📄 deflate.c
字号:
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;
}
#endif /* ASMV */
#ifdef DEBUG
/* ===========================================================================
* Check that the match at match_start is indeed a match.
*/
local void check_match(start, match, length)
IPos start, match;
int length;
{
/* check that the match is indeed a match */
if (memcmp((char*)window + match,
(char*)window + start, length) != EQUAL) {
fprintf(stderr,
" start %d, match %d, length %d\n",
start, match, length);
error("invalid match");
}
if (verbose > 1) {
fprintf(stderr,"\\[%d,%d]", start-match, length);
do { putc(window[start++], stderr); } while (--length != 0);
}
}
#else
# define check_match(start, match, length)
#endif
/* ===========================================================================
* 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).
*/
local void fill_window()
{
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: */
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;
}
}
}
/* ===========================================================================
* 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, (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.
*/
local ulg deflate_fast()
{
IPos hash_head; /* head of the hash chain */
int flush; /* set if current block must be flushed */
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) {
/* 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) {
check_match(strstart, match_start, match_length);
flush = ct_tally(strstart-match_start, match_length - MIN_MATCH);
lookahead -= 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 (0, window[strstart]);
lookahead--;
strstart++;
}
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();
}
return 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.
*/
ulg deflate()
{
IPos hash_head; /* head of hash chain */
IPos prev_match; /* previous match */
int flush; /* 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 */
#ifdef DEBUG
extern long isize; /* byte length of input file, for debug only */
#endif
if (compr_level <= 3) return deflate_fast(); /* optimized for speed */
/* 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) {
/* 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) {
check_match(strstart-1, prev_match, prev_length);
flush = ct_tally(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;
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 (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]));
if (ct_tally (0, window[strstart-1])) {
FLUSH_BLOCK(0), block_start = strstart;
}
strstart++;
lookahead--;
} else {
/* There is no previous match to compare with, wait for
* the next step to decide.
*/
match_available = 1;
strstart++;
lookahead--;
}
Assert (strstart <= isize && lookahead <= isize, "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 (0, window[strstart-1]);
return FLUSH_BLOCK(1); /* eof */
}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -