+.\" $NetBSD: vis.3,v 1.39 2013/02/20 20:05:26 christos Exp $
+.\" $FreeBSD$
+.\"
.\" Copyright (c) 1989, 1991, 1993
.\" The Regents of the University of California. All rights reserved.
.\"
.\" 2. Redistributions in binary form must reproduce the above copyright
.\" notice, this list of conditions and the following disclaimer in the
.\" documentation and/or other materials provided with the distribution.
-.\" 3. All advertising materials mentioning features or use of this software
-.\" must display the following acknowledgement:
-.\" This product includes software developed by the University of
-.\" California, Berkeley and its contributors.
-.\" 4. Neither the name of the University nor the names of its contributors
+.\" 3. Neither the name of the University nor the names of its contributors
.\" may be used to endorse or promote products derived from this software
.\" without specific prior written permission.
.\"
.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
.\" SUCH DAMAGE.
.\"
-.\" From: @(#)vis.3 8.1 (Berkeley) 6/9/93
-.\" $FreeBSD: src/lib/libc/gen/vis.3,v 1.26 2004/07/17 12:27:25 tjr Exp $
+.\" @(#)vis.3 8.1 (Berkeley) 6/9/93
.\"
-.Dd March 21, 2004
+.Dd February 19, 2013
.Dt VIS 3
.Os
.Sh NAME
-.Nm vis
+.Nm vis ,
+.Nm nvis ,
+.Nm strvis ,
+.Nm strnvis ,
+.Nm strvisx ,
+.Nm strnvisx ,
+.Nm strenvisx ,
+.Nm svis ,
+.Nm snvis ,
+.Nm strsvis ,
+.Nm strsnvis ,
+.Nm strsvisx ,
+.Nm strsnvisx ,
+.Nm strsenvisx
.Nd visually encode characters
.Sh LIBRARY
.Lb libc
.In vis.h
.Ft char *
.Fn vis "char *dst" "int c" "int flag" "int nextc"
+.Ft char *
+.Fn nvis "char *dst" "size_t dlen" "int c" "int flag" "int nextc"
.Ft int
.Fn strvis "char *dst" "const char *src" "int flag"
.Ft int
+.Fn strnvis "char *dst" "size_t dlen" "const char *src" "int flag"
+.Ft int
.Fn strvisx "char *dst" "const char *src" "size_t len" "int flag"
+.Ft int
+.Fn strnvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag"
+.Ft int
+.Fn strenvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag" "int *cerr_ptr"
+.Ft char *
+.Fn svis "char *dst" "int c" "int flag" "int nextc" "const char *extra"
+.Ft char *
+.Fn snvis "char *dst" "size_t dlen" "int c" "int flag" "int nextc" "const char *extra"
+.Ft int
+.Fn strsvis "char *dst" "const char *src" "int flag" "const char *extra"
+.Ft int
+.Fn strsnvis "char *dst" "size_t dlen" "const char *src" "int flag" "const char *extra"
+.Ft int
+.Fn strsvisx "char *dst" "const char *src" "size_t len" "int flag" "const char *extra"
+.Ft int
+.Fn strsnvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag" "const char *extra"
+.Ft int
+.Fn strsenvisx "char *dst" "size_t dlen" "const char *src" "size_t len" "int flag" "const char *extra" "int *cerr_ptr"
.Sh DESCRIPTION
The
.Fn vis
If
.Fa c
needs no encoding, it is copied in unaltered.
-The string is
-null terminated, and a pointer to the end of the string is
+The string is null terminated, and a pointer to the end of the string is
returned.
The maximum length of any encoding is four
-characters (not including the trailing
+bytes (not including the trailing
.Dv NUL ) ;
thus, when
encoding a set of characters into a buffer, the size of the buffer should
-be four times the number of characters encoded, plus one for the trailing
+be four times the number of bytes encoded, plus one for the trailing
.Dv NUL .
-The
-.Fa flag
-argument is used for altering the default range of
+The flag parameter is used for altering the default range of
characters considered for encoding and for altering the visual
representation.
The additional character,
encoding format (explained below).
.Pp
The
-.Fn strvis
+.Fn strvis ,
+.Fn strnvis ,
+.Fn strvisx ,
and
-.Fn strvisx
+.Fn strnvisx
functions copy into
.Fa dst
a visual representation of
.Fa src .
The
.Fn strvis
-function encodes characters from
+and
+.Fn strnvis
+functions encode characters from
.Fa src
up to the
first
.Dv NUL .
The
.Fn strvisx
-function encodes exactly
+and
+.Fn strnvisx
+functions encode exactly
.Fa len
characters from
.Fa src
The size of
.Fa dst
must be four times the number
-of characters encoded from
+of bytes encoded from
.Fa src
(plus one for the
.Dv NUL ) .
Both
-forms return the number of characters in dst (not including
-the trailing
+forms return the number of characters in
+.Fa dst
+(not including the trailing
.Dv NUL ) .
+The
+.Dq Nm n
+versions of the functions also take an additional argument
+.Fa dlen
+that indicates the length of the
+.Fa dst
+buffer.
+If
+.Fa dlen
+is not large enough to fit the converted string then the
+.Fn strnvis
+and
+.Fn strnvisx
+functions return \-1 and set
+.Va errno
+to
+.Dv ENOSPC .
+The
+.Fn strenvisx
+function takes an additional argument,
+.Fa cerr_ptr ,
+that is used to pass in and out a multibyte conversion error flag.
+This is useful when processing single characters at a time when
+it is possible that the locale may be set to something other
+than the locale of the characters in the input data.
+.Pp
+The functions
+.Fn svis ,
+.Fn snvis ,
+.Fn strsvis ,
+.Fn strsnvis ,
+.Fn strsvisx ,
+.Fn strsnvisx ,
+and
+.Fn strsenvisx
+correspond to
+.Fn vis ,
+.Fn nvis ,
+.Fn strvis ,
+.Fn strnvis ,
+.Fn strvisx ,
+.Fn strnvisx ,
+and
+.Fn strenvisx
+but have an additional argument
+.Fa extra ,
+pointing to a
+.Dv NUL
+terminated list of characters.
+These characters will be copied encoded or backslash-escaped into
+.Fa dst .
+These functions are useful e.g. to remove the special meaning
+of certain characters to shells.
.Pp
The encoding is a unique, invertible representation composed entirely of
graphic characters; it can be decoded back into the original form using
the
-.Xr unvis 3
-or
+.Xr unvis 3 ,
.Xr strunvis 3
+or
+.Xr strnunvis 3
functions.
.Pp
There are two parameters that can be controlled: the range of
-characters that are encoded, and the type
-of representation used.
-By default, all non-graphic characters
-except space, tab, and newline are encoded.
-(See
-.Xr isgraph 3 . )
+characters that are encoded (applies only to
+.Fn vis ,
+.Fn nvis ,
+.Fn strvis ,
+.Fn strnvis ,
+.Fn strvisx ,
+and
+.Fn strnvisx ) ,
+and the type of representation used.
+By default, all non-graphic characters,
+except space, tab, and newline are encoded (see
+.Xr isgraph 3 ) .
The following flags
alter this:
.Bl -tag -width VIS_WHITEX
.It Dv VIS_GLOB
-Also encode magic characters
+Also encode the magic characters
.Ql ( * ,
.Ql \&? ,
.Ql \&[
\&|
.Dv VIS_NL .
.It Dv VIS_SAFE
-Only encode "unsafe" characters.
-Unsafe means control
-characters which may cause common terminals to perform
+Only encode
+.Dq unsafe
+characters.
+Unsafe means control characters which may cause common terminals to perform
unexpected functions.
-Currently this form allows space,
-tab, newline, backspace, bell, and return - in addition
-to all graphic characters - unencoded.
+Currently this form allows space, tab, newline, backspace, bell, and
+return \(em in addition to all graphic characters \(em unencoded.
.El
.Pp
+(The above flags have no effect for
+.Fn svis ,
+.Fn snvis ,
+.Fn strsvis ,
+.Fn strsnvis ,
+.Fn strsvisx ,
+and
+.Fn strsnvisx .
+When using these functions, place all graphic characters to be
+encoded in an array pointed to by
+.Fa extra .
+In general, the backslash character should be included in this array, see the
+warning on the use of the
+.Dv VIS_NOSLASH
+flag below).
+.Pp
There are four forms of encoding.
-Most forms use the backslash character
+All forms use the backslash character
.Ql \e
to introduce a special
-sequence; two backslashes are used to represent a real backslash.
+sequence; two backslashes are used to represent a real backslash,
+except
+.Dv VIS_HTTPSTYLE
+that uses
+.Ql % ,
+or
+.Dv VIS_MIMESTYLE
+that uses
+.Ql = .
These are the visual formats:
-.Bl -tag -width VIS_HTTPSTYLE
+.Bl -tag -width VIS_CSTYLE
.It (default)
Use an
.Ql M
to represent meta characters (characters with the 8th
bit set), and use caret
.Ql ^
-to represent control characters see
-.Pf ( Xr iscntrl 3 ) .
+to represent control characters (see
+.Xr iscntrl 3 ) .
The following formats are used:
.Bl -tag -width xxxxx
.It Dv \e^C
characters.
The following sequences are used to represent the indicated characters:
.Bd -unfilled -offset indent
-.Li \ea Tn - BEL No (007)
-.Li \eb Tn - BS No (010)
-.Li \ef Tn - NP No (014)
-.Li \en Tn - NL No (012)
-.Li \er Tn - CR No (015)
-.Li \et Tn - HT No (011)
-.Li \ev Tn - VT No (013)
-.Li \e0 Tn - NUL No (000)
+.Li \ea Tn \(em BEL No (007)
+.Li \eb Tn \(em BS No (010)
+.Li \ef Tn \(em NP No (014)
+.Li \en Tn \(em NL No (012)
+.Li \er Tn \(em CR No (015)
+.Li \es Tn \(em SP No (040)
+.Li \et Tn \(em HT No (011)
+.Li \ev Tn \(em VT No (013)
+.Li \e0 Tn \(em NUL No (000)
.Ed
.Pp
When using this format, the
.Fa nextc
-argument is looked at to determine
-if a
+parameter is looked at to determine if a
.Dv NUL
character can be encoded as
.Ql \e0
.Fa nextc
is an octal digit, the latter representation is used to
avoid ambiguity.
-.It Dv VIS_HTTPSTYLE
-Use URI encoding as described in RFC 1808.
-The form is
-.Ql %dd
-where
-.Ar d
-represents a hexadecimal digit.
.It Dv VIS_OCTAL
Use a three digit octal sequence.
The form is
.Ql \eddd
where
-.Ar d
+.Em d
represents an octal digit.
+.It Dv VIS_HTTPSTYLE
+Use URI encoding as described in RFC 1738.
+The form is
+.Ql %xx
+where
+.Em x
+represents a lower case hexadecimal digit.
+.It Dv VIS_MIMESTYLE
+Use MIME Quoted-Printable encoding as described in RFC 2045, only don't
+break lines and don't handle CRLF.
+The form is
+.Ql =XX
+where
+.Em X
+represents an upper case hexadecimal digit.
.El
.Pp
There is one additional flag,
.Ql M-C ) .
With this flag set, the encoding is
ambiguous and non-invertible.
+.Sh MULTIBYTE CHARACTER SUPPORT
+These functions support multibyte character input.
+The encoding conversion is influenced by the setting of the
+.Ev LC_CTYPE
+environment variable which defines the set of characters
+that can be copied without encoding.
+.Pp
+When 8-bit data is present in the input,
+.Ev LC_CTYPE
+must be set to the correct locale or to the C locale.
+If the locales of the data and the conversion are mismatched,
+multibyte character recognition may fail and encoding will be performed
+byte-by-byte instead.
+.Pp
+As noted above,
+.Fa dst
+must be four times the number of bytes processed from
+.Fa src .
+But note that each multibyte character can be up to
+.Dv MB_LEN_MAX
+bytes
+.\" (see
+.\" .Xr multibyte 3 )
+so in terms of multibyte characters,
+.Fa dst
+must be four times
+.Dv MB_LEN_MAX
+times the number of characters processed from
+.Fa src .
+.Sh ENVIRONMENT
+.Bl -tag -width ".Ev LC_CTYPE"
+.It Ev LC_CTYPE
+Specify the locale of the input data.
+Set to C if the input data locale is unknown.
+.El
+.Sh ERRORS
+The functions
+.Fn nvis
+and
+.Fn snvis
+will return
+.Dv NULL
+and the functions
+.Fn strnvis ,
+.Fn strnvisx ,
+.Fn strsnvis ,
+and
+.Fn strsnvisx ,
+will return \-1 when the
+.Fa dlen
+destination buffer size is not enough to perform the conversion while
+setting
+.Va errno
+to:
+.Bl -tag -width ".Bq Er ENOSPC"
+.It Bq Er ENOSPC
+The destination buffer size is not large enough to perform the conversion.
+.El
.Sh SEE ALSO
.Xr unvis 1 ,
+.Xr vis 1 ,
+.Xr glob 3 ,
+.\" .Xr multibyte 3 ,
.Xr unvis 3
.Rs
-.%A R. Fielding
-.%T Relative Uniform Resource Locators
-.%O RFC1808
+.%A T. Berners-Lee
+.%T Uniform Resource Locators (URL)
+.%O "RFC 1738"
+.Re
+.Rs
+.%T "Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies"
+.%O "RFC 2045"
.Re
.Sh HISTORY
-These functions first appeared in
+The
+.Fn vis ,
+.Fn strvis ,
+and
+.Fn strvisx
+functions first appeared in
.Bx 4.4 .
-.Sh BUGS
The
-.Nm
-family of functions do not recognize multibyte characters, and thus
-may consider them to be non-printable when they are in fact printable
-(and vice versa.)
+.Fn svis ,
+.Fn strsvis ,
+.Fn strsvisx
+.Fn nvis ,
+.Fn strnvis ,
+.Fn strnvisx ,
+.Fn snvis ,
+.Fn strsnvis
+and
+.Fn strsnvisx
+functions as well as multibyte character support were added in OS X 10.12.
projects / apple / libc.git / blobdiff