aboutsummaryrefslogtreecommitdiff
path: root/lib/libz/trees.c
diff options
context:
space:
mode:
Diffstat (limited to 'lib/libz/trees.c')
-rw-r--r--lib/libz/trees.c245
1 files changed, 114 insertions, 131 deletions
diff --git a/lib/libz/trees.c b/lib/libz/trees.c
index c163626..0f43a16 100644
--- a/lib/libz/trees.c
+++ b/lib/libz/trees.c
@@ -1,6 +1,7 @@
-/* $OpenBSD: trees.c,v 1.8 2005/07/20 15:56:41 millert Exp $ */
+/* $OpenBSD: trees.c,v 1.9 2021/07/04 14:24:49 tb Exp $ */
/* trees.c -- output deflated data using Huffman coding
- * Copyright (C) 1995-2005 Jean-loup Gailly
+ * Copyright (C) 1995-2017 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
*/
@@ -30,12 +31,11 @@
* Addison-Wesley, 1983. ISBN 0-201-06672-6.
*/
-
/* #define GEN_TREES_H */
#include "deflate.h"
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
# include <ctype.h>
#endif
@@ -73,11 +73,6 @@ local const uch bl_order[BL_CODES]
* probability, to avoid transmitting the lengths for unused bit length codes.
*/
-#define Buf_size (8 * 2*sizeof(char))
-/* Number of bits used within bi_buf. (bi_buf might be implemented on
- * more than 16 bits on some systems.)
- */
-
/* ===========================================================================
* Local data. These are initialized only once.
*/
@@ -126,13 +121,13 @@ struct static_tree_desc_s {
int max_length; /* max bit length for the codes */
};
-local static_tree_desc static_l_desc =
+local const static_tree_desc static_l_desc =
{static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS};
-local static_tree_desc static_d_desc =
+local const static_tree_desc static_d_desc =
{static_dtree, extra_dbits, 0, D_CODES, MAX_BITS};
-local static_tree_desc static_bl_desc =
+local const static_tree_desc static_bl_desc =
{(const ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS};
/* ===========================================================================
@@ -150,24 +145,22 @@ local void send_tree OF((deflate_state *s, ct_data *tree, int max_code));
local int build_bl_tree OF((deflate_state *s));
local void send_all_trees OF((deflate_state *s, int lcodes, int dcodes,
int blcodes));
-local void compress_block OF((deflate_state *s, ct_data *ltree,
- ct_data *dtree));
-local void set_data_type OF((deflate_state *s));
+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 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));
#endif
-#ifndef DEBUG
+#ifndef ZLIB_DEBUG
# define send_code(s, c, tree) send_bits(s, tree[c].Code, tree[c].Len)
/* Send a code of the given tree. c and tree must not have side effects */
-#else /* DEBUG */
+#else /* !ZLIB_DEBUG */
# define send_code(s, c, tree) \
{ if (z_verbose>2) fprintf(stderr,"\ncd %3d ",(c)); \
send_bits(s, tree[c].Code, tree[c].Len); }
@@ -186,7 +179,7 @@ local void gen_trees_header OF((void));
* Send a value on a given number of bits.
* IN assertion: length <= 16 and value fits in length bits.
*/
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
local void send_bits OF((deflate_state *s, int value, int length));
local void send_bits(s, value, length)
@@ -203,31 +196,31 @@ local void send_bits(s, value, length)
* unused bits in value.
*/
if (s->bi_valid > (int)Buf_size - length) {
- s->bi_buf |= (value << s->bi_valid);
+ s->bi_buf |= (ush)value << s->bi_valid;
put_short(s, s->bi_buf);
s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
s->bi_valid += length - Buf_size;
} else {
- s->bi_buf |= value << s->bi_valid;
+ s->bi_buf |= (ush)value << s->bi_valid;
s->bi_valid += length;
}
}
-#else /* !DEBUG */
+#else /* !ZLIB_DEBUG */
#define send_bits(s, value, length) \
{ int len = length;\
if (s->bi_valid > (int)Buf_size - len) {\
- int val = value;\
- s->bi_buf |= (val << s->bi_valid);\
+ 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->bi_valid += len - Buf_size;\
} else {\
- s->bi_buf |= (value) << s->bi_valid;\
+ s->bi_buf |= (ush)(value) << s->bi_valid;\
s->bi_valid += len;\
}\
}
-#endif /* DEBUG */
+#endif /* ZLIB_DEBUG */
/* the arguments must not have side effects */
@@ -250,11 +243,13 @@ local void tr_static_init()
if (static_init_done) return;
/* For some embedded targets, global variables are not initialized: */
+#ifdef NO_INIT_GLOBAL_POINTERS
static_l_desc.static_tree = static_ltree;
static_l_desc.extra_bits = extra_lbits;
static_d_desc.static_tree = static_dtree;
static_d_desc.extra_bits = extra_dbits;
static_bl_desc.extra_bits = extra_blbits;
+#endif
/* Initialize the mapping length (0..255) -> length code (0..28) */
length = 0;
@@ -319,7 +314,7 @@ local void tr_static_init()
* Genererate the file trees.h describing the static trees.
*/
#ifdef GEN_TREES_H
-# ifndef DEBUG
+# ifndef ZLIB_DEBUG
# include <stdio.h>
# endif
@@ -348,13 +343,14 @@ void gen_trees_header()
static_dtree[i].Len, SEPARATOR(i, D_CODES-1, 5));
}
- fprintf(header, "const uch _dist_code[DIST_CODE_LEN] = {\n");
+ fprintf(header, "const uch ZLIB_INTERNAL _dist_code[DIST_CODE_LEN] = {\n");
for (i = 0; i < DIST_CODE_LEN; i++) {
fprintf(header, "%2u%s", _dist_code[i],
SEPARATOR(i, DIST_CODE_LEN-1, 20));
}
- fprintf(header, "const uch _length_code[MAX_MATCH-MIN_MATCH+1]= {\n");
+ fprintf(header,
+ "const uch ZLIB_INTERNAL _length_code[MAX_MATCH-MIN_MATCH+1]= {\n");
for (i = 0; i < MAX_MATCH-MIN_MATCH+1; i++) {
fprintf(header, "%2u%s", _length_code[i],
SEPARATOR(i, MAX_MATCH-MIN_MATCH, 20));
@@ -379,7 +375,7 @@ void gen_trees_header()
/* ===========================================================================
* Initialize the tree data structures for a new zlib stream.
*/
-void _tr_init(s)
+void ZLIB_INTERNAL _tr_init(s)
deflate_state *s;
{
tr_static_init();
@@ -395,8 +391,7 @@ void _tr_init(s)
s->bi_buf = 0;
s->bi_valid = 0;
- s->last_eob_len = 8; /* enough lookahead for inflate */
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
s->compressed_len = 0L;
s->bits_sent = 0L;
#endif
@@ -524,12 +519,12 @@ local void gen_bitlen(s, desc)
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: */
@@ -556,9 +551,8 @@ local void gen_bitlen(s, desc)
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--;
@@ -580,7 +574,7 @@ local void gen_codes (tree, max_code, bl_count)
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 */
@@ -588,7 +582,8 @@ local void gen_codes (tree, max_code, bl_count)
* 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.
@@ -601,7 +596,7 @@ local void gen_codes (tree, max_code, bl_count)
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));
@@ -823,7 +818,7 @@ local int build_bl_tree(s)
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));
@@ -864,65 +859,59 @@ local void send_all_trees(s, lcodes, dcodes, blcodes)
/* ===========================================================================
* Send a stored block
*/
-void _tr_stored_block(s, buf, stored_len, eof)
+void ZLIB_INTERNAL _tr_stored_block(s, buf, stored_len, last)
deflate_state *s;
charf *buf; /* input block */
ulg stored_len; /* length of input block */
- int eof; /* true if this is the last block for a file */
+ int last; /* one if this is the last block for a file */
{
- send_bits(s, (STORED_BLOCK<<1)+eof, 3); /* send block type */
-#ifdef DEBUG
+ 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);
+ 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 */
+}
+
+/* ===========================================================================
+ * Flush the bits in the bit buffer to pending output (leaves at most 7 bits)
+ */
+void ZLIB_INTERNAL _tr_flush_bits(s)
+ deflate_state *s;
+{
+ bi_flush(s);
}
/* ===========================================================================
* Send one empty static block to give enough lookahead for inflate.
* This takes 10 bits, of which 7 may remain in the bit buffer.
- * The current inflate code requires 9 bits of lookahead. If the
- * last two codes for the previous block (real code plus EOB) were coded
- * on 5 bits or less, inflate may have only 5+3 bits of lookahead to decode
- * the last real code. In this case we send two empty static blocks instead
- * of one. (There are no problems if the previous block is stored or fixed.)
- * To simplify the code, we assume the worst case of last real code encoded
- * on one bit only.
*/
-void _tr_align(s)
+void ZLIB_INTERNAL _tr_align(s)
deflate_state *s;
{
send_bits(s, STATIC_TREES<<1, 3);
send_code(s, END_BLOCK, static_ltree);
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
s->compressed_len += 10L; /* 3 for block type, 7 for EOB */
#endif
bi_flush(s);
- /* Of the 10 bits for the empty block, we have already sent
- * (10 - bi_valid) bits. The lookahead for the last real code (before
- * the EOB of the previous block) was thus at least one plus the length
- * of the EOB plus what we have just sent of the empty static block.
- */
- if (1 + s->last_eob_len + 10 - s->bi_valid < 9) {
- send_bits(s, STATIC_TREES<<1, 3);
- send_code(s, END_BLOCK, static_ltree);
-#ifdef DEBUG
- s->compressed_len += 10L;
-#endif
- bi_flush(s);
- }
- s->last_eob_len = 7;
}
/* ===========================================================================
* 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 _tr_flush_block(s, buf, stored_len, eof)
+void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last)
deflate_state *s;
charf *buf; /* input block, or NULL if too old */
ulg stored_len; /* length of input block */
- int eof; /* true if this is the last block for a file */
+ int last; /* one if this is the last block for a file */
{
ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */
int max_blindex = 0; /* index of last bit length code of non zero freq */
@@ -931,8 +920,8 @@ void _tr_flush_block(s, buf, stored_len, eof)
if (s->level > 0) {
/* Check if the file is binary or text */
- if (stored_len > 0 && s->strm->data_type == Z_UNKNOWN)
- set_data_type(s);
+ if (s->strm->data_type == Z_UNKNOWN)
+ s->strm->data_type = detect_data_type(s);
/* Construct the literal and distance trees */
build_tree(s, (tree_desc *)(&(s->l_desc)));
@@ -978,24 +967,26 @@ void _tr_flush_block(s, buf, stored_len, eof)
* successful. If LIT_BUFSIZE <= WSIZE, it is never too late to
* transform a block into a stored block.
*/
- _tr_stored_block(s, buf, stored_len, eof);
+ _tr_stored_block(s, buf, stored_len, last);
#ifdef FORCE_STATIC
} else if (static_lenb >= 0) { /* force static trees */
#else
} else if (s->strategy == Z_FIXED || static_lenb == opt_lenb) {
#endif
- send_bits(s, (STATIC_TREES<<1)+eof, 3);
- compress_block(s, (ct_data *)static_ltree, (ct_data *)static_dtree);
-#ifdef DEBUG
+ send_bits(s, (STATIC_TREES<<1)+last, 3);
+ compress_block(s, (const ct_data *)static_ltree,
+ (const ct_data *)static_dtree);
+#ifdef ZLIB_DEBUG
s->compressed_len += 3 + s->static_len;
#endif
} else {
- send_bits(s, (DYN_TREES<<1)+eof, 3);
+ send_bits(s, (DYN_TREES<<1)+last, 3);
send_all_trees(s, s->l_desc.max_code+1, s->d_desc.max_code+1,
max_blindex+1);
- compress_block(s, (ct_data *)s->dyn_ltree, (ct_data *)s->dyn_dtree);
-#ifdef DEBUG
+ compress_block(s, (const ct_data *)s->dyn_ltree,
+ (const ct_data *)s->dyn_dtree);
+#ifdef ZLIB_DEBUG
s->compressed_len += 3 + s->opt_len;
#endif
}
@@ -1005,21 +996,21 @@ void _tr_flush_block(s, buf, stored_len, eof)
*/
init_block(s);
- if (eof) {
+ if (last) {
bi_windup(s);
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
s->compressed_len += 7; /* align on byte boundary */
#endif
}
Tracev((stderr,"\ncomprlen %lu(%lu) ", s->compressed_len>>3,
- s->compressed_len-7*eof));
+ s->compressed_len-7*last));
}
/* ===========================================================================
* Save the match info and tally the frequency counts. Return true if
* the current block must be flushed.
*/
-int _tr_tally (s, dist, lc)
+int ZLIB_INTERNAL _tr_tally (s, dist, lc)
deflate_state *s;
unsigned dist; /* distance of matched string */
unsigned lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */
@@ -1071,8 +1062,8 @@ int _tr_tally (s, dist, lc)
*/
local void compress_block(s, ltree, dtree)
deflate_state *s;
- ct_data *ltree; /* literal tree */
- ct_data *dtree; /* distance tree */
+ const ct_data *ltree; /* literal tree */
+ const ct_data *dtree; /* distance tree */
{
unsigned dist; /* distance of matched string */
int lc; /* match length or unmatched char (if dist == 0) */
@@ -1102,7 +1093,7 @@ local void compress_block(s, ltree, dtree)
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 ? */
@@ -1114,28 +1105,48 @@ local void compress_block(s, ltree, dtree)
} while (lx < s->last_lit);
send_code(s, END_BLOCK, ltree);
- s->last_eob_len = ltree[END_BLOCK].Len;
}
/* ===========================================================================
- * Set the data type to BINARY or TEXT, using a crude approximation:
- * set it to Z_TEXT if all symbols are either printable characters (33 to 255)
- * or white spaces (9 to 13, or 32); or set it to Z_BINARY otherwise.
+ * 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).
+ * b) There is at least one printable character belonging to the
+ * "white 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:
+ * (7 {BEL}, 8 {BS}, 11 {VT}, 12 {FF}, 26 {SUB}, 27 {ESC}).
* IN assertion: the fields Freq of dyn_ltree are set.
*/
-local void set_data_type(s)
+local int detect_data_type(s)
deflate_state *s;
{
+ /* black_mask is the bit mask of black-listed bytes
+ * set bits 0..6, 14..25, and 28..31
+ * 0xf3ffc07f = binary 11110011111111111100000001111111
+ */
+ unsigned long black_mask = 0xf3ffc07fUL;
int n;
- for (n = 0; n < 9; 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))
+ return Z_BINARY;
+
+ /* Check for textual ("white-listed") bytes. */
+ if (s->dyn_ltree[9].Freq != 0 || s->dyn_ltree[10].Freq != 0
+ || s->dyn_ltree[13].Freq != 0)
+ return Z_TEXT;
+ for (n = 32; n < LITERALS; n++)
if (s->dyn_ltree[n].Freq != 0)
- break;
- if (n == 9)
- for (n = 14; n < 32; n++)
- if (s->dyn_ltree[n].Freq != 0)
- break;
- s->strm->data_type = (n == 32) ? Z_TEXT : Z_BINARY;
+ return Z_TEXT;
+
+ /* There are no "black-listed" or "white-listed" bytes:
+ * this stream either is empty or has tolerated ("gray-listed") bytes only.
+ */
+ return Z_BINARY;
}
/* ===========================================================================
@@ -1185,35 +1196,7 @@ local void bi_windup(s)
}
s->bi_buf = 0;
s->bi_valid = 0;
-#ifdef DEBUG
+#ifdef ZLIB_DEBUG
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 */
- s->last_eob_len = 8; /* enough lookahead for inflate */
-
- if (header) {
- put_short(s, (ush)len);
- put_short(s, (ush)~len);
-#ifdef DEBUG
- s->bits_sent += 2*16;
-#endif
- }
-#ifdef DEBUG
- s->bits_sent += (ulg)len<<3;
-#endif
- while (len--) {
- put_byte(s, *buf++);
- }
-}
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-19 10:00:47 +0000