1 /* $NetBSD: is_tar.c,v 1.1.1.4 2015/01/02 20:34:27 christos Exp $ */
2
3 /*
4 * Copyright (c) Ian F. Darwin 1986-1995.
5 * Software written by Ian F. Darwin and others;
6 * maintained 1995-present by Christos Zoulas and others.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 * notice immediately at the beginning of the file, without modification,
13 * this list of conditions, and the following disclaimer.
14 * 2. Redistributions in binary form must reproduce the above copyright
15 * notice, this list of conditions and the following disclaimer in the
16 * documentation and/or other materials provided with the distribution.
17 *
18 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR OR CONTRIBUTORS BE LIABLE FOR
22 * 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 /*
31 * is_tar() -- figure out whether file is a tar archive.
32 *
33 * Stolen (by the author!) from the public domain tar program:
34 * Public Domain version written 26 Aug 1985 John Gilmore (ihnp4!hoptoad!gnu).
35 *
36 * @(#)list.c 1.18 9/23/86 Public Domain - gnu
37 *
38 * Comments changed and some code/comments reformatted
39 * for file command by Ian Darwin.
40 */
41
42 #include "file.h"
43
44 #ifndef lint
45 #if 0
46 FILE_RCSID("@(#)$File: is_tar.c,v 1.37 2010/11/30 14:58:53 rrt Exp $")
47 #else
48 __RCSID("$NetBSD: is_tar.c,v 1.1.1.4 2015/01/02 20:34:27 christos Exp $");
49 #endif
50 #endif
51
52 #include "magic.h"
53 #include <string.h>
54 #include <ctype.h>
55 #include "tar.h"
56
57 #define isodigit(c) ( ((c) >= '0') && ((c) <= '7') )
58
59 private int is_tar(const unsigned char *, size_t);
60 private int from_oct(int, const char *); /* Decode octal number */
61
62 static const char tartype[][32] = {
63 "tar archive",
64 "POSIX tar archive",
65 "POSIX tar archive (GNU)",
66 };
67
68 protected int
file_is_tar(struct magic_set * ms,const unsigned char * buf,size_t nbytes)69 file_is_tar(struct magic_set *ms, const unsigned char *buf, size_t nbytes)
70 {
71 /*
72 * Do the tar test first, because if the first file in the tar
73 * archive starts with a dot, we can confuse it with an nroff file.
74 */
75 int tar;
76 int mime = ms->flags & MAGIC_MIME;
77
78 if ((ms->flags & MAGIC_APPLE) != 0)
79 return 0;
80
81 tar = is_tar(buf, nbytes);
82 if (tar < 1 || tar > 3)
83 return 0;
84
85 if (file_printf(ms, "%s", mime ? "application/x-tar" :
86 tartype[tar - 1]) == -1)
87 return -1;
88 return 1;
89 }
90
91 /*
92 * Return
93 * 0 if the checksum is bad (i.e., probably not a tar archive),
94 * 1 for old UNIX tar file,
95 * 2 for Unix Std (POSIX) tar file,
96 * 3 for GNU tar file.
97 */
98 private int
is_tar(const unsigned char * buf,size_t nbytes)99 is_tar(const unsigned char *buf, size_t nbytes)
100 {
101 const union record *header = (const union record *)(const void *)buf;
102 int i;
103 int sum, recsum;
104 const unsigned char *p;
105
106 if (nbytes < sizeof(union record))
107 return 0;
108
109 recsum = from_oct(8, header->header.chksum);
110
111 sum = 0;
112 p = header->charptr;
113 for (i = sizeof(union record); --i >= 0;)
114 sum += *p++;
115
116 /* Adjust checksum to count the "chksum" field as blanks. */
117 for (i = sizeof(header->header.chksum); --i >= 0;)
118 sum -= header->header.chksum[i];
119 sum += ' ' * sizeof header->header.chksum;
120
121 if (sum != recsum)
122 return 0; /* Not a tar archive */
123
124 if (strcmp(header->header.magic, GNUTMAGIC) == 0)
125 return 3; /* GNU Unix Standard tar archive */
126 if (strcmp(header->header.magic, TMAGIC) == 0)
127 return 2; /* Unix Standard tar archive */
128
129 return 1; /* Old fashioned tar archive */
130 }
131
132
133 /*
134 * Quick and dirty octal conversion.
135 *
136 * Result is -1 if the field is invalid (all blank, or non-octal).
137 */
138 private int
from_oct(int digs,const char * where)139 from_oct(int digs, const char *where)
140 {
141 int value;
142
143 while (isspace((unsigned char)*where)) { /* Skip spaces */
144 where++;
145 if (--digs <= 0)
146 return -1; /* All blank field */
147 }
148 value = 0;
149 while (digs > 0 && isodigit(*where)) { /* Scan til non-octal */
150 value = (value << 3) | (*where++ - '0');
151 --digs;
152 }
153
154 if (digs > 0 && *where && !isspace((unsigned char)*where))
155 return -1; /* Ended on non-(space/NUL) */
156
157 return value;
158 }
159