/* trees.c -- output deflated data using Huffman coding
- * Copyright (C) 1995-2012 Jean-loup Gailly
+ * Copyright (C) 1995-2021 Jean-loup Gailly
* detect_data_type() function provided freely by Cosmin Truta, 2006
* For conditions of distribution and use, see copyright notice in zlib.h
*/
local void compress_block OF((deflate_state *s, const ct_data *ltree,
const ct_data *dtree));
local int detect_data_type OF((deflate_state *s));
-local unsigned bi_reverse OF((unsigned value, int length));
+local unsigned bi_reverse OF((unsigned code, int len));
local void bi_windup OF((deflate_state *s));
local void bi_flush OF((deflate_state *s));
-local void copy_block OF((deflate_state *s, charf *buf, unsigned len,
- int header));
#ifdef GEN_TREES_H
local void gen_trees_header OF((void));
#define send_bits(s, value, length) \
{ int len = length;\
if (s->bi_valid > (int)Buf_size - len) {\
- int val = value;\
+ int val = (int)value;\
s->bi_buf |= (ush)val << s->bi_valid;\
put_short(s, s->bi_buf);\
s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
s->dyn_ltree[END_BLOCK].Freq = 1;
s->opt_len = s->static_len = 0L;
- s->last_lit = s->matches = 0;
+ s->sym_next = s->matches = 0;
}
#define SMALLEST 1
xbits = 0;
if (n >= base) xbits = extra[n-base];
f = tree[n].Freq;
- s->opt_len += (ulg)f * (bits + xbits);
- if (stree) s->static_len += (ulg)f * (stree[n].Len + xbits);
+ s->opt_len += (ulg)f * (unsigned)(bits + xbits);
+ if (stree) s->static_len += (ulg)f * (unsigned)(stree[n].Len + xbits);
}
if (overflow == 0) return;
- Trace((stderr,"\nbit length overflow\n"));
+ Tracev((stderr,"\nbit length overflow\n"));
/* This happens for example on obj2 and pic of the Calgary corpus */
/* Find the first bit length which could increase: */
m = s->heap[--h];
if (m > max_code) continue;
if ((unsigned) tree[m].Len != (unsigned) bits) {
- Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits));
- s->opt_len += ((long)bits - (long)tree[m].Len)
- *(long)tree[m].Freq;
+ Tracev((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits));
+ s->opt_len += ((ulg)bits - tree[m].Len) * tree[m].Freq;
tree[m].Len = (ush)bits;
}
n--;
ushf *bl_count; /* number of codes at each bit length */
{
ush next_code[MAX_BITS+1]; /* next code value for each bit length */
- ush code = 0; /* running code value */
+ unsigned code = 0; /* running code value */
int bits; /* bit index */
int n; /* code index */
* without bit reversal.
*/
for (bits = 1; bits <= MAX_BITS; bits++) {
- next_code[bits] = code = (code + bl_count[bits-1]) << 1;
+ code = (code + bl_count[bits-1]) << 1;
+ next_code[bits] = (ush)code;
}
/* Check that the bit counts in bl_count are consistent. The last code
* must be all ones.
int len = tree[n].Len;
if (len == 0) continue;
/* Now reverse the bits */
- tree[n].Code = bi_reverse(next_code[len]++, len);
+ tree[n].Code = (ush)bi_reverse(next_code[len]++, len);
Tracecv(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ",
n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1));
if (s->bl_tree[bl_order[max_blindex]].Len != 0) break;
}
/* Update opt_len to include the bit length tree and counts */
- s->opt_len += 3*(max_blindex+1) + 5+5+4;
+ s->opt_len += 3*((ulg)max_blindex+1) + 5+5+4;
Tracev((stderr, "\ndyn trees: dyn %ld, stat %ld",
s->opt_len, s->static_len));
int last; /* one if this is the last block for a file */
{
send_bits(s, (STORED_BLOCK<<1)+last, 3); /* send block type */
+ bi_windup(s); /* align on byte boundary */
+ put_short(s, (ush)stored_len);
+ put_short(s, (ush)~stored_len);
+ if (stored_len)
+ zmemcpy(s->pending_buf + s->pending, (Bytef *)buf, stored_len);
+ s->pending += stored_len;
#ifdef ZLIB_DEBUG
s->compressed_len = (s->compressed_len + 3 + 7) & (ulg)~7L;
s->compressed_len += (stored_len + 4) << 3;
+ s->bits_sent += 2*16;
+ s->bits_sent += stored_len<<3;
#endif
- copy_block(s, buf, (unsigned)stored_len, 1); /* with header */
}
/* ===========================================================================
/* ===========================================================================
* Determine the best encoding for the current block: dynamic trees, static
- * trees or store, and output the encoded block to the zip file.
+ * trees or store, and write out the encoded block.
*/
void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
deflate_state *s;
Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ",
opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len,
- s->last_lit));
+ s->sym_next / 3));
if (static_lenb <= opt_lenb) opt_lenb = static_lenb;
unsigned dist; /* distance of matched string */
unsigned lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */
{
- s->d_buf[s->last_lit] = (ush)dist;
- s->l_buf[s->last_lit++] = (uch)lc;
+ s->sym_buf[s->sym_next++] = dist;
+ s->sym_buf[s->sym_next++] = dist >> 8;
+ s->sym_buf[s->sym_next++] = lc;
if (dist == 0) {
/* lc is the unmatched char */
s->dyn_ltree[lc].Freq++;
s->dyn_ltree[_length_code[lc]+LITERALS+1].Freq++;
s->dyn_dtree[d_code(dist)].Freq++;
}
-
-#ifdef TRUNCATE_BLOCK
- /* Try to guess if it is profitable to stop the current block here */
- if ((s->last_lit & 0x1fff) == 0 && s->level > 2) {
- /* Compute an upper bound for the compressed length */
- ulg out_length = (ulg)s->last_lit*8L;
- ulg in_length = (ulg)((long)s->strstart - s->block_start);
- int dcode;
- for (dcode = 0; dcode < D_CODES; dcode++) {
- out_length += (ulg)s->dyn_dtree[dcode].Freq *
- (5L+extra_dbits[dcode]);
- }
- out_length >>= 3;
- Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ",
- s->last_lit, in_length, out_length,
- 100L - out_length*100L/in_length));
- if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1;
- }
-#endif
- return (s->last_lit == s->lit_bufsize-1);
- /* We avoid equality with lit_bufsize because of wraparound at 64K
- * on 16 bit machines and because stored blocks are restricted to
- * 64K-1 bytes.
- */
+ return (s->sym_next == s->sym_end);
}
/* ===========================================================================
{
unsigned dist; /* distance of matched string */
int lc; /* match length or unmatched char (if dist == 0) */
- unsigned lx = 0; /* running index in l_buf */
+ unsigned sx = 0; /* running index in sym_buf */
unsigned code; /* the code to send */
int extra; /* number of extra bits to send */
- if (s->last_lit != 0) do {
- dist = s->d_buf[lx];
- lc = s->l_buf[lx++];
+ if (s->sym_next != 0) do {
+ dist = s->sym_buf[sx++] & 0xff;
+ dist += (unsigned)(s->sym_buf[sx++] & 0xff) << 8;
+ lc = s->sym_buf[sx++];
if (dist == 0) {
send_code(s, lc, ltree); /* send a literal byte */
Tracecv(isgraph(lc), (stderr," '%c' ", lc));
send_code(s, code, dtree); /* send the distance code */
extra = extra_dbits[code];
if (extra != 0) {
- dist -= base_dist[code];
+ dist -= (unsigned)base_dist[code];
send_bits(s, dist, extra); /* send the extra distance bits */
}
} /* literal or match pair ? */
- /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */
- Assert((uInt)(s->pending) < s->lit_bufsize + 2*lx,
- "pendingBuf overflow");
+ /* Check that the overlay between pending_buf and sym_buf is ok: */
+ Assert(s->pending < s->lit_bufsize + sx, "pendingBuf overflow");
- } while (lx < s->last_lit);
+ } while (sx < s->sym_next);
send_code(s, END_BLOCK, ltree);
}
* Check if the data type is TEXT or BINARY, using the following algorithm:
* - TEXT if the two conditions below are satisfied:
* a) There are no non-portable control characters belonging to the
- * "black list" (0..6, 14..25, 28..31).
+ * "block list" (0..6, 14..25, 28..31).
* b) There is at least one printable character belonging to the
- * "white list" (9 {TAB}, 10 {LF}, 13 {CR}, 32..255).
+ * "allow list" (9 {TAB}, 10 {LF}, 13 {CR}, 32..255).
* - BINARY otherwise.
* - The following partially-portable control characters form a
* "gray list" that is ignored in this detection algorithm:
local int detect_data_type(s)
deflate_state *s;
{
- /* black_mask is the bit mask of black-listed bytes
+ /* block_mask is the bit mask of block-listed bytes
* set bits 0..6, 14..25, and 28..31
* 0xf3ffc07f = binary 11110011111111111100000001111111
*/
- unsigned long black_mask = 0xf3ffc07fUL;
+ unsigned long block_mask = 0xf3ffc07fUL;
int n;
- /* Check for non-textual ("black-listed") bytes. */
- for (n = 0; n <= 31; n++, black_mask >>= 1)
- if ((black_mask & 1) && (s->dyn_ltree[n].Freq != 0))
+ /* Check for non-textual ("block-listed") bytes. */
+ for (n = 0; n <= 31; n++, block_mask >>= 1)
+ if ((block_mask & 1) && (s->dyn_ltree[n].Freq != 0))
return Z_BINARY;
- /* Check for textual ("white-listed") bytes. */
+ /* Check for textual ("allow-listed") bytes. */
if (s->dyn_ltree[9].Freq != 0 || s->dyn_ltree[10].Freq != 0
|| s->dyn_ltree[13].Freq != 0)
return Z_TEXT;
if (s->dyn_ltree[n].Freq != 0)
return Z_TEXT;
- /* There are no "black-listed" or "white-listed" bytes:
+ /* There are no "block-listed" or "allow-listed" bytes:
* this stream either is empty or has tolerated ("gray-listed") bytes only.
*/
return Z_BINARY;
s->bits_sent = (s->bits_sent+7) & ~7;
#endif
}
-
-/* ===========================================================================
- * Copy a stored block, storing first the length and its
- * one's complement if requested.
- */
-local void copy_block(s, buf, len, header)
- deflate_state *s;
- charf *buf; /* the input data */
- unsigned len; /* its length */
- int header; /* true if block header must be written */
-{
- bi_windup(s); /* align on byte boundary */
-
- if (header) {
- put_short(s, (ush)len);
- put_short(s, (ush)~len);
-#ifdef ZLIB_DEBUG
- s->bits_sent += 2*16;
-#endif
- }
-#ifdef ZLIB_DEBUG
- s->bits_sent += (ulg)len<<3;
-#endif
- while (len--) {
- put_byte(s, *buf++);
- }
-}