| 1 | /*
|
|---|
| 2 | * Copyright (c) 2000-2005 Marc Alexander Lehmann <schmorp@schmorp.de>
|
|---|
| 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 | #ifdef USE_UINTPTR_T /* bird: use intptr_t for pointer acrobatics on 64-bit windows. */
|
|---|
| 44 | # if defined(_MSC_VER)
|
|---|
| 45 | # include <crtdefs.h>
|
|---|
| 46 | # else
|
|---|
| 47 | # include <stdint.h>
|
|---|
| 48 | # endif
|
|---|
| 49 | #endif
|
|---|
| 50 |
|
|---|
| 51 | #define HSIZE (1 << (HLOG))
|
|---|
| 52 |
|
|---|
| 53 | /*
|
|---|
| 54 | * don't play with this unless you benchmark!
|
|---|
| 55 | * decompression is not dependent on the hash function
|
|---|
| 56 | * the hashing function might seem strange, just believe me
|
|---|
| 57 | * it works ;)
|
|---|
| 58 | */
|
|---|
| 59 | #ifndef FRST
|
|---|
| 60 | # define FRST(p) (((p[0]) << 8) | p[1])
|
|---|
| 61 | # define NEXT(v,p) (((v) << 8) | p[2])
|
|---|
| 62 | # define IDX(h) ((((h ^ (h << 5)) >> (3*8 - HLOG)) - h*5) & (HSIZE - 1))
|
|---|
| 63 | #endif
|
|---|
| 64 | /*
|
|---|
| 65 | * IDX works because it is very similar to a multiplicative hash, e.g.
|
|---|
| 66 | * ((h * 57321 >> (3*8 - HLOG)) & (HSIZE - 1))
|
|---|
| 67 | * the latter is also quite fast on newer CPUs, and sligthly better
|
|---|
| 68 | *
|
|---|
| 69 | * the next one is also quite good, albeit slow ;)
|
|---|
| 70 | * (int)(cos(h & 0xffffff) * 1e6)
|
|---|
| 71 | */
|
|---|
| 72 |
|
|---|
| 73 | #if 0
|
|---|
| 74 | /* original lzv-like hash function, much worse and thus slower */
|
|---|
| 75 | # define FRST(p) (p[0] << 5) ^ p[1]
|
|---|
| 76 | # define NEXT(v,p) ((v) << 5) ^ p[2]
|
|---|
| 77 | # define IDX(h) ((h) & (HSIZE - 1))
|
|---|
| 78 | #endif
|
|---|
| 79 |
|
|---|
| 80 | #define MAX_LIT (1 << 5)
|
|---|
| 81 | #define MAX_OFF (1 << 13)
|
|---|
| 82 | #define MAX_REF ((1 << 8) + (1 << 3))
|
|---|
| 83 |
|
|---|
| 84 | /*
|
|---|
| 85 | * compressed format
|
|---|
| 86 | *
|
|---|
| 87 | * 000LLLLL <L+1> ; literal
|
|---|
| 88 | * LLLooooo oooooooo ; backref L
|
|---|
| 89 | * 111ooooo LLLLLLLL oooooooo ; backref L+7
|
|---|
| 90 | *
|
|---|
| 91 | */
|
|---|
| 92 |
|
|---|
| 93 | unsigned int
|
|---|
| 94 | lzf_compress (const void *const in_data, unsigned int in_len,
|
|---|
| 95 | void *out_data, unsigned int out_len
|
|---|
| 96 | #if LZF_STATE_ARG
|
|---|
| 97 | , LZF_STATE *htab
|
|---|
| 98 | #endif
|
|---|
| 99 | )
|
|---|
| 100 | {
|
|---|
| 101 | #if !LZF_STATE_ARG
|
|---|
| 102 | LZF_STATE htab;
|
|---|
| 103 | #endif
|
|---|
| 104 | const u8 **hslot;
|
|---|
| 105 | const u8 *ip = (const u8 *)in_data;
|
|---|
| 106 | u8 *op = (u8 *)out_data;
|
|---|
| 107 | const u8 *in_end = ip + in_len;
|
|---|
| 108 | u8 *out_end = op + out_len;
|
|---|
| 109 | const u8 *ref;
|
|---|
| 110 |
|
|---|
| 111 | unsigned int hval = FRST (ip);
|
|---|
| 112 | #ifdef USE_UINTPTR_T /* bird: use intptr_t for pointer acrobatics on 64-bit windows. */
|
|---|
| 113 | uintptr_t off;
|
|---|
| 114 | #else
|
|---|
| 115 | unsigned long off;
|
|---|
| 116 | #endif
|
|---|
| 117 | int lit = 0;
|
|---|
| 118 |
|
|---|
| 119 | #if INIT_HTAB
|
|---|
| 120 | # if USE_MEMCPY
|
|---|
| 121 | memset (htab, 0, sizeof (htab));
|
|---|
| 122 | # else
|
|---|
| 123 | for (hslot = htab; hslot < htab + HSIZE; hslot++)
|
|---|
| 124 | *hslot++ = ip;
|
|---|
| 125 | # endif
|
|---|
| 126 | #endif
|
|---|
| 127 |
|
|---|
| 128 | for (;;)
|
|---|
| 129 | {
|
|---|
| 130 | if (ip < in_end - 2)
|
|---|
| 131 | {
|
|---|
| 132 | hval = NEXT (hval, ip);
|
|---|
| 133 | hslot = htab + IDX (hval);
|
|---|
| 134 | ref = *hslot; *hslot = ip;
|
|---|
| 135 |
|
|---|
| 136 | if (1
|
|---|
| 137 | #if INIT_HTAB && !USE_MEMCPY
|
|---|
| 138 | && ref < ip /* the next test will actually take care of this, but this is faster */
|
|---|
| 139 | #endif
|
|---|
| 140 | && (off = ip - ref - 1) < MAX_OFF
|
|---|
| 141 | && ip + 4 < in_end
|
|---|
| 142 | && ref > (u8 *)in_data
|
|---|
| 143 | #if STRICT_ALIGN
|
|---|
| 144 | && ref[0] == ip[0]
|
|---|
| 145 | && ref[1] == ip[1]
|
|---|
| 146 | && ref[2] == ip[2]
|
|---|
| 147 | #else
|
|---|
| 148 | && *(u16 *)ref == *(u16 *)ip
|
|---|
| 149 | && ref[2] == ip[2]
|
|---|
| 150 | #endif
|
|---|
| 151 | )
|
|---|
| 152 | {
|
|---|
| 153 | /* match found at *ref++ */
|
|---|
| 154 | unsigned int len = 2;
|
|---|
| 155 | unsigned int maxlen = in_end - ip - len;
|
|---|
| 156 | maxlen = maxlen > MAX_REF ? MAX_REF : maxlen;
|
|---|
| 157 |
|
|---|
| 158 | if (op + lit + 1 + 3 >= out_end)
|
|---|
| 159 | return 0;
|
|---|
| 160 |
|
|---|
| 161 | do
|
|---|
| 162 | len++;
|
|---|
| 163 | while (len < maxlen && ref[len] == ip[len]);
|
|---|
| 164 |
|
|---|
| 165 | if (lit)
|
|---|
| 166 | {
|
|---|
| 167 | *op++ = lit - 1;
|
|---|
| 168 | lit = -lit;
|
|---|
| 169 | do
|
|---|
| 170 | *op++ = ip[lit];
|
|---|
| 171 | while (++lit);
|
|---|
| 172 | }
|
|---|
| 173 |
|
|---|
| 174 | len -= 2;
|
|---|
| 175 | ip++;
|
|---|
| 176 |
|
|---|
| 177 | if (len < 7)
|
|---|
| 178 | {
|
|---|
| 179 | *op++ = (off >> 8) + (len << 5);
|
|---|
| 180 | }
|
|---|
| 181 | else
|
|---|
| 182 | {
|
|---|
| 183 | *op++ = (off >> 8) + ( 7 << 5);
|
|---|
| 184 | *op++ = len - 7;
|
|---|
| 185 | }
|
|---|
| 186 |
|
|---|
| 187 | *op++ = off;
|
|---|
| 188 |
|
|---|
| 189 | #if ULTRA_FAST || VERY_FAST
|
|---|
| 190 | ip += len;
|
|---|
| 191 | #if VERY_FAST && !ULTRA_FAST
|
|---|
| 192 | --ip;
|
|---|
| 193 | #endif
|
|---|
| 194 | hval = FRST (ip);
|
|---|
| 195 |
|
|---|
| 196 | hval = NEXT (hval, ip);
|
|---|
| 197 | htab[IDX (hval)] = ip;
|
|---|
| 198 | ip++;
|
|---|
| 199 |
|
|---|
| 200 | #if VERY_FAST && !ULTRA_FAST
|
|---|
| 201 | hval = NEXT (hval, ip);
|
|---|
| 202 | htab[IDX (hval)] = ip;
|
|---|
| 203 | ip++;
|
|---|
| 204 | #endif
|
|---|
| 205 | #else
|
|---|
| 206 | do
|
|---|
| 207 | {
|
|---|
| 208 | hval = NEXT (hval, ip);
|
|---|
| 209 | htab[IDX (hval)] = ip;
|
|---|
| 210 | ip++;
|
|---|
| 211 | }
|
|---|
| 212 | while (len--);
|
|---|
| 213 | #endif
|
|---|
| 214 | continue;
|
|---|
| 215 | }
|
|---|
| 216 | }
|
|---|
| 217 | else if (ip == in_end)
|
|---|
| 218 | break;
|
|---|
| 219 |
|
|---|
| 220 | /* one more literal byte we must copy */
|
|---|
| 221 | lit++;
|
|---|
| 222 | ip++;
|
|---|
| 223 |
|
|---|
| 224 | if (lit == MAX_LIT)
|
|---|
| 225 | {
|
|---|
| 226 | if (op + 1 + MAX_LIT >= out_end)
|
|---|
| 227 | return 0;
|
|---|
| 228 |
|
|---|
| 229 | *op++ = MAX_LIT - 1;
|
|---|
| 230 | #if USE_MEMCPY
|
|---|
| 231 | memcpy (op, ip - MAX_LIT, MAX_LIT);
|
|---|
| 232 | op += MAX_LIT;
|
|---|
| 233 | lit = 0;
|
|---|
| 234 | #else
|
|---|
| 235 | lit = -lit;
|
|---|
| 236 | do
|
|---|
| 237 | *op++ = ip[lit];
|
|---|
| 238 | while (++lit);
|
|---|
| 239 | #endif
|
|---|
| 240 | }
|
|---|
| 241 | }
|
|---|
| 242 |
|
|---|
| 243 | if (lit)
|
|---|
| 244 | {
|
|---|
| 245 | if (op + lit + 1 >= out_end)
|
|---|
| 246 | return 0;
|
|---|
| 247 |
|
|---|
| 248 | *op++ = lit - 1;
|
|---|
| 249 | lit = -lit;
|
|---|
| 250 | do
|
|---|
| 251 | *op++ = ip[lit];
|
|---|
| 252 | while (++lit);
|
|---|
| 253 | }
|
|---|
| 254 |
|
|---|
| 255 | return op - (u8 *) out_data;
|
|---|
| 256 | }
|
|---|
