contrib/file/src/is_tar.c

   1 /*
   2  * Copyright (c) Ian F. Darwin 1986-1995.
   3  * Software written by Ian F. Darwin and others;
   4  * maintained 1995-present by Christos Zoulas and others.
   5  *
   6  * Redistribution and use in source and binary forms, with or without
   7  * modification, are permitted provided that the following conditions
   8  * are met:
   9  * 1. Redistributions of source code must retain the above copyright
  10  *    notice immediately at the beginning of the file, without modification,
  11  *    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  *
  16  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
  17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  18  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  19  * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
  20  * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
  21  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
  22  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
  23  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  24  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
  25  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  26  * SUCH DAMAGE.
  27  */
  28 /*
  29  * is_tar() -- figure out whether file is a tar archive.
  30  *
  31  * Stolen (by the author!) from the public domain tar program:
  32  * Public Domain version written 26 Aug 1985 John Gilmore (ihnp4!hoptoad!gnu).
  33  *
  34  * @(#)list.c 1.18 9/23/86 Public Domain - gnu
  35  *
  36  * Comments changed and some code/comments reformatted
  37  * for file command by Ian Darwin.
  38  */
  39
  40 #include "file.h"
  41
  42 #ifndef lint
  43 FILE_RCSID("@(#)$File: is_tar.c,v 1.39 2017/03/17 20:45:01 christos Exp $")
  44 #endif
  45
  46 #include "magic.h"
  47 #include <string.h>
  48 #include <ctype.h>
  49 #include "tar.h"
  50
  51 #define isodigit(c)     ( ((c) >= '0') && ((c) <= '7') )
  52
  53 private int is_tar(const unsigned char *, size_t);
  54 private int from_oct(const char *, size_t);     /* Decode octal number */
  55
  56 static const char tartype[][32] = {
  57         "tar archive",
  58         "POSIX tar archive",
  59         "POSIX tar archive (GNU)",
  60 };
  61
  62 protected int
  63 file_is_tar(struct magic_set *ms, const unsigned char *buf, size_t nbytes)
  64 {
  65         /*
  66          * Do the tar test first, because if the first file in the tar
  67          * archive starts with a dot, we can confuse it with an nroff file.
  68          */
  69         int tar;
  70         int mime = ms->flags & MAGIC_MIME;
  71
  72         if ((ms->flags & (MAGIC_APPLE|MAGIC_EXTENSION)) != 0)
  73                 return 0;
  74
  75         tar = is_tar(buf, nbytes);
  76         if (tar < 1 || tar > 3)
  77                 return 0;
  78
  79         if (file_printf(ms, "%s", mime ? "application/x-tar" :
  80             tartype[tar - 1]) == -1)
  81                 return -1;
  82         return 1;
  83 }
  84
  85 /*
  86  * Return
  87  *      0 if the checksum is bad (i.e., probably not a tar archive),
  88  *      1 for old UNIX tar file,
  89  *      2 for Unix Std (POSIX) tar file,
  90  *      3 for GNU tar file.
  91  */
  92 private int
  93 is_tar(const unsigned char *buf, size_t nbytes)
  94 {
  95         const union record *header = (const union record *)(const void *)buf;
  96         size_t i;
  97         int sum, recsum;
  98         const unsigned char *p, *ep;
  99
 100         if (nbytes < sizeof(*header))
 101                 return 0;
 102
 103         recsum = from_oct(header->header.chksum, sizeof(header->header.chksum));
 104
 105         sum = 0;
 106         p = header->charptr;
 107         ep = header->charptr + sizeof(*header);
 108         while (p < ep)
 109                 sum += *p++;
 110
 111         /* Adjust checksum to count the "chksum" field as blanks. */
 112         for (i = 0; i < sizeof(header->header.chksum); i++)
 113                 sum -= header->header.chksum[i];
 114         sum += ' ' * sizeof(header->header.chksum);
 115
 116         if (sum != recsum)
 117                 return 0;       /* Not a tar archive */
 118
 119         if (strncmp(header->header.magic, GNUTMAGIC,
 120             sizeof(header->header.magic)) == 0)
 121                 return 3;               /* GNU Unix Standard tar archive */
 122
 123         if (strncmp(header->header.magic, TMAGIC,
 124             sizeof(header->header.magic)) == 0)
 125                 return 2;               /* Unix Standard tar archive */
 126
 127         return 1;                       /* Old fashioned tar archive */
 128 }
 129
 130
 131 /*
 132  * Quick and dirty octal conversion.
 133  *
 134  * Result is -1 if the field is invalid (all blank, or non-octal).
 135  */
 136 private int
 137 from_oct(const char *where, size_t digs)
 138 {
 139         int     value;
 140
 141         if (digs == 0)
 142                 return -1;
 143
 144         while (isspace((unsigned char)*where)) {        /* Skip spaces */
 145                 where++;
 146                 if (digs-- == 0)
 147                         return -1;              /* All blank field */
 148         }
 149         value = 0;
 150         while (digs > 0 && isodigit(*where)) {  /* Scan til non-octal */
 151                 value = (value << 3) | (*where++ - '0');
 152                 digs--;
 153         }
 154
 155         if (digs > 0 && *where && !isspace((unsigned char)*where))
 156                 return -1;                      /* Ended on non-(space/NUL) */
 157
 158         return value;
 159 }