Julian: libsent/include/sent/dfa.h File Reference

DFA_INFO* dfa_info_new ( )

Allocate a new grammar information data structure and initialize it.

Returns:: pointer to the newly allocated DFA_INFO.

Definition at line 33 of file dfa_malloc.c.

Referenced by msock_read_grammar(), and multigram_read_file().

void dfa_info_free ( DFA_INFO * dfa )

Free all informations in the DFA_INFO.

Parameters:

dfa

[i/o] grammar information data to be freed.

Definition at line 54 of file dfa_malloc.c.

Referenced by msock_read_grammar(), and multigram_exec_delete().

void dfa_state_init ( DFA_INFO * dinfo )

Initialize and allocate DFA state information list in the grammar.

Parameters:

dinfo

[i/o] DFA grammar

Definition at line 35 of file rddfa.c.

Referenced by rddfa(), rddfa_fd(), and rddfa_sd().

void dfa_state_expand	(	DFA_INFO *	dinfo,
		int	needed
	)

Expand the state information list to the required length.

Parameters:

	dinfo	[i/o] DFA grammar
	needed	[in] required new length

Definition at line 56 of file rddfa.c.

Referenced by dfa_append(), and rddfa_line().

boolean rddfa	(	FILE *	fp,
		DFA_INFO *	dinfo
	)

Top loop function to read DFA grammar via file pointer

Parameters:

	fp	[in] file pointer that points to the DFA grammar data
	dinfo	[out] the read data will be stored in this DFA grammar structure

Returns:: TRUE on success, FALSE on failure.

Definition at line 79 of file rddfa.c.

Referenced by init_dfa().

boolean rddfa_fd	(	int	fd,
		DFA_INFO *	dinfo
	)

Top loop function to read DFA grammar via file descriptor

Parameters:

	fd	[in] file descriptor that points to the DFA grammar data
	dinfo	[out] the read data will be stored in this DFA grammar structure

Returns:: TRUE on success, FALSE on failure.

Definition at line 109 of file rddfa.c.

Referenced by msock_read_grammar().

boolean rddfa_sd	(	int	sd,
		DFA_INFO *	dinfo
	)

Top loop function to read DFA grammar via socket descriptor

Parameters:

	sd	[in] socket descriptor that points to the DFA grammar data
	dinfo	[out] the read data will be stored in this DFA grammar structure

Returns:: TRUE on success, FALSE on failure.

Definition at line 139 of file rddfa.c.

Referenced by msock_read_grammar().

boolean rddfa_line	(	char *	line,
		DFA_INFO *	dinfo,
		int *	state_max,
		int *	arc_num,
		int *	terminal_max
	)

Parse the input line and set grammar information, one by line.

Parameters:

	line	[in] text buffer that holds a line of DFA file
	dinfo	[i/o] the read data will be appended to this DFA data
	state_max	[i/o] maximum number of state id appeared, will be updated
	arc_num	[i/o] number of read arcs, will be updated
	terminal_max	[i/o] maximum number of state id appended, will be updated

Returns:: TRUE if the line was successfully parsed, FALSE if failed.

Definition at line 172 of file rddfa.c.

Referenced by rddfa(), rddfa_fd(), and rddfa_sd().

void dfa_append	(	DFA_INFO *	dst,
		DFA_INFO *	src,
		int	soffset,
		int	coffset
	)

Append the DFA state information to other

Parameters:

	dst	[i/o] DFA grammar
	src	[i/o] DFA grammar to be appended to dst
	soffset	[in] offset state number in dst where the new state should be stored
	coffset	[in] category id offset in dst where the new data should be stored

Definition at line 230 of file rddfa.c.

Referenced by multigram_build_append().

void init_dfa	(	DFA_INFO *	dinfo,
		char *	filename
	)

Read in a grammar file and set to DFA grammar structure

Parameters:

	dinfo	[i/o] a blank DFA data
	filename	[in] DFA grammar file name

Definition at line 45 of file init_dfa.c.

Referenced by multigram_read_file().

WORD_ID dfa_symbol_lookup	(	DFA_INFO *	dinfo,
		char *	terminalname
	)

Return category id corresponding to the given terminal name. Actually they are mere strings of ID itself.

Parameters:

	dinfo	[in] DFA grammar information
	terminalname	[in] name string

Returns:: the category id.

Definition at line 44 of file dfa_lookup.c.

Referenced by make_dfa_voca_ref().

void extract_cpair ( DFA_INFO * dinfo )

Extract category-pair constraint from DFA grammar and newly set the category pair matrix of the give DFA.

Parameters:

dinfo

[i/o] DFA grammar, in which the category-pair matrix will be created.

Definition at line 60 of file mkcpair.c.

Referenced by multigram_exec().

void cpair_append	(	DFA_INFO *	dst,
		DFA_INFO *	src,
		int	coffset
	)

Append the category pair matrix at the last.

Parameters:

	dst	[i/o] DFA grammar
	src	[in] DFA grammar to be appended to dst
	coffset	[in] category id in dst where the new data should be stored

Definition at line 113 of file mkcpair.c.

Referenced by multigram_build_append().

void print_dfa_info ( DFA_INFO * dinfo )

Output overall grammar information to stdout.

Parameters:

dinfo

[in] DFA grammar

Definition at line 33 of file dfa_util.c.

Referenced by print_info().

void print_dfa_cp ( DFA_INFO * dinfo )

Output the category-pair matrix in text format to stdout

Parameters:

dinfo

[in] DFA grammar that holds category pair matrix

Definition at line 48 of file dfa_util.c.

Referenced by print_info().

boolean dfa_cp	(	DFA_INFO *	dfa,
		int	i,
		int	j
	)

Return whether the given two category can be connected or not.

Parameters:

	dfa	[in] DFA grammar holding category pair matrix
	i	[in] category id of left word
	j	[in] category id of right word

Returns:: TRUE if connection is allowed by the grammar, FALSE if prohibited.

Definition at line 48 of file cpair.c.

Referenced by cpair_append(), lcdset_register_with_category(), lcdset_register_with_category_all(), and print_dfa_cp().

boolean dfa_cp_begin	(	DFA_INFO *	dfa,
		int	i
	)

Return whether the category can be appear at the beginning of sentence.

Parameters:

	dfa	[in] DFA grammar holding category pair matrix
	i	[in] category id of the word

Returns:: TRUE if it can appear at the beginning of sentence, FALSE if not.

Definition at line 63 of file cpair.c.

Referenced by cpair_append(), init_nodescore(), and print_dfa_cp().

boolean dfa_cp_end	(	DFA_INFO *	dfa,
		int	i
	)

Return whether the category can be appear at the end of sentence.

Parameters:

	dfa	[in] DFA grammar holding category pair matrix
	i	[in] category id of the word

Returns:: TRUE if it can appear at the end of sentence, FALSE if not.

Definition at line 78 of file cpair.c.

Referenced by cpair_append(), and print_dfa_cp().

void set_dfa_cp	(	DFA_INFO *	dfa,
		int	i,
		int	j,
		boolean	value
	)

Set the category-pair matrix bit

Parameters:

	dfa	[out] DFA grammar holding category pair matrix
	i	[in] category id of left word
	j	[in] category id of right word
	value	TRUE if connection allowed, FALSE if connection prohibited.

Definition at line 93 of file cpair.c.

Referenced by cpair_append(), malloc_dfa_cp(), and realloc_dfa_cp().

void set_dfa_cp_begin	(	DFA_INFO *	dfa,
		int	i,
		boolean	value
	)

Set the category-pair matrix bit at the beginning of sentence

Parameters:

	dfa	[out] DFA grammar holding category pair matrix
	i	[in] category id of the word
	value	TRUE if the category can appear at the beginning of sentence, FALSE if not.

Definition at line 112 of file cpair.c.

Referenced by cpair_append(), and realloc_dfa_cp().

void set_dfa_cp_end	(	DFA_INFO *	dfa,
		int	i,
		boolean	value
	)

Set the category-pair matrix bit at the end of sentence

Parameters:

	dfa	[out] DFA grammar holding category pair matrix
	i	[in] category id of the word
	value	TRUE if the category can appear at the end of sentence, FALSE if not.

Definition at line 131 of file cpair.c.

Referenced by cpair_append(), extract_cpair(), and realloc_dfa_cp().

void init_dfa_cp ( DFA_INFO * dfa )

Initialize category pair matrix in the grammar data.

Parameters:

dfa

[out] DFA grammar to hold category pair matrix

Definition at line 147 of file cpair.c.

Referenced by dfa_info_new().

void malloc_dfa_cp	(	DFA_INFO *	dfa,
		int	term_num
	)

Allocate memory for category pair matrix and initialize it.

Parameters:

	dfa	[out] DFA grammar to hold category pair matrix
	term_num	[in] number of categories in the grammar

Definition at line 162 of file cpair.c.

Referenced by extract_cpair(), and realloc_dfa_cp().

void realloc_dfa_cp	(	DFA_INFO *	dfa,
		int	old_term_num,
		int	new_term_num
	)

Re-allocate memory for category pair matrix, can be called when the number of category is expanded.

Parameters:

	dfa	[I/O] DFA grammar holding category pair matrix
	old_term_num	[in] number of categories when the last category pair matrix was allocated
	new_term_num	[in] new number of categories in the grammar

Definition at line 193 of file cpair.c.

Referenced by cpair_append().

void free_dfa_cp ( DFA_INFO * dfa )

Free the category pair matrix from DFA grammar.

Parameters:

dfa

[i/o] DFA grammar holding category pair matrix

Definition at line 254 of file cpair.c.

Referenced by dfa_info_free().

void make_dfa_voca_ref	(	DFA_INFO *	dinfo,
		WORD_INFO *	winfo
	)

Make correspondence between all words in dictionary and categories in grammar, both from a word to a category and from a category to words.

Parameters:

	dinfo	[i/o] DFA grammar, category information will be built here.
	winfo	[i/o] Word dictionary, word-to-category information will be build here.

Definition at line 71 of file init_dfa.c.

Referenced by multigram_exec().

void make_terminfo	(	TERM_INFO *	tinfo,
		DFA_INFO *	dinfo,
		WORD_INFO *	winfo
	)

Make a word list for each category.

Parameters:

	tinfo	[i/o] terminal data structure to hold the result
	dinfo	[in] DFA gammar to supply the number of category in the grammar
	winfo	[in] word dictionary.

Definition at line 38 of file mkterminfo.c.

void terminfo_append	(	TERM_INFO *	dst,
		TERM_INFO *	src,
		int	coffset,
		int	woffset
	)

Append the terminal(category) word list.

Parameters:

	dst	[i/o] category data
	src	[i/o] category data to be appended to dst
	coffset	[in] category id offset in dst where the new data should be stored
	woffset	[in] word id offset where the new data should be stored

Definition at line 76 of file mkterminfo.c.

Referenced by multigram_build_append().

void dfa_find_pause_word	(	DFA_INFO *	dfa,
		WORD_INFO *	winfo,
		HTK_HMM_INFO *	hmminfo
	)

Find pause word and pause category information, and set to the grammar data.

Parameters:

	dfa	[i/o] DFA grammar, sp_id and is_sp will be built here.
	winfo	[in] Word dictionary
	hmminfo	[in] HTK HMM to provide which is short pause HMM

Definition at line 104 of file init_dfa.c.

Referenced by multigram_exec().

void dfa_pause_word_append	(	DFA_INFO *	dst,
		DFA_INFO *	src,
		int	coffset
	)

Append the pause word/category information at the last.

Parameters:

	dst	[i/o] DFA grammar
	src	[in] DFA grammar to be appended to dst
	coffset	appending category point in dst

Definition at line 135 of file init_dfa.c.

Referenced by multigram_build_append().


Data Structures
struct	_dfa_arc
	Transition arc of DFA. More...
struct	DFA_STATE
	State of DFA. More...
struct	TERM_INFO
	Information of each terminal symbol (=category). More...
struct	DFA_INFO
	Top structure of a DFA. More...
Defines
#define	DFA_STATESTEP 1000
	Allocation step of DFA state.
#define	INITIAL_S 0x10000000
	Status flag mask specifying an initial state.
#define	ACCEPT_S 0x00000001
	Status flag mask specifying an accept state.
Typedefs
typedef _dfa_arc	DFA_ARC
	Transition arc of DFA.
Functions
DFA_INFO *	dfa_info_new ()
void	dfa_info_free (DFA_INFO *dfa)
void	dfa_state_init (DFA_INFO *dinfo)
void	dfa_state_expand (DFA_INFO *dinfo, int needed)
boolean	rddfa (FILE fp, DFA_INFO dinfo)
boolean	rddfa_fd (int fd, DFA_INFO *dinfo)
boolean	rddfa_sd (int sd, DFA_INFO *dinfo)
boolean	rddfa_line (char line, DFA_INFO dinfo, int state_max, int arc_num, int *terminal_max)
void	dfa_append (DFA_INFO dst, DFA_INFO src, int soffset, int coffset)
void	init_dfa (DFA_INFO dinfo, char filename)
WORD_ID	dfa_symbol_lookup (DFA_INFO dinfo, char terminalname)
void	extract_cpair (DFA_INFO *dinfo)
void	cpair_append (DFA_INFO dst, DFA_INFO src, int coffset)
void	print_dfa_info (DFA_INFO *dinfo)
void	print_dfa_cp (DFA_INFO *dinfo)
boolean	dfa_cp (DFA_INFO *dfa, int i, int j)
boolean	dfa_cp_begin (DFA_INFO *dfa, int i)
boolean	dfa_cp_end (DFA_INFO *dfa, int i)
void	set_dfa_cp (DFA_INFO *dfa, int i, int j, boolean value)
void	set_dfa_cp_begin (DFA_INFO *dfa, int i, boolean value)
void	set_dfa_cp_end (DFA_INFO *dfa, int i, boolean value)
void	init_dfa_cp (DFA_INFO *dfa)
void	malloc_dfa_cp (DFA_INFO *dfa, int term_num)
void	realloc_dfa_cp (DFA_INFO *dfa, int old_term_num, int new_term_num)
void	free_dfa_cp (DFA_INFO *dfa)
void	make_dfa_voca_ref (DFA_INFO dinfo, WORD_INFO winfo)
void	make_terminfo (TERM_INFO tinfo, DFA_INFO dinfo, WORD_INFO *winfo)
void	terminfo_append (TERM_INFO dst, TERM_INFO src, int coffset, int woffset)
void	dfa_find_pause_word (DFA_INFO dfa, WORD_INFO winfo, HTK_HMM_INFO *hmminfo)
void	dfa_pause_word_append (DFA_INFO dst, DFA_INFO src, int coffset)

libsent/include/sent/dfa.h File Reference

Data Structures

Defines

Typedefs

Functions

Detailed Description

Function Documentation