utf8.cc (1768B)
1 // Copyright 2017 The Abseil Authors. 2 // 3 // Licensed under the Apache License, Version 2.0 (the "License"); 4 // you may not use this file except in compliance with the License. 5 // You may obtain a copy of the License at 6 // 7 // https://www.apache.org/licenses/LICENSE-2.0 8 // 9 // Unless required by applicable law or agreed to in writing, software 10 // distributed under the License is distributed on an "AS IS" BASIS, 11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 // See the License for the specific language governing permissions and 13 // limitations under the License. 14 15 // UTF8 utilities, implemented to reduce dependencies. 16 17 #include "absl/strings/internal/utf8.h" 18 19 namespace absl { 20 ABSL_NAMESPACE_BEGIN 21 namespace strings_internal { 22 23 size_t EncodeUTF8Char(char *buffer, char32_t utf8_char) { 24 if (utf8_char <= 0x7F) { 25 *buffer = static_cast<char>(utf8_char); 26 return 1; 27 } else if (utf8_char <= 0x7FF) { 28 buffer[1] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 29 utf8_char >>= 6; 30 buffer[0] = static_cast<char>(0xC0 | utf8_char); 31 return 2; 32 } else if (utf8_char <= 0xFFFF) { 33 buffer[2] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 34 utf8_char >>= 6; 35 buffer[1] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 36 utf8_char >>= 6; 37 buffer[0] = static_cast<char>(0xE0 | utf8_char); 38 return 3; 39 } else { 40 buffer[3] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 41 utf8_char >>= 6; 42 buffer[2] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 43 utf8_char >>= 6; 44 buffer[1] = static_cast<char>(0x80 | (utf8_char & 0x3F)); 45 utf8_char >>= 6; 46 buffer[0] = static_cast<char>(0xF0 | utf8_char); 47 return 4; 48 } 49 } 50 51 } // namespace strings_internal 52 ABSL_NAMESPACE_END 53 } // namespace absl