diff options
Diffstat (limited to 'lib/libz')
35 files changed, 8896 insertions, 3699 deletions
diff --git a/lib/libz/CVS/Entries b/lib/libz/CVS/Entries index baf70f2..4506428 100644 --- a/lib/libz/CVS/Entries +++ b/lib/libz/CVS/Entries @@ -1,30 +1,34 @@ -/ChangeLog/1.4/Wed Jul 20 15:56:40 2005// -/Makefile/1.20/Wed Sep 14 06:26:03 2016// -/README/1.7/Wed Jul 20 15:56:40 2005// -/adler32.c/1.6/Wed Jul 20 15:56:40 2005// -/algorithm.doc/1.3/Tue Dec 16 22:33:02 2003// -/compress.3/1.19/Fri Mar 16 16:58:26 2018// -/compress.c/1.6/Wed Jul 20 15:56:41 2005// -/crc32.c/1.8/Wed Jul 20 15:56:41 2005// -/crc32.h/1.1/Tue Dec 16 22:33:02 2003// -/deflate.c/1.11/Tue Oct 27 23:59:31 2009// -/deflate.h/1.8/Mon Nov 26 09:28:33 2007// -/generate_pkgconfig.sh/1.2/Thu May 5 20:58:15 2011// -/gzio.c/1.15/Sat Apr 18 17:11:37 2020// -/infback.c/1.6/Sat Jun 1 11:39:57 2019// -/inffast.c/1.8/Sat Jun 1 11:39:57 2019// -/inffast.h/1.4/Tue Dec 16 22:33:02 2003// -/inffixed.h/1.3/Tue Dec 16 22:33:02 2003// -/inflate.c/1.10/Sat Jun 1 11:39:57 2019// -/inflate.h/1.2/Wed Jul 20 15:56:41 2005// -/inftrees.c/1.9/Tue Oct 27 23:59:31 2009// -/inftrees.h/1.5/Wed Jul 20 15:56:41 2005// -/shlib_version/1.10/Tue Aug 13 05:52:17 2013// -/trees.c/1.8/Wed Jul 20 15:56:41 2005// -/trees.h/1.2/Tue Mar 12 00:25:57 2002// -/uncompr.c/1.5/Tue Dec 16 22:33:02 2003// -/zconf.h/1.8/Sun May 12 15:56:56 2019// -/zlib.h/1.11/Sun May 12 15:56:56 2019// -/zutil.c/1.9/Fri Aug 21 23:30:59 2015// -/zutil.h/1.9/Wed Jul 20 15:56:42 2005// +/ChangeLog/1.5/Wed Jul 14 10:28:11 2021// +/Makefile/1.21/Wed Jul 14 10:28:11 2021// +/README/1.8/Wed Jul 14 10:28:11 2021// +/adler32.c/1.7/Wed Jul 14 10:28:11 2021// +/algorithm.doc/1.4/Wed Jul 14 10:28:12 2021// +/compress.3/1.21/Wed Jul 14 10:28:12 2021// +/compress.c/1.7/Wed Jul 14 10:28:12 2021// +/crc32.c/1.9/Wed Jul 14 10:28:12 2021// +/crc32.h/1.3/Wed Jul 14 10:28:12 2021// +/deflate.c/1.12/Wed Jul 14 10:28:12 2021// +/deflate.h/1.10/Wed Jul 14 10:28:12 2021// +/generate_pkgconfig.sh/1.2/Mon Oct 19 10:45:49 2020// +/gzclose.c/1.1/Sun Jul 4 14:24:49 2021// +/gzguts.h/1.2/Sun Jul 4 17:41:23 2021// +/gzlib.c/1.1/Sun Jul 4 14:24:49 2021// +/gzread.c/1.1/Sun Jul 4 14:24:49 2021// +/gzwrite.c/1.1/Sun Jul 4 14:24:49 2021// +/infback.c/1.7/Wed Jul 14 10:28:12 2021// +/inffast.c/1.9/Wed Jul 14 10:28:12 2021// +/inffast.h/1.6/Wed Jul 14 10:28:12 2021// +/inffixed.h/1.5/Wed Jul 14 10:28:12 2021// +/inflate.c/1.11/Wed Jul 14 10:28:12 2021// +/inflate.h/1.4/Wed Jul 14 10:28:12 2021// +/inftrees.c/1.10/Wed Jul 14 10:28:12 2021// +/inftrees.h/1.7/Wed Jul 14 10:28:12 2021// +/shlib_version/1.11/Wed Jul 14 10:28:12 2021// +/trees.c/1.9/Wed Jul 14 10:28:12 2021// +/trees.h/1.4/Wed Jul 14 10:28:12 2021// +/uncompr.c/1.6/Wed Jul 14 10:28:12 2021// +/zconf.h/1.10/Wed Jul 14 10:28:12 2021// +/zlib.h/1.13/Wed Jul 14 10:28:12 2021// +/zutil.c/1.10/Wed Jul 14 10:28:12 2021// +/zutil.h/1.11/Wed Jul 14 10:28:12 2021// D diff --git a/lib/libz/ChangeLog b/lib/libz/ChangeLog index c1b187d..c928c9d 100644 --- a/lib/libz/ChangeLog +++ b/lib/libz/ChangeLog @@ -1,6 +1,666 @@ ChangeLog file for zlib +Changes in 1.2.11 (15 Jan 2017) +- Fix deflate stored bug when pulling last block from window +- Permit immediate deflateParams changes before any deflate input + +Changes in 1.2.10 (2 Jan 2017) +- Avoid warnings on snprintf() return value +- Fix bug in deflate_stored() for zero-length input +- Fix bug in gzwrite.c that produced corrupt gzip files +- Remove files to be installed before copying them in Makefile.in +- Add warnings when compiling with assembler code + +Changes in 1.2.9 (31 Dec 2016) +- Fix contrib/minizip to permit unzipping with desktop API [Zouzou] +- Improve contrib/blast to return unused bytes +- Assure that gzoffset() is correct when appending +- Improve compress() and uncompress() to support large lengths +- Fix bug in test/example.c where error code not saved +- Remedy Coverity warning [Randers-Pehrson] +- Improve speed of gzprintf() in transparent mode +- Fix inflateInit2() bug when windowBits is 16 or 32 +- Change DEBUG macro to ZLIB_DEBUG +- Avoid uninitialized access by gzclose_w() +- Allow building zlib outside of the source directory +- Fix bug that accepted invalid zlib header when windowBits is zero +- Fix gzseek() problem on MinGW due to buggy _lseeki64 there +- Loop on write() calls in gzwrite.c in case of non-blocking I/O +- Add --warn (-w) option to ./configure for more compiler warnings +- Reject a window size of 256 bytes if not using the zlib wrapper +- Fix bug when level 0 used with Z_HUFFMAN or Z_RLE +- Add --debug (-d) option to ./configure to define ZLIB_DEBUG +- Fix bugs in creating a very large gzip header +- Add uncompress2() function, which returns the input size used +- Assure that deflateParams() will not switch functions mid-block +- Dramatically speed up deflation for level 0 (storing) +- Add gzfread(), duplicating the interface of fread() +- Add gzfwrite(), duplicating the interface of fwrite() +- Add deflateGetDictionary() function +- Use snprintf() for later versions of Microsoft C +- Fix *Init macros to use z_ prefix when requested +- Replace as400 with os400 for OS/400 support [Monnerat] +- Add crc32_z() and adler32_z() functions with size_t lengths +- Update Visual Studio project files [AraHaan] + +Changes in 1.2.8 (28 Apr 2013) +- Update contrib/minizip/iowin32.c for Windows RT [Vollant] +- Do not force Z_CONST for C++ +- Clean up contrib/vstudio [Ross] +- Correct spelling error in zlib.h +- Fix mixed line endings in contrib/vstudio + +Changes in 1.2.7.3 (13 Apr 2013) +- Fix version numbers and DLL names in contrib/vstudio/*/zlib.rc + +Changes in 1.2.7.2 (13 Apr 2013) +- Change check for a four-byte type back to hexadecimal +- Fix typo in win32/Makefile.msc +- Add casts in gzwrite.c for pointer differences + +Changes in 1.2.7.1 (24 Mar 2013) +- Replace use of unsafe string functions with snprintf if available +- Avoid including stddef.h on Windows for Z_SOLO compile [Niessink] +- Fix gzgetc undefine when Z_PREFIX set [Turk] +- Eliminate use of mktemp in Makefile (not always available) +- Fix bug in 'F' mode for gzopen() +- Add inflateGetDictionary() function +- Correct comment in deflate.h +- Use _snprintf for snprintf in Microsoft C +- On Darwin, only use /usr/bin/libtool if libtool is not Apple +- Delete "--version" file if created by "ar --version" [Richard G.] +- Fix configure check for veracity of compiler error return codes +- Fix CMake compilation of static lib for MSVC2010 x64 +- Remove unused variable in infback9.c +- Fix argument checks in gzlog_compress() and gzlog_write() +- Clean up the usage of z_const and respect const usage within zlib +- Clean up examples/gzlog.[ch] comparisons of different types +- Avoid shift equal to bits in type (caused endless loop) +- Fix uninitialized value bug in gzputc() introduced by const patches +- Fix memory allocation error in examples/zran.c [Nor] +- Fix bug where gzopen(), gzclose() would write an empty file +- Fix bug in gzclose() when gzwrite() runs out of memory +- Check for input buffer malloc failure in examples/gzappend.c +- Add note to contrib/blast to use binary mode in stdio +- Fix comparisons of differently signed integers in contrib/blast +- Check for invalid code length codes in contrib/puff +- Fix serious but very rare decompression bug in inftrees.c +- Update inflateBack() comments, since inflate() can be faster +- Use underscored I/O function names for WINAPI_FAMILY +- Add _tr_flush_bits to the external symbols prefixed by --zprefix +- Add contrib/vstudio/vc10 pre-build step for static only +- Quote --version-script argument in CMakeLists.txt +- Don't specify --version-script on Apple platforms in CMakeLists.txt +- Fix casting error in contrib/testzlib/testzlib.c +- Fix types in contrib/minizip to match result of get_crc_table() +- Simplify contrib/vstudio/vc10 with 'd' suffix +- Add TOP support to win32/Makefile.msc +- Suport i686 and amd64 assembler builds in CMakeLists.txt +- Fix typos in the use of _LARGEFILE64_SOURCE in zconf.h +- Add vc11 and vc12 build files to contrib/vstudio +- Add gzvprintf() as an undocumented function in zlib +- Fix configure for Sun shell +- Remove runtime check in configure for four-byte integer type +- Add casts and consts to ease user conversion to C++ +- Add man pages for minizip and miniunzip +- In Makefile uninstall, don't rm if preceding cd fails +- Do not return Z_BUF_ERROR if deflateParam() has nothing to write + +Changes in 1.2.7 (2 May 2012) +- Replace use of memmove() with a simple copy for portability +- Test for existence of strerror +- Restore gzgetc_ for backward compatibility with 1.2.6 +- Fix build with non-GNU make on Solaris +- Require gcc 4.0 or later on Mac OS X to use the hidden attribute +- Include unistd.h for Watcom C +- Use __WATCOMC__ instead of __WATCOM__ +- Do not use the visibility attribute if NO_VIZ defined +- Improve the detection of no hidden visibility attribute +- Avoid using __int64 for gcc or solo compilation +- Cast to char * in gzprintf to avoid warnings [Zinser] +- Fix make_vms.com for VAX [Zinser] +- Don't use library or built-in byte swaps +- Simplify test and use of gcc hidden attribute +- Fix bug in gzclose_w() when gzwrite() fails to allocate memory +- Add "x" (O_EXCL) and "e" (O_CLOEXEC) modes support to gzopen() +- Fix bug in test/minigzip.c for configure --solo +- Fix contrib/vstudio project link errors [Mohanathas] +- Add ability to choose the builder in make_vms.com [Schweda] +- Add DESTDIR support to mingw32 win32/Makefile.gcc +- Fix comments in win32/Makefile.gcc for proper usage +- Allow overriding the default install locations for cmake +- Generate and install the pkg-config file with cmake +- Build both a static and a shared version of zlib with cmake +- Include version symbols for cmake builds +- If using cmake with MSVC, add the source directory to the includes +- Remove unneeded EXTRA_CFLAGS from win32/Makefile.gcc [Truta] +- Move obsolete emx makefile to old [Truta] +- Allow the use of -Wundef when compiling or using zlib +- Avoid the use of the -u option with mktemp +- Improve inflate() documentation on the use of Z_FINISH +- Recognize clang as gcc +- Add gzopen_w() in Windows for wide character path names +- Rename zconf.h in CMakeLists.txt to move it out of the way +- Add source directory in CMakeLists.txt for building examples +- Look in build directory for zlib.pc in CMakeLists.txt +- Remove gzflags from zlibvc.def in vc9 and vc10 +- Fix contrib/minizip compilation in the MinGW environment +- Update ./configure for Solaris, support --64 [Mooney] +- Remove -R. from Solaris shared build (possible security issue) +- Avoid race condition for parallel make (-j) running example +- Fix type mismatch between get_crc_table() and crc_table +- Fix parsing of version with "-" in CMakeLists.txt [Snider, Ziegler] +- Fix the path to zlib.map in CMakeLists.txt +- Force the native libtool in Mac OS X to avoid GNU libtool [Beebe] +- Add instructions to win32/Makefile.gcc for shared install [Torri] + +Changes in 1.2.6.1 (12 Feb 2012) +- Avoid the use of the Objective-C reserved name "id" +- Include io.h in gzguts.h for Microsoft compilers +- Fix problem with ./configure --prefix and gzgetc macro +- Include gz_header definition when compiling zlib solo +- Put gzflags() functionality back in zutil.c +- Avoid library header include in crc32.c for Z_SOLO +- Use name in GCC_CLASSIC as C compiler for coverage testing, if set +- Minor cleanup in contrib/minizip/zip.c [Vollant] +- Update make_vms.com [Zinser] +- Remove unnecessary gzgetc_ function +- Use optimized byte swap operations for Microsoft and GNU [Snyder] +- Fix minor typo in zlib.h comments [Rzesniowiecki] + +Changes in 1.2.6 (29 Jan 2012) +- Update the Pascal interface in contrib/pascal +- Fix function numbers for gzgetc_ in zlibvc.def files +- Fix configure.ac for contrib/minizip [Schiffer] +- Fix large-entry detection in minizip on 64-bit systems [Schiffer] +- Have ./configure use the compiler return code for error indication +- Fix CMakeLists.txt for cross compilation [McClure] +- Fix contrib/minizip/zip.c for 64-bit architectures [Dalsnes] +- Fix compilation of contrib/minizip on FreeBSD [Marquez] +- Correct suggested usages in win32/Makefile.msc [Shachar, Horvath] +- Include io.h for Turbo C / Borland C on all platforms [Truta] +- Make version explicit in contrib/minizip/configure.ac [Bosmans] +- Avoid warning for no encryption in contrib/minizip/zip.c [Vollant] +- Minor cleanup up contrib/minizip/unzip.c [Vollant] +- Fix bug when compiling minizip with C++ [Vollant] +- Protect for long name and extra fields in contrib/minizip [Vollant] +- Avoid some warnings in contrib/minizip [Vollant] +- Add -I../.. -L../.. to CFLAGS for minizip and miniunzip +- Add missing libs to minizip linker command +- Add support for VPATH builds in contrib/minizip +- Add an --enable-demos option to contrib/minizip/configure +- Add the generation of configure.log by ./configure +- Exit when required parameters not provided to win32/Makefile.gcc +- Have gzputc return the character written instead of the argument +- Use the -m option on ldconfig for BSD systems [Tobias] +- Correct in zlib.map when deflateResetKeep was added + +Changes in 1.2.5.3 (15 Jan 2012) +- Restore gzgetc function for binary compatibility +- Do not use _lseeki64 under Borland C++ [Truta] +- Update win32/Makefile.msc to build test/*.c [Truta] +- Remove old/visualc6 given CMakefile and other alternatives +- Update AS400 build files and documentation [Monnerat] +- Update win32/Makefile.gcc to build test/*.c [Truta] +- Permit stronger flushes after Z_BLOCK flushes +- Avoid extraneous empty blocks when doing empty flushes +- Permit Z_NULL arguments to deflatePending +- Allow deflatePrime() to insert bits in the middle of a stream +- Remove second empty static block for Z_PARTIAL_FLUSH +- Write out all of the available bits when using Z_BLOCK +- Insert the first two strings in the hash table after a flush + +Changes in 1.2.5.2 (17 Dec 2011) +- fix ld error: unable to find version dependency 'ZLIB_1.2.5' +- use relative symlinks for shared libs +- Avoid searching past window for Z_RLE strategy +- Assure that high-water mark initialization is always applied in deflate +- Add assertions to fill_window() in deflate.c to match comments +- Update python link in README +- Correct spelling error in gzread.c +- Fix bug in gzgets() for a concatenated empty gzip stream +- Correct error in comment for gz_make() +- Change gzread() and related to ignore junk after gzip streams +- Allow gzread() and related to continue after gzclearerr() +- Allow gzrewind() and gzseek() after a premature end-of-file +- Simplify gzseek() now that raw after gzip is ignored +- Change gzgetc() to a macro for speed (~40% speedup in testing) +- Fix gzclose() to return the actual error last encountered +- Always add large file support for windows +- Include zconf.h for windows large file support +- Include zconf.h.cmakein for windows large file support +- Update zconf.h.cmakein on make distclean +- Merge vestigial vsnprintf determination from zutil.h to gzguts.h +- Clarify how gzopen() appends in zlib.h comments +- Correct documentation of gzdirect() since junk at end now ignored +- Add a transparent write mode to gzopen() when 'T' is in the mode +- Update python link in zlib man page +- Get inffixed.h and MAKEFIXED result to match +- Add a ./config --solo option to make zlib subset with no library use +- Add undocumented inflateResetKeep() function for CAB file decoding +- Add --cover option to ./configure for gcc coverage testing +- Add #define ZLIB_CONST option to use const in the z_stream interface +- Add comment to gzdopen() in zlib.h to use dup() when using fileno() +- Note behavior of uncompress() to provide as much data as it can +- Add files in contrib/minizip to aid in building libminizip +- Split off AR options in Makefile.in and configure +- Change ON macro to Z_ARG to avoid application conflicts +- Facilitate compilation with Borland C++ for pragmas and vsnprintf +- Include io.h for Turbo C / Borland C++ +- Move example.c and minigzip.c to test/ +- Simplify incomplete code table filling in inflate_table() +- Remove code from inflate.c and infback.c that is impossible to execute +- Test the inflate code with full coverage +- Allow deflateSetDictionary, inflateSetDictionary at any time (in raw) +- Add deflateResetKeep and fix inflateResetKeep to retain dictionary +- Fix gzwrite.c to accommodate reduced memory zlib compilation +- Have inflate() with Z_FINISH avoid the allocation of a window +- Do not set strm->adler when doing raw inflate +- Fix gzeof() to behave just like feof() when read is not past end of file +- Fix bug in gzread.c when end-of-file is reached +- Avoid use of Z_BUF_ERROR in gz* functions except for premature EOF +- Document gzread() capability to read concurrently written files +- Remove hard-coding of resource compiler in CMakeLists.txt [Blammo] + +Changes in 1.2.5.1 (10 Sep 2011) +- Update FAQ entry on shared builds (#13) +- Avoid symbolic argument to chmod in Makefile.in +- Fix bug and add consts in contrib/puff [Oberhumer] +- Update contrib/puff/zeros.raw test file to have all block types +- Add full coverage test for puff in contrib/puff/Makefile +- Fix static-only-build install in Makefile.in +- Fix bug in unzGetCurrentFileInfo() in contrib/minizip [Kuno] +- Add libz.a dependency to shared in Makefile.in for parallel builds +- Spell out "number" (instead of "nb") in zlib.h for total_in, total_out +- Replace $(...) with `...` in configure for non-bash sh [Bowler] +- Add darwin* to Darwin* and solaris* to SunOS\ 5* in configure [Groffen] +- Add solaris* to Linux* in configure to allow gcc use [Groffen] +- Add *bsd* to Linux* case in configure [Bar-Lev] +- Add inffast.obj to dependencies in win32/Makefile.msc +- Correct spelling error in deflate.h [Kohler] +- Change libzdll.a again to libz.dll.a (!) in win32/Makefile.gcc +- Add test to configure for GNU C looking for gcc in output of $cc -v +- Add zlib.pc generation to win32/Makefile.gcc [Weigelt] +- Fix bug in zlib.h for _FILE_OFFSET_BITS set and _LARGEFILE64_SOURCE not +- Add comment in zlib.h that adler32_combine with len2 < 0 makes no sense +- Make NO_DIVIDE option in adler32.c much faster (thanks to John Reiser) +- Make stronger test in zconf.h to include unistd.h for LFS +- Apply Darwin patches for 64-bit file offsets to contrib/minizip [Slack] +- Fix zlib.h LFS support when Z_PREFIX used +- Add updated as400 support (removed from old) [Monnerat] +- Avoid deflate sensitivity to volatile input data +- Avoid division in adler32_combine for NO_DIVIDE +- Clarify the use of Z_FINISH with deflateBound() amount of space +- Set binary for output file in puff.c +- Use u4 type for crc_table to avoid conversion warnings +- Apply casts in zlib.h to avoid conversion warnings +- Add OF to prototypes for adler32_combine_ and crc32_combine_ [Miller] +- Improve inflateSync() documentation to note indeterminancy +- Add deflatePending() function to return the amount of pending output +- Correct the spelling of "specification" in FAQ [Randers-Pehrson] +- Add a check in configure for stdarg.h, use for gzprintf() +- Check that pointers fit in ints when gzprint() compiled old style +- Add dummy name before $(SHAREDLIBV) in Makefile [Bar-Lev, Bowler] +- Delete line in configure that adds -L. libz.a to LDFLAGS [Weigelt] +- Add debug records in assmebler code [Londer] +- Update RFC references to use http://tools.ietf.org/html/... [Li] +- Add --archs option, use of libtool to configure for Mac OS X [Borstel] + +Changes in 1.2.5 (19 Apr 2010) +- Disable visibility attribute in win32/Makefile.gcc [Bar-Lev] +- Default to libdir as sharedlibdir in configure [Nieder] +- Update copyright dates on modified source files +- Update trees.c to be able to generate modified trees.h +- Exit configure for MinGW, suggesting win32/Makefile.gcc +- Check for NULL path in gz_open [Homurlu] + +Changes in 1.2.4.5 (18 Apr 2010) +- Set sharedlibdir in configure [Torok] +- Set LDFLAGS in Makefile.in [Bar-Lev] +- Avoid mkdir objs race condition in Makefile.in [Bowler] +- Add ZLIB_INTERNAL in front of internal inter-module functions and arrays +- Define ZLIB_INTERNAL to hide internal functions and arrays for GNU C +- Don't use hidden attribute when it is a warning generator (e.g. Solaris) + +Changes in 1.2.4.4 (18 Apr 2010) +- Fix CROSS_PREFIX executable testing, CHOST extract, mingw* [Torok] +- Undefine _LARGEFILE64_SOURCE in zconf.h if it is zero, but not if empty +- Try to use bash or ksh regardless of functionality of /bin/sh +- Fix configure incompatibility with NetBSD sh +- Remove attempt to run under bash or ksh since have better NetBSD fix +- Fix win32/Makefile.gcc for MinGW [Bar-Lev] +- Add diagnostic messages when using CROSS_PREFIX in configure +- Added --sharedlibdir option to configure [Weigelt] +- Use hidden visibility attribute when available [Frysinger] + +Changes in 1.2.4.3 (10 Apr 2010) +- Only use CROSS_PREFIX in configure for ar and ranlib if they exist +- Use CROSS_PREFIX for nm [Bar-Lev] +- Assume _LARGEFILE64_SOURCE defined is equivalent to true +- Avoid use of undefined symbols in #if with && and || +- Make *64 prototypes in gzguts.h consistent with functions +- Add -shared load option for MinGW in configure [Bowler] +- Move z_off64_t to public interface, use instead of off64_t +- Remove ! from shell test in configure (not portable to Solaris) +- Change +0 macro tests to -0 for possibly increased portability + +Changes in 1.2.4.2 (9 Apr 2010) +- Add consistent carriage returns to readme.txt's in masmx86 and masmx64 +- Really provide prototypes for *64 functions when building without LFS +- Only define unlink() in minigzip.c if unistd.h not included +- Update README to point to contrib/vstudio project files +- Move projects/vc6 to old/ and remove projects/ +- Include stdlib.h in minigzip.c for setmode() definition under WinCE +- Clean up assembler builds in win32/Makefile.msc [Rowe] +- Include sys/types.h for Microsoft for off_t definition +- Fix memory leak on error in gz_open() +- Symbolize nm as $NM in configure [Weigelt] +- Use TEST_LDSHARED instead of LDSHARED to link test programs [Weigelt] +- Add +0 to _FILE_OFFSET_BITS and _LFS64_LARGEFILE in case not defined +- Fix bug in gzeof() to take into account unused input data +- Avoid initialization of structures with variables in puff.c +- Updated win32/README-WIN32.txt [Rowe] + +Changes in 1.2.4.1 (28 Mar 2010) +- Remove the use of [a-z] constructs for sed in configure [gentoo 310225] +- Remove $(SHAREDLIB) from LIBS in Makefile.in [Creech] +- Restore "for debugging" comment on sprintf() in gzlib.c +- Remove fdopen for MVS from gzguts.h +- Put new README-WIN32.txt in win32 [Rowe] +- Add check for shell to configure and invoke another shell if needed +- Fix big fat stinking bug in gzseek() on uncompressed files +- Remove vestigial F_OPEN64 define in zutil.h +- Set and check the value of _LARGEFILE_SOURCE and _LARGEFILE64_SOURCE +- Avoid errors on non-LFS systems when applications define LFS macros +- Set EXE to ".exe" in configure for MINGW [Kahle] +- Match crc32() in crc32.c exactly to the prototype in zlib.h [Sherrill] +- Add prefix for cross-compilation in win32/makefile.gcc [Bar-Lev] +- Add DLL install in win32/makefile.gcc [Bar-Lev] +- Allow Linux* or linux* from uname in configure [Bar-Lev] +- Allow ldconfig to be redefined in configure and Makefile.in [Bar-Lev] +- Add cross-compilation prefixes to configure [Bar-Lev] +- Match type exactly in gz_load() invocation in gzread.c +- Match type exactly of zcalloc() in zutil.c to zlib.h alloc_func +- Provide prototypes for *64 functions when building zlib without LFS +- Don't use -lc when linking shared library on MinGW +- Remove errno.h check in configure and vestigial errno code in zutil.h + +Changes in 1.2.4 (14 Mar 2010) +- Fix VER3 extraction in configure for no fourth subversion +- Update zlib.3, add docs to Makefile.in to make .pdf out of it +- Add zlib.3.pdf to distribution +- Don't set error code in gzerror() if passed pointer is NULL +- Apply destination directory fixes to CMakeLists.txt [Lowman] +- Move #cmakedefine's to a new zconf.in.cmakein +- Restore zconf.h for builds that don't use configure or cmake +- Add distclean to dummy Makefile for convenience +- Update and improve INDEX, README, and FAQ +- Update CMakeLists.txt for the return of zconf.h [Lowman] +- Update contrib/vstudio/vc9 and vc10 [Vollant] +- Change libz.dll.a back to libzdll.a in win32/Makefile.gcc +- Apply license and readme changes to contrib/asm686 [Raiter] +- Check file name lengths and add -c option in minigzip.c [Li] +- Update contrib/amd64 and contrib/masmx86/ [Vollant] +- Avoid use of "eof" parameter in trees.c to not shadow library variable +- Update make_vms.com for removal of zlibdefs.h [Zinser] +- Update assembler code and vstudio projects in contrib [Vollant] +- Remove outdated assembler code contrib/masm686 and contrib/asm586 +- Remove old vc7 and vc8 from contrib/vstudio +- Update win32/Makefile.msc, add ZLIB_VER_SUBREVISION [Rowe] +- Fix memory leaks in gzclose_r() and gzclose_w(), file leak in gz_open() +- Add contrib/gcc_gvmat64 for longest_match and inflate_fast [Vollant] +- Remove *64 functions from win32/zlib.def (they're not 64-bit yet) +- Fix bug in void-returning vsprintf() case in gzwrite.c +- Fix name change from inflate.h in contrib/inflate86/inffas86.c +- Check if temporary file exists before removing in make_vms.com [Zinser] +- Fix make install and uninstall for --static option +- Fix usage of _MSC_VER in gzguts.h and zutil.h [Truta] +- Update readme.txt in contrib/masmx64 and masmx86 to assemble + +Changes in 1.2.3.9 (21 Feb 2010) +- Expunge gzio.c +- Move as400 build information to old +- Fix updates in contrib/minizip and contrib/vstudio +- Add const to vsnprintf test in configure to avoid warnings [Weigelt] +- Delete zconf.h (made by configure) [Weigelt] +- Change zconf.in.h to zconf.h.in per convention [Weigelt] +- Check for NULL buf in gzgets() +- Return empty string for gzgets() with len == 1 (like fgets()) +- Fix description of gzgets() in zlib.h for end-of-file, NULL return +- Update minizip to 1.1 [Vollant] +- Avoid MSVC loss of data warnings in gzread.c, gzwrite.c +- Note in zlib.h that gzerror() should be used to distinguish from EOF +- Remove use of snprintf() from gzlib.c +- Fix bug in gzseek() +- Update contrib/vstudio, adding vc9 and vc10 [Kuno, Vollant] +- Fix zconf.h generation in CMakeLists.txt [Lowman] +- Improve comments in zconf.h where modified by configure + +Changes in 1.2.3.8 (13 Feb 2010) +- Clean up text files (tabs, trailing whitespace, etc.) [Oberhumer] +- Use z_off64_t in gz_zero() and gz_skip() to match state->skip +- Avoid comparison problem when sizeof(int) == sizeof(z_off64_t) +- Revert to Makefile.in from 1.2.3.6 (live with the clutter) +- Fix missing error return in gzflush(), add zlib.h note +- Add *64 functions to zlib.map [Levin] +- Fix signed/unsigned comparison in gz_comp() +- Use SFLAGS when testing shared linking in configure +- Add --64 option to ./configure to use -m64 with gcc +- Fix ./configure --help to correctly name options +- Have make fail if a test fails [Levin] +- Avoid buffer overrun in contrib/masmx64/gvmat64.asm [Simpson] +- Remove assembler object files from contrib + +Changes in 1.2.3.7 (24 Jan 2010) +- Always gzopen() with O_LARGEFILE if available +- Fix gzdirect() to work immediately after gzopen() or gzdopen() +- Make gzdirect() more precise when the state changes while reading +- Improve zlib.h documentation in many places +- Catch memory allocation failure in gz_open() +- Complete close operation if seek forward in gzclose_w() fails +- Return Z_ERRNO from gzclose_r() if close() fails +- Return Z_STREAM_ERROR instead of EOF for gzclose() being passed NULL +- Return zero for gzwrite() errors to match zlib.h description +- Return -1 on gzputs() error to match zlib.h description +- Add zconf.in.h to allow recovery from configure modification [Weigelt] +- Fix static library permissions in Makefile.in [Weigelt] +- Avoid warnings in configure tests that hide functionality [Weigelt] +- Add *BSD and DragonFly to Linux case in configure [gentoo 123571] +- Change libzdll.a to libz.dll.a in win32/Makefile.gcc [gentoo 288212] +- Avoid access of uninitialized data for first inflateReset2 call [Gomes] +- Keep object files in subdirectories to reduce the clutter somewhat +- Remove default Makefile and zlibdefs.h, add dummy Makefile +- Add new external functions to Z_PREFIX, remove duplicates, z_z_ -> z_ +- Remove zlibdefs.h completely -- modify zconf.h instead + +Changes in 1.2.3.6 (17 Jan 2010) +- Avoid void * arithmetic in gzread.c and gzwrite.c +- Make compilers happier with const char * for gz_error message +- Avoid unused parameter warning in inflate.c +- Avoid signed-unsigned comparison warning in inflate.c +- Indent #pragma's for traditional C +- Fix usage of strwinerror() in glib.c, change to gz_strwinerror() +- Correct email address in configure for system options +- Update make_vms.com and add make_vms.com to contrib/minizip [Zinser] +- Update zlib.map [Brown] +- Fix Makefile.in for Solaris 10 make of example64 and minizip64 [Torok] +- Apply various fixes to CMakeLists.txt [Lowman] +- Add checks on len in gzread() and gzwrite() +- Add error message for no more room for gzungetc() +- Remove zlib version check in gzwrite() +- Defer compression of gzprintf() result until need to +- Use snprintf() in gzdopen() if available +- Remove USE_MMAP configuration determination (only used by minigzip) +- Remove examples/pigz.c (available separately) +- Update examples/gun.c to 1.6 + +Changes in 1.2.3.5 (8 Jan 2010) +- Add space after #if in zutil.h for some compilers +- Fix relatively harmless bug in deflate_fast() [Exarevsky] +- Fix same problem in deflate_slow() +- Add $(SHAREDLIBV) to LIBS in Makefile.in [Brown] +- Add deflate_rle() for faster Z_RLE strategy run-length encoding +- Add deflate_huff() for faster Z_HUFFMAN_ONLY encoding +- Change name of "write" variable in inffast.c to avoid library collisions +- Fix premature EOF from gzread() in gzio.c [Brown] +- Use zlib header window size if windowBits is 0 in inflateInit2() +- Remove compressBound() call in deflate.c to avoid linking compress.o +- Replace use of errno in gz* with functions, support WinCE [Alves] +- Provide alternative to perror() in minigzip.c for WinCE [Alves] +- Don't use _vsnprintf on later versions of MSVC [Lowman] +- Add CMake build script and input file [Lowman] +- Update contrib/minizip to 1.1 [Svensson, Vollant] +- Moved nintendods directory from contrib to . +- Replace gzio.c with a new set of routines with the same functionality +- Add gzbuffer(), gzoffset(), gzclose_r(), gzclose_w() as part of above +- Update contrib/minizip to 1.1b +- Change gzeof() to return 0 on error instead of -1 to agree with zlib.h + +Changes in 1.2.3.4 (21 Dec 2009) +- Use old school .SUFFIXES in Makefile.in for FreeBSD compatibility +- Update comments in configure and Makefile.in for default --shared +- Fix test -z's in configure [Marquess] +- Build examplesh and minigzipsh when not testing +- Change NULL's to Z_NULL's in deflate.c and in comments in zlib.h +- Import LDFLAGS from the environment in configure +- Fix configure to populate SFLAGS with discovered CFLAGS options +- Adapt make_vms.com to the new Makefile.in [Zinser] +- Add zlib2ansi script for C++ compilation [Marquess] +- Add _FILE_OFFSET_BITS=64 test to make test (when applicable) +- Add AMD64 assembler code for longest match to contrib [Teterin] +- Include options from $SFLAGS when doing $LDSHARED +- Simplify 64-bit file support by introducing z_off64_t type +- Make shared object files in objs directory to work around old Sun cc +- Use only three-part version number for Darwin shared compiles +- Add rc option to ar in Makefile.in for when ./configure not run +- Add -WI,-rpath,. to LDFLAGS for OSF 1 V4* +- Set LD_LIBRARYN32_PATH for SGI IRIX shared compile +- Protect against _FILE_OFFSET_BITS being defined when compiling zlib +- Rename Makefile.in targets allstatic to static and allshared to shared +- Fix static and shared Makefile.in targets to be independent +- Correct error return bug in gz_open() by setting state [Brown] +- Put spaces before ;;'s in configure for better sh compatibility +- Add pigz.c (parallel implementation of gzip) to examples/ +- Correct constant in crc32.c to UL [Leventhal] +- Reject negative lengths in crc32_combine() +- Add inflateReset2() function to work like inflateEnd()/inflateInit2() +- Include sys/types.h for _LARGEFILE64_SOURCE [Brown] +- Correct typo in doc/algorithm.txt [Janik] +- Fix bug in adler32_combine() [Zhu] +- Catch missing-end-of-block-code error in all inflates and in puff + Assures that random input to inflate eventually results in an error +- Added enough.c (calculation of ENOUGH for inftrees.h) to examples/ +- Update ENOUGH and its usage to reflect discovered bounds +- Fix gzerror() error report on empty input file [Brown] +- Add ush casts in trees.c to avoid pedantic runtime errors +- Fix typo in zlib.h uncompress() description [Reiss] +- Correct inflate() comments with regard to automatic header detection +- Remove deprecation comment on Z_PARTIAL_FLUSH (it stays) +- Put new version of gzlog (2.0) in examples with interruption recovery +- Add puff compile option to permit invalid distance-too-far streams +- Add puff TEST command options, ability to read piped input +- Prototype the *64 functions in zlib.h when _FILE_OFFSET_BITS == 64, but + _LARGEFILE64_SOURCE not defined +- Fix Z_FULL_FLUSH to truly erase the past by resetting s->strstart +- Fix deflateSetDictionary() to use all 32K for output consistency +- Remove extraneous #define MIN_LOOKAHEAD in deflate.c (in deflate.h) +- Clear bytes after deflate lookahead to avoid use of uninitialized data +- Change a limit in inftrees.c to be more transparent to Coverity Prevent +- Update win32/zlib.def with exported symbols from zlib.h +- Correct spelling errors in zlib.h [Willem, Sobrado] +- Allow Z_BLOCK for deflate() to force a new block +- Allow negative bits in inflatePrime() to delete existing bit buffer +- Add Z_TREES flush option to inflate() to return at end of trees +- Add inflateMark() to return current state information for random access +- Add Makefile for NintendoDS to contrib [Costa] +- Add -w in configure compile tests to avoid spurious warnings [Beucler] +- Fix typos in zlib.h comments for deflateSetDictionary() +- Fix EOF detection in transparent gzread() [Maier] + +Changes in 1.2.3.3 (2 October 2006) +- Make --shared the default for configure, add a --static option +- Add compile option to permit invalid distance-too-far streams +- Add inflateUndermine() function which is required to enable above +- Remove use of "this" variable name for C++ compatibility [Marquess] +- Add testing of shared library in make test, if shared library built +- Use ftello() and fseeko() if available instead of ftell() and fseek() +- Provide two versions of all functions that use the z_off_t type for + binary compatibility -- a normal version and a 64-bit offset version, + per the Large File Support Extension when _LARGEFILE64_SOURCE is + defined; use the 64-bit versions by default when _FILE_OFFSET_BITS + is defined to be 64 +- Add a --uname= option to configure to perhaps help with cross-compiling + +Changes in 1.2.3.2 (3 September 2006) +- Turn off silly Borland warnings [Hay] +- Use off64_t and define _LARGEFILE64_SOURCE when present +- Fix missing dependency on inffixed.h in Makefile.in +- Rig configure --shared to build both shared and static [Teredesai, Truta] +- Remove zconf.in.h and instead create a new zlibdefs.h file +- Fix contrib/minizip/unzip.c non-encrypted after encrypted [Vollant] +- Add treebuild.xml (see http://treebuild.metux.de/) [Weigelt] + +Changes in 1.2.3.1 (16 August 2006) +- Add watcom directory with OpenWatcom make files [Daniel] +- Remove #undef of FAR in zconf.in.h for MVS [Fedtke] +- Update make_vms.com [Zinser] +- Use -fPIC for shared build in configure [Teredesai, Nicholson] +- Use only major version number for libz.so on IRIX and OSF1 [Reinholdtsen] +- Use fdopen() (not _fdopen()) for Interix in zutil.h [Back] +- Add some FAQ entries about the contrib directory +- Update the MVS question in the FAQ +- Avoid extraneous reads after EOF in gzio.c [Brown] +- Correct spelling of "successfully" in gzio.c [Randers-Pehrson] +- Add comments to zlib.h about gzerror() usage [Brown] +- Set extra flags in gzip header in gzopen() like deflate() does +- Make configure options more compatible with double-dash conventions + [Weigelt] +- Clean up compilation under Solaris SunStudio cc [Rowe, Reinholdtsen] +- Fix uninstall target in Makefile.in [Truta] +- Add pkgconfig support [Weigelt] +- Use $(DESTDIR) macro in Makefile.in [Reinholdtsen, Weigelt] +- Replace set_data_type() with a more accurate detect_data_type() in + trees.c, according to the txtvsbin.txt document [Truta] +- Swap the order of #include <stdio.h> and #include "zlib.h" in + gzio.c, example.c and minigzip.c [Truta] +- Shut up annoying VS2005 warnings about standard C deprecation [Rowe, + Truta] (where?) +- Fix target "clean" from win32/Makefile.bor [Truta] +- Create .pdb and .manifest files in win32/makefile.msc [Ziegler, Rowe] +- Update zlib www home address in win32/DLL_FAQ.txt [Truta] +- Update contrib/masmx86/inffas32.asm for VS2005 [Vollant, Van Wassenhove] +- Enable browse info in the "Debug" and "ASM Debug" configurations in + the Visual C++ 6 project, and set (non-ASM) "Debug" as default [Truta] +- Add pkgconfig support [Weigelt] +- Add ZLIB_VER_MAJOR, ZLIB_VER_MINOR and ZLIB_VER_REVISION in zlib.h, + for use in win32/zlib1.rc [Polushin, Rowe, Truta] +- Add a document that explains the new text detection scheme to + doc/txtvsbin.txt [Truta] +- Add rfc1950.txt, rfc1951.txt and rfc1952.txt to doc/ [Truta] +- Move algorithm.txt into doc/ [Truta] +- Synchronize FAQ with website +- Fix compressBound(), was low for some pathological cases [Fearnley] +- Take into account wrapper variations in deflateBound() +- Set examples/zpipe.c input and output to binary mode for Windows +- Update examples/zlib_how.html with new zpipe.c (also web site) +- Fix some warnings in examples/gzlog.c and examples/zran.c (it seems + that gcc became pickier in 4.0) +- Add zlib.map for Linux: "All symbols from zlib-1.1.4 remain + un-versioned, the patch adds versioning only for symbols introduced in + zlib-1.2.0 or later. It also declares as local those symbols which are + not designed to be exported." [Levin] +- Update Z_PREFIX list in zconf.in.h, add --zprefix option to configure +- Do not initialize global static by default in trees.c, add a response + NO_INIT_GLOBAL_POINTERS to initialize them if needed [Marquess] +- Don't use strerror() in gzio.c under WinCE [Yakimov] +- Don't use errno.h in zutil.h under WinCE [Yakimov] +- Move arguments for AR to its usage to allow replacing ar [Marot] +- Add HAVE_VISIBILITY_PRAGMA in zconf.in.h for Mozilla [Randers-Pehrson] +- Improve inflateInit() and inflateInit2() documentation +- Fix structure size comment in inflate.h +- Change configure help option from --h* to --help [Santos] + Changes in 1.2.3 (18 July 2005) - Apply security vulnerability fixes to contrib/infback9 as well - Clean up some text files (carriage returns, trailing space) @@ -13,7 +673,7 @@ Changes in 1.2.2.4 (11 July 2005) compile - Fix some spelling errors in comments [Betts] - Correct inflateInit2() error return documentation in zlib.h -- Added zran.c example of compressed data random access to examples +- Add zran.c example of compressed data random access to examples directory, shows use of inflatePrime() - Fix cast for assignments to strm->state in inflate.c and infback.c - Fix zlibCompileFlags() in zutil.c to use 1L for long shifts [Oberhumer] @@ -561,7 +1221,7 @@ Changes in 1.0.6 (19 Jan 1998) 386 asm code replacing longest_match(). contrib/iostream/ by Kevin Ruland <kevin@rodin.wustl.edu> A C++ I/O streams interface to the zlib gz* functions - contrib/iostream2/ by Tyge Løvset <Tyge.Lovset@cmr.no> + contrib/iostream2/ by Tyge Lovset <Tyge.Lovset@cmr.no> Another C++ I/O streams interface contrib/untgz/ by "Pedro A. Aranda Guti\irrez" <paag@tid.es> A very simple tar.gz file extractor using zlib @@ -650,7 +1310,7 @@ Changes in 1.0.1 (20 May 96) [1.0 skipped to avoid confusion] - fix array overlay in deflate.c which sometimes caused bad compressed data - fix inflate bug with empty stored block - fix MSDOS medium model which was broken in 0.99 -- fix deflateParams() which could generated bad compressed data. +- fix deflateParams() which could generate bad compressed data. - Bytef is define'd instead of typedef'ed (work around Borland bug) - added an INDEX file - new makefiles for DJGPP (Makefile.dj2), 32-bit Borland (Makefile.b32), diff --git a/lib/libz/Makefile b/lib/libz/Makefile index cba7339..467668b 100644 --- a/lib/libz/Makefile +++ b/lib/libz/Makefile @@ -1,11 +1,11 @@ -# $OpenBSD: Makefile,v 1.20 2016/09/14 06:26:03 natano Exp $ +# $OpenBSD: Makefile,v 1.21 2021/07/04 14:24:49 tb Exp $ LIB= z HDRS= zconf.h zlib.h -SRCS= adler32.c compress.c crc32.c deflate.c gzio.c infback.c \ - inffast.c inflate.c inftrees.c trees.c uncompr.c zutil.c +SRCS= adler32.c compress.c crc32.c deflate.c gzclose.c gzlib.c \ + gzread.c gzwrite.c infback.c inffast.c inflate.c inftrees.c \ + trees.c uncompr.c zutil.c MAN= compress.3 -CFLAGS+=-DHAVE_STRERROR -DHAVE_MEMCPY -DHAS_vsnprintf -DHAS_snprintf PC_FILES=zlib.pc CLEANFILES+=${PC_FILES} diff --git a/lib/libz/README b/lib/libz/README index 758cc50..51106de 100644 --- a/lib/libz/README +++ b/lib/libz/README @@ -1,56 +1,52 @@ ZLIB DATA COMPRESSION LIBRARY -zlib 1.2.3 is a general purpose data compression library. All the code is +zlib 1.2.11 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) -and rfc1952.txt (gzip format). These documents are also available in other -formats from ftp://ftp.uu.net/graphics/png/documents/zlib/zdoc-index.html +http://tools.ietf.org/html/rfc1950 (zlib format), rfc1951 (deflate format) and +rfc1952 (gzip format). All functions of the compression library are documented in the file zlib.h -(volunteer to write man pages welcome, contact zlib@gzip.org). A usage example -of the library is given in the file example.c which also tests that the library -is working correctly. Another example is given in the file minigzip.c. The -compression library itself is composed of all source files except example.c and -minigzip.c. +(volunteer to write man pages welcome, contact zlib@gzip.org). A usage example +of the library is given in the file test/example.c which also tests that +the library is working correctly. Another example is given in the file +test/minigzip.c. The compression library itself is composed of all source +files in the root directory. 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. +the top of Makefile.in. In short "./configure; make test", and if that goes +well, "make install" should work for most flavors of Unix. For Windows, use +one of the special makefiles in win32/ or contrib/vstudio/ . For VMS, use +make_vms.com. Questions about zlib should be sent to <zlib@gzip.org>, or to Gilles Vollant -<info@winimage.com> for the Windows DLL version. The zlib home page is -http://www.zlib.org or http://www.gzip.org/zlib/ Before reporting a problem, -please check this site to verify that you have the latest version of zlib; -otherwise get the latest version and check whether the problem still exists or -not. +<info@winimage.com> for the Windows DLL version. The zlib home page is +http://zlib.net/ . Before reporting a problem, please check this site to +verify that you have the latest version of zlib; otherwise get the latest +version and check whether the problem still exists or not. -PLEASE read the zlib FAQ http://www.gzip.org/zlib/zlib_faq.html before asking -for help. +PLEASE read the zlib FAQ http://zlib.net/zlib_faq.html before asking for help. -Mark Nelson <markn@ieee.org> 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 +Mark Nelson <markn@ieee.org> wrote an article about zlib for the Jan. 1997 +issue of Dr. Dobb's Journal; a copy of the article is available at +http://marknelson.us/1997/01/01/zlib-engine/ . -The changes made in version 1.2.3 are documented in the file ChangeLog. +The changes made in version 1.2.11 are documented in the file ChangeLog. -Unsupported third party contributions are provided in directory "contrib". +Unsupported third party contributions are provided in directory contrib/ . -A Java implementation of zlib is available in the Java Development Kit -http://java.sun.com/j2se/1.4.2/docs/api/java/util/zip/package-summary.html -See the zlib home page http://www.zlib.org for details. +zlib is available in Java using the java.util.zip package, documented at +http://java.sun.com/developer/technicalArticles/Programming/compression/ . -A Perl interface to zlib written by Paul Marquess <pmqs@cpan.org> is in the -CPAN (Comprehensive Perl Archive Network) sites -http://www.cpan.org/modules/by-module/Compress/ +A Perl interface to zlib written by Paul Marquess <pmqs@cpan.org> is available +at CPAN (Comprehensive Perl Archive Network) sites, including +http://search.cpan.org/~pmqs/IO-Compress-Zlib/ . A Python interface to zlib written by A.M. Kuchling <amk@amk.ca> is available in Python 1.5 and later versions, see -http://www.python.org/doc/lib/module-zlib.html +http://docs.python.org/library/zlib.html . -A zlib binding for TCL written by Andreas Kupries <a.kupries@westend.com> is -availlable at http://www.oche.de/~akupries/soft/trf/trf_zip.html +zlib is built into tcl: http://wiki.tcl.tk/4610 . An experimental package to read and write files in .zip format, written on top of zlib by Gilles Vollant <info@winimage.com>, is available in the @@ -74,25 +70,21 @@ Notes for some targets: - zlib doesn't work on HP-UX 9.05 with some versions of /bin/cc. It works with other compilers. Use "make test" to check your compiler. -- gzdopen is not supported on RISCOS, BEOS and by some Mac compilers. +- gzdopen is not supported on RISCOS or BEOS. - For PalmOs, see http://palmzlib.sourceforge.net/ -- When building a shared, i.e. dynamic library on Mac OS X, the library must be - installed before testing (do "make install" before "make test"), since the - library location is specified in the library. - Acknowledgments: - The deflate format used by zlib was defined by Phil Katz. The deflate - and zlib specifications were written by L. Peter Deutsch. Thanks to all the - people who reported problems and suggested various improvements in zlib; - they are too numerous to cite here. + The deflate format used by zlib was defined by Phil Katz. The deflate and + zlib specifications were written by L. Peter Deutsch. Thanks to all the + people who reported problems and suggested various improvements in zlib; they + are too numerous to cite here. Copyright notice: - (C) 1995-2004 Jean-loup Gailly and Mark Adler + (C) 1995-2017 Jean-loup Gailly and Mark Adler This software is provided 'as-is', without any express or implied warranty. In no event will the authors be held liable for any damages @@ -113,13 +105,11 @@ Copyright notice: Jean-loup Gailly Mark Adler jloup@gzip.org madler@alumni.caltech.edu -If you use the zlib library in a product, we would appreciate *not* -receiving lengthy legal documents to sign. The sources are provided -for free but without warranty of any kind. The library has been -entirely written by Jean-loup Gailly and Mark Adler; it does not -include third-party code. +If you use the zlib library in a product, we would appreciate *not* receiving +lengthy legal documents to sign. The sources are provided for free but without +warranty of any kind. The library has been entirely written by Jean-loup +Gailly and Mark Adler; it does not include third-party code. -If you redistribute modified sources, we would appreciate that you include -in the file ChangeLog history information documenting your changes. Please -read the FAQ for more information on the distribution of modified source -versions. +If you redistribute modified sources, we would appreciate that you include in +the file ChangeLog history information documenting your changes. Please read +the FAQ for more information on the distribution of modified source versions. diff --git a/lib/libz/adler32.c b/lib/libz/adler32.c index 932094f..74a2000 100644 --- a/lib/libz/adler32.c +++ b/lib/libz/adler32.c @@ -1,13 +1,14 @@ -/* $OpenBSD: adler32.c,v 1.6 2005/07/20 15:56:40 millert Exp $ */ +/* $OpenBSD: adler32.c,v 1.7 2021/07/04 14:24:49 tb Exp $ */ /* adler32.c -- compute the Adler-32 checksum of a data stream - * Copyright (C) 1995-2004 Mark Adler + * Copyright (C) 1995-2011, 2016 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ -#define ZLIB_INTERNAL -#include "zlib.h" +#include "zutil.h" -#define BASE 65521UL /* largest prime smaller than 65536 */ +local uLong adler32_combine_ OF((uLong adler1, uLong adler2, z_off64_t len2)); + +#define BASE 65521U /* largest prime smaller than 65536 */ #define NMAX 5552 /* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */ @@ -17,46 +18,51 @@ #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 */ +/* use NO_DIVIDE if your processor does not do division in hardware -- + try it both ways to see which is faster */ #ifdef NO_DIVIDE -# define MOD(a) \ +/* note that this assumes BASE is 65521, where 65536 % 65521 == 15 + (thank you to John Reiser for pointing this out) */ +# define CHOP(a) \ + do { \ + unsigned long tmp = a >> 16; \ + a &= 0xffffUL; \ + a += (tmp << 4) - tmp; \ + } while (0) +# define MOD28(a) \ do { \ - if (a >= (BASE << 16)) a -= (BASE << 16); \ - if (a >= (BASE << 15)) a -= (BASE << 15); \ - if (a >= (BASE << 14)) a -= (BASE << 14); \ - if (a >= (BASE << 13)) a -= (BASE << 13); \ - if (a >= (BASE << 12)) a -= (BASE << 12); \ - if (a >= (BASE << 11)) a -= (BASE << 11); \ - if (a >= (BASE << 10)) a -= (BASE << 10); \ - if (a >= (BASE << 9)) a -= (BASE << 9); \ - if (a >= (BASE << 8)) a -= (BASE << 8); \ - if (a >= (BASE << 7)) a -= (BASE << 7); \ - if (a >= (BASE << 6)) a -= (BASE << 6); \ - if (a >= (BASE << 5)) a -= (BASE << 5); \ - 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); \ + CHOP(a); \ if (a >= BASE) a -= BASE; \ } while (0) -# define MOD4(a) \ +# define MOD(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); \ + CHOP(a); \ + MOD28(a); \ + } while (0) +# define MOD63(a) \ + do { /* this assumes a is not negative */ \ + z_off64_t tmp = a >> 32; \ + a &= 0xffffffffL; \ + a += (tmp << 8) - (tmp << 5) + tmp; \ + tmp = a >> 16; \ + a &= 0xffffL; \ + a += (tmp << 4) - tmp; \ + tmp = a >> 16; \ + a &= 0xffffL; \ + a += (tmp << 4) - tmp; \ if (a >= BASE) a -= BASE; \ } while (0) #else # define MOD(a) a %= BASE -# define MOD4(a) a %= BASE +# define MOD28(a) a %= BASE +# define MOD63(a) a %= BASE #endif /* ========================================================================= */ -uLong ZEXPORT adler32(adler, buf, len) +uLong ZEXPORT adler32_z(adler, buf, len) uLong adler; const Bytef *buf; - uInt len; + z_size_t len; { unsigned long sum2; unsigned n; @@ -88,7 +94,7 @@ uLong ZEXPORT adler32(adler, buf, len) } if (adler >= BASE) adler -= BASE; - MOD4(sum2); /* only added so many BASE's */ + MOD28(sum2); /* only added so many BASE's */ return adler | (sum2 << 16); } @@ -124,25 +130,56 @@ uLong ZEXPORT adler32(adler, buf, len) } /* ========================================================================= */ -uLong ZEXPORT adler32_combine(adler1, adler2, len2) +uLong ZEXPORT adler32(adler, buf, len) + uLong adler; + const Bytef *buf; + uInt len; +{ + return adler32_z(adler, buf, len); +} + +/* ========================================================================= */ +local uLong adler32_combine_(adler1, adler2, len2) uLong adler1; uLong adler2; - z_off_t len2; + z_off64_t len2; { unsigned long sum1; unsigned long sum2; unsigned rem; + /* for negative len, return invalid adler32 as a clue for debugging */ + if (len2 < 0) + return 0xffffffffUL; + /* the derivation of this formula is left as an exercise for the reader */ - rem = (unsigned)(len2 % BASE); + MOD63(len2); /* assumes len2 >= 0 */ + rem = (unsigned)len2; 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; + if (sum1 >= BASE) sum1 -= BASE; + if (sum1 >= BASE) sum1 -= BASE; + if (sum2 >= ((unsigned long)BASE << 1)) sum2 -= ((unsigned long)BASE << 1); + if (sum2 >= BASE) sum2 -= BASE; return sum1 | (sum2 << 16); } + +/* ========================================================================= */ +uLong ZEXPORT adler32_combine(adler1, adler2, len2) + uLong adler1; + uLong adler2; + z_off_t len2; +{ + return adler32_combine_(adler1, adler2, len2); +} + +uLong ZEXPORT adler32_combine64(adler1, adler2, len2) + uLong adler1; + uLong adler2; + z_off64_t len2; +{ + return adler32_combine_(adler1, adler2, len2); +} diff --git a/lib/libz/algorithm.doc b/lib/libz/algorithm.doc index b022dde..79839e6 100644 --- a/lib/libz/algorithm.doc +++ b/lib/libz/algorithm.doc @@ -207,3 +207,421 @@ pp. 337-343. ``DEFLATE Compressed Data Format Specification'' available in http://www.ietf.org/rfc/rfc1951.txt +1. Compression algorithm (deflate) + +The deflation algorithm used by gzip (also zip and zlib) is a variation of +LZ77 (Lempel-Ziv 1977, see reference below). It finds duplicated strings in +the input data. The second occurrence of a string is replaced by a +pointer to the previous string, in the form of a pair (distance, +length). Distances are limited to 32K bytes, and lengths are limited +to 258 bytes. When a string does not occur anywhere in the previous +32K bytes, it is emitted as a sequence of literal bytes. (In this +description, `string' must be taken as an arbitrary sequence of bytes, +and is not restricted to printable characters.) + +Literals or match lengths are compressed with one Huffman tree, and +match distances are compressed with another tree. The trees are stored +in a compact form at the start of each block. The blocks can have any +size (except that the compressed data for one block must fit in +available memory). A block is terminated when deflate() determines that +it would be useful to start another block with fresh trees. (This is +somewhat similar to the behavior of LZW-based _compress_.) + +Duplicated strings are found using a hash table. All input strings of +length 3 are inserted in the hash table. A hash index is computed for +the next 3 bytes. If the hash chain for this index is not empty, all +strings in the chain are compared with the current input string, and +the longest match is selected. + +The hash chains are searched starting with the most recent strings, to +favor small distances and thus take advantage of the Huffman encoding. +The hash chains are singly linked. There are no deletions from the +hash chains, the algorithm simply discards matches that are too old. + +To avoid a worst-case situation, very long hash chains are arbitrarily +truncated at a certain length, determined by a runtime option (level +parameter of deflateInit). So deflate() does not always find the longest +possible match but generally finds a match which is long enough. + +deflate() also defers the selection of matches with a lazy evaluation +mechanism. After a match of length N has been found, deflate() searches for +a longer match at the next input byte. If a longer match is found, the +previous match is truncated to a length of one (thus producing a single +literal byte) and the process of lazy evaluation begins again. Otherwise, +the original match is kept, and the next match search is attempted only N +steps later. + +The lazy match evaluation is also subject to a runtime parameter. If +the current match is long enough, deflate() reduces the search for a longer +match, thus speeding up the whole process. If compression ratio is more +important than speed, deflate() attempts a complete second search even if +the first match is already long enough. + +The lazy match evaluation is not performed for the fastest compression +modes (level parameter 1 to 3). For these fast modes, new strings +are inserted in the hash table only when no match was found, or +when the match is not too long. This degrades the compression ratio +but saves time since there are both fewer insertions and fewer searches. + + +2. Decompression algorithm (inflate) + +2.1 Introduction + +The key question is how to represent a Huffman code (or any prefix code) so +that you can decode fast. The most important characteristic is that shorter +codes are much more common than longer codes, so pay attention to decoding the +short codes fast, and let the long codes take longer to decode. + +inflate() sets up a first level table that covers some number of bits of +input less than the length of longest code. It gets that many bits from the +stream, and looks it up in the table. The table will tell if the next +code is that many bits or less and how many, and if it is, it will tell +the value, else it will point to the next level table for which inflate() +grabs more bits and tries to decode a longer code. + +How many bits to make the first lookup is a tradeoff between the time it +takes to decode and the time it takes to build the table. If building the +table took no time (and if you had infinite memory), then there would only +be a first level table to cover all the way to the longest code. However, +building the table ends up taking a lot longer for more bits since short +codes are replicated many times in such a table. What inflate() does is +simply to make the number of bits in the first table a variable, and then +to set that variable for the maximum speed. + +For inflate, which has 286 possible codes for the literal/length tree, the size +of the first table is nine bits. Also the distance trees have 30 possible +values, and the size of the first table is six bits. Note that for each of +those cases, the table ended up one bit longer than the ``average'' code +length, i.e. the code length of an approximately flat code which would be a +little more than eight bits for 286 symbols and a little less than five bits +for 30 symbols. + + +2.2 More details on the inflate table lookup + +Ok, you want to know what this cleverly obfuscated inflate tree actually +looks like. You are correct that it's not a Huffman tree. It is simply a +lookup table for the first, let's say, nine bits of a Huffman symbol. The +symbol could be as short as one bit or as long as 15 bits. If a particular +symbol is shorter than nine bits, then that symbol's translation is duplicated +in all those entries that start with that symbol's bits. For example, if the +symbol is four bits, then it's duplicated 32 times in a nine-bit table. If a +symbol is nine bits long, it appears in the table once. + +If the symbol is longer than nine bits, then that entry in the table points +to another similar table for the remaining bits. Again, there are duplicated +entries as needed. The idea is that most of the time the symbol will be short +and there will only be one table look up. (That's whole idea behind data +compression in the first place.) For the less frequent long symbols, there +will be two lookups. If you had a compression method with really long +symbols, you could have as many levels of lookups as is efficient. For +inflate, two is enough. + +So a table entry either points to another table (in which case nine bits in +the above example are gobbled), or it contains the translation for the symbol +and the number of bits to gobble. Then you start again with the next +ungobbled bit. + +You may wonder: why not just have one lookup table for how ever many bits the +longest symbol is? The reason is that if you do that, you end up spending +more time filling in duplicate symbol entries than you do actually decoding. +At least for deflate's output that generates new trees every several 10's of +kbytes. You can imagine that filling in a 2^15 entry table for a 15-bit code +would take too long if you're only decoding several thousand symbols. At the +other extreme, you could make a new table for every bit in the code. In fact, +that's essentially a Huffman tree. But then you spend two much time +traversing the tree while decoding, even for short symbols. + +So the number of bits for the first lookup table is a trade of the time to +fill out the table vs. the time spent looking at the second level and above of +the table. + +Here is an example, scaled down: + +The code being decoded, with 10 symbols, from 1 to 6 bits long: + +A: 0 +B: 10 +C: 1100 +D: 11010 +E: 11011 +F: 11100 +G: 11101 +H: 11110 +I: 111110 +J: 111111 + +Let's make the first table three bits long (eight entries): + +000: A,1 +001: A,1 +010: A,1 +011: A,1 +100: B,2 +101: B,2 +110: -> table X (gobble 3 bits) +111: -> table Y (gobble 3 bits) + +Each entry is what the bits decode as and how many bits that is, i.e. how +many bits to gobble. Or the entry points to another table, with the number of +bits to gobble implicit in the size of the table. + +Table X is two bits long since the longest code starting with 110 is five bits +long: + +00: C,1 +01: C,1 +10: D,2 +11: E,2 + +Table Y is three bits long since the longest code starting with 111 is six +bits long: + +000: F,2 +001: F,2 +010: G,2 +011: G,2 +100: H,2 +101: H,2 +110: I,3 +111: J,3 + +So what we have here are three tables with a total of 20 entries that had to +be constructed. That's compared to 64 entries for a single table. Or +compared to 16 entries for a Huffman tree (six two entry tables and one four +entry table). Assuming that the code ideally represents the probability of +the symbols, it takes on the average 1.25 lookups per symbol. That's compared +to one lookup for the single table, or 1.66 lookups per symbol for the +Huffman tree. + +There, I think that gives you a picture of what's going on. For inflate, the +meaning of a particular symbol is often more than just a letter. It can be a +byte (a "literal"), or it can be either a length or a distance which +indicates a base value and a number of bits to fetch after the code that is +added to the base value. Or it might be the special end-of-block code. The +data structures created in inftrees.c try to encode all that information +compactly in the tables. + + +Jean-loup Gailly Mark Adler +jloup@gzip.org madler@alumni.caltech.edu + + +References: + +[LZ77] Ziv J., Lempel A., ``A Universal Algorithm for Sequential Data +Compression,'' IEEE Transactions on Information Theory, Vol. 23, No. 3, +pp. 337-343. + +``DEFLATE Compressed Data Format Specification'' available in +http://www.ietf.org/rfc/rfc1951.txt +1. Compression algorithm (deflate) + +The deflation algorithm used by gzip (also zip and zlib) is a variation of +LZ77 (Lempel-Ziv 1977, see reference below). It finds duplicated strings in +the input data. The second occurrence of a string is replaced by a +pointer to the previous string, in the form of a pair (distance, +length). Distances are limited to 32K bytes, and lengths are limited +to 258 bytes. When a string does not occur anywhere in the previous +32K bytes, it is emitted as a sequence of literal bytes. (In this +description, `string' must be taken as an arbitrary sequence of bytes, +and is not restricted to printable characters.) + +Literals or match lengths are compressed with one Huffman tree, and +match distances are compressed with another tree. The trees are stored +in a compact form at the start of each block. The blocks can have any +size (except that the compressed data for one block must fit in +available memory). A block is terminated when deflate() determines that +it would be useful to start another block with fresh trees. (This is +somewhat similar to the behavior of LZW-based _compress_.) + +Duplicated strings are found using a hash table. All input strings of +length 3 are inserted in the hash table. A hash index is computed for +the next 3 bytes. If the hash chain for this index is not empty, all +strings in the chain are compared with the current input string, and +the longest match is selected. + +The hash chains are searched starting with the most recent strings, to +favor small distances and thus take advantage of the Huffman encoding. +The hash chains are singly linked. There are no deletions from the +hash chains, the algorithm simply discards matches that are too old. + +To avoid a worst-case situation, very long hash chains are arbitrarily +truncated at a certain length, determined by a runtime option (level +parameter of deflateInit). So deflate() does not always find the longest +possible match but generally finds a match which is long enough. + +deflate() also defers the selection of matches with a lazy evaluation +mechanism. After a match of length N has been found, deflate() searches for +a longer match at the next input byte. If a longer match is found, the +previous match is truncated to a length of one (thus producing a single +literal byte) and the process of lazy evaluation begins again. Otherwise, +the original match is kept, and the next match search is attempted only N +steps later. + +The lazy match evaluation is also subject to a runtime parameter. If +the current match is long enough, deflate() reduces the search for a longer +match, thus speeding up the whole process. If compression ratio is more +important than speed, deflate() attempts a complete second search even if +the first match is already long enough. + +The lazy match evaluation is not performed for the fastest compression +modes (level parameter 1 to 3). For these fast modes, new strings +are inserted in the hash table only when no match was found, or +when the match is not too long. This degrades the compression ratio +but saves time since there are both fewer insertions and fewer searches. + + +2. Decompression algorithm (inflate) + +2.1 Introduction + +The key question is how to represent a Huffman code (or any prefix code) so +that you can decode fast. The most important characteristic is that shorter +codes are much more common than longer codes, so pay attention to decoding the +short codes fast, and let the long codes take longer to decode. + +inflate() sets up a first level table that covers some number of bits of +input less than the length of longest code. It gets that many bits from the +stream, and looks it up in the table. The table will tell if the next +code is that many bits or less and how many, and if it is, it will tell +the value, else it will point to the next level table for which inflate() +grabs more bits and tries to decode a longer code. + +How many bits to make the first lookup is a tradeoff between the time it +takes to decode and the time it takes to build the table. If building the +table took no time (and if you had infinite memory), then there would only +be a first level table to cover all the way to the longest code. However, +building the table ends up taking a lot longer for more bits since short +codes are replicated many times in such a table. What inflate() does is +simply to make the number of bits in the first table a variable, and then +to set that variable for the maximum speed. + +For inflate, which has 286 possible codes for the literal/length tree, the size +of the first table is nine bits. Also the distance trees have 30 possible +values, and the size of the first table is six bits. Note that for each of +those cases, the table ended up one bit longer than the ``average'' code +length, i.e. the code length of an approximately flat code which would be a +little more than eight bits for 286 symbols and a little less than five bits +for 30 symbols. + + +2.2 More details on the inflate table lookup + +Ok, you want to know what this cleverly obfuscated inflate tree actually +looks like. You are correct that it's not a Huffman tree. It is simply a +lookup table for the first, let's say, nine bits of a Huffman symbol. The +symbol could be as short as one bit or as long as 15 bits. If a particular +symbol is shorter than nine bits, then that symbol's translation is duplicated +in all those entries that start with that symbol's bits. For example, if the +symbol is four bits, then it's duplicated 32 times in a nine-bit table. If a +symbol is nine bits long, it appears in the table once. + +If the symbol is longer than nine bits, then that entry in the table points +to another similar table for the remaining bits. Again, there are duplicated +entries as needed. The idea is that most of the time the symbol will be short +and there will only be one table look up. (That's whole idea behind data +compression in the first place.) For the less frequent long symbols, there +will be two lookups. If you had a compression method with really long +symbols, you could have as many levels of lookups as is efficient. For +inflate, two is enough. + +So a table entry either points to another table (in which case nine bits in +the above example are gobbled), or it contains the translation for the symbol +and the number of bits to gobble. Then you start again with the next +ungobbled bit. + +You may wonder: why not just have one lookup table for how ever many bits the +longest symbol is? The reason is that if you do that, you end up spending +more time filling in duplicate symbol entries than you do actually decoding. +At least for deflate's output that generates new trees every several 10's of +kbytes. You can imagine that filling in a 2^15 entry table for a 15-bit code +would take too long if you're only decoding several thousand symbols. At the +other extreme, you could make a new table for every bit in the code. In fact, +that's essentially a Huffman tree. But then you spend two much time +traversing the tree while decoding, even for short symbols. + +So the number of bits for the first lookup table is a trade of the time to +fill out the table vs. the time spent looking at the second level and above of +the table. + +Here is an example, scaled down: + +The code being decoded, with 10 symbols, from 1 to 6 bits long: + +A: 0 +B: 10 +C: 1100 +D: 11010 +E: 11011 +F: 11100 +G: 11101 +H: 11110 +I: 111110 +J: 111111 + +Let's make the first table three bits long (eight entries): + +000: A,1 +001: A,1 +010: A,1 +011: A,1 +100: B,2 +101: B,2 +110: -> table X (gobble 3 bits) +111: -> table Y (gobble 3 bits) + +Each entry is what the bits decode as and how many bits that is, i.e. how +many bits to gobble. Or the entry points to another table, with the number of +bits to gobble implicit in the size of the table. + +Table X is two bits long since the longest code starting with 110 is five bits +long: + +00: C,1 +01: C,1 +10: D,2 +11: E,2 + +Table Y is three bits long since the longest code starting with 111 is six +bits long: + +000: F,2 +001: F,2 +010: G,2 +011: G,2 +100: H,2 +101: H,2 +110: I,3 +111: J,3 + +So what we have here are three tables with a total of 20 entries that had to +be constructed. That's compared to 64 entries for a single table. Or +compared to 16 entries for a Huffman tree (six two entry tables and one four +entry table). Assuming that the code ideally represents the probability of +the symbols, it takes on the average 1.25 lookups per symbol. That's compared +to one lookup for the single table, or 1.66 lookups per symbol for the +Huffman tree. + +There, I think that gives you a picture of what's going on. For inflate, the +meaning of a particular symbol is often more than just a letter. It can be a +byte (a "literal"), or it can be either a length or a distance which +indicates a base value and a number of bits to fetch after the code that is +added to the base value. Or it might be the special end-of-block code. The +data structures created in inftrees.c try to encode all that information +compactly in the tables. + + +Jean-loup Gailly Mark Adler +jloup@gzip.org madler@alumni.caltech.edu + + +References: + +[LZ77] Ziv J., Lempel A., ``A Universal Algorithm for Sequential Data +Compression,'' IEEE Transactions on Information Theory, Vol. 23, No. 3, +pp. 337-343. + +``DEFLATE Compressed Data Format Specification'' available in +http://www.ietf.org/rfc/rfc1951.txt diff --git a/lib/libz/compress.3 b/lib/libz/compress.3 index cfac921..2ec0698 100644 --- a/lib/libz/compress.3 +++ b/lib/libz/compress.3 @@ -1,6 +1,6 @@ -.\" $OpenBSD: compress.3,v 1.19 2018/03/16 16:58:26 schwarze Exp $ +.\" $OpenBSD: compress.3,v 1.21 2021/07/06 06:26:05 jmc Exp $ .\" -.\" Copyright (C) 1995-2005 Jean-loup Gailly and Mark Adler +.\" Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler .\" .\" This software is provided 'as-is', without any express or implied .\" warranty. In no event will the authors be held liable for any damages @@ -23,7 +23,7 @@ .\" .\" This page corresponds to zlib version 1.2.3 .\" -.Dd $Mdocdate: March 16 2018 $ +.Dd $Mdocdate: July 6 2021 $ .Dt COMPRESS 3 .Os .Sh NAME @@ -37,19 +37,24 @@ .Nm inflateEnd , .Nm deflateInit2 , .Nm deflateSetDictionary , +.Nm deflateGetDictionary , .Nm deflateCopy , .Nm deflateReset , .Nm deflateParams , .Nm deflateTune , .Nm deflateBound , +.Nm deflatePending , .Nm deflatePrime , .Nm deflateSetHeader , .Nm inflateInit2 , .Nm inflateSetDictionary , +.Nm inflateGetDictionary , .Nm inflateSync , .Nm inflateCopy , .Nm inflateReset , +.Nm inflateReset2 , .Nm inflatePrime , +.Nm inflateMark , .Nm inflateGetHeader , .Nm inflateBackInit , .Nm inflateBack , @@ -58,11 +63,15 @@ .Nm compress2 , .Nm compressBound , .Nm uncompress , +.Nm uncompress2 , .Nm gzopen , .Nm gzdopen , +.Nm gzbuffer , .Nm gzsetparams , .Nm gzread , +.Nm gzfread , .Nm gzwrite , +.Nm gzfwrite , .Nm gzprintf , .Nm gzputs , .Nm gzgets , @@ -73,14 +82,19 @@ .Nm gzseek , .Nm gzrewind , .Nm gztell , +.Nm gzoffset , .Nm gzeof , .Nm gzdirect , .Nm gzclose , +.Nm gzclose_r , +.Nm gzclose_w , .Nm gzerror , .Nm gzclearerr , .Nm adler32 , +.Nm adler32_z , .Nm adler32_combine , .Nm crc32 , +.Nm crc32_z , .Nm crc32_combine .Nd zlib general purpose compression library .Sh SYNOPSIS @@ -110,6 +124,8 @@ Advanced functions .Ft int .Fn deflateSetDictionary "z_streamp strm" "const Bytef *dictionary" "uInt dictLength" .Ft int +.Fn deflateGetDictionary "z_streamp strm" "Bytef *dictionary" "uInt *dictLength" +.Ft int .Fn deflateCopy "z_streamp dest" "z_streamp source" .Ft int .Fn deflateReset "z_streamp strm" @@ -120,6 +136,8 @@ Advanced functions .Ft uLong .Fn deflateBound "z_streamp strm" "uLong sourceLen" .Ft int +.Fn deflatePending "z_streamp strm" "unsigned *pending" "int *bits" +.Ft int .Fn deflatePrime "z_streamp strm" "int bits" "int value" .Ft int .Fn deflateSetHeader "z_streamp strm" "gz_headerp head" @@ -128,14 +146,20 @@ Advanced functions .Ft int .Fn inflateSetDictionary "z_streamp strm" "const Bytef *dictionary" "uInt dictLength" .Ft int +.Fn inflateGetDictionary "z_streamp strm" "Bytef *dictionary" "uInt *dictLength" +.Ft int .Fn inflateSync "z_streamp strm" .Ft int .Fn inflateCopy "z_streamp dst" "z_streamp source" .Ft int .Fn inflateReset "z_streamp strm" .Ft int +.Fn inflateReset2 "z_streamp strm" "int windowBits" +.Ft int .Fn inflatePrime "z_streamp strm" "int bits" "int value" .Ft int +.Fn inflateMark "z_streamp strm" +.Ft int .Fn inflateGetHeader "z_streamp strm" "gz_headerp head" .Ft int .Fn inflateBackInit "z_stream *strm" "int windowBits" "unsigned char FAR *window" @@ -158,17 +182,25 @@ Utility functions .Fn compressBound "uLong sourceLen" .Ft int .Fn uncompress "Bytef *dest" "uLongf *destLen" "const Bytef *source" "uLong sourceLen" +.Ft int +.Fn uncompress2 "Bytef *dest" "uLongf *destLen" "const Bytef *source" "uLong *sourceLen" .Ft gzFile .Fn gzopen "const char *path" "const char *mode" .Ft gzFile .Fn gzdopen "int fd" "const char *mode" .Ft int +.Fn gzbuffer "gzFile file" "unsigned size" +.Ft int .Fn gzsetparams "gzFile file" "int level" "int strategy" .Ft int .Fn gzread "gzFile file" "voidp buf" "unsigned len" .Ft int +.Fn gzfread "voidp buf" "z_size_t size" "z_size_t nitems" "gzFile file" +.Ft int .Fn gzwrite "gzFile file" "voidpc buf" "unsigned len" .Ft int +.Fn gzfwrite "voidpc buf" "z_size_t size" "z_size_t nitems" "gzFile file" +.Ft int .Fn gzprintf "gzFile file" "const char *format" "..." .Ft int .Fn gzputs "gzFile file" "const char *s" @@ -189,11 +221,17 @@ Utility functions .Ft z_off_t .Fn gztell "gzFile file" .Ft int +.Fn gzoffset "gzFile file" +.Ft int .Fn gzeof "gzFile file" .Ft int .Fn gzdirect "gzFile file" .Ft int .Fn gzclose "gzFile file" +.Ft int +.Fn gzclose_r "gzFile file" +.Ft int +.Fn gzclose_w "gzFile file" .Ft const char * .Fn gzerror "gzFile file" "int *errnum" .Ft void @@ -204,15 +242,19 @@ Checksum functions .Ft uLong .Fn adler32 "uLong adler" "const Bytef *buf" "uInt len" .Ft uLong +.Fn adler32_z "uLong adler" "const Bytef *buf" "z_size_t len" +.Ft uLong .Fn adler32_combine "uLong adler1" "uLong adler2" "z_off_t len2" .Ft uLong .Fn crc32 "uLong crc" "const Bytef *buf" "uInt len" .Ft uLong +.Fn crc32_z "uLong adler" "const Bytef *buf" "z_size_t len" +.Ft uLong .Fn crc32_combine "uLong crc1" "uLong crc2" "z_off_t len2" .Sh DESCRIPTION This manual page describes the .Nm zlib -general purpose compression library, version 1.2.3. +general purpose compression library, version 1.2.11. .Pp The .Nm zlib @@ -224,7 +266,6 @@ but other algorithms will be added later and will have the same stream interface. .Pp Compression can be done in a single step if the buffers are large enough -.Pq for example if an input file is mmap'ed , or can be done by repeated calls of the compression function. In the latter case, the application must provide more input and/or consume the output @@ -245,7 +286,8 @@ using the functions that start with .Qq gz . The gzip format is different from the zlib format. gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate stream. -This library can optionally read and write gzip streams in memory as well. +This library can optionally read and write gzip and raw deflate streams +in memory as well. .Pp The zlib format was designed to be compact and fast for use in memory and on communications channels. @@ -255,7 +297,7 @@ and uses a different, slower, check method than zlib. .Pp The library does not install any signal handler. The decoder checks the consistency of the compressed data, -so the library should never crash even in case of corrupted input. +so the library should never crash even in the case of corrupted input. .Pp The functions within the library are divided into the following sections: .Pp @@ -308,7 +350,7 @@ If and .Fa zfree are set to -.Dv Z_NULL , +.Dv NULL , .Fn deflateInit updates them to use default allocation functions. .Pp @@ -373,7 +415,7 @@ and are updated and processing will resume at this point for the next call to .Fn deflate . .Pp -Provide more output starting at +Generate more output starting at .Fa next_out and update .Fa next_out @@ -386,8 +428,7 @@ is non-zero. Forcing .Fa flush frequently degrades the compression ratio, -so this parameter should be set only when necessary -.Pq in interactive applications . +so this parameter should be set only when necessary. Some output may be provided even if .Fa flush is not set. @@ -416,6 +457,10 @@ and with zero .Fa avail_out , it must be called again after making room in the output buffer because there might be more output pending. +See +.Fn deflatePending , +which can be used if desired to determine whether or not there is more output +in that case. .Pp Normally the parameter .Fa flush @@ -431,14 +476,45 @@ If the parameter is set to .Dv Z_SYNC_FLUSH , all pending output is flushed to the output buffer and the output -is aligned on a byte boundary, so that the decompressor can get all -input data available so far. -(In particular, +is aligned on a byte boundary, +so that the decompressor can get all input data available so far. +(In particular .Fa avail_in -is zero after the call if enough output space -has been provided before the call.) +is zero after the call +if enough output space has been provided before the call.) Flushing may degrade compression for some compression algorithms and so it should be used only when necessary. +This completes the current deflate block and follows it with +an empty stored block that is three bits plus filler bits to the next byte, +followed by four bytes (00 00 ff ff). +.Pp +If +.Fa flush +is set to +.Dv Z_PARTIAL_FLUSH , +all pending output is flushed to the output buffer, +but the output is not aligned to a byte boundary. +All of the input data so far will be available to the decompressor, as for +.Dv Z_SYNC_FLUSH . +This completes the current deflate block and follows it with an empty fixed +code block that is 10 bits long. +This assures that enough bytes are output in order for the decompressor to +finish the block before the empty fixed codes block. +.Pp +If +.Fa flush +is set to +.Dv Z_BLOCK , +a deflate block is completed and emitted, as for +.Dv Z_SYNC_FLUSH , +but the output is not aligned on a byte boundary, +and up to seven bits of the current block are held to be written as +the next byte after the next deflate block is completed. +In this case, the decompressor may not be provided enough bits at this point in +order to complete decompression of the data provided so far to the compressor. +It may need to wait for the next block to be emitted. +This is for advanced applications that need to control +the emission of deflate blocks. .Pp If .Fa flush @@ -480,10 +556,13 @@ pending input is processed, pending output is flushed and .Fn deflate returns with .Dv Z_STREAM_END -if there was enough output space; if +if there was enough output space. +If .Fn deflate returns with -.Dv Z_OK , +.Dv Z_OK +or +.Dv Z_BUF_ERROR , this function must be called again with .Dv Z_FINISH and more output space @@ -502,25 +581,34 @@ or .Fn deflateEnd . .Pp .Dv Z_FINISH -can be used immediately after +can be used in the first deflate call after .Fn deflateInit if all the compression is to be done in a single step. -In this case, +In order to complete in one call, .Fa avail_out must be at least the value returned by .Fn deflateBound -.Pq see below . -If +(see below). +Then .Fn deflate -does not return +is guaranteed to return +.Dv Z_STREAM_END . +If not enough output space is provided, +.Fn deflate +will not return .Dv Z_STREAM_END , -then it must be called again as described above. +and it must be called again as described above. .Pp .Fn deflate sets strm->adler to the Adler-32 checksum of all input read so far (that is, .Fa total_in bytes). +If a gzip stream is being generated, +then strm->adler will be the CRC-32 checksum of the input read so far. +(See +.Fn deflateInit2 +below.) .Pp .Fn deflate may update strm->data_type @@ -548,7 +636,8 @@ if the stream state was inconsistent or .Fa next_out was -.Dv NULL ) , +.Dv NULL +or the state was inadvertently written over by the application), or .Dv Z_BUF_ERROR if no progress is possible (for example, @@ -561,7 +650,7 @@ Note that is not fatal, and .Fn deflate can be called again with more input and more output space -to continue processing. +to continue compressing. .It Xo .Fa int .Fn deflateEnd "z_streamp strm" ; @@ -599,26 +688,18 @@ The fields and .Fa opaque must be initialized before by the caller. -If -.Fa next_in -is not -.Dv Z_NULL -and -.Fa avail_in -is large enough -.Pq the exact value depends on the compression method , -.Fn inflateInit -determines the compression method from the -.Nm zlib -header and allocates all data structures accordingly; -otherwise the allocation will be deferred to the first call to -.Fn inflate . +In the current version of +.Fn inflate , +the provided input is not read or consumed. +The allocation of a sliding window will be deferred to the first call of +.Fn inflate +(if the decompression does not complete on the first call). If .Fa zalloc and .Fa zfree are set to -.Dv Z_NULL , +.Dv NULL , .Fn inflateInit updates them to use default allocation functions. .Pp @@ -631,24 +712,26 @@ if there was not enough memory, .Dv Z_VERSION_ERROR if the .Nm zlib -library version is incompatible with the version assumed by the caller. +library version is incompatible with the version assumed by the caller or +.Dv Z_STREAM_ERROR +if the parameters are invalid, such as a null pointer to the structure. .Fa msg is set to null if there is no error message. .Fn inflateInit -does not perform any decompression apart from reading the -.Nm zlib -header if present: this will be done by +does not perform any decompression. +Actual decompression will be done by .Fn inflate . -(So -.Fa next_in -and -.Fa avail_in -may be modified, -but -.Fa next_out +So +.Fa next_in , avail_in , next_out , and .Fa avail_out -are unchanged.) +are unused and unchanged. +The current implementation of +.Fn inflateInit +does not process any header information \(em +that is deferred until +.Fn inflate +is called. .It Xo .Fa int .Fn inflate "z_streamp strm" "int flush" ; @@ -672,12 +755,15 @@ and .Fa avail_in accordingly. If not all input can be processed -(because there is not enough room in the output buffer), +(because there is not enough room in the output buffer), then .Fa next_in -is updated and processing will resume at this point for the next call to +and +.Fa avail_in +are updated accordingly, +and processing will resume at this point for the next call to .Fn inflate . .Pp -Provide more output starting at +Generate more output starting at .Fa next_out and update .Fa next_out @@ -694,6 +780,10 @@ Before the call to the application should ensure that at least one of the actions is possible, by providing more input and/or consuming more output, and updating the next_* and avail_* values accordingly. +If the caller of +.Fn inflate +does not provide both available input and available output space, +it is possible that there will be no progress made. The application can consume the uncompressed output when it wants, for example when the output buffer is full (avail_out == 0), or after each call to @@ -712,9 +802,9 @@ The parameter of .Fn inflate can be -.Dv Z_NO_FLUSH , Z_SYNC_FLUSH , Z_FINISH , +.Dv Z_NO_FLUSH , Z_SYNC_FLUSH , Z_FINISH , Z_BLOCK or -.Dv Z_BLOCK . +.Dv Z_TREES . .Dv Z_SYNC_FLUSH requests that .Fn inflate @@ -735,20 +825,37 @@ or when it runs out of data. The .Dv Z_BLOCK option assists in appending to or combining deflate streams. -Also to assist in this, on return +To assist in this, on return .Fn inflate -will set strm->data_type to the number of unused bits in the last byte -taken from strm->next_in, plus 64 if +always sets strm->data_type to the number of unused bits +in the last byte taken from strm->next_in, plus 64 if .Fn inflate is currently decoding the last block in the deflate stream, plus 128 if .Fn inflate -returned immediately after decoding an end-of-block code or decoding -the complete header up to just before the first byte of the deflate stream. -The end-of-block will not be indicated until all of the uncompressed data -from that block has been written to strm->next_out. +returned immediately after decoding an end-of-block code or decoding the +complete header up to just before the first byte of the deflate stream. +The end-of-block will not be indicated until all of the uncompressed +data from that block has been written to strm->next_out. The number of unused bits may in general be greater than seven, except when bit 7 of data_type is set, in which case the number of unused bits will be less than eight. +.Fa data_type +is set as noted here every time +.Fn inflate +returns for all flush options, +and so can be used to determine the amount of currently consumed input in bits. +.Pp +The +.Dv Z_TREES +option behaves as +.Dv Z_BLOCK +does, but it also returns when the end of each deflate block header is reached, +before any actual data in that block is decoded. +This allows the caller to determine the length of the deflate block header for +later use in random access within a deflate block. +256 is added to the value of strm->data_type when +.Fn inflate +returns immediately after reaching the end of the deflate block header. .Pp .Fn inflate should normally be called until it returns @@ -762,30 +869,49 @@ should be set to .Dv Z_FINISH . In this case all pending input is processed and all pending output is flushed; .Fa avail_out -must be large enough to hold all the uncompressed data. +must be large enough to hold all the uncompressed data +for the operation to complete. (The size of the uncompressed data may have been saved by the compressor for this purpose.) -The next operation on this stream must be -.Fn inflateEnd -to deallocate the decompression state. The use of .Dv Z_FINISH -is never required, but can be used to inform +is not required to perform an inflation in one step. +However it may be used to inform .Fn inflate -that a faster approach may be used for the single +that a faster approach can be used for the single .Fn inflate call. +.Dv Z_FINISH +also informs +.Fn inflate +to not maintain a sliding window if the stream completes, +which reduces its memory footprint. +If the stream does not complete, +either because not all of the stream is provided or not enough output space +is provided, then a sliding window will be allocated and +.Fn inflate +can be called again to continue the operation as if +.Dv Z_NO_FLUSH +had been used. .Pp In this implementation, .Fn inflate always flushes as much output as possible to the output buffer, and always uses the faster approach on the first call. -So the only effect of the -.Fa flush -parameter in this implementation is on the return value of -.Fn inflate , -as noted below, or when it returns early because +So the effects of the flush parameter in this implementation are +on the return value of +.Fn inflate +as noted below, +when +.Fn inflate +returns early when .Dv Z_BLOCK +or +.Dv Z_TREES +is used, and when +.Fn inflate +avoids the allocation of memory for a sliding window when +.Dv Z_FINISH is used. .Pp If a preset dictionary is needed after this call (see @@ -808,14 +934,16 @@ the compressor and returns only if the checksum is correct. .Pp .Fn inflate -will decompress and check either zlib-wrapped or gzip-wrapped deflate data. -The header type is detected automatically. -Any information contained in the gzip header is not retained, -so applications that need that information should instead use raw inflate; see -.Fn inflateInit2 -below, or -.Fn inflateBack -and perform their own processing of the gzip header and trailer. +can decompress and check either zlib-wrapped or gzip-wrapped deflate data. +The header type is detected automatically, if requested when initializing with +.Fn inflateInit2 . +Any information contained in the gzip header is not retained unless +.Fn inflateGetHeader +is used. +When processing gzip-wrapped deflate data, strm->adler32 is set to the CRC-32 +of the output produced so far. +The CRC-32 is checked against the gzip trailer, +as is the uncompressed length, modulo 2^32. .Pp .Fn inflate returns @@ -830,19 +958,21 @@ if a preset dictionary is needed at this point, .Dv Z_DATA_ERROR if the input data was corrupted (input stream not conforming to the .Nm zlib -format or incorrect check value), +format or incorrect check value, +in which case strm->msg points to a string with a more specific error), .Dv Z_STREAM_ERROR if the stream structure was inconsistent -(for example, if +(for example, .Fa next_in or .Fa next_out was -.Dv NULL ) , +.Dv NULL , +or the state was inadvertently over by the application), .Dv Z_MEM_ERROR if there was not enough memory, .Dv Z_BUF_ERROR -if no progress is possible or if there was not enough room in the output buffer +if no progress was possible or if there was not enough room in the output buffer when .Dv Z_FINISH is used. @@ -914,12 +1044,28 @@ The default value is 15 if .Fn deflateInit is used instead. .Pp +For the current implementation of +.Fn deflate , +a +.Fa windowBits +value of 8 (a window size of 256 bytes) is not supported. +As a result, a request for 8 will result in 9 (a 512-byte window). +In that case, providing 8 to +.Fn inflateInit2 +will result in an error when the zlib header with 9 is +checked against the initialization of +.Fn inflate . +The remedy is to not use 8 with +.Fn deflateInit2 +with this initialization, or at least in that case use 9 with +.Fn inflateInit2 . +.Pp .Fa windowBits can also be -8..-15 for raw deflate. In this case, -windowBits determines the window size. .Fn deflate will then generate raw deflate data with no zlib header or trailer, -and will not compute an Adler-32 check value. +and will not compute a check value. .Pp .Fa windowBits can also be greater than 15 for optional gzip encoding. @@ -930,10 +1076,15 @@ compressed data instead of a zlib wrapper. The gzip header will have no file name, no extra data, no comment, no modification time .Pq set to zero , -no header crc, and the operating system will be set to 255 -.Pq unknown . +no header crc, and the operating system will be set to +the appropriate value, +if the operating system was determined at compile time. If a gzip stream is being written, -strm->adler is a crc32 instead of an adler32. +strm->adler is a CRC-32 instead of an Adler-32. +.Pp +For raw deflate or gzip encoding, a request for a 256-byte window is +rejected as invalid, since only the zlib header provides a means of +transmitting the window size to the decompressor. .Pp The .Fa memLevel @@ -972,7 +1123,7 @@ The effect of .Dv Z_FILTERED is to force more Huffman coding and less string matching; it is somewhat intermediate between -.Dv Z_DEFAULT +.Dv Z_DEFAULT_STRATEGY and .Dv Z_HUFFMAN_ONLY . .Dv Z_RLE @@ -994,8 +1145,12 @@ if successful, .Dv Z_MEM_ERROR if there was not enough memory, .Dv Z_STREAM_ERROR -if a parameter is invalid -.Pq such as an invalid method . +if any parameter is invalid +.Pq such as an invalid method , +or +.Dv Z_VERSION_ERROR +if the zlib library version (zlib_version) is +incompatible with the version assumed by the caller (ZLIB_VERSION). .Fa msg is set to null if there is no error message. .Fn deflateInit2 @@ -1008,13 +1163,20 @@ does not perform any compression: this will be done by .Pp Initializes the compression dictionary from the given byte sequence without producing any compressed output. -This function must be called immediately after -.Fn deflateInit , -.Fn deflateInit2 , +When using the zlib format, this function must be called immediately after +.Fn deflateInit , deflateInit2 or .Fn deflateReset , -before any call to +and before any call of .Fn deflate . +When doing raw deflate, this function must be called either before any call of +.Fn deflate , +or immediately after the completion of a deflate block, +i.e. after all input has been consumed and all output has been delivered +when using any of the flush options +.Dv Z_BLOCK , Z_PARTIAL_FLUSH , Z_SYNC_FLUSH , +or +.Dv Z_FULL_FLUSH . The compressor and decompressor must use exactly the same dictionary (see .Fn inflateSetDictionary ) . @@ -1033,10 +1195,10 @@ Depending on the size of the compression data structures selected by or .Fn deflateInit2 , a part of the dictionary may in effect be discarded, -for example if the dictionary is larger than the window size in -.Fn deflate +for example if the dictionary is larger than the window size provided in +.Fn deflateInit or -.Fn deflate2 . +.Fn deflateInit2 . Thus the strings most likely to be useful should be put at the end of the dictionary, not at the front. In addition, the current implementation of @@ -1058,16 +1220,59 @@ if successful, or .Dv Z_STREAM_ERROR if a parameter is invalid -.Pq such as NULL dictionary +.Pq e.g. dictionary being NULL or the stream state is inconsistent (for example if .Fn deflate -has already been called for this stream or if the compression method is bsort). +has already been called for this stream or if not at a block boundary for raw +deflate). .Fn deflateSetDictionary does not perform any compression: this will be done by .Fn deflate . .It Xo .Fa int +.Fn deflateGetDictionary "z_streamp strm" "Bytef *dictionary uInt *dictLength" ; +.Xc +.Pp +Returns the sliding dictionary being maintained by +.Fn deflate . +.Fa dictLength +is set to the number of bytes in the dictionary, and that many bytes are copied +to +.Fa dictionary . +.Fa dictionary +must have enough space, where 32768 bytes is always enough. +If +.Fn deflateGetDictionary +is called with dictionary equal to +.Dv NULL , +then only the dictionary length is returned, and nothing is copied. +Similary, if +.Fa dictLength +is +.Dv NULL , +then it is not set. +.Pp +.Fn deflateGetDictionary +may return a length less than the window size, +even when more than the window size in input has been provided. +It may return up to 258 bytes less in that case, +due to how zlib's implementation of +.Fn deflate +manages the sliding window and lookahead for matches, +where matches can be up to 258 bytes long. +If the application needs the last window-size bytes of input, +then that would need to be saved by the application outside of +.Nm zlib . +.Pp +.Fn deflateGetDictionary +returns +.Dv Z_OK +on success, or +.Dv Z_STREAM_ERROR +if the stream state is inconsistent. +.It Xo +.Fa int .Fn deflateCopy "z_streamp dest" "z_streamp source" ; .Xc .Pp @@ -1107,10 +1312,9 @@ This function is equivalent to .Fn deflateEnd followed by .Fn deflateInit , -but does not free and reallocate all the internal compression state. -The stream will keep the same compression level and any other attributes -that may have been set by -.Fn deflateInit2 . +but does not free and reallocate the internal compression state. +The stream will leave the compression level and any other attributes +that may have been set unchanged. .Pp .Fn deflateReset returns @@ -1136,30 +1340,62 @@ The interpretation of level and strategy is as in This can be used to switch between compression and straight copy of the input data, or to switch to a different kind of input data requiring a different strategy. -If the compression level is changed, the input available so far -is compressed with the old level -.Pq and may be flushed ; -the new level will take effect only at the next call to +If the compression approach (which is a function of the level) or the +strategy is changed, and if any input has been consumed in a previous +.Fn deflate +call, then the input available so far is compressed with the old +level and strategy using deflate(strm, Z_BLOCK). +There are three approaches for the compression levels 0, 1..3, and 4..9, +respectively. +The new level and strategy will take effect at the next call of .Fn deflate . .Pp -Before the call to +If a deflate(strm, Z_BLOCK) is performed by .Fn deflateParams , -the stream state must be set as for a call to -.Fn deflate , -since the currently available input may have to be compressed and flushed. -In particular, strm->avail_out must be non-zero. +and it does not have enough output space to complete, +then the parameter change will not take effect. +In this case, +.Fn deflateParams +can be called again with the same parameters and more output space to try again. +.Pp +In order to assure a change in the parameters on the first try, the +deflate stream should be flushed using +.Fn deflate +with +.Dv Z_BLOCK +or other flush request until +.Fa strm.avail_out +is not zero, before calling +.Fn deflateParams . +Then no more input data should be provided before the +.Fn deflateParams +call. +If this is done, the old level and strategy will be applied to the data +compressed before +.Fn deflateParams , +and the new level and strategy will be applied to the the data compressed after +.Fn deflateParams . .Pp .Fn deflateParams returns .Dv Z_OK -if successful, +on success, .Dv Z_STREAM_ERROR if the source stream state was inconsistent or if a parameter was invalid, or .Dv Z_BUF_ERROR -if strm->avail_out was zero. +if there was not enough output space to complete the compression of the +available input data before a change in the strategy or approach. +Note that in the case of a +.Dv Z_BUF_ERROR , +the parameters are not changed. +A return value of +.Dv Z_BUF_ERROR +is not fatal, in which case +.Fn deflateParams +can be retried with more output space. .It Xo .Fa int -.Fn deflateTune "z_streamp strm" "int good_length" "int max_lazy" "int nice_length" "int max_chain" +.Fn deflateTune "z_streamp strm" "int good_length" "int max_lazy" "int nice_length" "int max_chain" ; .Xc .Pp Fine tune @@ -1189,7 +1425,7 @@ on success, or for an invalid deflate stream. .It Xo .Fa uLong -.Fn deflateBound "z_streamp strm" "uLong sourceLen" +.Fn deflateBound "z_streamp strm" "uLong sourceLen" ; .Xc .Pp .Fn deflateBound @@ -1200,12 +1436,60 @@ It must be called after .Fn deflateInit or .Fn deflateInit2 . +and after +.Fn deflateSetHeader , +if used. This would be used to allocate an output buffer for deflation in a single pass, and so would be called before .Fn deflate . +If that first +.Fn deflate +call is provided the +.Fa sourceLen +input bytes, an output buffer allocated to the size returned by +.Fn deflateBound , +and the flush value +.Dv Z_FINISH , +then +.Fn deflate +is guaranteed to return +.Dv Z_STREAM_END . +Note that it is possible for the compressed size to be larger than +the value returned by +.Fn deflateBound +if flush options other than +.Dv Z_FINISH +or +.Dv Z_NO_FLUSH +are used. .It Xo .Fa int -.Fn deflatePrime "z_streamp strm" "int bits" "int value" +.Fn deflatePending "z_streamp strm" "unsigned *pending" "int *bits" ; +.Xc +.Pp +.Fn deflatePending +returns the number of bytes and bits of output that have been generated, +but not yet provided in the available output. +The bytes not provided would be due to the available output space +having been consumed. +The number of bits of output not provided are between 0 and 7, +where they await more bits to join them in order to fill out a full byte. +If +.Fa pending +or +.Fa bits +are +.Dv NULL , +then those values are not set. +.Pp +.Fn deflatePending returns +.Dv Z_OK +if success, or +.Dv Z_STREAM_ERROR +if the source stream state was inconsistent. +.It Xo +.Fa int +.Fn deflatePrime "z_streamp strm" "int bits" "int value" ; .Xc .Pp .Fn deflatePrime @@ -1213,7 +1497,7 @@ inserts .Fa bits in the deflate output stream. The intent is that this function is used to start off the deflate output -with the bits leftover from a previous deflate stream when appending to it. +with the bits left over from a previous deflate stream when appending to it. As such, this function can only be used for raw deflate, and must be used before the first .Fn deflate @@ -1230,12 +1514,14 @@ will be inserted in the output. .Fn deflatePrime returns .Dv Z_OK -if successful, or +if successful, +.Dv Z_BUF_ERROR +if there was not enough room in the internal buffer to insert the bits, or .Dv Z_STREAM_ERROR if the source stream state was inconsistent. .It Xo .Fa int -.Fn deflateSetHeader "z_streamp strm" "gz_headerp head" +.Fn deflateSetHeader "z_streamp strm" "gz_headerp head" ; .Xc .Pp .Fn deflateSetHeader @@ -1254,7 +1540,7 @@ in the provided gz_header structure are written to the gzip header (xflag is ignored \- the extra flags are set according to the compression level). The caller must assure that, if not -.Dv Z_NULL , +.Dv NULL , .Fa name and .Fa comment @@ -1262,7 +1548,7 @@ are terminated with a zero byte, and that if .Fa extra is not -.Dv Z_NULL , +.Dv NULL , that .Fa extra_len bytes are available there. @@ -1327,6 +1613,10 @@ will return with the error code instead of trying to allocate a larger window. .Pp .Fa windowBits +can also be zero to request that inflate use the window size in the zlib header +of the compressed stream. +.Pp +.Fa windowBits can also be -8..-15 for raw inflate. In this case, -windowBits determines the window size. .Fn inflate @@ -1338,7 +1628,7 @@ such as zip. Those formats provide their own check values. If a custom format is developed using the raw deflate format for compressed data, it is recommended that a check value such as an Adler-32 -or a crc32 be applied to the uncompressed data as is done in the zlib, gzip, +or a CRC-32 be applied to the uncompressed data as is done in the zlib, gzip, and zip formats. For most applications, the zlib format should be used as is. Note that comments above on the use in @@ -1353,7 +1643,19 @@ detection, or add 16 to decode only the gzip format (the zlib format will return a .Dv Z_DATA_ERROR ) . If a gzip stream is being decoded, -strm->adler is a crc32 instead of an adler32. +strm->adler is a CRC-32 instead of an Adler-32. +Unlike the +.Xr gunzip 1 +utility and +.Fn gzread +(see below), +.Fn inflate +will not automatically decode concatenated gzip streams. +.Fn inflate +will return +.Dv Z_STREAM_END +at the end of the gzip stream. +The state would need to be reset to continue decoding a subsequent gzip stream. .Pp .Fn inflateInit2 returns @@ -1361,15 +1663,17 @@ returns if successful, .Dv Z_MEM_ERROR if there was not enough memory, +.Dv Z_VERSION_ERROR +if the +.Nm zlib +library version is incompatible with the version assumed by the caller, or .Dv Z_STREAM_ERROR -if a parameter is invalid -(such as a null strm). +if the parameters are invalid, such as a null pointer to the structure. .Fa msg is set to null if there is no error message. .Fn inflateInit2 -does not perform any decompression apart from reading the -.Nm zlib -header if present: this will be done by +does not perform any decompression apart from possibly reading the zlib header +if present: actual decompression will be done by .Fn inflate . (So .Fa next_in @@ -1379,7 +1683,12 @@ may be modified, but .Fa next_out and .Fa avail_out -are unchanged.) +are unused and unchanged.) +The current implementation of +.Fn inflateInit2 +does not process any header information \(em that is deferred until +.Fn inflate +is called. .It Xo .Fa int .Fn inflateSetDictionary "z_streamp strm" "const Bytef *dictionary" "uInt dictLength" ; @@ -1397,13 +1706,9 @@ Adler-32 value returned by that call to The compressor and decompressor must use exactly the same dictionary (see .Fn deflateSetDictionary ) . -For raw inflate, this function can be called immediately after -.Fn inflateInit2 -or -.Fn inflateReset -and before any call to -.Fn inflate -to set the dictionary. +For raw inflate, this function can be called at any time to set the dictionary. +If the provided dictionary is smaller than the window and there is already +data in the window, then the provided dictionary will amend what's there. The application must ensure that the dictionary that was used for compression is provided. .Pp @@ -1413,7 +1718,7 @@ returns if successful, .Dv Z_STREAM_ERROR if a parameter is invalid -.Pq such as NULL dictionary +.Pq e.g. dictionary being NULL or the stream state is inconsistent, .Dv Z_DATA_ERROR if the given dictionary doesn't match the expected one @@ -1423,10 +1728,39 @@ does not perform any decompression: this will be done by subsequent calls of .Fn inflate . .It Xo .Fa int +.Fn inflateGetDictionary "z_streamp strm" "Bytef *dictionary" "uInt *dictLength" ; +.Xc +.Pp +Returns the sliding dictionary being maintained by +.Fn inflate . +.Fa dictLength +is set to the number of bytes in the dictionary, and that many bytes are copied +to +.Fa dictionary . +.Fa dictionary +must have enough space, where 32768 bytes is always enough. +If +.Fn inflateGetDictionary +is called with dictionary equal to +.Dv NULL , +then only the dictionary length is returned, and nothing is copied. +Similary, if +.Fa dictLength is +.Dv NULL , +then it is not set. +.Pp +.Fn inflateGetDictionary +returns +.Dv Z_OK +on success, or +.Dv Z_STREAM_ERROR +if the stream state is inconsistent. +.It Xo +.Fa int .Fn inflateSync "z_streamp strm" ; .Xc .Pp -Skips invalid compressed data until a full flush point +Skips invalid compressed data until a possible full flush point (see above the description of .Fn deflate with @@ -1435,9 +1769,14 @@ can be found, or until all available input is skipped. No output is provided. .Pp .Fn inflateSync +searches for a 00 00 FF FF pattern in the compressed data. +All full flush points have this pattern, but not all occurrences of this +pattern are full flush points. +.Pp +.Fn inflateSync returns .Dv Z_OK -if a full flush point has been found, +if a possible full flush point has been found, .Dv Z_BUF_ERROR if no more input was provided, .Dv Z_DATA_ERROR @@ -1452,7 +1791,7 @@ In the error case, the application may repeatedly call providing more input each time, until success or end of the input data. .It Xo .Fa int -.Fn inflateCopy "z_streamp dest" "z_streamp source" +.Fn inflateCopy "z_streamp dest" "z_streamp source" ; .Xc .Pp Sets the destination stream as a complete copy of the source stream. @@ -1486,7 +1825,7 @@ This function is equivalent to .Fn inflateEnd followed by .Fn inflateInit , -but does not free and reallocate all the internal decompression state. +but does not free and reallocate the internal decompression state. The stream will keep attributes that may have been set by .Fn inflateInit2 . .Pp @@ -1503,7 +1842,39 @@ or being NULL). .It Xo .Fa int -.Fn inflatePrime "z_stream strm" "int bits" "int value" +.Fn inflateReset2 "z_streamp strm" "int windowBits" ; +.Xc +.Pp +This function is the same as +.Fn inflateReset , +but it also permits changing the wrap and window size requests. +The +.Fa windowBits +parameter is interpreted the same as it is for +.Fa inflateInit2 . +If the window size is changed, then the memory allocated for the window +is freed, and the window will be reallocated by +.Fn inflate +if needed. +.Pp +.Fn inflateReset2 +returns +.Dv Z_OK +if success, or +.Dv Z_STREAM_ERROR +if the source stream state was inconsistent +(such as +.Fa zalloc +or +.Fa state +being +.Dv NULL ) , +or if the +.Fa windowBits +parameter is invalid. +.It Xo +.Fa int +.Fn inflatePrime "z_stream strm" "int bits" "int value" ; .Xc .Pp This function inserts bits in the inflate input stream. @@ -1523,6 +1894,16 @@ must be less than or equal to 16, and that many of the least significant bits of value will be inserted in the input. .Pp +If +.Fa bits +is negative, then the input stream bit buffer is emptied. +Then +.Fn inflatePrime +can be called again to put bits in the buffer. +This is used to clear out bits left over after feeding +.Fn inflate +a block description prior to feeding it codes. +.Pp .Fn inflatePrime returns .Dv Z_OK @@ -1530,8 +1911,53 @@ if successful, or .Dv Z_STREAM_ERROR if the source stream state was inconsistent. .It Xo +.Fa long +.Fn inflateMark "z_streamp strm" ; +.Xc +.Pp +This function returns two values: one in the lower 16 bits of the return +value, and the other in the remaining upper bits, obtained by shifting the +return value down 16 bits. +If the upper value is -1 and the lower value is zero, then +.Fn inflate +is currently decoding information outside of a block. +If the upper value is -1 and the lower value is non-zero, then +.Fn inflate +is in the middle of a stored block, with the lower value equaling the number of +bytes from the input remaining to copy. +If the upper value is not -1, then it is the number of bits back from +the current bit position in the input of the code +(literal or length/distance pair) +currently being processed. +In that case the lower value is the number of bytes +already emitted for that code. +.Pp +A code is being processed if +.Fn inflate +is waiting for more input to complete decoding of the code, +or if it has completed decoding but is waiting for +more output space to write the literal or match data. +.Pp +.Fn inflateMark +is used to mark locations in the input data for random access, +which may be at bit positions, +and to note those cases where the output of a code may span +boundaries of random access blocks. +The current location in the input stream can be determined from +.Fa avail_in +and +.Fa data_type +as noted in the description for the +.Dv Z_BLOCK +flush parameter for +.Fn inflate . +.Pp +.Fn inflateMark +returns the value noted above, +or -65536 if the provided source stream state was inconsistent. +.It Xo .Fa int -.Fn inflateGetHeader "z_streamp strm" "gz_headerp head" +.Fn inflateGetHeader "z_streamp strm" "gz_headerp head" ; .Xc .Pp .Fn inflateGetHeader @@ -1549,10 +1975,12 @@ As processes the gzip stream, head->done is zero until the header is completed, at which time head->done is set to one. If a zlib stream is being decoded, -then head->done is set to \-1 to indicate that there will be +then head->done is set to -1 to indicate that there will be no gzip header information forthcoming. Note that .Dv Z_BLOCK +or +.Dv Z_TREES can be used to force .Fn inflate to return immediately after header processing is complete @@ -1563,7 +1991,7 @@ contents. hcrc is set to true if there is a header CRC. (The header CRC was valid if done is set to one.) If extra is not -.Dv Z_NULL , +.Dv NULL , then .Fa extra_max contains the maximum number of bytes to write to @@ -1577,24 +2005,24 @@ contains the extra field, or that field truncated if is less than .Fa extra_len . If name is not -.Dv Z_NULL , +.Dv NULL , then up to .Fa name_max characters are written there, terminated with a zero unless the length is greater than .Fa name_max . If comment is not -.Dv Z_NULL , +.Dv NULL , then up to .Fa comm_max characters are written there, terminated with a zero unless the length is greater than .Fa comm_max . When any of extra, name, or comment are not -.Dv Z_NULL +.Dv NULL and the respective field is not present in the header, then that field is set to -.Dv Z_NULL +.Dv NULL to signal its absence. This allows the use of .Fn deflateSetHeader @@ -1623,7 +2051,7 @@ or if the source stream state was inconsistent. .It Xo .Fa int -.Fn inflateBackInit "z_stream *strm" "int windowBits" "unsigned char FAR *window" +.Fn inflateBackInit "z_stream *strm" "int windowBits" "unsigned char FAR *window" ; .Xc .Pp Initialize the internal stream state for decompression using @@ -1641,7 +2069,7 @@ If and .Fa zfree are -.Dv Z_NULL , +.Dv NULL , then the default library-derived memory allocation routines are used. .Fa windowBits is the base two logarithm of the window size, in the range 8..15. @@ -1670,17 +2098,20 @@ if the internal state could not be allocated, or if the version of the library does not match the version of the header file. .It Xo .Fa int -.Fn inflateBack "z_stream *strm" "in_func in" "void FAR *in_desc" "out_func out" "void FAR *out_desc" +.Fn inflateBack "z_stream *strm" "in_func in" "void FAR *in_desc" "out_func out" "void FAR *out_desc" ; .Xc .Pp .Fn inflateBack does a raw inflate with a single call using a call-back interface for input and output. -This is more efficient than +This is potentially more efficient than .Fn inflate -for file I/O applications in that it avoids copying between the output and the +for file I/O applications, in that it avoids copying between the output and the sliding window by simply making the window itself the output buffer. -This function trusts the application to not change the output buffer passed by +.Fn inflate +can be faster on modern CPUs when used with large buffers. +.Fn inflateBack +trusts the application to not change the output buffer passed by the output function, at least until .Fn inflateBack returns. @@ -1699,10 +2130,9 @@ This routine would normally be used in a utility that reads zip or gzip files and writes out uncompressed files. The utility would decode the header and process the trailer on its own, hence this routine expects only the raw deflate stream to decompress. -This is different from the normal behavior of +This is different from the default behavior of .Fn inflate , -which expects either a zlib or gzip header and -trailer around the deflate stream. +which expects either a zlib header and trailer around the deflate stream. .Pp .Fn inflateBack uses two subroutines supplied by the caller that are then called by @@ -1758,12 +2188,12 @@ will be called. Therefore strm->next_in must be initialized before calling .Fn inflateBack . If strm->next_in is -.Dv Z_NULL , +.Dv NULL , then .Fn in will be called immediately for input. If strm->next_in is not -.Dv Z_NULL , +.Dv NULL , then strm->avail_in must also be initialized, and then if strm->avail_in is not zero, input will initially be taken from @@ -1778,8 +2208,8 @@ parameters of are passed as the first parameter of .Fn in and -.Fn out -respectively when they are called. +.Fn out , +respectively, when they are called. These descriptors can be optionally used to pass any information that the caller-supplied .Fn in @@ -1814,12 +2244,12 @@ In the case of .Dv Z_BUF_ERROR , an input or output error can be distinguished using strm->next_in which will be -.Dv Z_NULL +.Dv NULL only if .Fn in returned an error. If strm->next is not -.Dv Z_NULL , +.Dv NULL , then the .Dv Z_BUF_ERROR was due to @@ -1839,7 +2269,7 @@ cannot return .Dv Z_OK . .It Xo .Fa int -.Fn inflateBackEnd "z_stream *strm" +.Fn inflateBackEnd "z_stream *strm" ; .Xc .Pp All memory allocated by @@ -1854,7 +2284,7 @@ on success, or if the stream state was inconsistent. .It Xo .Fa uLong -.Fn zlibCompileFlags "void" +.Fn zlibCompileFlags "void" ; .Xc .Pp This function returns flags indicating compile-time options. @@ -1888,7 +2318,7 @@ Compiler, assembler, and debug options: .Pp .Bl -tag -width Ds -offset indent -compact .It 8 -DEBUG +ZLIB_DEBUG .It 9 ASMV or ASMINF \(em use ASM code .It 10 @@ -1966,7 +2396,7 @@ basic stream-oriented functions. To simplify the interface, some default options are assumed (compression level and memory usage, standard memory allocation functions). -The source code of these utility functions can easily be modified +The source code of these utility functions can be modified if you need special options. .Bl -tag -width Ds .It Xo @@ -1986,9 +2416,12 @@ which must be at least the value returned by .Fn compressBound sourcelen . Upon exit, .Fa destLen -is the actual size of the compressed buffer. -This function can be used to compress a whole file at once if the -input file is mmap'ed. +is the actual size of the compressed data. +.Fn compress +is equivalent to +.Fn compress2 +with a level parameter of +.Dv Z_DEFAULT_COMPRESSION . .Pp .Fn compress returns @@ -2032,8 +2465,8 @@ if there was not enough room in the output buffer, or .Dv Z_STREAM_ERROR if the level parameter is invalid. .It Xo -.Fa int -.Fn compressBound "uLong sourceLen" +.Fa uLong +.Fn compressBound "uLong sourceLen" ; .Xc .Pp .Fn compressBound @@ -2068,7 +2501,7 @@ by the compressor and transmitted to the decompressor by some mechanism outside the scope of this compression library.) Upon exit, .Fa destLen -is the actual size of the compressed buffer. +is the actual size of the uncompressed data. This function can be used to decompress a whole file at once if the input file is mmap'ed. .Pp @@ -2082,11 +2515,33 @@ if there was not enough memory, if there was not enough room in the output buffer, or .Dv Z_DATA_ERROR if the input data was corrupted or incomplete. +In the case where there is not enough room, +.Fn uncompress +will fill the output buffer with the uncompressed data up to that point. +.It Xo +.Fa int +.Fn uncompress2 "Bytef *dest" "uLongf *destLen" "const Bytef *source" "uLong *sourceLen" ; +.Xc +.Pp +Same as +.Fn uncompress , +except that +.Fa sourceLen +is a pointer, where the length of the source is +.Fa *sourceLen . +On return, +.Fa *sourceLen +is the number of source bytes consumed. .It Xo .Fa gzFile .Fn gzopen "const char *path" "const char *mode" ; .Xc .Pp +This library supports reading and writing files in gzip (.gz) format with +an interface similar to that of stdio, using the functions that start with "gz". +The gzip format is different from the zlib format. +gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate stream. +.Pp The .Fn gzopen function opens a gzip @@ -2111,26 +2566,76 @@ for Huffman only compression, as in or .Sq R for run-length encoding as in -.Qq wb1R . +.Qq wb1R , +or +.Sq F +for fixed code compression as in +.Qq wb9F . (See the description of .Fn deflateInit2 for more information about the strategy parameter.) +.Sq T +will request transparent writing or appending with no compression and not using +the gzip format. +.Pp +.Sq a +can be used instead of +.Sq w +to request that the gzip stream that will be written be appended to the file. +.Sq + +will result in an error, +since reading and writing to the same gzip file is not supported. +The addition of +.Sq x +when writing will create the file exclusively, +which fails if the file already exists. +On systems that support it, the addition of +.Sq e +when reading or writing will set the flag to close the file on an +.Xr execve 2 +call. +.Pp +These functions, as well as gzip, +will read and decode a sequence of gzip streams in a file. +The append function of +.Fn gzopen +can be used to create such a file. +(Also see +.Fn gzflush +for another way to do this.) +When appending, +.Fn gzopen +does not test whether the file begins with a gzip stream, +nor does it look for the end of the gzip streams to begin appending. +.Fn gzopen +will simply append a gzip stream to the existing file. .Pp .Fn gzopen can be used to read a file which is not in gzip format; in this case .Fn gzread will directly read from the file without decompression. +When reading, this will be detected automatically +by looking for the magic two-byte gzip header. .Pp .Fn gzopen returns .Dv NULL -if the file could not be opened or if there was -insufficient memory to allocate the (de)compression state; -errno can be checked to distinguish the two cases (if errno is zero, the -.Nm zlib -error is -.Dv Z_MEM_ERROR ) . +if the file could not be opened, +if there was insufficient memory to allocate the gzFile state, +or if an invalid mode was specified +(an +.Sq r , +.Sq w , +or +.Sq a +was not provided, or +.Sq + +was provided). +.Fa errno +can be checked to determine if the reason +.Fn gzopen +failed was that the file could not be opened. .It Xo .Fa gzFile .Fn gzdopen "int fd" "const char *mode" ; @@ -2158,12 +2663,54 @@ The next call to .Fn gzclose on the returned gzFile will also close the file descriptor fd, just like fclose(fdopen(fd), mode) closes the file descriptor fd. -If you want to keep fd open, use gzdopen(dup(fd), mode). +If you want to keep fd open, use +.Dq fd = dup(fd_keep); gz = gzdopen(fd, mode); . +The duplicated descriptor should be saved to avoid a leak, since +.Fn gzdopen +does not close fd if it fails. +If you are using +.Fn fileno +to get the file descriptor from a FILE *, +then you will have to use +.Xr dup 2 +to avoid double-closing the file descriptor. +Both +.Fn gzclose +and +.Fn fclose +will close the associated file descriptor, +so they need to have different file descriptors. .Pp .Fn gzdopen -returns -.Dv NULL -if there was insufficient memory to allocate the (de)compression state. +returns NULL if there was insufficient memory to allocate the gzFile state, +if an invalid mode was specified +(an 'r', 'w', or 'a' was not provided, or '+' was provided), or if fd is -1. +The file descriptor is not used until the next gz* read, write, seek, +or close operation, so +.Fn gzdopen +will not detect if fd is invalid (unless fd is -1). +.It Xo +.Fa int +.Fn gzbuffer "gzFile file" "unsigned size" ; +.Xc +.Pp +Set the internal buffer size used by this library's functions. +The default buffer size is 8192 bytes. +This function must be called after +.Fn gzopen +or +.Fn gzdopen , +and before any other calls that read or write the file. +The buffer memory allocation is always deferred to the first read or write. +Three times that size in buffer space is allocated. +A larger buffer size of, for example, 64K or 128K bytes, +will noticeably increase the speed of decompression (reading). +.Pp +The new buffer size also affects the maximum length for +.Fn gzprintf . +.Pp +.Fn gzbuffer +returns 0 on success, or -1 on failure, such as being called too late. .It Xo .Fa int .Fn gzsetparams "gzFile file" "int level" "int strategy" ; @@ -2175,28 +2722,137 @@ function dynamically updates the compression level or strategy. See the description of .Fn deflateInit2 for the meaning of these parameters. +Previously provided data is flushed before the parameter change. .Pp .Fn gzsetparams returns .Dv Z_OK -if successful, or +if successful, .Dv Z_STREAM_ERROR -if the file was not opened for writing. +if the file was not opened for writing, +.Dv Z_ERRNO +if there is an error writing the flushed data, or +.Dv Z_MEM_ERROR +if there is a memory allocation error. .It Xo .Fa int .Fn gzread "gzFile file" "voidp buf" "unsigned len" ; .Xc .Pp -The +Reads the given number of uncompressed bytes from the compressed file. +If the input file is not in gzip format, .Fn gzread -function reads the given number of uncompressed bytes from the compressed file. -If the input file was not in gzip format, +copies the given number ofbytes into the buffer directly from the file. +.Pp +After reaching the end of a gzip stream in the input, .Fn gzread -copies the given number of bytes into the buffer. +will continue to read, looking for another gzip stream. +Any number of gzip streams may be concatenated in the input file, +and will all be decompressed by +.Fn gzread . +If something other than a gzip stream is encountered after a gzip stream, +that remaining trailing garbage is ignored (and no error is returned). .Pp .Fn gzread -returns the number of uncompressed bytes actually read -(0 for end of file, \-1 for error). +can be used to read a gzip file that is being concurrently written. +Upon reaching the end of the input, +.Fn gzread +will return with the available data. +If the error code returned by +.Fn gzerror +is +.Dv Z_OK +or +.Dv Z_BUF_ERROR , +then +.Fn gzclearerr +can be used to clear the end of file indicator in order to permit +.Fn gzread +to be tried again. +.Dv Z_OK +indicates that a gzip stream was completed on the last +.Fn gzread . +.Dv Z_BUF_ERROR +indicates that the input file ended in the middle of a gzip stream. +Note that +.Fn gzread +does not return -1 in the event of an incomplete gzip stream. +This error is deferred until +.Fn gzclose , +which will return +.Dv Z_BUF_ERROR +if the last +.Fn gzread +ended in the middle of a gzip stream. +Alternatively, +.Fn gzerror +can be used before +.Fn gzclose +to detect this case. +.Pp +.Fn gzread +returns the number of uncompressed bytes actually read, +less than +.Fa len +for end of file, or -1 for error. +If +.Fa len +is too large to fit in an int, +then nothing is read, -1 is returned, and the error state is set to +.Dv Z_STREAM_ERROR . +.It Xo +.Fa z_size_t +.Fn gzfread "voidp buf" "z_size_t size" "z_size_t nitems" "gzFile file" ; +.Xc +.Pp +Read up to +.Fa nitems +items of size +.Fa size +from +.Fa file +to +.Fa buf , +otherwise operating as +.Fn gzread +does. +This duplicates the interface of stdio's +.Xr fread 3 , +with size_t request and return types. +If the library defines size_t, then z_size_t is identical to size_t. +If not, then z_size_t is an unsigned integer type that can contain a pointer. +.Pp +.Fn gzfread +returns the number of full items read of size +.Fa size , +or zero if the end of the file was reached and a full item could not be read, +or if there was an error. +.Fn gzerror +must be consulted if zero is returned in order to determine +if there was an error. +If the multiplication of +.Fa size +and +.Fa nitems +overflows, i.e. the product does not fit in a z_size_t, then nothing is read, +zero is returned, and the error state is set to +.Dv Z_STREAM_ERROR . +.Pp +In the event that the end of file is reached and only a partial item is +available at the end, i.e. the remaining uncompressed data length is not a +multiple of size, then the final partial item is nevetheless read into +.Fa buf +and the end-of-file flag is set. +The length of the partial item read is not provided, +but could be inferred from the result of +.Fn gztell . +This behavior is the same as the behavior of +.Xr fread 3 +implementations in common libraries, +but it prevents the direct use of +.Fn gzfread +to read a concurrently written file, resetting and retrying on end-of-file, +when size is not 1. .It Xo .Fa int .Fn gzwrite "gzFile file" "voidpc buf" "unsigned len" ; @@ -2206,8 +2862,39 @@ The .Fn gzwrite function writes the given number of uncompressed bytes into the compressed file. .Fn gzwrite -returns the number of uncompressed bytes actually written -.Pq 0 in case of error . +returns the number of uncompressed bytes written or 0 in case of error. +.It Xo +.Fa z_size_t +.Fn gzfwrite "voidpc buf" "z_size_t size" "z_size_t nitems" "gzFile file" ; +.Xc +.Pp +.Fn gzfwrite +writes +.Fa nitems +items of size +.Fa size +from +.Fa buf +to +.Fa file , +duplicating the interface of stdio's +.Xr fwrite 3 , +with size_t request and return types. +If the library defines size_t, then z_size_t is identical to size_t. +If not, then z_size_t is an unsigned integer type that can contain a pointer. +.Pp +.Fn gzfwrite +returns the number of full items written of size +.Fa size , +or zero if there was an error. +If the multiplication of +.Fa size +and +.Fa nitems +overflows, +i.e. the product does not fit in a z_size_t, then nothing is written, +zero is returned, and the error state is set to +.Dv Z_STREAM_ERROR . .It Xo .Fa int .Fn gzprintf "gzFile file" "const char *format" "..." ; @@ -2219,10 +2906,12 @@ function converts, formats, and writes the args to the compressed file under control of the format string, as in .Xr fprintf 3 . .Fn gzprintf -returns the number of uncompressed bytes actually written -.Pq 0 in case of error . -The number of uncompressed bytes written is limited to 4095. -The caller should make sure that this limit is not exceeded. +returns the number of uncompressed bytes actually written, +or a negative zlib error code in case of error. +The number of uncompressed bytes written is limited to 8191, +or one less than the buffer size given to +.Fn gzbuffer . +The caller should ensure that this limit is not exceeded. If it is exceeded, then .Fn gzprintf will return an error @@ -2240,6 +2929,8 @@ because the secure or .Fn vsnprintf functions were not available. +This can be determined using +.Fn zlibCompileFlags . .It Xo .Fa int .Fn gzputs "gzFile file" "const char *s" ; @@ -2247,11 +2938,11 @@ functions were not available. .Pp The .Fn gzputs -function writes the given null-terminated string to the compressed file, -excluding the terminating null character. +function writes the given NUL-terminated string to the compressed file, +excluding the terminating NUL character. .Pp .Fn gzputs -returns the number of characters written, or \-1 in case of error. +returns the number of characters written, or -1 in case of error. .It Xo .Fa char * .Fn gzgets "gzFile file" "char *buf" "int len" ; @@ -2259,17 +2950,30 @@ returns the number of characters written, or \-1 in case of error. .Pp The .Fn gzgets -function reads bytes from the compressed file until len\-1 characters are read, +function reads bytes from the compressed file until len-1 characters are read, or a newline character is read and transferred to .Fa buf , or an end-of-file condition is encountered. -The string is then terminated with a null character. +If any characters are read or if len == 1, +the string is terminated with a NUL character. +If no characters are read due to an end-of-file or len < 1, +then the buffer is left untouched. +.Pp +.Fn gzgets +returns +.Fa buf , +which is a NUL-terminated string, or it returns +.Dv NULL +for end-of-file or in case of error. +If there was an error, the contents at +.Fa buf +are indeterminate. .Pp .Fn gzgets returns .Fa buf , or -.Dv Z_NULL +.Dv NULL in case of error. .It Xo .Fa int @@ -2282,7 +2986,7 @@ function writes .Fa c , converted to an unsigned char, into the compressed file. .Fn gzputc -returns the value that was written, or \-1 in case of error. +returns the value that was written, or -1 in case of error. .It Xo .Fa int .Fn gzgetc "gzFile file" ; @@ -2292,20 +2996,37 @@ The .Fn gzgetc function reads one byte from the compressed file. .Fn gzgetc -returns this byte or \-1 in case of end of file or error. +returns this byte or -1 in case of end of file or error. +This is implemented as a macro for speed. +As such, it does not do all of the checking the other functions do. +That is, it does not check to see if file is +.Dv NULL , +nor whether the structure +.Fa file +points to has been clobbered or not. .It Xo .Fa int -.Fn gzungetc "int c" "gzFile file" +.Fn gzungetc "int c" "gzFile file" ; .Xc .Pp -Push one character back onto the stream to be read again later. -Only one character of push-back is allowed. +Push one character back onto the stream to be read as the first character +on the next read. +At least one character of push-back is allowed. +.Fn gzungetc +returns the character pushed, or -1 on failure. .Fn gzungetc -returns the character pushed, or \-1 on failure. +will fail if c is -1, +and may fail if a character has been pushed but not read yet. +If .Fn gzungetc -will fail if a character has been pushed but not read yet, or if -.Fa c -is \-1. +is used immediately after +.Fn gzopen +or +.Fn gzdopen , +at least the output buffer size of pushed characters is allowed. +(See +.Fn gzbuffer +above.) The pushed character will be discarded if the stream is repositioned with .Fn gzseek or @@ -2329,15 +3050,20 @@ error number (see function .Fn gzerror below). .Fn gzflush -returns -.Dv Z_OK -if the flush parameter is -.Dv Z_FINISH -and all output could be flushed. +is only permitted when writing. +.Pp +If the flush parameter is +.Dv Z_FINISH , +the remaining data is written and the gzip stream is completed in the output. +If +.Fn gzwrite +is called again, a new gzip stream will be started in the output. +.Fn gzread +is able to read such concatenated gzip streams. .Pp .Fn gzflush -should be called only when strictly necessary because it can -degrade compression. +should be called only when strictly necessary because it will +degrade compression if called too often. .It Xo .Fa z_off_t .Fn gzseek "gzFile file" "z_off_t offset" "int whence" ; @@ -2363,7 +3089,7 @@ then compresses a sequence of zeroes up to the new starting position. .Pp .Fn gzseek returns the resulting offset location as measured in bytes from -the beginning of the uncompressed stream, or \-1 in case of error, +the beginning of the uncompressed stream, or -1 in case of error, in particular if the file is opened for writing and the new starting position would be before the current position. .It Xo @@ -2390,43 +3116,151 @@ function returns the starting position for the next or .Fn gzwrite on the given compressed file. -This position represents a number of bytes in the uncompressed data stream. +This position represents a number of bytes in the uncompressed data stream, +and is zero when starting, +even if appending or reading a gzip stream from the middle of a file using +.Fn gzdopen . .Pp gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR). .It Xo .Fa int +.Fn gzeoffset "gzFile file" ; +.Xc +.Pp +Returns the current offset in the file being read or written. +This offset includes the count of bytes that precede the gzip stream, +for example when appending or when using +.Fn gzdopen +for reading. +When reading, the offset does not include as yet unused buffered input. +This information can be used for a progress indicator. +On error, +.Fn gzoffset +returns -1. +.It Xo +.Fa int .Fn gzeof "gzFile file" ; .Xc .Pp -The +Returns true (1) if the end-of-file indicator has been set while reading, +false (0) otherwise. +Note that the end-of-file indicator is set only if the +read tried to go past the end of the input, but came up short. +Therefore just like +.Xr feof 3 , .Fn gzeof -function returns 1 when -.Dv EOF -has previously been detected reading the given input stream, otherwise zero. +may return false even if there is no more data to read, +in the event that the last read request was for the exact number of +bytes remaining in the input file. +This will happen if the input file size is an exact multiple of the buffer size. +.Pp +If +.Fn gzeof +returns true, then the read functions will return no more data, +unless the end-of-file indicator is reset by +.Fn gzclearerr +and the input file has grown since the previous end of file was detected. .It Xo .Fa int .Fn gzdirect "gzFile file" ; .Xc .Pp -The +Returns true (1) if +.Fa file +is being copied directly while reading, +or false (0) if +.Fa file +is a gzip stream being decompressed. +.Pp +If the input file is empty, +.Fn gzdirect +will return true, since the input does not contain a gzip stream. +.Pp +If +.Fn gzdirect +is used immediately after +.Fn gzopen +or +.Fn gzdopen , +it will cause buffers to be allocated to allow reading the file +to determine if it is a gzip file. +Therefore if +.Fn gzbuffer +is used, it should be called before +.Fn gzdirect . +.Pp +When writing, +.Fn gzdirect +returns true (1) if transparent writing was requested +("wT" for the +.Fn gzopen +mode), +or false (0) otherwise. +(Note: +.Fn gzdirect +is not needed when writing. +Transparent writing must be explicitly requested, +so the application already knows the answer. +When linking statically, using .Fn gzdirect -function returns 1 if the file is being read directly -without compression; -otherwise it returns 0. +will include all of the zlib code for gzip file reading and decompression, +which may not be desired.) .It Xo .Fa int .Fn gzclose "gzFile file" ; .Xc .Pp -The -.Fn gzclose -function flushes all pending output if necessary, closes the compressed file -and deallocates all the (de)compression state. -The return value is the -.Nm zlib -error number (see function +Flushes all pending output if necessary, closes the compressed file and +deallocates the (de)compression state. +Note that once file is closed, you cannot call .Fn gzerror -below). +with +.Fa file , +since its structures have been deallocated. +.Fn gzclose +must not be called more than once on the same file, +just as +.Xr free 3 +must not be called more than once on the same allocation. +.Pp +.Fn gzclose +will return +.Dv Z_STREAM_ERROR +if +.Fa file +is not valid, +.Dv Z_ERRNO +on a file operation error, +.Dv Z_MEM_ERROR +if out of memory, +.Dv Z_BUF_ERROR +if the last read ended in the middle of a gzip stream, or +.Dv Z_OK +on success. +.It Xo +.Fa int +.Fn gzclose_r "gzFile file" ; +.Xc +.It Xo +.Fa int +.Fn gzclose_w "gzFile file" ; +.Xc +.Pp +Same as +.Fn gzclose , +but +.Fn gzclose_r +is only for use when reading, and +.Fn gzclose_w +is only for use when writing or appending. +The advantage to using these instead of +.Fn gzclose +is that they avoid linking in zlib compression or decompression code +that is not used when only reading or only writing, respectively. +If +.Fn gzclose +is used, then both compression and decompression code will be included +in the application when linking to a static zlib library. .It Xo .Fa const char * .Fn gzerror "gzFile file" "int *errnum" ; @@ -2446,9 +3280,21 @@ If an error occurred in the file system and not in the compression library, is set to .Dv Z_ERRNO and the application may consult errno to get the exact error code. +.Pp +The application must not modify the returned string. +Future calls to this function may invalidate the previously returned string. +If +.Ar file +is closed, then the string previously returned by +.Fn gzerror +will no longer be available. +.Pp +.Fn gzerror +should be used to distinguish errors from end-of-file for those +functions above that do not distinguish those cases in their return values. .It Xo .Fa void -.Fn gzclearerr "gzFile file" +.Fn gzclearerr "gzFile file" ; .Xc Clears the error and end-of-file flags for .Fa file . @@ -2477,11 +3323,11 @@ is .Dv NULL , this function returns the required initial value for the checksum. .Pp -An Adler-32 checksum is almost as reliable as a CRC32 but can be computed +An Adler-32 checksum is almost as reliable as a CRC-32 but can be computed much faster. Usage example: .Bd -unfilled -offset indent -uLong adler = adler32(0L, Z_NULL, 0); +uLong adler = adler32(0L, NULL, 0); while (read_buffer(buffer, length) != EOF) { adler = adler32(adler, buffer, length); @@ -2490,7 +3336,15 @@ if (adler != original_adler) error(); .Ed .It Xo .Fa uLong -.Fn adler32_combine "uLong adler1" "uLong adler2" "z_off_t len2" +.Fn adler32_z "uLong adler" "const Bytef *buf" "z_size_t len" ; +.Xc +.Pp +The same as +.Fn adler32 , +but with a size_t length. +.It Xo +.Fa uLong +.Fn adler32_combine "uLong adler1" "uLong adler2" "z_off_t len2" ; .Xc .Pp The @@ -2501,6 +3355,10 @@ Adler-32 checksums are calculated for each, adler1 and adler2. .Fn adler32_combine returns the Adler-32 checksum of seq1 and seq2 concatenated, requiring only adler1, adler2, and len2. +Note that the z_off_t type (like off_t) is a signed integer. +If +.Ar len2 +is negative, the result has no meaning or utility. .It Xo .Fa uLong .Fn crc32 "uLong crc" "const Bytef *buf" "uInt len" ; @@ -2520,7 +3378,7 @@ Pre- and post-conditioning is performed within this function so it shouldn't be done by the application. Usage example: .Bd -unfilled -offset indent -uLong crc = crc32(0L, Z_NULL, 0); +uLong crc = crc32(0L, NULL, 0); while (read_buffer(buffer, length) != EOF) { crc = crc32(crc, buffer, length); @@ -2529,7 +3387,15 @@ if (crc != original_crc) error(); .Ed .It Xo .Fa uLong -.Fn crc32_combine "uLong crc1" "uLong crc2" "z_off_t len2" +.Fn crc32_z "uLong adler "const Bytef *buf" "z_size_t len" ; +.Xc +.Pp +The same as +.Fn crc32 , +but with a size_t length. +.It Xo +.Fa uLong +.Fn crc32_combine "uLong crc1" "uLong crc2" "z_off_t len2" ; .Xc .Pp The @@ -2549,11 +3415,11 @@ struct internal_state; typedef struct z_stream_s { Bytef *next_in; /* next input byte */ uInt avail_in; /* number of bytes available at next_in */ - off_t total_in; /* total nb of input bytes read so far */ + off_t total_in; /* total number of input bytes read so far */ - Bytef *next_out; /* next output byte should be put there */ + Bytef *next_out; /* next output byte will go here */ uInt avail_out; /* remaining free space at next_out */ - off_t total_out; /* total nb of bytes output so far */ + off_t total_out; /* total number of bytes output so far */ char *msg; /* last error message, NULL if no error */ struct internal_state FAR *state; /* not visible by applications */ @@ -2562,8 +3428,9 @@ typedef struct z_stream_s { free_func zfree; /* used to free the internal state */ voidpf opaque; /* private data object passed to zalloc and zfree*/ - int data_type; /* best guess about the data type: binary or text*/ - uLong adler; /* adler32 value of the uncompressed data */ + int data_type; /* best guess about the data type: binary or text + for deflate, or the decoding state for inflate */ + uLong adler; /* Adler-32 or CRC-32 value of the uncompressed data */ uLong reserved; /* reserved for future use */ } z_stream; @@ -2579,12 +3446,12 @@ typedef struct gz_header_s { uLong time; /* modification time */ int xflags; /*extra flags (not used when writing a gzip file)*/ int os; /* operating system */ - Bytef *extra; /* pointer to extra field or Z_NULL if none */ - uInt extra_len; /* extra field length (valid if extra != Z_NULL) */ + Bytef *extra; /* pointer to extra field or NULL if none */ + uInt extra_len; /* extra field length (valid if extra != NULL) */ uInt extra_max; /* space at extra (only when reading header) */ - Bytef *name; /* pointer to zero-terminated file name or Z_NULL*/ + Bytef *name; /* pointer to zero-terminated file name or NULL*/ uInt name_max; /* space at name (only when reading header) */ - Bytef *comment; /* pointer to zero-terminated comment or Z_NULL */ + Bytef *comment; /* pointer to zero-terminated comment or NULL */ uInt comm_max; /* space at comment (only when reading header) */ int hcrc; /* true if there was or will be a header crc */ int done; /* true when done reading gzip header (not used @@ -2631,7 +3498,7 @@ value. .Pp .Fa zalloc must return -.Dv Z_NULL +.Dv NULL if there is not enough memory for the object. If .Nm zlib @@ -2640,6 +3507,20 @@ is used in a multi-threaded application, and .Fa zfree must be thread safe. +In that case, +.Nm zlib +is thread-safe. +When +.Fa zalloc +and +.Fa zfree +are +.Dv NULL +on entry to the initialization function, +they are set to internal routines that use the standard library functions +.Xr malloc 3 +and +.Xr free 3 . .Pp On 16-bit systems, the functions .Fa zalloc @@ -2674,11 +3555,12 @@ in a single step). .Sh CONSTANTS .Bd -unfilled #define Z_NO_FLUSH 0 -#define Z_PARTIAL_FLUSH 1 /* will be removed, use Z_SYNC_FLUSH instead */ +#define Z_PARTIAL_FLUSH 1 #define Z_SYNC_FLUSH 2 #define Z_FULL_FLUSH 3 #define Z_FINISH 4 -#define Z_BLOCK 5 +#define Z_BLOCK 5 +#define Z_TREES 6 /* Allowed flush values; see deflate() and inflate() below for details */ #define Z_OK 0 @@ -2712,7 +3594,7 @@ in a single step). #define Z_TEXT 1 #define Z_ASCII Z_TEXT /* for compatibility with 1.2.2 and earlier */ #define Z_UNKNOWN 2 -/* Possible values of the data_type field (though see inflate()) */ +/* Possible values of the data_type field for deflate() */ #define Z_DEFLATED 8 /* The deflate compression method @@ -2749,7 +3631,7 @@ version and the compiler's view of .Fa "int strategy" .Fa "const char *version" .Fa "int stream_size" -.Fc +.Fc ; .Xc .It Xo .Fa int @@ -2757,7 +3639,7 @@ version and the compiler's view of .Xc .It Xo .Fa int -.Fn inflateBackInit_ "z_stream *strm" "int windowBits" "unsigned char FAR *window" "const char *version" "int stream_size" +.Fn inflateBackInit_ "z_stream *strm" "int windowBits" "unsigned char FAR *window" "const char *version" "int stream_size" ; .Xc .It Xo .Fa const char * diff --git a/lib/libz/compress.c b/lib/libz/compress.c index f501874..ba5e377 100644 --- a/lib/libz/compress.c +++ b/lib/libz/compress.c @@ -1,10 +1,9 @@ -/* $OpenBSD: compress.c,v 1.6 2005/07/20 15:56:41 millert Exp $ */ +/* $OpenBSD: compress.c,v 1.7 2021/07/04 14:24:49 tb Exp $ */ /* compress.c -- compress a memory buffer - * Copyright (C) 1995-2003 Jean-loup Gailly. + * Copyright (C) 1995-2005, 2014, 2016 Jean-loup Gailly, Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ - #define ZLIB_INTERNAL #include "zlib.h" @@ -28,16 +27,11 @@ int ZEXPORT compress2 (dest, destLen, source, sourceLen, level) { z_stream stream; int err; + const uInt max = (uInt)-1; + uLong left; - stream.next_in = (Bytef*)source; - stream.avail_in = (uInt)sourceLen; -#ifdef MAXSEG_64K - /* Check for source > 64K on 16-bit machine: */ - if ((uLong)stream.avail_in != sourceLen) return Z_BUF_ERROR; -#endif - stream.next_out = dest; - stream.avail_out = (uInt)*destLen; - if ((uLong)stream.avail_out != *destLen) return Z_BUF_ERROR; + left = *destLen; + *destLen = 0; stream.zalloc = (alloc_func)0; stream.zfree = (free_func)0; @@ -46,15 +40,26 @@ int ZEXPORT compress2 (dest, destLen, source, sourceLen, level) err = deflateInit(&stream, level); if (err != Z_OK) return err; - err = deflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) { - deflateEnd(&stream); - return err == Z_OK ? Z_BUF_ERROR : err; - } - *destLen = stream.total_out; + stream.next_out = dest; + stream.avail_out = 0; + stream.next_in = (z_const Bytef *)source; + stream.avail_in = 0; + + do { + if (stream.avail_out == 0) { + stream.avail_out = left > (uLong)max ? max : (uInt)left; + left -= stream.avail_out; + } + if (stream.avail_in == 0) { + stream.avail_in = sourceLen > (uLong)max ? max : (uInt)sourceLen; + sourceLen -= stream.avail_in; + } + err = deflate(&stream, sourceLen ? Z_NO_FLUSH : Z_FINISH); + } while (err == Z_OK); - err = deflateEnd(&stream); - return err; + *destLen = stream.total_out; + deflateEnd(&stream); + return err == Z_STREAM_END ? Z_OK : err; } /* =========================================================================== @@ -75,5 +80,6 @@ int ZEXPORT compress (dest, destLen, source, sourceLen) uLong ZEXPORT compressBound (sourceLen) uLong sourceLen; { - return sourceLen + (sourceLen >> 12) + (sourceLen >> 14) + 11; + return sourceLen + (sourceLen >> 12) + (sourceLen >> 14) + + (sourceLen >> 25) + 13; } diff --git a/lib/libz/compress.cat3 b/lib/libz/compress.cat3 index bcd9add..02bb9c9 100644 --- a/lib/libz/compress.cat3 +++ b/lib/libz/compress.cat3 @@ -2,16 +2,19 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mNAME[0m [1mcompress[22m, [1mzlibVersion[22m, [1mdeflateInit[22m, [1mdeflate[22m, [1mdeflateEnd[22m, [1minflateInit[22m, - [1minflate[22m, [1minflateEnd[22m, [1mdeflateInit2[22m, [1mdeflateSetDictionary[22m, [1mdeflateCopy[22m, - [1mdeflateReset[22m, [1mdeflateParams[22m, [1mdeflateTune[22m, [1mdeflateBound[22m, [1mdeflatePrime[22m, - [1mdeflateSetHeader[22m, [1minflateInit2[22m, [1minflateSetDictionary[22m, [1minflateSync[22m, - [1minflateCopy[22m, [1minflateReset[22m, [1minflatePrime[22m, [1minflateGetHeader[22m, + [1minflate[22m, [1minflateEnd[22m, [1mdeflateInit2[22m, [1mdeflateSetDictionary[22m, + [1mdeflateGetDictionary[22m, [1mdeflateCopy[22m, [1mdeflateReset[22m, [1mdeflateParams[22m, + [1mdeflateTune[22m, [1mdeflateBound[22m, [1mdeflatePending[22m, [1mdeflatePrime[22m, + [1mdeflateSetHeader[22m, [1minflateInit2[22m, [1minflateSetDictionary[22m, + [1minflateGetDictionary[22m, [1minflateSync[22m, [1minflateCopy[22m, [1minflateReset[22m, + [1minflateReset2[22m, [1minflatePrime[22m, [1minflateMark[22m, [1minflateGetHeader[22m, [1minflateBackInit[22m, [1minflateBack[22m, [1minflateBackEnd[22m, [1mzlibCompileFlags[22m, - [1mcompress2[22m, [1mcompressBound[22m, [1muncompress[22m, [1mgzopen[22m, [1mgzdopen[22m, [1mgzsetparams[22m, - [1mgzread[22m, [1mgzwrite[22m, [1mgzprintf[22m, [1mgzputs[22m, [1mgzgets[22m, [1mgzputc[22m, [1mgzgetc[22m, [1mgzungetc[22m, - [1mgzflush[22m, [1mgzseek[22m, [1mgzrewind[22m, [1mgztell[22m, [1mgzeof[22m, [1mgzdirect[22m, [1mgzclose[22m, [1mgzerror[22m, - [1mgzclearerr[22m, [1madler32[22m, [1madler32_combine[22m, [1mcrc32[22m, [1mcrc32_combine [22m-- zlib gen- - eral purpose compression library + [1mcompress2[22m, [1mcompressBound[22m, [1muncompress[22m, [1muncompress2[22m, [1mgzopen[22m, [1mgzdopen[22m, + [1mgzbuffer[22m, [1mgzsetparams[22m, [1mgzread[22m, [1mgzfread[22m, [1mgzwrite[22m, [1mgzfwrite[22m, [1mgzprintf[22m, + [1mgzputs[22m, [1mgzgets[22m, [1mgzputc[22m, [1mgzgetc[22m, [1mgzungetc[22m, [1mgzflush[22m, [1mgzseek[22m, [1mgzrewind[22m, + [1mgztell[22m, [1mgzoffset[22m, [1mgzeof[22m, [1mgzdirect[22m, [1mgzclose[22m, [1mgzclose_r[22m, [1mgzclose_w[22m, + [1mgzerror[22m, [1mgzclearerr[22m, [1madler32[22m, [1madler32_z[22m, [1madler32_combine[22m, [1mcrc32[22m, [1mcrc32_z[22m, + [1mcrc32_combine [22m— zlib general purpose compression library [1mSYNOPSIS[0m [1m#include <zlib.h>[0m @@ -50,6 +53,10 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4muInt[24m [4mdictLength[24m); [4mint[0m + [1mdeflateGetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mBytef[24m [4m*dictionary[24m, + [4muInt[24m [4m*dictLength[24m); + + [4mint[0m [1mdeflateCopy[22m([4mz_streamp[24m [4mdest[24m, [4mz_streamp[24m [4msource[24m); [4mint[0m @@ -66,6 +73,9 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mdeflateBound[22m([4mz_streamp[24m [4mstrm[24m, [4muLong[24m [4msourceLen[24m); [4mint[0m + [1mdeflatePending[22m([4mz_streamp[24m [4mstrm[24m, [4munsigned[24m [4m*pending[24m, [4mint[24m [4m*bits[24m); + + [4mint[0m [1mdeflatePrime[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m); [4mint[0m @@ -79,6 +89,10 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4muInt[24m [4mdictLength[24m); [4mint[0m + [1minflateGetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mBytef[24m [4m*dictionary[24m, + [4muInt[24m [4m*dictLength[24m); + + [4mint[0m [1minflateSync[22m([4mz_streamp[24m [4mstrm[24m); [4mint[0m @@ -88,9 +102,15 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1minflateReset[22m([4mz_streamp[24m [4mstrm[24m); [4mint[0m + [1minflateReset2[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mwindowBits[24m); + + [4mint[0m [1minflatePrime[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m); [4mint[0m + [1minflateMark[22m([4mz_streamp[24m [4mstrm[24m); + + [4mint[0m [1minflateGetHeader[22m([4mz_streamp[24m [4mstrm[24m, [4mgz_headerp[24m [4mhead[24m); [4mint[0m @@ -126,6 +146,10 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1muncompress[22m([4mBytef[24m [4m*dest[24m, [4muLongf[24m [4m*destLen[24m, [4mconst[24m [4mBytef[24m [4m*source[24m, [4muLong[24m [4msourceLen[24m); + [4mint[0m + [1muncompress2[22m([4mBytef[24m [4m*dest[24m, [4muLongf[24m [4m*destLen[24m, [4mconst[24m [4mBytef[24m [4m*source[24m, + [4muLong[24m [4m*sourceLen[24m); + [4mgzFile[0m [1mgzopen[22m([4mconst[24m [4mchar[24m [4m*path[24m, [4mconst[24m [4mchar[24m [4m*mode[24m); @@ -133,15 +157,24 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mgzdopen[22m([4mint[24m [4mfd[24m, [4mconst[24m [4mchar[24m [4m*mode[24m); [4mint[0m + [1mgzbuffer[22m([4mgzFile[24m [4mfile[24m, [4munsigned[24m [4msize[24m); + + [4mint[0m [1mgzsetparams[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4mlevel[24m, [4mint[24m [4mstrategy[24m); [4mint[0m [1mgzread[22m([4mgzFile[24m [4mfile[24m, [4mvoidp[24m [4mbuf[24m, [4munsigned[24m [4mlen[24m); [4mint[0m + [1mgzfread[22m([4mvoidp[24m [4mbuf[24m, [4mz_size_t[24m [4msize[24m, [4mz_size_t[24m [4mnitems[24m, [4mgzFile[24m [4mfile[24m); + + [4mint[0m [1mgzwrite[22m([4mgzFile[24m [4mfile[24m, [4mvoidpc[24m [4mbuf[24m, [4munsigned[24m [4mlen[24m); [4mint[0m + [1mgzfwrite[22m([4mvoidpc[24m [4mbuf[24m, [4mz_size_t[24m [4msize[24m, [4mz_size_t[24m [4mnitems[24m, [4mgzFile[24m [4mfile[24m); + + [4mint[0m [1mgzprintf[22m([4mgzFile[24m [4mfile[24m, [4mconst[24m [4mchar[24m [4m*format[24m, [4m...[24m); [4mint[0m @@ -172,6 +205,9 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mgztell[22m([4mgzFile[24m [4mfile[24m); [4mint[0m + [1mgzoffset[22m([4mgzFile[24m [4mfile[24m); + + [4mint[0m [1mgzeof[22m([4mgzFile[24m [4mfile[24m); [4mint[0m @@ -180,6 +216,12 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mint[0m [1mgzclose[22m([4mgzFile[24m [4mfile[24m); + [4mint[0m + [1mgzclose_r[22m([4mgzFile[24m [4mfile[24m); + + [4mint[0m + [1mgzclose_w[22m([4mgzFile[24m [4mfile[24m); + [4mconst[24m [4mchar[24m [4m*[0m [1mgzerror[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4m*errnum[24m); @@ -192,40 +234,45 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1madler32[22m([4muLong[24m [4madler[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4muInt[24m [4mlen[24m); [4muLong[0m + [1madler32_z[22m([4muLong[24m [4madler[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4mz_size_t[24m [4mlen[24m); + + [4muLong[0m [1madler32_combine[22m([4muLong[24m [4madler1[24m, [4muLong[24m [4madler2[24m, [4mz_off_t[24m [4mlen2[24m); [4muLong[0m [1mcrc32[22m([4muLong[24m [4mcrc[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4muInt[24m [4mlen[24m); [4muLong[0m + [1mcrc32_z[22m([4muLong[24m [4madler[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4mz_size_t[24m [4mlen[24m); + + [4muLong[0m [1mcrc32_combine[22m([4muLong[24m [4mcrc1[24m, [4muLong[24m [4mcrc2[24m, [4mz_off_t[24m [4mlen2[24m); [1mDESCRIPTION[0m This manual page describes the [1mzlib [22mgeneral purpose compression library, - version 1.2.3. + version 1.2.11. - The [1mzlib [22mcompression library provides in-memory compression and decom- + The [1mzlib [22mcompression library provides in-memory compression and decom†pression functions, including integrity checks of the uncompressed data. This version of the library supports only one compression method (deflation) but other algorithms will be added later and will have the same stream interface. Compression can be done in a single step if the buffers are large enough - (for example if an input file is mmap'ed), or can be done by repeated - calls of the compression function. In the latter case, the application - must provide more input and/or consume the output (providing more output - space) before each call. + or can be done by repeated calls of the compression function. In the + latter case, the application must provide more input and/or consume the + output (providing more output space) before each call. The compressed data format used by default by the in-memory functions is the [1mzlib [22mformat, which is a zlib wrapper documented in RFC 1950, wrapped around a deflate stream, which is itself documented in RFC 1951. - The library also supports reading and writing files in gzip(1) (.gz) for- + The library also supports reading and writing files in gzip(1) (.gz) for†mat with an interface similar to that of stdio(3) using the functions that start with "gz". The gzip format is different from the zlib format. gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate - stream. This library can optionally read and write gzip streams in mem- - ory as well. + stream. This library can optionally read and write gzip and raw deflate + streams in memory as well. The zlib format was designed to be compact and fast for use in memory and on communications channels. The gzip format was designed for single-file @@ -235,7 +282,7 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The library does not install any signal handler. The decoder checks the consistency of the compressed data, so the library should never crash - even in case of corrupted input. + even in the case of corrupted input. The functions within the library are divided into the following sections: @@ -258,8 +305,8 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [1mdeflateInit[22m() function initializes the internal stream state for compression. The fields [4mzalloc[24m, [4mzfree[24m, and [4mopaque[24m must be initialized before by the caller. If [4mzalloc[24m and [4mzfree[24m are set to - Z_NULL, [1mdeflateInit[22m() updates them to use default allocation - functions. + NULL, [1mdeflateInit[22m() updates them to use default allocation func†+ tions. The compression level must be Z_DEFAULT_COMPRESSION, or between 0 and 9: 1 gives best speed, 9 gives best compression, 0 gives no @@ -293,12 +340,11 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mavail_in[24m are updated and processing will resume at this point for the next call to [1mdeflate[22m(). - Provide more output starting at [4mnext_out[24m and update [4mnext_out[24m and + Generate more output starting at [4mnext_out[24m and update [4mnext_out[24m and [4mavail_out[24m accordingly. This action is forced if the parameter - [4mflush[24m is non-zero. Forcing [4mflush[24m frequently degrades the com- - pression ratio, so this parameter should be set only when neces- - sary (in interactive applications). Some output may be provided - even if [4mflush[24m is not set. + [4mflush[24m is non-zero. Forcing [4mflush[24m frequently degrades the com†+ pression ratio, so this parameter should be set only when neces†+ sary. Some output may be provided even if [4mflush[24m is not set. Before the call to [1mdeflate[22m(), the application should ensure that at least one of the actions is possible, by providing more input @@ -307,8 +353,10 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) application can consume the compressed output when it wants, for example when the output buffer is full (avail_out == 0), or after each call to [1mdeflate[22m(). If [1mdeflate[22m() returns Z_OK and with zero - [4mavail_out[24m, it must be called again after making room in the out- - put buffer because there might be more output pending. + [4mavail_out[24m, it must be called again after making room in the out†+ put buffer because there might be more output pending. See + [1mdeflatePending[22m(), which can be used if desired to determine + whether or not there is more output in that case. Normally the parameter [4mflush[24m is set to Z_NO_FLUSH, which allows [1mdeflate[22m() to decide how much data to accumulate before producing @@ -317,13 +365,35 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) If the parameter [4mflush[24m is set to Z_SYNC_FLUSH, all pending output is flushed to the output buffer and the output is aligned on a byte boundary, so that the decompressor can get all input data - available so far. (In particular, [4mavail_in[24m is zero after the - call if enough output space has been provided before the call.) + available so far. (In particular [4mavail_in[24m is zero after the call + if enough output space has been provided before the call.) Flushing may degrade compression for some compression algorithms - and so it should be used only when necessary. + and so it should be used only when necessary. This completes the + current deflate block and follows it with an empty stored block + that is three bits plus filler bits to the next byte, followed by + four bytes (00 00 ff ff). + + If [4mflush[24m is set to Z_PARTIAL_FLUSH, all pending output is flushed + to the output buffer, but the output is not aligned to a byte + boundary. All of the input data so far will be available to the + decompressor, as for Z_SYNC_FLUSH. This completes the current + deflate block and follows it with an empty fixed code block that + is 10 bits long. This assures that enough bytes are output in + order for the decompressor to finish the block before the empty + fixed codes block. + + If [4mflush[24m is set to Z_BLOCK, a deflate block is completed and + emitted, as for Z_SYNC_FLUSH, but the output is not aligned on a + byte boundary, and up to seven bits of the current block are held + to be written as the next byte after the next deflate block is + completed. In this case, the decompressor may not be provided + enough bits at this point in order to complete decompression of + the data provided so far to the compressor. It may need to wait + for the next block to be emitted. This is for advanced applica†+ tions that need to control the emission of deflate blocks. If [4mflush[24m is set to Z_FULL_FLUSH, all output is flushed as with - Z_SYNC_FLUSH, and the compression state is reset so that decom- + Z_SYNC_FLUSH, and the compression state is reset so that decom†pression can restart from this point if previous compressed data has been damaged or if random access is desired. Using Z_FULL_FLUSH too often can seriously degrade compression. @@ -336,23 +406,27 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) greater than six to avoid repeated flush markers due to avail_out == 0 on return. - If the parameter [4mflush[24m is set to Z_FINISH, pending input is pro- + If the parameter [4mflush[24m is set to Z_FINISH, pending input is pro†cessed, pending output is flushed and [1mdeflate[22m() returns with - Z_STREAM_END if there was enough output space; if [1mdeflate[22m() re- - turns with Z_OK, this function must be called again with Z_FINISH - and more output space (updated [4mavail_out[24m but no more input data, - until it returns with Z_STREAM_END or an error. After [1mdeflate[22m() - has returned Z_STREAM_END, the only possible operations on the - stream are [1mdeflateReset[22m() or [1mdeflateEnd[22m(). - - Z_FINISH can be used immediately after [1mdeflateInit[22m() if all the - compression is to be done in a single step. In this case, - [4mavail_out[24m must be at least the value returned by [1mdeflateBound[22m() - (see below). If [1mdeflate[22m() does not return Z_STREAM_END, then it - must be called again as described above. + Z_STREAM_END if there was enough output space. If [1mdeflate[22m() re†+ turns with Z_OK or Z_BUF_ERROR, this function must be called + again with Z_FINISH and more output space (updated [4mavail_out[24m but + no more input data, until it returns with Z_STREAM_END or an er†+ ror. After [1mdeflate[22m() has returned Z_STREAM_END, the only possi†+ ble operations on the stream are [1mdeflateReset[22m() or [1mdeflateEnd[22m(). + + Z_FINISH can be used in the first deflate call after + [1mdeflateInit[22m() if all the compression is to be done in a single + step. In order to complete in one call, [4mavail_out[24m must be at + least the value returned by [1mdeflateBound[22m() (see below). Then + [1mdeflate[22m() is guaranteed to return Z_STREAM_END. If not enough + output space is provided, [1mdeflate[22m() will not return Z_STREAM_END, + and it must be called again as described above. [1mdeflate[22m() sets strm->adler to the Adler-32 checksum of all input - read so far (that is, [4mtotal_in[24m bytes). + read so far (that is, [4mtotal_in[24m bytes). If a gzip stream is being + generated, then strm->adler will be the CRC-32 checksum of the + input read so far. (See [1mdeflateInit2[22m() below.) [1mdeflate[22m() may update strm->data_type if it can make a good guess about the input data type (Z_BINARY or Z_TEXT). If in doubt, the @@ -363,12 +437,13 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mdeflate[22m() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if all input has been consumed and all output has been produced (only when [4mflush[0m - is set to Z_FINISH), Z_STREAM_ERROR if the stream state was in- - consistent (for example, if [4mnext_in[24m or [4mnext_out[24m was NULL), + is set to Z_FINISH), Z_STREAM_ERROR if the stream state was in†+ consistent (for example, if [4mnext_in[24m or [4mnext_out[24m was NULL or the + state was inadvertently written over by the application), or Z_BUF_ERROR if no progress is possible (for example, [4mavail_in[24m or [4mavail_out[24m was zero). Note that Z_BUF_ERROR is not fatal, and [1mdeflate[22m() can be called again with more input and more output - space to continue processing. + space to continue compressing. [4mint[24m [1mdeflateEnd[22m([4mz_streamp[24m [4mstrm[24m); @@ -385,23 +460,23 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mint[24m [1minflateInit[22m([4mz_streamp[24m [4mstrm[24m); The [1minflateInit[22m() function initializes the internal stream state for decompression. The fields [4mnext_in[24m, [4mavail_in[24m, [4mzalloc[24m, [4mzfree[24m, - and [4mopaque[24m must be initialized before by the caller. If [4mnext_in[0m - is not Z_NULL and [4mavail_in[24m is large enough (the exact value - depends on the compression method), [1minflateInit[22m() determines the - compression method from the [1mzlib [22mheader and allocates all data - structures accordingly; otherwise the allocation will be deferred - to the first call to [1minflate[22m(). If [4mzalloc[24m and [4mzfree[24m are set to - Z_NULL, [1minflateInit[22m() updates them to use default allocation - functions. + and [4mopaque[24m must be initialized before by the caller. In the cur†+ rent version of [1minflate[22m(), the provided input is not read or con†+ sumed. The allocation of a sliding window will be deferred to + the first call of [1minflate[22m() (if the decompression does not com†+ plete on the first call). If [4mzalloc[24m and [4mzfree[24m are set to NULL, + [1minflateInit[22m() updates them to use default allocation functions. [1minflateInit[22m() returns Z_OK if successful, Z_MEM_ERROR if there - was not enough memory, Z_VERSION_ERROR if the [1mzlib [22mlibrary ver- - sion is incompatible with the version assumed by the caller. [4mmsg[0m - is set to null if there is no error message. [1minflateInit[22m() does - not perform any decompression apart from reading the [1mzlib [22mheader - if present: this will be done by [1minflate[22m(). (So [4mnext_in[24m and - [4mavail_in[24m may be modified, but [4mnext_out[24m and [4mavail_out[24m are un- - changed.) + was not enough memory, Z_VERSION_ERROR if the [1mzlib [22mlibrary ver†+ sion is incompatible with the version assumed by the caller or + Z_STREAM_ERROR if the parameters are invalid, such as a null + pointer to the structure. [4mmsg[24m is set to null if there is no er†+ ror message. [1minflateInit[22m() does not perform any decompression. + Actual decompression will be done by [1minflate[22m(). So [4mnext_in[24m, + [4mavail_in[24m, [4mnext_out[24m, and [4mavail_out[24m are unused and unchanged. The + current implementation of [1minflateInit[22m() does not process any + header information — that is deferred until [1minflate[22m() is called. [4mint[24m [1minflate[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mflush[24m); [1minflate[22m() decompresses as much data as possible, and stops when @@ -414,66 +489,87 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) Decompress more input starting at [4mnext_in[24m and update [4mnext_in[24m and [4mavail_in[24m accordingly. If not all input can be processed (because - there is not enough room in the output buffer), [4mnext_in[24m is up- - dated and processing will resume at this point for the next call - to [1minflate[22m(). + there is not enough room in the output buffer), then [4mnext_in[24m and + [4mavail_in[24m are updated accordingly, and processing will resume at + this point for the next call to [1minflate[22m(). - Provide more output starting at [4mnext_out[24m and update [4mnext_out[24m and - [4mavail_out[24m accordingly. [1minflate[22m() provides as much output as pos- + Generate more output starting at [4mnext_out[24m and update [4mnext_out[24m and + [4mavail_out[24m accordingly. [1minflate[22m() provides as much output as pos†sible, until there is no more input data or no more space in the output buffer (see below about the flush parameter). Before the call to [1minflate[22m(), the application should ensure that at least one of the actions is possible, by providing more input and/or consuming more output, and updating the next_* and avail_* - values accordingly. The application can consume the uncompressed - output when it wants, for example when the output buffer is full - (avail_out == 0), or after each call to [1minflate[22m(). If [1minflate[22m() - returns Z_OK and with zero [4mavail_out[24m, it must be called again af- - ter making room in the output buffer because there might be more - output pending. + values accordingly. If the caller of [1minflate[22m() does not provide + both available input and available output space, it is possible + that there will be no progress made. The application can consume + the uncompressed output when it wants, for example when the out†+ put buffer is full (avail_out == 0), or after each call to + [1minflate[22m(). If [1minflate[22m() returns Z_OK and with zero [4mavail_out[24m, it + must be called again after making room in the output buffer be†+ cause there might be more output pending. The [4mflush[24m parameter of [1minflate[22m() can be Z_NO_FLUSH, Z_SYNC_FLUSH, - Z_FINISH, or Z_BLOCK. Z_SYNC_FLUSH requests that [1minflate[22m() flush - as much output as possible to the output buffer. Z_BLOCK re- - quests that [1minflate[22m() stop if and when it gets to the next de- - flate block boundary. When decoding the zlib or gzip format, - this will cause [1minflate[22m() to return immediately after the header - and before the first block. When doing a raw inflate, [1minflate[22m() - 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. + Z_FINISH, Z_BLOCK or Z_TREES. Z_SYNC_FLUSH requests that + [1minflate[22m() flush as much output as possible to the output buffer. + Z_BLOCK requests that [1minflate[22m() stop if and when it gets to the + next deflate block boundary. When decoding the zlib or gzip for†+ mat, this will cause [1minflate[22m() to return immediately after the + header and before the first block. When doing a raw inflate, + [1minflate[22m() will go ahead and process the first block, and will re†+ turn 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 [1minflate[22m() will set + streams. To assist in this, on return [1minflate[22m() always sets strm->data_type to the number of unused bits in the last byte - taken from strm->next_in, plus 64 if [1minflate[22m() is currently de- + taken from strm->next_in, plus 64 if [1minflate[22m() is currently de†coding the last block in the deflate stream, plus 128 if [1minflate[22m() returned immediately after decoding an end-of-block code or decoding the complete header up to just before the first - byte of the deflate stream. The end-of-block will not be indi- + byte of the deflate stream. The end-of-block will not be indi†cated until all of the uncompressed data from that block has been - written to strm->next_out. The number of unused bits may in gen- + written to strm->next_out. The number of unused bits may in gen†eral be greater than seven, except when bit 7 of data_type is set, in which case the number of unused bits will be less than - eight. + eight. [4mdata_type[24m is set as noted here every time [1minflate[22m() re†+ turns for all flush options, and so can be used to determine the + amount of currently consumed input in bits. + + The Z_TREES option behaves as Z_BLOCK does, but it also returns + when the end of each deflate block header is reached, before any + actual data in that block is decoded. This allows the caller to + determine the length of the deflate block header for later use in + random access within a deflate block. 256 is added to the value + of strm->data_type when [1minflate[22m() returns immediately after + reaching the end of the deflate block header. [1minflate[22m() should normally be called until it returns Z_STREAM_END or an error. However if all decompression is to be performed in a single step (a single call to inflate), the parameter [4mflush[0m should be set to Z_FINISH. In this case all pending input is processed and all pending output is flushed; [4mavail_out[24m must be - large enough to hold all the uncompressed data. (The size of the - uncompressed data may have been saved by the compressor for this - purpose.) The next operation on this stream must be [1minflateEnd[22m() - to deallocate the decompression state. The use of Z_FINISH is - never required, but can be used to inform [1minflate[22m() that a faster - approach may be used for the single [1minflate[22m() call. + large enough to hold all the uncompressed data for the operation + to complete. (The size of the uncompressed data may have been + saved by the compressor for this purpose.) The use of Z_FINISH + is not required to perform an inflation in one step. However it + may be used to inform [1minflate[22m() that a faster approach can be + used for the single [1minflate[22m() call. Z_FINISH also informs + [1minflate[22m() to not maintain a sliding window if the stream com†+ pletes, which reduces its memory footprint. If the stream does + not complete, either because not all of the stream is provided or + not enough output space is provided, then a sliding window will + be allocated and [1minflate[22m() can be called again to continue the + operation as if Z_NO_FLUSH had been used. In this implementation, [1minflate[22m() always flushes as much output - as possible to the output buffer, and always uses the faster ap- - proach on the first call. So the only effect of the [4mflush[24m param- - eter in this implementation is on the return value of [1minflate[22m(), - as noted below, or when it returns early because Z_BLOCK is used. + as possible to the output buffer, and always uses the faster ap†+ proach on the first call. So the effects of the flush parameter + in this implementation are on the return value of [1minflate[22m() as + noted below, when [1minflate[22m() returns early when Z_BLOCK or Z_TREES + is used, and when [1minflate[22m() avoids the allocation of memory for a + sliding window when Z_FINISH is used. If a preset dictionary is needed after this call (see [1minflateSetDictionary[22m() below), [1minflate[22m() sets strm->adler to the @@ -483,30 +579,34 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mtotal_out[24m bytes) and returns Z_OK, Z_STREAM_END or an error code as described below. At the end of the stream, [1minflate[22m() checks that its computed Adler-32 checksum is equal to that saved by the - compressor and returns Z_STREAM_END only if the checksum is cor- + compressor and returns Z_STREAM_END only if the checksum is cor†rect. - [1minflate[22m() will decompress and check either zlib-wrapped or gzip- - wrapped deflate data. The header type is detected automatically. - Any information contained in the gzip header is not retained, so - applications that need that information should instead use raw - inflate; see [1minflateInit2[22m() below, or [1minflateBack[22m() and perform - their own processing of the gzip header and trailer. + [1minflate[22m() can decompress and check either zlib-wrapped or gzip- + wrapped deflate data. The header type is detected automatically, + if requested when initializing with [1minflateInit2[22m(). Any informa†+ tion contained in the gzip header is not retained unless + [1minflateGetHeader[22m() is used. When processing gzip-wrapped deflate + data, strm->adler32 is set to the CRC-32 of the output produced + so far. The CRC-32 is checked against the gzip trailer, as is + the uncompressed length, modulo 2^32. [1minflate[22m() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if the end of the compressed data has been reached and all uncompressed output has been produced, Z_NEED_DICT if a preset dictionary is needed - at this point, Z_DATA_ERROR if the input data was corrupted (in- + at this point, Z_DATA_ERROR if the input data was corrupted (in†put stream not conforming to the [1mzlib [22mformat or incorrect check - value), Z_STREAM_ERROR if the stream structure was inconsistent - (for example, if [4mnext_in[24m or [4mnext_out[24m was NULL), Z_MEM_ERROR if - there was not enough memory, Z_BUF_ERROR if no progress is possi- - ble or if there was not enough room in the output buffer when + value, in which case strm->msg points to a string with a more + specific error), Z_STREAM_ERROR if the stream structure was in†+ consistent (for example, [4mnext_in[24m or [4mnext_out[24m was NULL, or the + state was inadvertently over by the application), Z_MEM_ERROR if + there was not enough memory, Z_BUF_ERROR if no progress was pos†+ sible or if there was not enough room in the output buffer when Z_FINISH is used. Note that Z_BUF_ERROR is not fatal, and [1minflate[22m() can be called again with more input and more output space to continue compressing. If Z_DATA_ERROR is returned, the - application may then call [1minflateSync[22m() to look for a good com- + application may then call [1minflateSync[22m() to look for a good com†pression block if a partial recovery of the data is desired. [4mint[24m [1minflateEnd[22m([4mz_streamp[24m [4mstrm[24m); @@ -534,25 +634,39 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [4mwindowBits[24m parameter is the base two logarithm of the window size (the size of the history buffer). It should be in the range - 8..15 for this version of the library. Larger values of this pa- - rameter result in better compression at the expense of memory us- + 8..15 for this version of the library. Larger values of this pa†+ rameter result in better compression at the expense of memory us†age. The default value is 15 if [1mdeflateInit[22m() is used instead. + For the current implementation of [1mdeflate[22m(), a [4mwindowBits[24m value + of 8 (a window size of 256 bytes) is not supported. As a result, + a request for 8 will result in 9 (a 512-byte window). In that + case, providing 8 to [1minflateInit2[22m() will result in an error when + the zlib header with 9 is checked against the initialization of + [1minflate[22m(). The remedy is to not use 8 with [1mdeflateInit2[22m() with + this initialization, or at least in that case use 9 with + [1minflateInit2[22m(). + [4mwindowBits[24m can also be -8..-15 for raw deflate. In this case, - -windowBits determines the window size. [1mdeflate[22m() will then gen- + -windowBits determines the window size. [1mdeflate[22m() will then gen†erate raw deflate data with no zlib header or trailer, and will - not compute an Adler-32 check value. + not compute a check value. - [4mwindowBits[24m can also be greater than 15 for optional gzip encod- + [4mwindowBits[24m can also be greater than 15 for optional gzip encod†ing. Add 16 to [4mwindowBits[24m to write a simple gzip header and trailer around the compressed data instead of a zlib wrapper. - The gzip header will have no file name, no extra data, no com- + The gzip header will have no file name, no extra data, no com†ment, no modification time (set to zero), no header crc, and the - operating system will be set to 255 (unknown). If a gzip stream - is being written, strm->adler is a crc32 instead of an adler32. + operating system will be set to the appropriate value, if the op†+ erating system was determined at compile time. If a gzip stream + is being written, strm->adler is a CRC-32 instead of an Adler-32. + + For raw deflate or gzip encoding, a request for a 256-byte window + is rejected as invalid, since only the zlib header provides a + means of transmitting the window size to the decompressor. - The [4mmemLevel[24m parameter specifies how much memory should be allo- - cated for the internal compression state. memLevel=1 uses mini- + The [4mmemLevel[24m parameter specifies how much memory should be allo†+ cated for the internal compression state. memLevel=1 uses mini†mum memory but is slow and reduces compression ratio; memLevel=9 uses maximum memory for optimal speed. The default value is 8. See <[4mzconf.h[24m> for total memory usage as a function of [4mwindowBits[0m @@ -567,29 +681,36 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) this case, the compression algorithm is tuned to compress them better. The effect of Z_FILTERED is to force more Huffman coding and less string matching; it is somewhat intermediate between - Z_DEFAULT and Z_HUFFMAN_ONLY. Z_RLE is designed to be almost as - fast as Z_HUFFMAN_ONLY, but gives better compression for PNG im- - age data. The [4mstrategy[24m parameter only affects the compression - ratio but not the correctness of the 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 appli- - cations. + Z_DEFAULT_STRATEGY and Z_HUFFMAN_ONLY. Z_RLE is designed to be + almost as fast as Z_HUFFMAN_ONLY, but gives better compression + for PNG image data. The [4mstrategy[24m parameter only affects the com†+ pression ratio but not the correctness of the 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. [1mdeflateInit2[22m() returns Z_OK if successful, Z_MEM_ERROR if there - was not enough memory, Z_STREAM_ERROR if a parameter is invalid - (such as an invalid method). [4mmsg[24m is set to null if there is no - error message. [1mdeflateInit2[22m() does not perform any compression: - this will be done by [1mdeflate[22m(). + was not enough memory, Z_STREAM_ERROR if any parameter is invalid + (such as an invalid method), or Z_VERSION_ERROR if the zlib li†+ brary version (zlib_version) is incompatible with the version as†+ sumed by the caller (ZLIB_VERSION). [4mmsg[24m is set to null if there + is no error message. [1mdeflateInit2[22m() does not perform any com†+ pression: this will be done by [1mdeflate[22m(). [4mint[24m [1mdeflateSetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mconst[24m [4mBytef[24m [4m*dictionary[24m, [4muInt[0m [4mdictLength[24m); - Initializes the compression dictionary from the given byte se- - quence without producing any compressed output. This function - must be called immediately after [1mdeflateInit[22m(), [1mdeflateInit2[22m(), - or [1mdeflateReset[22m(), before any call to [1mdeflate[22m(). The compressor - and decompressor must use exactly the same dictionary (see - [1minflateSetDictionary[22m()). + Initializes the compression dictionary from the given byte se†+ quence without producing any compressed output. When using the + zlib format, this function must be called immediately after + [1mdeflateInit[22m(), deflateInit2 or [1mdeflateReset[22m(), and before any + call of [1mdeflate[22m(). When doing raw deflate, this function must be + called either before any call of [1mdeflate[22m(), or immediately after + the completion of a deflate block, i.e. after all input has been + consumed and all output has been delivered when using any of the + flush options Z_BLOCK, Z_PARTIAL_FLUSH, Z_SYNC_FLUSH, or + Z_FULL_FLUSH. The compressor and decompressor must use exactly + the same dictionary (see [1minflateSetDictionary[22m()). The dictionary should consist of strings (byte sequences) that are likely to be encountered later in the data to be compressed, @@ -602,30 +723,53 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) Depending on the size of the compression data structures selected by [1mdeflateInit[22m() or [1mdeflateInit2[22m(), a part of the dictionary may in effect be discarded, for example if the dictionary is larger - than the window size in [1mdeflate[22m() or [1mdeflate2[22m(). Thus the - strings most likely to be useful should be put at the end of the - dictionary, not at the front. In addition, the current implemen- - tation of [1mdeflate[22m() will use at most the window size minus 262 - bytes of the provided dictionary. + than the window size provided in [1mdeflateInit[22m() or [1mdeflateInit2[22m(). + Thus the strings most likely to be useful should be put at the + end of the dictionary, not at the front. In addition, the cur†+ rent implementation of [1mdeflate[22m() will use at most the window size + minus 262 bytes of the provided dictionary. Upon return of this function, strm->adler is set to the Adler-32 value of the dictionary; the decompressor may later use this - value to determine which dictionary has been used by the compres- + value to determine which dictionary has been used by the compres†sor. (The Adler-32 value applies to the whole dictionary even if - only a subset of the dictionary is actually used by the compres- + only a subset of the dictionary is actually used by the compres†sor.) If a raw deflate was requested, then the Adler-32 value is not computed and strm->adler is not set. [1mdeflateSetDictionary[22m() returns Z_OK if successful, or - Z_STREAM_ERROR if a parameter is invalid (such as NULL - dictionary) or the stream state is inconsistent (for example if - [1mdeflate[22m() has already been called for this stream or if the com- - pression method is bsort). [1mdeflateSetDictionary[22m() does not per- - form any compression: this will be done by [1mdeflate[22m(). + Z_STREAM_ERROR if a parameter is invalid (e.g. dictionary being + NULL) or the stream state is inconsistent (for example if + [1mdeflate[22m() has already been called for this stream or if not at a + block boundary for raw deflate). [1mdeflateSetDictionary[22m() does not + perform any compression: this will be done by [1mdeflate[22m(). + + [4mint[24m [1mdeflateGetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mBytef[24m [4m*dictionary[24m [4muInt[0m + [4m*dictLength[24m); + + Returns the sliding dictionary being maintained by [1mdeflate[22m(). + [4mdictLength[24m is set to the number of bytes in the dictionary, and + that many bytes are copied to [4mdictionary[24m. [4mdictionary[24m must have + enough space, where 32768 bytes is always enough. If + [1mdeflateGetDictionary[22m() is called with dictionary equal to NULL, + then only the dictionary length is returned, and nothing is + copied. Similary, if [4mdictLength[24m is NULL, then it is not set. + + [1mdeflateGetDictionary[22m() may return a length less than the window + size, even when more than the window size in input has been pro†+ vided. It may return up to 258 bytes less in that case, due to + how zlib's implementation of [1mdeflate[22m() manages the sliding window + and lookahead for matches, where matches can be up to 258 bytes + long. If the application needs the last window-size bytes of in†+ put, then that would need to be saved by the application outside + of [1mzlib[22m. + + [1mdeflateGetDictionary[22m() returns Z_OK on success, or Z_STREAM_ERROR + if the stream state is inconsistent. [4mint[24m [1mdeflateCopy[22m([4mz_streamp[24m [4mdest[24m, [4mz_streamp[24m [4msource[24m); - The [1mdeflateCopy[22m() function sets the destination stream as a com- + The [1mdeflateCopy[22m() function sets the destination stream as a com†plete copy of the source stream. This function can be useful when several compression strategies @@ -633,21 +777,20 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) processing the input data with a filter. The streams that will be discarded should then be freed by calling [1mdeflateEnd[22m(). Note that [1mdeflateCopy[22m() duplicates the internal compression state - which can be quite large, so this strategy is slow and can con- + which can be quite large, so this strategy is slow and can con†sume lots of memory. [1mdeflateCopy[22m() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if the source stream state - was inconsistent (such as [4mzalloc[24m being NULL). [4mmsg[24m is left un- + was inconsistent (such as [4mzalloc[24m being NULL). [4mmsg[24m is left un†changed in both source and destination. [4mint[24m [1mdeflateReset[22m([4mz_streamp[24m [4mstrm[24m); This function is equivalent to [1mdeflateEnd[22m() followed by - [1mdeflateInit[22m(), but does not free and reallocate all the internal - compression state. The stream will keep the same compression - level and any other attributes that may have been set by - [1mdeflateInit2[22m(). + [1mdeflateInit[22m(), but does not free and reallocate the internal com†+ pression state. The stream will leave the compression level and + any other attributes that may have been set unchanged. [1mdeflateReset[22m() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent (such as [4mzalloc[24m or [4mstate[0m @@ -657,25 +800,43 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [1mdeflateParams[22m() function dynamically updates the compression level and compression strategy. The interpretation of level and - strategy is as in [1mdeflateInit2[22m(). This can be used to switch be- + strategy is as in [1mdeflateInit2[22m(). This can be used to switch be†tween compression and straight copy of the input data, or to switch to a different kind of input data requiring a different - strategy. If the compression level is changed, the input avail- - able so far is compressed with the old level (and may be - flushed); the new level will take effect only at the next call to - [1mdeflate[22m(). - - Before the call to [1mdeflateParams[22m(), the stream state must be set - as for a call to [1mdeflate[22m(), since the currently available input - may have to be compressed and flushed. In particular, - strm->avail_out must be non-zero. - - [1mdeflateParams[22m() returns Z_OK if successful, Z_STREAM_ERROR if the - source stream state was inconsistent or if a parameter was in- - valid, or Z_BUF_ERROR if strm->avail_out was zero. + strategy. If the compression approach (which is a function of + the level) or the strategy is changed, and if any input has been + consumed in a previous [1mdeflate[22m() call, then the input available + so far is compressed with the old level and strategy using de†+ flate(strm, Z_BLOCK). There are three approaches for the com†+ pression levels 0, 1..3, and 4..9, respectively. The new level + and strategy will take effect at the next call of [1mdeflate[22m(). + + If a deflate(strm, Z_BLOCK) is performed by [1mdeflateParams[22m(), and + it does not have enough output space to complete, then the param†+ eter change will not take effect. In this case, [1mdeflateParams[22m() + can be called again with the same parameters and more output + space to try again. + + In order to assure a change in the parameters on the first try, + the deflate stream should be flushed using [1mdeflate[22m() with Z_BLOCK + or other flush request until [4mstrm.avail_out[24m is not zero, before + calling [1mdeflateParams[22m(). Then no more input data should be pro†+ vided before the [1mdeflateParams[22m() call. If this is done, the old + level and strategy will be applied to the data compressed before + [1mdeflateParams[22m(), and the new level and strategy will be applied + to the the data compressed after [1mdeflateParams[22m(). + + [1mdeflateParams[22m() returns Z_OK on success, Z_STREAM_ERROR if the + source stream state was inconsistent or if a parameter was in†+ valid, or Z_BUF_ERROR if there was not enough output space to + complete the compression of the available input data before a + change in the strategy or approach. Note that in the case of a + Z_BUF_ERROR, the parameters are not changed. A return value of + Z_BUF_ERROR is not fatal, in which case [1mdeflateParams[22m() can be + retried with more output space. [4mint[24m [1mdeflateTune[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mgood_length[24m, [4mint[24m [4mmax_lazy[24m, [4mint[0m - [4mnice_length[24m, [4mint[24m [4mmax_chain[24m) + [4mnice_length[24m, [4mint[24m [4mmax_chain[24m); Fine tune [1mdeflate[22m()'s internal compression parameters. This should only be used by someone who understands the algorithm used @@ -689,29 +850,50 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mdeflateInit2[22m(), and returns Z_OK on success, or Z_STREAM_ERROR for an invalid deflate stream. - [4muLong[24m [1mdeflateBound[22m([4mz_streamp[24m [4mstrm[24m, [4muLong[24m [4msourceLen[24m) + [4muLong[24m [1mdeflateBound[22m([4mz_streamp[24m [4mstrm[24m, [4muLong[24m [4msourceLen[24m); - [1mdeflateBound[22m() returns an upper bound on the compressed size af- + [1mdeflateBound[22m() returns an upper bound on the compressed size af†ter deflation of [4msourceLen[24m bytes. It must be called after - [1mdeflateInit[22m() or [1mdeflateInit2[22m(). This would be used to allocate - an output buffer for deflation in a single pass, and so would be - called before [1mdeflate[22m(). - - [4mint[24m [1mdeflatePrime[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m) + [1mdeflateInit[22m() or [1mdeflateInit2[22m(). and after [1mdeflateSetHeader[22m(), + if used. This would be used to allocate an output buffer for de†+ flation in a single pass, and so would be called before + [1mdeflate[22m(). If that first [1mdeflate[22m() call is provided the + [4msourceLen[24m input bytes, an output buffer allocated to the size re†+ turned by [1mdeflateBound[22m(), and the flush value Z_FINISH, then + [1mdeflate[22m() is guaranteed to return Z_STREAM_END. Note that it is + possible for the compressed size to be larger than the value re†+ turned by [1mdeflateBound[22m() if flush options other than Z_FINISH or + Z_NO_FLUSH are used. + + [4mint[24m [1mdeflatePending[22m([4mz_streamp[24m [4mstrm[24m, [4munsigned[24m [4m*pending[24m, [4mint[24m [4m*bits[24m); + + [1mdeflatePending[22m() returns the number of bytes and bits of output + that have been generated, but not yet provided in the available + output. The bytes not provided would be due to the available + output space having been consumed. The number of bits of output + not provided are between 0 and 7, where they await more bits to + join them in order to fill out a full byte. If [4mpending[24m or [4mbits[0m + are NULL, then those values are not set. + + [1mdeflatePending[22m([4mreturns[24m) Z_OK if success, or Z_STREAM_ERROR if the + source stream state was inconsistent. + + [4mint[24m [1mdeflatePrime[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m); [1mdeflatePrime[22m() inserts [4mbits[24m in the deflate output stream. The intent is that this function is used to start off the deflate - output with the bits leftover from a previous deflate stream when - appending to it. As such, this function can only be used for raw - deflate, and must be used before the first [1mdeflate[22m() call after a - [1mdeflateInit2[22m() or [1mdeflateReset[22m(). [4mbits[24m must be less than or - equal to 16, and that many of the least significant bits of [4mvalue[0m - will be inserted in the output. - - [1mdeflatePrime[22m() returns Z_OK if successful, or Z_STREAM_ERROR if - the source stream state was inconsistent. + output with the bits left over from a previous deflate stream + when appending to it. As such, this function can only be used + for raw deflate, and must be used before the first [1mdeflate[22m() call + after a [1mdeflateInit2[22m() or [1mdeflateReset[22m(). [4mbits[24m must be less than + or equal to 16, and that many of the least significant bits of + [4mvalue[24m will be inserted in the output. + + [1mdeflatePrime[22m() returns Z_OK if successful, Z_BUF_ERROR if there + was not enough room in the internal buffer to insert the bits, or + Z_STREAM_ERROR if the source stream state was inconsistent. - [4mint[24m [1mdeflateSetHeader[22m([4mz_streamp[24m [4mstrm[24m, [4mgz_headerp[24m [4mhead[24m) + [4mint[24m [1mdeflateSetHeader[22m([4mz_streamp[24m [4mstrm[24m, [4mgz_headerp[24m [4mhead[24m); [1mdeflateSetHeader[22m() provides gzip header information for when a gzip stream is requested by [1mdeflateInit2[22m(). [1mdeflateSetHeader[22m() @@ -720,15 +902,15 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) name, and comment information in the provided gz_header structure are written to the gzip header (xflag is ignored - the extra flags are set according to the compression level). The caller - must assure that, if not Z_NULL, [4mname[24m and [4mcomment[24m are terminated - with a zero byte, and that if [4mextra[24m is not Z_NULL, that [4mextra_len[0m + must assure that, if not NULL, [4mname[24m and [4mcomment[24m are terminated + with a zero byte, and that if [4mextra[24m is not NULL, that [4mextra_len[0m bytes are available there. If hcrc is true, a gzip header CRC is included. Note that the current versions of the command-line version of gzip(1) do not support header CRCs, and will report - that it is a "multi-part gzip file" and give up. + that it is a “multi-part gzip file†and give up. If [1mdeflateSetHeader[22m() is not used, the default gzip header has - text false, the time set to zero, and os set to 255, with no ex- + text false, the time set to zero, and os set to 255, with no ex†tra, name, or comment fields. The gzip header is returned to the default state by [1mdeflateReset[22m(). @@ -752,74 +934,106 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) the error code Z_DATA_ERROR instead of trying to allocate a larger window. + [4mwindowBits[24m can also be zero to request that inflate use the win†+ dow size in the zlib header of the compressed stream. + [4mwindowBits[24m can also be -8..-15 for raw inflate. In this case, -windowBits determines the window size. [1minflate[22m() will then process raw deflate data, not looking for a zlib or gzip header, - not generating a check value, and not looking for any check val- + not generating a check value, and not looking for any check val†ues for comparison at the end of the stream. This is for use with other formats that use the deflate compressed data format such as zip. Those formats provide their own check values. If a - custom format is developed using the raw deflate format for com- + custom format is developed using the raw deflate format for com†pressed data, it is recommended that a check value such as an - Adler-32 or a crc32 be applied to the uncompressed data as is + Adler-32 or a CRC-32 be applied to the uncompressed data as is done in the zlib, gzip, and zip formats. For most applications, the zlib format should be used as is. Note that comments above on the use in [1mdeflateInit2[22m() applies to the magnitude of [4mwindowBits[24m. - [4mwindowBits[24m can also be greater than 15 for optional gzip decod- + [4mwindowBits[24m can also be greater than 15 for optional gzip decod†ing. Add 32 to windowBits to enable zlib and gzip decoding with automatic header detection, or add 16 to decode only the gzip format (the zlib format will return a Z_DATA_ERROR). If a gzip - stream is being decoded, strm->adler is a crc32 instead of an - adler32. + stream is being decoded, strm->adler is a CRC-32 instead of an + Adler-32. Unlike the gunzip(1) utility and [1mgzread[22m() (see below), + [1minflate[22m() will not automatically decode concatenated gzip + streams. [1minflate[22m() will return Z_STREAM_END at the end of the + gzip stream. The state would need to be reset to continue decod†+ ing a subsequent gzip stream. [1minflateInit2[22m() returns Z_OK if successful, Z_MEM_ERROR if there - was not enough memory, Z_STREAM_ERROR if a parameter is invalid - (such as a null strm). [4mmsg[24m is set to null if there is no error - message. [1minflateInit2[22m() does not perform any decompression apart - from reading the [1mzlib [22mheader if present: this will be done by - [1minflate[22m(). (So [4mnext_in[24m and [4mavail_in[24m may be modified, but - [4mnext_out[24m and [4mavail_out[24m are unchanged.) + was not enough memory, Z_VERSION_ERROR if the [1mzlib [22mlibrary ver†+ sion is incompatible with the version assumed by the caller, or + Z_STREAM_ERROR if the parameters are invalid, such as a null + pointer to the structure. [4mmsg[24m is set to null if there is no er†+ ror message. [1minflateInit2[22m() does not perform any decompression + apart from possibly reading the zlib header if present: actual + decompression will be done by [1minflate[22m(). (So [4mnext_in[24m and + [4mavail_in[24m may be modified, but [4mnext_out[24m and [4mavail_out[24m are unused + and unchanged.) The current implementation of [1minflateInit2[22m() + does not process any header information — that is deferred until + [1minflate[22m() is called. [4mint[24m [1minflateSetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mconst[24m [4mBytef[24m [4m*dictionary[24m, [4muInt[0m [4mdictLength[24m); - Initializes the decompression dictionary from the given uncom- + Initializes the decompression dictionary from the given uncom†pressed byte sequence. This function must be called immediately after a call to [1minflate[22m() if that call returned Z_NEED_DICT. The dictionary chosen by the compressor can be determined from the - Adler-32 value returned by that call to [1minflate[22m(). The compres- + Adler-32 value returned by that call to [1minflate[22m(). The compres†sor and decompressor must use exactly the same dictionary (see [1mdeflateSetDictionary[22m()). For raw inflate, this function can be - called immediately after [1minflateInit2[22m() or [1minflateReset[22m() and be- - fore any call to [1minflate[22m() to set the dictionary. The applica- - tion must ensure that the dictionary that was used for compres- - sion is provided. + called at any time to set the dictionary. If the provided dic†+ tionary is smaller than the window and there is already data in + the window, then the provided dictionary will amend what's there. + The application must ensure that the dictionary that was used for + compression is provided. [1minflateSetDictionary[22m() returns Z_OK if successful, Z_STREAM_ERROR - if a parameter is invalid (such as NULL dictionary) or the stream - state is inconsistent, Z_DATA_ERROR if the given dictionary - doesn't match the expected one (incorrect Adler-32 value). + if a parameter is invalid (e.g. dictionary being NULL) or the + stream state is inconsistent, Z_DATA_ERROR if the given dictio†+ nary doesn't match the expected one (incorrect Adler-32 value). [1minflateSetDictionary[22m() does not perform any decompression: this will be done by subsequent calls of [1minflate[22m(). + [4mint[24m [1minflateGetDictionary[22m([4mz_streamp[24m [4mstrm[24m, [4mBytef[24m [4m*dictionary[24m, [4muInt[0m + [4m*dictLength[24m); + + Returns the sliding dictionary being maintained by [1minflate[22m(). + [4mdictLength[24m is set to the number of bytes in the dictionary, and + that many bytes are copied to [4mdictionary[24m. [4mdictionary[24m must have + enough space, where 32768 bytes is always enough. If + [1minflateGetDictionary[22m() is called with dictionary equal to NULL, + then only the dictionary length is returned, and nothing is + copied. Similary, if [4mdictLength[24m [4mis[24m NULL, then it is not set. + + [1minflateGetDictionary[22m() returns Z_OK on success, or Z_STREAM_ERROR + if the stream state is inconsistent. + [4mint[24m [1minflateSync[22m([4mz_streamp[24m [4mstrm[24m); - Skips invalid compressed data until a full flush point (see above - the description of [1mdeflate[22m() with Z_FULL_FLUSH) can be found, or - until all available input is skipped. No output is provided. + Skips invalid compressed data until a possible full flush point + (see above the description of [1mdeflate[22m() with Z_FULL_FLUSH) can be + found, or until all available input is skipped. No output is + provided. + + [1minflateSync[22m() searches for a 00 00 FF FF pattern in the com†+ pressed data. All full flush points have this pattern, but not + all occurrences of this pattern are full flush points. - [1minflateSync[22m() returns Z_OK if a full flush point has been found, - Z_BUF_ERROR if no more input was provided, Z_DATA_ERROR if no - flush point has been found, or Z_STREAM_ERROR if the stream - structure was inconsistent. In the success case, the application - may save the current value of [4mtotal_in[24m which indicates where - valid compressed data was found. In the error case, the applica- - tion may repeatedly call [1minflateSync[22m(), providing more input each - time, until success or end of the input data. + [1minflateSync[22m() returns Z_OK if a possible full flush point has + been found, Z_BUF_ERROR if no more input was provided, + Z_DATA_ERROR if no flush point has been found, or Z_STREAM_ERROR + if the stream structure was inconsistent. In the success case, + the application may save the current value of [4mtotal_in[24m which in†+ dicates where valid compressed data was found. In the error + case, the application may repeatedly call [1minflateSync[22m(), provid†+ ing more input each time, until success or end of the input data. - [4mint[24m [1minflateCopy[22m([4mz_streamp[24m [4mdest[24m, [4mz_streamp[24m [4msource[24m) + [4mint[24m [1minflateCopy[22m([4mz_streamp[24m [4mdest[24m, [4mz_streamp[24m [4msource[24m); Sets the destination stream as a complete copy of the source stream. @@ -837,17 +1051,30 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mint[24m [1minflateReset[22m([4mz_streamp[24m [4mstrm[24m); This function is equivalent to [1minflateEnd[22m() followed by - [1minflateInit[22m(), but does not free and reallocate all the internal - decompression state. The stream will keep attributes that may - have been set by [1minflateInit2[22m(). + [1minflateInit[22m(), but does not free and reallocate the internal de†+ compression state. The stream will keep attributes that may have + been set by [1minflateInit2[22m(). [1minflateReset[22m() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent (such as [4mzalloc[24m or [4mstate[0m being NULL). - [4mint[24m [1minflatePrime[22m([4mz_stream[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m) + [4mint[24m [1minflateReset2[22m([4mz_streamp[24m [4mstrm[24m, [4mint[24m [4mwindowBits[24m); + + This function is the same as [1minflateReset[22m(), but it also permits + changing the wrap and window size requests. The [4mwindowBits[24m pa†+ rameter is interpreted the same as it is for [4minflateInit2[24m. If + the window size is changed, then the memory allocated for the + window is freed, and the window will be reallocated by [1minflate[22m() + if needed. + + [1minflateReset2[22m() returns Z_OK if success, or Z_STREAM_ERROR if the + source stream state was inconsistent (such as [4mzalloc[24m or [4mstate[24m be†+ ing NULL), or if the [4mwindowBits[24m parameter is invalid. - This function inserts bits in the inflate input stream. The in- + [4mint[24m [1minflatePrime[22m([4mz_stream[24m [4mstrm[24m, [4mint[24m [4mbits[24m, [4mint[24m [4mvalue[24m); + + This function inserts bits in the inflate input stream. The in†tent is that this function is used to start inflating at a bit position in the middle of a byte. The provided bits will be used before any bytes are used from [4mnext_in[24m. This function should @@ -856,10 +1083,45 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mbits[24m must be less than or equal to 16, and that many of the least significant bits of value will be inserted in the input. + If [4mbits[24m is negative, then the input stream bit buffer is emptied. + Then [1minflatePrime[22m() can be called again to put bits in the buf†+ fer. This is used to clear out bits left over after feeding + [1minflate[22m() a block description prior to feeding it codes. + [1minflatePrime[22m() returns Z_OK if successful, or Z_STREAM_ERROR if the source stream state was inconsistent. - [4mint[24m [1minflateGetHeader[22m([4mz_streamp[24m [4mstrm[24m, [4mgz_headerp[24m [4mhead[24m) + [4mlong[24m [1minflateMark[22m([4mz_streamp[24m [4mstrm[24m); + + This function returns two values: one in the lower 16 bits of the + return value, and the other in the remaining upper bits, obtained + by shifting the return value down 16 bits. If the upper value is + -1 and the lower value is zero, then [1minflate[22m() is currently de†+ coding information outside of a block. If the upper value is -1 + and the lower value is non-zero, then [1minflate[22m() is in the middle + of a stored block, with the lower value equaling the number of + bytes from the input remaining to copy. If the upper value is + not -1, then it is the number of bits back from the current bit + position in the input of the code (literal or length/distance + pair) currently being processed. In that case the lower value is + the number of bytes already emitted for that code. + + A code is being processed if [1minflate[22m() is waiting for more input + to complete decoding of the code, or if it has completed decoding + but is waiting for more output space to write the literal or + match data. + + [1minflateMark[22m() is used to mark locations in the input data for + random access, which may be at bit positions, and to note those + cases where the output of a code may span boundaries of random + access blocks. The current location in the input stream can be + determined from [4mavail_in[24m and [4mdata_type[24m as noted in the descrip†+ tion for the Z_BLOCK flush parameter for [1minflate[22m(). + + [1minflateMark[22m() returns the value noted above, or -65536 if the + provided source stream state was inconsistent. + + [4mint[24m [1minflateGetHeader[22m([4mz_streamp[24m [4mstrm[24m, [4mgz_headerp[24m [4mhead[24m); [1minflateGetHeader[22m() requests that gzip header information be stored in the provided gz_header structure. [1minflateGetHeader[22m() @@ -868,32 +1130,32 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) stream, head->done is zero until the header is completed, at which time head->done is set to one. If a zlib stream is being decoded, then head->done is set to -1 to indicate that there will - be no gzip header information forthcoming. Note that Z_BLOCK can - be used to force [1minflate[22m() to return immediately after header - processing is complete and before any actual data is decom- - pressed. + be no gzip header information forthcoming. Note that Z_BLOCK or + Z_TREES can be used to force [1minflate[22m() to return immediately af†+ ter header processing is complete and before any actual data is + decompressed. The text, time, xflags, and os fields are filled in with the gzip header contents. hcrc is set to true if there is a header CRC. (The header CRC was valid if done is set to one.) If extra is - not Z_NULL, then [4mextra_max[24m contains the maximum number of bytes - to write to [4mextra[24m. Once done is true, [4mextra_len[24m contains the ac- - tual extra field length, and [4mextra[24m contains the extra field, or - that field truncated if [4mextra_max[24m is less than [4mextra_len[24m. If - name is not Z_NULL, then up to [4mname_max[24m characters are written - there, terminated with a zero unless the length is greater than - [4mname_max[24m. If comment is not Z_NULL, then up to [4mcomm_max[24m charac- - ters are written there, terminated with a zero unless the length - is greater than [4mcomm_max[24m. When any of extra, name, or comment - are not Z_NULL and the respective field is not present in the - header, then that field is set to Z_NULL to signal its absence. - This allows the use of [1mdeflateSetHeader[22m() with the returned - structure to duplicate the header. However if those fields are - set to allocated memory, then the application will need to save - those pointers elsewhere so that they can be eventually freed. + not NULL, then [4mextra_max[24m contains the maximum number of bytes to + write to [4mextra[24m. Once done is true, [4mextra_len[24m contains the actual + extra field length, and [4mextra[24m contains the extra field, or that + field truncated if [4mextra_max[24m is less than [4mextra_len[24m. If name is + not NULL, then up to [4mname_max[24m characters are written there, ter†+ minated with a zero unless the length is greater than [4mname_max[24m. + If comment is not NULL, then up to [4mcomm_max[24m characters are writ†+ ten there, terminated with a zero unless the length is greater + than [4mcomm_max[24m. When any of extra, name, or comment are not NULL + and the respective field is not present in the header, then that + field is set to NULL to signal its absence. This allows the use + of [1mdeflateSetHeader[22m() with the returned structure to duplicate + the header. However if those fields are set to allocated memory, + then the application will need to save those pointers elsewhere + so that they can be eventually freed. If [1minflateGetHeader[22m() is not used, then the header information is - simply discarded. The header is always checked for validity, in- + simply discarded. The header is always checked for validity, in†cluding the header CRC if present. [1minflateReset[22m() will reset the process to discard the header information. The application would need to call [1minflateGetHeader[22m() again to retrieve the header from @@ -903,18 +1165,18 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) if the source stream state was inconsistent. [4mint[24m [1minflateBackInit[22m([4mz_stream[24m [4m*strm[24m, [4mint[24m [4mwindowBits[24m, [4munsigned[24m [4mchar[24m [4mFAR[0m - [4m*window[24m) + [4m*window[24m); Initialize the internal stream state for decompression using [1minflateBack[22m() calls. The fields [4mzalloc[24m, [4mzfree[24m and [4mopaque[24m in [4mstrm[0m must be initialized before the call. If [4mzalloc[24m and [4mzfree[24m are - Z_NULL, then the default library-derived memory allocation rou- - tines are used. [4mwindowBits[24m is the base two logarithm of the win- - dow size, in the range 8..15. [4mwindow[24m is a caller supplied buffer - of that size. Except for special applications where it is as- - sured that [1mdeflate[22m() was used with small window sizes, [4mwindowBits[0m - must be 15 and a 32K byte window must be supplied to be able to - decompress general deflate streams. + NULL, then the default library-derived memory allocation routines + are used. [4mwindowBits[24m is the base two logarithm of the window + size, in the range 8..15. [4mwindow[24m is a caller supplied buffer of + that size. Except for special applications where it is assured + that [1mdeflate[22m() was used with small window sizes, [4mwindowBits[24m must + be 15 and a 32K byte window must be supplied to be able to decom†+ press general deflate streams. See [1minflateBack[22m() for the usage of these routines. @@ -924,15 +1186,17 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) of the library does not match the version of the header file. [4mint[24m [1minflateBack[22m([4mz_stream[24m [4m*strm[24m, [4min_func[24m [4min[24m, [4mvoid[24m [4mFAR[24m [4m*in_desc[24m, [4mout_func[0m - [4mout[24m, [4mvoid[24m [4mFAR[24m [4m*out_desc[24m) + [4mout[24m, [4mvoid[24m [4mFAR[24m [4m*out_desc[24m); [1minflateBack[22m() does a raw inflate with a single call using a call- - back interface for input and output. This is more efficient than - [1minflate[22m() for file I/O applications in that it avoids copying be- - tween the output and the sliding window by simply making the win- - dow itself the output buffer. This function trusts the applica- - tion to not change the output buffer passed by the output func- - tion, at least until [1minflateBack[22m() returns. + back interface for input and output. This is potentially more + efficient than [1minflate[22m() for file I/O applications, in that it + avoids copying between the output and the sliding window by sim†+ ply making the window itself the output buffer. [1minflate[22m() can be + faster on modern CPUs when used with large buffers. + [1minflateBack[22m() trusts the application to not change the output + buffer passed by the output function, at least until + [1minflateBack[22m() returns. [1minflateBackInit[22m() must be called first to allocate the internal state and to initialize the state with the user-provided window @@ -945,41 +1209,41 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) reads zip or gzip files and writes out uncompressed files. The utility would decode the header and process the trailer on its own, hence this routine expects only the raw deflate stream to - decompress. This is different from the normal behavior of - [1minflate[22m(), which expects either a zlib or gzip header and trailer - around the deflate stream. + decompress. This is different from the default behavior of + [1minflate[22m(), which expects either a zlib header and trailer around + the deflate stream. [1minflateBack[22m() uses two subroutines supplied by the caller that are then called by [1minflateBack[22m() for input and output. - [1minflateBack[22m() calls those routines until it reads a complete de- - flate stream and writes out all of the uncompressed data, or un- + [1minflateBack[22m() calls those routines until it reads a complete de†+ flate stream and writes out all of the uncompressed data, or un†til it encounters an error. The function's parameters and return types are defined above in the in_func and out_func typedefs. [1minflateBack[22m() will call in(in_desc, &buf) which should return the number of bytes of provided input, and a pointer to that input in - [4mbuf[24m. If there is no input available, [1min[22m() must return zero -- - buf is ignored in that case -- and [1minflateBack[22m() will return a - buffer error. [1minflateBack[22m() will call out(out_desc, buf, len) to - write the uncompressed data buf[0..len-1]. [1mout[22m() should return - zero on success, or non-zero on failure. If [1mout[22m() returns non- - zero, [1minflateBack[22m() will return with an error. Neither [1min[22m() nor - [1mout[22m() are permitted to change the contents of the window provided - to [1minflateBackInit[22m(), which is also the buffer that [1mout[22m() uses to - write from. The length written by [1mout[22m() will be at most the win- + [4mbuf[24m. If there is no input available, [1min[22m() must return zero — buf + is ignored in that case — and [1minflateBack[22m() will return a buffer + error. [1minflateBack[22m() will call out(out_desc, buf, len) to write + the uncompressed data buf[0..len-1]. [1mout[22m() should return zero on + success, or non-zero on failure. If [1mout[22m() returns non-zero, + [1minflateBack[22m() will return with an error. Neither [1min[22m() nor [1mout[22m() + are permitted to change the contents of the window provided to + [1minflateBackInit[22m(), which is also the buffer that [1mout[22m() uses to + write from. The length written by [1mout[22m() will be at most the win†dow size. Any non-zero amount of input may be provided by [1min[22m(). For convenience, [1minflateBack[22m() can be provided input on the first call by setting strm->next_in and strm->avail_in. If that input is exhausted, then [1min[22m() will be called. Therefore strm->next_in must be initialized before calling [1minflateBack[22m(). If - strm->next_in is Z_NULL, then [1min[22m() will be called immediately for - input. If strm->next_in is not Z_NULL, then strm->avail_in must - also be initialized, and then if strm->avail_in is not zero, in- + strm->next_in is NULL, then [1min[22m() will be called immediately for + input. If strm->next_in is not NULL, then strm->avail_in must + also be initialized, and then if strm->avail_in is not zero, in†put will initially be taken from strm->next_in[0 .. strm->avail_in - 1]. The [4min_desc[24m and [4mout_desc[24m parameters of [1minflateBack[22m() are passed - as the first parameter of [1min[22m() and [1mout[22m() respectively when they + as the first parameter of [1min[22m() and [1mout[22m(), respectively, when they are called. These descriptors can be optionally used to pass any information that the caller-supplied [1min[22m() and [1mout[22m() functions need to do their job. @@ -990,23 +1254,23 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) Z_STREAM_END on success, Z_BUF_ERROR if [1min[22m() or [1mout[22m() returned an error, Z_DATA_ERROR if there was a format error in the deflate stream (in which case strm->msg is set to indicate the nature of - the error), or Z_STREAM_ERROR if the stream was not properly ini- + the error), or Z_STREAM_ERROR if the stream was not properly ini†tialized. In the case of Z_BUF_ERROR, an input or output error - can be distinguished using strm->next_in which will be Z_NULL - only if [1min[22m() returned an error. If strm->next is not Z_NULL, - then the Z_BUF_ERROR was due to [1mout[22m() returning non-zero. ([1min[22m() - will always be called before [1mout[22m(), so strm->next_in is assured - to be defined if [1mout[22m() returns non-zero.) Note that - [1minflateBack[22m() cannot return Z_OK. + can be distinguished using strm->next_in which will be NULL only + if [1min[22m() returned an error. If strm->next is not NULL, then the + Z_BUF_ERROR was due to [1mout[22m() returning non-zero. ([1min[22m() will + always be called before [1mout[22m(), so strm->next_in is assured to be + defined if [1mout[22m() returns non-zero.) Note that [1minflateBack[22m() can†+ not return Z_OK. - [4mint[24m [1minflateBackEnd[22m([4mz_stream[24m [4m*strm[24m) + [4mint[24m [1minflateBackEnd[22m([4mz_stream[24m [4m*strm[24m); All memory allocated by [1minflateBackInit[22m() is freed. [1minflateBackEnd[22m() returns Z_OK on success, or Z_STREAM_ERROR if the stream state was inconsistent. - [4muLong[24m [1mzlibCompileFlags[22m([4mvoid[24m) + [4muLong[24m [1mzlibCompileFlags[22m([4mvoid[24m); This function returns flags indicating compile-time options. @@ -1024,45 +1288,45 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) Compiler, assembler, and debug options: - 8 DEBUG - 9 ASMV or ASMINF -- use ASM code - 10 ZLIB_WINAPI -- exported functions use the WINAPI + 8 ZLIB_DEBUG + 9 ASMV or ASMINF — use ASM code + 10 ZLIB_WINAPI — exported functions use the WINAPI calling convention 11 0 (reserved) One-time table building (smaller code, but not thread-safe if true): - 12 BUILDFIXED -- build static block decoding tables + 12 BUILDFIXED — build static block decoding tables when needed - 13 DYNAMIC_CRC_TABLE -- build CRC calculation tables + 13 DYNAMIC_CRC_TABLE — build CRC calculation tables when needed 14,15 0 (reserved) Library content (indicates missing functionality): - 16 NO_GZCOMPRESS -- gz* functions cannot compress (to + 16 NO_GZCOMPRESS — gz* functions cannot compress (to avoid linking deflate code when not needed) - 17 NO_GZIP -- deflate can't write gzip streams, and - inflate can't detect and decode gzip streams (to + 17 NO_GZIP — deflate can't write gzip streams, and in†+ flate can't detect and decode gzip streams (to avoid linking CRC code) 18-19 0 (reserved) Operation variations (changes in library functionality): - 20 PKZIP_BUG_WORKAROUND -- slightly more permissive - inflate - 21 FASTEST -- deflate algorithm with only one, lowest + 20 PKZIP_BUG_WORKAROUND — slightly more permissive in†+ flate + 21 FASTEST — deflate algorithm with only one, lowest compression level 22,23 0 (reserved) The sprintf variant used by gzprintf (zero is best): - 24 0 = vs*, 1 = s* -- 1 means limited to 20 arguments + 24 0 = vs*, 1 = s* — 1 means limited to 20 arguments after the format - 25 0 = *nprintf, 1 = *printf -- 1 means [1mgzprintf[22m() not + 25 0 = *nprintf, 1 = *printf — 1 means [1mgzprintf[22m() not secure! - 26 0 = returns value, 1 = void -- 1 means inferred + 26 0 = returns value, 1 = void — 1 means inferred string length returned Remainder: @@ -1071,10 +1335,10 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mUTILITY FUNCTIONS[0m The following utility functions are implemented on top of the basic - stream-oriented functions. To simplify the interface, some default op- + stream-oriented functions. To simplify the interface, some default op†tions are assumed (compression level and memory usage, standard memory - allocation functions). The source code of these utility functions can - easily be modified if you need special options. + allocation functions). The source code of these utility functions can be + modified if you need special options. [4mint[24m [1mcompress[22m([4mBytef[24m [4m*dest[24m, [4muLongf[24m [4m*destLen[24m, [4mconst[24m [4mBytef[24m [4m*source[24m, [4muLong[0m [4msourceLen[24m); @@ -1084,8 +1348,8 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) buffer. Upon entry, [4mdestLen[24m is the total size of the destination buffer, which must be at least the value returned by [1mcompressBound[22m([4msourcelen[24m). Upon exit, [4mdestLen[24m is the actual size - of the compressed buffer. This function can be used to compress - a whole file at once if the input file is mmap'ed. + of the compressed data. [1mcompress[22m() is equivalent to [1mcompress2[22m() + with a level parameter of Z_DEFAULT_COMPRESSION. [1mcompress[22m() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, or Z_BUF_ERROR if there was not enough room in @@ -1107,11 +1371,11 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) the output buffer, or Z_STREAM_ERROR if the level parameter is invalid. - [4mint[24m [1mcompressBound[22m([4muLong[24m [4msourceLen[24m) + [4muLong[24m [1mcompressBound[22m([4muLong[24m [4msourceLen[24m); - [1mcompressBound[22m() returns an upper bound on the compressed size af- + [1mcompressBound[22m() returns an upper bound on the compressed size af†ter [1mcompress[22m() or [1mcompress2[22m() on [4msourceLen[24m bytes. It would be - used before a [1mcompress[22m() or [1mcompress2[22m() call to allocate the des- + used before a [1mcompress[22m() or [1mcompress2[22m() call to allocate the des†tination buffer. [4mint[24m [1muncompress[22m([4mBytef[24m [4m*dest[24m, [4muLongf[24m [4m*destLen[24m, [4mconst[24m [4mBytef[24m [4m*source[24m, [4muLong[0m @@ -1120,41 +1384,76 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [1muncompress[22m() function decompresses the source buffer into the destination buffer. [4msourceLen[24m is the byte length of the source buffer. Upon entry, [4mdestLen[24m is the total size of the destination - buffer, which must be large enough to hold the entire uncom- + buffer, which must be large enough to hold the entire uncom†pressed data. (The size of the uncompressed data must have been - saved previously by the compressor and transmitted to the decom- + saved previously by the compressor and transmitted to the decom†pressor by some mechanism outside the scope of this compression - library.) Upon exit, [4mdestLen[24m is the actual size of the com- - pressed buffer. This function can be used to decompress a whole + library.) Upon exit, [4mdestLen[24m is the actual size of the uncom†+ pressed data. This function can be used to decompress a whole file at once if the input file is mmap'ed. [1muncompress[22m() returns Z_OK if successful, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in - the output buffer, or Z_DATA_ERROR if the input data was cor- - rupted or incomplete. + the output buffer, or Z_DATA_ERROR if the input data was cor†+ rupted or incomplete. In the case where there is not enough + room, [1muncompress[22m() will fill the output buffer with the uncom†+ pressed data up to that point. + + [4mint[24m [1muncompress2[22m([4mBytef[24m [4m*dest[24m, [4muLongf[24m [4m*destLen[24m, [4mconst[24m [4mBytef[24m [4m*source[24m, [4muLong[0m + [4m*sourceLen[24m); + + Same as [1muncompress[22m(), except that [4msourceLen[24m is a pointer, where + the length of the source is [4m*sourceLen[24m. On return, [4m*sourceLen[24m is + the number of source bytes consumed. [4mgzFile[24m [1mgzopen[22m([4mconst[24m [4mchar[24m [4m*path[24m, [4mconst[24m [4mchar[24m [4m*mode[24m); + This library supports reading and writing files in gzip (.gz) + format with an interface similar to that of stdio, using the + functions that start with "gz". The gzip format is different + from the zlib format. gzip is a gzip wrapper, documented in RFC + 1952, wrapped around a deflate stream. + The [1mgzopen[22m() function opens a gzip (.gz) file for reading or writing. The mode parameter is as in fopen(3) ("rb" or "wb") but - can also include a compression level (wb9) or a strategy: `f' for - filtered data, as in "wb6f"; `h' for Huffman only compression, as - in "wb1h", or `R' for run-length encoding as in "wb1R". (See the - description of [1mdeflateInit2[22m() for more information about the - strategy parameter.) + can also include a compression level (wb9) or a strategy: ‘f’ for + filtered data, as in "wb6f"; ‘h’ for Huffman only compression, as + in "wb1h", or ‘R’ for run-length encoding as in "wb1R", or ‘F’ + for fixed code compression as in "wb9F". (See the description of + [1mdeflateInit2[22m() for more information about the strategy parame†+ ter.) ‘T’ will request transparent writing or appending with no + compression and not using the gzip format. + + ‘a’ can be used instead of ‘w’ to request that the gzip stream + that will be written be appended to the file. ‘+’ will result in + an error, since reading and writing to the same gzip file is not + supported. The addition of ‘x’ when writing will create the file + exclusively, which fails if the file already exists. On systems + that support it, the addition of ‘e’ when reading or writing will + set the flag to close the file on an execve(2) call. + + These functions, as well as gzip, will read and decode a sequence + of gzip streams in a file. The append function of [1mgzopen[22m() can + be used to create such a file. (Also see [1mgzflush[22m() for another + way to do this.) When appending, [1mgzopen[22m() does not test whether + the file begins with a gzip stream, nor does it look for the end + of the gzip streams to begin appending. [1mgzopen[22m() will simply ap†+ pend a gzip stream to the existing file. [1mgzopen[22m() can be used to read a file which is not in gzip format; in this case [1mgzread[22m() will directly read from the file without - decompression. + decompression. When reading, this will be detected automatically + by looking for the magic two-byte gzip header. - [1mgzopen[22m() returns NULL if the file could not be opened or if there - was insufficient memory to allocate the (de)compression state; - errno can be checked to distinguish the two cases (if errno is - zero, the [1mzlib [22merror is Z_MEM_ERROR). + [1mgzopen[22m() returns NULL if the file could not be opened, if there + was insufficient memory to allocate the gzFile state, or if an + invalid mode was specified (an ‘r’, ‘w’, or ‘a’ was not provided, + or ‘+’ was provided). [4merrno[24m can be checked to determine if the + reason [1mgzopen[22m() failed was that the file could not be opened. [4mgzFile[24m [1mgzdopen[22m([4mint[24m [4mfd[24m, [4mconst[24m [4mchar[24m [4m*mode[24m); - The [1mgzdopen[22m() function associates a gzFile with the file descrip- + The [1mgzdopen[22m() function associates a gzFile with the file descrip†tor [4mfd[24m. File descriptors are obtained from calls like open(2), dup(2), creat(3), pipe(2), or fileno(3) (if the file has been previously opened with fopen(3)). The [4mmode[24m parameter is as in @@ -1162,55 +1461,152 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The next call to [1mgzclose[22m() on the returned gzFile will also close the file descriptor fd, just like fclose(fdopen(fd), mode) closes - the file descriptor fd. If you want to keep fd open, use gz- - dopen(dup(fd), mode). - - [1mgzdopen[22m() returns NULL if there was insufficient memory to allo- - cate the (de)compression state. + the file descriptor fd. If you want to keep fd open, use “fd = + dup(fd_keep); gz = gzdopen(fd, mode);â€. The duplicated descrip†+ tor should be saved to avoid a leak, since [1mgzdopen[22m() does not + close fd if it fails. If you are using [1mfileno[22m() to get the file + descriptor from a FILE *, then you will have to use dup(2) to + avoid double-closing the file descriptor. Both [1mgzclose[22m() and + [1mfclose[22m() will close the associated file descriptor, so they need + to have different file descriptors. + + [1mgzdopen[22m() returns NULL if there was insufficient memory to allo†+ cate the gzFile state, if an invalid mode was specified (an 'r', + 'w', or 'a' was not provided, or '+' was provided), or if fd is + -1. The file descriptor is not used until the next gz* read, + write, seek, or close operation, so [1mgzdopen[22m() will not detect if + fd is invalid (unless fd is -1). + + [4mint[24m [1mgzbuffer[22m([4mgzFile[24m [4mfile[24m, [4munsigned[24m [4msize[24m); + + Set the internal buffer size used by this library's functions. + The default buffer size is 8192 bytes. This function must be + called after [1mgzopen[22m() or [1mgzdopen[22m(), and before any other calls + that read or write the file. The buffer memory allocation is al†+ ways deferred to the first read or write. Three times that size + in buffer space is allocated. A larger buffer size of, for exam†+ ple, 64K or 128K bytes, will noticeably increase the speed of de†+ compression (reading). + + The new buffer size also affects the maximum length for + [1mgzprintf[22m(). + + [1mgzbuffer[22m() returns 0 on success, or -1 on failure, such as being + called too late. [4mint[24m [1mgzsetparams[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4mlevel[24m, [4mint[24m [4mstrategy[24m); The [1mgzsetparams[22m() function dynamically updates the compression level or strategy. See the description of [1mdeflateInit2[22m() for the - meaning of these parameters. + meaning of these parameters. Previously provided data is flushed + before the parameter change. - [1mgzsetparams[22m() returns Z_OK if successful, or Z_STREAM_ERROR if - the file was not opened for writing. + [1mgzsetparams[22m() returns Z_OK if successful, Z_STREAM_ERROR if the + file was not opened for writing, Z_ERRNO if there is an error + writing the flushed data, or Z_MEM_ERROR if there is a memory al†+ location error. [4mint[24m [1mgzread[22m([4mgzFile[24m [4mfile[24m, [4mvoidp[24m [4mbuf[24m, [4munsigned[24m [4mlen[24m); - The [1mgzread[22m() function reads the given number of uncompressed - bytes from the compressed file. If the input file was not in - gzip format, [1mgzread[22m() copies the given number of bytes into the - buffer. - - [1mgzread[22m() returns the number of uncompressed bytes actually read - (0 for end of file, -1 for error). + Reads the given number of uncompressed bytes from the compressed + file. If the input file is not in gzip format, [1mgzread[22m() copies + the given number ofbytes into the buffer directly from the file. + + After reaching the end of a gzip stream in the input, [1mgzread[22m() + will continue to read, looking for another gzip stream. Any num†+ ber of gzip streams may be concatenated in the input file, and + will all be decompressed by [1mgzread[22m(). If something other than a + gzip stream is encountered after a gzip stream, that remaining + trailing garbage is ignored (and no error is returned). + + [1mgzread[22m() can be used to read a gzip file that is being concur†+ rently written. Upon reaching the end of the input, [1mgzread[22m() + will return with the available data. If the error code returned + by [1mgzerror[22m() is Z_OK or Z_BUF_ERROR, then [1mgzclearerr[22m() can be + used to clear the end of file indicator in order to permit + [1mgzread[22m() to be tried again. Z_OK indicates that a gzip stream + was completed on the last [1mgzread[22m(). Z_BUF_ERROR indicates that + the input file ended in the middle of a gzip stream. Note that + [1mgzread[22m() does not return -1 in the event of an incomplete gzip + stream. This error is deferred until [1mgzclose[22m(), which will re†+ turn Z_BUF_ERROR if the last [1mgzread[22m() ended in the middle of a + gzip stream. Alternatively, [1mgzerror[22m() can be used before + [1mgzclose[22m() to detect this case. + + [1mgzread[22m() returns the number of uncompressed bytes actually read, + less than [4mlen[24m for end of file, or -1 for error. If [4mlen[24m is too + large to fit in an int, then nothing is read, -1 is returned, and + the error state is set to Z_STREAM_ERROR. + + [4mz_size_t[24m [1mgzfread[22m([4mvoidp[24m [4mbuf[24m, [4mz_size_t[24m [4msize[24m, [4mz_size_t[24m [4mnitems[24m, [4mgzFile[24m [4mfile[24m); + + Read up to [4mnitems[24m items of size [4msize[24m from [4mfile[24m to [4mbuf[24m, otherwise + operating as [1mgzread[22m() does. This duplicates the interface of + stdio's fread(3), with size_t request and return types. If the + library defines size_t, then z_size_t is identical to size_t. If + not, then z_size_t is an unsigned integer type that can contain a + pointer. + + [1mgzfread[22m() returns the number of full items read of size [4msize[24m, or + zero if the end of the file was reached and a full item could not + be read, or if there was an error. [1mgzerror[22m() must be consulted + if zero is returned in order to determine if there was an error. + If the multiplication of [4msize[24m and [4mnitems[24m overflows, i.e. the + product does not fit in a z_size_t, then nothing is read, zero is + returned, and the error state is set to Z_STREAM_ERROR. + + In the event that the end of file is reached and only a partial + item is available at the end, i.e. the remaining uncompressed + data length is not a multiple of size, then the final partial + item is nevetheless read into [4mbuf[24m and the end-of-file flag is + set. The length of the partial item read is not provided, but + could be inferred from the result of [1mgztell[22m(). This behavior is + the same as the behavior of fread(3) implementations in common + libraries, but it prevents the direct use of [1mgzfread[22m() to read a + concurrently written file, resetting and retrying on end-of-file, + when size is not 1. [4mint[24m [1mgzwrite[22m([4mgzFile[24m [4mfile[24m, [4mvoidpc[24m [4mbuf[24m, [4munsigned[24m [4mlen[24m); The [1mgzwrite[22m() function writes the given number of uncompressed bytes into the compressed file. [1mgzwrite[22m() returns the number of - uncompressed bytes actually written (0 in case of error). + uncompressed bytes written or 0 in case of error. + + [4mz_size_t[24m [1mgzfwrite[22m([4mvoidpc[24m [4mbuf[24m, [4mz_size_t[24m [4msize[24m, [4mz_size_t[24m [4mnitems[24m, [4mgzFile[0m + [4mfile[24m); + + [1mgzfwrite[22m() writes [4mnitems[24m items of size [4msize[24m from [4mbuf[24m to [4mfile[24m, du†+ plicating the interface of stdio's fwrite(3), with size_t request + and return types. If the library defines size_t, then z_size_t + is identical to size_t. If not, then z_size_t is an unsigned in†+ teger type that can contain a pointer. + + [1mgzfwrite[22m() returns the number of full items written of size [4msize[24m, + or zero if there was an error. If the multiplication of [4msize[24m and + [4mnitems[24m overflows, i.e. the product does not fit in a z_size_t, + then nothing is written, zero is returned, and the error state is + set to Z_STREAM_ERROR. [4mint[24m [1mgzprintf[22m([4mgzFile[24m [4mfile[24m, [4mconst[24m [4mchar[24m [4m*format[24m, [4m...[24m); The [1mgzprintf[22m() function converts, formats, and writes the args to the compressed file under control of the format string, as in fprintf(3). [1mgzprintf[22m() returns the number of uncompressed bytes - actually written (0 in case of error). The number of uncom- - pressed bytes written is limited to 4095. The caller should make - sure that this limit is not exceeded. If it is exceeded, then - [1mgzprintf[22m() will return an error (0) with nothing written. In - this case, there may also be a buffer overflow with unpredictable - consequences, which is possible only if [1mzlib [22mwas compiled with - the insecure functions [1msprintf[22m() or [1mvsprintf[22m() because the secure - [1msnprintf[22m() or [1mvsnprintf[22m() functions were not available. + actually written, or a negative zlib error code in case of error. + The number of uncompressed bytes written is limited to 8191, or + one less than the buffer size given to [1mgzbuffer[22m(). The caller + should ensure that this limit is not exceeded. If it is ex†+ ceeded, then [1mgzprintf[22m() will return an error (0) with nothing + written. In this case, there may also be a buffer overflow with + unpredictable consequences, which is possible only if [1mzlib [22mwas + compiled with the insecure functions [1msprintf[22m() or [1mvsprintf[22m() be†+ cause the secure [1msnprintf[22m() or [1mvsnprintf[22m() functions were not + available. This can be determined using [1mzlibCompileFlags[22m(). [4mint[24m [1mgzputs[22m([4mgzFile[24m [4mfile[24m, [4mconst[24m [4mchar[24m [4m*s[24m); - The [1mgzputs[22m() function writes the given null-terminated string to - the compressed file, excluding the terminating null character. + The [1mgzputs[22m() function writes the given NUL-terminated string to + the compressed file, excluding the terminating NUL character. [1mgzputs[22m() returns the number of characters written, or -1 in case of error. @@ -1220,9 +1616,15 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [1mgzgets[22m() function reads bytes from the compressed file until len-1 characters are read, or a newline character is read and transferred to [4mbuf[24m, or an end-of-file condition is encountered. - The string is then terminated with a null character. + If any characters are read or if len == 1, the string is termi†+ nated with a NUL character. If no characters are read due to an + end-of-file or len < 1, then the buffer is left untouched. + + [1mgzgets[22m() returns [4mbuf[24m, which is a NUL-terminated string, or it re†+ turns NULL for end-of-file or in case of error. If there was an + error, the contents at [4mbuf[24m are indeterminate. - [1mgzgets[22m() returns [4mbuf[24m, or Z_NULL in case of error. + [1mgzgets[22m() returns [4mbuf[24m, or NULL in case of error. [4mint[24m [1mgzputc[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4mc[24m); @@ -1234,26 +1636,37 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) The [1mgzgetc[22m() function reads one byte from the compressed file. [1mgzgetc[22m() returns this byte or -1 in case of end of file or error. - - [4mint[24m [1mgzungetc[22m([4mint[24m [4mc[24m, [4mgzFile[24m [4mfile[24m) - - Push one character back onto the stream to be read again later. - Only one character of push-back is allowed. [1mgzungetc[22m() returns - the character pushed, or -1 on failure. [1mgzungetc[22m() will fail if - a character has been pushed but not read yet, or if [4mc[24m is -1. The - pushed character will be discarded if the stream is repositioned - with [1mgzseek[22m() or [1mgzrewind[22m(). + This is implemented as a macro for speed. As such, it does not + do all of the checking the other functions do. That is, it does + not check to see if file is NULL, nor whether the structure [4mfile[0m + points to has been clobbered or not. + + [4mint[24m [1mgzungetc[22m([4mint[24m [4mc[24m, [4mgzFile[24m [4mfile[24m); + + Push one character back onto the stream to be read as the first + character on the next read. At least one character of push-back + is allowed. [1mgzungetc[22m() returns the character pushed, or -1 on + failure. [1mgzungetc[22m() will fail if c is -1, and may fail if a + character has been pushed but not read yet. If [1mgzungetc[22m() is + used immediately after [1mgzopen[22m() or [1mgzdopen[22m(), at least the output + buffer size of pushed characters is allowed. (See [1mgzbuffer[22m() + above.) The pushed character will be discarded if the stream is + repositioned with [1mgzseek[22m() or [1mgzrewind[22m(). [4mint[24m [1mgzflush[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4mflush[24m); - The [1mgzflush[22m() function flushes all pending output into the com- - pressed file. The parameter [4mflush[24m is as in the [1mdeflate[22m() func- + The [1mgzflush[22m() function flushes all pending output into the com†+ pressed file. The parameter [4mflush[24m is as in the [1mdeflate[22m() func†tion. The return value is the [1mzlib [22merror number (see function - [1mgzerror[22m() below). [1mgzflush[22m() returns Z_OK if the flush parameter - is Z_FINISH and all output could be flushed. + [1mgzerror[22m() below). [1mgzflush[22m() is only permitted when writing. + + If the flush parameter is Z_FINISH, the remaining data is written + and the gzip stream is completed in the output. If [1mgzwrite[22m() is + called again, a new gzip stream will be started in the output. + [1mgzread[22m() is able to read such concatenated gzip streams. [1mgzflush[22m() should be called only when strictly necessary because - it can degrade compression. + it will degrade compression if called too often. [4mz_off_t[24m [1mgzseek[22m([4mgzFile[24m [4mfile[24m, [4mz_off_t[24m [4moffset[24m, [4mint[24m [4mwhence[24m); @@ -1270,7 +1683,7 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [1mgzseek[22m() returns the resulting offset location as measured in bytes from the beginning of the uncompressed stream, or -1 in case of error, in particular if the file is opened for writing - and the new starting position would be before the current posi- + and the new starting position would be before the current posi†tion. [4mint[24m [1mgzrewind[22m([4mgzFile[24m [4mfile[24m); @@ -1283,47 +1696,113 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mz_off_t[24m [1mgztell[22m([4mgzFile[24m [4mfile[24m); The [1mgztell[22m() function returns the starting position for the next - [1mgzread[22m() or [1mgzwrite[22m() on the given compressed file. This posi- + [1mgzread[22m() or [1mgzwrite[22m() on the given compressed file. This posi†tion represents a number of bytes in the uncompressed data - stream. + stream, and is zero when starting, even if appending or reading a + gzip stream from the middle of a file using [1mgzdopen[22m(). gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR). + [4mint[24m [1mgzeoffset[22m([4mgzFile[24m [4mfile[24m); + + Returns the current offset in the file being read or written. + This offset includes the count of bytes that precede the gzip + stream, for example when appending or when using [1mgzdopen[22m() for + reading. When reading, the offset does not include as yet unused + buffered input. This information can be used for a progress in†+ dicator. On error, [1mgzoffset[22m() returns -1. + [4mint[24m [1mgzeof[22m([4mgzFile[24m [4mfile[24m); - The [1mgzeof[22m() function returns 1 when EOF has previously been de- - tected reading the given input stream, otherwise zero. + Returns true (1) if the end-of-file indicator has been set while + reading, false (0) otherwise. Note that the end-of-file indica†+ tor is set only if the read tried to go past the end of the in†+ put, but came up short. Therefore just like feof(3), [1mgzeof[22m() may + return false even if there is no more data to read, in the event + that the last read request was for the exact number of bytes re†+ maining in the input file. This will happen if the input file + size is an exact multiple of the buffer size. + + If [1mgzeof[22m() returns true, then the read functions will return no + more data, unless the end-of-file indicator is reset by + [1mgzclearerr[22m() and the input file has grown since the previous end + of file was detected. [4mint[24m [1mgzdirect[22m([4mgzFile[24m [4mfile[24m); - The [1mgzdirect[22m() function returns 1 if the file is being read di- - rectly without compression; otherwise it returns 0. + Returns true (1) if [4mfile[24m is being copied directly while reading, + or false (0) if [4mfile[24m is a gzip stream being decompressed. + + If the input file is empty, [1mgzdirect[22m() will return true, since + the input does not contain a gzip stream. + + If [1mgzdirect[22m() is used immediately after [1mgzopen[22m() or [1mgzdopen[22m(), it + will cause buffers to be allocated to allow reading the file to + determine if it is a gzip file. Therefore if [1mgzbuffer[22m() is used, + it should be called before [1mgzdirect[22m(). + + When writing, [1mgzdirect[22m() returns true (1) if transparent writing + was requested ("wT" for the [1mgzopen[22m() mode), or false (0) other†+ wise. (Note: [1mgzdirect[22m() is not needed when writing. Transparent + writing must be explicitly requested, so the application already + knows the answer. When linking statically, using [1mgzdirect[22m() will + include all of the zlib code for gzip file reading and decompres†+ sion, which may not be desired.) [4mint[24m [1mgzclose[22m([4mgzFile[24m [4mfile[24m); - The [1mgzclose[22m() function flushes all pending output if necessary, - closes the compressed file and deallocates all the (de)compres- - sion state. The return value is the [1mzlib [22merror number (see func- - tion [1mgzerror[22m() below). + Flushes all pending output if necessary, closes the compressed + file and deallocates the (de)compression state. Note that once + file is closed, you cannot call [1mgzerror[22m() with [4mfile[24m, since its + structures have been deallocated. [1mgzclose[22m() must not be called + more than once on the same file, just as free(3) must not be + called more than once on the same allocation. + + [1mgzclose[22m() will return Z_STREAM_ERROR if [4mfile[24m is not valid, + Z_ERRNO on a file operation error, Z_MEM_ERROR if out of memory, + Z_BUF_ERROR if the last read ended in the middle of a gzip + stream, or Z_OK on success. + + [4mint[24m [1mgzclose_r[22m([4mgzFile[24m [4mfile[24m); + + [4mint[24m [1mgzclose_w[22m([4mgzFile[24m [4mfile[24m); + + Same as [1mgzclose[22m(), but [1mgzclose_r[22m() is only for use when reading, + and [1mgzclose_w[22m() is only for use when writing or appending. The + advantage to using these instead of [1mgzclose[22m() is that they avoid + linking in zlib compression or decompression code that is not + used when only reading or only writing, respectively. If + [1mgzclose[22m() is used, then both compression and decompression code + will be included in the application when linking to a static zlib + library. [4mconst[24m [4mchar[24m [4m*[24m [1mgzerror[22m([4mgzFile[24m [4mfile[24m, [4mint[24m [4m*errnum[24m); - The [1mgzerror[22m() function returns the error message for the last er- + The [1mgzerror[22m() function returns the error message for the last er†ror which occurred on the given compressed [4mfile[24m. [4merrnum[24m is set - to the [1mzlib [22merror number. If an error occurred in the file sys- + to the [1mzlib [22merror number. If an error occurred in the file sys†tem and not in the compression library, [4merrnum[24m is set to Z_ERRNO and the application may consult errno to get the exact error code. - [4mvoid[24m [1mgzclearerr[22m([4mgzFile[24m [4mfile[24m) - Clears the error and end-of-file flags for [4mfile[24m. This is analo- + The application must not modify the returned string. Future + calls to this function may invalidate the previously returned + string. If [4mfile[24m is closed, then the string previously returned + by [1mgzerror[22m() will no longer be available. + + [1mgzerror[22m() should be used to distinguish errors from end-of-file + for those functions above that do not distinguish those cases in + their return values. + + [4mvoid[24m [1mgzclearerr[22m([4mgzFile[24m [4mfile[24m); + Clears the error and end-of-file flags for [4mfile[24m. This is analo†gous to the [1mclearerr[22m() function in stdio. This is useful for - continuing to read a gzip file that is being written concur- + continuing to read a gzip file that is being written concur†rently. [1mCHECKSUM FUNCTIONS[0m These functions are not related to compression but are exported anyway - because they might be useful in applications using the compression li- + because they might be useful in applications using the compression li†brary. [4muLong[24m [1madler32[22m([4muLong[24m [4madler[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4muInt[24m [4mlen[24m); @@ -1332,24 +1811,29 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) is NULL, this function returns the required initial value for the checksum. - An Adler-32 checksum is almost as reliable as a CRC32 but can be + An Adler-32 checksum is almost as reliable as a CRC-32 but can be computed much faster. Usage example: - uLong adler = adler32(0L, Z_NULL, 0); + uLong adler = adler32(0L, NULL, 0); while (read_buffer(buffer, length) != EOF) { adler = adler32(adler, buffer, length); } if (adler != original_adler) error(); - [4muLong[24m [1madler32_combine[22m([4muLong[24m [4madler1[24m, [4muLong[24m [4madler2[24m, [4mz_off_t[24m [4mlen2[24m) + [4muLong[24m [1madler32_z[22m([4muLong[24m [4madler[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4mz_size_t[24m [4mlen[24m); + + The same as [1madler32[22m(), but with a size_t length. + + [4muLong[24m [1madler32_combine[22m([4muLong[24m [4madler1[24m, [4muLong[24m [4madler2[24m, [4mz_off_t[24m [4mlen2[24m); The [1madler32_combine[22m() function combines two Adler-32 checksums into one. For two sequences of bytes, seq1 and seq2 with lengths len1 and len2, Adler-32 checksums are calculated for each, adler1 and adler2. [1madler32_combine[22m() returns the Adler-32 checksum of seq1 and seq2 concatenated, requiring only adler1, adler2, and - len2. + len2. Note that the z_off_t type (like off_t) is a signed inte†+ ger. If [4mlen2[24m is negative, the result has no meaning or utility. [4muLong[24m [1mcrc32[22m([4muLong[24m [4mcrc[24m, [4mconst[24m [4mBytef[24m [4m*buf[24m, [4muInt[24m [4mlen[24m); @@ -1360,14 +1844,18 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) this function so it shouldn't be done by the application. Usage example: - uLong crc = crc32(0L, Z_NULL, 0); + uLong crc = crc32(0L, NULL, 0); while (read_buffer(buffer, length) != EOF) { crc = crc32(crc, buffer, length); } if (crc != original_crc) error(); - [4muLong[24m [1mcrc32_combine[22m([4muLong[24m [4mcrc1[24m, [4muLong[24m [4mcrc2[24m, [4mz_off_t[24m [4mlen2[24m) + [4muLong[24m [1mcrc32_z[22m([4muLong[24m [4madler[24m , [4mconst[24m, [4mBytef[24m, [4m*buf"[24m, [4mz_size_t[24m [4mlen[24m); + + The same as [1mcrc32[22m(), but with a size_t length. + + [4muLong[24m [1mcrc32_combine[22m([4muLong[24m [4mcrc1[24m, [4muLong[24m [4mcrc2[24m, [4mz_off_t[24m [4mlen2[24m); The [1mcrc32_combine[22m() function combines two CRC-32 check values into one. For two sequences of bytes, seq1 and seq2 with lengths @@ -1381,11 +1869,11 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) typedef struct z_stream_s { Bytef *next_in; /* next input byte */ uInt avail_in; /* number of bytes available at next_in */ - off_t total_in; /* total nb of input bytes read so far */ + off_t total_in; /* total number of input bytes read so far */ - Bytef *next_out; /* next output byte should be put there */ + Bytef *next_out; /* next output byte will go here */ uInt avail_out; /* remaining free space at next_out */ - off_t total_out; /* total nb of bytes output so far */ + off_t total_out; /* total number of bytes output so far */ char *msg; /* last error message, NULL if no error */ struct internal_state FAR *state; /* not visible by applications */ @@ -1394,8 +1882,9 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) free_func zfree; /* used to free the internal state */ voidpf opaque; /* private data object passed to zalloc and zfree*/ - int data_type; /* best guess about the data type: binary or text*/ - uLong adler; /* adler32 value of the uncompressed data */ + int data_type; /* best guess about the data type: binary or text + for deflate, or the decoding state for inflate */ + uLong adler; /* Adler-32 or CRC-32 value of the uncompressed data */ uLong reserved; /* reserved for future use */ } z_stream; @@ -1410,12 +1899,12 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) uLong time; /* modification time */ int xflags; /*extra flags (not used when writing a gzip file)*/ int os; /* operating system */ - Bytef *extra; /* pointer to extra field or Z_NULL if none */ - uInt extra_len; /* extra field length (valid if extra != Z_NULL) */ + Bytef *extra; /* pointer to extra field or NULL if none */ + uInt extra_len; /* extra field length (valid if extra != NULL) */ uInt extra_max; /* space at extra (only when reading header) */ - Bytef *name; /* pointer to zero-terminated file name or Z_NULL*/ + Bytef *name; /* pointer to zero-terminated file name or NULL*/ uInt name_max; /* space at name (only when reading header) */ - Bytef *comment; /* pointer to zero-terminated comment or Z_NULL */ + Bytef *comment; /* pointer to zero-terminated comment or NULL */ uInt comm_max; /* space at comment (only when reading header) */ int hcrc; /* true if there was or will be a header crc */ int done; /* true when done reading gzip header (not used @@ -1431,37 +1920,41 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) compression library and must not be updated by the application. The [4mopaque[24m value provided by the application will be passed as the first - parameter for calls to [1mzalloc[22m() and [1mzfree[22m(). This can be useful for cus- + parameter for calls to [1mzalloc[22m() and [1mzfree[22m(). This can be useful for cus†tom memory management. The compression library attaches no meaning to the [4mopaque[24m value. - [4mzalloc[24m must return Z_NULL if there is not enough memory for the object. - If [1mzlib [22mis used in a multi-threaded application, [4mzalloc[24m and [4mzfree[24m must be - thread safe. + [4mzalloc[24m must return NULL if there is not enough memory for the object. If + [1mzlib [22mis used in a multi-threaded application, [4mzalloc[24m and [4mzfree[24m must be + thread safe. In that case, [1mzlib [22mis thread-safe. When [4mzalloc[24m and [4mzfree[0m + are NULL on entry to the initialization function, they are set to inter†+ nal routines that use the standard library functions malloc(3) and + free(3). - On 16-bit systems, the functions [4mzalloc[24m and [4mzfree[24m must be able to allo- + On 16-bit systems, the functions [4mzalloc[24m and [4mzfree[24m must be able to allo†cate exactly 65536 bytes, but will not be required to allocate more than this if the symbol MAXSEG_64K is defined (see <[4mzconf.h[24m>). WARNING: On MSDOS, pointers returned by [4mzalloc[24m for objects of exactly - 65536 bytes *must* have their offset normalized to zero. The default al- + 65536 bytes *must* have their offset normalized to zero. The default al†location function provided by this library ensures this (see [4mzutil.c[24m). To reduce memory requirements and avoid any allocation of 64K objects, at the expense of compression ratio, compile the library with -DMAX_WBITS=14 (see <[4mzconf.h[24m>). The fields [4mtotal_in[24m and [4mtotal_out[24m can be used for statistics or progress - reports. After compression, [4mtotal_in[24m holds the total size of the uncom- + reports. After compression, [4mtotal_in[24m holds the total size of the uncom†pressed data and may be saved for use in the decompressor (particularly if the decompressor wants to decompress everything in a single step). [1mCONSTANTS[0m #define Z_NO_FLUSH 0 - #define Z_PARTIAL_FLUSH 1 /* will be removed, use Z_SYNC_FLUSH instead */ + #define Z_PARTIAL_FLUSH 1 #define Z_SYNC_FLUSH 2 #define Z_FULL_FLUSH 3 #define Z_FINISH 4 - #define Z_BLOCK 5 + #define Z_BLOCK 5 + #define Z_TREES 6 /* Allowed flush values; see deflate() and inflate() below for details */ #define Z_OK 0 @@ -1495,7 +1988,7 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) #define Z_TEXT 1 #define Z_ASCII Z_TEXT /* for compatibility with 1.2.2 and earlier */ #define Z_UNKNOWN 2 - /* Possible values of the data_type field (though see inflate()) */ + /* Possible values of the data_type field for deflate() */ #define Z_DEFLATED 8 /* The deflate compression method @@ -1517,13 +2010,14 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) [4mint[24m [1minflateInit_[22m([4mz_stream[24m [4mstrm[24m, [4mconst[24m [4mchar[24m [4m*version[24m, [4mint[24m [4mstream_size[24m); [4mint[24m [1mdeflateInit2_[22m([4mz_stream[24m [4mstrm[24m, [4mint[24m [4mlevel[24m, [4mint[24m [4mmethod[24m, [4mint[24m [4mwindowBits[24m, - [4mint[24m [4mmemLevel[24m, [4mint[24m [4mstrategy[24m, [4mconst[24m [4mchar[24m [4m*version[24m, [4mint[24m [4mstream_size[24m) + [4mint[24m [4mmemLevel[24m, [4mint[24m [4mstrategy[24m, [4mconst[24m [4mchar[24m [4m*version[24m, + [4mint[24m [4mstream_size[24m); [4mint[24m [1minflateInit2_[22m([4mz_stream[24m [4mstrm[24m, [4mint[24m [4mwindowBits[24m, [4mconst[24m [4mchar[24m [4m*version[24m, [4mint[0m [4mstream_size[24m); [4mint[24m [1minflateBackInit_[22m([4mz_stream[24m [4m*strm[24m, [4mint[24m [4mwindowBits[24m, [4munsigned[24m [4mchar[24m [4mFAR[0m - [4m*window[24m, [4mconst[24m [4mchar[24m [4m*version[24m, [4mint[24m [4mstream_size[24m) + [4m*window[24m, [4mconst[24m [4mchar[24m [4m*version[24m, [4mint[24m [4mstream_size[24m); [4mconst[24m [4mchar[24m [4m*[24m [1mzError[22m([4mint[24m [4merr[24m); @@ -1553,4 +2047,4 @@ COMPRESS(3) BSD Library Functions Manual COMPRESS(3) Jean-loup Gailly <[4mjloup@gzip.org[24m> Mark Adler <[4mmadler@alumni.caltech.edu[24m> -BSD March 16, 2018 BSD +BSD July 6, 2021 BSD diff --git a/lib/libz/crc32.c b/lib/libz/crc32.c index fe88dba..35417e2 100644 --- a/lib/libz/crc32.c +++ b/lib/libz/crc32.c @@ -1,6 +1,6 @@ -/* $OpenBSD: crc32.c,v 1.8 2005/07/20 15:56:41 millert Exp $ */ +/* $OpenBSD: crc32.c,v 1.9 2021/07/04 14:24:49 tb Exp $ */ /* crc32.c -- compute the CRC-32 of a data stream - * Copyright (C) 1995-2005 Mark Adler + * Copyright (C) 1995-2006, 2010, 2011, 2012, 2016 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h * * Thanks to Rodney Brown <rbrown64@csc.com.au> for his contribution of faster @@ -16,6 +16,8 @@ of the crc tables. Therefore, if you #define DYNAMIC_CRC_TABLE, you should first call get_crc_table() to initialize the tables before allowing more than one thread to use crc32(). + + DYNAMIC_CRC_TABLE and MAKECRCH can be #defined to write out crc32.h. */ #ifdef MAKECRCH @@ -24,40 +26,18 @@ # define DYNAMIC_CRC_TABLE # endif /* !DYNAMIC_CRC_TABLE */ #endif /* MAKECRCH */ - -#include "zutil.h" /* for STDC and FAR definitions */ -#define local static - -/* Find a four-byte integer type for crc32_little() and crc32_big(). */ -#ifndef NOBYFOUR -# ifdef STDC /* need ANSI C limits.h to determine sizes */ -# include <limits.h> -# define BYFOUR -# if (UINT_MAX == 0xffffffffUL) - typedef unsigned int u4; -# else -# if (ULONG_MAX == 0xffffffffUL) - typedef unsigned long u4; -# else -# if (USHRT_MAX == 0xffffffffUL) - typedef unsigned short u4; -# else -# undef BYFOUR /* can't find a four-byte integer type! */ -# endif -# endif -# endif -# endif /* STDC */ -#endif /* !NOBYFOUR */ +#include "zutil.h" /* for STDC and FAR definitions */ /* Definitions for doing the crc four data bytes at a time. */ +#if !defined(NOBYFOUR) && defined(Z_U4) +# define BYFOUR +#endif #ifdef BYFOUR -# define REV(w) (((w)>>24)+(((w)>>8)&0xff00)+ \ - (((w)&0xff00)<<8)+(((w)&0xff)<<24)) local unsigned long crc32_little OF((unsigned long, - const unsigned char FAR *, unsigned)); + const unsigned char FAR *, z_size_t)); local unsigned long crc32_big OF((unsigned long, - const unsigned char FAR *, unsigned)); + const unsigned char FAR *, z_size_t)); # define TBLS 8 #else # define TBLS 1 @@ -67,14 +47,16 @@ local unsigned long gf2_matrix_times OF((unsigned long *mat, unsigned long vec)); local void gf2_matrix_square OF((unsigned long *square, unsigned long *mat)); +local uLong crc32_combine_ OF((uLong crc1, uLong crc2, z_off64_t len2)); + #ifdef DYNAMIC_CRC_TABLE local volatile int crc_table_empty = 1; -local unsigned long FAR crc_table[TBLS][256]; +local z_crc_t FAR crc_table[TBLS][256]; local void make_crc_table OF((void)); #ifdef MAKECRCH - local void write_table OF((FILE *, const unsigned long FAR *)); + local void write_table OF((FILE *, const z_crc_t FAR *)); #endif /* MAKECRCH */ /* Generate tables for a byte-wise 32-bit CRC calculation on the polynomial: @@ -104,9 +86,9 @@ local void make_crc_table OF((void)); */ local void make_crc_table() { - unsigned long c; + z_crc_t c; int n, k; - unsigned long poly; /* polynomial exclusive-or pattern */ + z_crc_t poly; /* polynomial exclusive-or pattern */ /* terms of polynomial defining this crc (except x^32): */ static volatile int first = 1; /* flag to limit concurrent making */ static const unsigned char p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26}; @@ -118,13 +100,13 @@ local void make_crc_table() first = 0; /* make exclusive-or pattern from polynomial (0xedb88320UL) */ - poly = 0UL; - for (n = 0; n < sizeof(p)/sizeof(unsigned char); n++) - poly |= 1UL << (31 - p[n]); + poly = 0; + for (n = 0; n < (int)(sizeof(p)/sizeof(unsigned char)); n++) + poly |= (z_crc_t)1 << (31 - p[n]); /* generate a crc for every 8-bit value */ for (n = 0; n < 256; n++) { - c = (unsigned long)n; + c = (z_crc_t)n; for (k = 0; k < 8; k++) c = c & 1 ? poly ^ (c >> 1) : c >> 1; crc_table[0][n] = c; @@ -135,11 +117,11 @@ local void make_crc_table() and then the byte reversal of those as well as the first table */ for (n = 0; n < 256; n++) { c = crc_table[0][n]; - crc_table[4][n] = REV(c); + crc_table[4][n] = ZSWAP32(c); for (k = 1; k < 4; k++) { c = crc_table[0][c & 0xff] ^ (c >> 8); crc_table[k][n] = c; - crc_table[k + 4][n] = REV(c); + crc_table[k + 4][n] = ZSWAP32(c); } } #endif /* BYFOUR */ @@ -161,7 +143,7 @@ local void make_crc_table() if (out == NULL) return; fprintf(out, "/* crc32.h -- tables for rapid CRC calculation\n"); fprintf(out, " * Generated automatically by crc32.c\n */\n\n"); - fprintf(out, "local const unsigned long FAR "); + fprintf(out, "local const z_crc_t FAR "); fprintf(out, "crc_table[TBLS][256] =\n{\n {\n"); write_table(out, crc_table[0]); # ifdef BYFOUR @@ -181,12 +163,13 @@ local void make_crc_table() #ifdef MAKECRCH local void write_table(out, table) FILE *out; - const unsigned long FAR *table; + const z_crc_t FAR *table; { int n; for (n = 0; n < 256; n++) - fprintf(out, "%s0x%08lxUL%s", n % 5 ? "" : " ", table[n], + fprintf(out, "%s0x%08lxUL%s", n % 5 ? "" : " ", + (unsigned long)(table[n]), n == 255 ? "\n" : (n % 5 == 4 ? ",\n" : ", ")); } #endif /* MAKECRCH */ @@ -201,13 +184,13 @@ local void write_table(out, table) /* ========================================================================= * This function can be used by asm versions of crc32() */ -const unsigned long FAR * ZEXPORT get_crc_table() +const z_crc_t FAR * ZEXPORT get_crc_table() { #ifdef DYNAMIC_CRC_TABLE if (crc_table_empty) make_crc_table(); #endif /* DYNAMIC_CRC_TABLE */ - return (const unsigned long FAR *)crc_table; + return (const z_crc_t FAR *)crc_table; } /* ========================================================================= */ @@ -215,10 +198,10 @@ const unsigned long FAR * ZEXPORT get_crc_table() #define DO8 DO1; DO1; DO1; DO1; DO1; DO1; DO1; DO1 /* ========================================================================= */ -unsigned long ZEXPORT crc32(crc, buf, len) +unsigned long ZEXPORT crc32_z(crc, buf, len) unsigned long crc; const unsigned char FAR *buf; - unsigned len; + z_size_t len; { if (buf == Z_NULL) return 0UL; @@ -229,7 +212,7 @@ unsigned long ZEXPORT crc32(crc, buf, len) #ifdef BYFOUR if (sizeof(void *) == sizeof(ptrdiff_t)) { - u4 endian; + z_crc_t endian; endian = 1; if (*((unsigned char *)(&endian))) @@ -249,8 +232,29 @@ unsigned long ZEXPORT crc32(crc, buf, len) return crc ^ 0xffffffffUL; } +/* ========================================================================= */ +unsigned long ZEXPORT crc32(crc, buf, len) + unsigned long crc; + const unsigned char FAR *buf; + uInt len; +{ + return crc32_z(crc, buf, len); +} + #ifdef BYFOUR +/* + This BYFOUR code accesses the passed unsigned char * buffer with a 32-bit + integer pointer type. This violates the strict aliasing rule, where a + compiler can assume, for optimization purposes, that two pointers to + fundamentally different types won't ever point to the same memory. This can + manifest as a problem only if one of the pointers is written to. This code + only reads from those pointers. So long as this code remains isolated in + this compilation unit, there won't be a problem. For this reason, this code + should not be copied and pasted into a compilation unit in which other code + writes to the buffer that is passed to these routines. + */ + /* ========================================================================= */ #define DOLIT4 c ^= *buf4++; \ c = crc_table[3][c & 0xff] ^ crc_table[2][(c >> 8) & 0xff] ^ \ @@ -261,19 +265,19 @@ unsigned long ZEXPORT crc32(crc, buf, len) local unsigned long crc32_little(crc, buf, len) unsigned long crc; const unsigned char FAR *buf; - unsigned len; + z_size_t len; { - register u4 c; - register const u4 FAR *buf4; + register z_crc_t c; + register const z_crc_t FAR *buf4; - c = (u4)crc; + c = (z_crc_t)crc; c = ~c; while (len && ((ptrdiff_t)buf & 3)) { c = crc_table[0][(c ^ *buf++) & 0xff] ^ (c >> 8); len--; } - buf4 = (const u4 FAR *)(const void FAR *)buf; + buf4 = (const z_crc_t FAR *)(const void FAR *)buf; while (len >= 32) { DOLIT32; len -= 32; @@ -292,7 +296,7 @@ local unsigned long crc32_little(crc, buf, len) } /* ========================================================================= */ -#define DOBIG4 c ^= *++buf4; \ +#define DOBIG4 c ^= *buf4++; \ c = crc_table[4][c & 0xff] ^ crc_table[5][(c >> 8) & 0xff] ^ \ crc_table[6][(c >> 16) & 0xff] ^ crc_table[7][c >> 24] #define DOBIG32 DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4 @@ -301,20 +305,19 @@ local unsigned long crc32_little(crc, buf, len) local unsigned long crc32_big(crc, buf, len) unsigned long crc; const unsigned char FAR *buf; - unsigned len; + z_size_t len; { - register u4 c; - register const u4 FAR *buf4; + register z_crc_t c; + register const z_crc_t FAR *buf4; - c = REV((u4)crc); + c = ZSWAP32((z_crc_t)crc); c = ~c; while (len && ((ptrdiff_t)buf & 3)) { c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8); len--; } - buf4 = (const u4 FAR *)(const void FAR *)buf; - buf4--; + buf4 = (const z_crc_t FAR *)(const void FAR *)buf; while (len >= 32) { DOBIG32; len -= 32; @@ -323,14 +326,13 @@ local unsigned long crc32_big(crc, buf, len) DOBIG4; len -= 4; } - buf4++; buf = (const unsigned char FAR *)buf4; if (len) do { c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8); } while (--len); c = ~c; - return (unsigned long)(REV(c)); + return (unsigned long)(ZSWAP32(c)); } #endif /* BYFOUR */ @@ -366,22 +368,22 @@ local void gf2_matrix_square(square, mat) } /* ========================================================================= */ -uLong ZEXPORT crc32_combine(crc1, crc2, len2) +local uLong crc32_combine_(crc1, crc2, len2) uLong crc1; uLong crc2; - z_off_t len2; + z_off64_t len2; { int n; unsigned long row; unsigned long even[GF2_DIM]; /* even-power-of-two zeros operator */ unsigned long odd[GF2_DIM]; /* odd-power-of-two zeros operator */ - /* degenerate case */ - if (len2 == 0) + /* degenerate case (also disallow negative lengths) */ + if (len2 <= 0) return crc1; /* put operator for one zero bit in odd */ - odd[0] = 0xedb88320L; /* CRC-32 polynomial */ + odd[0] = 0xedb88320UL; /* CRC-32 polynomial */ row = 1; for (n = 1; n < GF2_DIM; n++) { odd[n] = row; @@ -420,3 +422,20 @@ uLong ZEXPORT crc32_combine(crc1, crc2, len2) crc1 ^= crc2; return crc1; } + +/* ========================================================================= */ +uLong ZEXPORT crc32_combine(crc1, crc2, len2) + uLong crc1; + uLong crc2; + z_off_t len2; +{ + return crc32_combine_(crc1, crc2, len2); +} + +uLong ZEXPORT crc32_combine64(crc1, crc2, len2) + uLong crc1; + uLong crc2; + z_off64_t len2; +{ + return crc32_combine_(crc1, crc2, len2); +} diff --git a/lib/libz/crc32.h b/lib/libz/crc32.h index 8053b61..8a4c267 100644 --- a/lib/libz/crc32.h +++ b/lib/libz/crc32.h @@ -1,8 +1,10 @@ +/* $OpenBSD: crc32.h,v 1.3 2021/07/04 17:41:23 tb Exp $ */ + /* crc32.h -- tables for rapid CRC calculation * Generated automatically by crc32.c */ -local const unsigned long FAR crc_table[TBLS][256] = +local const z_crc_t FAR crc_table[TBLS][256] = { { 0x00000000UL, 0x77073096UL, 0xee0e612cUL, 0x990951baUL, 0x076dc419UL, diff --git a/lib/libz/deflate.c b/lib/libz/deflate.c index 5cc3f7a..55cc69e 100644 --- a/lib/libz/deflate.c +++ b/lib/libz/deflate.c @@ -1,6 +1,6 @@ -/* $OpenBSD: deflate.c,v 1.11 2009/10/27 23:59:31 deraadt Exp $ */ +/* $OpenBSD: deflate.c,v 1.12 2021/07/04 14:24:49 tb Exp $ */ /* deflate.c -- compress data using the deflation algorithm - * Copyright (C) 1995-2005 Jean-loup Gailly. + * Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -38,7 +38,7 @@ * REFERENCES * * Deutsch, L.P.,"DEFLATE Compressed Data Format Specification". - * Available in http://www.ietf.org/rfc/rfc1951.txt + * Available in http://tools.ietf.org/html/rfc1951 * * A description of the Rabin and Karp algorithm is given in the book * "Algorithms" by R. Sedgewick, Addison-Wesley, p252. @@ -48,7 +48,6 @@ * */ - #include "deflate.h" /* @@ -71,27 +70,29 @@ typedef enum { typedef block_state (*compress_func) OF((deflate_state *s, int flush)); /* Compression function. Returns the block state after the call. */ +local int deflateStateCheck OF((z_streamp strm)); +local void slide_hash OF((deflate_state *s)); local void fill_window OF((deflate_state *s)); local block_state deflate_stored OF((deflate_state *s, int flush)); local block_state deflate_fast OF((deflate_state *s, int flush)); #ifndef FASTEST local block_state deflate_slow OF((deflate_state *s, int flush)); #endif +local block_state deflate_rle OF((deflate_state *s, int flush)); +local block_state deflate_huff OF((deflate_state *s, int flush)); local void lm_init OF((deflate_state *s)); local void putShortMSB OF((deflate_state *s, uInt b)); local void flush_pending OF((z_streamp strm)); -local int read_buf OF((z_streamp strm, Bytef *buf, unsigned size)); -#ifndef FASTEST +local unsigned read_buf OF((z_streamp strm, Bytef *buf, unsigned size)); #ifdef ASMV +# pragma message("Assembler code may have bugs -- use at your own risk") void match_init OF((void)); /* asm code initialization */ uInt longest_match OF((deflate_state *s, IPos cur_match)); #else local uInt longest_match OF((deflate_state *s, IPos cur_match)); #endif -#endif -local uInt longest_match_fast OF((deflate_state *s, IPos cur_match)); -#ifdef DEBUG +#ifdef ZLIB_DEBUG local void check_match OF((deflate_state *s, IPos start, IPos match, int length)); #endif @@ -108,11 +109,6 @@ local void check_match OF((deflate_state *s, IPos start, IPos match, #endif /* Matches of length 3 are discarded if their distance exceeds TOO_FAR */ -#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) -/* Minimum amount of lookahead, except at the end of the input file. - * See deflate.c for comments about the MIN_MATCH+1. - */ - /* Values for max_lazy_match, good_match and max_chain_length, depending on * the desired pack level (0..9). The values given below have been tuned to * exclude worst case performance for pathological files. Better values may be @@ -152,18 +148,14 @@ local const config configuration_table[10] = { * meaning. */ -#define EQUAL 0 -/* result of memcmp for equal strings */ - -#ifndef NO_DUMMY_DECL -struct static_tree_desc_s {int dummy;}; /* for buggy compilers */ -#endif +/* rank Z_BLOCK between Z_NO_FLUSH and Z_PARTIAL_FLUSH */ +#define RANK(f) (((f) * 2) - ((f) > 4 ? 9 : 0)) /* =========================================================================== * Update a hash value with the given input byte - * IN assertion: all calls to UPDATE_HASH are made with consecutive - * input characters, so that a running hash key can be computed from the - * previous key instead of complete recalculation each time. + * IN assertion: all calls to UPDATE_HASH are made with consecutive input + * characters, so that a running hash key can be computed from the previous + * key instead of complete recalculation each time. */ #define UPDATE_HASH(s,h,c) (h = (((h)<<s->hash_shift) ^ (c)) & s->hash_mask) @@ -174,9 +166,9 @@ struct static_tree_desc_s {int dummy;}; /* for buggy compilers */ * the previous length of the hash chain. * If this file is compiled with -DFASTEST, the compression level is forced * to 1, and no hash chains are maintained. - * IN assertion: all calls to INSERT_STRING are made with consecutive - * input characters and the first MIN_MATCH bytes of str are valid - * (except for the last MIN_MATCH-1 bytes of the input file). + * IN assertion: all calls to INSERT_STRING are made with consecutive input + * characters and the first MIN_MATCH bytes of str are valid (except for + * the last MIN_MATCH-1 bytes of the input file). */ #ifdef FASTEST #define INSERT_STRING(s, str, match_head) \ @@ -198,6 +190,37 @@ struct static_tree_desc_s {int dummy;}; /* for buggy compilers */ s->head[s->hash_size-1] = NIL; \ zmemzero((Bytef *)s->head, (unsigned)(s->hash_size-1)*sizeof(*s->head)); +/* =========================================================================== + * Slide the hash table when sliding the window down (could be avoided with 32 + * bit values at the expense of memory usage). We slide even when level == 0 to + * keep the hash table consistent if we switch back to level > 0 later. + */ +local void slide_hash(s) + deflate_state *s; +{ + unsigned n, m; + Posf *p; + uInt wsize = s->w_size; + + n = s->hash_size; + p = &s->head[n]; + do { + m = *--p; + *p = (Pos)(m >= wsize ? m - wsize : NIL); + } while (--n); + n = wsize; +#ifndef FASTEST + p = &s->prev[n]; + do { + m = *--p; + *p = (Pos)(m >= wsize ? m - wsize : NIL); + /* If n is not on any hash chain, prev[n] is garbage but + * its value will never be used. + */ + } while (--n); +#endif +} + /* ========================================================================= */ int ZEXPORT deflateInit_(strm, level, version, stream_size) z_streamp strm; @@ -239,10 +262,19 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, strm->msg = Z_NULL; if (strm->zalloc == (alloc_func)0) { +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else strm->zalloc = zcalloc; strm->opaque = (voidpf)0; +#endif } - if (strm->zfree == (free_func)0) strm->zfree = zcfree; + if (strm->zfree == (free_func)0) +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else + strm->zfree = zcfree; +#endif #ifdef FASTEST if (level != 0) level = 1; @@ -262,7 +294,7 @@ 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_FIXED) { + strategy < 0 || strategy > Z_FIXED || (windowBits == 8 && wrap != 1)) { return Z_STREAM_ERROR; } if (windowBits == 8) windowBits = 9; /* until 256-byte window bug fixed */ @@ -270,14 +302,15 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, if (s == Z_NULL) return Z_MEM_ERROR; strm->state = (struct internal_state FAR *)s; s->strm = strm; + s->status = INIT_STATE; /* to pass state test in deflateReset() */ s->wrap = wrap; s->gzhead = Z_NULL; - s->w_bits = windowBits; + s->w_bits = (uInt)windowBits; s->w_size = 1 << s->w_bits; s->w_mask = s->w_size - 1; - s->hash_bits = memLevel + 7; + s->hash_bits = (uInt)memLevel + 7; s->hash_size = 1 << s->hash_bits; s->hash_mask = s->hash_size - 1; s->hash_shift = ((s->hash_bits+MIN_MATCH-1)/MIN_MATCH); @@ -286,6 +319,8 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, s->prev = (Posf *) ZALLOC(strm, s->w_size, sizeof(Pos)); s->head = (Posf *) ZALLOC(strm, s->hash_size, sizeof(Pos)); + s->high_water = 0; /* nothing written to s->window yet */ + s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */ overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2); @@ -295,7 +330,7 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL || s->pending_buf == Z_NULL) { s->status = FINISH_STATE; - strm->msg = (char*)ERR_MSG(Z_MEM_ERROR); + strm->msg = ERR_MSG(Z_MEM_ERROR); deflateEnd (strm); return Z_MEM_ERROR; } @@ -309,6 +344,31 @@ int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, return deflateReset(strm); } +/* ========================================================================= + * Check for a valid deflate stream state. Return 0 if ok, 1 if not. + */ +local int deflateStateCheck (strm) + z_streamp strm; +{ + deflate_state *s; + if (strm == Z_NULL || + strm->zalloc == (alloc_func)0 || strm->zfree == (free_func)0) + return 1; + s = strm->state; + if (s == Z_NULL || s->strm != strm || (s->status != INIT_STATE && +#ifdef GZIP + s->status != GZIP_STATE && +#endif + s->status != EXTRA_STATE && + s->status != NAME_STATE && + s->status != COMMENT_STATE && + s->status != HCRC_STATE && + s->status != BUSY_STATE && + s->status != FINISH_STATE)) + return 1; + return 0; +} + /* ========================================================================= */ int ZEXPORT deflateSetDictionary (strm, dictionary, dictLength) z_streamp strm; @@ -316,49 +376,97 @@ int ZEXPORT deflateSetDictionary (strm, dictionary, dictLength) uInt dictLength; { deflate_state *s; - uInt length = dictLength; - uInt n; - IPos hash_head = 0; + uInt str, n; + int wrap; + unsigned avail; + z_const unsigned char *next; - if (strm == Z_NULL || strm->state == Z_NULL || dictionary == Z_NULL || - strm->state->wrap == 2 || - (strm->state->wrap == 1 && strm->state->status != INIT_STATE)) + if (deflateStateCheck(strm) || dictionary == Z_NULL) return Z_STREAM_ERROR; - s = strm->state; - if (s->wrap) - strm->adler = adler32(strm->adler, dictionary, dictLength); + wrap = s->wrap; + if (wrap == 2 || (wrap == 1 && s->status != INIT_STATE) || s->lookahead) + return Z_STREAM_ERROR; - if (length < MIN_MATCH) return Z_OK; - if (length > MAX_DIST(s)) { - length = MAX_DIST(s); - dictionary += dictLength - length; /* use the tail of the dictionary */ + /* when using zlib wrappers, compute Adler-32 for provided dictionary */ + if (wrap == 1) + strm->adler = adler32(strm->adler, dictionary, dictLength); + s->wrap = 0; /* avoid computing Adler-32 in read_buf */ + + /* if dictionary would fill window, just replace the history */ + if (dictLength >= s->w_size) { + if (wrap == 0) { /* already empty otherwise */ + CLEAR_HASH(s); + s->strstart = 0; + s->block_start = 0L; + s->insert = 0; + } + dictionary += dictLength - s->w_size; /* use the tail */ + dictLength = s->w_size; } - zmemcpy(s->window, dictionary, length); - s->strstart = length; - s->block_start = (long)length; - /* Insert all strings in the hash table (except for the last two bytes). - * s->lookahead stays null, so s->ins_h will be recomputed at the next - * call of fill_window. - */ - s->ins_h = s->window[0]; - UPDATE_HASH(s, s->ins_h, s->window[1]); - for (n = 0; n <= length - MIN_MATCH; n++) { - INSERT_STRING(s, n, hash_head); + /* insert dictionary into window and hash */ + avail = strm->avail_in; + next = strm->next_in; + strm->avail_in = dictLength; + strm->next_in = (z_const Bytef *)dictionary; + fill_window(s); + while (s->lookahead >= MIN_MATCH) { + str = s->strstart; + n = s->lookahead - (MIN_MATCH-1); + do { + UPDATE_HASH(s, s->ins_h, s->window[str + MIN_MATCH-1]); +#ifndef FASTEST + s->prev[str & s->w_mask] = s->head[s->ins_h]; +#endif + s->head[s->ins_h] = (Pos)str; + str++; + } while (--n); + s->strstart = str; + s->lookahead = MIN_MATCH-1; + fill_window(s); } - if (hash_head) hash_head = 0; /* to make compiler happy */ + s->strstart += s->lookahead; + s->block_start = (long)s->strstart; + s->insert = s->lookahead; + s->lookahead = 0; + s->match_length = s->prev_length = MIN_MATCH-1; + s->match_available = 0; + strm->next_in = next; + strm->avail_in = avail; + s->wrap = wrap; return Z_OK; } /* ========================================================================= */ -int ZEXPORT deflateReset (strm) +int ZEXPORT deflateGetDictionary (strm, dictionary, dictLength) z_streamp strm; + Bytef *dictionary; + uInt *dictLength; { deflate_state *s; + uInt len; - if (strm == Z_NULL || strm->state == Z_NULL || - strm->zalloc == (alloc_func)0 || strm->zfree == (free_func)0) { + if (deflateStateCheck(strm)) + return Z_STREAM_ERROR; + s = strm->state; + len = s->strstart + s->lookahead; + if (len > s->w_size) + len = s->w_size; + if (dictionary != Z_NULL && len) + zmemcpy(dictionary, s->window + s->strstart + s->lookahead - len, len); + if (dictLength != Z_NULL) + *dictLength = len; + return Z_OK; +} + +/* ========================================================================= */ +int ZEXPORT deflateResetKeep (strm) + z_streamp strm; +{ + deflate_state *s; + + if (deflateStateCheck(strm)) { return Z_STREAM_ERROR; } @@ -373,7 +481,11 @@ int ZEXPORT deflateReset (strm) if (s->wrap < 0) { s->wrap = -s->wrap; /* was made negative by deflate(..., Z_FINISH); */ } - s->status = s->wrap ? INIT_STATE : BUSY_STATE; + s->status = +#ifdef GZIP + s->wrap == 2 ? GZIP_STATE : +#endif + s->wrap ? INIT_STATE : BUSY_STATE; strm->adler = #ifdef GZIP s->wrap == 2 ? crc32(0L, Z_NULL, 0) : @@ -382,31 +494,70 @@ int ZEXPORT deflateReset (strm) s->last_flush = Z_NO_FLUSH; _tr_init(s); - lm_init(s); return Z_OK; } /* ========================================================================= */ +int ZEXPORT deflateReset (strm) + z_streamp strm; +{ + int ret; + + ret = deflateResetKeep(strm); + if (ret == Z_OK) + lm_init(strm->state); + return ret; +} + +/* ========================================================================= */ int ZEXPORT deflateSetHeader (strm, head) z_streamp strm; gz_headerp head; { - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; - if (strm->state->wrap != 2) return Z_STREAM_ERROR; + if (deflateStateCheck(strm) || strm->state->wrap != 2) + return Z_STREAM_ERROR; strm->state->gzhead = head; return Z_OK; } /* ========================================================================= */ +int ZEXPORT deflatePending (strm, pending, bits) + unsigned *pending; + int *bits; + z_streamp strm; +{ + if (deflateStateCheck(strm)) return Z_STREAM_ERROR; + if (pending != Z_NULL) + *pending = strm->state->pending; + if (bits != Z_NULL) + *bits = strm->state->bi_valid; + return Z_OK; +} + +/* ========================================================================= */ int ZEXPORT deflatePrime (strm, bits, value) z_streamp strm; int bits; int value; { - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; - strm->state->bi_valid = bits; - strm->state->bi_buf = (ush)(value & ((1 << bits) - 1)); + deflate_state *s; + int put; + + if (deflateStateCheck(strm)) return Z_STREAM_ERROR; + s = strm->state; + if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3)) + return Z_BUF_ERROR; + do { + put = Buf_size - s->bi_valid; + if (put > bits) + put = bits; + s->bi_buf |= (ush)((value & ((1 << put) - 1)) << s->bi_valid); + s->bi_valid += put; + _tr_flush_bits(s); + value >>= put; + bits -= put; + } while (bits); return Z_OK; } @@ -418,9 +569,8 @@ int ZEXPORT deflateParams(strm, level, strategy) { deflate_state *s; compress_func func; - int err = Z_OK; - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (deflateStateCheck(strm)) return Z_STREAM_ERROR; s = strm->state; #ifdef FASTEST @@ -433,11 +583,23 @@ int ZEXPORT deflateParams(strm, level, strategy) } func = configuration_table[s->level].func; - if (func != configuration_table[level].func && strm->total_in != 0) { + if ((strategy != s->strategy || func != configuration_table[level].func) && + s->high_water) { /* Flush the last buffer: */ - err = deflate(strm, Z_PARTIAL_FLUSH); + int err = deflate(strm, Z_BLOCK); + if (err == Z_STREAM_ERROR) + return err; + if (strm->avail_out == 0) + return Z_BUF_ERROR; } if (s->level != level) { + if (s->level == 0 && s->matches != 0) { + if (s->matches == 1) + slide_hash(s); + else + CLEAR_HASH(s); + s->matches = 0; + } s->level = level; s->max_lazy_match = configuration_table[level].max_lazy; s->good_match = configuration_table[level].good_length; @@ -445,7 +607,7 @@ int ZEXPORT deflateParams(strm, level, strategy) s->max_chain_length = configuration_table[level].max_chain; } s->strategy = strategy; - return err; + return Z_OK; } /* ========================================================================= */ @@ -458,12 +620,12 @@ int ZEXPORT deflateTune(strm, good_length, max_lazy, nice_length, max_chain) { deflate_state *s; - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (deflateStateCheck(strm)) return Z_STREAM_ERROR; s = strm->state; - s->good_match = good_length; - s->max_lazy_match = max_lazy; + s->good_match = (uInt)good_length; + s->max_lazy_match = (uInt)max_lazy; s->nice_match = nice_length; - s->max_chain_length = max_chain; + s->max_chain_length = (uInt)max_chain; return Z_OK; } @@ -479,33 +641,68 @@ int ZEXPORT deflateTune(strm, good_length, max_lazy, nice_length, max_chain) * resulting from using fixed blocks instead of stored blocks, which deflate * can emit on compressed data for some combinations of the parameters. * - * This function could be more sophisticated to provide closer upper bounds - * for every combination of windowBits and memLevel, as well as wrap. - * But even the conservative upper bound of about 14% expansion does not - * seem onerous for output buffer allocation. + * This function could be more sophisticated to provide closer upper bounds for + * every combination of windowBits and memLevel. But even the conservative + * upper bound of about 14% expansion does not seem onerous for output buffer + * allocation. */ uLong ZEXPORT deflateBound(strm, sourceLen) z_streamp strm; uLong sourceLen; { deflate_state *s; - uLong destLen; + uLong complen, wraplen; - /* conservative upper bound */ - destLen = sourceLen + - ((sourceLen + 7) >> 3) + ((sourceLen + 63) >> 6) + 11; + /* conservative upper bound for compressed data */ + complen = sourceLen + + ((sourceLen + 7) >> 3) + ((sourceLen + 63) >> 6) + 5; - /* if can't get parameters, return conservative bound */ - if (strm == Z_NULL || strm->state == Z_NULL) - return destLen; + /* if can't get parameters, return conservative bound plus zlib wrapper */ + if (deflateStateCheck(strm)) + return complen + 6; - /* if not default parameters, return conservative bound */ + /* compute wrapper length */ s = strm->state; + switch (s->wrap) { + case 0: /* raw deflate */ + wraplen = 0; + break; + case 1: /* zlib wrapper */ + wraplen = 6 + (s->strstart ? 4 : 0); + break; +#ifdef GZIP + case 2: /* gzip wrapper */ + wraplen = 18; + if (s->gzhead != Z_NULL) { /* user-supplied gzip header */ + Bytef *str; + if (s->gzhead->extra != Z_NULL) + wraplen += 2 + s->gzhead->extra_len; + str = s->gzhead->name; + if (str != Z_NULL) + do { + wraplen++; + } while (*str++); + str = s->gzhead->comment; + if (str != Z_NULL) + do { + wraplen++; + } while (*str++); + if (s->gzhead->hcrc) + wraplen += 2; + } + break; +#endif + default: /* for compiler happiness */ + wraplen = 6; + } + + /* if not default parameters, return conservative bound */ if (s->w_bits != 15 || s->hash_bits != 8 + 7) - return destLen; + return complen + wraplen; /* default settings: return tight bound for that case */ - return compressBound(sourceLen); + return sourceLen + (sourceLen >> 12) + (sourceLen >> 14) + + (sourceLen >> 25) + 13 - 6 + wraplen; } /* ========================================================================= @@ -522,30 +719,43 @@ local void putShortMSB (s, b) } /* ========================================================================= - * Flush as much pending output as possible. All deflate() output goes - * through this function so some applications may wish to modify it - * to avoid allocating a large strm->next_out buffer and copying into it. - * (See also read_buf()). + * Flush as much pending output as possible. All deflate() output, except for + * some deflate_stored() output, goes through this function so some + * applications may wish to modify it to avoid allocating a large + * strm->next_out buffer and copying into it. (See also read_buf()). */ local void flush_pending(strm) z_streamp strm; { - unsigned len = strm->state->pending; + unsigned len; + deflate_state *s = strm->state; + _tr_flush_bits(s); + len = s->pending; if (len > strm->avail_out) len = strm->avail_out; if (len == 0) return; - zmemcpy(strm->next_out, strm->state->pending_out, len); + zmemcpy(strm->next_out, s->pending_out, len); strm->next_out += len; - strm->state->pending_out += len; + s->pending_out += len; strm->total_out += len; - strm->avail_out -= len; - strm->state->pending -= len; - if (strm->state->pending == 0) { - strm->state->pending_out = strm->state->pending_buf; + strm->avail_out -= len; + s->pending -= len; + if (s->pending == 0) { + s->pending_out = s->pending_buf; } } +/* =========================================================================== + * Update the header CRC with the bytes s->pending_buf[beg..s->pending - 1]. + */ +#define HCRC_UPDATE(beg) \ + do { \ + if (s->gzhead->hcrc && s->pending > (beg)) \ + strm->adler = crc32(strm->adler, s->pending_buf + (beg), \ + s->pending - (beg)); \ + } while (0) + /* ========================================================================= */ int ZEXPORT deflate (strm, flush) z_streamp strm; @@ -554,230 +764,229 @@ int ZEXPORT deflate (strm, flush) int old_flush; /* value of flush param for previous deflate call */ deflate_state *s; - if (strm == Z_NULL || strm->state == Z_NULL || - flush > Z_FINISH || flush < 0) { + if (deflateStateCheck(strm) || flush > Z_BLOCK || flush < 0) { return Z_STREAM_ERROR; } s = strm->state; if (strm->next_out == Z_NULL || - (strm->next_in == Z_NULL && strm->avail_in != 0) || + (strm->avail_in != 0 && strm->next_in == Z_NULL) || (s->status == FINISH_STATE && flush != Z_FINISH)) { ERR_RETURN(strm, Z_STREAM_ERROR); } if (strm->avail_out == 0) ERR_RETURN(strm, Z_BUF_ERROR); - s->strm = strm; /* just in case */ old_flush = s->last_flush; s->last_flush = flush; + /* Flush as much pending output as possible */ + if (s->pending != 0) { + flush_pending(strm); + if (strm->avail_out == 0) { + /* Since avail_out is 0, deflate will be called again with + * more output space, but possibly with both pending and + * avail_in equal to zero. There won't be anything to do, + * but this is not an error situation so make sure we + * return OK instead of BUF_ERROR at next call of deflate: + */ + s->last_flush = -1; + return Z_OK; + } + + /* Make sure there is something to do and avoid duplicate consecutive + * flushes. For repeated and useless calls with Z_FINISH, we keep + * returning Z_STREAM_END instead of Z_BUF_ERROR. + */ + } else if (strm->avail_in == 0 && RANK(flush) <= RANK(old_flush) && + flush != Z_FINISH) { + ERR_RETURN(strm, Z_BUF_ERROR); + } + + /* User must not provide more input after the first FINISH: */ + if (s->status == FINISH_STATE && strm->avail_in != 0) { + ERR_RETURN(strm, Z_BUF_ERROR); + } + /* Write the header */ if (s->status == INIT_STATE) { -#ifdef GZIP - if (s->wrap == 2) { - strm->adler = crc32(0L, Z_NULL, 0); - put_byte(s, 31); - put_byte(s, 139); - put_byte(s, 8); - if (s->gzhead == NULL) { - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, s->level == 9 ? 2 : - (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? - 4 : 0)); - put_byte(s, OS_CODE); - s->status = BUSY_STATE; - } - else { - put_byte(s, (s->gzhead->text ? 1 : 0) + - (s->gzhead->hcrc ? 2 : 0) + - (s->gzhead->extra == Z_NULL ? 0 : 4) + - (s->gzhead->name == Z_NULL ? 0 : 8) + - (s->gzhead->comment == Z_NULL ? 0 : 16) - ); - put_byte(s, (Byte)(s->gzhead->time & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 8) & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 16) & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 24) & 0xff)); - put_byte(s, s->level == 9 ? 2 : - (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? - 4 : 0)); - put_byte(s, s->gzhead->os & 0xff); - if (s->gzhead->extra != NULL) { - put_byte(s, s->gzhead->extra_len & 0xff); - put_byte(s, (s->gzhead->extra_len >> 8) & 0xff); - } - if (s->gzhead->hcrc) - strm->adler = crc32(strm->adler, s->pending_buf, - s->pending); - s->gzindex = 0; - s->status = EXTRA_STATE; - } - } + /* zlib header */ + uInt header = (Z_DEFLATED + ((s->w_bits-8)<<4)) << 8; + uInt level_flags; + + if (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2) + level_flags = 0; + else if (s->level < 6) + level_flags = 1; + else if (s->level == 6) + level_flags = 2; else -#endif - { - uInt header = (Z_DEFLATED + ((s->w_bits-8)<<4)) << 8; - uInt level_flags; - - if (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2) - level_flags = 0; - else if (s->level < 6) - level_flags = 1; - else if (s->level == 6) - level_flags = 2; - else - level_flags = 3; - header |= (level_flags << 6); - if (s->strstart != 0) header |= PRESET_DICT; - header += 31 - (header % 31); + level_flags = 3; + header |= (level_flags << 6); + if (s->strstart != 0) header |= PRESET_DICT; + header += 31 - (header % 31); + + putShortMSB(s, header); + /* Save the adler32 of the preset dictionary: */ + if (s->strstart != 0) { + putShortMSB(s, (uInt)(strm->adler >> 16)); + putShortMSB(s, (uInt)(strm->adler & 0xffff)); + } + strm->adler = adler32(0L, Z_NULL, 0); + s->status = BUSY_STATE; + + /* Compression must start with an empty pending buffer */ + flush_pending(strm); + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; + } + } +#ifdef GZIP + if (s->status == GZIP_STATE) { + /* gzip header */ + strm->adler = crc32(0L, Z_NULL, 0); + put_byte(s, 31); + put_byte(s, 139); + put_byte(s, 8); + if (s->gzhead == Z_NULL) { + put_byte(s, 0); + put_byte(s, 0); + put_byte(s, 0); + put_byte(s, 0); + put_byte(s, 0); + put_byte(s, s->level == 9 ? 2 : + (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? + 4 : 0)); + put_byte(s, OS_CODE); s->status = BUSY_STATE; - putShortMSB(s, header); - /* Save the adler32 of the preset dictionary: */ - if (s->strstart != 0) { - putShortMSB(s, (uInt)(strm->adler >> 16)); - putShortMSB(s, (uInt)(strm->adler & 0xffff)); + /* Compression must start with an empty pending buffer */ + flush_pending(strm); + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; + } + } + else { + put_byte(s, (s->gzhead->text ? 1 : 0) + + (s->gzhead->hcrc ? 2 : 0) + + (s->gzhead->extra == Z_NULL ? 0 : 4) + + (s->gzhead->name == Z_NULL ? 0 : 8) + + (s->gzhead->comment == Z_NULL ? 0 : 16) + ); + put_byte(s, (Byte)(s->gzhead->time & 0xff)); + put_byte(s, (Byte)((s->gzhead->time >> 8) & 0xff)); + put_byte(s, (Byte)((s->gzhead->time >> 16) & 0xff)); + put_byte(s, (Byte)((s->gzhead->time >> 24) & 0xff)); + put_byte(s, s->level == 9 ? 2 : + (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? + 4 : 0)); + put_byte(s, s->gzhead->os & 0xff); + if (s->gzhead->extra != Z_NULL) { + put_byte(s, s->gzhead->extra_len & 0xff); + put_byte(s, (s->gzhead->extra_len >> 8) & 0xff); } - strm->adler = adler32(0L, Z_NULL, 0); + if (s->gzhead->hcrc) + strm->adler = crc32(strm->adler, s->pending_buf, + s->pending); + s->gzindex = 0; + s->status = EXTRA_STATE; } } -#ifdef GZIP if (s->status == EXTRA_STATE) { - if (s->gzhead->extra != NULL) { - uInt beg = s->pending; /* start of bytes to update crc */ - - while (s->gzindex < (s->gzhead->extra_len & 0xffff)) { - if (s->pending == s->pending_buf_size) { - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); - flush_pending(strm); - beg = s->pending; - if (s->pending == s->pending_buf_size) - break; + if (s->gzhead->extra != Z_NULL) { + ulg beg = s->pending; /* start of bytes to update crc */ + uInt left = (s->gzhead->extra_len & 0xffff) - s->gzindex; + while (s->pending + left > s->pending_buf_size) { + uInt copy = s->pending_buf_size - s->pending; + zmemcpy(s->pending_buf + s->pending, + s->gzhead->extra + s->gzindex, copy); + s->pending = s->pending_buf_size; + HCRC_UPDATE(beg); + s->gzindex += copy; + flush_pending(strm); + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; } - put_byte(s, s->gzhead->extra[s->gzindex]); - s->gzindex++; - } - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); - if (s->gzindex == s->gzhead->extra_len) { - s->gzindex = 0; - s->status = NAME_STATE; + beg = 0; + left -= copy; } + zmemcpy(s->pending_buf + s->pending, + s->gzhead->extra + s->gzindex, left); + s->pending += left; + HCRC_UPDATE(beg); + s->gzindex = 0; } - else - s->status = NAME_STATE; + s->status = NAME_STATE; } if (s->status == NAME_STATE) { - if (s->gzhead->name != NULL) { - uInt beg = s->pending; /* start of bytes to update crc */ + if (s->gzhead->name != Z_NULL) { + ulg beg = s->pending; /* start of bytes to update crc */ int val; - do { if (s->pending == s->pending_buf_size) { - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); + HCRC_UPDATE(beg); flush_pending(strm); - beg = s->pending; - if (s->pending == s->pending_buf_size) { - val = 1; - break; + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; } + beg = 0; } val = s->gzhead->name[s->gzindex++]; put_byte(s, val); } while (val != 0); - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); - if (val == 0) { - s->gzindex = 0; - s->status = COMMENT_STATE; - } + HCRC_UPDATE(beg); + s->gzindex = 0; } - else - s->status = COMMENT_STATE; + s->status = COMMENT_STATE; } if (s->status == COMMENT_STATE) { - if (s->gzhead->comment != NULL) { - uInt beg = s->pending; /* start of bytes to update crc */ + if (s->gzhead->comment != Z_NULL) { + ulg beg = s->pending; /* start of bytes to update crc */ int val; - do { if (s->pending == s->pending_buf_size) { - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); + HCRC_UPDATE(beg); flush_pending(strm); - beg = s->pending; - if (s->pending == s->pending_buf_size) { - val = 1; - break; + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; } + beg = 0; } val = s->gzhead->comment[s->gzindex++]; put_byte(s, val); } while (val != 0); - if (s->gzhead->hcrc && s->pending > beg) - strm->adler = crc32(strm->adler, s->pending_buf + beg, - s->pending - beg); - if (val == 0) - s->status = HCRC_STATE; + HCRC_UPDATE(beg); } - else - s->status = HCRC_STATE; + s->status = HCRC_STATE; } if (s->status == HCRC_STATE) { if (s->gzhead->hcrc) { - if (s->pending + 2 > s->pending_buf_size) + if (s->pending + 2 > s->pending_buf_size) { flush_pending(strm); - if (s->pending + 2 <= s->pending_buf_size) { - put_byte(s, (Byte)(strm->adler & 0xff)); - put_byte(s, (Byte)((strm->adler >> 8) & 0xff)); - strm->adler = crc32(0L, Z_NULL, 0); - s->status = BUSY_STATE; + if (s->pending != 0) { + s->last_flush = -1; + return Z_OK; + } } + put_byte(s, (Byte)(strm->adler & 0xff)); + put_byte(s, (Byte)((strm->adler >> 8) & 0xff)); + strm->adler = crc32(0L, Z_NULL, 0); } - else - s->status = BUSY_STATE; - } -#endif + s->status = BUSY_STATE; - /* Flush as much pending output as possible */ - if (s->pending != 0) { + /* Compression must start with an empty pending buffer */ flush_pending(strm); - if (strm->avail_out == 0) { - /* Since avail_out is 0, deflate will be called again with - * more output space, but possibly with both pending and - * avail_in equal to zero. There won't be anything to do, - * but this is not an error situation so make sure we - * return OK instead of BUF_ERROR at next call of deflate: - */ + if (s->pending != 0) { s->last_flush = -1; return Z_OK; } - - /* Make sure there is something to do and avoid duplicate consecutive - * flushes. For repeated and useless calls with Z_FINISH, we keep - * returning Z_STREAM_END instead of Z_BUF_ERROR. - */ - } else if (strm->avail_in == 0 && flush <= old_flush && - flush != Z_FINISH) { - ERR_RETURN(strm, Z_BUF_ERROR); - } - - /* User must not provide more input after the first FINISH: */ - if (s->status == FINISH_STATE && strm->avail_in != 0) { - ERR_RETURN(strm, Z_BUF_ERROR); } +#endif /* Start a new block or continue the current one. */ @@ -785,7 +994,10 @@ int ZEXPORT deflate (strm, flush) (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) { block_state bstate; - bstate = (*(configuration_table[s->level].func))(s, flush); + bstate = s->level == 0 ? deflate_stored(s, flush) : + s->strategy == Z_HUFFMAN_ONLY ? deflate_huff(s, flush) : + s->strategy == Z_RLE ? deflate_rle(s, flush) : + (*(configuration_table[s->level].func))(s, flush); if (bstate == finish_started || bstate == finish_done) { s->status = FINISH_STATE; @@ -806,13 +1018,18 @@ int ZEXPORT deflate (strm, flush) if (bstate == block_done) { if (flush == Z_PARTIAL_FLUSH) { _tr_align(s); - } else { /* FULL_FLUSH or SYNC_FLUSH */ + } else if (flush != Z_BLOCK) { /* FULL_FLUSH or SYNC_FLUSH */ _tr_stored_block(s, (char*)0, 0L, 0); /* For a full flush, this empty block will be recognized * as a special marker by inflate_sync(). */ if (flush == Z_FULL_FLUSH) { CLEAR_HASH(s); /* forget history */ + if (s->lookahead == 0) { + s->strstart = 0; + s->block_start = 0L; + s->insert = 0; + } } } flush_pending(strm); @@ -822,7 +1039,6 @@ int ZEXPORT deflate (strm, flush) } } } - Assert(strm->avail_out > 0, "bug2"); if (flush != Z_FINISH) return Z_OK; if (s->wrap <= 0) return Z_STREAM_END; @@ -859,18 +1075,9 @@ int ZEXPORT deflateEnd (strm) { int status; - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (deflateStateCheck(strm)) return Z_STREAM_ERROR; status = strm->state->status; - if (status != INIT_STATE && - status != EXTRA_STATE && - status != NAME_STATE && - status != COMMENT_STATE && - status != HCRC_STATE && - status != BUSY_STATE && - status != FINISH_STATE) { - return Z_STREAM_ERROR; - } /* Deallocate in reverse order of allocations: */ TRY_FREE(strm, strm->state->pending_buf); @@ -901,18 +1108,18 @@ int ZEXPORT deflateCopy (dest, source) ushf *overlay; - if (source == Z_NULL || dest == Z_NULL || source->state == Z_NULL) { + if (deflateStateCheck(source) || dest == Z_NULL) { return Z_STREAM_ERROR; } ss = source->state; - zmemcpy(dest, source, sizeof(z_stream)); + zmemcpy((voidpf)dest, (voidpf)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; - zmemcpy(ds, ss, sizeof(deflate_state)); + zmemcpy((voidpf)ds, (voidpf)ss, sizeof(deflate_state)); ds->strm = dest; ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte)); @@ -928,8 +1135,8 @@ int ZEXPORT deflateCopy (dest, source) } /* following zmemcpy do not work for 16-bit MSDOS */ zmemcpy(ds->window, ss->window, ds->w_size * 2 * sizeof(Byte)); - zmemcpy(ds->prev, ss->prev, ds->w_size * sizeof(Pos)); - zmemcpy(ds->head, ss->head, ds->hash_size * sizeof(Pos)); + zmemcpy((voidpf)ds->prev, (voidpf)ss->prev, ds->w_size * sizeof(Pos)); + zmemcpy((voidpf)ds->head, (voidpf)ss->head, ds->hash_size * sizeof(Pos)); zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size); ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf); @@ -951,7 +1158,7 @@ int ZEXPORT deflateCopy (dest, source) * allocating a large strm->next_in buffer and copying from it. * (See also flush_pending()). */ -local int read_buf(strm, buf, size) +local unsigned read_buf(strm, buf, size) z_streamp strm; Bytef *buf; unsigned size; @@ -963,19 +1170,19 @@ local int read_buf(strm, buf, size) strm->avail_in -= len; + zmemcpy(buf, strm->next_in, len); if (strm->state->wrap == 1) { - strm->adler = adler32(strm->adler, strm->next_in, len); + strm->adler = adler32(strm->adler, buf, len); } #ifdef GZIP else if (strm->state->wrap == 2) { - strm->adler = crc32(strm->adler, strm->next_in, len); + strm->adler = crc32(strm->adler, buf, len); } #endif - zmemcpy(buf, strm->next_in, len); strm->next_in += len; strm->total_in += len; - return (int)len; + return len; } /* =========================================================================== @@ -998,6 +1205,7 @@ local void lm_init (s) s->strstart = 0; s->block_start = 0L; s->lookahead = 0; + s->insert = 0; s->match_length = s->prev_length = MIN_MATCH-1; s->match_available = 0; s->ins_h = 0; @@ -1028,9 +1236,9 @@ local uInt longest_match(s, cur_match) { unsigned chain_length = s->max_chain_length;/* max hash chain length */ register Bytef *scan = s->window + s->strstart; /* current string */ - register Bytef *match; /* matched string */ + register Bytef *match; /* matched string */ register int len; /* length of current match */ - int best_len = s->prev_length; /* best match length so far */ + int best_len = (int)s->prev_length; /* best match length so far */ int nice_match = s->nice_match; /* stop if match long enough */ IPos limit = s->strstart > (IPos)MAX_DIST(s) ? s->strstart - (IPos)MAX_DIST(s) : NIL; @@ -1065,7 +1273,7 @@ local uInt longest_match(s, cur_match) /* Do not look for matches beyond the end of the input. This is necessary * to make deflate deterministic. */ - if ((uInt)nice_match > s->lookahead) nice_match = s->lookahead; + if ((uInt)nice_match > s->lookahead) nice_match = (int)s->lookahead; Assert((ulg)s->strstart <= s->window_size-MIN_LOOKAHEAD, "need lookahead"); @@ -1165,12 +1373,13 @@ local uInt longest_match(s, cur_match) return s->lookahead; } #endif /* ASMV */ -#endif /* FASTEST */ + +#else /* FASTEST */ /* --------------------------------------------------------------------------- - * Optimized version for level == 1 or strategy == Z_RLE only + * Optimized version for FASTEST only */ -local uInt longest_match_fast(s, cur_match) +local uInt longest_match(s, cur_match) deflate_state *s; IPos cur_match; /* current match */ { @@ -1223,7 +1432,13 @@ local uInt longest_match_fast(s, cur_match) return (uInt)len <= s->lookahead ? (uInt)len : s->lookahead; } -#ifdef DEBUG +#endif /* FASTEST */ + +#ifdef ZLIB_DEBUG + +#define EQUAL 0 +/* result of memcmp for equal strings */ + /* =========================================================================== * Check that the match at match_start is indeed a match. */ @@ -1249,7 +1464,7 @@ local void check_match(s, start, match, length) } #else # define check_match(s, start, match, length) -#endif /* DEBUG */ +#endif /* ZLIB_DEBUG */ /* =========================================================================== * Fill the window when the lookahead becomes insufficient. @@ -1264,11 +1479,12 @@ local void check_match(s, start, match, length) local void fill_window(s) deflate_state *s; { - register unsigned n, m; - register Posf *p; + unsigned n; unsigned more; /* Amount of free space at the end of the window. */ uInt wsize = s->w_size; + Assert(s->lookahead < MIN_LOOKAHEAD, "already enough lookahead"); + do { more = (unsigned)(s->window_size -(ulg)s->lookahead -(ulg)s->strstart); @@ -1290,39 +1506,14 @@ local void fill_window(s) */ if (s->strstart >= wsize+MAX_DIST(s)) { - zmemcpy(s->window, s->window+wsize, (unsigned)wsize); + zmemcpy(s->window, s->window+wsize, (unsigned)wsize - more); s->match_start -= wsize; s->strstart -= wsize; /* we now have strstart >= MAX_DIST */ s->block_start -= (long) wsize; - - /* Slide the hash table (could be avoided with 32 bit values - at the expense of memory usage). We slide even when level == 0 - to keep the hash table consistent if we switch back to level > 0 - later. (Using level 0 permanently is not an optimal usage of - zlib, so we don't care about this pathological case.) - */ - /* %%% avoid this when Z_RLE */ - n = s->hash_size; - p = &s->head[n]; - do { - m = *--p; - *p = (Pos)(m >= wsize ? m-wsize : NIL); - } while (--n); - - n = wsize; -#ifndef FASTEST - p = &s->prev[n]; - do { - m = *--p; - *p = (Pos)(m >= wsize ? m-wsize : NIL); - /* If n is not on any hash chain, prev[n] is garbage but - * its value will never be used. - */ - } while (--n); -#endif + slide_hash(s); more += wsize; } - if (s->strm->avail_in == 0) return; + if (s->strm->avail_in == 0) break; /* If there was no sliding: * strstart <= WSIZE+MAX_DIST-1 && lookahead <= MIN_LOOKAHEAD - 1 && @@ -1341,99 +1532,283 @@ local void fill_window(s) s->lookahead += n; /* Initialize the hash value now that we have some input: */ - if (s->lookahead >= MIN_MATCH) { - s->ins_h = s->window[s->strstart]; - UPDATE_HASH(s, s->ins_h, s->window[s->strstart+1]); + if (s->lookahead + s->insert >= MIN_MATCH) { + uInt str = s->strstart - s->insert; + s->ins_h = s->window[str]; + UPDATE_HASH(s, s->ins_h, s->window[str + 1]); #if MIN_MATCH != 3 Call UPDATE_HASH() MIN_MATCH-3 more times #endif + while (s->insert) { + UPDATE_HASH(s, s->ins_h, s->window[str + MIN_MATCH-1]); +#ifndef FASTEST + s->prev[str & s->w_mask] = s->head[s->ins_h]; +#endif + s->head[s->ins_h] = (Pos)str; + str++; + s->insert--; + if (s->lookahead + s->insert < MIN_MATCH) + break; + } } /* If the whole input has less than MIN_MATCH bytes, ins_h is garbage, * but this is not important since only literal bytes will be emitted. */ } while (s->lookahead < MIN_LOOKAHEAD && s->strm->avail_in != 0); + + /* If the WIN_INIT bytes after the end of the current data have never been + * written, then zero those bytes in order to avoid memory check reports of + * the use of uninitialized (or uninitialised as Julian writes) bytes by + * the longest match routines. Update the high water mark for the next + * time through here. WIN_INIT is set to MAX_MATCH since the longest match + * routines allow scanning to strstart + MAX_MATCH, ignoring lookahead. + */ + if (s->high_water < s->window_size) { + ulg curr = s->strstart + (ulg)(s->lookahead); + ulg init; + + if (s->high_water < curr) { + /* Previous high water mark below current data -- zero WIN_INIT + * bytes or up to end of window, whichever is less. + */ + init = s->window_size - curr; + if (init > WIN_INIT) + init = WIN_INIT; + zmemzero(s->window + curr, (unsigned)init); + s->high_water = curr + init; + } + else if (s->high_water < (ulg)curr + WIN_INIT) { + /* High water mark at or above current data, but below current data + * plus WIN_INIT -- zero out to current data plus WIN_INIT, or up + * to end of window, whichever is less. + */ + init = (ulg)curr + WIN_INIT - s->high_water; + if (init > s->window_size - s->high_water) + init = s->window_size - s->high_water; + zmemzero(s->window + s->high_water, (unsigned)init); + s->high_water += init; + } + } + + Assert((ulg)s->strstart <= s->window_size - MIN_LOOKAHEAD, + "not enough room for search"); } /* =========================================================================== * Flush the current block, with given end-of-file flag. * IN assertion: strstart is set to the end of the current match. */ -#define FLUSH_BLOCK_ONLY(s, eof) { \ +#define FLUSH_BLOCK_ONLY(s, last) { \ _tr_flush_block(s, (s->block_start >= 0L ? \ (charf *)&s->window[(unsigned)s->block_start] : \ (charf *)Z_NULL), \ (ulg)((long)s->strstart - s->block_start), \ - (eof)); \ + (last)); \ s->block_start = s->strstart; \ flush_pending(s->strm); \ Tracev((stderr,"[FLUSH]")); \ } /* Same but force premature exit if necessary. */ -#define FLUSH_BLOCK(s, eof) { \ - FLUSH_BLOCK_ONLY(s, eof); \ - if (s->strm->avail_out == 0) return (eof) ? finish_started : need_more; \ +#define FLUSH_BLOCK(s, last) { \ + FLUSH_BLOCK_ONLY(s, last); \ + if (s->strm->avail_out == 0) return (last) ? finish_started : need_more; \ } +/* Maximum stored block length in deflate format (not including header). */ +#define MAX_STORED 65535 + +/* Minimum of a and b. */ +#define MIN(a, b) ((a) > (b) ? (b) : (a)) + /* =========================================================================== * Copy without compression as much as possible from the input stream, return * the current block state. - * This function does not insert new strings in the dictionary since - * uncompressible data is probably not useful. This function is used - * only for the level=0 compression option. - * NOTE: this function should be optimized to avoid extra copying from - * window to pending_buf. + * + * In case deflateParams() is used to later switch to a non-zero compression + * level, s->matches (otherwise unused when storing) keeps track of the number + * of hash table slides to perform. If s->matches is 1, then one hash table + * slide will be done when switching. If s->matches is 2, the maximum value + * allowed here, then the hash table will be cleared, since two or more slides + * is the same as a clear. + * + * deflate_stored() is written to minimize the number of times an input byte is + * copied. It is most efficient with large input and output buffers, which + * maximizes the opportunites to have a single copy from next_in to next_out. */ local block_state deflate_stored(s, flush) deflate_state *s; int flush; { - /* Stored blocks are limited to 0xffff bytes, pending_buf is limited - * to pending_buf_size, and each stored block has a 5 byte header: + /* Smallest worthy block size when not flushing or finishing. By default + * this is 32K. This can be as small as 507 bytes for memLevel == 1. For + * large input and output buffers, the stored block size will be larger. */ - ulg max_block_size = 0xffff; - ulg max_start; + unsigned min_block = MIN(s->pending_buf_size - 5, s->w_size); - if (max_block_size > s->pending_buf_size - 5) { - max_block_size = s->pending_buf_size - 5; - } - - /* Copy as much as possible from input to output: */ - for (;;) { - /* Fill the window as much as possible: */ - if (s->lookahead <= 1) { - - Assert(s->strstart < s->w_size+MAX_DIST(s) || - s->block_start >= (long)s->w_size, "slide too late"); + /* Copy as many min_block or larger stored blocks directly to next_out as + * possible. If flushing, copy the remaining available input to next_out as + * stored blocks, if there is enough space. + */ + unsigned len, left, have, last = 0; + unsigned used = s->strm->avail_in; + do { + /* Set len to the maximum size block that we can copy directly with the + * available input data and output space. Set left to how much of that + * would be copied from what's left in the window. + */ + len = MAX_STORED; /* maximum deflate stored block length */ + have = (s->bi_valid + 42) >> 3; /* number of header bytes */ + if (s->strm->avail_out < have) /* need room for header */ + break; + /* maximum stored block length that will fit in avail_out: */ + have = s->strm->avail_out - have; + left = s->strstart - s->block_start; /* bytes left in window */ + if (len > (ulg)left + s->strm->avail_in) + len = left + s->strm->avail_in; /* limit len to the input */ + if (len > have) + len = have; /* limit len to the output */ + + /* If the stored block would be less than min_block in length, or if + * unable to copy all of the available input when flushing, then try + * copying to the window and the pending buffer instead. Also don't + * write an empty block when flushing -- deflate() does that. + */ + if (len < min_block && ((len == 0 && flush != Z_FINISH) || + flush == Z_NO_FLUSH || + len != left + s->strm->avail_in)) + break; - fill_window(s); - if (s->lookahead == 0 && flush == Z_NO_FLUSH) return need_more; + /* Make a dummy stored block in pending to get the header bytes, + * including any pending bits. This also updates the debugging counts. + */ + last = flush == Z_FINISH && len == left + s->strm->avail_in ? 1 : 0; + _tr_stored_block(s, (char *)0, 0L, last); + + /* Replace the lengths in the dummy stored block with len. */ + s->pending_buf[s->pending - 4] = len; + s->pending_buf[s->pending - 3] = len >> 8; + s->pending_buf[s->pending - 2] = ~len; + s->pending_buf[s->pending - 1] = ~len >> 8; + + /* Write the stored block header bytes. */ + flush_pending(s->strm); + +#ifdef ZLIB_DEBUG + /* Update debugging counts for the data about to be copied. */ + s->compressed_len += len << 3; + s->bits_sent += len << 3; +#endif - if (s->lookahead == 0) break; /* flush the current block */ + /* Copy uncompressed bytes from the window to next_out. */ + if (left) { + if (left > len) + left = len; + zmemcpy(s->strm->next_out, s->window + s->block_start, left); + s->strm->next_out += left; + s->strm->avail_out -= left; + s->strm->total_out += left; + s->block_start += left; + len -= left; } - Assert(s->block_start >= 0L, "block gone"); - - s->strstart += s->lookahead; - s->lookahead = 0; - - /* Emit a stored block if pending_buf will be full: */ - max_start = s->block_start + max_block_size; - if (s->strstart == 0 || (ulg)s->strstart >= max_start) { - /* strstart == 0 is possible when wraparound on 16-bit machine */ - s->lookahead = (uInt)(s->strstart - max_start); - s->strstart = (uInt)max_start; - FLUSH_BLOCK(s, 0); + + /* Copy uncompressed bytes directly from next_in to next_out, updating + * the check value. + */ + if (len) { + read_buf(s->strm, s->strm->next_out, len); + s->strm->next_out += len; + s->strm->avail_out -= len; + s->strm->total_out += len; } - /* Flush if we may have to slide, otherwise block_start may become - * negative and the data will be gone: + } while (last == 0); + + /* Update the sliding window with the last s->w_size bytes of the copied + * data, or append all of the copied data to the existing window if less + * than s->w_size bytes were copied. Also update the number of bytes to + * insert in the hash tables, in the event that deflateParams() switches to + * a non-zero compression level. + */ + used -= s->strm->avail_in; /* number of input bytes directly copied */ + if (used) { + /* If any input was used, then no unused input remains in the window, + * therefore s->block_start == s->strstart. */ - if (s->strstart - (uInt)s->block_start >= MAX_DIST(s)) { - FLUSH_BLOCK(s, 0); + if (used >= s->w_size) { /* supplant the previous history */ + s->matches = 2; /* clear hash */ + zmemcpy(s->window, s->strm->next_in - s->w_size, s->w_size); + s->strstart = s->w_size; } + else { + if (s->window_size - s->strstart <= used) { + /* Slide the window down. */ + s->strstart -= s->w_size; + zmemcpy(s->window, s->window + s->w_size, s->strstart); + if (s->matches < 2) + s->matches++; /* add a pending slide_hash() */ + } + zmemcpy(s->window + s->strstart, s->strm->next_in - used, used); + s->strstart += used; + } + s->block_start = s->strstart; + s->insert += MIN(used, s->w_size - s->insert); + } + if (s->high_water < s->strstart) + s->high_water = s->strstart; + + /* If the last block was written to next_out, then done. */ + if (last) + return finish_done; + + /* If flushing and all input has been consumed, then done. */ + if (flush != Z_NO_FLUSH && flush != Z_FINISH && + s->strm->avail_in == 0 && (long)s->strstart == s->block_start) + return block_done; + + /* Fill the window with any remaining input. */ + have = s->window_size - s->strstart - 1; + if (s->strm->avail_in > have && s->block_start >= (long)s->w_size) { + /* Slide the window down. */ + s->block_start -= s->w_size; + s->strstart -= s->w_size; + zmemcpy(s->window, s->window + s->w_size, s->strstart); + if (s->matches < 2) + s->matches++; /* add a pending slide_hash() */ + have += s->w_size; /* more space now */ + } + if (have > s->strm->avail_in) + have = s->strm->avail_in; + if (have) { + read_buf(s->strm, s->window + s->strstart, have); + s->strstart += have; + } + if (s->high_water < s->strstart) + s->high_water = s->strstart; + + /* There was not enough avail_out to write a complete worthy or flushed + * stored block to next_out. Write a stored block to pending instead, if we + * have enough input for a worthy block, or if flushing and there is enough + * room for the remaining input as a stored block in the pending buffer. + */ + have = (s->bi_valid + 42) >> 3; /* number of header bytes */ + /* maximum stored block length that will fit in pending: */ + have = MIN(s->pending_buf_size - have, MAX_STORED); + min_block = MIN(have, s->w_size); + left = s->strstart - s->block_start; + if (left >= min_block || + ((left || flush == Z_FINISH) && flush != Z_NO_FLUSH && + s->strm->avail_in == 0 && left <= have)) { + len = MIN(left, have); + last = flush == Z_FINISH && s->strm->avail_in == 0 && + len == left ? 1 : 0; + _tr_stored_block(s, (charf *)s->window + s->block_start, len, last); + s->block_start += len; + flush_pending(s->strm); } - FLUSH_BLOCK(s, flush == Z_FINISH); - return flush == Z_FINISH ? finish_done : block_done; + + /* We've done all we can with the available input and output. */ + return last ? finish_started : need_more; } /* =========================================================================== @@ -1447,7 +1822,7 @@ local block_state deflate_fast(s, flush) deflate_state *s; int flush; { - IPos hash_head = NIL; /* head of the hash chain */ + IPos hash_head; /* head of the hash chain */ int bflush; /* set if current block must be flushed */ for (;;) { @@ -1467,6 +1842,7 @@ local block_state deflate_fast(s, flush) /* Insert the string window[strstart .. strstart+2] in the * dictionary, and set hash_head to the head of the hash chain: */ + hash_head = NIL; if (s->lookahead >= MIN_MATCH) { INSERT_STRING(s, s->strstart, hash_head); } @@ -1479,19 +1855,8 @@ local block_state deflate_fast(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). */ -#ifdef FASTEST - 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 && 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); - } -#endif - /* longest_match() or longest_match_fast() sets match_start */ + s->match_length = longest_match (s, hash_head); + /* longest_match() sets match_start */ } if (s->match_length >= MIN_MATCH) { check_match(s, s->strstart, s->match_start, s->match_length); @@ -1539,8 +1904,14 @@ local block_state deflate_fast(s, flush) } if (bflush) FLUSH_BLOCK(s, 0); } - FLUSH_BLOCK(s, flush == Z_FINISH); - return flush == Z_FINISH ? finish_done : block_done; + s->insert = s->strstart < MIN_MATCH-1 ? s->strstart : MIN_MATCH-1; + if (flush == Z_FINISH) { + FLUSH_BLOCK(s, 1); + return finish_done; + } + if (s->last_lit) + FLUSH_BLOCK(s, 0); + return block_done; } #ifndef FASTEST @@ -1553,7 +1924,7 @@ local block_state deflate_slow(s, flush) deflate_state *s; int flush; { - IPos hash_head = NIL; /* head of hash chain */ + IPos hash_head; /* head of hash chain */ int bflush; /* set if current block must be flushed */ /* Process the input block. */ @@ -1574,6 +1945,7 @@ local block_state deflate_slow(s, flush) /* Insert the string window[strstart .. strstart+2] in the * dictionary, and set hash_head to the head of the hash chain: */ + hash_head = NIL; if (s->lookahead >= MIN_MATCH) { INSERT_STRING(s, s->strstart, hash_head); } @@ -1589,12 +1961,8 @@ 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 && 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); - } - /* longest_match() or longest_match_fast() sets match_start */ + s->match_length = longest_match (s, hash_head); + /* longest_match() sets match_start */ if (s->match_length <= 5 && (s->strategy == Z_FILTERED #if TOO_FAR <= 32767 @@ -1667,12 +2035,17 @@ local block_state deflate_slow(s, flush) _tr_tally_lit(s, s->window[s->strstart-1], bflush); s->match_available = 0; } - FLUSH_BLOCK(s, flush == Z_FINISH); - return flush == Z_FINISH ? finish_done : block_done; + s->insert = s->strstart < MIN_MATCH-1 ? s->strstart : MIN_MATCH-1; + if (flush == Z_FINISH) { + FLUSH_BLOCK(s, 1); + return finish_done; + } + if (s->last_lit) + FLUSH_BLOCK(s, 0); + return block_done; } #endif /* FASTEST */ -#if 0 /* =========================================================================== * For Z_RLE, simply look for runs of bytes, generate matches only of distance * one. Do not maintain a hash table. (It will be regenerated if this run of @@ -1682,43 +2055,52 @@ local block_state deflate_rle(s, flush) deflate_state *s; int flush; { - int bflush; /* set if current block must be flushed */ - uInt run; /* length of run */ - uInt max; /* maximum length of run */ - uInt prev; /* byte at distance one to match */ - Bytef *scan; /* scan for end of run */ + int bflush; /* set if current block must be flushed */ + uInt prev; /* byte at distance one to match */ + Bytef *scan, *strend; /* scan goes up to strend for length of run */ for (;;) { /* Make sure that we always have enough lookahead, except * at the end of the input file. We need MAX_MATCH bytes - * for the longest encodable run. + * for the longest run, plus one for the unrolled loop. */ - if (s->lookahead < MAX_MATCH) { + if (s->lookahead <= MAX_MATCH) { fill_window(s); - if (s->lookahead < MAX_MATCH && flush == Z_NO_FLUSH) { + if (s->lookahead <= MAX_MATCH && flush == Z_NO_FLUSH) { return need_more; } if (s->lookahead == 0) break; /* flush the current block */ } /* See how many times the previous byte repeats */ - run = 0; - if (s->strstart > 0) { /* if there is a previous byte, that is */ - max = s->lookahead < MAX_MATCH ? s->lookahead : MAX_MATCH; + s->match_length = 0; + if (s->lookahead >= MIN_MATCH && s->strstart > 0) { scan = s->window + s->strstart - 1; - prev = *scan++; - do { - if (*scan++ != prev) - break; - } while (++run < max); + prev = *scan; + if (prev == *++scan && prev == *++scan && prev == *++scan) { + strend = s->window + s->strstart + MAX_MATCH; + do { + } while (prev == *++scan && prev == *++scan && + prev == *++scan && prev == *++scan && + prev == *++scan && prev == *++scan && + prev == *++scan && prev == *++scan && + scan < strend); + s->match_length = MAX_MATCH - (uInt)(strend - scan); + if (s->match_length > s->lookahead) + s->match_length = s->lookahead; + } + Assert(scan <= s->window+(uInt)(s->window_size-1), "wild scan"); } /* Emit match if have run of MIN_MATCH or longer, else emit literal */ - if (run >= MIN_MATCH) { - check_match(s, s->strstart, s->strstart - 1, run); - _tr_tally_dist(s, 1, run - MIN_MATCH, bflush); - s->lookahead -= run; - s->strstart += run; + if (s->match_length >= MIN_MATCH) { + check_match(s, s->strstart, s->strstart - 1, s->match_length); + + _tr_tally_dist(s, 1, s->match_length - MIN_MATCH, bflush); + + s->lookahead -= s->match_length; + s->strstart += s->match_length; + s->match_length = 0; } else { /* No match, output a literal byte */ Tracevv((stderr,"%c", s->window[s->strstart])); @@ -1728,7 +2110,51 @@ local block_state deflate_rle(s, flush) } if (bflush) FLUSH_BLOCK(s, 0); } - FLUSH_BLOCK(s, flush == Z_FINISH); - return flush == Z_FINISH ? finish_done : block_done; + s->insert = 0; + if (flush == Z_FINISH) { + FLUSH_BLOCK(s, 1); + return finish_done; + } + if (s->last_lit) + FLUSH_BLOCK(s, 0); + return block_done; +} + +/* =========================================================================== + * For Z_HUFFMAN_ONLY, do not look for matches. Do not maintain a hash table. + * (It will be regenerated if this run of deflate switches away from Huffman.) + */ +local block_state deflate_huff(s, flush) + deflate_state *s; + int flush; +{ + int bflush; /* set if current block must be flushed */ + + for (;;) { + /* Make sure that we have a literal to write. */ + if (s->lookahead == 0) { + fill_window(s); + if (s->lookahead == 0) { + if (flush == Z_NO_FLUSH) + return need_more; + break; /* flush the current block */ + } + } + + /* Output a literal byte */ + s->match_length = 0; + Tracevv((stderr,"%c", s->window[s->strstart])); + _tr_tally_lit (s, s->window[s->strstart], bflush); + s->lookahead--; + s->strstart++; + if (bflush) FLUSH_BLOCK(s, 0); + } + s->insert = 0; + if (flush == Z_FINISH) { + FLUSH_BLOCK(s, 1); + return finish_done; + } + if (s->last_lit) + FLUSH_BLOCK(s, 0); + return block_done; } -#endif diff --git a/lib/libz/deflate.h b/lib/libz/deflate.h index 8d2a878..11c60ec 100644 --- a/lib/libz/deflate.h +++ b/lib/libz/deflate.h @@ -1,6 +1,7 @@ -/* $OpenBSD: deflate.h,v 1.8 2007/11/26 09:28:33 martynas Exp $ */ +/* $OpenBSD: deflate.h,v 1.10 2021/07/04 17:41:23 tb Exp $ */ + /* deflate.h -- internal compression state - * Copyright (C) 1995-2004 Jean-loup Gailly + * Copyright (C) 1995-2016 Jean-loup Gailly * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -9,7 +10,6 @@ subject to change. Applications should only use zlib.h. */ - #ifndef DEFLATE_H #define DEFLATE_H @@ -48,13 +48,19 @@ #define MAX_BITS 15 /* All codes must not exceed MAX_BITS bits */ -#define INIT_STATE 42 -#define EXTRA_STATE 69 -#define NAME_STATE 73 -#define COMMENT_STATE 91 -#define HCRC_STATE 103 -#define BUSY_STATE 113 -#define FINISH_STATE 666 +#define Buf_size 16 +/* size of bit buffer in bi_buf */ + +#define INIT_STATE 42 /* zlib header -> BUSY_STATE */ +#ifdef GZIP +# define GZIP_STATE 57 /* gzip header -> BUSY_STATE | EXTRA_STATE */ +#endif +#define EXTRA_STATE 69 /* gzip extra block -> NAME_STATE */ +#define NAME_STATE 73 /* gzip file name -> COMMENT_STATE */ +#define COMMENT_STATE 91 /* gzip comment -> HCRC_STATE */ +#define HCRC_STATE 103 /* gzip header CRC -> BUSY_STATE */ +#define BUSY_STATE 113 /* deflate -> FINISH_STATE */ +#define FINISH_STATE 666 /* stream complete */ /* Stream status */ @@ -80,7 +86,7 @@ typedef struct static_tree_desc_s static_tree_desc; typedef struct tree_desc_s { ct_data *dyn_tree; /* the dynamic tree */ int max_code; /* largest code with non zero frequency */ - static_tree_desc *stat_desc; /* the corresponding static tree */ + const static_tree_desc *stat_desc; /* the corresponding static tree */ } FAR tree_desc; typedef ush Pos; @@ -97,11 +103,11 @@ typedef struct internal_state { Bytef *pending_buf; /* output still pending */ ulg pending_buf_size; /* size of pending_buf */ Bytef *pending_out; /* next pending byte to output to the stream */ - uInt pending; /* nb of bytes in the pending buffer */ + ulg pending; /* nb of bytes in the pending buffer */ int wrap; /* bit 0 true for zlib, bit 1 true for gzip */ gz_headerp gzhead; /* gzip header information to write */ - uInt gzindex; /* where in extra, name, or comment */ - Byte method; /* STORED (for zip only) or DEFLATED */ + ulg gzindex; /* where in extra, name, or comment */ + Byte method; /* can only be DEFLATED */ int last_flush; /* value of flush param for previous deflate call */ /* used by deflate.c: */ @@ -244,9 +250,9 @@ typedef struct internal_state { ulg opt_len; /* bit length of current block with optimal trees */ ulg static_len; /* bit length of current block with static trees */ uInt matches; /* number of string matches in current block */ - int last_eob_len; /* bit length of EOB code for last block */ + uInt insert; /* bytes at end of window left to insert */ -#ifdef DEBUG +#ifdef ZLIB_DEBUG ulg compressed_len; /* total bit length of compressed file mod 2^32 */ ulg bits_sent; /* bit length of compressed data sent mod 2^32 */ #endif @@ -260,12 +266,19 @@ typedef struct internal_state { * are always zero. */ + ulg high_water; + /* High water mark offset in window for initialized bytes -- bytes above + * this are set to zero in order to avoid memory check warnings when + * longest match routines access bytes past the input. This is then + * updated to the new high water mark. + */ + } FAR deflate_state; /* Output a byte on the stream. * IN assertion: there is enough room in pending_buf. */ -#define put_byte(s, c) {s->pending_buf[s->pending++] = (c);} +#define put_byte(s, c) {s->pending_buf[s->pending++] = (Bytef)(c);} #define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) @@ -278,14 +291,19 @@ typedef struct internal_state { * distances are limited to MAX_DIST instead of WSIZE. */ +#define WIN_INIT MAX_MATCH +/* Number of bytes after end of data in window to initialize in order to avoid + memory checker errors from longest match routines */ + /* in trees.c */ -void _tr_init OF((deflate_state *s)); -int _tr_tally OF((deflate_state *s, unsigned dist, unsigned lc)); -void _tr_flush_block OF((deflate_state *s, charf *buf, ulg stored_len, - int eof)); -void _tr_align OF((deflate_state *s)); -void _tr_stored_block OF((deflate_state *s, charf *buf, ulg stored_len, - int eof)); +void ZLIB_INTERNAL _tr_init OF((deflate_state *s)); +int ZLIB_INTERNAL _tr_tally OF((deflate_state *s, unsigned dist, unsigned lc)); +void ZLIB_INTERNAL _tr_flush_block OF((deflate_state *s, charf *buf, + ulg stored_len, int last)); +void ZLIB_INTERNAL _tr_flush_bits OF((deflate_state *s)); +void ZLIB_INTERNAL _tr_align OF((deflate_state *s)); +void ZLIB_INTERNAL _tr_stored_block OF((deflate_state *s, charf *buf, + ulg stored_len, int last)); #define d_code(dist) \ ((dist) < 256 ? _dist_code[dist] : _dist_code[256+((dist)>>7)]) @@ -294,15 +312,15 @@ void _tr_stored_block OF((deflate_state *s, charf *buf, ulg stored_len, * used. */ -#ifndef DEBUG +#ifndef ZLIB_DEBUG /* Inline versions of _tr_tally for speed: */ #if defined(GEN_TREES_H) || !defined(STDC) - extern uch _length_code[]; - extern uch _dist_code[]; + extern uch ZLIB_INTERNAL _length_code[]; + extern uch ZLIB_INTERNAL _dist_code[]; #else - extern const uch _length_code[]; - extern const uch _dist_code[]; + extern const uch ZLIB_INTERNAL _length_code[]; + extern const uch ZLIB_INTERNAL _dist_code[]; #endif # define _tr_tally_lit(s, c, flush) \ @@ -313,8 +331,8 @@ void _tr_stored_block OF((deflate_state *s, charf *buf, ulg stored_len, flush = (s->last_lit == s->lit_bufsize-1); \ } # define _tr_tally_dist(s, distance, length, flush) \ - { uch len = (length); \ - ush dist = (distance); \ + { uch len = (uch)(length); \ + ush dist = (ush)(distance); \ s->d_buf[s->last_lit] = dist; \ s->l_buf[s->last_lit++] = len; \ dist--; \ diff --git a/lib/libz/gzclose.c b/lib/libz/gzclose.c new file mode 100644 index 0000000..b2b4188 --- /dev/null +++ b/lib/libz/gzclose.c @@ -0,0 +1,26 @@ +/* $OpenBSD: gzclose.c,v 1.1 2021/07/04 14:24:49 tb Exp $ */ +/* gzclose.c -- zlib gzclose() function + * Copyright (C) 2004, 2010 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "gzguts.h" + +/* gzclose() is in a separate file so that it is linked in only if it is used. + That way the other gzclose functions can be used instead to avoid linking in + unneeded compression or decompression routines. */ +int ZEXPORT gzclose(file) + gzFile file; +{ +#ifndef NO_GZCOMPRESS + gz_statep state; + + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + + return state->mode == GZ_READ ? gzclose_r(file) : gzclose_w(file); +#else + return gzclose_r(file); +#endif +} diff --git a/lib/libz/gzguts.h b/lib/libz/gzguts.h new file mode 100644 index 0000000..0f4c499 --- /dev/null +++ b/lib/libz/gzguts.h @@ -0,0 +1,220 @@ +/* $OpenBSD: gzguts.h,v 1.2 2021/07/04 17:41:23 tb Exp $ */ + +/* gzguts.h -- zlib internal header definitions for gz* operations + * Copyright (C) 2004, 2005, 2010, 2011, 2012, 2013, 2016 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#ifdef _LARGEFILE64_SOURCE +# ifndef _LARGEFILE_SOURCE +# define _LARGEFILE_SOURCE 1 +# endif +# ifdef _FILE_OFFSET_BITS +# undef _FILE_OFFSET_BITS +# endif +#endif + +#ifdef HAVE_HIDDEN +# define ZLIB_INTERNAL __attribute__((visibility ("hidden"))) +#else +# define ZLIB_INTERNAL +#endif + +#include <stdio.h> +#include "zlib.h" +#ifdef STDC +# include <string.h> +# include <stdlib.h> +# include <limits.h> +#endif + +#ifndef _POSIX_SOURCE +# define _POSIX_SOURCE +#endif +#include <fcntl.h> + +#ifdef _WIN32 +# include <stddef.h> +#endif + +#if defined(__TURBOC__) || defined(_MSC_VER) || defined(_WIN32) +# include <io.h> +#endif + +#if defined(_WIN32) || defined(__CYGWIN__) +# define WIDECHAR +#endif + +#ifdef WINAPI_FAMILY +# define open _open +# define read _read +# define write _write +# define close _close +#endif + +#ifdef NO_DEFLATE /* for compatibility with old definition */ +# define NO_GZCOMPRESS +#endif + +#if defined(STDC99) || (defined(__TURBOC__) && __TURBOC__ >= 0x550) +# ifndef HAVE_VSNPRINTF +# define HAVE_VSNPRINTF +# endif +#endif + +#if defined(__CYGWIN__) +# ifndef HAVE_VSNPRINTF +# define HAVE_VSNPRINTF +# endif +#endif + +#if defined(MSDOS) && defined(__BORLANDC__) && (BORLANDC > 0x410) +# ifndef HAVE_VSNPRINTF +# define HAVE_VSNPRINTF +# endif +#endif + +#ifndef HAVE_VSNPRINTF +# ifdef MSDOS +/* vsnprintf may exist on some MS-DOS compilers (DJGPP?), + but for now we just assume it doesn't. */ +# define NO_vsnprintf +# endif +# ifdef __TURBOC__ +# define NO_vsnprintf +# endif +# ifdef WIN32 +/* In Win32, vsnprintf is available as the "non-ANSI" _vsnprintf. */ +# if !defined(vsnprintf) && !defined(NO_vsnprintf) +# if !defined(_MSC_VER) || ( defined(_MSC_VER) && _MSC_VER < 1500 ) +# define vsnprintf _vsnprintf +# endif +# endif +# endif +# ifdef __SASC +# define NO_vsnprintf +# endif +# ifdef VMS +# define NO_vsnprintf +# endif +# ifdef __OS400__ +# define NO_vsnprintf +# endif +# ifdef __MVS__ +# define NO_vsnprintf +# endif +#endif + +/* unlike snprintf (which is required in C99), _snprintf does not guarantee + null termination of the result -- however this is only used in gzlib.c where + the result is assured to fit in the space provided */ +#if defined(_MSC_VER) && _MSC_VER < 1900 +# define snprintf _snprintf +#endif + +#ifndef local +# define local static +#endif +/* since "static" is used to mean two completely different things in C, we + define "local" for the non-static meaning of "static", for readability + (compile with -Dlocal if your debugger can't find static symbols) */ + +/* gz* functions always use library allocation functions */ +#ifndef STDC + extern voidp malloc OF((uInt size)); + extern void free OF((voidpf ptr)); +#endif + +/* get errno and strerror definition */ +#if defined UNDER_CE +# include <windows.h> +# define zstrerror() gz_strwinerror((DWORD)GetLastError()) +#else +# ifndef NO_STRERROR +# include <errno.h> +# define zstrerror() strerror(errno) +# else +# define zstrerror() "stdio error (consult errno)" +# endif +#endif + +/* provide prototypes for these when building zlib without LFS */ +#if !defined(_LARGEFILE64_SOURCE) || _LFS64_LARGEFILE-0 == 0 + ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); + ZEXTERN z_off64_t ZEXPORT gzseek64 OF((gzFile, z_off64_t, int)); + ZEXTERN z_off64_t ZEXPORT gztell64 OF((gzFile)); + ZEXTERN z_off64_t ZEXPORT gzoffset64 OF((gzFile)); +#endif + +/* default memLevel */ +#if MAX_MEM_LEVEL >= 8 +# define DEF_MEM_LEVEL 8 +#else +# define DEF_MEM_LEVEL MAX_MEM_LEVEL +#endif + +/* default i/o buffer size -- double this for output when reading (this and + twice this must be able to fit in an unsigned type) */ +#define GZBUFSIZE 8192 + +/* gzip modes, also provide a little integrity check on the passed structure */ +#define GZ_NONE 0 +#define GZ_READ 7247 +#define GZ_WRITE 31153 +#define GZ_APPEND 1 /* mode set to GZ_WRITE after the file is opened */ + +/* values for gz_state how */ +#define LOOK 0 /* look for a gzip header */ +#define COPY 1 /* copy input directly */ +#define GZIP 2 /* decompress a gzip stream */ + +/* internal gzip file state data structure */ +typedef struct { + /* exposed contents for gzgetc() macro */ + struct gzFile_s x; /* "x" for exposed */ + /* x.have: number of bytes available at x.next */ + /* x.next: next output data to deliver or write */ + /* x.pos: current position in uncompressed data */ + /* used for both reading and writing */ + int mode; /* see gzip modes above */ + int fd; /* file descriptor */ + char *path; /* path or fd for error messages */ + unsigned size; /* buffer size, zero if not allocated yet */ + unsigned want; /* requested buffer size, default is GZBUFSIZE */ + unsigned char *in; /* input buffer (double-sized when writing) */ + unsigned char *out; /* output buffer (double-sized when reading) */ + int direct; /* 0 if processing gzip, 1 if transparent */ + /* just for reading */ + int how; /* 0: get header, 1: copy, 2: decompress */ + z_off64_t start; /* where the gzip data started, for rewinding */ + int eof; /* true if end of input file reached */ + int past; /* true if read requested past end */ + /* just for writing */ + int level; /* compression level */ + int strategy; /* compression strategy */ + /* seek request */ + z_off64_t skip; /* amount to skip (already rewound if backwards) */ + int seek; /* true if seek request pending */ + /* error information */ + int err; /* error code */ + char *msg; /* error message */ + /* zlib inflate or deflate stream */ + z_stream strm; /* stream structure in-place (not a pointer) */ +} gz_state; +typedef gz_state FAR *gz_statep; + +/* shared functions */ +void ZLIB_INTERNAL gz_error OF((gz_statep, int, const char *)); +#if defined UNDER_CE +char ZLIB_INTERNAL *gz_strwinerror OF((DWORD error)); +#endif + +/* GT_OFF(x), where x is an unsigned value, is true if x > maximum z_off64_t + value -- needed when comparing unsigned to z_off64_t, which is signed + (possible z_off64_t types off_t, off64_t, and long are all signed) */ +#ifdef INT_MAX +# define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > INT_MAX) +#else +unsigned ZLIB_INTERNAL gz_intmax OF((void)); +# define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > gz_intmax()) +#endif diff --git a/lib/libz/gzio.c b/lib/libz/gzio.c deleted file mode 100644 index ab77ad9..0000000 --- a/lib/libz/gzio.c +++ /dev/null @@ -1,1003 +0,0 @@ -/* $OpenBSD: gzio.c,v 1.15 2020/04/18 17:11:37 schwarze Exp $ */ -/* gzio.c -- IO on .gz files - * Copyright (C) 1995-2005 Jean-loup Gailly. - * For conditions of distribution and use, see copyright notice in zlib.h - * - * Compile this file with -DNO_GZCOMPRESS to avoid the compression code. - */ - - -#include <stdio.h> - -#include "zutil.h" - -#ifdef NO_DEFLATE /* for compatibility with old definition */ -# define NO_GZCOMPRESS -#endif - -#ifndef NO_DUMMY_DECL -struct internal_state {int dummy;}; /* for buggy compilers */ -#endif - -#ifndef Z_BUFSIZE -# ifdef MAXSEG_64K -# define Z_BUFSIZE 4096 /* minimize memory usage for 16-bit DOS */ -# else -# define Z_BUFSIZE 16384 -# endif -#endif -#ifndef Z_PRINTF_BUFSIZE -# define Z_PRINTF_BUFSIZE 4096 -#endif - -#ifdef __MVS__ -# pragma map (fdopen , "\174\174FDOPEN") - FILE *fdopen(int, const char *); -#endif - -#ifndef STDC -extern voidp malloc OF((uInt size)); -extern void free OF((voidpf ptr)); -#endif - -#define ALLOC(size) malloc(size) -#define TRYFREE(p) {if (p) free(p);} - -static int const gz_magic[2] = {0x1f, 0x8b}; /* gzip magic header */ - -/* gzip flag byte */ -#define ASCII_FLAG 0x01 /* bit 0 set: file probably ascii text */ -#define HEAD_CRC 0x02 /* bit 1 set: header CRC present */ -#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ -#define ORIG_NAME 0x08 /* bit 3 set: original file name present */ -#define COMMENT 0x10 /* bit 4 set: file comment present */ -#define RESERVED 0xE0 /* bits 5..7: reserved */ - -typedef struct gz_stream { - z_stream stream; - int z_err; /* error code for last stream operation */ - int z_eof; /* set if end of input file */ - FILE *file; /* .gz file */ - Byte *inbuf; /* input buffer */ - Byte *outbuf; /* output buffer */ - uLong crc; /* crc32 of uncompressed data */ - char *msg; /* error message */ - char *path; /* path name for debugging only */ - int transparent; /* 1 if input file is not a .gz file */ - char mode; /* 'w' or 'r' */ - z_off_t start; /* start of compressed data in file (header skipped) */ - z_off_t in; /* bytes into deflate or inflate */ - z_off_t out; /* bytes out of deflate or inflate */ - int back; /* one character push-back */ - int last; /* true if push-back is last character */ -} gz_stream; - - -local gzFile gz_open OF((const char *path, const char *mode, int fd)); -local int do_flush OF((gzFile file, int flush)); -local int get_byte OF((gz_stream *s)); -local void check_header OF((gz_stream *s)); -local int destroy OF((gz_stream *s)); -local void putLong OF((FILE *file, uLong x)); -local uLong getLong OF((gz_stream *s)); - -/* =========================================================================== - Opens a gzip (.gz) file for reading or writing. The mode parameter - is as in fopen ("rb" or "wb"). The file is given either by file descriptor - or path name (if fd == -1). - gz_open returns NULL if the file could not be opened or if there was - insufficient memory to allocate the (de)compression state; errno - can be checked to distinguish the two cases (if errno is zero, the - zlib error is Z_MEM_ERROR). -*/ -local gzFile gz_open (path, mode, fd) - const char *path; - const char *mode; - int fd; -{ - int err; - int level = Z_DEFAULT_COMPRESSION; /* compression level */ - int strategy = Z_DEFAULT_STRATEGY; /* compression strategy */ - char *p = (char*)mode; - gz_stream *s; - char fmode[80]; /* copy of mode, without the compression level */ - char *m = fmode; - size_t len; - - if (!path || !mode) return Z_NULL; - - s = (gz_stream *)ALLOC(sizeof(gz_stream)); - if (!s) return Z_NULL; - - s->stream.zalloc = (alloc_func)0; - s->stream.zfree = (free_func)0; - s->stream.opaque = (voidpf)0; - s->stream.next_in = s->inbuf = Z_NULL; - s->stream.next_out = s->outbuf = Z_NULL; - s->stream.avail_in = s->stream.avail_out = 0; - s->file = NULL; - s->z_err = Z_OK; - s->z_eof = 0; - s->in = 0; - s->out = 0; - s->back = EOF; - s->crc = crc32(0L, Z_NULL, 0); - s->msg = NULL; - s->transparent = 0; - - len = strlen(path)+1; - s->path = (char*)ALLOC(len); - if (s->path == NULL) { - return destroy(s), (gzFile)Z_NULL; - } - strlcpy(s->path, path, len); /* do this early for debugging */ - - s->mode = '\0'; - do { - if (*p == 'r') s->mode = 'r'; - if (*p == 'w' || *p == 'a') s->mode = 'w'; - if (*p >= '0' && *p <= '9') { - level = *p - '0'; - } else if (*p == 'f') { - strategy = Z_FILTERED; - } else if (*p == 'h') { - strategy = Z_HUFFMAN_ONLY; - } else if (*p == 'R') { - strategy = Z_RLE; - } else { - *m++ = *p; /* copy the mode */ - } - } while (*p++ && m != fmode + sizeof(fmode)); - if (s->mode == '\0') return destroy(s), (gzFile)Z_NULL; - - if (s->mode == 'w') { -#ifdef NO_GZCOMPRESS - err = Z_STREAM_ERROR; -#else - err = deflateInit2(&(s->stream), level, - Z_DEFLATED, -MAX_WBITS, DEF_MEM_LEVEL, strategy); - /* windowBits is passed < 0 to suppress zlib header */ - - s->stream.next_out = s->outbuf = (Byte*)ALLOC(Z_BUFSIZE); -#endif - if (err != Z_OK || s->outbuf == Z_NULL) { - return destroy(s), (gzFile)Z_NULL; - } - } else { - s->stream.next_in = s->inbuf = (Byte*)ALLOC(Z_BUFSIZE); - - err = inflateInit2(&(s->stream), -MAX_WBITS); - /* windowBits is passed < 0 to tell that there is no zlib header. - * Note that in this case inflate *requires* an extra "dummy" byte - * after the compressed stream in order to complete decompression and - * return Z_STREAM_END. Here the gzip CRC32 ensures that 4 bytes are - * present after the compressed stream. - */ - if (err != Z_OK || s->inbuf == Z_NULL) { - return destroy(s), (gzFile)Z_NULL; - } - } - s->stream.avail_out = Z_BUFSIZE; - - errno = 0; - s->file = fd < 0 ? F_OPEN(path, fmode) : (FILE*)fdopen(fd, fmode); - - if (s->file == NULL) { - return destroy(s), (gzFile)Z_NULL; - } - if (s->mode == 'w') { - /* Write a very simple .gz header: - */ - fprintf(s->file, "%c%c%c%c%c%c%c%c%c%c", gz_magic[0], gz_magic[1], - Z_DEFLATED, 0 /*flags*/, 0,0,0,0 /*time*/, 0 /*xflags*/, OS_CODE); - s->start = 10L; - /* We use 10L instead of ftell(s->file) to because ftell causes an - * fflush on some systems. This version of the library doesn't use - * start anyway in write mode, so this initialization is not - * necessary. - */ - } else { - check_header(s); /* skip the .gz header */ - s->start = ftell(s->file) - s->stream.avail_in; - } - - return (gzFile)s; -} - -/* =========================================================================== - Opens a gzip (.gz) file for reading or writing. -*/ -gzFile ZEXPORT gzopen (path, mode) - const char *path; - const char *mode; -{ - return gz_open (path, mode, -1); -} - -/* =========================================================================== - Associate a gzFile with the file descriptor fd. fd is not dup'ed here - to mimic the behavio(u)r of fdopen. -*/ -gzFile ZEXPORT gzdopen (fd, mode) - int fd; - const char *mode; -{ - char name[46]; /* allow for up to 128-bit integers */ - - if (fd < 0) return (gzFile)Z_NULL; - snprintf(name, sizeof name, "<fd:%d>", fd); /* for debugging */ - - return gz_open (name, mode, fd); -} - -/* =========================================================================== - * Update the compression level and strategy - */ -int ZEXPORT gzsetparams (file, level, strategy) - gzFile file; - int level; - int strategy; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'w') return Z_STREAM_ERROR; - - /* Make room to allow flushing */ - if (s->stream.avail_out == 0) { - - s->stream.next_out = s->outbuf; - if (fwrite(s->outbuf, 1, Z_BUFSIZE, s->file) != Z_BUFSIZE) { - s->z_err = Z_ERRNO; - } - s->stream.avail_out = Z_BUFSIZE; - } - - return deflateParams (&(s->stream), level, strategy); -} - -/* =========================================================================== - Read a byte from a gz_stream; update next_in and avail_in. Return EOF - for end of file. - IN assertion: the stream s has been successfully opened for reading. -*/ -local int get_byte(s) - gz_stream *s; -{ - if (s->z_eof) return EOF; - if (s->stream.avail_in == 0) { - errno = 0; - s->stream.avail_in = (uInt)fread(s->inbuf, 1, Z_BUFSIZE, s->file); - if (s->stream.avail_in == 0) { - s->z_eof = 1; - if (ferror(s->file)) s->z_err = Z_ERRNO; - return EOF; - } - s->stream.next_in = s->inbuf; - } - s->stream.avail_in--; - return *(s->stream.next_in)++; -} - -/* =========================================================================== - Check the gzip header of a gz_stream opened for reading. Set the stream - mode to transparent if the gzip magic header is not present; set s->err - to Z_DATA_ERROR if the magic header is present but the rest of the header - is incorrect. - IN assertion: the stream s has already been created successfully; - s->stream.avail_in is zero for the first time, but may be non-zero - for concatenated .gz files. -*/ -local void check_header(s) - gz_stream *s; -{ - int method; /* method byte */ - int flags; /* flags byte */ - uInt len; - int c; - - /* Assure two bytes in the buffer so we can peek ahead -- handle case - where first byte of header is at the end of the buffer after the last - gzip segment */ - len = s->stream.avail_in; - if (len < 2) { - if (len) s->inbuf[0] = s->stream.next_in[0]; - errno = 0; - len = (uInt)fread(s->inbuf + len, 1, Z_BUFSIZE >> len, s->file); - if (len == 0 && ferror(s->file)) s->z_err = Z_ERRNO; - s->stream.avail_in += len; - s->stream.next_in = s->inbuf; - if (s->stream.avail_in < 2) { - s->transparent = 1; - return; - } - } - - /* Peek ahead to check the gzip magic header */ - if (s->stream.next_in[0] != gz_magic[0] || - s->stream.next_in[1] != gz_magic[1]) { - s->transparent = 1; - return; - } - s->stream.avail_in -= 2; - s->stream.next_in += 2; - - /* Check the rest of the gzip header */ - method = get_byte(s); - flags = get_byte(s); - if (method != Z_DEFLATED || (flags & RESERVED) != 0) { - s->z_err = Z_DATA_ERROR; - return; - } - - /* Discard time, xflags and OS code: */ - for (len = 0; len < 6; len++) (void)get_byte(s); - - if ((flags & EXTRA_FIELD) != 0) { /* skip the extra field */ - len = (uInt)get_byte(s); - len += ((uInt)get_byte(s))<<8; - /* len is garbage if EOF but the loop below will quit anyway */ - while (len-- != 0 && get_byte(s) != EOF) ; - } - if ((flags & ORIG_NAME) != 0) { /* skip the original file name */ - while ((c = get_byte(s)) != 0 && c != EOF) ; - } - if ((flags & COMMENT) != 0) { /* skip the .gz file comment */ - while ((c = get_byte(s)) != 0 && c != EOF) ; - } - if ((flags & HEAD_CRC) != 0) { /* skip the header crc */ - for (len = 0; len < 2; len++) (void)get_byte(s); - } - s->z_err = s->z_eof ? Z_DATA_ERROR : Z_OK; -} - - /* =========================================================================== - * Cleanup then free the given gz_stream. Return a zlib error code. - Try freeing in the reverse order of allocations. - */ -local int destroy (s) - gz_stream *s; -{ - int err = Z_OK; - - if (!s) return Z_STREAM_ERROR; - - TRYFREE(s->msg); - - if (s->stream.state != NULL) { - if (s->mode == 'w') { -#ifdef NO_GZCOMPRESS - err = Z_STREAM_ERROR; -#else - err = deflateEnd(&(s->stream)); -#endif - } else if (s->mode == 'r') { - err = inflateEnd(&(s->stream)); - } - } - if (s->file != NULL && fclose(s->file)) { -#ifdef ESPIPE - if (errno != ESPIPE) /* fclose is broken for pipes in HP/UX */ -#endif - err = Z_ERRNO; - } - if (s->z_err < 0) err = s->z_err; - - TRYFREE(s->inbuf); - TRYFREE(s->outbuf); - TRYFREE(s->path); - TRYFREE(s); - return err; -} - -/* =========================================================================== - Reads the given number of uncompressed bytes from the compressed file. - gzread returns the number of bytes actually read (0 for end of file). -*/ -int ZEXPORT gzread (file, buf, len) - gzFile file; - voidp buf; - unsigned len; -{ - gz_stream *s = (gz_stream*)file; - Bytef *start = (Bytef*)buf; /* starting point for crc computation */ - Byte *next_out; /* == stream.next_out but not forced far (for MSDOS) */ - - if (s == NULL || s->mode != 'r') return Z_STREAM_ERROR; - - if (s->z_err == Z_DATA_ERROR || s->z_err == Z_ERRNO) return -1; - if (s->z_err == Z_STREAM_END) return 0; /* EOF */ - - next_out = (Byte*)buf; - s->stream.next_out = (Bytef*)buf; - s->stream.avail_out = len; - - if (s->stream.avail_out && s->back != EOF) { - *next_out++ = s->back; - s->stream.next_out++; - s->stream.avail_out--; - s->back = EOF; - s->out++; - start++; - if (s->last) { - s->z_err = Z_STREAM_END; - return 1; - } - } - - while (s->stream.avail_out != 0) { - - if (s->transparent) { - /* Copy first the lookahead bytes: */ - uInt n = s->stream.avail_in; - if (n > s->stream.avail_out) n = s->stream.avail_out; - if (n > 0) { - zmemcpy(s->stream.next_out, s->stream.next_in, n); - next_out += n; - s->stream.next_out = next_out; - s->stream.next_in += n; - s->stream.avail_out -= n; - s->stream.avail_in -= n; - } - if (s->stream.avail_out > 0) { - s->stream.avail_out -= - (uInt)fread(next_out, 1, s->stream.avail_out, s->file); - } - len -= s->stream.avail_out; - s->in += len; - s->out += len; - if (len == 0) s->z_eof = 1; - return (int)len; - } - if (s->stream.avail_in == 0 && !s->z_eof) { - - errno = 0; - s->stream.avail_in = (uInt)fread(s->inbuf, 1, Z_BUFSIZE, s->file); - if (s->stream.avail_in == 0) { - s->z_eof = 1; - if (ferror(s->file)) { - s->z_err = Z_ERRNO; - break; - } - } - s->stream.next_in = s->inbuf; - } - s->in += s->stream.avail_in; - s->out += s->stream.avail_out; - s->z_err = inflate(&(s->stream), Z_NO_FLUSH); - s->in -= s->stream.avail_in; - s->out -= s->stream.avail_out; - - if (s->z_err == Z_STREAM_END) { - /* Check CRC and original size */ - s->crc = crc32(s->crc, start, (uInt)(s->stream.next_out - start)); - start = s->stream.next_out; - - if (getLong(s) != s->crc) { - s->z_err = Z_DATA_ERROR; - } else { - (void)getLong(s); - /* The uncompressed length returned by above getlong() may be - * different from s->out in case of concatenated .gz files. - * Check for such files: - */ - check_header(s); - if (s->z_err == Z_OK) { - inflateReset(&(s->stream)); - s->crc = crc32(0L, Z_NULL, 0); - } - } - } - if (s->z_err != Z_OK || s->z_eof) break; - } - s->crc = crc32(s->crc, start, (uInt)(s->stream.next_out - start)); - - if (len == s->stream.avail_out && - (s->z_err == Z_DATA_ERROR || s->z_err == Z_ERRNO)) - return -1; - return (int)(len - s->stream.avail_out); -} - - -/* =========================================================================== - Reads one byte from the compressed file. gzgetc returns this byte - or -1 in case of end of file or error. -*/ -int ZEXPORT gzgetc(file) - gzFile file; -{ - unsigned char c; - - return gzread(file, &c, 1) == 1 ? c : -1; -} - - -/* =========================================================================== - Push one byte back onto the stream. -*/ -int ZEXPORT gzungetc(c, file) - int c; - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'r' || c == EOF || s->back != EOF) return EOF; - s->back = c; - s->out--; - s->last = (s->z_err == Z_STREAM_END); - if (s->last) s->z_err = Z_OK; - s->z_eof = 0; - return c; -} - - -/* =========================================================================== - Reads bytes from the compressed file until len-1 characters are - read, or a newline character is read and transferred to buf, or an - end-of-file condition is encountered. The string is then terminated - with a null character. - gzgets returns buf, or Z_NULL in case of error. - - The current implementation is not optimized at all. -*/ -char * ZEXPORT gzgets(file, buf, len) - gzFile file; - char *buf; - int len; -{ - char *b = buf; - if (buf == Z_NULL || len <= 0) return Z_NULL; - - while (--len > 0 && gzread(file, buf, 1) == 1 && *buf++ != '\n') ; - *buf = '\0'; - return b == buf && len > 0 ? Z_NULL : b; -} - - -#ifndef NO_GZCOMPRESS -/* =========================================================================== - Writes the given number of uncompressed bytes into the compressed file. - gzwrite returns the number of bytes actually written (0 in case of error). -*/ -int ZEXPORT gzwrite (file, buf, len) - gzFile file; - voidpc buf; - unsigned len; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'w') return Z_STREAM_ERROR; - - s->stream.next_in = (Bytef*)buf; - s->stream.avail_in = len; - - while (s->stream.avail_in != 0) { - - if (s->stream.avail_out == 0) { - - s->stream.next_out = s->outbuf; - if (fwrite(s->outbuf, 1, Z_BUFSIZE, s->file) != Z_BUFSIZE) { - s->z_err = Z_ERRNO; - break; - } - s->stream.avail_out = Z_BUFSIZE; - } - s->in += s->stream.avail_in; - s->out += s->stream.avail_out; - s->z_err = deflate(&(s->stream), Z_NO_FLUSH); - s->in -= s->stream.avail_in; - s->out -= s->stream.avail_out; - if (s->z_err != Z_OK) break; - } - s->crc = crc32(s->crc, (const Bytef *)buf, len); - - return (int)(len - s->stream.avail_in); -} - - -/* =========================================================================== - Converts, formats, and writes the args to the compressed file under - control of the format string, as in fprintf. gzprintf returns the number of - uncompressed bytes actually written (0 in case of error). -*/ -#ifdef STDC -#include <stdarg.h> - -int ZEXPORTVA gzprintf (gzFile file, const char *format, /* args */ ...) -{ - char buf[Z_PRINTF_BUFSIZE]; - va_list va; - int len; - - va_start(va, format); -#ifdef HAS_vsnprintf - len = vsnprintf(buf, sizeof(buf), format, va); -#else - (void)vsprintf(buf, format, va); - len = strlen(buf); /* some *sprintf don't return the nb of bytes written */ -#endif - va_end(va); - if (len <= 0 || len >= sizeof(buf)) return 0; - - return gzwrite(file, buf, (unsigned)len); -} -#else /* not ANSI C */ - -int ZEXPORTVA gzprintf (file, format, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, - a11, a12, a13, a14, a15, a16, a17, a18, a19, a20) - gzFile file; - const char *format; - int a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, - a11, a12, a13, a14, a15, a16, a17, a18, a19, a20; -{ - char buf[Z_PRINTF_BUFSIZE]; - int len; - -#ifdef HAS_snprintf - len = snprintf(buf, sizeof(buf), format, a1, a2, a3, a4, a5, a6, a7, a8, - a9, a10, a11, a12, a13, a14, a15, a16, a17, a18, a19, a20); -#else - sprintf(buf, format, a1, a2, a3, a4, a5, a6, a7, a8, - a9, a10, a11, a12, a13, a14, a15, a16, a17, a18, a19, a20); - len = strlen(buf); /* old sprintf doesn't return the nb of bytes written */ -#endif - if (len <= 0 || len >= sizeof(buf)) return 0; - - return gzwrite(file, buf, len); -} -#endif - -/* =========================================================================== - Writes c, converted to an unsigned char, into the compressed file. - gzputc returns the value that was written, or -1 in case of error. -*/ -int ZEXPORT gzputc(file, c) - gzFile file; - int c; -{ - unsigned char cc = (unsigned char) c; /* required for big endian systems */ - - return gzwrite(file, &cc, 1) == 1 ? (int)cc : -1; -} - - -/* =========================================================================== - Writes the given null-terminated string to the compressed file, excluding - the terminating null character. - gzputs returns the number of characters written, or -1 in case of error. -*/ -int ZEXPORT gzputs(file, s) - gzFile file; - const char *s; -{ - return gzwrite(file, (char*)s, (unsigned)strlen(s)); -} - - -/* =========================================================================== - Flushes all pending output into the compressed file. The parameter - flush is as in the deflate() function. -*/ -local int do_flush (file, flush) - gzFile file; - int flush; -{ - uInt len; - int done = 0; - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'w') return Z_STREAM_ERROR; - - s->stream.avail_in = 0; /* should be zero already anyway */ - - for (;;) { - len = Z_BUFSIZE - s->stream.avail_out; - - if (len != 0) { - if ((uInt)fwrite(s->outbuf, 1, len, s->file) != len) { - s->z_err = Z_ERRNO; - return Z_ERRNO; - } - s->stream.next_out = s->outbuf; - s->stream.avail_out = Z_BUFSIZE; - } - if (done) break; - s->out += s->stream.avail_out; - s->z_err = deflate(&(s->stream), flush); - s->out -= s->stream.avail_out; - - /* Ignore the second of two consecutive flushes: */ - if (len == 0 && s->z_err == Z_BUF_ERROR) s->z_err = Z_OK; - - /* deflate has finished flushing only when it hasn't used up - * all the available space in the output buffer: - */ - done = (s->stream.avail_out != 0 || s->z_err == Z_STREAM_END); - - if (s->z_err != Z_OK && s->z_err != Z_STREAM_END) break; - } - return s->z_err == Z_STREAM_END ? Z_OK : s->z_err; -} - -int ZEXPORT gzflush (file, flush) - gzFile file; - int flush; -{ - gz_stream *s = (gz_stream*)file; - int err = do_flush (file, flush); - - if (err) return err; - fflush(s->file); - return s->z_err == Z_STREAM_END ? Z_OK : s->z_err; -} -#endif /* NO_GZCOMPRESS */ - -/* =========================================================================== - Sets the starting position for the next gzread or gzwrite on the given - compressed file. The offset represents a number of bytes in the - gzseek returns the resulting offset location as measured in bytes from - the beginning of the uncompressed stream, or -1 in case of error. - SEEK_END is not implemented, returns error. - In this version of the library, gzseek can be extremely slow. -*/ -z_off_t ZEXPORT gzseek (file, offset, whence) - gzFile file; - z_off_t offset; - int whence; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || whence == SEEK_END || - s->z_err == Z_ERRNO || s->z_err == Z_DATA_ERROR) { - return -1L; - } - - if (s->mode == 'w') { -#ifdef NO_GZCOMPRESS - return -1L; -#else - if (whence == SEEK_SET) { - offset -= s->in; - } - if (offset < 0) return -1L; - - /* At this point, offset is the number of zero bytes to write. */ - if (s->inbuf == Z_NULL) { - s->inbuf = (Byte*)ALLOC(Z_BUFSIZE); /* for seeking */ - if (s->inbuf == Z_NULL) return -1L; - zmemzero(s->inbuf, Z_BUFSIZE); - } - while (offset > 0) { - uInt size = Z_BUFSIZE; - if (offset < Z_BUFSIZE) size = (uInt)offset; - - size = gzwrite(file, s->inbuf, size); - if (size == 0) return -1L; - - offset -= size; - } - return s->in; -#endif - } - /* Rest of function is for reading only */ - - /* compute absolute position */ - if (whence == SEEK_CUR) { - offset += s->out; - } - if (offset < 0) return -1L; - - if (s->transparent) { - /* map to fseek */ - s->back = EOF; - s->stream.avail_in = 0; - s->stream.next_in = s->inbuf; - if (fseek(s->file, offset, SEEK_SET) < 0) return -1L; - - s->in = s->out = offset; - return offset; - } - - /* For a negative seek, rewind and use positive seek */ - if (offset >= s->out) { - offset -= s->out; - } else if (gzrewind(file) < 0) { - return -1L; - } - /* offset is now the number of bytes to skip. */ - - if (offset != 0 && s->outbuf == Z_NULL) { - s->outbuf = (Byte*)ALLOC(Z_BUFSIZE); - if (s->outbuf == Z_NULL) return -1L; - } - if (offset && s->back != EOF) { - s->back = EOF; - s->out++; - offset--; - if (s->last) s->z_err = Z_STREAM_END; - } - while (offset > 0) { - int size = Z_BUFSIZE; - if (offset < Z_BUFSIZE) size = (int)offset; - - size = gzread(file, s->outbuf, (uInt)size); - if (size <= 0) return -1L; - offset -= size; - } - return s->out; -} - -/* =========================================================================== - Rewinds input file. -*/ -int ZEXPORT gzrewind (file) - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'r') return -1; - - s->z_err = Z_OK; - s->z_eof = 0; - s->back = EOF; - s->stream.avail_in = 0; - s->stream.next_in = s->inbuf; - s->crc = crc32(0L, Z_NULL, 0); - if (!s->transparent) (void)inflateReset(&s->stream); - s->in = 0; - s->out = 0; - return fseek(s->file, s->start, SEEK_SET); -} - -/* =========================================================================== - Returns the starting position for the next gzread or gzwrite on the - given compressed file. This position represents a number of bytes in the - uncompressed data stream. -*/ -z_off_t ZEXPORT gztell (file) - gzFile file; -{ - return gzseek(file, 0L, SEEK_CUR); -} - -/* =========================================================================== - Returns 1 when EOF has previously been detected reading the given - input stream, otherwise zero. -*/ -int ZEXPORT gzeof (file) - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - /* With concatenated compressed files that can have embedded - * crc trailers, z_eof is no longer the only/best indicator of EOF - * on a gz_stream. Handle end-of-stream error explicitly here. - */ - if (s == NULL || s->mode != 'r') return 0; - if (s->z_eof) return 1; - return s->z_err == Z_STREAM_END; -} - -/* =========================================================================== - Returns 1 if reading and doing so transparently, otherwise zero. -*/ -int ZEXPORT gzdirect (file) - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL || s->mode != 'r') return 0; - return s->transparent; -} - -/* =========================================================================== - Outputs a long in LSB order to the given file -*/ -local void putLong (file, x) - FILE *file; - uLong x; -{ - int n; - for (n = 0; n < 4; n++) { - fputc((int)(x & 0xff), file); - x >>= 8; - } -} - -/* =========================================================================== - Reads a long in LSB order from the given gz_stream. Sets z_err in case - of error. -*/ -local uLong getLong (s) - gz_stream *s; -{ - uLong x = (uLong)get_byte(s); - int c; - - x += ((uLong)get_byte(s))<<8; - x += ((uLong)get_byte(s))<<16; - c = get_byte(s); - if (c == EOF) s->z_err = Z_DATA_ERROR; - x += ((uLong)c)<<24; - return x; -} - -/* =========================================================================== - Flushes all pending output if necessary, closes the compressed file - and deallocates all the (de)compression state. -*/ -int ZEXPORT gzclose (file) - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL) return Z_STREAM_ERROR; - - if (s->mode == 'w') { -#ifdef NO_GZCOMPRESS - return Z_STREAM_ERROR; -#else - if (do_flush (file, Z_FINISH) != Z_OK) - return destroy((gz_stream*)file); - - putLong (s->file, s->crc); - putLong (s->file, (uLong)(s->in & 0xffffffff)); -#endif - } - 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 occurred on the - given compressed file. errnum is set to zlib error number. If an - error occurred in the file system and not in the compression library, - errnum is set to Z_ERRNO and the application may consult errno - to get the exact error code. -*/ -const char * ZEXPORT gzerror (file, errnum) - gzFile file; - int *errnum; -{ - char *m; - gz_stream *s = (gz_stream*)file; - size_t len; - - if (s == NULL) { - *errnum = Z_STREAM_ERROR; - return (const char*)ERR_MSG(Z_STREAM_ERROR); - } - *errnum = s->z_err; - if (*errnum == Z_OK) return (const char*)""; - - m = (char*)(*errnum == Z_ERRNO ? zstrerror(errno) : s->stream.msg); - - if (m == NULL || *m == '\0') m = (char*)ERR_MSG(s->z_err); - - TRYFREE(s->msg); - len = strlen(s->path) + strlen(m) + 3; - s->msg = (char*)ALLOC(len); - if (s->msg == Z_NULL) return (const char*)ERR_MSG(Z_MEM_ERROR); - strlcpy(s->msg, s->path, len); - strlcat(s->msg, ": ", len); - strlcat(s->msg, m, len); - return (const char*)s->msg; -} - -/* =========================================================================== - Clear the error and end-of-file flags, and do the same for the real file. -*/ -void ZEXPORT gzclearerr (file) - gzFile file; -{ - gz_stream *s = (gz_stream*)file; - - if (s == NULL) return; - if (s->z_err != Z_STREAM_END) s->z_err = Z_OK; - s->z_eof = 0; - clearerr(s->file); -} diff --git a/lib/libz/gzlib.c b/lib/libz/gzlib.c new file mode 100644 index 0000000..003ee4f --- /dev/null +++ b/lib/libz/gzlib.c @@ -0,0 +1,638 @@ +/* $OpenBSD: gzlib.c,v 1.1 2021/07/04 14:24:49 tb Exp $ */ +/* gzlib.c -- zlib functions common to reading and writing gzip files + * Copyright (C) 2004-2017 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "gzguts.h" + +#if defined(_WIN32) && !defined(__BORLANDC__) && !defined(__MINGW32__) +# define LSEEK _lseeki64 +#else +#if defined(_LARGEFILE64_SOURCE) && _LFS64_LARGEFILE-0 +# define LSEEK lseek64 +#else +# define LSEEK lseek +#endif +#endif + +/* Local functions */ +local void gz_reset OF((gz_statep)); +local gzFile gz_open OF((const void *, int, const char *)); + +#if defined UNDER_CE + +/* Map the Windows error number in ERROR to a locale-dependent error message + string and return a pointer to it. Typically, the values for ERROR come + from GetLastError. + + The string pointed to shall not be modified by the application, but may be + overwritten by a subsequent call to gz_strwinerror + + The gz_strwinerror function does not change the current setting of + GetLastError. */ +char ZLIB_INTERNAL *gz_strwinerror (error) + DWORD error; +{ + static char buf[1024]; + + wchar_t *msgbuf; + DWORD lasterr = GetLastError(); + DWORD chars = FormatMessage(FORMAT_MESSAGE_FROM_SYSTEM + | FORMAT_MESSAGE_ALLOCATE_BUFFER, + NULL, + error, + 0, /* Default language */ + (LPVOID)&msgbuf, + 0, + NULL); + if (chars != 0) { + /* If there is an \r\n appended, zap it. */ + if (chars >= 2 + && msgbuf[chars - 2] == '\r' && msgbuf[chars - 1] == '\n') { + chars -= 2; + msgbuf[chars] = 0; + } + + if (chars > sizeof (buf) - 1) { + chars = sizeof (buf) - 1; + msgbuf[chars] = 0; + } + + wcstombs(buf, msgbuf, chars + 1); + LocalFree(msgbuf); + } + else { + sprintf(buf, "unknown win32 error (%ld)", error); + } + + SetLastError(lasterr); + return buf; +} + +#endif /* UNDER_CE */ + +/* Reset gzip file state */ +local void gz_reset(state) + gz_statep state; +{ + state->x.have = 0; /* no output data available */ + if (state->mode == GZ_READ) { /* for reading ... */ + state->eof = 0; /* not at end of file */ + state->past = 0; /* have not read past end yet */ + state->how = LOOK; /* look for gzip header */ + } + state->seek = 0; /* no seek request pending */ + gz_error(state, Z_OK, NULL); /* clear error */ + state->x.pos = 0; /* no uncompressed data yet */ + state->strm.avail_in = 0; /* no input data yet */ +} + +/* Open a gzip file either by name or file descriptor. */ +local gzFile gz_open(path, fd, mode) + const void *path; + int fd; + const char *mode; +{ + gz_statep state; + z_size_t len; + int oflag; +#ifdef O_CLOEXEC + int cloexec = 0; +#endif +#ifdef O_EXCL + int exclusive = 0; +#endif + + /* check input */ + if (path == NULL) + return NULL; + + /* allocate gzFile structure to return */ + state = (gz_statep)malloc(sizeof(gz_state)); + if (state == NULL) + return NULL; + state->size = 0; /* no buffers allocated yet */ + state->want = GZBUFSIZE; /* requested buffer size */ + state->msg = NULL; /* no error message yet */ + + /* interpret mode */ + state->mode = GZ_NONE; + state->level = Z_DEFAULT_COMPRESSION; + state->strategy = Z_DEFAULT_STRATEGY; + state->direct = 0; + while (*mode) { + if (*mode >= '0' && *mode <= '9') + state->level = *mode - '0'; + else + switch (*mode) { + case 'r': + state->mode = GZ_READ; + break; +#ifndef NO_GZCOMPRESS + case 'w': + state->mode = GZ_WRITE; + break; + case 'a': + state->mode = GZ_APPEND; + break; +#endif + case '+': /* can't read and write at the same time */ + free(state); + return NULL; + case 'b': /* ignore -- will request binary anyway */ + break; +#ifdef O_CLOEXEC + case 'e': + cloexec = 1; + break; +#endif +#ifdef O_EXCL + case 'x': + exclusive = 1; + break; +#endif + case 'f': + state->strategy = Z_FILTERED; + break; + case 'h': + state->strategy = Z_HUFFMAN_ONLY; + break; + case 'R': + state->strategy = Z_RLE; + break; + case 'F': + state->strategy = Z_FIXED; + break; + case 'T': + state->direct = 1; + break; + default: /* could consider as an error, but just ignore */ + ; + } + mode++; + } + + /* must provide an "r", "w", or "a" */ + if (state->mode == GZ_NONE) { + free(state); + return NULL; + } + + /* can't force transparent read */ + if (state->mode == GZ_READ) { + if (state->direct) { + free(state); + return NULL; + } + state->direct = 1; /* for empty file */ + } + + /* save the path name for error messages */ +#ifdef WIDECHAR + if (fd == -2) { + len = wcstombs(NULL, path, 0); + if (len == (z_size_t)-1) + len = 0; + } + else +#endif + len = strlen((const char *)path); + state->path = (char *)malloc(len + 1); + if (state->path == NULL) { + free(state); + return NULL; + } +#ifdef WIDECHAR + if (fd == -2) + if (len) + wcstombs(state->path, path, len + 1); + else + *(state->path) = 0; + else +#endif +#if !defined(NO_snprintf) && !defined(NO_vsnprintf) + (void)snprintf(state->path, len + 1, "%s", (const char *)path); +#else + strcpy(state->path, path); +#endif + + /* compute the flags for open() */ + oflag = +#ifdef O_LARGEFILE + O_LARGEFILE | +#endif +#ifdef O_BINARY + O_BINARY | +#endif +#ifdef O_CLOEXEC + (cloexec ? O_CLOEXEC : 0) | +#endif + (state->mode == GZ_READ ? + O_RDONLY : + (O_WRONLY | O_CREAT | +#ifdef O_EXCL + (exclusive ? O_EXCL : 0) | +#endif + (state->mode == GZ_WRITE ? + O_TRUNC : + O_APPEND))); + + /* open the file with the appropriate flags (or just use fd) */ + state->fd = fd > -1 ? fd : ( +#ifdef WIDECHAR + fd == -2 ? _wopen(path, oflag, 0666) : +#endif + open((const char *)path, oflag, 0666)); + if (state->fd == -1) { + free(state->path); + free(state); + return NULL; + } + if (state->mode == GZ_APPEND) { + LSEEK(state->fd, 0, SEEK_END); /* so gzoffset() is correct */ + state->mode = GZ_WRITE; /* simplify later checks */ + } + + /* save the current position for rewinding (only if reading) */ + if (state->mode == GZ_READ) { + state->start = LSEEK(state->fd, 0, SEEK_CUR); + if (state->start == -1) state->start = 0; + } + + /* initialize stream */ + gz_reset(state); + + /* return stream */ + return (gzFile)state; +} + +/* -- see zlib.h -- */ +gzFile ZEXPORT gzopen(path, mode) + const char *path; + const char *mode; +{ + return gz_open(path, -1, mode); +} + +/* -- see zlib.h -- */ +gzFile ZEXPORT gzopen64(path, mode) + const char *path; + const char *mode; +{ + return gz_open(path, -1, mode); +} + +/* -- see zlib.h -- */ +gzFile ZEXPORT gzdopen(fd, mode) + int fd; + const char *mode; +{ + char *path; /* identifier for error messages */ + gzFile gz; + + if (fd == -1 || (path = (char *)malloc(7 + 3 * sizeof(int))) == NULL) + return NULL; +#if !defined(NO_snprintf) && !defined(NO_vsnprintf) + (void)snprintf(path, 7 + 3 * sizeof(int), "<fd:%d>", fd); +#else + sprintf(path, "<fd:%d>", fd); /* for debugging */ +#endif + gz = gz_open(path, fd, mode); + free(path); + return gz; +} + +/* -- see zlib.h -- */ +#ifdef WIDECHAR +gzFile ZEXPORT gzopen_w(path, mode) + const wchar_t *path; + const char *mode; +{ + return gz_open(path, -2, mode); +} +#endif + +/* -- see zlib.h -- */ +int ZEXPORT gzbuffer(file, size) + gzFile file; + unsigned size; +{ + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return -1; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return -1; + + /* make sure we haven't already allocated memory */ + if (state->size != 0) + return -1; + + /* check and set requested size */ + if ((size << 1) < size) + return -1; /* need to be able to double it */ + if (size < 2) + size = 2; /* need two bytes to check magic header */ + state->want = size; + return 0; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzrewind(file) + gzFile file; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + + /* check that we're reading and that there's no error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* back up and start over */ + if (LSEEK(state->fd, state->start, SEEK_SET) == -1) + return -1; + gz_reset(state); + return 0; +} + +/* -- see zlib.h -- */ +z_off64_t ZEXPORT gzseek64(file, offset, whence) + gzFile file; + z_off64_t offset; + int whence; +{ + unsigned n; + z_off64_t ret; + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return -1; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return -1; + + /* check that there's no error */ + if (state->err != Z_OK && state->err != Z_BUF_ERROR) + return -1; + + /* can only seek from start or relative to current position */ + if (whence != SEEK_SET && whence != SEEK_CUR) + return -1; + + /* normalize offset to a SEEK_CUR specification */ + if (whence == SEEK_SET) + offset -= state->x.pos; + else if (state->seek) + offset += state->skip; + state->seek = 0; + + /* if within raw area while reading, just go there */ + if (state->mode == GZ_READ && state->how == COPY && + state->x.pos + offset >= 0) { + ret = LSEEK(state->fd, offset - state->x.have, SEEK_CUR); + if (ret == -1) + return -1; + state->x.have = 0; + state->eof = 0; + state->past = 0; + state->seek = 0; + gz_error(state, Z_OK, NULL); + state->strm.avail_in = 0; + state->x.pos += offset; + return state->x.pos; + } + + /* calculate skip amount, rewinding if needed for back seek when reading */ + if (offset < 0) { + if (state->mode != GZ_READ) /* writing -- can't go backwards */ + return -1; + offset += state->x.pos; + if (offset < 0) /* before start of file! */ + return -1; + if (gzrewind(file) == -1) /* rewind, then skip to offset */ + return -1; + } + + /* if reading, skip what's in output buffer (one less gzgetc() check) */ + if (state->mode == GZ_READ) { + n = GT_OFF(state->x.have) || (z_off64_t)state->x.have > offset ? + (unsigned)offset : state->x.have; + state->x.have -= n; + state->x.next += n; + state->x.pos += n; + offset -= n; + } + + /* request skip (if not zero) */ + if (offset) { + state->seek = 1; + state->skip = offset; + } + return state->x.pos + offset; +} + +/* -- see zlib.h -- */ +z_off_t ZEXPORT gzseek(file, offset, whence) + gzFile file; + z_off_t offset; + int whence; +{ + z_off64_t ret; + + ret = gzseek64(file, (z_off64_t)offset, whence); + return ret == (z_off_t)ret ? (z_off_t)ret : -1; +} + +/* -- see zlib.h -- */ +z_off64_t ZEXPORT gztell64(file) + gzFile file; +{ + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return -1; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return -1; + + /* return position */ + return state->x.pos + (state->seek ? state->skip : 0); +} + +/* -- see zlib.h -- */ +z_off_t ZEXPORT gztell(file) + gzFile file; +{ + z_off64_t ret; + + ret = gztell64(file); + return ret == (z_off_t)ret ? (z_off_t)ret : -1; +} + +/* -- see zlib.h -- */ +z_off64_t ZEXPORT gzoffset64(file) + gzFile file; +{ + z_off64_t offset; + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return -1; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return -1; + + /* compute and return effective offset in file */ + offset = LSEEK(state->fd, 0, SEEK_CUR); + if (offset == -1) + return -1; + if (state->mode == GZ_READ) /* reading */ + offset -= state->strm.avail_in; /* don't count buffered input */ + return offset; +} + +/* -- see zlib.h -- */ +z_off_t ZEXPORT gzoffset(file) + gzFile file; +{ + z_off64_t ret; + + ret = gzoffset64(file); + return ret == (z_off_t)ret ? (z_off_t)ret : -1; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzeof(file) + gzFile file; +{ + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return 0; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return 0; + + /* return end-of-file state */ + return state->mode == GZ_READ ? state->past : 0; +} + +/* -- see zlib.h -- */ +const char * ZEXPORT gzerror(file, errnum) + gzFile file; + int *errnum; +{ + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return NULL; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return NULL; + + /* return error information */ + if (errnum != NULL) + *errnum = state->err; + return state->err == Z_MEM_ERROR ? "out of memory" : + (state->msg == NULL ? "" : state->msg); +} + +/* -- see zlib.h -- */ +void ZEXPORT gzclearerr(file) + gzFile file; +{ + gz_statep state; + + /* get internal structure and check integrity */ + if (file == NULL) + return; + state = (gz_statep)file; + if (state->mode != GZ_READ && state->mode != GZ_WRITE) + return; + + /* clear error and end-of-file */ + if (state->mode == GZ_READ) { + state->eof = 0; + state->past = 0; + } + gz_error(state, Z_OK, NULL); +} + +/* Create an error message in allocated memory and set state->err and + state->msg accordingly. Free any previous error message already there. Do + not try to free or allocate space if the error is Z_MEM_ERROR (out of + memory). Simply save the error message as a static string. If there is an + allocation failure constructing the error message, then convert the error to + out of memory. */ +void ZLIB_INTERNAL gz_error(state, err, msg) + gz_statep state; + int err; + const char *msg; +{ + /* free previously allocated message and clear */ + if (state->msg != NULL) { + if (state->err != Z_MEM_ERROR) + free(state->msg); + state->msg = NULL; + } + + /* if fatal, set state->x.have to 0 so that the gzgetc() macro fails */ + if (err != Z_OK && err != Z_BUF_ERROR) + state->x.have = 0; + + /* set error code, and if no message, then done */ + state->err = err; + if (msg == NULL) + return; + + /* for an out of memory error, return literal string when requested */ + if (err == Z_MEM_ERROR) + return; + + /* construct error message with path */ + if ((state->msg = (char *)malloc(strlen(state->path) + strlen(msg) + 3)) == + NULL) { + state->err = Z_MEM_ERROR; + return; + } +#if !defined(NO_snprintf) && !defined(NO_vsnprintf) + (void)snprintf(state->msg, strlen(state->path) + strlen(msg) + 3, + "%s%s%s", state->path, ": ", msg); +#else + strcpy(state->msg, state->path); + strcat(state->msg, ": "); + strcat(state->msg, msg); +#endif +} + +#ifndef INT_MAX +/* portably return maximum value for an int (when limits.h presumed not + available) -- we need to do this to cover cases where 2's complement not + used, since C standard permits 1's complement and sign-bit representations, + otherwise we could just use ((unsigned)-1) >> 1 */ +unsigned ZLIB_INTERNAL gz_intmax() +{ + unsigned p, q; + + p = 1; + do { + q = p; + p <<= 1; + p++; + } while (p > q); + return q >> 1; +} +#endif diff --git a/lib/libz/gzread.c b/lib/libz/gzread.c new file mode 100644 index 0000000..abbd531 --- /dev/null +++ b/lib/libz/gzread.c @@ -0,0 +1,655 @@ +/* $OpenBSD: gzread.c,v 1.1 2021/07/04 14:24:49 tb Exp $ */ +/* gzread.c -- zlib functions for reading gzip files + * Copyright (C) 2004, 2005, 2010, 2011, 2012, 2013, 2016 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "gzguts.h" + +/* Local functions */ +local int gz_load OF((gz_statep, unsigned char *, unsigned, unsigned *)); +local int gz_avail OF((gz_statep)); +local int gz_look OF((gz_statep)); +local int gz_decomp OF((gz_statep)); +local int gz_fetch OF((gz_statep)); +local int gz_skip OF((gz_statep, z_off64_t)); +local z_size_t gz_read OF((gz_statep, voidp, z_size_t)); + +/* Use read() to load a buffer -- return -1 on error, otherwise 0. Read from + state->fd, and update state->eof, state->err, and state->msg as appropriate. + This function needs to loop on read(), since read() is not guaranteed to + read the number of bytes requested, depending on the type of descriptor. */ +local int gz_load(state, buf, len, have) + gz_statep state; + unsigned char *buf; + unsigned len; + unsigned *have; +{ + int ret; + unsigned get, max = ((unsigned)-1 >> 2) + 1; + + *have = 0; + do { + get = len - *have; + if (get > max) + get = max; + ret = read(state->fd, buf + *have, get); + if (ret <= 0) + break; + *have += (unsigned)ret; + } while (*have < len); + if (ret < 0) { + gz_error(state, Z_ERRNO, zstrerror()); + return -1; + } + if (ret == 0) + state->eof = 1; + return 0; +} + +/* Load up input buffer and set eof flag if last data loaded -- return -1 on + error, 0 otherwise. Note that the eof flag is set when the end of the input + file is reached, even though there may be unused data in the buffer. Once + that data has been used, no more attempts will be made to read the file. + If strm->avail_in != 0, then the current data is moved to the beginning of + the input buffer, and then the remainder of the buffer is loaded with the + available data from the input file. */ +local int gz_avail(state) + gz_statep state; +{ + unsigned got; + z_streamp strm = &(state->strm); + + if (state->err != Z_OK && state->err != Z_BUF_ERROR) + return -1; + if (state->eof == 0) { + if (strm->avail_in) { /* copy what's there to the start */ + unsigned char *p = state->in; + unsigned const char *q = strm->next_in; + unsigned n = strm->avail_in; + do { + *p++ = *q++; + } while (--n); + } + if (gz_load(state, state->in + strm->avail_in, + state->size - strm->avail_in, &got) == -1) + return -1; + strm->avail_in += got; + strm->next_in = state->in; + } + return 0; +} + +/* Look for gzip header, set up for inflate or copy. state->x.have must be 0. + If this is the first time in, allocate required memory. state->how will be + left unchanged if there is no more input data available, will be set to COPY + if there is no gzip header and direct copying will be performed, or it will + be set to GZIP for decompression. If direct copying, then leftover input + data from the input buffer will be copied to the output buffer. In that + case, all further file reads will be directly to either the output buffer or + a user buffer. If decompressing, the inflate state will be initialized. + gz_look() will return 0 on success or -1 on failure. */ +local int gz_look(state) + gz_statep state; +{ + z_streamp strm = &(state->strm); + + /* allocate read buffers and inflate memory */ + if (state->size == 0) { + /* allocate buffers */ + state->in = (unsigned char *)malloc(state->want); + state->out = (unsigned char *)malloc(state->want << 1); + if (state->in == NULL || state->out == NULL) { + free(state->out); + free(state->in); + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + state->size = state->want; + + /* allocate inflate memory */ + state->strm.zalloc = Z_NULL; + state->strm.zfree = Z_NULL; + state->strm.opaque = Z_NULL; + state->strm.avail_in = 0; + state->strm.next_in = Z_NULL; + if (inflateInit2(&(state->strm), 15 + 16) != Z_OK) { /* gunzip */ + free(state->out); + free(state->in); + state->size = 0; + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + } + + /* get at least the magic bytes in the input buffer */ + if (strm->avail_in < 2) { + if (gz_avail(state) == -1) + return -1; + if (strm->avail_in == 0) + return 0; + } + + /* look for gzip magic bytes -- if there, do gzip decoding (note: there is + a logical dilemma here when considering the case of a partially written + gzip file, to wit, if a single 31 byte is written, then we cannot tell + whether this is a single-byte file, or just a partially written gzip + file -- for here we assume that if a gzip file is being written, then + the header will be written in a single operation, so that reading a + single byte is sufficient indication that it is not a gzip file) */ + if (strm->avail_in > 1 && + strm->next_in[0] == 31 && strm->next_in[1] == 139) { + inflateReset(strm); + state->how = GZIP; + state->direct = 0; + return 0; + } + + /* no gzip header -- if we were decoding gzip before, then this is trailing + garbage. Ignore the trailing garbage and finish. */ + if (state->direct == 0) { + strm->avail_in = 0; + state->eof = 1; + state->x.have = 0; + return 0; + } + + /* doing raw i/o, copy any leftover input to output -- this assumes that + the output buffer is larger than the input buffer, which also assures + space for gzungetc() */ + state->x.next = state->out; + if (strm->avail_in) { + memcpy(state->x.next, strm->next_in, strm->avail_in); + state->x.have = strm->avail_in; + strm->avail_in = 0; + } + state->how = COPY; + state->direct = 1; + return 0; +} + +/* Decompress from input to the provided next_out and avail_out in the state. + On return, state->x.have and state->x.next point to the just decompressed + data. If the gzip stream completes, state->how is reset to LOOK to look for + the next gzip stream or raw data, once state->x.have is depleted. Returns 0 + on success, -1 on failure. */ +local int gz_decomp(state) + gz_statep state; +{ + int ret = Z_OK; + unsigned had; + z_streamp strm = &(state->strm); + + /* fill output buffer up to end of deflate stream */ + had = strm->avail_out; + do { + /* get more input for inflate() */ + if (strm->avail_in == 0 && gz_avail(state) == -1) + return -1; + if (strm->avail_in == 0) { + gz_error(state, Z_BUF_ERROR, "unexpected end of file"); + break; + } + + /* decompress and handle errors */ + ret = inflate(strm, Z_NO_FLUSH); + if (ret == Z_STREAM_ERROR || ret == Z_NEED_DICT) { + gz_error(state, Z_STREAM_ERROR, + "internal error: inflate stream corrupt"); + return -1; + } + if (ret == Z_MEM_ERROR) { + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + if (ret == Z_DATA_ERROR) { /* deflate stream invalid */ + gz_error(state, Z_DATA_ERROR, + strm->msg == NULL ? "compressed data error" : strm->msg); + return -1; + } + } while (strm->avail_out && ret != Z_STREAM_END); + + /* update available output */ + state->x.have = had - strm->avail_out; + state->x.next = strm->next_out - state->x.have; + + /* if the gzip stream completed successfully, look for another */ + if (ret == Z_STREAM_END) + state->how = LOOK; + + /* good decompression */ + return 0; +} + +/* Fetch data and put it in the output buffer. Assumes state->x.have is 0. + Data is either copied from the input file or decompressed from the input + file depending on state->how. If state->how is LOOK, then a gzip header is + looked for to determine whether to copy or decompress. Returns -1 on error, + otherwise 0. gz_fetch() will leave state->how as COPY or GZIP unless the + end of the input file has been reached and all data has been processed. */ +local int gz_fetch(state) + gz_statep state; +{ + z_streamp strm = &(state->strm); + + do { + switch(state->how) { + case LOOK: /* -> LOOK, COPY (only if never GZIP), or GZIP */ + if (gz_look(state) == -1) + return -1; + if (state->how == LOOK) + return 0; + break; + case COPY: /* -> COPY */ + if (gz_load(state, state->out, state->size << 1, &(state->x.have)) + == -1) + return -1; + state->x.next = state->out; + return 0; + case GZIP: /* -> GZIP or LOOK (if end of gzip stream) */ + strm->avail_out = state->size << 1; + strm->next_out = state->out; + if (gz_decomp(state) == -1) + return -1; + } + } while (state->x.have == 0 && (!state->eof || strm->avail_in)); + return 0; +} + +/* Skip len uncompressed bytes of output. Return -1 on error, 0 on success. */ +local int gz_skip(state, len) + gz_statep state; + z_off64_t len; +{ + unsigned n; + + /* skip over len bytes or reach end-of-file, whichever comes first */ + while (len) + /* skip over whatever is in output buffer */ + if (state->x.have) { + n = GT_OFF(state->x.have) || (z_off64_t)state->x.have > len ? + (unsigned)len : state->x.have; + state->x.have -= n; + state->x.next += n; + state->x.pos += n; + len -= n; + } + + /* output buffer empty -- return if we're at the end of the input */ + else if (state->eof && state->strm.avail_in == 0) + break; + + /* need more data to skip -- load up output buffer */ + else { + /* get more output, looking for header if required */ + if (gz_fetch(state) == -1) + return -1; + } + return 0; +} + +/* Read len bytes into buf from file, or less than len up to the end of the + input. Return the number of bytes read. If zero is returned, either the + end of file was reached, or there was an error. state->err must be + consulted in that case to determine which. */ +local z_size_t gz_read(state, buf, len) + gz_statep state; + voidp buf; + z_size_t len; +{ + z_size_t got; + unsigned n; + + /* if len is zero, avoid unnecessary operations */ + if (len == 0) + return 0; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return 0; + } + + /* get len bytes to buf, or less than len if at the end */ + got = 0; + do { + /* set n to the maximum amount of len that fits in an unsigned int */ + n = -1; + if (n > len) + n = len; + + /* first just try copying data from the output buffer */ + if (state->x.have) { + if (state->x.have < n) + n = state->x.have; + memcpy(buf, state->x.next, n); + state->x.next += n; + state->x.have -= n; + } + + /* output buffer empty -- return if we're at the end of the input */ + else if (state->eof && state->strm.avail_in == 0) { + state->past = 1; /* tried to read past end */ + break; + } + + /* need output data -- for small len or new stream load up our output + buffer */ + else if (state->how == LOOK || n < (state->size << 1)) { + /* get more output, looking for header if required */ + if (gz_fetch(state) == -1) + return 0; + continue; /* no progress yet -- go back to copy above */ + /* the copy above assures that we will leave with space in the + output buffer, allowing at least one gzungetc() to succeed */ + } + + /* large len -- read directly into user buffer */ + else if (state->how == COPY) { /* read directly */ + if (gz_load(state, (unsigned char *)buf, n, &n) == -1) + return 0; + } + + /* large len -- decompress directly into user buffer */ + else { /* state->how == GZIP */ + state->strm.avail_out = n; + state->strm.next_out = (unsigned char *)buf; + if (gz_decomp(state) == -1) + return 0; + n = state->x.have; + state->x.have = 0; + } + + /* update progress */ + len -= n; + buf = (char *)buf + n; + got += n; + state->x.pos += n; + } while (len); + + /* return number of bytes read into user buffer */ + return got; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzread(file, buf, len) + gzFile file; + voidp buf; + unsigned len; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* since an int is returned, make sure len fits in one, otherwise return + with an error (this avoids a flaw in the interface) */ + if ((int)len < 0) { + gz_error(state, Z_STREAM_ERROR, "request does not fit in an int"); + return -1; + } + + /* read len or fewer bytes to buf */ + len = gz_read(state, buf, len); + + /* check for an error */ + if (len == 0 && state->err != Z_OK && state->err != Z_BUF_ERROR) + return -1; + + /* return the number of bytes read (this is assured to fit in an int) */ + return (int)len; +} + +/* -- see zlib.h -- */ +z_size_t ZEXPORT gzfread(buf, size, nitems, file) + voidp buf; + z_size_t size; + z_size_t nitems; + gzFile file; +{ + z_size_t len; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return 0; + state = (gz_statep)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return 0; + + /* compute bytes to read -- error on overflow */ + len = nitems * size; + if (size && len / size != nitems) { + gz_error(state, Z_STREAM_ERROR, "request does not fit in a size_t"); + return 0; + } + + /* read len or fewer bytes to buf, return the number of full items read */ + return len ? gz_read(state, buf, len) / size : 0; +} + +/* -- see zlib.h -- */ +#ifdef Z_PREFIX_SET +# undef z_gzgetc +#else +# undef gzgetc +#endif +int ZEXPORT gzgetc(file) + gzFile file; +{ + int ret; + unsigned char buf[1]; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* try output buffer (no need to check for skip request) */ + if (state->x.have) { + state->x.have--; + state->x.pos++; + return *(state->x.next)++; + } + + /* nothing there -- try gz_read() */ + ret = gz_read(state, buf, 1); + return ret < 1 ? -1 : buf[0]; +} + +int ZEXPORT gzgetc_(file) +gzFile file; +{ + return gzgetc(file); +} + +/* -- see zlib.h -- */ +int ZEXPORT gzungetc(c, file) + int c; + gzFile file; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return -1; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return -1; + } + + /* can't push EOF */ + if (c < 0) + return -1; + + /* if output buffer empty, put byte at end (allows more pushing) */ + if (state->x.have == 0) { + state->x.have = 1; + state->x.next = state->out + (state->size << 1) - 1; + state->x.next[0] = (unsigned char)c; + state->x.pos--; + state->past = 0; + return c; + } + + /* if no room, give up (must have already done a gzungetc()) */ + if (state->x.have == (state->size << 1)) { + gz_error(state, Z_DATA_ERROR, "out of room to push characters"); + return -1; + } + + /* slide output data if needed and insert byte before existing data */ + if (state->x.next == state->out) { + unsigned char *src = state->out + state->x.have; + unsigned char *dest = state->out + (state->size << 1); + while (src > state->out) + *--dest = *--src; + state->x.next = dest; + } + state->x.have++; + state->x.next--; + state->x.next[0] = (unsigned char)c; + state->x.pos--; + state->past = 0; + return c; +} + +/* -- see zlib.h -- */ +char * ZEXPORT gzgets(file, buf, len) + gzFile file; + char *buf; + int len; +{ + unsigned left, n; + char *str; + unsigned char *eol; + gz_statep state; + + /* check parameters and get internal structure */ + if (file == NULL || buf == NULL || len < 1) + return NULL; + state = (gz_statep)file; + + /* check that we're reading and that there's no (serious) error */ + if (state->mode != GZ_READ || + (state->err != Z_OK && state->err != Z_BUF_ERROR)) + return NULL; + + /* process a skip request */ + if (state->seek) { + state->seek = 0; + if (gz_skip(state, state->skip) == -1) + return NULL; + } + + /* copy output bytes up to new line or len - 1, whichever comes first -- + append a terminating zero to the string (we don't check for a zero in + the contents, let the user worry about that) */ + str = buf; + left = (unsigned)len - 1; + if (left) do { + /* assure that something is in the output buffer */ + if (state->x.have == 0 && gz_fetch(state) == -1) + return NULL; /* error */ + if (state->x.have == 0) { /* end of file */ + state->past = 1; /* read past end */ + break; /* return what we have */ + } + + /* look for end-of-line in current output buffer */ + n = state->x.have > left ? left : state->x.have; + eol = (unsigned char *)memchr(state->x.next, '\n', n); + if (eol != NULL) + n = (unsigned)(eol - state->x.next) + 1; + + /* copy through end-of-line, or remainder if not found */ + memcpy(buf, state->x.next, n); + state->x.have -= n; + state->x.next += n; + state->x.pos += n; + left -= n; + buf += n; + } while (left && eol == NULL); + + /* return terminated string, or if nothing, end of file */ + if (buf == str) + return NULL; + buf[0] = 0; + return str; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzdirect(file) + gzFile file; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return 0; + state = (gz_statep)file; + + /* if the state is not known, but we can find out, then do so (this is + mainly for right after a gzopen() or gzdopen()) */ + if (state->mode == GZ_READ && state->how == LOOK && state->x.have == 0) + (void)gz_look(state); + + /* return 1 if transparent, 0 if processing a gzip stream */ + return state->direct; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzclose_r(file) + gzFile file; +{ + int ret, err; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + + /* check that we're reading */ + if (state->mode != GZ_READ) + return Z_STREAM_ERROR; + + /* free memory and close file */ + if (state->size) { + inflateEnd(&(state->strm)); + free(state->out); + free(state->in); + } + err = state->err == Z_BUF_ERROR ? Z_BUF_ERROR : Z_OK; + gz_error(state, Z_OK, NULL); + free(state->path); + ret = close(state->fd); + free(state); + return ret ? Z_ERRNO : err; +} diff --git a/lib/libz/gzwrite.c b/lib/libz/gzwrite.c new file mode 100644 index 0000000..915edb9 --- /dev/null +++ b/lib/libz/gzwrite.c @@ -0,0 +1,666 @@ +/* $OpenBSD: gzwrite.c,v 1.1 2021/07/04 14:24:49 tb Exp $ */ +/* gzwrite.c -- zlib functions for writing gzip files + * Copyright (C) 2004-2017 Mark Adler + * For conditions of distribution and use, see copyright notice in zlib.h + */ + +#include "gzguts.h" + +/* Local functions */ +local int gz_init OF((gz_statep)); +local int gz_comp OF((gz_statep, int)); +local int gz_zero OF((gz_statep, z_off64_t)); +local z_size_t gz_write OF((gz_statep, voidpc, z_size_t)); + +/* Initialize state for writing a gzip file. Mark initialization by setting + state->size to non-zero. Return -1 on a memory allocation failure, or 0 on + success. */ +local int gz_init(state) + gz_statep state; +{ + int ret; + z_streamp strm = &(state->strm); + + /* allocate input buffer (double size for gzprintf) */ + state->in = (unsigned char *)malloc(state->want << 1); + if (state->in == NULL) { + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + + /* only need output buffer and deflate state if compressing */ + if (!state->direct) { + /* allocate output buffer */ + state->out = (unsigned char *)malloc(state->want); + if (state->out == NULL) { + free(state->in); + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + + /* allocate deflate memory, set up for gzip compression */ + strm->zalloc = Z_NULL; + strm->zfree = Z_NULL; + strm->opaque = Z_NULL; + ret = deflateInit2(strm, state->level, Z_DEFLATED, + MAX_WBITS + 16, DEF_MEM_LEVEL, state->strategy); + if (ret != Z_OK) { + free(state->out); + free(state->in); + gz_error(state, Z_MEM_ERROR, "out of memory"); + return -1; + } + strm->next_in = NULL; + } + + /* mark state as initialized */ + state->size = state->want; + + /* initialize write buffer if compressing */ + if (!state->direct) { + strm->avail_out = state->size; + strm->next_out = state->out; + state->x.next = strm->next_out; + } + return 0; +} + +/* Compress whatever is at avail_in and next_in and write to the output file. + Return -1 if there is an error writing to the output file or if gz_init() + fails to allocate memory, otherwise 0. flush is assumed to be a valid + deflate() flush value. If flush is Z_FINISH, then the deflate() state is + reset to start a new gzip stream. If gz->direct is true, then simply write + to the output file without compressing, and ignore flush. */ +local int gz_comp(state, flush) + gz_statep state; + int flush; +{ + int ret, writ; + unsigned have, put, max = ((unsigned)-1 >> 2) + 1; + z_streamp strm = &(state->strm); + + /* allocate memory if this is the first time through */ + if (state->size == 0 && gz_init(state) == -1) + return -1; + + /* write directly if requested */ + if (state->direct) { + while (strm->avail_in) { + put = strm->avail_in > max ? max : strm->avail_in; + writ = write(state->fd, strm->next_in, put); + if (writ < 0) { + gz_error(state, Z_ERRNO, zstrerror()); + return -1; + } + strm->avail_in -= (unsigned)writ; + strm->next_in += writ; + } + return 0; + } + + /* run deflate() on provided input until it produces no more output */ + ret = Z_OK; + do { + /* write out current buffer contents if full, or if flushing, but if + doing Z_FINISH then don't write until we get to Z_STREAM_END */ + if (strm->avail_out == 0 || (flush != Z_NO_FLUSH && + (flush != Z_FINISH || ret == Z_STREAM_END))) { + while (strm->next_out > state->x.next) { + put = strm->next_out - state->x.next > (int)max ? max : + (unsigned)(strm->next_out - state->x.next); + writ = write(state->fd, state->x.next, put); + if (writ < 0) { + gz_error(state, Z_ERRNO, zstrerror()); + return -1; + } + state->x.next += writ; + } + if (strm->avail_out == 0) { + strm->avail_out = state->size; + strm->next_out = state->out; + state->x.next = state->out; + } + } + + /* compress */ + have = strm->avail_out; + ret = deflate(strm, flush); + if (ret == Z_STREAM_ERROR) { + gz_error(state, Z_STREAM_ERROR, + "internal error: deflate stream corrupt"); + return -1; + } + have -= strm->avail_out; + } while (have); + + /* if that completed a deflate stream, allow another to start */ + if (flush == Z_FINISH) + deflateReset(strm); + + /* all done, no errors */ + return 0; +} + +/* Compress len zeros to output. Return -1 on a write error or memory + allocation failure by gz_comp(), or 0 on success. */ +local int gz_zero(state, len) + gz_statep state; + z_off64_t len; +{ + int first; + unsigned n; + z_streamp strm = &(state->strm); + + /* consume whatever's left in the input buffer */ + if (strm->avail_in && gz_comp(state, Z_NO_FLUSH) == -1) + return -1; + + /* compress len zeros (len guaranteed > 0) */ + first = 1; + while (len) { + n = GT_OFF(state->size) || (z_off64_t)state->size > len ? + (unsigned)len : state->size; + if (first) { + memset(state->in, 0, n); + first = 0; + } + strm->avail_in = n; + strm->next_in = state->in; + state->x.pos += n; + if (gz_comp(state, Z_NO_FLUSH) == -1) + return -1; + len -= n; + } + return 0; +} + +/* Write len bytes from buf to file. Return the number of bytes written. If + the returned value is less than len, then there was an error. */ +local z_size_t gz_write(state, buf, len) + gz_statep state; + voidpc buf; + z_size_t len; +{ + z_size_t put = len; + + /* if len is zero, avoid unnecessary operations */ + if (len == 0) + return 0; + + /* allocate memory if this is the first time through */ + if (state->size == 0 && gz_init(state) == -1) + return 0; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return 0; + } + + /* for small len, copy to input buffer, otherwise compress directly */ + if (len < state->size) { + /* copy to input buffer, compress when full */ + do { + unsigned have, copy; + + if (state->strm.avail_in == 0) + state->strm.next_in = state->in; + have = (unsigned)((state->strm.next_in + state->strm.avail_in) - + state->in); + copy = state->size - have; + if (copy > len) + copy = len; + memcpy(state->in + have, buf, copy); + state->strm.avail_in += copy; + state->x.pos += copy; + buf = (const char *)buf + copy; + len -= copy; + if (len && gz_comp(state, Z_NO_FLUSH) == -1) + return 0; + } while (len); + } + else { + /* consume whatever's left in the input buffer */ + if (state->strm.avail_in && gz_comp(state, Z_NO_FLUSH) == -1) + return 0; + + /* directly compress user buffer to file */ + state->strm.next_in = (z_const Bytef *)buf; + do { + unsigned n = (unsigned)-1; + if (n > len) + n = len; + state->strm.avail_in = n; + state->x.pos += n; + if (gz_comp(state, Z_NO_FLUSH) == -1) + return 0; + len -= n; + } while (len); + } + + /* input was all buffered or compressed */ + return put; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzwrite(file, buf, len) + gzFile file; + voidpc buf; + unsigned len; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return 0; + state = (gz_statep)file; + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return 0; + + /* since an int is returned, make sure len fits in one, otherwise return + with an error (this avoids a flaw in the interface) */ + if ((int)len < 0) { + gz_error(state, Z_DATA_ERROR, "requested length does not fit in int"); + return 0; + } + + /* write len bytes from buf (the return value will fit in an int) */ + return (int)gz_write(state, buf, len); +} + +/* -- see zlib.h -- */ +z_size_t ZEXPORT gzfwrite(buf, size, nitems, file) + voidpc buf; + z_size_t size; + z_size_t nitems; + gzFile file; +{ + z_size_t len; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return 0; + state = (gz_statep)file; + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return 0; + + /* compute bytes to read -- error on overflow */ + len = nitems * size; + if (size && len / size != nitems) { + gz_error(state, Z_STREAM_ERROR, "request does not fit in a size_t"); + return 0; + } + + /* write len bytes to buf, return the number of full items written */ + return len ? gz_write(state, buf, len) / size : 0; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzputc(file, c) + gzFile file; + int c; +{ + unsigned have; + unsigned char buf[1]; + gz_statep state; + z_streamp strm; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + strm = &(state->strm); + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return -1; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return -1; + } + + /* try writing to input buffer for speed (state->size == 0 if buffer not + initialized) */ + if (state->size) { + if (strm->avail_in == 0) + strm->next_in = state->in; + have = (unsigned)((strm->next_in + strm->avail_in) - state->in); + if (have < state->size) { + state->in[have] = (unsigned char)c; + strm->avail_in++; + state->x.pos++; + return c & 0xff; + } + } + + /* no room in buffer or not initialized, use gz_write() */ + buf[0] = (unsigned char)c; + if (gz_write(state, buf, 1) != 1) + return -1; + return c & 0xff; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzputs(file, str) + gzFile file; + const char *str; +{ + int ret; + z_size_t len; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return -1; + state = (gz_statep)file; + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return -1; + + /* write string */ + len = strlen(str); + ret = gz_write(state, str, len); + return ret == 0 && len != 0 ? -1 : ret; +} + +#if defined(STDC) || defined(Z_HAVE_STDARG_H) +#include <stdarg.h> + +/* -- see zlib.h -- */ +int ZEXPORTVA gzvprintf(gzFile file, const char *format, va_list va) +{ + int len; + unsigned left; + char *next; + gz_statep state; + z_streamp strm; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + strm = &(state->strm); + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return Z_STREAM_ERROR; + + /* make sure we have some buffer space */ + if (state->size == 0 && gz_init(state) == -1) + return state->err; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return state->err; + } + + /* do the printf() into the input buffer, put length in len -- the input + buffer is double-sized just for this function, so there is guaranteed to + be state->size bytes available after the current contents */ + if (strm->avail_in == 0) + strm->next_in = state->in; + next = (char *)(state->in + (strm->next_in - state->in) + strm->avail_in); + next[state->size - 1] = 0; +#ifdef NO_vsnprintf +# ifdef HAS_vsprintf_void + (void)vsprintf(next, format, va); + for (len = 0; len < state->size; len++) + if (next[len] == 0) break; +# else + len = vsprintf(next, format, va); +# endif +#else +# ifdef HAS_vsnprintf_void + (void)vsnprintf(next, state->size, format, va); + len = strlen(next); +# else + len = vsnprintf(next, state->size, format, va); +# endif +#endif + + /* check that printf() results fit in buffer */ + if (len == 0 || (unsigned)len >= state->size || next[state->size - 1] != 0) + return 0; + + /* update buffer and position, compress first half if past that */ + strm->avail_in += (unsigned)len; + state->x.pos += len; + if (strm->avail_in >= state->size) { + left = strm->avail_in - state->size; + strm->avail_in = state->size; + if (gz_comp(state, Z_NO_FLUSH) == -1) + return state->err; + memcpy(state->in, state->in + state->size, left); + strm->next_in = state->in; + strm->avail_in = left; + } + return len; +} + +int ZEXPORTVA gzprintf(gzFile file, const char *format, ...) +{ + va_list va; + int ret; + + va_start(va, format); + ret = gzvprintf(file, format, va); + va_end(va); + return ret; +} + +#else /* !STDC && !Z_HAVE_STDARG_H */ + +/* -- see zlib.h -- */ +int ZEXPORTVA gzprintf (file, format, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, + a11, a12, a13, a14, a15, a16, a17, a18, a19, a20) + gzFile file; + const char *format; + int a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, + a11, a12, a13, a14, a15, a16, a17, a18, a19, a20; +{ + unsigned len, left; + char *next; + gz_statep state; + z_streamp strm; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + strm = &(state->strm); + + /* check that can really pass pointer in ints */ + if (sizeof(int) != sizeof(void *)) + return Z_STREAM_ERROR; + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return Z_STREAM_ERROR; + + /* make sure we have some buffer space */ + if (state->size == 0 && gz_init(state) == -1) + return state->error; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return state->error; + } + + /* do the printf() into the input buffer, put length in len -- the input + buffer is double-sized just for this function, so there is guaranteed to + be state->size bytes available after the current contents */ + if (strm->avail_in == 0) + strm->next_in = state->in; + next = (char *)(strm->next_in + strm->avail_in); + next[state->size - 1] = 0; +#ifdef NO_snprintf +# ifdef HAS_sprintf_void + sprintf(next, format, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, a11, a12, + a13, a14, a15, a16, a17, a18, a19, a20); + for (len = 0; len < size; len++) + if (next[len] == 0) + break; +# else + len = sprintf(next, format, a1, a2, a3, a4, a5, a6, a7, a8, a9, a10, a11, + a12, a13, a14, a15, a16, a17, a18, a19, a20); +# endif +#else +# ifdef HAS_snprintf_void + snprintf(next, state->size, format, a1, a2, a3, a4, a5, a6, a7, a8, a9, + a10, a11, a12, a13, a14, a15, a16, a17, a18, a19, a20); + len = strlen(next); +# else + len = snprintf(next, state->size, format, a1, a2, a3, a4, a5, a6, a7, a8, + a9, a10, a11, a12, a13, a14, a15, a16, a17, a18, a19, a20); +# endif +#endif + + /* check that printf() results fit in buffer */ + if (len == 0 || len >= state->size || next[state->size - 1] != 0) + return 0; + + /* update buffer and position, compress first half if past that */ + strm->avail_in += len; + state->x.pos += len; + if (strm->avail_in >= state->size) { + left = strm->avail_in - state->size; + strm->avail_in = state->size; + if (gz_comp(state, Z_NO_FLUSH) == -1) + return state->err; + memcpy(state->in, state->in + state->size, left); + strm->next_in = state->in; + strm->avail_in = left; + } + return (int)len; +} + +#endif + +/* -- see zlib.h -- */ +int ZEXPORT gzflush(file, flush) + gzFile file; + int flush; +{ + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return Z_STREAM_ERROR; + + /* check flush parameter */ + if (flush < 0 || flush > Z_FINISH) + return Z_STREAM_ERROR; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return state->err; + } + + /* compress remaining data with requested flush */ + (void)gz_comp(state, flush); + return state->err; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzsetparams(file, level, strategy) + gzFile file; + int level; + int strategy; +{ + gz_statep state; + z_streamp strm; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + strm = &(state->strm); + + /* check that we're writing and that there's no error */ + if (state->mode != GZ_WRITE || state->err != Z_OK) + return Z_STREAM_ERROR; + + /* if no change is requested, then do nothing */ + if (level == state->level && strategy == state->strategy) + return Z_OK; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + return state->err; + } + + /* change compression parameters for subsequent input */ + if (state->size) { + /* flush previous input with previous parameters before changing */ + if (strm->avail_in && gz_comp(state, Z_BLOCK) == -1) + return state->err; + deflateParams(strm, level, strategy); + } + state->level = level; + state->strategy = strategy; + return Z_OK; +} + +/* -- see zlib.h -- */ +int ZEXPORT gzclose_w(file) + gzFile file; +{ + int ret = Z_OK; + gz_statep state; + + /* get internal structure */ + if (file == NULL) + return Z_STREAM_ERROR; + state = (gz_statep)file; + + /* check that we're writing */ + if (state->mode != GZ_WRITE) + return Z_STREAM_ERROR; + + /* check for seek request */ + if (state->seek) { + state->seek = 0; + if (gz_zero(state, state->skip) == -1) + ret = state->err; + } + + /* flush, free memory, and close file */ + if (gz_comp(state, Z_FINISH) == -1) + ret = state->err; + if (state->size) { + if (!state->direct) { + (void)deflateEnd(&(state->strm)); + free(state->out); + } + free(state->in); + } + gz_error(state, Z_OK, NULL); + free(state->path); + if (close(state->fd) == -1) + ret = Z_ERRNO; + free(state); + return ret; +} diff --git a/lib/libz/infback.c b/lib/libz/infback.c index e980358..037ecac 100644 --- a/lib/libz/infback.c +++ b/lib/libz/infback.c @@ -1,5 +1,6 @@ +/* $OpenBSD: infback.c,v 1.7 2021/07/04 14:24:49 tb Exp $ */ /* infback.c -- inflate using a call-back interface - * Copyright (C) 1995-2005 Mark Adler + * Copyright (C) 1995-2016 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -42,20 +43,29 @@ int stream_size; return Z_STREAM_ERROR; strm->msg = Z_NULL; /* in case we return an error */ if (strm->zalloc == (alloc_func)0) { +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else strm->zalloc = zcalloc; strm->opaque = (voidpf)0; +#endif } - if (strm->zfree == (free_func)0) strm->zfree = zcfree; + if (strm->zfree == (free_func)0) +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else + strm->zfree = zcfree; +#endif state = (struct inflate_state FAR *)ZALLOC(strm, 1, sizeof(struct inflate_state)); if (state == Z_NULL) return Z_MEM_ERROR; Tracev((stderr, "inflate: allocated\n")); strm->state = (struct internal_state FAR *)state; state->dmax = 32768U; - state->wbits = windowBits; + state->wbits = (uInt)windowBits; state->wsize = 1U << windowBits; state->window = window; - state->write = 0; + state->wnext = 0; state->whave = 0; return Z_OK; } @@ -253,7 +263,7 @@ void FAR *out_desc; unsigned bits; /* bits in bit buffer */ unsigned copy; /* number of stored or match bytes to copy */ unsigned char FAR *from; /* where to copy match bytes from */ - code this; /* current decoding table entry */ + code here; /* current decoding table entry */ code last; /* parent table entry */ unsigned len; /* length to copy for repeats, bits to drop */ int ret; /* return code */ @@ -308,8 +318,8 @@ void FAR *out_desc; state->mode = TABLE; break; case 3: -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid block type"; #endif @@ -323,8 +333,8 @@ void FAR *out_desc; BYTEBITS(); /* go to byte boundary */ NEEDBITS(32); if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid stored block lengths"; #endif @@ -365,8 +375,8 @@ void FAR *out_desc; DROPBITS(4); #ifndef PKZIP_BUG_WORKAROUND if (state->nlen > 286 || state->ndist > 30) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"too many length or distance symbols"; #endif @@ -391,7 +401,11 @@ void FAR *out_desc; ret = inflate_table(CODES, state->lens, 19, &(state->next), &(state->lenbits), state->work); if (ret) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid code lengths set"; +#endif state->mode = BAD; break; } @@ -401,21 +415,24 @@ void FAR *out_desc; state->have = 0; while (state->have < state->nlen + state->ndist) { for (;;) { - this = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->lencode[BITS(state->lenbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if (this.val < 16) { - NEEDBITS(this.bits); - DROPBITS(this.bits); - state->lens[state->have++] = this.val; + if (here.val < 16) { + DROPBITS(here.bits); + state->lens[state->have++] = here.val; } else { - if (this.val == 16) { - NEEDBITS(this.bits + 2); - DROPBITS(this.bits); + if (here.val == 16) { + NEEDBITS(here.bits + 2); + DROPBITS(here.bits); if (state->have == 0) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid bit length repeat"; +#endif state->mode = BAD; break; } @@ -423,22 +440,26 @@ void FAR *out_desc; copy = 3 + BITS(2); DROPBITS(2); } - else if (this.val == 17) { - NEEDBITS(this.bits + 3); - DROPBITS(this.bits); + else if (here.val == 17) { + NEEDBITS(here.bits + 3); + DROPBITS(here.bits); len = 0; copy = 3 + BITS(3); DROPBITS(3); } else { - NEEDBITS(this.bits + 7); - DROPBITS(this.bits); + NEEDBITS(here.bits + 7); + DROPBITS(here.bits); len = 0; copy = 11 + BITS(7); DROPBITS(7); } if (state->have + copy > state->nlen + state->ndist) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid bit length repeat"; +#endif state->mode = BAD; break; } @@ -450,14 +471,31 @@ void FAR *out_desc; /* handle error breaks in while */ if (state->mode == BAD) break; - /* build code tables */ + /* check for end-of-block code (better have one) */ + if (state->lens[256] == 0) { +#ifdef SMALL + strm->msg = "error"; +#else + strm->msg = (char *)"invalid code -- missing end-of-block"; +#endif + state->mode = BAD; + break; + } + + /* build code tables -- note: do not change the lenbits or distbits + values here (9 and 6) without reading the comments in inftrees.h + concerning the ENOUGH constants, which depend on those values */ state->next = state->codes; state->lencode = (code const FAR *)(state->next); state->lenbits = 9; ret = inflate_table(LENS, state->lens, state->nlen, &(state->next), &(state->lenbits), state->work); if (ret) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid literal/lengths set"; +#endif state->mode = BAD; break; } @@ -466,7 +504,11 @@ void FAR *out_desc; ret = inflate_table(DISTS, state->lens + state->nlen, state->ndist, &(state->next), &(state->distbits), state->work); if (ret) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid distances set"; +#endif state->mode = BAD; break; } @@ -488,28 +530,28 @@ void FAR *out_desc; /* get a literal, length, or end-of-block code */ for (;;) { - this = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->lencode[BITS(state->lenbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if (this.op && (this.op & 0xf0) == 0) { - last = this; + if (here.op && (here.op & 0xf0) == 0) { + last = here; for (;;) { - this = state->lencode[last.val + + here = state->lencode[last.val + (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + this.bits) <= bits) break; + if ((unsigned)(last.bits + here.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); } - DROPBITS(this.bits); - state->length = (unsigned)this.val; + DROPBITS(here.bits); + state->length = (unsigned)here.val; /* process literal */ - if (this.op == 0) { - Tracevv((stderr, this.val >= 0x20 && this.val < 0x7f ? + if (here.op == 0) { + Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", this.val)); + "inflate: literal 0x%02x\n", here.val)); ROOM(); *put++ = (unsigned char)(state->length); left--; @@ -518,21 +560,25 @@ void FAR *out_desc; } /* process end of block */ - if (this.op & 32) { + if (here.op & 32) { Tracevv((stderr, "inflate: end of block\n")); state->mode = TYPE; break; } /* invalid code */ - if (this.op & 64) { + if (here.op & 64) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid literal/length code"; +#endif state->mode = BAD; break; } /* length code -- get extra bits, if any */ - state->extra = (unsigned)(this.op) & 15; + state->extra = (unsigned)(here.op) & 15; if (state->extra != 0) { NEEDBITS(state->extra); state->length += BITS(state->extra); @@ -542,30 +588,34 @@ void FAR *out_desc; /* get distance code */ for (;;) { - this = state->distcode[BITS(state->distbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->distcode[BITS(state->distbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if ((this.op & 0xf0) == 0) { - last = this; + if ((here.op & 0xf0) == 0) { + last = here; for (;;) { - this = state->distcode[last.val + + here = state->distcode[last.val + (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + this.bits) <= bits) break; + if ((unsigned)(last.bits + here.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); } - DROPBITS(this.bits); - if (this.op & 64) { + DROPBITS(here.bits); + if (here.op & 64) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid distance code"; +#endif state->mode = BAD; break; } - state->offset = (unsigned)this.val; + state->offset = (unsigned)here.val; /* get distance extra bits, if any */ - state->extra = (unsigned)(this.op) & 15; + state->extra = (unsigned)(here.op) & 15; if (state->extra != 0) { NEEDBITS(state->extra); state->offset += BITS(state->extra); @@ -573,7 +623,11 @@ void FAR *out_desc; } if (state->offset > state->wsize - (state->whave < state->wsize ? left : 0)) { +#ifdef SMALL + strm->msg = "error"; +#else strm->msg = (char *)"invalid distance too far back"; +#endif state->mode = BAD; break; } diff --git a/lib/libz/inffast.c b/lib/libz/inffast.c index 988806c..6a4d4cc 100644 --- a/lib/libz/inffast.c +++ b/lib/libz/inffast.c @@ -1,6 +1,6 @@ -/* $OpenBSD: inffast.c,v 1.8 2019/06/01 11:39:57 jca Exp $ */ +/* $OpenBSD: inffast.c,v 1.9 2021/07/04 14:24:49 tb Exp $ */ /* inffast.c -- fast decoding - * Copyright (C) 1995-2004 Mark Adler + * Copyright (C) 1995-2017 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -9,26 +9,9 @@ #include "inflate.h" #include "inffast.h" -#ifndef ASMINF - -/* Allow machine dependent optimization for post-increment or pre-increment. - Based on testing to date, - Pre-increment preferred for: - - PowerPC G3 (Adler) - - MIPS R5000 (Randers-Pehrson) - Post-increment preferred for: - - none - No measurable difference: - - Pentium III (Anderson) - - M68060 (Nikl) - */ -#ifdef POSTINC -# define OFF 0 -# define PUP(a) *(a)++ +#ifdef ASMINF +# pragma message("Assembler code may have bugs -- use at your own risk") #else -# define OFF 1 -# define PUP(a) *++(a) -#endif /* Decode literal, length, and distance codes and write out the resulting @@ -65,13 +48,13 @@ requires strm->avail_out >= 258 for each loop to avoid checking for output space. */ -void inflate_fast(strm, start) +void ZLIB_INTERNAL inflate_fast(strm, start) z_streamp strm; unsigned start; /* inflate()'s starting value for strm->avail_out */ { struct inflate_state FAR *state; z_const unsigned char FAR *in; /* local strm->next_in */ - z_const unsigned char FAR *last; /* while in < last, enough input available */ + z_const unsigned char FAR *last; /* have enough input while in < last */ 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 */ @@ -80,7 +63,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ #endif unsigned wsize; /* window size or zero if not using window */ unsigned whave; /* valid bytes in the window */ - unsigned write; /* window write index */ + unsigned wnext; /* window write index */ unsigned char FAR *window; /* allocated sliding window, if wsize != 0 */ unsigned long hold; /* local strm->hold */ unsigned bits; /* local strm->bits */ @@ -88,7 +71,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ code const FAR *dcode; /* local strm->distcode */ unsigned lmask; /* mask for first level of length codes */ unsigned dmask; /* mask for first level of distance codes */ - code this; /* retrieved table entry */ + code here; /* retrieved table entry */ unsigned op; /* code bits, operation, extra bits, or */ /* window position, window bytes to copy */ unsigned len; /* match length, unused bytes */ @@ -97,9 +80,9 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ /* copy state to local variables */ state = (struct inflate_state FAR *)strm->state; - in = strm->next_in - OFF; + in = strm->next_in; last = in + (strm->avail_in - 5); - out = strm->next_out - OFF; + out = strm->next_out; beg = out - (start - strm->avail_out); end = out + (strm->avail_out - 257); #ifdef INFLATE_STRICT @@ -107,7 +90,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ #endif wsize = state->wsize; whave = state->whave; - write = state->write; + wnext = state->wnext; window = state->window; hold = state->hold; bits = state->bits; @@ -120,29 +103,29 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ input data or output space */ do { if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } - this = lcode[hold & lmask]; + here = lcode[hold & lmask]; dolen: - op = (unsigned)(this.bits); + op = (unsigned)(here.bits); hold >>= op; bits -= op; - op = (unsigned)(this.op); + op = (unsigned)(here.op); if (op == 0) { /* literal */ - Tracevv((stderr, this.val >= 0x20 && this.val < 0x7f ? + Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", this.val)); - PUP(out) = (unsigned char)(this.val); + "inflate: literal 0x%02x\n", here.val)); + *out++ = (unsigned char)(here.val); } else if (op & 16) { /* length base */ - len = (unsigned)(this.val); + len = (unsigned)(here.val); op &= 15; /* number of extra bits */ if (op) { if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } len += (unsigned)hold & ((1U << op) - 1); @@ -151,25 +134,25 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ } Tracevv((stderr, "inflate: length %u\n", len)); if (bits < 15) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } - this = dcode[hold & dmask]; + here = dcode[hold & dmask]; dodist: - op = (unsigned)(this.bits); + op = (unsigned)(here.bits); hold >>= op; bits -= op; - op = (unsigned)(this.op); + op = (unsigned)(here.op); if (op & 16) { /* distance base */ - dist = (unsigned)(this.val); + dist = (unsigned)(here.val); op &= 15; /* number of extra bits */ if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; if (bits < op) { - hold += (unsigned long)(PUP(in)) << bits; + hold += (unsigned long)(*in++) << bits; bits += 8; } } @@ -188,88 +171,110 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ if (dist > op) { /* see if copy from window */ op = dist - op; /* distance back in window */ if (op > whave) { -#ifdef SMALL - strm->msg = "error"; + if (state->sane) { +#ifdef SMALL + strm->msg = "error"; #else - strm->msg = (char *)"invalid distance too far back"; + strm->msg = + (char *)"invalid distance too far back"; +#endif + state->mode = BAD; + break; + } +#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR + if (len <= op - whave) { + do { + *out++ = 0; + } while (--len); + continue; + } + len -= op - whave; + do { + *out++ = 0; + } while (--op > whave); + if (op == 0) { + from = out - dist; + do { + *out++ = *from++; + } while (--len); + continue; + } #endif - state->mode = BAD; - break; } - from = window - OFF; - if (write == 0) { /* very common case */ + from = window; + if (wnext == 0) { /* very common case */ from += wsize - op; if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } - else if (write < op) { /* wrap around window */ - from += wsize + write - op; - op -= write; + else if (wnext < op) { /* wrap around window */ + from += wsize + wnext - op; + op -= wnext; if (op < len) { /* some from end of window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); - from = window - OFF; - if (write < len) { /* some from start of window */ - op = write; + from = window; + if (wnext < len) { /* some from start of window */ + op = wnext; len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } } else { /* contiguous in window */ - from += write - op; + from += wnext - op; if (op < len) { /* some from window */ len -= op; do { - PUP(out) = PUP(from); + *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } while (len > 2) { - PUP(out) = PUP(from); - PUP(out) = PUP(from); - PUP(out) = PUP(from); + *out++ = *from++; + *out++ = *from++; + *out++ = *from++; len -= 3; } if (len) { - PUP(out) = PUP(from); + *out++ = *from++; if (len > 1) - PUP(out) = PUP(from); + *out++ = *from++; } } else { from = out - dist; /* copy direct from output */ do { /* minimum length is three */ - PUP(out) = PUP(from); - PUP(out) = PUP(from); - PUP(out) = PUP(from); + *out++ = *from++; + *out++ = *from++; + *out++ = *from++; len -= 3; } while (len > 2); if (len) { - PUP(out) = PUP(from); + *out++ = *from++; if (len > 1) - PUP(out) = PUP(from); + *out++ = *from++; } } } else if ((op & 64) == 0) { /* 2nd level distance code */ - this = dcode[this.val + (hold & ((1U << op) - 1))]; + here = dcode[here.val + (hold & ((1U << op) - 1))]; goto dodist; } else { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid distance code"; #endif @@ -278,7 +283,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ } } else if ((op & 64) == 0) { /* 2nd level length code */ - this = lcode[this.val + (hold & ((1U << op) - 1))]; + here = lcode[here.val + (hold & ((1U << op) - 1))]; goto dolen; } else if (op & 32) { /* end-of-block */ @@ -287,8 +292,8 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ break; } else { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid literal/length code"; #endif @@ -304,8 +309,8 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ hold &= (1U << bits) - 1; /* update state and return */ - strm->next_in = in + OFF; - strm->next_out = out + OFF; + strm->next_in = in; + strm->next_out = out; strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); strm->avail_out = (unsigned)(out < end ? 257 + (end - out) : 257 - (out - end)); @@ -318,7 +323,7 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */ inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe): - Using bit fields for code structure - Different op definition to avoid & for extra bits (do & for table bits) - - Three separate decoding do-loops for direct, window, and write == 0 + - Three separate decoding do-loops for direct, window, and wnext == 0 - Special case for distance > 1 copies to do overlapped load and store copy - Explicit branch predictions (based on measured branch probabilities) - Deferring match copy and interspersed it with decoding subsequent codes diff --git a/lib/libz/inffast.h b/lib/libz/inffast.h index 0283eea..cb80787 100644 --- a/lib/libz/inffast.h +++ b/lib/libz/inffast.h @@ -1,6 +1,7 @@ -/* $OpenBSD: inffast.h,v 1.4 2003/12/16 22:33:02 henning Exp $ */ +/* $OpenBSD: inffast.h,v 1.6 2021/07/04 17:41:23 tb Exp $ */ + /* inffast.h -- header to use inffast.c - * Copyright (C) 1995-2003 Mark Adler + * Copyright (C) 1995-2003, 2010 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -9,4 +10,4 @@ subject to change. Applications should only use zlib.h. */ -void inflate_fast OF((z_streamp strm, unsigned start)); +void ZLIB_INTERNAL inflate_fast OF((z_streamp strm, unsigned start)); diff --git a/lib/libz/inffixed.h b/lib/libz/inffixed.h index be9fb24..9784be0 100644 --- a/lib/libz/inffixed.h +++ b/lib/libz/inffixed.h @@ -1,11 +1,12 @@ -/* $OpenBSD: inffixed.h,v 1.3 2003/12/16 22:33:02 henning Exp $ */ +/* $OpenBSD: inffixed.h,v 1.5 2021/07/04 17:41:23 tb Exp $ */ + /* inffixed.h -- table for decoding fixed codes * Generated automatically by makefixed(). */ - /* WARNING: this file should *not* be used by applications. It - is part of the implementation of the compression library and - is subject to change. Applications should only use zlib.h. + /* WARNING: this file should *not* be used by applications. + It is part of the implementation of this library and is + subject to change. Applications should only use zlib.h. */ static const code lenfix[512] = { diff --git a/lib/libz/inflate.c b/lib/libz/inflate.c index 37930a9..af68b49 100644 --- a/lib/libz/inflate.c +++ b/lib/libz/inflate.c @@ -1,6 +1,6 @@ -/* $OpenBSD: inflate.c,v 1.10 2019/06/01 11:39:57 jca Exp $ */ +/* $OpenBSD: inflate.c,v 1.11 2021/07/04 14:24:49 tb Exp $ */ /* inflate.c -- zlib decompression - * Copyright (C) 1995-2005 Mark Adler + * Copyright (C) 1995-2016 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -46,7 +46,7 @@ * - Rearrange window copies in inflate_fast() for speed and simplification * - Unroll last copy for window match in inflate_fast() * - Use local copies of window variables in inflate_fast() for speed - * - Pull out common write == 0 case for speed in inflate_fast() + * - Pull out common wnext == 0 case for speed in inflate_fast() * - Make op and len in inflate_fast() unsigned for consistency * - Add FAR to lcode and dcode declarations in inflate_fast() * - Simplified bad distance check in inflate_fast() @@ -93,53 +93,104 @@ #endif /* function prototypes */ +local int inflateStateCheck OF((z_streamp strm)); local void fixedtables OF((struct inflate_state FAR *state)); -local int updatewindow OF((z_streamp strm, unsigned out)); +local int updatewindow OF((z_streamp strm, const unsigned char FAR *end, + unsigned copy)); #ifdef BUILDFIXED void makefixed OF((void)); #endif -local unsigned syncsearch OF((unsigned FAR *have, z_const unsigned char FAR *buf, +local unsigned syncsearch OF((unsigned FAR *have, const unsigned char FAR *buf, unsigned len)); -int ZEXPORT inflateReset(strm) +local int inflateStateCheck(strm) z_streamp strm; { struct inflate_state FAR *state; + if (strm == Z_NULL || + strm->zalloc == (alloc_func)0 || strm->zfree == (free_func)0) + return 1; + state = (struct inflate_state FAR *)strm->state; + if (state == Z_NULL || state->strm != strm || + state->mode < HEAD || state->mode > SYNC) + return 1; + return 0; +} - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; +int ZEXPORT inflateResetKeep(strm) +z_streamp strm; +{ + struct inflate_state FAR *state; + + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; strm->total_in = strm->total_out = state->total = 0; strm->msg = Z_NULL; - strm->adler = 1; /* to support ill-conceived Java test suite */ + if (state->wrap) /* to support ill-conceived Java test suite */ + strm->adler = state->wrap & 1; state->mode = HEAD; state->last = 0; state->havedict = 0; state->dmax = 32768U; state->head = Z_NULL; - state->wsize = 0; - state->whave = 0; - state->write = 0; state->hold = 0; state->bits = 0; state->lencode = state->distcode = state->next = state->codes; + state->sane = 1; + state->back = -1; Tracev((stderr, "inflate: reset\n")); return Z_OK; } -int ZEXPORT inflatePrime(strm, bits, value) +int ZEXPORT inflateReset(strm) z_streamp strm; -int bits; -int value; { struct inflate_state FAR *state; - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; - if (bits > 16 || state->bits + bits > 32) return Z_STREAM_ERROR; - value &= (1L << bits) - 1; - state->hold += value << state->bits; - state->bits += bits; - return Z_OK; + state->wsize = 0; + state->whave = 0; + state->wnext = 0; + return inflateResetKeep(strm); +} + +int ZEXPORT inflateReset2(strm, windowBits) +z_streamp strm; +int windowBits; +{ + int wrap; + struct inflate_state FAR *state; + + /* get the state */ + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; + state = (struct inflate_state FAR *)strm->state; + + /* extract wrap request from windowBits parameter */ + if (windowBits < 0) { + wrap = 0; + windowBits = -windowBits; + } + else { + wrap = (windowBits >> 4) + 5; +#ifdef GUNZIP + if (windowBits < 48) + windowBits &= 15; +#endif + } + + /* set number of window bits, free window if different */ + if (windowBits && (windowBits < 8 || windowBits > 15)) + return Z_STREAM_ERROR; + if (state->window != Z_NULL && state->wbits != (unsigned)windowBits) { + ZFREE(strm, state->window); + state->window = Z_NULL; + } + + /* update state and reset the rest of it */ + state->wrap = wrap; + state->wbits = (unsigned)windowBits; + return inflateReset(strm); } int ZEXPORT inflateInit2_(strm, windowBits, version, stream_size) @@ -148,6 +199,7 @@ int windowBits; const char *version; int stream_size; { + int ret; struct inflate_state FAR *state; if (version == Z_NULL || version[0] != ZLIB_VERSION[0] || @@ -156,33 +208,33 @@ int stream_size; if (strm == Z_NULL) return Z_STREAM_ERROR; strm->msg = Z_NULL; /* in case we return an error */ if (strm->zalloc == (alloc_func)0) { +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else strm->zalloc = zcalloc; strm->opaque = (voidpf)0; +#endif } - if (strm->zfree == (free_func)0) strm->zfree = zcfree; + if (strm->zfree == (free_func)0) +#ifdef Z_SOLO + return Z_STREAM_ERROR; +#else + strm->zfree = zcfree; +#endif state = (struct inflate_state FAR *) ZALLOC(strm, 1, sizeof(struct inflate_state)); if (state == Z_NULL) return Z_MEM_ERROR; Tracev((stderr, "inflate: allocated\n")); strm->state = (struct internal_state FAR *)state; - if (windowBits < 0) { - state->wrap = 0; - windowBits = -windowBits; - } - else { - state->wrap = (windowBits >> 4) + 1; -#ifdef GUNZIP - if (windowBits < 48) windowBits &= 15; -#endif - } - if (windowBits < 8 || windowBits > 15) { + state->strm = strm; + state->window = Z_NULL; + state->mode = HEAD; /* to pass state test in inflateReset2() */ + ret = inflateReset2(strm, windowBits); + if (ret != Z_OK) { ZFREE(strm, state); strm->state = Z_NULL; - return Z_STREAM_ERROR; } - state->wbits = (unsigned)windowBits; - state->window = Z_NULL; - return inflateReset(strm); + return ret; } int ZEXPORT inflateInit_(strm, version, stream_size) @@ -193,6 +245,27 @@ int stream_size; return inflateInit2_(strm, DEF_WBITS, version, stream_size); } +int ZEXPORT inflatePrime(strm, bits, value) +z_streamp strm; +int bits; +int value; +{ + struct inflate_state FAR *state; + + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; + state = (struct inflate_state FAR *)strm->state; + if (bits < 0) { + state->hold = 0; + state->bits = 0; + return Z_OK; + } + if (bits > 16 || state->bits + (uInt)bits > 32) return Z_STREAM_ERROR; + value &= (1L << bits) - 1; + state->hold += (unsigned)value << state->bits; + state->bits += (uInt)bits; + return Z_OK; +} + /* Return state with length and distance decoding tables and index sizes set to fixed code decoding. Normally this returns fixed tables from inffixed.h. @@ -287,8 +360,8 @@ void makefixed() low = 0; for (;;) { if ((low % 7) == 0) printf("\n "); - printf("{%u,%u,%d}", state.lencode[low].op, state.lencode[low].bits, - state.lencode[low].val); + printf("{%u,%u,%d}", (low & 127) == 99 ? 64 : state.lencode[low].op, + state.lencode[low].bits, state.lencode[low].val); if (++low == size) break; putchar(','); } @@ -321,12 +394,13 @@ void makefixed() output will fall in the output data, making match copies simpler and faster. The advantage may be dependent on the size of the processor's data caches. */ -local int updatewindow(strm, out) +local int updatewindow(strm, end, copy) z_streamp strm; -unsigned out; +const Bytef *end; +unsigned copy; { struct inflate_state FAR *state; - unsigned copy, dist; + unsigned dist; state = (struct inflate_state FAR *)strm->state; @@ -341,30 +415,29 @@ unsigned out; /* if window not in use yet, initialize */ if (state->wsize == 0) { state->wsize = 1U << state->wbits; - state->write = 0; + state->wnext = 0; state->whave = 0; } /* copy state->wsize or less output bytes into the circular window */ - copy = out - strm->avail_out; if (copy >= state->wsize) { - zmemcpy(state->window, strm->next_out - state->wsize, state->wsize); - state->write = 0; + zmemcpy(state->window, end - state->wsize, state->wsize); + state->wnext = 0; state->whave = state->wsize; } else { - dist = state->wsize - state->write; + dist = state->wsize - state->wnext; if (dist > copy) dist = copy; - zmemcpy(state->window + state->write, strm->next_out - copy, dist); + zmemcpy(state->window + state->wnext, end - copy, dist); copy -= dist; if (copy) { - zmemcpy(state->window, strm->next_out - copy, copy); - state->write = copy; + zmemcpy(state->window, end - copy, copy); + state->wnext = copy; state->whave = state->wsize; } else { - state->write += dist; - if (state->write == state->wsize) state->write = 0; + state->wnext += dist; + if (state->wnext == state->wsize) state->wnext = 0; if (state->whave < state->wsize) state->whave += dist; } } @@ -465,11 +538,6 @@ unsigned out; bits -= bits & 7; \ } while (0) -/* Reverse the bytes in a 32-bit value */ -#define REVERSE(q) \ - ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \ - (((q) & 0xff00) << 8) + (((q) & 0xff) << 24)) - /* inflate() uses a state machine to process as much input data and generate as much output data as possible before returning. The state machine is @@ -565,7 +633,7 @@ int flush; unsigned in, out; /* save starting available input and output */ unsigned copy; /* number of stored or match bytes to copy */ unsigned char FAR *from; /* where to copy match bytes from */ - code this; /* current decoding table entry */ + code here; /* current decoding table entry */ code last; /* parent table entry */ unsigned len; /* length to copy for repeats, bits to drop */ int ret; /* return code */ @@ -575,7 +643,7 @@ int flush; static const unsigned short order[19] = /* permutation of code lengths */ {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; - if (strm == Z_NULL || strm->state == Z_NULL || strm->next_out == Z_NULL || + if (inflateStateCheck(strm) || strm->next_out == Z_NULL || (strm->next_in == Z_NULL && strm->avail_in != 0)) return Z_STREAM_ERROR; @@ -595,6 +663,8 @@ int flush; NEEDBITS(16); #ifdef GUNZIP if ((state->wrap & 2) && hold == 0x8b1f) { /* gzip header */ + if (state->wbits == 0) + state->wbits = 15; state->check = crc32(0L, Z_NULL, 0); CRC2(state->check, hold); INITBITS(); @@ -609,8 +679,8 @@ int flush; if ( #endif ((BITS(8) << 8) + (hold >> 8)) % 31) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"incorrect header check"; #endif @@ -618,8 +688,8 @@ int flush; break; } if (BITS(4) != Z_DEFLATED) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"unknown compression method"; #endif @@ -627,17 +697,19 @@ int flush; break; } DROPBITS(4); - len = BITS(4) + 8; - if (len > state->wbits) { -#ifdef SMALL - strm->msg = "error"; + len = BITS(4) + 8; + if (state->wbits == 0) + state->wbits = len; + if (len > 15 || len > state->wbits) { +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid window size"; #endif state->mode = BAD; break; } - state->dmax = 1U << len; + 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; @@ -648,8 +720,8 @@ int flush; NEEDBITS(16); state->flags = (int)(hold); if ((state->flags & 0xff) != Z_DEFLATED) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"unknown compression method"; #endif @@ -657,8 +729,8 @@ int flush; break; } if (state->flags & 0xe000) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"unknown header flags set"; #endif @@ -667,14 +739,16 @@ int flush; } if (state->head != Z_NULL) state->head->text = (int)((hold >> 8) & 1); - if (state->flags & 0x0200) CRC2(state->check, hold); + if ((state->flags & 0x0200) && (state->wrap & 4)) + CRC2(state->check, hold); INITBITS(); state->mode = TIME; case TIME: NEEDBITS(32); if (state->head != Z_NULL) state->head->time = hold; - if (state->flags & 0x0200) CRC4(state->check, hold); + if ((state->flags & 0x0200) && (state->wrap & 4)) + CRC4(state->check, hold); INITBITS(); state->mode = OS; case OS: @@ -683,7 +757,8 @@ int flush; state->head->xflags = (int)(hold & 0xff); state->head->os = (int)(hold >> 8); } - if (state->flags & 0x0200) CRC2(state->check, hold); + if ((state->flags & 0x0200) && (state->wrap & 4)) + CRC2(state->check, hold); INITBITS(); state->mode = EXLEN; case EXLEN: @@ -692,7 +767,8 @@ int flush; state->length = (unsigned)(hold); if (state->head != Z_NULL) state->head->extra_len = (unsigned)hold; - if (state->flags & 0x0200) CRC2(state->check, hold); + if ((state->flags & 0x0200) && (state->wrap & 4)) + CRC2(state->check, hold); INITBITS(); } else if (state->head != Z_NULL) @@ -710,7 +786,7 @@ int flush; len + copy > state->head->extra_max ? state->head->extra_max - len : copy); } - if (state->flags & 0x0200) + if ((state->flags & 0x0200) && (state->wrap & 4)) state->check = crc32(state->check, next, copy); have -= copy; next += copy; @@ -729,9 +805,9 @@ int flush; if (state->head != Z_NULL && state->head->name != Z_NULL && state->length < state->head->name_max) - state->head->name[state->length++] = len; + state->head->name[state->length++] = (Bytef)len; } while (len && copy < have); - if (state->flags & 0x0200) + if ((state->flags & 0x0200) && (state->wrap & 4)) state->check = crc32(state->check, next, copy); have -= copy; next += copy; @@ -750,9 +826,9 @@ int flush; if (state->head != Z_NULL && state->head->comment != Z_NULL && state->length < state->head->comm_max) - state->head->comment[state->length++] = len; + state->head->comment[state->length++] = (Bytef)len; } while (len && copy < have); - if (state->flags & 0x0200) + if ((state->flags & 0x0200) && (state->wrap & 4)) state->check = crc32(state->check, next, copy); have -= copy; next += copy; @@ -764,9 +840,9 @@ int flush; case HCRC: if (state->flags & 0x0200) { NEEDBITS(16); - if (hold != (state->check & 0xffff)) { -#ifdef SMALL - strm->msg = "error"; + if ((state->wrap & 4) && hold != (state->check & 0xffff)) { +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"header crc mismatch"; #endif @@ -785,7 +861,7 @@ int flush; #endif case DICTID: NEEDBITS(32); - strm->adler = state->check = REVERSE(hold); + strm->adler = state->check = ZSWAP32(hold); INITBITS(); state->mode = DICT; case DICT: @@ -796,7 +872,7 @@ int flush; strm->adler = state->check = adler32(0L, Z_NULL, 0); state->mode = TYPE; case TYPE: - if (flush == Z_BLOCK) goto inf_leave; + if (flush == Z_BLOCK || flush == Z_TREES) goto inf_leave; case TYPEDO: if (state->last) { BYTEBITS(); @@ -816,7 +892,11 @@ int flush; fixedtables(state); Tracev((stderr, "inflate: fixed codes block%s\n", state->last ? " (last)" : "")); - state->mode = LEN; /* decode codes */ + state->mode = LEN_; /* decode codes */ + if (flush == Z_TREES) { + DROPBITS(2); + goto inf_leave; + } break; case 2: /* dynamic block */ Tracev((stderr, "inflate: dynamic codes block%s\n", @@ -824,8 +904,8 @@ int flush; state->mode = TABLE; break; case 3: -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid block type"; #endif @@ -837,8 +917,8 @@ int flush; BYTEBITS(); /* go to byte boundary */ NEEDBITS(32); if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid stored block lengths"; #endif @@ -849,6 +929,9 @@ int flush; Tracev((stderr, "inflate: stored length %u\n", state->length)); INITBITS(); + state->mode = COPY_; + if (flush == Z_TREES) goto inf_leave; + case COPY_: state->mode = COPY; case COPY: copy = state->length; @@ -877,8 +960,8 @@ int flush; DROPBITS(4); #ifndef PKZIP_BUG_WORKAROUND if (state->nlen > 286 || state->ndist > 30) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"too many length or distance symbols"; #endif @@ -898,13 +981,13 @@ int flush; while (state->have < 19) state->lens[order[state->have++]] = 0; state->next = state->codes; - state->lencode = (code const FAR *)(state->next); + state->lencode = (const code FAR *)(state->next); state->lenbits = 7; ret = inflate_table(CODES, state->lens, 19, &(state->next), &(state->lenbits), state->work); if (ret) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid code lengths set"; #endif @@ -917,22 +1000,21 @@ int flush; case CODELENS: while (state->have < state->nlen + state->ndist) { for (;;) { - this = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->lencode[BITS(state->lenbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if (this.val < 16) { - NEEDBITS(this.bits); - DROPBITS(this.bits); - state->lens[state->have++] = this.val; + if (here.val < 16) { + DROPBITS(here.bits); + state->lens[state->have++] = here.val; } else { - if (this.val == 16) { - NEEDBITS(this.bits + 2); - DROPBITS(this.bits); + if (here.val == 16) { + NEEDBITS(here.bits + 2); + DROPBITS(here.bits); if (state->have == 0) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid bit length repeat"; #endif @@ -943,23 +1025,23 @@ int flush; copy = 3 + BITS(2); DROPBITS(2); } - else if (this.val == 17) { - NEEDBITS(this.bits + 3); - DROPBITS(this.bits); + else if (here.val == 17) { + NEEDBITS(here.bits + 3); + DROPBITS(here.bits); len = 0; copy = 3 + BITS(3); DROPBITS(3); } else { - NEEDBITS(this.bits + 7); - DROPBITS(this.bits); + NEEDBITS(here.bits + 7); + DROPBITS(here.bits); len = 0; copy = 11 + BITS(7); DROPBITS(7); } if (state->have + copy > state->nlen + state->ndist) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid bit length repeat"; #endif @@ -974,28 +1056,41 @@ int flush; /* handle error breaks in while */ if (state->mode == BAD) break; - /* build code tables */ + /* check for end-of-block code (better have one) */ + if (state->lens[256] == 0) { +#ifdef SMALL + strm->msg = "error"; +#else + strm->msg = (char *)"invalid code -- missing end-of-block"; +#endif + state->mode = BAD; + break; + } + + /* build code tables -- note: do not change the lenbits or distbits + values here (9 and 6) without reading the comments in inftrees.h + concerning the ENOUGH constants, which depend on those values */ state->next = state->codes; - state->lencode = (code const FAR *)(state->next); + state->lencode = (const code FAR *)(state->next); state->lenbits = 9; ret = inflate_table(LENS, state->lens, state->nlen, &(state->next), &(state->lenbits), state->work); if (ret) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid literal/lengths set"; #endif state->mode = BAD; break; } - state->distcode = (code const FAR *)(state->next); + state->distcode = (const code FAR *)(state->next); state->distbits = 6; ret = inflate_table(DISTS, state->lens + state->nlen, state->ndist, &(state->next), &(state->distbits), state->work); if (ret) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid distances set"; #endif @@ -1003,6 +1098,9 @@ int flush; break; } Tracev((stderr, "inflate: codes ok\n")); + state->mode = LEN_; + if (flush == Z_TREES) goto inf_leave; + case LEN_: state->mode = LEN; case LEN: #ifndef SLOW @@ -1010,108 +1108,114 @@ int flush; RESTORE(); inflate_fast(strm, out); LOAD(); + if (state->mode == TYPE) + state->back = -1; break; } #endif + state->back = 0; for (;;) { - this = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->lencode[BITS(state->lenbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if (this.op && (this.op & 0xf0) == 0) { - last = this; + if (here.op && (here.op & 0xf0) == 0) { + last = here; for (;;) { - this = state->lencode[last.val + + here = state->lencode[last.val + (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + this.bits) <= bits) break; + if ((unsigned)(last.bits + here.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); + state->back += last.bits; } - DROPBITS(this.bits); - state->length = (unsigned)this.val; - if ((int)(this.op) == 0) { - Tracevv((stderr, this.val >= 0x20 && this.val < 0x7f ? + DROPBITS(here.bits); + state->back += here.bits; + state->length = (unsigned)here.val; + if ((int)(here.op) == 0) { + Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", this.val)); + "inflate: literal 0x%02x\n", here.val)); state->mode = LIT; break; } - if (this.op & 32) { + if (here.op & 32) { Tracevv((stderr, "inflate: end of block\n")); + state->back = -1; state->mode = TYPE; break; } - if (this.op & 64) { -#ifdef SMALL - strm->msg = "error"; + if (here.op & 64) { +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid literal/length code"; #endif state->mode = BAD; break; } - state->extra = (unsigned)(this.op) & 15; + state->extra = (unsigned)(here.op) & 15; state->mode = LENEXT; case LENEXT: if (state->extra) { NEEDBITS(state->extra); state->length += BITS(state->extra); DROPBITS(state->extra); + state->back += state->extra; } Tracevv((stderr, "inflate: length %u\n", state->length)); + state->was = state->length; state->mode = DIST; case DIST: for (;;) { - this = state->distcode[BITS(state->distbits)]; - if ((unsigned)(this.bits) <= bits) break; + here = state->distcode[BITS(state->distbits)]; + if ((unsigned)(here.bits) <= bits) break; PULLBYTE(); } - if ((this.op & 0xf0) == 0) { - last = this; + if ((here.op & 0xf0) == 0) { + last = here; for (;;) { - this = state->distcode[last.val + + here = state->distcode[last.val + (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + this.bits) <= bits) break; + if ((unsigned)(last.bits + here.bits) <= bits) break; PULLBYTE(); } DROPBITS(last.bits); + state->back += last.bits; } - DROPBITS(this.bits); - if (this.op & 64) { -#ifdef SMALL - strm->msg = "error"; + DROPBITS(here.bits); + state->back += here.bits; + if (here.op & 64) { +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid distance code"; #endif state->mode = BAD; break; } - state->offset = (unsigned)this.val; - state->extra = (unsigned)(this.op) & 15; + state->offset = (unsigned)here.val; + state->extra = (unsigned)(here.op) & 15; state->mode = DISTEXT; case DISTEXT: if (state->extra) { NEEDBITS(state->extra); state->offset += BITS(state->extra); DROPBITS(state->extra); + state->back += 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) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"invalid distance too far back"; #endif state->mode = BAD; break; } +#endif Tracevv((stderr, "inflate: distance %u\n", state->offset)); state->mode = MATCH; case MATCH: @@ -1119,12 +1223,36 @@ int flush; copy = out - left; if (state->offset > copy) { /* copy from window */ copy = state->offset - copy; - if (copy > state->write) { - copy -= state->write; + if (copy > state->whave) { + if (state->sane) { +#ifdef SMALL + strm->msg = "error"; +#else + strm->msg = (char *)"invalid distance too far back"; +#endif + state->mode = BAD; + break; + } +#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR + Trace((stderr, "inflate.c too far\n")); + copy -= state->whave; + if (copy > state->length) copy = state->length; + if (copy > left) copy = left; + left -= copy; + state->length -= copy; + do { + *put++ = 0; + } while (--copy); + if (state->length == 0) state->mode = LEN; + break; +#endif + } + if (copy > state->wnext) { + copy -= state->wnext; from = state->window + (state->wsize - copy); } else - from = state->window + (state->write - copy); + from = state->window + (state->wnext - copy); if (copy > state->length) copy = state->length; } else { /* copy from output */ @@ -1151,17 +1279,17 @@ int flush; out -= left; strm->total_out += out; state->total += out; - if (out) + if ((state->wrap & 4) && out) strm->adler = state->check = UPDATE(state->check, put - out, out); out = left; - if (( + if ((state->wrap & 4) && ( #ifdef GUNZIP state->flags ? hold : #endif - REVERSE(hold)) != state->check) { -#ifdef SMALL - strm->msg = "error"; + ZSWAP32(hold)) != state->check) { +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"incorrect data check"; #endif @@ -1177,8 +1305,8 @@ int flush; if (state->wrap && state->flags) { NEEDBITS(32); if (hold != (state->total & 0xffffffffUL)) { -#ifdef SMALL - strm->msg = "error"; +#ifdef SMALL + strm->msg = "error"; #else strm->msg = (char *)"incorrect length check"; #endif @@ -1211,8 +1339,9 @@ int flush; */ inf_leave: RESTORE(); - if (state->wsize || (state->mode < CHECK && out != strm->avail_out)) - if (updatewindow(strm, out)) { + if (state->wsize || (out != strm->avail_out && state->mode < BAD && + (state->mode < CHECK || flush != Z_FINISH))) + if (updatewindow(strm, strm->next_out, out - strm->avail_out)) { state->mode = MEM; return Z_MEM_ERROR; } @@ -1221,11 +1350,12 @@ int flush; strm->total_in += in; strm->total_out += out; state->total += out; - if (state->wrap && out) + if ((state->wrap & 4) && out) strm->adler = state->check = UPDATE(state->check, strm->next_out - out, out); - strm->data_type = state->bits + (state->last ? 64 : 0) + - (state->mode == TYPE ? 128 : 0); + strm->data_type = (int)state->bits + (state->last ? 64 : 0) + + (state->mode == TYPE ? 128 : 0) + + (state->mode == LEN_ || state->mode == COPY_ ? 256 : 0); if (((in == 0 && out == 0) || flush == Z_FINISH) && ret == Z_OK) ret = Z_BUF_ERROR; return ret; @@ -1235,7 +1365,7 @@ int ZEXPORT inflateEnd(strm) z_streamp strm; { struct inflate_state FAR *state; - if (strm == Z_NULL || strm->state == Z_NULL || strm->zfree == (free_func)0) + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; if (state->window != Z_NULL) ZFREE(strm, state->window); @@ -1245,43 +1375,59 @@ z_streamp strm; return Z_OK; } +int ZEXPORT inflateGetDictionary(strm, dictionary, dictLength) +z_streamp strm; +Bytef *dictionary; +uInt *dictLength; +{ + struct inflate_state FAR *state; + + /* check state */ + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; + state = (struct inflate_state FAR *)strm->state; + + /* copy dictionary */ + if (state->whave && dictionary != Z_NULL) { + zmemcpy(dictionary, state->window + state->wnext, + state->whave - state->wnext); + zmemcpy(dictionary + state->whave - state->wnext, + state->window, state->wnext); + } + if (dictLength != Z_NULL) + *dictLength = state->whave; + return Z_OK; +} + int ZEXPORT inflateSetDictionary(strm, dictionary, dictLength) z_streamp strm; const Bytef *dictionary; uInt dictLength; { struct inflate_state FAR *state; - unsigned long id; + unsigned long dictid; + int ret; /* check state */ - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; if (state->wrap != 0 && state->mode != DICT) return Z_STREAM_ERROR; - /* check for correct dictionary id */ + /* check for correct dictionary identifier */ if (state->mode == DICT) { - id = adler32(0L, Z_NULL, 0); - id = adler32(id, dictionary, dictLength); - if (id != state->check) + dictid = adler32(0L, Z_NULL, 0); + dictid = adler32(dictid, dictionary, dictLength); + if (dictid != state->check) return Z_DATA_ERROR; } - /* copy dictionary to window */ - if (updatewindow(strm, strm->avail_out)) { + /* copy dictionary to window using updatewindow(), which will amend the + existing dictionary if appropriate */ + ret = updatewindow(strm, dictionary + dictLength, dictLength); + if (ret) { state->mode = MEM; return Z_MEM_ERROR; } - if (dictLength > state->wsize) { - zmemcpy(state->window, dictionary + dictLength - state->wsize, - state->wsize); - state->whave = state->wsize; - } - else { - zmemcpy(state->window + state->wsize - dictLength, dictionary, - dictLength); - state->whave = dictLength; - } state->havedict = 1; Tracev((stderr, "inflate: dictionary set\n")); return Z_OK; @@ -1294,7 +1440,7 @@ gz_headerp head; struct inflate_state FAR *state; /* check state */ - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; if ((state->wrap & 2) == 0) return Z_STREAM_ERROR; @@ -1317,7 +1463,7 @@ gz_headerp head; */ local unsigned syncsearch(have, buf, len) unsigned FAR *have; -z_const unsigned char FAR *buf; +const unsigned char FAR *buf; unsigned len; { unsigned got; @@ -1347,7 +1493,7 @@ z_streamp strm; struct inflate_state FAR *state; /* check parameters */ - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; if (strm->avail_in == 0 && state->bits < 8) return Z_BUF_ERROR; @@ -1394,7 +1540,7 @@ z_streamp strm; { struct inflate_state FAR *state; - if (strm == Z_NULL || strm->state == Z_NULL) return Z_STREAM_ERROR; + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)strm->state; return state->mode == STORED && state->bits == 0; } @@ -1409,8 +1555,7 @@ z_streamp source; unsigned wsize; /* check input */ - if (dest == Z_NULL || source == Z_NULL || source->state == Z_NULL || - source->zalloc == (alloc_func)0 || source->zfree == (free_func)0) + if (inflateStateCheck(source) || dest == Z_NULL) return Z_STREAM_ERROR; state = (struct inflate_state FAR *)source->state; @@ -1429,8 +1574,9 @@ z_streamp source; } /* copy state */ - zmemcpy(dest, source, sizeof(z_stream)); - zmemcpy(copy, state, sizeof(struct inflate_state)); + zmemcpy((voidpf)dest, (voidpf)source, sizeof(z_stream)); + zmemcpy((voidpf)copy, (voidpf)state, sizeof(struct inflate_state)); + copy->strm = dest; if (state->lencode >= state->codes && state->lencode <= state->codes + ENOUGH - 1) { copy->lencode = copy->codes + (state->lencode - state->codes); @@ -1445,3 +1591,58 @@ z_streamp source; dest->state = (struct internal_state FAR *)copy; return Z_OK; } + +int ZEXPORT inflateUndermine(strm, subvert) +z_streamp strm; +int subvert; +{ + struct inflate_state FAR *state; + + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; + state = (struct inflate_state FAR *)strm->state; +#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR + state->sane = !subvert; + return Z_OK; +#else + (void)subvert; + state->sane = 1; + return Z_DATA_ERROR; +#endif +} + +int ZEXPORT inflateValidate(strm, check) +z_streamp strm; +int check; +{ + struct inflate_state FAR *state; + + if (inflateStateCheck(strm)) return Z_STREAM_ERROR; + state = (struct inflate_state FAR *)strm->state; + if (check) + state->wrap |= 4; + else + state->wrap &= ~4; + return Z_OK; +} + +long ZEXPORT inflateMark(strm) +z_streamp strm; +{ + struct inflate_state FAR *state; + + if (inflateStateCheck(strm)) + return -(1L << 16); + state = (struct inflate_state FAR *)strm->state; + return (long)(((unsigned long)((long)state->back)) << 16) + + (state->mode == COPY ? state->length : + (state->mode == MATCH ? state->was - state->length : 0)); +} + +unsigned long ZEXPORT inflateCodesUsed(strm) +z_streamp strm; +{ + struct inflate_state FAR *state; + if (inflateStateCheck(strm)) return (unsigned long)-1; + state = (struct inflate_state FAR *)strm->state; + return (unsigned long)(state->next - state->codes); +} diff --git a/lib/libz/inflate.h b/lib/libz/inflate.h index 07bd3e7..63c1487 100644 --- a/lib/libz/inflate.h +++ b/lib/libz/inflate.h @@ -1,5 +1,7 @@ +/* $OpenBSD: inflate.h,v 1.4 2021/07/04 17:41:23 tb Exp $ */ + /* inflate.h -- internal inflate state definition - * Copyright (C) 1995-2004 Mark Adler + * Copyright (C) 1995-2016 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -18,7 +20,7 @@ /* Possible inflate modes between inflate() calls */ typedef enum { - HEAD, /* i: waiting for magic header */ + HEAD = 16180, /* i: waiting for magic header */ FLAGS, /* i: waiting for method and flags (gzip) */ TIME, /* i: waiting for modification time (gzip) */ OS, /* i: waiting for extra flags and operating system (gzip) */ @@ -32,11 +34,13 @@ typedef enum { TYPE, /* i: waiting for type bits, including last-flag bit */ TYPEDO, /* i: same, but skip check to exit inflate on new block */ STORED, /* i: waiting for stored size (length and complement) */ + COPY_, /* i/o: same as COPY below, but only first time in */ COPY, /* i/o: waiting for input or output to copy stored block */ TABLE, /* i: waiting for dynamic block table lengths */ LENLENS, /* i: waiting for code length code lengths */ CODELENS, /* i: waiting for length/lit and distance code lengths */ - LEN, /* i: waiting for length/lit code */ + LEN_, /* i: same as LEN below, but only first time in */ + LEN, /* i: waiting for length/lit/eob code */ LENEXT, /* i: waiting for length extra bits */ DIST, /* i: waiting for distance code */ DISTEXT, /* i: waiting for distance extra bits */ @@ -53,19 +57,21 @@ typedef enum { /* State transitions between above modes - - (most modes can go to the BAD or MEM mode -- not shown for clarity) + (most modes can go to BAD or MEM on error -- not shown for clarity) Process header: - HEAD -> (gzip) or (zlib) - (gzip) -> FLAGS -> TIME -> OS -> EXLEN -> EXTRA -> NAME - NAME -> COMMENT -> HCRC -> TYPE + HEAD -> (gzip) or (zlib) or (raw) + (gzip) -> FLAGS -> TIME -> OS -> EXLEN -> EXTRA -> NAME -> COMMENT -> + HCRC -> TYPE (zlib) -> DICTID or TYPE DICTID -> DICT -> TYPE + (raw) -> TYPEDO Read deflate blocks: - TYPE -> STORED or TABLE or LEN or CHECK - STORED -> COPY -> TYPE - TABLE -> LENLENS -> CODELENS -> LEN - Read deflate codes: + TYPE -> TYPEDO -> STORED or TABLE or LEN_ or CHECK + STORED -> COPY_ -> COPY -> TYPE + TABLE -> LENLENS -> CODELENS -> LEN_ + LEN_ -> LEN + Read deflate codes in fixed or dynamic block: LEN -> LENEXT or LIT or TYPE LENEXT -> DIST -> DISTEXT -> MATCH -> LEN LIT -> LEN @@ -73,11 +79,14 @@ typedef enum { CHECK -> LENGTH -> DONE */ -/* state maintained between inflate() calls. Approximately 7K bytes. */ +/* State maintained between inflate() calls -- approximately 7K bytes, not + including the allocated sliding window, which is up to 32K bytes. */ struct inflate_state { + z_streamp strm; /* pointer back to this zlib stream */ inflate_mode mode; /* current inflate mode */ int last; /* true if processing last block */ - int wrap; /* bit 0 true for zlib, bit 1 true for gzip */ + int wrap; /* bit 0 true for zlib, bit 1 true for gzip, + bit 2 true to validate check value */ int havedict; /* true if dictionary provided */ int flags; /* gzip header method and flags (0 if zlib) */ unsigned dmax; /* zlib header max distance (INFLATE_STRICT) */ @@ -88,7 +97,7 @@ struct inflate_state { unsigned wbits; /* log base 2 of requested window size */ unsigned wsize; /* window size or zero if not using window */ unsigned whave; /* valid bytes in the window */ - unsigned write; /* window write index */ + unsigned wnext; /* window write index */ unsigned char FAR *window; /* allocated sliding window, if needed */ /* bit accumulator */ unsigned long hold; /* input bit accumulator */ @@ -112,4 +121,7 @@ struct inflate_state { unsigned short lens[320]; /* temporary storage for code lengths */ unsigned short work[288]; /* work area for code table building */ code codes[ENOUGH]; /* space for code tables */ + int sane; /* if false, allow invalid distance too far */ + int back; /* bits back of last unprocessed length/lit */ + unsigned was; /* initial length of match */ }; diff --git a/lib/libz/inftrees.c b/lib/libz/inftrees.c index 0b879cd..514b1a6 100644 --- a/lib/libz/inftrees.c +++ b/lib/libz/inftrees.c @@ -1,6 +1,6 @@ -/* $OpenBSD: inftrees.c,v 1.9 2009/10/27 23:59:31 deraadt Exp $ */ +/* $OpenBSD: inftrees.c,v 1.10 2021/07/04 14:24:49 tb Exp $ */ /* inftrees.c -- generate Huffman trees for efficient decoding - * Copyright (C) 1995-2005 Mark Adler + * Copyright (C) 1995-2017 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -28,7 +28,7 @@ table index bits. It will differ if the request is greater than the longest code or if it is less than the shortest code. */ -int inflate_table(type, lens, codes, table, bits, work) +int ZLIB_INTERNAL inflate_table(type, lens, codes, table, bits, work) codetype type; unsigned short FAR *lens; unsigned codes; @@ -49,11 +49,11 @@ unsigned short FAR *work; unsigned fill; /* index for replicating entries */ unsigned low; /* low bits for current root entry */ unsigned mask; /* mask for low root bits */ - code this; /* table entry for duplication */ + code here; /* table entry for duplication */ code FAR *next; /* next available space in table */ const unsigned short FAR *base; /* base value table to use */ const unsigned short FAR *extra; /* extra bits table to use */ - int end; /* use base and extra for symbol > end */ + unsigned match; /* use base and extra for symbol >= match */ unsigned short count[MAXBITS+1]; /* number of codes of each length */ unsigned short offs[MAXBITS+1]; /* offsets in table for each length */ static const unsigned short lbase[31] = { /* Length codes 257..285 base */ @@ -61,7 +61,7 @@ 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, 201, 196}; + 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 77, 202}; 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, @@ -114,15 +114,15 @@ unsigned short FAR *work; if (count[max] != 0) break; if (root > max) root = max; if (max == 0) { /* no symbols to code at all */ - this.op = (unsigned char)64; /* invalid code marker */ - this.bits = (unsigned char)1; - this.val = (unsigned short)0; - *(*table)++ = this; /* make a table to force an error */ - *(*table)++ = this; + here.op = (unsigned char)64; /* invalid code marker */ + here.bits = (unsigned char)1; + here.val = (unsigned short)0; + *(*table)++ = here; /* make a table to force an error */ + *(*table)++ = here; *bits = 1; return 0; /* no symbols, but wait for decoding to report error */ } - for (min = 1; min <= MAXBITS; min++) + for (min = 1; min < max; min++) if (count[min] != 0) break; if (root < min) root = min; @@ -165,11 +165,10 @@ unsigned short FAR *work; entered in the tables. used keeps track of how many table entries have been allocated from the - provided *table space. It is checked when a LENS table is being made - against the space in *table, ENOUGH, minus the maximum space needed by - the worst case distance code, MAXD. This should never happen, but the - sufficiency of ENOUGH has not been proven exhaustively, hence the check. - This assumes that when type == LENS, bits == 9. + provided *table space. It is checked for LENS and DIST tables against + the constants ENOUGH_LENS and ENOUGH_DISTS to guard against changes in + the initial root table size constants. See the comments in inftrees.h + for more information. sym increments through all symbols, and the loop terminates when all codes of length max, i.e. all codes, have been processed. This @@ -181,19 +180,17 @@ unsigned short FAR *work; switch (type) { case CODES: base = extra = work; /* dummy value--not used */ - end = 19; + match = 20; break; case LENS: base = lbase; - base -= 257; extra = lext; - extra -= 257; - end = 256; + match = 257; break; - default: /* DISTS */ + default: /* DISTS */ base = dbase; extra = dext; - end = -1; + match = 0; } /* initialize state for loop */ @@ -208,24 +205,25 @@ unsigned short FAR *work; mask = used - 1; /* mask for comparing low */ /* check available table space */ - if (type == LENS && used >= ENOUGH - MAXD) + if ((type == LENS && used > ENOUGH_LENS) || + (type == DISTS && used > ENOUGH_DISTS)) return 1; /* process all codes and make table entries */ for (;;) { /* create table entry */ - this.bits = (unsigned char)(len - drop); - if ((int)(work[sym]) < end) { - this.op = (unsigned char)0; - this.val = work[sym]; + here.bits = (unsigned char)(len - drop); + if (work[sym] + 1U < match) { + here.op = (unsigned char)0; + here.val = work[sym]; } - else if ((int)(work[sym]) > end) { - this.op = (unsigned char)(extra[work[sym]]); - this.val = base[work[sym]]; + else if (work[sym] >= match) { + here.op = (unsigned char)(extra[work[sym] - match]); + here.val = base[work[sym] - match]; } else { - this.op = (unsigned char)(32 + 64); /* end of block */ - this.val = 0; + here.op = (unsigned char)(32 + 64); /* end of block */ + here.val = 0; } /* replicate for those indices with low len bits equal to huff */ @@ -234,7 +232,7 @@ unsigned short FAR *work; min = fill; /* save offset to next table */ do { fill -= incr; - next[(huff >> drop) + fill] = this; + next[(huff >> drop) + fill] = here; } while (fill != 0); /* backwards increment the len-bit code huff */ @@ -276,7 +274,8 @@ unsigned short FAR *work; /* check for enough space */ used += 1U << curr; - if (type == LENS && used >= ENOUGH - MAXD) + if ((type == LENS && used > ENOUGH_LENS) || + (type == DISTS && used > ENOUGH_DISTS)) return 1; /* point entry in root table to sub-table */ @@ -287,38 +286,14 @@ unsigned short FAR *work; } } - /* - Fill in rest of table for incomplete codes. This loop is similar to the - loop above in incrementing huff for table indices. It is assumed that - len is equal to curr + drop, so there is no loop needed to increment - through high index bits. When the current sub-table is filled, the loop - drops back to the root table to fill in any remaining entries there. - */ - this.op = (unsigned char)64; /* invalid code marker */ - this.bits = (unsigned char)(len - drop); - this.val = (unsigned short)0; - while (huff != 0) { - /* when done with sub-table, drop back to root table */ - if (drop != 0 && (huff & mask) != low) { - drop = 0; - len = root; - next = *table; - this.bits = (unsigned char)len; - } - - /* put invalid code marker in table */ - next[huff >> drop] = this; - - /* backwards increment the len-bit code huff */ - incr = 1U << (len - 1); - while (huff & incr) - incr >>= 1; - if (incr != 0) { - huff &= incr - 1; - huff += incr; - } - else - huff = 0; + /* fill in remaining table entry if code is incomplete (guaranteed to have + at most one remaining entry, since if the code is incomplete, the + maximum code length that was allowed to get this far is one bit) */ + if (huff != 0) { + here.op = (unsigned char)64; /* invalid code marker */ + here.bits = (unsigned char)(len - drop); + here.val = (unsigned short)0; + next[huff] = here; } /* set return parameters */ diff --git a/lib/libz/inftrees.h b/lib/libz/inftrees.h index e032c6b..9596303 100644 --- a/lib/libz/inftrees.h +++ b/lib/libz/inftrees.h @@ -1,6 +1,7 @@ -/* $OpenBSD: inftrees.h,v 1.5 2005/07/20 15:56:41 millert Exp $ */ +/* $OpenBSD: inftrees.h,v 1.7 2021/07/04 17:41:23 tb Exp $ */ + /* inftrees.h -- header to use inftrees.c - * Copyright (C) 1995-2005 Mark Adler + * Copyright (C) 1995-2005, 2010 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -36,21 +37,28 @@ typedef struct { 01000000 - invalid code */ -/* Maximum size of dynamic tree. The maximum found in a long but non- - exhaustive search was 1444 code structures (852 for length/literals - and 592 for distances, the latter actually the result of an - exhaustive search). The true maximum is not known, but the value - below is more than safe. */ -#define ENOUGH 2048 -#define MAXD 592 +/* Maximum size of the dynamic table. The maximum number of code structures is + 1444, which is the sum of 852 for literal/length codes and 592 for distance + codes. These values were found by exhaustive searches using the program + examples/enough.c found in the zlib distribtution. The arguments to that + program are the number of symbols, the initial root table size, and the + maximum bit length of a code. "enough 286 9 15" for literal/length codes + returns returns 852, and "enough 30 6 15" for distance codes returns 592. + The initial root table size (9 or 6) is found in the fifth argument of the + inflate_table() calls in inflate.c and infback.c. If the root table size is + changed, then these maximum sizes would be need to be recalculated and + updated. */ +#define ENOUGH_LENS 852 +#define ENOUGH_DISTS 592 +#define ENOUGH (ENOUGH_LENS+ENOUGH_DISTS) -/* Type of code to build for inftable() */ +/* Type of code to build for inflate_table() */ typedef enum { CODES, LENS, DISTS } codetype; -extern int inflate_table OF((codetype type, unsigned short FAR *lens, +int ZLIB_INTERNAL inflate_table OF((codetype type, unsigned short FAR *lens, unsigned codes, code FAR * FAR *table, unsigned FAR *bits, unsigned short FAR *work)); diff --git a/lib/libz/shlib_version b/lib/libz/shlib_version index 3066b97..9c15516 100644 --- a/lib/libz/shlib_version +++ b/lib/libz/shlib_version @@ -1,2 +1,2 @@ -major=5 +major=6 minor=0 diff --git a/lib/libz/trees.c b/lib/libz/trees.c index c163626..0f43a16 100644 --- a/lib/libz/trees.c +++ b/lib/libz/trees.c @@ -1,6 +1,7 @@ -/* $OpenBSD: trees.c,v 1.8 2005/07/20 15:56:41 millert Exp $ */ +/* $OpenBSD: trees.c,v 1.9 2021/07/04 14:24:49 tb Exp $ */ /* trees.c -- output deflated data using Huffman coding - * Copyright (C) 1995-2005 Jean-loup Gailly + * Copyright (C) 1995-2017 Jean-loup Gailly + * detect_data_type() function provided freely by Cosmin Truta, 2006 * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -30,12 +31,11 @@ * Addison-Wesley, 1983. ISBN 0-201-06672-6. */ - /* #define GEN_TREES_H */ #include "deflate.h" -#ifdef DEBUG +#ifdef ZLIB_DEBUG # include <ctype.h> #endif @@ -73,11 +73,6 @@ local const uch bl_order[BL_CODES] * probability, to avoid transmitting the lengths for unused bit length codes. */ -#define Buf_size (8 * 2*sizeof(char)) -/* Number of bits used within bi_buf. (bi_buf might be implemented on - * more than 16 bits on some systems.) - */ - /* =========================================================================== * Local data. These are initialized only once. */ @@ -126,13 +121,13 @@ struct static_tree_desc_s { int max_length; /* max bit length for the codes */ }; -local static_tree_desc static_l_desc = +local const static_tree_desc static_l_desc = {static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS}; -local static_tree_desc static_d_desc = +local const static_tree_desc static_d_desc = {static_dtree, extra_dbits, 0, D_CODES, MAX_BITS}; -local static_tree_desc static_bl_desc = +local const static_tree_desc static_bl_desc = {(const ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS}; /* =========================================================================== @@ -150,24 +145,22 @@ local void send_tree OF((deflate_state *s, ct_data *tree, int max_code)); local int build_bl_tree OF((deflate_state *s)); local void send_all_trees OF((deflate_state *s, int lcodes, int dcodes, int blcodes)); -local void compress_block OF((deflate_state *s, ct_data *ltree, - ct_data *dtree)); -local void set_data_type OF((deflate_state *s)); +local void compress_block OF((deflate_state *s, const ct_data *ltree, + const ct_data *dtree)); +local int detect_data_type OF((deflate_state *s)); local unsigned bi_reverse OF((unsigned value, int length)); local void bi_windup OF((deflate_state *s)); local void bi_flush OF((deflate_state *s)); -local void copy_block OF((deflate_state *s, charf *buf, unsigned len, - int header)); #ifdef GEN_TREES_H local void gen_trees_header OF((void)); #endif -#ifndef DEBUG +#ifndef ZLIB_DEBUG # define send_code(s, c, tree) send_bits(s, tree[c].Code, tree[c].Len) /* Send a code of the given tree. c and tree must not have side effects */ -#else /* DEBUG */ +#else /* !ZLIB_DEBUG */ # define send_code(s, c, tree) \ { if (z_verbose>2) fprintf(stderr,"\ncd %3d ",(c)); \ send_bits(s, tree[c].Code, tree[c].Len); } @@ -186,7 +179,7 @@ local void gen_trees_header OF((void)); * Send a value on a given number of bits. * IN assertion: length <= 16 and value fits in length bits. */ -#ifdef DEBUG +#ifdef ZLIB_DEBUG local void send_bits OF((deflate_state *s, int value, int length)); local void send_bits(s, value, length) @@ -203,31 +196,31 @@ local void send_bits(s, value, length) * unused bits in value. */ if (s->bi_valid > (int)Buf_size - length) { - s->bi_buf |= (value << s->bi_valid); + s->bi_buf |= (ush)value << s->bi_valid; put_short(s, s->bi_buf); s->bi_buf = (ush)value >> (Buf_size - s->bi_valid); s->bi_valid += length - Buf_size; } else { - s->bi_buf |= value << s->bi_valid; + s->bi_buf |= (ush)value << s->bi_valid; s->bi_valid += length; } } -#else /* !DEBUG */ +#else /* !ZLIB_DEBUG */ #define send_bits(s, value, length) \ { int len = length;\ if (s->bi_valid > (int)Buf_size - len) {\ - int val = value;\ - s->bi_buf |= (val << s->bi_valid);\ + int val = (int)value;\ + s->bi_buf |= (ush)val << s->bi_valid;\ put_short(s, s->bi_buf);\ s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\ s->bi_valid += len - Buf_size;\ } else {\ - s->bi_buf |= (value) << s->bi_valid;\ + s->bi_buf |= (ush)(value) << s->bi_valid;\ s->bi_valid += len;\ }\ } -#endif /* DEBUG */ +#endif /* ZLIB_DEBUG */ /* the arguments must not have side effects */ @@ -250,11 +243,13 @@ local void tr_static_init() if (static_init_done) return; /* For some embedded targets, global variables are not initialized: */ +#ifdef NO_INIT_GLOBAL_POINTERS static_l_desc.static_tree = static_ltree; static_l_desc.extra_bits = extra_lbits; static_d_desc.static_tree = static_dtree; static_d_desc.extra_bits = extra_dbits; static_bl_desc.extra_bits = extra_blbits; +#endif /* Initialize the mapping length (0..255) -> length code (0..28) */ length = 0; @@ -319,7 +314,7 @@ local void tr_static_init() * Genererate the file trees.h describing the static trees. */ #ifdef GEN_TREES_H -# ifndef DEBUG +# ifndef ZLIB_DEBUG # include <stdio.h> # endif @@ -348,13 +343,14 @@ void gen_trees_header() static_dtree[i].Len, SEPARATOR(i, D_CODES-1, 5)); } - fprintf(header, "const uch _dist_code[DIST_CODE_LEN] = {\n"); + fprintf(header, "const uch ZLIB_INTERNAL _dist_code[DIST_CODE_LEN] = {\n"); for (i = 0; i < DIST_CODE_LEN; i++) { fprintf(header, "%2u%s", _dist_code[i], SEPARATOR(i, DIST_CODE_LEN-1, 20)); } - fprintf(header, "const uch _length_code[MAX_MATCH-MIN_MATCH+1]= {\n"); + fprintf(header, + "const uch ZLIB_INTERNAL _length_code[MAX_MATCH-MIN_MATCH+1]= {\n"); for (i = 0; i < MAX_MATCH-MIN_MATCH+1; i++) { fprintf(header, "%2u%s", _length_code[i], SEPARATOR(i, MAX_MATCH-MIN_MATCH, 20)); @@ -379,7 +375,7 @@ void gen_trees_header() /* =========================================================================== * Initialize the tree data structures for a new zlib stream. */ -void _tr_init(s) +void ZLIB_INTERNAL _tr_init(s) deflate_state *s; { tr_static_init(); @@ -395,8 +391,7 @@ void _tr_init(s) s->bi_buf = 0; s->bi_valid = 0; - s->last_eob_len = 8; /* enough lookahead for inflate */ -#ifdef DEBUG +#ifdef ZLIB_DEBUG s->compressed_len = 0L; s->bits_sent = 0L; #endif @@ -524,12 +519,12 @@ local void gen_bitlen(s, desc) xbits = 0; if (n >= base) xbits = extra[n-base]; f = tree[n].Freq; - s->opt_len += (ulg)f * (bits + xbits); - if (stree) s->static_len += (ulg)f * (stree[n].Len + xbits); + s->opt_len += (ulg)f * (unsigned)(bits + xbits); + if (stree) s->static_len += (ulg)f * (unsigned)(stree[n].Len + xbits); } if (overflow == 0) return; - Trace((stderr,"\nbit length overflow\n")); + Tracev((stderr,"\nbit length overflow\n")); /* This happens for example on obj2 and pic of the Calgary corpus */ /* Find the first bit length which could increase: */ @@ -556,9 +551,8 @@ local void gen_bitlen(s, desc) m = s->heap[--h]; if (m > max_code) continue; if ((unsigned) tree[m].Len != (unsigned) bits) { - Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); - s->opt_len += ((long)bits - (long)tree[m].Len) - *(long)tree[m].Freq; + Tracev((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); + s->opt_len += ((ulg)bits - tree[m].Len) * tree[m].Freq; tree[m].Len = (ush)bits; } n--; @@ -580,7 +574,7 @@ local void gen_codes (tree, max_code, bl_count) ushf *bl_count; /* number of codes at each bit length */ { ush next_code[MAX_BITS+1]; /* next code value for each bit length */ - ush code = 0; /* running code value */ + unsigned code = 0; /* running code value */ int bits; /* bit index */ int n; /* code index */ @@ -588,7 +582,8 @@ local void gen_codes (tree, max_code, bl_count) * without bit reversal. */ for (bits = 1; bits <= MAX_BITS; bits++) { - next_code[bits] = code = (code + bl_count[bits-1]) << 1; + code = (code + bl_count[bits-1]) << 1; + next_code[bits] = (ush)code; } /* Check that the bit counts in bl_count are consistent. The last code * must be all ones. @@ -601,7 +596,7 @@ local void gen_codes (tree, max_code, bl_count) int len = tree[n].Len; if (len == 0) continue; /* Now reverse the bits */ - tree[n].Code = bi_reverse(next_code[len]++, len); + tree[n].Code = (ush)bi_reverse(next_code[len]++, len); Tracecv(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ", n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1)); @@ -823,7 +818,7 @@ local int build_bl_tree(s) if (s->bl_tree[bl_order[max_blindex]].Len != 0) break; } /* Update opt_len to include the bit length tree and counts */ - s->opt_len += 3*(max_blindex+1) + 5+5+4; + s->opt_len += 3*((ulg)max_blindex+1) + 5+5+4; Tracev((stderr, "\ndyn trees: dyn %ld, stat %ld", s->opt_len, s->static_len)); @@ -864,65 +859,59 @@ local void send_all_trees(s, lcodes, dcodes, blcodes) /* =========================================================================== * Send a stored block */ -void _tr_stored_block(s, buf, stored_len, eof) +void ZLIB_INTERNAL _tr_stored_block(s, buf, stored_len, last) deflate_state *s; charf *buf; /* input block */ ulg stored_len; /* length of input block */ - int eof; /* true if this is the last block for a file */ + int last; /* one if this is the last block for a file */ { - send_bits(s, (STORED_BLOCK<<1)+eof, 3); /* send block type */ -#ifdef DEBUG + send_bits(s, (STORED_BLOCK<<1)+last, 3); /* send block type */ + bi_windup(s); /* align on byte boundary */ + put_short(s, (ush)stored_len); + put_short(s, (ush)~stored_len); + zmemcpy(s->pending_buf + s->pending, (Bytef *)buf, stored_len); + s->pending += stored_len; +#ifdef ZLIB_DEBUG s->compressed_len = (s->compressed_len + 3 + 7) & (ulg)~7L; s->compressed_len += (stored_len + 4) << 3; + s->bits_sent += 2*16; + s->bits_sent += stored_len<<3; #endif - copy_block(s, buf, (unsigned)stored_len, 1); /* with header */ +} + +/* =========================================================================== + * Flush the bits in the bit buffer to pending output (leaves at most 7 bits) + */ +void ZLIB_INTERNAL _tr_flush_bits(s) + deflate_state *s; +{ + bi_flush(s); } /* =========================================================================== * Send one empty static block to give enough lookahead for inflate. * This takes 10 bits, of which 7 may remain in the bit buffer. - * The current inflate code requires 9 bits of lookahead. If the - * last two codes for the previous block (real code plus EOB) were coded - * on 5 bits or less, inflate may have only 5+3 bits of lookahead to decode - * the last real code. In this case we send two empty static blocks instead - * of one. (There are no problems if the previous block is stored or fixed.) - * To simplify the code, we assume the worst case of last real code encoded - * on one bit only. */ -void _tr_align(s) +void ZLIB_INTERNAL _tr_align(s) deflate_state *s; { send_bits(s, STATIC_TREES<<1, 3); send_code(s, END_BLOCK, static_ltree); -#ifdef DEBUG +#ifdef ZLIB_DEBUG s->compressed_len += 10L; /* 3 for block type, 7 for EOB */ #endif bi_flush(s); - /* Of the 10 bits for the empty block, we have already sent - * (10 - bi_valid) bits. The lookahead for the last real code (before - * the EOB of the previous block) was thus at least one plus the length - * of the EOB plus what we have just sent of the empty static block. - */ - if (1 + s->last_eob_len + 10 - s->bi_valid < 9) { - send_bits(s, STATIC_TREES<<1, 3); - send_code(s, END_BLOCK, static_ltree); -#ifdef DEBUG - s->compressed_len += 10L; -#endif - bi_flush(s); - } - s->last_eob_len = 7; } /* =========================================================================== * Determine the best encoding for the current block: dynamic trees, static - * trees or store, and output the encoded block to the zip file. + * trees or store, and write out the encoded block. */ -void _tr_flush_block(s, buf, stored_len, eof) +void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last) deflate_state *s; charf *buf; /* input block, or NULL if too old */ ulg stored_len; /* length of input block */ - int eof; /* true if this is the last block for a file */ + int last; /* one if this is the last block for a file */ { ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */ int max_blindex = 0; /* index of last bit length code of non zero freq */ @@ -931,8 +920,8 @@ void _tr_flush_block(s, buf, stored_len, eof) if (s->level > 0) { /* Check if the file is binary or text */ - if (stored_len > 0 && s->strm->data_type == Z_UNKNOWN) - set_data_type(s); + if (s->strm->data_type == Z_UNKNOWN) + s->strm->data_type = detect_data_type(s); /* Construct the literal and distance trees */ build_tree(s, (tree_desc *)(&(s->l_desc))); @@ -978,24 +967,26 @@ void _tr_flush_block(s, buf, stored_len, eof) * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to * transform a block into a stored block. */ - _tr_stored_block(s, buf, stored_len, eof); + _tr_stored_block(s, buf, stored_len, last); #ifdef FORCE_STATIC } else if (static_lenb >= 0) { /* force static trees */ #else } else if (s->strategy == Z_FIXED || static_lenb == opt_lenb) { #endif - send_bits(s, (STATIC_TREES<<1)+eof, 3); - compress_block(s, (ct_data *)static_ltree, (ct_data *)static_dtree); -#ifdef DEBUG + send_bits(s, (STATIC_TREES<<1)+last, 3); + compress_block(s, (const ct_data *)static_ltree, + (const ct_data *)static_dtree); +#ifdef ZLIB_DEBUG s->compressed_len += 3 + s->static_len; #endif } else { - send_bits(s, (DYN_TREES<<1)+eof, 3); + send_bits(s, (DYN_TREES<<1)+last, 3); send_all_trees(s, s->l_desc.max_code+1, s->d_desc.max_code+1, max_blindex+1); - compress_block(s, (ct_data *)s->dyn_ltree, (ct_data *)s->dyn_dtree); -#ifdef DEBUG + compress_block(s, (const ct_data *)s->dyn_ltree, + (const ct_data *)s->dyn_dtree); +#ifdef ZLIB_DEBUG s->compressed_len += 3 + s->opt_len; #endif } @@ -1005,21 +996,21 @@ void _tr_flush_block(s, buf, stored_len, eof) */ init_block(s); - if (eof) { + if (last) { bi_windup(s); -#ifdef DEBUG +#ifdef ZLIB_DEBUG s->compressed_len += 7; /* align on byte boundary */ #endif } Tracev((stderr,"\ncomprlen %lu(%lu) ", s->compressed_len>>3, - s->compressed_len-7*eof)); + s->compressed_len-7*last)); } /* =========================================================================== * Save the match info and tally the frequency counts. Return true if * the current block must be flushed. */ -int _tr_tally (s, dist, lc) +int ZLIB_INTERNAL _tr_tally (s, dist, lc) deflate_state *s; unsigned dist; /* distance of matched string */ unsigned lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */ @@ -1071,8 +1062,8 @@ int _tr_tally (s, dist, lc) */ local void compress_block(s, ltree, dtree) deflate_state *s; - ct_data *ltree; /* literal tree */ - ct_data *dtree; /* distance tree */ + const ct_data *ltree; /* literal tree */ + const ct_data *dtree; /* distance tree */ { unsigned dist; /* distance of matched string */ int lc; /* match length or unmatched char (if dist == 0) */ @@ -1102,7 +1093,7 @@ local void compress_block(s, ltree, dtree) send_code(s, code, dtree); /* send the distance code */ extra = extra_dbits[code]; if (extra != 0) { - dist -= base_dist[code]; + dist -= (unsigned)base_dist[code]; send_bits(s, dist, extra); /* send the extra distance bits */ } } /* literal or match pair ? */ @@ -1114,28 +1105,48 @@ local void compress_block(s, ltree, dtree) } while (lx < s->last_lit); send_code(s, END_BLOCK, ltree); - s->last_eob_len = ltree[END_BLOCK].Len; } /* =========================================================================== - * Set the data type to BINARY or TEXT, using a crude approximation: - * set it to Z_TEXT if all symbols are either printable characters (33 to 255) - * or white spaces (9 to 13, or 32); or set it to Z_BINARY otherwise. + * Check if the data type is TEXT or BINARY, using the following algorithm: + * - TEXT if the two conditions below are satisfied: + * a) There are no non-portable control characters belonging to the + * "black list" (0..6, 14..25, 28..31). + * b) There is at least one printable character belonging to the + * "white list" (9 {TAB}, 10 {LF}, 13 {CR}, 32..255). + * - BINARY otherwise. + * - The following partially-portable control characters form a + * "gray list" that is ignored in this detection algorithm: + * (7 {BEL}, 8 {BS}, 11 {VT}, 12 {FF}, 26 {SUB}, 27 {ESC}). * IN assertion: the fields Freq of dyn_ltree are set. */ -local void set_data_type(s) +local int detect_data_type(s) deflate_state *s; { + /* black_mask is the bit mask of black-listed bytes + * set bits 0..6, 14..25, and 28..31 + * 0xf3ffc07f = binary 11110011111111111100000001111111 + */ + unsigned long black_mask = 0xf3ffc07fUL; int n; - for (n = 0; n < 9; n++) + /* Check for non-textual ("black-listed") bytes. */ + for (n = 0; n <= 31; n++, black_mask >>= 1) + if ((black_mask & 1) && (s->dyn_ltree[n].Freq != 0)) + return Z_BINARY; + + /* Check for textual ("white-listed") bytes. */ + if (s->dyn_ltree[9].Freq != 0 || s->dyn_ltree[10].Freq != 0 + || s->dyn_ltree[13].Freq != 0) + return Z_TEXT; + for (n = 32; n < LITERALS; n++) if (s->dyn_ltree[n].Freq != 0) - break; - if (n == 9) - for (n = 14; n < 32; n++) - if (s->dyn_ltree[n].Freq != 0) - break; - s->strm->data_type = (n == 32) ? Z_TEXT : Z_BINARY; + return Z_TEXT; + + /* There are no "black-listed" or "white-listed" bytes: + * this stream either is empty or has tolerated ("gray-listed") bytes only. + */ + return Z_BINARY; } /* =========================================================================== @@ -1185,35 +1196,7 @@ local void bi_windup(s) } s->bi_buf = 0; s->bi_valid = 0; -#ifdef DEBUG +#ifdef ZLIB_DEBUG s->bits_sent = (s->bits_sent+7) & ~7; #endif } - -/* =========================================================================== - * Copy a stored block, storing first the length and its - * one's complement if requested. - */ -local void copy_block(s, buf, len, header) - deflate_state *s; - charf *buf; /* the input data */ - unsigned len; /* its length */ - int header; /* true if block header must be written */ -{ - bi_windup(s); /* align on byte boundary */ - s->last_eob_len = 8; /* enough lookahead for inflate */ - - if (header) { - put_short(s, (ush)len); - put_short(s, (ush)~len); -#ifdef DEBUG - s->bits_sent += 2*16; -#endif - } -#ifdef DEBUG - s->bits_sent += (ulg)len<<3; -#endif - while (len--) { - put_byte(s, *buf++); - } -} diff --git a/lib/libz/trees.h b/lib/libz/trees.h index ca79189..d692724 100644 --- a/lib/libz/trees.h +++ b/lib/libz/trees.h @@ -1,4 +1,5 @@ -/* $OpenBSD: trees.h,v 1.2 2002/03/12 00:25:57 millert Exp $ */ +/* $OpenBSD: trees.h,v 1.4 2021/07/04 17:41:23 tb Exp $ */ + /* header created automatically with -DGEN_TREES_H */ local const ct_data static_ltree[L_CODES+2] = { @@ -71,7 +72,7 @@ local const ct_data static_dtree[D_CODES] = { {{19},{ 5}}, {{11},{ 5}}, {{27},{ 5}}, {{ 7},{ 5}}, {{23},{ 5}} }; -const uch _dist_code[DIST_CODE_LEN] = { +const uch ZLIB_INTERNAL _dist_code[DIST_CODE_LEN] = { 0, 1, 2, 3, 4, 4, 5, 5, 6, 6, 6, 6, 7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, @@ -100,7 +101,7 @@ const uch _dist_code[DIST_CODE_LEN] = { 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29 }; -const uch _length_code[MAX_MATCH-MIN_MATCH+1]= { +const uch ZLIB_INTERNAL _length_code[MAX_MATCH-MIN_MATCH+1]= { 0, 1, 2, 3, 4, 5, 6, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 12, 12, 13, 13, 13, 13, 14, 14, 14, 14, 15, 15, 15, 15, 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 17, 17, 17, 17, 18, 18, 18, 18, 18, 18, 18, 18, 19, 19, 19, 19, diff --git a/lib/libz/uncompr.c b/lib/libz/uncompr.c index 2b50fa3..3bbe21d 100644 --- a/lib/libz/uncompr.c +++ b/lib/libz/uncompr.c @@ -1,61 +1,92 @@ -/* $OpenBSD: uncompr.c,v 1.5 2003/12/16 22:33:02 henning Exp $ */ +/* $OpenBSD: uncompr.c,v 1.6 2021/07/04 14:24:49 tb Exp $ */ /* uncompr.c -- decompress a memory buffer - * Copyright (C) 1995-2003 Jean-loup Gailly. + * Copyright (C) 1995-2003, 2010, 2014, 2016 Jean-loup Gailly, Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ - #define ZLIB_INTERNAL #include "zlib.h" /* =========================================================================== - Decompresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total - size of the destination buffer, which must be large enough to hold the - entire uncompressed data. (The size of the uncompressed data must have - been saved previously by the compressor and transmitted to the decompressor - by some mechanism outside the scope of this compression library.) - Upon exit, destLen is the actual size of the compressed buffer. - This function can be used to decompress a whole file at once if the - input file is mmap'ed. - - uncompress returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer, or Z_DATA_ERROR if the input data was corrupted. + Decompresses the source buffer into the destination buffer. *sourceLen is + the byte length of the source buffer. Upon entry, *destLen is the total size + of the destination buffer, which must be large enough to hold the entire + uncompressed data. (The size of the uncompressed data must have been saved + previously by the compressor and transmitted to the decompressor by some + mechanism outside the scope of this compression library.) Upon exit, + *destLen is the size of the decompressed data and *sourceLen is the number + of source bytes consumed. Upon return, source + *sourceLen points to the + first unused input byte. + + uncompress returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_BUF_ERROR if there was not enough room in the output buffer, or + Z_DATA_ERROR if the input data was corrupted, including if the input data is + an incomplete zlib stream. */ -int ZEXPORT uncompress (dest, destLen, source, sourceLen) +int ZEXPORT uncompress2 (dest, destLen, source, sourceLen) Bytef *dest; uLongf *destLen; const Bytef *source; - uLong sourceLen; + uLong *sourceLen; { z_stream stream; int err; + const uInt max = (uInt)-1; + uLong len, left; + Byte buf[1]; /* for detection of incomplete stream when *destLen == 0 */ - stream.next_in = (Bytef*)source; - stream.avail_in = (uInt)sourceLen; - /* Check for source > 64K on 16-bit machine: */ - if ((uLong)stream.avail_in != sourceLen) return Z_BUF_ERROR; - - stream.next_out = dest; - stream.avail_out = (uInt)*destLen; - if ((uLong)stream.avail_out != *destLen) return Z_BUF_ERROR; + len = *sourceLen; + if (*destLen) { + left = *destLen; + *destLen = 0; + } + else { + left = 1; + dest = buf; + } + stream.next_in = (z_const Bytef *)source; + stream.avail_in = 0; stream.zalloc = (alloc_func)0; stream.zfree = (free_func)0; + stream.opaque = (voidpf)0; err = inflateInit(&stream); if (err != Z_OK) return err; - err = inflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) { - inflateEnd(&stream); - if (err == Z_NEED_DICT || (err == Z_BUF_ERROR && stream.avail_in == 0)) - return Z_DATA_ERROR; - return err; - } - *destLen = stream.total_out; + stream.next_out = dest; + stream.avail_out = 0; - err = inflateEnd(&stream); - return err; + do { + if (stream.avail_out == 0) { + stream.avail_out = left > (uLong)max ? max : (uInt)left; + left -= stream.avail_out; + } + if (stream.avail_in == 0) { + stream.avail_in = len > (uLong)max ? max : (uInt)len; + len -= stream.avail_in; + } + err = inflate(&stream, Z_NO_FLUSH); + } while (err == Z_OK); + + *sourceLen -= len + stream.avail_in; + if (dest != buf) + *destLen = stream.total_out; + else if (stream.total_out && err == Z_BUF_ERROR) + left = 1; + + inflateEnd(&stream); + return err == Z_STREAM_END ? Z_OK : + err == Z_NEED_DICT ? Z_DATA_ERROR : + err == Z_BUF_ERROR && left + stream.avail_out ? Z_DATA_ERROR : + err; +} + +int ZEXPORT uncompress (dest, destLen, source, sourceLen) + Bytef *dest; + uLongf *destLen; + const Bytef *source; + uLong sourceLen; +{ + return uncompress2(dest, destLen, source, &sourceLen); } diff --git a/lib/libz/zconf.h b/lib/libz/zconf.h index 7ac5b7b..99f1fde 100644 --- a/lib/libz/zconf.h +++ b/lib/libz/zconf.h @@ -1,62 +1,168 @@ -/* $OpenBSD: zconf.h,v 1.8 2019/05/12 15:56:56 jca Exp $ */ +/* $OpenBSD: zconf.h,v 1.10 2021/07/04 17:41:23 tb Exp $ */ + /* zconf.h -- configuration of the zlib compression library - * Copyright (C) 1995-2005 Jean-loup Gailly. + * Copyright (C) 1995-2016 Jean-loup Gailly, Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ - #ifndef ZCONF_H #define ZCONF_H /* * If you *really* need a unique prefix for all types and library functions, * compile with -DZ_PREFIX. The "standard" zlib should be compiled without it. + * Even better than compiling with -DZ_PREFIX would be to use configure to set + * this permanently in zconf.h using "./configure --zprefix". */ -#ifdef Z_PREFIX -# define deflateInit_ z_deflateInit_ +#ifdef Z_PREFIX /* may be set to #if 1 by ./configure */ +# define Z_PREFIX_SET + +/* all linked symbols and init macros */ +# define _dist_code z__dist_code +# define _length_code z__length_code +# define _tr_align z__tr_align +# define _tr_flush_bits z__tr_flush_bits +# define _tr_flush_block z__tr_flush_block +# define _tr_init z__tr_init +# define _tr_stored_block z__tr_stored_block +# define _tr_tally z__tr_tally +# define adler32 z_adler32 +# define adler32_combine z_adler32_combine +# define adler32_combine64 z_adler32_combine64 +# define adler32_z z_adler32_z +# ifndef Z_SOLO +# define compress z_compress +# define compress2 z_compress2 +# define compressBound z_compressBound +# endif +# define crc32 z_crc32 +# define crc32_combine z_crc32_combine +# define crc32_combine64 z_crc32_combine64 +# define crc32_z z_crc32_z # define deflate z_deflate +# define deflateBound z_deflateBound +# define deflateCopy z_deflateCopy # define deflateEnd z_deflateEnd -# define inflateInit_ z_inflateInit_ -# define inflate z_inflate -# define inflateEnd z_inflateEnd +# define deflateGetDictionary z_deflateGetDictionary +# define deflateInit z_deflateInit +# define deflateInit2 z_deflateInit2 # define deflateInit2_ z_deflateInit2_ -# define deflateSetDictionary z_deflateSetDictionary -# define deflateCopy z_deflateCopy -# define deflateReset z_deflateReset +# define deflateInit_ z_deflateInit_ # define deflateParams z_deflateParams -# define deflateBound z_deflateBound +# define deflatePending z_deflatePending # define deflatePrime z_deflatePrime +# define deflateReset z_deflateReset +# define deflateResetKeep z_deflateResetKeep +# define deflateSetDictionary z_deflateSetDictionary +# define deflateSetHeader z_deflateSetHeader +# define deflateTune z_deflateTune +# define deflate_copyright z_deflate_copyright +# define get_crc_table z_get_crc_table +# ifndef Z_SOLO +# define gz_error z_gz_error +# define gz_intmax z_gz_intmax +# define gz_strwinerror z_gz_strwinerror +# define gzbuffer z_gzbuffer +# define gzclearerr z_gzclearerr +# define gzclose z_gzclose +# define gzclose_r z_gzclose_r +# define gzclose_w z_gzclose_w +# define gzdirect z_gzdirect +# define gzdopen z_gzdopen +# define gzeof z_gzeof +# define gzerror z_gzerror +# define gzflush z_gzflush +# define gzfread z_gzfread +# define gzfwrite z_gzfwrite +# define gzgetc z_gzgetc +# define gzgetc_ z_gzgetc_ +# define gzgets z_gzgets +# define gzoffset z_gzoffset +# define gzoffset64 z_gzoffset64 +# define gzopen z_gzopen +# define gzopen64 z_gzopen64 +# ifdef _WIN32 +# define gzopen_w z_gzopen_w +# endif +# define gzprintf z_gzprintf +# define gzputc z_gzputc +# define gzputs z_gzputs +# define gzread z_gzread +# define gzrewind z_gzrewind +# define gzseek z_gzseek +# define gzseek64 z_gzseek64 +# define gzsetparams z_gzsetparams +# define gztell z_gztell +# define gztell64 z_gztell64 +# define gzungetc z_gzungetc +# define gzvprintf z_gzvprintf +# define gzwrite z_gzwrite +# endif +# define inflate z_inflate +# define inflateBack z_inflateBack +# define inflateBackEnd z_inflateBackEnd +# define inflateBackInit z_inflateBackInit +# define inflateBackInit_ z_inflateBackInit_ +# define inflateCodesUsed z_inflateCodesUsed +# define inflateCopy z_inflateCopy +# define inflateEnd z_inflateEnd +# define inflateGetDictionary z_inflateGetDictionary +# define inflateGetHeader z_inflateGetHeader +# define inflateInit z_inflateInit +# define inflateInit2 z_inflateInit2 # define inflateInit2_ z_inflateInit2_ +# define inflateInit_ z_inflateInit_ +# define inflateMark z_inflateMark +# define inflatePrime z_inflatePrime +# define inflateReset z_inflateReset +# define inflateReset2 z_inflateReset2 +# define inflateResetKeep z_inflateResetKeep # define inflateSetDictionary z_inflateSetDictionary # define inflateSync z_inflateSync # define inflateSyncPoint z_inflateSyncPoint -# define inflateCopy z_inflateCopy -# define inflateReset z_inflateReset -# define inflateBack z_inflateBack -# define inflateBackEnd z_inflateBackEnd -# define compress z_compress -# define compress2 z_compress2 -# define compressBound z_compressBound -# define uncompress z_uncompress -# define adler32 z_adler32 -# define crc32 z_crc32 -# define get_crc_table z_get_crc_table +# define inflateUndermine z_inflateUndermine +# define inflateValidate z_inflateValidate +# define inflate_copyright z_inflate_copyright +# define inflate_fast z_inflate_fast +# define inflate_table z_inflate_table +# ifndef Z_SOLO +# define uncompress z_uncompress +# define uncompress2 z_uncompress2 +# endif # define zError z_zError +# ifndef Z_SOLO +# define zcalloc z_zcalloc +# define zcfree z_zcfree +# endif +# define zlibCompileFlags z_zlibCompileFlags +# define zlibVersion z_zlibVersion +/* all zlib typedefs in zlib.h and zconf.h */ +# define Byte z_Byte +# define Bytef z_Bytef # define alloc_func z_alloc_func +# define charf z_charf # define free_func z_free_func +# ifndef Z_SOLO +# define gzFile z_gzFile +# endif +# define gz_header z_gz_header +# define gz_headerp z_gz_headerp # define in_func z_in_func +# define intf z_intf # define out_func z_out_func -# define Byte z_Byte # define uInt z_uInt -# define uLong z_uLong -# define Bytef z_Bytef -# define charf z_charf -# define intf z_intf # define uIntf z_uIntf +# define uLong z_uLong # define uLongf z_uLongf -# define voidpf z_voidpf # define voidp z_voidp +# define voidpc z_voidpc +# define voidpf z_voidpf + +/* all zlib structs in zlib.h and zconf.h */ +# define gz_header_s z_gz_header_s +# define internal_state z_internal_state + #endif #if defined(__MSDOS__) && !defined(MSDOS) @@ -131,9 +237,19 @@ # define z_const #endif -/* Some Mac compilers merge all .h files incorrectly: */ -#if defined(__MWERKS__)||defined(applec)||defined(THINK_C)||defined(__SC__) -# define NO_DUMMY_DECL +#ifdef Z_SOLO + typedef unsigned long z_size_t; +#else +# define z_longlong long long +# if defined(NO_SIZE_T) + typedef unsigned NO_SIZE_T z_size_t; +# elif defined(STDC) +# include <stddef.h> + typedef size_t z_size_t; +# else + typedef unsigned long z_size_t; +# endif +# undef z_longlong #endif /* Maximum value for memLevel in deflateInit2 */ @@ -163,7 +279,7 @@ Of course this will generally degrade compression (there's no free lunch). The memory requirements for inflate are (in bytes) 1 << windowBits - that is, 32K for windowBits=15 (default value) plus a few kilobytes + that is, 32K for windowBits=15 (default value) plus about 7 kilobytes for small objects. */ @@ -177,6 +293,14 @@ # endif #endif +#ifndef Z_ARG /* function prototypes for stdarg */ +# if defined(STDC) || defined(Z_HAVE_STDARG_H) +# define Z_ARG(args) args +# else +# define Z_ARG(args) () +# endif +#endif + /* The following definitions for FAR are needed only for MSDOS mixed * model programming (small or medium model with some far allocations). * This was tested only with MSC; for other MSDOS compilers you may have @@ -290,41 +414,121 @@ typedef uLong FAR uLongf; typedef Byte *voidp; #endif -#include <sys/types.h> /* for off_t */ -#include <unistd.h> /* for SEEK_* and off_t */ -#define z_off_t off_t -#ifndef SEEK_SET +#if !defined(Z_U4) && !defined(Z_SOLO) && defined(STDC) +# include <limits.h> +# if (UINT_MAX == 0xffffffffUL) +# define Z_U4 unsigned +# elif (ULONG_MAX == 0xffffffffUL) +# define Z_U4 unsigned long +# elif (USHRT_MAX == 0xffffffffUL) +# define Z_U4 unsigned short +# endif +#endif + +#ifdef Z_U4 + typedef Z_U4 z_crc_t; +#else + typedef unsigned long z_crc_t; +#endif + +#if 1 +# define Z_HAVE_UNISTD_H +#endif + +#if 1 +# define Z_HAVE_STDARG_H +#endif + +#ifdef STDC +# ifndef Z_SOLO +# include <sys/types.h> /* for off_t */ +# endif +#endif + +#if defined(STDC) || defined(Z_HAVE_STDARG_H) +# ifndef Z_SOLO +# include <stdarg.h> /* for va_list */ +# endif +#endif + +#ifdef _WIN32 +# ifndef Z_SOLO +# include <stddef.h> /* for wchar_t */ +# endif +#endif + +/* a little trick to accommodate both "#define _LARGEFILE64_SOURCE" and + * "#define _LARGEFILE64_SOURCE 1" as requesting 64-bit operations, (even + * though the former does not conform to the LFS document), but considering + * both "#undef _LARGEFILE64_SOURCE" and "#define _LARGEFILE64_SOURCE 0" as + * equivalently requesting no 64-bit operations + */ +#if defined(_LARGEFILE64_SOURCE) && -_LARGEFILE64_SOURCE - -1 == 1 +# undef _LARGEFILE64_SOURCE +#endif + +#if defined(__WATCOMC__) && !defined(Z_HAVE_UNISTD_H) +# define Z_HAVE_UNISTD_H +#endif +#ifndef Z_SOLO +# if defined(Z_HAVE_UNISTD_H) || defined(_LARGEFILE64_SOURCE) +# include <unistd.h> /* for SEEK_*, off_t, and _LFS64_LARGEFILE */ +# ifdef VMS +# include <unixio.h> /* for off_t */ +# endif +# ifndef z_off_t +# define z_off_t off_t +# endif +# endif +#endif + +#if defined(_LFS64_LARGEFILE) && _LFS64_LARGEFILE-0 +# define Z_LFS64 +#endif + +#if defined(_LARGEFILE64_SOURCE) && defined(Z_LFS64) +# define Z_LARGE64 +#endif + +#if defined(_FILE_OFFSET_BITS) && _FILE_OFFSET_BITS-0 == 64 && defined(Z_LFS64) +# define Z_WANT64 +#endif + +#if !defined(SEEK_SET) && !defined(Z_SOLO) # define SEEK_SET 0 /* Seek from beginning of file. */ # define SEEK_CUR 1 /* Seek from current position. */ # define SEEK_END 2 /* Set file pointer to EOF plus "offset" */ #endif -#if defined(__OS400__) -#define NO_vsnprintf +#ifndef z_off_t +# define z_off_t long #endif -#if defined(__MVS__) -# define NO_vsnprintf -# ifdef FAR -# undef FAR +#if !defined(_WIN32) && defined(Z_LARGE64) +# define z_off64_t off64_t +#else +# if defined(_WIN32) && !defined(__GNUC__) && !defined(Z_SOLO) +# define z_off64_t __int64 +# else +# define z_off64_t z_off_t # endif #endif /* MVS linker does not support external names larger than 8 bytes */ #if defined(__MVS__) -# pragma map(deflateInit_,"DEIN") -# pragma map(deflateInit2_,"DEIN2") -# pragma map(deflateEnd,"DEEND") -# pragma map(deflateBound,"DEBND") -# pragma map(inflateInit_,"ININ") -# pragma map(inflateInit2_,"ININ2") -# pragma map(inflateEnd,"INEND") -# pragma map(inflateSync,"INSY") -# pragma map(inflateSetDictionary,"INSEDI") -# pragma map(compressBound,"CMBND") -# pragma map(inflate_table,"INTABL") -# pragma map(inflate_fast,"INFA") -# pragma map(inflate_copyright,"INCOPY") + #pragma map(deflateInit_,"DEIN") + #pragma map(deflateInit2_,"DEIN2") + #pragma map(deflateEnd,"DEEND") + #pragma map(deflateBound,"DEBND") + #pragma map(inflateInit_,"ININ") + #pragma map(inflateInit2_,"ININ2") + #pragma map(inflateEnd,"INEND") + #pragma map(inflateSync,"INSY") + #pragma map(inflateSetDictionary,"INSEDI") + #pragma map(compressBound,"CMBND") + #pragma map(inflate_table,"INTABL") + #pragma map(inflate_fast,"INFA") + #pragma map(inflate_copyright,"INCOPY") #endif #endif /* ZCONF_H */ diff --git a/lib/libz/zlib.h b/lib/libz/zlib.h index a2c23f0..e2d1d34 100644 --- a/lib/libz/zlib.h +++ b/lib/libz/zlib.h @@ -1,8 +1,9 @@ -/* $OpenBSD: zlib.h,v 1.11 2019/05/12 15:56:56 jca Exp $ */ +/* $OpenBSD: zlib.h,v 1.13 2021/07/04 17:41:23 tb Exp $ */ + /* zlib.h -- interface of the 'zlib' general purpose compression library - version 1.2.3, July 18th, 2005 + version 1.2.11, January 15th, 2017 - Copyright (C) 1995-2005 Jean-loup Gailly and Mark Adler + Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler This software is provided 'as-is', without any express or implied warranty. In no event will the authors be held liable for any damages @@ -25,8 +26,8 @@ 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) and rfc1952.txt (gzip format). + Comments) 1950 to 1952 in the files http://tools.ietf.org/html/rfc1950 + (zlib format), rfc1951 (deflate format) and rfc1952 (gzip format). */ #ifndef ZLIB_H @@ -38,41 +39,45 @@ extern "C" { #endif -#define ZLIB_VERSION "1.2.3" -#define ZLIB_VERNUM 0x1230 +#define ZLIB_VERSION "1.2.11" +#define ZLIB_VERNUM 0x12b0 +#define ZLIB_VER_MAJOR 1 +#define ZLIB_VER_MINOR 2 +#define ZLIB_VER_REVISION 11 +#define ZLIB_VER_SUBREVISION 0 /* - The 'zlib' compression library provides in-memory compression and - decompression functions, including integrity checks of the uncompressed - data. This version of the library supports only one compression method - (deflation) but other algorithms will be added later and will have the same - stream interface. - - Compression can be done in a single step if the buffers are large - enough (for example if an input file is mmap'ed), or can be done by - repeated calls of the compression function. In the latter case, the - application must provide more input and/or consume the output + The 'zlib' compression library provides in-memory compression and + decompression functions, including integrity checks of the uncompressed data. + This version of the library supports only one compression method (deflation) + but other algorithms will be added later and will have the same stream + interface. + + Compression can be done in a single step if the buffers are large enough, + or can be done by repeated calls of the compression function. In the latter + case, the application must provide more input and/or consume the output (providing more output space) before each call. - The compressed data format used by default by the in-memory functions is + The compressed data format used by default by the in-memory functions is the zlib format, which is a zlib wrapper documented in RFC 1950, wrapped around a deflate stream, which is itself documented in RFC 1951. - The library also supports reading and writing files in gzip (.gz) format + The library also supports reading and writing files in gzip (.gz) format with an interface similar to that of stdio using the functions that start with "gz". The gzip format is different from the zlib format. gzip is a gzip wrapper, documented in RFC 1952, wrapped around a deflate stream. - This library can optionally read and write gzip streams in memory as well. + This library can optionally read and write gzip and raw deflate streams in + memory as well. - The zlib format was designed to be compact and fast for use in memory + The zlib format was designed to be compact and fast for use in memory and on communications channels. The gzip format was designed for single- file compression on file systems, has a larger header than zlib to maintain directory information, and uses a different, slower check method than zlib. - The library does not install any signal handler. The decoder checks - the consistency of the compressed data, so the library should never - crash even in case of corrupted input. + The library does not install any signal handler. The decoder checks + the consistency of the compressed data, so the library should never crash + even in the case of corrupted input. */ typedef voidpf (*alloc_func) OF((voidpf opaque, uInt items, uInt size)); @@ -83,11 +88,11 @@ struct internal_state; typedef struct z_stream_s { z_const Bytef *next_in; /* next input byte */ uInt avail_in; /* number of bytes available at next_in */ - z_off_t total_in; /* total nb of input bytes read so far */ + z_off_t total_in; /* total number of input bytes read so far */ - Bytef *next_out; /* next output byte should be put there */ + Bytef *next_out; /* next output byte will go here */ uInt avail_out; /* remaining free space at next_out */ - z_off_t total_out; /* total nb of bytes output so far */ + z_off_t total_out; /* total number of bytes output so far */ z_const char *msg; /* last error message, NULL if no error */ struct internal_state FAR *state; /* not visible by applications */ @@ -96,8 +101,9 @@ typedef struct z_stream_s { free_func zfree; /* used to free the internal state */ voidpf opaque; /* private data object passed to zalloc and zfree */ - int data_type; /* best guess about the data type: binary or text */ - uLong adler; /* adler32 value of the uncompressed data */ + int data_type; /* best guess about the data type: binary or text + for deflate, or the decoding state for inflate */ + uLong adler; /* Adler-32 or CRC-32 value of the uncompressed data */ uLong reserved; /* reserved for future use */ } z_stream; @@ -127,45 +133,47 @@ typedef struct gz_header_s { typedef gz_header FAR *gz_headerp; /* - The application must update next_in and avail_in when avail_in has - dropped to zero. It must update next_out and avail_out when avail_out - has dropped to zero. The application must initialize zalloc, zfree and - opaque before calling the init function. All other fields are set by the - compression library and must not be updated by the application. - - The opaque value provided by the application will be passed as the first - parameter for calls of zalloc and zfree. This can be useful for custom - memory management. The compression library attaches no meaning to the + The application must update next_in and avail_in when avail_in has dropped + to zero. It must update next_out and avail_out when avail_out has dropped + to zero. The application must initialize zalloc, zfree and opaque before + calling the init function. All other fields are set by the compression + library and must not be updated by the application. + + The opaque value provided by the application will be passed as the first + parameter for calls of zalloc and zfree. This can be useful for custom + memory management. The compression library attaches no meaning to the opaque value. - zalloc must return Z_NULL if there is not enough memory for the object. + zalloc must return Z_NULL if there is not enough memory for the object. If zlib is used in a multi-threaded application, zalloc and zfree must be - thread safe. - - On 16-bit systems, the functions zalloc and zfree must be able to allocate - exactly 65536 bytes, but will not be required to allocate more than this - if the symbol MAXSEG_64K is defined (see zconf.h). WARNING: On MSDOS, - pointers returned by zalloc for objects of exactly 65536 bytes *must* - have their offset normalized to zero. The default allocation function - provided by this library ensures this (see zutil.c). To reduce memory - requirements and avoid any allocation of 64K objects, at the expense of - compression ratio, compile the library with -DMAX_WBITS=14 (see zconf.h). - - The fields total_in and total_out can be used for statistics or - progress reports. After compression, total_in holds the total size of - the uncompressed data and may be saved for use in the decompressor - (particularly if the decompressor wants to decompress everything in - a single step). + thread safe. In that case, zlib is thread-safe. When zalloc and zfree are + Z_NULL on entry to the initialization function, they are set to internal + routines that use the standard library functions malloc() and free(). + + On 16-bit systems, the functions zalloc and zfree must be able to allocate + exactly 65536 bytes, but will not be required to allocate more than this if + the symbol MAXSEG_64K is defined (see zconf.h). WARNING: On MSDOS, pointers + returned by zalloc for objects of exactly 65536 bytes *must* have their + offset normalized to zero. The default allocation function provided by this + library ensures this (see zutil.c). To reduce memory requirements and avoid + any allocation of 64K objects, at the expense of compression ratio, compile + the library with -DMAX_WBITS=14 (see zconf.h). + + The fields total_in and total_out can be used for statistics or progress + reports. After compression, total_in holds the total size of the + uncompressed data and may be saved for use by the decompressor (particularly + if the decompressor wants to decompress everything in a single step). */ /* constants */ #define Z_NO_FLUSH 0 -#define Z_PARTIAL_FLUSH 1 /* will be removed, use Z_SYNC_FLUSH instead */ +#define Z_PARTIAL_FLUSH 1 #define Z_SYNC_FLUSH 2 #define Z_FULL_FLUSH 3 #define Z_FINISH 4 #define Z_BLOCK 5 +#define Z_TREES 6 /* Allowed flush values; see deflate() and inflate() below for details */ #define Z_OK 0 @@ -177,8 +185,8 @@ typedef gz_header FAR *gz_headerp; #define Z_MEM_ERROR (-4) #define Z_BUF_ERROR (-5) #define Z_VERSION_ERROR (-6) -/* Return codes for the compression/decompression functions. Negative - * values are errors, positive values are used for special but normal events. +/* Return codes for the compression/decompression functions. Negative values + * are errors, positive values are used for special but normal events. */ #define Z_NO_COMPRESSION 0 @@ -198,7 +206,7 @@ typedef gz_header FAR *gz_headerp; #define Z_TEXT 1 #define Z_ASCII Z_TEXT /* for compatibility with 1.2.2 and earlier */ #define Z_UNKNOWN 2 -/* Possible values of the data_type field (though see inflate()) */ +/* Possible values of the data_type field for deflate() */ #define Z_DEFLATED 8 /* The deflate compression method (the only one supported in this version) */ @@ -208,67 +216,70 @@ typedef gz_header FAR *gz_headerp; #define zlib_version zlibVersion() /* for compatibility with versions < 1.0.2 */ + /* basic functions */ ZEXTERN const char * ZEXPORT zlibVersion OF((void)); /* The application can compare zlibVersion and ZLIB_VERSION for consistency. - If the first character differs, the library code actually used is - not compatible with the zlib.h header file used by the application. - This check is automatically made by deflateInit and inflateInit. + If the first character differs, the library code actually used is not + compatible with the zlib.h header file used by the application. This check + is automatically made by deflateInit and inflateInit. */ /* ZEXTERN int ZEXPORT deflateInit OF((z_streamp strm, int level)); - Initializes the internal stream state for compression. The fields - zalloc, zfree and opaque must be initialized before by the caller. - If zalloc and zfree are set to Z_NULL, deflateInit updates them to - use default allocation functions. + Initializes the internal stream state for compression. The fields + zalloc, zfree and opaque must be initialized before by the caller. If + zalloc and zfree are set to Z_NULL, deflateInit updates them to use default + allocation functions. The compression level must be Z_DEFAULT_COMPRESSION, or between 0 and 9: - 1 gives best speed, 9 gives best compression, 0 gives no compression at - all (the input data is simply copied a block at a time). - Z_DEFAULT_COMPRESSION requests a default compromise between speed and - compression (currently equivalent to level 6). + 1 gives best speed, 9 gives best compression, 0 gives no compression at all + (the input data is simply copied a block at a time). Z_DEFAULT_COMPRESSION + requests a default compromise between speed and compression (currently + equivalent to level 6). - deflateInit returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_STREAM_ERROR if level is not a valid compression level, + deflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough + memory, Z_STREAM_ERROR if level is not a valid compression level, or Z_VERSION_ERROR if the zlib library version (zlib_version) is incompatible - with the version assumed by the caller (ZLIB_VERSION). - msg is set to null if there is no error message. deflateInit does not - perform any compression: this will be done by deflate(). + with the version assumed by the caller (ZLIB_VERSION). msg is set to null + if there is no error message. deflateInit does not perform any compression: + this will be done by deflate(). */ ZEXTERN int ZEXPORT deflate OF((z_streamp strm, int flush)); /* deflate compresses as much data as possible, and stops when the input - buffer becomes empty or the output buffer becomes full. It may introduce some - output latency (reading input without producing any output) except when + buffer becomes empty or the output buffer becomes full. It may introduce + some output latency (reading input without producing any output) except when forced to flush. - The detailed semantics are as follows. deflate performs one or both of the + The detailed semantics are as follows. deflate performs one or both of the following actions: - Compress more input starting at next_in and update next_in and avail_in - accordingly. If not all input can be processed (because there is not + accordingly. If not all input can be processed (because there is not enough room in the output buffer), next_in and avail_in are updated and processing will resume at this point for the next call of deflate(). - - Provide more output starting at next_out and update next_out and avail_out - accordingly. This action is forced if the parameter flush is non zero. + - Generate more output starting at next_out and update next_out and avail_out + accordingly. This action is forced if the parameter flush is non zero. Forcing flush frequently degrades the compression ratio, so this parameter - should be set only when necessary (in interactive applications). - Some output may be provided even if flush is not set. - - Before the call of deflate(), the application should ensure that at least - one of the actions is possible, by providing more input and/or consuming - more output, and updating avail_in or avail_out accordingly; avail_out - should never be zero before the call. The application can consume the - compressed output when it wants, for example when the output buffer is full - (avail_out == 0), or after each call of deflate(). If deflate returns Z_OK - and with zero avail_out, it must be called again after making room in the - output buffer because there might be more output pending. + should be set only when necessary. Some output may be provided even if + flush is zero. + + Before the call of deflate(), the application should ensure that at least + one of the actions is possible, by providing more input and/or consuming more + output, and updating avail_in or avail_out accordingly; avail_out should + never be zero before the call. The application can consume the compressed + output when it wants, for example when the output buffer is full (avail_out + == 0), or after each call of deflate(). If deflate returns Z_OK and with + zero avail_out, it must be called again after making room in the output + buffer because there might be more output pending. See deflatePending(), + which can be used if desired to determine whether or not there is more ouput + in that case. Normally the parameter flush is set to Z_NO_FLUSH, which allows deflate to decide how much data to accumulate before producing output, in order to @@ -276,66 +287,91 @@ ZEXTERN int ZEXPORT deflate OF((z_streamp strm, int flush)); If the parameter flush is set to Z_SYNC_FLUSH, all pending output is flushed to the output buffer and the output is aligned on a byte boundary, so - that the decompressor can get all input data available so far. (In particular - avail_in is zero after the call if enough output space has been provided - before the call.) Flushing may degrade compression for some compression - algorithms and so it should be used only when necessary. + that the decompressor can get all input data available so far. (In + particular avail_in is zero after the call if enough output space has been + provided before the call.) Flushing may degrade compression for some + compression algorithms and so it should be used only when necessary. This + completes the current deflate block and follows it with an empty stored block + that is three bits plus filler bits to the next byte, followed by four bytes + (00 00 ff ff). + + If flush is set to Z_PARTIAL_FLUSH, all pending output is flushed to the + output buffer, but the output is not aligned to a byte boundary. All of the + input data so far will be available to the decompressor, as for Z_SYNC_FLUSH. + This completes the current deflate block and follows it with an empty fixed + codes block that is 10 bits long. This assures that enough bytes are output + in order for the decompressor to finish the block before the empty fixed + codes block. + + If flush is set to Z_BLOCK, a deflate block is completed and emitted, as + for Z_SYNC_FLUSH, but the output is not aligned on a byte boundary, and up to + seven bits of the current block are held to be written as the next byte after + the next deflate block is completed. In this case, the decompressor may not + be provided enough bits at this point in order to complete decompression of + the data provided so far to the compressor. It may need to wait for the next + block to be emitted. This is for advanced applications that need to control + the emission of deflate blocks. If flush is set to Z_FULL_FLUSH, all output is flushed as with Z_SYNC_FLUSH, and the compression state is reset so that decompression can restart from this point if previous compressed data has been damaged or if - random access is desired. Using Z_FULL_FLUSH too often can seriously degrade + random access is desired. Using Z_FULL_FLUSH too often can seriously degrade compression. If deflate returns with avail_out == 0, this function must be called again with the same value of the flush parameter and more output space (updated avail_out), until the flush is complete (deflate returns with non-zero - avail_out). In the case of a Z_FULL_FLUSH or Z_SYNC_FLUSH, make sure that + avail_out). In the case of a Z_FULL_FLUSH or Z_SYNC_FLUSH, make sure that avail_out is greater than six to avoid repeated flush markers due to avail_out == 0 on return. If the parameter flush is set to Z_FINISH, pending input is processed, - pending output is flushed and deflate returns with Z_STREAM_END if there - was enough output space; if deflate returns with Z_OK, this function must be - called again with Z_FINISH and more output space (updated avail_out) but no - more input data, until it returns with Z_STREAM_END or an error. After - deflate has returned Z_STREAM_END, the only possible operations on the - stream are deflateReset or deflateEnd. - - Z_FINISH can be used immediately after deflateInit if all the compression - is to be done in a single step. In this case, avail_out must be at least - the value returned by deflateBound (see below). If deflate does not return - Z_STREAM_END, then it must be called again as described above. - - deflate() sets strm->adler to the adler32 checksum of all input read - so far (that is, total_in bytes). + pending output is flushed and deflate returns with Z_STREAM_END if there was + enough output space. If deflate returns with Z_OK or Z_BUF_ERROR, this + function must be called again with Z_FINISH and more output space (updated + avail_out) but no more input data, until it returns with Z_STREAM_END or an + error. After deflate has returned Z_STREAM_END, the only possible operations + on the stream are deflateReset or deflateEnd. + + Z_FINISH can be used in the first deflate call after deflateInit if all the + compression is to be done in a single step. In order to complete in one + call, avail_out must be at least the value returned by deflateBound (see + below). Then deflate is guaranteed to return Z_STREAM_END. If not enough + output space is provided, deflate will not return Z_STREAM_END, and it must + be called again as described above. + + deflate() sets strm->adler to the Adler-32 checksum of all input read + so far (that is, total_in bytes). If a gzip stream is being generated, then + strm->adler will be the CRC-32 checksum of the input read so far. (See + deflateInit2 below.) deflate() may update strm->data_type if it can make a good guess about - the input data type (Z_BINARY or Z_TEXT). In doubt, the data is considered - binary. This field is only for information purposes and does not affect - the compression algorithm in any manner. + the input data type (Z_BINARY or Z_TEXT). If in doubt, the data is + considered binary. This field is only for information purposes and does not + affect the compression algorithm in any manner. deflate() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if all input has been consumed and all output has been produced (only when flush is set to Z_FINISH), Z_STREAM_ERROR if the stream state was inconsistent (for example - if next_in or next_out was NULL), Z_BUF_ERROR if no progress is possible - (for example avail_in or avail_out was zero). Note that Z_BUF_ERROR is not - fatal, and deflate() can be called again with more input and more output - space to continue compressing. + if next_in or next_out was Z_NULL or the state was inadvertently written over + by the application), or Z_BUF_ERROR if no progress is possible (for example + avail_in or avail_out was zero). Note that Z_BUF_ERROR is not fatal, and + deflate() can be called again with more input and more output space to + continue compressing. */ ZEXTERN int ZEXPORT deflateEnd OF((z_streamp strm)); /* All dynamically allocated data structures for this stream are freed. - This function discards any unprocessed input and does not flush any - pending output. + This function discards any unprocessed input and does not flush any pending + output. deflateEnd returns Z_OK if success, Z_STREAM_ERROR if the stream state was inconsistent, Z_DATA_ERROR if the stream was freed - prematurely (some input or output was discarded). In the error case, - msg may be set but then points to a static string (which must not be + prematurely (some input or output was discarded). In the error case, msg + may be set but then points to a static string (which must not be deallocated). */ @@ -343,134 +379,157 @@ ZEXTERN int ZEXPORT deflateEnd OF((z_streamp strm)); /* ZEXTERN int ZEXPORT inflateInit OF((z_streamp strm)); - Initializes the internal stream state for decompression. The fields + Initializes the internal stream state for decompression. The fields next_in, avail_in, zalloc, zfree and opaque must be initialized before by - the caller. If next_in is not Z_NULL and avail_in is large enough (the exact - value depends on the compression method), inflateInit determines the - compression method from the zlib header and allocates all data structures - accordingly; otherwise the allocation will be deferred to the first call of - inflate. If zalloc and zfree are set to Z_NULL, inflateInit updates them to - use default allocation functions. + the caller. In the current version of inflate, the provided input is not + read or consumed. The allocation of a sliding window will be deferred to + the first call of inflate (if the decompression does not complete on the + first call). If zalloc and zfree are set to Z_NULL, inflateInit updates + them to use default allocation functions. inflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_VERSION_ERROR if the zlib library version is incompatible with the - version assumed by the caller. msg is set to null if there is no error - message. inflateInit does not perform any decompression apart from reading - the zlib header if present: this will be done by inflate(). (So next_in and - avail_in may be modified, but next_out and avail_out are unchanged.) + version assumed by the caller, or Z_STREAM_ERROR if the parameters are + invalid, such as a null pointer to the structure. msg is set to null if + there is no error message. inflateInit does not perform any decompression. + Actual decompression will be done by inflate(). So next_in, and avail_in, + next_out, and avail_out are unused and unchanged. The current + implementation of inflateInit() does not process any header information -- + that is deferred until inflate() is called. */ ZEXTERN int ZEXPORT inflate OF((z_streamp strm, int flush)); /* inflate decompresses as much data as possible, and stops when the input - buffer becomes empty or the output buffer becomes full. It may introduce + buffer becomes empty or the output buffer becomes full. It may introduce some output latency (reading input without producing any output) except when forced to flush. - The detailed semantics are as follows. inflate performs one or both of the + The detailed semantics are as follows. inflate performs one or both of the following actions: - Decompress more input starting at next_in and update next_in and avail_in - accordingly. If not all input can be processed (because there is not - enough room in the output buffer), next_in is updated and processing - will resume at this point for the next call of inflate(). - - - Provide more output starting at next_out and update next_out and avail_out - accordingly. inflate() provides as much output as possible, until there - is no more input data or no more space in the output buffer (see below - about the flush parameter). - - Before the call of inflate(), the application should ensure that at least - one of the actions is possible, by providing more input and/or consuming - more output, and updating the next_* and avail_* values accordingly. - The application can consume the uncompressed output when it wants, for - example when the output buffer is full (avail_out == 0), or after each - call of inflate(). If inflate returns Z_OK and with zero avail_out, it - must be called again after making room in the output buffer because there - might be more output pending. - - 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 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. + accordingly. If not all input can be processed (because there is not + enough room in the output buffer), then next_in and avail_in are updated + accordingly, and processing will resume at this point for the next call of + inflate(). + + - Generate more output starting at next_out and update next_out and avail_out + accordingly. inflate() provides as much output as possible, until there is + no more input data or no more space in the output buffer (see below about + the flush parameter). + + Before the call of inflate(), the application should ensure that at least + one of the actions is possible, by providing more input and/or consuming more + output, and updating the next_* and avail_* values accordingly. If the + caller of inflate() does not provide both available input and available + output space, it is possible that there will be no progress made. The + application can consume the uncompressed output when it wants, for example + when the output buffer is full (avail_out == 0), or after each call of + inflate(). If inflate returns Z_OK and with zero avail_out, it must be + called again after making room in the output buffer because there might be + more output pending. + + The flush parameter of inflate() can be Z_NO_FLUSH, Z_SYNC_FLUSH, Z_FINISH, + Z_BLOCK, or Z_TREES. 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 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 - number of unused bits in the last byte taken from strm->next_in, plus 64 - if inflate() is currently decoding the last block in the deflate stream, - plus 128 if inflate() returned immediately after decoding an end-of-block - code or decoding the complete header up to just before the first byte of the - deflate stream. The end-of-block will not be indicated until all of the - uncompressed data from that block has been written to strm->next_out. The - number of unused bits may in general be greater than seven, except when - bit 7 of data_type is set, in which case the number of unused bits will be - less than eight. + To assist in this, on return inflate() always sets strm->data_type to the + number of unused bits in the last byte taken from strm->next_in, plus 64 if + inflate() is currently decoding the last block in the deflate stream, plus + 128 if inflate() returned immediately after decoding an end-of-block code or + decoding the complete header up to just before the first byte of the deflate + stream. The end-of-block will not be indicated until all of the uncompressed + data from that block has been written to strm->next_out. The number of + unused bits may in general be greater than seven, except when bit 7 of + data_type is set, in which case the number of unused bits will be less than + eight. data_type is set as noted here every time inflate() returns for all + flush options, and so can be used to determine the amount of currently + consumed input in bits. + + The Z_TREES option behaves as Z_BLOCK does, but it also returns when the + end of each deflate block header is reached, before any actual data in that + block is decoded. This allows the caller to determine the length of the + deflate block header for later use in random access within a deflate block. + 256 is added to the value of strm->data_type when inflate() returns + immediately after reaching the end of the deflate block header. inflate() should normally be called until it returns Z_STREAM_END or an - error. However if all decompression is to be performed in a single step - (a single call of inflate), the parameter flush should be set to - Z_FINISH. In this case all pending input is processed and all pending - output is flushed; avail_out must be large enough to hold all the - uncompressed data. (The size of the uncompressed data may have been saved - by the compressor for this purpose.) The next operation on this stream must - be inflateEnd to deallocate the decompression state. The use of Z_FINISH - is never required, but can be used to inform inflate that a faster approach - may be used for the single inflate() call. + error. However if all decompression is to be performed in a single step (a + single call of inflate), the parameter flush should be set to Z_FINISH. In + this case all pending input is processed and all pending output is flushed; + avail_out must be large enough to hold all of the uncompressed data for the + operation to complete. (The size of the uncompressed data may have been + saved by the compressor for this purpose.) The use of Z_FINISH is not + required to perform an inflation in one step. However it may be used to + inform inflate that a faster approach can be used for the single inflate() + call. Z_FINISH also informs inflate to not maintain a sliding window if the + stream completes, which reduces inflate's memory footprint. If the stream + does not complete, either because not all of the stream is provided or not + enough output space is provided, then a sliding window will be allocated and + inflate() can be called again to continue the operation as if Z_NO_FLUSH had + been used. In this implementation, inflate() always flushes as much output as possible to the output buffer, and always uses the faster approach on the - first call. So the only effect of the flush parameter in this implementation - is on the return value of inflate(), as noted below, or when it returns early - because Z_BLOCK is used. + first call. So the effects of the flush parameter in this implementation are + on the return value of inflate() as noted below, when inflate() returns early + when Z_BLOCK or Z_TREES is used, and when inflate() avoids the allocation of + memory for a sliding window when Z_FINISH is used. If a preset dictionary is needed after this call (see inflateSetDictionary - below), inflate sets strm->adler to the adler32 checksum of the dictionary + below), inflate sets strm->adler to the Adler-32 checksum of the dictionary chosen by the compressor and returns Z_NEED_DICT; otherwise it sets - strm->adler to the adler32 checksum of all output produced so far (that is, + strm->adler to the Adler-32 checksum of all output produced so far (that is, total_out bytes) and returns Z_OK, Z_STREAM_END or an error code as described - below. At the end of the stream, inflate() checks that its computed adler32 + below. At the end of the stream, inflate() checks that its computed Adler-32 checksum is equal to that saved by the compressor and returns Z_STREAM_END only if the checksum is correct. - inflate() will decompress and check either zlib-wrapped or gzip-wrapped - deflate data. The header type is detected automatically. Any information - contained in the gzip header is not retained, so applications that need that - information should instead use raw inflate, see inflateInit2() below, or - inflateBack() and perform their own processing of the gzip header and - trailer. + inflate() can decompress and check either zlib-wrapped or gzip-wrapped + deflate data. The header type is detected automatically, if requested when + initializing with inflateInit2(). Any information contained in the gzip + header is not retained unless inflateGetHeader() is used. When processing + gzip-wrapped deflate data, strm->adler32 is set to the CRC-32 of the output + produced so far. The CRC-32 is checked against the gzip trailer, as is the + uncompressed length, modulo 2^32. inflate() returns Z_OK if some progress has been made (more input processed or more output produced), Z_STREAM_END if the end of the compressed data has been reached and all uncompressed output has been produced, Z_NEED_DICT if a preset dictionary is needed at this point, Z_DATA_ERROR if the input data was corrupted (input stream not conforming to the zlib format or incorrect check - value), Z_STREAM_ERROR if the stream structure was inconsistent (for example - if next_in or next_out was NULL), Z_MEM_ERROR if there was not enough memory, - Z_BUF_ERROR if no progress is possible or if there was not enough room in the - output buffer when Z_FINISH is used. Note that Z_BUF_ERROR is not fatal, and + value, in which case strm->msg points to a string with a more specific + error), Z_STREAM_ERROR if the stream structure was inconsistent (for example + next_in or next_out was Z_NULL, or the state was inadvertently written over + by the application), Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR + if no progress was possible or if there was not enough room in the output + buffer when Z_FINISH is used. Note that Z_BUF_ERROR is not fatal, and inflate() can be called again with more input and more output space to - continue decompressing. If Z_DATA_ERROR is returned, the application may then - call inflateSync() to look for a good compression block if a partial recovery - of the data is desired. + continue decompressing. If Z_DATA_ERROR is returned, the application may + then call inflateSync() to look for a good compression block if a partial + recovery of the data is to be attempted. */ ZEXTERN int ZEXPORT inflateEnd OF((z_streamp strm)); /* All dynamically allocated data structures for this stream are freed. - This function discards any unprocessed input and does not flush any - pending output. + This function discards any unprocessed input and does not flush any pending + output. - inflateEnd returns Z_OK if success, Z_STREAM_ERROR if the stream state - was inconsistent. In the error case, msg may be set but then points to a - static string (which must not be deallocated). + inflateEnd returns Z_OK if success, or Z_STREAM_ERROR if the stream state + was inconsistent. */ + /* Advanced functions */ /* @@ -485,55 +544,70 @@ ZEXTERN int ZEXPORT deflateInit2 OF((z_streamp strm, int memLevel, int strategy)); - This is another version of deflateInit with more compression options. The - fields next_in, zalloc, zfree and opaque must be initialized before by - the caller. + This is another version of deflateInit with more compression options. The + fields next_in, zalloc, zfree and opaque must be initialized before by the + caller. - The method parameter is the compression method. It must be Z_DEFLATED in + The method parameter is the compression method. It must be Z_DEFLATED in this version of the library. The windowBits parameter is the base two logarithm of the window size - (the size of the history buffer). It should be in the range 8..15 for this - version of the library. Larger values of this parameter result in better - compression at the expense of memory usage. The default value is 15 if + (the size of the history buffer). It should be in the range 8..15 for this + version of the library. Larger values of this parameter result in better + compression at the expense of memory usage. The default value is 15 if deflateInit is used instead. - windowBits can also be -8..-15 for raw deflate. In this case, -windowBits - determines the window size. deflate() will then generate raw deflate data - with no zlib header or trailer, and will not compute an adler32 check value. + For the current implementation of deflate(), a windowBits value of 8 (a + window size of 256 bytes) is not supported. As a result, a request for 8 + will result in 9 (a 512-byte window). In that case, providing 8 to + inflateInit2() will result in an error when the zlib header with 9 is + checked against the initialization of inflate(). The remedy is to not use 8 + with deflateInit2() with this initialization, or at least in that case use 9 + with inflateInit2(). - windowBits can also be greater than 15 for optional gzip encoding. Add + windowBits can also be -8..-15 for raw deflate. In this case, -windowBits + determines the window size. deflate() will then generate raw deflate data + with no zlib header or trailer, and will not compute a check value. + + windowBits can also be greater than 15 for optional gzip encoding. Add 16 to windowBits to write a simple gzip header and trailer around the - compressed data instead of a zlib wrapper. The gzip header will have no - file name, no extra data, no comment, no modification time (set to zero), - no header crc, and the operating system will be set to 255 (unknown). If a - gzip stream is being written, strm->adler is a crc32 instead of an adler32. + compressed data instead of a zlib wrapper. The gzip header will have no + file name, no extra data, no comment, no modification time (set to zero), no + header crc, and the operating system will be set to the appropriate value, + if the operating system was determined at compile time. If a gzip stream is + being written, strm->adler is a CRC-32 instead of an Adler-32. + + For raw deflate or gzip encoding, a request for a 256-byte window is + rejected as invalid, since only the zlib header provides a means of + transmitting the window size to the decompressor. The memLevel parameter specifies how much memory should be allocated - for the internal compression state. memLevel=1 uses minimum memory but - is slow and reduces compression ratio; memLevel=9 uses maximum memory - for optimal speed. The default value is 8. See zconf.h for total memory - usage as a function of windowBits and memLevel. + for the internal compression state. memLevel=1 uses minimum memory but is + slow and reduces compression ratio; memLevel=9 uses maximum memory for + optimal speed. The default value is 8. See zconf.h for total memory usage + as a function of windowBits and memLevel. - The strategy parameter is used to tune the compression algorithm. Use the + The strategy parameter is used to tune the compression algorithm. Use the value Z_DEFAULT_STRATEGY for normal data, Z_FILTERED for data produced by a filter (or predictor), Z_HUFFMAN_ONLY to force Huffman encoding only (no string match), or Z_RLE to limit match distances to one (run-length - encoding). Filtered data consists mostly of small values with a somewhat - random distribution. In this case, the compression algorithm is tuned to - compress them better. The effect of Z_FILTERED is to force more Huffman + encoding). Filtered data consists mostly of small values with a somewhat + random distribution. In this case, the compression algorithm is tuned to + compress them better. The effect of Z_FILTERED is to force more Huffman coding and less string matching; it is somewhat intermediate between - 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. 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 - method). msg is set to null if there is no error message. deflateInit2 does - not perform any compression: this will be done by deflate(). + Z_DEFAULT_STRATEGY 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. + 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 any parameter is invalid (such as an invalid + method), or Z_VERSION_ERROR if the zlib library version (zlib_version) is + incompatible with the version assumed by the caller (ZLIB_VERSION). msg is + set to null if there is no error message. deflateInit2 does not perform any + compression: this will be done by deflate(). */ ZEXTERN int ZEXPORT deflateSetDictionary OF((z_streamp strm, @@ -541,38 +615,65 @@ ZEXTERN int ZEXPORT deflateSetDictionary OF((z_streamp strm, uInt dictLength)); /* Initializes the compression dictionary from the given byte sequence - without producing any compressed output. This function must be called - immediately after deflateInit, deflateInit2 or deflateReset, before any - call of deflate. The compressor and decompressor must use exactly the same - dictionary (see inflateSetDictionary). + without producing any compressed output. When using the zlib format, this + function must be called immediately after deflateInit, deflateInit2 or + deflateReset, and before any call of deflate. When doing raw deflate, this + function must be called either before any call of deflate, or immediately + after the completion of a deflate block, i.e. after all input has been + consumed and all output has been delivered when using any of the flush + options Z_BLOCK, Z_PARTIAL_FLUSH, Z_SYNC_FLUSH, or Z_FULL_FLUSH. The + compressor and decompressor must use exactly the same dictionary (see + inflateSetDictionary). The dictionary should consist of strings (byte sequences) that are likely to be encountered later in the data to be compressed, with the most commonly - used strings preferably put towards the end of the dictionary. Using a + used strings preferably put towards the end of the dictionary. Using a dictionary is most useful when the data to be compressed is short and can be predicted with good accuracy; the data can then be compressed better than with the default empty dictionary. Depending on the size of the compression data structures selected by deflateInit or deflateInit2, a part of the dictionary may in effect be - discarded, for example if the dictionary is larger than the window size in - deflate or deflate2. Thus the strings most likely to be useful should be - put at the end of the dictionary, not at the front. In addition, the - current implementation of deflate will use at most the window size minus - 262 bytes of the provided dictionary. + discarded, for example if the dictionary is larger than the window size + provided in deflateInit or deflateInit2. Thus the strings most likely to be + useful should be put at the end of the dictionary, not at the front. In + addition, the current implementation of deflate will use at most the window + size minus 262 bytes of the provided dictionary. - Upon return of this function, strm->adler is set to the adler32 value + Upon return of this function, strm->adler is set to the Adler-32 value of the dictionary; the decompressor may later use this value to determine - which dictionary has been used by the compressor. (The adler32 value + which dictionary has been used by the compressor. (The Adler-32 value applies to the whole dictionary even if only a subset of the dictionary is actually used by the compressor.) If a raw deflate was requested, then the - adler32 value is not computed and strm->adler is not set. + Adler-32 value is not computed and strm->adler is not set. deflateSetDictionary returns Z_OK if success, or Z_STREAM_ERROR if a - parameter is invalid (such as NULL dictionary) or the stream state is + parameter is invalid (e.g. dictionary being Z_NULL) or the stream state is inconsistent (for example if deflate has already been called for this stream - or if the compression method is bsort). deflateSetDictionary does not - perform any compression: this will be done by deflate(). + or if not at a block boundary for raw deflate). deflateSetDictionary does + not perform any compression: this will be done by deflate(). +*/ + +ZEXTERN int ZEXPORT deflateGetDictionary OF((z_streamp strm, + Bytef *dictionary, + uInt *dictLength)); +/* + Returns the sliding dictionary being maintained by deflate. dictLength is + set to the number of bytes in the dictionary, and that many bytes are copied + to dictionary. dictionary must have enough space, where 32768 bytes is + always enough. If deflateGetDictionary() is called with dictionary equal to + Z_NULL, then only the dictionary length is returned, and nothing is copied. + Similary, if dictLength is Z_NULL, then it is not set. + + deflateGetDictionary() may return a length less than the window size, even + when more than the window size in input has been provided. It may return up + to 258 bytes less in that case, due to how zlib's implementation of deflate + manages the sliding window and lookahead for matches, where matches can be + up to 258 bytes long. If the application needs the last window-size bytes of + input, then that would need to be saved by the application outside of zlib. + + deflateGetDictionary returns Z_OK on success, or Z_STREAM_ERROR if the + stream state is inconsistent. */ ZEXTERN int ZEXPORT deflateCopy OF((z_streamp dest, @@ -582,26 +683,26 @@ ZEXTERN int ZEXPORT deflateCopy OF((z_streamp dest, This function can be useful when several compression strategies will be tried, for example when there are several ways of pre-processing the input - data with a filter. The streams that will be discarded should then be freed + data with a filter. The streams that will be discarded should then be freed by calling deflateEnd. Note that deflateCopy duplicates the internal - compression state which can be quite large, so this strategy is slow and - can consume lots of memory. + compression state which can be quite large, so this strategy is slow and can + consume lots of memory. deflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if the source stream state was inconsistent - (such as zalloc being NULL). msg is left unchanged in both source and + (such as zalloc being Z_NULL). msg is left unchanged in both source and destination. */ ZEXTERN int ZEXPORT deflateReset OF((z_streamp strm)); /* - This function is equivalent to deflateEnd followed by deflateInit, - but does not free and reallocate all the internal compression state. - The stream will keep the same compression level and any other attributes - that may have been set by deflateInit2. + This function is equivalent to deflateEnd followed by deflateInit, but + does not free and reallocate the internal compression state. The stream + will leave the compression level and any other attributes that may have been + set unchanged. - deflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent (such as zalloc or state being NULL). + deflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent (such as zalloc or state being Z_NULL). */ ZEXTERN int ZEXPORT deflateParams OF((z_streamp strm, @@ -609,20 +710,36 @@ ZEXTERN int ZEXPORT deflateParams OF((z_streamp strm, int strategy)); /* Dynamically update the compression level and compression strategy. The - interpretation of level and strategy is as in deflateInit2. This can be + interpretation of level and strategy is as in deflateInit2(). This can be used to switch between compression and straight copy of the input data, or - to switch to a different kind of input data requiring a different - strategy. If the compression level is changed, the input available so far - is compressed with the old level (and may be flushed); the new level will - take effect only at the next call of deflate(). - - Before the call of deflateParams, the stream state must be set as for - a call of deflate(), since the currently available input may have to - be compressed and flushed. In particular, strm->avail_out must be non-zero. - - deflateParams returns Z_OK if success, Z_STREAM_ERROR if the source - stream state was inconsistent or if a parameter was invalid, Z_BUF_ERROR - if strm->avail_out was zero. + to switch to a different kind of input data requiring a different strategy. + If the compression approach (which is a function of the level) or the + strategy is changed, and if any input has been consumed in a previous + deflate() call, then the input available so far is compressed with the old + level and strategy using deflate(strm, Z_BLOCK). There are three approaches + for the compression levels 0, 1..3, and 4..9 respectively. The new level + and strategy will take effect at the next call of deflate(). + + If a deflate(strm, Z_BLOCK) is performed by deflateParams(), and it does + not have enough output space to complete, then the parameter change will not + take effect. In this case, deflateParams() can be called again with the + same parameters and more output space to try again. + + In order to assure a change in the parameters on the first try, the + deflate stream should be flushed using deflate() with Z_BLOCK or other flush + request until strm.avail_out is not zero, before calling deflateParams(). + Then no more input data should be provided before the deflateParams() call. + If this is done, the old level and strategy will be applied to the data + compressed before deflateParams(), and the new level and strategy will be + applied to the the data compressed after deflateParams(). + + deflateParams returns Z_OK on success, Z_STREAM_ERROR if the source stream + state was inconsistent or if a parameter was invalid, or Z_BUF_ERROR if + there was not enough output space to complete the compression of the + available input data before a change in the strategy or approach. Note that + in the case of a Z_BUF_ERROR, the parameters are not changed. A return + value of Z_BUF_ERROR is not fatal, in which case deflateParams() can be + retried with more output space. */ ZEXTERN int ZEXPORT deflateTune OF((z_streamp strm, @@ -646,31 +763,53 @@ ZEXTERN uLong ZEXPORT deflateBound OF((z_streamp strm, uLong sourceLen)); /* deflateBound() returns an upper bound on the compressed size after - deflation of sourceLen bytes. It must be called after deflateInit() - or deflateInit2(). This would be used to allocate an output buffer - for deflation in a single pass, and so would be called before deflate(). + deflation of sourceLen bytes. It must be called after deflateInit() or + deflateInit2(), and after deflateSetHeader(), if used. This would be used + to allocate an output buffer for deflation in a single pass, and so would be + called before deflate(). If that first deflate() call is provided the + sourceLen input bytes, an output buffer allocated to the size returned by + deflateBound(), and the flush value Z_FINISH, then deflate() is guaranteed + to return Z_STREAM_END. Note that it is possible for the compressed size to + be larger than the value returned by deflateBound() if flush options other + than Z_FINISH or Z_NO_FLUSH are used. */ +ZEXTERN int ZEXPORT deflatePending OF((z_streamp strm, + unsigned *pending, + int *bits)); +/* + deflatePending() returns the number of bytes and bits of output that have + been generated, but not yet provided in the available output. The bytes not + provided would be due to the available output space having being consumed. + The number of bits of output not provided are between 0 and 7, where they + await more bits to join them in order to fill out a full byte. If pending + or bits are Z_NULL, then those values are not set. + + deflatePending returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent. + */ + ZEXTERN int ZEXPORT deflatePrime OF((z_streamp strm, int bits, int value)); /* deflatePrime() inserts bits in the deflate output stream. The intent - is that this function is used to start off the deflate output with the - bits leftover from a previous deflate stream when appending to it. As such, - this function can only be used for raw deflate, and must be used before the - first deflate() call after a deflateInit2() or deflateReset(). bits must be - less than or equal to 16, and that many of the least significant bits of - value will be inserted in the output. - - deflatePrime returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent. + is that this function is used to start off the deflate output with the bits + leftover from a previous deflate stream when appending to it. As such, this + function can only be used for raw deflate, and must be used before the first + deflate() call after a deflateInit2() or deflateReset(). bits must be less + than or equal to 16, and that many of the least significant bits of value + will be inserted in the output. + + deflatePrime returns Z_OK if success, Z_BUF_ERROR if there was not enough + room in the internal buffer to insert the bits, or Z_STREAM_ERROR if the + source stream state was inconsistent. */ ZEXTERN int ZEXPORT deflateSetHeader OF((z_streamp strm, gz_headerp head)); /* - deflateSetHeader() provides gzip header information for when a gzip + deflateSetHeader() provides gzip header information for when a gzip stream is requested by deflateInit2(). deflateSetHeader() may be called after deflateInit2() or deflateReset() and before the first call of deflate(). The text, time, os, extra field, name, and comment information @@ -683,11 +822,11 @@ ZEXTERN int ZEXPORT deflateSetHeader OF((z_streamp strm, 1.3.x) do not support header crc's, and will report that it is a "multi-part gzip file" and give up. - If deflateSetHeader is not used, the default gzip header has text false, + If deflateSetHeader is not used, the default gzip header has text false, the time set to zero, and os set to 255, with no extra, name, or comment fields. The gzip header is returned to the default state by deflateReset(). - deflateSetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source + deflateSetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source stream state was inconsistent. */ @@ -695,43 +834,53 @@ ZEXTERN int ZEXPORT deflateSetHeader OF((z_streamp strm, ZEXTERN int ZEXPORT inflateInit2 OF((z_streamp strm, int windowBits)); - This is another version of inflateInit with an extra parameter. The + This is another version of inflateInit with an extra parameter. The fields next_in, avail_in, zalloc, zfree and opaque must be initialized before by the caller. The windowBits parameter is the base two logarithm of the maximum window size (the size of the history buffer). It should be in the range 8..15 for - this version of the library. The default value is 15 if inflateInit is used - instead. windowBits must be greater than or equal to the windowBits value + this version of the library. The default value is 15 if inflateInit is used + instead. windowBits must be greater than or equal to the windowBits value provided to deflateInit2() while compressing, or it must be equal to 15 if - deflateInit2() was not used. If a compressed stream with a larger window + deflateInit2() was not used. If a compressed stream with a larger window size is given as input, inflate() will return with the error code Z_DATA_ERROR instead of trying to allocate a larger window. - windowBits can also be -8..-15 for raw inflate. In this case, -windowBits - determines the window size. inflate() will then process raw deflate data, + windowBits can also be zero to request that inflate use the window size in + the zlib header of the compressed stream. + + windowBits can also be -8..-15 for raw inflate. In this case, -windowBits + determines the window size. inflate() will then process raw deflate data, not looking for a zlib or gzip header, not generating a check value, and not - looking for any check values for comparison at the end of the stream. This + looking for any check values for comparison at the end of the stream. This is for use with other formats that use the deflate compressed data format - such as zip. Those formats provide their own check values. If a custom + such as zip. Those formats provide their own check values. If a custom format is developed using the raw deflate format for compressed data, it is - recommended that a check value such as an adler32 or a crc32 be applied to + recommended that a check value such as an Adler-32 or a CRC-32 be applied to the uncompressed data as is done in the zlib, gzip, and zip formats. For - most applications, the zlib format should be used as is. Note that comments + most applications, the zlib format should be used as is. Note that comments above on the use in deflateInit2() applies to the magnitude of windowBits. - windowBits can also be greater than 15 for optional gzip decoding. Add + windowBits can also be greater than 15 for optional gzip decoding. Add 32 to windowBits to enable zlib and gzip decoding with automatic header detection, or add 16 to decode only the gzip format (the zlib format will - return a Z_DATA_ERROR). If a gzip stream is being decoded, strm->adler is - a crc32 instead of an adler32. + return a Z_DATA_ERROR). If a gzip stream is being decoded, strm->adler is a + CRC-32 instead of an Adler-32. Unlike the gunzip utility and gzread() (see + below), inflate() will not automatically decode concatenated gzip streams. + inflate() will return Z_STREAM_END at the end of the gzip stream. The state + would need to be reset to continue decoding a subsequent gzip stream. inflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_STREAM_ERROR if a parameter is invalid (such as a null strm). msg - is set to null if there is no error message. inflateInit2 does not perform - any decompression apart from reading the zlib header if present: this will - be done by inflate(). (So next_in and avail_in may be modified, but next_out - and avail_out are unchanged.) + memory, Z_VERSION_ERROR if the zlib library version is incompatible with the + version assumed by the caller, or Z_STREAM_ERROR if the parameters are + invalid, such as a null pointer to the structure. msg is set to null if + there is no error message. inflateInit2 does not perform any decompression + apart from possibly reading the zlib header if present: actual decompression + will be done by inflate(). (So next_in and avail_in may be modified, but + next_out and avail_out are unused and unchanged.) The current implementation + of inflateInit2() does not process any header information -- that is + deferred until inflate() is called. */ ZEXTERN int ZEXPORT inflateSetDictionary OF((z_streamp strm, @@ -739,36 +888,56 @@ ZEXTERN int ZEXPORT inflateSetDictionary OF((z_streamp strm, uInt dictLength)); /* Initializes the decompression dictionary from the given uncompressed byte - sequence. This function must be called immediately after a call of inflate, - if that call returned Z_NEED_DICT. The dictionary chosen by the compressor - can be determined from the adler32 value returned by that call of inflate. + sequence. This function must be called immediately after a call of inflate, + if that call returned Z_NEED_DICT. The dictionary chosen by the compressor + can be determined from the Adler-32 value returned by that call of inflate. The compressor and decompressor must use exactly the same dictionary (see - deflateSetDictionary). For raw inflate, this function can be called - immediately after inflateInit2() or inflateReset() and before any call of - inflate() to set the dictionary. The application must insure that the - dictionary that was used for compression is provided. + deflateSetDictionary). For raw inflate, this function can be called at any + time to set the dictionary. If the provided dictionary is smaller than the + window and there is already data in the window, then the provided dictionary + will amend what's there. The application must insure that the dictionary + that was used for compression is provided. inflateSetDictionary returns Z_OK if success, Z_STREAM_ERROR if a - parameter is invalid (such as NULL dictionary) or the stream state is + parameter is invalid (e.g. dictionary being Z_NULL) or the stream state is inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the - expected one (incorrect adler32 value). inflateSetDictionary does not + expected one (incorrect Adler-32 value). inflateSetDictionary does not perform any decompression: this will be done by subsequent calls of inflate(). */ -ZEXTERN int ZEXPORT inflateSync OF((z_streamp strm)); +ZEXTERN int ZEXPORT inflateGetDictionary OF((z_streamp strm, + Bytef *dictionary, + uInt *dictLength)); /* - Skips invalid compressed data until a full flush point (see above the - description of deflate with Z_FULL_FLUSH) can be found, or until all - available input is skipped. No output is provided. + Returns the sliding dictionary being maintained by inflate. dictLength is + set to the number of bytes in the dictionary, and that many bytes are copied + to dictionary. dictionary must have enough space, where 32768 bytes is + always enough. If inflateGetDictionary() is called with dictionary equal to + Z_NULL, then only the dictionary length is returned, and nothing is copied. + Similary, if dictLength is Z_NULL, then it is not set. + + inflateGetDictionary returns Z_OK on success, or Z_STREAM_ERROR if the + stream state is inconsistent. +*/ - inflateSync returns Z_OK if a full flush point has been found, Z_BUF_ERROR - if no more input was provided, Z_DATA_ERROR if no flush point has been found, - or Z_STREAM_ERROR if the stream structure was inconsistent. In the success - case, the application may save the current current value of total_in which - indicates where valid compressed data was found. In the error case, the - application may repeatedly call inflateSync, providing more input each time, - until success or end of the input data. +ZEXTERN int ZEXPORT inflateSync OF((z_streamp strm)); +/* + Skips invalid compressed data until a possible full flush point (see above + for the description of deflate with Z_FULL_FLUSH) can be found, or until all + available input is skipped. No output is provided. + + inflateSync searches for a 00 00 FF FF pattern in the compressed data. + All full flush points have this pattern, but not all occurrences of this + pattern are full flush points. + + inflateSync returns Z_OK if a possible full flush point has been found, + Z_BUF_ERROR if no more input was provided, Z_DATA_ERROR if no flush point + has been found, or Z_STREAM_ERROR if the stream structure was inconsistent. + In the success case, the application may save the current current value of + total_in which indicates where valid compressed data was found. In the + error case, the application may repeatedly call inflateSync, providing more + input each time, until success or end of the input data. */ ZEXTERN int ZEXPORT inflateCopy OF((z_streamp dest, @@ -783,18 +952,32 @@ ZEXTERN int ZEXPORT inflateCopy OF((z_streamp dest, inflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_STREAM_ERROR if the source stream state was inconsistent - (such as zalloc being NULL). msg is left unchanged in both source and + (such as zalloc being Z_NULL). msg is left unchanged in both source and destination. */ ZEXTERN int ZEXPORT inflateReset OF((z_streamp strm)); /* This function is equivalent to inflateEnd followed by inflateInit, - but does not free and reallocate all the internal decompression state. - The stream will keep attributes that may have been set by inflateInit2. + but does not free and reallocate the internal decompression state. The + stream will keep attributes that may have been set by inflateInit2. + + inflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent (such as zalloc or state being Z_NULL). +*/ - inflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent (such as zalloc or state being NULL). +ZEXTERN int ZEXPORT inflateReset2 OF((z_streamp strm, + int windowBits)); +/* + This function is the same as inflateReset, but it also permits changing + the wrap and window size requests. The windowBits parameter is interpreted + the same as it is for inflateInit2. If the window size is changed, then the + memory allocated for the window is freed, and the window will be reallocated + by inflate() if needed. + + inflateReset2 returns Z_OK if success, or Z_STREAM_ERROR if the source + stream state was inconsistent (such as zalloc or state being Z_NULL), or if + the windowBits parameter is invalid. */ ZEXTERN int ZEXPORT inflatePrime OF((z_streamp strm, @@ -802,54 +985,87 @@ ZEXTERN int ZEXPORT inflatePrime OF((z_streamp strm, int value)); /* This function inserts bits in the inflate input stream. The intent is - that this function is used to start inflating at a bit position in the - middle of a byte. The provided bits will be used before any bytes are used - from next_in. This function should only be used with raw inflate, and - should be used before the first inflate() call after inflateInit2() or - inflateReset(). bits must be less than or equal to 16, and that many of the - least significant bits of value will be inserted in the input. - - inflatePrime returns Z_OK if success, or Z_STREAM_ERROR if the source + that this function is used to start inflating at a bit position in the + middle of a byte. The provided bits will be used before any bytes are used + from next_in. This function should only be used with raw inflate, and + should be used before the first inflate() call after inflateInit2() or + inflateReset(). bits must be less than or equal to 16, and that many of the + least significant bits of value will be inserted in the input. + + If bits is negative, then the input stream bit buffer is emptied. Then + inflatePrime() can be called again to put bits in the buffer. This is used + to clear out bits leftover after feeding inflate a block description prior + to feeding inflate codes. + + inflatePrime returns Z_OK if success, or Z_STREAM_ERROR if the source stream state was inconsistent. */ +ZEXTERN long ZEXPORT inflateMark OF((z_streamp strm)); +/* + This function returns two values, one in the lower 16 bits of the return + value, and the other in the remaining upper bits, obtained by shifting the + return value down 16 bits. If the upper value is -1 and the lower value is + zero, then inflate() is currently decoding information outside of a block. + If the upper value is -1 and the lower value is non-zero, then inflate is in + the middle of a stored block, with the lower value equaling the number of + bytes from the input remaining to copy. If the upper value is not -1, then + it is the number of bits back from the current bit position in the input of + the code (literal or length/distance pair) currently being processed. In + that case the lower value is the number of bytes already emitted for that + code. + + A code is being processed if inflate is waiting for more input to complete + decoding of the code, or if it has completed decoding but is waiting for + more output space to write the literal or match data. + + inflateMark() is used to mark locations in the input data for random + access, which may be at bit positions, and to note those cases where the + output of a code may span boundaries of random access blocks. The current + location in the input stream can be determined from avail_in and data_type + as noted in the description for the Z_BLOCK flush parameter for inflate. + + inflateMark returns the value noted above, or -65536 if the provided + source stream state was inconsistent. +*/ + ZEXTERN int ZEXPORT inflateGetHeader OF((z_streamp strm, gz_headerp head)); /* - inflateGetHeader() requests that gzip header information be stored in the + inflateGetHeader() requests that gzip header information be stored in the provided gz_header structure. inflateGetHeader() may be called after inflateInit2() or inflateReset(), and before the first call of inflate(). As inflate() processes the gzip stream, head->done is zero until the header is completed, at which time head->done is set to one. If a zlib stream is being decoded, then head->done is set to -1 to indicate that there will be - no gzip header information forthcoming. Note that Z_BLOCK can be used to - force inflate() to return immediately after header processing is complete - and before any actual data is decompressed. + no gzip header information forthcoming. Note that Z_BLOCK or Z_TREES can be + used to force inflate() to return immediately after header processing is + complete and before any actual data is decompressed. - The text, time, xflags, and os fields are filled in with the gzip header + The text, time, xflags, and os fields are filled in with the gzip header contents. hcrc is set to true if there is a header CRC. (The header CRC - was valid if done is set to one.) If extra is not Z_NULL, then extra_max + was valid if done is set to one.) If extra is not Z_NULL, then extra_max contains the maximum number of bytes to write to extra. Once done is true, extra_len contains the actual extra field length, and extra contains the extra field, or that field truncated if extra_max is less than extra_len. If name is not Z_NULL, then up to name_max characters are written there, terminated with a zero unless the length is greater than name_max. If comment is not Z_NULL, then up to comm_max characters are written there, - terminated with a zero unless the length is greater than comm_max. When - any of extra, name, or comment are not Z_NULL and the respective field is - not present in the header, then that field is set to Z_NULL to signal its + terminated with a zero unless the length is greater than comm_max. When any + of extra, name, or comment are not Z_NULL and the respective field is not + present in the header, then that field is set to Z_NULL to signal its absence. This allows the use of deflateSetHeader() with the returned structure to duplicate the header. However if those fields are set to allocated memory, then the application will need to save those pointers elsewhere so that they can be eventually freed. - If inflateGetHeader is not used, then the header information is simply + If inflateGetHeader is not used, then the header information is simply discarded. The header is always checked for validity, including the header CRC if present. inflateReset() will reset the process to discard the header information. The application would need to call inflateGetHeader() again to retrieve the header from the next gzip stream. - inflateGetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source + inflateGetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source stream state was inconsistent. */ @@ -870,9 +1086,9 @@ ZEXTERN int ZEXPORT inflateBackInit OF((z_streamp strm, int windowBits, See inflateBack() for the usage of these routines. inflateBackInit will return Z_OK on success, Z_STREAM_ERROR if any of - the parameters are invalid, Z_MEM_ERROR if the internal state could not - be allocated, or Z_VERSION_ERROR if the version of the library does not - match the version of the header file. + the parameters are invalid, Z_MEM_ERROR if the internal state could not be + allocated, or Z_VERSION_ERROR if the version of the library does not match + the version of the header file. */ typedef unsigned (*in_func) OF((void FAR *, @@ -884,25 +1100,26 @@ ZEXTERN int ZEXPORT inflateBack OF((z_streamp strm, out_func out, void FAR *out_desc)); /* inflateBack() does a raw inflate with a single call using a call-back - interface for input and output. This is more efficient than inflate() for - file i/o applications in that it avoids copying between the output and the - sliding window by simply making the window itself the output buffer. This - function trusts the application to not change the output buffer passed by - the output function, at least until inflateBack() returns. + interface for input and output. This is potentially more efficient than + inflate() for file i/o applications, in that it avoids copying between the + output and the sliding window by simply making the window itself the output + buffer. inflate() can be faster on modern CPUs when used with large + buffers. inflateBack() trusts the application to not change the output + buffer passed by the output function, at least until inflateBack() returns. inflateBackInit() must be called first to allocate the internal state and to initialize the state with the user-provided window buffer. inflateBack() may then be used multiple times to inflate a complete, raw - deflate stream with each call. inflateBackEnd() is then called to free - the allocated state. + deflate stream with each call. inflateBackEnd() is then called to free the + allocated state. A raw deflate stream is one with no zlib or gzip header or trailer. This routine would normally be used in a utility that reads zip or gzip files and writes out uncompressed files. The utility would decode the - header and process the trailer on its own, hence this routine expects - only the raw deflate stream to decompress. This is different from the - normal behavior of inflate(), which expects either a zlib or gzip header and - trailer around the deflate stream. + header and process the trailer on its own, hence this routine expects only + the raw deflate stream to decompress. This is different from the default + behavior of inflate(), which expects a zlib header and trailer around the + deflate stream. inflateBack() uses two subroutines supplied by the caller that are then called by inflateBack() for input and output. inflateBack() calls those @@ -911,12 +1128,12 @@ ZEXTERN int ZEXPORT inflateBack OF((z_streamp strm, parameters and return types are defined above in the in_func and out_func typedefs. inflateBack() will call in(in_desc, &buf) which should return the number of bytes of provided input, and a pointer to that input in buf. If - there is no input available, in() must return zero--buf is ignored in that - case--and inflateBack() will return a buffer error. inflateBack() will call - out(out_desc, buf, len) to write the uncompressed data buf[0..len-1]. out() - should return zero on success, or non-zero on failure. If out() returns - non-zero, inflateBack() will return with an error. Neither in() nor out() - are permitted to change the contents of the window provided to + there is no input available, in() must return zero -- buf is ignored in that + case -- and inflateBack() will return a buffer error. inflateBack() will + call out(out_desc, buf, len) to write the uncompressed data buf[0..len-1]. + out() should return zero on success, or non-zero on failure. If out() + returns non-zero, inflateBack() will return with an error. Neither in() nor + out() are permitted to change the contents of the window provided to inflateBackInit(), which is also the buffer that out() uses to write from. The length written by out() will be at most the window size. Any non-zero amount of input may be provided by in(). @@ -927,7 +1144,7 @@ ZEXTERN int ZEXPORT inflateBack OF((z_streamp strm, calling inflateBack(). If strm->next_in is Z_NULL, then in() will be called immediately for input. If strm->next_in is not Z_NULL, then strm->avail_in must also be initialized, and then if strm->avail_in is not zero, input will - initially be taken from strm->next_in[0 .. strm->avail_in - 1]. + initially be taken from strm->next_in[0 .. strm->avail_in - 1]. The in_desc and out_desc parameters of inflateBack() is passed as the first parameter of in() and out() respectively when they are called. These @@ -937,15 +1154,15 @@ ZEXTERN int ZEXPORT inflateBack OF((z_streamp strm, On return, inflateBack() will set strm->next_in and strm->avail_in to pass back any unused input that was provided by the last in() call. The return values of inflateBack() can be Z_STREAM_END on success, Z_BUF_ERROR - if in() or out() returned an error, Z_DATA_ERROR if there was a format - error in the deflate stream (in which case strm->msg is set to indicate the - nature of the error), or Z_STREAM_ERROR if the stream was not properly - initialized. In the case of Z_BUF_ERROR, an input or output error can be - distinguished using strm->next_in which will be Z_NULL only if in() returned - an error. If strm->next is not Z_NULL, then the Z_BUF_ERROR was due to - out() returning non-zero. (in() will always be called before out(), so - strm->next_in is assured to be defined if out() returns non-zero.) Note - that inflateBack() cannot return Z_OK. + if in() or out() returned an error, Z_DATA_ERROR if there was a format error + in the deflate stream (in which case strm->msg is set to indicate the nature + of the error), or Z_STREAM_ERROR if the stream was not properly initialized. + In the case of Z_BUF_ERROR, an input or output error can be distinguished + using strm->next_in which will be Z_NULL only if in() returned an error. If + strm->next_in is not Z_NULL, then the Z_BUF_ERROR was due to out() returning + non-zero. (in() will always be called before out(), so strm->next_in is + assured to be defined if out() returns non-zero.) Note that inflateBack() + cannot return Z_OK. */ ZEXTERN int ZEXPORT inflateBackEnd OF((z_streamp strm)); @@ -966,7 +1183,7 @@ ZEXTERN uLong ZEXPORT zlibCompileFlags OF((void)); 7.6: size of z_off_t Compiler, assembler, and debug options: - 8: DEBUG + 8: ZLIB_DEBUG 9: ASMV or ASMINF -- use ASM code 10: ZLIB_WINAPI -- exported functions use the WINAPI calling convention 11: 0 (reserved) @@ -997,27 +1214,28 @@ ZEXTERN uLong ZEXPORT zlibCompileFlags OF((void)); 27-31: 0 (reserved) */ +#ifndef Z_SOLO /* utility functions */ /* - The following utility functions are implemented on top of the - basic stream-oriented functions. To simplify the interface, some - default options are assumed (compression level and memory usage, - standard memory allocation functions). The source code of these - utility functions can easily be modified if you need special options. + The following utility functions are implemented on top of the basic + stream-oriented functions. To simplify the interface, some default options + are assumed (compression level and memory usage, standard memory allocation + functions). The source code of these utility functions can be modified if + you need special options. */ ZEXTERN int ZEXPORT compress OF((Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen)); /* Compresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total - size of the destination buffer, which must be at least the value returned - by compressBound(sourceLen). Upon exit, destLen is the actual size of the - compressed buffer. - This function can be used to compress a whole file at once if the - input file is mmap'ed. + the byte length of the source buffer. Upon entry, destLen is the total size + of the destination buffer, which must be at least the value returned by + compressBound(sourceLen). Upon exit, destLen is the actual size of the + compressed data. compress() is equivalent to compress2() with a level + parameter of Z_DEFAULT_COMPRESSION. + compress returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in the output buffer. @@ -1027,12 +1245,12 @@ ZEXTERN int ZEXPORT compress2 OF((Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen, int level)); /* - Compresses the source buffer into the destination buffer. The level + Compresses the source buffer into the destination buffer. The level parameter has the same meaning as in deflateInit. sourceLen is the byte - length of the source buffer. Upon entry, destLen is the total size of the + length of the source buffer. Upon entry, destLen is the total size of the destination buffer, which must be at least the value returned by - compressBound(sourceLen). Upon exit, destLen is the actual size of the - compressed buffer. + compressBound(sourceLen). Upon exit, destLen is the actual size of the + compressed data. compress2 returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in the output buffer, @@ -1042,159 +1260,306 @@ ZEXTERN int ZEXPORT compress2 OF((Bytef *dest, uLongf *destLen, ZEXTERN uLong ZEXPORT compressBound OF((uLong sourceLen)); /* compressBound() returns an upper bound on the compressed size after - compress() or compress2() on sourceLen bytes. It would be used before - a compress() or compress2() call to allocate the destination buffer. + compress() or compress2() on sourceLen bytes. It would be used before a + compress() or compress2() call to allocate the destination buffer. */ ZEXTERN int ZEXPORT uncompress OF((Bytef *dest, uLongf *destLen, const Bytef *source, uLong sourceLen)); /* Decompresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total - size of the destination buffer, which must be large enough to hold the - entire uncompressed data. (The size of the uncompressed data must have - been saved previously by the compressor and transmitted to the decompressor - by some mechanism outside the scope of this compression library.) - Upon exit, destLen is the actual size of the compressed buffer. - This function can be used to decompress a whole file at once if the - input file is mmap'ed. + the byte length of the source buffer. Upon entry, destLen is the total size + of the destination buffer, which must be large enough to hold the entire + uncompressed data. (The size of the uncompressed data must have been saved + previously by the compressor and transmitted to the decompressor by some + mechanism outside the scope of this compression library.) Upon exit, destLen + is the actual size of the uncompressed data. uncompress returns Z_OK if success, Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer, or Z_DATA_ERROR if the input data was corrupted or incomplete. + buffer, or Z_DATA_ERROR if the input data was corrupted or incomplete. In + the case where there is not enough room, uncompress() will fill the output + buffer with the uncompressed data up to that point. */ +ZEXTERN int ZEXPORT uncompress2 OF((Bytef *dest, uLongf *destLen, + const Bytef *source, uLong *sourceLen)); +/* + Same as uncompress, except that sourceLen is a pointer, where the + length of the source is *sourceLen. On return, *sourceLen is the number of + source bytes consumed. +*/ + + /* gzip file access functions */ + +/* + This library supports reading and writing files in gzip (.gz) format with + an interface similar to that of stdio, using the functions that start with + "gz". The gzip format is different from the zlib format. gzip is a gzip + wrapper, documented in RFC 1952, wrapped around a deflate stream. +*/ -typedef voidp gzFile; +typedef struct gzFile_s *gzFile; /* semi-opaque gzip file descriptor */ -ZEXTERN gzFile ZEXPORT gzopen OF((const char *path, const char *mode)); /* - Opens a gzip (.gz) file for reading or writing. The mode parameter - is as in fopen ("rb" or "wb") but can also include a compression level - ("wb9") or a strategy: 'f' for filtered data as in "wb6f", 'h' for - Huffman only compression as in "wb1h", or 'R' for run-length encoding - as in "wb1R". (See the description of deflateInit2 for more information - about the strategy parameter.) +ZEXTERN gzFile ZEXPORT gzopen OF((const char *path, const char *mode)); + + Opens a gzip (.gz) file for reading or writing. The mode parameter is as + in fopen ("rb" or "wb") but can also include a compression level ("wb9") or + a strategy: 'f' for filtered data as in "wb6f", 'h' for Huffman-only + compression as in "wb1h", 'R' for run-length encoding as in "wb1R", or 'F' + for fixed code compression as in "wb9F". (See the description of + deflateInit2 for more information about the strategy parameter.) 'T' will + request transparent writing or appending with no compression and not using + the gzip format. + + "a" can be used instead of "w" to request that the gzip stream that will + be written be appended to the file. "+" will result in an error, since + reading and writing to the same gzip file is not supported. The addition of + "x" when writing will create the file exclusively, which fails if the file + already exists. On systems that support it, the addition of "e" when + reading or writing will set the flag to close the file on an execve() call. + + These functions, as well as gzip, will read and decode a sequence of gzip + streams in a file. The append function of gzopen() can be used to create + such a file. (Also see gzflush() for another way to do this.) When + appending, gzopen does not test whether the file begins with a gzip stream, + nor does it look for the end of the gzip streams to begin appending. gzopen + will simply append a gzip stream to the existing file. gzopen can be used to read a file which is not in gzip format; in this - case gzread will directly read from the file without decompression. + case gzread will directly read from the file without decompression. When + reading, this will be detected automatically by looking for the magic two- + byte gzip header. + + gzopen returns NULL if the file could not be opened, if there was + insufficient memory to allocate the gzFile state, or if an invalid mode was + specified (an 'r', 'w', or 'a' was not provided, or '+' was provided). + errno can be checked to determine if the reason gzopen failed was that the + file could not be opened. +*/ - gzopen returns NULL if the file could not be opened or if there was - insufficient memory to allocate the (de)compression state; errno - can be checked to distinguish the two cases (if errno is zero, the - zlib error is Z_MEM_ERROR). */ +ZEXTERN gzFile ZEXPORT gzdopen OF((int fd, const char *mode)); +/* + gzdopen associates a gzFile with the file descriptor fd. File descriptors + are obtained from calls like open, dup, creat, pipe or fileno (if the file + has been previously opened with fopen). The mode parameter is as in gzopen. + + The next call of gzclose on the returned gzFile will also close the file + descriptor fd, just like fclose(fdopen(fd, mode)) closes the file descriptor + fd. If you want to keep fd open, use fd = dup(fd_keep); gz = gzdopen(fd, + mode);. The duplicated descriptor should be saved to avoid a leak, since + gzdopen does not close fd if it fails. If you are using fileno() to get the + file descriptor from a FILE *, then you will have to use dup() to avoid + double-close()ing the file descriptor. Both gzclose() and fclose() will + close the associated file descriptor, so they need to have different file + descriptors. + + gzdopen returns NULL if there was insufficient memory to allocate the + gzFile state, if an invalid mode was specified (an 'r', 'w', or 'a' was not + provided, or '+' was provided), or if fd is -1. The file descriptor is not + used until the next gz* read, write, seek, or close operation, so gzdopen + will not detect if fd is invalid (unless fd is -1). +*/ -ZEXTERN gzFile ZEXPORT gzdopen OF((int fd, const char *mode)); +ZEXTERN int ZEXPORT gzbuffer OF((gzFile file, unsigned size)); /* - gzdopen() associates a gzFile with the file descriptor fd. File - descriptors are obtained from calls like open, dup, creat, pipe or - fileno (in the file has been previously opened with fopen). - The mode parameter is as in gzopen. - The next call of gzclose on the returned gzFile will also close the - file descriptor fd, just like fclose(fdopen(fd), mode) closes the file - descriptor fd. If you want to keep fd open, use gzdopen(dup(fd), mode). - gzdopen returns NULL if there was insufficient memory to allocate - the (de)compression state. + Set the internal buffer size used by this library's functions. The + default buffer size is 8192 bytes. This function must be called after + gzopen() or gzdopen(), and before any other calls that read or write the + file. The buffer memory allocation is always deferred to the first read or + write. Three times that size in buffer space is allocated. A larger buffer + size of, for example, 64K or 128K bytes will noticeably increase the speed + of decompression (reading). + + The new buffer size also affects the maximum length for gzprintf(). + + gzbuffer() returns 0 on success, or -1 on failure, such as being called + too late. */ ZEXTERN int ZEXPORT gzsetparams OF((gzFile file, int level, int strategy)); /* - Dynamically update the compression level or strategy. See the description - of deflateInit2 for the meaning of these parameters. - gzsetparams returns Z_OK if success, or Z_STREAM_ERROR if the file was not - opened for writing. + Dynamically update the compression level or strategy. See the description + of deflateInit2 for the meaning of these parameters. Previously provided + data is flushed before the parameter change. + + gzsetparams returns Z_OK if success, Z_STREAM_ERROR if the file was not + opened for writing, Z_ERRNO if there is an error writing the flushed data, + or Z_MEM_ERROR if there is a memory allocation error. */ -ZEXTERN int ZEXPORT gzread OF((gzFile file, voidp buf, unsigned len)); +ZEXTERN int ZEXPORT gzread OF((gzFile file, voidp buf, unsigned len)); /* - Reads the given number of uncompressed bytes from the compressed file. - If the input file was not in gzip format, gzread copies the given number - of bytes into the buffer. - gzread returns the number of uncompressed bytes actually read (0 for - end of file, -1 for error). */ + Reads the given number of uncompressed bytes from the compressed file. If + the input file is not in gzip format, gzread copies the given number of + bytes into the buffer directly from the file. + + After reaching the end of a gzip stream in the input, gzread will continue + to read, looking for another gzip stream. Any number of gzip streams may be + concatenated in the input file, and will all be decompressed by gzread(). + If something other than a gzip stream is encountered after a gzip stream, + that remaining trailing garbage is ignored (and no error is returned). + + gzread can be used to read a gzip file that is being concurrently written. + Upon reaching the end of the input, gzread will return with the available + data. If the error code returned by gzerror is Z_OK or Z_BUF_ERROR, then + gzclearerr can be used to clear the end of file indicator in order to permit + gzread to be tried again. Z_OK indicates that a gzip stream was completed + on the last gzread. Z_BUF_ERROR indicates that the input file ended in the + middle of a gzip stream. Note that gzread does not return -1 in the event + of an incomplete gzip stream. This error is deferred until gzclose(), which + will return Z_BUF_ERROR if the last gzread ended in the middle of a gzip + stream. Alternatively, gzerror can be used before gzclose to detect this + case. + + gzread returns the number of uncompressed bytes actually read, less than + len for end of file, or -1 for error. If len is too large to fit in an int, + then nothing is read, -1 is returned, and the error state is set to + Z_STREAM_ERROR. +*/ -ZEXTERN int ZEXPORT gzwrite OF((gzFile file, - voidpc buf, unsigned len)); +ZEXTERN z_size_t ZEXPORT gzfread OF((voidp buf, z_size_t size, z_size_t nitems, + gzFile file)); +/* + Read up to nitems items of size size from file to buf, otherwise operating + as gzread() does. This duplicates the interface of stdio's fread(), with + size_t request and return types. If the library defines size_t, then + z_size_t is identical to size_t. If not, then z_size_t is an unsigned + integer type that can contain a pointer. + + gzfread() returns the number of full items read of size size, or zero if + the end of the file was reached and a full item could not be read, or if + there was an error. gzerror() must be consulted if zero is returned in + order to determine if there was an error. If the multiplication of size and + nitems overflows, i.e. the product does not fit in a z_size_t, then nothing + is read, zero is returned, and the error state is set to Z_STREAM_ERROR. + + In the event that the end of file is reached and only a partial item is + available at the end, i.e. the remaining uncompressed data length is not a + multiple of size, then the final partial item is nevetheless read into buf + and the end-of-file flag is set. The length of the partial item read is not + provided, but could be inferred from the result of gztell(). This behavior + is the same as the behavior of fread() implementations in common libraries, + but it prevents the direct use of gzfread() to read a concurrently written + file, reseting and retrying on end-of-file, when size is not 1. +*/ + +ZEXTERN int ZEXPORT gzwrite OF((gzFile file, + voidpc buf, unsigned len)); /* Writes the given number of uncompressed bytes into the compressed file. - gzwrite returns the number of uncompressed bytes actually written - (0 in case of error). + gzwrite returns the number of uncompressed bytes written or 0 in case of + error. +*/ + +ZEXTERN z_size_t ZEXPORT gzfwrite OF((voidpc buf, z_size_t size, + z_size_t nitems, gzFile file)); +/* + gzfwrite() writes nitems items of size size from buf to file, duplicating + the interface of stdio's fwrite(), with size_t request and return types. If + the library defines size_t, then z_size_t is identical to size_t. If not, + then z_size_t is an unsigned integer type that can contain a pointer. + + gzfwrite() returns the number of full items written of size size, or zero + if there was an error. If the multiplication of size and nitems overflows, + i.e. the product does not fit in a z_size_t, then nothing is written, zero + is returned, and the error state is set to Z_STREAM_ERROR. */ -ZEXTERN int ZEXPORTVA gzprintf OF((gzFile file, const char *format, ...)); +ZEXTERN int ZEXPORTVA gzprintf Z_ARG((gzFile file, const char *format, ...)); /* - Converts, formats, and writes the args to the compressed file under - control of the format string, as in fprintf. gzprintf returns the number of - uncompressed bytes actually written (0 in case of error). The number of - uncompressed bytes written is limited to 4095. The caller should assure that - this limit is not exceeded. If it is exceeded, then gzprintf() will return - return an error (0) with nothing written. In this case, there may also be a + Converts, formats, and writes the arguments to the compressed file under + control of the format string, as in fprintf. gzprintf returns the number of + uncompressed bytes actually written, or a negative zlib error code in case + of error. The number of uncompressed bytes written is limited to 8191, or + one less than the buffer size given to gzbuffer(). The caller should assure + that this limit is not exceeded. If it is exceeded, then gzprintf() will + return an error (0) with nothing written. In this case, there may also be a buffer overflow with unpredictable consequences, which is possible only if zlib was compiled with the insecure functions sprintf() or vsprintf() because the secure snprintf() or vsnprintf() functions were not available. + This can be determined using zlibCompileFlags(). */ ZEXTERN int ZEXPORT gzputs OF((gzFile file, const char *s)); /* - Writes the given null-terminated string to the compressed file, excluding + Writes the given null-terminated string to the compressed file, excluding the terminating null character. - gzputs returns the number of characters written, or -1 in case of error. + + gzputs returns the number of characters written, or -1 in case of error. */ ZEXTERN char * ZEXPORT gzgets OF((gzFile file, char *buf, int len)); /* - Reads bytes from the compressed file until len-1 characters are read, or - a newline character is read and transferred to buf, or an end-of-file - condition is encountered. The string is then terminated with a null - character. - gzgets returns buf, or Z_NULL in case of error. + Reads bytes from the compressed file until len-1 characters are read, or a + newline character is read and transferred to buf, or an end-of-file + condition is encountered. If any characters are read or if len == 1, the + string is terminated with a null character. If no characters are read due + to an end-of-file or len < 1, then the buffer is left untouched. + + gzgets returns buf which is a null-terminated string, or it returns NULL + for end-of-file or in case of error. If there was an error, the contents at + buf are indeterminate. */ -ZEXTERN int ZEXPORT gzputc OF((gzFile file, int c)); +ZEXTERN int ZEXPORT gzputc OF((gzFile file, int c)); /* - Writes c, converted to an unsigned char, into the compressed file. - gzputc returns the value that was written, or -1 in case of error. + Writes c, converted to an unsigned char, into the compressed file. gzputc + returns the value that was written, or -1 in case of error. */ -ZEXTERN int ZEXPORT gzgetc OF((gzFile file)); +ZEXTERN int ZEXPORT gzgetc OF((gzFile file)); /* - Reads one byte from the compressed file. gzgetc returns this byte - or -1 in case of end of file or error. + Reads one byte from the compressed file. gzgetc returns this byte or -1 + in case of end of file or error. This is implemented as a macro for speed. + As such, it does not do all of the checking the other functions do. I.e. + it does not check to see if file is NULL, nor whether the structure file + points to has been clobbered or not. */ -ZEXTERN int ZEXPORT gzungetc OF((int c, gzFile file)); +ZEXTERN int ZEXPORT gzungetc OF((int c, gzFile file)); /* - Push one character back onto the stream to be read again later. - Only one character of push-back is allowed. gzungetc() returns the - character pushed, or -1 on failure. gzungetc() will fail if a - character has been pushed but not read yet, or if c is -1. The pushed - character will be discarded if the stream is repositioned with gzseek() - or gzrewind(). + Push one character back onto the stream to be read as the first character + on the next read. At least one character of push-back is allowed. + gzungetc() returns the character pushed, or -1 on failure. gzungetc() will + fail if c is -1, and may fail if a character has been pushed but not read + yet. If gzungetc is used immediately after gzopen or gzdopen, at least the + output buffer size of pushed characters is allowed. (See gzbuffer above.) + The pushed character will be discarded if the stream is repositioned with + gzseek() or gzrewind(). */ -ZEXTERN int ZEXPORT gzflush OF((gzFile file, int flush)); +ZEXTERN int ZEXPORT gzflush OF((gzFile file, int flush)); /* - Flushes all pending output into the compressed file. The parameter - flush is as in the deflate() function. The return value is the zlib - error number (see function gzerror below). gzflush returns Z_OK if - the flush parameter is Z_FINISH and all output could be flushed. - gzflush should be called only when strictly necessary because it can - degrade compression. + Flushes all pending output into the compressed file. The parameter flush + is as in the deflate() function. The return value is the zlib error number + (see function gzerror below). gzflush is only permitted when writing. + + If the flush parameter is Z_FINISH, the remaining data is written and the + gzip stream is completed in the output. If gzwrite() is called again, a new + gzip stream will be started in the output. gzread() is able to read such + concatenated gzip streams. + + gzflush should be called only when strictly necessary because it will + degrade compression if called too often. */ -ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile file, - z_off_t offset, int whence)); /* - Sets the starting position for the next gzread or gzwrite on the - given compressed file. The offset represents a number of bytes in the - uncompressed data stream. The whence parameter is defined as in lseek(2); +ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile file, + z_off_t offset, int whence)); + + Sets the starting position for the next gzread or gzwrite on the given + compressed file. The offset represents a number of bytes in the + uncompressed data stream. The whence parameter is defined as in lseek(2); the value SEEK_END is not supported. + If the file is opened for reading, this function is emulated but can be - extremely slow. If the file is opened for writing, only forward seeks are + extremely slow. If the file is opened for writing, only forward seeks are supported; gzseek then compresses a sequence of zeroes up to the new starting position. - gzseek returns the resulting offset location as measured in bytes from + gzseek returns the resulting offset location as measured in bytes from the beginning of the uncompressed stream, or -1 in case of error, in particular if the file is opened for writing and the new starting position would be before the current position. @@ -1204,68 +1569,134 @@ ZEXTERN int ZEXPORT gzrewind OF((gzFile file)); /* Rewinds the given file. This function is supported only for reading. - gzrewind(file) is equivalent to (int)gzseek(file, 0L, SEEK_SET) + gzrewind(file) is equivalent to (int)gzseek(file, 0L, SEEK_SET) */ +/* ZEXTERN z_off_t ZEXPORT gztell OF((gzFile file)); + + Returns the starting position for the next gzread or gzwrite on the given + compressed file. This position represents a number of bytes in the + uncompressed data stream, and is zero when starting, even if appending or + reading a gzip stream from the middle of a file using gzdopen(). + + gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR) +*/ + /* - Returns the starting position for the next gzread or gzwrite on the - given compressed file. This position represents a number of bytes in the - uncompressed data stream. +ZEXTERN z_off_t ZEXPORT gzoffset OF((gzFile file)); - gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR) + Returns the current offset in the file being read or written. This offset + includes the count of bytes that precede the gzip stream, for example when + appending or when using gzdopen() for reading. When reading, the offset + does not include as yet unused buffered input. This information can be used + for a progress indicator. On error, gzoffset() returns -1. */ ZEXTERN int ZEXPORT gzeof OF((gzFile file)); /* - Returns 1 when EOF has previously been detected reading the given - input stream, otherwise zero. + Returns true (1) if the end-of-file indicator has been set while reading, + false (0) otherwise. Note that the end-of-file indicator is set only if the + read tried to go past the end of the input, but came up short. Therefore, + just like feof(), gzeof() may return false even if there is no more data to + read, in the event that the last read request was for the exact number of + bytes remaining in the input file. This will happen if the input file size + is an exact multiple of the buffer size. + + If gzeof() returns true, then the read functions will return no more data, + unless the end-of-file indicator is reset by gzclearerr() and the input file + has grown since the previous end of file was detected. */ ZEXTERN int ZEXPORT gzdirect OF((gzFile file)); /* - Returns 1 if file is being read directly without decompression, otherwise - zero. + Returns true (1) if file is being copied directly while reading, or false + (0) if file is a gzip stream being decompressed. + + If the input file is empty, gzdirect() will return true, since the input + does not contain a gzip stream. + + If gzdirect() is used immediately after gzopen() or gzdopen() it will + cause buffers to be allocated to allow reading the file to determine if it + is a gzip file. Therefore if gzbuffer() is used, it should be called before + gzdirect(). + + When writing, gzdirect() returns true (1) if transparent writing was + requested ("wT" for the gzopen() mode), or false (0) otherwise. (Note: + gzdirect() is not needed when writing. Transparent writing must be + explicitly requested, so the application already knows the answer. When + linking statically, using gzdirect() will include all of the zlib code for + gzip file reading and decompression, which may not be desired.) */ ZEXTERN int ZEXPORT gzclose OF((gzFile file)); /* - Flushes all pending output if necessary, closes the compressed file - and deallocates all the (de)compression state. The return value is the zlib - error number (see function gzerror below). + Flushes all pending output if necessary, closes the compressed file and + deallocates the (de)compression state. Note that once file is closed, you + cannot call gzerror with file, since its structures have been deallocated. + gzclose must not be called more than once on the same file, just as free + must not be called more than once on the same allocation. + + gzclose will return Z_STREAM_ERROR if file is not valid, Z_ERRNO on a + file operation error, Z_MEM_ERROR if out of memory, Z_BUF_ERROR if the + last read ended in the middle of a gzip stream, or Z_OK on success. +*/ + +ZEXTERN int ZEXPORT gzclose_r OF((gzFile file)); +ZEXTERN int ZEXPORT gzclose_w OF((gzFile file)); +/* + Same as gzclose(), but gzclose_r() is only for use when reading, and + gzclose_w() is only for use when writing or appending. The advantage to + using these instead of gzclose() is that they avoid linking in zlib + compression or decompression code that is not used when only reading or only + writing respectively. If gzclose() is used, then both compression and + decompression code will be included the application when linking to a static + zlib library. */ ZEXTERN const char * ZEXPORT gzerror OF((gzFile file, int *errnum)); /* - Returns the error message for the last error which occurred on the - given compressed file. errnum is set to zlib error number. If an - error occurred in the file system and not in the compression library, - errnum is set to Z_ERRNO and the application may consult errno - to get the exact error code. + Returns the error message for the last error which occurred on the given + compressed file. errnum is set to zlib error number. If an error occurred + in the file system and not in the compression library, errnum is set to + Z_ERRNO and the application may consult errno to get the exact error code. + + The application must not modify the returned string. Future calls to + this function may invalidate the previously returned string. If file is + closed, then the string previously returned by gzerror will no longer be + available. + + gzerror() should be used to distinguish errors from end-of-file for those + functions above that do not distinguish those cases in their return values. */ ZEXTERN void ZEXPORT gzclearerr OF((gzFile file)); /* - Clears the error and end-of-file flags for file. This is analogous to the - clearerr() function in stdio. This is useful for continuing to read a gzip + Clears the error and end-of-file flags for file. This is analogous to the + clearerr() function in stdio. This is useful for continuing to read a gzip file that is being written concurrently. */ +#endif /* !Z_SOLO */ + /* checksum functions */ /* These functions are not related to compression but are exported - anyway because they might be useful in applications using the - compression library. + anyway because they might be useful in applications using the compression + library. */ ZEXTERN uLong ZEXPORT adler32 OF((uLong adler, const Bytef *buf, uInt len)); /* Update a running Adler-32 checksum with the bytes buf[0..len-1] and - return the updated checksum. If buf is NULL, this function returns - the required initial value for the checksum. - An Adler-32 checksum is almost as reliable as a CRC32 but can be computed - much faster. Usage example: + return the updated checksum. If buf is Z_NULL, this function returns the + required initial value for the checksum. + + An Adler-32 checksum is almost as reliable as a CRC-32 but can be computed + much faster. + + Usage example: uLong adler = adler32(0L, Z_NULL, 0); @@ -1275,21 +1706,31 @@ ZEXTERN uLong ZEXPORT adler32 OF((uLong adler, const Bytef *buf, uInt len)); if (adler != original_adler) error(); */ +ZEXTERN uLong ZEXPORT adler32_z OF((uLong adler, const Bytef *buf, + z_size_t len)); +/* + Same as adler32(), but with a size_t length. +*/ + +/* ZEXTERN uLong ZEXPORT adler32_combine OF((uLong adler1, uLong adler2, 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 each, adler1 and adler2. adler32_combine() returns the Adler-32 checksum of - seq1 and seq2 concatenated, requiring only adler1, adler2, and len2. + seq1 and seq2 concatenated, requiring only adler1, adler2, and len2. Note + that the z_off_t type (like off_t) is a signed integer. If len2 is + negative, the result has no meaning or utility. */ ZEXTERN uLong ZEXPORT crc32 OF((uLong crc, const Bytef *buf, uInt len)); /* Update a running CRC-32 with the bytes buf[0..len-1] and return the - updated CRC-32. If buf is NULL, this function returns the required initial - value for the for the crc. Pre- and post-conditioning (one's complement) is + updated CRC-32. If buf is Z_NULL, this function returns the required + initial value for the crc. Pre- and post-conditioning (one's complement) is performed within this function so it shouldn't be done by the application. + Usage example: uLong crc = crc32(0L, Z_NULL, 0); @@ -1300,9 +1741,15 @@ 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, z_off_t len2)); +ZEXTERN uLong ZEXPORT crc32_z OF((uLong adler, const Bytef *buf, + z_size_t len)); +/* + Same as crc32(), but with a size_t length. +*/ /* +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, seq1 and seq2 with lengths len1 and len2, CRC-32 check values were calculated for each, crc1 and crc2. crc32_combine() returns the CRC-32 @@ -1330,27 +1777,135 @@ ZEXTERN int ZEXPORT inflateBackInit_ OF((z_streamp strm, int windowBits, unsigned char FAR *window, const char *version, int stream_size)); -#define deflateInit(strm, level) \ - deflateInit_((strm), (level), ZLIB_VERSION, sizeof(z_stream)) -#define inflateInit(strm) \ - inflateInit_((strm), ZLIB_VERSION, sizeof(z_stream)) -#define deflateInit2(strm, level, method, windowBits, memLevel, strategy) \ - deflateInit2_((strm),(level),(method),(windowBits),(memLevel),\ - (strategy), ZLIB_VERSION, sizeof(z_stream)) -#define inflateInit2(strm, windowBits) \ - inflateInit2_((strm), (windowBits), ZLIB_VERSION, sizeof(z_stream)) -#define inflateBackInit(strm, windowBits, window) \ - inflateBackInit_((strm), (windowBits), (window), \ - ZLIB_VERSION, sizeof(z_stream)) - - -#if !defined(ZUTIL_H) && !defined(NO_DUMMY_DECL) - struct internal_state {int dummy;}; /* hack for buggy compilers */ +#ifdef Z_PREFIX_SET +# define z_deflateInit(strm, level) \ + deflateInit_((strm), (level), ZLIB_VERSION, (int)sizeof(z_stream)) +# define z_inflateInit(strm) \ + inflateInit_((strm), ZLIB_VERSION, (int)sizeof(z_stream)) +# define z_deflateInit2(strm, level, method, windowBits, memLevel, strategy) \ + deflateInit2_((strm),(level),(method),(windowBits),(memLevel),\ + (strategy), ZLIB_VERSION, (int)sizeof(z_stream)) +# define z_inflateInit2(strm, windowBits) \ + inflateInit2_((strm), (windowBits), ZLIB_VERSION, \ + (int)sizeof(z_stream)) +# define z_inflateBackInit(strm, windowBits, window) \ + inflateBackInit_((strm), (windowBits), (window), \ + ZLIB_VERSION, (int)sizeof(z_stream)) +#else +# define deflateInit(strm, level) \ + deflateInit_((strm), (level), ZLIB_VERSION, (int)sizeof(z_stream)) +# define inflateInit(strm) \ + inflateInit_((strm), ZLIB_VERSION, (int)sizeof(z_stream)) +# define deflateInit2(strm, level, method, windowBits, memLevel, strategy) \ + deflateInit2_((strm),(level),(method),(windowBits),(memLevel),\ + (strategy), ZLIB_VERSION, (int)sizeof(z_stream)) +# define inflateInit2(strm, windowBits) \ + inflateInit2_((strm), (windowBits), ZLIB_VERSION, \ + (int)sizeof(z_stream)) +# define inflateBackInit(strm, windowBits, window) \ + inflateBackInit_((strm), (windowBits), (window), \ + ZLIB_VERSION, (int)sizeof(z_stream)) +#endif + +#ifndef Z_SOLO + +/* gzgetc() macro and its supporting function and exposed data structure. Note + * that the real internal state is much larger than the exposed structure. + * This abbreviated structure exposes just enough for the gzgetc() macro. The + * user should not mess with these exposed elements, since their names or + * behavior could change in the future, perhaps even capriciously. They can + * only be used by the gzgetc() macro. You have been warned. + */ +struct gzFile_s { + unsigned have; + unsigned char *next; + z_off64_t pos; +}; +ZEXTERN int ZEXPORT gzgetc_ OF((gzFile file)); /* backward compatibility */ +#ifdef Z_PREFIX_SET +# undef z_gzgetc +# define z_gzgetc(g) \ + ((g)->have ? ((g)->have--, (g)->pos++, *((g)->next)++) : (gzgetc)(g)) +#else +# define gzgetc(g) \ + ((g)->have ? ((g)->have--, (g)->pos++, *((g)->next)++) : (gzgetc)(g)) +#endif + +/* provide 64-bit offset functions if _LARGEFILE64_SOURCE defined, and/or + * change the regular functions to 64 bits if _FILE_OFFSET_BITS is 64 (if + * both are true, the application gets the *64 functions, and the regular + * functions are changed to 64 bits) -- in case these are set on systems + * without large file support, _LFS64_LARGEFILE must also be true + */ +#ifdef Z_LARGE64 + ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); + ZEXTERN z_off64_t ZEXPORT gzseek64 OF((gzFile, z_off64_t, int)); + ZEXTERN z_off64_t ZEXPORT gztell64 OF((gzFile)); + ZEXTERN z_off64_t ZEXPORT gzoffset64 OF((gzFile)); + ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off64_t)); + ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off64_t)); +#endif + +#if !defined(ZLIB_INTERNAL) && defined(Z_WANT64) +# ifdef Z_PREFIX_SET +# define z_gzopen z_gzopen64 +# define z_gzseek z_gzseek64 +# define z_gztell z_gztell64 +# define z_gzoffset z_gzoffset64 +# define z_adler32_combine z_adler32_combine64 +# define z_crc32_combine z_crc32_combine64 +# else +# define gzopen gzopen64 +# define gzseek gzseek64 +# define gztell gztell64 +# define gzoffset gzoffset64 +# define adler32_combine adler32_combine64 +# define crc32_combine crc32_combine64 +# endif +# ifndef Z_LARGE64 + ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); + ZEXTERN z_off_t ZEXPORT gzseek64 OF((gzFile, z_off_t, int)); + ZEXTERN z_off_t ZEXPORT gztell64 OF((gzFile)); + ZEXTERN z_off_t ZEXPORT gzoffset64 OF((gzFile)); + ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off_t)); + ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off_t)); +# endif +#else + ZEXTERN gzFile ZEXPORT gzopen OF((const char *, const char *)); + ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile, z_off_t, int)); + ZEXTERN z_off_t ZEXPORT gztell OF((gzFile)); + ZEXTERN z_off_t ZEXPORT gzoffset OF((gzFile)); + ZEXTERN uLong ZEXPORT adler32_combine OF((uLong, uLong, z_off_t)); + ZEXTERN uLong ZEXPORT crc32_combine OF((uLong, uLong, z_off_t)); #endif +#else /* Z_SOLO */ + + ZEXTERN uLong ZEXPORT adler32_combine OF((uLong, uLong, z_off_t)); + ZEXTERN uLong ZEXPORT crc32_combine OF((uLong, uLong, z_off_t)); + +#endif /* !Z_SOLO */ + +/* undocumented functions */ ZEXTERN const char * ZEXPORT zError OF((int)); -ZEXTERN int ZEXPORT inflateSyncPoint OF((z_streamp z)); -ZEXTERN const uLongf * ZEXPORT get_crc_table OF((void)); +ZEXTERN int ZEXPORT inflateSyncPoint OF((z_streamp)); +ZEXTERN const z_crc_t FAR * ZEXPORT get_crc_table OF((void)); +ZEXTERN int ZEXPORT inflateUndermine OF((z_streamp, int)); +ZEXTERN int ZEXPORT inflateValidate OF((z_streamp, int)); +ZEXTERN unsigned long ZEXPORT inflateCodesUsed OF ((z_streamp)); +ZEXTERN int ZEXPORT inflateResetKeep OF((z_streamp)); +ZEXTERN int ZEXPORT deflateResetKeep OF((z_streamp)); +#if (defined(_WIN32) || defined(__CYGWIN__)) && !defined(Z_SOLO) +ZEXTERN gzFile ZEXPORT gzopen_w OF((const wchar_t *path, + const char *mode)); +#endif +#if defined(STDC) || defined(Z_HAVE_STDARG_H) +# ifndef Z_SOLO +ZEXTERN int ZEXPORTVA gzvprintf Z_ARG((gzFile file, + const char *format, + va_list va)); +# endif +#endif #ifdef __cplusplus } diff --git a/lib/libz/zutil.c b/lib/libz/zutil.c index 42813db..f51420c 100644 --- a/lib/libz/zutil.c +++ b/lib/libz/zutil.c @@ -1,27 +1,26 @@ -/* $OpenBSD: zutil.c,v 1.9 2015/08/21 23:30:59 deraadt Exp $ */ +/* $OpenBSD: zutil.c,v 1.10 2021/07/04 14:24:49 tb Exp $ */ /* zutil.c -- target dependent utility functions for the compression library - * Copyright (C) 1995-2005 Jean-loup Gailly. + * Copyright (C) 1995-2017 Jean-loup Gailly * For conditions of distribution and use, see copyright notice in zlib.h */ - #include "zutil.h" - -#ifndef NO_DUMMY_DECL -struct internal_state {int dummy;}; /* for buggy compilers */ +#ifndef Z_SOLO +# include "gzguts.h" #endif -const char * const z_errmsg[10] = { -"need dictionary", /* Z_NEED_DICT 2 */ -"stream end", /* Z_STREAM_END 1 */ -"", /* Z_OK 0 */ -"file error", /* Z_ERRNO (-1) */ -"stream error", /* Z_STREAM_ERROR (-2) */ -"data error", /* Z_DATA_ERROR (-3) */ -"insufficient memory", /* Z_MEM_ERROR (-4) */ -"buffer error", /* Z_BUF_ERROR (-5) */ -"incompatible version",/* Z_VERSION_ERROR (-6) */ -""}; +z_const char * const z_errmsg[10] = { + (z_const char *)"need dictionary", /* Z_NEED_DICT 2 */ + (z_const char *)"stream end", /* Z_STREAM_END 1 */ + (z_const char *)"", /* Z_OK 0 */ + (z_const char *)"file error", /* Z_ERRNO (-1) */ + (z_const char *)"stream error", /* Z_STREAM_ERROR (-2) */ + (z_const char *)"data error", /* Z_DATA_ERROR (-3) */ + (z_const char *)"insufficient memory", /* Z_MEM_ERROR (-4) */ + (z_const char *)"buffer error", /* Z_BUF_ERROR (-5) */ + (z_const char *)"incompatible version",/* Z_VERSION_ERROR (-6) */ + (z_const char *)"" +}; const char * ZEXPORT zlibVersion() @@ -34,31 +33,31 @@ uLong ZEXPORT zlibCompileFlags() uLong flags; flags = 0; - switch (sizeof(uInt)) { + switch ((int)(sizeof(uInt))) { case 2: break; case 4: flags += 1; break; case 8: flags += 2; break; default: flags += 3; } - switch (sizeof(uLong)) { + switch ((int)(sizeof(uLong))) { case 2: break; case 4: flags += 1 << 2; break; case 8: flags += 2 << 2; break; default: flags += 3 << 2; } - switch (sizeof(voidpf)) { + switch ((int)(sizeof(voidpf))) { case 2: break; case 4: flags += 1 << 4; break; case 8: flags += 2 << 4; break; default: flags += 3 << 4; } - switch (sizeof(z_off_t)) { + switch ((int)(sizeof(z_off_t))) { case 2: break; case 4: flags += 1 << 6; break; case 8: flags += 2 << 6; break; default: flags += 3 << 6; } -#ifdef DEBUG +#ifdef ZLIB_DEBUG flags += 1 << 8; #endif #if defined(ASMV) || defined(ASMINF) @@ -85,41 +84,41 @@ uLong ZEXPORT zlibCompileFlags() #ifdef FASTEST flags += 1L << 21; #endif -#ifdef STDC +#if defined(STDC) || defined(Z_HAVE_STDARG_H) # ifdef NO_vsnprintf - flags += 1L << 25; + flags += 1L << 25; # ifdef HAS_vsprintf_void - flags += 1L << 26; + flags += 1L << 26; # endif # else # ifdef HAS_vsnprintf_void - flags += 1L << 26; + flags += 1L << 26; # endif # endif #else - flags += 1L << 24; + flags += 1L << 24; # ifdef NO_snprintf - flags += 1L << 25; + flags += 1L << 25; # ifdef HAS_sprintf_void - flags += 1L << 26; + flags += 1L << 26; # endif # else # ifdef HAS_snprintf_void - flags += 1L << 26; + flags += 1L << 26; # endif # endif #endif return flags; } -#ifdef DEBUG - +#ifdef ZLIB_DEBUG +#include <stdlib.h> # ifndef verbose # define verbose 0 # endif -int z_verbose = verbose; +int ZLIB_INTERNAL z_verbose = verbose; -void z_error (m) +void ZLIB_INTERNAL z_error (m) char *m; { fprintf(stderr, "%s\n", m); @@ -146,7 +145,7 @@ const char * ZEXPORT zError(err) #ifndef HAVE_MEMCPY -void zmemcpy(dest, source, len) +void ZLIB_INTERNAL zmemcpy(dest, source, len) Bytef* dest; const Bytef* source; uInt len; @@ -157,7 +156,7 @@ void zmemcpy(dest, source, len) } while (--len != 0); } -int zmemcmp(s1, s2, len) +int ZLIB_INTERNAL zmemcmp(s1, s2, len) const Bytef* s1; const Bytef* s2; uInt len; @@ -170,7 +169,7 @@ int zmemcmp(s1, s2, len) return 0; } -void zmemzero(dest, len) +void ZLIB_INTERNAL zmemzero(dest, len) Bytef* dest; uInt len; { @@ -181,6 +180,7 @@ void zmemzero(dest, len) } #endif +#ifndef Z_SOLO #ifdef SYS16BIT @@ -213,11 +213,13 @@ local ptr_table table[MAX_PTR]; * a protected system like OS/2. Use Microsoft C instead. */ -voidpf zcalloc (voidpf opaque, unsigned items, unsigned size) +voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, unsigned items, unsigned size) { - voidpf buf = opaque; /* just to make some compilers happy */ + voidpf buf; ulg bsize = (ulg)items*size; + (void)opaque; + /* If we allocate less than 65520 bytes, we assume that farmalloc * will return a usable pointer which doesn't have to be normalized. */ @@ -237,9 +239,12 @@ voidpf zcalloc (voidpf opaque, unsigned items, unsigned size) return buf; } -void zcfree (voidpf opaque, voidpf ptr) +void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) { int n; + + (void)opaque; + if (*(ush*)&ptr != 0) { /* object < 64K */ farfree(ptr); return; @@ -255,7 +260,6 @@ void zcfree (voidpf opaque, voidpf ptr) next_ptr--; return; } - ptr = opaque; /* just to make some compilers happy */ Assert(0, "zcfree: ptr not found"); } @@ -272,15 +276,15 @@ void zcfree (voidpf opaque, voidpf ptr) # define _hfree hfree #endif -voidpf zcalloc (voidpf opaque, unsigned items, unsigned size) +voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, uInt items, uInt size) { - if (opaque) opaque = 0; /* to make compiler happy */ + (void)opaque; return _halloc((long)items, size); } -void zcfree (voidpf opaque, voidpf ptr) +void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) { - if (opaque) opaque = 0; /* to make compiler happy */ + (void)opaque; _hfree(ptr); } @@ -297,23 +301,25 @@ extern voidp calloc OF((uInt items, uInt size)); extern void free OF((voidpf ptr)); #endif -voidpf zcalloc (opaque, items, size) +voidpf ZLIB_INTERNAL zcalloc (opaque, items, size) voidpf opaque; unsigned items; unsigned size; { - if (opaque) items += size - size; /* make compiler happy */ + (void)opaque; if (items == 0 || size == 0) return (NULL); return reallocarray(NULL, items, size); } -void zcfree (opaque, ptr) +void ZLIB_INTERNAL zcfree (opaque, ptr) voidpf opaque; voidpf ptr; { + (void)opaque; free(ptr); - if (opaque) return; /* make compiler happy */ } #endif /* MY_ZCALLOC */ + +#endif /* !Z_SOLO */ diff --git a/lib/libz/zutil.h b/lib/libz/zutil.h index 5726e18..eb85027 100644 --- a/lib/libz/zutil.h +++ b/lib/libz/zutil.h @@ -1,6 +1,7 @@ -/* $OpenBSD: zutil.h,v 1.9 2005/07/20 15:56:42 millert Exp $ */ +/* $OpenBSD: zutil.h,v 1.11 2021/07/04 17:41:23 tb Exp $ */ + /* zutil.h -- internal interface and configuration of the compression library - * Copyright (C) 1995-2005 Jean-loup Gailly. + * Copyright (C) 1995-2016 Jean-loup Gailly, Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ @@ -9,44 +10,39 @@ subject to change. Applications should only use zlib.h. */ - #ifndef ZUTIL_H #define ZUTIL_H -#define ZLIB_INTERNAL +#ifdef HAVE_HIDDEN +# define ZLIB_INTERNAL __attribute__((visibility ("hidden"))) +#else +# define ZLIB_INTERNAL +#endif + #include "zlib.h" #ifdef _STANDALONE #include <stand.h> #else -#ifdef STDC -# ifndef _WIN32_WCE +#if defined(STDC) && !defined(Z_SOLO) +# if !(defined(_WIN32_WCE) && defined(_MSC_VER)) # include <stddef.h> # endif # include <string.h> # include <stdlib.h> #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 -# ifndef _WIN32_WCE -# include <errno.h> -# endif #endif + +#ifdef Z_SOLO + typedef long ptrdiff_t; /* guess -- will be caught if guess is wrong */ #endif #ifndef local # define local static #endif -/* compile with -Dlocal if your debugger can't find static symbols */ +/* since "static" is used to mean two completely different things in C, we + define "local" for the non-static meaning of "static", for readability + (compile with -Dlocal if your debugger can't find static symbols) */ typedef unsigned char uch; typedef uch FAR uchf; @@ -54,13 +50,13 @@ typedef unsigned short ush; typedef ush FAR ushf; typedef unsigned long ulg; -extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ +extern z_const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ /* (size given to avoid silly warnings with Visual C++) */ #define ERR_MSG(err) z_errmsg[Z_NEED_DICT-(err)] #define ERR_RETURN(strm,err) \ - return (strm->msg = (char*)ERR_MSG(err), (err)) + return (strm->msg = ERR_MSG(err), (err)) /* To be used only when the state is known to be valid */ /* common constants */ @@ -92,70 +88,90 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ #if defined(MSDOS) || (defined(WINDOWS) && !defined(WIN32)) # define OS_CODE 0x00 -# if defined(__TURBOC__) || defined(__BORLANDC__) -# if(__STDC__ == 1) && (defined(__LARGE__) || defined(__COMPACT__)) - /* Allow compilation with ANSI keywords only enabled */ - void _Cdecl farfree( void *block ); - void *_Cdecl farmalloc( unsigned long nbytes ); -# else -# include <alloc.h> +# ifndef Z_SOLO +# if defined(__TURBOC__) || defined(__BORLANDC__) +# if (__STDC__ == 1) && (defined(__LARGE__) || defined(__COMPACT__)) + /* Allow compilation with ANSI keywords only enabled */ + void _Cdecl farfree( void *block ); + void *_Cdecl farmalloc( unsigned long nbytes ); +# else +# include <alloc.h> +# endif +# else /* MSC or DJGPP */ +# include <malloc.h> # endif -# else /* MSC or DJGPP */ -# include <malloc.h> # endif #endif #ifdef AMIGA -# define OS_CODE 0x01 +# define OS_CODE 1 #endif #if defined(VAXC) || defined(VMS) -# define OS_CODE 0x02 +# define OS_CODE 2 # define F_OPEN(name, mode) \ fopen((name), (mode), "mbc=60", "ctx=stm", "rfm=fix", "mrs=512") #endif +#ifdef __370__ +# if __TARGET_LIB__ < 0x20000000 +# define OS_CODE 4 +# elif __TARGET_LIB__ < 0x40000000 +# define OS_CODE 11 +# else +# define OS_CODE 8 +# endif +#endif + #if defined(ATARI) || defined(atarist) -# define OS_CODE 0x05 +# define OS_CODE 5 #endif #ifdef OS2 -# define OS_CODE 0x06 -# ifdef M_I86 - #include <malloc.h> +# define OS_CODE 6 +# if defined(M_I86) && !defined(Z_SOLO) +# include <malloc.h> # endif #endif #if defined(MACOS) || defined(TARGET_OS_MAC) -# define OS_CODE 0x07 -# if defined(__MWERKS__) && __dest_os != __be_os && __dest_os != __win32_os -# include <unix.h> /* for fdopen */ -# else -# ifndef fdopen -# define fdopen(fd,mode) NULL /* No fdopen() */ +# define OS_CODE 7 +# ifndef Z_SOLO +# if defined(__MWERKS__) && __dest_os != __be_os && __dest_os != __win32_os +# include <unix.h> /* for fdopen */ +# else +# ifndef fdopen +# define fdopen(fd,mode) NULL /* No fdopen() */ +# endif # endif # endif #endif -#ifdef TOPS20 -# define OS_CODE 0x0a +#ifdef __acorn +# define OS_CODE 13 #endif -#ifdef WIN32 -# ifndef __CYGWIN__ /* Cygwin is Unix, not Win32 */ -# define OS_CODE 0x0b -# endif +#if defined(WIN32) && !defined(__CYGWIN__) +# define OS_CODE 10 #endif -#ifdef __50SERIES /* Prime/PRIMOS */ -# define OS_CODE 0x0f +#ifdef _BEOS_ +# define OS_CODE 16 +#endif + +#ifdef __TOS_OS400__ +# define OS_CODE 18 +#endif + +#ifdef __APPLE__ +# define OS_CODE 19 #endif #if defined(_BEOS_) || defined(RISCOS) # define fdopen(fd,mode) NULL /* No fdopen() */ #endif -#if (defined(_MSC_VER) && (_MSC_VER > 600)) +#if (defined(_MSC_VER) && (_MSC_VER > 600)) && !defined __INTERIX # if defined(_WIN32_WCE) # define fdopen(fd,mode) NULL /* No fdopen() */ # ifndef _PTRDIFF_T_DEFINED @@ -167,10 +183,23 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ # endif #endif +#if defined(__BORLANDC__) && !defined(MSDOS) + #pragma warn -8004 + #pragma warn -8008 + #pragma warn -8066 +#endif + +/* provide prototypes for these when building zlib without LFS */ +#if !defined(_WIN32) && \ + (!defined(_LARGEFILE64_SOURCE) || _LFS64_LARGEFILE-0 == 0) + ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off_t)); + ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off_t)); +#endif + /* common defaults */ #ifndef OS_CODE -# define OS_CODE 0x03 /* assume Unix */ +# define OS_CODE 3 /* assume Unix */ #endif #ifndef F_OPEN @@ -179,40 +208,7 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ /* functions */ -#if defined(STDC99) || (defined(__TURBOC__) && __TURBOC__ >= 0x550) -# ifndef HAVE_VSNPRINTF -# define HAVE_VSNPRINTF -# endif -#endif -#if defined(__CYGWIN__) -# ifndef HAVE_VSNPRINTF -# define HAVE_VSNPRINTF -# endif -#endif -#ifndef HAVE_VSNPRINTF -# ifdef MSDOS - /* vsnprintf may exist on some MS-DOS compilers (DJGPP?), - but for now we just assume it doesn't. */ -# define NO_vsnprintf -# endif -# ifdef __TURBOC__ -# define NO_vsnprintf -# endif -# ifdef WIN32 - /* In Win32, vsnprintf is available as the "non-ANSI" _vsnprintf. */ -# if !defined(vsnprintf) && !defined(NO_vsnprintf) -# define vsnprintf _vsnprintf -# endif -# endif -# ifdef __SASC -# define NO_vsnprintf -# endif -#endif -#ifdef VMS -# define NO_vsnprintf -#endif - -#if defined(pyr) +#if defined(pyr) || defined(Z_SOLO) # define NO_MEMCPY #endif #if defined(SMALL_MEDIUM) && !defined(_MSC_VER) && !defined(__SC__) @@ -236,16 +232,16 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ # define zmemzero(dest, len) memset(dest, 0, len) # endif #else - extern void zmemcpy OF((Bytef* dest, const Bytef* source, uInt len)); - extern int zmemcmp OF((const Bytef* s1, const Bytef* s2, uInt len)); - extern void zmemzero OF((Bytef* dest, uInt len)); + void ZLIB_INTERNAL zmemcpy OF((Bytef* dest, const Bytef* source, uInt len)); + int ZLIB_INTERNAL zmemcmp OF((const Bytef* s1, const Bytef* s2, uInt len)); + void ZLIB_INTERNAL zmemzero OF((Bytef* dest, uInt len)); #endif /* Diagnostic functions */ -#ifdef DEBUG +#ifdef ZLIB_DEBUG # include <stdio.h> - extern int z_verbose; - extern void z_error OF((char *m)); + extern int ZLIB_INTERNAL z_verbose; + extern void ZLIB_INTERNAL z_error OF((char *m)); # define Assert(cond,msg) {if(!(cond)) z_error(msg);} # define Trace(x) {if (z_verbose>=0) fprintf x ;} # define Tracev(x) {if (z_verbose>0) fprintf x ;} @@ -261,13 +257,19 @@ extern const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ # define Tracecv(c,x) #endif - -voidpf zcalloc OF((voidpf opaque, unsigned items, unsigned size)); -void zcfree OF((voidpf opaque, voidpf ptr)); +#ifndef Z_SOLO + voidpf ZLIB_INTERNAL zcalloc OF((voidpf opaque, unsigned items, + unsigned size)); + void ZLIB_INTERNAL zcfree OF((voidpf opaque, voidpf ptr)); +#endif #define ZALLOC(strm, items, size) \ (*((strm)->zalloc))((strm)->opaque, (items), (size)) #define ZFREE(strm, addr) (*((strm)->zfree))((strm)->opaque, (voidpf)(addr)) #define TRY_FREE(s, p) {if (p) ZFREE(s, p);} +/* Reverse the bytes in a 32-bit value */ +#define ZSWAP32(q) ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \ + (((q) & 0xff00) << 8) + (((q) & 0xff) << 24)) + #endif /* ZUTIL_H */ |