1 |
/* |
2 |
* Copyright (c) 2000-2003 Marc Alexander Lehmann <pcg@goof.com> |
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 |
|
41 |
#define HSIZE (1 << (HLOG)) |
42 |
|
43 |
/* |
44 |
* don't play with this unless you benchmark! |
45 |
* decompression is not dependent on the hash function |
46 |
* the hashing function might seem strange, just believe me |
47 |
* it works ;) |
48 |
*/ |
49 |
#define FRST(p) (((p[0]) << 8) + p[1]) |
50 |
#define NEXT(v,p) (((v) << 8) + p[2]) |
51 |
#define IDX(h) ((((h ^ (h << 5)) >> (3*8 - HLOG)) + h*3) & (HSIZE - 1)) |
52 |
/* |
53 |
* IDX works because it is very similar to a multiplicative hash, e.g. |
54 |
* (h * 57321 >> (3*8 - HLOG)) |
55 |
* the next one is also quite good, albeit slow ;) |
56 |
* (int)(cos(h & 0xffffff) * 1e6) |
57 |
*/ |
58 |
|
59 |
#if 0 |
60 |
/* original lzv-like hash function */ |
61 |
# define FRST(p) (p[0] << 5) ^ p[1] |
62 |
# define NEXT(v,p) ((v) << 5) ^ p[2] |
63 |
# define IDX(h) ((h) & (HSIZE - 1)) |
64 |
#endif |
65 |
|
66 |
#define MAX_LIT (1 << 5) |
67 |
#define MAX_OFF (1 << 13) |
68 |
#define MAX_REF ((1 << 8) + (1 << 3)) |
69 |
|
70 |
/* |
71 |
* compressed format |
72 |
* |
73 |
* 000LLLLL <L+1> ; literal |
74 |
* LLLOOOOO oooooooo ; backref L |
75 |
* 111OOOOO LLLLLLLL oooooooo ; backref L+7 |
76 |
* |
77 |
*/ |
78 |
|
79 |
unsigned int |
80 |
lzf_compress (const void *const in_data, unsigned int in_len, |
81 |
void *out_data, unsigned int out_len |
82 |
#if LZF_STATE_ARG |
83 |
, LZF_STATE *htab |
84 |
#endif |
85 |
) |
86 |
{ |
87 |
#if !LZF_STATE_ARG |
88 |
LZF_STATE htab; |
89 |
#endif |
90 |
const u8 **hslot; |
91 |
const u8 *ip = (const u8 *)in_data; |
92 |
u8 *op = (u8 *)out_data; |
93 |
const u8 *in_end = ip + in_len; |
94 |
u8 *out_end = op + out_len; |
95 |
const u8 *ref; |
96 |
|
97 |
unsigned int hval = FRST (ip); |
98 |
unsigned long off; |
99 |
int lit = 0; |
100 |
|
101 |
#if INIT_HTAB |
102 |
# if USE_MEMCPY |
103 |
memset (htab, 0, sizeof (htab)); |
104 |
# else |
105 |
for (hslot = htab; hslot < htab + HSIZE; hslot++) |
106 |
*hslot++ = ip; |
107 |
# endif |
108 |
#endif |
109 |
|
110 |
for (;;) |
111 |
{ |
112 |
if (ip < in_end - 2) |
113 |
{ |
114 |
hval = NEXT (hval, ip); |
115 |
hslot = htab + IDX (hval); |
116 |
ref = *hslot; *hslot = ip; |
117 |
|
118 |
if (1 |
119 |
#if INIT_HTAB && !USE_MEMCPY |
120 |
&& ref < ip /* the next test will actually take care of this, but this is faster */ |
121 |
#endif |
122 |
&& (off = ip - ref - 1) < MAX_OFF |
123 |
&& ip + 4 < in_end |
124 |
&& ref > (u8 *)in_data |
125 |
#if STRICT_ALIGN |
126 |
&& ref[0] == ip[0] |
127 |
&& ref[1] == ip[1] |
128 |
&& ref[2] == ip[2] |
129 |
#else |
130 |
&& *(u16 *)ref == *(u16 *)ip |
131 |
&& ref[2] == ip[2] |
132 |
#endif |
133 |
) |
134 |
{ |
135 |
/* match found at *ref++ */ |
136 |
unsigned int len = 2; |
137 |
unsigned int maxlen = in_end - ip - len; |
138 |
maxlen = maxlen > MAX_REF ? MAX_REF : maxlen; |
139 |
|
140 |
do |
141 |
len++; |
142 |
while (len < maxlen && ref[len] == ip[len]); |
143 |
|
144 |
if (op + lit + 1 + 3 >= out_end) |
145 |
return 0; |
146 |
|
147 |
if (lit) |
148 |
{ |
149 |
*op++ = lit - 1; |
150 |
lit = -lit; |
151 |
do |
152 |
*op++ = ip[lit]; |
153 |
while (++lit); |
154 |
} |
155 |
|
156 |
len -= 2; |
157 |
ip++; |
158 |
|
159 |
if (len < 7) |
160 |
{ |
161 |
*op++ = (off >> 8) + (len << 5); |
162 |
} |
163 |
else |
164 |
{ |
165 |
*op++ = (off >> 8) + ( 7 << 5); |
166 |
*op++ = len - 7; |
167 |
} |
168 |
|
169 |
*op++ = off; |
170 |
|
171 |
#if ULTRA_FAST |
172 |
ip += len; |
173 |
hval = FRST (ip); |
174 |
hval = NEXT (hval, ip); |
175 |
htab[IDX (hval)] = ip; |
176 |
ip++; |
177 |
#else |
178 |
do |
179 |
{ |
180 |
hval = NEXT (hval, ip); |
181 |
htab[IDX (hval)] = ip; |
182 |
ip++; |
183 |
} |
184 |
while (len--); |
185 |
#endif |
186 |
continue; |
187 |
} |
188 |
} |
189 |
else if (ip == in_end) |
190 |
break; |
191 |
|
192 |
/* one more literal byte we must copy */ |
193 |
lit++; |
194 |
ip++; |
195 |
|
196 |
if (lit == MAX_LIT) |
197 |
{ |
198 |
if (op + 1 + MAX_LIT >= out_end) |
199 |
return 0; |
200 |
|
201 |
*op++ = MAX_LIT - 1; |
202 |
#if USE_MEMCPY |
203 |
memcpy (op, ip - MAX_LIT, MAX_LIT); |
204 |
op += MAX_LIT; |
205 |
lit = 0; |
206 |
#else |
207 |
lit = -lit; |
208 |
do |
209 |
*op++ = ip[lit]; |
210 |
while (++lit); |
211 |
#endif |
212 |
} |
213 |
} |
214 |
|
215 |
if (lit) |
216 |
{ |
217 |
if (op + lit + 1 >= out_end) |
218 |
return 0; |
219 |
|
220 |
*op++ = lit - 1; |
221 |
lit = -lit; |
222 |
do |
223 |
*op++ = ip[lit]; |
224 |
while (++lit); |
225 |
} |
226 |
|
227 |
return op - (u8 *) out_data; |
228 |
} |