expression library, version 0.12.
Copyright (C) 1985, 1989, 1990, 1991, 1992, 1993, 1995, 1996, 1997,
1998, 2000, 2005 Free Software Foundation, Inc.
This file is part of the GNU C Library. Its master source is NOT part of
the C library, however. The master source lives in /gd/gnu/lib.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, write to the Free
Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
02110-1301 USA. */
#ifndef _REGEX_H
#define _REGEX_H 1
#ifdef __cplusplus
extern "C" {
#endif
<regex.h>. */
#if !defined _POSIX_C_SOURCE && !defined _POSIX_SOURCE && defined VMS
should be there. */
# include <stddef.h>
#endif
wide enough to hold a value of a pointer. For most ANSI compilers
ptrdiff_t and size_t should be likely OK. Still size of these two
types is 2 for Microsoft C. Ugh... */
typedef long int s_reg_t;
typedef unsigned long int active_reg_t;
recognize. The set/not-set meanings are chosen so that Emacs syntax
remains the value 0. The bits are given in alphabetical order, and
the definitions shifted by one from the previous bit; thus, when we
add or remove a bit, only one other definition need change. */
typedef unsigned long int reg_syntax_t;
If set, then such a \ quotes the following character. */
#define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)
literals.
If set, then \+ and \? are operators and + and ? are literals. */
#define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)
[:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:],
[:space:], [:print:], [:punct:], [:graph:], and [:cntrl:].
If not set, then character classes are not supported. */
#define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1)
expressions, of course).
If this bit is not set, then it depends:
^ is an anchor if it is at the beginning of a regular
expression or after an open-group or an alternation operator;
$ is an anchor if it is at the end of a regular expression, or
before a close-group or an alternation operator.
This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because
POSIX draft 11.2 says that * etc. in leading positions is undefined.
We already implemented a previous draft which made those constructs
invalid, though, so we haven't changed the code back. */
#define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1)
regardless of where they are in the pattern.
If this bit is not set, then special characters are special only in
some contexts; otherwise they are ordinary. Specifically,
* + ? and intervals are only special when not after the beginning,
open-group, or alternation operator. */
#define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1)
immediately after an alternation or begin-group operator. */
#define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1)
If not set, then it doesn't. */
#define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1)
If not set, then it does. */
#define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1)
If not set, they do. */
#define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1)
interval, depending on RE_NO_BK_BRACES.
If not set, \{, \}, {, and } are literals. */
#define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)
If not set, they are. */
#define RE_LIMITED_OPS (RE_INTERVALS << 1)
If not set, newline is literal. */
#define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1)
are literals.
If not set, then `\{...\}' defines an interval. */
#define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1)
If not set, \(...\) defines a group, and ( and ) are literals. */
#define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1)
If not set, then \<digit> is a back-reference. */
#define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1)
If not set, then \| is an alternation operator, and | is literal. */
#define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1)
than the starting range point, as in [z-a], is invalid.
If not set, then when ending range point collates higher than the
starting range point, the range is ignored. */
#define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1)
If not set, then an unmatched ) is invalid. */
#define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1)
without further backtracking. */
#define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)
If not set, then the GNU regex operators are recognized. */
#define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)
If not set, and debugging was on, turn it off.
This only works if regex.c is compiled -DDEBUG.
We define this bit always, so that all that's needed to turn on
debugging is to recompile regex.c; the calling code can always have
this bit set, and it won't affect anything in the normal case. */
#define RE_DEBUG (RE_NO_GNU_OPS << 1)
a string of ordinary characters. For example, the ERE 'a{1' is
treated as 'a\{1'. */
#define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)
some interfaces). When a regexp is compiled, the syntax used is
stored in the pattern buffer, so changing this does not affect
already-compiled regexps. */
extern reg_syntax_t re_syntax_options;
(The [[[ comments delimit what gets put into the Texinfo file, so
don't delete them!) */
#define RE_SYNTAX_EMACS 0
#define RE_SYNTAX_AWK \
(RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \
| RE_NO_BK_PARENS | RE_NO_BK_REFS \
| RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \
| RE_DOT_NEWLINE | RE_CONTEXT_INDEP_ANCHORS \
| RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS)
#define RE_SYNTAX_GNU_AWK \
((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DEBUG) \
& ~(RE_DOT_NOT_NULL | RE_INTERVALS | RE_CONTEXT_INDEP_OPS))
#define RE_SYNTAX_POSIX_AWK \
(RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \
| RE_INTERVALS | RE_NO_GNU_OPS)
#define RE_SYNTAX_GREP \
(RE_BK_PLUS_QM | RE_CHAR_CLASSES \
| RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \
| RE_NEWLINE_ALT)
#define RE_SYNTAX_EGREP \
(RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \
| RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \
| RE_NEWLINE_ALT | RE_NO_BK_PARENS \
| RE_NO_BK_VBAR)
#define RE_SYNTAX_POSIX_EGREP \
(RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES \
| RE_INVALID_INTERVAL_ORD)
#define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC
#define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC
#define _RE_SYNTAX_POSIX_COMMON \
(RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \
| RE_INTERVALS | RE_NO_EMPTY_RANGES)
#define RE_SYNTAX_POSIX_BASIC \
(_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM)
RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this
isn't minimal, since other operators, such as \`, aren't disabled. */
#define RE_SYNTAX_POSIX_MINIMAL_BASIC \
(_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS)
#define RE_SYNTAX_POSIX_EXTENDED \
(_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
| RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \
| RE_NO_BK_PARENS | RE_NO_BK_VBAR \
| RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD)
removed and RE_NO_BK_REFS is added. */
#define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \
(_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
| RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \
| RE_NO_BK_PARENS | RE_NO_BK_REFS \
| RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD)
(erroneously) define this in other header files, but we want our
value, so remove any previous define. */
#ifdef RE_DUP_MAX
# undef RE_DUP_MAX
#endif
#define RE_DUP_MAX (0x7fff)
If not set, then use basic regular expression syntax. */
#define REG_EXTENDED 1
If not set, then case is significant. */
#define REG_ICASE (REG_EXTENDED << 1)
characters in the string.
If not set, then anchors do match at newlines. */
#define REG_NEWLINE (REG_ICASE << 1)
If not set, then returns differ between not matching and errors. */
#define REG_NOSUB (REG_NEWLINE << 1)
the beginning of the string (presumably because it's not the
beginning of a line).
If not set, then the beginning-of-line operator does match the
beginning of the string. */
#define REG_NOTBOL 1
#define REG_NOTEOL (1 << 1)
`re_error_msg' table in regex.c. */
typedef enum
{
#ifdef _XOPEN_SOURCE
REG_ENOSYS = -1,
#endif
REG_NOERROR = 0,
REG_NOMATCH,
standard.) */
REG_BADPAT,
REG_ECOLLATE,
REG_ECTYPE,
REG_EESCAPE,
REG_ESUBREG,
REG_EBRACK,
REG_EPAREN,
REG_EBRACE,
REG_BADBR,
REG_ERANGE,
REG_ESPACE,
REG_BADRPT,
REG_EEND,
REG_ESIZE,
REG_ERPAREN
} reg_errcode_t;
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. */
#ifndef RE_TRANSLATE_TYPE
# define RE_TRANSLATE_TYPE char *
#endif
struct re_pattern_buffer
{
`unsigned char *' because its elements are
sometimes used as array indexes. */
unsigned char *buffer;
unsigned long int allocated;
unsigned long int used;
reg_syntax_t syntax;
the fastmap, if there is one, to skip over impossible
starting points for matches. */
char *fastmap;
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. */
RE_TRANSLATE_TYPE translate;
size_t re_nsub;
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;
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;
by `re_compile_fastmap' if it updates the fastmap. */
unsigned fastmap_accurate : 1;
subexpressions. */
unsigned no_sub : 1;
beginning of the string. */
unsigned not_bol : 1;
unsigned not_eol : 1;
unsigned newline_anchor : 1;
};
typedef struct re_pattern_buffer regex_t;
typedef int regoff_t;
regex.texinfo for a full description of what registers match. */
struct re_registers
{
unsigned num_regs;
regoff_t *start;
regoff_t *end;
};
`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
`re_registers', POSIX uses an array of structures, instead of a
structure of arrays. */
typedef struct
{
regoff_t rm_so;
regoff_t rm_eo;
} regmatch_t;
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. */
You can also simply assign to the `re_syntax_options' variable. */
extern reg_syntax_t re_set_syntax (reg_syntax_t syntax);
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 (const char *pattern, size_t length,
struct re_pattern_buffer *buffer);
accelerate searches. Return 0 if successful and -2 if was an
internal error. */
extern int re_compile_fastmap (struct re_pattern_buffer *buffer);
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 (struct re_pattern_buffer *buffer, const char *string,
int length, int start, int range,
struct re_registers *regs);
STRING2. Also, stop searching at index START + STOP. */
extern int re_search_2 (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);
in BUFFER matched, starting at position START. */
extern int re_match (struct re_pattern_buffer *buffer, const char *string,
int length, int start, struct re_registers *regs);
extern int re_match_2 (struct re_pattern_buffer *buffer, const char *string1,
int length1, const char *string2, int length2,
int start, struct re_registers *regs, int stop);
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 (struct re_pattern_buffer *buffer,
struct re_registers *regs,
unsigned num_regs, regoff_t *starts,
regoff_t *ends);
#if defined _REGEX_RE_COMP || defined _LIBC
# ifndef _CRAY
extern char *re_comp (const char *);
extern int re_exec (const char *);
# endif
#endif
"restrict", and "configure" may have defined "restrict". */
#ifndef __restrict
# if ! (2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__))
# if defined restrict || 199901L <= __STDC_VERSION__
# define __restrict restrict
# else
# define __restrict
# endif
# endif
#endif
using the syntax array_name[restrict] */
#ifndef __restrict_arr
# if ! (3 < __GNUC__ || (3 == __GNUC__ && 1 <= __GNUC_MINOR__)) || defined (__GNUG__)
# define __restrict_arr
# else
# define __restrict_arr __restrict
# endif
#endif
extern int regcomp (regex_t *__restrict __preg,
const char *__restrict __pattern,
int __cflags);
#if (__GNUC__)
__extension__
#endif
extern int regexec (const regex_t *__restrict __preg,
const char *__restrict __string, size_t __nmatch,
regmatch_t __pmatch[__restrict_arr],
int __eflags);
extern size_t regerror (int __errcode, const regex_t *__preg,
char *__errbuf, size_t __errbuf_size);
extern void regfree (regex_t *__preg);
#ifdef __cplusplus
}
#endif
#endif
Local variables:
make-backup-files: t
version-control: t
trim-versions-without-asking: nil
End:
*/