1.\" $NetBSD: unvis.3,v 1.27 2012/12/15 07:34:36 wiz Exp $ 2.\" $FreeBSD$ 3.\" 4.\" Copyright (c) 1989, 1991, 1993 5.\" The Regents of the University of California. All rights reserved. 6.\" 7.\" Redistribution and use in source and binary forms, with or without 8.\" modification, are permitted provided that the following conditions 9.\" are met: 10.\" 1. Redistributions of source code must retain the above copyright 11.\" notice, this list of conditions and the following disclaimer. 12.\" 2. Redistributions in binary form must reproduce the above copyright 13.\" notice, this list of conditions and the following disclaimer in the 14.\" documentation and/or other materials provided with the distribution. 15.\" 3. Neither the name of the University nor the names of its contributors 16.\" may be used to endorse or promote products derived from this software 17.\" without specific prior written permission. 18.\" 19.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 20.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 21.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 22.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 23.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 24.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 25.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 26.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 27.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 28.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 29.\" SUCH DAMAGE. 30.\" 31.\" @(#)unvis.3 8.2 (Berkeley) 12/11/93 32.\" 33.Dd March 12, 2011 34.Dt UNVIS 3 35.Os 36.Sh NAME 37.Nm unvis , 38.Nm strunvis 39.Nd decode a visual representation of characters 40.Sh LIBRARY 41.Lb libc 42.Sh SYNOPSIS 43.In vis.h 44.Ft int 45.Fn unvis "char *cp" "int c" "int *astate" "int flag" 46.Ft int 47.Fn strunvis "char *dst" "const char *src" 48.Ft int 49.Fn strnunvis "char *dst" "size_t dlen" "const char *src" 50.Ft int 51.Fn strunvisx "char *dst" "const char *src" "int flag" 52.Ft int 53.Fn strnunvisx "char *dst" "size_t dlen" "const char *src" "int flag" 54.Sh DESCRIPTION 55The 56.Fn unvis , 57.Fn strunvis 58and 59.Fn strunvisx 60functions 61are used to decode a visual representation of characters, as produced 62by the 63.Xr vis 3 64function, back into 65the original form. 66.Pp 67The 68.Fn unvis 69function is called with successive characters in 70.Ar c 71until a valid sequence is recognized, at which time the decoded 72character is available at the character pointed to by 73.Ar cp . 74.Pp 75The 76.Fn strunvis 77function decodes the characters pointed to by 78.Ar src 79into the buffer pointed to by 80.Ar dst . 81The 82.Fn strunvis 83function simply copies 84.Ar src 85to 86.Ar dst , 87decoding any escape sequences along the way, 88and returns the number of characters placed into 89.Ar dst , 90or \-1 if an 91invalid escape sequence was detected. 92The size of 93.Ar dst 94should be equal to the size of 95.Ar src 96(that is, no expansion takes place during decoding). 97.Pp 98The 99.Fn strunvisx 100function does the same as the 101.Fn strunvis 102function, 103but it allows you to add a flag that specifies the style the string 104.Ar src 105is encoded with. 106Currently, the supported flags are: 107.Dv VIS_HTTPSTYLE 108and 109.Dv VIS_MIMESTYLE . 110.Pp 111The 112.Fn unvis 113function implements a state machine that can be used to decode an 114arbitrary stream of bytes. 115All state associated with the bytes being decoded is stored outside the 116.Fn unvis 117function (that is, a pointer to the state is passed in), so 118calls decoding different streams can be freely intermixed. 119To start decoding a stream of bytes, first initialize an integer to zero. 120Call 121.Fn unvis 122with each successive byte, along with a pointer 123to this integer, and a pointer to a destination character. 124The 125.Fn unvis 126function has several return codes that must be handled properly. 127They are: 128.Bl -tag -width UNVIS_VALIDPUSH 129.It Li \&0 No (zero) 130Another character is necessary; nothing has been recognized yet. 131.It Dv UNVIS_VALID 132A valid character has been recognized and is available at the location 133pointed to by 134.Fa cp . 135.It Dv UNVIS_VALIDPUSH 136A valid character has been recognized and is available at the location 137pointed to by 138.Fa cp ; 139however, the character currently passed in should be passed in again. 140.It Dv UNVIS_NOCHAR 141A valid sequence was detected, but no character was produced. 142This return code is necessary to indicate a logical break between characters. 143.It Dv UNVIS_SYNBAD 144An invalid escape sequence was detected, or the decoder is in an unknown state. 145The decoder is placed into the starting state. 146.El 147.Pp 148When all bytes in the stream have been processed, call 149.Fn unvis 150one more time with flag set to 151.Dv UNVIS_END 152to extract any remaining character (the character passed in is ignored). 153.Pp 154The 155.Fa flag 156argument is also used to specify the encoding style of the source. 157If set to 158.Dv VIS_HTTPSTYLE 159or 160.Dv VIS_HTTP1808 , 161.Fn unvis 162will decode URI strings as specified in RFC 1808. 163If set to 164.Dv VIS_HTTP1866 , 165.Fn unvis 166will decode entity references and numeric character references 167as specified in RFC 1866. 168If set to 169.Dv VIS_MIMESTYLE , 170.Fn unvis 171will decode MIME Quoted-Printable strings as specified in RFC 2045. 172If set to 173.Dv VIS_NOESCAPE , 174.Fn unvis 175will not decode 176.Ql \e 177quoted characters. 178.Pp 179The following code fragment illustrates a proper use of 180.Fn unvis . 181.Bd -literal -offset indent 182int state = 0; 183char out; 184 185while ((ch = getchar()) != EOF) { 186again: 187 switch(unvis(\*[Am]out, ch, \*[Am]state, 0)) { 188 case 0: 189 case UNVIS_NOCHAR: 190 break; 191 case UNVIS_VALID: 192 (void)putchar(out); 193 break; 194 case UNVIS_VALIDPUSH: 195 (void)putchar(out); 196 goto again; 197 case UNVIS_SYNBAD: 198 errx(EXIT_FAILURE, "Bad character sequence!"); 199 } 200} 201if (unvis(\*[Am]out, '\e0', \*[Am]state, UNVIS_END) == UNVIS_VALID) 202 (void)putchar(out); 203.Ed 204.Sh ERRORS 205The functions 206.Fn strunvis , 207.Fn strnunvis , 208.Fn strunvisx , 209and 210.Fn strnunvisx 211will return \-1 on error and set 212.Va errno 213to: 214.Bl -tag -width Er 215.It Bq Er EINVAL 216An invalid escape sequence was detected, or the decoder is in an unknown state. 217.El 218.Pp 219In addition the functions 220.Fn strnunvis 221and 222.Fn strnunvisx 223will can also set 224.Va errno 225on error to: 226.Bl -tag -width Er 227.It Bq Er ENOSPC 228Not enough space to perform the conversion. 229.El 230.Sh SEE ALSO 231.Xr unvis 1 , 232.Xr vis 1 , 233.Xr vis 3 234.Rs 235.%A R. Fielding 236.%T Relative Uniform Resource Locators 237.%O RFC1808 238.Re 239.Sh HISTORY 240The 241.Fn unvis 242function 243first appeared in 244.Bx 4.4 . 245The 246.Fn strnunvis 247and 248.Fn strnunvisx 249functions appeared in 250.Nx 6.0 251and 252.Fx 9.2 . 253.Sh BUGS 254The names 255.Dv VIS_HTTP1808 256and 257.Dv VIS_HTTP1866 258are wrong. 259Percent-encoding was defined in RFC 1738, the original RFC for URL. 260RFC 1866 defines HTML 2.0, an application of SGML, from which it 261inherits concepts of numeric character references and entity 262references. 263