pkgsrc-Changes-HG archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

[pkgsrc/trunk]: pkgsrc/devel/zlib zlib: apply patches directly on in-tree sou...



details:   https://anonhg.NetBSD.org/pkgsrc/rev/d4cdec23486d
branches:  trunk
changeset: 375737:d4cdec23486d
user:      wiz <wiz%pkgsrc.org@localhost>
date:      Thu Mar 24 07:57:47 2022 +0000

description:
zlib: apply patches directly on in-tree sources

diffstat:

 devel/zlib/files/deflate.c         |   76 ++++++++++++----
 devel/zlib/files/deflate.h         |   27 ++---
 devel/zlib/files/trees.c           |   52 +++--------
 devel/zlib/patches/patch-deflate.c |  158 -------------------------------------
 devel/zlib/patches/patch-deflate.h |   61 --------------
 devel/zlib/patches/patch-trees.c   |  103 ------------------------
 6 files changed, 82 insertions(+), 395 deletions(-)

diffs (truncated from 671 to 300 lines):

diff -r 3e997cad3222 -r d4cdec23486d devel/zlib/files/deflate.c
--- a/devel/zlib/files/deflate.c        Thu Mar 24 07:56:00 2022 +0000
+++ b/devel/zlib/files/deflate.c        Thu Mar 24 07:57:47 2022 +0000
@@ -47,7 +47,7 @@
  *
  */
 
-/* @(#) $Id: deflate.c,v 1.5 2017/04/04 08:57:33 adam Exp $ */
+/* @(#) $Id: deflate.c,v 1.6 2022/03/24 07:57:47 wiz Exp $ */
 
 #include "deflate.h"
 
@@ -252,11 +252,6 @@
     int wrap = 1;
     static const char my_version[] = ZLIB_VERSION;
 
-    ushf *overlay;
-    /* We overlay pending_buf and d_buf+l_buf. This works since the average
-     * output size for (length,distance) codes is <= 24 bits.
-     */
-
     if (version == Z_NULL || version[0] != my_version[0] ||
         stream_size != sizeof(z_stream)) {
         return Z_VERSION_ERROR;
@@ -326,9 +321,47 @@
 
     s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */
 
-    overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2);
-    s->pending_buf = (uchf *) overlay;
-    s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L);
+    /* We overlay pending_buf and sym_buf. This works since the average size
+     * for length/distance pairs over any compressed block is assured to be 31
+     * bits or less.
+     *
+     * Analysis: The longest fixed codes are a length code of 8 bits plus 5
+     * extra bits, for lengths 131 to 257. The longest fixed distance codes are
+     * 5 bits plus 13 extra bits, for distances 16385 to 32768. The longest
+     * possible fixed-codes length/distance pair is then 31 bits total.
+     *
+     * sym_buf starts one-fourth of the way into pending_buf. So there are
+     * three bytes in sym_buf for every four bytes in pending_buf. Each symbol
+     * in sym_buf is three bytes -- two for the distance and one for the
+     * literal/length. As each symbol is consumed, the pointer to the next
+     * sym_buf value to read moves forward three bytes. From that symbol, up to
+     * 31 bits are written to pending_buf. The closest the written pending_buf
+     * bits gets to the next sym_buf symbol to read is just before the last
+     * code is written. At that time, 31*(n-2) bits have been written, just
+     * after 24*(n-2) bits have been consumed from sym_buf. sym_buf starts at
+     * 8*n bits into pending_buf. (Note that the symbol buffer fills when n-1
+     * symbols are written.) The closest the writing gets to what is unread is
+     * then n+14 bits. Here n is lit_bufsize, which is 16384 by default, and
+     * can range from 128 to 32768.
+     *
+     * Therefore, at a minimum, there are 142 bits of space between what is
+     * written and what is read in the overlain buffers, so the symbols cannot
+     * be overwritten by the compressed data. That space is actually 139 bits,
+     * due to the three-bit fixed-code block header.
+     *
+     * That covers the case where either Z_FIXED is specified, forcing fixed
+     * codes, or when the use of fixed codes is chosen, because that choice
+     * results in a smaller compressed block than dynamic codes. That latter
+     * condition then assures that the above analysis also covers all dynamic
+     * blocks. A dynamic-code block will only be chosen to be emitted if it has
+     * fewer bits than a fixed-code block would for the same set of symbols.
+     * Therefore its average symbol length is assured to be less than 31. So
+     * the compressed data for a dynamic block also cannot overwrite the
+     * symbols from which it is being constructed.
+     */
+
+    s->pending_buf = (uchf *) ZALLOC(strm, s->lit_bufsize, 4);
+    s->pending_buf_size = (ulg)s->lit_bufsize * 4;
 
     if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL ||
         s->pending_buf == Z_NULL) {
@@ -337,8 +370,12 @@
         deflateEnd (strm);
         return Z_MEM_ERROR;
     }
-    s->d_buf = overlay + s->lit_bufsize/sizeof(ush);
-    s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize;
+    s->sym_buf = s->pending_buf + s->lit_bufsize;
+    s->sym_end = (s->lit_bufsize - 1) * 3;
+    /* We avoid equality with lit_bufsize*3 because of wraparound at 64K
+     * on 16 bit machines and because stored blocks are restricted to
+     * 64K-1 bytes.
+     */
 
     s->level = level;
     s->strategy = strategy;
@@ -549,7 +586,7 @@
 
     if (deflateStateCheck(strm)) return Z_STREAM_ERROR;
     s = strm->state;
-    if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3))
+    if (s->sym_buf < s->pending_out + ((Buf_size + 7) >> 3))
         return Z_BUF_ERROR;
     do {
         put = Buf_size - s->bi_valid;
@@ -1108,7 +1145,6 @@
 #else
     deflate_state *ds;
     deflate_state *ss;
-    ushf *overlay;
 
 
     if (deflateStateCheck(source) || dest == Z_NULL) {
@@ -1128,8 +1164,7 @@
     ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte));
     ds->prev   = (Posf *)  ZALLOC(dest, ds->w_size, sizeof(Pos));
     ds->head   = (Posf *)  ZALLOC(dest, ds->hash_size, sizeof(Pos));
-    overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2);
-    ds->pending_buf = (uchf *) overlay;
+    ds->pending_buf = (uchf *) ZALLOC(dest, ds->lit_bufsize, 4);
 
     if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL ||
         ds->pending_buf == Z_NULL) {
@@ -1143,8 +1178,7 @@
     zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size);
 
     ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf);
-    ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush);
-    ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize;
+    ds->sym_buf = ds->pending_buf + ds->lit_bufsize;
 
     ds->l_desc.dyn_tree = ds->dyn_ltree;
     ds->d_desc.dyn_tree = ds->dyn_dtree;
@@ -1912,7 +1946,7 @@
         FLUSH_BLOCK(s, 1);
         return finish_done;
     }
-    if (s->last_lit)
+    if (s->sym_next)
         FLUSH_BLOCK(s, 0);
     return block_done;
 }
@@ -2043,7 +2077,7 @@
         FLUSH_BLOCK(s, 1);
         return finish_done;
     }
-    if (s->last_lit)
+    if (s->sym_next)
         FLUSH_BLOCK(s, 0);
     return block_done;
 }
@@ -2118,7 +2152,7 @@
         FLUSH_BLOCK(s, 1);
         return finish_done;
     }
-    if (s->last_lit)
+    if (s->sym_next)
         FLUSH_BLOCK(s, 0);
     return block_done;
 }
@@ -2157,7 +2191,7 @@
         FLUSH_BLOCK(s, 1);
         return finish_done;
     }
-    if (s->last_lit)
+    if (s->sym_next)
         FLUSH_BLOCK(s, 0);
     return block_done;
 }
diff -r 3e997cad3222 -r d4cdec23486d devel/zlib/files/deflate.h
--- a/devel/zlib/files/deflate.h        Thu Mar 24 07:56:00 2022 +0000
+++ b/devel/zlib/files/deflate.h        Thu Mar 24 07:57:47 2022 +0000
@@ -8,7 +8,7 @@
    subject to change. Applications should only use zlib.h.
  */
 
-/* @(#) $Id: deflate.h,v 1.5 2017/04/04 08:57:33 adam Exp $ */
+/* @(#) $Id: deflate.h,v 1.6 2022/03/24 07:57:47 wiz Exp $ */
 
 #ifndef DEFLATE_H
 #define DEFLATE_H
@@ -217,7 +217,7 @@
     /* Depth of each subtree used as tie breaker for trees of equal frequency
      */
 
-    uchf *l_buf;          /* buffer for literals or lengths */
+    uchf *sym_buf;        /* buffer for distances and literals/lengths */
 
     uInt  lit_bufsize;
     /* Size of match buffer for literals/lengths.  There are 4 reasons for
@@ -239,13 +239,8 @@
      *   - I can't count above 4
      */
 
-    uInt last_lit;      /* running index in l_buf */
-
-    ushf *d_buf;
-    /* Buffer for distances. To simplify the code, d_buf and l_buf have
-     * the same number of elements. To use different lengths, an extra flag
-     * array would be necessary.
-     */
+    uInt sym_next;      /* running index in sym_buf */
+    uInt sym_end;       /* symbol table full when sym_next reaches this */
 
     ulg opt_len;        /* bit length of current block with optimal trees */
     ulg static_len;     /* bit length of current block with static trees */
@@ -325,20 +320,22 @@
 
 # define _tr_tally_lit(s, c, flush) \
   { uch cc = (c); \
-    s->d_buf[s->last_lit] = 0; \
-    s->l_buf[s->last_lit++] = cc; \
+    s->sym_buf[s->sym_next++] = 0; \
+    s->sym_buf[s->sym_next++] = 0; \
+    s->sym_buf[s->sym_next++] = cc; \
     s->dyn_ltree[cc].Freq++; \
-    flush = (s->last_lit == s->lit_bufsize-1); \
+    flush = (s->sym_next == s->sym_end); \
    }
 # define _tr_tally_dist(s, distance, length, flush) \
   { uch len = (uch)(length); \
     ush dist = (ush)(distance); \
-    s->d_buf[s->last_lit] = dist; \
-    s->l_buf[s->last_lit++] = len; \
+    s->sym_buf[s->sym_next++] = dist; \
+    s->sym_buf[s->sym_next++] = dist >> 8; \
+    s->sym_buf[s->sym_next++] = len; \
     dist--; \
     s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \
     s->dyn_dtree[d_code(dist)].Freq++; \
-    flush = (s->last_lit == s->lit_bufsize-1); \
+    flush = (s->sym_next == s->sym_end); \
   }
 #else
 # define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c)
diff -r 3e997cad3222 -r d4cdec23486d devel/zlib/files/trees.c
--- a/devel/zlib/files/trees.c  Thu Mar 24 07:56:00 2022 +0000
+++ b/devel/zlib/files/trees.c  Thu Mar 24 07:57:47 2022 +0000
@@ -30,7 +30,7 @@
  *          Addison-Wesley, 1983. ISBN 0-201-06672-6.
  */
 
-/* @(#) $Id: trees.c,v 1.5 2017/04/04 08:57:33 adam Exp $ */
+/* @(#) $Id: trees.c,v 1.6 2022/03/24 07:57:47 wiz Exp $ */
 
 /* #define GEN_TREES_H */
 
@@ -416,7 +416,7 @@
 
     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
@@ -947,7 +947,7 @@
 
         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;
 
@@ -1016,8 +1016,9 @@
     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++;
@@ -1032,30 +1033,7 @@
         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);



Home | Main Index | Thread Index | Old Index