utf8.h 1.7 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
  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. #ifndef ABSL_STRINGS_INTERNAL_UTF8_H_
  17. #define ABSL_STRINGS_INTERNAL_UTF8_H_
  18. #include <cstddef>
  19. #include <cstdint>
  20. #include "absl/base/config.h"
  21. namespace absl {
  22. ABSL_NAMESPACE_BEGIN
  23. namespace strings_internal {
  24. // For Unicode code points 0 through 0x10FFFF, EncodeUTF8Char writes
  25. // out the UTF-8 encoding into buffer, and returns the number of chars
  26. // it wrote.
  27. //
  28. // As described in https://tools.ietf.org/html/rfc3629#section-3 , the encodings
  29. // are:
  30. // 00 - 7F : 0xxxxxxx
  31. // 80 - 7FF : 110xxxxx 10xxxxxx
  32. // 800 - FFFF : 1110xxxx 10xxxxxx 10xxxxxx
  33. // 10000 - 10FFFF : 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
  34. //
  35. // Values greater than 0x10FFFF are not supported and may or may not write
  36. // characters into buffer, however never will more than kMaxEncodedUTF8Size
  37. // bytes be written, regardless of the value of utf8_char.
  38. enum { kMaxEncodedUTF8Size = 4 };
  39. size_t EncodeUTF8Char(char *buffer, char32_t utf8_char);
  40. } // namespace strings_internal
  41. ABSL_NAMESPACE_END
  42. } // namespace absl
  43. #endif // ABSL_STRINGS_INTERNAL_UTF8_H_