1
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
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
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
|
/* $OpenBSD: zopen.c,v 1.21 2016/09/03 11:41:10 tedu Exp $ */
/* $NetBSD: zopen.c,v 1.5 1995/03/26 09:44:53 glass Exp $ */
/*-
* Copyright (c) 1985, 1986, 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Diomidis Spinellis and James A. Woods, derived from original
* work by Spencer Thomas and Joseph Orost.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* From: @(#)zopen.c 8.1 (Berkeley) 6/27/93
*/
/*-
* fcompress.c - File compression ala IEEE Computer, June 1984.
*
* Compress authors:
* Spencer W. Thomas (decvax!utah-cs!thomas)
* Jim McKie (decvax!mcvax!jim)
* Steve Davies (decvax!vax135!petsd!peora!srd)
* Ken Turkowski (decvax!decwrl!turtlevax!ken)
* James A. Woods (decvax!ihnp4!ames!jaw)
* Joe Orost (decvax!vax135!petsd!joe)
*
* Cleaned up and converted to library returning I/O streams by
* Diomidis Spinellis <dds@doc.ic.ac.uk>.
*
* zopen(filename, mode, bits)
* Returns a FILE * that can be used for read or write. The modes
* supported are only "r" and "w". Seeking is not allowed. On
* reading the file is decompressed, on writing it is compressed.
* The output is compatible with compress(1) with 16 bit tables.
* Any file produced by compress(1) can be read.
*/
#include <sys/stat.h>
#include <ctype.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include "compress.h"
#define MINIMUM(a, b) (((a) < (b)) ? (a) : (b))
#define BITS 16 /* Default bits. */
#define HSIZE 69001 /* 95% occupancy */
#define ZBUFSIZ 8192 /* I/O buffer size */
/* A code_int must be able to hold 2**BITS values of type int, and also -1. */
typedef long code_int;
typedef long count_int;
static const u_char z_magic[] =
{'\037', '\235'}; /* 1F 9D */
#define BIT_MASK 0x1f /* Defines for third byte of header. */
#define BLOCK_MASK 0x80
/*
* Masks 0x40 and 0x20 are free. I think 0x20 should mean that there is
* a fourth header byte (for expansion).
*/
#define INIT_BITS 9 /* Initial number of bits/code. */
#define MAXCODE(n_bits) ((1 << (n_bits)) - 1)
struct s_zstate {
int zs_fd; /* File stream for I/O */
char zs_mode; /* r or w */
enum {
S_START, S_MAGIC, S_MIDDLE, S_EOF
} zs_state; /* State of computation */
int zs_n_bits; /* Number of bits/code. */
int zs_maxbits; /* User settable max # bits/code. */
code_int zs_maxcode; /* Maximum code, given n_bits. */
code_int zs_maxmaxcode; /* Should NEVER generate this code. */
count_int zs_htab[HSIZE];
u_short zs_codetab[HSIZE];
code_int zs_hsize; /* For dynamic table sizing. */
code_int zs_free_ent; /* First unused entry. */
/*
* Block compression parameters -- after all codes are used up,
* and compression rate changes, start over.
*/
int zs_block_compress;
int zs_clear_flg;
long zs_ratio;
count_int zs_checkpoint;
long zs_in_count; /* Length of input. */
long zs_bytes_out; /* Length of output. */
long zs_out_count; /* # of codes output (for debugging).*/
u_char zs_buf[ZBUFSIZ]; /* I/O buffer */
u_char *zs_bp; /* Current I/O window in the zs_buf */
int zs_offset; /* Number of bits in the zs_buf */
union {
struct {
long zs_fcode;
code_int zs_ent;
code_int zs_hsize_reg;
int zs_hshift;
} w; /* Write parameters */
struct {
u_char *zs_stackp, *zs_ebp;
int zs_finchar;
code_int zs_code, zs_oldcode, zs_incode;
int zs_size;
} r; /* Read parameters */
} u;
};
/* Definitions to retain old variable names */
#define zs_fcode u.w.zs_fcode
#define zs_ent u.w.zs_ent
#define zs_hsize_reg u.w.zs_hsize_reg
#define zs_hshift u.w.zs_hshift
#define zs_stackp u.r.zs_stackp
#define zs_finchar u.r.zs_finchar
#define zs_code u.r.zs_code
#define zs_oldcode u.r.zs_oldcode
#define zs_incode u.r.zs_incode
#define zs_size u.r.zs_size
#define zs_ebp u.r.zs_ebp
/*
* To save much memory, we overlay the table used by compress() with those
* used by decompress(). The tab_prefix table is the same size and type as
* the codetab. The tab_suffix table needs 2**BITS characters. We get this
* from the beginning of htab. The output stack uses the rest of htab, and
* contains characters. There is plenty of room for any possible stack
* (stack used to be 8000 characters).
*/
#define htabof(i) zs->zs_htab[i]
#define codetabof(i) zs->zs_codetab[i]
#define tab_prefixof(i) codetabof(i)
#define tab_suffixof(i) ((u_char *)(zs->zs_htab))[i]
#define de_stack ((u_char *)&tab_suffixof(1 << BITS))
#define CHECK_GAP 10000 /* Ratio check interval. */
/*
* the next two codes should not be changed lightly, as they must not
* lie within the contiguous general code space.
*/
#define FIRST 257 /* First free entry. */
#define CLEAR 256 /* Table clear output code. */
static int cl_block(struct s_zstate *);
static void cl_hash(struct s_zstate *, count_int);
static code_int getcode(struct s_zstate *);
static int output(struct s_zstate *, code_int);
/*-
* Algorithm from "A Technique for High Performance Data Compression",
* Terry A. Welch, IEEE Computer Vol 17, No 6 (June 1984), pp 8-19.
*
* Algorithm:
* Modified Lempel-Ziv method (LZW). Basically finds common
* substrings and replaces them with a variable size code. This is
* deterministic, and can be done on the fly. Thus, the decompression
* procedure needs no input table, but tracks the way the table was built.
*/
/*-
* compress write
*
* Algorithm: use open addressing double hashing (no chaining) on the
* prefix code / next character combination. We do a variant of Knuth's
* algorithm D (vol. 3, sec. 6.4) along with G. Knott's relatively-prime
* secondary probe. Here, the modular division first probe is gives way
* to a faster exclusive-or manipulation. Also do block compression with
* an adaptive reset, whereby the code table is cleared when the compression
* ratio decreases, but after the table fills. The variable-length output
* codes are re-sized at this point, and a special CLEAR code is generated
* for the decompressor. Late addition: construct the table according to
* file size for noticeable speed improvement on small files. Please direct
* questions about this implementation to ames!jaw.
*/
int
zwrite(void *cookie, const char *wbp, int num)
{
code_int i;
int c, disp;
struct s_zstate *zs;
const u_char *bp;
u_char tmp;
int count;
zs = cookie;
count = num;
bp = (u_char *)wbp;
switch (zs->zs_state) {
case S_MAGIC:
return -1;
case S_EOF:
return 0;
case S_START:
zs->zs_state = S_MIDDLE;
zs->zs_maxmaxcode = 1L << zs->zs_maxbits;
if (write(zs->zs_fd, z_magic, sizeof(z_magic)) !=
sizeof(z_magic))
return (-1);
tmp = (u_char)(zs->zs_maxbits | zs->zs_block_compress);
if (write(zs->zs_fd, &tmp, sizeof(tmp)) != sizeof(tmp))
return (-1);
zs->zs_bp = zs->zs_buf;
zs->zs_offset = 0;
zs->zs_bytes_out = 3; /* Includes 3-byte header mojo. */
zs->zs_out_count = 0;
zs->zs_clear_flg = 0;
zs->zs_ratio = 0;
zs->zs_in_count = 1;
zs->zs_checkpoint = CHECK_GAP;
zs->zs_maxcode = MAXCODE(zs->zs_n_bits = INIT_BITS);
zs->zs_free_ent = ((zs->zs_block_compress) ? FIRST : 256);
zs->zs_ent = *bp++;
--count;
zs->zs_hshift = 0;
for (zs->zs_fcode = (long)zs->zs_hsize; zs->zs_fcode < 65536L;
zs->zs_fcode *= 2L)
zs->zs_hshift++;
/* Set hash code range bound. */
zs->zs_hshift = 8 - zs->zs_hshift;
zs->zs_hsize_reg = zs->zs_hsize;
/* Clear hash table. */
cl_hash(zs, (count_int)zs->zs_hsize_reg);
case S_MIDDLE:
for (i = 0; count-- > 0;) {
c = *bp++;
zs->zs_in_count++;
zs->zs_fcode = (long)(((long)c << zs->zs_maxbits) +
zs->zs_ent);
/* Xor hashing. */
i = ((c << zs->zs_hshift) ^ zs->zs_ent);
if (htabof(i) == zs->zs_fcode) {
zs->zs_ent = codetabof(i);
continue;
} else if ((long)htabof(i) < 0) /* Empty slot. */
goto nomatch;
/* Secondary hash (after G. Knott). */
disp = zs->zs_hsize_reg - i;
if (i == 0)
disp = 1;
probe: if ((i -= disp) < 0)
i += zs->zs_hsize_reg;
if (htabof(i) == zs->zs_fcode) {
zs->zs_ent = codetabof(i);
continue;
}
if ((long)htabof(i) >= 0)
goto probe;
nomatch: if (output(zs, (code_int) zs->zs_ent) == -1)
return (-1);
zs->zs_out_count++;
zs->zs_ent = c;
if (zs->zs_free_ent < zs->zs_maxmaxcode) {
/* code -> hashtable */
codetabof(i) = zs->zs_free_ent++;
htabof(i) = zs->zs_fcode;
} else if ((count_int)zs->zs_in_count >=
zs->zs_checkpoint && zs->zs_block_compress) {
if (cl_block(zs) == -1)
return (-1);
}
}
}
return (num);
}
int
z_close(void *cookie, struct z_info *info, const char *name, struct stat *sb)
{
struct s_zstate *zs;
int rval;
zs = cookie;
if (zs->zs_mode == 'w') { /* Put out the final code. */
if (output(zs, (code_int) zs->zs_ent) == -1) {
(void)close(zs->zs_fd);
free(zs);
return (-1);
}
zs->zs_out_count++;
if (output(zs, (code_int) - 1) == -1) {
(void)close(zs->zs_fd);
free(zs);
return (-1);
}
}
if (info != NULL) {
info->mtime = 0;
info->crc = (u_int32_t)-1;
info->hlen = 0;
info->total_in = (off_t)zs->zs_in_count;
info->total_out = (off_t)zs->zs_bytes_out;
}
#ifndef SAVECORE
setfile(name, zs->zs_fd, sb);
#endif
rval = close(zs->zs_fd);
free(zs);
return (rval);
}
static int
zclose(void *cookie)
{
return z_close(cookie, NULL, NULL, NULL);
}
/*-
* Output the given code.
* Inputs:
* code: A n_bits-bit integer. If == -1, then EOF. This assumes
* that n_bits =< (long)wordsize - 1.
* Outputs:
* Outputs code to the file.
* Assumptions:
* Chars are 8 bits long.
* Algorithm:
* Maintain a BITS character long buffer (so that 8 codes will
* fit in it exactly). Use the VAX insv instruction to insert each
* code in turn. When the buffer fills up empty it and start over.
*/
static const u_char lmask[9] =
{0xff, 0xfe, 0xfc, 0xf8, 0xf0, 0xe0, 0xc0, 0x80, 0x00};
static const u_char rmask[9] =
{0x00, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff};
static int
output(struct s_zstate *zs, code_int ocode)
{
int bits;
if (ocode >= 0) {
int r_off;
u_char *bp;
/* Get to the first byte. */
bp = zs->zs_bp + (zs->zs_offset >> 3);
r_off = zs->zs_offset & 7;
bits = zs->zs_n_bits;
/*
* Since ocode is always >= 8 bits, only need to mask the first
* hunk on the left.
*/
*bp = (*bp & rmask[r_off]) | ((ocode << r_off) & lmask[r_off]);
bp++;
bits -= (8 - r_off);
ocode >>= 8 - r_off;
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits) */
if (bits >= 8) {
*bp++ = ocode;
ocode >>= 8;
bits -= 8;
}
/* Last bits. */
if (bits)
*bp = ocode;
zs->zs_offset += zs->zs_n_bits;
if (zs->zs_offset == (zs->zs_n_bits << 3)) {
zs->zs_bp += zs->zs_n_bits;
zs->zs_offset = 0;
}
/*
* If the next entry is going to be too big for the ocode size,
* then increase it, if possible.
*/
if (zs->zs_free_ent > zs->zs_maxcode ||
(zs->zs_clear_flg > 0)) {
/*
* Write the whole buffer, because the input side won't
* discover the size increase until after it has read it
*/
if (zs->zs_offset > 0) {
zs->zs_bp += zs->zs_n_bits;
zs->zs_offset = 0;
}
if (zs->zs_clear_flg) {
zs->zs_maxcode =
MAXCODE(zs->zs_n_bits = INIT_BITS);
zs->zs_clear_flg = 0;
} else {
zs->zs_n_bits++;
if (zs->zs_n_bits == zs->zs_maxbits)
zs->zs_maxcode = zs->zs_maxmaxcode;
else
zs->zs_maxcode =
MAXCODE(zs->zs_n_bits);
}
}
if (zs->zs_bp + zs->zs_n_bits > &zs->zs_buf[ZBUFSIZ]) {
bits = zs->zs_bp - zs->zs_buf;
if (write(zs->zs_fd, zs->zs_buf, bits) != bits)
return (-1);
zs->zs_bytes_out += bits;
if (zs->zs_offset > 0)
fprintf (stderr, "zs_offset != 0\n");
zs->zs_bp = zs->zs_buf;
}
} else {
/* At EOF, write the rest of the buffer. */
if (zs->zs_offset > 0)
zs->zs_bp += (zs->zs_offset + 7) / 8;
if (zs->zs_bp > zs->zs_buf) {
bits = zs->zs_bp - zs->zs_buf;
if (write(zs->zs_fd, zs->zs_buf, bits) != bits)
return (-1);
zs->zs_bytes_out += bits;
}
zs->zs_offset = 0;
zs->zs_bp = zs->zs_buf;
}
return (0);
}
/*
* Decompress read. This routine adapts to the codes in the file building
* the "string" table on-the-fly; requiring no table to be stored in the
* compressed file. The tables used herein are shared with those of the
* compress() routine. See the definitions above.
*/
int
zread(void *cookie, char *rbp, int num)
{
u_int count;
struct s_zstate *zs;
u_char *bp, header[3];
if (num == 0)
return (0);
zs = cookie;
count = num;
bp = (u_char *)rbp;
switch (zs->zs_state) {
case S_START:
zs->zs_state = S_MIDDLE;
zs->zs_bp = zs->zs_buf;
header[0] = header[1] = header[2] = '\0';
read(zs->zs_fd, header, sizeof(header));
break;
case S_MAGIC:
zs->zs_state = S_MIDDLE;
zs->zs_bp = zs->zs_buf;
header[0] = z_magic[0];
header[1] = z_magic[1];
header[2] = '\0';
read(zs->zs_fd, &header[2], 1);
break;
case S_MIDDLE:
goto middle;
case S_EOF:
goto eof;
}
/* Check the magic number */
if (header[0] != z_magic[0] || header[1] != z_magic[1]) {
errno = EFTYPE;
return (-1);
}
zs->zs_maxbits = header[2]; /* Set -b from file. */
zs->zs_in_count += sizeof(header);
zs->zs_block_compress = zs->zs_maxbits & BLOCK_MASK;
zs->zs_maxbits &= BIT_MASK;
zs->zs_maxmaxcode = 1L << zs->zs_maxbits;
if (zs->zs_maxbits > BITS) {
errno = EFTYPE;
return (-1);
}
/* As above, initialize the first 256 entries in the table. */
zs->zs_maxcode = MAXCODE(zs->zs_n_bits = INIT_BITS);
for (zs->zs_code = 255; zs->zs_code >= 0; zs->zs_code--) {
tab_prefixof(zs->zs_code) = 0;
tab_suffixof(zs->zs_code) = (u_char) zs->zs_code;
}
zs->zs_free_ent = zs->zs_block_compress ? FIRST : 256;
zs->zs_finchar = zs->zs_oldcode = getcode(zs);
if (zs->zs_oldcode == -1) /* EOF already? */
return (0); /* Get out of here */
/* First code must be 8 bits = char. */
*bp++ = (u_char)zs->zs_finchar;
count--;
zs->zs_stackp = de_stack;
while ((zs->zs_code = getcode(zs)) > -1) {
if ((zs->zs_code == CLEAR) && zs->zs_block_compress) {
for (zs->zs_code = 255; zs->zs_code >= 0;
zs->zs_code--)
tab_prefixof(zs->zs_code) = 0;
zs->zs_clear_flg = 1;
zs->zs_free_ent = FIRST - 1;
if ((zs->zs_code = getcode(zs)) == -1) /* O, untimely death! */
break;
}
zs->zs_incode = zs->zs_code;
/* Special case for KwKwK string. */
if (zs->zs_code >= zs->zs_free_ent) {
*zs->zs_stackp++ = zs->zs_finchar;
zs->zs_code = zs->zs_oldcode;
}
/* Generate output characters in reverse order. */
while (zs->zs_code >= 256) {
/*
* Bad input file may cause zs_stackp to overflow
* zs_htab; check here and abort decompression,
* that's better than dumping core.
*/
if (zs->zs_stackp >= (u_char *)&zs->zs_htab[HSIZE]) {
errno = EINVAL;
return (-1);
}
*zs->zs_stackp++ = tab_suffixof(zs->zs_code);
zs->zs_code = tab_prefixof(zs->zs_code);
}
*zs->zs_stackp++ = zs->zs_finchar = tab_suffixof(zs->zs_code);
/* And put them out in forward order. */
middle: do {
if (count-- == 0) {
zs->zs_bytes_out += num;
return (num);
}
*bp++ = *--zs->zs_stackp;
} while (zs->zs_stackp > de_stack);
/* Generate the new entry. */
if ((zs->zs_code = zs->zs_free_ent) < zs->zs_maxmaxcode) {
tab_prefixof(zs->zs_code) = (u_short) zs->zs_oldcode;
tab_suffixof(zs->zs_code) = zs->zs_finchar;
zs->zs_free_ent = zs->zs_code + 1;
}
/* Remember previous code. */
zs->zs_oldcode = zs->zs_incode;
}
zs->zs_state = S_EOF;
zs->zs_bytes_out += num - count;
eof: return (num - count);
}
/*-
* Read one code from the standard input. If EOF, return -1.
* Inputs:
* stdin
* Outputs:
* code or -1 is returned.
*/
static code_int
getcode(struct s_zstate *zs)
{
code_int gcode;
int r_off, bits;
u_char *bp;
if (zs->zs_clear_flg > 0 || zs->zs_offset >= zs->zs_size ||
zs->zs_free_ent > zs->zs_maxcode) {
zs->zs_bp += zs->zs_n_bits;
/*
* If the next entry will be too big for the current gcode
* size, then we must increase the size. This implies reading
* a new buffer full, too.
*/
if (zs->zs_free_ent > zs->zs_maxcode) {
zs->zs_n_bits++;
if (zs->zs_n_bits == zs->zs_maxbits) {
/* Won't get any bigger now. */
zs->zs_maxcode = zs->zs_maxmaxcode;
} else
zs->zs_maxcode = MAXCODE(zs->zs_n_bits);
}
if (zs->zs_clear_flg > 0) {
zs->zs_maxcode = MAXCODE(zs->zs_n_bits = INIT_BITS);
zs->zs_clear_flg = 0;
}
/* fill the buffer up to the neck */
if (zs->zs_bp + zs->zs_n_bits > zs->zs_ebp) {
for (bp = zs->zs_buf; zs->zs_bp < zs->zs_ebp;
*bp++ = *zs->zs_bp++);
if ((bits = read(zs->zs_fd, bp, ZBUFSIZ -
(bp - zs->zs_buf))) < 0)
return -1;
zs->zs_in_count += bits;
zs->zs_bp = zs->zs_buf;
zs->zs_ebp = bp + bits;
}
zs->zs_offset = 0;
zs->zs_size = MINIMUM(zs->zs_n_bits, zs->zs_ebp - zs->zs_bp);
if (zs->zs_size == 0)
return -1;
/* Round size down to integral number of codes. */
zs->zs_size = (zs->zs_size << 3) - (zs->zs_n_bits - 1);
}
bp = zs->zs_bp;
r_off = zs->zs_offset;
bits = zs->zs_n_bits;
/* Get to the first byte. */
bp += (r_off >> 3);
r_off &= 7;
/* Get first part (low order bits). */
gcode = (*bp++ >> r_off);
bits -= (8 - r_off);
r_off = 8 - r_off; /* Now, roffset into gcode word. */
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
if (bits >= 8) {
gcode |= *bp++ << r_off;
r_off += 8;
bits -= 8;
}
/* High order bits. */
gcode |= (*bp & rmask[bits]) << r_off;
zs->zs_offset += zs->zs_n_bits;
return (gcode);
}
/* Table clear for block compress. */
static int
cl_block(struct s_zstate *zs)
{
long rat;
zs->zs_checkpoint = zs->zs_in_count + CHECK_GAP;
if (zs->zs_in_count > 0x007fffff) { /* Shift will overflow. */
rat = zs->zs_bytes_out >> 8;
if (rat == 0) /* Don't divide by zero. */
rat = 0x7fffffff;
else
rat = zs->zs_in_count / rat;
} else {
/* 8 fractional bits. */
rat = (zs->zs_in_count << 8) / zs->zs_bytes_out;
}
if (rat > zs->zs_ratio)
zs->zs_ratio = rat;
else {
zs->zs_ratio = 0;
cl_hash(zs, (count_int) zs->zs_hsize);
zs->zs_free_ent = FIRST;
zs->zs_clear_flg = 1;
if (output(zs, (code_int) CLEAR) == -1)
return (-1);
}
return (0);
}
/* Reset code table. */
static void
cl_hash(struct s_zstate *zs, count_int cl_hsize)
{
count_int *htab_p;
long i, m1;
m1 = -1;
htab_p = zs->zs_htab + cl_hsize;
i = cl_hsize - 16;
do { /* Might use Sys V memset(3) here. */
*(htab_p - 16) = m1;
*(htab_p - 15) = m1;
*(htab_p - 14) = m1;
*(htab_p - 13) = m1;
*(htab_p - 12) = m1;
*(htab_p - 11) = m1;
*(htab_p - 10) = m1;
*(htab_p - 9) = m1;
*(htab_p - 8) = m1;
*(htab_p - 7) = m1;
*(htab_p - 6) = m1;
*(htab_p - 5) = m1;
*(htab_p - 4) = m1;
*(htab_p - 3) = m1;
*(htab_p - 2) = m1;
*(htab_p - 1) = m1;
htab_p -= 16;
} while ((i -= 16) >= 0);
for (i += 16; i > 0; i--)
*--htab_p = m1;
}
void *
z_wopen(int fd, char *name, int bits, u_int32_t mtime)
{
struct s_zstate *zs;
if (bits < 0 || bits > BITS) {
errno = EINVAL;
return (NULL);
}
if ((zs = calloc(1, sizeof(struct s_zstate))) == NULL)
return (NULL);
/* User settable max # bits/code. */
zs->zs_maxbits = bits ? bits : BITS;
/* Should NEVER generate this code. */
zs->zs_maxmaxcode = 1 << zs->zs_maxbits;
zs->zs_hsize = HSIZE; /* For dynamic table sizing. */
zs->zs_free_ent = 0; /* First unused entry. */
zs->zs_block_compress = BLOCK_MASK;
zs->zs_clear_flg = 0;
zs->zs_ratio = 0;
zs->zs_checkpoint = CHECK_GAP;
zs->zs_in_count = 0; /* Length of input. */
zs->zs_out_count = 0; /* # of codes output (for debugging).*/
zs->zs_state = S_START;
zs->zs_offset = 0;
zs->zs_size = 0;
zs->zs_mode = 'w';
zs->zs_bp = zs->zs_ebp = zs->zs_buf;
zs->zs_fd = fd;
return zs;
}
void *
z_ropen(int fd, char *name, int gotmagic)
{
struct s_zstate *zs;
if ((zs = calloc(1, sizeof(struct s_zstate))) == NULL)
return (NULL);
/* User settable max # bits/code. */
zs->zs_maxbits = BITS;
/* Should NEVER generate this code. */
zs->zs_maxmaxcode = 1 << zs->zs_maxbits;
zs->zs_hsize = HSIZE; /* For dynamic table sizing. */
zs->zs_free_ent = 0; /* First unused entry. */
zs->zs_block_compress = BLOCK_MASK;
zs->zs_clear_flg = 0;
zs->zs_ratio = 0;
zs->zs_checkpoint = CHECK_GAP;
zs->zs_in_count = 0; /* Length of input. */
zs->zs_out_count = 0; /* # of codes output (for debugging).*/
zs->zs_state = gotmagic ? S_MAGIC : S_START;
zs->zs_offset = 0;
zs->zs_size = 0;
zs->zs_mode = 'r';
zs->zs_bp = zs->zs_ebp = zs->zs_buf;
zs->zs_fd = fd;
return zs;
}
|