From 0484693e1723bbab791c56f95597bd7dbe867d03 Mon Sep 17 00:00:00 2001 From: Mark Adler Date: Fri, 9 Sep 2011 23:24:33 -0700 Subject: [PATCH] zlib 1.2.2.2 --- ChangeLog | 21 + FAQ | 26 +- Makefile | 2 +- Makefile.in | 2 +- README | 9 +- adler32.c | 115 +++-- as400/zlib.inc | 6 +- configure | 5 +- contrib/README.contrib | 3 - contrib/delphi/ZLib.pas | 2 +- contrib/infback9/inftree9.c | 4 +- contrib/masmx86/gvmat32.asm | 56 +-- contrib/masmx86/inffas32.asm | 21 +- contrib/vstudio/readme.txt | 2 +- contrib/vstudio/vc7/zlib.rc | 6 +- crc32.c | 2 +- deflate.c | 25 +- examples/README.examples | 29 ++ examples/fitblk.c | 235 ++++++++++ {contrib/gzappend => examples}/gzappend.c | 0 examples/gzjoin.c | 447 ++++++++++++++++++ examples/gzlog.c | 413 +++++++++++++++++ examples/gzlog.h | 58 +++ examples/zlib_how.html | 522 ++++++++++++++++++++++ examples/zpipe.c | 191 ++++++++ gzio.c | 8 +- infback.c | 1 + inffast.c | 13 + inflate.c | 16 +- inflate.h | 1 + inftrees.c | 4 +- old/Make_vms.com => make_vms.com | 23 +- qnx/package.qpg | 10 +- trees.c | 18 +- win32/zlib1.rc | 8 +- zlib.3 | 4 +- zlib.h | 25 +- zutil.c | 5 +- zutil.h | 17 +- 39 files changed, 2178 insertions(+), 177 deletions(-) create mode 100644 examples/README.examples create mode 100644 examples/fitblk.c rename {contrib/gzappend => examples}/gzappend.c (100%) create mode 100644 examples/gzjoin.c create mode 100644 examples/gzlog.c create mode 100644 examples/gzlog.h create mode 100644 examples/zlib_how.html create mode 100644 examples/zpipe.c rename old/Make_vms.com => make_vms.com (82%) mode change 100755 => 100644 diff --git a/ChangeLog b/ChangeLog index 84f9306..d162e90 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,26 @@ ChangeLog file for zlib +Changes in 1.2.2.2 (30 December 2004) +- Replace structure assignments in deflate.c and inflate.c with zmemcpy to + avoid implicit memcpy calls (portability for no-library compilation) +- Increase sprintf() buffer size in gzdopen() to allow for large numbers +- Add INFLATE_STRICT to check distances against zlib header +- Improve WinCE errno handling and comments [Chang] +- Remove comment about no gzip header processing in FAQ +- Add Z_FIXED strategy option to deflateInit2() to force fixed trees +- Add updated make_vms.com [Coghlan], update README +- Create a new "examples" directory, move gzappend.c there, add zpipe.c, + fitblk.c, gzlog.[ch], gzjoin.c, and zlib_how.html. +- Add FAQ entry and comments in deflate.c on uninitialized memory access +- Add Solaris 9 make options in configure [Gilbert] +- Allow strerror() usage in gzio.c for STDC +- Fix DecompressBuf in contrib/delphi/ZLib.pas [ManChesTer] +- Update contrib/masmx86/inffas32.asm and gvmat32.asm [Vollant] +- Use z_off_t for adler32_combine() and crc32_combine() lengths +- Make adler32() much faster for small len +- Use OS_CODE in deflate() default gzip header + Changes in 1.2.2.1 (31 October 2004) - Allow inflateSetDictionary() call for raw inflate - Fix inflate header crc check bug for file names and comments @@ -20,6 +40,7 @@ Changes in 1.2.2.1 (31 October 2004) - Do not define an exit() prototype in zutil.c unless DEBUG defined - Remove prototype of exit() from zutil.c, example.c, minigzip.c [Truta] - Add comment in zlib.h for Z_NO_FLUSH parameter to deflate() +- Fix Darwin build version identification [Peterson] Changes in 1.2.2 (3 October 2004) - Update zlib.h comments on gzip in-memory processing diff --git a/FAQ b/FAQ index 4f61f10..441d910 100644 --- a/FAQ +++ b/FAQ @@ -148,13 +148,6 @@ The lastest zlib FAQ is at http://www.gzip.org/zlib/zlib_faq.html format using deflateInit2(). You can also request that inflate decode the gzip format using inflateInit2(). Read zlib.h for more details. - Note that you cannot specify special gzip header contents (e.g. a file - name or modification date), nor will inflate tell you what was in the - gzip header. If you need to customize the header or see what's in it, - you can use the raw deflate and inflate operations and the crc32() - function and roll your own gzip encoding and decoding. Read the gzip - RFC 1952 for details of the header and trailer format. - 21. Is zlib thread-safe? Yes. However any library routines that zlib uses and any application- @@ -295,20 +288,29 @@ The lastest zlib FAQ is at http://www.gzip.org/zlib/zlib_faq.html were downright silly. So now, we simply make sure that the code always works. -36. Will zlib read the (insert any ancient or arcane format here) compressed +36. Valgrind (or some similar memory access checker) says that deflate is + performing a conditional jump that depends on an uninitialized value. + Isn't that a bug? + + No. That is intentional for performance reasons, and the output of + deflate is not affected. This only started showing up recently since + zlib 1.2.x uses malloc() by default for allocations, whereas earlier + versions used calloc(), which zeros out the allocated memory. + +37. Will zlib read the (insert any ancient or arcane format here) compressed data format? Probably not. Look in the comp.compression FAQ for pointers to various formats and associated software. -37. How can I encrypt/decrypt zip files with zlib? +38. How can I encrypt/decrypt zip files with zlib? zlib doesn't support encryption. The original PKZIP encryption is very weak and can be broken with freely available programs. To get strong encryption, use GnuPG, http://www.gnupg.org/ , which already includes zlib compression. For PKZIP compatible "encryption", look at http://www.info-zip.org/ -38. What's the difference between the "gzip" and "deflate" HTTP 1.1 encodings? +39. What's the difference between the "gzip" and "deflate" HTTP 1.1 encodings? "gzip" is the gzip format, and "deflate" is the zlib format. They should probably have called the second one "zlib" instead to avoid confusion @@ -324,14 +326,14 @@ The lastest zlib FAQ is at http://www.gzip.org/zlib/zlib_faq.html Bottom line: use the gzip format for HTTP 1.1 encoding. -39. Does zlib support the new "Deflate64" format introduced by PKWare? +40. Does zlib support the new "Deflate64" format introduced by PKWare? No. PKWare has apparently decided to keep that format proprietary, since they have not documented it as they have previous compression formats. In any case, the compression improvements are so modest compared to other more modern approaches, that it's not worth the effort to implement. -40. Can you please sign these lengthy legal documents and fax them back to us +41. Can you please sign these lengthy legal documents and fax them back to us so that we can use your software in our product? No. Go away. Shoo. diff --git a/Makefile b/Makefile index 7a6bd9a..29f53de 100644 --- a/Makefile +++ b/Makefile @@ -30,7 +30,7 @@ CPP=$(CC) -E LIBS=libz.a SHAREDLIB=libz.so -SHAREDLIBV=libz.so.1.2.2.1 +SHAREDLIBV=libz.so.1.2.2.2 SHAREDLIBM=libz.so.1 AR=ar rc diff --git a/Makefile.in b/Makefile.in index 7a6bd9a..29f53de 100644 --- a/Makefile.in +++ b/Makefile.in @@ -30,7 +30,7 @@ CPP=$(CC) -E LIBS=libz.a SHAREDLIB=libz.so -SHAREDLIBV=libz.so.1.2.2.1 +SHAREDLIBV=libz.so.1.2.2.2 SHAREDLIBM=libz.so.1 AR=ar rc diff --git a/README b/README index f148864..e91a7a4 100644 --- a/README +++ b/README @@ -1,6 +1,6 @@ ZLIB DATA COMPRESSION LIBRARY -zlib 1.2.2.1 is a general purpose data compression library. All the code is +zlib 1.2.2.2 is a general purpose data compression library. All the code is thread safe. The data format used by the zlib library is described by RFCs (Request for Comments) 1950 to 1952 in the files http://www.ietf.org/rfc/rfc1950.txt (zlib format), rfc1951.txt (deflate format) @@ -16,9 +16,8 @@ minigzip.c. To compile all files and run the test program, follow the instructions given at the top of Makefile. In short "make test; make install" should work for most -machines. For Unix: "./configure; make test; make install" For MSDOS, use one -of the special makefiles such as Makefile.msc. For VMS, use Make_vms.com or -descrip.mms. +machines. For Unix: "./configure; make test; make install". For MSDOS, use one +of the special makefiles such as Makefile.msc. For VMS, use make_vms.com. Questions about zlib should be sent to , or to Gilles Vollant for the Windows DLL version. The zlib home page is @@ -34,7 +33,7 @@ Mark Nelson wrote an article about zlib for the Jan. 1997 issue of Dr. Dobb's Journal; a copy of the article is available in http://dogma.net/markn/articles/zlibtool/zlibtool.htm -The changes made in version 1.2.2.1 are documented in the file ChangeLog. +The changes made in version 1.2.2.2 are documented in the file ChangeLog. Unsupported third party contributions are provided in directory "contrib". diff --git a/adler32.c b/adler32.c index 94f1021..007ba26 100644 --- a/adler32.c +++ b/adler32.c @@ -12,12 +12,13 @@ #define NMAX 5552 /* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */ -#define DO1(buf,i) {s1 += buf[i]; s2 += s1;} +#define DO1(buf,i) {adler += (buf)[i]; sum2 += adler;} #define DO2(buf,i) DO1(buf,i); DO1(buf,i+1); #define DO4(buf,i) DO2(buf,i); DO2(buf,i+2); #define DO8(buf,i) DO4(buf,i); DO4(buf,i+4); #define DO16(buf) DO8(buf,0); DO8(buf,8); +/* use NO_DIVIDE if your processor does not do division in hardware */ #ifdef NO_DIVIDE # define MOD(a) \ do { \ @@ -39,8 +40,17 @@ if (a >= (BASE << 1)) a -= (BASE << 1); \ if (a >= BASE) a -= BASE; \ } while (0) +# define MOD4(a) \ + do { \ + if (a >= (BASE << 4)) a -= (BASE << 4); \ + if (a >= (BASE << 3)) a -= (BASE << 3); \ + if (a >= (BASE << 2)) a -= (BASE << 2); \ + if (a >= (BASE << 1)) a -= (BASE << 1); \ + if (a >= BASE) a -= BASE; \ + } while (0) #else # define MOD(a) a %= BASE +# define MOD4(a) a %= BASE #endif /* ========================================================================= */ @@ -49,48 +59,91 @@ uLong ZEXPORT adler32(adler, buf, len) const Bytef *buf; uInt len; { - unsigned long s1 = adler & 0xffff; - unsigned long s2 = (adler >> 16) & 0xffff; - int k; + unsigned long sum2; + unsigned n; - if (buf == Z_NULL) return 1L; + /* split Adler-32 into component sums */ + sum2 = (adler >> 16) & 0xffff; + adler &= 0xffff; - while (len > 0) { - k = len < NMAX ? (int)len : NMAX; - len -= k; - while (k >= 16) { + /* in case user likes doing a byte at a time, keep it fast */ + if (len == 1) { + adler += buf[0]; + if (adler >= BASE) + adler -= BASE; + sum2 += adler; + if (sum2 >= BASE) + sum2 -= BASE; + return adler | (sum2 << 16); + } + + /* initial Adler-32 value (deferred check for len == 1 speed) */ + if (buf == Z_NULL) + return 1L; + + /* in case short lengths are provided, keep it somewhat fast */ + if (len < 16) { + while (len--) { + adler += *buf++; + sum2 += adler; + } + if (adler >= BASE) + adler -= BASE; + MOD4(sum2); /* only added so many BASE's */ + return adler | (sum2 << 16); + } + + /* do length NMAX blocks -- requires just one modulo operation */ + while (len >= NMAX) { + len -= NMAX; + n = NMAX / 16; /* NMAX is divisible by 16 */ + do { + DO16(buf); /* 16 sums unrolled */ + buf += 16; + } while (--n); + MOD(adler); + MOD(sum2); + } + + /* do remaining bytes (less than NMAX, still just one modulo) */ + if (len) { /* avoid modulos if none remaining */ + while (len >= 16) { + len -= 16; DO16(buf); buf += 16; - k -= 16; } - if (k != 0) do { - s1 += *buf++; - s2 += s1; - } while (--k); - MOD(s1); - MOD(s2); + while (len--) { + adler += *buf++; + sum2 += adler; + } + MOD(adler); + MOD(sum2); } - return (s2 << 16) | s1; + + /* return recombined sums */ + return adler | (sum2 << 16); } /* ========================================================================= */ uLong ZEXPORT adler32_combine(adler1, adler2, len2) uLong adler1; uLong adler2; - uLong len2; + z_off_t len2; { - unsigned long s1; - unsigned long s2; + unsigned long sum1; + unsigned long sum2; + unsigned rem; - len2 %= BASE; - s1 = adler1 & 0xffff; - s2 = len2 * s1; - MOD(s2); - s1 += (adler2 & 0xffff) + BASE - 1; - s2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - len2; - if (s1 > BASE) s1 -= BASE; - if (s1 > BASE) s1 -= BASE; - if (s2 > (BASE << 1)) s2 -= (BASE << 1); - if (s2 > BASE) s2 -= BASE; - return (s2 << 16) | s1; + /* the derivation of this formula is left as an exercise for the reader */ + rem = (unsigned)(len2 % BASE); + sum1 = adler1 & 0xffff; + sum2 = rem * sum1; + MOD(sum2); + sum1 += (adler2 & 0xffff) + BASE - 1; + sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem; + if (sum1 > BASE) sum1 -= BASE; + if (sum1 > BASE) sum1 -= BASE; + if (sum2 > (BASE << 1)) sum2 -= (BASE << 1); + if (sum2 > BASE) sum2 -= BASE; + return sum1 | (sum2 << 16); } diff --git a/as400/zlib.inc b/as400/zlib.inc index f85473e..04c3309 100644 --- a/as400/zlib.inc +++ b/as400/zlib.inc @@ -1,7 +1,7 @@ * ZLIB.INC - Interface to the general purpose compression library * * ILE RPG400 version by Patrick Monnerat, DATASPHERE. - * Version 1.2.2.1 + * Version 1.2.2.2 * * * WARNING: @@ -20,8 +20,8 @@ * Constants ************************************************************************** * - D ZLIB_VERSION C '1.2.2.1' Header's version - D ZLIB_VERNUM C X'1221' + D ZLIB_VERSION C '1.2.2.2' Header's version + D ZLIB_VERNUM C X'1222' * D Z_NO_FLUSH C 0 D Z_SYNC_FLUSH C 2 diff --git a/configure b/configure index 6e13859..e3ea897 100755 --- a/configure +++ b/configure @@ -89,7 +89,7 @@ if test "$gcc" -eq 1 && ($cc -c $cflags $test.c) 2>/dev/null; then SHAREDLIB=libz$shared_ext SHAREDLIBV=libz.$VER$shared_ext SHAREDLIBM=libz.$VER1$shared_ext - LDSHARED=${LDSHARED-"$cc -dynamiclib -install_name $libdir/$SHAREDLIBV -compatibility_version $VER2 -current_version $VER"};; + LDSHARED=${LDSHARED-"$cc -dynamiclib -install_name $libdir/$SHAREDLIBM -compatibility_version $VER1 -current_version $VER"};; *) LDSHARED=${LDSHARED-"$cc -shared"};; esac else @@ -125,6 +125,9 @@ else SunOS\ 4*) SFLAGS=${CFLAGS-"-O2 -PIC"} CFLAGS=${CFLAGS-"-O2"} LDSHARED=${LDSHARED-"ld"};; + SunStudio\ 9*) SFLAGS=${CFLAGS-"-DUSE_MMAP -fast -xcode=pic32 -xtarget=ultra3 -xarch=v9b"} + CFLAGS=${CFLAGS-"-DUSE_MMAP -fast -xtarget=ultra3 -xarch=v9b"} + LDSHARED=${LDSHARED-"cc -xarch=v9b"};; UNIX_System_V\ 4.2.0) SFLAGS=${CFLAGS-"-KPIC -O"} CFLAGS=${CFLAGS-"-O"} diff --git a/contrib/README.contrib b/contrib/README.contrib index 7778980..732d48c 100644 --- a/contrib/README.contrib +++ b/contrib/README.contrib @@ -22,9 +22,6 @@ delphi/ by Cosmin Truta dotzlib/ by Henrik Ravn Support for Microsoft .Net and Visual C++ .Net -gzappend/ by Mark Adler - append to a gzip file -- illustrates the use of Z_BLOCK - infback9/ by Mark Adler Unsupported diffs to infback to decode the deflate64 format diff --git a/contrib/delphi/ZLib.pas b/contrib/delphi/ZLib.pas index 8853866..b9d33e2 100644 --- a/contrib/delphi/ZLib.pas +++ b/contrib/delphi/ZLib.pas @@ -344,7 +344,7 @@ begin strm.avail_out := OutBytes; DCheck(inflateInit_(strm, zlib_version, sizeof(strm))); try - while DCheck(inflate(strm, Z_FINISH)) <> Z_STREAM_END do + while DCheck(inflate(strm, Z_NO_FLUSH)) <> Z_STREAM_END do begin P := OutBuf; Inc(OutBytes, BufInc); diff --git a/contrib/infback9/inftree9.c b/contrib/infback9/inftree9.c index 7325873..29bef6a 100644 --- a/contrib/infback9/inftree9.c +++ b/contrib/infback9/inftree9.c @@ -9,7 +9,7 @@ #define MAXBITS 15 const char inflate9_copyright[] = - " inflate9 1.2.2.1 Copyright 1995-2004 Mark Adler "; + " inflate9 1.2.2.2 Copyright 1995-2004 Mark Adler "; /* If you use the zlib library in a product, an acknowledgment is welcome in the documentation of your product. If for some reason you cannot @@ -64,7 +64,7 @@ unsigned short FAR *work; static const unsigned short lext[31] = { /* Length codes 257..285 extra */ 128, 128, 128, 128, 128, 128, 128, 128, 129, 129, 129, 129, 130, 130, 130, 130, 131, 131, 131, 131, 132, 132, 132, 132, - 133, 133, 133, 133, 144, 77, 207}; + 133, 133, 133, 133, 144, 72, 199}; static const unsigned short dbase[32] = { /* Distance codes 0..31 base */ 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, diff --git a/contrib/masmx86/gvmat32.asm b/contrib/masmx86/gvmat32.asm index ec360e6..e841a7f 100644 --- a/contrib/masmx86/gvmat32.asm +++ b/contrib/masmx86/gvmat32.asm @@ -47,21 +47,25 @@ -; all the +4 offsets are due to the addition of pending_buf_size (in zlib +; all the +addstr offsets are due to the addition of pending_buf_size in zlib 1.04 +; and adding gzhead and gzindex in zlib 1.2.2.1 ; in the deflate_state structure since the asm code was first written -; (if you compile with zlib 1.0.4 or older, remove the +4). +; (if you compile with zlib 1.0.4 or older, set addstr to 0). +; (if you compiler with zlib between 1.04 and 1.2.1, set addstr to 4) ; Note : these value are good with a 8 bytes boundary pack structure - dep_chain_length equ 70h+4 - dep_window equ 2ch+4 - dep_strstart equ 60h+4 - dep_prev_length equ 6ch+4 - dep_nice_match equ 84h+4 - dep_w_size equ 20h+4 - dep_prev equ 34h+4 - dep_w_mask equ 28h+4 - dep_good_match equ 80h+4 - dep_match_start equ 64h+4 - dep_lookahead equ 68h+4 + + addstr equ 4+8 + dep_chain_length equ 70h+addstr + dep_window equ 2ch+addstr + dep_strstart equ 60h+addstr + dep_prev_length equ 6ch+addstr + dep_nice_match equ 84h+addstr + dep_w_size equ 20h+addstr + dep_prev equ 34h+addstr + dep_w_mask equ 28h+addstr + dep_good_match equ 80h+addstr + dep_match_start equ 64h+addstr + dep_lookahead equ 68h+addstr _TEXT segment @@ -597,19 +601,19 @@ curmatch equ esp + 60 ;;; program to crash horribly, without so much as a warning at ;;; compile time. Sigh.) -dsWSize equ 36 -dsWMask equ 44 -dsWindow equ 48 -dsPrev equ 56 -dsMatchLen equ 88 -dsPrevMatch equ 92 -dsStrStart equ 100 -dsMatchStart equ 104 -dsLookahead equ 108 -dsPrevLen equ 112 -dsMaxChainLen equ 116 -dsGoodMatch equ 132 -dsNiceMatch equ 136 +dsWSize equ 36+addstr-4 +dsWMask equ 44+addstr-4 +dsWindow equ 48+addstr-4 +dsPrev equ 56+addstr-4 +dsMatchLen equ 88+addstr-4 +dsPrevMatch equ 92+addstr-4 +dsStrStart equ 100+addstr-4 +dsMatchStart equ 104+addstr-4 +dsLookahead equ 108+addstr-4 +dsPrevLen equ 112+addstr-4 +dsMaxChainLen equ 116+addstr-4 +dsGoodMatch equ 132+addstr-4 +dsNiceMatch equ 136+addstr-4 ;;; match.asm -- Pentium-Pro-optimized version of longest_match() diff --git a/contrib/masmx86/inffas32.asm b/contrib/masmx86/inffas32.asm index 7d76e1c..531bcef 100644 --- a/contrib/masmx86/inffas32.asm +++ b/contrib/masmx86/inffas32.asm @@ -84,17 +84,20 @@ dd 2147483647 dd 4294967295 +; head was added in zlib 1.2.2.1, so we add addstr +; set addstr to 0 with zlib 1.2.1 of below +addstr equ 4 mode_state equ 0 ;/* state->mode */ -wsize_state equ 32 ;/* state->wsize */ -write_state equ (36+4) ;/* state->write */ -window_state equ (40+4) ;/* state->window */ -hold_state equ (44+4) ;/* state->hold */ -bits_state equ (48+4) ;/* state->bits */ -lencode_state equ (64+4) ;/* state->lencode */ -distcode_state equ (68+4) ;/* state->distcode */ -lenbits_state equ (72+4) ;/* state->lenbits */ -distbits_state equ (76+4) ;/* state->distbits */ +wsize_state equ 32+addstr ;/* state->wsize */ +write_state equ (36+4+addstr) ;/* state->write */ +window_state equ (40+4+addstr) ;/* state->window */ +hold_state equ (44+4+addstr) ;/* state->hold */ +bits_state equ (48+4+addstr) ;/* state->bits */ +lencode_state equ (64+4+addstr) ;/* state->lencode */ +distcode_state equ (68+4+addstr) ;/* state->distcode */ +lenbits_state equ (72+4+addstr) ;/* state->lenbits */ +distbits_state equ (76+4+addstr) ;/* state->distbits */ ;;SECTION .text diff --git a/contrib/vstudio/readme.txt b/contrib/vstudio/readme.txt index 3a4b85c..e709d1b 100644 --- a/contrib/vstudio/readme.txt +++ b/contrib/vstudio/readme.txt @@ -1,4 +1,4 @@ -Building instructions for the DLL versions of Zlib 1.21 +Building instructions for the DLL versions of Zlib 1.2.x ======================================================= This directory contains projects that build zlib and minizip using diff --git a/contrib/vstudio/vc7/zlib.rc b/contrib/vstudio/vc7/zlib.rc index cb779f7..d35cef0 100644 --- a/contrib/vstudio/vc7/zlib.rc +++ b/contrib/vstudio/vc7/zlib.rc @@ -2,8 +2,8 @@ #define IDR_VERSION1 1 IDR_VERSION1 VERSIONINFO MOVEABLE IMPURE LOADONCALL DISCARDABLE - FILEVERSION 1,2,2,1 - PRODUCTVERSION 1,2,2,1 + FILEVERSION 1,2,2,2 + PRODUCTVERSION 1,2,2,2 FILEFLAGSMASK VS_FFI_FILEFLAGSMASK FILEFLAGS 0 FILEOS VOS_DOS_WINDOWS32 @@ -17,7 +17,7 @@ BEGIN BEGIN VALUE "FileDescription", "zlib data compression library\0" - VALUE "FileVersion", "1.2.2.1\0" + VALUE "FileVersion", "1.2.2.2\0" VALUE "InternalName", "zlib\0" VALUE "OriginalFilename", "zlib.dll\0" VALUE "ProductName", "ZLib.DLL\0" diff --git a/crc32.c b/crc32.c index a7fd3f8..62b025f 100644 --- a/crc32.c +++ b/crc32.c @@ -369,7 +369,7 @@ local void gf2_matrix_square(square, mat) uLong ZEXPORT crc32_combine(crc1, crc2, len2) uLong crc1; uLong crc2; - uLong len2; + z_off_t len2; { int n; unsigned long row; diff --git a/deflate.c b/deflate.c index cb723a1..159f946 100644 --- a/deflate.c +++ b/deflate.c @@ -52,7 +52,7 @@ #include "deflate.h" const char deflate_copyright[] = - " deflate 1.2.2.1 Copyright 1995-2004 Jean-loup Gailly "; + " deflate 1.2.2.2 Copyright 1995-2004 Jean-loup Gailly "; /* If you use the zlib library in a product, an acknowledgment is welcome in the documentation of your product. If for some reason you cannot @@ -264,7 +264,7 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, #endif if (memLevel < 1 || memLevel > MAX_MEM_LEVEL || method != Z_DEFLATED || windowBits < 8 || windowBits > 15 || level < 0 || level > 9 || - strategy < 0 || strategy > Z_RLE) { + strategy < 0 || strategy > Z_FIXED) { return Z_STREAM_ERROR; } if (windowBits == 8) windowBits = 9; /* until 256-byte window bug fixed */ @@ -432,7 +432,7 @@ int ZEXPORT deflateParams(strm, level, strategy) #else if (level == Z_DEFAULT_COMPRESSION) level = 6; #endif - if (level < 0 || level > 9 || strategy < 0 || strategy > Z_RLE) { + if (level < 0 || level > 9 || strategy < 0 || strategy > Z_FIXED) { return Z_STREAM_ERROR; } func = configuration_table[s->level].func; @@ -573,7 +573,7 @@ int ZEXPORT deflate (strm, flush) put_byte(s, s->level == 9 ? 2 : (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? 4 : 0)); - put_byte(s, 255); + put_byte(s, OS_CODE); s->status = BUSY_STATE; } else { @@ -892,12 +892,12 @@ int ZEXPORT deflateCopy (dest, source) ss = source->state; - *dest = *source; + zmemcpy(dest, source, sizeof(z_stream)); ds = (deflate_state *) ZALLOC(dest, 1, sizeof(deflate_state)); if (ds == Z_NULL) return Z_MEM_ERROR; dest->state = (struct internal_state FAR *) ds; - *ds = *ss; + zmemcpy(ds, ss, sizeof(deflate_state)); ds->strm = dest; ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte)); @@ -1057,7 +1057,12 @@ local uInt longest_match(s, cur_match) match = s->window + cur_match; /* Skip to next match if the match length cannot increase - * or if the match length is less than 2: + * or if the match length is less than 2. Note that the checks below + * for insufficient lookahead only occur occasionally for performance + * reasons. Therefore uninitialized memory will be accessed, and + * conditional jumps will be made that depend on those values. + * However the length of the match is limited to the lookahead, so + * the output of deflate is not affected by the uninitialized values. */ #if (defined(UNALIGNED_OK) && MAX_MATCH == 258) /* This code assumes sizeof(unsigned short) == 2. Do not use @@ -1457,12 +1462,12 @@ local block_state deflate_fast(s, flush) * of the string with itself at the start of the input file). */ #ifdef FASTEST - if ((s->strategy < Z_HUFFMAN_ONLY) || + if ((s->strategy != Z_HUFFMAN_ONLY && s->strategy != Z_RLE) || (s->strategy == Z_RLE && s->strstart - hash_head == 1)) { s->match_length = longest_match_fast (s, hash_head); } #else - if (s->strategy < Z_HUFFMAN_ONLY) { + if (s->strategy != Z_HUFFMAN_ONLY && s->strategy != Z_RLE) { s->match_length = longest_match (s, hash_head); } else if (s->strategy == Z_RLE && s->strstart - hash_head == 1) { s->match_length = longest_match_fast (s, hash_head); @@ -1566,7 +1571,7 @@ local block_state deflate_slow(s, flush) * of window index 0 (in particular we have to avoid a match * of the string with itself at the start of the input file). */ - if (s->strategy < Z_HUFFMAN_ONLY) { + if (s->strategy != Z_HUFFMAN_ONLY && s->strategy != Z_RLE) { s->match_length = longest_match (s, hash_head); } else if (s->strategy == Z_RLE && s->strstart - hash_head == 1) { s->match_length = longest_match_fast (s, hash_head); diff --git a/examples/README.examples b/examples/README.examples new file mode 100644 index 0000000..1084525 --- /dev/null +++ b/examples/README.examples @@ -0,0 +1,29 @@ +This directory contains examples of the use of zlib. + +fitblk.c + compress just enough input to nearly fill a requested output size + - zlib isn't designed to do this, but fitblk does it anyway + +gzappend.c + append to a gzip file + - illustrates the use of the Z_BLOCK flush parameter for inflate() + - illustrates the use of deflatePrime() to start at any bit + +gzjoin.c + join gzip files without recalculating the crc or recompressing + - illustrates the use of the Z_BLOCK flush parameter for inflate() + - illustrates the use of crc32_combine() + +gzlog.c +gzlog.h + efficiently maintain a message log file in gzip format + - illustrates use of raw deflate and Z_SYNC_FLUSH + - illustrates use of gzip header extra field + +zlib_how.html + painfully comprehensive description of zpipe.c (see below) + - describes in excruciating detail the use of deflate() and inflate() + +zpipe.c + reads and writes zlib streams from stdin to stdout + - illustrates the proper use of deflate() and inflate() diff --git a/examples/fitblk.c b/examples/fitblk.c new file mode 100644 index 0000000..5f83114 --- /dev/null +++ b/examples/fitblk.c @@ -0,0 +1,235 @@ +/* fitblk.c: example of fitting compressed output to a specified size + Not copyrighted -- provided to the public domain + Version 1.1 25 November 2004 Mark Adler */ + +/* Version history: + 1.0 24 Nov 2004 First version + 1.1 25 Nov 2004 Change deflateInit2() to deflateInit() + Use fixed-size, stack-allocated raw buffers + Simplify code moving compression to subroutines + Use assert() for internal errors + Add detailed description of approach + */ + +/* Approach to just fitting a requested compressed size: + + fitblk performs three compression passes on a portion of the input + data in order to determine how much of that input will compress to + nearly the requested output block size. The first pass generates + enough deflate blocks to produce output to fill the requested + output size plus a specfied excess amount (see the EXCESS define + below). The last deflate block may go quite a bit past that, but + is discarded. The second pass decompresses and recompresses just + the compressed data that fit in the requested plus excess sized + buffer. The deflate process is terminated after that amount of + input, which is less than the amount consumed on the first pass. + The last deflate block of the result will be of a comparable size + to the final product, so that the header for that deflate block and + the compression ratio for that block will be about the same as in + the final product. The third compression pass decompresses the + result of the second step, but only the compressed data up to the + requested size minus an amount to allow the compressed stream to + complete (see the MARGIN define below). That will result in a + final compressed stream whose length is less than or equal to the + requested size. Assuming sufficient input and a requested size + greater than a few hundred bytes, the shortfall will typically be + less than ten bytes. + + If the input is short enough that the first compression completes + before filling the requested output size, then that compressed + stream is return with no recompression. + + EXCESS is chosen to be just greater than the shortfall seen in a + two pass approach similar to the above. That shortfall is due to + the last deflate block compressing more efficiently with a smaller + header on the second pass. EXCESS is set to be large enough so + that there is enough uncompressed data for the second pass to fill + out the requested size, and small enough so that the final deflate + block of the second pass will be close in size to the final deflate + block of the third and final pass. MARGIN is chosen to be just + large enough to assure that the final compression has enough room + to complete in all cases. + */ + +#include +#include +#include +#include "zlib.h" + +#define local static + +/* print nastygram and leave */ +local void quit(char *why) +{ + fprintf(stderr, "fitblk abort: %s\n", why); + exit(1); +} + +#define RAWLEN 4096 /* intermediate uncompressed buffer size */ + +/* compress from file to def until provided buffer is full or end of + input reached; return last deflate() return value, or Z_ERRNO if + there was read error on the file */ +local int partcompress(FILE *in, z_streamp def) +{ + int ret, flush; + char raw[RAWLEN]; + + flush = Z_NO_FLUSH; + do { + def->avail_in = fread(raw, 1, RAWLEN, in); + if (ferror(in)) + return Z_ERRNO; + def->next_in = raw; + if (feof(in)) + flush = Z_FINISH; + ret = deflate(def, flush); + assert(ret != Z_STREAM_ERROR); + } while (def->avail_out != 0 && flush == Z_NO_FLUSH); + return ret; +} + +/* recompress from inf's input to def's output; the input for inf and + the output for def are set in those structures before calling; + return last deflate() return value, or Z_MEM_ERROR if inflate() + was not able to allocate enough memory when it needed to */ +local int recompress(z_streamp inf, z_streamp def) +{ + int ret, flush; + char raw[RAWLEN]; + + flush = Z_NO_FLUSH; + do { + /* decompress */ + inf->avail_out = RAWLEN; + inf->next_out = raw; + ret = inflate(inf, Z_NO_FLUSH); + assert(ret != Z_STREAM_ERROR && ret != Z_DATA_ERROR && + ret != Z_NEED_DICT); + if (ret == Z_MEM_ERROR) + return ret; + + /* compress what was decompresed until done or no room */ + def->avail_in = RAWLEN - inf->avail_out; + def->next_in = raw; + if (inf->avail_out != 0) + flush = Z_FINISH; + ret = deflate(def, flush); + assert(ret != Z_STREAM_ERROR); + } while (ret != Z_STREAM_END && def->avail_out != 0); + return ret; +} + +#define EXCESS 256 /* empirically determined stream overage */ +#define MARGIN 8 /* amount to back off for completion */ + +/* compress from stdin to fixed-size block on stdout */ +int main(int argc, char **argv) +{ + int ret; /* return code */ + unsigned size; /* requested fixed output block size */ + unsigned have; /* bytes written by deflate() call */ + char *blk; /* intermediate and final stream */ + char *tmp; /* close to desired size stream */ + z_stream def, inf; /* zlib deflate and inflate states */ + + /* get requested output size */ + if (argc != 2) + quit("need one argument: size of output block"); + ret = strtol(argv[1], argv + 1, 10); + if (argv[1][0] != 0) + quit("argument must be a number"); + if (ret < 8) /* 8 is minimum zlib stream size */ + quit("need positive size of 8 or greater"); + size = (unsigned)ret; + + /* allocate memory for buffers and compression engine */ + blk = malloc(size + EXCESS); + def.zalloc = Z_NULL; + def.zfree = Z_NULL; + def.opaque = Z_NULL; + ret = deflateInit(&def, Z_DEFAULT_COMPRESSION); + if (ret != Z_OK || blk == NULL) + quit("out of memory"); + + /* compress from stdin until output full, or no more input */ + def.avail_out = size + EXCESS; + def.next_out = blk; + ret = partcompress(stdin, &def); + if (ret == Z_ERRNO) + quit("error reading input"); + + /* if it all fit, then size was undersubscribed -- done! */ + if (ret == Z_STREAM_END && def.avail_out >= EXCESS) { + /* write block to stdout */ + have = size + EXCESS - def.avail_out; + ret = fwrite(blk, 1, have, stdout); + if (ret != have || ferror(stdout)) + quit("error writing output"); + + /* clean up and print results to stderr */ + ret = deflateEnd(&def); + assert(ret != Z_STREAM_ERROR); + free(blk); + fprintf(stderr, + "%u bytes unused out of %u requested (all input)\n", + size - have, size); + return 0; + } + + /* it didn't all fit -- set up for recompression */ + inf.zalloc = Z_NULL; + inf.zfree = Z_NULL; + inf.opaque = Z_NULL; + inf.avail_in = 0; + inf.next_in = Z_NULL; + ret = inflateInit(&inf); + tmp = malloc(size + EXCESS); + if (ret != Z_OK || tmp == NULL) + quit("out of memory"); + ret = deflateReset(&def); + assert(ret != Z_STREAM_ERROR); + + /* do first recompression close to the right amount */ + inf.avail_in = size + EXCESS; + inf.next_in = blk; + def.avail_out = size + EXCESS; + def.next_out = tmp; + ret = recompress(&inf, &def); + if (ret == Z_MEM_ERROR) + quit("out of memory"); + + /* set up for next reocmpression */ + ret = inflateReset(&inf); + assert(ret != Z_STREAM_ERROR); + ret = deflateReset(&def); + assert(ret != Z_STREAM_ERROR); + + /* do second and final recompression (third compression) */ + inf.avail_in = size - MARGIN; /* assure stream will complete */ + inf.next_in = tmp; + def.avail_out = size; + def.next_out = blk; + ret = recompress(&inf, &def); + if (ret == Z_MEM_ERROR) + quit("out of memory"); + assert(ret == Z_STREAM_END); /* otherwise MARGIN too small */ + + /* done -- write block to stdout */ + have = size - def.avail_out; + ret = fwrite(blk, 1, have, stdout); + if (ret != have || ferror(stdout)) + quit("error writing output"); + + /* clean up and print results to stderr */ + free(tmp); + ret = inflateEnd(&inf); + assert(ret != Z_STREAM_ERROR); + ret = deflateEnd(&def); + assert(ret != Z_STREAM_ERROR); + free(blk); + fprintf(stderr, + "%u bytes unused out of %u requested (%lu input)\n", + size - have, size, def.total_in); + return 0; +} diff --git a/contrib/gzappend/gzappend.c b/examples/gzappend.c similarity index 100% rename from contrib/gzappend/gzappend.c rename to examples/gzappend.c diff --git a/examples/gzjoin.c b/examples/gzjoin.c new file mode 100644 index 0000000..7434c5b --- /dev/null +++ b/examples/gzjoin.c @@ -0,0 +1,447 @@ +/* gzjoin -- command to join gzip files into one gzip file + + Copyright (C) 2004 Mark Adler, all rights reserved + version 1.0, 11 Dec 2004 + + This software is provided 'as-is', without any express or implied + warranty. In no event will the author be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + Mark Adler madler@alumni.caltech.edu + */ + +/* + * Change history: + * + * 1.0 11 Dec 2004 - First version + */ + +/* + gzjoin takes one or more gzip files on the command line and writes out a + single gzip file that will uncompress to the concatenation of the + uncompressed data from the individual gzip files. gzjoin does this without + having to recompress any of the data and without having to calculate a new + crc32 for the concatenated uncompressed data. gzjoin does however have to + decompress all of the input data in order to find the bits in the compressed + data that need to be modified to concatenate the streams. + + gzjoin does not do an integrity check on the input gzip files other than + checking the gzip header and decompressing the compressed data. They are + otherwise assumed to be complete and correct. + + Each joint between gzip files removes at least 18 bytes of previous trailer + and subsequent header, and inserts an average of about three bytes to the + compressed data in order to connect the streams. The output gzip file + has a minimal ten-byte gzip header with no file name or modification time. + + This program was written to illustrate the use of the Z_BLOCK option of + inflate() and the crc32_combine() function. gzjoin will not compile with + versions of zlib earlier than 1.2.3. + */ + +#include /* fputs(), fprintf(), fwrite(), putc() */ +#include /* exit(), malloc(), free() */ +#include /* open() */ +#include /* close(), read(), lseek() */ +#include "zlib.h" + /* crc32(), crc32_combine(), inflateInit2(), inflate(), inflateEnd() */ + +#define local static + +/* exit with an error (return a value to allow use in an expression) */ +local int bail(char *why1, char *why2) +{ + fprintf(stderr, "gzjoin error: %s%s, output incomplete\n", why1, why2); + exit(1); + return 0; +} + +/* -- simple buffered file input with access to the buffer -- */ + +#define CHUNK 32768 /* must be a power of two and fit in unsigned */ + +/* bin buffered input file type */ +typedef struct { + char *name; /* name of file for error messages */ + int fd; /* file descriptor */ + unsigned left; /* bytes remaining at next */ + unsigned char *next; /* next byte to read */ + unsigned char *buf; /* allocated buffer of length CHUNK */ +} bin; + +/* close a buffered file and free allocated memory */ +local void bclose(bin *in) +{ + if (in != NULL) { + if (in->fd != -1) + close(in->fd); + if (in->buf != NULL) + free(in->buf); + free(in); + } +} + +/* open a buffered file for input, return a pointer to type bin, or NULL on + failure */ +local bin *bopen(char *name) +{ + bin *in; + + in = malloc(sizeof(bin)); + if (in == NULL) + return NULL; + in->buf = malloc(CHUNK); + in->fd = open(name, O_RDONLY, 0); + if (in->buf == NULL || in->fd == -1) { + bclose(in); + return NULL; + } + in->left = 0; + in->next = in->buf; + in->name = name; + return in; +} + +/* load buffer from file, return -1 on read error, 0 or 1 on success, with + 1 indicating that end-of-file was reached */ +local int bload(bin *in) +{ + ssize_t len; + + if (in == NULL) + return -1; + if (in->left != 0) + return 0; + in->next = in->buf; + do { + len = read(in->fd, in->buf + in->left, CHUNK - in->left); + if (len < 0) + return -1; + in->left += (unsigned)len; + } while (len != 0 && in->left < CHUNK); + return len == 0 ? 1 : 0; +} + +/* get a byte from the file, bail if end of file */ +#define bget(in) (in->left ? 0 : bload(in), \ + in->left ? (in->left--, *(in->next)++) : \ + bail("unexpected end of file on ", in->name)) + +/* get a four-byte little-endian unsigned integer from file */ +local unsigned long bget4(bin *in) +{ + unsigned long val; + + val = bget(in); + val += (unsigned long)(bget(in)) << 8; + val += (unsigned long)(bget(in)) << 16; + val += (unsigned long)(bget(in)) << 24; + return val; +} + +/* skip bytes in file */ +local void bskip(bin *in, unsigned skip) +{ + /* check pointer */ + if (in == NULL) + return; + + /* easy case -- skip bytes in buffer */ + if (skip <= in->left) { + in->left -= skip; + in->next += skip; + return; + } + + /* skip what's in buffer, discard buffer contents */ + skip -= in->left; + in->left = 0; + + /* seek past multiples of CHUNK bytes */ + if (skip > CHUNK) { + unsigned left; + + left = skip & (CHUNK - 1); + if (left == 0) { + /* exact number of chunks: seek all the way minus one byte to check + for end-of-file with a read */ + lseek(in->fd, skip - 1, SEEK_CUR); + if (read(in->fd, in->buf, 1) != 1) + bail("unexpected end of file on ", in->name); + return; + } + + /* skip the integral chunks, update skip with remainder */ + lseek(in->fd, skip - left, SEEK_CUR); + skip = left; + } + + /* read more input and skip remainder */ + bload(in); + if (skip > in->left) + bail("unexpected end of file on ", in->name); + in->left -= skip; + in->next += skip; +} + +/* -- end of buffered input functions -- */ + +/* skip the gzip header from file in */ +local void gzhead(bin *in) +{ + int flags; + + /* verify gzip magic header and compression method */ + if (bget(in) != 0x1f || bget(in) != 0x8b || bget(in) != 8) + bail(in->name, " is not a valid gzip file"); + + /* get and verify flags */ + flags = bget(in); + if ((flags & 0xe0) != 0) + bail("unknown reserved bits set in ", in->name); + + /* skip modification time, extra flags, and os */ + bskip(in, 6); + + /* skip extra field if present */ + if (flags & 4) { + unsigned len; + + len = bget(in); + len += (unsigned)(bget(in)) << 8; + bskip(in, len); + } + + /* skip file name if present */ + if (flags & 8) + while (bget(in) != 0) + ; + + /* skip comment if present */ + if (flags & 16) + while (bget(in) != 0) + ; + + /* skip header crc if present */ + if (flags & 2) + bskip(in, 2); +} + +/* write a four-byte little-endian unsigned integer to out */ +local void put4(unsigned long val, FILE *out) +{ + putc(val & 0xff, out); + putc((val >> 8) & 0xff, out); + putc((val >> 16) & 0xff, out); + putc((val >> 24) & 0xff, out); +} + +/* Load up zlib stream from buffered input, bail if end of file */ +local void zpull(z_streamp strm, bin *in) +{ + if (in->left == 0) + bload(in); + if (in->left == 0) + bail("unexpected end of file on ", in->name); + strm->avail_in = in->left; + strm->next_in = in->next; +} + +/* Write header for gzip file to out and initialize trailer. */ +local void gzinit(unsigned long *crc, unsigned long *tot, FILE *out) +{ + fwrite("\x1f\x8b\x08\0\0\0\0\0\0\xff", 1, 10, out); + *crc = crc32(0L, Z_NULL, 0); + *tot = 0; +} + +/* Copy the compressed data from name, zeroing the last block bit of the last + block if clr is true, and adding empty blocks as needed to get to a byte + boundary. If clr is false, then the last block becomes the last block of + the output, and the gzip trailer is written. crc and tot maintains the + crc and length (modulo 2^32) of the output for the trailer. The resulting + gzip file is written to out. gzinit() must be called before the first call + of gzcopy() to write the gzip header and to initialize crc and tot. */ +local void gzcopy(char *name, int clr, unsigned long *crc, unsigned long *tot, + FILE *out) +{ + int ret; /* return value from zlib functions */ + int pos; /* where the "last block" bit is in byte */ + int last; /* true if processing the last block */ + bin *in; /* buffered input file */ + unsigned char *start; /* start of compressed data in buffer */ + unsigned char *junk; /* buffer for uncompressed data -- discarded */ + z_off_t len; /* length of uncompressed data (support > 4 GB) */ + z_stream strm; /* zlib inflate stream */ + + /* open gzip file and skip header */ + in = bopen(name); + if (in == NULL) + bail("could not open ", name); + gzhead(in); + + /* allocate buffer for uncompressed data and initialize raw inflate + stream */ + junk = malloc(CHUNK); + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + strm.avail_in = 0; + strm.next_in = Z_NULL; + ret = inflateInit2(&strm, -15); + if (junk == NULL || ret != Z_OK) + bail("out of memory", ""); + + /* inflate and copy compressed data, clear last-block bit if requested */ + len = 0; + zpull(&strm, in); + start = strm.next_in; + last = start[0] & 1; + if (last && clr) + start[0] &= ~1; + strm.avail_out = 0; + for (;;) { + /* if input used and output done, write used input and get more */ + if (strm.avail_in == 0 && strm.avail_out != 0) { + fwrite(start, 1, strm.next_in - start, out); + start = in->buf; + in->left = 0; + zpull(&strm, in); + } + + /* decompress -- return early when end-of-block reached */ + strm.avail_out = CHUNK; + strm.next_out = junk; + ret = inflate(&strm, Z_BLOCK); + switch (ret) { + case Z_MEM_ERROR: + bail("out of memory", ""); + case Z_DATA_ERROR: + bail("invalid compressed data in ", in->name); + } + + /* update length of uncompressed data */ + len += CHUNK - strm.avail_out; + + /* check for block boundary (only get this when block copied out) */ + if (strm.data_type & 128) { + /* if that was the last block, then done */ + if (last) + break; + + /* number of unused bits in last byte */ + pos = strm.data_type & 7; + + /* find the next last-block bit */ + if (pos != 0) { + /* next last-block bit is in last used byte */ + pos = 0x100 >> pos; + last = strm.next_in[-1] & pos; + if (last && clr) + strm.next_in[-1] &= ~pos; + } + else { + /* next last-block bit is in next unused byte */ + if (strm.avail_in == 0) { + /* don't have that byte yet -- get it */ + fwrite(start, 1, strm.next_in - start, out); + start = in->buf; + in->left = 0; + zpull(&strm, in); + } + last = strm.next_in[0] & 1; + if (last && clr) + strm.next_in[0] &= ~1; + } + } + } + + /* update buffer with unused input */ + in->left = strm.avail_in; + in->next = strm.next_in; + + /* copy used input, write empty blocks to get to byte boundary */ + pos = strm.data_type & 7; + fwrite(start, 1, in->next - start - 1, out); + last = in->next[-1]; + if (pos == 0 || !clr) + /* already at byte boundary, or last file: write last byte */ + putc(last, out); + else { + /* append empty blocks to last byte */ + last &= ((0x100 >> pos) - 1); /* assure unused bits are zero */ + if (pos & 1) { + /* odd -- append an empty stored block */ + putc(last, out); + if (pos == 1) + putc(0, out); /* two more bits in block header */ + fwrite("\0\0\xff\xff", 1, 4, out); + } + else { + /* even -- append 1, 2, or 3 empty fixed blocks */ + switch (pos) { + case 6: + putc(last | 8, out); + last = 0; + case 4: + putc(last | 0x20, out); + last = 0; + case 2: + putc(last | 0x80, out); + putc(0, out); + } + } + } + + /* update crc and tot */ + *crc = crc32_combine(*crc, bget4(in), len); + *tot += (unsigned long)len; + + /* clean up */ + inflateEnd(&strm); + free(junk); + bclose(in); + + /* write trailer if this is the last gzip file */ + if (!clr) { + put4(*crc, out); + put4(*tot, out); + } +} + +/* join the gzip files on the command line, write result to stdout */ +int main(int argc, char **argv) +{ + unsigned long crc, tot; /* running crc and total uncompressed length */ + + /* skip command name */ + argc--; + argv++; + + /* show usage if no arguments */ + if (argc == 0) { + fputs("gzjoin usage: gzjoin f1.gz [f2.gz [f3.gz ...]] > fjoin.gz\n", + stderr); + return 0; + } + + /* join gzip files on command line and write to stdout */ + gzinit(&crc, &tot, stdout); + while (argc--) + gzcopy(*argv++, argc, &crc, &tot, stdout); + + /* done */ + return 0; +} diff --git a/examples/gzlog.c b/examples/gzlog.c new file mode 100644 index 0000000..f71f817 --- /dev/null +++ b/examples/gzlog.c @@ -0,0 +1,413 @@ +/* + * gzlog.c + * Copyright (C) 2004 Mark Adler + * For conditions of distribution and use, see copyright notice in gzlog.h + * version 1.0, 26 Nov 2004 + * + */ + +#include /* memcmp() */ +#include /* malloc(), free(), NULL */ +#include /* size_t, off_t */ +#include /* read(), close(), sleep(), ftruncate(), */ + /* lseek() */ +#include /* open() */ +#include /* flock() */ +#include "zlib.h" /* deflateInit2(), deflate(), deflateEnd() */ + +#include "gzlog.h" /* interface */ +#define local static + +/* log object structure */ +typedef struct { + int id; /* object identifier */ + int fd; /* log file descriptor */ + off_t extra; /* offset of extra "ap" subfield */ + off_t mark_off; /* offset of marked data */ + off_t last_off; /* offset of last block */ + unsigned long crc; /* uncompressed crc */ + unsigned long len; /* uncompressed length (modulo 2^32) */ + unsigned stored; /* length of current stored block */ +} gz_log; + +#define GZLOGID 19334 /* gz_log object identifier */ + +#define LOCK_RETRY 1 /* retry lock once a second */ +#define LOCK_PATIENCE 1200 /* try about twenty minutes before forcing */ + +/* acquire a lock on a file */ +local int lock(int fd) +{ + int patience; + + /* try to lock every LOCK_RETRY seconds for LOCK_PATIENCE seconds */ + patience = LOCK_PATIENCE; + do { + if (flock(fd, LOCK_EX + LOCK_NB) == 0) + return 0; + (void)sleep(LOCK_RETRY); + patience -= LOCK_RETRY; + } while (patience > 0); + + /* we've run out of patience -- give up */ + return -1; +} + +/* release lock */ +local void unlock(int fd) +{ + (void)flock(fd, LOCK_UN); +} + +/* release a log object */ +local void log_clean(gz_log *log) +{ + unlock(log->fd); + (void)close(log->fd); + free(log); +} + +/* read an unsigned long from a byte buffer little-endian */ +local unsigned long make_ulg(unsigned char *buf) +{ + int n; + unsigned long val; + + val = (unsigned long)(*buf++); + for (n = 8; n < 32; n += 8) + val += (unsigned long)(*buf++) << n; + return val; +} + +/* read an off_t from a byte buffer little-endian */ +local off_t make_off(unsigned char *buf) +{ + int n; + off_t val; + + val = (off_t)(*buf++); + for (n = 8; n < 64; n += 8) + val += (off_t)(*buf++) << n; + return val; +} + +/* write an unsigned long little-endian to byte buffer */ +local void dice_ulg(unsigned long val, unsigned char *buf) +{ + int n; + + for (n = 0; n < 4; n++) { + *buf++ = val & 0xff; + val >>= 8; + } +} + +/* write an off_t little-endian to byte buffer */ +local void dice_off(off_t val, unsigned char *buf) +{ + int n; + + for (n = 0; n < 8; n++) { + *buf++ = val & 0xff; + val >>= 8; + } +} + +/* initial, empty gzip file for appending */ +local char empty_gz[] = { + 0x1f, 0x8b, /* magic gzip id */ + 8, /* compression method is deflate */ + 4, /* there is an extra field */ + 0, 0, 0, 0, /* no modification time provided */ + 0, 0xff, /* no extra flags, no OS */ + 20, 0, 'a', 'p', 16, 0, /* extra field with "ap" subfield */ + 32, 0, 0, 0, 0, 0, 0, 0, /* offset of uncompressed data */ + 32, 0, 0, 0, 0, 0, 0, 0, /* offset of last block */ + 1, 0, 0, 0xff, 0xff, /* empty stored block (last) */ + 0, 0, 0, 0, /* crc */ + 0, 0, 0, 0 /* uncompressed length */ +}; + +/* initialize a log object with locking */ +void *gzlog_open(char *path) +{ + unsigned xlen; + unsigned char temp[20]; + unsigned sub_len; + int good; + gz_log *log; + + /* allocate log structure */ + log = malloc(sizeof(gz_log)); + if (log == NULL) + return NULL; + log->id = GZLOGID; + + /* open file, creating it if necessary, and locking it */ + log->fd = open(path, O_RDWR | O_CREAT, 0600); + if (log->fd < 0) { + free(log); + return NULL; + } + if (lock(log->fd)) { + close(log->fd); + free(log); + return NULL; + } + + /* if file is empty, write new gzip stream */ + if (lseek(log->fd, 0, SEEK_END) == 0) { + if (write(log->fd, empty_gz, sizeof(empty_gz)) != sizeof(empty_gz)) { + log_clean(log); + return NULL; + } + } + + /* check gzip header */ + (void)lseek(log->fd, 0, SEEK_SET); + if (read(log->fd, temp, 12) != 12 || temp[0] != 0x1f || + temp[1] != 0x8b || temp[2] != 8 || (temp[3] & 4) == 0) { + log_clean(log); + return NULL; + } + + /* process extra field to find "ap" sub-field */ + xlen = temp[10] + (temp[11] << 8); + good = 0; + while (xlen) { + if (xlen < 4 || read(log->fd, temp, 4) != 4) + break; + sub_len = temp[2]; + sub_len += temp[3] << 8; + xlen -= 4; + if (memcmp(temp, "ap", 2) == 0 && sub_len == 16) { + good = 1; + break; + } + if (xlen < sub_len) + break; + (void)lseek(log->fd, sub_len, SEEK_CUR); + xlen -= sub_len; + } + if (!good) { + log_clean(log); + return NULL; + } + + /* read in "ap" sub-field */ + log->extra = lseek(log->fd, 0, SEEK_CUR); + if (read(log->fd, temp, 16) != 16) { + log_clean(log); + return NULL; + } + log->mark_off = make_off(temp); + log->last_off = make_off(temp + 8); + + /* get crc, length of gzip file */ + (void)lseek(log->fd, log->last_off, SEEK_SET); + if (read(log->fd, temp, 13) != 13 || + memcmp(temp, "\001\000\000\377\377", 5) != 0) { + log_clean(log); + return NULL; + } + log->crc = make_ulg(temp + 5); + log->len = make_ulg(temp + 9); + + /* set up to write over empty last block */ + (void)lseek(log->fd, log->last_off + 5, SEEK_SET); + log->stored = 0; + return (void *)log; +} + +/* maximum amount to put in a stored block before starting a new one */ +#define MAX_BLOCK 16384 + +/* write a block to a log object */ +int gzlog_write(void *obj, char *data, size_t len) +{ + size_t some; + unsigned char temp[5]; + gz_log *log; + + /* check object */ + log = (gz_log *)obj; + if (log == NULL || log->id != GZLOGID) + return 1; + + /* write stored blocks until all of the input is written */ + do { + some = MAX_BLOCK - log->stored; + if (some > len) + some = len; + if (write(log->fd, data, some) != some) + return 1; + log->crc = crc32(log->crc, data, some); + log->len += some; + len -= some; + data += some; + log->stored += some; + + /* if the stored block is full, end it and start another */ + if (log->stored == MAX_BLOCK) { + (void)lseek(log->fd, log->last_off, SEEK_SET); + temp[0] = 0; + dice_ulg(log->stored + ((unsigned long)(~log->stored) << 16), + temp + 1); + if (write(log->fd, temp, 5) != 5) + return 1; + log->last_off = lseek(log->fd, log->stored, SEEK_CUR); + (void)lseek(log->fd, 5, SEEK_CUR); + log->stored = 0; + } + } while (len); + return 0; +} + +/* recompress the remaining stored deflate data in place */ +local int recomp(gz_log *log) +{ + z_stream strm; + size_t len, max; + unsigned char *in; + unsigned char *out; + unsigned char temp[16]; + + /* allocate space and read it all in (it's around 1 MB) */ + len = log->last_off - log->mark_off; + max = len + (len >> 12) + (len >> 14) + 11; + out = malloc(max); + if (out == NULL) + return 1; + in = malloc(len); + if (in == NULL) { + free(out); + return 1; + } + (void)lseek(log->fd, log->mark_off, SEEK_SET); + if (read(log->fd, in, len) != len) { + free(in); + free(out); + return 1; + } + + /* recompress in memory, decoding stored data as we go */ + /* note: this assumes that unsigned is four bytes or more */ + /* consider not making that assumption */ + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + if (deflateInit2(&strm, Z_BEST_COMPRESSION, Z_DEFLATED, -15, 8, + Z_DEFAULT_STRATEGY) != Z_OK) { + free(in); + free(out); + return 1; + } + strm.next_in = in; + strm.avail_out = max; + strm.next_out = out; + while (len >= 5) { + if (strm.next_in[0] != 0) + break; + strm.avail_in = strm.next_in[1] + (strm.next_in[2] << 8); + strm.next_in += 5; + len -= 5; + if (strm.avail_in != 0) { + if (len < strm.avail_in) + break; + len -= strm.avail_in; + (void)deflate(&strm, Z_NO_FLUSH); + if (strm.avail_in != 0 || strm.avail_out == 0) + break; + } + } + (void)deflate(&strm, Z_SYNC_FLUSH); + (void)deflateEnd(&strm); + free(in); + if (len != 0 || strm.avail_out == 0) { + free(out); + return 1; + } + + /* overwrite stored data with compressed data */ + (void)lseek(log->fd, log->mark_off, SEEK_SET); + len = max - strm.avail_out; + if (write(log->fd, out, len) != len) { + free(out); + return 1; + } + free(out); + + /* write last empty block, crc, and length */ + log->mark_off = log->last_off = lseek(log->fd, 0, SEEK_CUR); + temp[0] = 1; + dice_ulg(0xffffL << 16, temp + 1); + dice_ulg(log->crc, temp + 5); + dice_ulg(log->len, temp + 9); + if (write(log->fd, temp, 13) != 13) + return 1; + + /* truncate file to discard remaining stored data and old trailer */ + ftruncate(log->fd, lseek(log->fd, 0, SEEK_CUR)); + + /* update extra field to point to new last empty block */ + (void)lseek(log->fd, log->extra, SEEK_SET); + dice_off(log->mark_off, temp); + dice_off(log->last_off, temp + 8); + if (write(log->fd, temp, 16) != 16) + return 1; + return 0; +} + +/* maximum accumulation of stored blocks before compressing */ +#define MAX_STORED 1048576 + +/* close log object */ +int gzlog_close(void *obj) +{ + unsigned char temp[8]; + gz_log *log; + + /* check object */ + log = (gz_log *)obj; + if (log == NULL || log->id != GZLOGID) + return 1; + + /* go to start of most recent block being written */ + (void)lseek(log->fd, log->last_off, SEEK_SET); + + /* if some stuff was put there, update block */ + if (log->stored) { + temp[0] = 0; + dice_ulg(log->stored + ((unsigned long)(~log->stored) << 16), + temp + 1); + if (write(log->fd, temp, 5) != 5) + return 1; + log->last_off = lseek(log->fd, log->stored, SEEK_CUR); + } + + /* write last block (empty) */ + if (write(log->fd, "\001\000\000\377\377", 5) != 5) + return 1; + + /* write updated crc and uncompressed length */ + dice_ulg(log->crc, temp); + dice_ulg(log->len, temp + 4); + if (write(log->fd, temp, 8) != 8) + return 1; + + /* put offset of that last block in gzip extra block */ + (void)lseek(log->fd, log->extra + 8, SEEK_SET); + dice_off(log->last_off, temp); + if (write(log->fd, temp, 8) != 8) + return 1; + + /* if more than 1 MB stored, then time to compress it */ + if (log->last_off - log->mark_off > MAX_STORED) { + if (recomp(log)) + return 1; + } + + /* unlock and close file */ + log_clean(log); + return 0; +} diff --git a/examples/gzlog.h b/examples/gzlog.h new file mode 100644 index 0000000..a800bd5 --- /dev/null +++ b/examples/gzlog.h @@ -0,0 +1,58 @@ +/* gzlog.h + Copyright (C) 2004 Mark Adler, all rights reserved + version 1.0, 26 Nov 2004 + + This software is provided 'as-is', without any express or implied + warranty. In no event will the author be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + Mark Adler madler@alumni.caltech.edu + */ + +/* + The gzlog object allows writing short messages to a gzipped log file, + opening the log file locked for small bursts, and then closing it. The log + object works by appending stored data to the gzip file until 1 MB has been + accumulated. At that time, the stored data is compressed, and replaces the + uncompressed data in the file. The log file is truncated to its new size at + that time. After closing, the log file is always valid gzip file that can + decompressed to recover what was written. + + A gzip header "extra" field contains two file offsets for appending. The + first points to just after the last compressed data. The second points to + the last stored block in the deflate stream, which is empty. All of the + data between those pointers is uncompressed. + */ + +/* Open a gzlog object, creating the log file if it does not exist. Return + NULL on error. Note that gzlog_open() could take a long time to return if + there is difficulty in locking the file. */ +void *gzlog_open(char *path); + +/* Write to a gzlog object. Return non-zero on error. This function will + simply write data to the file uncompressed. Compression of the data + will not occur until gzlog_close() is called. It is expected that + gzlog_write() is used for a short message, and then gzlog_close() is + called. If a large amount of data is to be written, then the application + should write no more than 1 MB at a time with gzlog_write() before + calling gzlog_close() and then gzlog_open() again. */ +int gzlog_write(void *log, char *data, size_t len); + +/* Close a gzlog object. Return non-zero on error. The log file is locked + until this function is called. This function will compress stored data + at the end of the gzip file if at least 1 MB has been accumulated. Note + that the file will not be a valid gzip file until this function completes. + */ +int gzlog_close(void *log); diff --git a/examples/zlib_how.html b/examples/zlib_how.html new file mode 100644 index 0000000..b2bda6b --- /dev/null +++ b/examples/zlib_how.html @@ -0,0 +1,522 @@ + + + + +zlib Usage Example + + + +

zlib Usage Example

+We often get questions about how the deflate() and inflate() functions should be used. +Users wonder when they should provide more input, when they should use more output, +what to do with a Z_BUF_ERROR, how to make sure the process terminates properly, and +so on. So for those who have read zlib.h (a few times), and +would like further edification, below is an annotated example in C of simple routines to compress and decompress +from an input file to an output file using deflate() and inflate() respectively. The +annotations are interspersed between lines of the code. So please read between the lines. +We hope this helps explain some of the intricacies of zlib. +

+Without further adieu, here is the program zpipe.c: +


+/* zpipe.c: example of proper use of zlib's inflate() and deflate()
+   Not copyrighted -- provided to the public domain
+   Version 1.2  9 November 2004  Mark Adler */
+
+/* Version history:
+   1.0  30 Oct 2004  First version
+   1.1   8 Nov 2004  Add void casting for unused return values
+                     Use switch statement for inflate() return values
+   1.2   9 Nov 2004  Add assertions to document zlib guarantees
+ */
+
+We now include the header files for the required definitions. From +stdio.h we use fopen(), fread(), fwrite(), +feof(), ferror(), and fclose() for file i/o, and +fputs() for error messages. From string.h we use +strcmp() for command line argument processing. +From assert.h we use the assert() macro. +From zlib.h +we use the basic compression functions deflateInit(), +deflate(), and deflateEnd(), and the basic decompression +functions inflateInit(), inflate(), and +inflateEnd(). +

+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include "zlib.h"
+
+CHUNK is simply the buffer size for feeding data to and pulling data +from the zlib routines. Larger buffer sizes would be more efficient, +especially for inflate(). If the memory is available, buffers sizes +on the order of 128K or 256K bytes should be used. +

+#define CHUNK 16384
+
+The def() routine compresses data from an input file to an output file. The output data +will be in the zlib format, which is different from the gzip or zip +formats. The zlib format has a very small header of only two bytes to identify it as +a zlib stream and to provide decoding information, and a four-byte trailer with a fast +check value to verify the integrity of the uncompressed data after decoding. +

+/* Compress from file source to file dest until EOF on source.
+   def() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+   allocated for processing, Z_STREAM_ERROR if an invalid compression
+   level is supplied, Z_VERSION_ERROR if the version of zlib.h and the
+   version of the library linked do not match, or Z_ERRNO if there is
+   an error reading or writing the files. */
+int def(FILE *source, FILE *dest, int level)
+{
+
+Here are the local variables for def(). ret will be used for zlib +return codes. flush will keep track of the current flushing state for deflate(), +which is either no flushing, or flush to completion after the end of the input file is reached. +have is the amount of data returned from deflate(). The strm structure +is used to pass information to and from the zlib routines, and to maintain the +deflate() state. in and out are the input and output buffers for +deflate(). +

+    int ret, flush;
+    unsigned have;
+    z_stream strm;
+    char in[CHUNK];
+    char out[CHUNK];
+
+The first thing we do is to initialize the zlib state for compression using +deflateInit(). This must be done before the first use of deflate(). +The zalloc, zfree, and opaque fields in the strm +structure must be initialized before calling deflateInit(). Here they are +set to the zlib constant Z_NULL to request that zlib use +the default memory allocation routines. An application may also choose to provide +custom memory allocation routines here. deflateInit() will allocate on the +order of 256K bytes for the internal state. +(See zlib Technical Details.) +

+deflateInit() is called with a pointer to the structure to be initialized and +the compression level, which is an integer in the range of -1 to 9. Lower compression +levels result in faster execution, but less compression. Higher levels result in +greater compression, but slower execution. The zlib constant Z_DEFAULT_COMPRESSION, +equal to -1, +provides a good compromise between compression and speed and is equivalent to level 6. +Level 0 actually does no compression at all, and in fact expands the data slightly to produce +the zlib format (it is not a byte-for-byte copy of the input). +More advanced applications of zlib +may use deflateInit2() here instead. Such an application may want to reduce how +much memory will be used, at some price in compression. Or it may need to request a +gzip header and trailer instead of a zlib header and trailer, or raw +encoding with no header or trailer at all. +

+We must check the return value of deflateInit() against the zlib constant +Z_OK to make sure that it was able to +allocate memory for the internal state, and that the provided arguments were valid. +deflateInit() will also check that the version of zlib that the zlib.h +file came from matches the version of zlib actually linked with the program. This +is especially important for environments in which zlib is a shared library. +

+Note that an application can initialize multiple, independent zlib streams, which can +operate in parallel. The state information maintained in the structure allows the zlib +routines to be reentrant. +


+    /* allocate deflate state */
+    strm.zalloc = Z_NULL;
+    strm.zfree = Z_NULL;
+    strm.opaque = Z_NULL;
+    ret = deflateInit(&strm, level);
+    if (ret != Z_OK)
+        return ret;
+
+With the pleasantries out of the way, now we can get down to business. The outer do-loop +reads all of the input file and exits at the bottom of the loop once end-of-file is reached. +This loop contains the only call of deflate(). So we must make sure that all of the +input data has been processed and that all of the output data has been generated and consumed +before we fall out of the loop at the bottom. +

+    /* compress until end of file */
+    do {
+
+We start off by reading data from the input file. The number of bytes read is put directly +into avail_in, and a pointer to those bytes is put into next_in. We also +check to see if end-of-file on the input has been reached. If we are at the end of file, then flush is set to the +zlib constant Z_FINISH, which is later passed to deflate() to +indicate that this is the last chunk of input data to compress. We need to use feof() +to check for end-of-file as opposed to seeing if fewer than CHUNK bytes have been read. The +reason is that if the input file length is an exact multiple of CHUNK, we will miss +the fact that we got to the end-of-file, and not know to tell deflate() to finish +up the compressed stream. If we are not yet at the end of the input, then the zlib +constant Z_NO_FLUSH will be passed to deflate to indicate that we are still +in the middle of the uncompressed data. +

+If there is an error in reading from the input file, the process is aborted with +deflateEnd() being called to free the allocated zlib state before returning +the error. We wouldn't want a memory leak, now would we? deflateEnd() can be called +at any time after the state has been initialized. Once that's done, deflateInit() (or +deflateInit2()) would have to be called to start a new compression process. There is +no point here in checking the deflateEnd() return code. The deallocation can't fail. +


+        strm.avail_in = fread(in, 1, CHUNK, source);
+        if (ferror(source)) {
+            (void)deflateEnd(&strm);
+            return Z_ERRNO;
+        }
+        flush = feof(source) ? Z_FINISH : Z_NO_FLUSH;
+        strm.next_in = in;
+
+The inner do-loop passes our chunk of input data to deflate(), and then +keeps calling deflate() until it is done producing output. Once there is no more +new output, deflate() is guaranteed to have consumed all of the input, i.e., +avail_in will be zero. +

+        /* run deflate() on input until output buffer not full, finish
+           compression if all of source has been read in */
+        do {
+
+Output space is provided to deflate() by setting avail_out to the number +of available output bytes and next_out to a pointer to that space. +

+            strm.avail_out = CHUNK;
+            strm.next_out = out;
+
+Now we call the compression engine itself, deflate(). It takes as many of the +avail_in bytes at next_in as it can process, and writes as many as +avail_out bytes to next_out. Those counters and pointers are then +updated past the input data consumed and the output data written. It is the amount of +output space available that may limit how much input is consumed. +Hence the inner loop to make sure that +all of the input is consumed by providing more output space each time. Since avail_in +and next_in are updated by deflate(), we don't have to mess with those +between deflate() calls until it's all used up. +

+The parameters to deflate() are a pointer to the strm structure containing +the input and output information and the internal compression engine state, and a parameter +indicating whether and how to flush data to the output. Normally deflate will consume +several K bytes of input data before producing any output (except for the header), in order +to accumulate statistics on the data for optimum compression. It will then put out a burst of +compressed data, and proceed to consume more input before the next burst. Eventually, +deflate() +must be told to terminate the stream, complete the compression with provided input data, and +write out the trailer check value. deflate() will continue to compress normally as long +as the flush parameter is Z_NO_FLUSH. Once the Z_FINISH parameter is provided, +deflate() will begin to complete the compressed output stream. However depending on how +much output space is provided, deflate() may have to be called several times until it +has provided the complete compressed stream, even after it has consumed all of the input. The flush +parameter must continue to be Z_FINISH for those subsequent calls. +

+There are other values of the flush parameter that are used in more advanced applications. You can +force deflate() to produce a burst of output that encodes all of the input data provided +so far, even if it wouldn't have otherwise, for example to control data latency on a link with +compressed data. You can also ask that deflate() do that as well as erase any history up to +that point so that what follows can be decompressed independently, for example for random access +applications. Both requests will degrade compression by an amount depending on how often such +requests are made. +

+deflate() has a return value that can indicate errors, yet we do not check it here. Why +not? Well, it turns out that deflate() can do no wrong here. Let's go through +deflate()'s return values and dispense with them one by one. The possible values are +Z_OK, Z_STREAM_END, Z_STREAM_ERROR, or Z_BUF_ERROR. Z_OK +is, well, ok. Z_STREAM_END is also ok and will be returned for the last call of +deflate(). This is already guaranteed by calling deflate() with Z_FINISH +until it has no more output. Z_STREAM_ERROR is only possible if the stream is not +initialized properly, but we did initialize it properly. There is no harm in checking for +Z_STREAM_ERROR here, for example to check for the possibility that some +other part of the application inadvertently clobbered the memory containing the zlib state. +Z_BUF_ERROR will be explained further below, but +suffice it to say that this is simply an indication that deflate() could not consume +more input or produce more output. deflate() can be called again with more output space +or more available input, which it will be in this code. +


+            ret = deflate(&strm, flush);    /* no bad return value */
+            assert(ret != Z_STREAM_ERROR);  /* state not clobbered */
+
+Now we compute how much output deflate() provided on the last call, which is the +difference between how much space was provided before the call, and how much output space +is still available after the call. Then that data, if any, is written to the output file. +We can then reuse the output buffer for the next call of deflate(). Again if there +is a file i/o error, we call deflateEnd() before returning to avoid a memory leak. +

+            have = CHUNK - strm.avail_out;
+            if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+                (void)deflateEnd(&strm);
+                return Z_ERRNO;
+            }
+
+The inner do-loop is repeated until the last deflate() call fails to fill the +provided output buffer. Then we know that deflate() has done as much as it can with +the provided input, and that all of that input has been consumed. We can then fall out of this +loop and reuse the input buffer. +

+The way we tell that deflate() has no more output is by seeing that it did not fill +the output buffer, leaving avail_out greater than zero. However suppose that +deflate() has no more output, but just so happened to exactly fill the output buffer! +avail_out is zero, and we can't tell that deflate() has done all it can. +As far as we know, deflate() +has more output for us. So we call it again. But now deflate() produces no output +at all, and avail_out remains unchanged as CHUNK. That deflate() call +wasn't able to do anything, either consume input or produce output, and so it returns +Z_BUF_ERROR. (See, I told you I'd cover this later.) However this is not a problem at +all. Now we finally have the desired indication that deflate() is really done, +and so we drop out of the inner loop to provide more input to deflate(). +

+With flush set to Z_FINISH, this final set of deflate() calls will +complete the output stream. Once that is done, subsequent calls of deflate() would return +Z_STREAM_ERROR if the flush parameter is not Z_FINISH, and do no more processing +until the state is reinitialized. +

+Some applications of zlib have two loops that call deflate() +instead of the single inner loop we have here. The first loop would call +without flushing and feed all of the data to deflate(). The second loop would call +deflate() with no more +data and the Z_FINISH parameter to complete the process. As you can see from this +example, that can be avoided by simply keeping track of the current flush state. +


+        } while (strm.avail_out == 0);
+        assert(strm.avail_in == 0);     /* all input will be used */
+
+Now we check to see if we have already processed all of the input file. That information was +saved in the flush variable, so we see if that was set to Z_FINISH. If so, +then we're done and we fall out of the outer loop. We're guaranteed to get Z_STREAM_END +from the last deflate() call, since we ran it until the last chunk of input was +consumed and all of the output was generated. +

+        /* done when last data in file processed */
+    } while (flush != Z_FINISH);
+    assert(ret == Z_STREAM_END);        /* stream will be complete */
+
+The process is complete, but we still need to deallocate the state to avoid a memory leak +(or rather more like a memory hemorrhage if you didn't do this). Then +finally we can return with a happy return value. +

+    /* clean up and return */
+    (void)deflateEnd(&strm);
+    return Z_OK;
+}
+
+Now we do the same thing for decompression in the inf() routine. inf() +decompresses what is hopefully a valid zlib stream from the input file and writes the +uncompressed data to the output file. Much of the discussion above for def() +applies to inf() as well, so the discussion here will focus on the differences between +the two. +

+/* Decompress from file source to file dest until stream ends or EOF.
+   inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+   allocated for processing, Z_DATA_ERROR if the deflate data is
+   invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and
+   the version of the library linked do not match, or Z_ERRNO if there
+   is an error reading or writing the files. */
+int inf(FILE *source, FILE *dest)
+{
+
+The local variables have the same functionality as they do for def(). The +only difference is that there is no flush variable, since inflate() +can tell from the zlib stream itself when the stream is complete. +

+    int ret;
+    unsigned have;
+    z_stream strm;
+    char in[CHUNK];
+    char out[CHUNK];
+
+The initialization of the state is the same, except that there is no compression level, +of course, and two more elements of the structure are initialized. avail_in +and next_in must be initialized before calling inflateInit(). This +is because the application has the option to provide the start of the zlib stream in +order for inflateInit() to have access to information about the compression +method to aid in memory allocation. In the current implementation of zlib +(up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of +inflate() anyway. However those fields must be initialized since later versions +of zlib that provide more compression methods may take advantage of this interface. +In any case, no decompression is performed by inflateInit(), so the +avail_out and next_out fields do not need to be initialized before calling. +

+Here avail_in is set to zero and next_in is set to Z_NULL to +indicate that no input data is being provided. +


+    /* allocate inflate state */
+    strm.zalloc = Z_NULL;
+    strm.zfree = Z_NULL;
+    strm.opaque = Z_NULL;
+    strm.avail_in = 0;
+    strm.next_in = Z_NULL;
+    ret = inflateInit(&strm);
+    if (ret != Z_OK)
+        return ret;
+
+The outer do-loop decompresses input until inflate() indicates +that it has reached the end of the compressed data and has produced all of the uncompressed +output. This is in contrast to def() which processes all of the input file. +If end-of-file is reached before the compressed data self-terminates, then the compressed +data is incomplete and an error is returned. +

+    /* decompress until deflate stream ends or end of file */
+    do {
+
+We read input data and set the strm structure accordingly. If we've reached the +end of the input file, then we leave the outer loop and report an error, since the +compressed data is incomplete. Note that we may read more data than is eventually consumed +by inflate(), if the input file continues past the zlib stream. +For applications where zlib streams are embedded in other data, this routine would +need to be modified to return the unused data, or at least indicate how much of the input +data was not used, so the application would know where to pick up after the zlib stream. +

+        strm.avail_in = fread(in, 1, CHUNK, source);
+        if (ferror(source)) {
+            (void)inflateEnd(&strm);
+            return Z_ERRNO;
+        }
+        if (strm.avail_in == 0)
+            break;
+        strm.next_in = in;
+
+The inner do-loop has the same function it did in def(), which is to +keep calling inflate() until has generated all of the output it can with the +provided input. +

+        /* run inflate() on input until output buffer not full */
+        do {
+
+Just like in def(), the same output space is provided for each call of inflate(). +

+            strm.avail_out = CHUNK;
+            strm.next_out = out;
+
+Now we run the decompression engine itself. There is no need to adjust the flush parameter, since +the zlib format is self-terminating. The main difference here is that there are +return values that we need to pay attention to. Z_DATA_ERROR +indicates that inflate() detected an error in the zlib compressed data format, +which means that either the data is not a zlib stream to begin with, or that the data was +corrupted somewhere along the way since it was compressed. The other error to be processed is +Z_MEM_ERROR, which can occur since memory allocation is deferred until inflate() +needs it, unlike deflate(), whose memory is allocated at the start by deflateInit(). +

+Advanced applications may use +deflateSetDictionary() to prime deflate() with a set of likely data to improve the +first 32K or so of compression. This is noted in the zlib header, so inflate() +requests that that dictionary be provided before it can start to decompress. Without the dictionary, +correct decompression is not possible. For this routine, we have no idea what the dictionary is, +so the Z_NEED_DICT indication is converted to a Z_DATA_ERROR. +

+inflate() can also return Z_STREAM_ERROR, which should not be possible here, +but could be checked for as noted above for def(). Z_BUF_ERROR does not need to be +checked for here, for the same reasons noted for def(). Z_STREAM_END will be +checked for later. +


+            ret = inflate(&strm, Z_NO_FLUSH);
+            assert(ret != Z_STREAM_ERROR);  /* state not clobbered */
+            switch (ret) {
+            case Z_NEED_DICT:
+                ret = Z_DATA_ERROR;     /* and fall through */
+            case Z_DATA_ERROR:
+            case Z_MEM_ERROR:
+                (void)inflateEnd(&strm);
+                return ret;
+            }
+
+The output of inflate() is handled identically to that of deflate(). +

+            have = CHUNK - strm.avail_out;
+            if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+                (void)inflateEnd(&strm);
+                return Z_ERRNO;
+            }
+
+The inner do-loop ends when inflate() has no more output as indicated +by not filling the output buffer, just as for deflate(). +

+        } while (strm.avail_out == 0);
+        assert(strm.avail_in == 0);     /* all input will be used */
+
+The outer do-loop ends when inflate() reports that it has reached the +end of the input zlib stream, has completed the decompression and integrity +check, and has provided all of the output. This is indicated by the inflate() +return value Z_STREAM_END. The inner loop is guaranteed to leave ret +equal to Z_STREAM_END if the last chunk of the input file read contained the end +of the zlib stream. So if the return value is not Z_STREAM_END, the +loop continues to read more input. +

+        /* done when inflate() says it's done */
+    } while (ret != Z_STREAM_END);
+
+At this point, decompression successfully completed, or we broke out of the loop due to no +more data being available from the input file. If the last inflate() return value +is not Z_STREAM_END, then the zlib stream was incomplete and a data error +is returned. Otherwise, we return with a happy return value. Of course, inflateEnd() +is called first to avoid a memory leak. +

+    /* clean up and return */
+    (void)inflateEnd(&strm);
+    return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
+}
+
+That ends the routines that directly use zlib. The following routines make this +a command-line program by running data through the above routines from stdin to +stdout, and handling any errors reported by def() or inf(). +

+zerr() is used to interpret the possible error codes from def() +and inf(), as detailed in their comments above, and print out an error message. +Note that these are only a subset of the possible return values from deflate() +and inflate(). +


+/* report a zlib or i/o error */
+void zerr(int ret)
+{
+    fputs("zpipe: ", stderr);
+    switch (ret) {
+    case Z_ERRNO:
+        if (ferror(stdin))
+            fputs("error reading stdin\n", stderr);
+        if (ferror(stdout))
+            fputs("error writing stdout\n", stderr);
+        break;
+    case Z_STREAM_ERROR:
+        fputs("invalid compression level\n", stderr);
+        break;
+    case Z_DATA_ERROR:
+        fputs("invalid or incomplete deflate data\n", stderr);
+        break;
+    case Z_MEM_ERROR:
+        fputs("out of memory\n", stderr);
+        break;
+    case Z_VERSION_ERROR:
+        fputs("zlib version mismatch!\n", stderr);
+    }
+}
+
+Here is the main() routine used to test def() and inf(). The +zpipe command is simply a compression pipe from stdin to stdout, if +no arguments are given, or it is a decompression pipe if zpipe -d is used. If any other +arguments are provided, no compression or decompression is performed. Instead a usage +message is displayed. Examples are zpipe < foo.txt > foo.txt.z to compress, and +zpipe -d < foo.txt.z > foo.txt to decompress. +

+/* compress or decompress from stdin to stdout */
+int main(int argc, char **argv)
+{
+    int ret;
+
+    /* do compression if no arguments */
+    if (argc == 1) {
+        ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION);
+        if (ret != Z_OK)
+            zerr(ret);
+        return ret;
+    }
+
+    /* do decompression if -d specified */
+    else if (argc == 2 && strcmp(argv[1], "-d") == 0) {
+        ret = inf(stdin, stdout);
+        if (ret != Z_OK)
+            zerr(ret);
+        return ret;
+    }
+
+    /* otherwise, report usage */
+    else {
+        fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr);
+        return 1;
+    }
+}
+
+
+Copyright (c) 2004 by Mark Adler
Last modified 13 November 2004 + + diff --git a/examples/zpipe.c b/examples/zpipe.c new file mode 100644 index 0000000..a602d59 --- /dev/null +++ b/examples/zpipe.c @@ -0,0 +1,191 @@ +/* zpipe.c: example of proper use of zlib's inflate() and deflate() + Not copyrighted -- provided to the public domain + Version 1.2 9 November 2004 Mark Adler */ + +/* Version history: + 1.0 30 Oct 2004 First version + 1.1 8 Nov 2004 Add void casting for unused return values + Use switch statement for inflate() return values + 1.2 9 Nov 2004 Add assertions to document zlib guarantees + */ + +#include +#include +#include +#include "zlib.h" + +#define CHUNK 16384 + +/* Compress from file source to file dest until EOF on source. + def() returns Z_OK on success, Z_MEM_ERROR if memory could not be + allocated for processing, Z_STREAM_ERROR if an invalid compression + level is supplied, Z_VERSION_ERROR if the version of zlib.h and the + version of the library linked do not match, or Z_ERRNO if there is + an error reading or writing the files. */ +int def(FILE *source, FILE *dest, int level) +{ + int ret, flush; + unsigned have; + z_stream strm; + char in[CHUNK]; + char out[CHUNK]; + + /* allocate deflate state */ + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + ret = deflateInit(&strm, level); + if (ret != Z_OK) + return ret; + + /* compress until end of file */ + do { + strm.avail_in = fread(in, 1, CHUNK, source); + if (ferror(source)) { + (void)deflateEnd(&strm); + return Z_ERRNO; + } + flush = feof(source) ? Z_FINISH : Z_NO_FLUSH; + strm.next_in = in; + + /* run deflate() on input until output buffer not full, finish + compression if all of source has been read in */ + do { + strm.avail_out = CHUNK; + strm.next_out = out; + ret = deflate(&strm, flush); /* no bad return value */ + assert(ret != Z_STREAM_ERROR); /* state not clobbered */ + have = CHUNK - strm.avail_out; + if (fwrite(out, 1, have, dest) != have || ferror(dest)) { + (void)deflateEnd(&strm); + return Z_ERRNO; + } + } while (strm.avail_out == 0); + assert(strm.avail_in == 0); /* all input will be used */ + + /* done when last data in file processed */ + } while (flush != Z_FINISH); + assert(ret == Z_STREAM_END); /* stream will be complete */ + + /* clean up and return */ + (void)deflateEnd(&strm); + return Z_OK; +} + +/* Decompress from file source to file dest until stream ends or EOF. + inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be + allocated for processing, Z_DATA_ERROR if the deflate data is + invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and + the version of the library linked do not match, or Z_ERRNO if there + is an error reading or writing the files. */ +int inf(FILE *source, FILE *dest) +{ + int ret; + unsigned have; + z_stream strm; + char in[CHUNK]; + char out[CHUNK]; + + /* allocate inflate state */ + strm.zalloc = Z_NULL; + strm.zfree = Z_NULL; + strm.opaque = Z_NULL; + strm.avail_in = 0; + strm.next_in = Z_NULL; + ret = inflateInit(&strm); + if (ret != Z_OK) + return ret; + + /* decompress until deflate stream ends or end of file */ + do { + strm.avail_in = fread(in, 1, CHUNK, source); + if (ferror(source)) { + (void)inflateEnd(&strm); + return Z_ERRNO; + } + if (strm.avail_in == 0) + break; + strm.next_in = in; + + /* run inflate() on input until output buffer not full */ + do { + strm.avail_out = CHUNK; + strm.next_out = out; + ret = inflate(&strm, Z_NO_FLUSH); + assert(ret != Z_STREAM_ERROR); /* state not clobbered */ + switch (ret) { + case Z_NEED_DICT: + ret = Z_DATA_ERROR; /* and fall through */ + case Z_DATA_ERROR: + case Z_MEM_ERROR: + (void)inflateEnd(&strm); + return ret; + } + have = CHUNK - strm.avail_out; + if (fwrite(out, 1, have, dest) != have || ferror(dest)) { + (void)inflateEnd(&strm); + return Z_ERRNO; + } + } while (strm.avail_out == 0); + assert(strm.avail_in == 0); /* all input will be used */ + + /* done when inflate() says it's done */ + } while (ret != Z_STREAM_END); + + /* clean up and return */ + (void)inflateEnd(&strm); + return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR; +} + +/* report a zlib or i/o error */ +void zerr(int ret) +{ + fputs("zpipe: ", stderr); + switch (ret) { + case Z_ERRNO: + if (ferror(stdin)) + fputs("error reading stdin\n", stderr); + if (ferror(stdout)) + fputs("error writing stdout\n", stderr); + break; + case Z_STREAM_ERROR: + fputs("invalid compression level\n", stderr); + break; + case Z_DATA_ERROR: + fputs("invalid or incomplete deflate data\n", stderr); + break; + case Z_MEM_ERROR: + fputs("out of memory\n", stderr); + break; + case Z_VERSION_ERROR: + fputs("zlib version mismatch!\n", stderr); + } +} + +/* compress or decompress from stdin to stdout */ +int main(int argc, char **argv) +{ + int ret; + + /* do compression if no arguments */ + if (argc == 1) { + ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION); + if (ret != Z_OK) + zerr(ret); + return ret; + } + + /* do decompression if -d specified */ + else if (argc == 2 && strcmp(argv[1], "-d") == 0) { + ret = inf(stdin, stdout); + if (ret != Z_OK) + zerr(ret); + return ret; + } + + /* otherwise, report usage */ + else { + fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr); + return 1; + } +} diff --git a/gzio.c b/gzio.c index ce55f2d..217a4cc 100644 --- a/gzio.c +++ b/gzio.c @@ -220,7 +220,7 @@ gzFile ZEXPORT gzdopen (fd, mode) int fd; const char *mode; { - char name[20]; + char name[46]; /* allow for up to 128-bit integers */ if (fd < 0) return (gzFile)Z_NULL; sprintf(name, "", fd); /* for debugging */ @@ -959,6 +959,12 @@ int ZEXPORT gzclose (file) return destroy((gz_stream*)file); } +#ifdef STDC +# define zstrerror(errnum) strerror(errnum) +#else +# define zstrerror(errnum) "" +#endif + /* =========================================================================== Returns the error message for the last error which occured on the given compressed file. errnum is set to zlib error number. If an diff --git a/infback.c b/infback.c index 005ddec..c78d273 100644 --- a/infback.c +++ b/infback.c @@ -51,6 +51,7 @@ int stream_size; if (state == Z_NULL) return Z_MEM_ERROR; Tracev((stderr, "inflate: allocated\n")); strm->state = (voidpf)state; + state->dmax = 32768U; state->wbits = windowBits; state->wsize = 1U << windowBits; state->window = window; diff --git a/inffast.c b/inffast.c index 8c02a17..bbee92e 100644 --- a/inffast.c +++ b/inffast.c @@ -74,6 +74,9 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ unsigned char FAR *out; /* local strm->next_out */ unsigned char FAR *beg; /* inflate()'s initial strm->next_out */ unsigned char FAR *end; /* while out < end, enough space available */ +#ifdef INFLATE_STRICT + unsigned dmax; /* maximum distance from zlib header */ +#endif unsigned wsize; /* window size or zero if not using window */ unsigned whave; /* valid bytes in the window */ unsigned write; /* window write index */ @@ -98,6 +101,9 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ out = strm->next_out - OFF; beg = out - (start - strm->avail_out); end = out + (strm->avail_out - 257); +#ifdef INFLATE_STRICT + dmax = state->dmax; +#endif wsize = state->wsize; whave = state->whave; write = state->write; @@ -167,6 +173,13 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ } } dist += (unsigned)hold & ((1U << op) - 1); +#ifdef INFLATE_STRICT + if (dist > dmax) { + strm->msg = (char *)"invalid distance too far back"; + state->mode = BAD; + break; + } +#endif hold >>= op; bits -= op; Tracevv((stderr, "inflate: distance %u\n", dist)); diff --git a/inflate.c b/inflate.c index cca1d3b..5733437 100644 --- a/inflate.c +++ b/inflate.c @@ -113,6 +113,7 @@ z_streamp strm; state->mode = HEAD; state->last = 0; state->havedict = 0; + state->dmax = 32768U; state->head = Z_NULL; state->wsize = 0; state->whave = 0; @@ -600,11 +601,13 @@ int flush; break; } DROPBITS(4); - if (BITS(4) + 8 > state->wbits) { + len = BITS(4) + 8; + if (len > state->wbits) { strm->msg = (char *)"invalid window size"; state->mode = BAD; break; } + state->dmax = 1U << len; Tracev((stderr, "inflate: zlib header ok\n")); strm->adler = state->check = adler32(0L, Z_NULL, 0); state->mode = hold & 0x200 ? DICTID : TYPE; @@ -1009,6 +1012,13 @@ int flush; state->offset += BITS(state->extra); DROPBITS(state->extra); } +#ifdef INFLATE_STRICT + if (state->offset > state->dmax) { + strm->msg = (char *)"invalid distance too far back"; + state->mode = BAD; + break; + } +#endif if (state->offset > state->whave + out - left) { strm->msg = (char *)"invalid distance too far back"; state->mode = BAD; @@ -1322,8 +1332,8 @@ z_streamp source; } /* copy state */ - *dest = *source; - *copy = *state; + zmemcpy(dest, source, sizeof(z_stream)); + zmemcpy(copy, state, sizeof(struct inflate_state)); copy->lencode = copy->codes + (state->lencode - state->codes); copy->distcode = copy->codes + (state->distcode - state->codes); copy->next = copy->codes + (state->next - state->codes); diff --git a/inflate.h b/inflate.h index 3628603..07bd3e7 100644 --- a/inflate.h +++ b/inflate.h @@ -80,6 +80,7 @@ struct inflate_state { int wrap; /* bit 0 true for zlib, bit 1 true for gzip */ int havedict; /* true if dictionary provided */ int flags; /* gzip header method and flags (0 if zlib) */ + unsigned dmax; /* zlib header max distance (INFLATE_STRICT) */ unsigned long check; /* protected copy of check value */ unsigned long total; /* protected copy of output count */ gz_headerp head; /* where to save gzip header information */ diff --git a/inftrees.c b/inftrees.c index b594995..72c5b75 100644 --- a/inftrees.c +++ b/inftrees.c @@ -9,7 +9,7 @@ #define MAXBITS 15 const char inflate_copyright[] = - " inflate 1.2.2.1 Copyright 1995-2004 Mark Adler "; + " inflate 1.2.2.2 Copyright 1995-2004 Mark Adler "; /* If you use the zlib library in a product, an acknowledgment is welcome in the documentation of your product. If for some reason you cannot @@ -62,7 +62,7 @@ unsigned short FAR *work; 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; static const unsigned short lext[31] = { /* Length codes 257..285 extra */ 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18, - 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 77, 207}; + 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 72, 199}; static const unsigned short dbase[32] = { /* Distance codes 0..29 base */ 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, diff --git a/old/Make_vms.com b/make_vms.com old mode 100755 new mode 100644 similarity index 82% rename from old/Make_vms.com rename to make_vms.com index 4fe3013..e6587cd --- a/old/Make_vms.com +++ b/make_vms.com @@ -32,25 +32,24 @@ $ CALL MAKE adler32.OBJ "CC ''CCOPT' adler32" - $ CALL MAKE compress.OBJ "CC ''CCOPT' compress" - compress.c zlib.h zconf.h $ CALL MAKE crc32.OBJ "CC ''CCOPT' crc32" - - crc32.c zlib.h zconf.h + crc32.c crc32.h zlib.h zconf.h zutil.h $ CALL MAKE deflate.OBJ "CC ''CCOPT' deflate" - deflate.c deflate.h zutil.h zlib.h zconf.h -$ CALL MAKE gzio.OBJ "CC ''CCOPT' gzio" - +$ CALL MAKE gzio.OBJ "CC ''CCOPT' gzio /define=""NO_vsnprintf""" - gzio.c zutil.h zlib.h zconf.h -$ CALL MAKE infblock.OBJ "CC ''CCOPT' infblock" - - infblock.c zutil.h zlib.h zconf.h infblock.h -$ CALL MAKE infcodes.OBJ "CC ''CCOPT' infcodes" - - infcodes.c zutil.h zlib.h zconf.h inftrees.h +$ CALL MAKE infback.OBJ "CC ''CCOPT' infback" - + infback.c zutil.h zlib.h zconf.h - + "inftrees.h inflate.h inffast.h inffixed.h" $ CALL MAKE inffast.OBJ "CC ''CCOPT' inffast" - - inffast.c zutil.h zlib.h zconf.h inffast.h + inffast.c zutil.h zlib.h zconf.h - + "inftrees.h inflate.h inffast.h" $ CALL MAKE inflate.OBJ "CC ''CCOPT' inflate" - - inflate.c zutil.h zlib.h zconf.h infblock.h + inflate.c zutil.h zlib.h zconf.h - + "inftrees.h inflate.h inffast.h inffixed.h" $ CALL MAKE inftrees.OBJ "CC ''CCOPT' inftrees" - inftrees.c zutil.h zlib.h zconf.h inftrees.h -$ CALL MAKE infutil.OBJ "CC ''CCOPT' infutil" - - infutil.c zutil.h zlib.h zconf.h inftrees.h infutil.h $ CALL MAKE trees.OBJ "CC ''CCOPT' trees" - - trees.c deflate.h zutil.h zlib.h zconf.h + trees.c trees.h deflate.h zutil.h zlib.h zconf.h $ CALL MAKE uncompr.OBJ "CC ''CCOPT' uncompr" - uncompr.c zlib.h zconf.h $ CALL MAKE zutil.OBJ "CC ''CCOPT' zutil" - @@ -65,7 +64,7 @@ $ write sys$output "Building minigzip..." $ CALL MAKE minigzip.OBJ "CC ''CCOPT' minigzip" - minigzip.c zlib.h zconf.h $ call make minigzip.exe - - "LINK minigzip,libz.olb/lib,x11vms:xvmsutils.olb/lib" - + "LINK minigzip,libz.olb/lib" - minigzip.obj libz.olb $ else $ mms/macro=('comp') diff --git a/qnx/package.qpg b/qnx/package.qpg index e80311c..03cd351 100644 --- a/qnx/package.qpg +++ b/qnx/package.qpg @@ -25,10 +25,10 @@ - - - - + + + + @@ -63,7 +63,7 @@ - 1.2.2.1 + 1.2.2.2 Medium Stable diff --git a/trees.c b/trees.c index e5c66f6..48c651b 100644 --- a/trees.c +++ b/trees.c @@ -934,22 +934,6 @@ void _tr_flush_block(s, buf, stored_len, eof) if (stored_len > 0 && s->strm->data_type == Z_UNKNOWN) set_data_type(s); -#ifdef DEBUG - /* Write out literal/length frequencies for benchmarking */ - if (z_verbose) { - FILE *freq; - freq = fopen("defreq.txt", "a"); - if (freq != NULL) { - int n; - fputs("ltree:", freq); - for (n = 0; n < L_CODES; n++) - fprintf(freq, " %d", s->dyn_ltree[n].Freq); - putc('\n', freq); - fclose(freq); - } - } -#endif - /* 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, @@ -999,7 +983,7 @@ void _tr_flush_block(s, buf, stored_len, eof) #ifdef FORCE_STATIC } else if (static_lenb >= 0) { /* force static trees */ #else - } else if (static_lenb == opt_lenb) { + } 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); diff --git a/win32/zlib1.rc b/win32/zlib1.rc index 2e98542..1d37694 100644 --- a/win32/zlib1.rc +++ b/win32/zlib1.rc @@ -5,8 +5,8 @@ VS_VERSION_INFO VERSIONINFO #else VS_VERSION_INFO VERSIONINFO MOVEABLE IMPURE LOADONCALL DISCARDABLE #endif - FILEVERSION 1,2,2,1 - PRODUCTVERSION 1,2,2,1 + FILEVERSION 1,2,2,2 + PRODUCTVERSION 1,2,2,2 FILEFLAGSMASK VS_FFI_FILEFLAGSMASK #ifdef _DEBUG FILEFLAGS 1 @@ -23,12 +23,12 @@ BEGIN //language ID = U.S. English, char set = Windows, Multilingual BEGIN VALUE "FileDescription", "zlib data compression library\0" - VALUE "FileVersion", "1.2.2.1\0" + VALUE "FileVersion", "1.2.2.2\0" VALUE "InternalName", "zlib1.dll\0" VALUE "LegalCopyright", "(C) 1995-2004 Jean-loup Gailly & Mark Adler\0" VALUE "OriginalFilename", "zlib1.dll\0" VALUE "ProductName", "zlib\0" - VALUE "ProductVersion", "1.2.2.1\0" + VALUE "ProductVersion", "1.2.2.2\0" VALUE "Comments","DLL support by Alessandro Iacopetti & Gilles Vollant\0" END END diff --git a/zlib.3 b/zlib.3 index 0e8d735..17491cc 100644 --- a/zlib.3 +++ b/zlib.3 @@ -1,4 +1,4 @@ -.TH ZLIB 3 "31 October 2004" +.TH ZLIB 3 "30 December 2004" .SH NAME zlib \- compression/decompression library .SH SYNOPSIS @@ -133,7 +133,7 @@ before asking for help. Send questions and/or comments to zlib@gzip.org, or (for the Windows DLL version) to Gilles Vollant (info@winimage.com). .SH AUTHORS -Version 1.2.2.1 +Version 1.2.2.2 Copyright (C) 1995-2004 Jean-loup Gailly (jloup@gzip.org) and Mark Adler (madler@alumni.caltech.edu). .LP diff --git a/zlib.h b/zlib.h index 6417650..b13ca6f 100644 --- a/zlib.h +++ b/zlib.h @@ -1,5 +1,5 @@ /* zlib.h -- interface of the 'zlib' general purpose compression library - version 1.2.2.1, October 31st, 2004 + version 1.2.2.2, December 30th, 2004 Copyright (C) 1995-2004 Jean-loup Gailly and Mark Adler @@ -37,8 +37,8 @@ extern "C" { #endif -#define ZLIB_VERSION "1.2.2.1" -#define ZLIB_VERNUM 0x1221 +#define ZLIB_VERSION "1.2.2.2" +#define ZLIB_VERNUM 0x1222 /* The 'zlib' compression library provides in-memory compression and @@ -189,6 +189,7 @@ typedef gz_header FAR *gz_headerp; #define Z_FILTERED 1 #define Z_HUFFMAN_ONLY 2 #define Z_RLE 3 +#define Z_FIXED 4 #define Z_DEFAULT_STRATEGY 0 /* compression strategy; see deflateInit2() below for details */ @@ -391,11 +392,11 @@ ZEXTERN int ZEXPORT inflate OF((z_streamp strm, int flush)); The flush parameter of inflate() can be Z_NO_FLUSH, Z_SYNC_FLUSH, Z_FINISH, or Z_BLOCK. Z_SYNC_FLUSH requests that inflate() flush as much output as possible to the output buffer. Z_BLOCK requests that inflate() stop - if and when it get to the next deflate block boundary. When decoding the zlib - or gzip format, this will cause inflate() to return immediately after the - header and before the first block. When doing a raw inflate, inflate() will - go ahead and process the first block, and will return when it gets to the end - of that block, or when it runs out of data. + if and when it gets to the next deflate block boundary. When decoding the + zlib or gzip format, this will cause inflate() to return immediately after + the header and before the first block. When doing a raw inflate, inflate() + will go ahead and process the first block, and will return when it gets to + the end of that block, or when it runs out of data. The Z_BLOCK option assists in appending to or combining deflate streams. Also to assist in this, on return inflate() will set strm->data_type to the @@ -524,7 +525,9 @@ ZEXTERN int ZEXPORT deflateInit2 OF((z_streamp strm, Z_DEFAULT and Z_HUFFMAN_ONLY. Z_RLE is designed to be almost as fast as Z_HUFFMAN_ONLY, but give better compression for PNG image data. The strategy parameter only affects the compression ratio but not the correctness of the - compressed output even if it is not set appropriately. + compressed output even if it is not set appropriately. Z_FIXED prevents the + use of dynamic Huffman codes, allowing for a simpler decoder for special + applications. deflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if a parameter is invalid (such as an invalid @@ -1230,7 +1233,7 @@ ZEXTERN uLong ZEXPORT adler32 OF((uLong adler, const Bytef *buf, uInt len)); */ ZEXTERN uLong ZEXPORT adler32_combine OF((uLong adler1, uLong adler2, - uLong len2)); + z_off_t len2)); /* Combine two Adler-32 checksums into one. For two sequences of bytes, seq1 and seq2 with lengths len1 and len2, Adler-32 checksums were calculated for @@ -1254,7 +1257,7 @@ ZEXTERN uLong ZEXPORT crc32 OF((uLong crc, const Bytef *buf, uInt len)); if (crc != original_crc) error(); */ -ZEXTERN uLong ZEXPORT crc32_combine OF((uLong crc1, uLong crc2, uLong len2)); +ZEXTERN uLong ZEXPORT crc32_combine OF((uLong crc1, uLong crc2, z_off_t len2)); /* Combine two CRC-32 check values into one. For two sequences of bytes, diff --git a/zutil.c b/zutil.c index 6c08d13..868d42f 100644 --- a/zutil.c +++ b/zutil.c @@ -137,7 +137,10 @@ const char * ZEXPORT zError(err) } #if defined(_WIN32_WCE) - /* does not exist on WCE */ + /* The Microsoft C Run-Time Library for Windows CE doesn't have + * errno. We define it as a global variable to simplify porting. + * Its value is always 0 and should not be used. + */ int errno = 0; #endif diff --git a/zutil.h b/zutil.h index 579e9fc..5209d65 100644 --- a/zutil.h +++ b/zutil.h @@ -22,6 +22,14 @@ # include #endif #ifdef NO_ERRNO_H +# ifdef _WIN32_WCE + /* The Microsoft C Run-Time Library for Windows CE doesn't have + * errno. We define it as a global variable to simplify porting. + * Its value is always 0 and should not be used. We rename it to + * avoid conflict with other libraries that use the same workaround. + */ +# define errno z_errno +# endif extern int errno; #else # include @@ -193,15 +201,6 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ # define NO_vsnprintf #endif -#ifdef HAVE_STRERROR -# ifndef VMS - extern char *strerror OF((int)); -# endif -# define zstrerror(errnum) strerror(errnum) -#else -# define zstrerror(errnum) "" -#endif - #if defined(pyr) # define NO_MEMCPY #endif