misc/regexp.h

   1 /* Copyright (C) 1996, 1997, 1998, 1999, 2004, 2008, 2012
   2    Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   4    Contributed by Ulrich Drepper <drepper@cygnus.com>, 1996.
   5
   6    The GNU C Library is free software; you can redistribute it and/or
   7    modify it under the terms of the GNU Lesser General Public
   8    License as published by the Free Software Foundation; either
   9    version 2.1 of the License, or (at your option) any later version.
  10
  11    The GNU C Library is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public
  17    License along with the GNU C Library; if not, see
  18    <http://www.gnu.org/licenses/>.  */
  19
  20 #ifndef _REGEXP_H
  21 #define _REGEXP_H       1
  22
  23 /* The contents of this header file was first standardized in X/Open
  24    System Interface and Headers Issue 2, originally coming from SysV.
  25    In issue 4, version 2, it is marked as TO BE WITDRAWN, and it has
  26    been withdrawn in SUSv3.
  27
  28    This code shouldn't be used in any newly written code.  It is
  29    included only for compatibility reasons.  Use the POSIX definition
  30    in <regex.h> for portable applications and a reasonable interface.  */
  31
  32 #include <features.h>
  33 #include <alloca.h>
  34 #include <regex.h>
  35 #include <stdlib.h>
  36 #include <string.h>
  37
  38 /* The implementation provided here emulates the needed functionality
  39    by mapping to the POSIX regular expression matcher.  The interface
  40    for the here included function is weird (this really is a harmless
  41    word).
  42
  43    The user has to provide six macros before this header file can be
  44    included:
  45
  46    INIT         Declarations vor variables which can be used by the
  47                 other macros.
  48
  49    GETC()       Return the value of the next character in the regular
  50                 expression pattern.  Successive calls should return
  51                 successive characters.
  52
  53    PEEKC()      Return the value of the next character in the regular
  54                 expression pattern.  Immediately successive calls to
  55                 PEEKC() should return the same character which should
  56                 also be the next character returned by GETC().
  57
  58    UNGETC(c)    Cause `c' to be returned by the next call to GETC() and
  59                 PEEKC().
  60
  61    RETURN(ptr)  Used for normal exit of the `compile' function.  `ptr'
  62                 is a pointer to the character after the last character of
  63                 the compiled regular expression.
  64
  65    ERROR(val)   Used for abnormal return from `compile'.  `val' is the
  66                 error number.  The error codes are:
  67                 11      Range endpoint too large.
  68                 16      Bad number.
  69                 25      \digit out of range.
  70                 36      Illegal or missing delimiter.
  71                 41      No remembered search string.
  72                 42      \( \) imbalance.
  73                 43      Too many \(.
  74                 44      More tan two numbers given in \{ \}.
  75                 45      } expected after \.
  76                 46      First number exceeds second in \{ \}.
  77                 49      [ ] imbalance.
  78                 50      Regular expression overflow.
  79
  80   */
  81
  82 __BEGIN_DECLS
  83
  84 /* Interface variables.  They contain the results of the successful
  85    calls to `setp' and `advance'.  */
  86 extern char *loc1;
  87 extern char *loc2;
  88
  89 /* The use of this variable in the `advance' function is not
  90    supported.  */
  91 extern char *locs;
  92
  93
  94 #ifndef __DO_NOT_DEFINE_COMPILE
  95 /* Get and compile the user supplied pattern up to end of line or
  96    string or until EOF is seen, whatever happens first.  The result is
  97    placed in the buffer starting at EXPBUF and delimited by ENDBUF.
  98
  99    This function cannot be defined in the libc itself since it depends
 100    on the macros.  */
 101 char *
 102 compile (char *__restrict instring, char *__restrict expbuf,
 103          const char *__restrict endbuf, int eof)
 104 {
 105   char *__input_buffer = NULL;
 106   size_t __input_size = 0;
 107   size_t __current_size = 0;
 108   int __ch;
 109   int __error;
 110   INIT
 111
 112   /* Align the expression buffer according to the needs for an object
 113      of type `regex_t'.  Then check for minimum size of the buffer for
 114      the compiled regular expression.  */
 115   regex_t *__expr_ptr;
 116 # if defined __GNUC__ && __GNUC__ >= 2
 117   const size_t __req = __alignof__ (regex_t *);
 118 # else
 119   /* How shall we find out?  We simply guess it and can change it is
 120      this really proofs to be wrong.  */
 121   const size_t __req = 8;
 122 # endif
 123   expbuf += __req;
 124   expbuf -= (expbuf - ((char *) 0)) % __req;
 125   if (endbuf < expbuf + sizeof (regex_t))
 126     {
 127       ERROR (50);
 128     }
 129   __expr_ptr = (regex_t *) expbuf;
 130   /* The remaining space in the buffer can be used for the compiled
 131      pattern.  */
 132   __expr_ptr->__REPB_PREFIX (buffer) = expbuf + sizeof (regex_t);
 133   __expr_ptr->__REPB_PREFIX (allocated)
 134     = endbuf - (char *) __expr_ptr->__REPB_PREFIX (buffer);
 135
 136   while ((__ch = (GETC ())) != eof)
 137     {
 138       if (__ch == '\0' || __ch == '\n')
 139         {
 140           UNGETC (__ch);
 141           break;
 142         }
 143
 144       if (__current_size + 1 >= __input_size)
 145         {
 146           size_t __new_size = __input_size ? 2 * __input_size : 128;
 147           char *__new_room = (char *) alloca (__new_size);
 148           /* See whether we can use the old buffer.  */
 149           if (__new_room + __new_size == __input_buffer)
 150             {
 151               __input_size += __new_size;
 152               __input_buffer = (char *) memcpy (__new_room, __input_buffer,
 153                                                __current_size);
 154             }
 155           else if (__input_buffer + __input_size == __new_room)
 156             __input_size += __new_size;
 157           else
 158             {
 159               __input_size = __new_size;
 160               __input_buffer = (char *) memcpy (__new_room, __input_buffer,
 161                                                 __current_size);
 162             }
 163         }
 164       __input_buffer[__current_size++] = __ch;
 165     }
 166   if (__current_size)
 167     __input_buffer[__current_size++] = '\0';
 168   else
 169     __input_buffer = "";
 170
 171   /* Now compile the pattern.  */
 172   __error = regcomp (__expr_ptr, __input_buffer, REG_NEWLINE);
 173   if (__error != 0)
 174     /* Oh well, we have to translate POSIX error codes.  */
 175     switch (__error)
 176       {
 177       case REG_BADPAT:
 178       case REG_ECOLLATE:
 179       case REG_ECTYPE:
 180       case REG_EESCAPE:
 181       case REG_BADRPT:
 182       case REG_EEND:
 183       case REG_ERPAREN:
 184       default:
 185         /* There is no matching error code.  */
 186         RETURN (36);
 187       case REG_ESUBREG:
 188         RETURN (25);
 189       case REG_EBRACK:
 190         RETURN (49);
 191       case REG_EPAREN:
 192         RETURN (42);
 193       case REG_EBRACE:
 194         RETURN (44);
 195       case REG_BADBR:
 196         RETURN (46);
 197       case REG_ERANGE:
 198         RETURN (11);
 199       case REG_ESPACE:
 200       case REG_ESIZE:
 201         ERROR (50);
 202       }
 203
 204   /* Everything is ok.  */
 205   RETURN ((char *) (__expr_ptr->__REPB_PREFIX (buffer)
 206                     + __expr_ptr->__REPB_PREFIX (used)));
 207 }
 208 #endif
 209
 210
 211 /* Find the next match in STRING.  The compiled regular expression is
 212    found in the buffer starting at EXPBUF.  `loc1' will return the
 213    first character matched and `loc2' points to the next unmatched
 214    character.  */
 215 extern int step (const char *__restrict __string,
 216                  const char *__restrict __expbuf) __THROW;
 217
 218 /* Match the beginning of STRING with the compiled regular expression
 219    in EXPBUF.  If the match is successful `loc2' will contain the
 220    position of the first unmatched character.  */
 221 extern int advance (const char *__restrict __string,
 222                     const char *__restrict __expbuf) __THROW;
 223
 224
 225 __END_DECLS
 226
 227 #endif /* regexp.h */