Commit 0b32bf0e authored by Stefan Monnier's avatar Stefan Monnier

* regex.c: Indent cpp directives and remove parens after `defined'.

(PTR_TO_OFFSET, POS_AS_IN_BUFFER): Move to a better place.
(ISDIGIT, ISCNTRL, ISXDIGIT) [!emacs]: Remove duplicate definition.
(regex_compile): Use RE_FRUGAL instead of RE_ALL_GREEDY.
(re_compile_pattern): Use size_t for length.
(init_syntax_once): Move to a better place.
* regex.h: Merge changes from GNU libc.  Indent cpp directives.
(RE_FRUGAL): Replaces RE_ALL_GREEDY (inverted meaning).
parent 28bb2cef
2000-08-27 Stefan Monnier <monnier@cs.yale.edu>
* regex.c: Indent cpp directives and remove parens after `defined'.
(PTR_TO_OFFSET, POS_AS_IN_BUFFER): Move to a better place.
(ISDIGIT, ISCNTRL, ISXDIGIT) [!emacs]: Remove duplicate definition.
(regex_compile): Use RE_FRUGAL instead of RE_ALL_GREEDY.
(re_compile_pattern): Use size_t for length.
(init_syntax_once): Move to a better place.
* regex.h: Merge changes from GNU libc. Indent cpp directives.
(RE_FRUGAL): Replaces RE_ALL_GREEDY (inverted meaning).
* syntax.c (back_comment): Detect cases where a comment-starter is
actually inside another comment as in: /* a // b */ c // d \n.
Make it clear that `comstart_pos' is unused for nested comments.
......
This diff is collapsed.
......@@ -18,36 +18,37 @@
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
USA. */
#ifndef __REGEXP_LIBRARY_H__
#define __REGEXP_LIBRARY_H__
#ifndef _REGEX_H
#define _REGEX_H 1
/* Allow the use in C++ code. */
#ifdef __cplusplus
extern "C" {
#endif
/* POSIX says that <sys/types.h> must be included (by the caller) before
<regex.h>. */
#if !defined (_POSIX_C_SOURCE) && !defined (_POSIX_SOURCE) && defined (VMS)
#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>
# 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 reg_syntax_t;
/* If this bit is set, then even *?, +? and ?? match greedily. */
#define RE_ALL_GREEDY (1)
typedef unsigned long int 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 (RE_ALL_GREEDY << 1)
#define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)
/* If this bit is not set, then + and ? are operators, and \+ and \? are
literals.
literals.
If set, then \+ and \? are operators and + and ? are literals. */
#define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)
......@@ -63,7 +64,7 @@ typedef unsigned reg_syntax_t;
^ 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.
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.
......@@ -74,7 +75,7 @@ typedef unsigned reg_syntax_t;
/* 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,
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)
......@@ -96,7 +97,7 @@ typedef unsigned reg_syntax_t;
#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.
interval, depending on RE_NO_BK_BRACES.
If not set, \{, \}, {, and } are literals. */
#define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)
......@@ -121,7 +122,7 @@ typedef unsigned reg_syntax_t;
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 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)
......@@ -131,16 +132,31 @@ typedef unsigned reg_syntax_t;
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_NO_EMPTY_RANGES << 1)
#define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)
/* If this bit is set, then (?:...) is treated as a shy group. */
#define RE_SHY_GROUPS (RE_NO_POSIX_BACKTRACKING << 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 an unmatched ) is ordinary.
If not set, then an unmatched ) is invalid. */
#define RE_UNMATCHED_RIGHT_PAREN_ORD (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.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)
/* If this bit is set, then *?, +? and ?? match non greedily. */
#define RE_FRUGAL (RE_DEBUG << 1)
/* If this bit is set, then (?:...) is treated as a shy group. */
#define RE_SHY_GROUPS (RE_FRUGAL << 1)
/* This global variable defines the particular regexp syntax to use (for
some interfaces). When a regexp is compiled, the syntax used is
......@@ -159,27 +175,34 @@ extern Lisp_Object re_match_object;
(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)
#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_UNMATCHED_RIGHT_PAREN_ORD | RE_ALL_GREEDY)
(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_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 | RE_ALL_GREEDY)
| 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 | RE_ALL_GREEDY)
| RE_NO_BK_VBAR)
#define RE_SYNTAX_POSIX_EGREP \
(RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES)
......@@ -192,7 +215,7 @@ extern Lisp_Object re_match_object;
/* 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 | RE_ALL_GREEDY)
| RE_INTERVALS | RE_NO_EMPTY_RANGES)
#define RE_SYNTAX_POSIX_BASIC \
(_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM)
......@@ -204,13 +227,13 @@ extern Lisp_Object re_match_object;
(_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_UNMATCHED_RIGHT_PAREN_ORD)
(_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_INVALID_OPS
replaces RE_CONTEXT_INDEP_OPS and RE_NO_BK_REFS is added. */
/* 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 \
......@@ -222,9 +245,10 @@ extern Lisp_Object re_match_object;
(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
# undef RE_DUP_MAX
#endif
#define RE_DUP_MAX ((1 << 15) - 1)
/* If sizeof(int) == 2, then ((1 << 15) - 1) overflows. */
#define RE_DUP_MAX (0x7fff)
/* POSIX `cflags' bits (i.e., information for `regcomp'). */
......@@ -236,7 +260,7 @@ extern Lisp_Object re_match_object;
/* 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. */
......@@ -264,6 +288,10 @@ extern Lisp_Object re_match_object;
`re_error_msg' table in regex.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). */
......@@ -275,7 +303,7 @@ typedef enum
REG_EESCAPE, /* Trailing backslash. */
REG_ESUBREG, /* Invalid back reference. */
REG_EBRACK, /* Unmatched left bracket. */
REG_EPAREN, /* Parenthesis imbalance. */
REG_EPAREN, /* Parenthesis imbalance. */
REG_EBRACE, /* Unmatched \{. */
REG_BADBR, /* Invalid contents of \{\}. */
REG_ERANGE, /* Invalid range end. */
......@@ -295,7 +323,7 @@ typedef enum
private to the regex routines. */
#ifndef RE_TRANSLATE_TYPE
#define RE_TRANSLATE_TYPE char *
# define RE_TRANSLATE_TYPE char *
#endif
struct re_pattern_buffer
......@@ -307,10 +335,10 @@ struct re_pattern_buffer
unsigned char *buffer;
/* Number of bytes to which `buffer' points. */
unsigned long allocated;
unsigned long int allocated;
/* Number of bytes actually used in `buffer'. */
unsigned long used;
unsigned long int used;
/* Syntax setting with which the pattern was compiled. */
reg_syntax_t syntax;
......@@ -353,7 +381,7 @@ struct re_pattern_buffer
unsigned no_sub : 1;
/* If set, a beginning-of-line anchor doesn't match at the
beginning of the string. */
beginning of the string. */
unsigned not_bol : 1;
/* Similarly for an end-of-line anchor. */
......@@ -391,7 +419,7 @@ struct re_registers
`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
# define RE_NREGS 30
#endif
......@@ -414,11 +442,11 @@ typedef struct
#if defined __STDC__ || defined PROTOTYPES
#define _RE_ARGS(args) args
# define _RE_ARGS(args) args
#else /* not __STDC__ || PROTOTYPES */
#define _RE_ARGS(args) ()
# define _RE_ARGS(args) ()
#endif /* not __STDC__ || PROTOTYPES */
......@@ -430,7 +458,7 @@ extern reg_syntax_t re_set_syntax _RE_ARGS ((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
_RE_ARGS ((const char *pattern, int length,
_RE_ARGS ((const char *pattern, size_t length,
struct re_pattern_buffer *buffer));
......@@ -466,7 +494,7 @@ extern int re_match
/* Relates to `re_match' as `re_search_2' relates to `re_search'. */
extern int re_match_2
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));
......@@ -488,23 +516,51 @@ 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));
#ifdef _REGEX_RE_COMP
#if defined _REGEX_RE_COMP || defined _LIBC
# ifndef _CRAY
/* 4.2 bsd compatibility. */
extern char *re_comp _RE_ARGS ((const char *));
extern int re_exec _RE_ARGS ((const char *));
# endif
#endif
/* GCC 2.95 and later have "__restrict"; C99 compilers have
"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
/* For now unconditionally define __restrict_arr to expand to nothing.
Ideally we would have a test for the compiler which allows defining
it to restrict. */
#define __restrict_arr
/* 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__ */
extern int regcomp _RE_ARGS ((regex_t *__restrict __preg,
const char *__restrict __pattern,
int __cflags));
extern int regexec _RE_ARGS ((const regex_t *__restrict __preg,
const char *__restrict __string, size_t __nmatch,
regmatch_t __pmatch[__restrict_arr],
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));
#ifdef __cplusplus
}
#endif /* C++ */
#endif /* regex.h */
/*
Local variables:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment