ref: 7a493e3a404cd04ad2d798e985d7441bd2d955ea
dir: /src/gzip/infblock.c/
/* infblock.c -- interpret and process block types to last block
* Copyright (C) 1995-2002 Mark Adler
* For conditions of distribution and use, see copyright notice in zlib.h
*/
#include "zutil.h"
#include "infblock.h"
#include "inftrees.h"
#include "infcodes.h"
#include "infutil.h"
/* simplify the use of the inflate_huft type with some defines */
#define exop word.what.Exop
#define bits word.what.Bits
/* Table for deflate from PKZIP's appnote.txt. */
local const uInt border[] = { /* Order of the bit length code lengths */
16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15};
/*
Notes beyond the 1.93a appnote.txt:
1. Distance pointers never point before the beginning of the output
stream.
2. Distance pointers can point back across blocks, up to 32k away.
3. There is an implied maximum of 7 bits for the bit length table and
15 bits for the actual data.
4. If only one code exists, then it is encoded using one bit. (Zero
would be more efficient, but perhaps a little confusing.) If two
codes exist, they are coded using one bit each (0 and 1).
5. There is no way of sending zero distance codes--a dummy must be
sent if there are none. (History: a pre 2.0 version of PKZIP would
store blocks with no distance codes, but this was discovered to be
too harsh a criterion.) Valid only for 1.93a. 2.04c does allow
zero distance codes, which is sent as one code of zero bits in
length.
6. There are up to 286 literal/length codes. Code 256 represents the
end-of-block. Note however that the static length tree defines
288 codes just to fill out the Huffman codes. Codes 286 and 287
cannot be used though, since there is no length base or extra bits
defined for them. Similarily, there are up to 30 distance codes.
However, static trees define 32 codes (all 5 bits) to fill out the
Huffman codes, but the last two had better not show up in the data.
7. Unzip can check dynamic Huffman blocks for complete code sets.
The exception is that a single code would not be complete (see #4).
8. The five bits following the block type is really the number of
literal codes sent minus 257.
9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits
(1+6+6). Therefore, to output three times the length, you output
three codes (1+1+1), whereas to output four times the same length,
you only need two codes (1+3). Hmm.
10. In the tree reconstruction algorithm, Code = Code + Increment
only if BitLength(i) is not zero. (Pretty obvious.)
11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19)
12. Note: length code 284 can represent 227-258, but length code 285
really is 258. The last length deserves its own, short code
since it gets used a lot in very redundant files. The length
258 is special since 258 - 3 (the min match length) is 255.
13. The literal/length and distance code bit lengths are read as a
single stream of lengths. It is possible (and advantageous) for
a repeat code (16, 17, or 18) to go across the boundary between
the two sets of lengths.
*/
local void inflate_blocks_reset( /* s, z, c) */
inflate_blocks_statef *s,
z_streamp z,
uLongf *c )
{
if (c != Z_NULL)
*c = s->check;
if (s->mode == BTREE || s->mode == DTREE)
ZFREE(z, s->sub.trees.blens);
if (s->mode == CODES)
inflate_codes_free(s->sub.decode.codes, z);
s->mode = TYPE;
s->bitk = 0;
s->bitb = 0;
s->read = s->write = s->window;
if (s->checkfn != Z_NULL)
z->adler = s->check = (*s->checkfn)(0L, (const Bytef *)Z_NULL, 0);
Tracev((stderr, "inflate: blocks reset\n"));
}
local inflate_blocks_statef *inflate_blocks_new( /* z, c, w) */
z_streamp z,
check_func c,
uInt w )
{
inflate_blocks_statef *s;
if ((s = (inflate_blocks_statef *)ZALLOC
(z,1,sizeof(struct inflate_blocks_state))) == Z_NULL)
return s;
if ((s->hufts =
(inflate_huft *)ZALLOC(z, sizeof(inflate_huft), MANY)) == Z_NULL)
{
ZFREE(z, s);
return Z_NULL;
}
if ((s->window = (Bytef *)ZALLOC(z, 1, w)) == Z_NULL)
{
ZFREE(z, s->hufts);
ZFREE(z, s);
return Z_NULL;
}
s->end = s->window + w;
s->checkfn = c;
s->mode = TYPE;
Tracev((stderr, "inflate: blocks allocated\n"));
inflate_blocks_reset(s, z, Z_NULL);
return s;
}
local int inflate_blocks( /* s, z, r) */
inflate_blocks_statef *s,
z_streamp z,
int r )
{
uInt t; /* temporary storage */
uLong b; /* bit buffer */
uInt k; /* bits in bit buffer */
Bytef *p; /* input data pointer */
uInt n; /* bytes available there */
Bytef *q; /* output window write pointer */
uInt m; /* bytes to end of window or read pointer */
/* copy input/output information to locals (UPDATE macro restores) */
LOAD
/* process input based on current state */
while (1) switch (s->mode)
{
case TYPE:
NEEDBITS(3)
t = (uInt)b & 7;
s->last = t & 1;
switch (t >> 1)
{
case 0: /* stored */
Tracev((stderr, "inflate: stored block%s\n",
s->last ? " (last)" : ""));
DUMPBITS(3)
t = k & 7; /* go to byte boundary */
DUMPBITS(t)
s->mode = LENS; /* get length of stored block */
break;
case 1: /* fixed */
Tracev((stderr, "inflate: fixed codes block%s\n",
s->last ? " (last)" : ""));
{
uInt bl, bd;
inflate_huft *tl, *td;
inflate_trees_fixed(&bl, &bd, (const inflate_huft**)&tl,
(const inflate_huft**)&td, z);
s->sub.decode.codes = inflate_codes_new(bl, bd, tl, td, z);
if (s->sub.decode.codes == Z_NULL)
{
r = Z_MEM_ERROR;
LEAVE
}
}
DUMPBITS(3)
s->mode = CODES;
break;
case 2: /* dynamic */
Tracev((stderr, "inflate: dynamic codes block%s\n",
s->last ? " (last)" : ""));
DUMPBITS(3)
s->mode = TABLE;
break;
case 3: /* illegal */
DUMPBITS(3)
s->mode = BAD;
z->msg = (char*)"invalid block type";
r = Z_DATA_ERROR;
LEAVE
}
break;
case LENS:
NEEDBITS(32)
if ((((~b) >> 16) & 0xffff) != (b & 0xffff))
{
s->mode = BAD;
z->msg = (char*)"invalid stored block lengths";
r = Z_DATA_ERROR;
LEAVE
}
s->sub.left = (uInt)b & 0xffff;
b = k = 0; /* dump bits */
Tracev((stderr, "inflate: stored length %u\n", s->sub.left));
s->mode = s->sub.left ? STORED : (s->last ? DRY : TYPE);
break;
case STORED:
if (n == 0)
LEAVE
NEEDOUT
t = s->sub.left;
if (t > n) t = n;
if (t > m) t = m;
zmemcpy(q, p, t);
p += t; n -= t;
q += t; m -= t;
if ((s->sub.left -= t) != 0)
break;
Tracev((stderr, "inflate: stored end, %lu total out\n",
z->total_out + (q >= s->read ? q - s->read :
(s->end - s->read) + (q - s->window))));
s->mode = s->last ? DRY : TYPE;
break;
case TABLE:
NEEDBITS(14)
s->sub.trees.table = t = (uInt)b & 0x3fff;
#ifndef PKZIP_BUG_WORKAROUND
if ((t & 0x1f) > 29 || ((t >> 5) & 0x1f) > 29)
{
s->mode = BAD;
z->msg = (char*)"too many length or distance symbols";
r = Z_DATA_ERROR;
LEAVE
}
#endif
t = 258 + (t & 0x1f) + ((t >> 5) & 0x1f);
if ((s->sub.trees.blens = (uIntf*)ZALLOC(z, t, sizeof(uInt))) == Z_NULL)
{
r = Z_MEM_ERROR;
LEAVE
}
DUMPBITS(14)
s->sub.trees.index = 0;
Tracev((stderr, "inflate: table sizes ok\n"));
s->mode = BTREE;
/* fall through */
case BTREE:
while (s->sub.trees.index < 4 + (s->sub.trees.table >> 10))
{
NEEDBITS(3)
s->sub.trees.blens[border[s->sub.trees.index++]] = (uInt)b & 7;
DUMPBITS(3)
}
while (s->sub.trees.index < 19)
s->sub.trees.blens[border[s->sub.trees.index++]] = 0;
s->sub.trees.bb = 7;
t = inflate_trees_bits(s->sub.trees.blens, &s->sub.trees.bb,
&s->sub.trees.tb, s->hufts, z);
if (t != Z_OK)
{
r = t;
if (r == Z_DATA_ERROR)
{
ZFREE(z, s->sub.trees.blens);
s->mode = BAD;
}
LEAVE
}
s->sub.trees.index = 0;
Tracev((stderr, "inflate: bits tree ok\n"));
s->mode = DTREE;
/* fall through */
case DTREE:
while (t = s->sub.trees.table,
s->sub.trees.index < 258 + (t & 0x1f) + ((t >> 5) & 0x1f))
{
inflate_huft *h;
uInt i, j, c;
t = s->sub.trees.bb;
NEEDBITS(t)
h = s->sub.trees.tb + ((uInt)b & inflate_mask[t]);
t = h->bits;
c = h->base;
if (c < 16)
{
DUMPBITS(t)
s->sub.trees.blens[s->sub.trees.index++] = c;
}
else /* c == 16..18 */
{
i = c == 18 ? 7 : c - 14;
j = c == 18 ? 11 : 3;
NEEDBITS(t + i)
DUMPBITS(t)
j += (uInt)b & inflate_mask[i];
DUMPBITS(i)
i = s->sub.trees.index;
t = s->sub.trees.table;
if (i + j > 258 + (t & 0x1f) + ((t >> 5) & 0x1f) ||
(c == 16 && i < 1))
{
ZFREE(z, s->sub.trees.blens);
s->mode = BAD;
z->msg = (char*)"invalid bit length repeat";
r = Z_DATA_ERROR;
LEAVE
}
c = c == 16 ? s->sub.trees.blens[i - 1] : 0;
do {
s->sub.trees.blens[i++] = c;
} while (--j);
s->sub.trees.index = i;
}
}
s->sub.trees.tb = Z_NULL;
{
uInt bl, bd;
inflate_huft *tl, *td;
inflate_codes_statef *c;
bl = 9; /* must be <= 9 for lookahead assumptions */
bd = 6; /* must be <= 9 for lookahead assumptions */
t = s->sub.trees.table;
t = inflate_trees_dynamic(257 + (t & 0x1f), 1 + ((t >> 5) & 0x1f),
s->sub.trees.blens, &bl, &bd, &tl, &td,
s->hufts, z);
if (t != Z_OK)
{
if (t == (uInt)Z_DATA_ERROR)
{
ZFREE(z, s->sub.trees.blens);
s->mode = BAD;
}
r = t;
LEAVE
}
Tracev((stderr, "inflate: trees ok\n"));
if ((c = inflate_codes_new(bl, bd, tl, td, z)) == Z_NULL)
{
r = Z_MEM_ERROR;
LEAVE
}
s->sub.decode.codes = c;
}
ZFREE(z, s->sub.trees.blens);
s->mode = CODES;
/* fall through */
case CODES:
UPDATE
if ((r = inflate_codes(s, z, r)) != Z_STREAM_END)
return inflate_flush(s, z, r);
r = Z_OK;
inflate_codes_free(s->sub.decode.codes, z);
LOAD
Tracev((stderr, "inflate: codes end, %lu total out\n",
z->total_out + (q >= s->read ? q - s->read :
(s->end - s->read) + (q - s->window))));
if (!s->last)
{
s->mode = TYPE;
break;
}
s->mode = DRY;
/* fall through */
case DRY:
FLUSH
if (s->read != s->write)
LEAVE
s->mode = DONE;
/* fall through */
case DONE:
r = Z_STREAM_END;
LEAVE
case BAD:
r = Z_DATA_ERROR;
LEAVE
default:
r = Z_STREAM_ERROR;
LEAVE
}
#ifdef NEED_DUMMY_RETURN
return 0;
#endif
}
local int inflate_blocks_free( /* s, z) */
inflate_blocks_statef *s,
z_streamp z )
{
inflate_blocks_reset(s, z, Z_NULL);
ZFREE(z, s->window);
ZFREE(z, s->hufts);
ZFREE(z, s);
Tracev((stderr, "inflate: blocks freed\n"));
return Z_OK;
}