mirrors/emacs
1
Fork 0
mirror of git://git.sv.gnu.org/emacs.git synced 2025-12-09 15:50:40 -08:00
Code Issues Projects Releases Wiki Activity

Simplify regex-emacs code by assuming Emacs

Browse source 
* src/regex-emacs.c: Omit no-longer-needed AIX code.
Don’t ignore GCC warnings.
Include regex-emacs.h immediately after config.h,
to test that it’s independent.
Omit the "#ifndef emacs" and "#ifdef REGEX_MALLOC" and
"#if WIDE_CHAR_SUPPORT" or "#ifdef _REGEX_RE_COMP",
code, as we are no longer interested in compiling outside
Emacs (with or without debugging or native wide char support)
or in avoiding alloca.
(REGEX_EMACS_DEBUG, regex_emacs_debug): Rename from DEBUG and debug,
to avoid collision with other DEBUGS.  All uses changed.
In debugging output, change %ld and %zd to %zu when appropriate.
No need to include stddef.h, stdlib.h, sys/types.h, wchar.h,
wctype.h, locale/localeinfo.h, locale/elem-hash.h, langinfo.h,
libintl.h, unistd.h, stdbool.h, string.h, stdio.h, assert.h.
All uses of assert changed to eassert.
(RE_DUP_MAX, reg_syntax_t, RE_BACKSLASH_ESCAPE_IN_LISTS)
(RE_BK_PLUS_QM, RE_CHAR_CLASSES, RE_CONTEXT_INDEP_ANCHORS)
(RE_CONTEXT_INDEP_OPS, RE_CONTEXT_INVALID_OPS, RE_DOT_NEWLINE)
(RE_DOT_NOT_NULL, RE_HAT_LISTS_NOT_NEWLINE, RE_INTERVALS)
(RE_LIMITED_OPS, RE_NEWLINE_ALT, RE_NO_BK_BRACES)
(RE_NO_BK_PARENS, RE_NO_BK_REFS, RE_NO_BK_VBAR)
(RE_NO_EMPTY_RANGES, RE_UNMATCHED_RIGHT_PAREN_ORD)
(RE_NO_POSIX_BACKTRACKING, RE_NO_GNU_OPS, RE_FRUGAL)
(RE_SHY_GROUPS, RE_NO_NEWLINE_ANCHOR, RE_SYNTAX_EMACS)
(REG_NOERROR, REG_NOMATCH, 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_ERANGEX, REG_ESIZEBR)
(reg_errcode_t, REGS_UNALLOCATED, REGS_REALLOCATE, REGS_FIXED)
(RE_NREGS, RE_TRANSLATE, RE_TRANSLATE_P):
Move here from regex-emacs.h.
(RE_NREGS): Define unconditionally.
(boolean): Remove.  All uses replaced by bool.
(WIDE_CHAR_SUPPORT, regfree, regexec, regcomp, regerror):
(re_set_syntax, re_syntax_options, WEAK_ALIAS, gettext, gettext_noop):
Remove.  All uses removed.
(malloc, realloc, free): Do not redefine.  Adjust all callers
to use xmalloc, xrealloc, xfree instead.
(re_error_msgid): Use C99 to avoid need to keep in same order
as reg_error_t.
(REGEX_USE_SAFE_ALLOCA): Simplify by using USE_SAFE_ALLOCA.
(REGEX_ALLOCATE, REGEX_REALLOCATE, REGEX_FREE, REGEX_ALLOCATE_STACK)
(REGEX_REALLOCATE_STACK, REGEX_FREE_STACK): Remove.
All callers changed to use the non-REGEX_MALLOC version.
(REGEX_TALLOC): Remove.  All callers changed to use SAFE_ALLOCA.
(re_set_syntax): Remove; unused.
(MATCH_MAY_ALLOCATE): Remove; now always true.  All uses simplified.
(INIT_FAILURE_ALLOC): Define unconditionally.
(re_compile_fastmap): Now static.
(re_compile_pattern): Avoid unnecessary cast.
* src/regex-emacs.h (EMACS_REGEX_H): Renamed from _REGEX_H to
avoid possible collision with glibc.
Don’t include sys/types.h.  All uses of ssize_t changed to ptrdiff_t.
Don’t worry about C++ or VMS.
Assume emacs is defined and that _REGEX_RE_COMP and WIDE_CHAR_SUPPORT
are not.
Define struct re_registers before including lisp.h.
(REG_ENOSYS, RE_TRANSLATE_TYPE): Remove; all uses replaced by
Lisp_Object.
(regoff_t): Remove.  All uses replaced with ptrdiff_t.
(re_match, regcomp, regexec, regerror, regfree):
Remove decl of nonexistent functions.
(RE_DEBUG, RE_SYNTAX_AWK, RE_SYNTAX_GNU_AWK)
(RE_SYNTAX_POSIX_AWK, RE_SYNTAX_GREP, RE_SYNTAX_EGREP)
(RE_SYNTAX_POSIX_EGREP, RE_SYNTAX_ED, RE_SYNTAX_SED)
(_RE_SYNTAX_POSIX_COMMON, RE_SYNTAX_POSIX_BASIC)
(RE_SYNTAX_POSIX_MINIMAL_BASIC, RE_SYNTAX_POSIX_EXTENDED)
(RE_SYNTAX_POSIX_MINIMAL_EXTENDED, REG_EXTENDED, REG_ICASE)
(REG_NEWLINE, REG_NOSUB, REG_NOTBOL, REG_NOTEOL, regmatch_t):
Remove; unused.
* src/search.c (Fset_match_data): Simplify range test now that
we know it’s ptrdiff_t.
This commit is contained in:
Paul Eggert 2018-08-05 18:41:20 -07:00
parent d904cc83f3
commit 3a6abe65c1
4 changed files with 486 additions and 2067 deletions
Download patch file Download diff file Expand all files Collapse all files

535
src/regex-emacs.h
View file

@ -17,163 +17,24 @@
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
#ifndef _REGEX_H
#define _REGEX_H 1
#ifndef EMACS_REGEX_H
#define EMACS_REGEX_H 1
#if defined emacs && (defined _REGEX_RE_COMP || defined _LIBC)
/* We're not defining re_set_syntax and using a different prototype of
re_compile_pattern when building Emacs so fail compilation early with
a (somewhat helpful) error message when conflict is detected. */
# error "_REGEX_RE_COMP nor _LIBC can be defined if emacs is defined."
#endif
#include <stddef.h>
#include <sys/types.h>
/* This is the structure we store register match data in. See
regex.texinfo for a full description of what registers match.
Declare this before including lisp.h, since lisp.h (via thread.h)
uses struct re_registers. */
struct re_registers
{
unsigned num_regs;
ptrdiff_t *start;
ptrdiff_t *end;
};
/* Allow the use in C++ code. */
#ifdef __cplusplus
extern "C" {
#endif
#include "lisp.h"
#if !defined _POSIX_C_SOURCE && !defined _POSIX_SOURCE && defined VMS
/* VMS doesn't have `size_t' in <sys/types.h>, even though POSIX says it
should be there. */
# include <stddef.h>
#endif
/* The following bits are used to determine the regexp syntax we
recognize. The set/not-set meanings where historically chosen so
that Emacs syntax had 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 reg_syntax_t;
/* If this bit is not set, then \ inside a bracket expression is literal.
If set, then such a \ quotes the following character. */
#define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)
/* If this bit is not set, then + and ? are operators, and \+ and \? are
literals.
If set, then \+ and \? are operators and + and ? are literals. */
#define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)
/* If this bit is set, then character classes are supported. They are:
[: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)
/* If this bit is set, then ^ and $ are always anchors (outside bracket
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)
/* If this bit is set, then special characters are always special
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)
/* If this bit is set, then *, +, ?, and { cannot be first in an re or
immediately after an alternation or begin-group operator. */
#define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1)
/* If this bit is set, then . matches newline.
If not set, then it doesn't. */
#define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1)
/* If this bit is set, then . doesn't match NUL.
If not set, then it does. */
#define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1)
/* If this bit is set, nonmatching lists [^...] do not match newline.
If not set, they do. */
#define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1)
/* If this bit is set, either \{...\} or {...} defines an
interval, depending on RE_NO_BK_BRACES.
If not set, \{, \}, {, and } are literals. */
#define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)
/* If this bit is set, +, ? and | aren't recognized as operators.
If not set, they are. */
#define RE_LIMITED_OPS (RE_INTERVALS << 1)
/* If this bit is set, newline is an alternation operator.
If not set, newline is literal. */
#define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1)
/* If this bit is set, then `{...}' defines an interval, and \{ and \}
are literals.
If not set, then `\{...\}' defines an interval. */
#define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1)
/* If this bit is set, (...) defines a group, and \( and \) are literals.
If not set, \(...\) defines a group, and ( and ) are literals. */
#define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1)
/* If this bit is set, then \<digit> matches <digit>.
If not set, then \<digit> is a back-reference. */
#define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1)
/* If this bit is set, then | is an alternation operator, and \| is literal.
If not set, then \| is an alternation operator, and | is literal. */
#define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1)
/* If this bit is set, then an ending range point collating higher
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 this bit is set, then an unmatched ) is ordinary.
If not set, then an unmatched ) is invalid. */
#define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1)
/* If this bit is set, succeed as soon as we match the whole pattern,
without further backtracking. */
#define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)
/* If this bit is set, do not process the GNU regex operators.
If not set, then the GNU regex operators are recognized. */
#define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)
/* If this bit is set, then *?, +? and ?? match non greedily. */
#define RE_FRUGAL (RE_NO_GNU_OPS << 1)
/* If this bit is set, then (?:...) is treated as a shy group. */
#define RE_SHY_GROUPS (RE_FRUGAL << 1)
/* If this bit is set, ^ and $ only match at beg/end of buffer. */
#define RE_NO_NEWLINE_ANCHOR (RE_SHY_GROUPS << 1)
/* If this bit is set, turn on internal regex debugging.
If not set, and debugging was on, turn it off.
This only works if regex-emacs.c is compiled -DDEBUG.
We define this bit always, so that all that's needed to turn on
debugging is to recompile regex-emacs.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_NEWLINE_ANCHOR << 1)
/* This global variable defines the particular regexp syntax to use (for
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; */
#ifdef emacs
# include "lisp.h"
/* In Emacs, this is the string or buffer in which we are matching.
It is used for looking up syntax properties.
@ -187,187 +48,23 @@ typedef unsigned long reg_syntax_t;
and match functions. These functions capture the current value of
re_match_object into gl_state on entry.
TODO: once we get rid of the !emacs case in this code, turn into an
actual function parameter. */
TODO: turn into an actual function parameter. */
extern Lisp_Object re_match_object;
#endif
/* Roughly the maximum number of failure points on the stack. */
extern size_t emacs_re_max_failures;
#ifdef emacs
/* Amount of memory that we can safely stack allocate. */
extern ptrdiff_t emacs_re_safe_alloca;
#endif
/* Define combinations of the above bits for the standard possibilities.
(The [[[ comments delimit what gets put into the Texinfo file, so
don't delete them!) */
/* [[[begin syntaxes]]] */
#define RE_SYNTAX_EMACS \
(RE_CHAR_CLASSES | RE_INTERVALS | RE_SHY_GROUPS | RE_FRUGAL)
#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)
/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */
#define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC
#define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC
/* Syntax bits common to both basic and extended POSIX regex syntax. */
#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)
/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes
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)
/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is
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)
/* [[[end syntaxes]]] */
/* Maximum number of duplicates an interval can allow. Some systems
(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
/* Repeat counts are stored in opcodes as 2 byte integers. This was
previously limited to 7fff because the parsing code uses signed
ints. But Emacs only runs on 32 bit platforms anyway. */
#define RE_DUP_MAX (0xffff)
/* POSIX `cflags' bits (i.e., information for `regcomp'). */
/* If this bit is set, then use extended regular expression syntax.
If not set, then use basic regular expression syntax. */
#define REG_EXTENDED 1
/* If this bit is set, then ignore case when matching.
If not set, then case is significant. */
#define REG_ICASE (REG_EXTENDED << 1)
/* If this bit is set, then anchors do not match at newline
characters in the string.
If not set, then anchors do match at newlines. */
#define REG_NEWLINE (REG_ICASE << 1)
/* If this bit is set, then report only success or fail in regexec.
If not set, then returns differ between not matching and errors. */
#define REG_NOSUB (REG_NEWLINE << 1)
/* POSIX `eflags' bits (i.e., information for regexec). */
/* If this bit is set, then the beginning-of-line operator doesn't match
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
/* Like REG_NOTBOL, except for the end-of-line. */
#define REG_NOTEOL (1 << 1)
/* If any error codes are removed, changed, or added, update the
`re_error_msg' table in regex-emacs.c. */
typedef enum
{
#ifdef _XOPEN_SOURCE
REG_ENOSYS = -1, /* This will never happen for this implementation. */
#endif
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_ERANGEX, /* Range striding over charsets. */
REG_ESIZEBR /* n or m too big in \{n,m\} */
} reg_errcode_t;
/* Use a type compatible with Emacs. */
#define RE_TRANSLATE_TYPE Lisp_Object
#define RE_TRANSLATE(TBL, C) char_table_translate (TBL, C)
#define RE_TRANSLATE_P(TBL) (!EQ (TBL, make_number (0)))
/* 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. */
#ifndef RE_TRANSLATE_TYPE
# define RE_TRANSLATE_TYPE char *
#endif
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. */
@ -379,13 +76,9 @@ struct re_pattern_buffer
/* Number of bytes actually used in `buffer'. */
size_t used;
#ifdef emacs
/* Charset of unibyte characters at compiling time. */
int charset_unibyte;
#else
/* Syntax setting with which the pattern was compiled. */
reg_syntax_t syntax;
#endif
/* 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. */
@ -395,7 +88,7 @@ struct re_pattern_buffer
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;
Lisp_Object translate;
/* Number of subexpressions found by the compiler. */
size_t re_nsub;
@ -410,9 +103,6 @@ struct re_pattern_buffer
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
@ -434,7 +124,6 @@ struct re_pattern_buffer
so the compiled pattern is only valid for the current syntax table. */
unsigned used_syntax : 1;
#ifdef emacs
/* If true, multi-byte form in the regexp pattern should be
recognized as a multibyte character. */
unsigned multibyte : 1;
@ -442,72 +131,17 @@ struct re_pattern_buffer
/* If true, multi-byte form in the target of match should be
recognized as a multibyte character. */
unsigned target_multibyte : 1;
#endif
/* [[[end pattern_buffer]]] */
};
typedef struct re_pattern_buffer regex_t;
/* POSIX 1003.1-2008 requires that regoff_t be at least as wide as
ptrdiff_t and ssize_t. We don't know of any hosts where ptrdiff_t
is wider than ssize_t, so ssize_t is safe. ptrdiff_t is not
necessarily visible here, so use ssize_t. */
typedef ssize_t 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. */
#ifndef emacs
/* 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 (reg_syntax_t __syntax);
#endif
/* 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 (const char *__pattern, size_t __length,
#ifdef emacs
extern const char *re_compile_pattern (const char *pattern, size_t length,
bool posix_backtracking,
const char *whitespace_regexp,
#endif
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 (struct re_pattern_buffer *__buffer);
struct re_pattern_buffer *buffer);
/* Search in the string STRING (with length LENGTH) for the pattern
@ -515,42 +149,36 @@ extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);
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 regoff_t re_search (struct re_pattern_buffer *__buffer,
const char *__string, size_t __length,
ssize_t __start, ssize_t __range,
struct re_registers *__regs);
extern ptrdiff_t re_search (struct re_pattern_buffer *buffer,
const char *string, size_t length,
ptrdiff_t start, ptrdiff_t 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 regoff_t re_search_2 (struct re_pattern_buffer *__buffer,
const char *__string1, size_t __length1,
const char *__string2, size_t __length2,
ssize_t __start, ssize_t __range,
struct re_registers *__regs,
ssize_t __stop);
extern ptrdiff_t re_search_2 (struct re_pattern_buffer *buffer,
const char *string1, size_t length1,
const char *string2, size_t length2,
ptrdiff_t start, ptrdiff_t range,
struct re_registers *regs,
ptrdiff_t stop);
/* Like `re_search', but return how many characters in STRING the regexp
/* Like 're_search_2', but return how many characters in STRING the regexp
in BUFFER matched, starting at position START. */
extern regoff_t re_match (struct re_pattern_buffer *__buffer,
const char *__string, size_t __length,
ssize_t __start, struct re_registers *__regs);
/* Relates to `re_match' as `re_search_2' relates to `re_search'. */
extern regoff_t re_match_2 (struct re_pattern_buffer *__buffer,
const char *__string1, size_t __length1,
const char *__string2, size_t __length2,
ssize_t __start, struct re_registers *__regs,
ssize_t __stop);
extern ptrdiff_t re_match_2 (struct re_pattern_buffer *buffer,
const char *string1, size_t length1,
const char *string2, size_t length2,
ptrdiff_t start, struct re_registers *regs,
ptrdiff_t 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.
(ptrdiff_t)' bytes long.
If NUM_REGS == 0, then subsequent matches should allocate their own
register data.
@ -558,83 +186,10 @@ extern regoff_t re_match_2 (struct re_pattern_buffer *__buffer,
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
/* 4.2 bsd compatibility. */
extern char *re_comp (const char *);
extern int re_exec (const char *);
# endif
#endif
/* GCC 2.95 and later have "__restrict"; C99 compilers have
"restrict", and "configure" may have defined "restrict".
Other compilers use __restrict, __restrict__, and _Restrict, and
'configure' might #define 'restrict' to those words, so pick a
different name. */
#ifndef _Restrict_
# if 199901L <= __STDC_VERSION__
# define _Restrict_ restrict
# elif 2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)
# define _Restrict_ __restrict
# else
# define _Restrict_
# endif
#endif
/* gcc 3.1 and up support the [restrict] syntax. Don't trust
sys/cdefs.h's definition of __restrict_arr, though, as it
mishandles gcc -ansi -pedantic. */
#ifndef _Restrict_arr_
# if ((199901L <= __STDC_VERSION__ \
|| ((3 < __GNUC__ || (3 == __GNUC__ && 1 <= __GNUC_MINOR__)) \
&& !defined __STRICT_ANSI__)) \
&& !defined __GNUG__)
# define _Restrict_arr_ _Restrict_
# else
# define _Restrict_arr_
# endif
#endif
/* POSIX compatibility. */
extern reg_errcode_t regcomp (regex_t *_Restrict_ __preg,
const char *_Restrict_ __pattern,
int __cflags);
extern reg_errcode_t 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 /* C++ */
/* For platform which support the ISO C amendment 1 functionality we
support user defined character classes. */
#if WIDE_CHAR_SUPPORT
/* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>. */
# include <wchar.h>
# include <wctype.h>
typedef wctype_t re_wctype_t;
typedef wchar_t re_wchar_t;
# define re_wctype wctype
# define re_iswctype iswctype
# define re_wctype_to_bit(cc) 0
#else
# ifndef emacs
# define btowc(c) c
# endif
extern void re_set_registers (struct re_pattern_buffer *buffer,
struct re_registers *regs,
unsigned num_regs,
ptrdiff_t *starts, ptrdiff_t *ends);
/* Character classes. */
typedef enum { RECC_ERROR = 0,
@ -648,12 +203,8 @@ typedef enum { RECC_ERROR = 0,
RECC_ASCII, RECC_UNIBYTE
} re_wctype_t;
extern char re_iswctype (int ch, re_wctype_t cc);
extern re_wctype_t re_wctype_parse (const unsigned char **strp, unsigned limit);
typedef int re_wchar_t;
#endif /* not WIDE_CHAR_SUPPORT */
extern bool re_iswctype (int ch, re_wctype_t cc);
extern re_wctype_t re_wctype_parse (const unsigned char **strp,
unsigned limit);
#endif /* regex-emacs.h */