m4/resyntax.c

   1 /* GNU m4 -- A simple macro processor
   2    Copyright (C) 2006, 2007, 2008 Free Software Foundation, Inc.
   3
   4    This file is part of GNU M4.
   5
   6    GNU M4 is free software: you can redistribute it and/or modify
   7    it under the terms of the GNU General Public License as published by
   8    the Free Software Foundation, either version 3 of the License, or
   9    (at your option) any later version.
  10
  11    GNU M4 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
  14    GNU General Public License for more details.
  15
  16    You should have received a copy of the GNU General Public License
  17    along with this program.  If not, see <http://www.gnu.org/licenses/>.
  18 */
  19
  20 #include <config.h>
  21
  22 #include <regex.h>
  23 #include <string.h>
  24
  25 #include "m4private.h"
  26
  27 typedef struct {
  28   const char    *spec;
  29   const int     code;
  30 } m4_resyntax;
  31
  32 /* The syntaxes named in this table are saved into frozen files.  Changing
  33    the mappings will break programs that load a frozen file made before
  34    such a change...  */
  35
  36 static m4_resyntax const m4_resyntax_map[] =
  37 {
  38   /* First, the canonical definitions for reverse lookups:  */
  39
  40   { "AWK",                      RE_SYNTAX_AWK },
  41   { "ED",                       RE_SYNTAX_ED },
  42   { "EGREP",                    RE_SYNTAX_EGREP },
  43   { "EMACS",                    RE_SYNTAX_EMACS },
  44   { "GNU_AWK",                  RE_SYNTAX_GNU_AWK },
  45   { "GREP",                     RE_SYNTAX_GREP },
  46   { "POSIX_AWK",                RE_SYNTAX_POSIX_AWK },
  47   { "POSIX_BASIC",              RE_SYNTAX_POSIX_BASIC },
  48   { "POSIX_EGREP",              RE_SYNTAX_POSIX_EGREP },
  49   { "POSIX_EXTENDED",           RE_SYNTAX_POSIX_EXTENDED },
  50   { "POSIX_MINIMAL_BASIC",      RE_SYNTAX_POSIX_MINIMAL_BASIC },
  51   { "SED",                      RE_SYNTAX_SED },
  52
  53   /* The rest are aliases, for forward lookups only:  */
  54
  55   { "",                         RE_SYNTAX_EMACS },
  56   { "BASIC",                    RE_SYNTAX_POSIX_BASIC },
  57   { "BSD_M4",                   RE_SYNTAX_POSIX_EXTENDED },
  58   { "EXTENDED",                 RE_SYNTAX_POSIX_EXTENDED },
  59   { "GAWK",                     RE_SYNTAX_GNU_AWK },
  60   { "GNU_EGREP",                RE_SYNTAX_EGREP },
  61   { "GNU_EMACS",                RE_SYNTAX_EMACS },
  62   { "GNU_M4",                   RE_SYNTAX_EMACS },
  63   { "MINIMAL",                  RE_SYNTAX_POSIX_MINIMAL_BASIC },
  64   { "MINIMAL_BASIC",            RE_SYNTAX_POSIX_MINIMAL_BASIC },
  65   { "POSIX_MINIMAL",            RE_SYNTAX_POSIX_MINIMAL_BASIC },
  66
  67   /* End marker:  */
  68
  69   { NULL,                       -1 }
  70 };
  71
  72
  73 /* Return the internal code representing the syntax SPEC, or -1 if
  74    SPEC is invalid.  The `m4_syntax_map' table is searched case
  75    insensitively, after replacing any spaces or dashes in SPEC with
  76    underscore characters.  Possible matches for the "GNU_M4" element
  77    then, are "gnu m4", "GNU-m4" or "Gnu_M4".  */
  78 int
  79 m4_regexp_syntax_encode (const char *spec)
  80 {
  81   const m4_resyntax *resyntax;
  82   char *canonical;
  83   char *p;
  84
  85   /* Unless specified otherwise, return the historical GNU M4 default.  */
  86   if (!spec)
  87     return RE_SYNTAX_EMACS;
  88
  89   canonical = xstrdup (spec);
  90
  91   /* Canonicalise SPEC.  */
  92   for (p = canonical; *p != '\0'; ++p)
  93     {
  94       if ((*p == ' ') || (*p == '-'))
  95         *p = '_';
  96       else if (islower (to_uchar (*p)))
  97         *p = toupper (to_uchar (*p));
  98     }
  99
 100   for (resyntax = m4_resyntax_map; resyntax->spec != NULL; ++resyntax)
 101     {
 102       if (!strcmp (resyntax->spec, canonical))
 103         break;
 104     }
 105
 106   free (canonical);
 107
 108   return resyntax->code;
 109 }
 110
 111
 112 /* Return the syntax specifier that matches CODE, or NULL if there is
 113    no match.  */
 114 const char *
 115 m4_regexp_syntax_decode (int code)
 116 {
 117   const m4_resyntax *resyntax;
 118
 119   for (resyntax = m4_resyntax_map; resyntax->spec != NULL; ++resyntax)
 120     {
 121       if (resyntax->code == code)
 122         break;
 123     }
 124
 125   return resyntax->spec;
 126 }