1 // Protocol Buffers - Google's data interchange format 2 // Copyright 2023 Google LLC. All rights reserved. 3 // 4 // Use of this source code is governed by a BSD-style 5 // license that can be found in the LICENSE file or at 6 // https://developers.google.com/open-source/licenses/bsd 7 8 #ifndef UPB_LEX_UNICODE_H_ 9 #define UPB_LEX_UNICODE_H_ 10 11 #include <stdint.h> 12 13 // Must be last. 14 #include "upb/port/def.inc" 15 16 #ifdef __cplusplus 17 extern "C" { 18 #endif 19 20 // Returns true iff a codepoint is the value for a high surrogate. upb_Unicode_IsHigh(uint32_t cp)21UPB_INLINE bool upb_Unicode_IsHigh(uint32_t cp) { 22 return (cp >= 0xd800 && cp <= 0xdbff); 23 } 24 25 // Returns true iff a codepoint is the value for a low surrogate. upb_Unicode_IsLow(uint32_t cp)26UPB_INLINE bool upb_Unicode_IsLow(uint32_t cp) { 27 return (cp >= 0xdc00 && cp <= 0xdfff); 28 } 29 30 // Returns the high 16-bit surrogate value for a supplementary codepoint. 31 // Does not sanity-check the input. upb_Unicode_ToHigh(uint32_t cp)32UPB_INLINE uint16_t upb_Unicode_ToHigh(uint32_t cp) { 33 return (cp >> 10) + 0xd7c0; 34 } 35 36 // Returns the low 16-bit surrogate value for a supplementary codepoint. 37 // Does not sanity-check the input. upb_Unicode_ToLow(uint32_t cp)38UPB_INLINE uint16_t upb_Unicode_ToLow(uint32_t cp) { 39 return (cp & 0x3ff) | 0xdc00; 40 } 41 42 // Returns the 32-bit value corresponding to a pair of 16-bit surrogates. 43 // Does not sanity-check the input. upb_Unicode_FromPair(uint32_t high,uint32_t low)44UPB_INLINE uint32_t upb_Unicode_FromPair(uint32_t high, uint32_t low) { 45 return ((high & 0x3ff) << 10) + (low & 0x3ff) + 0x10000; 46 } 47 48 // Outputs a codepoint as UTF8. 49 // Returns the number of bytes written (1-4 on success, 0 on error). 50 // Does not sanity-check the input. Specifically does not check for surrogates. 51 int upb_Unicode_ToUTF8(uint32_t cp, char* out); 52 53 #ifdef __cplusplus 54 } /* extern "C" */ 55 #endif 56 57 #include "upb/port/undef.inc" 58 59 #endif /* UPB_LEX_UNICODE_H_ */ 60