diff options
Diffstat (limited to 'src/Common/zlib/trees.c')
-rw-r--r-- | src/Common/zlib/trees.c | 75 |
1 files changed, 27 insertions, 48 deletions
diff --git a/src/Common/zlib/trees.c b/src/Common/zlib/trees.c index 50cf4b45..f73fd99c 100644 --- a/src/Common/zlib/trees.c +++ b/src/Common/zlib/trees.c @@ -1,37 +1,37 @@ /* trees.c -- output deflated data using Huffman coding - * Copyright (C) 1995-2017 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 */ /* * ALGORITHM * * The "deflation" process uses several Huffman trees. The more * common source values are represented by shorter bit sequences. * * Each code tree is stored in a compressed form which is itself * a Huffman encoding of the lengths of all the code strings (in * ascending order by source values). The actual code strings are * reconstructed from the lengths in the inflate process, as described * in the deflate specification. * * REFERENCES * * Deutsch, L.P.,"'Deflate' Compressed Data Format Specification". * Available in ftp.uu.net:/pub/archiving/zip/doc/deflate-1.1.doc * * Storer, James A. * Data Compression: Methods and Theory, pp. 49-50. * Computer Science Press, 1988. ISBN 0-7167-8156-5. * * Sedgewick, R. * Algorithms, p290. * Addison-Wesley, 1983. ISBN 0-201-06672-6. */ /* @(#) $Id$ */ /* #define GEN_TREES_H */ #include "deflate.h" @@ -117,71 +117,71 @@ local int base_dist[D_CODES]; struct static_tree_desc_s { const ct_data *static_tree; /* static tree or NULL */ const intf *extra_bits; /* extra bits for each code or NULL */ int extra_base; /* base index for extra_bits */ int elems; /* max number of elements in the tree */ int max_length; /* max bit length for the codes */ }; local const static_tree_desc static_l_desc = {static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS}; local const static_tree_desc static_d_desc = {static_dtree, extra_dbits, 0, D_CODES, MAX_BITS}; local const static_tree_desc static_bl_desc = {(const ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS}; /* =========================================================================== * Local (static) routines in this file. */ local void tr_static_init OF((void)); local void init_block OF((deflate_state *s)); local void pqdownheap OF((deflate_state *s, ct_data *tree, int k)); local void gen_bitlen OF((deflate_state *s, tree_desc *desc)); local void gen_codes OF((ct_data *tree, int max_code, ushf *bl_count)); local void build_tree OF((deflate_state *s, tree_desc *desc)); local void scan_tree OF((deflate_state *s, ct_data *tree, int max_code)); 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, 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)); #ifdef GEN_TREES_H local void gen_trees_header OF((void)); #endif #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 /* !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); } #endif /* =========================================================================== * Output a short LSB first on the stream. * IN assertion: there is enough room in pendingBuf. */ #define put_short(s, w) { \ put_byte(s, (uch)((w) & 0xff)); \ put_byte(s, (uch)((ush)(w) >> 8)); \ } /* =========================================================================== * Send a value on a given number of bits. * IN assertion: length <= 16 and value fits in length bits. */ #ifdef ZLIB_DEBUG local void send_bits OF((deflate_state *s, int value, int length)); local void send_bits(s, value, length) deflate_state *s; @@ -384,71 +384,71 @@ void ZLIB_INTERNAL _tr_init(s) s->l_desc.dyn_tree = s->dyn_ltree; s->l_desc.stat_desc = &static_l_desc; s->d_desc.dyn_tree = s->dyn_dtree; s->d_desc.stat_desc = &static_d_desc; s->bl_desc.dyn_tree = s->bl_tree; s->bl_desc.stat_desc = &static_bl_desc; s->bi_buf = 0; s->bi_valid = 0; #ifdef ZLIB_DEBUG s->compressed_len = 0L; s->bits_sent = 0L; #endif /* Initialize the first block of the first file: */ init_block(s); } /* =========================================================================== * Initialize a new block. */ local void init_block(s) deflate_state *s; { int n; /* iterates over tree elements */ /* Initialize the trees. */ for (n = 0; n < L_CODES; n++) s->dyn_ltree[n].Freq = 0; for (n = 0; n < D_CODES; n++) s->dyn_dtree[n].Freq = 0; for (n = 0; n < BL_CODES; n++) s->bl_tree[n].Freq = 0; 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 /* Index within the heap array of least frequent node in the Huffman tree */ /* =========================================================================== * Remove the smallest element from the heap and recreate the heap with * one less element. Updates heap and heap_len. */ #define pqremove(s, tree, top) \ {\ top = s->heap[SMALLEST]; \ s->heap[SMALLEST] = s->heap[s->heap_len--]; \ pqdownheap(s, tree, SMALLEST); \ } /* =========================================================================== * Compares to subtrees, using the tree depth as tie breaker when * the subtrees have equal frequency. This minimizes the worst case length. */ #define smaller(tree, n, m, depth) \ (tree[n].Freq < tree[m].Freq || \ (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m])) /* =========================================================================== * Restore the heap property by moving down the tree starting at node k, * exchanging a node with the smallest of its two sons if necessary, stopping * when the heap property is re-established (each father smaller than its * two sons). */ local void pqdownheap(s, tree, k) deflate_state *s; ct_data *tree; /* the tree to restore */ int k; /* node to move down */ @@ -838,71 +838,72 @@ local void send_all_trees(s, lcodes, dcodes, blcodes) int rank; /* index in bl_order */ Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes"); Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES, "too many codes"); Tracev((stderr, "\nbl counts: ")); send_bits(s, lcodes-257, 5); /* not +255 as stated in appnote.txt */ send_bits(s, dcodes-1, 5); send_bits(s, blcodes-4, 4); /* not -3 as stated in appnote.txt */ for (rank = 0; rank < blcodes; rank++) { Tracev((stderr, "\nbl code %2d ", bl_order[rank])); send_bits(s, s->bl_tree[bl_order[rank]].Len, 3); } Tracev((stderr, "\nbl tree: sent %ld", s->bits_sent)); send_tree(s, (ct_data *)s->dyn_ltree, lcodes-1); /* literal tree */ Tracev((stderr, "\nlit tree: sent %ld", s->bits_sent)); send_tree(s, (ct_data *)s->dyn_dtree, dcodes-1); /* distance tree */ Tracev((stderr, "\ndist tree: sent %ld", s->bits_sent)); } /* =========================================================================== * Send a stored block */ 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 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); - zmemcpy(s->pending_buf + s->pending, (Bytef *)buf, 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 } /* =========================================================================== * 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. */ void ZLIB_INTERNAL _tr_align(s) deflate_state *s; { send_bits(s, STATIC_TREES<<1, 3); send_code(s, END_BLOCK, static_ltree); #ifdef ZLIB_DEBUG s->compressed_len += 10L; /* 3 for block type, 7 for EOB */ #endif bi_flush(s); } /* =========================================================================== * Determine the best encoding for the current block: dynamic trees, static @@ -915,268 +916,246 @@ void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last) 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 */ /* Build the Huffman trees unless a stored block is forced */ if (s->level > 0) { /* Check if the file is binary or text */ 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))); Tracev((stderr, "\nlit data: dyn %ld, stat %ld", s->opt_len, s->static_len)); build_tree(s, (tree_desc *)(&(s->d_desc))); Tracev((stderr, "\ndist data: dyn %ld, stat %ld", s->opt_len, s->static_len)); /* At this point, opt_len and static_len are the total bit lengths of * the compressed block data, excluding the tree representations. */ /* Build the bit length tree for the above two trees, and get the index * in bl_order of the last bit length code to send. */ max_blindex = build_bl_tree(s); /* Determine the best encoding. Compute the block lengths in bytes. */ opt_lenb = (s->opt_len+3+7)>>3; static_lenb = (s->static_len+3+7)>>3; 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; } else { Assert(buf != (char*)0, "lost buf"); opt_lenb = static_lenb = stored_len + 5; /* force a stored block */ } #ifdef FORCE_STORED if (buf != (char*)0) { /* force stored block */ #else if (stored_len+4 <= opt_lenb && buf != (char*)0) { /* 4: two words for the lengths */ #endif /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE. * Otherwise we can't have processed more than WSIZE input bytes since * the last block flush, because compression would have been * 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, 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)+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)+last, 3); send_all_trees(s, s->l_desc.max_code+1, s->d_desc.max_code+1, max_blindex+1); 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 } Assert (s->compressed_len == s->bits_sent, "bad compressed size"); /* The above check is made mod 2^32, for files larger than 512 MB * and uLong implemented on 32 bits. */ init_block(s); if (last) { bi_windup(s); #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*last)); } /* =========================================================================== * Save the match info and tally the frequency counts. Return true if * the current block must be flushed. */ 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) */ { - 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++; } else { s->matches++; /* Here, lc is the match length - MIN_MATCH */ dist--; /* dist = match distance - 1 */ Assert((ush)dist < (ush)MAX_DIST(s) && (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) && (ush)d_code(dist) < (ush)D_CODES, "_tr_tally: bad match"); 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); } /* =========================================================================== * Send the block data compressed using the given Huffman trees */ local void compress_block(s, ltree, dtree) deflate_state *s; 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) */ - 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)); } else { /* Here, lc is the match length - MIN_MATCH */ code = _length_code[lc]; send_code(s, code+LITERALS+1, ltree); /* send the length code */ extra = extra_lbits[code]; if (extra != 0) { lc -= base_length[code]; send_bits(s, lc, extra); /* send the extra length bits */ } dist--; /* dist is now the match distance - 1 */ code = d_code(dist); Assert (code < D_CODES, "bad d_code"); send_code(s, code, dtree); /* send the distance code */ extra = extra_dbits[code]; if (extra != 0) { 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: * (7 {BEL}, 8 {BS}, 11 {VT}, 12 {FF}, 26 {SUB}, 27 {ESC}). * IN assertion: the fields Freq of dyn_ltree are set. */ 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; for (n = 32; n < LITERALS; n++) 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; } /* =========================================================================== * Reverse the first len bits of a code, using straightforward code (a faster * method would use a table) * IN assertion: 1 <= len <= 15 */ local unsigned bi_reverse(code, len) unsigned code; /* the value to invert */ int len; /* its bit length */ { register unsigned res = 0; do { res |= code & 1; code >>= 1, res <<= 1; } while (--len > 0); return res >> 1; } /* =========================================================================== * Flush the bit buffer, keeping at most 7 bits in it. */ local void bi_flush(s) deflate_state *s; { if (s->bi_valid == 16) { put_short(s, s->bi_buf); s->bi_buf = 0; s->bi_valid = 0; } else if (s->bi_valid >= 8) { put_byte(s, (Byte)s->bi_buf); s->bi_buf >>= 8; |