diff options
Diffstat (limited to 'man/u8tor.3')
| -rw-r--r-- | man/u8tor.3 | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/man/u8tor.3 b/man/u8tor.3 new file mode 100644 index 0000000..ba08110 --- /dev/null +++ b/man/u8tor.3 @@ -0,0 +1,65 @@ +.Dd March 10 2024 +.Dt U8TOR 3 +.Os +.Sh NAME +.Nm u8tor +.Nd decode UTF-8 into a rune +.Sh LIBRARY +.Lb mlib +.Sh SYNOPSIS +.In mbstring.h +.Ft int +.Fn u8tor "rune *ch" "const char8_t *s" +.Sh DESCRIPTION +The +.Fn u8tor +function decodes the first rune in the UTF-8 buffer +.Fa s , +storing the result in the rune pointed to by +.Fa ch +and returns the number of bytes which compose the decoded +UTF-8. +.Pp +If attempting to decode an invalid byte, +.Va *ch +will be set to +.Dv RUNE_ERROR. +.Sh RETURN VALUES +The +.Fn u8tor +function returns the number of bytes from +.Fa s +decoded into +.Fa ch . +.Sh EXAMPLES +The following call to +.Fn u8tor +attempts to decode the first UTF-8 codepoint in +.Va buf . +.Bd -literal -offset indent +/* Implementation of read_codepoint() omitted */ + +rune ch; +char8_t *buf = read_codepoint(stdin); +int w = u8tor(&ch, buf); +if (ch == RUNE_ERROR) + errx("Got invalid UTF-8 codepoint"); +printf("Got rune ‘%.*s’\en", w, buf); +.Ed +.Sh SEE ALSO +.Xr errx 3mlib , +.Xr rtou8 3 , +.Xr u8chk 3 , +.Xr u8next 3 , +.Xr RUNE_ERROR 3const , +.Xr unicode 7 , +.Xr utf\-8 7 +.Sh STANDARDS +.Rs +.%A F. Yergeau +.%D November 2003 +.%R RFC 3629 +.%T UTF-8, a transformation format of ISO 10646 +.Re +.Sh AUTHORS +.An Thomas Voss Aq Mt mail@thomasvoss.com |