1 /* $NetBSD: is_tar.c,v 1.1.1.11 2023/08/18 18:36:49 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 file_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 1.50 2022/12/26 17:31:14 christos Exp $")
47 #else
48 __RCSID("$NetBSD: is_tar.c,v 1.1.1.11 2023/08/18 18:36:49 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 file_private int is_tar(const unsigned char *, size_t);
60 file_private int from_oct(const char *, size_t); /* Decode octal number */
61
62 static const char tartype[][32] = { /* should be equal to messages */
63 "tar archive", /* found in ../magic/Magdir/archive */
64 "POSIX tar archive",
65 "POSIX tar archive (GNU)", /* */
66 };
67
68 file_protected int
file_is_tar(struct magic_set * ms,const struct buffer * b)69 file_is_tar(struct magic_set *ms, const struct buffer *b)
70 {
71 const unsigned char *buf = CAST(const unsigned char *, b->fbuf);
72 size_t nbytes = b->flen;
73 /*
74 * Do the tar test first, because if the first file in the tar
75 * archive starts with a dot, we can confuse it with an nroff file.
76 */
77 int tar;
78 int mime = ms->flags & MAGIC_MIME;
79
80 if ((ms->flags & (MAGIC_APPLE|MAGIC_EXTENSION)) != 0)
81 return 0;
82
83 tar = is_tar(buf, nbytes);
84 if (tar < 1 || tar > 3)
85 return 0;
86
87 if (mime == MAGIC_MIME_ENCODING)
88 return 1;
89
90 if (file_printf(ms, "%s", mime ? "application/x-tar" :
91 tartype[tar - 1]) == -1)
92 return -1;
93
94 return 1;
95 }
96
97 /*
98 * Return
99 * 0 if the checksum is bad (i.e., probably not a tar archive),
100 * 1 for old UNIX tar file,
101 * 2 for Unix Std (POSIX) tar file,
102 * 3 for GNU tar file.
103 */
104 file_private int
is_tar(const unsigned char * buf,size_t nbytes)105 is_tar(const unsigned char *buf, size_t nbytes)
106 {
107 static const char gpkg_match[] = "/gpkg-1";
108
109 const union record *header = RCAST(const union record *,
110 RCAST(const void *, buf));
111 size_t i;
112 int sum, recsum;
113 const unsigned char *p, *ep;
114 const char *nulp;
115
116 if (nbytes < sizeof(*header))
117 return 0;
118
119 /* If the file looks like Gentoo GLEP 78 binary package (GPKG),
120 * don't waste time on further checks and fall back to magic rules.
121 */
122 nulp = CAST(const char *,
123 memchr(header->header.name, 0, sizeof(header->header.name)));
124 if (nulp != NULL && nulp >= header->header.name + sizeof(gpkg_match) &&
125 memcmp(nulp - sizeof(gpkg_match) + 1, gpkg_match,
126 sizeof(gpkg_match)) == 0)
127 return 0;
128
129 recsum = from_oct(header->header.chksum, sizeof(header->header.chksum));
130
131 sum = 0;
132 p = header->charptr;
133 ep = header->charptr + sizeof(*header);
134 while (p < ep)
135 sum += *p++;
136
137 /* Adjust checksum to count the "chksum" field as blanks. */
138 for (i = 0; i < sizeof(header->header.chksum); i++)
139 sum -= header->header.chksum[i];
140 sum += ' ' * sizeof(header->header.chksum);
141
142 if (sum != recsum)
143 return 0; /* Not a tar archive */
144
145 if (strncmp(header->header.magic, GNUTMAGIC,
146 sizeof(header->header.magic)) == 0)
147 return 3; /* GNU Unix Standard tar archive */
148
149 if (strncmp(header->header.magic, TMAGIC,
150 sizeof(header->header.magic)) == 0)
151 return 2; /* Unix Standard tar archive */
152
153 return 1; /* Old fashioned tar archive */
154 }
155
156
157 /*
158 * Quick and dirty octal conversion.
159 *
160 * Result is -1 if the field is invalid (all blank, or non-octal).
161 */
162 file_private int
from_oct(const char * where,size_t digs)163 from_oct(const char *where, size_t digs)
164 {
165 int value;
166
167 if (digs == 0)
168 return -1;
169
170 while (isspace(CAST(unsigned char, *where))) { /* Skip spaces */
171 where++;
172 if (digs-- == 0)
173 return -1; /* All blank field */
174 }
175 value = 0;
176 while (digs > 0 && isodigit(*where)) { /* Scan til non-octal */
177 value = (value << 3) | (*where++ - '0');
178 digs--;
179 }
180
181 if (digs > 0 && *where && !isspace(CAST(unsigned char, *where)))
182 return -1; /* Ended on non-(space/NUL) */
183
184 return value;
185 }
186