path: root/static/openbsd/man3/c16rtomb.3

.\" $OpenBSD: c16rtomb.3,v 1.1 2023/08/20 15:02:51 schwarze Exp $
.\"
.\" Copyright (c) 2023 Ingo Schwarze <schwarze@openbsd.org>
.\"
.\" Permission to use, copy, modify, and distribute this software for any
.\" purpose with or without fee is hereby granted, provided that the above
.\" copyright notice and this permission notice appear in all copies.
.\"
.\" THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
.\" WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
.\" MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
.\" ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
.\" WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
.\" ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
.\" OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
.\"
.Dd $Mdocdate: August 20 2023 $
.Dt C16RTOMB 3
.Os
.Sh NAME
.Nm c16rtomb
.Nd convert one UTF-16 encoded character to UTF-8
.Sh SYNOPSIS
.In uchar.h
.Ft size_t
.Fo c16rtomb
.Fa "char * restrict s"
.Fa "char16_t c16"
.Fa "mbstate_t * restrict mbs"
.Fc
.Sh DESCRIPTION
This function converts one UTF-16 encoded character to UTF-8.
In some cases, it is necessary to call the function twice
to convert a single character.
.Pp
First, call
.Fn c16rtomb
passing the first 16-bit code unit of the UTF-16 encoded character in
.Fa c16 .
If the return value is greater than 0, the character is part of the UCS-2
range, the complete UTF-8 encoding consisting of at most
.Dv MB_CUR_MAX
bytes has been written to the storage starting at
.Fa s ,
and the function does not need to be called again.
.Pp
If the return value is 0, the first 16-bit code unit is a UTF-16
high surrogate and the function needs to be called a second time,
this time passing the second 16-bit code unit of the UTF-16 encoded
character in
.Fa c16
and passing the same
.Fa mbs
again that was also passed to the first call.
If the second 16-bit code unit is a UTF-16 low surrogate,
the second call returns a value greater than 0,
the surrogate pair represents a Unicode code point
beyond the basic multilingual plane,
and the complete UTF-8 encoding consisting of at most
.Dv MB_CUR_MAX
bytes is written to the storage starting at
.Fa s .
.Pp
The output encoding that
.Fn c16rtomb
uses in
.Fa s
is determined by the
.Dv LC_CTYPE
category of the current locale.
.Ox
only supports UTF-8 and ASCII output,
and this function is only useful for UTF-8.
.Pp
The following arguments cause special processing:
.Bl -tag -width 012345678901
.It Fa c16 No == 0
A NUL byte is stored to
.Pf * Fa s
and the state object pointed to by
.Fa mbs
is reset to the initial state.
On operating systems other than
.Ox
that support state-dependent multibyte encodings,
a special byte sequence
.Pq Dq shift sequence
is written before the NUL byte to return to the initial state
if that is required by the output encoding
and by the current output encoding state.
.It Fa mbs No == Dv NULL
An internal
.Vt mbstate_t
object specific to the
.Fn c16rtomb
function is used instead of the
.Fa mbs
argument.
This internal object is automatically initialized at program startup
and never changed by any
.Em libc
function except
.Fn c16rtomb .
.It Fa s No == Dv NULL
The object pointed to by
.Fa mbs ,
or the internal object if
.Fa mbs
is a
.Dv NULL
pointer, is reset to its initial state,
.Fa c16
is ignored, and 1 is returned.
.El
.Sh RETURN VALUES
.Fn c16rtomb
returns the number of bytes written to
.Fa s
on success or
.Po Vt size_t Pc Ns \-1
on failure, specifically:
.Bl -tag -width 10n
.It 0
The first 16-bit code unit was successfully decoded
as a UTF-16 high surrogate.
Nothing was written to
.Fa s
yet.
.It 1
The first 16-bit code unit was successfully decoded
as a character in the range U+0000 to U+007F, or
.Fa s
is
.Dv NULL .
.It 2
The first 16-bit code unit was successfully decoded
as a character in the range U+0080 to U+07FF.
.It 3
The first 16-bit code unit was successfully decoded
as a character in the range U+0800 to U+D7FF or U+E000 to U+FFFF.
.It 4
The second 16-bit code unit was successfully decoded as a UTF-16 low
surrogate, resulting in a character in the range U+10000 to U+10FFFF.
.It greater
Return values greater than 4 may occur on operating systems other than
.Ox
for output encodings other than UTF-8, in particular when a shift
sequence was written.
.It Po Vt size_t Pc Ns \-1
UTF-16 input decoding or
.Dv LC_CTYPE
output encoding failed, or
.Fa mbs
is invalid.
Nothing was written to
.Fa s ,
and
.Va errno
has been set.
.El
.Sh ERRORS
.Fn c16rtomb
causes an error in the following cases:
.Bl -tag -width Er
.It Bq Er EILSEQ
UTF-16 input decoding failed because the first 16-bit code unit
is neither a UCS-2 character nor a UTF-16 high surrogate,
or because the second 16-bit code unit is not a UTF-16 low surrogate;
or output encoding failed because the resulting character
cannot be represented in the output encoding selected with
.Dv LC_CTYPE .
.It Bq Er EINVAL
.Fa mbs
points to an invalid or uninitialized
.Vt mbstate_t
object.
.El
.Sh SEE ALSO
.Xr mbrtoc16 3 ,
.Xr setlocale 3 ,
.Xr wcrtomb 3
.Sh STANDARDS
.Fn c16rtomb
conforms to
.St -isoC-2011 .
.Sh HISTORY
.Fn c16rtomb
has been available since
.Ox 7.4 .
.Sh CAVEATS
The C11 standard only requires the
.Fa c16
argument to be interpreted according to UTF-16
if the predefined environment macro
.Dv __STDC_UTF_16__
is defined with a value of 1.
On
.Ox ,
.In uchar.h
provides this definition.
Other operating systems which do not define
.Dv __STDC_UTF_16__
could theoretically use a different,
implementation-defined input encoding for
.Fa c16
instead of UTF-16.
Using UTF-16 becomes mandatory in C23.