1 /* $NetBSD: is_tar.c,v 1.1.1.9 2019/05/22 17:19:56 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 1.44 2019/02/20 02:35:27 christos Exp $") 47 #else 48 __RCSID("$NetBSD: is_tar.c,v 1.1.1.9 2019/05/22 17:19:56 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(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 protected int 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 private int 105 is_tar(const unsigned char *buf, size_t nbytes) 106 { 107 const union record *header = RCAST(const union record *, 108 RCAST(const void *, buf)); 109 size_t i; 110 int sum, recsum; 111 const unsigned char *p, *ep; 112 113 if (nbytes < sizeof(*header)) 114 return 0; 115 116 recsum = from_oct(header->header.chksum, sizeof(header->header.chksum)); 117 118 sum = 0; 119 p = header->charptr; 120 ep = header->charptr + sizeof(*header); 121 while (p < ep) 122 sum += *p++; 123 124 /* Adjust checksum to count the "chksum" field as blanks. */ 125 for (i = 0; i < sizeof(header->header.chksum); i++) 126 sum -= header->header.chksum[i]; 127 sum += ' ' * sizeof(header->header.chksum); 128 129 if (sum != recsum) 130 return 0; /* Not a tar archive */ 131 132 if (strncmp(header->header.magic, GNUTMAGIC, 133 sizeof(header->header.magic)) == 0) 134 return 3; /* GNU Unix Standard tar archive */ 135 136 if (strncmp(header->header.magic, TMAGIC, 137 sizeof(header->header.magic)) == 0) 138 return 2; /* Unix Standard tar archive */ 139 140 return 1; /* Old fashioned tar archive */ 141 } 142 143 144 /* 145 * Quick and dirty octal conversion. 146 * 147 * Result is -1 if the field is invalid (all blank, or non-octal). 148 */ 149 private int 150 from_oct(const char *where, size_t digs) 151 { 152 int value; 153 154 if (digs == 0) 155 return -1; 156 157 while (isspace(CAST(unsigned char, *where))) { /* Skip spaces */ 158 where++; 159 if (digs-- == 0) 160 return -1; /* All blank field */ 161 } 162 value = 0; 163 while (digs > 0 && isodigit(*where)) { /* Scan til non-octal */ 164 value = (value << 3) | (*where++ - '0'); 165 digs--; 166 } 167 168 if (digs > 0 && *where && !isspace(CAST(unsigned char, *where))) 169 return -1; /* Ended on non-(space/NUL) */ 170 171 return value; 172 } 173