| 34 | } |
| 35 | |
| 36 | uint32_t unicode_cpt_from_utf8(const std::string & utf8, size_t & offset) { |
| 37 | assert(offset < utf8.size()); |
| 38 | if (!(utf8[offset + 0] & 0x80)) { |
| 39 | auto result = utf8[offset + 0]; |
| 40 | offset += 1; |
| 41 | return result; |
| 42 | } |
| 43 | if (!(utf8[offset + 0] & 0x40)) { |
| 44 | throw std::invalid_argument("invalid character"); |
| 45 | } |
| 46 | if (!(utf8[offset + 0] & 0x20)) { |
| 47 | if (offset + 1 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80)) { |
| 48 | throw std::invalid_argument("invalid character"); |
| 49 | } |
| 50 | auto result = ((utf8[offset + 0] & 0x1f) << 6) | (utf8[offset + 1] & 0x3f); |
| 51 | offset += 2; |
| 52 | return result; |
| 53 | } |
| 54 | if (!(utf8[offset + 0] & 0x10)) { |
| 55 | if (offset + 2 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80)) { |
| 56 | throw std::invalid_argument("invalid character"); |
| 57 | } |
| 58 | auto result = ((utf8[offset + 0] & 0x0f) << 12) | ((utf8[offset + 1] & 0x3f) << 6) | (utf8[offset + 2] & 0x3f); |
| 59 | offset += 3; |
| 60 | return result; |
| 61 | } |
| 62 | if (!(utf8[offset + 0] & 0x08)) { |
| 63 | if (offset + 3 >= utf8.size() || ! ((utf8[offset + 1] & 0xc0) == 0x80) || ! ((utf8[offset + 2] & 0xc0) == 0x80) || !((utf8[offset + 3] & 0xc0) == 0x80)) { |
| 64 | throw std::invalid_argument("invalid character"); |
| 65 | } |
| 66 | auto result = ((utf8[offset + 0] & 0x07) << 18) | ((utf8[offset + 1] & 0x3f) << 12) | ((utf8[offset + 2] & 0x3f) << 6) | (utf8[offset + 3] & 0x3f); |
| 67 | offset += 4; |
| 68 | return result; |
| 69 | } |
| 70 | throw std::invalid_argument("failed to convert utf8 to codepoint"); |
| 71 | } |
| 72 | |
| 73 | //static std::vector<uint16_t> unicode_cpt_to_utf16(uint32_t cpt) { |
| 74 | // std::vector<uint16_t> result; |
no test coverage detected