::create_proxy_impl	(	std::vector< array > &&	children,
		type_id_buffer_type &&	element_type,
		offset_buffer_type &&	offsets,
		std::string &&	format,
		std::optional< std::string_view >	name,
		std::optional< METADATA_RANGE >	metadata ) -> arrow_proxy

Definition at line 1205 of file union_array.hpp.

Here is the call graph for this function:

operator=() [1/2]

SPARROW_API dense_union_array & sparrow::dense_union_array::operator=

(

const dense_union_array &

rhs

)

Copy assignment operator.

Parameters

rhs	Source dense union array to copy from

Returns

Reference to this array

Precondition

rhs must be in a valid state

Postcondition

This array contains a copy of rhs data

Previous data is properly released

Offset buffer pointer is updated

Here is the call graph for this function:

operator=() [2/2]

dense_union_array & sparrow::dense_union_array::operator= ( dense_union_array && rhs )

default

Here is the call graph for this function:

Friends And Related Symbol Documentation

union_array_crtp_base< dense_union_array >

friend class union_array_crtp_base< dense_union_array >

friend

Definition at line 771 of file union_array.hpp.

---

The documentation for this class was generated from the following file:

• /home/runner/work/sparrow/sparrow/include/sparrow/union_array.hpp