diff options
Diffstat (limited to 'include/regex.h')
| -rw-r--r-- | include/regex.h | 138 |
1 files changed, 73 insertions, 65 deletions
diff --git a/include/regex.h b/include/regex.h index 1d4ddd27d..f5dda89f7 100644 --- a/include/regex.h +++ b/include/regex.h @@ -1,6 +1,6 @@ /* Definitions for data structures and routines for the regular expression library. - Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005 + Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005,2006,2008 Free Software Foundation, Inc. This file is part of the GNU C Library. @@ -22,21 +22,10 @@ #ifndef _REGEX_H #define _REGEX_H 1 -#include <features.h> - #include <sys/types.h> __BEGIN_DECLS -/* 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 -/* VMS doesn't have `size_t' in <sys/types.h>, even though POSIX says it - should be there. */ -# include <stddef.h> -#endif - /* The following two types have to be signed and unsigned integer type 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 @@ -51,20 +40,21 @@ typedef unsigned long int active_reg_t; add or remove a bit, only one other definition need change. */ typedef unsigned long int reg_syntax_t; +#ifdef __USE_GNU /* 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) +# 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) +# 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) +# define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1) /* If this bit is set, then ^ and $ are always anchors (outside bracket expressions, of course). @@ -78,7 +68,7 @@ typedef unsigned long int reg_syntax_t; 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) +# 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. @@ -86,71 +76,71 @@ typedef unsigned long int reg_syntax_t; 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# 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) +# define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1) /* If this bit is set, turn on internal regex debugging. If not set, and debugging was on, turn it off. @@ -158,29 +148,30 @@ typedef unsigned long int reg_syntax_t; 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) +# define RE_DEBUG (RE_NO_GNU_OPS << 1) /* If this bit is set, a syntactically invalid interval is treated as a string of ordinary characters. For example, the ERE 'a{1' is treated as 'a\{1'. */ -#define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1) +# define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1) /* If this bit is set, then ignore case when matching. If not set, then case is significant. */ -#define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1) +# define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1) /* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only for ^, because it is difficult to scan the regex backwards to find whether ^ should be special. */ -#define RE_CARET_ANCHORS_HERE (RE_ICASE << 1) +# define RE_CARET_ANCHORS_HERE (RE_ICASE << 1) /* If this bit is set, then \{ cannot be first in an bre or immediately after an alternation or begin-group operator. */ -#define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1) +# define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1) /* If this bit is set, then no_sub will be set to 1 during re_compile_pattern. */ -#define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1) +# define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1) +#endif /* This global variable defines the particular regexp syntax to use (for some interfaces). When a regexp is compiled, the syntax used is @@ -188,6 +179,7 @@ typedef unsigned long int reg_syntax_t; already-compiled regexps. */ extern reg_syntax_t re_syntax_options; +#ifdef __USE_GNU /* 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!) */ @@ -262,11 +254,12 @@ extern reg_syntax_t re_syntax_options; /* 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 +# ifdef RE_DUP_MAX +# undef RE_DUP_MAX +# endif /* If sizeof(int) == 2, then ((1 << 15) - 1) overflows. */ -#define RE_DUP_MAX (0x7fff) +# define RE_DUP_MAX (0x7fff) +#endif /* POSIX `cflags' bits (i.e., information for `regcomp'). */ @@ -310,7 +303,7 @@ extern reg_syntax_t re_syntax_options; `re_error_msg' table in regex.c. */ typedef enum { -#ifdef _XOPEN_SOURCE +#if defined _XOPEN_SOURCE || defined __USE_XOPEN2K REG_ENOSYS = -1, /* This will never happen for this implementation. */ #endif @@ -345,7 +338,16 @@ typedef enum private to the regex routines. */ #ifndef RE_TRANSLATE_TYPE -# define RE_TRANSLATE_TYPE unsigned char * +# define __RE_TRANSLATE_TYPE unsigned char * +# ifdef __USE_GNU +# define RE_TRANSLATE_TYPE __RE_TRANSLATE_TYPE +# endif +#endif + +#ifdef __USE_GNU +# define __REPB_PREFIX(name) name +#else +# define __REPB_PREFIX(name) __##name #endif struct re_pattern_buffer @@ -353,27 +355,27 @@ struct re_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; + unsigned char *__REPB_PREFIX(buffer); /* Number of bytes to which `buffer' points. */ - unsigned long int allocated; + unsigned long int __REPB_PREFIX(allocated); /* Number of bytes actually used in `buffer'. */ - unsigned long int used; + unsigned long int __REPB_PREFIX(used); /* Syntax setting with which the pattern was compiled. */ - reg_syntax_t syntax; + reg_syntax_t __REPB_PREFIX(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; + char *__REPB_PREFIX(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. */ - RE_TRANSLATE_TYPE translate; + __RE_TRANSLATE_TYPE __REPB_PREFIX(translate); /* Number of subexpressions found by the compiler. */ size_t re_nsub; @@ -382,34 +384,36 @@ struct re_pattern_buffer 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; + unsigned __REPB_PREFIX(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; +#ifdef __USE_GNU +# define REGS_UNALLOCATED 0 +# define REGS_REALLOCATE 1 +# define REGS_FIXED 2 +#endif + unsigned __REPB_PREFIX(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; + unsigned __REPB_PREFIX(fastmap_accurate) : 1; /* If set, `re_match_2' does not return information about subexpressions. */ - unsigned no_sub : 1; + unsigned __REPB_PREFIX(no_sub) : 1; /* If set, a beginning-of-line anchor doesn't match at the beginning of the string. */ - unsigned not_bol : 1; + unsigned __REPB_PREFIX(not_bol) : 1; /* Similarly for an end-of-line anchor. */ - unsigned not_eol : 1; + unsigned __REPB_PREFIX(not_eol) : 1; /* If true, an anchor at a newline matches. */ - unsigned newline_anchor : 1; + unsigned __REPB_PREFIX(newline_anchor) : 1; }; typedef struct re_pattern_buffer regex_t; @@ -418,6 +422,7 @@ typedef struct re_pattern_buffer regex_t; typedef int regoff_t; +#ifdef __USE_GNU /* This is the structure we store register match data in. See regex.texinfo for a full description of what registers match. */ struct re_registers @@ -431,8 +436,9 @@ struct re_registers /* 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 +# ifndef RE_NREGS +# define RE_NREGS 30 +# endif #endif @@ -447,7 +453,7 @@ typedef struct /* Declarations for routines. */ - +#ifdef __USE_GNU /* 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); @@ -515,8 +521,9 @@ extern void re_set_registers (struct re_pattern_buffer *__buffer, struct re_registers *__regs, unsigned int __num_regs, regoff_t *__starts, regoff_t *__ends); +#endif /* Use GNU */ -#if defined _REGEX_RE_COMP || defined _LIBC +#if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_BSD) # ifndef _CRAY /* 4.2 bsd compatibility. */ extern char *re_comp (const char *); @@ -537,7 +544,8 @@ extern int re_exec (const char *); #endif /* gcc 3.1 and up support the [restrict] syntax. */ #ifndef __restrict_arr -# if __GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1) +# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) \ + && !defined __GNUG__ # define __restrict_arr __restrict # else # define __restrict_arr |