diff options
Diffstat (limited to 'src/basic/utf8.h')
-rw-r--r-- | src/basic/utf8.h | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/src/basic/utf8.h b/src/basic/utf8.h index e8af7a576b..628456936e 100644 --- a/src/basic/utf8.h +++ b/src/basic/utf8.h @@ -7,14 +7,14 @@ #include <uchar.h> #include "macro.h" -#include "missing.h" +#include "missing_type.h" #define UTF8_REPLACEMENT_CHARACTER "\xef\xbf\xbd" #define UTF8_BYTE_ORDER_MARK "\xef\xbb\xbf" bool unichar_is_valid(char32_t c); -const char *utf8_is_valid(const char *s) _pure_; +char *utf8_is_valid(const char *s) _pure_; char *ascii_is_valid(const char *s) _pure_; char *ascii_is_valid_n(const char *str, size_t len); @@ -25,21 +25,26 @@ char *utf8_escape_invalid(const char *s); char *utf8_escape_non_printable(const char *str); size_t utf8_encode_unichar(char *out_utf8, char32_t g); -char *utf16_to_utf8(const void *s, size_t length); +size_t utf16_encode_unichar(char16_t *out, char32_t c); + +char *utf16_to_utf8(const char16_t *s, size_t length /* bytes! */); +char16_t *utf8_to_utf16(const char *s, size_t length); + +size_t char16_strlen(const char16_t *s); /* returns the number of 16bit words in the string (not bytes!) */ int utf8_encoded_valid_unichar(const char *str); int utf8_encoded_to_unichar(const char *str, char32_t *ret_unichar); static inline bool utf16_is_surrogate(char16_t c) { - return (0xd800 <= c && c <= 0xdfff); + return c >= 0xd800U && c <= 0xdfffU; } static inline bool utf16_is_trailing_surrogate(char16_t c) { - return (0xdc00 <= c && c <= 0xdfff); + return c >= 0xdc00U && c <= 0xdfffU; } static inline char32_t utf16_surrogate_pair_to_unichar(char16_t lead, char16_t trail) { - return ((lead - 0xd800) << 10) + (trail - 0xdc00) + 0x10000; + return ((((char32_t) lead - 0xd800U) << 10) + ((char32_t) trail - 0xdc00U) + 0x10000U); } size_t utf8_n_codepoints(const char *str); |