| 1 | /*
|
|---|
| 2 | * Copyright (c) 2000-2005 Marc Alexander Lehmann <[email protected]>
|
|---|
| 3 | *
|
|---|
| 4 | * Redistribution and use in source and binary forms, with or without modifica-
|
|---|
| 5 | * tion, are permitted provided that the following conditions are met:
|
|---|
| 6 | *
|
|---|
| 7 | * 1. Redistributions of source code must retain the above copyright notice,
|
|---|
| 8 | * this list of conditions and the following disclaimer.
|
|---|
| 9 | *
|
|---|
| 10 | * 2. Redistributions in binary form must reproduce the above copyright
|
|---|
| 11 | * notice, this list of conditions and the following disclaimer in the
|
|---|
| 12 | * documentation and/or other materials provided with the distribution.
|
|---|
| 13 | *
|
|---|
| 14 | * 3. The name of the author may not be used to endorse or promote products
|
|---|
| 15 | * derived from this software without specific prior written permission.
|
|---|
| 16 | *
|
|---|
| 17 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
|---|
| 18 | * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MER-
|
|---|
| 19 | * CHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
|---|
| 20 | * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPE-
|
|---|
| 21 | * CIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|---|
| 22 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
|
|---|
| 23 | * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
|
|---|
| 24 | * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTH-
|
|---|
| 25 | * ERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
|---|
| 26 | * OF THE POSSIBILITY OF SUCH DAMAGE.
|
|---|
| 27 | *
|
|---|
| 28 | * Alternatively, the contents of this file may be used under the terms of
|
|---|
| 29 | * the GNU General Public License version 2 (the "GPL"), in which case the
|
|---|
| 30 | * provisions of the GPL are applicable instead of the above. If you wish to
|
|---|
| 31 | * allow the use of your version of this file only under the terms of the
|
|---|
| 32 | * GPL and not to allow others to use your version of this file under the
|
|---|
| 33 | * BSD license, indicate your decision by deleting the provisions above and
|
|---|
| 34 | * replace them with the notice and other provisions required by the GPL. If
|
|---|
| 35 | * you do not delete the provisions above, a recipient may use your version
|
|---|
| 36 | * of this file under either the BSD or the GPL.
|
|---|
| 37 | */
|
|---|
| 38 |
|
|---|
| 39 | #include "lzfP.h"
|
|---|
| 40 | #ifdef VBOX
|
|---|
| 41 | #include "lzf.h"
|
|---|
| 42 | #endif
|
|---|
| 43 |
|
|---|
| 44 | #define HSIZE (1 << (HLOG))
|
|---|
| 45 |
|
|---|
| 46 | /*
|
|---|
| 47 | * don't play with this unless you benchmark!
|
|---|
| 48 | * decompression is not dependent on the hash function
|
|---|
| 49 | * the hashing function might seem strange, just believe me
|
|---|
| 50 | * it works ;)
|
|---|
| 51 | */
|
|---|
| 52 | #ifndef FRST
|
|---|
| 53 | # define FRST(p) (((p[0]) << 8) | p[1])
|
|---|
| 54 | # define NEXT(v,p) (((v) << 8) | p[2])
|
|---|
| 55 | # define IDX(h) ((((h ^ (h << 5)) >> (3*8 - HLOG)) - h*5) & (HSIZE - 1))
|
|---|
| 56 | #endif
|
|---|
| 57 | /*
|
|---|
| 58 | * IDX works because it is very similar to a multiplicative hash, e.g.
|
|---|
| 59 | * ((h * 57321 >> (3*8 - HLOG)) & (HSIZE - 1))
|
|---|
| 60 | * the latter is also quite fast on newer CPUs, and sligthly better
|
|---|
| 61 | *
|
|---|
| 62 | * the next one is also quite good, albeit slow ;)
|
|---|
| 63 | * (int)(cos(h & 0xffffff) * 1e6)
|
|---|
| 64 | */
|
|---|
| 65 |
|
|---|
| 66 | #if 0
|
|---|
| 67 | /* original lzv-like hash function, much worse and thus slower */
|
|---|
| 68 | # define FRST(p) (p[0] << 5) ^ p[1]
|
|---|
| 69 | # define NEXT(v,p) ((v) << 5) ^ p[2]
|
|---|
| 70 | # define IDX(h) ((h) & (HSIZE - 1))
|
|---|
| 71 | #endif
|
|---|
| 72 |
|
|---|
| 73 | #define MAX_LIT (1 << 5)
|
|---|
| 74 | #define MAX_OFF (1 << 13)
|
|---|
| 75 | #define MAX_REF ((1 << 8) + (1 << 3))
|
|---|
| 76 |
|
|---|
| 77 | /*
|
|---|
| 78 | * compressed format
|
|---|
| 79 | *
|
|---|
| 80 | * 000LLLLL <L+1> ; literal
|
|---|
| 81 | * LLLooooo oooooooo ; backref L
|
|---|
| 82 | * 111ooooo LLLLLLLL oooooooo ; backref L+7
|
|---|
| 83 | *
|
|---|
| 84 | */
|
|---|
| 85 |
|
|---|
| 86 | unsigned int
|
|---|
| 87 | lzf_compress (const void *const in_data, unsigned int in_len,
|
|---|
| 88 | void *out_data, unsigned int out_len
|
|---|
| 89 | #if LZF_STATE_ARG
|
|---|
| 90 | , LZF_STATE *htab
|
|---|
| 91 | #endif
|
|---|
| 92 | )
|
|---|
| 93 | {
|
|---|
| 94 | #if !LZF_STATE_ARG
|
|---|
| 95 | LZF_STATE htab;
|
|---|
| 96 | #endif
|
|---|
| 97 | const u8 **hslot;
|
|---|
| 98 | const u8 *ip = (const u8 *)in_data;
|
|---|
| 99 | u8 *op = (u8 *)out_data;
|
|---|
| 100 | const u8 *in_end = ip + in_len;
|
|---|
| 101 | u8 *out_end = op + out_len;
|
|---|
| 102 | const u8 *ref;
|
|---|
| 103 |
|
|---|
| 104 | unsigned int hval = FRST (ip);
|
|---|
| 105 | unsigned long off;
|
|---|
| 106 | int lit = 0;
|
|---|
| 107 |
|
|---|
| 108 | #if INIT_HTAB
|
|---|
| 109 | # if USE_MEMCPY
|
|---|
| 110 | memset (htab, 0, sizeof (htab));
|
|---|
| 111 | # else
|
|---|
| 112 | for (hslot = htab; hslot < htab + HSIZE; hslot++)
|
|---|
| 113 | *hslot++ = ip;
|
|---|
| 114 | # endif
|
|---|
| 115 | #endif
|
|---|
| 116 |
|
|---|
| 117 | for (;;)
|
|---|
| 118 | {
|
|---|
| 119 | if (ip < in_end - 2)
|
|---|
| 120 | {
|
|---|
| 121 | hval = NEXT (hval, ip);
|
|---|
| 122 | hslot = htab + IDX (hval);
|
|---|
| 123 | ref = *hslot; *hslot = ip;
|
|---|
| 124 |
|
|---|
| 125 | if (1
|
|---|
| 126 | #if INIT_HTAB && !USE_MEMCPY
|
|---|
| 127 | && ref < ip /* the next test will actually take care of this, but this is faster */
|
|---|
| 128 | #endif
|
|---|
| 129 | && (off = ip - ref - 1) < MAX_OFF
|
|---|
| 130 | && ip + 4 < in_end
|
|---|
| 131 | && ref > (u8 *)in_data
|
|---|
| 132 | #if STRICT_ALIGN
|
|---|
| 133 | && ref[0] == ip[0]
|
|---|
| 134 | && ref[1] == ip[1]
|
|---|
| 135 | && ref[2] == ip[2]
|
|---|
| 136 | #else
|
|---|
| 137 | && *(u16 *)ref == *(u16 *)ip
|
|---|
| 138 | && ref[2] == ip[2]
|
|---|
| 139 | #endif
|
|---|
| 140 | )
|
|---|
| 141 | {
|
|---|
| 142 | /* match found at *ref++ */
|
|---|
| 143 | unsigned int len = 2;
|
|---|
| 144 | unsigned int maxlen = in_end - ip - len;
|
|---|
| 145 | maxlen = maxlen > MAX_REF ? MAX_REF : maxlen;
|
|---|
| 146 |
|
|---|
| 147 | if (op + lit + 1 + 3 >= out_end)
|
|---|
| 148 | return 0;
|
|---|
| 149 |
|
|---|
| 150 | do
|
|---|
| 151 | len++;
|
|---|
| 152 | while (len < maxlen && ref[len] == ip[len]);
|
|---|
| 153 |
|
|---|
| 154 | if (lit)
|
|---|
| 155 | {
|
|---|
| 156 | *op++ = lit - 1;
|
|---|
| 157 | lit = -lit;
|
|---|
| 158 | do
|
|---|
| 159 | *op++ = ip[lit];
|
|---|
| 160 | while (++lit);
|
|---|
| 161 | }
|
|---|
| 162 |
|
|---|
| 163 | len -= 2;
|
|---|
| 164 | ip++;
|
|---|
| 165 |
|
|---|
| 166 | if (len < 7)
|
|---|
| 167 | {
|
|---|
| 168 | *op++ = (off >> 8) + (len << 5);
|
|---|
| 169 | }
|
|---|
| 170 | else
|
|---|
| 171 | {
|
|---|
| 172 | *op++ = (off >> 8) + ( 7 << 5);
|
|---|
| 173 | *op++ = len - 7;
|
|---|
| 174 | }
|
|---|
| 175 |
|
|---|
| 176 | *op++ = off;
|
|---|
| 177 |
|
|---|
| 178 | #if ULTRA_FAST || VERY_FAST
|
|---|
| 179 | ip += len;
|
|---|
| 180 | #if VERY_FAST && !ULTRA_FAST
|
|---|
| 181 | --ip;
|
|---|
| 182 | #endif
|
|---|
| 183 | hval = FRST (ip);
|
|---|
| 184 |
|
|---|
| 185 | hval = NEXT (hval, ip);
|
|---|
| 186 | htab[IDX (hval)] = ip;
|
|---|
| 187 | ip++;
|
|---|
| 188 |
|
|---|
| 189 | #if VERY_FAST && !ULTRA_FAST
|
|---|
| 190 | hval = NEXT (hval, ip);
|
|---|
| 191 | htab[IDX (hval)] = ip;
|
|---|
| 192 | ip++;
|
|---|
| 193 | #endif
|
|---|
| 194 | #else
|
|---|
| 195 | do
|
|---|
| 196 | {
|
|---|
| 197 | hval = NEXT (hval, ip);
|
|---|
| 198 | htab[IDX (hval)] = ip;
|
|---|
| 199 | ip++;
|
|---|
| 200 | }
|
|---|
| 201 | while (len--);
|
|---|
| 202 | #endif
|
|---|
| 203 | continue;
|
|---|
| 204 | }
|
|---|
| 205 | }
|
|---|
| 206 | else if (ip == in_end)
|
|---|
| 207 | break;
|
|---|
| 208 |
|
|---|
| 209 | /* one more literal byte we must copy */
|
|---|
| 210 | lit++;
|
|---|
| 211 | ip++;
|
|---|
| 212 |
|
|---|
| 213 | if (lit == MAX_LIT)
|
|---|
| 214 | {
|
|---|
| 215 | if (op + 1 + MAX_LIT >= out_end)
|
|---|
| 216 | return 0;
|
|---|
| 217 |
|
|---|
| 218 | *op++ = MAX_LIT - 1;
|
|---|
| 219 | #if USE_MEMCPY
|
|---|
| 220 | memcpy (op, ip - MAX_LIT, MAX_LIT);
|
|---|
| 221 | op += MAX_LIT;
|
|---|
| 222 | lit = 0;
|
|---|
| 223 | #else
|
|---|
| 224 | lit = -lit;
|
|---|
| 225 | do
|
|---|
| 226 | *op++ = ip[lit];
|
|---|
| 227 | while (++lit);
|
|---|
| 228 | #endif
|
|---|
| 229 | }
|
|---|
| 230 | }
|
|---|
| 231 |
|
|---|
| 232 | if (lit)
|
|---|
| 233 | {
|
|---|
| 234 | if (op + lit + 1 >= out_end)
|
|---|
| 235 | return 0;
|
|---|
| 236 |
|
|---|
| 237 | *op++ = lit - 1;
|
|---|
| 238 | lit = -lit;
|
|---|
| 239 | do
|
|---|
| 240 | *op++ = ip[lit];
|
|---|
| 241 | while (++lit);
|
|---|
| 242 | }
|
|---|
| 243 |
|
|---|
| 244 | return op - (u8 *) out_data;
|
|---|
| 245 | }
|
|---|
