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