| 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 | { |
| 34 | int charsNeeded; |
| 35 | uint32_t uc, min_uc; |
| 36 | uint8_t b; |
| 37 | ptrdiff_t n = end - *buffer; |
| 38 | if (n == 0) |
| 39 | return ~0U; |
| 40 | |
| 41 | uc = *(*buffer)++; |
| 42 | if (uc < 0x80) { |
| 43 | /* single-byte UTF-8 */ |
| 44 | return uc; |
| 45 | } |
| 46 | |
| 47 | /* multi-byte UTF-8, decode it */ |
| 48 | if (unlikely(uc <= 0xC1)) |
| 49 | return ~0U; |
| 50 | if (uc < 0xE0) { |
| 51 | /* two-byte UTF-8 */ |
| 52 | charsNeeded = 2; |
| 53 | min_uc = 0x80; |
| 54 | uc &= 0x1f; |
| 55 | } else if (uc < 0xF0) { |
| 56 | /* three-byte UTF-8 */ |
| 57 | charsNeeded = 3; |
| 58 | min_uc = 0x800; |
| 59 | uc &= 0x0f; |
| 60 | } else if (uc < 0xF5) { |
| 61 | /* four-byte UTF-8 */ |
| 62 | charsNeeded = 4; |
| 63 | min_uc = 0x10000; |
| 64 | uc &= 0x07; |
| 65 | } else { |
| 66 | return ~0U; |
| 67 | } |
| 68 | |
| 69 | if (n < charsNeeded) |
| 70 | return ~0U; |
| 71 | |
| 72 | /* first continuation character */ |
| 73 | b = *(*buffer)++; |
| 74 | if ((b & 0xc0) != 0x80) |
| 75 | return ~0U; |
| 76 | uc <<= 6; |
| 77 | uc |= b & 0x3f; |
| 78 | |
| 79 | if (charsNeeded > 2) { |
| 80 | /* second continuation character */ |
| 81 | b = *(*buffer)++; |
| 82 | if ((b & 0xc0) != 0x80) |
| 83 | return ~0U; |
| 84 | uc <<= 6; |
| 85 | uc |= b & 0x3f; |
| 86 | |
| 87 | if (charsNeeded > 3) { |
| 88 | /* third continuation character */ |
| 89 | b = *(*buffer)++; |
| 90 | if ((b & 0xc0) != 0x80) |
| 91 | return ~0U; |
| 92 | uc <<= 6; |
| 93 | uc |= b & 0x3f; |
| 94 | } |
| 95 | } |
| 96 | |
| 97 | /* overlong sequence? surrogate pair? out or range? */ |
| 98 | if (uc < min_uc || uc - 0xd800U < 2048U || uc > 0x10ffff) |
| 99 | return ~0U; |
| 100 | |
| 101 | return uc; |
| 102 | } |
| 103 | |
| 104 | #endif /* CBOR_UTF8_H */ |