Pattern class holds a regex pattern and its compiled FSM opcode table or code for the reflex::Matcher engine. More...

#include <pattern.h>

Collaboration diagram for reflex::Pattern:

[legend]

Classes
struct	Error
	Throwable error structure reflex::Pattern::Error. More...

struct	Option
	Global modifier modes, syntax flags, and compiler options. More...

struct	Position
	Finite state machine construction position information. More...

struct	State
	Finite state machine. More...

Public Types
enum	Const { IMAX = 0xffff }
	Common constants. More...

typedef uint16_t	Index
	index into opcodes array Pattern::opc_ and subpattern indexing More...

typedef uint32_t	Opcode
	32 bit opcode word More...

typedef void(*	FSM) (class Matcher &)

Public Member Functions
	Pattern (const char regex, const char options=NULL) throw (Error)
	Construct a pattern object given a regex string. More...

	Pattern (const char *regex, const std::string &options) throw (Error)
	Construct a pattern object given a regex string. More...

	Pattern (const std::string &regex, const char *options=NULL) throw (Error)
	Construct a pattern object given a regex string. More...

	Pattern (const std::string &regex, const std::string &options) throw (Error)
	Construct a pattern object given a regex string. More...

	Pattern (const Opcode *code) throw (Error)
	Construct a pattern object given an opcode table. More...

	Pattern (FSM fsm) throw (Error)
	Construct a pattern object given a function pointer to FSM code. More...

virtual	~Pattern (void)
	Destructor, deletes internal code array when owned and allocated. More...

Index	size (void) const
	Number of subpatterns of this pattern object. More...

const std::string	operator[] (Index choice) const
	Get subpattern of this pattern object. More...

bool	reachable (Index choice) const
	Check is subpattern is reachable by a match. More...

size_t	nodes (void) const
	Get the number of finite state machine nodes (vertices). More...

size_t	edges (void) const
	Get the number of finite state machine edges (transitions on input characters). More...

size_t	words (void) const
	Get the code size in number of words. More...

Protected Member Functions
virtual void	error (enum Error::Code code, const char *message, size_t loc=0) const throw (Error)
	Throw an error. More...

Private Types
enum	Meta { META_MIN = 0x100, META_NWB = 0x101, META_NWE = 0x102, META_BWB = 0x103, META_EWB = 0x104, META_BWE = 0x105, META_EWE = 0x106, META_BOL = 0x107, META_EOL = 0x108, META_BOB = 0x109, META_EOB = 0x10a, META_IND = 0x10b, META_DED = 0x10c, META_MAX }
	Meta characters. More...

typedef unsigned int	Char

typedef ORanges< Char >	Chars
	represent (wide) char set as a set of ranges More...

typedef size_t	Location

typedef ORanges< Location >	Ranges

typedef std::set< Location >	Set

typedef std::map< int, Ranges >	Map

typedef std::set< Position >	Positions

typedef std::map< Position, Positions >	Follow

typedef std::pair< Chars, Positions >	Move

typedef std::list< Move >	Moves

Private Member Functions
void	init (const char *options) throw (Error)
	Initialize the pattern at construction. More...

void	init_options (const char *options)

void	parse (Positions &startpos, Follow &followpos, Map &modifiers, Map &lookahead) throw (Error)

void	parse1 (bool begin, Location &loc, Positions &firstpos, Positions &lastpos, bool &nullable, Follow &followpos, Positions &lazypos, Map &modifiers, Ranges &lookahead, Index &iter) throw (Error)

void	parse2 (bool begin, Location &loc, Positions &firstpos, Positions &lastpos, bool &nullable, Follow &followpos, Positions &lazypos, Map &modifiers, Ranges &lookahead, Index &iter) throw (Error)

void	parse3 (bool begin, Location &loc, Positions &firstpos, Positions &lastpos, bool &nullable, Follow &followpos, Positions &lazypos, Map &modifiers, Ranges &lookahead, Index &iter) throw (Error)

void	parse4 (bool begin, Location &loc, Positions &firstpos, Positions &lastpos, bool &nullable, Follow &followpos, Positions &lazypos, Map &modifiers, Ranges &lookahead, Index &iter) throw (Error)

void	parse_esc (Location &loc) const throw (Error)

void	compile (State &start, Follow &followpos, const Map &modifiers, const Map &lookahead) throw (Error)

void	lazy (const Positions &lazypos, Positions &pos) const

void	lazy (const Positions &lazypos, const Positions &pos, Positions &pos1) const

void	greedy (Positions &pos) const

void	trim_lazy (Positions &pos) const

void	compile_transition (State *state, Follow &followpos, const Map &modifiers, const Map &lookahead, Moves &moves) const throw (Error)

void	transition (Moves &moves, const Chars &chars, const Positions &follow) const

Char	compile_esc (Location loc, Chars &chars) const throw (Error)

void	compile_list (Location loc, Chars &chars, const Map &modifiers) const throw (Error)

void	posix (size_t index, Chars &chars) const

void	flip (Chars &chars) const

void	assemble (State &start) throw (Error)

void	compact_dfa (State &start)

void	encode_dfa (State &start) throw (Error)

void	gencode_dfa (const State &start) const

void	gencode_dfa_closure (FILE fd, const State start, int nest) const

void	delete_dfa (State &start)

void	export_dfa (const State &start) const

void	export_code (void) const

Location	find_at (Location loc, char c) const

Char	at (Location k) const

bool	eq_at (Location loc, const char *s) const

Char	escape_at (Location loc) const

Char	escapes_at (Location loc, const char *escapes) const

Static Private Member Functions
static bool	is_modified (int mode, const Map &modifiers, Location loc)

static bool	is_meta (Char c)

static Opcode	opcode_take (Index index)

static Opcode	opcode_redo (void)

static Opcode	opcode_tail (Index index)

static Opcode	opcode_head (Index index)

static Opcode	opcode_goto (Char lo, Char hi, Index index)

static Opcode	opcode_halt (void)

static bool	is_opcode_redo (Opcode opcode)

static bool	is_opcode_take (Opcode opcode)

static bool	is_opcode_tail (Opcode opcode)

static bool	is_opcode_head (Opcode opcode)

static bool	is_opcode_halt (Opcode opcode)

static bool	is_opcode_meta (Opcode opcode)

static bool	is_opcode_meta (Opcode opcode, Char a)

static bool	is_opcode_match (Opcode opcode, unsigned char c)

static Char	meta_of (Opcode opcode)

static Char	lo_of (Opcode opcode)

static Char	hi_of (Opcode opcode)

static Index	index_of (Opcode opcode)

Private Attributes
Option	opt_
	pattern compiler options More...

std::string	rex_
	regular expression string More...

std::vector< Location >	end_
	entries point to the subpattern's ending '\|' or '\0' More...

std::vector< bool >	acc_
	true if subpattern n is acceptable (state is reachable) More...

size_t	vno_
	number of finite state machine vertices \|V\| More...

size_t	eno_
	number of finite state machine edges \|E\| More...

const Opcode *	opc_
	points to the opcode table More...

Index	nop_
	number of opcodes generated More...

FSM	fsm_
	function pointer to FSM code More...

Friends
class	Matcher
	permit access by the reflex::Matcher engine More...

Detailed Description

Pattern class holds a regex pattern and its compiled FSM opcode table or code for the reflex::Matcher engine.

More info TODO

Member Typedef Documentation

typedef unsigned int reflex::Pattern::Char

private

typedef ORanges<Char> reflex::Pattern::Chars

private

represent (wide) char set as a set of ranges

typedef std::map<Position,Positions> reflex::Pattern::Follow

private

typedef void(* reflex::Pattern::FSM) (class Matcher &)

function pointer to FSM code

typedef uint16_t reflex::Pattern::Index

index into opcodes array Pattern::opc_ and subpattern indexing

typedef size_t reflex::Pattern::Location

private

typedef std::map<int,Ranges> reflex::Pattern::Map

private

typedef std::pair<Chars,Positions> reflex::Pattern::Move

private

typedef std::list<Move> reflex::Pattern::Moves

private

typedef uint32_t reflex::Pattern::Opcode

32 bit opcode word

typedef std::set<Position> reflex::Pattern::Positions

private

typedef ORanges<Location> reflex::Pattern::Ranges

private

typedef std::set<Location> reflex::Pattern::Set

private

Member Enumeration Documentation

enum reflex::Pattern::Const

Common constants.

Enumerator
IMAX	max index, also serves as a marker

enum reflex::Pattern::Meta

private

Meta characters.

Enumerator
META_MIN
META_NWB	non-word at begin `\Bx`
META_NWE	non-word at end `x\B`
META_BWB	begin of word at begin `\<x`
META_EWB	end of word at begin `\>x`
META_BWE	begin of word at end `x\<`
META_EWE	end of word at end `x\>`
META_BOL	begin of line `^`
META_EOL	end of line `$`
META_BOB	begin of buffer `\A`
META_EOB	end of buffer `\Z`
META_IND	indent boundary `\i`
META_DED	dedent boundary `\j` (must be the largest META code)
META_MAX	max meta characters

Constructor & Destructor Documentation

reflex::Pattern::Pattern	(	const char *	regex,
		const char *	options = `NULL`
	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given a regex string.

reflex::Pattern::Pattern	(	const char *	regex,
		const std::string &	options
	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given a regex string.

reflex::Pattern::Pattern	(	const std::string &	regex,
		const char *	options = `NULL`
	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given a regex string.

reflex::Pattern::Pattern	(	const std::string &	regex,
		const std::string &	options
	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given a regex string.

reflex::Pattern::Pattern	(	const Opcode *	code	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given an opcode table.

reflex::Pattern::Pattern	(	FSM	fsm	)
throw	(	Error
	)

inlineexplicit

Construct a pattern object given a function pointer to FSM code.

virtual reflex::Pattern::~Pattern ( void )

inlinevirtual

Destructor, deletes internal code array when owned and allocated.

Member Function Documentation

void reflex::Pattern::assemble	(	State &	start	)
throw	(	Error
	)

private

Char reflex::Pattern::at ( Location k ) const

inlineprivate

void reflex::Pattern::compact_dfa ( State & start )

private

void reflex::Pattern::compile	(	State &	start,
		Follow &	followpos,
		const Map &	modifiers,
		const Map &	lookahead
	)
throw	(	Error
	)

private

Char reflex::Pattern::compile_esc	(	Location	loc,
		Chars &	chars
	)		const
throw	(	Error
	)

private

void reflex::Pattern::compile_list	(	Location	loc,
		Chars &	chars,
		const Map &	modifiers
	)		const
throw	(	Error
	)

private

void reflex::Pattern::compile_transition	(	State *	state,
		Follow &	followpos,
		const Map &	modifiers,
		const Map &	lookahead,
		Moves &	moves
	)		const
throw	(	Error
	)

private

void reflex::Pattern::delete_dfa ( State & start )

private

size_t reflex::Pattern::edges ( void ) const

inline

Get the number of finite state machine edges (transitions on input characters).

Returns: number of edges or 0 when no finite state machine was constructed by this pattern.

void reflex::Pattern::encode_dfa	(	State &	start	)
throw	(	Error
	)

private

bool reflex::Pattern::eq_at	(	Location	loc,
		const char *	s
	)		const

inlineprivate

virtual void reflex::Pattern::error	(	enum Error::Code	code,
		const char *	message,
		size_t	loc = `0`
	)		const
throw	(	Error
	)

protectedvirtual

Throw an error.

Parameters

code	error code
message	a human-readable error message (not NULL)
loc	optional location of the error in regex string Pattern::rex_

Char reflex::Pattern::escape_at ( Location loc ) const

inlineprivate

Char reflex::Pattern::escapes_at	(	Location	loc,
		const char *	escapes
	)		const

inlineprivate

void reflex::Pattern::export_code ( void ) const

private

void reflex::Pattern::export_dfa ( const State & start ) const

private

Location reflex::Pattern::find_at	(	Location	loc,
		char	c
	)		const

inlineprivate

void reflex::Pattern::flip ( Chars & chars ) const

private

void reflex::Pattern::gencode_dfa ( const State & start ) const

private

void reflex::Pattern::gencode_dfa_closure	(	FILE *	fd,
		const State *	start,
		int	nest
	)		const

private

void reflex::Pattern::greedy ( Positions & pos ) const

private

static Char reflex::Pattern::hi_of ( Opcode opcode )

inlinestaticprivate

static Index reflex::Pattern::index_of ( Opcode opcode )

inlinestaticprivate

void reflex::Pattern::init	(	const char *	options	)
throw	(	Error
	)

private

Initialize the pattern at construction.

void reflex::Pattern::init_options ( const char * options )

private

static bool reflex::Pattern::is_meta ( Char c )

inlinestaticprivate

static bool reflex::Pattern::is_modified	(	int	mode,
		const Map &	modifiers,
		Location	loc
	)

inlinestaticprivate

static bool reflex::Pattern::is_opcode_halt ( Opcode opcode )

inlinestaticprivate

static bool reflex::Pattern::is_opcode_head ( Opcode opcode )

inlinestaticprivate

static bool reflex::Pattern::is_opcode_match	(	Opcode	opcode,
		unsigned char	c
	)

inlinestaticprivate

static bool reflex::Pattern::is_opcode_meta ( Opcode opcode )

inlinestaticprivate

static bool reflex::Pattern::is_opcode_meta	(	Opcode	opcode,
		Char	a
	)

inlinestaticprivate

static bool reflex::Pattern::is_opcode_redo ( Opcode opcode )

inlinestaticprivate

static bool reflex::Pattern::is_opcode_tail ( Opcode opcode )

inlinestaticprivate

static bool reflex::Pattern::is_opcode_take ( Opcode opcode )

inlinestaticprivate

void reflex::Pattern::lazy	(	const Positions &	lazypos,
		Positions &	pos
	)		const

private

void reflex::Pattern::lazy	(	const Positions &	lazypos,
		const Positions &	pos,
		Positions &	pos1
	)		const

private

static Char reflex::Pattern::lo_of ( Opcode opcode )

inlinestaticprivate

static Char reflex::Pattern::meta_of ( Opcode opcode )

inlinestaticprivate

size_t reflex::Pattern::nodes ( void ) const

inline

Get the number of finite state machine nodes (vertices).

Returns: number of nodes or 0 when no finite state machine was constructed by this pattern.

static Opcode reflex::Pattern::opcode_goto	(	Char	lo,
		Char	hi,
		Index	index
	)

inlinestaticprivate

static Opcode reflex::Pattern::opcode_halt ( void )

inlinestaticprivate

static Opcode reflex::Pattern::opcode_head ( Index index )

inlinestaticprivate

static Opcode reflex::Pattern::opcode_redo ( void )

inlinestaticprivate

static Opcode reflex::Pattern::opcode_tail ( Index index )

inlinestaticprivate

static Opcode reflex::Pattern::opcode_take ( Index index )

inlinestaticprivate

const std::string reflex::Pattern::operator[] ( Index choice ) const

Get subpattern of this pattern object.

Returns: subpattern string or "".

void reflex::Pattern::parse	(	Positions &	startpos,
		Follow &	followpos,
		Map &	modifiers,
		Map &	lookahead
	)
throw	(	Error
	)

private

void reflex::Pattern::parse1	(	bool	begin,
		Location &	loc,
		Positions &	firstpos,
		Positions &	lastpos,
		bool &	nullable,
		Follow &	followpos,
		Positions &	lazypos,
		Map &	modifiers,
		Ranges &	lookahead,
		Index &	iter
	)
throw	(	Error
	)

private

void reflex::Pattern::parse2	(	bool	begin,
		Location &	loc,
		Positions &	firstpos,
		Positions &	lastpos,
		bool &	nullable,
		Follow &	followpos,
		Positions &	lazypos,
		Map &	modifiers,
		Ranges &	lookahead,
		Index &	iter
	)
throw	(	Error
	)

private

void reflex::Pattern::parse3	(	bool	begin,
		Location &	loc,
		Positions &	firstpos,
		Positions &	lastpos,
		bool &	nullable,
		Follow &	followpos,
		Positions &	lazypos,
		Map &	modifiers,
		Ranges &	lookahead,
		Index &	iter
	)
throw	(	Error
	)

private

void reflex::Pattern::parse4	(	bool	begin,
		Location &	loc,
		Positions &	firstpos,
		Positions &	lastpos,
		bool &	nullable,
		Follow &	followpos,
		Positions &	lazypos,
		Map &	modifiers,
		Ranges &	lookahead,
		Index &	iter
	)
throw	(	Error
	)

private

void reflex::Pattern::parse_esc	(	Location &	loc	)	const
throw	(	Error
	)

private

void reflex::Pattern::posix	(	size_t	index,
		Chars &	chars
	)		const

private

bool reflex::Pattern::reachable ( Index choice ) const

inline

Check is subpattern is reachable by a match.

Returns: true if subpattern is reachable.

Index reflex::Pattern::size ( void ) const

inline

Number of subpatterns of this pattern object.

Returns: number of subpatterns.

void reflex::Pattern::transition	(	Moves &	moves,
		const Chars &	chars,
		const Positions &	follow
	)		const

private

void reflex::Pattern::trim_lazy ( Positions & pos ) const

private

size_t reflex::Pattern::words ( void ) const

inline

Get the code size in number of words.

Returns: number of words or 0 when no code was generated by this pattern.

Friends And Related Function Documentation

friend class Matcher

friend

permit access by the reflex::Matcher engine

Member Data Documentation

std::vector<bool> reflex::Pattern::acc_

private

true if subpattern n is acceptable (state is reachable)

std::vector<Location> reflex::Pattern::end_

private

entries point to the subpattern's ending '|' or '\0'

size_t reflex::Pattern::eno_

private

number of finite state machine edges |E|

FSM reflex::Pattern::fsm_

private

function pointer to FSM code

Index reflex::Pattern::nop_

private

number of opcodes generated

const Opcode* reflex::Pattern::opc_

private

points to the opcode table

Option reflex::Pattern::opt_

private

pattern compiler options

std::string reflex::Pattern::rex_

private

regular expression string

size_t reflex::Pattern::vno_

private

number of finite state machine vertices |V|

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

pattern.h

Classes

Public Types

Public Member Functions

Protected Member Functions

Private Types

Private Member Functions

Static Private Member Functions

Private Attributes

Friends

Detailed Description

Member Typedef Documentation

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

Friends And Related Function Documentation

Member Data Documentation