mirror of https://github.com/mkerrisk/man-pages
135 lines
2.9 KiB
Groff
135 lines
2.9 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 MBTOWC 3 2014-03-18 "GNU" "Linux Programmer's Manual"
|
|
.SH NAME
|
|
mbtowc \- convert a multibyte sequence to a wide character
|
|
.SH SYNOPSIS
|
|
.nf
|
|
.B #include <stdlib.h>
|
|
.sp
|
|
.BI "int mbtowc(wchar_t *" pwc ", const char *" s ", size_t " n );
|
|
.fi
|
|
.SH DESCRIPTION
|
|
The main case for this function is when
|
|
.IR s
|
|
is not NULL and
|
|
.I pwc
|
|
is
|
|
not NULL.
|
|
In this case, the
|
|
.BR mbtowc ()
|
|
function inspects at most
|
|
.I n
|
|
bytes of the multibyte string starting at
|
|
.IR s ,
|
|
extracts the next complete
|
|
multibyte character, converts it to a wide character and stores it at
|
|
.IR *pwc .
|
|
It updates an internal shift state known only to the
|
|
.BR mbtowc ()
|
|
function.
|
|
If
|
|
.I s
|
|
does not point to a null byte (\(aq\\0\(aq), it returns the number
|
|
of bytes that were consumed from
|
|
.IR s ,
|
|
otherwise it returns 0.
|
|
.PP
|
|
If the
|
|
.IR n
|
|
bytes starting at
|
|
.I s
|
|
do not contain a complete multibyte
|
|
character, or if they contain an invalid multibyte sequence,
|
|
.BR mbtowc ()
|
|
returns \-1.
|
|
This can happen even if
|
|
.I n
|
|
>=
|
|
.IR MB_CUR_MAX ,
|
|
if the multibyte string contains redundant shift sequences.
|
|
.PP
|
|
A different case is when
|
|
.IR s
|
|
is not NULL but
|
|
.I pwc
|
|
is NULL.
|
|
In this case, the
|
|
.BR mbtowc ()
|
|
function behaves as above, except that it does not
|
|
store the converted wide character in memory.
|
|
.PP
|
|
A third case is when
|
|
.I s
|
|
is NULL.
|
|
In this case,
|
|
.IR pwc
|
|
and
|
|
.I n
|
|
are
|
|
ignored.
|
|
The
|
|
.BR mbtowc ()
|
|
function
|
|
.\" The Dinkumware doc and the Single UNIX specification say this, but
|
|
.\" glibc doesn't implement this.
|
|
resets the shift state, only known to this function,
|
|
to the initial state, and
|
|
returns nonzero if the encoding has nontrivial shift state, or zero if the
|
|
encoding is stateless.
|
|
.SH RETURN VALUE
|
|
If
|
|
.I s
|
|
is not NULL, the
|
|
.BR mbtowc ()
|
|
function returns the number of
|
|
consumed bytes starting at
|
|
.IR s ,
|
|
or 0 if
|
|
.I s
|
|
points to a null byte,
|
|
or \-1 upon failure.
|
|
.PP
|
|
If
|
|
.I s
|
|
is NULL, the
|
|
.BR mbtowc ()
|
|
function
|
|
returns nonzero if the encoding
|
|
has nontrivial shift state, or zero if the encoding is stateless.
|
|
.SH CONFORMING TO
|
|
C99.
|
|
.SH NOTES
|
|
The behavior of
|
|
.BR mbtowc ()
|
|
depends on the
|
|
.B LC_CTYPE
|
|
category of the
|
|
current locale.
|
|
.PP
|
|
This function is not multithread safe.
|
|
The function
|
|
.BR mbrtowc (3)
|
|
provides
|
|
a better interface to the same functionality.
|
|
.SH SEE ALSO
|
|
.BR MB_CUR_MAX (3),
|
|
.BR mblen (3),
|
|
.BR mbrtowc (3),
|
|
.BR mbstowcs (3),
|
|
.BR wctomb (3),
|
|
.BR wcstombs (3)
|