1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984
|
/* Inflate deflated data
Copyright (C) 1997-1999, 2002, 2006, 2009-2013 Free Software Foundation,
Inc.
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
/* Not copyrighted 1992 by Mark Adler
version c10p1, 10 January 1993 */
/* You can do whatever you like with this source file, though I would
prefer that if you modify it and redistribute it that you include
comments to that effect with your name and the date. Thank you.
[The history has been moved to the file ChangeLog.]
*/
/*
Inflate deflated (PKZIP's method 8 compressed) data. The compression
method searches for as much of the current string of bytes (up to a
length of 258) in the previous 32K bytes. If it doesn't find any
matches (of at least length 3), it codes the next byte. Otherwise, it
codes the length of the matched string and its distance backwards from
the current position. There is a single Huffman code that codes both
single bytes (called "literals") and match lengths. A second Huffman
code codes the distance information, which follows a length code. Each
length or distance code actually represents a base value and a number
of "extra" (sometimes zero) bits to get to add to the base value. At
the end of each deflated block is a special end-of-block (EOB) literal/
length code. The decoding process is basically: get a literal/length
code; if EOB then done; if a literal, emit the decoded byte; if a
length then get the distance and emit the referred-to bytes from the
sliding window of previously emitted data.
There are (currently) three kinds of inflate blocks: stored, fixed, and
dynamic. The compressor deals with some chunk of data at a time, and
decides which method to use on a chunk-by-chunk basis. A chunk might
typically be 32K or 64K. If the chunk is uncompressible, then the
"stored" method is used. In this case, the bytes are simply stored as
is, eight bits per byte, with none of the above coding. The bytes are
preceded by a count, since there is no longer an EOB code.
If the data is compressible, then either the fixed or dynamic methods
are used. In the dynamic method, the compressed data is preceded by
an encoding of the literal/length and distance Huffman codes that are
to be used to decode this block. The representation is itself Huffman
coded, and so is preceded by a description of that code. These code
descriptions take up a little space, and so for small blocks, there is
a predefined set of codes, called the fixed codes. The fixed method is
used if the block codes up smaller that way (usually for quite small
chunks), otherwise the dynamic method is used. In the latter case, the
codes are customized to the probabilities in the current block, and so
can code it much better than the pre-determined fixed codes.
The Huffman codes themselves are decoded using a multi-level table
lookup, in order to maximize the speed of decoding plus the speed of
building the decoding tables. See the comments below that precede the
lbits and dbits tuning parameters.
*/
/*
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. Similarly, 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.
*/
#include <config.h>
#include "tailor.h"
#include <stdlib.h>
#include "gzip.h"
#define slide window
/* Huffman code lookup table entry--this entry is four bytes for machines
that have 16-bit pointers (e.g. PC's in the small or medium model).
Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16
means that v is a literal, 16 < e < 32 means that v is a pointer to
the next table, which codes e - 16 bits, and lastly e == 99 indicates
an unused code. If a code with e == 99 is looked up, this implies an
error in the data. */
struct huft {
uch e; /* number of extra bits or operation */
uch b; /* number of bits in this code or subcode */
union {
ush n; /* literal, length base, or distance base */
struct huft *t; /* pointer to next level of table */
} v;
};
/* Function prototypes */
static int huft_free (struct huft *);
/* The inflate algorithm uses a sliding 32K byte window on the uncompressed
stream to find repeated byte strings. This is implemented here as a
circular buffer. The index is updated simply by incrementing and then
and'ing with 0x7fff (32K-1). */
/* It is left to other modules to supply the 32K area. It is assumed
to be usable as if it were declared "uch slide[32768];" or as just
"uch *slide;" and then malloc'ed in the latter case. The definition
must be in unzip.h, included above. */
/* unsigned wp; current position in slide */
#define wp outcnt
#define flush_output(w) (wp=(w),flush_window())
/* Tables for deflate from PKZIP's appnote.txt. */
static unsigned 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};
static ush cplens[] = { /* Copy lengths for literal codes 257..285 */
3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
/* note: see note #13 above about the 258 in this list. */
static ush cplext[] = { /* Extra bits for literal codes 257..285 */
0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2,
3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */
static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */
1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
8193, 12289, 16385, 24577};
static ush cpdext[] = { /* Extra bits for distance codes */
0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6,
7, 7, 8, 8, 9, 9, 10, 10, 11, 11,
12, 12, 13, 13};
/* Macros for inflate() bit peeking and grabbing.
The usage is:
NEEDBITS(j)
x = b & mask_bits[j];
DUMPBITS(j)
where NEEDBITS makes sure that b has at least j bits in it, and
DUMPBITS removes the bits from b. The macros use the variable k
for the number of bits in b. Normally, b and k are register
variables for speed, and are initialized at the beginning of a
routine that uses these macros from a global bit buffer and count.
The macros also use the variable w, which is a cached copy of wp.
If we assume that EOB will be the longest code, then we will never
ask for bits with NEEDBITS that are beyond the end of the stream.
So, NEEDBITS should not read any more bytes than are needed to
meet the request. Then no bytes need to be "returned" to the buffer
at the end of the last block.
However, this assumption is not true for fixed blocks--the EOB code
is 7 bits, but the other literal/length codes can be 8 or 9 bits.
(The EOB code is shorter than other codes because fixed blocks are
generally short. So, while a block always has an EOB, many other
literal/length codes have a significantly lower probability of
showing up at all.) However, by making the first table have a
lookup of seven bits, the EOB code will be found in that first
lookup, and so will not require that too many bits be pulled from
the stream.
*/
static ulg bb; /* bit buffer */
static unsigned bk; /* bits in bit buffer */
static ush mask_bits[] = {
0x0000,
0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff,
0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff
};
#define GETBYTE() (inptr < insize ? inbuf[inptr++] : (wp = w, fill_inbuf(0)))
#ifdef CRYPT
uch cc;
# define NEXTBYTE() \
(decrypt ? (cc = GETBYTE(), zdecode(cc), cc) : GETBYTE())
#else
# define NEXTBYTE() (uch)GETBYTE()
#endif
#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}}
#define DUMPBITS(n) {b>>=(n);k-=(n);}
/*
Huffman code decoding is performed using a multi-level table lookup.
The fastest way to decode is to simply build a lookup table whose
size is determined by the longest code. However, the time it takes
to build this table can also be a factor if the data being decoded
is not very long. The most common codes are necessarily the
shortest codes, so those codes dominate the decoding time, and hence
the speed. The idea is you can have a shorter table that decodes the
shorter, more probable codes, and then point to subsidiary tables for
the longer codes. The time it costs to decode the longer codes is
then traded against the time it takes to make longer tables.
This results of this trade are in the variables lbits and dbits
below. lbits is the number of bits the first level table for literal/
length codes can decode in one step, and dbits is the same thing for
the distance codes. Subsequent tables are also less than or equal to
those sizes. These values may be adjusted either when all of the
codes are shorter than that, in which case the longest code length in
bits is used, or when the shortest code is *longer* than the requested
table size, in which case the length of the shortest code in bits is
used.
There are two different values for the two tables, since they code a
different number of possibilities each. The literal/length table
codes 286 possible values, or in a flat code, a little over eight
bits. The distance table codes 30 possible values, or a little less
than five bits, flat. The optimum values for speed end up being
about one bit more than those, so lbits is 8+1 and dbits is 5+1.
The optimum values may differ though from machine to machine, and
possibly even between compilers. Your mileage may vary.
*/
static int lbits = 9; /* bits in base literal/length lookup table */
static int dbits = 6; /* bits in base distance lookup table */
/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */
#define BMAX 16 /* maximum bit length of any code (16 for explode) */
#define N_MAX 288 /* maximum number of codes in any set */
static unsigned hufts; /* track memory usage */
static int
huft_build(
unsigned *b, /* code lengths in bits (all assumed <= BMAX) */
unsigned n, /* number of codes (assumed <= N_MAX) */
unsigned s, /* number of simple-valued codes (0..s-1) */
ush *d, /* list of base values for non-simple codes */
ush *e, /* list of extra bits for non-simple codes */
struct huft **t, /* result: starting table */
int *m /* maximum lookup bits, returns actual */
)
/* Given a list of code lengths and a maximum table size, make a set of
tables to decode that set of codes. Return zero on success, one if
the given code set is incomplete (the tables are still built in this
case), two if the input is invalid (all zero length codes or an
oversubscribed set of lengths), and three if not enough memory. */
{
unsigned a; /* counter for codes of length k */
unsigned c[BMAX+1]; /* bit length count table */
unsigned f; /* i repeats in table every f entries */
int g; /* maximum code length */
int h; /* table level */
register unsigned i; /* counter, current code */
register unsigned j; /* counter */
register int k; /* number of bits in current code */
int l; /* bits per table (returned in m) */
register unsigned *p; /* pointer into c[], b[], or v[] */
register struct huft *q; /* points to current table */
struct huft r; /* table entry for structure assignment */
struct huft *u[BMAX]; /* table stack */
unsigned v[N_MAX]; /* values in order of bit length */
register int w; /* bits before this table == (l * h) */
unsigned x[BMAX+1]; /* bit offsets, then code stack */
unsigned *xp; /* pointer into x */
int y; /* number of dummy codes added */
unsigned z; /* number of entries in current table */
/* Generate counts for each bit length */
memzero(c, sizeof(c));
p = b; i = n;
do {
Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"),
n-i, *p));
c[*p]++; /* assume all entries <= BMAX */
p++; /* Can't combine with above line (Solaris bug) */
} while (--i);
if (c[0] == n) /* null input--all zero length codes */
{
q = (struct huft *) malloc (3 * sizeof *q);
if (!q)
return 3;
hufts += 3;
q[0].v.t = (struct huft *) NULL;
q[1].e = 99; /* invalid code marker */
q[1].b = 1;
q[2].e = 99; /* invalid code marker */
q[2].b = 1;
*t = q + 1;
*m = 1;
return 0;
}
/* Find minimum and maximum length, bound *m by those */
l = *m;
for (j = 1; j <= BMAX; j++)
if (c[j])
break;
k = j; /* minimum code length */
if ((unsigned)l < j)
l = j;
for (i = BMAX; i; i--)
if (c[i])
break;
g = i; /* maximum code length */
if ((unsigned)l > i)
l = i;
*m = l;
/* Adjust last length count to fill out codes, if needed */
for (y = 1 << j; j < i; j++, y <<= 1)
if ((y -= c[j]) < 0)
return 2; /* bad input: more codes than bits */
if ((y -= c[i]) < 0)
return 2;
c[i] += y;
/* Generate starting offsets into the value table for each length */
x[1] = j = 0;
p = c + 1; xp = x + 2;
while (--i) { /* note that i == g from above */
*xp++ = (j += *p++);
}
/* Make a table of values in order of bit lengths */
p = b; i = 0;
do {
if ((j = *p++) != 0)
v[x[j]++] = i;
} while (++i < n);
n = x[g]; /* set n to length of v */
/* Generate the Huffman codes and for each, make the table entries */
x[0] = i = 0; /* first Huffman code is zero */
p = v; /* grab values in bit order */
h = -1; /* no tables yet--level -1 */
w = -l; /* bits decoded == (l * h) */
u[0] = (struct huft *)NULL; /* just to keep compilers happy */
q = (struct huft *)NULL; /* ditto */
z = 0; /* ditto */
/* go through the bit lengths (k already is bits in shortest code) */
for (; k <= g; k++)
{
a = c[k];
while (a--)
{
/* here i is the Huffman code of length k bits for value *p */
/* make tables up to required level */
while (k > w + l)
{
h++;
w += l; /* previous table always l bits */
/* compute minimum size table less than or equal to l bits */
z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */
if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */
{ /* too few codes for k-w bit table */
f -= a + 1; /* deduct codes from patterns left */
xp = c + k;
if (j < z)
while (++j < z) /* try smaller tables up to z bits */
{
if ((f <<= 1) <= *++xp)
break; /* enough codes to use up j bits */
f -= *xp; /* else deduct codes from patterns */
}
}
z = 1 << j; /* table entries for j-bit table */
/* allocate and link in new table */
if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) ==
(struct huft *)NULL)
{
if (h)
huft_free(u[0]);
return 3; /* not enough memory */
}
hufts += z + 1; /* track memory usage */
*t = q + 1; /* link to list for huft_free() */
*(t = &(q->v.t)) = (struct huft *)NULL;
u[h] = ++q; /* table starts after link */
/* connect to last table, if there is one */
if (h)
{
x[h] = i; /* save pattern for backing up */
r.b = (uch)l; /* bits to dump before this table */
r.e = (uch)(16 + j); /* bits in this table */
r.v.t = q; /* pointer to this table */
j = i >> (w - l); /* (get around Turbo C bug) */
u[h-1][j] = r; /* connect to last table */
}
}
/* set up table entry in r */
r.b = (uch)(k - w);
if (p >= v + n)
r.e = 99; /* out of values--invalid code */
else if (*p < s)
{
r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */
r.v.n = (ush)(*p); /* simple code is just the value */
p++; /* one compiler does not like *p++ */
}
else
{
r.e = (uch)e[*p - s]; /* non-simple--look up in lists */
r.v.n = d[*p++ - s];
}
/* fill code-like entries with r */
f = 1 << (k - w);
for (j = i >> w; j < z; j += f)
q[j] = r;
/* backwards increment the k-bit code i */
for (j = 1 << (k - 1); i & j; j >>= 1)
i ^= j;
i ^= j;
/* backup over finished tables */
while ((i & ((1 << w) - 1)) != x[h])
{
h--; /* don't need to update q */
w -= l;
}
}
}
/* Return true (1) if we were given an incomplete table */
return y != 0 && g != 1;
}
/* Free the malloc'ed tables T built by huft_build(), which makes a linked
list of the tables it made, with the links in a dummy first entry of
each table. */
static int
huft_free(struct huft *t)
{
register struct huft *p, *q;
/* Go through linked list, freeing from the malloced (t[-1]) address. */
p = t;
while (p != (struct huft *)NULL)
{
q = (--p)->v.t;
free(p);
p = q;
}
return 0;
}
/* tl, td: literal/length and distance decoder tables */
/* bl, bd: number of bits decoded by tl[] and td[] */
/* inflate (decompress) the codes in a deflated (compressed) block.
Return an error code or zero if it all goes ok. */
static int
inflate_codes(struct huft *tl, struct huft *td, int bl, int bd)
{
register unsigned e; /* table entry flag/number of extra bits */
unsigned n, d; /* length and index for copy */
unsigned w; /* current window position */
struct huft *t; /* pointer to table entry */
unsigned ml, md; /* masks for bl and bd bits */
register ulg b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
/* make local copies of globals */
b = bb; /* initialize bit buffer */
k = bk;
w = wp; /* initialize window position */
/* inflate the coded data */
ml = mask_bits[bl]; /* precompute masks for speed */
md = mask_bits[bd];
for (;;) /* do until end of block */
{
NEEDBITS((unsigned)bl)
if ((e = (t = tl + ((unsigned)b & ml))->e) > 16)
do {
if (e == 99)
return 1;
DUMPBITS(t->b)
e -= 16;
NEEDBITS(e)
} while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
DUMPBITS(t->b)
if (e == 16) /* then it's a literal */
{
slide[w++] = (uch)t->v.n;
Tracevv((stderr, "%c", slide[w-1]));
if (w == WSIZE)
{
flush_output(w);
w = 0;
}
}
else /* it's an EOB or a length */
{
/* exit if end of block */
if (e == 15)
break;
/* get length of block to copy */
NEEDBITS(e)
n = t->v.n + ((unsigned)b & mask_bits[e]);
DUMPBITS(e);
/* decode distance of block to copy */
NEEDBITS((unsigned)bd)
if ((e = (t = td + ((unsigned)b & md))->e) > 16)
do {
if (e == 99)
return 1;
DUMPBITS(t->b)
e -= 16;
NEEDBITS(e)
} while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16);
DUMPBITS(t->b)
NEEDBITS(e)
d = w - t->v.n - ((unsigned)b & mask_bits[e]);
DUMPBITS(e)
Tracevv((stderr,"\\[%d,%d]", w-d, n));
/* do the copy */
do {
n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e);
#ifndef DEBUG
if (e <= (d < w ? w - d : d - w))
{
memcpy(slide + w, slide + d, e);
w += e;
d += e;
}
else /* do it slow to avoid memcpy() overlap */
#endif
do {
slide[w++] = slide[d++];
Tracevv((stderr, "%c", slide[w-1]));
} while (--e);
if (w == WSIZE)
{
flush_output(w);
w = 0;
}
} while (n);
}
}
/* restore the globals from the locals */
wp = w; /* restore global window pointer */
bb = b; /* restore global bit buffer */
bk = k;
/* done */
return 0;
}
/* "decompress" an inflated type 0 (stored) block. */
static int
inflate_stored(void)
{
unsigned n; /* number of bytes in block */
unsigned w; /* current window position */
register ulg b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
/* make local copies of globals */
b = bb; /* initialize bit buffer */
k = bk;
w = wp; /* initialize window position */
/* go to byte boundary */
n = k & 7;
DUMPBITS(n);
/* get the length and its complement */
NEEDBITS(16)
n = ((unsigned)b & 0xffff);
DUMPBITS(16)
NEEDBITS(16)
if (n != (unsigned)((~b) & 0xffff))
return 1; /* error in compressed data */
DUMPBITS(16)
/* read and output the compressed data */
while (n--)
{
NEEDBITS(8)
slide[w++] = (uch)b;
if (w == WSIZE)
{
flush_output(w);
w = 0;
}
DUMPBITS(8)
}
/* restore the globals from the locals */
wp = w; /* restore global window pointer */
bb = b; /* restore global bit buffer */
bk = k;
return 0;
}
/* decompress an inflated type 1 (fixed Huffman codes) block. We should
either replace this with a custom decoder, or at least precompute the
Huffman tables. */
static int
inflate_fixed(void)
{
int i; /* temporary variable */
struct huft *tl; /* literal/length code table */
struct huft *td; /* distance code table */
int bl; /* lookup bits for tl */
int bd; /* lookup bits for td */
unsigned l[288]; /* length list for huft_build */
/* set up literal table */
for (i = 0; i < 144; i++)
l[i] = 8;
for (; i < 256; i++)
l[i] = 9;
for (; i < 280; i++)
l[i] = 7;
for (; i < 288; i++) /* make a complete, but wrong code set */
l[i] = 8;
bl = 7;
if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0)
return i;
/* set up distance table */
for (i = 0; i < 30; i++) /* make an incomplete code set */
l[i] = 5;
bd = 5;
if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1)
{
huft_free(tl);
return i;
}
/* decompress until an end-of-block code */
if (inflate_codes(tl, td, bl, bd))
return 1;
/* free the decoding tables, return */
huft_free(tl);
huft_free(td);
return 0;
}
/* decompress an inflated type 2 (dynamic Huffman codes) block. */
static int
inflate_dynamic(void)
{
int i; /* temporary variables */
unsigned j;
unsigned l; /* last length */
unsigned m; /* mask for bit lengths table */
unsigned n; /* number of lengths to get */
unsigned w; /* current window position */
struct huft *tl; /* literal/length code table */
struct huft *td; /* distance code table */
int bl; /* lookup bits for tl */
int bd; /* lookup bits for td */
unsigned nb; /* number of bit length codes */
unsigned nl; /* number of literal/length codes */
unsigned nd; /* number of distance codes */
#ifdef PKZIP_BUG_WORKAROUND
unsigned ll[288+32]; /* literal/length and distance code lengths */
#else
unsigned ll[286+30]; /* literal/length and distance code lengths */
#endif
register ulg b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
/* make local bit buffer */
b = bb;
k = bk;
w = wp;
/* read in table lengths */
NEEDBITS(5)
nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */
DUMPBITS(5)
NEEDBITS(5)
nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */
DUMPBITS(5)
NEEDBITS(4)
nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */
DUMPBITS(4)
#ifdef PKZIP_BUG_WORKAROUND
if (nl > 288 || nd > 32)
#else
if (nl > 286 || nd > 30)
#endif
return 1; /* bad lengths */
/* read in bit-length-code lengths */
for (j = 0; j < nb; j++)
{
NEEDBITS(3)
ll[border[j]] = (unsigned)b & 7;
DUMPBITS(3)
}
for (; j < 19; j++)
ll[border[j]] = 0;
/* build decoding table for trees--single level, 7 bit lookup */
bl = 7;
if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0)
{
if (i == 1)
huft_free(tl);
return i; /* incomplete code set */
}
if (tl == NULL) /* Grrrhhh */
return 2;
/* read in literal and distance code lengths */
n = nl + nd;
m = mask_bits[bl];
i = l = 0;
while ((unsigned)i < n)
{
NEEDBITS((unsigned)bl)
j = (td = tl + ((unsigned)b & m))->b;
DUMPBITS(j)
j = td->v.n;
if (j < 16) /* length of code in bits (0..15) */
ll[i++] = l = j; /* save last length in l */
else if (j == 16) /* repeat last length 3 to 6 times */
{
NEEDBITS(2)
j = 3 + ((unsigned)b & 3);
DUMPBITS(2)
if ((unsigned)i + j > n)
return 1;
while (j--)
ll[i++] = l;
}
else if (j == 17) /* 3 to 10 zero length codes */
{
NEEDBITS(3)
j = 3 + ((unsigned)b & 7);
DUMPBITS(3)
if ((unsigned)i + j > n)
return 1;
while (j--)
ll[i++] = 0;
l = 0;
}
else /* j == 18: 11 to 138 zero length codes */
{
NEEDBITS(7)
j = 11 + ((unsigned)b & 0x7f);
DUMPBITS(7)
if ((unsigned)i + j > n)
return 1;
while (j--)
ll[i++] = 0;
l = 0;
}
}
/* free decoding table for trees */
huft_free(tl);
/* restore the global bit buffer */
bb = b;
bk = k;
/* build the decoding tables for literal/length and distance codes */
bl = lbits;
if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0)
{
if (i == 1) {
Trace ((stderr, " incomplete literal tree\n"));
huft_free(tl);
}
return i; /* incomplete code set */
}
bd = dbits;
if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0)
{
if (i == 1) {
Trace ((stderr, " incomplete distance tree\n"));
#ifdef PKZIP_BUG_WORKAROUND
i = 0;
}
#else
huft_free(td);
}
huft_free(tl);
return i; /* incomplete code set */
#endif
}
{
/* decompress until an end-of-block code */
int err = inflate_codes(tl, td, bl, bd) ? 1 : 0;
/* free the decoding tables */
huft_free(tl);
huft_free(td);
return err;
}
}
/* decompress an inflated block */
/* E is the last block flag */
static int inflate_block(int *e)
{
unsigned t; /* block type */
unsigned w; /* current window position */
register ulg b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
/* make local bit buffer */
b = bb;
k = bk;
w = wp;
/* read in last block bit */
NEEDBITS(1)
*e = (int)b & 1;
DUMPBITS(1)
/* read in block type */
NEEDBITS(2)
t = (unsigned)b & 3;
DUMPBITS(2)
/* restore the global bit buffer */
bb = b;
bk = k;
/* inflate that block type */
if (t == 2)
return inflate_dynamic();
if (t == 0)
return inflate_stored();
if (t == 1)
return inflate_fixed();
/* bad block type */
return 2;
}
int
inflate(void)
/* decompress an inflated entry */
{
int e; /* last block flag */
int r; /* result code */
unsigned h; /* maximum struct huft's malloc'ed */
/* initialize window, bit buffer */
wp = 0;
bk = 0;
bb = 0;
/* decompress until the last block */
h = 0;
do {
hufts = 0;
if ((r = inflate_block(&e)) != 0)
return r;
if (hufts > h)
h = hufts;
} while (!e);
/* Undo too much lookahead. The next read will be byte aligned so we
* can discard unused bits in the last meaningful byte.
*/
while (bk >= 8) {
bk -= 8;
inptr--;
}
/* flush out slide */
flush_output(wp);
/* return success */
Trace ((stderr, "<%u> ", h));
return 0;
}
|