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
|
/* deflate.c -- compress data using the deflation algorithm
Copyright (C) 1999, 2006 Free Software Foundation, Inc.
Copyright (C) 1992-1993 Jean-loup Gailly
Copyright (C) 2008 Josh Triplett
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software Foundation,
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
/*
* PURPOSE
*
* Identify new text as repetitions of old text within a fixed-
* length sliding window trailing behind the new text.
*
* DISCUSSION
*
* The "deflation" process depends on being able to identify portions
* of the input text which are identical to earlier input (within a
* sliding window trailing behind the input currently being processed).
*
* The most straightforward technique turns out to be the fastest for
* most input files: try all possible matches and select the longest.
* The key feature of this algorithm is that insertions into the string
* dictionary are very simple and thus fast, and deletions are avoided
* completely. Insertions are performed at each input character, whereas
* string matches are performed only when the previous match ends. So it
* is preferable to spend more time in matches to allow very fast string
* insertions and avoid deletions. The matching algorithm for small
* strings is inspired from that of Rabin & Karp. A brute force approach
* is used to find longer strings when a small match has been found.
* A similar algorithm is used in comic (by Jan-Mark Wams) and freeze
* (by Leonid Broukhis).
* A previous version of this file used a more sophisticated algorithm
* (by Fiala and Greene) which is guaranteed to run in linear amortized
* time, but has a larger average cost, uses more memory and is patented.
* However the F&G algorithm may be faster for some highly redundant
* files if the parameter max_chain_length (described below) is too large.
*
* ACKNOWLEDGEMENTS
*
* The idea of lazy evaluation of matches is due to Jan-Mark Wams, and
* I found it in 'freeze' written by Leonid Broukhis.
* Thanks to many info-zippers for bug reports and testing.
*
* REFERENCES
*
* APPNOTE.TXT documentation file in PKZIP 1.93a distribution.
*
* A description of the Rabin and Karp algorithm is given in the book
* "Algorithms" by R. Sedgewick, Addison-Wesley, p252.
*
* Fiala,E.R., and Greene,D.H.
* Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595
*
* INTERFACE
*
* void lm_init (int pack_level, ush *flags)
* Initialize the "longest match" routines for a new file
*
* void deflate (void)
* Processes a new input file. Sets the compressed length, crc,
* deflate flags and internal file attributes.
*/
#include <stdio.h>
#include "gzip.h"
/* ===========================================================================
* Configuration parameters
*/
#define HASH_BITS 15
#define HASH_SIZE (unsigned)(1<<HASH_BITS)
#define HASH_MASK (HASH_SIZE-1)
#define WMASK (WSIZE-1)
/* HASH_SIZE and WSIZE must be powers of two */
#define NIL 0
/* Tail of hash chains */
#define FAST 4
#define SLOW 2
/* speed options for the general purpose bit flag */
#ifndef TOO_FAR
# define TOO_FAR 4096
#endif
/* Matches of length 3 are discarded if their distance exceeds TOO_FAR */
#ifndef RSYNC_WIN
# define RSYNC_WIN 4096
#endif
/* Size of rsync window, must be < MAX_DIST */
#define RSYNC_SUM_MATCH(sum) ((sum) % RSYNC_WIN == 0)
/* Whether window sum matches magic value */
/* ===========================================================================
* Local data used by the "longest match" routines.
*/
typedef ush Pos;
typedef unsigned IPos;
/* A Pos is an index in the character window. We use short instead of int to
* save space in the various tables. IPos is used only for parameter passing.
*/
static uch window[2L*WSIZE];
/* Sliding window. Input bytes are read into the second half of the window,
* and move to the first half later to keep a dictionary of at least WSIZE
* bytes. With this organization, matches are limited to a distance of
* WSIZE-MAX_MATCH bytes, but this ensures that IO is always
* performed with a length multiple of the block size. Also, it limits
* the window size to 64K, which is quite useful on MSDOS.
*/
Pos prev[WSIZE];
/* Link to older string with same hash index. To limit the size of this
* array to 64K, this link is maintained only for the last 32K strings.
* An index in this array is thus a window index modulo 32K.
*/
Pos head[1<<HASH_BITS];
/* Heads of the hash chains or NIL. */
ulg window_size = (ulg)2*WSIZE;
/* window size, 2*WSIZE except for MMAP or BIG_MEM, where it is the
* input file length plus MIN_LOOKAHEAD.
*/
long block_start;
/* window position at the beginning of the current output block. Gets
* negative when the window is moved backwards.
*/
static unsigned ins_h; /* hash index of string to be inserted */
#define H_SHIFT ((HASH_BITS+MIN_MATCH-1)/MIN_MATCH)
/* Number of bits by which ins_h and del_h must be shifted at each
* input step. It must be such that after MIN_MATCH steps, the oldest
* byte no longer takes part in the hash key, that is:
* H_SHIFT * MIN_MATCH >= HASH_BITS
*/
unsigned int prev_length;
/* Length of the best match at previous step. Matches not greater than this
* are discarded. This is used in the lazy match evaluation.
*/
unsigned strstart; /* start of string to insert */
unsigned match_start; /* start of matching string */
static int eofile; /* flag set at end of input file */
static unsigned lookahead; /* number of valid bytes ahead in window */
unsigned max_chain_length;
/* To speed up deflation, hash chains are never searched beyond this length.
* A higher limit improves compression ratio but degrades the speed.
*/
static unsigned int max_lazy_match;
/* Attempt to find a better match only when the current match is strictly
* smaller than this value. This mechanism is used only for compression
* levels >= 4.
*/
#define max_insert_length max_lazy_match
/* Insert new strings in the hash table only if the match length
* is not greater than this length. This saves time but degrades compression.
* max_insert_length is used only for compression levels <= 3.
*/
static unsigned good_match;
/* Use a faster search when the previous match is longer than this */
static ulg rsync_sum; /* rolling sum of rsync window */
static ulg rsync_chunk_end; /* next rsync sequence point */
/* Values for max_lazy_match, good_match and max_chain_length, depending on
* the desired pack level (0..9). The values given below have been tuned to
* exclude worst case performance for pathological files. Better values may be
* found for specific files.
*/
typedef struct config {
ush good_length; /* reduce lazy search above this match length */
ush max_lazy; /* do not perform lazy search above this match length */
ush nice_length; /* quit search above this match length */
ush max_chain;
} config;
#ifdef FULL_SEARCH
# define nice_match MAX_MATCH
#else
int nice_match; /* Stop searching when current match exceeds this */
#endif
static config configuration_table[10] = {
/* good lazy nice chain */
/* 0 */ {0, 0, 0, 0}, /* store only */
/* 1 */ {4, 4, 8, 4}, /* maximum speed, no lazy matches */
/* 2 */ {4, 5, 16, 8},
/* 3 */ {4, 6, 32, 32},
/* 4 */ {4, 4, 16, 16}, /* lazy matches */
/* 5 */ {8, 16, 32, 32},
/* 6 */ {8, 16, 128, 128},
/* 7 */ {8, 32, 128, 256},
/* 8 */ {32, 128, 258, 1024},
/* 9 */ {32, 258, 258, 4096}}; /* maximum compression */
/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4
* For deflate_fast() (levels <= 3) good is ignored and lazy has a different
* meaning.
*/
#define EQUAL 0
/* result of memcmp for equal strings */
/* ===========================================================================
* Prototypes for local functions.
*/
static void fill_window(void);
int longest_match(IPos cur_match);
/* ===========================================================================
* Update a hash value with the given input byte
* IN assertion: all calls to to UPDATE_HASH are made with consecutive
* input characters, so that a running hash key can be computed from the
* previous key instead of complete recalculation each time.
*/
#define UPDATE_HASH(h,c) (h = (((h)<<H_SHIFT) ^ (c)) & HASH_MASK)
/* ===========================================================================
* Insert string s in the dictionary and set match_head to the previous head
* of the hash chain (the most recent string with same hash key). Return
* the previous length of the hash chain.
* IN assertion: all calls to to INSERT_STRING are made with consecutive
* input characters and the first MIN_MATCH bytes of s are valid
* (except for the last MIN_MATCH-1 bytes of the input file).
*/
#define INSERT_STRING(s, match_head) \
(UPDATE_HASH(ins_h, window[(s) + MIN_MATCH-1]), \
prev[(s) & WMASK] = match_head = head[ins_h], \
head[ins_h] = (s))
/* ===========================================================================
* Initialize the "longest match" routines for a new file
*/
void lm_init (int pack_level, /* 1: best speed, 9: best compression */
ush *flags) /* general purpose bit flag */
{
register unsigned j;
if (pack_level < 1 || pack_level > 9) gzip_error ("bad pack level");
/* Initialize the hash table. */
memzero((char*)head, HASH_SIZE*sizeof(*head));
/* prev will be initialized on the fly */
/* rsync params */
rsync_chunk_end = 0xFFFFFFFFUL;
rsync_sum = 0;
/* Set the default configuration parameters:
*/
max_lazy_match = configuration_table[pack_level].max_lazy;
good_match = configuration_table[pack_level].good_length;
#ifndef FULL_SEARCH
nice_match = configuration_table[pack_level].nice_length;
#endif
max_chain_length = configuration_table[pack_level].max_chain;
if (pack_level == 1) {
*flags |= FAST;
} else if (pack_level == 9) {
*flags |= SLOW;
}
/* ??? reduce max_chain_length for binary files */
strstart = 0;
block_start = 0L;
lookahead = read_buf((char*)window,
sizeof(int) <= 2 ? (unsigned)WSIZE : 2*WSIZE);
if (lookahead == 0 || lookahead == (unsigned)EOF) {
eofile = 1, lookahead = 0;
return;
}
eofile = 0;
/* Make sure that we always have enough lookahead. This is important
* if input comes from a device such as a tty.
*/
while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
ins_h = 0;
for (j=0; j<MIN_MATCH-1; j++) UPDATE_HASH(ins_h, window[j]);
/* If lookahead < MIN_MATCH, ins_h is garbage, but this is
* not important since only literal bytes will be emitted.
*/
}
/* ===========================================================================
* Set match_start to the longest match starting at the given string and
* return its length. Matches shorter or equal to prev_length are discarded,
* in which case the result is equal to prev_length and match_start is
* garbage.
* IN assertions: cur_match is the head of the hash chain for the current
* string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1
*/
int longest_match(IPos cur_match)
{
unsigned chain_length = max_chain_length; /* max hash chain length */
register uch *scan = window + strstart; /* current string */
register uch *match; /* matched string */
register int len; /* length of current match */
int best_len = prev_length; /* best match length so far */
IPos limit = strstart > (IPos)MAX_DIST ? strstart - (IPos)MAX_DIST : NIL;
/* Stop when cur_match becomes <= limit. To simplify the code,
* we prevent matches with the string of window index 0.
*/
/* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16.
* It is easy to get rid of this optimization if necessary.
*/
#if HASH_BITS < 8 || MAX_MATCH != 258
error: Code too clever
#endif
#ifdef UNALIGNED_OK
/* Compare two bytes at a time. Note: this is not always beneficial.
* Try with and without -DUNALIGNED_OK to check.
*/
register uch *strend = window + strstart + MAX_MATCH - 1;
register ush scan_start = *(ush*)scan;
register ush scan_end = *(ush*)(scan+best_len-1);
#else
register uch *strend = window + strstart + MAX_MATCH;
register uch scan_end1 = scan[best_len-1];
register uch scan_end = scan[best_len];
#endif
/* Do not waste too much time if we already have a good match: */
if (prev_length >= good_match) {
chain_length >>= 2;
}
Assert(strstart <= window_size-MIN_LOOKAHEAD, "insufficient lookahead");
do {
Assert(cur_match < strstart, "no future");
match = window + cur_match;
/* Skip to next match if the match length cannot increase
* or if the match length is less than 2:
*/
#if (defined(UNALIGNED_OK) && MAX_MATCH == 258)
/* This code assumes sizeof(unsigned short) == 2. Do not use
* UNALIGNED_OK if your compiler uses a different size.
*/
if (*(ush*)(match+best_len-1) != scan_end ||
*(ush*)match != scan_start) continue;
/* It is not necessary to compare scan[2] and match[2] since they are
* always equal when the other bytes match, given that the hash keys
* are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at
* strstart+3, +5, ... up to strstart+257. We check for insufficient
* lookahead only every 4th comparison; the 128th check will be made
* at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is
* necessary to put more guard bytes at the end of the window, or
* to check more often for insufficient lookahead.
*/
scan++, match++;
do {
} while (*(ush*)(scan+=2) == *(ush*)(match+=2) &&
*(ush*)(scan+=2) == *(ush*)(match+=2) &&
*(ush*)(scan+=2) == *(ush*)(match+=2) &&
*(ush*)(scan+=2) == *(ush*)(match+=2) &&
scan < strend);
/* The funny "do {}" generates better code on most compilers */
/* Here, scan <= window+strstart+257 */
Assert(scan <= window+(unsigned)(window_size-1), "wild scan");
if (*scan == *match) scan++;
len = (MAX_MATCH - 1) - (int)(strend-scan);
scan = strend - (MAX_MATCH-1);
#else /* UNALIGNED_OK */
if (match[best_len] != scan_end ||
match[best_len-1] != scan_end1 ||
*match != *scan ||
*++match != scan[1]) continue;
/* The check at best_len-1 can be removed because it will be made
* again later. (This heuristic is not always a win.)
* It is not necessary to compare scan[2] and match[2] since they
* are always equal when the other bytes match, given that
* the hash keys are equal and that HASH_BITS >= 8.
*/
scan += 2, match++;
/* We check for insufficient lookahead only every 8th comparison;
* the 256th check will be made at strstart+258.
*/
do {
} while (*++scan == *++match && *++scan == *++match &&
*++scan == *++match && *++scan == *++match &&
*++scan == *++match && *++scan == *++match &&
*++scan == *++match && *++scan == *++match &&
scan < strend);
len = MAX_MATCH - (int)(strend - scan);
scan = strend - MAX_MATCH;
#endif /* UNALIGNED_OK */
if (len > best_len) {
match_start = cur_match;
best_len = len;
if (len >= nice_match) break;
#ifdef UNALIGNED_OK
scan_end = *(ush*)(scan+best_len-1);
#else
scan_end1 = scan[best_len-1];
scan_end = scan[best_len];
#endif
}
} while ((cur_match = prev[cur_match & WMASK]) > limit
&& --chain_length != 0);
return best_len;
}
/* ===========================================================================
* Fill the window when the lookahead becomes insufficient.
* Updates strstart and lookahead, and sets eofile if end of input file.
* IN assertion: lookahead < MIN_LOOKAHEAD && strstart + lookahead > 0
* OUT assertions: at least one byte has been read, or eofile is set;
* file reads are performed for at least two bytes (required for the
* translate_eol option).
*/
static void fill_window(void)
{
register unsigned n, m;
unsigned more = (unsigned)(window_size - (ulg)lookahead - (ulg)strstart);
/* Amount of free space at the end of the window. */
/* If the window is almost full and there is insufficient lookahead,
* move the upper half to the lower one to make room in the upper half.
*/
if (more == (unsigned)EOF) {
/* Very unlikely, but possible on 16 bit machine if strstart == 0
* and lookahead == 1 (input done one byte at time)
*/
more--;
} else if (strstart >= WSIZE+MAX_DIST) {
/* By the IN assertion, the window is not empty so we can't confuse
* more == 0 with more == 64K on a 16 bit machine.
*/
Assert(window_size == (ulg)2*WSIZE, "no sliding with BIG_MEM");
memcpy((char*)window, (char*)window+WSIZE, (unsigned)WSIZE);
match_start -= WSIZE;
strstart -= WSIZE; /* we now have strstart >= MAX_DIST: */
if (rsync_chunk_end != 0xFFFFFFFFUL)
rsync_chunk_end -= WSIZE;
block_start -= (long) WSIZE;
for (n = 0; n < HASH_SIZE; n++) {
m = head[n];
head[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL);
}
for (n = 0; n < WSIZE; n++) {
m = prev[n];
prev[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL);
/* If n is not on any hash chain, prev[n] is garbage but
* its value will never be used.
*/
}
more += WSIZE;
}
/* At this point, more >= 2 */
if (!eofile) {
n = read_buf((char*)window+strstart+lookahead, more);
if (n == 0 || n == (unsigned)EOF) {
eofile = 1;
} else {
lookahead += n;
}
}
}
static void rsync_roll(unsigned start, unsigned num)
{
unsigned i;
if (start < RSYNC_WIN) {
/* before window fills. */
for (i = start; i < RSYNC_WIN; i++) {
if (i == start + num) return;
rsync_sum += (ulg)window[i];
}
num -= (RSYNC_WIN - start);
start = RSYNC_WIN;
}
/* buffer after window full */
for (i = start; i < start+num; i++) {
/* New character in */
rsync_sum += (ulg)window[i];
/* Old character out */
rsync_sum -= (ulg)window[i - RSYNC_WIN];
if (rsync_chunk_end == 0xFFFFFFFFUL && RSYNC_SUM_MATCH(rsync_sum))
rsync_chunk_end = i;
}
}
/* ===========================================================================
* Set rsync_chunk_end if window sum matches magic value.
*/
#define RSYNC_ROLL(s, n) \
do { if (rsync) rsync_roll((s), (n)); } while(0)
/* ===========================================================================
* Flush the current block, with given end-of-file flag.
* IN assertion: strstart is set to the end of the current match.
*/
#define FLUSH_BLOCK(eof) \
flush_block(block_start >= 0L ? (char*)&window[(unsigned)block_start] : \
(char*)NULL, (long)strstart - block_start, flush-1, (eof))
/* ===========================================================================
* Processes a new input file and return its compressed length. This
* function does not perform lazy evaluationof matches and inserts
* new strings in the dictionary only for unmatched strings or for short
* matches. It is used only for the fast compression options.
*/
static void deflate_fast(int pack_level, int rsync)
{
IPos hash_head; /* head of the hash chain */
int flush; /* set if current block must be flushed, 2=>and padded */
unsigned match_length = 0; /* length of best match */
prev_length = MIN_MATCH-1;
while (lookahead != 0) {
/* Insert the string window[strstart .. strstart+2] in the
* dictionary, and set hash_head to the head of the hash chain:
*/
INSERT_STRING(strstart, hash_head);
/* Find the longest match, discarding those <= prev_length.
* At this point we have always match_length < MIN_MATCH
*/
if (hash_head != NIL && strstart - hash_head <= MAX_DIST
&& strstart <= window_size - MIN_LOOKAHEAD) {
/* To simplify the code, we prevent matches with the string
* of window index 0 (in particular we have to avoid a match
* of the string with itself at the start of the input file).
*/
match_length = longest_match (hash_head);
/* longest_match() sets match_start */
if (match_length > lookahead) match_length = lookahead;
}
if (match_length >= MIN_MATCH) {
flush = ct_tally(pack_level, strstart-match_start, match_length - MIN_MATCH);
lookahead -= match_length;
RSYNC_ROLL(strstart, match_length);
/* Insert new strings in the hash table only if the match length
* is not too large. This saves time but degrades compression.
*/
if (match_length <= max_insert_length) {
match_length--; /* string at strstart already in hash table */
do {
strstart++;
INSERT_STRING(strstart, hash_head);
/* strstart never exceeds WSIZE-MAX_MATCH, so there are
* always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH
* these bytes are garbage, but it does not matter since
* the next lookahead bytes will be emitted as literals.
*/
} while (--match_length != 0);
strstart++;
} else {
strstart += match_length;
match_length = 0;
ins_h = window[strstart];
UPDATE_HASH(ins_h, window[strstart+1]);
#if MIN_MATCH != 3
Call UPDATE_HASH() MIN_MATCH-3 more times
#endif
}
} else {
/* No match, output a literal byte */
Tracevv((stderr,"%c",window[strstart]));
flush = ct_tally (pack_level, 0, window[strstart]);
RSYNC_ROLL(strstart, 1);
lookahead--;
strstart++;
}
if (rsync && strstart > rsync_chunk_end) {
rsync_chunk_end = 0xFFFFFFFFUL;
flush = 2;
}
if (flush) FLUSH_BLOCK(0), block_start = strstart;
/* Make sure that we always have enough lookahead, except
* at the end of the input file. We need MAX_MATCH bytes
* for the next match, plus MIN_MATCH bytes to insert the
* string following the next match.
*/
while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
}
FLUSH_BLOCK(1); /* eof */
}
/* ===========================================================================
* Same as above, but achieves better compression. We use a lazy
* evaluation for matches: a match is finally adopted only if there is
* no better match at the next window position.
*/
void gnu_deflate(int pack_level, int rsync)
{
IPos hash_head; /* head of hash chain */
IPos prev_match; /* previous match */
int flush = 0; /* set if current block must be flushed */
int match_available = 0; /* set if previous match exists */
register unsigned match_length = MIN_MATCH-1; /* length of best match */
if (pack_level <= 3) {
deflate_fast(pack_level, rsync); /* optimized for speed */
return;
}
/* Process the input block. */
while (lookahead != 0) {
/* Insert the string window[strstart .. strstart+2] in the
* dictionary, and set hash_head to the head of the hash chain:
*/
INSERT_STRING(strstart, hash_head);
/* Find the longest match, discarding those <= prev_length.
*/
prev_length = match_length, prev_match = match_start;
match_length = MIN_MATCH-1;
if (hash_head != NIL && prev_length < max_lazy_match &&
strstart - hash_head <= MAX_DIST &&
strstart <= window_size - MIN_LOOKAHEAD) {
/* To simplify the code, we prevent matches with the string
* of window index 0 (in particular we have to avoid a match
* of the string with itself at the start of the input file).
*/
match_length = longest_match (hash_head);
/* longest_match() sets match_start */
if (match_length > lookahead) match_length = lookahead;
/* Ignore a length 3 match if it is too distant: */
if (match_length == MIN_MATCH && strstart-match_start > TOO_FAR){
/* If prev_match is also MIN_MATCH, match_start is garbage
* but we will ignore the current match anyway.
*/
match_length--;
}
}
/* If there was a match at the previous step and the current
* match is not better, output the previous match:
*/
if (prev_length >= MIN_MATCH && match_length <= prev_length) {
flush = ct_tally(pack_level, strstart-1-prev_match, prev_length - MIN_MATCH);
/* Insert in hash table all strings up to the end of the match.
* strstart-1 and strstart are already inserted.
*/
lookahead -= prev_length-1;
prev_length -= 2;
RSYNC_ROLL(strstart, prev_length+1);
do {
strstart++;
INSERT_STRING(strstart, hash_head);
/* strstart never exceeds WSIZE-MAX_MATCH, so there are
* always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH
* these bytes are garbage, but it does not matter since the
* next lookahead bytes will always be emitted as literals.
*/
} while (--prev_length != 0);
match_available = 0;
match_length = MIN_MATCH-1;
strstart++;
if (rsync && strstart > rsync_chunk_end) {
rsync_chunk_end = 0xFFFFFFFFUL;
flush = 2;
}
if (flush) FLUSH_BLOCK(0), block_start = strstart;
} else if (match_available) {
/* If there was no match at the previous position, output a
* single literal. If there was a match but the current match
* is longer, truncate the previous match to a single literal.
*/
Tracevv((stderr,"%c",window[strstart-1]));
flush = ct_tally (pack_level, 0, window[strstart-1]);
if (rsync && strstart > rsync_chunk_end) {
rsync_chunk_end = 0xFFFFFFFFUL;
flush = 2;
}
if (flush) FLUSH_BLOCK(0), block_start = strstart;
RSYNC_ROLL(strstart, 1);
strstart++;
lookahead--;
} else {
/* There is no previous match to compare with, wait for
* the next step to decide.
*/
if (rsync && strstart > rsync_chunk_end) {
/* Reset huffman tree */
rsync_chunk_end = 0xFFFFFFFFUL;
flush = 2;
FLUSH_BLOCK(0), block_start = strstart;
}
match_available = 1;
RSYNC_ROLL(strstart, 1);
strstart++;
lookahead--;
}
/* Assert (strstart <= bytes_in && lookahead <= bytes_in, "a bit too far"); */
/* Make sure that we always have enough lookahead, except
* at the end of the input file. We need MAX_MATCH bytes
* for the next match, plus MIN_MATCH bytes to insert the
* string following the next match.
*/
while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window();
}
if (match_available) ct_tally (pack_level, 0, window[strstart-1]);
FLUSH_BLOCK(1); /* eof */
}
|