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
|
/*
* Heirloom mailx - a mail user agent derived from Berkeley Mail.
*
* Copyright (c) 2000-2004 Gunnar Ritter, Freiburg i. Br., Germany.
*/
/*-
* 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. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. 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 */
/* from FreeBSD: /repoman/r/ncvs/src/usr.bin/compress/zopen.c,v
* 1.5.6.1 2002/07/16 00:52:08 tjr Exp */
/*-
* lzw.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>.
*
* Adopted for Heirloom mailx by Gunnar Ritter.
*
* Sccsid @(#)lzw.c 1.11 (gritter) 3/4/06
*/
#include "config.h"
#include "rcv.h"
#include "extern.h"
#include <stdio.h>
#define BITS 16 /* Default bits. */
#define HSIZE 69001 /* 95% occupancy */
/* 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;
typedef unsigned char char_type;
static char_type magic_header[] =
{037, 0235}; /* 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 {
FILE *zs_fp; /* File stream for I/O */
char zs_mode; /* r or w */
enum {
ST_START, ST_MIDDLE, ST_EOF
} zs_state; /* State of computation */
unsigned zs_n_bits; /* Number of bits/code. */
unsigned 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];
unsigned 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;
unsigned zs_offset;
long zs_in_count; /* Length of input. */
long zs_bytes_out; /* Length of compressed output. */
long zs_out_count; /* # of codes output (for debugging). */
char_type zs_buf[BITS+1];
union {
struct {
long zs_fcode;
code_int zs_ent;
code_int zs_hsize_reg;
int zs_hshift;
} w; /* Write paramenters */
struct {
char_type *zs_stackp;
int zs_finchar;
code_int zs_code, zs_oldcode, zs_incode;
int zs_roffset, zs_size;
char_type zs_gbuf[BITS+1];
} r; /* Read parameters */
} u;
};
/* Definitions to retain old variable names */
#define fp zs->zs_fp
#define zmode zs->zs_mode
#define state zs->zs_state
#define n_bits zs->zs_n_bits
#define maxbits zs->zs_maxbits
#define maxcode zs->zs_maxcode
#define maxmaxcode zs->zs_maxmaxcode
#define htab zs->zs_htab
#define codetab zs->zs_codetab
#define hsize zs->zs_hsize
#define free_ent zs->zs_free_ent
#define block_compress zs->zs_block_compress
#define clear_flg zs->zs_clear_flg
#define ratio zs->zs_ratio
#define checkpoint zs->zs_checkpoint
#define offset zs->zs_offset
#define in_count zs->zs_in_count
#define bytes_out zs->zs_bytes_out
#define out_count zs->zs_out_count
#define buf zs->zs_buf
#define fcode zs->u.w.zs_fcode
#define hsize_reg zs->u.w.zs_hsize_reg
#define ent zs->u.w.zs_ent
#define hshift zs->u.w.zs_hshift
#define stackp zs->u.r.zs_stackp
#define finchar zs->u.r.zs_finchar
#define code zs->u.r.zs_code
#define oldcode zs->u.r.zs_oldcode
#define incode zs->u.r.zs_incode
#define roffset zs->u.r.zs_roffset
#define size zs->u.r.zs_size
#define gbuf zs->u.r.zs_gbuf
/*
* 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) htab[i]
#define codetabof(i) codetab[i]
#define tab_prefixof(i) codetabof(i)
#define tab_suffixof(i) ((char_type *)(htab))[i]
#define de_stack ((char_type *)&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 output(struct s_zstate *zs, code_int ocode);
static code_int getcode(struct s_zstate *zs);
static int cl_block(struct s_zstate *zs);
static void cl_hash(struct s_zstate *zs, count_int cl_hsize);
/*-
* 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 unsigned char *bp;
unsigned char tmp;
int count;
if (num == 0)
return (0);
zs = cookie;
zmode = 'w';
count = num;
bp = (const unsigned char *)wbp;
if (state == ST_MIDDLE)
goto middle;
state = ST_MIDDLE;
maxmaxcode = 1L << maxbits;
if (fwrite(magic_header,
sizeof(char), sizeof(magic_header), fp) != sizeof(magic_header))
return (-1);
tmp = (unsigned char)((maxbits) | block_compress);
if (fwrite(&tmp, sizeof(char), sizeof(tmp), fp) != sizeof(tmp))
return (-1);
offset = 0;
bytes_out = 3; /* Includes 3-byte header mojo. */
out_count = 0;
clear_flg = 0;
ratio = 0;
in_count = 1;
checkpoint = CHECK_GAP;
maxcode = MAXCODE(n_bits = INIT_BITS);
free_ent = ((block_compress) ? FIRST : 256);
ent = *bp++;
--count;
hshift = 0;
for (fcode = (long)hsize; fcode < 65536L; fcode *= 2L)
hshift++;
hshift = 8 - hshift; /* Set hash code range bound. */
hsize_reg = hsize;
cl_hash(zs, (count_int)hsize_reg); /* Clear hash table. */
middle: for (i = 0; count--;) {
c = *bp++;
in_count++;
fcode = (long)(((long)c << maxbits) + ent);
i = ((c << hshift) ^ ent); /* Xor hashing. */
if (htabof(i) == fcode) {
ent = codetabof(i);
continue;
} else if ((long)htabof(i) < 0) /* Empty slot. */
goto nomatch;
disp = hsize_reg - i; /* Secondary hash (after G. Knott). */
if (i == 0)
disp = 1;
probe: if ((i -= disp) < 0)
i += hsize_reg;
if (htabof(i) == fcode) {
ent = codetabof(i);
continue;
}
if ((long)htabof(i) >= 0)
goto probe;
nomatch: if (output(zs, (code_int) ent) == -1)
return (-1);
out_count++;
ent = c;
if (free_ent < maxmaxcode) {
codetabof(i) = free_ent++; /* code -> hashtable */
htabof(i) = fcode;
} else if ((count_int)in_count >=
checkpoint && block_compress) {
if (cl_block(zs) == -1)
return (-1);
}
}
return (num);
}
int
zfree(void *cookie)
{
struct s_zstate *zs;
zs = cookie;
if (zmode == 'w') { /* Put out the final code. */
if (output(zs, (code_int) ent) == -1) {
free(zs);
return (-1);
}
out_count++;
if (output(zs, (code_int) - 1) == -1) {
free(zs);
return (-1);
}
}
free(zs);
return (0);
}
/*-
* 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 char_type lmask[9] =
{0xff, 0xfe, 0xfc, 0xf8, 0xf0, 0xe0, 0xc0, 0x80, 0x00};
static char_type rmask[9] =
{0x00, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff};
static int
output(struct s_zstate *zs, code_int ocode)
{
int r_off;
unsigned bits;
char_type *bp;
r_off = offset;
bits = n_bits;
bp = buf;
if (ocode >= 0) {
/* Get to the first byte. */
bp += (r_off >> 3);
r_off &= 7;
/*
* 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;
offset += n_bits;
if (offset == (n_bits << 3)) {
bp = buf;
bits = n_bits;
bytes_out += bits;
if (fwrite(bp, sizeof(char), bits, fp) != bits)
return (-1);
bp += bits;
bits = 0;
offset = 0;
}
/*
* If the next entry is going to be too big for the ocode size,
* then increase it, if possible.
*/
if (free_ent > maxcode || (clear_flg > 0)) {
/*
* Write the whole buffer, because the input side won't
* discover the size increase until after it has read it.
*/
if (offset > 0) {
if (fwrite(buf, 1, n_bits, fp) != n_bits)
return (-1);
bytes_out += n_bits;
}
offset = 0;
if (clear_flg) {
maxcode = MAXCODE(n_bits = INIT_BITS);
clear_flg = 0;
} else {
n_bits++;
if (n_bits == maxbits)
maxcode = maxmaxcode;
else
maxcode = MAXCODE(n_bits);
}
}
} else {
/* At EOF, write the rest of the buffer. */
if (offset > 0) {
offset = (offset + 7) / 8;
if (fwrite(buf, 1, offset, fp) != offset)
return (-1);
bytes_out += offset;
}
offset = 0;
}
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)
{
unsigned count;
struct s_zstate *zs;
unsigned char *bp, header[3];
if (num == 0)
return (0);
zs = cookie;
count = num;
bp = (unsigned char *)rbp;
switch (state) {
case ST_START:
state = ST_MIDDLE;
break;
case ST_MIDDLE:
goto middle;
case ST_EOF:
goto eof;
}
/* Check the magic number */
if (fread(header,
sizeof(char), sizeof(header), fp) != sizeof(header) ||
memcmp(header, magic_header, sizeof(magic_header)) != 0) {
return (-1);
}
maxbits = header[2]; /* Set -b from file. */
block_compress = maxbits & BLOCK_MASK;
maxbits &= BIT_MASK;
maxmaxcode = 1L << maxbits;
if (maxbits > BITS) {
return (-1);
}
/* As above, initialize the first 256 entries in the table. */
maxcode = MAXCODE(n_bits = INIT_BITS);
for (code = 255; code >= 0; code--) {
tab_prefixof(code) = 0;
tab_suffixof(code) = (char_type) code;
}
free_ent = block_compress ? FIRST : 256;
finchar = oldcode = getcode(zs);
if (oldcode == -1) /* EOF already? */
return (0); /* Get out of here */
/* First code must be 8 bits = char. */
*bp++ = (unsigned char)finchar;
count--;
stackp = de_stack;
while ((code = getcode(zs)) > -1) {
if ((code == CLEAR) && block_compress) {
for (code = 255; code >= 0; code--)
tab_prefixof(code) = 0;
clear_flg = 1;
free_ent = FIRST - 1;
if ((code = getcode(zs)) == -1) /* O, untimely death! */
break;
}
incode = code;
/* Special case for KwKwK string. */
if (code >= free_ent) {
*stackp++ = finchar;
code = oldcode;
}
/* Generate output characters in reverse order. */
while (code >= 256) {
*stackp++ = tab_suffixof(code);
code = tab_prefixof(code);
}
*stackp++ = finchar = tab_suffixof(code);
/* And put them out in forward order. */
middle: do {
if (count-- == 0)
return (num);
*bp++ = *--stackp;
} while (stackp > de_stack);
/* Generate the new entry. */
if ((code = free_ent) < maxmaxcode) {
tab_prefixof(code) = (unsigned short) oldcode;
tab_suffixof(code) = finchar;
free_ent = code + 1;
}
/* Remember previous code. */
oldcode = incode;
}
state = ST_EOF;
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;
char_type *bp;
bp = gbuf;
if (clear_flg > 0 || roffset >= size || free_ent > maxcode) {
/*
* 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 (free_ent > maxcode) {
n_bits++;
if (n_bits == maxbits) /* Won't get any bigger now. */
maxcode = maxmaxcode;
else
maxcode = MAXCODE(n_bits);
}
if (clear_flg > 0) {
maxcode = MAXCODE(n_bits = INIT_BITS);
clear_flg = 0;
}
size = fread(gbuf, 1, n_bits, fp);
if (size <= 0) /* End of file. */
return (-1);
roffset = 0;
/* Round size down to integral number of codes. */
size = (size << 3) - (n_bits - 1);
}
r_off = roffset;
bits = 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;
roffset += n_bits;
return (gcode);
}
static int
cl_block ( /* Table clear for block compress. */
struct s_zstate *zs
)
{
long rat;
checkpoint = in_count + CHECK_GAP;
if (in_count > 0x007fffff) { /* Shift will overflow. */
rat = bytes_out >> 8;
if (rat == 0) /* Don't divide by zero. */
rat = 0x7fffffff;
else
rat = in_count / rat;
} else
rat = (in_count << 8) / bytes_out; /* 8 fractional bits. */
if (rat > ratio)
ratio = rat;
else {
ratio = 0;
cl_hash(zs, (count_int) hsize);
free_ent = FIRST;
clear_flg = 1;
if (output(zs, (code_int) CLEAR) == -1)
return (-1);
}
return (0);
}
static void
cl_hash ( /* Reset code table. */
struct s_zstate *zs,
count_int cl_hsize
)
{
count_int *htab_p;
long i, m1;
m1 = -1;
htab_p = 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;
}
#undef fp
void *
zalloc(FILE *fp)
{
#define bits BITS
struct s_zstate *zs;
zs = scalloc(1, sizeof *zs);
maxbits = bits ? bits : BITS; /* User settable max # bits/code. */
maxmaxcode = 1L << maxbits; /* Should NEVER generate this code. */
hsize = HSIZE; /* For dynamic table sizing. */
free_ent = 0; /* First unused entry. */
block_compress = BLOCK_MASK;
clear_flg = 0;
ratio = 0;
checkpoint = CHECK_GAP;
in_count = 1; /* Length of input. */
out_count = 0; /* # of codes output (for debugging). */
state = ST_START;
roffset = 0;
size = 0;
zs->zs_fp = fp;
return zs;
}
|