xref: /freebsd/usr.bin/hexdump/conv.c (revision f6a3b357e9be4c6423c85eff9a847163a0d307c8)
1 /*-
2  * SPDX-License-Identifier: BSD-3-Clause
3  *
4  * Copyright (c) 1989, 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 
32 #ifndef lint
33 static const char sccsid[] = "@(#)conv.c	8.1 (Berkeley) 6/6/93";
34 #endif /* not lint */
35 #include <sys/cdefs.h>
36 __FBSDID("$FreeBSD$");
37 
38 #include <sys/types.h>
39 
40 #include <assert.h>
41 #include <ctype.h>
42 #include <limits.h>
43 #include <stdio.h>
44 #include <stdlib.h>
45 #include <string.h>
46 #include <wchar.h>
47 #include <wctype.h>
48 #include "hexdump.h"
49 
50 void
51 conv_c(PR *pr, u_char *p, size_t bufsize)
52 {
53 	char buf[10];
54 	char const *str;
55 	wchar_t wc;
56 	size_t clen, oclen;
57 	int converr, pad, width;
58 	u_char peekbuf[MB_LEN_MAX];
59 	u_char *op;
60 
61 	op = NULL;
62 
63 	if (pr->mbleft > 0) {
64 		str = "**";
65 		pr->mbleft--;
66 		goto strpr;
67 	}
68 
69 	switch(*p) {
70 	case '\0':
71 		str = "\\0";
72 		goto strpr;
73 	/* case '\a': */
74 	case '\007':
75 		str = "\\a";
76 		goto strpr;
77 	case '\b':
78 		str = "\\b";
79 		goto strpr;
80 	case '\f':
81 		str = "\\f";
82 		goto strpr;
83 	case '\n':
84 		str = "\\n";
85 		goto strpr;
86 	case '\r':
87 		str = "\\r";
88 		goto strpr;
89 	case '\t':
90 		str = "\\t";
91 		goto strpr;
92 	case '\v':
93 		str = "\\v";
94 		goto strpr;
95 	default:
96 		break;
97 	}
98 	/*
99 	 * Multibyte characters are disabled for hexdump(1) for backwards
100 	 * compatibility and consistency (none of its other output formats
101 	 * recognize them correctly).
102 	 */
103 	converr = 0;
104 	if (odmode && MB_CUR_MAX > 1) {
105 		oclen = 0;
106 retry:
107 		clen = mbrtowc(&wc, p, bufsize, &pr->mbstate);
108 		if (clen == 0)
109 			clen = 1;
110 		else if (clen == (size_t)-1 || (clen == (size_t)-2 &&
111 		    p == peekbuf)) {
112 			memset(&pr->mbstate, 0, sizeof(pr->mbstate));
113 			if (p == peekbuf) {
114 				/*
115 				 * We peeked ahead, but that didn't help --
116 				 * we either got an illegal sequence or still
117 				 * can't complete; restore original character.
118 				 */
119 				oclen = 0;
120 				p = op;
121 			}
122 			wc = *p;
123 			clen = 1;
124 			converr = 1;
125 		} else if (clen == (size_t)-2) {
126 			/*
127 			 * Incomplete character; peek ahead and see if we
128 			 * can complete it.
129 			 */
130 			oclen = bufsize;
131 			op = p;
132 			bufsize = peek(p = peekbuf, MB_CUR_MAX);
133 			goto retry;
134 		}
135 		clen += oclen;
136 	} else {
137 		wc = *p;
138 		clen = 1;
139 	}
140 	if (!converr && iswprint(wc)) {
141 		if (!odmode) {
142 			*pr->cchar = 'c';
143 			(void)printf(pr->fmt, (int)wc);
144 		} else {
145 			*pr->cchar = 'C';
146 			assert(strcmp(pr->fmt, "%3C") == 0);
147 			width = wcwidth(wc);
148 			assert(width >= 0);
149 			pad = 3 - width;
150 			if (pad < 0)
151 				pad = 0;
152 			(void)printf("%*s%C", pad, "", wc);
153 			pr->mbleft = clen - 1;
154 		}
155 	} else {
156 		(void)sprintf(buf, "%03o", (int)*p);
157 		str = buf;
158 strpr:		*pr->cchar = 's';
159 		(void)printf(pr->fmt, str);
160 	}
161 }
162 
163 void
164 conv_u(PR *pr, u_char *p)
165 {
166 	static char const * list[] = {
167 		"nul", "soh", "stx", "etx", "eot", "enq", "ack", "bel",
168 		 "bs",  "ht",  "lf",  "vt",  "ff",  "cr",  "so",  "si",
169 		"dle", "dc1", "dc2", "dc3", "dc4", "nak", "syn", "etb",
170 		"can",  "em", "sub", "esc",  "fs",  "gs",  "rs",  "us",
171 	};
172 
173 						/* od used nl, not lf */
174 	if (*p <= 0x1f) {
175 		*pr->cchar = 's';
176 		if (odmode && *p == 0x0a)
177 			(void)printf(pr->fmt, "nl");
178 		else
179 			(void)printf(pr->fmt, list[*p]);
180 	} else if (*p == 0x7f) {
181 		*pr->cchar = 's';
182 		(void)printf(pr->fmt, "del");
183 	} else if (odmode && *p == 0x20) {	/* od replaced space with sp */
184 		*pr->cchar = 's';
185 		(void)printf(pr->fmt, " sp");
186 	} else if (isprint(*p)) {
187 		*pr->cchar = 'c';
188 		(void)printf(pr->fmt, *p);
189 	} else {
190 		*pr->cchar = 'x';
191 		(void)printf(pr->fmt, (int)*p);
192 	}
193 }
194