misc/regexp.h

   1 /* Copyright (C) 1996, 1997 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Contributed by Ulrich Drepper <drepper@cygnus.com>, 1996.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Library General Public License as
   7    published by the Free Software Foundation; either version 2 of the
   8    License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Library General Public License for more details.
  14
  15    You should have received a copy of the GNU Library General Public
  16    License along with the GNU C Library; see the file COPYING.LIB.  If not,
  17    write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  18    Boston, MA 02111-1307, USA.  */
  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.
  26
  27    This code shouldn't be used in any newly written code.  It is
  28    included only for compatibility reasons.  Use the POSIX definition
  29    in <regex.h> for portable applications and a reasonable interface.  */
  30
  31 #include <alloca.h>
  32 #include <regex.h>
  33 #include <stdlib.h>
  34 #include <string.h>
  35
  36 /* The implementation provided here emulates the needed functionality
  37    by mapping to the POSIX regular expression matcher.  The interface
  38    for the here included function is weird (this really is a harmless
  39    word).
  40
  41    The user has to provide six macros before this header file can be
  42    included:
  43
  44    INIT         Declarations vor variables which can be used by the
  45                 other macros.
  46
  47    GETC()       Return the value of the next character in the regular
  48                 expression pattern.  Successive calls should return
  49                 successive characters.
  50
  51    PEEKC()      Return the value of the next character in the regular
  52                 expression pattern.  Immediately successive calls to
  53                 PEEKC() should return the same character which should
  54                 also be the next character returned by GETC().
  55
  56    UNGETC(c)    Cause `c' to be returned by the next call to GETC() and
  57                 PEEKC().
  58
  59    RETURN(ptr)  Used for normal exit of the `compile' function.  `ptr'
  60                 is a pointer to the character after the last character of
  61                 the compiled regular expression.
  62
  63    ERROR(val)   Used for abnormal return from `compile'.  `val' is the
  64                 error number.  The error codes are:
  65                 11      Range endpoint too large.
  66                 16      Bad number.
  67                 25      \digit out of range.
  68                 36      Illegal or missing delimiter.
  69                 41      No remembered search string.
  70                 42      \( \) imbalance.
  71                 43      Too many \(.
  72                 44      More tan two numbers given in \{ \}.
  73                 45      } expected after \.
  74                 46      First number exceeds second in \{ \}.
  75                 49      [ ] imbalance.
  76                 50      Regular expression overflow.
  77
  78   */
  79
  80 __BEGIN_DECLS
  81
  82 /* Interface variables.  They contain the results of the successful
  83    calls to `setp' and `advance'.  */
  84 extern char *loc1;
  85 extern char *loc2;
  86
  87 /* The use of this variable in the `advance' function is not
  88    supported.  */
  89 extern char *locs;
  90
  91
  92 #ifndef __DO_NOT_DEFINE_COMPILE
  93 /* Get and compile the user supplied pattern up to end of line or
  94    string or until EOF is seen, whatever happens first.  The result is
  95    placed in the buffer starting at EXPBUG and delimited by ENDBUF.
  96
  97    This function cannot be defined in the libc itself since it depends
  98    on the macros.  */
  99 char *
 100 compile (char *instring, char *expbuf, __const char *endbuf, int eof)
 101 {
 102   char *__input_buffer = NULL;
 103   size_t __input_size = 0;
 104   size_t __current_size = 0;
 105   int __ch;
 106   int __error;
 107   INIT
 108
 109   /* Align the expression buffer according to the needs for an object
 110      of type `regex_t'.  Then check for minimum size of the buffer for
 111      the compiled regular expression.  */
 112   regex_t *__expr_ptr;
 113 #if defined __GNUC__ && __GNUC__ >= 2
 114   const size_t __req = __alignof__ (regex_t *);
 115 #else
 116   /* How shall we find out?  We simply guess it and can change it is
 117      this really proofs to be wrong.  */
 118   const size_t __req = 8;
 119 #endif
 120   expbuf += __req;
 121   expbuf -= (expbuf - ((char *) 0)) % __req;
 122   if (endbuf < expbuf + sizeof (regex_t))
 123     {
 124       ERROR (50);
 125     }
 126   __expr_ptr = (regex_t *) expbuf;
 127   /* The remaining space in the buffer can be used for the compiled
 128      pattern.  */
 129   __expr_ptr->buffer = expbuf + sizeof (regex_t);
 130   __expr_ptr->allocated = endbuf -  (char *) __expr_ptr->buffer;
 131
 132   while ((__ch = (GETC ())) != eof)
 133     {
 134       if (__ch == '\0' || __ch == 'n')
 135         {
 136           UNGETC (__ch);
 137           break;
 138         }
 139
 140       if (__current_size + 1 >= __input_size)
 141         {
 142           size_t __new_size = __input_size ? 2 * __input_size : 128;
 143           char *__new_room = __alloca (__new_size);
 144           /* See whether we can use the old buffer.  */
 145           if (__new_room + __new_size == __input_buffer)
 146             {
 147               __input_size += __new_size;
 148               __input_buffer = memcpy (__new_room, __input_buffer,
 149                                        __current_size);
 150             }
 151           else if (__input_buffer + __input_size == __new_room)
 152             __input_size += __new_size;
 153           else
 154             {
 155               __input_size = __new_size;
 156               __input_buffer = memcpy (__new_room, __input_buffer,
 157                                        __current_size);
 158             }
 159         }
 160       __input_buffer[__current_size++] = __ch;
 161     }
 162   __input_buffer[__current_size++] = '\0';
 163
 164   /* Now compile the pattern.  */
 165   __error = regcomp (__expr_ptr, __input_buffer, REG_NEWLINE);
 166   if (__error != 0)
 167     /* Oh well, we have to translate POSIX error codes.  */
 168     switch (__error)
 169       {
 170       case REG_BADPAT:
 171       case REG_ECOLLATE:
 172       case REG_ECTYPE:
 173       case REG_EESCAPE:
 174       case REG_BADRPT:
 175       case REG_EEND:
 176       case REG_ERPAREN:
 177       default:
 178         /* There is no matching error code.  */
 179         RETURN (36);
 180       case REG_ESUBREG:
 181         RETURN (25);
 182       case REG_EBRACK:
 183         RETURN (49);
 184       case REG_EPAREN:
 185         RETURN (42);
 186       case REG_EBRACE:
 187         RETURN (44);
 188       case REG_BADBR:
 189         RETURN (46);
 190       case REG_ERANGE:
 191         RETURN (11);
 192       case REG_ESPACE:
 193       case REG_ESIZE:
 194         ERROR (50);
 195       }
 196
 197   /* Everything is ok.  */
 198   RETURN ((char *) (__expr_ptr->buffer + __expr_ptr->used));
 199 }
 200 #endif
 201
 202
 203 /* Find the next match in STRING.  The compiled regular expression is
 204    found in the buffer starting at EXPBUF.  `loc1' will return the
 205    first character matched and `loc2' points to the next unmatched
 206    character.  */
 207 extern int step __P ((__const char *__string, __const char *__expbuf));
 208
 209 /* Match the beginning of STRING with the compiled regular expression
 210    in EXPBUF.  If the match is successful `loc2' will contain the
 211    position of the first unmatched character.  */
 212 extern int advance __P ((__const char *__string, __const char *__expbuf));
 213
 214
 215 __END_DECLS
 216
 217 #endif /* regexp.h */