unpack.c

   1 /* unpack.c -- decompress files in pack format.
   2
   3    Copyright (C) 1997, 1999, 2006 Free Software Foundation, Inc.
   4    Copyright (C) 1992-1993 Jean-loup Gailly
   5
   6    This program is free software; you can redistribute it and/or modify
   7    it under the terms of the GNU General Public License as published by
   8    the Free Software Foundation; either version 3, or (at your option)
   9    any later version.
  10
  11    This program is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14    GNU General Public License for more details.
  15
  16    You should have received a copy of the GNU General Public License
  17    along with this program; if not, write to the Free Software Foundation,
  18    Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
  19
  20 #ifdef RCSID
  21 static char rcsid[] = "$Id$";
  22 #endif
  23
  24 #include <config.h>
  25 #include "tailor.h"
  26 #include "gzip.h"
  27 #include "crypt.h"
  28
  29 #define MIN(a,b) ((a) <= (b) ? (a) : (b))
  30 /* The arguments must not have side effects. */
  31
  32 #define MAX_BITLEN 25
  33 /* Maximum length of Huffman codes. (Minor modifications to the code
  34  * would be needed to support 32 bits codes, but pack never generates
  35  * more than 24 bits anyway.)
  36  */
  37
  38 #define LITERALS 256
  39 /* Number of literals, excluding the End of Block (EOB) code */
  40
  41 #define MAX_PEEK 12
  42 /* Maximum number of 'peek' bits used to optimize traversal of the
  43  * Huffman tree.
  44  */
  45
  46 local ulg orig_len;       /* original uncompressed length */
  47 local int max_len;        /* maximum bit length of Huffman codes */
  48
  49 local uch literal[LITERALS];
  50 /* The literal bytes present in the Huffman tree. The EOB code is not
  51  * represented.
  52  */
  53
  54 local int lit_base[MAX_BITLEN+1];
  55 /* All literals of a given bit length are contiguous in literal[] and
  56  * have contiguous codes. literal[code+lit_base[len]] is the literal
  57  * for a code of len bits.
  58  */
  59
  60 local int leaves [MAX_BITLEN+1]; /* Number of leaves for each bit length */
  61 local int parents[MAX_BITLEN+1]; /* Number of parents for each bit length */
  62
  63 local int peek_bits; /* Number of peek bits currently used */
  64
  65 /* local uch prefix_len[1 << MAX_PEEK]; */
  66 #define prefix_len outbuf
  67 /* For each bit pattern b of peek_bits bits, prefix_len[b] is the length
  68  * of the Huffman code starting with a prefix of b (upper bits), or 0
  69  * if all codes of prefix b have more than peek_bits bits. It is not
  70  * necessary to have a huge table (large MAX_PEEK) because most of the
  71  * codes encountered in the input stream are short codes (by construction).
  72  * So for most codes a single lookup will be necessary.
  73  */
  74 #if (1<<MAX_PEEK) > OUTBUFSIZ
  75     error cannot overlay prefix_len and outbuf
  76 #endif
  77
  78 local ulg bitbuf;
  79 /* Bits are added on the low part of bitbuf and read from the high part. */
  80
  81 local int valid;                  /* number of valid bits in bitbuf */
  82 /* all bits above the last valid bit are always zero */
  83
  84 /* Set code to the next 'bits' input bits without skipping them. code
  85  * must be the name of a simple variable and bits must not have side effects.
  86  * IN assertions: bits <= 25 (so that we still have room for an extra byte
  87  * when valid is only 24), and mask = (1<<bits)-1.
  88  */
  89 #define look_bits(code,bits,mask) \
  90 { \
  91   while (valid < (bits)) bitbuf = (bitbuf<<8) | (ulg)get_byte(), valid += 8; \
  92   code = (bitbuf >> (valid-(bits))) & (mask); \
  93 }
  94
  95 /* Skip the given number of bits (after having peeked at them): */
  96 #define skip_bits(bits)  (valid -= (bits))
  97
  98 #define clear_bitbuf() (valid = 0, bitbuf = 0)
  99
 100 /* Local functions */
 101
 102 local void read_tree  OF((void));
 103 local void build_tree OF((void));
 104
 105 /* ===========================================================================
 106  * Read the Huffman tree.
 107  */
 108 local void read_tree()
 109 {
 110     int len;  /* bit length */
 111     int base; /* base offset for a sequence of leaves */
 112     int n;
 113     int max_leaves = 1;
 114
 115     /* Read the original input size, MSB first */
 116     orig_len = 0;
 117     for (n = 1; n <= 4; n++) orig_len = (orig_len << 8) | (ulg)get_byte();
 118
 119     max_len = (int)get_byte(); /* maximum bit length of Huffman codes */
 120     if (max_len > MAX_BITLEN) {
 121         gzip_error ("invalid compressed data -- Huffman code > 32 bits");
 122     }
 123
 124     /* Get the number of leaves at each bit length */
 125     n = 0;
 126     for (len = 1; len <= max_len; len++) {
 127         leaves[len] = (int)get_byte();
 128         if (max_leaves - (len == max_len) < leaves[len])
 129           gzip_error ("too many leaves in Huffman tree");
 130         max_leaves = (max_leaves - leaves[len] + 1) * 2 - 1;
 131         n += leaves[len];
 132     }
 133     if (LITERALS <= n) {
 134         gzip_error ("too many leaves in Huffman tree");
 135     }
 136     Trace((stderr, "orig_len %lu, max_len %d, leaves %d\n",
 137            orig_len, max_len, n));
 138     /* There are at least 2 and at most 256 leaves of length max_len.
 139      * (Pack arbitrarily rejects empty files and files consisting of
 140      * a single byte even repeated.) To fit the last leaf count in a
 141      * byte, it is offset by 2. However, the last literal is the EOB
 142      * code, and is not transmitted explicitly in the tree, so we must
 143      * adjust here by one only.
 144      */
 145     leaves[max_len]++;
 146
 147     /* Now read the leaves themselves */
 148     base = 0;
 149     for (len = 1; len <= max_len; len++) {
 150         /* Remember where the literals of this length start in literal[] : */
 151         lit_base[len] = base;
 152         /* And read the literals: */
 153         for (n = leaves[len]; n > 0; n--) {
 154             literal[base++] = (uch)get_byte();
 155         }
 156     }
 157     leaves[max_len]++; /* Now include the EOB code in the Huffman tree */
 158 }
 159
 160 /* ===========================================================================
 161  * Build the Huffman tree and the prefix table.
 162  */
 163 local void build_tree()
 164 {
 165     int nodes = 0; /* number of nodes (parents+leaves) at current bit length */
 166     int len;       /* current bit length */
 167     uch *prefixp;  /* pointer in prefix_len */
 168
 169     for (len = max_len; len >= 1; len--) {
 170         /* The number of parent nodes at this level is half the total
 171          * number of nodes at parent level:
 172          */
 173         nodes >>= 1;
 174         parents[len] = nodes;
 175         /* Update lit_base by the appropriate bias to skip the parent nodes
 176          * (which are not represented in the literal array):
 177          */
 178         lit_base[len] -= nodes;
 179         /* Restore nodes to be parents+leaves: */
 180         nodes += leaves[len];
 181     }
 182     /* Construct the prefix table, from shortest leaves to longest ones.
 183      * The shortest code is all ones, so we start at the end of the table.
 184      */
 185     peek_bits = MIN(max_len, MAX_PEEK);
 186     prefixp = &prefix_len[1<<peek_bits];
 187     for (len = 1; len <= peek_bits; len++) {
 188         int prefixes = leaves[len] << (peek_bits-len); /* may be 0 */
 189         while (prefixes--) *--prefixp = (uch)len;
 190     }
 191     /* The length of all other codes is unknown: */
 192     while (prefixp > prefix_len) *--prefixp = 0;
 193 }
 194
 195 /* ===========================================================================
 196  * Unpack in to out.  This routine does not support the old pack format
 197  * with magic header \037\037.
 198  *
 199  * IN assertions: the buffer inbuf contains already the beginning of
 200  *   the compressed data, from offsets inptr to insize-1 included.
 201  *   The magic header has already been checked. The output buffer is cleared.
 202  */
 203 int unpack(in, out)
 204     int in, out;            /* input and output file descriptors */
 205 {
 206     int len;                /* Bit length of current code */
 207     unsigned eob;           /* End Of Block code */
 208     register unsigned peek; /* lookahead bits */
 209     unsigned peek_mask;     /* Mask for peek_bits bits */
 210
 211     ifd = in;
 212     ofd = out;
 213
 214     read_tree();     /* Read the Huffman tree */
 215     build_tree();    /* Build the prefix table */
 216     clear_bitbuf();  /* Initialize bit input */
 217     peek_mask = (1<<peek_bits)-1;
 218
 219     /* The eob code is the largest code among all leaves of maximal length: */
 220     eob = leaves[max_len]-1;
 221     Trace((stderr, "eob %d %x\n", max_len, eob));
 222
 223     /* Decode the input data: */
 224     for (;;) {
 225         /* Since eob is the longest code and not shorter than max_len,
 226          * we can peek at max_len bits without having the risk of reading
 227          * beyond the end of file.
 228          */
 229         look_bits(peek, peek_bits, peek_mask);
 230         len = prefix_len[peek];
 231         if (len > 0) {
 232             peek >>= peek_bits - len; /* discard the extra bits */
 233         } else {
 234             /* Code of more than peek_bits bits, we must traverse the tree */
 235             ulg mask = peek_mask;
 236             len = peek_bits;
 237             do {
 238                 len++, mask = (mask<<1)+1;
 239                 look_bits(peek, len, mask);
 240             } while (peek < (unsigned)parents[len]);
 241             /* loop as long as peek is a parent node */
 242         }
 243         /* At this point, peek is the next complete code, of len bits */
 244         if (peek == eob && len == max_len) break; /* end of file? */
 245         put_ubyte(literal[peek+lit_base[len]]);
 246         Tracev((stderr,"%02d %04x %c\n", len, peek,
 247                 literal[peek+lit_base[len]]));
 248         skip_bits(len);
 249     } /* for (;;) */
 250
 251     flush_window();
 252     if (orig_len != (ulg)(bytes_out & 0xffffffff)) {
 253         gzip_error ("invalid compressed data--length error");
 254     }
 255     return OK;
 256 }