#include <xg.hpp>

Inheritance diagram for xg::XG:

Public Member Functions
	XG (void)=default

	~XG (void)

	XG (const XG &other)=delete

	XG (XG &&other)=delete

XG &	operator= (const XG &other)=delete

XG &	operator= (XG &&other)=delete

void	from_handle_graph (const HandleGraph &graph)
	build the graph from another simple graph More...

void	from_path_handle_graph (const PathHandleGraph &graph)
	build the graph from another path handle graph More...

void	from_enumerators (const std::function< void(const std::function< void(const std::string &seq, const nid_t &node_id)> &)> &for_each_sequence, const std::function< void(const std::function< void(const nid_t &from, const bool &from_rev, const nid_t &to, const bool &to_rev)> &)> &for_each_edge, const std::function< void(const std::function< void(const std::string &path_name, const nid_t &node_id, const bool &is_rev, const std::string &cigar, const bool &is_empty, const bool &is_circular)> &)> &for_each_path_element, bool validate=false, std::string basename="")

void	from_gfa (const std::string &gfa_filename, bool validate=false, std::string basename="")
	Use a memory-mapped GFA file to build the index in low memory. More...

void	to_gfa (std::ostream &out) const

uint32_t	get_magic_number (void) const
	Get the magic number used to prefix serialized streams. More...

size_t	serialize_and_measure (std::ostream &out, sdsl::structure_tree_node *s=nullptr, std::string name="") const
	Like serialize() (inherited from SerializableHandleGraph) but logs internal member sizes and returns total size. More...

void	dump_to_stream (std::ostream &out) const
	Dump information about the XG to the given stream for debugging. More...

virtual handle_t	get_handle (const nid_t &node_id, bool is_reverse=false) const
	Look up the handle for the node with the given ID in the given orientation. More...

virtual nid_t	get_id (const handle_t &handle) const
	Get the ID from a handle. More...

virtual bool	has_node (nid_t node_id) const
	If the node with the given id exists. More...

virtual bool	get_is_reverse (const handle_t &handle) const
	Get the orientation of a handle. More...

virtual handle_t	flip (const handle_t &handle) const
	Invert the orientation of a handle (potentially without getting its ID) More...

virtual size_t	get_length (const handle_t &handle) const
	Get the length of a node. More...

virtual std::string	get_sequence (const handle_t &handle) const

virtual bool	follow_edges_impl (const handle_t &handle, bool go_left, const std::function< bool(const handle_t &)> &iteratee) const

virtual bool	for_each_handle_impl (const std::function< bool(const handle_t &)> &iteratee, bool parallel=false) const

virtual size_t	get_node_count () const
	Return the number of nodes in the graph. More...

virtual size_t	get_edge_count () const
	Return the number of edges in the graph. More...

virtual size_t	get_total_length () const
	Return the number of bases in the graph. More...

virtual nid_t	min_node_id () const
	Get the minimum node ID used in the graph, if any are used. More...

virtual nid_t	max_node_id () const
	Get the maximum node ID used in the graph, if any are used. More...

virtual char	get_base (const handle_t &handle, size_t index) const

virtual std::string	get_subsequence (const handle_t &handle, size_t index, size_t size) const

size_t	get_path_count (void) const
	Returns the number of paths stored in the graph. More...

bool	has_path (const std::string &path_name) const
	Determine if a path with a given name exists. More...

path_handle_t	get_path_handle (const std::string &path_name) const
	Look up the path handle for the given path name. More...

std::string	get_path_name (const path_handle_t &path_handle) const
	Look up the name of a path from a handle to it. More...

bool	get_is_circular (const path_handle_t &path_handle) const
	Look up whether a path is circular. More...

size_t	get_step_count (const path_handle_t &path_handle) const
	Returns the number of node steps in the path. More...

size_t	get_path_length (const path_handle_t &path_handle) const
	Returns the total length of sequence in the path. More...

handle_t	get_handle_of_step (const step_handle_t &step_handle) const
	Get a node handle (node ID and orientation) from a handle to a step on a path. More...

path_handle_t	get_path_handle_of_step (const step_handle_t &step_handle) const
	Returns a handle to the path that an step is on. More...

step_handle_t	path_begin (const path_handle_t &path_handle) const

step_handle_t	path_end (const path_handle_t &path_handle) const

step_handle_t	path_back (const path_handle_t &path_handle) const

step_handle_t	path_front_end (const path_handle_t &path_handle) const

bool	has_next_step (const step_handle_t &step_handle) const
	Returns true if the step is not the last step in a non-circular path. More...

bool	has_previous_step (const step_handle_t &step_handle) const
	Returns true if the step is not the first step in a non-circular path. More...

step_handle_t	get_next_step (const step_handle_t &step_handle) const

step_handle_t	get_previous_step (const step_handle_t &step_handle) const

bool	for_each_path_handle_impl (const std::function< bool(const path_handle_t &)> &iteratee) const
	Execute a function on each path in the graph. More...

bool	for_each_step_on_handle_impl (const handle_t &handle, const std::function< bool(const step_handle_t &)> &iteratee) const
	Executes a function on each step of a handle in any path. More...

size_t	get_position_of_step (const step_handle_t &step) const
	Gets the position of a given step in the path it's from. More...

step_handle_t	get_step_at_position (const path_handle_t &path, const size_t &position) const
	Get the step at a given position. More...

size_t	id_to_rank (const nid_t &id) const
	id to rank helper function More...

size_t	handle_rank (const handle_t &handle) const

nid_t	rank_to_id (const size_t &rank) const
	rank to id helper function More...

size_t	max_node_rank (void) const

size_t	node_vector_offset (const nid_t &id) const

nid_t	node_at_vector_offset (const size_t &offset) const
	Return the node overlapping the given offset in the implicit node vector. More...

size_t	max_path_rank (void) const

size_t	node_graph_idx (const nid_t &id) const

const XGPath &	get_path (const std::string &name) const

std::string	path_name (const size_t &rank) const

std::vector< size_t >	path_ranks_by_prefix (const std::string &prefix) const

std::vector< std::string >	path_names_by_prefix (const std::string &prefix) const

std::vector< path_handle_t >	paths_of_handle (const handle_t &handle) const

bool	path_contains_handle (const std::string &name, const handle_t &handle) const

std::pair< pos_t, int64_t >	next_path_position (const pos_t &pos, const int64_t &max_search) const

std::pair< nid_t, std::vector< path_handle_t > >	nearest_path_node (const nid_t &id, int64_t max_steps=16) const

int64_t	min_approx_path_distance (const nid_t &id1, const nid_t &id2) const

std::vector< size_t >	position_in_path (const handle_t &handle, const path_handle_t &path) const

std::unordered_map< path_handle_t, std::vector< size_t > >	position_in_paths (const handle_t &handle, const size_t &offset) const

void	for_path_range (const std::string &name, int64_t start, int64_t stop, std::function< void(const handle_t &)> lambda, bool is_rev) const

std::unordered_map< path_handle_t, std::vector< std::pair< size_t, bool > > >	offsets_in_paths (const pos_t &gpos) const

std::unordered_map< path_handle_t, std::vector< std::pair< size_t, bool > > >	nearest_offsets_in_paths (const pos_t &pos, int64_t max_search) const

handle_t	handle_at_path_position (const path_handle_t &path, size_t pos) const

size_t	node_start_at_path_position (const path_handle_t &path, size_t pos) const

pos_t	graph_pos_at_path_position (const path_handle_t &path, size_t path_pos) const

pos_t	graph_pos_at_path_position (const std::string &name, size_t path_pos) const

char	pos_char (nid_t id, bool is_rev, size_t off) const

std::string	pos_substr (nid_t id, bool is_rev, size_t off, size_t len) const

size_t	edge_index (const edge_t &edge) const
	Return a unique index among edges in the graph. More...

size_t	get_g_iv_size (void) const

Public Member Functions inherited from handlegraph::PathPositionHandleGraph
virtual	~PathPositionHandleGraph ()=default

virtual bool	for_each_step_position_on_handle (const handle_t &handle, const std::function< bool(const step_handle_t &, const bool &, const size_t &)> &iteratee) const

Public Member Functions inherited from handlegraph::PathHandleGraph
virtual	~PathHandleGraph ()=default

virtual size_t	get_step_count (const handle_t &handle) const
	Returns the number of node steps on a handle. More...

template<typename Iteratee >
bool	for_each_path_handle (const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_step_on_handle (const handle_t &handle, const Iteratee &iteratee) const

virtual std::vector< step_handle_t >	steps_of_handle (const handle_t &handle, bool match_orientation=false) const

virtual bool	is_empty (const path_handle_t &path_handle) const
	Returns true if the given path is empty, and false otherwise. More...

PathForEachSocket	scan_path (const path_handle_t &path) const

template<typename Iteratee >
bool	for_each_step_in_path (const path_handle_t &path, const Iteratee &iteratee) const

Public Member Functions inherited from handlegraph::HandleGraph
virtual	~HandleGraph ()=default

template<typename Iteratee >
bool	follow_edges (const handle_t &handle, bool go_left, const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_handle (const Iteratee &iteratee, bool parallel=false) const

virtual size_t	get_degree (const handle_t &handle, bool go_left) const

virtual bool	has_edge (const handle_t &left, const handle_t &right) const

bool	has_edge (const edge_t &edge) const
	Convenient wrapper of has_edge for edge_t argument. More...

handle_t	forward (const handle_t &handle) const
	Get the locally forward version of a handle. More...

edge_t	edge_handle (const handle_t &left, const handle_t &right) const

handle_t	traverse_edge_handle (const edge_t &edge, const handle_t &left) const

template<typename Iteratee >
bool	for_each_edge (const Iteratee &iteratee, bool parallel=false) const

Public Member Functions inherited from handlegraph::PathMetadata
virtual	~PathMetadata ()=default

virtual PathSense	get_sense (const path_handle_t &handle) const
	What is the given path meant to be representing? More...

virtual std::string	get_sample_name (const path_handle_t &handle) const

virtual std::string	get_locus_name (const path_handle_t &handle) const

virtual size_t	get_haplotype (const path_handle_t &handle) const

virtual size_t	get_phase_block (const path_handle_t &handle) const

virtual subrange_t	get_subrange (const path_handle_t &handle) const

template<typename Iteratee >
bool	for_each_path_of_sense (const PathSense &sense, const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_path_of_sample (const std::string &sample, const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_path_matching (const std::unordered_set< PathSense > senses, const std::unordered_set< std::string > samples, const std::unordered_set< std::string > *loci, const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_path_matching (const std::unordered_set< PathSense > &senses, const std::unordered_set< std::string > &samples, const std::unordered_set< std::string > &loci, const Iteratee &iteratee) const

template<typename Iteratee >
bool	for_each_step_of_sense (const handle_t &visited, const PathSense &sense, const Iteratee &iteratee) const

Public Member Functions inherited from handlegraph::Serializable
virtual	~Serializable ()=default

virtual void	serialize (std::ostream &out) const

virtual void	serialize (const std::string &filename) const

virtual void	deserialize (std::istream &in)

virtual void	deserialize (const std::string &filename)

virtual void	serialize (std::ostream &out)

virtual void	serialize (const std::string &filename)

Public Member Functions inherited from handlegraph::VectorizableHandleGraph
virtual	~VectorizableHandleGraph ()=default

Public Member Functions inherited from handlegraph::RankedHandleGraph
virtual size_t	handle_to_rank (const handle_t &handle) const

virtual handle_t	rank_to_handle (const size_t &rank) const
	Return the handle with a given rank. More...

Public Attributes
size_t	seq_length = 0

size_t	node_count = 0

size_t	edge_count = 0

size_t	path_count = 0

Static Public Attributes
const static uint32_t	CURRENT_VERSION = 16

static const char	path_name_csa_delim = '$'

static const char	old_version_path_name_start = '#'

static const char	old_version_path_name_end = '$'

Static Public Attributes inherited from handlegraph::PathMetadata
static const std::string	NO_SAMPLE_NAME = ""

static const std::string	NO_LOCUS_NAME = ""

static const size_t	NO_HAPLOTYPE = std::numeric_limits<size_t>::max()

static const size_t	NO_PHASE_BLOCK = std::numeric_limits<size_t>::max()

static const subrange_t	NO_SUBRANGE {PathMetadata::NO_END_POSITION, PathMetadata::NO_END_POSITION}

static const offset_t	NO_END_POSITION = std::numeric_limits<offset_t>::max()

Protected Member Functions
void	deserialize_members (std::istream &in)

void	serialize_members (std::ostream &out) const
	Write the XG's contents to a stream aready prefixed with a magic number. More...

size_t	serialize_members_and_measure (std::ostream &out, sdsl::structure_tree_node *s=nullptr, std::string name="") const
	Like serialize_members() but logs internal member sizes and returns total size. More...

Protected Member Functions inherited from handlegraph::PathMetadata
virtual bool	for_each_path_matching_impl (const std::unordered_set< PathSense > senses, const std::unordered_set< std::string > samples, const std::unordered_set< std::string > *loci, const std::function< bool(const path_handle_t &)> &iteratee) const

virtual bool	for_each_step_of_sense_impl (const handle_t &visited, const PathSense &sense, const std::function< bool(const step_handle_t &)> &iteratee) const

Private Member Functions
void	orientation_from_old_edge_type (int type, bool &from_rev, bool &to_rev) const

void	reencode_old_g_vector (const sdsl::int_vector<> &old_g_iv, const sdsl::rank_support_v< 1 > &old_g_bv_rank)

void	index_path_names ()

void	index_node_to_path (const std::string &basename)

void	print_graph () const

Static Private Member Functions
static bool	edge_orientation (const uint64_t &raw_edge)

static int64_t	edge_relative_offset (const uint64_t &raw_edge)

static uint64_t	encode_edge (const size_t &offest_from, const size_t &offest_to, const bool &to_rev)

Private Attributes
sdsl::int_vector	g_iv

sdsl::bit_vector	g_bv
	delimit node records to allow lookup of nodes in g_civ by rank More...

sdsl::rank_support_v< 1 >	g_bv_rank

sdsl::bit_vector::select_1_type	g_bv_select

sdsl::int_vector	s_iv

sdsl::bit_vector	s_bv

sdsl::rank_support_v< 1 >	s_bv_rank

sdsl::bit_vector::select_1_type	s_bv_select

nid_t	min_id = 0

nid_t	max_id = 0

sdsl::int_vector	r_iv

sdsl::int_vector	pn_iv

sdsl::csa_wt	pn_csa

sdsl::bit_vector	pn_bv

sdsl::rank_support_v< 1 >	pn_bv_rank

sdsl::bit_vector::select_1_type	pn_bv_select

sdsl::int_vector	pi_iv

std::vector< XGPath * >	paths

sdsl::int_vector	np_iv

sdsl::int_vector	nr_iv

sdsl::int_vector	nx_iv

sdsl::bit_vector	np_bv

sdsl::bit_vector::select_1_type	np_bv_select

Static Private Attributes
const static int	G_NODE_ID_OFFSET = 0

const static int	G_NODE_SEQ_START_OFFSET = 1

const static int	G_NODE_LENGTH_OFFSET = 2

const static int	G_NODE_LEFT_COUNT_OFFSET = 3

const static int	G_NODE_RIGHT_COUNT_OFFSET = 4

const static int	G_NODE_HEADER_LENGTH = 5

const static int	OLD_G_NODE_TO_COUNT_OFFSET = 3

const static int	OLD_G_NODE_FROM_COUNT_OFFSET = 4

const static int	OLD_G_EDGE_OFFSET_OFFSET = 0

const static int	OLD_G_EDGE_TYPE_OFFSET = 1

const static int	OLD_G_EDGE_LENGTH = 2

const static int	OLD_EDGE_TYPE_MIN = 1

const static int	OLD_EDGE_TYPE_END_START = 1

const static int	OLD_EDGE_TYPE_END_END = 2

const static int	OLD_EDGE_TYPE_START_START = 3

const static int	OLD_EDGE_TYPE_START_END = 4

const static int	OLD_EDGE_TYPE_MAX = 4

Additional Inherited Members
Static Public Member Functions inherited from handlegraph::PathMetadata
static PathSense	parse_sense (const std::string &path_name)

static std::string	parse_sample_name (const std::string &path_name)

static std::string	parse_locus_name (const std::string &path_name)

static size_t	parse_haplotype (const std::string &path_name)

static size_t	parse_phase_block (const std::string &path_name)

static subrange_t	parse_subrange (const std::string &path_name)

static void	parse_path_name (const std::string &path_name, PathSense &sense, std::string &sample, std::string &locus, size_t &haplotype, size_t &phase_block, subrange_t &subrange)
	Decompose a formatted path name into metadata. More...

static std::string	create_path_name (const PathSense &sense, const std::string &sample, const std::string &locus, const size_t &haplotype, const size_t &phase_block, const subrange_t &subrange)

Detailed Description

Provides succinct storage for a graph, its positional paths, and a set of embedded threads.

Constructor & Destructor Documentation

◆ XG() [1/3]

xg::XG::XG ( void )

default

◆ ~XG()

xg::XG::~XG ( void )

◆ XG() [2/3]

xg::XG::XG ( const XG & other )

delete

◆ XG() [3/3]

xg::XG::XG ( XG && other )

delete

Member Function Documentation

◆ deserialize_members()

void xg::XG::deserialize_members ( std::istream & in )

protectedvirtual

Load this XG index from a stream from which the magic number has already been read. Throw an XGFormatError if the stream does not produce a valid XG file.

Implements handlegraph::Serializable.

◆ dump_to_stream()

void xg::XG::dump_to_stream ( std::ostream & out ) const

Dump information about the XG to the given stream for debugging.

◆ edge_index()

size_t xg::XG::edge_index ( const edge_t & edge ) const

virtual

Return a unique index among edges in the graph.

Implements handlegraph::VectorizableHandleGraph.

◆ edge_orientation()

bool xg::XG::edge_orientation ( const uint64_t & raw_edge )

staticprivate

◆ edge_relative_offset()

int64_t xg::XG::edge_relative_offset ( const uint64_t & raw_edge )

staticprivate

◆ encode_edge()

uint64_t xg::XG::encode_edge	(	const size_t &	offest_from,
		const size_t &	offest_to,
		const bool &	to_rev
	)

staticprivate

◆ flip()

handle_t xg::XG::flip ( const handle_t & handle ) const

virtual

Invert the orientation of a handle (potentially without getting its ID)

Implements handlegraph::HandleGraph.

◆ follow_edges_impl()

bool xg::XG::follow_edges_impl	(	const handle_t &	handle,
		bool	go_left,
		const std::function< bool(const handle_t &)> &	iteratee
	)		const

virtual

Loop over all the handles to next/previous (right/left) nodes. Passes them to a callback which returns false to stop iterating and true to continue.

Implements handlegraph::HandleGraph.

◆ for_each_handle_impl()

bool xg::XG::for_each_handle_impl	(	const std::function< bool(const handle_t &)> &	iteratee,
		bool	parallel = `false`
	)		const

virtual

Loop over all the nodes in the graph in their local forward orientations, in their internal stored order. Stop if the iteratee returns false.

Implements handlegraph::HandleGraph.

◆ for_each_path_handle_impl()

bool xg::XG::for_each_path_handle_impl ( const std::function< bool(const path_handle_t &)> & iteratee ) const

virtual

Execute a function on each path in the graph.

Implements handlegraph::PathHandleGraph.

◆ for_each_step_on_handle_impl()

bool xg::XG::for_each_step_on_handle_impl	(	const handle_t &	handle,
		const std::function< bool(const step_handle_t &)> &	iteratee
	)		const

virtual

Executes a function on each step of a handle in any path.

Implements handlegraph::PathHandleGraph.

◆ for_path_range()

void xg::XG::for_path_range	(	const std::string &	name,
		int64_t	start,
		int64_t	stop,
		std::function< void(const handle_t &)>	lambda,
		bool	is_rev
	)		const

◆ from_enumerators()

void xg::XG::from_enumerators	(	const std::function< void(const std::function< void(const std::string &seq, const nid_t &node_id)> &)> &	for_each_sequence,
		const std::function< void(const std::function< void(const nid_t &from, const bool &from_rev, const nid_t &to, const bool &to_rev)> &)> &	for_each_edge,
		const std::function< void(const std::function< void(const std::string &path_name, const nid_t &node_id, const bool &is_rev, const std::string &cigar, const bool &is_empty, const bool &is_circular)> &)> &	for_each_path_element,
		bool	validate = `false`,
		std::string	basename = `""`
	)

Use external enumerators to drive graph construction. The order in which nodes are enumerated becomes the XG's node order. Note that we will get the best efficiency if the graph is enumerated in topological order.

◆ from_gfa()

void xg::XG::from_gfa	(	const std::string &	gfa_filename,
		bool	validate = `false`,
		std::string	basename = `""`
	)

Use a memory-mapped GFA file to build the index in low memory.

◆ from_handle_graph()

void xg::XG::from_handle_graph ( const HandleGraph & graph )

build the graph from another simple graph

Build the graph from another simple graph. The order in which nodes are enumerated becomes the XG's node order. Note that we will get the best efficiency if the graph enumerates itself in topological order.

◆ from_path_handle_graph()

void xg::XG::from_path_handle_graph ( const PathHandleGraph & graph )

build the graph from another path handle graph

Build the graph from another path handle graph. The order in which nodes are enumerated becomes the XG's node order. Note that we will get the best efficiency if the graph enumerates itself in topological order.

◆ get_base()

char xg::XG::get_base	(	const handle_t &	handle,
		size_t	index
	)		const

virtual

Returns one base of a handle's sequence, in the orientation of the handle.

Reimplemented from handlegraph::HandleGraph.

◆ get_edge_count()

size_t xg::XG::get_edge_count ( ) const

virtual

Return the number of edges in the graph.

Reimplemented from handlegraph::HandleGraph.

◆ get_g_iv_size()

size_t xg::XG::get_g_iv_size ( void ) const

◆ get_handle()

handle_t xg::XG::get_handle	(	const nid_t &	node_id,
		bool	is_reverse = `false`
	)		const

virtual

Look up the handle for the node with the given ID in the given orientation.

Implements handlegraph::HandleGraph.

◆ get_handle_of_step()

handle_t xg::XG::get_handle_of_step ( const step_handle_t & step_handle ) const

virtual

Get a node handle (node ID and orientation) from a handle to a step on a path.

Implements handlegraph::PathHandleGraph.

◆ get_id()

nid_t xg::XG::get_id ( const handle_t & handle ) const

virtual

Get the ID from a handle.

Implements handlegraph::HandleGraph.

◆ get_is_circular()

bool xg::XG::get_is_circular ( const path_handle_t & path_handle ) const

virtual

Look up whether a path is circular.

Implements handlegraph::PathHandleGraph.

◆ get_is_reverse()

bool xg::XG::get_is_reverse ( const handle_t & handle ) const

virtual

Get the orientation of a handle.

Implements handlegraph::HandleGraph.

◆ get_length()

size_t xg::XG::get_length ( const handle_t & handle ) const

virtual

Get the length of a node.

Implements handlegraph::HandleGraph.

◆ get_magic_number()

uint32_t xg::XG::get_magic_number ( void ) const

virtual

Get the magic number used to prefix serialized streams.

Implements handlegraph::Serializable.

◆ get_next_step()

step_handle_t xg::XG::get_next_step ( const step_handle_t & step_handle ) const

virtual

Returns a handle to the next step on the path. If the given step is the final step of a non-circular path, returns the past-the-last step that is also returned by path_end. In a circular path, the "last" step will loop around to the "first" (i.e. the one returned by path_begin). Note: to iterate over each step one time, even in a circular path, consider for_each_step_in_path.

Implements handlegraph::PathHandleGraph.

◆ get_node_count()

size_t xg::XG::get_node_count ( ) const

virtual

Return the number of nodes in the graph.

Implements handlegraph::HandleGraph.

◆ get_path()

const XGPath& xg::XG::get_path ( const std::string & name ) const

◆ get_path_count()

size_t xg::XG::get_path_count ( void ) const

virtual

Returns the number of paths stored in the graph.

Implements handlegraph::PathHandleGraph.

◆ get_path_handle()

path_handle_t xg::XG::get_path_handle ( const std::string & path_name ) const

virtual

Look up the path handle for the given path name.

Implements handlegraph::PathHandleGraph.

◆ get_path_handle_of_step()

path_handle_t xg::XG::get_path_handle_of_step ( const step_handle_t & step_handle ) const

virtual

Returns a handle to the path that an step is on.

Implements handlegraph::PathHandleGraph.

◆ get_path_length()

size_t xg::XG::get_path_length ( const path_handle_t & path_handle ) const

virtual

Returns the total length of sequence in the path.

Implements handlegraph::PathPositionHandleGraph.

◆ get_path_name()

std::string xg::XG::get_path_name ( const path_handle_t & path_handle ) const

virtual

Look up the name of a path from a handle to it.

Implements handlegraph::PathHandleGraph.

◆ get_position_of_step()

size_t xg::XG::get_position_of_step ( const step_handle_t & step ) const

virtual

Gets the position of a given step in the path it's from.

Implements handlegraph::PathPositionHandleGraph.

◆ get_previous_step()

step_handle_t xg::XG::get_previous_step ( const step_handle_t & step_handle ) const

virtual

Returns a handle to the previous step on the path. If the given step is the first step of a non-circular path, this method has undefined behavior. In a circular path, it will loop around from the "first" step (i.e. the one returned by path_begin) to the "last" step. Note: to iterate over each step one time, even in a circular path, consider for_each_step_in_path.

Implements handlegraph::PathHandleGraph.

◆ get_sequence()

std::string xg::XG::get_sequence ( const handle_t & handle ) const

virtual

Get the sequence of a node, presented in the handle's local forward orientation.

Implements handlegraph::HandleGraph.

◆ get_step_at_position()

step_handle_t xg::XG::get_step_at_position	(	const path_handle_t &	path,
		const size_t &	position
	)		const

virtual

Get the step at a given position.

Implements handlegraph::PathPositionHandleGraph.

◆ get_step_count()

size_t xg::XG::get_step_count ( const path_handle_t & path_handle ) const

virtual

Returns the number of node steps in the path.

Implements handlegraph::PathHandleGraph.

◆ get_subsequence()

std::string xg::XG::get_subsequence	(	const handle_t &	handle,
		size_t	index,
		size_t	size
	)		const

virtual

Returns a substring of a handle's sequence, in the orientation of the handle. If the indicated substring would extend beyond the end of the handle's sequence, the return value is truncated to the sequence's end.

Reimplemented from handlegraph::HandleGraph.

◆ get_total_length()

size_t xg::XG::get_total_length ( ) const

virtual

Return the number of bases in the graph.

Reimplemented from handlegraph::HandleGraph.

◆ graph_pos_at_path_position() [1/2]

pos_t xg::XG::graph_pos_at_path_position	(	const path_handle_t &	path,
		size_t	path_pos
	)		const

◆ graph_pos_at_path_position() [2/2]

pos_t xg::XG::graph_pos_at_path_position	(	const std::string &	name,
		size_t	path_pos
	)		const

◆ handle_at_path_position()

handle_t xg::XG::handle_at_path_position	(	const path_handle_t &	path,
		size_t	pos
	)		const

◆ handle_rank()

size_t xg::XG::handle_rank ( const handle_t & handle ) const

◆ has_next_step()

bool xg::XG::has_next_step ( const step_handle_t & step_handle ) const

virtual

Returns true if the step is not the last step in a non-circular path.

Implements handlegraph::PathHandleGraph.

◆ has_node()

bool xg::XG::has_node ( nid_t node_id ) const

virtual

If the node with the given id exists.

Implements handlegraph::HandleGraph.

◆ has_path()

bool xg::XG::has_path ( const std::string & path_name ) const

virtual

Determine if a path with a given name exists.

Implements handlegraph::PathHandleGraph.

◆ has_previous_step()

bool xg::XG::has_previous_step ( const step_handle_t & step_handle ) const

virtual

Returns true if the step is not the first step in a non-circular path.

Implements handlegraph::PathHandleGraph.

◆ id_to_rank()

size_t xg::XG::id_to_rank ( const nid_t & id ) const

virtual

id to rank helper function

Implements handlegraph::RankedHandleGraph.

◆ index_node_to_path()

void xg::XG::index_node_to_path ( const std::string & basename )

private

◆ index_path_names()

void xg::XG::index_path_names ( )

private

◆ max_node_id()

nid_t xg::XG::max_node_id ( ) const

virtual

Get the maximum node ID used in the graph, if any are used.

Implements handlegraph::HandleGraph.

◆ max_node_rank()

size_t xg::XG::max_node_rank ( void ) const

◆ max_path_rank()

size_t xg::XG::max_path_rank ( void ) const

◆ min_approx_path_distance()

int64_t xg::XG::min_approx_path_distance	(	const nid_t &	id1,
		const nid_t &	id2
	)		const

◆ min_node_id()

nid_t xg::XG::min_node_id ( ) const

virtual

Get the minimum node ID used in the graph, if any are used.

Implements handlegraph::HandleGraph.

◆ nearest_offsets_in_paths()

std::unordered_map< path_handle_t, std::vector< std::pair< size_t, bool > > > xg::XG::nearest_offsets_in_paths	(	const pos_t &	pos,
		int64_t	max_search
	)		const

◆ nearest_path_node()

std::pair< nid_t, std::vector< path_handle_t > > xg::XG::nearest_path_node	(	const nid_t &	id,
		int64_t	max_steps = `16`
	)		const

◆ next_path_position()

std::pair< pos_t, int64_t > xg::XG::next_path_position	(	const pos_t &	pos,
		const int64_t &	max_search
	)		const

◆ node_at_vector_offset()

nid_t xg::XG::node_at_vector_offset ( const size_t & offset ) const

virtual

Return the node overlapping the given offset in the implicit node vector.

Implements handlegraph::VectorizableHandleGraph.

◆ node_graph_idx()

size_t xg::XG::node_graph_idx ( const nid_t & id ) const

◆ node_start_at_path_position()

size_t xg::XG::node_start_at_path_position	(	const path_handle_t &	path,
		size_t	pos
	)		const

◆ node_vector_offset()

size_t xg::XG::node_vector_offset ( const nid_t & node_id ) const

virtual

Return the start position of the node in a (possibly implict) sorted array constructed from the concatenation of the node sequences

Implements handlegraph::VectorizableHandleGraph.

◆ offsets_in_paths()

std::unordered_map< path_handle_t, std::vector< std::pair< size_t, bool > > > xg::XG::offsets_in_paths ( const pos_t & gpos ) const

◆ operator=() [1/2]

XG& xg::XG::operator= ( const XG & other )

delete

◆ operator=() [2/2]

XG& xg::XG::operator= ( XG && other )

delete

◆ orientation_from_old_edge_type()

void xg::XG::orientation_from_old_edge_type	(	int	type,
		bool &	from_rev,
		bool &	to_rev
	)		const

private

◆ path_back()

step_handle_t xg::XG::path_back ( const path_handle_t & path_handle ) const

virtual

Get a handle to the last step, which will be an arbitrary step in a circular path that we consider "last" based on our construction of the path. If the path is empty then the implementation must return the same value as path_front_end().

Implements handlegraph::PathHandleGraph.

◆ path_begin()

step_handle_t xg::XG::path_begin ( const path_handle_t & path_handle ) const

virtual

Get a handle to the first step, or in a circular path to an arbitrary step considered "first". If the path is empty, returns the past-the-last step returned by path_end.

Implements handlegraph::PathHandleGraph.

◆ path_contains_handle()

bool xg::XG::path_contains_handle	(	const std::string &	name,
		const handle_t &	handle
	)		const

◆ path_end()

step_handle_t xg::XG::path_end ( const path_handle_t & path_handle ) const

virtual

Get a handle to a fictitious position past the end of a path. This position is return by get_next_step for the final step in a path in a non-circular path. Note that get_next_step will NEVER return this value for a circular path.

Implements handlegraph::PathHandleGraph.

◆ path_front_end()

step_handle_t xg::XG::path_front_end ( const path_handle_t & path_handle ) const

virtual

Get a handle to a fictitious position before the beginning of a path. This position is return by get_previous_step for the first step in a path in a non-circular path. Note: get_previous_step will NEVER return this value for a circular path.

Implements handlegraph::PathHandleGraph.

◆ path_name()

std::string xg::XG::path_name ( const size_t & rank ) const

◆ path_names_by_prefix()

std::vector<std::string> xg::XG::path_names_by_prefix ( const std::string & prefix ) const

◆ path_ranks_by_prefix()

std::vector<size_t> xg::XG::path_ranks_by_prefix ( const std::string & prefix ) const

◆ paths_of_handle()

std::vector< path_handle_t > xg::XG::paths_of_handle ( const handle_t & handle ) const

◆ pos_char()

char xg::XG::pos_char	(	nid_t	id,
		bool	is_rev,
		size_t	off
	)		const

◆ pos_substr()

std::string xg::XG::pos_substr	(	nid_t	id,
		bool	is_rev,
		size_t	off,
		size_t	len
	)		const

◆ position_in_path()

std::vector< size_t > xg::XG::position_in_path	(	const handle_t &	handle,
		const path_handle_t &	path
	)		const

◆ position_in_paths()

std::unordered_map< path_handle_t, std::vector< size_t > > xg::XG::position_in_paths	(	const handle_t &	handle,
		const size_t &	offset
	)		const

◆ print_graph()

void xg::XG::print_graph ( ) const

private

◆ rank_to_id()

nid_t xg::XG::rank_to_id ( const size_t & rank ) const

virtual

rank to id helper function

Implements handlegraph::RankedHandleGraph.

◆ reencode_old_g_vector()

void xg::XG::reencode_old_g_vector	(	const sdsl::int_vector<> &	old_g_iv,
		const sdsl::rank_support_v< 1 > &	old_g_bv_rank
	)

private

◆ serialize_and_measure()

size_t xg::XG::serialize_and_measure	(	std::ostream &	out,
		sdsl::structure_tree_node *	s = `nullptr`,
		std::string	name = `""`
	)		const

Like serialize() (inherited from SerializableHandleGraph) but logs internal member sizes and returns total size.

◆ serialize_members()

void xg::XG::serialize_members ( std::ostream & out ) const

protectedvirtual

Write the XG's contents to a stream aready prefixed with a magic number.

Implements handlegraph::Serializable.

◆ serialize_members_and_measure()

size_t xg::XG::serialize_members_and_measure	(	std::ostream &	out,
		sdsl::structure_tree_node *	s = `nullptr`,
		std::string	name = `""`
	)		const

protected

Like serialize_members() but logs internal member sizes and returns total size.

◆ to_gfa()

void xg::XG::to_gfa ( std::ostream & out ) const

Member Data Documentation

◆ CURRENT_VERSION

const static uint32_t xg::XG::CURRENT_VERSION = 16

static

◆ edge_count

size_t xg::XG::edge_count = 0

◆ g_bv

sdsl::bit_vector xg::XG::g_bv

private

delimit node records to allow lookup of nodes in g_civ by rank

◆ g_bv_rank

sdsl::rank_support_v<1> xg::XG::g_bv_rank

private

◆ g_bv_select

sdsl::bit_vector::select_1_type xg::XG::g_bv_select

private

◆ g_iv

sdsl::int_vector xg::XG::g_iv

private

locally traversable graph storage

Encoding designed for efficient compression, cache locality, and relativistic traversal of the graph.

node := { header, left_side_edges, right_side_edges } header := { node_id, node_start, node_length, edges_left_count, edges_right_count } node_id := integer node_start := integer (offset in s_iv) node_length := integer edges_left_count := integer edges_right_count := integer left_side_edges := { edge, ... } right_side_edges := { edge, ... } edge := { relative_offset | target_is_rev } (bit-packed)

targets are considered reverse if you should end up on their reverse strand by traversing left out of left side edges or traversing right out of right side edges (starting on the forward strand).
relative offset is converted to positive numbers with this mapping 0 -1 1 -2 2 ... 0 1 2 3 4 ... TODO: most edges will be separated in increments of at least the header length, this could be exploited to have a more efficient encoding

◆ G_NODE_HEADER_LENGTH

const static int xg::XG::G_NODE_HEADER_LENGTH = 5

staticprivate

◆ G_NODE_ID_OFFSET

const static int xg::XG::G_NODE_ID_OFFSET = 0

staticprivate

◆ G_NODE_LEFT_COUNT_OFFSET

const static int xg::XG::G_NODE_LEFT_COUNT_OFFSET = 3

staticprivate

◆ G_NODE_LENGTH_OFFSET

const static int xg::XG::G_NODE_LENGTH_OFFSET = 2

staticprivate

◆ G_NODE_RIGHT_COUNT_OFFSET

const static int xg::XG::G_NODE_RIGHT_COUNT_OFFSET = 4

staticprivate

◆ G_NODE_SEQ_START_OFFSET

const static int xg::XG::G_NODE_SEQ_START_OFFSET = 1

staticprivate

◆ max_id

nid_t xg::XG::max_id = 0

private

◆ min_id

nid_t xg::XG::min_id = 0

private

◆ node_count

size_t xg::XG::node_count = 0

◆ np_bv

sdsl::bit_vector xg::XG::np_bv

private

◆ np_bv_select

sdsl::bit_vector::select_1_type xg::XG::np_bv_select

private

◆ np_iv

sdsl::int_vector xg::XG::np_iv

private

◆ nr_iv

sdsl::int_vector xg::XG::nr_iv

private

◆ nx_iv

sdsl::int_vector xg::XG::nx_iv

private

◆ OLD_EDGE_TYPE_END_END

const static int xg::XG::OLD_EDGE_TYPE_END_END = 2

staticprivate

◆ OLD_EDGE_TYPE_END_START

const static int xg::XG::OLD_EDGE_TYPE_END_START = 1

staticprivate

◆ OLD_EDGE_TYPE_MAX

const static int xg::XG::OLD_EDGE_TYPE_MAX = 4

staticprivate

◆ OLD_EDGE_TYPE_MIN

const static int xg::XG::OLD_EDGE_TYPE_MIN = 1

staticprivate

◆ OLD_EDGE_TYPE_START_END

const static int xg::XG::OLD_EDGE_TYPE_START_END = 4

staticprivate

◆ OLD_EDGE_TYPE_START_START

const static int xg::XG::OLD_EDGE_TYPE_START_START = 3

staticprivate

◆ OLD_G_EDGE_LENGTH

const static int xg::XG::OLD_G_EDGE_LENGTH = 2

staticprivate

◆ OLD_G_EDGE_OFFSET_OFFSET

const static int xg::XG::OLD_G_EDGE_OFFSET_OFFSET = 0

staticprivate

◆ OLD_G_EDGE_TYPE_OFFSET

const static int xg::XG::OLD_G_EDGE_TYPE_OFFSET = 1

staticprivate

◆ OLD_G_NODE_FROM_COUNT_OFFSET

const static int xg::XG::OLD_G_NODE_FROM_COUNT_OFFSET = 4

staticprivate

◆ OLD_G_NODE_TO_COUNT_OFFSET

const static int xg::XG::OLD_G_NODE_TO_COUNT_OFFSET = 3

staticprivate

◆ old_version_path_name_end

const char xg::XG::old_version_path_name_end = '$'

static

◆ old_version_path_name_start

const char xg::XG::old_version_path_name_start = '#'

static

◆ path_count

size_t xg::XG::path_count = 0

◆ path_name_csa_delim

const char xg::XG::path_name_csa_delim = '$'

static

◆ paths

std::vector<XGPath*> xg::XG::paths

private

◆ pi_iv

sdsl::int_vector xg::XG::pi_iv

private

◆ pn_bv

sdsl::bit_vector xg::XG::pn_bv

private

◆ pn_bv_rank

sdsl::rank_support_v<1> xg::XG::pn_bv_rank

private

◆ pn_bv_select

sdsl::bit_vector::select_1_type xg::XG::pn_bv_select

private

◆ pn_csa

sdsl::csa_wt xg::XG::pn_csa

private

◆ pn_iv

sdsl::int_vector xg::XG::pn_iv

private

◆ r_iv

sdsl::int_vector xg::XG::r_iv

private

◆ s_bv

sdsl::bit_vector xg::XG::s_bv

private

◆ s_bv_rank

sdsl::rank_support_v<1> xg::XG::s_bv_rank

private

◆ s_bv_select

sdsl::bit_vector::select_1_type xg::XG::s_bv_select

private

◆ s_iv

sdsl::int_vector xg::XG::s_iv

private

◆ seq_length

size_t xg::XG::seq_length = 0

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

deps/xg/src/xg.hpp
deps/xg/src/xg.cpp

Public Member Functions

Public Attributes

Static Public Attributes

Protected Member Functions

Private Member Functions

Static Private Member Functions

Private Attributes

Static Private Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ XG() [1/3]

◆ ~XG()

◆ XG() [2/3]

◆ XG() [3/3]

Member Function Documentation

◆ deserialize_members()

◆ dump_to_stream()

◆ edge_index()

◆ edge_orientation()

◆ edge_relative_offset()

◆ encode_edge()

◆ flip()

◆ follow_edges_impl()

◆ for_each_handle_impl()

◆ for_each_path_handle_impl()

◆ for_each_step_on_handle_impl()

◆ for_path_range()

◆ from_enumerators()

◆ from_gfa()

◆ from_handle_graph()

◆ from_path_handle_graph()

◆ get_base()

◆ get_edge_count()

◆ get_g_iv_size()

◆ get_handle()

◆ get_handle_of_step()

◆ get_id()

◆ get_is_circular()

◆ get_is_reverse()

◆ get_length()

◆ get_magic_number()

◆ get_next_step()

◆ get_node_count()

◆ get_path()

◆ get_path_count()

◆ get_path_handle()

◆ get_path_handle_of_step()

◆ get_path_length()

◆ get_path_name()

◆ get_position_of_step()

◆ get_previous_step()

◆ get_sequence()

◆ get_step_at_position()

◆ get_step_count()

◆ get_subsequence()

◆ get_total_length()

◆ graph_pos_at_path_position() [1/2]

◆ graph_pos_at_path_position() [2/2]

◆ handle_at_path_position()

◆ handle_rank()

◆ has_next_step()

◆ has_node()

◆ has_path()

◆ has_previous_step()

◆ id_to_rank()

◆ index_node_to_path()

◆ index_path_names()

◆ max_node_id()

◆ max_node_rank()

◆ max_path_rank()

◆ min_approx_path_distance()

◆ min_node_id()

◆ nearest_offsets_in_paths()

◆ nearest_path_node()

◆ next_path_position()

◆ node_at_vector_offset()

◆ node_graph_idx()

◆ node_start_at_path_position()

◆ node_vector_offset()