1/*-
2 * Copyright (c) 1989, 1993
3 *	The Regents of the University of California.  All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 * 3. All advertising materials mentioning features or use of this software
14 *    must display the following acknowledgement:
15 *	This product includes software developed by the University of
16 *	California, Berkeley and its contributors.
17 * 4. Neither the name of the University nor the names of its contributors
18 *    may be used to endorse or promote products derived from this software
19 *    without specific prior written permission.
20 *
21 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
22 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
25 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31 * SUCH DAMAGE.
32 */
33
34#if defined(LIBC_SCCS) && !defined(lint)
35static char sccsid[] = "@(#)unvis.c	8.1 (Berkeley) 6/4/93";
36#endif /* LIBC_SCCS and not lint */
37#include <sys/cdefs.h>
38__FBSDID("$FreeBSD: src/lib/libc/gen/unvis.c,v 1.9 2004/08/02 08:46:23 stefanf Exp $");
39
40#include <sys/types.h>
41#include <ctype.h>
42#include <vis.h>
43
44/*
45 * decode driven by state machine
46 */
47#define	S_GROUND	0	/* haven't seen escape char */
48#define	S_START		1	/* start decoding special sequence */
49#define	S_META		2	/* metachar started (M) */
50#define	S_META1		3	/* metachar more, regular char (-) */
51#define	S_CTRL		4	/* control char started (^) */
52#define	S_OCTAL2	5	/* octal digit 2 */
53#define	S_OCTAL3	6	/* octal digit 3 */
54#define	S_HEX2		7	/* hex digit 2 */
55
56#define	S_HTTP		0x080	/* %HEXHEX escape */
57
58#define	isoctal(c)	(((u_char)(c)) >= '0' && ((u_char)(c)) <= '7')
59#define	ishex(c)	((((u_char)(c)) >= '0' && ((u_char)(c)) <= '9') || (((u_char)(c)) >= 'a' && ((u_char)(c)) <= 'f'))
60
61/*
62 * unvis - decode characters previously encoded by vis
63 */
64int
65unvis(char *cp, int c, int *astate, int flag)
66{
67
68	if (flag & UNVIS_END) {
69		if (*astate == S_OCTAL2 || *astate == S_OCTAL3) {
70			*astate = S_GROUND;
71			return (UNVIS_VALID);
72		}
73		return (*astate == S_GROUND ? UNVIS_NOCHAR : UNVIS_SYNBAD);
74	}
75
76	switch (*astate & ~S_HTTP) {
77
78	case S_GROUND:
79		*cp = 0;
80		if (c == '\\') {
81			*astate = S_START;
82			return (0);
83		}
84		if (flag & VIS_HTTPSTYLE && c == '%') {
85			*astate = S_START | S_HTTP;
86			return (0);
87		}
88		*cp = c;
89		return (UNVIS_VALID);
90
91	case S_START:
92		if (*astate & S_HTTP) {
93		    if (ishex(tolower(c))) {
94			*cp = isdigit(c) ? (c - '0') : (tolower(c) - 'a');
95			*astate = S_HEX2;
96			return (0);
97		    }
98		}
99		switch(c) {
100		case '\\':
101			*cp = c;
102			*astate = S_GROUND;
103			return (UNVIS_VALID);
104		case '0': case '1': case '2': case '3':
105		case '4': case '5': case '6': case '7':
106			*cp = (c - '0');
107			*astate = S_OCTAL2;
108			return (0);
109		case 'M':
110			*cp = 0200;
111			*astate = S_META;
112			return (0);
113		case '^':
114			*astate = S_CTRL;
115			return (0);
116		case 'n':
117			*cp = '\n';
118			*astate = S_GROUND;
119			return (UNVIS_VALID);
120		case 'r':
121			*cp = '\r';
122			*astate = S_GROUND;
123			return (UNVIS_VALID);
124		case 'b':
125			*cp = '\b';
126			*astate = S_GROUND;
127			return (UNVIS_VALID);
128		case 'a':
129			*cp = '\007';
130			*astate = S_GROUND;
131			return (UNVIS_VALID);
132		case 'v':
133			*cp = '\v';
134			*astate = S_GROUND;
135			return (UNVIS_VALID);
136		case 't':
137			*cp = '\t';
138			*astate = S_GROUND;
139			return (UNVIS_VALID);
140		case 'f':
141			*cp = '\f';
142			*astate = S_GROUND;
143			return (UNVIS_VALID);
144		case 's':
145			*cp = ' ';
146			*astate = S_GROUND;
147			return (UNVIS_VALID);
148		case 'E':
149			*cp = '\033';
150			*astate = S_GROUND;
151			return (UNVIS_VALID);
152		case '\n':
153			/*
154			 * hidden newline
155			 */
156			*astate = S_GROUND;
157			return (UNVIS_NOCHAR);
158		case '$':
159			/*
160			 * hidden marker
161			 */
162			*astate = S_GROUND;
163			return (UNVIS_NOCHAR);
164		}
165		*astate = S_GROUND;
166		return (UNVIS_SYNBAD);
167
168	case S_META:
169		if (c == '-')
170			*astate = S_META1;
171		else if (c == '^')
172			*astate = S_CTRL;
173		else {
174			*astate = S_GROUND;
175			return (UNVIS_SYNBAD);
176		}
177		return (0);
178
179	case S_META1:
180		*astate = S_GROUND;
181		*cp |= c;
182		return (UNVIS_VALID);
183
184	case S_CTRL:
185		if (c == '?')
186			*cp |= 0177;
187		else
188			*cp |= c & 037;
189		*astate = S_GROUND;
190		return (UNVIS_VALID);
191
192	case S_OCTAL2:	/* second possible octal digit */
193		if (isoctal(c)) {
194			/*
195			 * yes - and maybe a third
196			 */
197			*cp = (*cp << 3) + (c - '0');
198			*astate = S_OCTAL3;
199			return (0);
200		}
201		/*
202		 * no - done with current sequence, push back passed char
203		 */
204		*astate = S_GROUND;
205		return (UNVIS_VALIDPUSH);
206
207	case S_OCTAL3:	/* third possible octal digit */
208		*astate = S_GROUND;
209		if (isoctal(c)) {
210			*cp = (*cp << 3) + (c - '0');
211			return (UNVIS_VALID);
212		}
213		/*
214		 * we were done, push back passed char
215		 */
216		return (UNVIS_VALIDPUSH);
217
218	case S_HEX2:	/* second mandatory hex digit */
219		if (ishex(tolower(c))) {
220			*cp = (isdigit(c) ? (*cp << 4) + (c - '0') : (*cp << 4) + (tolower(c) - 'a' + 10));
221		}
222		*astate = S_GROUND;
223		return (UNVIS_VALID);
224
225	default:
226		/*
227		 * decoder in unknown state - (probably uninitialized)
228		 */
229		*astate = S_GROUND;
230		return (UNVIS_SYNBAD);
231	}
232}
233
234/*
235 * strunvis - decode src into dst
236 *
237 *	Number of chars decoded into dst is returned, -1 on error.
238 *	Dst is null terminated.
239 */
240
241int
242strunvis(char *dst, const char *src)
243{
244	char c;
245	char *start = dst;
246	int state = 0;
247
248	while ( (c = *src++) ) {
249	again:
250		switch (unvis(dst, c, &state, 0)) {
251		case UNVIS_VALID:
252			dst++;
253			break;
254		case UNVIS_VALIDPUSH:
255			dst++;
256			goto again;
257		case 0:
258		case UNVIS_NOCHAR:
259			break;
260		default:
261			return (-1);
262		}
263	}
264	if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
265		dst++;
266	*dst = '\0';
267	return (dst - start);
268}
269
270int
271strunvisx(char *dst, const char *src, int flag)
272{
273	char c;
274	char *start = dst;
275	int state = 0;
276
277	while ( (c = *src++) ) {
278	again:
279		switch (unvis(dst, c, &state, flag)) {
280		case UNVIS_VALID:
281			dst++;
282			break;
283		case UNVIS_VALIDPUSH:
284			dst++;
285			goto again;
286		case 0:
287		case UNVIS_NOCHAR:
288			break;
289		default:
290			return (-1);
291		}
292	}
293	if (unvis(dst, c, &state, UNVIS_END) == UNVIS_VALID)
294		dst++;
295	*dst = '\0';
296	return (dst - start);
297}
298