inet/idna_name_classify.c

   1 /* Classify a domain name for IDNA purposes.
   2    Copyright (C) 2018-2021 Free Software Foundation, Inc.
   3    This file is part of the GNU C Library.
   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    <https://www.gnu.org/licenses/>.  */
  18
  19 #include <errno.h>
  20 #include <inet/net-internal.h>
  21 #include <stdbool.h>
  22 #include <string.h>
  23 #include <wchar.h>
  24
  25 enum idna_name_classification
  26 __idna_name_classify (const char *name)
  27 {
  28   mbstate_t mbs;
  29   memset (&mbs, 0, sizeof (mbs));
  30   const char *p = name;
  31   const char *end = p + strlen (p) + 1;
  32   bool nonascii = false;
  33   bool backslash = false;
  34   while (true)
  35     {
  36       wchar_t wc;
  37       size_t result = mbrtowc (&wc, p, end - p, &mbs);
  38       if (result == 0)
  39         /* NUL terminator was reached.  */
  40         break;
  41       else if (result == (size_t) -2)
  42         /* Incomplete trailing multi-byte character.  This is an
  43            encoding error becaue we received the full name.  */
  44         return idna_name_encoding_error;
  45       else if (result == (size_t) -1)
  46         {
  47           /* Other error, including EILSEQ.  */
  48           if (errno == EILSEQ)
  49             return idna_name_encoding_error;
  50           else if (errno == ENOMEM)
  51             return idna_name_memory_error;
  52           else
  53             return idna_name_error;
  54         }
  55       else
  56         {
  57           /* A wide character was decoded.  */
  58           p += result;
  59           if (wc == L'\\')
  60             backslash = true;
  61           else if (wc > 127)
  62             nonascii = true;
  63         }
  64     }
  65
  66   if (nonascii)
  67     {
  68       if (backslash)
  69         return idna_name_nonascii_backslash;
  70       else
  71         return idna_name_nonascii;
  72     }
  73   else
  74     return idna_name_ascii;
  75 }