xref: /freebsd/usr.bin/hexdump/conv.c (revision 6ef644f5889afbd0f681b08ed1a2f369524af83e)
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 #include <sys/types.h>
37 
38 #include <assert.h>
39 #include <ctype.h>
40 #include <limits.h>
41 #include <stdio.h>
42 #include <stdlib.h>
43 #include <string.h>
44 #include <wchar.h>
45 #include <wctype.h>
46 #include "hexdump.h"
47 
48 void
49 conv_c(PR *pr, u_char *p, size_t bufsize)
50 {
51 	char buf[10];
52 	char const *str;
53 	wchar_t wc;
54 	size_t clen, oclen;
55 	int converr, pad, width;
56 	u_char peekbuf[MB_LEN_MAX];
57 	u_char *op;
58 
59 	op = NULL;
60 
61 	if (pr->mbleft > 0) {
62 		str = "**";
63 		pr->mbleft--;
64 		goto strpr;
65 	}
66 
67 	switch(*p) {
68 	case '\0':
69 		str = "\\0";
70 		goto strpr;
71 	/* case '\a': */
72 	case '\007':
73 		str = "\\a";
74 		goto strpr;
75 	case '\b':
76 		str = "\\b";
77 		goto strpr;
78 	case '\f':
79 		str = "\\f";
80 		goto strpr;
81 	case '\n':
82 		str = "\\n";
83 		goto strpr;
84 	case '\r':
85 		str = "\\r";
86 		goto strpr;
87 	case '\t':
88 		str = "\\t";
89 		goto strpr;
90 	case '\v':
91 		str = "\\v";
92 		goto strpr;
93 	default:
94 		break;
95 	}
96 	/*
97 	 * Multibyte characters are disabled for hexdump(1) for backwards
98 	 * compatibility and consistency (none of its other output formats
99 	 * recognize them correctly).
100 	 */
101 	converr = 0;
102 	if (odmode && MB_CUR_MAX > 1) {
103 		oclen = 0;
104 retry:
105 		clen = mbrtowc(&wc, p, bufsize, &pr->mbstate);
106 		if (clen == 0)
107 			clen = 1;
108 		else if (clen == (size_t)-1 || (clen == (size_t)-2 &&
109 		    p == peekbuf)) {
110 			memset(&pr->mbstate, 0, sizeof(pr->mbstate));
111 			if (p == peekbuf) {
112 				/*
113 				 * We peeked ahead, but that didn't help --
114 				 * we either got an illegal sequence or still
115 				 * can't complete; restore original character.
116 				 */
117 				oclen = 0;
118 				p = op;
119 			}
120 			wc = *p;
121 			clen = 1;
122 			converr = 1;
123 		} else if (clen == (size_t)-2) {
124 			/*
125 			 * Incomplete character; peek ahead and see if we
126 			 * can complete it.
127 			 */
128 			oclen = bufsize;
129 			op = p;
130 			bufsize = peek(p = peekbuf, MB_CUR_MAX);
131 			goto retry;
132 		}
133 		clen += oclen;
134 	} else {
135 		wc = *p;
136 		clen = 1;
137 	}
138 	if (!converr && iswprint(wc)) {
139 		if (!odmode) {
140 			*pr->cchar = 'c';
141 			(void)printf(pr->fmt, (int)wc);
142 		} else {
143 			*pr->cchar = 'C';
144 			assert(strcmp(pr->fmt, "%3C") == 0);
145 			width = wcwidth(wc);
146 			assert(width >= 0);
147 			pad = 3 - width;
148 			if (pad < 0)
149 				pad = 0;
150 			(void)printf("%*s%C", pad, "", wc);
151 			pr->mbleft = clen - 1;
152 		}
153 	} else {
154 		(void)sprintf(buf, "%03o", (int)*p);
155 		str = buf;
156 strpr:		*pr->cchar = 's';
157 		(void)printf(pr->fmt, str);
158 	}
159 }
160 
161 void
162 conv_u(PR *pr, u_char *p)
163 {
164 	static char const * list[] = {
165 		"nul", "soh", "stx", "etx", "eot", "enq", "ack", "bel",
166 		 "bs",  "ht",  "lf",  "vt",  "ff",  "cr",  "so",  "si",
167 		"dle", "dc1", "dc2", "dc3", "dc4", "nak", "syn", "etb",
168 		"can",  "em", "sub", "esc",  "fs",  "gs",  "rs",  "us",
169 	};
170 
171 						/* od used nl, not lf */
172 	if (*p <= 0x1f) {
173 		*pr->cchar = 's';
174 		if (odmode && *p == 0x0a)
175 			(void)printf(pr->fmt, "nl");
176 		else
177 			(void)printf(pr->fmt, list[*p]);
178 	} else if (*p == 0x7f) {
179 		*pr->cchar = 's';
180 		(void)printf(pr->fmt, "del");
181 	} else if (odmode && *p == 0x20) {	/* od replaced space with sp */
182 		*pr->cchar = 's';
183 		(void)printf(pr->fmt, " sp");
184 	} else if (isprint(*p)) {
185 		*pr->cchar = 'c';
186 		(void)printf(pr->fmt, *p);
187 	} else {
188 		*pr->cchar = 'x';
189 		(void)printf(pr->fmt, (int)*p);
190 	}
191 }
192