misc/regexp.h

   1 /* Copyright (C) 1996-2013 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 Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the 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    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <http://www.gnu.org/licenses/>.  */
  18
  19 #ifndef _REGEXP_H
  20 #define _REGEXP_H       1
  21
  22 /* The contents of this header file was first standardized in X/Open
  23    System Interface and Headers Issue 2, originally coming from SysV.
  24    In issue 4, version 2, it is marked as TO BE WITDRAWN, and it has
  25    been withdrawn in SUSv3.
  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 <features.h>
  32 #include <alloca.h>
  33 #include <regex.h>
  34 #include <stdlib.h>
  35 #include <string.h>
  36
  37 /* The implementation provided here emulates the needed functionality
  38    by mapping to the POSIX regular expression matcher.  The interface
  39    for the here included function is weird (this really is a harmless
  40    word).
  41
  42    The user has to provide six macros before this header file can be
  43    included:
  44
  45    INIT         Declarations vor variables which can be used by the
  46                 other macros.
  47
  48    GETC()       Return the value of the next character in the regular
  49                 expression pattern.  Successive calls should return
  50                 successive characters.
  51
  52    PEEKC()      Return the value of the next character in the regular
  53                 expression pattern.  Immediately successive calls to
  54                 PEEKC() should return the same character which should
  55                 also be the next character returned by GETC().
  56
  57    UNGETC(c)    Cause `c' to be returned by the next call to GETC() and
  58                 PEEKC().
  59
  60    RETURN(ptr)  Used for normal exit of the `compile' function.  `ptr'
  61                 is a pointer to the character after the last character of
  62                 the compiled regular expression.
  63
  64    ERROR(val)   Used for abnormal return from `compile'.  `val' is the
  65                 error number.  The error codes are:
  66                 11      Range endpoint too large.
  67                 16      Bad number.
  68                 25      \digit out of range.
  69                 36      Illegal or missing delimiter.
  70                 41      No remembered search string.
  71                 42      \( \) imbalance.
  72                 43      Too many \(.
  73                 44      More tan two numbers given in \{ \}.
  74                 45      } expected after \.
  75                 46      First number exceeds second in \{ \}.
  76                 49      [ ] imbalance.
  77                 50      Regular expression overflow.
  78
  79   */
  80
  81 __BEGIN_DECLS
  82
  83 /* Interface variables.  They contain the results of the successful
  84    calls to `setp' and `advance'.  */
  85 extern char *loc1;
  86 extern char *loc2;
  87
  88 /* The use of this variable in the `advance' function is not
  89    supported.  */
  90 extern char *locs;
  91
  92
  93 #ifndef __DO_NOT_DEFINE_COMPILE
  94 /* Get and compile the user supplied pattern up to end of line or
  95    string or until EOF is seen, whatever happens first.  The result is
  96    placed in the buffer starting at EXPBUF and delimited by ENDBUF.
  97
  98    This function cannot be defined in the libc itself since it depends
  99    on the macros.  */
 100 char *
 101 compile (char *__restrict instring, char *__restrict expbuf,
 102          const char *__restrict endbuf, int eof)
 103 {
 104   char *__input_buffer = NULL;
 105   size_t __input_size = 0;
 106   size_t __current_size = 0;
 107   int __ch;
 108   int __error;
 109   INIT
 110
 111   /* Align the expression buffer according to the needs for an object
 112      of type `regex_t'.  Then check for minimum size of the buffer for
 113      the compiled regular expression.  */
 114   regex_t *__expr_ptr;
 115 # if defined __GNUC__ && __GNUC__ >= 2
 116   const size_t __req = __alignof__ (regex_t *);
 117 # else
 118   /* How shall we find out?  We simply guess it and can change it is
 119      this really proofs to be wrong.  */
 120   const size_t __req = 8;
 121 # endif
 122   expbuf += __req;
 123   expbuf -= (expbuf - ((char *) 0)) % __req;
 124   if (endbuf < expbuf + sizeof (regex_t))
 125     {
 126       ERROR (50);
 127     }
 128   __expr_ptr = (regex_t *) expbuf;
 129   /* The remaining space in the buffer can be used for the compiled
 130      pattern.  */
 131   __expr_ptr->__REPB_PREFIX (buffer) = expbuf + sizeof (regex_t);
 132   __expr_ptr->__REPB_PREFIX (allocated)
 133     = endbuf - (char *) __expr_ptr->__REPB_PREFIX (buffer);
 134
 135   while ((__ch = (GETC ())) != eof)
 136     {
 137       if (__ch == '\0' || __ch == '\n')
 138         {
 139           UNGETC (__ch);
 140           break;
 141         }
 142
 143       if (__current_size + 1 >= __input_size)
 144         {
 145           size_t __new_size = __input_size ? 2 * __input_size : 128;
 146           char *__new_room = (char *) alloca (__new_size);
 147           /* See whether we can use the old buffer.  */
 148           if (__new_room + __new_size == __input_buffer)
 149             {
 150               __input_size += __new_size;
 151               __input_buffer = (char *) memcpy (__new_room, __input_buffer,
 152                                                __current_size);
 153             }
 154           else if (__input_buffer + __input_size == __new_room)
 155             __input_size += __new_size;
 156           else
 157             {
 158               __input_size = __new_size;
 159               __input_buffer = (char *) memcpy (__new_room, __input_buffer,
 160                                                 __current_size);
 161             }
 162         }
 163       __input_buffer[__current_size++] = __ch;
 164     }
 165   if (__current_size)
 166     __input_buffer[__current_size++] = '\0';
 167   else
 168     __input_buffer = "";
 169
 170   /* Now compile the pattern.  */
 171   __error = regcomp (__expr_ptr, __input_buffer, REG_NEWLINE);
 172   if (__error != 0)
 173     /* Oh well, we have to translate POSIX error codes.  */
 174     switch (__error)
 175       {
 176       case REG_BADPAT:
 177       case REG_ECOLLATE:
 178       case REG_ECTYPE:
 179       case REG_EESCAPE:
 180       case REG_BADRPT:
 181       case REG_EEND:
 182       case REG_ERPAREN:
 183       default:
 184         /* There is no matching error code.  */
 185         RETURN (36);
 186       case REG_ESUBREG:
 187         RETURN (25);
 188       case REG_EBRACK:
 189         RETURN (49);
 190       case REG_EPAREN:
 191         RETURN (42);
 192       case REG_EBRACE:
 193         RETURN (44);
 194       case REG_BADBR:
 195         RETURN (46);
 196       case REG_ERANGE:
 197         RETURN (11);
 198       case REG_ESPACE:
 199       case REG_ESIZE:
 200         ERROR (50);
 201       }
 202
 203   /* Everything is ok.  */
 204   RETURN ((char *) (__expr_ptr->__REPB_PREFIX (buffer)
 205                     + __expr_ptr->__REPB_PREFIX (used)));
 206 }
 207 #endif
 208
 209
 210 /* Find the next match in STRING.  The compiled regular expression is
 211    found in the buffer starting at EXPBUF.  `loc1' will return the
 212    first character matched and `loc2' points to the next unmatched
 213    character.  */
 214 extern int step (const char *__restrict __string,
 215                  const char *__restrict __expbuf) __THROW;
 216
 217 /* Match the beginning of STRING with the compiled regular expression
 218    in EXPBUF.  If the match is successful `loc2' will contain the
 219    position of the first unmatched character.  */
 220 extern int advance (const char *__restrict __string,
 221                     const char *__restrict __expbuf) __THROW;
 222
 223
 224 __END_DECLS
 225
 226 #endif /* regexp.h */