wcsmbs/mbrtowc.c

   1 /* Copyright (C) 1996 Free Software Foundation, Inc.
   2 This file is part of the GNU C Library.
   3 Contributed by Ulrich Drepper <drepper@gnu.ai.mit.edu>, 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
  17 not, write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  18 Boston, MA 02111-1307, USA.  */
  19
  20 #include <errno.h>
  21 #include <wchar.h>
  22
  23 #ifndef EILSEQ
  24 #define EILSEQ EINVAL
  25 #endif
  26
  27
  28 static mbstate_t internal;
  29
  30 size_t
  31 mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
  32 {
  33   size_t used = 0;
  34
  35   if (ps == NULL)
  36     ps = &internal;
  37
  38   if (s == NULL)
  39     {
  40       /* See first paragraph of description in 7.16.6.3.2.  */
  41       pwc = NULL;
  42       s = "";
  43       n = 1;
  44     }
  45
  46   if (n > 0)
  47     {
  48       if (ps->count == 0)
  49         {
  50           unsigned char byte = (unsigned char) *s++;
  51           ++used;
  52
  53           /* We must look for a possible first byte of a UTF8 sequence.  */
  54           if (byte < 0x80)
  55             {
  56               /* One byte sequence.  */
  57               if (pwc != NULL)
  58                 *pwc = (wchar_t) byte;
  59               return byte ? used : 0;
  60             }
  61
  62           if ((byte & 0xc0) == 0x80 || (byte & 0xfe) == 0xfe)
  63             {
  64               /* Oh, oh.  An encoding error.  */
  65               errno = EILSEQ;
  66               return (size_t) -1;
  67             }
  68
  69           if ((byte & 0xe0) == 0xc0)
  70             {
  71               /* We expect two bytes.  */
  72               ps->count = 1;
  73               ps->value = byte & 0x1f;
  74             }
  75           else if ((byte & 0xf0) == 0xe0)
  76             {
  77               /* We expect three bytes.  */
  78               ps->count = 2;
  79               ps->value = byte & 0x0f;
  80             }
  81           else if ((byte & 0xf8) == 0xf0)
  82             {
  83               /* We expect four bytes.  */
  84               ps->count = 3;
  85               ps->value = byte & 0x07;
  86             }
  87           else if ((byte & 0xfc) == 0xf8)
  88             {
  89               /* We expect five bytes.  */
  90               ps->count = 4;
  91               ps->value = byte & 0x03;
  92             }
  93           else
  94             {
  95               /* We expect six bytes.  */
  96               ps->count = 5;
  97               ps->value = byte & 0x01;
  98             }
  99         }
 100
 101       /* We know we have to handle a multibyte character and there are
 102          some more bytes to read.  */
 103       while (used < n)
 104         {
 105           /* The second to sixths byte must be of the form 10xxxxxx.  */
 106           unsigned char byte = (unsigned char) *s++;
 107           ++used;
 108
 109           if ((byte & 0xc0) != 0x80)
 110             {
 111               /* Oh, oh.  An encoding error.  */
 112               errno = EILSEQ;
 113               return (size_t) -1;
 114             }
 115
 116           ps->value <<= 6;
 117           ps->value |= byte & 0x3f;
 118
 119           if (--ps->count == 0)
 120             {
 121               /* The character is finished.  */
 122               if (pwc != NULL)
 123                 *pwc = (wchar_t) ps->value;
 124               return ps->value ? used : 0;
 125             }
 126         }
 127     }
 128
 129   return (size_t) -2;
 130 }