📄 explode.c
字号:
/* explode.c -- Not copyrighted 1992 by Mark Adler
version c7, 27 June 1992 */
/* 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.
History:
vers date who what
---- --------- -------------- ------------------------------------
c1 30 Mar 92 M. Adler explode that uses huft_build from inflate
(this gives over a 70% speed improvement
over the original unimplode.c, which
decoded a bit at a time)
c2 4 Apr 92 M. Adler fixed bug for file sizes a multiple of 32k.
c3 10 Apr 92 M. Adler added a little memory tracking if DEBUG
c4 11 Apr 92 M. Adler added NOMEMCPY do kill use of memcpy()
c5 21 Apr 92 M. Adler added the WSIZE #define to allow reducing
the 32K window size for specialized
applications.
c6 31 May 92 M. Adler added typecasts to eliminate some warnings
c7 27 Jun 92 G. Roelofs added more typecasts
*/
/*
Explode imploded (PKZIP method 6 compressed) data. This compression
method searches for as much of the current string of bytes (up to a length
of ~320) in the previous 4K or 8K bytes. If it doesn't find any matches
(of at least length 2 or 3), it codes the next byte. Otherwise, it codes
the length of the matched string and its distance backwards from the
current position. Single bytes ("literals") are preceded by a one (a
single bit) and are either uncoded (the eight bits go directly into the
compressed stream for a total of nine bits) or Huffman coded with a
supplied literal code tree. If literals are coded, then the minimum match
length is three, otherwise it is two.
There are therefore four kinds of imploded streams: 8K search with coded
literals (min match = 3), 4K search with coded literals (min match = 3),
8K with uncoded literals (min match = 2), and 4K with uncoded literals
(min match = 2). The kind of stream is identified in two bits of a
general purpose bit flag that is outside of the compressed stream.
Distance-length pairs are always coded. Distance-length pairs for matched
strings are preceded by a zero bit (to distinguish them from literals) and
are always coded. The distance comes first and is either the low six (4K)
or low seven (8K) bits of the distance (uncoded), followed by the high six
bits of the distance coded. Then the length is six bits coded (0..63 +
min match length), and if the maximum such length is coded, then it's
followed by another eight bits (uncoded) to be added to the coded length.
This gives a match length range of 2..320 or 3..321 bytes.
The literal, length, and distance codes are all represented in a slightly
compressed form themselves. What is sent are the lengths of the codes for
each value, which is sufficient to construct the codes. Each byte of the
code representation is the code length (the low four bits representing
1..16), and the number of values sequentially with that length (the high
four bits also representing 1..16). There are 256 literal code values (if
literals are coded), 64 length code values, and 64 distance code values,
in that order at the beginning of the compressed stream. Each set of code
values is preceded (redundantly) with a byte indicating how many bytes are
in the code description that follows, in the range 1..256.
The codes themselves are decoded using tables made by huft_build() from
the bit lengths. That routine and its comments are in the inflate.c
module.
*/
#include "unzip.h" /* this must supply the slide[] (byte) array */
#ifndef WSIZE
# define WSIZE 0x8000 /* window size--must be a power of two, and at least
8K for zip's implode method */
#endif /* !WSIZE */
struct huft {
byte e; /* number of extra bits or operation */
byte b; /* number of bits in this code or subcode */
union {
UWORD n; /* literal, length base, or distance base */
struct huft *t; /* pointer to next level of table */
} v;
};
/* Function prototypes */
/* routines from inflate.c */
extern unsigned hufts;
int huft_build OF((unsigned *, unsigned, unsigned, UWORD *, UWORD *,
struct huft **, int *));
int huft_free OF((struct huft *));
void flush OF((unsigned));
/* routines here */
int get_tree OF((unsigned *, unsigned));
int explode_lit8 OF((struct huft *, struct huft *, struct huft *,
int, int, int));
int explode_lit4 OF((struct huft *, struct huft *, struct huft *,
int, int, int));
int explode_nolit8 OF((struct huft *, struct huft *, int, int));
int explode_nolit4 OF((struct huft *, struct huft *, int, int));
int explode OF((void));
/* The implode algorithm uses a sliding 4K or 8K 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 0x0fff (4K-1) or 0x1fff (8K-1). Here, the 32K
buffer of inflate is used, and it works just as well to always have
a 32K circular buffer, so the index is anded with 0x7fff. This is
done to allow the window to also be used as the output buffer. */
/* This must be supplied in an external module useable like "byte slide[8192];"
or "byte *slide;", where the latter would be malloc'ed. In unzip, slide[]
is actually a 32K area for use by inflate, which uses a 32K sliding window.
*/
/* Tables for length and distance */
UWORD cplen2[] = {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};
UWORD cplen3[] = {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};
UWORD extra[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
8};
UWORD cpdist4[] = {1, 65, 129, 193, 257, 321, 385, 449, 513, 577, 641, 705,
769, 833, 897, 961, 1025, 1089, 1153, 1217, 1281, 1345, 1409, 1473,
1537, 1601, 1665, 1729, 1793, 1857, 1921, 1985, 2049, 2113, 2177,
2241, 2305, 2369, 2433, 2497, 2561, 2625, 2689, 2753, 2817, 2881,
2945, 3009, 3073, 3137, 3201, 3265, 3329, 3393, 3457, 3521, 3585,
3649, 3713, 3777, 3841, 3905, 3969, 4033};
UWORD cpdist8[] = {1, 129, 257, 385, 513, 641, 769, 897, 1025, 1153, 1281,
1409, 1537, 1665, 1793, 1921, 2049, 2177, 2305, 2433, 2561, 2689,
2817, 2945, 3073, 3201, 3329, 3457, 3585, 3713, 3841, 3969, 4097,
4225, 4353, 4481, 4609, 4737, 4865, 4993, 5121, 5249, 5377, 5505,
5633, 5761, 5889, 6017, 6145, 6273, 6401, 6529, 6657, 6785, 6913,
7041, 7169, 7297, 7425, 7553, 7681, 7809, 7937, 8065};
/* 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.
*/
extern UWORD bytebuf; /* (use the one in inflate.c) */
#define NEXTBYTE (ReadByte(&bytebuf), bytebuf)
#define NEEDBITS(n) {while(k<(n)){b|=((ULONG)NEXTBYTE)<<k;k+=8;}}
#define DUMPBITS(n) {b>>=(n);k-=(n);}
int get_tree(l, n)
unsigned *l; /* bit lengths */
unsigned n; /* number expected */
/* Get the bit lengths for a code representation from the compressed
stream. If get_tree() returns 4, then there is an error in the data.
Otherwise zero is returned. */
{
unsigned i; /* bytes remaining in list */
unsigned k; /* lengths entered */
unsigned j; /* number of codes */
unsigned b; /* bit length for those codes */
/* get bit lengths */
ReadByte(&bytebuf);
i = bytebuf + 1; /* length/count pairs to read */
k = 0; /* next code */
do {
ReadByte(&bytebuf);
b = ((j = bytebuf) & 0xf) + 1; /* bits in code (1..16) */
j = ((j & 0xf0) >> 4) + 1; /* codes with those bits (1..16) */
if (k + j > n)
return 4; /* don't overflow l[] */
do {
l[k++] = b;
} while (--j);
} while (--i);
return k != n ? 4 : 0; /* should have read n of them */
}
int explode_lit8(tb, tl, td, bb, bl, bd)
struct huft *tb, *tl, *td; /* literal, length, and distance tables */
int bb, bl, bd; /* number of bits decoded by those */
/* Decompress the imploded data using coded literals and an 8K sliding
window. */
{
longint s; /* bytes to decompress */
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 mb, ml, md; /* masks for bb, bl, and bd bits */
register ULONG b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
unsigned u; /* true if unflushed */
/* explode the coded data */
b = k = w = 0; /* initialize bit buffer, window */
u = 1; /* buffer unflushed */
mb = mask_bits[bb]; /* precompute masks for speed */
ml = mask_bits[bl];
md = mask_bits[bd];
s = ucsize;
while (s > 0) /* do until ucsize bytes uncompressed */
{
NEEDBITS(1)
if (b & 1) /* then literal--decode it */
{
DUMPBITS(1)
s--;
NEEDBITS((unsigned)bb) /* get coded literal */
if ((e = (t = tb + ((~(unsigned)b) & mb))->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)
slide[w++] = (byte)t->v.n;
if (w == WSIZE)
{
flush(w);
w = u = 0;
}
}
else /* else distance/length */
{
DUMPBITS(1)
NEEDBITS(7) /* get distance low bits */
d = (unsigned)b & 0x7f;
DUMPBITS(7)
NEEDBITS((unsigned)bd) /* get coded distance high bits */
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)
d = w - d - t->v.n; /* construct offset */
NEEDBITS((unsigned)bl) /* get coded length */
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)
n = t->v.n;
if (e) /* get length extra bits */
{
NEEDBITS(8)
n += (unsigned)b & 0xff;
DUMPBITS(8)
}
/* do the copy */
s -= n;
do {
n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e);
if (u && w <= d)
{
memset(slide + w, 0, e);
w += e;
d += e;
}
else
#ifndef NOMEMCPY
if (w - d >= e) /* (this test assumes unsigned comparison) */
{
memcpy(slide + w, slide + d, e);
w += e;
d += e;
}
else /* do it slow to avoid memcpy() overlap */
#endif /* !NOMEMCPY */
do {
slide[w++] = slide[d++];
} while (--e);
if (w == WSIZE)
{
flush(w);
w = u = 0;
}
} while (n);
}
}
/* flush out slide */
flush(w);
return csize ? 5 : 0; /* should have read csize bytes */
}
int explode_lit4(tb, tl, td, bb, bl, bd)
struct huft *tb, *tl, *td; /* literal, length, and distance tables */
int bb, bl, bd; /* number of bits decoded by those */
/* Decompress the imploded data using coded literals and a 4K sliding
window. */
{
longint s; /* bytes to decompress */
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 mb, ml, md; /* masks for bb, bl, and bd bits */
register ULONG b; /* bit buffer */
register unsigned k; /* number of bits in bit buffer */
unsigned u; /* true if unflushed */
/* explode the coded data */
b = k = w = 0; /* initialize bit buffer, window */
u = 1; /* buffer unflushed */
mb = mask_bits[bb]; /* precompute masks for speed */
ml = mask_bits[bl];
md = mask_bits[bd];
s = ucsize;
while (s > 0) /* do until ucsize bytes uncompressed */
{
NEEDBITS(1)
if (b & 1) /* then literal--decode it */
{
DUMPBITS(1)
s--;
NEEDBITS((unsigned)bb) /* get coded literal */
if ((e = (t = tb + ((~(unsigned)b) & mb))->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)
slide[w++] = (byte)t->v.n;
if (w == WSIZE)
{
flush(w);
w = u = 0;
}
}
else /* else distance/length */
{
DUMPBITS(1)
NEEDBITS(6) /* get distance low bits */
d = (unsigned)b & 0x3f;
DUMPBITS(6)
NEEDBITS((unsigned)bd) /* get coded distance high bits */
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)
d = w - d - t->v.n; /* construct offset */
NEEDBITS((unsigned)bl) /* get coded length */
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)
n = t->v.n;
if (e) /* get length extra bits */
{
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -