mirror of https://github.com/mkerrisk/man-pages
127 lines
2.7 KiB
Groff
127 lines
2.7 KiB
Groff
.\" Copyright (c) Bruno Haible <haible@clisp.cons.org>
|
|
.\"
|
|
.\" %%%LICENSE_START(GPLv2+_DOC_ONEPARA)
|
|
.\" This is free documentation; you can redistribute it and/or
|
|
.\" modify it under the terms of the GNU General Public License as
|
|
.\" published by the Free Software Foundation; either version 2 of
|
|
.\" the License, or (at your option) any later version.
|
|
.\" %%%LICENSE_END
|
|
.\"
|
|
.\" References consulted:
|
|
.\" GNU glibc-2 source code and manual
|
|
.\" Dinkumware C library reference http://www.dinkumware.com/
|
|
.\" OpenGroup's Single UNIX specification http://www.UNIX-systems.org/online.html
|
|
.\" ISO/IEC 9899:1999
|
|
.\"
|
|
.TH MBRLEN 3 2015-08-08 "GNU" "Linux Programmer's Manual"
|
|
.SH NAME
|
|
mbrlen \- determine number of bytes in next multibyte character
|
|
.SH SYNOPSIS
|
|
.nf
|
|
.B #include <wchar.h>
|
|
.sp
|
|
.BI "size_t mbrlen(const char *" s ", size_t " n ", mbstate_t *" ps );
|
|
.fi
|
|
.SH DESCRIPTION
|
|
The
|
|
.BR mbrlen ()
|
|
function inspects at most
|
|
.I n
|
|
bytes of the multibyte
|
|
string starting at
|
|
.I s
|
|
and extracts the next complete multibyte character.
|
|
It updates the shift state
|
|
.IR *ps .
|
|
If the multibyte character is not the
|
|
null wide character, it returns the number of bytes that were consumed from
|
|
.IR s .
|
|
If the multibyte character is the null wide character, it resets the
|
|
shift state
|
|
.I *ps
|
|
to the initial state and returns 0.
|
|
.PP
|
|
If the
|
|
.IR n
|
|
bytes starting at
|
|
.I s
|
|
do not contain a complete multibyte
|
|
character,
|
|
.BR mbrlen ()
|
|
returns
|
|
.IR "(size_t)\ \-2" .
|
|
This can happen even if
|
|
.I n
|
|
>=
|
|
.IR MB_CUR_MAX ,
|
|
if the multibyte string contains redundant shift
|
|
sequences.
|
|
.PP
|
|
If the multibyte string starting at
|
|
.I s
|
|
contains an invalid multibyte
|
|
sequence before the next complete character,
|
|
.BR mbrlen ()
|
|
returns
|
|
.IR "(size_t)\ \-1"
|
|
and sets
|
|
.I errno
|
|
to
|
|
.BR EILSEQ .
|
|
In this case,
|
|
the effects on
|
|
.I *ps
|
|
are undefined.
|
|
.PP
|
|
If
|
|
.I ps
|
|
is NULL, a static anonymous state known only to the
|
|
.BR mbrlen ()
|
|
function is used instead.
|
|
.SH RETURN VALUE
|
|
The
|
|
.BR mbrlen ()
|
|
function returns the number of bytes
|
|
parsed from the multibyte
|
|
sequence starting at
|
|
.IR s ,
|
|
if a non-null wide character was recognized.
|
|
It returns 0, if a null wide character was recognized.
|
|
It returns
|
|
.I "(size_t)\ \-1"
|
|
and sets
|
|
.I errno
|
|
to
|
|
.BR EILSEQ ,
|
|
if an invalid multibyte sequence was
|
|
encountered.
|
|
It returns
|
|
.IR "(size_t)\ \-2"
|
|
if it couldn't parse a complete multibyte
|
|
character, meaning that
|
|
.I n
|
|
should be increased.
|
|
.SH ATTRIBUTES
|
|
For an explanation of the terms used in this section, see
|
|
.BR attributes (7).
|
|
.TS
|
|
allbox;
|
|
lb lb lb
|
|
l l l.
|
|
Interface Attribute Value
|
|
T{
|
|
.BR mbrlen ()
|
|
T} Thread safety MT-Unsafe race:mbrlen/!ps
|
|
.TE
|
|
.SH CONFORMING TO
|
|
POSIX.1-2001, POSIX.1-2008, C99.
|
|
.SH NOTES
|
|
The behavior of
|
|
.BR mbrlen ()
|
|
depends on the
|
|
.B LC_CTYPE
|
|
category of the
|
|
current locale.
|
|
.SH SEE ALSO
|
|
.BR mbrtowc (3)
|