client/deps/tinycbor/utf8_p.h

   1 /****************************************************************************
   2 **
   3 ** Copyright (C) 2017 Intel Corporation
   4 **
   5 ** Permission is hereby granted, free of charge, to any person obtaining a copy
   6 ** of this software and associated documentation files (the "Software"), to deal
   7 ** in the Software without restriction, including without limitation the rights
   8 ** to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
   9 ** copies of the Software, and to permit persons to whom the Software is
  10 ** furnished to do so, subject to the following conditions:
  11 **
  12 ** The above copyright notice and this permission notice shall be included in
  13 ** all copies or substantial portions of the Software.
  14 **
  15 ** THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  16 ** IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  17 ** FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  18 ** AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  19 ** LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  20 ** OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  21 ** THE SOFTWARE.
  22 **
  23 ****************************************************************************/
  24
  25 #ifndef CBOR_UTF8_H
  26 #define CBOR_UTF8_H
  27
  28 #include "compilersupport_p.h"
  29
  30 #include <stdint.h>
  31
  32 static inline uint32_t get_utf8(const uint8_t **buffer, const uint8_t *end) {
  33     int charsNeeded;
  34     uint32_t uc, min_uc;
  35     uint8_t b;
  36     ptrdiff_t n = end - *buffer;
  37     if (n == 0)
  38         return ~0U;
  39
  40     uc = *(*buffer)++;
  41     if (uc < 0x80) {
  42         /* single-byte UTF-8 */
  43         return uc;
  44     }
  45
  46     /* multi-byte UTF-8, decode it */
  47     if (unlikely(uc <= 0xC1))
  48         return ~0U;
  49     if (uc < 0xE0) {
  50         /* two-byte UTF-8 */
  51         charsNeeded = 2;
  52         min_uc = 0x80;
  53         uc &= 0x1f;
  54     } else if (uc < 0xF0) {
  55         /* three-byte UTF-8 */
  56         charsNeeded = 3;
  57         min_uc = 0x800;
  58         uc &= 0x0f;
  59     } else if (uc < 0xF5) {
  60         /* four-byte UTF-8 */
  61         charsNeeded = 4;
  62         min_uc = 0x10000;
  63         uc &= 0x07;
  64     } else {
  65         return ~0U;
  66     }
  67
  68     if (n < charsNeeded)
  69         return ~0U;
  70
  71     /* first continuation character */
  72     b = *(*buffer)++;
  73     if ((b & 0xc0) != 0x80)
  74         return ~0U;
  75     uc <<= 6;
  76     uc |= b & 0x3f;
  77
  78     if (charsNeeded > 2) {
  79         /* second continuation character */
  80         b = *(*buffer)++;
  81         if ((b & 0xc0) != 0x80)
  82             return ~0U;
  83         uc <<= 6;
  84         uc |= b & 0x3f;
  85
  86         if (charsNeeded > 3) {
  87             /* third continuation character */
  88             b = *(*buffer)++;
  89             if ((b & 0xc0) != 0x80)
  90                 return ~0U;
  91             uc <<= 6;
  92             uc |= b & 0x3f;
  93         }
  94     }
  95
  96     /* overlong sequence? surrogate pair? out or range? */
  97     if (uc < min_uc || uc - 0xd800U < 2048U || uc > 0x10ffff)
  98         return ~0U;
  99
 100     return uc;
 101 }
 102
 103 #endif /* CBOR_UTF8_H */