xref: /freebsd/lib/libc/locale/mbrlen.3 (revision f126890a)
1.\" Copyright (c) 2002-2004 Tim J. Robbins
2.\" All rights reserved.
3.\"
4.\" Redistribution and use in source and binary forms, with or without
5.\" modification, are permitted provided that the following conditions
6.\" are met:
7.\" 1. Redistributions of source code must retain the above copyright
8.\"    notice, this list of conditions and the following disclaimer.
9.\" 2. Redistributions in binary form must reproduce the above copyright
10.\"    notice, this list of conditions and the following disclaimer in the
11.\"    documentation and/or other materials provided with the distribution.
12.\"
13.\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
14.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
16.\" ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
17.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
18.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
19.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
20.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
21.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
22.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
23.\" SUCH DAMAGE.
24.\"
25.Dd April 7, 2004
26.Dt MBRLEN 3
27.Os
28.Sh NAME
29.Nm mbrlen
30.Nd "get number of bytes in a character (restartable)"
31.Sh LIBRARY
32.Lb libc
33.Sh SYNOPSIS
34.In wchar.h
35.Ft size_t
36.Fn mbrlen "const char * restrict s" "size_t n" "mbstate_t * restrict ps"
37.Sh DESCRIPTION
38The
39.Fn mbrlen
40function inspects at most
41.Fa n
42bytes pointed to by
43.Fa s
44to determine the number of bytes needed to complete the next
45multibyte character.
46.Pp
47The
48.Vt mbstate_t
49argument,
50.Fa ps ,
51is used to keep track of the shift state.
52If it is
53.Dv NULL ,
54.Fn mbrlen
55uses an internal, static
56.Vt mbstate_t
57object, which is initialized to the initial conversion state
58at program startup.
59.Pp
60It is equivalent to:
61.Pp
62.Dl "mbrtowc(NULL, s, n, ps);"
63.Pp
64Except that when
65.Fa ps
66is a
67.Dv NULL
68pointer,
69.Fn mbrlen
70uses its own static, internal
71.Vt mbstate_t
72object to keep track of the shift state.
73.Sh RETURN VALUES
74The
75.Fn mbrlen
76functions returns:
77.Bl -tag -width indent
78.It 0
79The next
80.Fa n
81or fewer bytes
82represent the null wide character
83.Pq Li "L'\e0'" .
84.It >0
85The next
86.Fa n
87or fewer bytes
88represent a valid character,
89.Fn mbrlen
90returns the number of bytes used to complete the multibyte character.
91.It Po Vt size_t Pc Ns \-2
92The next
93.Fa n
94contribute to, but do not complete, a valid multibyte character sequence,
95and all
96.Fa n
97bytes have been processed.
98.It Po Vt size_t Pc Ns \-1
99An encoding error has occurred.
100The next
101.Fa n
102or fewer bytes do not contribute to a valid multibyte character.
103.El
104.Sh EXAMPLES
105A function that calculates the number of characters in a multibyte
106character string:
107.Bd -literal -offset indent
108size_t
109nchars(const char *s)
110{
111	size_t charlen, chars;
112	mbstate_t mbs;
113
114	chars = 0;
115	memset(&mbs, 0, sizeof(mbs));
116	while ((charlen = mbrlen(s, MB_CUR_MAX, &mbs)) != 0 &&
117	    charlen != (size_t)-1 && charlen != (size_t)-2) {
118		s += charlen;
119		chars++;
120	}
121
122	return (chars);
123}
124.Ed
125.Sh ERRORS
126The
127.Fn mbrlen
128function will fail if:
129.Bl -tag -width Er
130.It Bq Er EILSEQ
131An invalid multibyte sequence was detected.
132.It Bq Er EINVAL
133The conversion state is invalid.
134.El
135.Sh SEE ALSO
136.Xr mblen 3 ,
137.Xr mbrtowc 3 ,
138.Xr multibyte 3
139.Sh STANDARDS
140The
141.Fn mbrlen
142function conforms to
143.St -isoC-99 .
144