gnuregex.h

-

/* If any error codes are removed, changed, or added, update the
 * `re_error_msg' table in regex.c.  */
typedef enum {
    REG_NOERROR = 0,		/* Success.  */
    REG_NOMATCH,		/* Didn't find a match (for regexec).  */

    /* POSIX regcomp return error codes.  (In the order listed in the
     * standard.)  */
    REG_BADPAT,			/* Invalid pattern.  */
    REG_ECOLLATE,		/* Not implemented.  */
    REG_ECTYPE,			/* Invalid character class name.  */
    REG_EESCAPE,		/* Trailing backslash.  */
    REG_ESUBREG,		/* Invalid back reference.  */
    REG_EBRACK,			/* Unmatched left bracket.  */
    REG_EPAREN,			/* Parenthesis imbalance.  */
    REG_EBRACE,			/* Unmatched \{.  */
    REG_BADBR,			/* Invalid contents of \{\}.  */
    REG_ERANGE,			/* Invalid range end.  */
    REG_ESPACE,			/* Ran out of memory.  */
    REG_BADRPT,			/* No preceding re for repetition op.  */

    /* Error codes we've added.  */
    REG_EEND,			/* Premature end.  */
    REG_ESIZE,			/* Compiled pattern bigger than 2^16 bytes.  */
    REG_ERPAREN			/* Unmatched ) or \); not returned from regcomp.  */
} reg_errcode_t;

/* This data structure represents a compiled pattern.  Before calling
 * the pattern compiler, the fields `buffer', `allocated', `fastmap',
 * `translate', and `no_sub' can be set.  After the pattern has been
 * compiled, the `re_nsub' field is available.  All other fields are
 * private to the regex routines.  */

struct re_pattern_buffer {
/* [[[begin pattern_buffer]]] */
    /* Space that holds the compiled pattern.  It is declared as
     * `unsigned char *' because its elements are
     * sometimes used as array indexes.  */
    unsigned char *buffer;

    /* Number of bytes to which `buffer' points.  */
    unsigned long allocated;

    /* Number of bytes actually used in `buffer'.  */
    unsigned long used;

    /* Syntax setting with which the pattern was compiled.  */
    reg_syntax_t syntax;

    /* Pointer to a fastmap, if any, otherwise zero.  re_search uses
     * the fastmap, if there is one, to skip over impossible
     * starting points for matches.  */
    char *fastmap;

    /* Either a translate table to apply to all characters before
     * comparing them, or zero for no translation.  The translation
     * is applied to a pattern when it is compiled and to a string
     * when it is matched.  */
    char *translate;

    /* Number of subexpressions found by the compiler.  */
    size_t re_nsub;

    /* Zero if this pattern cannot match the empty string, one else.
     * Well, in truth it's used only in `re_search_2', to see
     * whether or not we should use the fastmap, so we don't set
     * this absolutely perfectly; see `re_compile_fastmap' (the
     * `duplicate' case).  */
    unsigned can_be_null:1;

    /* If REGS_UNALLOCATED, allocate space in the `regs' structure
     * for `max (RE_NREGS, re_nsub + 1)' groups.
     * If REGS_REALLOCATE, reallocate space if necessary.
     * If REGS_FIXED, use what's there.  */
#define REGS_UNALLOCATED 0
#define REGS_REALLOCATE 1
#define REGS_FIXED 2
    unsigned regs_allocated:2;

    /* Set to zero when `regex_compile' compiles a pattern; set to one
     * by `re_compile_fastmap' if it updates the fastmap.  */
    unsigned fastmap_accurate:1;

    /* If set, `re_match_2' does not return information about
     * subexpressions.  */
    unsigned no_sub:1;

    /* If set, a beginning-of-line anchor doesn't match at the
     * beginning of the string.  */
    unsigned not_bol:1;

    /* Similarly for an end-of-line anchor.  */
    unsigned not_eol:1;

    /* If true, an anchor at a newline matches.  */
    unsigned newline_anchor:1;

/* [[[end pattern_buffer]]] */
};

typedef struct re_pattern_buffer regex_t;


/* search.c (search_buffer) in Emacs needs this one opcode value.  It is
 * defined both in `regex.c' and here.  */
#define RE_EXACTN_VALUE 1

/* Type for byte offsets within the string.  POSIX mandates this.  */
typedef int regoff_t;


/* This is the structure we store register match data in.  See
 * regex.texinfo for a full description of what registers match.  */
struct re_registers {
    unsigned num_regs;
    regoff_t *start;
    regoff_t *end;
};


/* If `regs_allocated' is REGS_UNALLOCATED in the pattern buffer,
 * `re_match_2' returns information about at least this many registers
 * the first time a `regs' structure is passed.  */
#ifndef RE_NREGS
#define RE_NREGS 30
#endif


/* POSIX specification for registers.  Aside from the different names than
 * `re_registers', POSIX uses an array of structures, instead of a
 * structure of arrays.  */
typedef struct {
    regoff_t rm_so;		/* Byte offset from string's start to substring's start.  */
    regoff_t rm_eo;		/* Byte offset from string's start to substring's end.  */
} regmatch_t;

/* Declarations for routines.  */

/* To avoid duplicating every routine declaration -- once with a
 * prototype (if we are ANSI), and once without (if we aren't) -- we
 * use the following macro to declare argument types.  This
 * unfortunately clutters up the declarations a bit, but I think it's
 * worth it.  */

#if STDC_HEADERS

#define _RE_ARGS(args) args

#else /* not __STDC__ */

#define _RE_ARGS(args) ()

#endif /* not __STDC__ */

/* Sets the current default syntax to SYNTAX, and return the old syntax.
 * You can also simply assign to the `re_syntax_options' variable.  */
extern reg_syntax_t re_set_syntax _RE_ARGS((reg_syntax_t syntax));

/* Compile the regular expression PATTERN, with length LENGTH
 * and syntax given by the global `re_syntax_options', into the buffer
 * BUFFER.  Return NULL if successful, and an error string if not.  */
extern const char *re_compile_pattern
     _RE_ARGS((const char *pattern, int length,
	struct re_pattern_buffer * buffer));


/* Compile a fastmap for the compiled pattern in BUFFER; used to
 * accelerate searches.  Return 0 if successful and -2 if was an
 * internal error.  */
extern int re_compile_fastmap _RE_ARGS((struct re_pattern_buffer * buffer));


/* Search in the string STRING (with length LENGTH) for the pattern
 * compiled into BUFFER.  Start searching at position START, for RANGE
 * characters.  Return the starting position of the match, -1 for no
 * match, or -2 for an internal error.  Also return register
 * information in REGS (if REGS and BUFFER->no_sub are nonzero).  */
extern int re_search
    _RE_ARGS((struct re_pattern_buffer * buffer, const char *string,
	int length, int start, int range, struct re_registers * regs));


/* Like `re_search', but search in the concatenation of STRING1 and
 * STRING2.  Also, stop searching at index START + STOP.  */
extern int re_search_2
    _RE_ARGS((struct re_pattern_buffer * buffer, const char *string1,
	int length1, const char *string2, int length2,
	int start, int range, struct re_registers * regs, int stop));


/* Like `re_search', but return how many characters in STRING the regexp
 * in BUFFER matched, starting at position START.  */
extern int re_match
    _RE_ARGS((struct re_pattern_buffer * buffer, const char *string,
	int length, int start, struct re_registers * regs));


/* Relates to `re_match' as `re_search_2' relates to `re_search'.  */
extern int re_match_2
    _RE_ARGS((struct re_pattern_buffer * buffer, const char *string1,
	int length1, const char *string2, int length2,
	int start, struct re_registers * regs, int stop));


/* Set REGS to hold NUM_REGS registers, storing them in STARTS and
 * ENDS.  Subsequent matches using BUFFER and REGS will use this memory
 * for recording register information.  STARTS and ENDS must be
 * allocated with malloc, and must each be at least `NUM_REGS * sizeof
 * (regoff_t)' bytes long.
 * 
 * If NUM_REGS == 0, then subsequent matches should allocate their own
 * register data.
 * 
 * Unless this function is called, the first search or match using
 * PATTERN_BUFFER will allocate its own register data, without
 * freeing the old data.  */
extern void re_set_registers
     _RE_ARGS((struct re_pattern_buffer * buffer, struct re_registers * regs,
	unsigned num_regs, regoff_t * starts, regoff_t * ends));

/* 4.2 bsd compatibility.  */
extern char *re_comp _RE_ARGS((const char *));
extern int re_exec _RE_ARGS((const char *));

/* POSIX compatibility.  */
extern int regcomp _RE_ARGS((regex_t * preg, const char *pattern, int cflags));
extern int regexec
    _RE_ARGS((const regex_t * preg, const char *string, size_t nmatch,
	regmatch_t pmatch[], int eflags));
extern size_t regerror
       _RE_ARGS((int errcode, const regex_t * preg, char *errbuf,
	size_t errbuf_size));
extern void regfree _RE_ARGS((regex_t * preg));

#endif /* not __REGEXP_LIBRARY_H__ */

/*
 * Local variables:
 * make-backup-files: t
 * version-control: t
 * trim-versions-without-asking: nil
 * End:
 */