utf8.h (1707B)
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 #ifndef ABSL_STRINGS_INTERNAL_UTF8_H_ 18 #define ABSL_STRINGS_INTERNAL_UTF8_H_ 19 20 #include <cstddef> 21 #include <cstdint> 22 23 #include "absl/base/config.h" 24 25 namespace absl { 26 ABSL_NAMESPACE_BEGIN 27 namespace strings_internal { 28 29 // For Unicode code points 0 through 0x10FFFF, EncodeUTF8Char writes 30 // out the UTF-8 encoding into buffer, and returns the number of chars 31 // it wrote. 32 // 33 // As described in https://tools.ietf.org/html/rfc3629#section-3 , the encodings 34 // are: 35 // 00 - 7F : 0xxxxxxx 36 // 80 - 7FF : 110xxxxx 10xxxxxx 37 // 800 - FFFF : 1110xxxx 10xxxxxx 10xxxxxx 38 // 10000 - 10FFFF : 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 39 // 40 // Values greater than 0x10FFFF are not supported and may or may not write 41 // characters into buffer, however never will more than kMaxEncodedUTF8Size 42 // bytes be written, regardless of the value of utf8_char. 43 enum { kMaxEncodedUTF8Size = 4 }; 44 size_t EncodeUTF8Char(char *buffer, char32_t utf8_char); 45 46 } // namespace strings_internal 47 ABSL_NAMESPACE_END 48 } // namespace absl 49 50 #endif // ABSL_STRINGS_INTERNAL_UTF8_H_