.\" $NetBSD: unvis.3,v 1.14 2002/03/23 17:38:27 christos Exp $ .\" .\" Copyright (c) 1989, 1991, 1993 .\" The Regents of the University of California. All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 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 .\" may be used to endorse or promote products derived from this software .\" without specific prior written permission. .\" .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" @(#)unvis.3 8.2 (Berkeley) 12/11/93 .\" .Dd December 11, 1993 .Dt UNVIS 3 .Os .Sh NAME .Nm unvis , .Nm strunvis .Nd decode a visual representation of characters .Sh LIBRARY .Lb libc .Sh SYNOPSIS .Fd #include \*[Lt]vis.h\*[Gt] .Ft int .Fn unvis "char *cp" "int c" "int *astate" "int flag" .Ft int .Fn strunvis "char *dst" "const char *src" .Ft int .Fn strunvisx "char *dst" "const char *src" "int flag" .Sh DESCRIPTION The .Fn unvis , .Fn strunvis and .Fn strunvisx functions are used to decode a visual representation of characters, as produced by the .Xr vis 3 function, back into the original form. .Pp The .Fn unvis function is called with successive characters in .Ar c until a valid sequence is recognized, at which time the decoded character is available at the character pointed to by .Ar cp . .Pp The .Fn strunvis function decodes the characters pointed to by .Ar src into the buffer pointed to by .Ar dst . The .Fn strunvis function simply copies .Ar src to .Ar dst , decoding any escape sequences along the way, and returns the number of characters placed into .Ar dst , or \-1 if an invalid escape sequence was detected. The size of .Ar dst should be equal to the size of .Ar src (that is, no expansion takes place during decoding). .Pp The .Fn strunvisx function does the same as the .Fn strunvis function, but it allows you to add a flag that specifies the style the string .Ar src is encoded with. Currently, the only supported flag is .Dv VIS_HTTPSTYLE . .Pp The .Fn unvis function implements a state machine that can be used to decode an arbitrary stream of bytes. All state associated with the bytes being decoded is stored outside the .Fn unvis function (that is, a pointer to the state is passed in), so calls decoding different streams can be freely intermixed. To start decoding a stream of bytes, first initialize an integer to zero. Call .Fn unvis with each successive byte, along with a pointer to this integer, and a pointer to a destination character. The .Fn unvis function has several return codes that must be handled properly. They are: .Bl -tag -width UNVIS_VALIDPUSH .It Li \&0 (zero) Another character is necessary; nothing has been recognized yet. .It Dv UNVIS_VALID A valid character has been recognized and is available at the location pointed to by cp. .It Dv UNVIS_VALIDPUSH A valid character has been recognized and is available at the location pointed to by cp; however, the character currently passed in should be passed in again. .It Dv UNVIS_NOCHAR A valid sequence was detected, but no character was produced. This return code is necessary to indicate a logical break between characters. .It Dv UNVIS_SYNBAD An invalid escape sequence was detected, or the decoder is in an unknown state. The decoder is placed into the starting state. .El .Pp When all bytes in the stream have been processed, call .Fn unvis one more time with flag set to .Dv UNVIS_END to extract any remaining character (the character passed in is ignored). .Pp The .Ar flag argument is also used to specify the encoding style of the source. If set to .Dv VIS_HTTPSTYLE , .Fn unvis will decode URI strings as specified in RFC 1808. .Pp The following code fragment illustrates a proper use of .Fn unvis . .Bd -literal -offset indent int state = 0; char out; while ((ch = getchar()) != EOF) { again: switch(unvis(\*[Am]out, ch, \*[Am]state, 0)) { case 0: case UNVIS_NOCHAR: break; case UNVIS_VALID: (void) putchar(out); break; case UNVIS_VALIDPUSH: (void) putchar(out); goto again; case UNVIS_SYNBAD: (void)fprintf(stderr, "bad sequence!\n"); exit(1); } } if (unvis(\*[Am]out, (char)0, \*[Am]state, UNVIS_END) == UNVIS_VALID) (void) putchar(out); .Ed .Sh SEE ALSO .Xr unvis 1 , .Xr vis 1 , .Xr vis 3 .Rs .%A R. Fielding .%T Relative Uniform Resource Locators .%O RFC1808 .Re .Sh HISTORY The .Fn unvis function first appeared in .Bx 4.4 .