⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 gnu-regex.c

📁 gcc-2.95.3 Linux下最常用的C编译器
💻 C
📖 第 1 页 / 共 5 页
字号:
/* Extended regular expression matching and search library,   version 0.12.   (Implements POSIX draft P1003.2/D11.2, except for some of the   internationalization features.)   Copyright (C) 1993, 94, 95, 96, 97, 98 Free Software Foundation, Inc.   NOTE: The canonical source of this file is maintained with the    GNU C Library.  Bugs can be reported to bug-glibc@prep.ai.mit.edu.   This program is free software; you can redistribute it and/or modify it   under the terms of the GNU General Public License as published by the   Free Software Foundation; either version 2, or (at your option) any   later version.   This program 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 General Public License for more details.   You should have received a copy of the GNU General Public License   along with this program; if not, write to the Free Software Foundation,    Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.  *//* AIX requires this to be the first thing in the file. */#if defined _AIX && !defined REGEX_MALLOC  #pragma alloca#endif#undef	_GNU_SOURCE#define _GNU_SOURCE#ifdef HAVE_CONFIG_H# include <config.h>#endif#ifndef PARAMS# if defined __GNUC__ || (defined __STDC__ && __STDC__)#  define PARAMS(args) args# else#  define PARAMS(args) ()# endif  /* GCC.  */#endif  /* Not PARAMS.  */#if defined STDC_HEADERS && !defined emacs# include <stddef.h>#else/* We need this for `gnu-regex.h', and perhaps for the Emacs include files.  */# include <sys/types.h>#endif/* For platform which support the ISO C amendement 1 functionality we   support user defined character classes.  */#if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) /* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>.  */# include <wchar.h># include <wctype.h>#endif/* This is for other GNU distributions with internationalized messages.  *//* CYGNUS LOCAL: ../intl will handle this for us */#ifdef ENABLE_NLS# include <libintl.h>#else# define gettext(msgid) (msgid)#endif#ifndef gettext_noop/* This define is so xgettext can find the internationalizable   strings.  */# define gettext_noop(String) String#endif/* The `emacs' switch turns on certain matching commands   that make sense only in Emacs. */#ifdef emacs# include "lisp.h"# include "buffer.h"# include "syntax.h"#else  /* not emacs */# include "auto-host.h"# if !defined(const) && !defined(HAVE_CONST)#  define const# endif# if !defined(volatile) && !defined(HAVE_VOLATILE)#  define volatile# endif/* If we are not linking with Emacs proper,   we can't use the relocating allocator   even if config.h says that we can.  */# undef REL_ALLOC# if defined STDC_HEADERS || defined _LIBC#  include <stdlib.h># elsechar *malloc ();char *realloc ();# endif/* When used in Emacs's lib-src, we need to get bzero and bcopy somehow.   If nothing else has been done, use the method below.  */# ifdef INHIBIT_STRING_HEADER#  if !(defined HAVE_BZERO && defined HAVE_BCOPY)#   if !defined bzero && !defined bcopy#    undef INHIBIT_STRING_HEADER#   endif#  endif# endif/* This is the normal way of making sure we have a bcopy and a bzero.   This is used in most programs--a few other programs avoid this   by defining INHIBIT_STRING_HEADER.  */# ifndef INHIBIT_STRING_HEADER#  if defined HAVE_STRING_H || defined STDC_HEADERS || defined _LIBC#   include <string.h>#   ifndef bzero#    ifndef _LIBC#     define bzero(s, n)	(memset (s, '\0', n), (s))#    else#     define bzero(s, n)	__bzero (s, n)#    endif#   endif#  else#   include <strings.h>#   ifndef memcmp#    define memcmp(s1, s2, n)	bcmp (s1, s2, n)#   endif#   ifndef memcpy#    define memcpy(d, s, n)	(bcopy (s, d, n), (d))#   endif#  endif# endif/* Define the syntax stuff for \<, \>, etc.  *//* This must be nonzero for the wordchar and notwordchar pattern   commands in re_match_2.  */# ifndef Sword#  define Sword 1# endif# ifdef SWITCH_ENUM_BUG#  define SWITCH_ENUM_CAST(x) ((int)(x))# else#  define SWITCH_ENUM_CAST(x) (x)# endif/* How many characters in the character set.  */# define CHAR_SET_SIZE 256/* GDB LOCAL: define _REGEX_RE_COMP to get BSD style re_comp and re_exec */#ifndef _REGEX_RE_COMP#define _REGEX_RE_COMP#endif# ifdef SYNTAX_TABLEextern char *re_syntax_table;# else /* not SYNTAX_TABLE */static char re_syntax_table[CHAR_SET_SIZE];static voidinit_syntax_once (){   register int c;   static int done = 0;   if (done)     return;   bzero (re_syntax_table, sizeof re_syntax_table);   for (c = 'a'; c <= 'z'; c++)     re_syntax_table[c] = Sword;   for (c = 'A'; c <= 'Z'; c++)     re_syntax_table[c] = Sword;   for (c = '0'; c <= '9'; c++)     re_syntax_table[c] = Sword;   re_syntax_table['_'] = Sword;   done = 1;}# endif /* not SYNTAX_TABLE */# define SYNTAX(c) re_syntax_table[c]#endif /* not emacs *//* Get the interface, including the syntax bits.  *//* CYGNUS LOCAL: call it gnu-regex.h, not regex.h, to avoid name conflicts */#include "gnu-regex.h"/* isalpha etc. are used for the character classes.  */#include <ctype.h>/* Jim Meyering writes:   "... Some ctype macros are valid only for character codes that   isascii says are ASCII (SGI's IRIX-4.0.5 is one such system --when   using /bin/cc or gcc but without giving an ansi option).  So, all   ctype uses should be through macros like ISPRINT...  If   STDC_HEADERS is defined, then autoconf has verified that the ctype   macros don't need to be guarded with references to isascii. ...   Defining isascii to 1 should let any compiler worth its salt   eliminate the && through constant folding."   Solaris defines some of these symbols so we must undefine them first.  */#undef ISASCII#if defined STDC_HEADERS || (!defined isascii && !defined HAVE_ISASCII)# define ISASCII(c) 1#else# define ISASCII(c) isascii(c)#endif#ifdef isblank# define ISBLANK(c) (ISASCII (c) && isblank (c))#else# define ISBLANK(c) ((c) == ' ' || (c) == '\t')#endif#ifdef isgraph# define ISGRAPH(c) (ISASCII (c) && isgraph (c))#else# define ISGRAPH(c) (ISASCII (c) && isprint (c) && !isspace (c))#endif#undef ISPRINT#define ISPRINT(c) (ISASCII (c) && isprint (c))#define ISDIGIT(c) (ISASCII (c) && isdigit (c))#define ISALNUM(c) (ISASCII (c) && isalnum (c))#define ISALPHA(c) (ISASCII (c) && isalpha (c))#define ISCNTRL(c) (ISASCII (c) && iscntrl (c))#define ISLOWER(c) (ISASCII (c) && islower (c))#define ISPUNCT(c) (ISASCII (c) && ispunct (c))#define ISSPACE(c) (ISASCII (c) && isspace (c))#define ISUPPER(c) (ISASCII (c) && isupper (c))#define ISXDIGIT(c) (ISASCII (c) && isxdigit (c))#ifndef NULL# define NULL (void *)0#endif/* We remove any previous definition of `SIGN_EXTEND_CHAR',   since ours (we hope) works properly with all combinations of   machines, compilers, `char' and `unsigned char' argument types.   (Per Bothner suggested the basic approach.)  */#undef SIGN_EXTEND_CHAR#if __STDC__# define SIGN_EXTEND_CHAR(c) ((signed char) (c))#else  /* not __STDC__ *//* As in Harbison and Steele.  */# define SIGN_EXTEND_CHAR(c) ((((unsigned char) (c)) ^ 128) - 128)#endif/* Should we use malloc or alloca?  If REGEX_MALLOC is not defined, we   use `alloca' instead of `malloc'.  This is because using malloc in   re_search* or re_match* could cause memory leaks when C-g is used in   Emacs; also, malloc is slower and causes storage fragmentation.  On   the other hand, malloc is more portable, and easier to debug.   Because we sometimes use alloca, some routines have to be macros,   not functions -- `alloca'-allocated space disappears at the end of the   function it is called in.  */#ifdef REGEX_MALLOC# define REGEX_ALLOCATE malloc# define REGEX_REALLOCATE(source, osize, nsize) realloc (source, nsize)# define REGEX_FREE free#else /* not REGEX_MALLOC  *//* Emacs already defines alloca, sometimes.  */# ifndef alloca/* Make alloca work the best possible way.  */#  ifdef __GNUC__#   define alloca __builtin_alloca#  else /* not __GNUC__ */#   if HAVE_ALLOCA_H#    include <alloca.h>#   endif /* HAVE_ALLOCA_H */#  endif /* not __GNUC__ */# endif /* not alloca */# define REGEX_ALLOCATE alloca/* Assumes a `char *destination' variable.  */# define REGEX_REALLOCATE(source, osize, nsize)				\  (destination = (char *) alloca (nsize),				\   memcpy (destination, source, osize))/* No need to do anything to free, after alloca.  */# define REGEX_FREE(arg) ((void)0) /* Do nothing!  But inhibit gcc warning.  */#endif /* not REGEX_MALLOC *//* Define how to allocate the failure stack.  */#if defined REL_ALLOC && defined REGEX_MALLOC# define REGEX_ALLOCATE_STACK(size)				\  r_alloc (&failure_stack_ptr, (size))# define REGEX_REALLOCATE_STACK(source, osize, nsize)		\  r_re_alloc (&failure_stack_ptr, (nsize))# define REGEX_FREE_STACK(ptr)					\  r_alloc_free (&failure_stack_ptr)#else /* not using relocating allocator */# ifdef REGEX_MALLOC#  define REGEX_ALLOCATE_STACK malloc#  define REGEX_REALLOCATE_STACK(source, osize, nsize) realloc (source, nsize)#  define REGEX_FREE_STACK free# else /* not REGEX_MALLOC */#  define REGEX_ALLOCATE_STACK alloca#  define REGEX_REALLOCATE_STACK(source, osize, nsize)			\   REGEX_REALLOCATE (source, osize, nsize)/* No need to explicitly free anything.  */#  define REGEX_FREE_STACK(arg)# endif /* not REGEX_MALLOC */#endif /* not using relocating allocator *//* True if `size1' is non-NULL and PTR is pointing anywhere inside   `string1' or just past its end.  This works if PTR is NULL, which is   a good thing.  */#define FIRST_STRING_P(ptr) 					\  (size1 && string1 <= (ptr) && (ptr) <= string1 + size1)/* (Re)Allocate N items of type T using malloc, or fail.  */#define TALLOC(n, t) ((t *) malloc ((n) * sizeof (t)))#define RETALLOC(addr, n, t) ((addr) = (t *) realloc (addr, (n) * sizeof (t)))#define RETALLOC_IF(addr, n, t) \  if (addr) RETALLOC((addr), (n), t); else (addr) = TALLOC ((n), t)#define REGEX_TALLOC(n, t) ((t *) REGEX_ALLOCATE ((n) * sizeof (t)))#define BYTEWIDTH 8 /* In bits.  */#define STREQ(s1, s2) ((strcmp (s1, s2) == 0))#undef MAX#undef MIN#define MAX(a, b) ((a) > (b) ? (a) : (b))#define MIN(a, b) ((a) < (b) ? (a) : (b))typedef char boolean;#define false 0#define true 1static int re_match_2_internal PARAMS ((struct re_pattern_buffer *bufp,					const char *string1, int size1,					const char *string2, int size2,					int pos,					struct re_registers *regs,					int stop));/* These are the command codes that appear in compiled regular   expressions.  Some opcodes are followed by argument bytes.  A   command code can specify any interpretation whatsoever for its   arguments.  Zero bytes may appear in the compiled regular expression.  */typedef enum{  no_op = 0,  /* Succeed right away--no more backtracking.  */  succeed,        /* Followed by one byte giving n, then by n literal bytes.  */  exactn,        /* Matches any (more or less) character.  */  anychar,        /* Matches any one char belonging to specified set.  First           following byte is number of bitmap bytes.  Then come bytes           for a bitmap saying which chars are in.  Bits in each byte           are ordered low-bit-first.  A character is in the set if its           bit is 1.  A character too large to have a bit in the map is           automatically not in the set.  */  charset,        /* Same parameters as charset, but match any character that is           not one of those specified.  */  charset_not,        /* Start remembering the text that is matched, for storing in a           register.  Followed by one byte with the register number, in           the range 0 to one less than the pattern buffer's re_nsub           field.  Then followed by one byte with the number of groups           inner to this one.  (This last has to be part of the           start_memory only because we need it in the on_failure_jump           of re_match_2.)  */  start_memory,        /* Stop remembering the text that is matched and store it in a           memory register.  Followed by one byte with the register           number, in the range 0 to one less than `re_nsub' in the

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -