Chameleon

Chameleon Commit Details

Date:2014-01-20 14:02:05 (10 years 1 month ago)
Author:ErmaC
Commit:2343
Parents: 2342
Message:Add lzss compression.
Changes:
M/trunk/i386/boot2/lzss.c

File differences

trunk/i386/boot2/lzss.c
4848
4949
5050
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
5167
5268
5369
......
90106
91107
92108
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
if match_length is greater than this */
#define NIL N /* index for root of binary search trees */
struct encode_state {
/*
* left & right children & parent. These constitute binary search trees.
*/
int lchild[N + 1], rchild[N + 257], parent[N + 1];
/* ring buffer of size N, with extra F-1 bytes to aid string comparison */
u_int8_t text_buf[N + F - 1];
/*
* match_length of longest match.
* These are set by the insert_node() procedure.
*/
int match_position, match_length;
};
int
decompress_lzss(u_int8_t *dst, u_int8_t *src, u_int32_t srclen)
{
return dst - dststart;
}
/*
* initialize state, mostly the trees
*
* For i = 0 to N - 1, rchild[i] and lchild[i] will be the right and left
* children of node i. These nodes need not be initialized. Also, parent[i]
* is the parent of node i. These are initialized to NIL (= N), which stands
* for 'not used.' For i = 0 to 255, rchild[N + i + 1] is the root of the
* tree for strings that begin with character i. These are initialized to NIL.
* Note there are 256 trees. */
static void init_state(struct encode_state *sp)
{
int i;
bzero(sp, sizeof(*sp));
for (i = 0; i < N - F; i++)
sp->text_buf[i] = ' ';
for (i = N + 1; i <= N + 256; i++)
sp->rchild[i] = NIL;
for (i = 0; i < N; i++)
sp->parent[i] = NIL;
}
/*
* Inserts string of length F, text_buf[r..r+F-1], into one of the trees
* (text_buf[r]'th tree) and returns the longest-match position and length
* via the global variables match_position and match_length.
* If match_length = F, then removes the old node in favor of the new one,
* because the old one will be deleted sooner. Note r plays double role,
* as tree node and position in buffer.
*/
static void insert_node(struct encode_state *sp, int r)
{
int i, p, cmp;
u_int8_t *key;
cmp = 1;
key = &sp->text_buf[r];
p = N + 1 + key[0];
sp->rchild[r] = sp->lchild[r] = NIL;
sp->match_length = 0;
for ( ; ; ) {
if (cmp >= 0) {
if (sp->rchild[p] != NIL)
p = sp->rchild[p];
else {
sp->rchild[p] = r;
sp->parent[r] = p;
return;
}
} else {
if (sp->lchild[p] != NIL)
p = sp->lchild[p];
else {
sp->lchild[p] = r;
sp->parent[r] = p;
return;
}
}
for (i = 1; i < F; i++) {
if ((cmp = key[i] - sp->text_buf[p + i]) != 0)
break;
}
if (i > sp->match_length) {
sp->match_position = p;
if ((sp->match_length = i) >= F)
break;
}
}
sp->parent[r] = sp->parent[p];
sp->lchild[r] = sp->lchild[p];
sp->rchild[r] = sp->rchild[p];
sp->parent[sp->lchild[p]] = r;
sp->parent[sp->rchild[p]] = r;
if (sp->rchild[sp->parent[p]] == p)
sp->rchild[sp->parent[p]] = r;
else
sp->lchild[sp->parent[p]] = r;
sp->parent[p] = NIL; /* remove p */
}
/* deletes node p from tree */
static void delete_node(struct encode_state *sp, int p)
{
int q;
if (sp->parent[p] == NIL)
return; /* not in tree */
if (sp->rchild[p] == NIL)
q = sp->lchild[p];
else if (sp->lchild[p] == NIL)
q = sp->rchild[p];
else {
q = sp->lchild[p];
if (sp->rchild[q] != NIL) {
do {
q = sp->rchild[q];
} while (sp->rchild[q] != NIL);
sp->rchild[sp->parent[q]] = sp->lchild[q];
sp->parent[sp->lchild[q]] = sp->parent[q];
sp->lchild[q] = sp->lchild[p];
sp->parent[sp->lchild[p]] = q;
}
sp->rchild[q] = sp->rchild[p];
sp->parent[sp->rchild[p]] = q;
}
sp->parent[q] = sp->parent[p];
if (sp->rchild[sp->parent[p]] == p)
sp->rchild[sp->parent[p]] = q;
else
sp->lchild[sp->parent[p]] = q;
sp->parent[p] = NIL;
}
u_int8_t *compress_lzss(
u_int8_t * dst,
u_int32_t dstlen,
u_int8_t * src,
u_int32_t srclen)
{
u_int8_t * result = NULL;
/* Encoding state, mostly tree but some current match stuff */
struct encode_state *sp;
int i, c, len, r, s, last_match_length, code_buf_ptr;
u_int8_t code_buf[17], mask;
u_int8_t * srcend = src + srclen;
u_int8_t *dstend = dst + dstlen;
/* initialize trees */
sp = (struct encode_state *) malloc(sizeof(*sp));
if (!sp) goto finish;
init_state(sp);
/*
* code_buf[1..16] saves eight units of code, and code_buf[0] works
* as eight flags, "1" representing that the unit is an unencoded
* letter (1 byte), "0" a position-and-length pair (2 bytes).
* Thus, eight units require at most 16 bytes of code.
*/
code_buf[0] = 0;
code_buf_ptr = mask = 1;
/* Clear the buffer with any character that will appear often. */
s = 0; r = N - F;
/* Read F bytes into the last F bytes of the buffer */
for (len = 0; len < F && src < srcend; len++)
sp->text_buf[r + len] = *src++;
if (!len)
goto finish;
/*
* Insert the F strings, each of which begins with one or more
* 'space' characters. Note the order in which these strings are
* inserted. This way, degenerate trees will be less likely to occur.
*/
for (i = 1; i <= F; i++)
insert_node(sp, r - i);
/*
* Finally, insert the whole string just read.
* The global variables match_length and match_position are set.
*/
insert_node(sp, r);
do {
/* match_length may be spuriously long near the end of text. */
if (sp->match_length > len)
sp->match_length = len;
if (sp->match_length <= THRESHOLD) {
sp->match_length = 1; /* Not long enough match. Send one byte. */
code_buf[0] |= mask; /* 'send one byte' flag */
code_buf[code_buf_ptr++] = sp->text_buf[r]; /* Send uncoded. */
} else {
/* Send position and length pair. Note match_length > THRESHOLD. */
code_buf[code_buf_ptr++] = (u_int8_t) sp->match_position;
code_buf[code_buf_ptr++] = (u_int8_t)
( ((sp->match_position >> 4) & 0xF0)
| (sp->match_length - (THRESHOLD + 1)) );
}
if ((mask <<= 1) == 0) { /* Shift mask left one bit. */
/* Send at most 8 units of code together */
for (i = 0; i < code_buf_ptr; i++)
if (dst < dstend)
*dst++ = code_buf[i];
else
goto finish;
code_buf[0] = 0;
code_buf_ptr = mask = 1;
}
last_match_length = sp->match_length;
for (i = 0; i < last_match_length && src < srcend; i++) {
delete_node(sp, s); /* Delete old strings and */
c = *src++;
sp->text_buf[s] = c; /* read new bytes */
/*
* If the position is near the end of buffer, extend the buffer
* to make string comparison easier.
*/
if (s < F - 1)
sp->text_buf[s + N] = c;
/* Since this is a ring buffer, increment the position modulo N. */
s = (s + 1) & (N - 1);
r = (r + 1) & (N - 1);
/* Register the string in text_buf[r..r+F-1] */
insert_node(sp, r);
}
while (i++ < last_match_length) {
delete_node(sp, s);
/* After the end of text, no need to read, */
s = (s + 1) & (N - 1);
r = (r + 1) & (N - 1);
/* but buffer may not be empty. */
if (--len)
insert_node(sp, r);
}
} while (len > 0); /* until length of string to be processed is zero */
if (code_buf_ptr > 1) { /* Send remaining code. */
for (i = 0; i < code_buf_ptr; i++)
if (dst < dstend)
*dst++ = code_buf[i];
else
goto finish;
}
result = dst;
finish:
if (sp) free(sp);
return result;
}

Archive Download the corresponding diff file

Revision: 2343