diff options
author | nate <nate@FreeBSD.org> | 1993-06-18 18:39:41 +0000 |
---|---|---|
committer | nate <nate@FreeBSD.org> | 1993-06-18 18:39:41 +0000 |
commit | 12c4fd169736d45ab4b2b3f55301ecceaf9c67b3 (patch) | |
tree | ff423954f6049c9cdc9673d76e5867f99adeeb7e | |
parent | 7067738d6ce62410bf037507ed279733f38b3910 (diff) | |
download | FreeBSD-src-12c4fd169736d45ab4b2b3f55301ecceaf9c67b3.zip FreeBSD-src-12c4fd169736d45ab4b2b3f55301ecceaf9c67b3.tar.gz |
Gzip 1.1
41 files changed, 10430 insertions, 0 deletions
diff --git a/gnu/usr.bin/gzip/COPYING b/gnu/usr.bin/gzip/COPYING new file mode 100644 index 0000000..a43ea21 --- /dev/null +++ b/gnu/usr.bin/gzip/COPYING @@ -0,0 +1,339 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 675 Mass Ave, Cambridge, MA 02139, USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + Appendix: How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) 19yy <name of author> + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) 19yy name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + <signature of Ty Coon>, 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/gnu/usr.bin/gzip/ChangeLog b/gnu/usr.bin/gzip/ChangeLog new file mode 100644 index 0000000..5238071 --- /dev/null +++ b/gnu/usr.bin/gzip/ChangeLog @@ -0,0 +1,450 @@ +Tue Jun 1 09:07:15 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.1.1 + Fix serious bug in vms.c (== instead of =). + Added --ascii option. + Add workaround in configure.in for Ultrix (quote eval argument) + Do not use unset in znew (not supported on Ultrix) + Use tar.gz instead of tar.z for the distribution of gzip. + Add missing menu item in gzip.texi. + Use size_t instead of unsigned, add AC_SIZE_T in configure.in. + +Fri May 28 11:40:01 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.1 + Use .gz suffix by default, add --suffix option. + Let gunzip accept a "_z" suffix (used by one 'compress' on Vax/VMS). + Quit when reading garbage from stdin instead of reporting an error. + Added sub.c and add.c for compression of 8 bit images. + Added makefile for VAX/MMS and support for wildcards on VMS. + Added support for MSC under OS/2. + Added support for Prime/PRIMOS. + Display compression ratio also when decompressing. + Quit after --version (GNU standard) + Use --force to bypass isatty() check. + Accept --silent as synonym for --quiet (see longopts.table) + Accept --to-stdout as synonym for --stdout (see longopts.table) + Accept -H and -? in addition to -h and --help. + Added comparison of zip and gzip in the readme file. + Return an error code in all main compression/decompression functions. + Continue processing other files in case of recoverable error. + Add description of -f in znew.1. + Do not keep uncompressed version for znew -t if .gz already exists. + On Unix, use only st_ino and st_dev in same_file(). + Use S_IRUSR and S_IWUSR if they exist. + "test $1 = -d" -> "test x$1 = x-d" in gzexe. + In match.S, use symbol sysV68 to detect the Motorola Delta. + Do not include memory.h with gcc (conflicting declarations on Sun). + Fix more typos. + On VMS, define unlink as delete also for gcc. + In "make check", unset LANG because "wc -c" fails on Kanji. + Renamed shdir as scriptdir. + Use the 68020 code instead of 68000 code on the NeXT. + Documented --uncompress as synonym for --decompress. + Include the standard header files before gzip.h (needed on Bull). + Do not assume that _POSIX_VERSION implies dirent.h present. + Removed gzip-tar.patch since tar 1.11.2 handles gzip directly. + Use less memory when compiled with -DSMALL_MEM (for MSDOS). + Optimized updcrc(). + Don't complain if cc -E does not work correctly. + Do not attempt reading 64K bytes on 16 bit Unix systems. + Do not use the variable name 'overhead' which is reserved on Lynx! + One BULL compiler does not like *p++ in inflate.c => *p, p++. + Use casts on free and memcmp to avoid warnings. + Remove the "off by more than one minute" time stamp kludge, but + document how to avoid saving the time stamp on pipes if desired. + Include crypt.h in inflate.c (one system predefines the CRYPT symbol). + Add links to gunzip and (g)zcat in the default make rule. + Create installation directories if they do not exist. + Clarified --prefix option in INSTALL. + Use symbol mc68k in match.S for the DIAB DS90. + Guard against zero length _match.s in configure.in. + In zmore, restore all tty options using stty -g. + Added support for MacOS + Simplified makecrc.c. + Avoid warnings in getopt.c, util.c, unlzw.c. + Use autoconf 1.4, in particular for INSTALL and AC_HAVE_POUNDBANG + Use .so instead of hard links for zcat.1, gunzip.1 and zcmp.1. + Fixed declration of sig_type. + Make consistency check in fcfree. + Added ztouch. + Do not complain if utime fails on a directory (for OS/2). + +Thu Mar 18 18:56:43 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.7 + Allow zmore to read from standard input (like more). + Support the 68000 (Atari ST) in match.S. + Retry partial writes (required on Linux when gzip is suspended in + a pipe). + Allow full pathnames and renamings in gzexe. + Don't let gzexe compress setuid executables or gzip itself. + Added vms/Makefile.gcc for gcc on the Vax. + Give a pointer to Solaris and VMS executables of gzip in README. + Allow installation of binaries and shell scripts in different dirs. + Do not use alloca on the Cray. + Provide strspn and strcspn if string.h does not exist. + Define O_CREAT and O_EXCL from FCREAT and FEXCL if necessary. + Remove gzip.doc in make realclean. + Fixed many typos. (Corrections to my English are welcome.) + Put "make manext=l install" at the correct place in INSTALL. + Fix incorrect examples in INSTALL and give more examples. + Include zdiff.1 for install and uninstall. + Allows complex PAGER variable in zmore (e.g.: PAGER="col -x | more") + Avoid warning on unused indfound in getopt.c. + Cast memset arg to void* (required by some buggy compilers). + Include sys/types.h before dirent.h in acgeneral.m4. + Fix acgeneral.m4 AC_COMPILE_CHECK to avoid warnings. + Don't use alloca.c with gcc. (One NeXT user did not have alloca.h). + Change all error messages according to GNU standards. + Restore time stamp only if off by more than one minute. + Allow installation of zcat as gzcat. + Suppress help message and send compressed data to the terminal when + gzip is invoked without parameters and without redirection. + (Explicit request from Noah Friedman.) + Add compile option GNU_STANDARD to respect the GNU coding standards: + with -DGNU_STANDARD, behave as gzip even if invoked under the + name gunzip. (Complaints to /dev/null or the FSF, not to me!) + +Fri Mar 10 13:27:18 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.6 + Let gzexe detect executables that are already gzexe'd. + Don't try restoring record format on VMS (the simple 1.0.5 code + worked correctly only on fixed-512 files). Suppress text_mode. + Added asm version for 68000 in amiga/match.a. + Use asm version for Atari TT. + Fix "make clean" in vms/Makefile.vms. + For OS/2, assume HPFS by default, add flag OS2FAT if necessary. + Fixed some bugs in zdiff and define zcmp as a link to zdiff. + Added zdiff.1 + Remove configure hack for NeXT; add general fix to autoconf instead + Do not strip a ".z" extension if this results in an empty name. + Avoid array overflow in get_prefix() for extensions > 10 chars. + Accept either q or e to quit zmore. + In zmore, try restoring tty mode in all cases. + Use Motorola style for match.S on the NeXT. + configure.in: unsetenv *hangs* with the Siemens csh... + Update vms/gzip.hlp. + +Thu Mar 4 14:13:34 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.5 + For VMS, restore the file type for variable record format, otherwise + extract in fixed length format (not perfect, but better than + forcing all files to be in stream_LF format). + Use "-z" suffix for VMS. + Use only .z, .*-z, .tgz, .taz as valid gzip extensions; update + zforce accordingly. + Allow a version number in input file names for VMS. + Added sample program zread.c. + Fix "make check" for some implementations of /bin/sh. + Don't rely on stat() for filenames with extension > 3 chars + on MSDOS, OS2 and Atari. + Garbage collect files in /tmp created by gzexe. + Quote $opt in znew. + Use TOUCH env variable in znew if it exists. + Better error message for gunzip on empty or truncated file. + Allow prototypes in getopt.h when __STDC__ defined but 0. + Added "make clean" in vms/Makefile.vms. + Removed -g from default CFLAGS (with Noah's permission!) + Avoid too many HAVE_xxx_H for most systems; use common defaults. + Moved default Atari flags into tailor.h for consistency. + Use memzero() to clear the hash table. + Update vms/gzip.hlp to reflect the VMS behavior. + Fix OS_CODE (to fit in a byte). + Add utime.h for the Amiga. + Add gcc support for the Amiga. + Work around incorrect dirent.h for NeXT 2.0. + Added Makefile entry for Coherent. + +Fri Feb 22 11:20:49 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.4 + Added optimized asm version for 68020. + Add support for DJGPP. + Add support for the Atari ST. + Added zforce to rename gzip'ed files with truncated names. + Do not install with name uncompress (some systems rely on the + absence of any check in the old uncompress). + Added missing function (fcfree) in msdos/tailor.c + Let gunzip handle .tgz files, and let gzip skip them. + Added 'stty min 1' in zmore for SysV and fixed trap code. + Suppress .PHONY in Makefile.in, which breaks old makes. + Added documentation about pcat and unpack in INSTALL. + Add cast to getenv for systems without stdlib.h. + Use VAXC instead of VMS to avoid confusion for gcc. + Add -K to znew.1. + Add gzexe.1. + Try preserving file permissions in gzexe. + Added -d option for gzexe. + Guard against spaces in file names in gzexe. + Use CMP env. variable in zcmp. + Return a warning exit status for gzip of file with .z suffix. + Suppress usage of d_ino which is not portable to all systems. + Use #ifdef instead of #if for consistency. + For VMS, use "cc util.c" instead of "cc util" (pb with logical names) + Added utime() for Amiga. + Renamed gzcat.1 as zcat.1. + Include fcntl.h for Amiga (for read and write). + For VMS, add definition of symbols and links in the makefiles. + Give a VMS look to vms/gzip.hlp. + Save the original name only when necessary. + Add a mode parameter for open in read mode (required by VMS). + For VMS, remove the version suffix from the original name. + Accept both / and \ as path separator for MSDOS. + Let gunzip extract stored .zip files correctly. + Added warning about VFC format in vms/gzip.hlp. + In znew, skip a bad file but process the others. + Cleanup tailor.h. + Use GZIP_OPT for VMS to avoid conflict with program name. + Added description of GZIP variable in gzip.texi. + +Thu Feb 11 17:21:32 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.3 + Add -K option for znew to keep old .Z files if smaller. + Add -q option (quiet) to cancel -v in GZIP env variable. + For Turbo C, normalize pointers before freeing them. + Add more safety checks in add_envopt(). + Add do_exit() for uniform exit path (always free memory). + Reduce MAX_PATH_LEN for MSDOS. + Include sys/types.h before signal.h + Avoid strdup, the NeXT does not have it. + Made gzexe safer on systems with filename limitation to 14 chars. + +Fri Feb 10 09:45:49 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.2 + Added env variable GZIP for default options. + Added support for the Amiga. + znew now keeps the old .Z if it is smaller than the .z file. + Added gzexe to compress rarely used executables. + Reduce memory usage when using static allocation (no DYN_ALLOC). + Better separation of warning and error return codes. + Fix unlzw.c to make DYN_ALLOC and MAXSEG_64K independent options. + Allow INBUFSIZ to be >= 32K in unlzw (don't use sign of rsize) + Generate tar file in old format to avoid problems with old systems. + Preserve time stamp in znew -P if touch -r works. + Use ${PAGER-more} instead of ${PAGER:-more} in zmore. + Do not use unsigned instead of mode_t. + Better error message for trailing garbage in .z file; ignore this + garbage on VMS. + In zmore, use icanon instead of -cbreak on SYSV. + Add trap handler in zmore. + Use char* instead of void* for non STDC compilers. + Added makefile entry for Xenix on 286. + Return an error code when existing file was not overwritten. + Use prototype of lzw.h for lzw.c. + Fix znew with -P option alone. + Give warning for directories even without -v. + Close output file before unlink() in case of error. + Suppress all target dependent ifdef from the portable files. + Free all dynamically allocated variables upon exit. + +Thu Feb 4 18:23:56 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0.1 + Fixed some trivial errors in msdos/Makefile.bor + +Thu Feb 4 10:00:59 1993 Jean-loup Gailly (jloup@chorus.fr) + + * version 1.0 + gzip now runs on Vax/VMS (Amiga support will come in next version). + Do not overwrite files without -f when using /bin/sh. + Support the test option -t for compressed (.Z) files. + Flush output for bad compressed files. Add warning in README. + Added makefiles for MSDOS. + Don't rely on presence of csh in configure + Added gunzip.1 and gzcat.1. + Updated znew.1. + Check reserved flags in unlzw(). + Return dummy value in main to avoid lint warning. + Define OF in lzw.h for lint. + Allow both "znew -v -t" and "znew -vt". + Don't overwrite the output file name for multiple parts. + Echo just a warning if configure is out of date. + Use ; instead of , in trees.c (confuses the SAS Amiga compiler). + In INSTALL, document "DEFS='-DM_XENIX' ./configure". + Use OTHER_PATH_SEP for more portability (DOS, OS2, VMS, AMIGA). + Make all directories world writable for broken versions of tar. + Use gzip -cd instead of zcat in zmore, zcmp, zdiff. + Don't use GNU tar for distributions, some systems can't untar. + Do not exit() for gzip --version. + +Mon Jan 26 10:26:42 1993 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.8.2 + Avoid 'far' declarations for MSDOS. + Use test -f instead of test -x in configure.in (for Ultrix) + Add empty else part to if in Makefile.in for broken shells. + Use NO_UNDERLINE instead of UNDERLINE (pb with Linux cpp) + Accept continuation files with -ff (for damage recovery) + Small patch to Makefile.os2 + Use memzero instead of bzero to avoid potential conflicts + Document restriction on extraction of zip files. + Fix quoting in ACL_HAVE_SHELL_HACK. + Do not check file size on MSDOS because of bug in DIET. + Allow zcat on a file with multiple links. + Add fix in inflate.c for compatibility with pkzip 2.04c. + Release gzip in tar.z and tar format. (No tar.Z). + +Fri Jan 22 10:04:13 1993 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.8.1 + Fixed Makefile.os2 + Fixed #if directives that TurboC does not like. + Don't rely on uncompress in znew, use gzip -d. + Add the pipe option -P in znew. + Add some more ideas in TODO. + Support both NDIR and SYSNDIR. + +Sat Jan 21 15:46:38 1993 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.8 + Support unpack. + Check for _match.o in configure.in in addition to return status. + Include <sys/types.h> in zip.c + Define local variables and functions as local. + Accept more alternative names for the program (pcat, gzcat, ...). + Accept .exe as well as .EXE. + Uncompress files with multiple links only with -f. + Better error message for gunzip of non-existent file.z. + Fix the entry for /etc/magic in INSTALL. + Use AC_HAVE_HEADERS uniformly instead of special macros. + Install the man pages as .1 by default instead of .l. + Document crypt++.el in README. + Fix for unlzw() on 16-bit machines (bitmask must be unsigned). + Complain if input and output files are identical. + Create a correct output name for files of exactly 13 chars. + Do not overwrite CPP if set + Check for i386 before trying to assemble match.s + Check for underline in external name before assembling + Add patch for tar 1.11.1. + +Mon Jan 5 10:16:24 1993 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.7 + Use "make check" instead of "make test". + Do not rely on dirname in znew. + Keep time stamp and pass options to gzip in znew. + Rename .l files back to .1 to avoid conflict with lex + Do not create .z.z files with gzip -r. + Use nice_match in match.asm + Unroll loops in deflate.c + Do not attempt matches beyond the window end + Allow again gunzip .zip files (was working in 0.5) + Allow again compilation with TurboC 2.0 (was working in 0.4) + +Tue Dec 30 20:00:19 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.6 + The .z extension is used by pack, not compact (README, gzip.1) + Accept gzcat in addition to zcat. + Use PAGER in zmore if defined. + Man pages for /usr/local/man/manl should have extension .l. + Don't redefine bzero on the NeXT + Allow incomplete Huffman table if there is only one code. + Don't lookahead more than 7 bits (caused premature EOF). + Added "make test" to check for compiler bugs. + Don't rely on `i386`; try to assemble directly + Change magic header to avoid conflict with freeze 1.x. + Added entry for /etc/magic in INSTALL. + Do not destroy an input .zip file with more than one member. + Display "untested" instead of "OK" for gzip -t foo.Z + With -t, skip stdin in .Z format + Allow multiple compressed members in an input file. + Ignore a zero time stamp. + Made znew safer. + +Tue Dec 29 10:00:19 1992 Noah Friedman (friedman@gnu.ai.mit.edu) + + Added test for #!/bin/sh in configure.in. + Fix some references to $srcdir in Makefile.in + +Mon Dec 21 17:33:35 1992 Jean-Loup Gailly (jloup@chorus.fr) + + * Beta version 0.5 + Put RCS ids in all files. + Added znew to recompress old .Z files with gzip. + Avoid "already .z suffix" messages for -r and no -v. + Put back check for d_ino in treat_dir(). + Use HAVE_STRING_H instead of USG. + Added os2/Makefile.os2 + Use SYSUTIME on OS/2. + Info dir is $(prefix)/info, not $(prefix)/lib/info. + Support long options, added getopt and alloca + Support -V and -t + Reorder configure.in according to suggestions in autoconf.info + Allow links when not removing original file + Allow either .z or .Z in zdiff + +Wed Nov 25 11:40:04 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.4.1 + Save only the original base name, don't include any directory prefix. + Don't use HAVE_LONG_FILE_NAMES (support multiple file system types). + Fix declaration of abort_gzip in gzip.h. + Include unistd.h when it exists to avoid warnings with gcc -Wall. + +Mon Nov 23 12:39:01 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.4 + Lots of cleanup + Use autoconf generated 'configure' + Fixed the NO_MULTIPLE_DOTS code + Fixed the save_orig_name code + Support for MSDOS (Turbo C) + +Thu Nov 19 15:18:22 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Beta version 0.3 + Added auto configuration. Just type "make" now. + Don't overwrite compress by default in "make install". Use + "make install_compress" to overwrite. + Add match.s for 386 boxes. + Added documentation in texinfo format. + Provide help for "gunzip" invoked without redirected input. + Save original file name when necessary. + Support OS/2 (Kai-Uwe Rommel). + +Tue Nov 17 14:32:53 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.2.4 + Return 0 in get_istat() when ok (caused error with zcat). + Don't update crc on compressed data (caused crc errors on + large files). + +Fri Nov 13 15:04:12 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.2.3 + Initialize rsize in unlzw.c + Initialize ofd for zcat. + Do not use volatile ifname as argument of treat_dir. + Add -1 to -9 in gzip.1. + +Sat Oct 31 18:30:00 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.2.2. + Fix error messages. + Accept gunzip on zip files. + +Sat Oct 31 17:15:00 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.2.1 + Use ctype.h in util.c (problem on SysV). + Create BINDIR if it does not exist. + Use cc by default. + Added zcmp, zmore, zdiff. + Fixed the man page gzip.1. + +Sat Oct 31 17:00:00 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.2 + Fixed compilation problems with gcc + +Sat Oct 31 12:46:00 1992 Jean-loup Gailly (jloup@chorus.fr) + + * Alpha version 0.1 released (under time pressure), so it's not + much tested, sorry. + diff --git a/gnu/usr.bin/gzip/Makefile b/gnu/usr.bin/gzip/Makefile new file mode 100644 index 0000000..36200b8 --- /dev/null +++ b/gnu/usr.bin/gzip/Makefile @@ -0,0 +1,25 @@ +# @(#)Makefile 5.3 (Berkeley) 5/12/90 + +PROG= gzip +SRCS= gzip.c zip.c deflate.c trees.c bits.c unzip.c inflate.c util.c \ + crypt.c lzw.c unlzw.c unpack.c getopt.c match.S +MAN1= gzexe.0 gzip.0 zdiff.0 zforce.0 zmore.0 znew.0 +CFLAGS+=-DASMV -DHAVE_UNISTD_H=1 -DDIRENT=1 +MLINKS= zdiff.1 zcmp.1 gzip.1 gunzip.1 gzip.1 zcat.1 gzip.1 gzcat.1 +LINKS+= ${DESTDIR}${BINDIR}/gzip ${DESTDIR}${BINDIR}/gunzip +LINKS+= ${DESTDIR}${BINDIR}/gzip ${DESTDIR}${BINDIR}/gzcat +LINKS+= ${DESTDIR}${BINDIR}/gzip ${DESTDIR}${BINDIR}/zcat + +afterinstall: + install -c -o ${BINOWN} -g ${BINGRP} -m ${BINMODE} \ + ${.CURDIR}/zforce ${.CURDIR}/gzexe ${.CURDIR}/znew \ + ${.CURDIR}/zmore ${.CURDIR}/zdiff ${.CURDIR}/zcmp \ + ${DESTDIR}${BINDIR} + +match.o: ${.CURDIR}/match.S + $(CPP) ${.CURDIR}/match.S >_match.s + $(CC) -c _match.s + mv _match.o match.o + rm -f _match.s + +.include <bsd.prog.mk> diff --git a/gnu/usr.bin/gzip/NEWS b/gnu/usr.bin/gzip/NEWS new file mode 100644 index 0000000..097f7b1 --- /dev/null +++ b/gnu/usr.bin/gzip/NEWS @@ -0,0 +1,158 @@ +Current Version: 1.1.1 +See the file ChangeLog for the details of all changes. + +Major changes from 1.1 to 1.1.1. +* Fix serious bug in vms.c (affects Vax/VMS only). +* Added --ascii option. +* Add workaround in configure.in for Ultrix (quote eval argument) + +Major changes from 1.0.7 to 1.1. +* Use .gz suffix by default, add --suffix option. +* Let gunzip accept a "_z" suffix (used by one 'compress' on Vax/VMS). +* Quit when reading garbage from stdin instead of reporting an error. +* Added makefile for VAX/MMS and support for wildcards on VMS. +* Added support for MSC under OS/2. +* Added support for Prime/PRIMOS. +* Display compression ratio also when decompressing (with --verbose). +* Quit after --version (GNU standard) +* Use --force to bypass isatty() check +* Continue processing other files in case of recoverable error. +* Added comparison of zip and gzip in the readme file. +* Added small sample programs (ztouch, sub, add) +* Use less memory when compiled with -DSMALL_MEM (for MSDOS). +* Remove the "off by more than one minute" time stamp kludge + +Major changes from 1.0.6 to 1.0.7. +* Allow zmore to read from standard input (like more). +* Support the 68000 (Atari ST) in match.S. +* Retry partial writes (required on Linux when gzip is suspended in a pipe). +* Allow full pathnames and renamings in gzexe. +* Don't let gzexe compress setuid executables or gzip itself. +* Added vms/Makefile.gcc for gcc on the Vax. +* Allow installation of binaries and shell scripts in different dirs. +* Allows complex PAGER variable in zmore (e.g.: PAGER="col -x | more") +* Allow installation of zcat as gzcat. +* Several small changes for portability to old or weird systems. +* Suppress help message and send compressed data to the terminal when + gzip is invoked without parameters and without redirection. +* Add compile option GNU_STANDARD to respect the GNU coding standards: + with -DGNU_STANDARD, behave as gzip even if invoked under the name gunzip. +(I don't like the last two changes, which were requested by the FSF.) + +Major changes from 1.0.5 to 1.0.6. +* Let gzexe detect executables that are already gzexe'd. +* Keep file attributes in znew and gzexe if cpmod is available. +* Don't try restoring record format on VMS (1.0.5 did not work correctly) +* Added asm version for 68000 in amiga/match.a. + Use asm version for Atari TT and NeXT. +* For OS/2, assume HPFS by default, add flag OS2FAT if necessary. +* Fixed some bugs in zdiff and define zcmp as a link to zdiff. + + +Major changes from 1.0.4 to 1.0.5. +* For VMS, restore the file type for variable record format, otherwise + extract in fixed length format (not perfect, but better than + forcing all files to be in stream_LF format). +* For VMS, use "-z" default suffix and accept a version number in file names. +* For Unix, allow compression of files with name ending in 'z'. Use only + .z, .*-z, .tgz, .taz as valid gzip extensions. In the last two cases, + extract to .tar by default. +* On some versions of MSDOS, files with a 3 character extension could not + be compressed. +* Garbage collect files in /tmp created by gzexe. +* Fix the 'OS code' byte in the gzip header. +* For the Amiga, add the missing utime.h and add support for gcc. + + +Major changes from 1.0.3 to 1.0.4. +* Added optimized asm version for 68020. +* Add support for DJGPP. + +* Add support for the Atari ST. +* Added zforce to rename gzip'ed files with truncated names. +* Do not install with name uncompress (some systems rely on the + absence of any check in the old uncompress). +* Added missing function (fcfree) in msdos/tailor.c +* Let gunzip handle .tgz files, and let gzip skip them. +* Added -d option (decompress) for gzexe and try preserving file permissions. +* Suppress all warnings with -q. +* Use GZIP_OPT for VMS to avoid conflict with program name. +* ... and many other small changes (see ChangeLog) + + +Major changes from 1.0.2 to 1.0.3 +* Added -K option for znew to keep old .Z files if smaller +* Added -q option (quiet) to cancel -v in GZIP env variable. +* Made gzexe safer on systems with filename limitation to 14 chars. +* Fixed bugs in handling of GZIP env variable and incorrect free with Turbo C. + + +Major changes from 1.0.1 to 1.0.2 +* Added env variable GZIP for default options. Example: + for sh: GZIP="-8 -v"; export GZIP + for csh: setenv GZIP "-8 -v" +* Added support for the Amiga. +* znew now keeps the old .Z if it is smaller than the .z file. + This can happen for some large and very redundant files. +* Do not complain about trailing garbage for record oriented IO (Vax/VMS). + This implies however that multi-part gzip files are not supported + on such systems. +* Added gzexe to compress rarely used executables. +* Reduce memory usage (required for MSDOS and useful on all systems). +* Preserve time stamp in znew -P (pipe option) if touch -r works. + + +Major changes from 1.0 to 1.0.1 +* fix trivial errors in the Borland makefile (msdos/Makefile.bor) + + +Major changes from 0.8.2 to 1.0 +* gzip now runs on Vax/VMS +* gzip will not not overwrite files without -f when using /bin/sh in + background. +* Support the test option -t for compressed (.Z) files. + Allow some data recovery for bad .Z files. +* Added makefiles for MSDOS (Only tested for MSC, not Borland). +* still more changes to configure for several systems + + +Major changes from 0.8.1 to 0.8.2: +* yet more changes to configure for Linux and other systems +* Allow zcat on a file with multiple links. + + +Major changes from 0.8 to 0.8.1: +* znew has now a pipe option -P to reduce the disk space requirements, + but this option does not preserve timestamps. +* Fixed some #if directives for compilation with TurboC. + + +Major changes from 0.7 to 0.8: +* gzip can now extract .z files created by 'pack'. +* configure should no longer believe that every machine is a 386 +* Fix the entry for /etc/magic in INSTALL. +* Add patch for GNU tar 1.11.1 and a pointer to crypt++.el +* Uncompress files with multiple links only with -f. +* Fix for uncompress of .Z files on 16-bit machines +* Create a correct output name for file names of exactly N-1 chars when + the system has a limit of N chars. + + +Major changes from 0.6 to 0.7: +* Use "make check" instead of "make test". +* Keep time stamp and pass options to gzip in znew. +* Do not create .z.z files with gzip -r. +* Allow again gunzip .zip files (was working in 0.5) +* Allow again compilation with TurboC 2.0 (was working in 0.4) + + +Major changes form 0.5 to 0.6: +* gunzip reported an error when extracting certain .z files. The .z files + produced by gzip 0.5 are correct and can be read by gunzip 0.6. +* gunzip now supports multiple compressed members within a single .z file. +* Fix the check for i386 in configure. +* Added "make test" to check for compiler bugs. (gcc -finline-functions + is broken at least on the NeXT.) +* Use environment variable PAGER in zmore if it is defined. +* Accept gzcat in addition to zcat for people having /usr/bin before + /usr/local/bin in their path. diff --git a/gnu/usr.bin/gzip/README b/gnu/usr.bin/gzip/README new file mode 100644 index 0000000..152b7e5 --- /dev/null +++ b/gnu/usr.bin/gzip/README @@ -0,0 +1,147 @@ +This is the file README for the gzip distribution, version 1.1.1. + +gzip (GNU zip) is a compression utility designed to be a replacement +for 'compress'. Its main advantages over compress are much better +compression and freedom from patented algorithms. The GNU Project +uses it as the standard compression program for its system. + +gzip currently uses by default the LZ77 algorithm used in zip 1.9 (the +portable pkzip compatible archiver). The gzip format was however +designed to accommodate several compression algorithms. See below +for a comparison of zip and gzip. + +gunzip can currently decompress files created by gzip, compress or +pack. The detection of the input format is automatic. For the +gzip format, gunzip checks a 32 bit CRC. For pack, gunzip checks the +uncompressed length. The 'compress' format was not designed to allow +consistency checks. However gunzip is sometimes able to detect a bad +.Z file because there is some redundancy in the .Z compression format. +If you get an error when uncompressing a .Z file, do not assume that +the .Z file is correct simply because the standard uncompress does not +complain. This generally means that the standard uncompress does not +check its input, and happily generates garbage output. + +gzip produces files with a .gz extension. Previous versions of gzip +used the .z extension, which was already used by the 'pack' +Huffman encoder. gunzip is able to decompress .z files (packed +or gzip'ed). + +Several planned features are not yet supported (see the file TODO). +See the file NEWS for a summary of changes since 0.5. See the file +INSTALL for installation instructions. Some answers to frequently +asked questions are given in the file INSTALL, please read it. (In +particular, please don't ask me once more for an /etc/magic entry.) + +WARNINGS about broken optimizers: + +- on the NeXT, "cc -finline-functions" is broken. gzip produces + valid .z files but they are much too large because the string + matching code misses most matches. Use "cc -O" instead. + +- on the Mips R4000, gcc -O (version 2.3.1) generates bad code, use cc + or just gcc -g instead. + +- gcc 2.3.3 on the SGI Indigo IRIX 4.0.5 also produces bad code. Use + instead: make CC='cc -O2' or gcc without -O. + +- on Sparc with SunOS 4.1.1 and the SC1.0 compiler, the optimizer + works up to -O3 but -O4 does not work. + +- MSC 5.1 with -Ox and -DDYN_ALLOC generates bad code in inflate.c. + The default is static allocation (no DYN_ALLOC) and -Ox works on inflate.c. + But -Ox does not work on util.c, so you must use -Oait -Gs. + +- On dnix 5.3 2.2 cc version 2.37c is buggy. Version 2.38d works. + +For all machines, Use "make check" to check that gzip was compiled correctly. + +Please send all comments and bug reports by electronic mail to: + Jean-loup Gailly <jloup@chorus.fr> + +or, if this fails, to bug-gnu-utils@prep.ai.mit.edu. +Bug reports should ideally include: + + * The complete output of "gzip -V" (or the contents of revision.h + if you can't get gzip to compile) + * The hardware and operating system (try "uname -a") + * The compiler used to compile (if it is gcc, use "gcc -v") + * A description of the bug behavior + * The input to gzip, that triggered the bug + +The package crypt++.el is highly recommended to manipulate gzip'ed +file from emacs. It recognizes automatically encrypted and compressed +files when they are first visited or written. It is available via +anonymous ftp to roebling.poly.edu [128.238.5.31] in /pub/crypt++.el. +The same directory contains also patches to dired, ange-ftp and info. +GNU tar 1.11.2 has a -z option to invoke directly gzip, so you don't have +to patch it. + +The znew and gzexe shell scripts provided with gzip benefit from +(but do not require) the cpmod utility to transfer file attributes. +It is available by anonymous ftp on gatekeeper.dec.com in +/.0/usenet/comp.sources.unix/volume11/cpmod.Z. + +The sample programs zread.c, sub.c and add.c are provided as examples +of useful complements to gzip. Read the comments inside each source file. +The perl script ztouch is also provided as example (not installed +by default since it relies on perl). + + +gzip is free software, you can redistribute it and/or modify it under +the terms of the GNU General Public License, a copy of which is +provided under the name COPYING. The latest version of gzip are always +available by ftp in prep.ai.mit.edu:/pub/gnu, or in any of the prep +mirror sites: + +- sources in gzip-*.tar (or .shar or .tar.z) +- Solaris 2 executables in sparc-sun-solaris2/gzip-binaries-*.tar +- MSDOS lha self-extracting exe in gzip-msdos-*.exe. Once extracted, + copy gzip.exe to gunzip.exe and zcat.exe, or use "gzip -d" to decompress. + +A VMS executable is available in ftp.spc.edu:[.macro32.savesets]gzip-1-*.zip +(use [.macro32]unzip.exe to extract). + +Many thanks to those who provided me with bug reports and feedback. +See the files THANKS and ChangeLog for more details. + + + Note about zip vs. gzip: + +The name 'gzip' was a very unfortunate choice, because zip and gzip +are two really different programs, although the actual compression and +decompression sources were written by the same persons. A different +name should have been used for gzip, but it is too late to change now. + +zip is an archiver: it compresses several files into a single archive +file. gzip is a simple compressor: each file is compressed separately. +Both share the same compression and decompression code for the +'deflate' method. unzip can also decompress old zip archives +(implode, shrink and reduce methods). gunzip can also decompress files +created by compress and pack. zip 1.9 and gzip do not support +compression methods other than deflation. (zip 1.0 supports shrink and +implode). Better compression methods may be added in future versions +of gzip. zip will always stick to absolute compatibility with pkzip, +it is thus constrained by PKWare, which is a commercial company. The +gzip header format is deliberately different from that of pkzip to +avoid such a constraint. + +On Unix, gzip is mostly useful in combination with tar. GNU tar +1.11.2 has a -z option to invoke gzip automatically. "tar -z" +compresses better than zip, since gzip can then take advantage of +redundancy between distinct files. The drawback is that you must +scan the whole tar.z file in order to extract a single file near +the end; unzip can directly seek to the end of the zip file. There +is no overhead when you extract the whole archive anyway. +If a member of a .zip archive is damaged, other files can still +be recovered. If a .tar.z file is damaged, files beyond the failure +point cannot be recovered. (Future versions of gzip will have +error recovery features.) + +gzip and gunzip are distributed as a single program. zip and unzip +are, for historical reasons, two separate programs, although the +authors of these two programs work closely together in the info-zip +team. zip and unzip are not associated with the GNU project. +The sources are available by ftp in + + oak.oakland.edu:/pub/misc/unix/zip19p1.zip + oak.oakland.edu:/pub/misc/unix/unz50p1.tar-z diff --git a/gnu/usr.bin/gzip/THANKS b/gnu/usr.bin/gzip/THANKS new file mode 100644 index 0000000..5c9a47b --- /dev/null +++ b/gnu/usr.bin/gzip/THANKS @@ -0,0 +1,196 @@ +gzip was written by Jean-loup Gailly <jloup@chorus.fr>, with +portions written by Mark Adler (inflate.c) and Peter Jannesen +(unlzw.c). The zip deflate format was defined by Phil Katz. +Thanks to those who reported problems and suggested +various improvements. Here is a partial list of them: + +Mark Adler madler@cco.caltech.edu +Edwin Allum edwin@csri.toronto.edu +Joseph Arceneaux jla@gnu.ai.mit.edu +Tim Auckland tda10@cus.cam.ac.uk +Ken-ichiro Aoki aoki@madonna.physics.ucla.edu +David Ascher da@marlowe.cog.brown.edu +Eric Backus ericb@lsid.hp.com +Becky A. Badgett badgett@cs.utexas.edu +Dave Barber dbarber@apocalypse.bbn.com +Rene Beaulieu reneb@distri.hydro.qc.ca +Neal Becker neal@ctd.comsat.com +Dieter Becker becker@med-in.uni-sb.de +Nelson H. F. Beebe beebe@geronimo.math.utah.edu +Jeff Beadles jeff@onion.rain.com +David J. N. Begley dbegley@st.nepean.uws.edu.au +Jim Bernard jbernard@iola.mines.colorado.edu +Karl Berry karl@cs.umb.edu +James W. Birdsall jwbirdsa@picarefy.picarefy.com +Wayne E. Bouchard web@paladine.hacks.arizona.edu +Marc Boucher marc@cam.org +Ola Brahammar pt90ob@pt.hk-r.se +Dave Brennan brennan@hal.com +Alan Brown dogbowl@dogbox.acme.gen.nz +Rodney Brown rdb@mel.cocam.oz.au +Bruce bde@runx.oz.au +Leila Burrell-Davis leilabd@syma.sussex.ac.uk +Roger Butenuth butenuth@ira.uka.de +Bud Carlson bud@isle.pegasus.com +Lim Fung Chai fclim@i1sin.daq.semi.harris.com +Wes Chalfant wes@kofax.com +Paul Close pdc@lunch.wpd.sgi.com +Kevin Cosgrove kevinc@tekig6.pen.tek.com +Stephen J Cowley s.j.cowley@amtp.cam.ac.uk +Frank Crawford frank@photon.ansto.gov.au +James R. Crawford qralston@cislabs.pitt.edu +Lawrence Crowl crowl@research.cs.orst.edu +Klaus Dahlenburg kdburg@incoahe.hanse.de +William E Davidsen davidsen@ariel.crd.ge.com +Jeff Deifik jdeifik@isi.edu +Vince DeMarco vince@whatnxt.cuc.ab.ca +Michael De La Rue p91152@cplab.physics.edinburgh.ac.uk +Lawrence R. Dodd dodd@roebling.poly.edu +Matthew Donadio donadio@mxd120.rh.psu.edu +Andy Dougherty andy@crystal.phys.lafayette.edu +John Eaton jwe@che.utexas.edu +Brian Edmonds edmonds@edmonds.home.cs.ubc.ca +Paul Eggert eggert@twinsun.com +Enami enami@sys.ptg.sony.co.jp +Kristoffer Eriksson ske@pkmab.se +Daniel Eriksson m91der@bellatrix.tdb.uu.se +Rik Faith faith@cs.unc.edu +Larry Fahnoe fahnoe@c1mpls.mn.org +Cristian Ferretti cfs@poincare.mat.puc.cl +Karl-Jose Filler pla_jfi@pki-nbg.philips.de +Per Foreby perf@efd.lth.se +Alexander Fraser alex@cs.umb.edu +Noah Friedman friedman@gnu.ai.mit.edu +Bob Friesenhahn bfriesen@iphase.com +Andy Fyfe andy@scp.caltech.edu +Geoff geoff@frs.faxon.com +Kaveh R. Ghazi ghazi@staccato.rutgers.edu +Torbjorn Granlund tege@sics.se +Carl Greco cgreco@parrot.creighton.edu +Bruno Haible haible@ma2s2.mathematik.uni-karlsruhe.de +Junio Hamano junio@shadow.twinsun.com +Harald Hanche-Olsen hanche@ams.sunysb.edu +Darrel R. Hankerson hankedr@mail.auburn.edu +Ruediger Helsch ruediger@ramz.ing.tu-bs.de +Mark C. Henderson mch@sqwest.wimsey.bc.ca +Karl Heuer karl@kelp.boston.ma.us +Thomas Hiller hiller@fzi.de +Eiji Hirai hirai@cc.swarthmore.edu +Kjetil Torgrim Homme kjetilho@ifi.uio.no +Preston Hunt gt5708a@prism.gatech.edu +Shane C Hutchins sch@nymph.msel.unh.edu +Hutch hutchinson@wrair-emh1.army.mil +Lester Ingber ingber@alumni.caltech.edu +Ken Ishii ishii@sni-usa.com +Per Steinar Iversen iversen@vsfys1.fi.uib.no +Michal Jaegermann ntomczak@vm.ucs.ualberta.ca +Brian Jones brianj@skat.usc.edu +Denny de Jonge witaddj@dutrex.tudelft.nl +Arne H. Juul arnej@lise.unit.no +Dana Jacobsen jacobsd@solar.cor2.epa.gov +Peter Jannesen peter@ncs.nl +Sarantos Kapidakis sarantos%manteion@ics.forth.gr +Amir J. Katz amir@matis.ingr.com +Steve Kelem kelem@castor.xilinx.com +Randy Kirchhof rkk@posms.aus.tx.us +Ned Kittlitz kittlitz@seagoon.sw.stratus.com +Pete Klammer pklammer@ouray.denver.colorado.edu +Fritz Kleemann kleemann@informatik.uni-wuerzburg.dbp.de +Tom Kloos tk@sequent.com +Carsten Koch carsten.koch@icem.de +Winfried Koenig win@in.rhein-main.de +Steph Konigsdorfer s.konigsdorfer@frmy.bull.fr +Michael D. Lawler mdlawler@bsu-cs.bsu.edu +Kevin Layer layer@franz.com +Howard D. Leadmon howardl@wb3ffv.ampr.org +Alexander Lehmann alex@hal.rhein-main.de +Simon Leinen simon@lia.di.epfl.ch +Hugues Leroy hugues.leroy@irisa.fr +Charles Levert charles@aramis.comm.polymtl.ca +Torbj|rn Lindh toobii@elixir.e.kth.se +David R. Linn drl@vuse.vanderbilt.edu +Antonio Lioy cat@athena.polito.it +Jamie Lokier u90jl@ecs.oxford.ac.uk +David J. MacKenzie djm@eng.umd.edu +John R MacMillan john@chance.gts.org +Ron Male male@eso.mc.xerox.com +Steeve McCauley steeve@pooh.geophys.mcgill.ca +Tod McQuillin mcquill@ccit05.duq.edu +Tye McQueen tye@spillman.com +Bernd Melchers melchers@chemie.fu-berlin.de +Jason Merrill jason@jarthur.claremont.edu +Dean S. Messing deanm@medulla.labs.tek.com +Luke Mewburn zak@rmit.edu.au +Jim Meyering meyering@cs.utexas.edu +Frederic Miserey miserey@laguna.ics.uci.edu +Marcel J.E. Mol marcel@duteca.et.tudelft.nl +Chris Moore moore@src.bae.co.uk +Helmut Muelner hmuelner@fiicmds04.tu-graz.ac.at +Urban D Mueller umueller@amiga.physik.unizh.ch +Timothy Murphy tim@maths.tcd.ie +Greg Naber greg@squally.halcyon.com +Karl L. Noell noell@informatik.fh-wiesbaden.dbp.de +Arthur David Olson ado@elsie.nci.nih.gov +Piet van Oostrum piet@cs.ruu.nl +Rafael R. Pappalardo rafapa@obelix.cica.es +Hal Peterson hrp@pecan.cray.com +Pascal Petit petit@cadillac.ibp.fr +Bruno Pillard bp@chorus.fr +Franc,ois Pinard pinard@iro.umontreal.ca +Jay Pinkos pinkos@butyng.bu.edu +Thomas Plass thomas@cogsci.ed.ac.uk +Mike Polo mikep@cfsmo.honeywell.com +Francesco Potorti pot@fly.cnuce.cnr.it +David Purves purves@apogee.com +Andreas Raab ar@nvmr.robin.de +Eric S. Raymond esr@snark.thyrsus.com +Klaus Reimann kr@cip.physik.uni-stuttgart.de +Michael Rendell michael@mercury.cs.mun.ca +Roland B Roberts roberts@nsrl31.nsrl.rochester.edu +Kevin Rodgers kevin@rolling-stone.den.mmc.com +Kai Uwe Rommel rommel@informatik.tu-muenchen.de +Paul Rubin phr@america.telebit.com +Wolfgang Rupprecht wolfgang@wsrcc.com +Jonathan Ryshpan jon@amito.hitachi.com +Paul A Sand pas@unh.edu +Tony Sanders sanders@bsdi.com +Mike Sangrey mike@sojurn.lns.pa.us +Niimi Satoshi a01309@cfi.waseda.ac.jp +Marc Schaefer sysadm@alphanet.ch +Andreas Schwab schwab@lamothe.informatik.uni-dortmund.de +Eric Schenk schenk@cs.toronto.edu +Rick Sladkey jrs@world.std.com +Daniel L Smith dls@autodesk.com +Fred Smith fredex%fcshome@merk.merk.com +Paul Southworth pauls@css.itd.umich.edu +Rob Spencer robbie@winkle.bhpese.oz.au +Richard Stallman rms@gnu.ai.mit.edu +Carsten Steger carsten.steger@informatik.tu-muenchen.de +Ed Sznyter ews@babel.babel.com +Hideaki Tanabe arctanx@iyeyasu.ynl.t.u-tokyo.ac.jp +Andrew Telford ajt@peregrin.resmel.bhp.com.au +Glenn E. Thobe thobe@getunx.info.com +Kei Thomsen kt@keihh.hanse.de +Karsten Thygesen karthy@dannug.dk +Mark Towfiq towfiq@microdyne.com +Jeff Treece treece@sabbagh.com +Oliver Trepte oliver@ikaros.fysik4.kth.se +Stephane Tsacas slt@is21.isoft.fr +Stephen Tweedie sct@dcs.ed.ac.uk +Sotiris Vassilopoulos vassilopoulos@virginia.edu +Pedro A. M. Vazquez vazquez@iqm.unicamp.br +Arjan de Vet devet@win.tue.nl +Vadim V. Vlasov vvlasov@inucres.msk.su +Eduard Vopicka eduard.vopicka@vse.cs +Theo Vosse vosse@ruls41.leidenuniv.nl +Marcel Waldvogel marcel@nice.usergroup.ethz.ch +Stephen J. Walick steve@nshore.org +Gray Watson gray@antaire.com +Scott Weikart scott@igc.apc.org +Ivo Welch iwelch@agsm.ucla.edu +Gijsb. Wiesenekker wiesenecker@sara.nl +Wietze van Winden wietze@swi.psy.uva.nl +Larry W. Virden lwv26@cas.org +Bill Wohler wohler@sap-ag.de +Jamie Zawinski jwz@lucid.com +Christos Zoulas christos@deshaw.com diff --git a/gnu/usr.bin/gzip/TODO b/gnu/usr.bin/gzip/TODO new file mode 100644 index 0000000..1587c75 --- /dev/null +++ b/gnu/usr.bin/gzip/TODO @@ -0,0 +1,58 @@ +TODO file for gzip. + +Some of the planned features include: + +- Structure the sources so that the compression and decompression code + form a library usable by any program, and write both gzip and zip on + top of this library. This would ideally be a reentrant (thread safe) + library, but this would degrade performance. In the meantime, you can + look at the sample program zread.c. + +- Make it convenient to define alternative user interfaces (in + particular for windowing environments). + +- Support in-memory compression for arbitrarily large amounts of data + (zip currently supports in-memory compression only for a single buffer.) + +- Map files in memory when possible, this is generally much faster + than read/write. (zip currently maps entire files at once, this + should be done in chunks to reduce memory usage.) + +- Add a super-fast compression method, suitable for implementing + file systems with transparent compression. One problem is that the + best candidate (lzrw1) is patented twice (Waterworth 4,701,745 + and Gibson & Graybill 5,049,881). The lzrw series of algorithms + are available by ftp in ftp.adelaide.edu.au:/pub/compression/lzrw*. + +- Add a super-tight (but slow) compression method, suitable for long + term archives. One problem is that the best versions of arithmetic + coding are patented (4,286,256 4,295,125 4,463,342 4,467,317 + 4,633,490 4,652,856 4,891,643 4,905,297 4,935,882 4,973,961 + 5,023,611 5,025,258). + + Note: I will introduce new compression methods only if they are + significantly better in either speed or compression ratio than the + existing method(s). So the total number of different methods should + reasonably not exceed 3. (The current 9 compression levels are just + tuning parameters for a single method, deflation.) + +- Add optional error correction. One problem is that the current version + of ecc cannot recover from inserted or missing bytes. It would be + nice to recover from the most common error (transfer of a binary + file in ascii mode). + +- Add a block size (-b) option to improve error recovery in case of + failure of a complete sector. Each block could be extracted + independently, but this reduces the compression ratio. + +- Use a larger window size to deal with some large redundant files that + 'compress' currently handles better than gzip. + +- implement the following options: + + -e encrypt + -l list .z file contents + +- support .Z files in SCO 'compress -H' format. + +Send comments to Jean-loup Gailly <jloup@chorus.fr>. diff --git a/gnu/usr.bin/gzip/algorithm.doc b/gnu/usr.bin/gzip/algorithm.doc new file mode 100644 index 0000000..9c4b0c2 --- /dev/null +++ b/gnu/usr.bin/gzip/algorithm.doc @@ -0,0 +1,141 @@ +1. Algorithm + +The deflation algorithm used by zip and gzip 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 zip determines that it +would be useful to start another block with fresh trees. (This is +somewhat similar to 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 (zip -1 +to -9). So zip does not always find the longest possible match but +generally finds a match which is long enough. + +zip also defers the selection of matches with a lazy evaluation +mechanism. After a match of length N has been found, zip 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 longer match is emitted afterwards. 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, zip reduces the search for a longer +match, thus speeding up the whole process. If compression ratio is more +important than speed, zip attempts a complete second search even if +the first match is already long enough. + + +2. gzip file format + +The pkzip format imposes a lot of overhead in various headers, which +are useful for an archiver but not necessary when only one file is +compressed. gzip uses a much simpler structure. Numbers are in little +endian format, and bit 0 is the least significant bit. +A gzip file is a sequence of compressed members. Each member has the +following structure: + +2 bytes magic header 0x1f, 0x8b (\037 \213) +1 byte compression method (0..7 reserved, 8 = deflate) +1 byte flags + bit 0 set: file probably ascii text + bit 1 set: continuation of multi-part gzip file + bit 2 set: extra field present + bit 3 set: original file name present + bit 4 set: file comment present + bit 5 set: file is encrypted + bit 6,7: reserved +4 bytes file modification time in Unix format +1 byte extra flags (depend on compression method) +1 byte operating system on which compression took place + +2 bytes optional part number (second part=1) +2 bytes optional extra field length +? bytes optional extra field +? bytes optional original file name, zero terminated +? bytes optional file comment, zero terminated +12 bytes optional encryption header +? bytes compressed data +4 bytes crc32 +4 bytes uncompressed input size modulo 2^32 + +The format was designed to allow single pass compression without any +backwards seek, and without a priori knowledge of the uncompressed +input size or the available size on the output media. If input does +not come from a regular disk file, the file modification time is set +to the time at which compression started. + +The time stamp is useful mainly when one gzip file is transferred over +a network. In this case it would not help to keep ownership +attributes. In the local case, the ownership attributes are preserved +by gzip when compressing/decompressing the file. A time stamp of zero +is ignored. + +Bit 0 in the flags is only an optional indication, which can be set by +a small lookahead in the input data. In case of doubt, the flag is +cleared indicating binary data. For systems which have different +file formats for ascii text and binary data, the decompressor can +use the flag to choose the appropriate format. + +It must be possible to detect the end of the compressed data with any +compression format, regardless of the actual size of the compressed +data. If the compressed data cannot fit in one file (in particular for +diskettes), each part starts with a header as described above, but +only the last part has the crc32 and uncompressed size. A decompressor +may prompt for additional data for multipart compressed files. It is +desirable but not mandatory that multiple parts be extractable +independently so that partial data can be recovered if one of the +parts is damaged. This is possible only if no compression state is +kept from one part to the other. The compression-type dependent flags +can indicate this. + +If the file being compressed is on a file system with case insensitive +names, the original name field must be forced to lower case. There is +no original file name if the data was compressed from standard input. + +Compression is always performed, even if the compressed file is +slightly larger than the original. The worst case expansion is +a few bytes for the gzip file header, plus 5 bytes every 32K block, +or an expansion ratio of 0.015% for large files. Note that the actual +number of used disk blocks almost never increases. + +The encryption is that of zip 1.9. For the encryption check, the +last byte of the decoded encryption header must be zero. The time +stamp of an encrypted file might be set to zero to avoid giving a clue +about the construction of the random header. + +Jean-loup Gailly +jloup@chorus.fr + +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. + +APPNOTE.TXT documentation file in PKZIP 1.93a. It is available by +ftp in ftp.cso.uiuc.edu:/pc/exec-pc/pkz193a.exe [128.174.5.59] +Use "unzip pkz193a.exe APPNOTE.TXT" to extract. diff --git a/gnu/usr.bin/gzip/bits.c b/gnu/usr.bin/gzip/bits.c new file mode 100644 index 0000000..65e78a6 --- /dev/null +++ b/gnu/usr.bin/gzip/bits.c @@ -0,0 +1,205 @@ +/* bits.c -- output variable-length bit strings + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + + +/* + * PURPOSE + * + * Output variable-length bit strings. Compression can be done + * to a file or to memory. (The latter is not supported in this version.) + * + * DISCUSSION + * + * The PKZIP "deflate" file format interprets compressed file data + * as a sequence of bits. Multi-bit strings in the file may cross + * byte boundaries without restriction. + * + * The first bit of each byte is the low-order bit. + * + * The routines in this file allow a variable-length bit value to + * be output right-to-left (useful for literal values). For + * left-to-right output (useful for code strings from the tree routines), + * the bits must have been reversed first with bi_reverse(). + * + * For in-memory compression, the compressed bit stream goes directly + * into the requested output buffer. The input data is read in blocks + * by the mem_read() function. The buffer is limited to 64K on 16 bit + * machines. + * + * INTERFACE + * + * void bi_init (FILE *zipfile) + * Initialize the bit string routines. + * + * void send_bits (int value, int length) + * Write out a bit string, taking the source bits right to + * left. + * + * int bi_reverse (int value, int length) + * Reverse the bits of a bit string, taking the source bits left to + * right and emitting them right to left. + * + * void bi_windup (void) + * Write out any remaining bits in an incomplete byte. + * + * void copy_block(char *buf, unsigned len, int header) + * Copy a stored block to the zip file, storing first the length and + * its one's complement if requested. + * + */ + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#ifdef DEBUG +# include <stdio.h> +#endif + +#ifndef lint +static char rcsid[] = "$Id: bits.c,v 0.8 1993/02/04 13:21:06 jloup Exp $"; +#endif + +/* =========================================================================== + * Local data used by the "bit string" routines. + */ + +local file_t zfile; /* output gzip file */ + +local unsigned short bi_buf; +/* Output buffer. bits are inserted starting at the bottom (least significant + * bits). + */ + +#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 int bi_valid; +/* Number of valid bits in bi_buf. All bits above the last valid bit + * are always zero. + */ + +int (*read_buf) OF((char *buf, unsigned size)) = file_read; +/* Current input function. Set to mem_read for in-memory compression */ + +#ifdef DEBUG + ulg bits_sent; /* bit length of the compressed data */ +#endif + +/* =========================================================================== + * Initialize the bit string routines. + */ +void bi_init (zipfile) + file_t zipfile; /* output zip file, NO_FILE for in-memory compression */ +{ + zfile = zipfile; + bi_buf = 0; + bi_valid = 0; +#ifdef DEBUG + bits_sent = 0L; +#endif + + /* Set the defaults for file compression. They are set by memcompress + * for in-memory compression. + */ + if (zfile != NO_FILE) { + read_buf = file_read; + } +} + +/* =========================================================================== + * Send a value on a given number of bits. + * IN assertion: length <= 16 and value fits in length bits. + */ +void send_bits(value, length) + int value; /* value to send */ + int length; /* number of bits */ +{ +#ifdef DEBUG + Tracev((stderr," l %2d v %4x ", length, value)); + Assert(length > 0 && length <= 15, "invalid length"); + bits_sent += (ulg)length; +#endif + /* If not enough room in bi_buf, use (valid) bits from bi_buf and + * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) + * unused bits in value. + */ + if (bi_valid > (int)Buf_size - length) { + bi_buf |= (value << bi_valid); + put_short(bi_buf); + bi_buf = (ush)value >> (Buf_size - bi_valid); + bi_valid += length - Buf_size; + } else { + bi_buf |= value << bi_valid; + bi_valid += length; + } +} + +/* =========================================================================== + * Reverse the first len bits of a code, using straightforward code (a faster + * method would use a table) + * IN assertion: 1 <= len <= 15 + */ +unsigned bi_reverse(code, len) + unsigned code; /* the value to invert */ + int len; /* its bit length */ +{ + register unsigned res = 0; + do { + res |= code & 1; + code >>= 1, res <<= 1; + } while (--len > 0); + return res >> 1; +} + +/* =========================================================================== + * Write out any remaining bits in an incomplete byte. + */ +void bi_windup() +{ + if (bi_valid > 8) { + put_short(bi_buf); + } else if (bi_valid > 0) { + put_byte(bi_buf); + } + bi_buf = 0; + bi_valid = 0; +#ifdef DEBUG + bits_sent = (bits_sent+7) & ~7; +#endif +} + +/* =========================================================================== + * Copy a stored block to the zip file, storing first the length and its + * one's complement if requested. + */ +void copy_block(buf, len, header) + char *buf; /* the input data */ + unsigned len; /* its length */ + int header; /* true if block header must be written */ +{ + bi_windup(); /* align on byte boundary */ + + if (header) { + put_short((ush)len); + put_short((ush)~len); +#ifdef DEBUG + bits_sent += 2*16; +#endif + } +#ifdef DEBUG + bits_sent += (ulg)len<<3; +#endif + while (len--) { +#ifdef CRYPT + int t; + if (key) zencode(*buf, t); +#endif + put_byte(*buf++); + } +} diff --git a/gnu/usr.bin/gzip/crypt.c b/gnu/usr.bin/gzip/crypt.c new file mode 100644 index 0000000..c6c7358 --- /dev/null +++ b/gnu/usr.bin/gzip/crypt.c @@ -0,0 +1,6 @@ +/* crypt.c (dummy version) -- do not perform encryption + * Hardly worth copyrighting :-) + */ +#ifndef lint +static char rcsid[] = "$Id: crypt.c,v 0.6 1993/03/22 09:48:47 jloup Exp $"; +#endif diff --git a/gnu/usr.bin/gzip/crypt.h b/gnu/usr.bin/gzip/crypt.h new file mode 100644 index 0000000..2a4c203 --- /dev/null +++ b/gnu/usr.bin/gzip/crypt.h @@ -0,0 +1,12 @@ +/* crypt.h (dummy version) -- do not perform encryption + * Hardly worth copyrighting :-) + */ + +#ifdef CRYPT +# undef CRYPT /* dummy version */ +#endif + +#define RAND_HEAD_LEN 12 /* length of encryption random header */ + +#define zencode +#define zdecode diff --git a/gnu/usr.bin/gzip/deflate.c b/gnu/usr.bin/gzip/deflate.c new file mode 100644 index 0000000..0b3af93 --- /dev/null +++ b/gnu/usr.bin/gzip/deflate.c @@ -0,0 +1,730 @@ +/* deflate.c -- compress data using the deflation algorithm + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +/* + * PURPOSE + * + * Identify new text as repetitions of old text within a fixed- + * length sliding window trailing behind the new text. + * + * DISCUSSION + * + * The "deflation" process depends on being able to identify portions + * of the input text which are identical to earlier input (within a + * sliding window trailing behind the input currently being processed). + * + * The most straightforward technique turns out to be the fastest for + * most input files: try all possible matches and select the longest. + * The key feature of this algorithm is that insertions into the string + * dictionary are very simple and thus fast, and deletions are avoided + * completely. Insertions are performed at each input character, whereas + * string matches are performed only when the previous match ends. So it + * is preferable to spend more time in matches to allow very fast string + * insertions and avoid deletions. The matching algorithm for small + * strings is inspired from that of Rabin & Karp. A brute force approach + * is used to find longer strings when a small match has been found. + * A similar algorithm is used in comic (by Jan-Mark Wams) and freeze + * (by Leonid Broukhis). + * A previous version of this file used a more sophisticated algorithm + * (by Fiala and Greene) which is guaranteed to run in linear amortized + * time, but has a larger average cost, uses more memory and is patented. + * However the F&G algorithm may be faster for some highly redundant + * files if the parameter max_chain_length (described below) is too large. + * + * ACKNOWLEDGEMENTS + * + * The idea of lazy evaluation of matches is due to Jan-Mark Wams, and + * I found it in 'freeze' written by Leonid Broukhis. + * Thanks to many info-zippers for bug reports and testing. + * + * REFERENCES + * + * APPNOTE.TXT documentation file in PKZIP 1.93a distribution. + * + * A description of the Rabin and Karp algorithm is given in the book + * "Algorithms" by R. Sedgewick, Addison-Wesley, p252. + * + * Fiala,E.R., and Greene,D.H. + * Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595 + * + * INTERFACE + * + * void lm_init (int pack_level, ush *flags) + * Initialize the "longest match" routines for a new file + * + * ulg deflate (void) + * Processes a new input file and return its compressed length. Sets + * the compressed length, crc, deflate flags and internal file + * attributes. + */ + +#include <stdio.h> + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" /* just for consistency checking */ + +#ifndef lint +static char rcsid[] = "$Id: deflate.c,v 0.13 1993/05/25 16:25:40 jloup Exp $"; +#endif + +/* =========================================================================== + * Configuration parameters + */ + +/* Compile with MEDIUM_MEM to reduce the memory requirements or + * with SMALL_MEM to use as little memory as possible. Use BIG_MEM if the + * entire input file can be held in memory (not possible on 16 bit systems). + * Warning: defining these symbols affects HASH_BITS (see below) and thus + * affects the compression ratio. The compressed output + * is still correct, and might even be smaller in some cases. + */ + +#ifdef SMALL_MEM +# define HASH_BITS 13 /* Number of bits used to hash strings */ +#endif +#ifdef MEDIUM_MEM +# define HASH_BITS 14 +#endif +#ifndef HASH_BITS +# define HASH_BITS 15 + /* For portability to 16 bit machines, do not use values above 15. */ +#endif + +/* To save space (see unlzw.c), we overlay prev+head with tab_prefix and + * window with tab_suffix. Check that we can do this: + */ +#if WSIZE<<1 > 1<<BITS + error: cannot overlay window with tab_suffix and prev with tab_prefix0 +#endif +#if HASH_BITS > BITS-1 + error: cannot overlay head with tab_prefix1 +#endif + +#define HASH_SIZE (unsigned)(1<<HASH_BITS) +#define HASH_MASK (HASH_SIZE-1) +#define WMASK (WSIZE-1) +/* HASH_SIZE and WSIZE must be powers of two */ + +#define NIL 0 +/* Tail of hash chains */ + +#define FAST 4 +#define SLOW 2 +/* speed options for the general purpose bit flag */ + +#ifndef TOO_FAR +# define TOO_FAR 4096 +#endif +/* Matches of length 3 are discarded if their distance exceeds TOO_FAR */ + +/* =========================================================================== + * Local data used by the "longest match" routines. + */ + +typedef ush Pos; +typedef unsigned IPos; +/* A Pos is an index in the character window. We use short instead of int to + * save space in the various tables. IPos is used only for parameter passing. + */ + +/* DECLARE(uch, window, 2L*WSIZE); */ +/* Sliding window. Input bytes are read into the second half of the window, + * and move to the first half later to keep a dictionary of at least WSIZE + * bytes. With this organization, matches are limited to a distance of + * WSIZE-MAX_MATCH bytes, but this ensures that IO is always + * performed with a length multiple of the block size. Also, it limits + * the window size to 64K, which is quite useful on MSDOS. + * To do: limit the window size to WSIZE+BSZ if SMALL_MEM (the code would + * be less efficient). + */ + +/* DECLARE(Pos, prev, WSIZE); */ +/* Link to older string with same hash index. To limit the size of this + * array to 64K, this link is maintained only for the last 32K strings. + * An index in this array is thus a window index modulo 32K. + */ + +/* DECLARE(Pos, head, 1<<HASH_BITS); */ +/* Heads of the hash chains or NIL. */ + +ulg window_size = (ulg)2*WSIZE; +/* window size, 2*WSIZE except for MMAP or BIG_MEM, where it is the + * input file length plus MIN_LOOKAHEAD. + */ + +long block_start; +/* window position at the beginning of the current output block. Gets + * negative when the window is moved backwards. + */ + +local unsigned ins_h; /* hash index of string to be inserted */ + +#define H_SHIFT ((HASH_BITS+MIN_MATCH-1)/MIN_MATCH) +/* Number of bits by which ins_h and del_h must be shifted at each + * input step. It must be such that after MIN_MATCH steps, the oldest + * byte no longer takes part in the hash key, that is: + * H_SHIFT * MIN_MATCH >= HASH_BITS + */ + +unsigned int near prev_length; +/* Length of the best match at previous step. Matches not greater than this + * are discarded. This is used in the lazy match evaluation. + */ + + unsigned near strstart; /* start of string to insert */ + unsigned near match_start; /* start of matching string */ +local int eofile; /* flag set at end of input file */ +local unsigned lookahead; /* number of valid bytes ahead in window */ + +unsigned near max_chain_length; +/* To speed up deflation, hash chains are never searched beyond this length. + * A higher limit improves compression ratio but degrades the speed. + */ + +local unsigned int max_lazy_match; +/* Attempt to find a better match only when the current match is strictly + * smaller than this value. + */ + +int near good_match; +/* Use a faster search when the previous match is longer than this */ + + +/* 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 + * found for specific files. + */ + +typedef struct config { + ush good_length; /* reduce lazy search above this match length */ + ush max_lazy; /* do not perform lazy search above this match length */ + ush nice_length; /* quit search above this match length */ + ush max_chain; +} config; + +#ifdef FULL_SEARCH +# define nice_match MAX_MATCH +#else + int near nice_match; /* Stop searching when current match exceeds this */ +#endif + +local config configuration_table[10] = { +/* good lazy nice chain */ +/* 0 */ {0, 0, 0, 0}, /* store only */ +/* 1 */ {4, 4, 16, 16}, /* maximum speed */ +/* 2 */ {6, 8, 16, 16}, +/* 3 */ {8, 16, 32, 32}, +/* 4 */ {8, 16, 64, 64}, +/* 5 */ {8, 16, 128, 128}, +/* 6 */ {8, 32, 128, 256}, +/* 7 */ {8, 64, 128, 512}, +/* 8 */ {32, 128, 258, 1024}, +/* 9 */ {32, 258, 258, 4096}}; /* maximum compression */ + +/* Note: the current code requires max_lazy >= MIN_MATCH and max_chain >= 4 + * but these restrictions can easily be removed at a small cost. + */ + +#define EQUAL 0 +/* result of memcmp for equal strings */ + +/* =========================================================================== + * Prototypes for local functions. + */ +local void fill_window OF((void)); + int longest_match OF((IPos cur_match)); +#ifdef ASMV + void match_init OF((void)); /* asm code initialization */ +#endif + +#ifdef DEBUG +local void check_match OF((IPos start, IPos match, int length)); +#endif + +/* =========================================================================== + * Update a hash value with the given input byte + * IN assertion: all calls to 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(h,c) (h = (((h)<<H_SHIFT) ^ (c)) & HASH_MASK) + +/* =========================================================================== + * Insert string s in the dictionary and set match_head to the previous head + * of the hash chain (the most recent string with same hash key). Return + * the previous length of the hash chain. + * IN assertion: all calls to to INSERT_STRING are made with consecutive + * input characters and the first MIN_MATCH bytes of s are valid + * (except for the last MIN_MATCH-1 bytes of the input file). + */ +#define INSERT_STRING(s, match_head) \ + (UPDATE_HASH(ins_h, window[(s) + MIN_MATCH-1]), \ + prev[(s) & WMASK] = match_head = head[ins_h], \ + head[ins_h] = (s)) + +/* =========================================================================== + * Initialize the "longest match" routines for a new file + */ +void lm_init (pack_level, flags) + int pack_level; /* 0: store, 1: best speed, 9: best compression */ + ush *flags; /* general purpose bit flag */ +{ + register unsigned j; + + if (pack_level < 1 || pack_level > 9) error("bad pack level"); + + /* Initialize the hash table. */ +#if defined(MAXSEG_64K) && HASH_BITS == 15 + for (j = 0; j < HASH_SIZE; j++) head[j] = NIL; +#else + memzero((char*)head, HASH_SIZE*sizeof(*head)); +#endif + /* prev will be initialized on the fly */ + + /* Set the default configuration parameters: + */ + max_lazy_match = configuration_table[pack_level].max_lazy; + good_match = configuration_table[pack_level].good_length; +#ifndef FULL_SEARCH + nice_match = configuration_table[pack_level].nice_length; +#endif + max_chain_length = configuration_table[pack_level].max_chain; + if (pack_level == 1) { + *flags |= FAST; + } else if (pack_level == 9) { + *flags |= SLOW; + } + /* ??? reduce max_chain_length for binary files */ + + strstart = 0; + block_start = 0L; +#ifdef ASMV + match_init(); /* initialize the asm code */ +#endif + + lookahead = read_buf((char*)window, + sizeof(int) <= 2 ? (unsigned)WSIZE : 2*WSIZE); + + if (lookahead == 0 || lookahead == (unsigned)EOF) { + eofile = 1, lookahead = 0; + return; + } + eofile = 0; + /* Make sure that we always have enough lookahead. This is important + * if input comes from a device such as a tty. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + + ins_h = 0; + for (j=0; j<MIN_MATCH-1; j++) UPDATE_HASH(ins_h, window[j]); + /* If lookahead < MIN_MATCH, ins_h is garbage, but this is + * not important since only literal bytes will be emitted. + */ +} + +/* =========================================================================== + * Set match_start to the longest match starting at the given string and + * return its length. Matches shorter or equal to prev_length are discarded, + * in which case the result is equal to prev_length and match_start is + * garbage. + * IN assertions: cur_match is the head of the hash chain for the current + * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1 + */ +#ifndef ASMV +/* For MSDOS, OS/2 and 386 Unix, an optimized version is in match.asm or + * match.s. The code is functionally equivalent, so you can use the C version + * if desired. + */ +int longest_match(cur_match) + IPos cur_match; /* current match */ +{ + unsigned chain_length = max_chain_length; /* max hash chain length */ + register uch *scan = window + strstart; /* current string */ + register uch *match; /* matched string */ + register int len; /* length of current match */ + int best_len = prev_length; /* best match length so far */ + IPos limit = strstart > (IPos)MAX_DIST ? strstart - (IPos)MAX_DIST : NIL; + /* Stop when cur_match becomes <= limit. To simplify the code, + * we prevent matches with the string of window index 0. + */ + +/* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16. + * It is easy to get rid of this optimization if necessary. + */ +#if HASH_BITS < 8 || MAX_MATCH != 258 + error: Code too clever +#endif + +#ifdef UNALIGNED_OK + /* Compare two bytes at a time. Note: this is not always beneficial. + * Try with and without -DUNALIGNED_OK to check. + */ + register uch *strend = window + strstart + MAX_MATCH - 1; + register ush scan_start = *(ush*)scan; + register ush scan_end = *(ush*)(scan+best_len-1); +#else + register uch *strend = window + strstart + MAX_MATCH; + register uch scan_end1 = scan[best_len-1]; + register uch scan_end = scan[best_len]; +#endif + + /* Do not waste too much time if we already have a good match: */ + if (prev_length >= good_match) { + chain_length >>= 2; + } + Assert(strstart <= window_size-MIN_LOOKAHEAD, "insufficient lookahead"); + + do { + Assert(cur_match < strstart, "no future"); + match = window + cur_match; + + /* Skip to next match if the match length cannot increase + * or if the match length is less than 2: + */ +#if (defined(UNALIGNED_OK) && MAX_MATCH == 258) + /* This code assumes sizeof(unsigned short) == 2. Do not use + * UNALIGNED_OK if your compiler uses a different size. + */ + if (*(ush*)(match+best_len-1) != scan_end || + *(ush*)match != scan_start) continue; + + /* It is not necessary to compare scan[2] and match[2] since they are + * always equal when the other bytes match, given that the hash keys + * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at + * strstart+3, +5, ... up to strstart+257. We check for insufficient + * lookahead only every 4th comparison; the 128th check will be made + * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is + * necessary to put more guard bytes at the end of the window, or + * to check more often for insufficient lookahead. + */ + scan++, match++; + do { + } while (*(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + scan < strend); + /* The funny "do {}" generates better code on most compilers */ + + /* Here, scan <= window+strstart+257 */ + Assert(scan <= window+(unsigned)(window_size-1), "wild scan"); + if (*scan == *match) scan++; + + len = (MAX_MATCH - 1) - (int)(strend-scan); + scan = strend - (MAX_MATCH-1); + +#else /* UNALIGNED_OK */ + + if (match[best_len] != scan_end || + match[best_len-1] != scan_end1 || + *match != *scan || + *++match != scan[1]) continue; + + /* The check at best_len-1 can be removed because it will be made + * again later. (This heuristic is not always a win.) + * It is not necessary to compare scan[2] and match[2] since they + * are always equal when the other bytes match, given that + * the hash keys are equal and that HASH_BITS >= 8. + */ + scan += 2, match++; + + /* We check for insufficient lookahead only every 8th comparison; + * the 256th check will be made at strstart+258. + */ + do { + } while (*++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + scan < strend); + + len = MAX_MATCH - (int)(strend - scan); + scan = strend - MAX_MATCH; + +#endif /* UNALIGNED_OK */ + + if (len > best_len) { + match_start = cur_match; + best_len = len; + if (len >= nice_match) break; +#ifdef UNALIGNED_OK + scan_end = *(ush*)(scan+best_len-1); +#else + scan_end1 = scan[best_len-1]; + scan_end = scan[best_len]; +#endif + } + } while ((cur_match = prev[cur_match & WMASK]) > limit + && --chain_length != 0); + + return best_len; +} +#endif /* ASMV */ + +#ifdef DEBUG +/* =========================================================================== + * Check that the match at match_start is indeed a match. + */ +local void check_match(start, match, length) + IPos start, match; + int length; +{ + /* check that the match is indeed a match */ + if (memcmp((char*)window + match, + (char*)window + start, length) != EQUAL) { + fprintf(stderr, + " start %d, match %d, length %d\n", + start, match, length); + error("invalid match"); + } + if (verbose > 1) { + fprintf(stderr,"\\[%d,%d]", start-match, length); + do { putc(window[start++], stderr); } while (--length != 0); + } +} +#else +# define check_match(start, match, length) +#endif + +/* =========================================================================== + * Fill the window when the lookahead becomes insufficient. + * Updates strstart and lookahead, and sets eofile if end of input file. + * IN assertion: lookahead < MIN_LOOKAHEAD && strstart + lookahead > 0 + * OUT assertions: at least one byte has been read, or eofile is set; + * file reads are performed for at least two bytes (required for the + * translate_eol option). + */ +local void fill_window() +{ + register unsigned n, m; + unsigned more = (unsigned)(window_size - (ulg)lookahead - (ulg)strstart); + /* Amount of free space at the end of the window. */ + + /* If the window is almost full and there is insufficient lookahead, + * move the upper half to the lower one to make room in the upper half. + */ + if (more == (unsigned)EOF) { + /* Very unlikely, but possible on 16 bit machine if strstart == 0 + * and lookahead == 1 (input done one byte at time) + */ + more--; + } else if (strstart >= WSIZE+MAX_DIST) { + /* By the IN assertion, the window is not empty so we can't confuse + * more == 0 with more == 64K on a 16 bit machine. + */ + Assert(window_size == (ulg)2*WSIZE, "no sliding with BIG_MEM"); + + memcpy((char*)window, (char*)window+WSIZE, (unsigned)WSIZE); + match_start -= WSIZE; + strstart -= WSIZE; /* we now have strstart >= MAX_DIST: */ + + block_start -= (long) WSIZE; + + for (n = 0; n < HASH_SIZE; n++) { + m = head[n]; + head[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL); + } + for (n = 0; n < WSIZE; n++) { + m = prev[n]; + prev[n] = (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. + */ + } + more += WSIZE; + } + /* At this point, more >= 2 */ + if (!eofile) { + n = read_buf((char*)window+strstart+lookahead, more); + if (n == 0 || n == (unsigned)EOF) { + eofile = 1; + } else { + lookahead += n; + } + } +} + +/* =========================================================================== + * 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(eof) \ + flush_block(block_start >= 0L ? (char*)&window[(unsigned)block_start] : \ + (char*)NULL, (long)strstart - block_start, (eof)) + +/* =========================================================================== + * Processes a new input file and return its compressed length. + */ +#ifdef NO_LAZY +ulg deflate() +{ + IPos hash_head; /* head of the hash chain */ + int flush; /* set if current block must be flushed */ + unsigned match_length = 0; /* length of best match */ + + prev_length = MIN_MATCH-1; + while (lookahead != 0) { + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + INSERT_STRING(strstart, hash_head); + + /* Find the longest match, discarding those <= prev_length. + * At this point we have always match_length < MIN_MATCH + */ + if (hash_head != NIL && strstart - hash_head <= MAX_DIST) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + match_length = longest_match (hash_head); + /* longest_match() sets match_start */ + if (match_length > lookahead) match_length = lookahead; + } + if (match_length >= MIN_MATCH) { + check_match(strstart, match_start, match_length); + + flush = ct_tally(strstart-match_start, match_length - MIN_MATCH); + + lookahead -= match_length; + match_length--; /* string at strstart already in hash table */ + do { + strstart++; + INSERT_STRING(strstart, hash_head); + /* strstart never exceeds WSIZE-MAX_MATCH, so there are + * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH + * these bytes are garbage, but it does not matter since the + * next lookahead bytes will always be emitted as literals. + */ + } while (--match_length != 0); + } else { + /* No match, output a literal byte */ + flush = ct_tally (0, window[strstart]); + lookahead--; + } + strstart++; + if (flush) FLUSH_BLOCK(0), block_start = strstart; + + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + + } + return FLUSH_BLOCK(1); /* eof */ +} +#else /* LAZY */ +/* =========================================================================== + * Same as above, but achieves better compression. We use a lazy + * evaluation for matches: a match is finally adopted only if there is + * no better match at the next window position. + */ +ulg deflate() +{ + IPos hash_head; /* head of hash chain */ + IPos prev_match; /* previous match */ + int flush; /* set if current block must be flushed */ + int match_available = 0; /* set if previous match exists */ + register unsigned match_length = MIN_MATCH-1; /* length of best match */ +#ifdef DEBUG + extern long isize; /* byte length of input file, for debug only */ +#endif + + /* Process the input block. */ + while (lookahead != 0) { + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + INSERT_STRING(strstart, hash_head); + + /* Find the longest match, discarding those <= prev_length. + */ + prev_length = match_length, prev_match = match_start; + match_length = MIN_MATCH-1; + + if (hash_head != NIL && prev_length < max_lazy_match && + strstart - hash_head <= MAX_DIST) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + match_length = longest_match (hash_head); + /* longest_match() sets match_start */ + if (match_length > lookahead) match_length = lookahead; + + /* Ignore a length 3 match if it is too distant: */ + if (match_length == MIN_MATCH && strstart-match_start > TOO_FAR){ + /* If prev_match is also MIN_MATCH, match_start is garbage + * but we will ignore the current match anyway. + */ + match_length--; + } + } + /* If there was a match at the previous step and the current + * match is not better, output the previous match: + */ + if (prev_length >= MIN_MATCH && match_length <= prev_length) { + + check_match(strstart-1, prev_match, prev_length); + + flush = ct_tally(strstart-1-prev_match, prev_length - MIN_MATCH); + + /* Insert in hash table all strings up to the end of the match. + * strstart-1 and strstart are already inserted. + */ + lookahead -= prev_length-1; + prev_length -= 2; + do { + strstart++; + INSERT_STRING(strstart, hash_head); + /* strstart never exceeds WSIZE-MAX_MATCH, so there are + * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH + * these bytes are garbage, but it does not matter since the + * next lookahead bytes will always be emitted as literals. + */ + } while (--prev_length != 0); + match_available = 0; + match_length = MIN_MATCH-1; + strstart++; + if (flush) FLUSH_BLOCK(0), block_start = strstart; + + } else if (match_available) { + /* If there was no match at the previous position, output a + * single literal. If there was a match but the current match + * is longer, truncate the previous match to a single literal. + */ + Tracevv((stderr,"%c",window[strstart-1])); + if (ct_tally (0, window[strstart-1])) { + FLUSH_BLOCK(0), block_start = strstart; + } + strstart++; + lookahead--; + } else { + /* There is no previous match to compare with, wait for + * the next step to decide. + */ + match_available = 1; + strstart++; + lookahead--; + } + Assert (strstart <= isize && lookahead <= isize, "a bit too far"); + + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + } + if (match_available) ct_tally (0, window[strstart-1]); + + return FLUSH_BLOCK(1); /* eof */ +} +#endif /* LAZY */ diff --git a/gnu/usr.bin/gzip/getopt.c b/gnu/usr.bin/gzip/getopt.c new file mode 100644 index 0000000..3bf0277 --- /dev/null +++ b/gnu/usr.bin/gzip/getopt.c @@ -0,0 +1,711 @@ +/* Getopt for GNU. + NOTE: getopt is now part of the C library, so if you don't know what + "Keep this file name-space clean" means, talk to roland@gnu.ai.mit.edu + before changing it! + + Copyright (C) 1987, 88, 89, 90, 91, 1992 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2, or (at your option) any + later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ + +/* AIX requires this to be the first thing in the file. */ +#ifdef __GNUC__ +#define alloca __builtin_alloca +#else /* not __GNUC__ */ +#if defined (HAVE_ALLOCA_H) || (defined(sparc) && (defined(sun) || (!defined(USG) && !defined(SVR4) && !defined(__svr4__)))) +#include <alloca.h> +#else +#ifdef _AIX + #pragma alloca +#else +char *alloca (); +#endif +#endif /* alloca.h */ +#endif /* not __GNUC__ */ + +#include <stdio.h> + +#if defined(USG) || defined(STDC_HEADERS) || defined(__GNU_LIBRARY__) +#include <string.h> +#endif + +/* This needs to come after some library #include + to get __GNU_LIBRARY__ defined. */ +#ifdef __GNU_LIBRARY__ +#undef alloca +/* Don't include stdlib.h for non-GNU C libraries because some of them + contain conflicting prototypes for getopt. */ +#include <stdlib.h> +#else /* Not GNU C library. */ +#define __alloca alloca +#endif /* GNU C library. */ + +#if !__STDC__ +#define const +#endif + +/* If GETOPT_COMPAT is defined, `+' as well as `--' can introduce a + long-named option. Because this is not POSIX.2 compliant, it is + being phased out. */ +#define GETOPT_COMPAT + +/* This version of `getopt' appears to the caller like standard Unix `getopt' + but it behaves differently for the user, since it allows the user + to intersperse the options with the other arguments. + + As `getopt' works, it permutes the elements of ARGV so that, + when it is done, all the options precede everything else. Thus + all application programs are extended to handle flexible argument order. + + Setting the environment variable POSIXLY_CORRECT disables permutation. + Then the behavior is completely standard. + + GNU application programs can use a third alternative mode in which + they can distinguish the relative order of options and other arguments. */ + +#include "getopt.h" + +/* For communication from `getopt' to the caller. + When `getopt' finds an option that takes an argument, + the argument value is returned here. + Also, when `ordering' is RETURN_IN_ORDER, + each non-option ARGV-element is returned here. */ + +char *optarg = 0; + +/* Index in ARGV of the next element to be scanned. + This is used for communication to and from the caller + and for communication between successive calls to `getopt'. + + On entry to `getopt', zero means this is the first call; initialize. + + When `getopt' returns EOF, this is the index of the first of the + non-option elements that the caller should itself scan. + + Otherwise, `optind' communicates from one call to the next + how much of ARGV has been scanned so far. */ + +int optind = 0; + +/* The next char to be scanned in the option-element + in which the last option character we returned was found. + This allows us to pick up the scan where we left off. + + If this is zero, or a null string, it means resume the scan + by advancing to the next ARGV-element. */ + +static char *nextchar; + +/* Callers store zero here to inhibit the error message + for unrecognized options. */ + +int opterr = 1; + +/* Describe how to deal with options that follow non-option ARGV-elements. + + If the caller did not specify anything, + the default is REQUIRE_ORDER if the environment variable + POSIXLY_CORRECT is defined, PERMUTE otherwise. + + REQUIRE_ORDER means don't recognize them as options; + stop option processing when the first non-option is seen. + This is what Unix does. + This mode of operation is selected by either setting the environment + variable POSIXLY_CORRECT, or using `+' as the first character + of the list of option characters. + + PERMUTE is the default. We permute the contents of ARGV as we scan, + so that eventually all the non-options are at the end. This allows options + to be given in any order, even with programs that were not written to + expect this. + + RETURN_IN_ORDER is an option available to programs that were written + to expect options and other ARGV-elements in any order and that care about + the ordering of the two. We describe each non-option ARGV-element + as if it were the argument of an option with character code 1. + Using `-' as the first character of the list of option characters + selects this mode of operation. + + The special argument `--' forces an end of option-scanning regardless + of the value of `ordering'. In the case of RETURN_IN_ORDER, only + `--' can cause `getopt' to return EOF with `optind' != ARGC. */ + +static enum +{ + REQUIRE_ORDER, PERMUTE, RETURN_IN_ORDER +} ordering; + +#ifdef __GNU_LIBRARY__ +#include <string.h> +#define my_index strchr +#define my_bcopy(src, dst, n) memcpy ((dst), (src), (n)) +#else + +/* Avoid depending on library functions or files + whose names are inconsistent. */ + +char *getenv (); + +static char * +my_index (string, chr) + char *string; + int chr; +{ + while (*string) + { + if (*string == chr) + return string; + string++; + } + return 0; +} + +static void +my_bcopy (from, to, size) + char *from, *to; + int size; +{ + int i; + for (i = 0; i < size; i++) + to[i] = from[i]; +} +#endif /* GNU C library. */ + +/* Handle permutation of arguments. */ + +/* Describe the part of ARGV that contains non-options that have + been skipped. `first_nonopt' is the index in ARGV of the first of them; + `last_nonopt' is the index after the last of them. */ + +static int first_nonopt; +static int last_nonopt; + +/* Exchange two adjacent subsequences of ARGV. + One subsequence is elements [first_nonopt,last_nonopt) + which contains all the non-options that have been skipped so far. + The other is elements [last_nonopt,optind), which contains all + the options processed since those non-options were skipped. + + `first_nonopt' and `last_nonopt' are relocated so that they describe + the new indices of the non-options in ARGV after they are moved. */ + +static void +exchange (argv) + char **argv; +{ + int nonopts_size = (last_nonopt - first_nonopt) * sizeof (char *); +#ifdef _CRAY + char *temp[last_nonopt - first_nonopt]; +#else + char **temp = (char **) __alloca (nonopts_size); +#endif + + /* Interchange the two blocks of data in ARGV. */ + + my_bcopy ((char *) &argv[first_nonopt], (char *) temp, nonopts_size); + my_bcopy ((char *) &argv[last_nonopt], (char *) &argv[first_nonopt], + (optind - last_nonopt) * sizeof (char *)); + my_bcopy ((char *) temp, + (char *) &argv[first_nonopt + optind - last_nonopt], + nonopts_size); + + /* Update records for the slots the non-options now occupy. */ + + first_nonopt += (optind - last_nonopt); + last_nonopt = optind; +} + +/* Scan elements of ARGV (whose length is ARGC) for option characters + given in OPTSTRING. + + If an element of ARGV starts with '-', and is not exactly "-" or "--", + then it is an option element. The characters of this element + (aside from the initial '-') are option characters. If `getopt' + is called repeatedly, it returns successively each of the option characters + from each of the option elements. + + If `getopt' finds another option character, it returns that character, + updating `optind' and `nextchar' so that the next call to `getopt' can + resume the scan with the following option character or ARGV-element. + + If there are no more option characters, `getopt' returns `EOF'. + Then `optind' is the index in ARGV of the first ARGV-element + that is not an option. (The ARGV-elements have been permuted + so that those that are not options now come last.) + + OPTSTRING is a string containing the legitimate option characters. + If an option character is seen that is not listed in OPTSTRING, + return '?' after printing an error message. If you set `opterr' to + zero, the error message is suppressed but we still return '?'. + + If a char in OPTSTRING is followed by a colon, that means it wants an arg, + so the following text in the same ARGV-element, or the text of the following + ARGV-element, is returned in `optarg'. Two colons mean an option that + wants an optional arg; if there is text in the current ARGV-element, + it is returned in `optarg', otherwise `optarg' is set to zero. + + If OPTSTRING starts with `-' or `+', it requests different methods of + handling the non-option ARGV-elements. + See the comments about RETURN_IN_ORDER and REQUIRE_ORDER, above. + + Long-named options begin with `--' instead of `-'. + Their names may be abbreviated as long as the abbreviation is unique + or is an exact match for some defined option. If they have an + argument, it follows the option name in the same ARGV-element, separated + from the option name by a `=', or else the in next ARGV-element. + When `getopt' finds a long-named option, it returns 0 if that option's + `flag' field is nonzero, the value of the option's `val' field + if the `flag' field is zero. + + The elements of ARGV aren't really const, because we permute them. + But we pretend they're const in the prototype to be compatible + with other systems. + + LONGOPTS is a vector of `struct option' terminated by an + element containing a name which is zero. + + LONGIND returns the index in LONGOPT of the long-named option found. + It is only valid when a long-named option has been found by the most + recent call. + + If LONG_ONLY is nonzero, '-' as well as '--' can introduce + long-named options. */ + +int +_getopt_internal (argc, argv, optstring, longopts, longind, long_only) + int argc; + char *const *argv; + const char *optstring; + const struct option *longopts; + int *longind; + int long_only; +{ + int option_index; + + optarg = 0; + + /* Initialize the internal data when the first call is made. + Start processing options with ARGV-element 1 (since ARGV-element 0 + is the program name); the sequence of previously skipped + non-option ARGV-elements is empty. */ + + if (optind == 0) + { + first_nonopt = last_nonopt = optind = 1; + + nextchar = NULL; + + /* Determine how to handle the ordering of options and nonoptions. */ + + if (optstring[0] == '-') + { + ordering = RETURN_IN_ORDER; + ++optstring; + } + else if (optstring[0] == '+') + { + ordering = REQUIRE_ORDER; + ++optstring; + } + else if (getenv ("POSIXLY_CORRECT") != NULL) + ordering = REQUIRE_ORDER; + else + ordering = PERMUTE; + } + + if (nextchar == NULL || *nextchar == '\0') + { + if (ordering == PERMUTE) + { + /* If we have just processed some options following some non-options, + exchange them so that the options come first. */ + + if (first_nonopt != last_nonopt && last_nonopt != optind) + exchange ((char **) argv); + else if (last_nonopt != optind) + first_nonopt = optind; + + /* Now skip any additional non-options + and extend the range of non-options previously skipped. */ + + while (optind < argc + && (argv[optind][0] != '-' || argv[optind][1] == '\0') +#ifdef GETOPT_COMPAT + && (longopts == NULL + || argv[optind][0] != '+' || argv[optind][1] == '\0') +#endif /* GETOPT_COMPAT */ + ) + optind++; + last_nonopt = optind; + } + + /* Special ARGV-element `--' means premature end of options. + Skip it like a null option, + then exchange with previous non-options as if it were an option, + then skip everything else like a non-option. */ + + if (optind != argc && !strcmp (argv[optind], "--")) + { + optind++; + + if (first_nonopt != last_nonopt && last_nonopt != optind) + exchange ((char **) argv); + else if (first_nonopt == last_nonopt) + first_nonopt = optind; + last_nonopt = argc; + + optind = argc; + } + + /* If we have done all the ARGV-elements, stop the scan + and back over any non-options that we skipped and permuted. */ + + if (optind == argc) + { + /* Set the next-arg-index to point at the non-options + that we previously skipped, so the caller will digest them. */ + if (first_nonopt != last_nonopt) + optind = first_nonopt; + return EOF; + } + + /* If we have come to a non-option and did not permute it, + either stop the scan or describe it to the caller and pass it by. */ + + if ((argv[optind][0] != '-' || argv[optind][1] == '\0') +#ifdef GETOPT_COMPAT + && (longopts == NULL + || argv[optind][0] != '+' || argv[optind][1] == '\0') +#endif /* GETOPT_COMPAT */ + ) + { + if (ordering == REQUIRE_ORDER) + return EOF; + optarg = argv[optind++]; + return 1; + } + + /* We have found another option-ARGV-element. + Start decoding its characters. */ + + nextchar = (argv[optind] + 1 + + (longopts != NULL && argv[optind][1] == '-')); + } + + if (longopts != NULL + && ((argv[optind][0] == '-' + && (argv[optind][1] == '-' || long_only)) +#ifdef GETOPT_COMPAT + || argv[optind][0] == '+' +#endif /* GETOPT_COMPAT */ + )) + { + const struct option *p; + char *s = nextchar; + int exact = 0; + int ambig = 0; + const struct option *pfound = NULL; + int indfound = 0; + + while (*s && *s != '=') + s++; + + /* Test all options for either exact match or abbreviated matches. */ + for (p = longopts, option_index = 0; p->name; + p++, option_index++) + if (!strncmp (p->name, nextchar, s - nextchar)) + { + if (s - nextchar == strlen (p->name)) + { + /* Exact match found. */ + pfound = p; + indfound = option_index; + exact = 1; + break; + } + else if (pfound == NULL) + { + /* First nonexact match found. */ + pfound = p; + indfound = option_index; + } + else + /* Second nonexact match found. */ + ambig = 1; + } + + if (ambig && !exact) + { + if (opterr) + fprintf (stderr, "%s: option `%s' is ambiguous\n", + argv[0], argv[optind]); + nextchar += strlen (nextchar); + optind++; + return '?'; + } + + if (pfound != NULL) + { + option_index = indfound; + optind++; + if (*s) + { + /* Don't test has_arg with >, because some C compilers don't + allow it to be used on enums. */ + if (pfound->has_arg) + optarg = s + 1; + else + { + if (opterr) + { + if (argv[optind - 1][1] == '-') + /* --option */ + fprintf (stderr, + "%s: option `--%s' doesn't allow an argument\n", + argv[0], pfound->name); + else + /* +option or -option */ + fprintf (stderr, + "%s: option `%c%s' doesn't allow an argument\n", + argv[0], argv[optind - 1][0], pfound->name); + } + nextchar += strlen (nextchar); + return '?'; + } + } + else if (pfound->has_arg == 1) + { + if (optind < argc) + optarg = argv[optind++]; + else + { + if (opterr) + fprintf (stderr, "%s: option `%s' requires an argument\n", + argv[0], argv[optind - 1]); + nextchar += strlen (nextchar); + return '?'; + } + } + nextchar += strlen (nextchar); + if (longind != NULL) + *longind = option_index; + if (pfound->flag) + { + *(pfound->flag) = pfound->val; + return 0; + } + return pfound->val; + } + /* Can't find it as a long option. If this is not getopt_long_only, + or the option starts with '--' or is not a valid short + option, then it's an error. + Otherwise interpret it as a short option. */ + if (!long_only || argv[optind][1] == '-' +#ifdef GETOPT_COMPAT + || argv[optind][0] == '+' +#endif /* GETOPT_COMPAT */ + || my_index ((char*)optstring, *nextchar) == NULL) + { + if (opterr) + { + if (argv[optind][1] == '-') + /* --option */ + fprintf (stderr, "%s: unrecognized option `--%s'\n", + argv[0], nextchar); + else + /* +option or -option */ + fprintf (stderr, "%s: unrecognized option `%c%s'\n", + argv[0], argv[optind][0], nextchar); + } + nextchar = (char *) ""; + optind++; + return '?'; + } + } + + /* Look at and handle the next option-character. */ + + { + char c = *nextchar++; + char *temp = my_index ((char*)optstring, c); + + /* Increment `optind' when we start to process its last character. */ + if (*nextchar == '\0') + ++optind; + + if (temp == NULL || c == ':') + { + if (opterr) + { + if (c < 040 || c >= 0177) + fprintf (stderr, "%s: unrecognized option, character code 0%o\n", + argv[0], c); + else + fprintf (stderr, "%s: unrecognized option `-%c'\n", argv[0], c); + } + return '?'; + } + if (temp[1] == ':') + { + if (temp[2] == ':') + { + /* This is an option that accepts an argument optionally. */ + if (*nextchar != '\0') + { + optarg = nextchar; + optind++; + } + else + optarg = 0; + nextchar = NULL; + } + else + { + /* This is an option that requires an argument. */ + if (*nextchar != '\0') + { + optarg = nextchar; + /* If we end this ARGV-element by taking the rest as an arg, + we must advance to the next element now. */ + optind++; + } + else if (optind == argc) + { + if (opterr) + fprintf (stderr, "%s: option `-%c' requires an argument\n", + argv[0], c); + c = '?'; + } + else + /* We already incremented `optind' once; + increment it again when taking next ARGV-elt as argument. */ + optarg = argv[optind++]; + nextchar = NULL; + } + } + return c; + } +} + +int +getopt (argc, argv, optstring) + int argc; + char *const *argv; + const char *optstring; +{ + return _getopt_internal (argc, argv, optstring, + (const struct option *) 0, + (int *) 0, + 0); +} + +int +getopt_long (argc, argv, options, long_options, opt_index) + int argc; + char *const *argv; + const char *options; + const struct option *long_options; + int *opt_index; +{ + return _getopt_internal (argc, argv, options, long_options, opt_index, 0); +} + +/* Like getopt_long, but '-' as well as '--' can indicate a long option. + If an option that starts with '-' (not '--') doesn't match a long option, + but does match a short option, it is parsed as a short option + instead. */ + +int +getopt_long_only (argc, argv, options, long_options, opt_index) + int argc; + char *const *argv; + const char *options; + const struct option *long_options; + int *opt_index; +{ + return _getopt_internal (argc, argv, options, long_options, opt_index, 1); +} + + +#ifdef TEST + +/* Compile with -DTEST to make an executable for use in testing + the above definition of `getopt'. */ + +int +main (argc, argv) + int argc; + char **argv; +{ + int c; + int digit_optind = 0; + + while (1) + { + int this_option_optind = optind ? optind : 1; + + c = getopt (argc, argv, "abc:d:0123456789"); + if (c == EOF) + break; + + switch (c) + { + case '0': + case '1': + case '2': + case '3': + case '4': + case '5': + case '6': + case '7': + case '8': + case '9': + if (digit_optind != 0 && digit_optind != this_option_optind) + printf ("digits occur in two different argv-elements.\n"); + digit_optind = this_option_optind; + printf ("option %c\n", c); + break; + + case 'a': + printf ("option a\n"); + break; + + case 'b': + printf ("option b\n"); + break; + + case 'c': + printf ("option c with value `%s'\n", optarg); + break; + + case '?': + break; + + default: + printf ("?? getopt returned character code 0%o ??\n", c); + } + } + + if (optind < argc) + { + printf ("non-option ARGV-elements: "); + while (optind < argc) + printf ("%s ", argv[optind++]); + printf ("\n"); + } + + exit (0); +} + +#endif /* TEST */ diff --git a/gnu/usr.bin/gzip/getopt.h b/gnu/usr.bin/gzip/getopt.h new file mode 100644 index 0000000..764f2f4 --- /dev/null +++ b/gnu/usr.bin/gzip/getopt.h @@ -0,0 +1,128 @@ +/* Declarations for getopt. + Copyright (C) 1989, 1990, 1991, 1992 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify it + under the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2, or (at your option) any + later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ + +#ifndef _GETOPT_H +#define _GETOPT_H 1 + +#ifdef __cplusplus +extern "C" { +#endif + +/* For communication from `getopt' to the caller. + When `getopt' finds an option that takes an argument, + the argument value is returned here. + Also, when `ordering' is RETURN_IN_ORDER, + each non-option ARGV-element is returned here. */ + +extern char *optarg; + +/* Index in ARGV of the next element to be scanned. + This is used for communication to and from the caller + and for communication between successive calls to `getopt'. + + On entry to `getopt', zero means this is the first call; initialize. + + When `getopt' returns EOF, this is the index of the first of the + non-option elements that the caller should itself scan. + + Otherwise, `optind' communicates from one call to the next + how much of ARGV has been scanned so far. */ + +extern int optind; + +/* Callers store zero here to inhibit the error message `getopt' prints + for unrecognized options. */ + +extern int opterr; + +/* Describe the long-named options requested by the application. + The LONG_OPTIONS argument to getopt_long or getopt_long_only is a vector + of `struct option' terminated by an element containing a name which is + zero. + + The field `has_arg' is: + no_argument (or 0) if the option does not take an argument, + required_argument (or 1) if the option requires an argument, + optional_argument (or 2) if the option takes an optional argument. + + If the field `flag' is not NULL, it points to a variable that is set + to the value given in the field `val' when the option is found, but + left unchanged if the option is not found. + + To have a long-named option do something other than set an `int' to + a compiled-in constant, such as set a value from `optarg', set the + option's `flag' field to zero and its `val' field to a nonzero + value (the equivalent single-letter option character, if there is + one). For long options that have a zero `flag' field, `getopt' + returns the contents of the `val' field. */ + +struct option +{ +#if __STDC__ + const char *name; +#else + char *name; +#endif + /* has_arg can't be an enum because some compilers complain about + type mismatches in all the code that assumes it is an int. */ + int has_arg; + int *flag; + int val; +}; + +/* Names for the values of the `has_arg' field of `struct option'. */ + +enum _argtype +{ + no_argument, + required_argument, + optional_argument +}; + +#if __STDC__ || defined(PROTO) +#if defined(__GNU_LIBRARY__) +/* Many other libraries have conflicting prototypes for getopt, with + differences in the consts, in stdlib.h. To avoid compilation + errors, only prototype getopt for the GNU C library. */ +extern int getopt (int argc, char *const *argv, const char *shortopts); +#else /* not __GNU_LIBRARY__ */ +extern int getopt (); +#endif /* not __GNU_LIBRARY__ */ +extern int getopt_long (int argc, char *const *argv, const char *shortopts, + const struct option *longopts, int *longind); +extern int getopt_long_only (int argc, char *const *argv, + const char *shortopts, + const struct option *longopts, int *longind); + +/* Internal only. Users should not call this directly. */ +extern int _getopt_internal (int argc, char *const *argv, + const char *shortopts, + const struct option *longopts, int *longind, + int long_only); +#else /* not __STDC__ */ +extern int getopt (); +extern int getopt_long (); +extern int getopt_long_only (); + +extern int _getopt_internal (); +#endif /* not __STDC__ */ + +#ifdef __cplusplus +} +#endif + +#endif /* _GETOPT_H */ diff --git a/gnu/usr.bin/gzip/gzexe b/gnu/usr.bin/gzip/gzexe new file mode 100644 index 0000000..ba22eb1 --- /dev/null +++ b/gnu/usr.bin/gzip/gzexe @@ -0,0 +1,134 @@ +#!/bin/sh +# gzexe: compressor for Unix executables. +# Use this only for binaries that you do not use frequently. +# +# The compressed version is a shell script which decompresses itself after +# skipping $skip lines of shell commands. We try invoking the compressed +# executable with the original name (for programs looking at their name). +# We also try to retain the original file permissions on the compressed file. +# For safety reasons, gzexe will not create setuid or setgid shell scripts. + +# Warning: the first line of this file must be either : or #!/bin/sh +# The : is required for some old versions of csh. + +x=`basename $0` +if test $# = 0; then + echo compress executables. original file foo is renamed to foo~ + echo usage: ${x} [-d] files... + echo " -d decompress the executables" + exit 1 +fi + +tmp=gz$$ +trap "rm -f $tmp; exit 1" 1 2 3 5 10 13 15 + +decomp=0 +res=0 +test "$x" = "ungzexe" && decomp=1 +if test "x$1" = "x-d"; then + decomp=1 + shift +fi + +echo hi > zfoo1$$ +echo hi > zfoo2$$ +if test -z "`(${CPMOD-cpmod} zfoo1$$ zfoo2$$) 2>&1`"; then + cpmod=${CPMOD-cpmod} +fi +rm -f zfoo[12]$$ + +for i do + if test ! -f "$i" ; then + echo ${x}: $i not a file + res=1 + continue + fi + if test $decomp -eq 0; then + if sed -e 1d -e 2q "$i" | grep "^skip=[0-9]*$" >/dev/null; then + echo "${x}: $i is already gzexe'd" + continue + fi + fi + if ls -l "$i" | grep '^...[sS]' > /dev/null; then + echo "${x}: $i has setuid permission, unchanged" + continue + fi + if ls -l "$i" | grep '^......[sS]' > /dev/null; then + echo "${x}: $i has setgid permission, unchanged" + continue + fi + if test "`basename $i`" = gzip; then + echo "${x}: cannot compress gzip itself" + continue + fi + if test -z "$cpmod"; then + cp -p "$i" $tmp 2>/dev/null || cp "$i" $tmp + if test -w $tmp 2>/dev/null; then + writable=1 + else + writable=0 + chmod u+w $tmp 2>/dev/null + fi + fi + if test $decomp -eq 0; then + sed 1q $0 > $tmp + cat >> $tmp <<'EOF' +skip=18 +if tail +$skip $0 | gzip -cd > /tmp/gztmp$$; then + chmod 755 /tmp/gztmp$$ + prog="`basename $0`" + if ln /tmp/gztmp$$ "/tmp/$prog" 2>/dev/null; then + trap '/bin/rm -f /tmp/gztmp$$ "/tmp/$prog"; exit $res' 0 + (sleep 5; /bin/rm -f /tmp/gztmp$$ "/tmp/$prog") 2>/dev/null & + /tmp/"$prog" ${1+"$@"}; res=$? + else + trap '/bin/rm -f /tmp/gztmp$$; exit $res' 0 + (sleep 5; /bin/rm -f /tmp/gztmp$$) 2>/dev/null & + /tmp/gztmp$$ ${1+"$@"}; res=$? + fi +else + echo Cannot decompress $0; exit 1 +fi; exit $res +EOF + gzip -cv9 "$i" >> $tmp || { + /bin/rm -f $tmp + echo ${x}: compression not possible for $i, file unchanged. + res=1 + continue + } + + else + # decompression + skip=18 + if sed -e 1d -e 2q "$i" | grep "^skip=[0-9]*$" >/dev/null; then + eval `sed -e 1d -e 2q "$i"` + fi + if tail +$skip "$i" | gzip -cd > $tmp; then + : + else + echo ${x}: $i probably not in gzexe format, file unchanged. + res=1 + continue + fi + fi + rm -f "$i~" + mv "$i" "$i~" || { + echo ${x}: cannot backup $i as $i~ + rm -f $tmp + res=1 + continue + } + mv $tmp "$i" || cp -p $tmp "$i" 2>/dev/null || cp $tmp "$i" || { + echo ${x}: cannot create $i + rm -f $tmp + res=1 + continue + } + rm -f $tmp + if test -n "$cpmod"; then + $cpmod "$i~" "$i" 2>/dev/null + elif test $writable -eq 0; then + chmod u-w $i 2>/dev/null + fi +done +exit $res diff --git a/gnu/usr.bin/gzip/gzexe.1 b/gnu/usr.bin/gzip/gzexe.1 new file mode 100644 index 0000000..68e4127 --- /dev/null +++ b/gnu/usr.bin/gzip/gzexe.1 @@ -0,0 +1,36 @@ +.TH GZEXE 1 +.SH NAME +gzexe \- compress executable files in place +.SH SYNOPSIS +.B gzexe +[ name ... ] +.SH DESCRIPTION +The +.I gzexe +utility allows you to compress executables in place and have them +automatically uncompress and execute when you run them (at a penalty +in performance). For example if you execute ``gzexe /bin/cat'' it +will create the following two files: +.nf +.br + -r-xr-xr-x 1 root bin 9644 Feb 11 11:16 /bin/cat + -r-xr-xr-x 1 bin bin 24576 Nov 23 13:21 /bin/cat~ +.fi +/bin/cat~ is the original file and /bin/cat is the self-uncompressing +executable file. You can remove /bin/cat~ once you are sure that +/bin/cat works properly. +.PP +This utility is most useful on systems with very small disks. +.SH OPTIONS +.TP +.B \-d +Decompress the given executables instead of compressing them. +.SH "SEE ALSO" +gzip(1), znew(1), zmore(1), zcmp(1), zforce(1) +.SH "BUGS" +.I gzexe +attempts to retain the original file attributes on the compressed executable, +but you may have to fix them manually in some cases, using +.I chmod +or +.I chown. diff --git a/gnu/usr.bin/gzip/gzexe.in b/gnu/usr.bin/gzip/gzexe.in new file mode 100644 index 0000000..dcbab88 --- /dev/null +++ b/gnu/usr.bin/gzip/gzexe.in @@ -0,0 +1,135 @@ +: +#!/bin/sh +# gzexe: compressor for Unix executables. +# Use this only for binaries that you do not use frequently. +# +# The compressed version is a shell script which decompresses itself after +# skipping $skip lines of shell commands. We try invoking the compressed +# executable with the original name (for programs looking at their name). +# We also try to retain the original file permissions on the compressed file. +# For safety reasons, gzexe will not create setuid or setgid shell scripts. + +# Warning: the first line of this file must be either : or #!/bin/sh +# The : is required for some old versions of csh. + +x=`basename $0` +if test $# = 0; then + echo compress executables. original file foo is renamed to foo~ + echo usage: ${x} [-d] files... + echo " -d decompress the executables" + exit 1 +fi + +tmp=gz$$ +trap "rm -f $tmp; exit 1" 1 2 3 5 10 13 15 + +decomp=0 +res=0 +test "$x" = "ungzexe" && decomp=1 +if test "x$1" = "x-d"; then + decomp=1 + shift +fi + +echo hi > zfoo1$$ +echo hi > zfoo2$$ +if test -z "`(${CPMOD-cpmod} zfoo1$$ zfoo2$$) 2>&1`"; then + cpmod=${CPMOD-cpmod} +fi +rm -f zfoo[12]$$ + +for i do + if test ! -f "$i" ; then + echo ${x}: $i not a file + res=1 + continue + fi + if test $decomp -eq 0; then + if sed -e 1d -e 2q "$i" | grep "^skip=[0-9]*$" >/dev/null; then + echo "${x}: $i is already gzexe'd" + continue + fi + fi + if ls -l "$i" | grep '^...[sS]' > /dev/null; then + echo "${x}: $i has setuid permission, unchanged" + continue + fi + if ls -l "$i" | grep '^......[sS]' > /dev/null; then + echo "${x}: $i has setgid permission, unchanged" + continue + fi + if test "`basename $i`" = gzip; then + echo "${x}: cannot compress gzip itself" + continue + fi + if test -z "$cpmod"; then + cp -p "$i" $tmp 2>/dev/null || cp "$i" $tmp + if test -w $tmp 2>/dev/null; then + writable=1 + else + writable=0 + chmod u+w $tmp 2>/dev/null + fi + fi + if test $decomp -eq 0; then + sed 1q $0 > $tmp + cat >> $tmp <<'EOF' +skip=18 +if tail +$skip $0 | gzip -cd > /tmp/gztmp$$; then + chmod 755 /tmp/gztmp$$ + prog="`basename $0`" + if ln /tmp/gztmp$$ "/tmp/$prog" 2>/dev/null; then + trap '/bin/rm -f /tmp/gztmp$$ "/tmp/$prog"; exit $res' 0 + (sleep 5; /bin/rm -f /tmp/gztmp$$ "/tmp/$prog") 2>/dev/null & + /tmp/"$prog" ${1+"$@"}; res=$? + else + trap '/bin/rm -f /tmp/gztmp$$; exit $res' 0 + (sleep 5; /bin/rm -f /tmp/gztmp$$) 2>/dev/null & + /tmp/gztmp$$ ${1+"$@"}; res=$? + fi +else + echo Cannot decompress $0; exit 1 +fi; exit $res +EOF + gzip -cv9 "$i" >> $tmp || { + /bin/rm -f $tmp + echo ${x}: compression not possible for $i, file unchanged. + res=1 + continue + } + + else + # decompression + skip=18 + if sed -e 1d -e 2q "$i" | grep "^skip=[0-9]*$" >/dev/null; then + eval `sed -e 1d -e 2q "$i"` + fi + if tail +$skip "$i" | gzip -cd > $tmp; then + : + else + echo ${x}: $i probably not in gzexe format, file unchanged. + res=1 + continue + fi + fi + rm -f "$i~" + mv "$i" "$i~" || { + echo ${x}: cannot backup $i as $i~ + rm -f $tmp + res=1 + continue + } + mv $tmp "$i" || cp -p $tmp "$i" 2>/dev/null || cp $tmp "$i" || { + echo ${x}: cannot create $i + rm -f $tmp + res=1 + continue + } + rm -f $tmp + if test -n "$cpmod"; then + $cpmod "$i~" "$i" 2>/dev/null + elif test $writable -eq 0; then + chmod u-w $i 2>/dev/null + fi +done +exit $res diff --git a/gnu/usr.bin/gzip/gzip.1 b/gnu/usr.bin/gzip/gzip.1 new file mode 100644 index 0000000..a7d331f --- /dev/null +++ b/gnu/usr.bin/gzip/gzip.1 @@ -0,0 +1,360 @@ +.PU +.TH GZIP 1 +.SH NAME +gzip, gunzip, zcat \- compress or expand files +.SH SYNOPSIS +.ll +8 +.B gzip +.RB [ " \-acdfhLrtvV19 " ] +.RB [ \-S\ suffix ] +[ +.I "name \&..." +] +.ll -8 +.br +.B gunzip +.RB [ " \-acfhLrtvV " ] +.RB [ \-S\ suffix ] +[ +.I "name \&..." +] +.br +.B zcat +.RB [ " \-hLV " ] +[ +.I "name \&..." +] +.SH DESCRIPTION +.I Gzip +reduces the size of the named files using Lempel-Ziv coding (LZ77). +Whenever possible, +each file is replaced by one with the extension +.B "\&.gz," +while keeping the same ownership modes, access and modification times. +(The default extension is +.B "\-gz" +for VMS, +.B "z" +for MSDOS, OS/2 and Atari.) +If no files are specified, the standard input is compressed to the +standard output. If the new file name is too long, +.I gzip +truncates it and keeps the original file name in the compressed file. +.I Gzip +will only attempt to compress regular files. +In particular, it will ignore symbolic links. +.PP +Compressed files can be restored to their original form using +.I gzip -d +or +.I gunzip +or +.I zcat. +.PP +.I gunzip +takes a list of files on its command line and replaces each +file whose name ends with .gz, -gz, .z, -z, _z or .Z +and which begins with the correct magic number with an uncompressed +file without the original extension. +.I gunzip +also recognizes the special extensions +.B "\&.tgz" +and +.B "\&.taz" +as shorthands for +.B "\&.tar.gz" +and +.B "\&.tar.Z" +respectively. +.PP +.I gunzip +can currently decompress files created by +.I gzip, zip, compress +or +.I pack. +The detection of the input format is automatic. When using +the first two formats, +.I gunzip +checks a 32 bit CRC. For +.I pack, gunzip +checks the uncompressed length. The +.I compress +format was not designed to allow consistency checks. However +.I gunzip +is sometimes able to detect a bad .Z file. If you get an error +when uncompressing a .Z file, do not assume that the .Z file is +correct simply because the standard +.I uncompress +does not complain. This generally means that the standard +.I uncompress +does not check its input, and happily generates garbage output. +.PP +Files created by +.I zip +can be uncompressed by gzip only if they have a single member compressed +with the 'deflation' method. This feature is only intended to help +conversion of tar.zip files to the tar.gz format. To extract zip files +with several members, use +.I unzip +instead of +.I gunzip. +.PP +.I zcat +is identical to +.I gunzip +.B \-c. +(On some systems, +.I zcat +may be installed as +.I gzcat +to preserve the original link to +.I compress.) +.I zcat +uncompresses either a list of files on the command line or its +standard input and writes the uncompressed data on standard output. +.I zcat +will uncompress files that have the correct magic number whether +they have a +.B "\&.gz" +suffix or not. +.PP +.I Gzip +uses the Lempel-Ziv algorithm used in +.I zip +and PKZIP. +The amount of compression obtained depends on the size of the +input and the distribution of common substrings. +Typically, text such as source code or English +is reduced by 60\-70%. +Compression is generally much better than that achieved by +LZW (as used in +.IR compress ), +Huffman coding (as used in +.IR pack ), +or adaptive Huffman coding +.RI ( compact ). +.PP +Compression is always performed, even if the compressed file is +slightly larger than the original. The worst case expansion is +a few bytes for the gzip file header, plus 5 bytes every 32K block, +or an expansion ratio of 0.015% for large files. Note that the actual +number of used disk blocks almost never increases. +.I gzip +preserves the mode, ownership and timestamps of files when compressing +or decompressing. + +.SH OPTIONS +.TP +.B \-a --ascii +Ascii text mode: convert end-of-lines using local conventions. This option +is supported only on some non-Unix systems. For MSDOS, CR LF is converted +to LF when compressing, and LF is converted to CR LF when decompressing. +.TP +.B \-c --stdout +Write output on standard output; keep original files unchanged. +If there are several input files, the output consists of a sequence of +independently compressed members. To obtain better compression, +concatenate all input files before compressing them. +.TP +.B \-d --decompress --uncompress +Decompress. +.TP +.B \-f --force +Force compression or decompression even if the file has multiple links +or the corresponding file already exists, or if the compressed data +is read from or written to a terminal. If +.B \-f +is not given, +and when not running in the background, +.I gzip +prompts to verify whether an existing file should be overwritten. +.TP +.B \-h --help +Display a help screen and quit. +.TP +.B \-L --license +Display the +.I gzip +license. +.TP +.B \-q --quiet +Suppress all warnings. +.TP +.B \-r --recurse +Travel the directory structure recursively. If any of the file names +specified on the command line are directories, +.I gzip +will descend into the directory and compress all the files it finds there +(or decompress them in the case of +.I gunzip +). +.TP +.B \-S .z --suffix .z +Use suffix .z instead of .gz. Any suffix can be given, but suffixes +other than .z and .gz should be avoided to avoid confusion when files +are transferred to other systems. Previous versions of gzip used +the .z suffix. This was changed to avoid a conflict with +.IR pack "(1)". +.TP +.B \-t --test +Test. Check the compressed file integrity. +.TP +.B \-v --verbose +Verbose. Display the name and percentage reduction for each file compressed. +.TP +.B \-V --version +Version. Display the version number and compilation options then quit. +.TP +.B \-# --fast --best +Regulate the speed of compression using the specified digit +.IR # , +where +.B \-1 +or +.B \-\-fast +indicates the fastest compression method (less compression) +and +.B \-9 +or +.B \-\-best +indicates the slowest compression method (optimal compression). +The default compression level is +.BR \-5. +.SH "ADVANCED USAGE" +Multiple compressed files can be concatenated. In this case, +.I gunzip +will extract all members at once. For example: + + gzip -c file1 > foo.gz + gzip -c file2 >> foo.gz + +Then + gunzip -c foo + +is equivalent to + + cat file1 file2 + +In case of damage to one member of a .gz file, other members can +still be recovered (if the damaged member is removed). However, +you can get better compression by compressing all members at once: + + cat file1 file2 | gzip > foo.gz + +compresses better than + + gzip -c file1 file2 > foo.gz + +If you want to recompress concatenated files to get better compression, do: + + zcat old.gz | gzip > new.gz +.SH "ENVIRONMENT" +The environment variable +.B GZIP +can hold a set of default options for +.I gzip. +These options are interpreted first and can be overwritten by +explicit command line parameters. For example: + for sh: GZIP="-8 -v"; export GZIP + for csh: setenv GZIP "-8 -v" + for MSDOS: set GZIP=-8 -v + +On Vax/VMS, the name of the environment variable is GZIP_OPT, to +avoid a conflict with the symbol set for invocation of the program. +.SH "SEE ALSO" +znew(1), zcmp(1), zmore(1), zforce(1), gzexe(1), zip(1), unzip(1), compress(1), +pack(1), compact(1) +.SH "DIAGNOSTICS" +Exit status is normally 0; +if an error occurs, exit status is 1. If a warning occurs, exit status is 2. +.PP +Usage: gzip [-cdfhLrtvV19] [-S suffix] [file ...] +.in +8 +Invalid options were specified on the command line. +.in -8 +.IR file : +not in gzip format +.in +8 +The file specified to +.I gunzip +has not been compressed. +.in -8 +.IR file: +Corrupt input. Use zcat to recover some data. +.in +8 +The compressed file has been damaged. The data up to the point of failure +can be recovered using +.in +8 +zcat file > recover +.in -16 +.IR file : +compressed with +.I xx +bits, can only handle +.I yy +bits +.in +8 +.I File +was compressed (using LZW) by a program that could deal with +more +.I bits +than the decompress code on this machine. +Recompress the file with gzip, which compresses better and uses +less memory. +.in -8 +.IR file : +already has .gz suffix -- no change +.in +8 +The file is assumed to be already compressed. +Rename the file and try again. +.in -8 +.I file +already exists; do you wish to overwrite (y or n)? +.in +8 +Respond "y" if you want the output file to be replaced; "n" if not. +.in -8 +gunzip: corrupt input +.in +8 +A SIGSEGV violation was detected which usually means that the input file has +been corrupted. +.in -8 +.I "xx.x%" +.in +8 +Percentage of the input saved by compression. +(Relevant only for +.BR \-v \.) +.in -8 +-- not a regular file or directory: ignored +.in +8 +When the input file is not a regular file or directory, +(e.g. a symbolic link, socket, FIFO, device file), it is +left unaltered. +.in -8 +-- has +.I xx +other links: unchanged +.in +8 +The input file has links; it is left unchanged. See +.IR ln "(1)" +for more information. Use the +.B \-f +flag to force compression of multiply-linked files. +.in -8 +.SH CAVEATS +When writing compressed data to a tape, it is generally necessary to +pad the output with zeroes up to a block boundary. When the data is +read and the whole block is passed to +.I gunzip +for decompression, +.I gunzip +detects that there is extra trailing garbage after the compressed data +and emits a warning by default. You have to use the --quiet option to +suppress the warning. This option can be set in the +.B GZIP +environment variable as in: + for sh: GZIP="-q" tar xfz /dev/rmt/datn + for csh: (setenv GZIP "-q"; tar xfz /dev/rmt/datn) + +In the above example, gzip is invoked implicitly by the -z option +of GNU tar. Make sure that the same block size (-b option of +tar) is used for reading and writing compressed data on tapes. diff --git a/gnu/usr.bin/gzip/gzip.c b/gnu/usr.bin/gzip/gzip.c new file mode 100644 index 0000000..2bc1c5f --- /dev/null +++ b/gnu/usr.bin/gzip/gzip.c @@ -0,0 +1,1458 @@ +/* gzip (GNU zip) -- compress files with zip algorithm and 'compress' interface + * Copyright (C) 1992-1993 Jean-loup Gailly + * The unzip code was written and put in the public domain by Mark Adler. + * Portions of the lzw code are derived from the public domain 'compress' + * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies, + * Ken Turkowski, Dave Mack and Peter Jannesen. + * + * See the license_msg below and the file COPYING for the software license. + * See the file algorithm.doc for the compression algorithms and file formats. + */ + +static char *license_msg[] = { +" Copyright (C) 1992-1993 Jean-loup Gailly", +" This program is free software; you can redistribute it and/or modify", +" it under the terms of the GNU General Public License as published by", +" the Free Software Foundation; either version 2, or (at your option)", +" any later version.", +"", +" This program is distributed in the hope that it will be useful,", +" but WITHOUT ANY WARRANTY; without even the implied warranty of", +" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the", +" GNU General Public License for more details.", +"", +" You should have received a copy of the GNU General Public License", +" along with this program; if not, write to the Free Software", +" Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.", +0}; + +/* Compress files with zip algorithm and 'compress' interface. + * See usage() and help() functions below for all options. + * Outputs: + * file.gz: compressed file with same mode, owner, and utimes + * or stdout with -c option or if stdin used as input. + * If the OS does not support file names with multiple dots (MSDOS, VMS) or + * if the output file name had to be truncated, the original name is kept + * in the compressed file. + * On MSDOS, file.tmp -> file.tmz. On VMS, file.tmp -> file.tmp-gz. + * + * For the meaning of all compilation flags, see comments in Makefile.in. + */ + +#ifndef lint +static char rcsid[] = "$Id: gzip.c,v 0.19 1993/06/01 14:21:46 jloup Exp $"; +#endif + +#include <stdio.h> +#include <ctype.h> +#include <sys/types.h> +#include <signal.h> +#include <sys/stat.h> +#include <errno.h> + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" +#include "revision.h" +#include "getopt.h" + + /* configuration */ + +#ifndef NO_FCNTL_H +# include <fcntl.h> +#endif + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif + +#if defined(STDC_HEADERS) || !defined(NO_STDLIB_H) +# include <stdlib.h> +#else + extern int errno; +#endif + +#if defined(DIRENT) +# include <dirent.h> + typedef struct dirent dir_type; +# define NLENGTH(dirent) ((int)strlen((dirent)->d_name)) +# define DIR_OPT "DIRENT" +#else +# define NLENGTH(dirent) ((dirent)->d_namlen) +# ifdef SYSDIR +# include <sys/dir.h> + typedef struct direct dir_type; +# define DIR_OPT "SYSDIR" +# else +# ifdef SYSNDIR +# include <sys/ndir.h> + typedef struct direct dir_type; +# define DIR_OPT "SYSNDIR" +# else +# ifdef NDIR +# include <ndir.h> + typedef struct direct dir_type; +# define DIR_OPT "NDIR" +# else +# define NO_DIR +# define DIR_OPT "NO_DIR" +# endif +# endif +# endif +#endif + +#ifndef NO_UTIME +# ifndef NO_UTIME_H +# include <utime.h> +# define TIME_OPT "UTIME" +# else +# ifdef HAVE_SYS_UTIME_H +# include <sys/utime.h> +# define TIME_OPT "SYS_UTIME" +# else + struct utimbuf { + time_t actime; + time_t modtime; + }; +# define TIME_OPT "" +# endif +# endif +#else +# define TIME_OPT "NO_UTIME" +#endif + +#if !defined(S_ISDIR) && defined(S_IFDIR) +# define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR) +#endif +#if !defined(S_ISREG) && defined(S_IFREG) +# define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#endif + +typedef RETSIGTYPE (*sig_type) OF((int)); + +#ifndef O_BINARY +# define O_BINARY 0 /* creation mode for open() */ +#endif + +#ifndef O_CREAT + /* Pure BSD system? */ +# include <sys/file.h> +# ifndef O_CREAT +# define O_CREAT FCREAT +# endif +# ifndef O_EXCL +# define O_EXCL FEXCL +# endif +#endif + +#ifndef S_IRUSR +# define S_IRUSR 0400 +#endif +#ifndef S_IWUSR +# define S_IWUSR 0200 +#endif +#define RW_USER (S_IRUSR | S_IWUSR) /* creation mode for open() */ + +#ifndef MAX_PATH_LEN +# define MAX_PATH_LEN 1024 /* max pathname length */ +#endif + +#define MAX_HEADER_LEN 16 +/* max length of a compressed file header, fixed part only */ + + /* global buffers */ + +DECLARE(uch, inbuf, INBUFSIZ +INBUF_EXTRA); +DECLARE(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA); +DECLARE(ush, d_buf, DIST_BUFSIZE); +DECLARE(uch, window, 2L*WSIZE); +#ifndef MAXSEG_64K + DECLARE(ush, tab_prefix, 1L<<BITS); +#else + DECLARE(ush, tab_prefix0, 1L<<(BITS-1)); + DECLARE(ush, tab_prefix1, 1L<<(BITS-1)); +#endif + + /* local variables */ + +int ascii = 0; /* convert end-of-lines to local OS conventions */ +int to_stdout = 0; /* output to stdout (-c) */ +int decompress = 0; /* decompress (-d) */ +int force = 0; /* don't ask questions, compress links (-f) */ +int recursive = 0; /* recurse through directories (-r) */ +int verbose = 0; /* be verbose (-v) */ +int quiet = 0; /* be very quiet (-q) */ +int do_lzw = 0; /* generate output compatible with old compress (-Z) */ +int test = 0; /* test .gz file integrity */ +int foreground; /* set if program run in foreground */ +char *progname; /* program name */ +int maxbits = BITS; /* max bits per code for LZW */ +int method = DEFLATED;/* compression method */ +int level = 5; /* compression level */ +int exit_code = OK; /* program exit code */ +int save_orig_name; /* set if original name must be saved */ +int last_member; /* set for .zip and .Z files */ +int part_nb; /* number of parts in .gz file */ +ulg time_stamp; /* original time stamp (modification time) */ +long ifile_size; /* input file size, -1 for devices (debug only) */ +char *env; /* contents of GZIP env variable */ +char **args = NULL; /* argv pointer if GZIP env variable defined */ +char z_suffix[MAX_SUFFIX+1]; /* default suffix (can be set with --suffix) */ +int z_len; /* strlen(z_suffix) */ + +long bytes_in; /* number of input bytes */ +long bytes_out; /* number of output bytes */ +char ifname[MAX_PATH_LEN]; /* input file name */ +char ofname[MAX_PATH_LEN]; /* output file name */ +int remove_ofname = 0; /* remove output file on error */ +struct stat istat; /* status for input file */ +int ifd; /* input file descriptor */ +int ofd; /* output file descriptor */ +unsigned insize; /* valid bytes in inbuf */ +unsigned inptr; /* index of next byte to be processed in inbuf */ +unsigned outcnt; /* bytes in output buffer */ + +struct option longopts[] = +{ + /* { name has_arg *flag val } */ + {"ascii", 0, 0, 'a'}, /* ascii text mode */ + {"to-stdout", 0, 0, 'c'}, /* write output on standard output */ + {"stdout", 0, 0, 'c'}, /* write output on standard output */ + {"decompress", 0, 0, 'd'}, /* decompress */ + {"uncompress", 0, 0, 'd'}, /* decompress */ + /* {"encrypt", 0, 0, 'e'}, encrypt */ + {"force", 0, 0, 'f'}, /* force overwrite of output file */ + {"help", 0, 0, 'h'}, /* give help */ + /* {"pkzip", 0, 0, 'k'}, force output in pkzip format */ + /* {"list", 0, 0, 'l'}, list .gz file contents */ + {"license", 0, 0, 'L'}, /* display software license */ + {"quiet", 0, 0, 'q'}, /* quiet mode */ + {"silent", 0, 0, 'q'}, /* quiet mode */ + {"recurse", 0, 0, 'r'}, /* recurse through directories */ + {"suffix", 1, 0, 'S'}, /* use given suffix instead of .gz */ + {"test", 0, 0, 't'}, /* test compressed file integrity */ + {"verbose", 0, 0, 'v'}, /* verbose mode */ + {"version", 0, 0, 'V'}, /* display version number */ + {"fast", 0, 0, '1'}, /* compress faster */ + {"best", 0, 0, '9'}, /* compress better */ + {"lzw", 0, 0, 'Z'}, /* make output compatible with old compress */ + {"bits", 1, 0, 'b'}, /* max number of bits per code (implies -Z) */ + { 0, 0, 0, 0 } +}; + +/* local functions */ + +local void usage OF((void)); +local void help OF((void)); +local void license OF((void)); +local void version OF((void)); +local void treat_stdin OF((void)); +local void treat_file OF((char *iname)); +local int create_outfile OF((void)); +local int do_stat OF((char *name, struct stat *sbuf)); +local char *get_suffix OF((char *name)); +local int get_istat OF((char *iname, struct stat *sbuf)); +local int make_ofname OF((void)); +local int same_file OF((struct stat *stat1, struct stat *stat2)); +local int name_too_long OF((char *name, struct stat *statb)); +local int get_method OF((int in)); +local int check_ofname OF((void)); +local void reset_times OF((char *name, struct stat *statb)); +local void copy_stat OF((struct stat *ifstat)); +local void treat_dir OF((char *dir)); +local void do_exit OF((int exitcode)); + int main OF((int argc, char **argv)); + +int (*work) OF((int infile, int outfile)) = zip; /* function to call */ + +#define strequ(s1, s2) (strcmp((s1),(s2)) == 0) + +/* ======================================================================== */ +local void usage() +{ + fprintf(stderr, "usage: %s [-%scdfhL%stvV19] [-S suffix] [file ...]\n", + progname, +#if O_BINARY + "a", +#else + "", +#endif +#ifdef NO_DIR + "" +#else + "r" +#endif + ); +} + +/* ======================================================================== */ +local void help() +{ + static char *help_msg[] = { +#if O_BINARY + " -a --ascii ascii text; convert end-of-lines using local conventions", +#endif + " -c --stdout write on standard output, keep original files unchanged", + " -d --decompress decompress", +/* -e --encrypt encrypt */ + " -f --force force overwrite of output file and compress links", + " -h --help give this help", +/* -k --pkzip force output in pkzip format */ +/* -l --list list .gz file contents */ + " -L --license display software license", + " -q --quiet suppress all warnings", +#ifndef NO_DIR + " -r --recurse recurse through directories", +#endif +#ifdef MAX_EXT_CHARS + " -S --suffix .gz use suffix .gz instead of .z", +#else + " -S --suffix .z use suffix .z instead of .gz", +#endif + " -t --test test compressed file integrity", + " -v --verbose verbose mode", + " -V --version display version number", + " -1 --fast compress faster", + " -9 --best compress better", +#ifdef LZW + " -Z --lzw produce output compatible with old compress", + " -b --bits maxbits max number of bits per code (implies -Z)", +#endif + " file... files to (de)compress. If none given, use standard input.", + 0}; + char **p = help_msg; + + fprintf(stderr,"%s %s (%s)\n", progname, VERSION, REVDATE); + usage(); + while (*p) fprintf(stderr, "%s\n", *p++); +} + +/* ======================================================================== */ +local void license() +{ + char **p = license_msg; + + fprintf(stderr,"%s %s (%s)\n", progname, VERSION, REVDATE); + while (*p) fprintf(stderr, "%s\n", *p++); +} + +/* ======================================================================== */ +local void version() +{ + fprintf(stderr,"%s %s (%s)\n", progname, VERSION, REVDATE); + + fprintf(stderr, "Compilation options:\n%s %s ", DIR_OPT, TIME_OPT); +#ifdef STDC_HEADERS + fprintf(stderr, "STDC_HEADERS "); +#endif +#ifdef HAVE_UNISTD_H + fprintf(stderr, "HAVE_UNISTD_H "); +#endif +#ifdef NO_MEMORY_H + fprintf(stderr, "NO_MEMORY_H "); +#endif +#ifdef NO_STRING_H + fprintf(stderr, "NO_STRING_H "); +#endif +#ifdef NO_SYMLINK + fprintf(stderr, "NO_SYMLINK "); +#endif +#ifdef NO_MULTIPLE_DOTS + fprintf(stderr, "NO_MULTIPLE_DOTS "); +#endif +#ifdef NO_CHOWN + fprintf(stderr, "NO_CHOWN "); +#endif +#ifdef PROTO + fprintf(stderr, "PROTO "); +#endif +#ifdef ASMV + fprintf(stderr, "ASMV "); +#endif +#ifdef DEBUG + fprintf(stderr, "DEBUG "); +#endif +#ifdef DYN_ALLOC + fprintf(stderr, "DYN_ALLOC "); +#endif +#ifdef MAXSEG_64K + fprintf(stderr, "MAXSEG_64K"); +#endif + fprintf(stderr, "\n"); +} + +/* ======================================================================== */ +int main (argc, argv) + int argc; + char **argv; +{ + int file_count = 0; /* number of files to precess */ + int proglen; /* length of progname */ + int optc; /* current option */ + + EXPAND(argc, argv); /* wild card expansion if necessary */ + + progname = basename(argv[0]); + proglen = strlen(progname); + + /* Suppress .exe for MSDOS, OS/2 and VMS: */ + if (proglen > 4 && strequ(progname+proglen-4, ".exe")) { + progname[proglen-4] = '\0'; + } + + /* Add options in GZIP environment variable if there is one */ + env = add_envopt(&argc, &argv, OPTIONS_VAR); + if (env != NULL) args = argv; + + foreground = signal(SIGINT, SIG_IGN) != SIG_IGN; + if (foreground) { + signal (SIGINT, (sig_type)abort_gzip); + } +#ifdef SIGTERM + signal(SIGTERM, (sig_type)abort_gzip); +#endif +#ifdef SIGHUP + signal(SIGHUP, (sig_type)abort_gzip); +#endif + +#ifndef GNU_STANDARD + /* For compatibility with old compress, use program name as an option. + * If you compile with -DGNU_STANDARD, this program will behave as + * gzip even if it is invoked under the name gunzip or zcat. + * + * Systems which do not support links can still use -d or -dc. + * Ignore an .exe extension for MSDOS, OS/2 and VMS. + */ + if ( strncmp(progname, "un", 2) == 0 /* ungzip, uncompress */ + || strncmp(progname, "gun", 3) == 0) { /* gunzip */ + decompress = 1; + } else if (strequ(progname+1, "cat") /* zcat, pcat, gcat */ + || strequ(progname, "gzcat")) { /* gzcat */ + decompress = to_stdout = 1; + } +#endif + + strncpy(z_suffix, Z_SUFFIX, sizeof(z_suffix)-1); + z_len = strlen(z_suffix); + + while ((optc = getopt_long (argc, argv, "ab:cdfhLqrS:tvVZ123456789", + longopts, (int *)0)) != EOF) { + switch (optc) { + case 'a': + ascii = 1; break; + case 'b': + maxbits = atoi(optarg); + break; + case 'c': + to_stdout = 1; break; + case 'd': + decompress = 1; break; + case 'f': + force++; break; + case 'h': case 'H': case '?': + help(); do_exit(OK); break; + case 'L': + license(); do_exit(OK); break; + case 'q': + quiet = 1; verbose = 0; break; + case 'r': +#ifdef NO_DIR + fprintf(stderr, "%s: -r not supported on this system\n", progname); + usage(); + do_exit(ERROR); break; +#else + recursive = 1; break; +#endif + case 'S': +#ifdef NO_MULTIPLE_DOTS + if (*optarg == '.') optarg++; +#endif + z_len = strlen(optarg); + if (z_len == 0 || z_len > MAX_SUFFIX) { + fprintf(stderr, "%s: incorrect suffix '%s'\n", + progname, optarg); + do_exit(ERROR); + } + strcpy(z_suffix, optarg); + break; + case 't': + test = decompress = to_stdout = 1; + break; + case 'v': + verbose++; quiet = 0; break; + case 'V': + version(); do_exit(OK); break; + case 'Z': +#ifdef LZW + do_lzw = 1; break; +#else + fprintf(stderr, "%s: -Z not supported in this version\n", + progname); + usage(); + do_exit(ERROR); break; +#endif + case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + level = optc - '0'; + break; + default: + /* Error message already emitted by getopt_long. */ + usage(); + do_exit(ERROR); + } + } /* loop on all arguments */ + + file_count = argc - optind; + +#if O_BINARY +#else + if (ascii && !quiet) { + fprintf(stderr, "%s: option --ascii ignored on this system\n", + progname); + } +#endif + if (do_lzw && !decompress) work = lzw; + + /* Allocate all global buffers (for DYN_ALLOC option) */ + ALLOC(uch, inbuf, INBUFSIZ +INBUF_EXTRA); + ALLOC(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA); + ALLOC(ush, d_buf, DIST_BUFSIZE); + ALLOC(uch, window, 2L*WSIZE); +#ifndef MAXSEG_64K + ALLOC(ush, tab_prefix, 1L<<BITS); +#else + ALLOC(ush, tab_prefix0, 1L<<(BITS-1)); + ALLOC(ush, tab_prefix1, 1L<<(BITS-1)); +#endif + + /* And get to work */ + if (file_count != 0) { + if (to_stdout && !test && (!decompress || !ascii)) { + SET_BINARY_MODE(fileno(stdout)); + } + while (optind < argc) { + treat_file(argv[optind++]); + } + } else { /* Standard input */ + treat_stdin(); + } + do_exit(exit_code); + return exit_code; /* just to avoid lint warning */ +} + +/* ======================================================================== + * Compress or decompress stdin + */ +local void treat_stdin() +{ + if (!force && isatty(fileno((FILE *)(decompress ? stdin : stdout)))) { + /* Do not send compressed data to the terminal or read it from + * the terminal. We get here when user invoked the program + * without parameters, so be helpful. According to the GNU standards: + * + * If there is one behavior you think is most useful when the output + * is to a terminal, and another that you think is most useful when + * the output is a file or a pipe, then it is usually best to make + * the default behavior the one that is useful with output to a + * terminal, and have an option for the other behavior. + * + * Here we use the --force option to get the other behavior. + */ + fprintf(stderr, + "%s: compressed data not %s a terminal. Use -f to force %scompression.\n", + progname, decompress ? "read from" : "written to", + decompress ? "de" : ""); + fprintf(stderr,"For help, type: %s -h\n", progname); + do_exit(ERROR); + } + + if (decompress || !ascii) { + SET_BINARY_MODE(fileno(stdin)); + } + if (!test && (!decompress || !ascii)) { + SET_BINARY_MODE(fileno(stdout)); + } + strcpy(ifname, "stdin"); + strcpy(ofname, "stdout"); + + /* Get the time stamp on the input file. */ +#ifdef NO_STDIN_FSTAT + time_stamp = 0; /* time unknown */ +#else + if (fstat(fileno(stdin), &istat) != 0) { + error("fstat(stdin)"); + } + /* If you do not wish to save the time stamp when input comes from a pipe, + * compile with -DNO_PIPE_TIMESTAMP. + */ +#ifdef NO_PIPE_TIMESTAMP + if (!S_ISREG(istat.st_mode)) + time_stamp = 0; + else +#endif + time_stamp = istat.st_mtime; +#endif + ifile_size = -1L; /* convention for unknown size */ + + clear_bufs(); /* clear input and output buffers */ + to_stdout = 1; + part_nb = 0; + + if (decompress) { + method = get_method(ifd); + if (method < 0) { + do_exit(exit_code); /* error message already emitted */ + } + } + + /* Actually do the compression/decompression. Loop over zipped members. + */ + for (;;) { + if ((*work)(fileno(stdin), fileno(stdout)) != OK) return; + + if (!decompress || last_member || inptr == insize) break; + /* end of file */ + + method = get_method(ifd); + if (method < 0) return; /* error message already emitted */ + bytes_out = 0; /* required for length check */ + } + + if (verbose) { + if (test) { + fprintf(stderr, " OK"); + + } else if (decompress) { + display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out); + } else { + display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in); + } + fprintf(stderr, "\n"); + } +} + +/* ======================================================================== + * Compress or decompress the given file + */ +local void treat_file(iname) + char *iname; +{ + /* Check if the input file is present, set ifname and istat: */ + if (get_istat(iname, &istat) != OK) return; + + /* If the input name is that of a directory, recurse or ignore: */ + if (S_ISDIR(istat.st_mode)) { +#ifndef NO_DIR + if (recursive) { + struct stat st; + st = istat; + treat_dir(iname); + /* Warning: ifname is now garbage */ + reset_times (iname, &st); + } else +#endif + WARN((stderr,"%s: %s is a directory -- ignored\n", progname, ifname)); + return; + } + if (!S_ISREG(istat.st_mode)) { + WARN((stderr, + "%s: %s is not a directory or a regular file - ignored\n", + progname, ifname)); + return; + } + if (istat.st_nlink > 1 && !to_stdout && !force) { + WARN((stderr, "%s: %s has %d other link%c -- unchanged\n", + progname, ifname, + (int)istat.st_nlink - 1, istat.st_nlink > 2 ? 's' : ' ')); + return; + } + + ifile_size = istat.st_size; + time_stamp = istat.st_mtime; + + /* Generate output file name */ + if (to_stdout) { + strcpy(ofname, "stdout"); + + } else if (make_ofname() != OK) { + return; + } + + /* Open the input file and determine compression method. The mode + * parameter is ignored but required by some systems (VMS) and forbidden + * on other systems (MacOS). + */ + ifd = OPEN(ifname, ascii && !decompress ? O_RDONLY : O_RDONLY | O_BINARY, + RW_USER); + if (ifd == -1) { + fprintf(stderr, "%s: ", progname); + perror(ifname); + exit_code = ERROR; + return; + } + clear_bufs(); /* clear input and output buffers */ + part_nb = 0; + + if (decompress) { + method = get_method(ifd); /* updates ofname if original given */ + if (method < 0) { + close(ifd); + return; /* error message already emitted */ + } + } + + /* If compressing to a file, check if ofname is not ambiguous + * because the operating system truncates names. Otherwise, generate + * a new ofname and save the original name in the compressed file. + */ + if (to_stdout) { + ofd = fileno(stdout); + /* keep remove_ofname as zero */ + } else { + if (create_outfile() != OK) return; + + if (save_orig_name && !verbose && !quiet) { + fprintf(stderr, "%s: %s compressed to %s\n", + progname, ifname, ofname); + } + } + if (verbose) { + fprintf(stderr, "%s:\t%s", ifname, (int)strlen(ifname) >= 15 ? + "" : ((int)strlen(ifname) >= 7 ? "\t" : "\t\t")); + } + + /* Actually do the compression/decompression. Loop over zipped members. + */ + for (;;) { + if ((*work)(ifd, ofd) != OK) { + method = -1; /* force cleanup */ + break; + } + if (!decompress || last_member || inptr == insize) break; + /* end of file */ + + method = get_method(ifd); + if (method < 0) break; /* error message already emitted */ + bytes_out = 0; /* required for length check */ + } + + close(ifd); + if (!to_stdout && close(ofd)) { + write_error(); + } + if (method == -1) { + if (!to_stdout) unlink (ofname); + return; + } + /* Display statistics */ + if(verbose) { + if (test) { + fprintf(stderr, " OK"); + } else if (decompress) { + display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out); + } else { + display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in); + } + if (!test && !to_stdout) { + fprintf(stderr, " -- replaced with %s", ofname); + } + fprintf(stderr, "\n"); + } + /* Copy modes, times, ownership, and remove the input file */ + if (!to_stdout) { + copy_stat(&istat); + } +} + +/* ======================================================================== + * Create the output file. Return OK or ERROR. + * Try several times if necessary to avoid truncating the z_suffix. For + * example, do not create a compressed file of name "1234567890123." + * IN assertions: the input file has already been open (ifd is set) and + * ofname has already been updated if there was an original name. + * OUT assertions: ifd and ofd are closed in case of error. + */ +local int create_outfile() +{ + struct stat ostat; /* stat for ofname */ + int len; + int flags = O_WRONLY | O_CREAT | O_EXCL | O_BINARY; + + if (ascii && decompress) { + flags &= ~O_BINARY; /* force ascii text mode */ + } + for (;;) { + len = strlen(ofname); + if (len == 0 || ofname[len] == PATH_SEP) break; + if (check_ofname() != OK) { + close(ifd); + return ERROR; + } + /* Create the output file */ + remove_ofname = 1; + ofd = OPEN(ofname, flags, RW_USER); + if (ofd == -1) { + perror(ofname); + close(ifd); + exit_code = ERROR; + return ERROR; + } + + /* Check for name truncation on new file (1234567890123.gz) */ + if (fstat(ofd, &ostat) != 0) { + fprintf(stderr, "%s: ", progname); + perror(ofname); + close(ifd); close(ofd); + unlink(ofname); + exit_code = ERROR; + return ERROR; + } + if (!name_too_long(ofname, &ostat)) return OK; + + if (decompress) { + /* name might be too long if an original name was saved */ + WARN((stderr, "%s: %s: warning, name truncated\n", + progname, ofname)); + return OK; + } else { +#ifdef NO_MULTIPLE_DOTS + /* Should never happen, see check_ofname() */ + fprintf(stderr, "%s: %s: name too long\n", progname, ofname); + do_exit(ERROR); +#else + close(ofd); + unlink(ofname); + save_orig_name = 1; + strcpy(ofname+strlen(ofname)-z_len-1, z_suffix); + /* 123456789012.gz -> 12345678901.gz */ +#endif + } /* decompress ? */ + } /* while non null name */ + + close(ifd); + fprintf(stderr, "%s: %s: name too long\n", progname, ofname); + exit_code = ERROR; + return ERROR; +} + +/* ======================================================================== + * Use lstat if available, except for -c or -f. Use stat otherwise. + * This allows links when not removing the original file. + */ +local int do_stat(name, sbuf) + char *name; + struct stat *sbuf; +{ + errno = 0; +#if (defined(S_IFLNK) || defined (S_ISLNK)) && !defined(NO_SYMLINK) + if (!to_stdout && !force) { + return lstat(name, sbuf); + } +#endif + return stat(name, sbuf); +} + +/* ======================================================================== + * Return a pointer to the 'z' suffix of a file name, or NULL. For all + * systems, ".gz", ".z", ".Z", ".taz", ".tgz", "-gz", "-z" and "_z" are + * accepted suffixes, in addition to the value of the --suffix option. + * ".tgz" is a useful convention for tar.z files on systems limited + * to 3 characters extensions. On such systems, ".?z" and ".??z" are + * also accepted suffixes. For Unix, we do not want to accept any + * .??z suffix as indicating a compressed file; some people use .xyz + * to denote volume data. + */ +local char *get_suffix(name) + char *name; +{ + int nlen, slen; + char suffix[MAX_SUFFIX+3]; /* last chars of name, forced to lower case */ + static char *known_suffixes[] = + {z_suffix, ".gz", ".z", ".taz", ".tgz", "-gz", "-z", "_z", +#ifdef MAX_EXT_CHARS + "z", +#endif + NULL}; + char **suf = known_suffixes; + + if (strequ(z_suffix, "z")) suf++; /* check long suffixes first */ + + nlen = strlen(name); + if (nlen <= MAX_SUFFIX+2) { + strcpy(suffix, name); + } else { + strcpy(suffix, name+nlen-MAX_SUFFIX-2); + } +#ifdef SUFFIX_SEP + /* strip a version number from the file name */ + { + char *v = strrchr(suffix, SUFFIX_SEP); + if (v != NULL) *v = '\0', nlen = v - name; + } +#endif + strlwr(suffix); + slen = strlen(suffix); + do { + int s = strlen(*suf); + if (slen > s && suffix[slen-s-1] != PATH_SEP + && strequ(suffix + slen - s, *suf)) { + return name+nlen-s; + } + } while (*++suf != NULL); + + return NULL; +} + + +/* ======================================================================== + * Set ifname to the input file name (with a suffix appended if necessary) + * and istat to its stats. For decompression, if no file exists with the + * original name, try adding successively z_suffix, .gz, .z, -z and .Z. + * For MSDOS, we try only z_suffix and z. + * Return OK or ERROR. + */ +local int get_istat(iname, sbuf) + char *iname; + struct stat *sbuf; +{ + int ilen; /* strlen(ifname) */ + static char *suffixes[] = {z_suffix, ".gz", ".z", "-z", ".Z", NULL}; + char **suf = suffixes; + char *s; +#ifdef NO_MULTIPLE_DOTS + char *dot; /* pointer to ifname extension, or NULL */ +#endif + + strcpy(ifname, iname); + + /* If input file exists, return OK. */ + if (do_stat(ifname, sbuf) == 0) return OK; + + if (!decompress || errno != ENOENT) { + perror(ifname); + exit_code = ERROR; + return ERROR; + } + /* file.ext doesn't exist, try adding a suffix. + */ + s = get_suffix(ifname); + if (s != NULL) { + perror(ifname); /* ifname already has z suffix and does not exist */ + exit_code = ERROR; + return ERROR; + } +#ifdef SUFFIX_SEP + /* strip a version number from the input file name */ + if ((s = strrchr(ifname, SUFFIX_SEP)) != NULL) *s = '\0'; +#endif +#ifdef NO_MULTIPLE_DOTS + dot = strrchr(ifname, '.'); + if (dot == NULL) { + strcat(ifname, "."); + dot = strrchr(ifname, '.'); + } +#endif + ilen = strlen(ifname); + if (strequ(z_suffix, ".gz")) suf++; + + /* Search for all suffixes */ + do { + s = *suf; +#ifdef NO_MULTIPLE_DOTS + if (*s == '.') s++; +#endif +#ifdef MAX_EXT_CHARS + strcpy(ifname, iname); + /* Needed if the suffixes are not sorted by increasing length */ + + if (*dot == '\0') strcpy(dot, "."); + dot[MAX_EXT_CHARS+1-strlen(s)] = '\0'; +#endif + strcat(ifname, s); + if (do_stat(ifname, sbuf) == 0) return OK; + ifname[ilen] = '\0'; + } while (*++suf != NULL); + + /* No suffix found, complain using z_suffix: */ +#ifdef MAX_EXT_CHARS + strcpy(ifname, iname); + if (*dot == '\0') strcpy(dot, "."); + dot[MAX_EXT_CHARS+1-z_len] = '\0'; +#endif + strcat(ifname, z_suffix); + perror(ifname); + exit_code = ERROR; + return ERROR; +} + +/* ======================================================================== + * Generate ofname given ifname. Return OK, or WARNING if file must be skipped. + * Initializes save_orig_name. + * IN assertion: this function is not called if to_stdout is true. + */ +local int make_ofname() +{ + char *suff; /* ofname z suffix */ + + strcpy(ofname, ifname); + suff = get_suffix(ofname); + + if (decompress) { + if (suff == NULL) { + WARN((stderr,"%s: %s: unknown suffix -- ignored\n", + progname, ifname)); + return WARNING; + } + /* Make a special case for .tgz and .taz: */ + strlwr(suff); + if (strequ(suff, ".tgz") || strequ(suff, ".taz")) { + strcpy(suff, ".tar"); + } else { + *suff = '\0'; /* strip z suffix and optional version number */ + } + /* ofname might be changed later if infile contains an original name */ + + } else if (suff != NULL) { + /* Avoid annoying messages with -r (see treat_dir()) */ + if (verbose || (!recursive && !quiet)) { + fprintf(stderr, "%s: %s already has %s suffix -- unchanged\n", + progname, ifname, suff); + } + if (exit_code == OK) exit_code = WARNING; + return WARNING; + } else { + save_orig_name = 0; + +#ifdef SUFFIX_SEP + /* strip a version number from the file name */ + if ((suff = strrchr(ofname, SUFFIX_SEP)) != NULL) *suff = '\0'; +#endif + +#ifdef NO_MULTIPLE_DOTS + suff = strrchr(ofname, '.'); + if (suff == NULL) { + strcat(ofname, "."); +# ifdef MAX_EXT_CHARS + /* On the Atari and some versions of MSDOS, name_too_long() + * does not work correctly because of a bug in stat(). So we + * must truncate here. + */ + } else if (strlen(suff)-1 + z_len > MAX_SUFFIX) { + suff[MAX_SUFFIX+1-z_len] = '\0'; + save_orig_name = 1; +# endif + } +#endif /* NO_MULTIPLE_DOTS */ + strcat(ofname, z_suffix); + + } /* decompress ? */ + return OK; +} + + +/* ======================================================================== + * Check the magic number of the input file and update ofname if an + * original name was given and to_stdout is not set. + * Return the compression method, -1 for error, -2 for warning. + * Set inptr to the offset of the next byte to be processed. + * This function may be called repeatedly for an input file consisting + * of several contiguous gzip'ed members. + * IN assertions: there is at least one remaining compressed member. + * If the member is a zip file, it must be the only one. + */ +local int get_method(in) + int in; /* input file descriptor */ +{ + uch flags; + char magic[2]; /* magic header */ + + magic[0] = (char)get_byte(); + magic[1] = (char)get_byte(); + + time_stamp = istat.st_mtime; /* may be modified later for some methods */ + method = -1; /* unknown yet */ + part_nb++; /* number of parts in gzip file */ + header_bytes = 0; + last_member = RECORD_IO; + /* assume multiple members in gzip file except for record oriented I/O */ + + if (memcmp(magic, GZIP_MAGIC, 2) == 0 + || memcmp(magic, OLD_GZIP_MAGIC, 2) == 0) { + + work = unzip; + method = (int)get_byte(); + flags = (uch)get_byte(); + + if ((flags & ENCRYPTED) != 0) { + fprintf(stderr, + "%s: %s is encrypted -- get newer version of gzip\n", + progname, ifname); + exit_code = ERROR; + return -1; + } + if ((flags & CONTINUATION) != 0) { + fprintf(stderr, + "%s: %s is a a multi-part gzip file -- get newer version of gzip\n", + progname, ifname); + exit_code = ERROR; + if (force <= 1) return -1; + } + if ((flags & RESERVED) != 0) { + fprintf(stderr, + "%s: %s has flags 0x%x -- get newer version of gzip\n", + progname, ifname, flags); + exit_code = ERROR; + if (force <= 1) return -1; + } + time_stamp = (ulg)get_byte(); + time_stamp |= ((ulg)get_byte()) << 8; + time_stamp |= ((ulg)get_byte()) << 16; + time_stamp |= ((ulg)get_byte()) << 24; + + (void)get_byte(); /* Ignore extra flags for the moment */ + (void)get_byte(); /* Ignore OS type for the moment */ + + if ((flags & CONTINUATION) != 0) { + unsigned part = (unsigned)get_byte(); + part |= ((unsigned)get_byte())<<8; + if (verbose) { + fprintf(stderr,"%s: %s: part number %u\n", + progname, ifname, part); + } + } + if ((flags & EXTRA_FIELD) != 0) { + unsigned len = (unsigned)get_byte(); + len |= ((unsigned)get_byte())<<8; + if (verbose) { + fprintf(stderr,"%s: %s: extra field of %u bytes ignored\n", + progname, ifname, len); + } + while (len--) (void)get_byte(); + } + + /* Get original file name if it was truncated */ + if ((flags & ORIG_NAME) != 0) { + if (to_stdout || part_nb > 1) { + /* Discard the old name */ + char c; /* dummy used for NeXTstep 3.0 cc optimizer bug */ + while ((c=get_byte()) != 0) c++; + } else { + /* Copy the base name. Keep a directory prefix intact. */ + char *p = basename(ofname); + for (;;) { + *p = (char)get_char(); + if (*p++ == '\0') break; + if (p >= ofname+sizeof(ofname)) { + error("corrupted input -- file name too large"); + } + } + } /* to_stdout */ + } /* orig_name */ + + /* Discard file comment if any */ + if ((flags & COMMENT) != 0) { + while (get_char() != 0) /* null */ ; + } + if (part_nb == 1) { + header_bytes = inptr + 2*sizeof(long); /* include crc and size */ + } + + } else if (memcmp(magic, PKZIP_MAGIC, 2) == 0 && inptr == 2 + && memcmp((char*)inbuf, PKZIP_MAGIC, 4) == 0) { + /* To simplify the code, we support a zip file when alone only. + * We are thus guaranteed that the entire local header fits in inbuf. + */ + inptr = 0; + work = unzip; + if (check_zipfile(in) != OK) return -1; + /* check_zipfile may get ofname from the local header */ + last_member = 1; + + } else if (memcmp(magic, PACK_MAGIC, 2) == 0) { + work = unpack; + method = PACKED; + } else if (memcmp(magic, LZW_MAGIC, 2) == 0) { + work = unlzw; + method = COMPRESSED; + last_member = 1; + } + if (method >= 0) return method; + if (part_nb == 1) { + fprintf(stderr, "\n%s: %s: not in gzip format\n", progname, ifname); + exit_code = ERROR; + return -1; + } else { + WARN((stderr, "\n%s: %s: trailing garbage ignored\n", + progname, ifname)); + return -2; + } +} + +/* ======================================================================== + * Return true if the two stat structures correspond to the same file. + */ +local int same_file(stat1, stat2) + struct stat *stat1; + struct stat *stat2; +{ + return stat1->st_ino == stat2->st_ino + && stat1->st_dev == stat2->st_dev +#ifdef NO_ST_INO + /* Can't rely on st_ino and st_dev, use other fields: */ + && stat1->st_mode == stat2->st_mode + && stat1->st_uid == stat2->st_uid + && stat1->st_gid == stat2->st_gid + && stat1->st_size == stat2->st_size + && stat1->st_atime == stat2->st_atime + && stat1->st_mtime == stat2->st_mtime + && stat1->st_ctime == stat2->st_ctime +#endif + ; +} + +/* ======================================================================== + * Return true if a file name is ambiguous because the operating system + * truncates file names. + */ +local int name_too_long(name, statb) + char *name; /* file name to check */ + struct stat *statb; /* stat buf for this file name */ +{ + int s = strlen(name); + char c = name[s-1]; + struct stat tstat; /* stat for truncated name */ + int res; + + tstat = *statb; /* Just in case OS does not fill all fields */ + name[s-1] = '\0'; + res = stat(name, &tstat) == 0 && same_file(statb, &tstat); + name[s-1] = c; + Trace((stderr, " too_long(%s) => %d\n", name, res)); + return res; +} + +/* ======================================================================== + * If compressing to a file, check if ofname is not ambiguous + * because the operating system truncates names. Otherwise, generate + * a new ofname and save the original name in the compressed file. + * If the compressed file already exists, ask for confirmation. + * The check for name truncation is made dynamically, because different + * file systems on the same OS might use different truncation rules (on SVR4 + * s5 truncates to 14 chars and ufs does not truncate). + * This function returns -1 if the file must be skipped, and + * updates save_orig_name if necessary. + * IN assertions: save_orig_name is already set if ofname has been + * already truncated because of NO_MULTIPLE_DOTS. The input file has + * already been open and istat is set. + */ +local int check_ofname() +{ + int s = strlen(ofname); + struct stat ostat; /* stat for ofname */ + + if (stat(ofname, &ostat) != 0) return 0; + + /* Check for name truncation on existing file: */ +#ifdef NO_MULTIPLE_DOTS + if (!decompress && name_too_long(ofname, &ostat)) { +#else + if (!decompress && s > 8 && name_too_long(ofname, &ostat)) { +#endif + save_orig_name = 1; + strcpy(ofname+s-z_len-1, z_suffix); /* f.ext.gz -> f.ex.gz */ + + if (stat(ofname, &ostat) != 0) return 0; + } /* !decompress && name_too_long */ + + /* Check that the input and output files are different (could be + * the same by name truncation or links). + */ + if (same_file(&istat, &ostat)) { + fprintf(stderr, "%s: %s and %s are the same file\n", + progname, ifname, ofname); + exit_code = ERROR; + return ERROR; + } + /* Ask permission to overwrite the existing file */ + if (!force) { + char response[80]; + strcpy(response,"n"); + fprintf(stderr, "%s: %s already exists;", progname, ofname); + if (foreground && isatty(fileno(stdin))) { + fprintf(stderr, " do you wish to overwrite (y or n)? "); + fflush(stderr); + (void)fgets(response, sizeof(response)-1, stdin); + } + if (tolow(*response) != 'y') { + fprintf(stderr, "\tnot overwritten\n"); + if (exit_code == OK) exit_code = WARNING; + return ERROR; + } + } + (void) chmod(ofname, 0777); + if (unlink(ofname)) { + fprintf(stderr, "%s: ", progname); + perror(ofname); + exit_code = ERROR; + return ERROR; + } + return OK; +} + + +/* ======================================================================== + * Set the access and modification times from the given stat buffer. + */ +local void reset_times (name, statb) + char *name; + struct stat *statb; +{ +#ifndef NO_UTIME + struct utimbuf timep; + + /* Copy the time stamp */ + timep.actime = statb->st_atime; + timep.modtime = statb->st_mtime; + + /* Some systems (at least OS/2) do not support utime on directories */ + if (utime(name, &timep) && !S_ISDIR(statb->st_mode)) { + WARN((stderr, "%s: ", progname)); + if (!quiet) perror(ofname); + } +#else + name = name; statb = statb; /* avoid warnings */ +#endif +} + + +/* ======================================================================== + * Copy modes, times, ownership from input file to output file. + * IN assertion: to_stdout is false. + */ +local void copy_stat(ifstat) + struct stat *ifstat; +{ +#ifndef NO_UTIME + if (decompress && time_stamp != 0 && ifstat->st_mtime != time_stamp) { + ifstat->st_mtime = time_stamp; + if (verbose) { + fprintf(stderr, "%s: time stamp restored\n", ofname); + } + } + reset_times(ofname, ifstat); +#endif + /* Copy the protection modes */ + if (chmod(ofname, ifstat->st_mode & 07777)) { + WARN((stderr, "%s: ", progname)); + if (!quiet) perror(ofname); + } +#ifndef NO_CHOWN + chown(ofname, ifstat->st_uid, ifstat->st_gid); /* Copy ownership */ +#endif + remove_ofname = 0; + /* It's now safe to remove the input file: */ + (void) chmod(ifname, 0777); + if (unlink(ifname)) { + WARN((stderr, "%s: ", progname)); + if (!quiet) perror(ifname); + } +} + +#ifndef NO_DIR + +/* ======================================================================== + * Recurse through the given directory. This code is taken from ncompress. + */ +local void treat_dir(dir) + char *dir; +{ + dir_type *dp; + DIR *dirp; + char nbuf[MAX_PATH_LEN]; + int len; + + dirp = opendir(dir); + + if (dirp == NULL) { + fprintf(stderr, "%s: %s unreadable\n", progname, dir); + exit_code = ERROR; + return ; + } + /* + ** WARNING: the following algorithm could occasionally cause + ** compress to produce error warnings of the form "<filename>.gz + ** already has .gz suffix - ignored". This occurs when the + ** .gz output file is inserted into the directory below + ** readdir's current pointer. + ** These warnings are harmless but annoying, so they are suppressed + ** with option -r (except when -v is on). An alternative + ** to allowing this would be to store the entire directory + ** list in memory, then compress the entries in the stored + ** list. Given the depth-first recursive algorithm used here, + ** this could use up a tremendous amount of memory. I don't + ** think it's worth it. -- Dave Mack + ** (An other alternative might be two passes to avoid depth-first.) + */ + + while ((dp = readdir(dirp)) != NULL) { + + if (strequ(dp->d_name,".") || strequ(dp->d_name,"..")) { + continue; + } + len = strlen(dir); + if (len + NLENGTH(dp) + 1 < MAX_PATH_LEN - 1) { + strcpy(nbuf,dir); + if (len != 0 /* dir = "" means current dir on Amiga */ +#ifdef PATH_SEP2 + && dir[len-1] != PATH_SEP2 +#endif +#ifdef PATH_SEP3 + && dir[len-1] != PATH_SEP3 +#endif + ) { + nbuf[len++] = PATH_SEP; + } + strcpy(nbuf+len, dp->d_name); + treat_file(nbuf); + } else { + fprintf(stderr,"%s: %s/%s: pathname too long\n", + progname, dir, dp->d_name); + exit_code = ERROR; + } + } + closedir(dirp); +} +#endif /* ? NO_DIR */ + +/* ======================================================================== + * Free all dynamically allocated variables and exit with the given code. + */ +local void do_exit(exitcode) + int exitcode; +{ + if (env != NULL) free(env), env = NULL; + if (args != NULL) free((char*)args), args = NULL; + FREE(inbuf); + FREE(outbuf); + FREE(d_buf); + FREE(window); +#ifndef MAXSEG_64K + FREE(tab_prefix); +#else + FREE(tab_prefix0); + FREE(tab_prefix1); +#endif + exit(exitcode); +} + +/* ======================================================================== + * Signal and error handler. + */ +RETSIGTYPE abort_gzip() +{ + if (remove_ofname) { + close(ofd); + unlink (ofname); + } + do_exit(ERROR); +} diff --git a/gnu/usr.bin/gzip/gzip.h b/gnu/usr.bin/gzip/gzip.h new file mode 100644 index 0000000..a4d6376 --- /dev/null +++ b/gnu/usr.bin/gzip/gzip.h @@ -0,0 +1,302 @@ +/* gzip.h -- common declarations for all gzip modules + * Copyright (C) 1992-1993 Jean-loup Gailly. + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#if defined(__STDC__) || defined(PROTO) +# define OF(args) args +#else +# define OF(args) () +#endif + +#ifdef __STDC__ + typedef void *voidp; +#else + typedef char *voidp; +#endif + +/* I don't like nested includes, but the string functions are used too often */ +#if !defined(NO_STRING_H) || defined(STDC_HEADERS) +# include <string.h> +# if !defined(STDC_HEADERS) && !defined(NO_MEMORY_H) && !defined(__GNUC__) +# include <memory.h> +# endif +# define memzero(s, n) memset ((voidp)(s), 0, (n)) +#else +# include <strings.h> +# define strchr index +# define strrchr rindex +# define memcpy(d, s, n) bcopy((s), (d), (n)) +# define memcmp(s1, s2, n) bcmp((s1), (s2), (n)) +# define memzero(s, n) bzero((s), (n)) +#endif + +#ifndef RETSIGTYPE +# define RETSIGTYPE void +#endif + +#define local static + +typedef unsigned char uch; +typedef unsigned short ush; +typedef unsigned long ulg; + +/* Return codes from gzip */ +#define OK 0 +#define ERROR 1 +#define WARNING 2 + +/* Compression methods (see algorithm.doc) */ +#define STORED 0 +#define COMPRESSED 1 +#define PACKED 2 +/* methods 3 to 7 reserved */ +#define DEFLATED 8 +extern int method; /* compression method */ + +/* To save memory for 16 bit systems, some arrays are overlaid between + * the various modules: + * deflate: prev+head window d_buf l_buf outbuf + * unlzw: tab_prefix tab_suffix stack inbuf outbuf + * inflate: window inbuf + * unpack: window inbuf + * For compression, input is done in window[]. For decompression, output + * is done in window except for unlzw. + */ + +#ifndef INBUFSIZ +# ifdef SMALL_MEM +# define INBUFSIZ 0x2000 /* input buffer size */ +# else +# define INBUFSIZ 0x8000 /* input buffer size */ +# endif +#endif +#define INBUF_EXTRA 64 /* required by unlzw() */ + +#ifndef OUTBUFSIZ +# ifdef SMALL_MEM +# define OUTBUFSIZ 8192 /* output buffer size */ +# else +# define OUTBUFSIZ 16384 /* output buffer size */ +# endif +#endif +#define OUTBUF_EXTRA 2048 /* required by unlzw() */ + +#ifndef DIST_BUFSIZE +# ifdef SMALL_MEM +# define DIST_BUFSIZE 0x2000 /* buffer for distances, see trees.c */ +# else +# define DIST_BUFSIZE 0x8000 /* buffer for distances, see trees.c */ +# endif +#endif + +#ifdef DYN_ALLOC +# define EXTERN(type, array) extern type * near array +# define DECLARE(type, array, size) type * near array +# define ALLOC(type, array, size) { \ + array = (type*)fcalloc((size_t)(((size)+1L)/2), 2*sizeof(type)); \ + if (array == NULL) error("insufficient memory"); \ + } +# define FREE(array) {if (array != NULL) fcfree(array), array=NULL;} +#else +# define EXTERN(type, array) extern type array[] +# define DECLARE(type, array, size) type array[size] +# define ALLOC(type, array, size) +# define FREE(array) +#endif + +EXTERN(uch, inbuf); /* input buffer */ +EXTERN(uch, outbuf); /* output buffer */ +EXTERN(ush, d_buf); /* buffer for distances, see trees.c */ +EXTERN(uch, window); /* Sliding window and suffix table (unlzw) */ +#define tab_suffix window +#ifndef MAXSEG_64K +# define tab_prefix prev /* hash link (see deflate.c) */ +# define head (prev+WSIZE) /* hash head (see deflate.c) */ + EXTERN(ush, tab_prefix); /* prefix code (see unlzw.c) */ +#else +# define tab_prefix0 prev +# define head tab_prefix1 + EXTERN(ush, tab_prefix0); /* prefix for even codes */ + EXTERN(ush, tab_prefix1); /* prefix for odd codes */ +#endif + +extern unsigned insize; /* valid bytes in inbuf */ +extern unsigned inptr; /* index of next byte to be processed in inbuf */ +extern unsigned outcnt; /* bytes in output buffer */ + +extern long bytes_in; /* number of input bytes */ +extern long bytes_out; /* number of output bytes */ +extern long header_bytes;/* number of bytes in gzip header */ + +#define isize bytes_in +/* for compatibility with old zip sources (to be cleaned) */ + +extern int ifd; /* input file descriptor */ +extern int ofd; /* output file descriptor */ +extern char ifname[]; /* input file name or "stdin" */ +extern char ofname[]; /* output file name or "stdout" */ +extern char *progname; /* program name */ + +extern ulg time_stamp; /* original time stamp (modification time) */ +extern long ifile_size; /* input file size, -1 for devices (debug only) */ + +typedef int file_t; /* Do not use stdio */ +#define NO_FILE (-1) /* in memory compression */ + + +#define GZIP_MAGIC "\037\213" /* Magic header for gzip files, 1F 8B */ +#define OLD_GZIP_MAGIC "\037\236" /* Magic header for gzip 0.5 = freeze 1.x */ +#define PKZIP_MAGIC "\120\113\003\004" /* Magic header for pkzip files */ +#define PACK_MAGIC "\037\036" /* Magic header for packed files */ + +/* gzip flag byte */ +#define ASCII_FLAG 0x01 /* bit 0 set: file probably ascii text */ +#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ +#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 ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ +#define RESERVED 0xC0 /* bit 6,7: reserved */ + +/* internal file attribute */ +#define UNKNOWN 0xffff +#define BINARY 0 +#define ASCII 1 + +#ifndef WSIZE +# define WSIZE 0x8000 /* window size--must be a power of two, and */ +#endif /* at least 32K for zip's deflate method */ + +#define MIN_MATCH 3 +#define MAX_MATCH 258 +/* The minimum and maximum match lengths */ + +#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. + */ + +#define MAX_DIST (WSIZE-MIN_LOOKAHEAD) +/* In order to simplify the code, particularly on 16 bit machines, match + * distances are limited to MAX_DIST instead of WSIZE. + */ + +extern int decrypt; /* flag to turn on decryption */ +extern int exit_code; /* program exit code */ +extern int verbose; /* be verbose (-v) */ +extern int quiet; /* be quiet (-q) */ +extern int level; /* compression level */ +extern int test; /* check .z file integrity */ +extern int to_stdout; /* output to stdout (-c) */ +extern int save_orig_name; /* set if original name must be saved */ + +#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) + +/* put_byte is used for the compressed output, put_ubyte for the + * uncompressed output. However unlzw() uses window for its + * suffix table instead of its output buffer, so it does not use put_ubyte + * (to be cleaned up). + */ +#define put_byte(c) {outbuf[outcnt++]=(uch)(c); if (outcnt==OUTBUFSIZ)\ + flush_outbuf();} +#define put_ubyte(c) {window[outcnt++]=(uch)(c); if (outcnt==WSIZE)\ + flush_window();} + +/* Output a 16 bit value, lsb first */ +#define put_short(w) \ +{ if (outcnt < OUTBUFSIZ-2) { \ + outbuf[outcnt++] = (uch) ((w) & 0xff); \ + outbuf[outcnt++] = (uch) ((ush)(w) >> 8); \ + } else { \ + put_byte((uch)((w) & 0xff)); \ + put_byte((uch)((ush)(w) >> 8)); \ + } \ +} + +/* Output a 32 bit value to the bit stream, lsb first */ +#define put_long(n) { \ + put_short((n) & 0xffff); \ + put_short(((ulg)(n)) >> 16); \ +} + +#define seekable() 0 /* force sequential output */ +#define translate_eol 0 /* no option -a yet */ + +#define tolow(c) (isupper(c) ? (c)-'A'+'a' : (c)) /* force to lower case */ + +/* Macros for getting two-byte and four-byte header values */ +#define SH(p) ((ush)(uch)((p)[0]) | ((ush)(uch)((p)[1]) << 8)) +#define LG(p) ((ulg)(SH(p)) | ((ulg)(SH((p)+2)) << 16)) + +/* Diagnostic functions */ +#ifdef DEBUG +# define Assert(cond,msg) {if(!(cond)) error(msg);} +# define Trace(x) fprintf x +# define Tracev(x) {if (verbose) fprintf x ;} +# define Tracevv(x) {if (verbose>1) fprintf x ;} +# define Tracec(c,x) {if (verbose && (c)) fprintf x ;} +# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;} +#else +# define Assert(cond,msg) +# define Trace(x) +# define Tracev(x) +# define Tracevv(x) +# define Tracec(c,x) +# define Tracecv(c,x) +#endif + +#define WARN(msg) {if (!quiet) fprintf msg ; \ + if (exit_code == OK) exit_code = WARNING;} + + /* in zip.c: */ +extern int zip OF((int in, int out)); +extern int file_read OF((char *buf, unsigned size)); + + /* in unzip.c */ +extern int unzip OF((int in, int out)); +extern int check_zipfile OF((int in)); + + /* in unpack.c */ +extern int unpack OF((int in, int out)); + + /* in gzip.c */ +RETSIGTYPE abort_gzip OF((void)); + + /* in deflate.c */ +void lm_init OF((int pack_level, ush *flags)); +ulg deflate OF((void)); + + /* in trees.c */ +void ct_init OF((ush *attr, int *method)); +int ct_tally OF((int dist, int lc)); +ulg flush_block OF((char *buf, ulg stored_len, int eof)); + + /* in bits.c */ +void bi_init OF((file_t zipfile)); +void send_bits OF((int value, int length)); +unsigned bi_reverse OF((unsigned value, int length)); +void bi_windup OF((void)); +void copy_block OF((char *buf, unsigned len, int header)); +extern int (*read_buf) OF((char *buf, unsigned size)); + + /* in util.c: */ +extern ulg updcrc OF((uch *s, unsigned n)); +extern void clear_bufs OF((void)); +extern int fill_inbuf OF((void)); +extern void flush_outbuf OF((void)); +extern void flush_window OF((void)); +extern void write_buf OF((int fd, voidp buf, unsigned cnt)); +extern char *strlwr OF((char *s)); +extern char *basename OF((char *fname)); +extern char *add_envopt OF((int *argcp, char ***argvp, char *env)); +extern void error OF((char *m)); +extern void warn OF((char *a, char *b)); +extern void read_error OF((void)); +extern void write_error OF((void)); +extern void display_ratio OF((long num, long den)); +extern voidp xmalloc OF((unsigned int size)); + + /* in inflate.c */ +extern int inflate OF((void)); diff --git a/gnu/usr.bin/gzip/inflate.c b/gnu/usr.bin/gzip/inflate.c new file mode 100644 index 0000000..aa31f9e --- /dev/null +++ b/gnu/usr.bin/gzip/inflate.c @@ -0,0 +1,954 @@ +/* inflate.c -- Not copyrighted 1992 by Mark Adler + version c10p1, 10 January 1993 */ + +/* You can do whatever you like with this source file, though I would + prefer that if you modify it and redistribute it that you include + comments to that effect with your name and the date. Thank you. + [The history has been moved to the file ChangeLog.] + */ + +/* + Inflate deflated (PKZIP's method 8 compressed) data. The compression + method searches for as much of the current string of bytes (up to a + length of 258) in the previous 32K bytes. If it doesn't find any + matches (of at least length 3), it codes the next byte. Otherwise, it + codes the length of the matched string and its distance backwards from + the current position. There is a single Huffman code that codes both + single bytes (called "literals") and match lengths. A second Huffman + code codes the distance information, which follows a length code. Each + length or distance code actually represents a base value and a number + of "extra" (sometimes zero) bits to get to add to the base value. At + the end of each deflated block is a special end-of-block (EOB) literal/ + length code. The decoding process is basically: get a literal/length + code; if EOB then done; if a literal, emit the decoded byte; if a + length then get the distance and emit the referred-to bytes from the + sliding window of previously emitted data. + + There are (currently) three kinds of inflate blocks: stored, fixed, and + dynamic. The compressor deals with some chunk of data at a time, and + decides which method to use on a chunk-by-chunk basis. A chunk might + typically be 32K or 64K. If the chunk is uncompressible, then the + "stored" method is used. In this case, the bytes are simply stored as + is, eight bits per byte, with none of the above coding. The bytes are + preceded by a count, since there is no longer an EOB code. + + If the data is compressible, then either the fixed or dynamic methods + are used. In the dynamic method, the compressed data is preceded by + an encoding of the literal/length and distance Huffman codes that are + to be used to decode this block. The representation is itself Huffman + coded, and so is preceded by a description of that code. These code + descriptions take up a little space, and so for small blocks, there is + a predefined set of codes, called the fixed codes. The fixed method is + used if the block codes up smaller that way (usually for quite small + chunks), otherwise the dynamic method is used. In the latter case, the + codes are customized to the probabilities in the current block, and so + can code it much better than the pre-determined fixed codes. + + The Huffman codes themselves are decoded using a mutli-level table + lookup, in order to maximize the speed of decoding plus the speed of + building the decoding tables. See the comments below that precede the + lbits and dbits tuning parameters. + */ + + +/* + Notes beyond the 1.93a appnote.txt: + + 1. Distance pointers never point before the beginning of the output + stream. + 2. Distance pointers can point back across blocks, up to 32k away. + 3. There is an implied maximum of 7 bits for the bit length table and + 15 bits for the actual data. + 4. If only one code exists, then it is encoded using one bit. (Zero + would be more efficient, but perhaps a little confusing.) If two + codes exist, they are coded using one bit each (0 and 1). + 5. There is no way of sending zero distance codes--a dummy must be + sent if there are none. (History: a pre 2.0 version of PKZIP would + store blocks with no distance codes, but this was discovered to be + too harsh a criterion.) Valid only for 1.93a. 2.04c does allow + zero distance codes, which is sent as one code of zero bits in + length. + 6. There are up to 286 literal/length codes. Code 256 represents the + end-of-block. Note however that the static length tree defines + 288 codes just to fill out the Huffman codes. Codes 286 and 287 + cannot be used though, since there is no length base or extra bits + defined for them. Similarly, there are up to 30 distance codes. + However, static trees define 32 codes (all 5 bits) to fill out the + Huffman codes, but the last two had better not show up in the data. + 7. Unzip can check dynamic Huffman blocks for complete code sets. + The exception is that a single code would not be complete (see #4). + 8. The five bits following the block type is really the number of + literal codes sent minus 257. + 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits + (1+6+6). Therefore, to output three times the length, you output + three codes (1+1+1), whereas to output four times the same length, + you only need two codes (1+3). Hmm. + 10. In the tree reconstruction algorithm, Code = Code + Increment + only if BitLength(i) is not zero. (Pretty obvious.) + 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) + 12. Note: length code 284 can represent 227-258, but length code 285 + really is 258. The last length deserves its own, short code + since it gets used a lot in very redundant files. The length + 258 is special since 258 - 3 (the min match length) is 255. + 13. The literal/length and distance code bit lengths are read as a + single stream of lengths. It is possible (and advantageous) for + a repeat code (16, 17, or 18) to go across the boundary between + the two sets of lengths. + */ + +#ifndef lint +static char rcsid[] = "$Id: inflate.c,v 0.13 1993/04/26 14:18:22 jloup Exp $"; +#endif + +#include <stdio.h> +#include <sys/types.h> + +#include "tailor.h" + +#if defined(STDC_HEADERS) || !defined(NO_STDLIB_H) +# include <stdlib.h> +#endif + +#include "gzip.h" +#define slide window + +/* Huffman code lookup table entry--this entry is four bytes for machines + that have 16-bit pointers (e.g. PC's in the small or medium model). + Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16 + means that v is a literal, 16 < e < 32 means that v is a pointer to + the next table, which codes e - 16 bits, and lastly e == 99 indicates + an unused code. If a code with e == 99 is looked up, this implies an + error in the data. */ +struct huft { + uch e; /* number of extra bits or operation */ + uch b; /* number of bits in this code or subcode */ + union { + ush n; /* literal, length base, or distance base */ + struct huft *t; /* pointer to next level of table */ + } v; +}; + + +/* Function prototypes */ +int huft_build OF((unsigned *, unsigned, unsigned, ush *, ush *, + struct huft **, int *)); +int huft_free OF((struct huft *)); +int inflate_codes OF((struct huft *, struct huft *, int, int)); +int inflate_stored OF((void)); +int inflate_fixed OF((void)); +int inflate_dynamic OF((void)); +int inflate_block OF((int *)); +int inflate OF((void)); + + +/* The inflate algorithm uses a sliding 32K byte window on the uncompressed + stream to find repeated byte strings. This is implemented here as a + circular buffer. The index is updated simply by incrementing and then + and'ing with 0x7fff (32K-1). */ +/* It is left to other modules to supply the 32K area. It is assumed + to be usable as if it were declared "uch slide[32768];" or as just + "uch *slide;" and then malloc'ed in the latter case. The definition + must be in unzip.h, included above. */ +/* unsigned wp; current position in slide */ +#define wp outcnt +#define flush_output(w) (wp=(w),flush_window()) + +/* Tables for deflate from PKZIP's appnote.txt. */ +static unsigned border[] = { /* Order of the bit length code lengths */ + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; +static ush cplens[] = { /* Copy lengths for literal codes 257..285 */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + /* note: see note #13 above about the 258 in this list. */ +static ush cplext[] = { /* Extra bits for literal codes 257..285 */ + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, + 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */ +static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */ + 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, + 8193, 12289, 16385, 24577}; +static ush cpdext[] = { /* Extra bits for distance codes */ + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, + 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, + 12, 12, 13, 13}; + + + +/* Macros for inflate() bit peeking and grabbing. + The usage is: + + NEEDBITS(j) + x = b & mask_bits[j]; + DUMPBITS(j) + + where NEEDBITS makes sure that b has at least j bits in it, and + DUMPBITS removes the bits from b. The macros use the variable k + for the number of bits in b. Normally, b and k are register + variables for speed, and are initialized at the beginning of a + routine that uses these macros from a global bit buffer and count. + + If we assume that EOB will be the longest code, then we will never + ask for bits with NEEDBITS that are beyond the end of the stream. + So, NEEDBITS should not read any more bytes than are needed to + meet the request. Then no bytes need to be "returned" to the buffer + at the end of the last block. + + However, this assumption is not true for fixed blocks--the EOB code + is 7 bits, but the other literal/length codes can be 8 or 9 bits. + (The EOB code is shorter than other codes because fixed blocks are + generally short. So, while a block always has an EOB, many other + literal/length codes have a significantly lower probability of + showing up at all.) However, by making the first table have a + lookup of seven bits, the EOB code will be found in that first + lookup, and so will not require that too many bits be pulled from + the stream. + */ + +ulg bb; /* bit buffer */ +unsigned bk; /* bits in bit buffer */ + +ush mask_bits[] = { + 0x0000, + 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + +#ifdef CRYPT + uch cc; +# define NEXTBYTE() \ + (decrypt ? (cc = get_byte(), zdecode(cc), cc) : get_byte()) +#else +# define NEXTBYTE() (uch)get_byte() +#endif +#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}} +#define DUMPBITS(n) {b>>=(n);k-=(n);} + + +/* + Huffman code decoding is performed using a multi-level table lookup. + The fastest way to decode is to simply build a lookup table whose + size is determined by the longest code. However, the time it takes + to build this table can also be a factor if the data being decoded + is not very long. The most common codes are necessarily the + shortest codes, so those codes dominate the decoding time, and hence + the speed. The idea is you can have a shorter table that decodes the + shorter, more probable codes, and then point to subsidiary tables for + the longer codes. The time it costs to decode the longer codes is + then traded against the time it takes to make longer tables. + + This results of this trade are in the variables lbits and dbits + below. lbits is the number of bits the first level table for literal/ + length codes can decode in one step, and dbits is the same thing for + the distance codes. Subsequent tables are also less than or equal to + those sizes. These values may be adjusted either when all of the + codes are shorter than that, in which case the longest code length in + bits is used, or when the shortest code is *longer* than the requested + table size, in which case the length of the shortest code in bits is + used. + + There are two different values for the two tables, since they code a + different number of possibilities each. The literal/length table + codes 286 possible values, or in a flat code, a little over eight + bits. The distance table codes 30 possible values, or a little less + than five bits, flat. The optimum values for speed end up being + about one bit more than those, so lbits is 8+1 and dbits is 5+1. + The optimum values may differ though from machine to machine, and + possibly even between compilers. Your mileage may vary. + */ + + +int lbits = 9; /* bits in base literal/length lookup table */ +int dbits = 6; /* bits in base distance lookup table */ + + +/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ +#define BMAX 16 /* maximum bit length of any code (16 for explode) */ +#define N_MAX 288 /* maximum number of codes in any set */ + + +unsigned hufts; /* track memory usage */ + + +int huft_build(b, n, s, d, e, t, m) +unsigned *b; /* code lengths in bits (all assumed <= BMAX) */ +unsigned n; /* number of codes (assumed <= N_MAX) */ +unsigned s; /* number of simple-valued codes (0..s-1) */ +ush *d; /* list of base values for non-simple codes */ +ush *e; /* list of extra bits for non-simple codes */ +struct huft **t; /* result: starting table */ +int *m; /* maximum lookup bits, returns actual */ +/* Given a list of code lengths and a maximum table size, make a set of + tables to decode that set of codes. Return zero on success, one if + the given code set is incomplete (the tables are still built in this + case), two if the input is invalid (all zero length codes or an + oversubscribed set of lengths), and three if not enough memory. */ +{ + unsigned a; /* counter for codes of length k */ + unsigned c[BMAX+1]; /* bit length count table */ + unsigned f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int h; /* table level */ + register unsigned i; /* counter, current code */ + register unsigned j; /* counter */ + register int k; /* number of bits in current code */ + int l; /* bits per table (returned in m) */ + register unsigned *p; /* pointer into c[], b[], or v[] */ + register struct huft *q; /* points to current table */ + struct huft r; /* table entry for structure assignment */ + struct huft *u[BMAX]; /* table stack */ + unsigned v[N_MAX]; /* values in order of bit length */ + register int w; /* bits before this table == (l * h) */ + unsigned x[BMAX+1]; /* bit offsets, then code stack */ + unsigned *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + unsigned z; /* number of entries in current table */ + + + /* Generate counts for each bit length */ + memzero(c, sizeof(c)); + p = b; i = n; + do { + Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), + n-i, *p)); + c[*p++]++; /* assume all entries <= BMAX */ + } while (--i); + if (c[0] == n) /* null input--all zero length codes */ + { + *t = (struct huft *)NULL; + *m = 0; + return 0; + } + + + /* Find minimum and maximum length, bound *m by those */ + l = *m; + for (j = 1; j <= BMAX; j++) + if (c[j]) + break; + k = j; /* minimum code length */ + if ((unsigned)l < j) + l = j; + for (i = BMAX; i; i--) + if (c[i]) + break; + g = i; /* maximum code length */ + if ((unsigned)l > i) + l = i; + *m = l; + + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) + if ((y -= c[j]) < 0) + return 2; /* bad input: more codes than bits */ + if ((y -= c[i]) < 0) + return 2; + c[i] += y; + + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; xp = x + 2; + while (--i) { /* note that i == g from above */ + *xp++ = (j += *p++); + } + + + /* Make a table of values in order of bit lengths */ + p = b; i = 0; + do { + if ((j = *p++) != 0) + v[x[j]++] = i; + } while (++i < n); + + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + h = -1; /* no tables yet--level -1 */ + w = -l; /* bits decoded == (l * h) */ + u[0] = (struct huft *)NULL; /* just to keep compilers happy */ + q = (struct huft *)NULL; /* ditto */ + z = 0; /* ditto */ + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) + { + a = c[k]; + while (a--) + { + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > w + l) + { + h++; + w += l; /* previous table always l bits */ + + /* compute minimum size table less than or equal to l bits */ + z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */ + if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ + { /* too few codes for k-w bit table */ + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + while (++j < z) /* try smaller tables up to z bits */ + { + if ((f <<= 1) <= *++xp) + break; /* enough codes to use up j bits */ + f -= *xp; /* else deduct codes from patterns */ + } + } + z = 1 << j; /* table entries for j-bit table */ + + /* allocate and link in new table */ + if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) == + (struct huft *)NULL) + { + if (h) + huft_free(u[0]); + return 3; /* not enough memory */ + } + hufts += z + 1; /* track memory usage */ + *t = q + 1; /* link to list for huft_free() */ + *(t = &(q->v.t)) = (struct huft *)NULL; + u[h] = ++q; /* table starts after link */ + + /* connect to last table, if there is one */ + if (h) + { + x[h] = i; /* save pattern for backing up */ + r.b = (uch)l; /* bits to dump before this table */ + r.e = (uch)(16 + j); /* bits in this table */ + r.v.t = q; /* pointer to this table */ + j = i >> (w - l); /* (get around Turbo C bug) */ + u[h-1][j] = r; /* connect to last table */ + } + } + + /* set up table entry in r */ + r.b = (uch)(k - w); + if (p >= v + n) + r.e = 99; /* out of values--invalid code */ + else if (*p < s) + { + r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */ + r.v.n = (ush)(*p); /* simple code is just the value */ + p++; /* one compiler does not like *p++ */ + } + else + { + r.e = (uch)e[*p - s]; /* non-simple--look up in lists */ + r.v.n = d[*p++ - s]; + } + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) + q[j] = r; + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) + i ^= j; + i ^= j; + + /* backup over finished tables */ + while ((i & ((1 << w) - 1)) != x[h]) + { + h--; /* don't need to update q */ + w -= l; + } + } + } + + + /* Return true (1) if we were given an incomplete table */ + return y != 0 && g != 1; +} + + + +int huft_free(t) +struct huft *t; /* table to free */ +/* Free the malloc'ed tables built by huft_build(), which makes a linked + list of the tables it made, with the links in a dummy first entry of + each table. */ +{ + register struct huft *p, *q; + + + /* Go through linked list, freeing from the malloced (t[-1]) address. */ + p = t; + while (p != (struct huft *)NULL) + { + q = (--p)->v.t; + free((char*)p); + p = q; + } + return 0; +} + + +int inflate_codes(tl, td, bl, bd) +struct huft *tl, *td; /* literal/length and distance decoder tables */ +int bl, bd; /* number of bits decoded by tl[] and td[] */ +/* inflate (decompress) the codes in a deflated (compressed) block. + Return an error code or zero if it all goes ok. */ +{ + register unsigned e; /* table entry flag/number of extra bits */ + unsigned n, d; /* length and index for copy */ + unsigned w; /* current window position */ + struct huft *t; /* pointer to table entry */ + unsigned ml, md; /* masks for bl and bd bits */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + /* inflate the coded data */ + ml = mask_bits[bl]; /* precompute masks for speed */ + md = mask_bits[bd]; + for (;;) /* do until end of block */ + { + NEEDBITS((unsigned)bl) + if ((e = (t = tl + ((unsigned)b & ml))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + if (e == 16) /* then it's a literal */ + { + slide[w++] = (uch)t->v.n; + Tracevv((stderr, "%c", slide[w-1])); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } + else /* it's an EOB or a length */ + { + /* exit if end of block */ + if (e == 15) + break; + + /* get length of block to copy */ + NEEDBITS(e) + n = t->v.n + ((unsigned)b & mask_bits[e]); + DUMPBITS(e); + + /* decode distance of block to copy */ + NEEDBITS((unsigned)bd) + if ((e = (t = td + ((unsigned)b & md))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + NEEDBITS(e) + d = w - t->v.n - ((unsigned)b & mask_bits[e]); + DUMPBITS(e) + Tracevv((stderr,"\\[%d,%d]", w-d, n)); + + /* do the copy */ + do { + n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e); +#if !defined(NOMEMCPY) && !defined(DEBUG) + if (w - d >= e) /* (this test assumes unsigned comparison) */ + { + memcpy(slide + w, slide + d, e); + w += e; + d += e; + } + else /* do it slow to avoid memcpy() overlap */ +#endif /* !NOMEMCPY */ + do { + slide[w++] = slide[d++]; + Tracevv((stderr, "%c", slide[w-1])); + } while (--e); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } while (n); + } + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + + /* done */ + return 0; +} + + + +int inflate_stored() +/* "decompress" an inflated type 0 (stored) block. */ +{ + unsigned n; /* number of bytes in block */ + unsigned w; /* current window position */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + + /* go to byte boundary */ + n = k & 7; + DUMPBITS(n); + + + /* get the length and its complement */ + NEEDBITS(16) + n = ((unsigned)b & 0xffff); + DUMPBITS(16) + NEEDBITS(16) + if (n != (unsigned)((~b) & 0xffff)) + return 1; /* error in compressed data */ + DUMPBITS(16) + + + /* read and output the compressed data */ + while (n--) + { + NEEDBITS(8) + slide[w++] = (uch)b; + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + DUMPBITS(8) + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + return 0; +} + + + +int inflate_fixed() +/* decompress an inflated type 1 (fixed Huffman codes) block. We should + either replace this with a custom decoder, or at least precompute the + Huffman tables. */ +{ + int i; /* temporary variable */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned l[288]; /* length list for huft_build */ + + + /* set up literal table */ + for (i = 0; i < 144; i++) + l[i] = 8; + for (; i < 256; i++) + l[i] = 9; + for (; i < 280; i++) + l[i] = 7; + for (; i < 288; i++) /* make a complete, but wrong code set */ + l[i] = 8; + bl = 7; + if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0) + return i; + + + /* set up distance table */ + for (i = 0; i < 30; i++) /* make an incomplete code set */ + l[i] = 5; + bd = 5; + if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1) + { + huft_free(tl); + return i; + } + + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + return 0; +} + + + +int inflate_dynamic() +/* decompress an inflated type 2 (dynamic Huffman codes) block. */ +{ + int i; /* temporary variables */ + unsigned j; + unsigned l; /* last length */ + unsigned m; /* mask for bit lengths table */ + unsigned n; /* number of lengths to get */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned nb; /* number of bit length codes */ + unsigned nl; /* number of literal/length codes */ + unsigned nd; /* number of distance codes */ +#ifdef PKZIP_BUG_WORKAROUND + unsigned ll[288+32]; /* literal/length and distance code lengths */ +#else + unsigned ll[286+30]; /* literal/length and distance code lengths */ +#endif + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in table lengths */ + NEEDBITS(5) + nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */ + DUMPBITS(5) + NEEDBITS(5) + nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */ + DUMPBITS(5) + NEEDBITS(4) + nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */ + DUMPBITS(4) +#ifdef PKZIP_BUG_WORKAROUND + if (nl > 288 || nd > 32) +#else + if (nl > 286 || nd > 30) +#endif + return 1; /* bad lengths */ + + + /* read in bit-length-code lengths */ + for (j = 0; j < nb; j++) + { + NEEDBITS(3) + ll[border[j]] = (unsigned)b & 7; + DUMPBITS(3) + } + for (; j < 19; j++) + ll[border[j]] = 0; + + + /* build decoding table for trees--single level, 7 bit lookup */ + bl = 7; + if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0) + { + if (i == 1) + huft_free(tl); + return i; /* incomplete code set */ + } + + + /* read in literal and distance code lengths */ + n = nl + nd; + m = mask_bits[bl]; + i = l = 0; + while ((unsigned)i < n) + { + NEEDBITS((unsigned)bl) + j = (td = tl + ((unsigned)b & m))->b; + DUMPBITS(j) + j = td->v.n; + if (j < 16) /* length of code in bits (0..15) */ + ll[i++] = l = j; /* save last length in l */ + else if (j == 16) /* repeat last length 3 to 6 times */ + { + NEEDBITS(2) + j = 3 + ((unsigned)b & 3); + DUMPBITS(2) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = l; + } + else if (j == 17) /* 3 to 10 zero length codes */ + { + NEEDBITS(3) + j = 3 + ((unsigned)b & 7); + DUMPBITS(3) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + else /* j == 18: 11 to 138 zero length codes */ + { + NEEDBITS(7) + j = 11 + ((unsigned)b & 0x7f); + DUMPBITS(7) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + } + + + /* free decoding table for trees */ + huft_free(tl); + + + /* restore the global bit buffer */ + bb = b; + bk = k; + + + /* build the decoding tables for literal/length and distance codes */ + bl = lbits; + if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0) + { + if (i == 1) { + fprintf(stderr, " incomplete literal tree\n"); + huft_free(tl); + } + return i; /* incomplete code set */ + } + bd = dbits; + if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) + { + if (i == 1) { + fprintf(stderr, " incomplete distance tree\n"); +#ifdef PKZIP_BUG_WORKAROUND + i = 0; + } +#else + huft_free(td); + } + huft_free(tl); + return i; /* incomplete code set */ +#endif + } + + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + return 0; +} + + + +int inflate_block(e) +int *e; /* last block flag */ +/* decompress an inflated block */ +{ + unsigned t; /* block type */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in last block bit */ + NEEDBITS(1) + *e = (int)b & 1; + DUMPBITS(1) + + + /* read in block type */ + NEEDBITS(2) + t = (unsigned)b & 3; + DUMPBITS(2) + + + /* restore the global bit buffer */ + bb = b; + bk = k; + + + /* inflate that block type */ + if (t == 2) + return inflate_dynamic(); + if (t == 0) + return inflate_stored(); + if (t == 1) + return inflate_fixed(); + + + /* bad block type */ + return 2; +} + + + +int inflate() +/* decompress an inflated entry */ +{ + int e; /* last block flag */ + int r; /* result code */ + unsigned h; /* maximum struct huft's malloc'ed */ + + + /* initialize window, bit buffer */ + wp = 0; + bk = 0; + bb = 0; + + + /* decompress until the last block */ + h = 0; + do { + hufts = 0; + if ((r = inflate_block(&e)) != 0) + return r; + if (hufts > h) + h = hufts; + } while (!e); + + /* Undo too much lookahead. The next read will be byte aligned so we + * can discard unused bits in the last meaningful byte. + */ + while (bk >= 8) { + bk -= 8; + inptr--; + } + + /* flush out slide */ + flush_output(wp); + + + /* return success */ +#ifdef DEBUG + fprintf(stderr, "<%u> ", h); +#endif /* DEBUG */ + return 0; +} diff --git a/gnu/usr.bin/gzip/lzw.c b/gnu/usr.bin/gzip/lzw.c new file mode 100644 index 0000000..cd09047 --- /dev/null +++ b/gnu/usr.bin/gzip/lzw.c @@ -0,0 +1,27 @@ +/* lzw.c -- compress files in LZW format. + * This is a dummy version avoiding patent problems. + */ + +#ifndef lint +static char rcsid[] = "$Id: lzw.c,v 0.8 1993/04/25 08:09:58 jloup Exp $"; +#endif + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" + +#include <stdio.h> + +static int msg_done = 0; + +/* Compress in to out with lzw method. */ +int lzw(in, out) + int in, out; +{ + if (msg_done) return ERROR; + msg_done = 1; + fprintf(stderr,"output in compress .Z format not supported\n"); + in++, out++; /* avoid warnings on unused variables */ + exit_code = ERROR; + return ERROR; +} diff --git a/gnu/usr.bin/gzip/lzw.h b/gnu/usr.bin/gzip/lzw.h new file mode 100644 index 0000000..4b7ac86 --- /dev/null +++ b/gnu/usr.bin/gzip/lzw.h @@ -0,0 +1,42 @@ +/* lzw.h -- define the lzw functions. + * Copyright (C) 1992-1993 Jean-loup Gailly. + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#if !defined(OF) && defined(lint) +# include "gzip.h" +#endif + +#ifndef BITS +# define BITS 16 +#endif +#define INIT_BITS 9 /* Initial number of bits per code */ + +#define LZW_MAGIC "\037\235" /* Magic header for lzw files, 1F 9D */ + +#define BIT_MASK 0x1f /* Mask for 'number of compression bits' */ +/* Mask 0x20 is reserved to mean a fourth header byte, and 0x40 is free. + * It's a pity that old uncompress does not check bit 0x20. That makes + * extension of the format actually undesirable because old compress + * would just crash on the new format instead of giving a meaningful + * error message. It does check the number of bits, but it's more + * helpful to say "unsupported format, get a new version" than + * "can only handle 16 bits". + */ + +#define BLOCK_MODE 0x80 +/* Block compression: if table is full and compression rate is dropping, + * clear the dictionary. + */ + +#define LZW_RESERVED 0x60 /* reserved bits */ + +#define CLEAR 256 /* flush the dictionary */ +#define FIRST (CLEAR+1) /* first free entry */ + +extern int maxbits; /* max bits per code for LZW */ +extern int block_mode; /* block compress mode -C compatible with 2.0 */ + +extern int lzw OF((int in, int out)); +extern int unlzw OF((int in, int out)); diff --git a/gnu/usr.bin/gzip/match.S b/gnu/usr.bin/gzip/match.S new file mode 100644 index 0000000..cd3176b --- /dev/null +++ b/gnu/usr.bin/gzip/match.S @@ -0,0 +1,379 @@ +/* match.s -- optional optimized asm version of longest match in deflate.c + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + * + * The 68020 version has been written by Francesco Potorti` <pot@cnuce.cnr.it> + * with adaptations by Carsten Steger <stegerc@informatik.tu-muenchen.de>, + * Andreas Schwab <schwab@lamothe.informatik.uni-dortmund.de> and + * Kristoffer Eriksson <ske@pkmab.se> + */ + +/* $Id: match.S,v 0.13 1993/05/24 12:03:03 jloup Exp $ */ + +/* Preprocess with -DNO_UNDERLINE if your C compiler does not prefix + * external symbols with an underline character '_'. + */ +#ifdef NO_UNDERLINE +# define _prev prev +# define _window window +# define _match_start match_start +# define _prev_length prev_length +# define _good_match good_match +# define _nice_match nice_match +# define _strstart strstart +# define _max_chain_length max_chain_length + +# define _match_init match_init +# define _longest_match longest_match +#endif + +#ifdef DYN_ALLOC + error: DYN_ALLOC not yet supported in match.s +#endif + +#if defined(i386) || defined(_I386) + +/* This version is for 386 Unix or OS/2 in 32 bit mode. + * Warning: it uses the AT&T syntax: mov source,dest + * This file is only optional. If you want to force the C version, + * add -DNO_ASM to CFLAGS in Makefile and set OBJA to an empty string. + * If you have reduced WSIZE in gzip.h, then change its value below. + * This version assumes static allocation of the arrays (-DDYN_ALLOC not used). + */ + + .file "match.S" + +#define MAX_MATCH 258 +#define MAX_MATCH2 128 /* MAX_MATCH/2-1 */ +#define MIN_MATCH 3 +#define WSIZE 32768 +#define MAX_DIST WSIZE - MAX_MATCH - MIN_MATCH - 1 + + .globl _match_init + .globl _longest_match + + .text + +_match_init: + ret + +/*----------------------------------------------------------------------- + * Set match_start to the longest match starting at the given string and + * return its length. Matches shorter or equal to prev_length are discarded, + * in which case the result is equal to prev_length and match_start is + * garbage. + * IN assertions: cur_match is the head of the hash chain for the current + * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1 + */ + +_longest_match: /* int longest_match(cur_match) */ + +#define cur_match 20(%esp) + /* return address */ /* esp+16 */ + push %ebp /* esp+12 */ + push %edi /* esp+8 */ + push %esi /* esp+4 */ + push %ebx /* esp */ + +/* + * match equ esi + * scan equ edi + * chain_length equ ebp + * best_len equ ebx + * limit equ edx + */ + mov cur_match,%esi + mov _max_chain_length,%ebp /* chain_length = max_chain_length */ + mov _strstart,%edi + mov %edi,%edx + sub $ MAX_DIST,%edx /* limit = strstart-MAX_DIST */ + jae limit_ok + sub %edx,%edx /* limit = NIL */ +limit_ok: + add $ _window+2,%edi /* edi = offset(window+strstart+2) */ + mov _prev_length,%ebx /* best_len = prev_length */ + movw -3(%ebx,%edi),%ax /* ax = scan[best_len-1..best_len] */ + movw -2(%edi),%cx /* cx = scan[0..1] */ + cmp _good_match,%ebx /* do we have a good match already? */ + jb do_scan + shr $2,%ebp /* chain_length >>= 2 */ + jmp do_scan + + .align 4 +long_loop: +/* at this point, edi == scan+2, esi == cur_match */ + movw -3(%ebx,%edi),%ax /* ax = scan[best_len-1..best_len] */ + movw -2(%edi),%cx /* cx = scan[0..1] */ +short_loop: +/* + * at this point, di == scan+2, si == cur_match, + * ax = scan[best_len-1..best_len] and cx = scan[0..1] + */ + and $ WSIZE-1, %esi + movw _prev(%esi,%esi),%si /* cur_match = prev[cur_match] */ + /* top word of esi is still 0 */ + cmp %edx,%esi /* cur_match <= limit ? */ + jbe the_end + dec %ebp /* --chain_length */ + jz the_end +do_scan: + cmpw _window-1(%ebx,%esi),%ax/* check match at best_len-1 */ + jne short_loop + cmpw _window(%esi),%cx /* check min_match_length match */ + jne short_loop + + lea _window+2(%esi),%esi /* si = match */ + mov %edi,%eax /* ax = scan+2 */ + mov $ MAX_MATCH2,%ecx /* scan for at most MAX_MATCH bytes */ + rep; cmpsw /* loop until mismatch */ + je maxmatch /* match of length MAX_MATCH? */ +mismatch: + movb -2(%edi),%cl /* mismatch on first or second byte? */ + subb -2(%esi),%cl /* cl = 0 if first bytes equal */ + xchg %edi,%eax /* edi = scan+2, eax = end of scan */ + sub %edi,%eax /* eax = len */ + sub %eax,%esi /* esi = cur_match + 2 + offset(window) */ + sub $ _window+2,%esi /* esi = cur_match */ + subb $1,%cl /* set carry if cl == 0 (cannot use DEC) */ + adc $0,%eax /* eax = carry ? len+1 : len */ + cmp %ebx,%eax /* len > best_len ? */ + jle long_loop + mov %esi,_match_start /* match_start = cur_match */ + mov %eax,%ebx /* ebx = best_len = len */ + cmp _nice_match,%eax /* len >= nice_match ? */ + jl long_loop +the_end: + mov %ebx,%eax /* result = eax = best_len */ + pop %ebx + pop %esi + pop %edi + pop %ebp + ret +maxmatch: + cmpsb + jmp mismatch + +#else + +/* ======================== 680x0 version ================================= */ + +#if defined(m68k)||defined(mc68k)||defined(__mc68000__)||defined(__MC68000__) +# ifndef mc68000 +# define mc68000 +# endif +#endif + +#if defined(__mc68020__) || defined(__MC68020__) || defined(sysV68) +# ifndef mc68020 +# define mc68020 +# endif +#endif + +#if defined(mc68020) || defined(mc68000) + +#if (defined(mc68020) || defined(NeXT)) && !defined(UNALIGNED_OK) +# define UNALIGNED_OK +#endif + +#ifdef sysV68 /* Try Motorola Delta style */ + +# define GLOBAL(symbol) global symbol +# define TEXT text +# define FILE(filename) file filename +# define invert_maybe(src,dst) dst,src +# define imm(data) &data +# define reg(register) %register + +# define addl add.l +# define addql addq.l +# define blos blo.b +# define bhis bhi.b +# define bras bra.b +# define clrl clr.l +# define cmpmb cmpm.b +# define cmpw cmp.w +# define cmpl cmp.l +# define lslw lsl.w +# define lsrl lsr.l +# define movel move.l +# define movew move.w +# define moveb move.b +# define moveml movem.l +# define subl sub.l +# define subw sub.w +# define subql subq.l + +# define IndBase(bd,An) (bd,An) +# define IndBaseNdxl(bd,An,Xn) (bd,An,Xn.l) +# define IndBaseNdxw(bd,An,Xn) (bd,An,Xn.w) +# define predec(An) -(An) +# define postinc(An) (An)+ + +#else /* default style (Sun 3, NeXT, Amiga, Atari) */ + +# define GLOBAL(symbol) .globl symbol +# define TEXT .text +# define FILE(filename) .even +# define invert_maybe(src,dst) src,dst +# if defined(sun) || defined(mc68k) +# define imm(data) #data +# else +# define imm(data) \#data +# endif +# define reg(register) register + +# define blos bcss +# if defined(sun) || defined(mc68k) +# define movel movl +# define movew movw +# define moveb movb +# endif +# define IndBase(bd,An) An@(bd) +# define IndBaseNdxl(bd,An,Xn) An@(bd,Xn:l) +# define IndBaseNdxw(bd,An,Xn) An@(bd,Xn:w) +# define predec(An) An@- +# define postinc(An) An@+ + +#endif /* styles */ + +#define Best_Len reg(d0) /* unsigned */ +#define Cur_Match reg(d1) /* Ipos */ +#define Loop_Counter reg(d2) /* int */ +#define Scan_Start reg(d3) /* unsigned short */ +#define Scan_End reg(d4) /* unsigned short */ +#define Limit reg(d5) /* IPos */ +#define Chain_Length reg(d6) /* unsigned */ +#define Scan_Test reg(d7) +#define Scan reg(a0) /* *uch */ +#define Match reg(a1) /* *uch */ +#define Prev_Address reg(a2) /* *Pos */ +#define Scan_Ini reg(a3) /* *uch */ +#define Match_Ini reg(a4) /* *uch */ +#define Stack_Pointer reg(sp) + +#define MAX_MATCH 258 +#define MIN_MATCH 3 +#define WSIZE 32768 +#define MAX_DIST (WSIZE - MAX_MATCH - MIN_MATCH - 1) + + GLOBAL (_match_init) + GLOBAL (_longest_match) + + TEXT + + FILE ("match.S") + +_match_init: + rts + +/*----------------------------------------------------------------------- + * Set match_start to the longest match starting at the given string and + * return its length. Matches shorter or equal to prev_length are discarded, + * in which case the result is equal to prev_length and match_start is + * garbage. + * IN assertions: cur_match is the head of the hash chain for the current + * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1 + */ + +/* int longest_match (cur_match) */ + +#ifdef UNALIGNED_OK +# define pushreg 15928 /* d2-d6/a2-a4 */ +# define popreg 7292 +#else +# define pushreg 16184 /* d2-d7/a2-a4 */ +# define popreg 7420 +#endif + +_longest_match: + movel IndBase(4,Stack_Pointer),Cur_Match + moveml imm(pushreg),predec(Stack_Pointer) + movel _max_chain_length,Chain_Length + movel _prev_length,Best_Len + movel imm(_prev),Prev_Address + movel imm(_window+MIN_MATCH),Match_Ini + movel _strstart,Limit + movel Match_Ini,Scan_Ini + addl Limit,Scan_Ini + subw imm(MAX_DIST),Limit + bhis L__limit_ok + clrl Limit +L__limit_ok: + cmpl invert_maybe(_good_match,Best_Len) + blos L__length_ok + lsrl imm(2),Chain_Length +L__length_ok: + subql imm(1),Chain_Length +#ifdef UNALIGNED_OK + movew IndBase(-MIN_MATCH,Scan_Ini),Scan_Start + movew IndBaseNdxw(-MIN_MATCH-1,Scan_Ini,Best_Len),Scan_End +#else + moveb IndBase(-MIN_MATCH,Scan_Ini),Scan_Start + lslw imm(8),Scan_Start + moveb IndBase(-MIN_MATCH+1,Scan_Ini),Scan_Start + moveb IndBaseNdxw(-MIN_MATCH-1,Scan_Ini,Best_Len),Scan_End + lslw imm(8),Scan_End + moveb IndBaseNdxw(-MIN_MATCH,Scan_Ini,Best_Len),Scan_End +#endif + bras L__do_scan + +L__long_loop: +#ifdef UNALIGNED_OK + movew IndBaseNdxw(-MIN_MATCH-1,Scan_Ini,Best_Len),Scan_End +#else + moveb IndBaseNdxw(-MIN_MATCH-1,Scan_Ini,Best_Len),Scan_End + lslw imm(8),Scan_End + moveb IndBaseNdxw(-MIN_MATCH,Scan_Ini,Best_Len),Scan_End +#endif + +L__short_loop: + lslw imm(1),Cur_Match + movew IndBaseNdxl(0,Prev_Address,Cur_Match),Cur_Match + cmpw invert_maybe(Limit,Cur_Match) + dbls Chain_Length,L__do_scan + bras L__return + +L__do_scan: + movel Match_Ini,Match + addl Cur_Match,Match +#ifdef UNALIGNED_OK + cmpw invert_maybe(IndBaseNdxw(-MIN_MATCH-1,Match,Best_Len),Scan_End) + bne L__short_loop + cmpw invert_maybe(IndBase(-MIN_MATCH,Match),Scan_Start) + bne L__short_loop +#else + moveb IndBaseNdxw(-MIN_MATCH-1,Match,Best_Len),Scan_Test + lslw imm(8),Scan_Test + moveb IndBaseNdxw(-MIN_MATCH,Match,Best_Len),Scan_Test + cmpw invert_maybe(Scan_Test,Scan_End) + bne L__short_loop + moveb IndBase(-MIN_MATCH,Match),Scan_Test + lslw imm(8),Scan_Test + moveb IndBase(-MIN_MATCH+1,Match),Scan_Test + cmpw invert_maybe(Scan_Test,Scan_Start) + bne L__short_loop +#endif + + movew imm((MAX_MATCH-MIN_MATCH+1)-1),Loop_Counter + movel Scan_Ini,Scan +L__scan_loop: + cmpmb postinc(Match),postinc(Scan) + dbne Loop_Counter,L__scan_loop + + subl Scan_Ini,Scan + addql imm(MIN_MATCH-1),Scan + cmpl invert_maybe(Best_Len,Scan) + bls L__short_loop + movel Scan,Best_Len + movel Cur_Match,_match_start + cmpl invert_maybe(_nice_match,Best_Len) + blos L__long_loop +L__return: + moveml postinc(Stack_Pointer),imm(popreg) + rts + +#else + error: this asm version is for 386 or 680x0 only +#endif /* mc68000 || mc68020 */ +#endif /* i386 || _I386 */ diff --git a/gnu/usr.bin/gzip/revision.h b/gnu/usr.bin/gzip/revision.h new file mode 100644 index 0000000..5a4e1e6 --- /dev/null +++ b/gnu/usr.bin/gzip/revision.h @@ -0,0 +1,16 @@ +/* revision.h -- define the version number + * Copyright (C) 1992-1993 Jean-loup Gailly. + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#define VERSION "1.1.1" +#define PATCHLEVEL 0 +#define REVDATE "1 Jun 93" + +/* This version does not support compression into old compress format: */ +#ifdef LZW +# undef LZW +#endif + +/* $Id: revision.h,v 0.20 1993/06/01 14:03:17 jloup Exp $ */ diff --git a/gnu/usr.bin/gzip/tailor.h b/gnu/usr.bin/gzip/tailor.h new file mode 100644 index 0000000..915760a --- /dev/null +++ b/gnu/usr.bin/gzip/tailor.h @@ -0,0 +1,268 @@ +/* tailor.h -- target dependent definitions + * Copyright (C) 1992-1993 Jean-loup Gailly. + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +/* The target dependent definitions should be defined here only. + * The target dependent functions should be defined in tailor.c. + */ + +/* $Id: tailor.h,v 0.16 1993/06/01 12:46:03 jloup Exp $ */ + +#if defined(__MSDOS__) && !defined(MSDOS) +# define MSDOS +#endif + +#if defined(OS2) && defined(MSDOS) /* MS C under OS/2 */ +# undef MSDOS +#endif + +#ifdef MSDOS +# ifdef __GNUC__ + /* DJGPP version 1.09+ on MS-DOS. + * The DJGPP 1.09 stat() function must be upgraded before gzip will + * fully work. + * No need for DIRENT, since <unistd.h> defines POSIX_SOURCE which + * implies DIRENT. + */ +# define near +# else +# define MAXSEG_64K +# ifdef __TURBOC__ +# define NO_UTIME +# else /* MSC */ +# define HAVE_SYS_UTIME_H +# define NO_UTIME_H +# endif +# endif +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 128 +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define NO_CHOWN +# define PROTO +# define STDC_HEADERS +# define NO_SIZE_CHECK +# define casemap(c) tolow(c) /* Force file names to lower case */ +# include <io.h> +# define OS_CODE 0x00 +# define SET_BINARY_MODE(fd) setmode(fd, O_BINARY) +# if !defined(NO_ASM) && !defined(ASMV) +# define ASMV +# endif +#else +# define near +#endif + +#ifdef OS2 +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 260 +# ifdef OS2FAT +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# endif +# define NO_CHOWN +# define PROTO +# define STDC_HEADERS +# define HAVE_SYS_UTIME_H +# define NO_UTIME_H +# define casemap(c) tolow(c) +# include <io.h> +# define OS_CODE 0x06 +# define SET_BINARY_MODE(fd) setmode(fd, O_BINARY) +# ifdef _MSC_VER +# define MAXSEG_64K +# undef near +# define near _near +# endif +# ifdef __EMX__ +# define DIRENT +# define EXPAND(argc,argv) \ + {_response(&argc, &argv); _wildcard(&argc, &argv);} +# endif +#endif + +#ifdef MSDOS +# ifdef __TURBOC__ +# include <alloc.h> +# define DYN_ALLOC + /* Turbo C 2.0 does not accept static allocations of large arrays */ + void * fcalloc (unsigned items, unsigned size); + void fcfree (void *ptr); +# else /* MSC */ +# include <malloc.h> +# define fcalloc(nitems,itemsize) halloc((long)(nitems),(itemsize)) +# define fcfree(ptr) hfree(ptr) +# endif +#else +# ifdef MAXSEG_64K +# define fcalloc(items,size) calloc((items),(size)) +# else +# define fcalloc(items,size) malloc((size_t)(items)*(size_t)(size)) +# endif +# define fcfree(ptr) free(ptr) +#endif + +#if defined(VAXC) || defined(VMS) +# define PATH_SEP ']' +# define PATH_SEP2 ':' +# define SUFFIX_SEP ';' +# define NO_MULTIPLE_DOTS +# define Z_SUFFIX "-gz" +# define RECORD_IO 1 +# define casemap(c) tolow(c) +# define OS_CODE 0x02 +# define OPTIONS_VAR "GZIP_OPT" +# define STDC_HEADERS +# define NO_UTIME +# define EXPAND(argc,argv) vms_expand_args(&argc,&argv); +# include <file.h> +# define unlink delete +# ifdef VAXC +# define NO_FCNTL_H +# include <unixio.h> +# endif +#endif + +#ifdef AMIGA +# define PATH_SEP2 ':' +# define STDC_HEADERS +# define casemap(c) tolow(c) /* Force file names to lower case */ +# define OS_CODE 0x01 +# define ASMV +# ifdef __GNUC__ +# define DIRENT +# define HAVE_UNISTD_H +# define RETSIGTYPE int +# else /* SASC */ +# define NO_STDIN_FSTAT +# define SYSDIR +# define NO_SYMLINK +# define NO_CHOWN +# define NO_FCNTL_H +# include <fcntl.h> /* for read() and write() */ +# define direct dirent + extern void _expand_args(int *argc, char ***argv); +# define EXPAND(argc,argv) _expand_args(&argc,&argv); +# endif +#endif + +#if defined(ATARI) || defined(atarist) +# ifndef STDC_HEADERS +# define STDC_HEADERS +# define HAVE_UNISTD_H +# define DIRENT +# endif +# define ASMV +# define OS_CODE 0x05 +# ifdef TOSFS +# define NO_SYMLINK +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define NO_CHOWN +# endif +#endif + +#ifdef MACOS +# define PATH_SEP ':' +# define DYN_ALLOC +# define PROTO +# define NO_STDIN_FSTAT +# define NO_CHOWN +# define NO_UTIME +# define chmod(file, mode) (0) +# define OPEN(name, flags, mode) open(name, flags) +# define OS_CODE 0x07 +# ifdef MPW +# define isatty(fd) ((fd) <= 2) +# endif +#endif + +#ifdef __50SERIES /* Prime/PRIMOS */ +# define PATH_SEP '>' +# define STDC_HEADERS +# define NO_MEMORY_H +# define NO_UTIME_H +# define NO_UTIME +# define NO_CHOWN +# define NO_STDIN_FSTAT +# define NO_SIZE_CHECK +# define NO_SYMLINK +# define RECORD_IO 1 +# define casemap(c) tolow(c) /* Force file names to lower case */ +# define put_char(c) put_byte((c) & 0x7F) +# define get_char(c) ascii2pascii(get_byte()) +# define OS_CODE 0x0F /* temporary, subject to change */ +# undef SIGTERM /* We don't want a signal handler for SIGTERM */ +#endif + +#ifdef WIN32 +# define OS_CODE 0x0b +#endif + +#ifdef TOPS20 +# define OS_CODE 0x0a +#endif + +#ifndef unix +# define NO_ST_INO /* don't rely on inode numbers */ +#endif + + + /* Common defaults */ + +#ifndef OS_CODE +# define OS_CODE 0x03 /* assume Unix */ +#endif + +#ifndef PATH_SEP +# define PATH_SEP '/' +#endif + +#ifndef casemap +# define casemap(c) (c) +#endif + +#ifndef OPTIONS_VAR +# define OPTIONS_VAR "GZIP" +#endif + +#ifndef Z_SUFFIX +# define Z_SUFFIX ".gz" +#endif + +#ifdef MAX_EXT_CHARS +# define MAX_SUFFIX MAX_EXT_CHARS +#else +# define MAX_SUFFIX 30 +#endif + +#ifndef EXPAND +# define EXPAND(argc,argv) +#endif + +#ifndef RECORD_IO +# define RECORD_IO 0 +#endif + +#ifndef SET_BINARY_MODE +# define SET_BINARY_MODE(fd) +#endif + +#ifndef OPEN +# define OPEN(name, flags, mode) open(name, flags, mode) +#endif + +#ifndef get_char +# define get_char() get_byte() +#endif + +#ifndef put_char +# define put_char(c) put_byte(c) +#endif diff --git a/gnu/usr.bin/gzip/trees.c b/gnu/usr.bin/gzip/trees.c new file mode 100644 index 0000000..2cf380a --- /dev/null +++ b/gnu/usr.bin/gzip/trees.c @@ -0,0 +1,1076 @@ +/* trees.c -- output deflated data using Huffman coding + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +/* + * PURPOSE + * + * Encode various sets of source values using variable-length + * binary code trees. + * + * DISCUSSION + * + * The PKZIP "deflation" process uses several Huffman trees. The more + * common source values are represented by shorter bit sequences. + * + * Each code tree is stored in the ZIP file in a compressed form + * which is itself a Huffman encoding of the lengths of + * all the code strings (in ascending order by source values). + * The actual code strings are reconstructed from the lengths in + * the UNZIP process, as described in the "application note" + * (APPNOTE.TXT) distributed as part of PKWARE's PKZIP program. + * + * REFERENCES + * + * Lynch, Thomas J. + * Data Compression: Techniques and Applications, pp. 53-55. + * Lifetime Learning Publications, 1985. ISBN 0-534-03418-7. + * + * Storer, James A. + * Data Compression: Methods and Theory, pp. 49-50. + * Computer Science Press, 1988. ISBN 0-7167-8156-5. + * + * Sedgewick, R. + * Algorithms, p290. + * Addison-Wesley, 1983. ISBN 0-201-06672-6. + * + * INTERFACE + * + * void ct_init (ush *attr, int *methodp) + * Allocate the match buffer, initialize the various tables and save + * the location of the internal file attribute (ascii/binary) and + * method (DEFLATE/STORE) + * + * void ct_tally (int dist, int lc); + * Save the match info and tally the frequency counts. + * + * long flush_block (char *buf, ulg stored_len, int eof) + * Determine the best encoding for the current block: dynamic trees, + * static trees or store, and output the encoded block to the zip + * file. Returns the total compressed length for the file so far. + * + */ + +#include <ctype.h> +#include <stdio.h> + +#include "tailor.h" +#include "gzip.h" + +#ifndef lint +static char rcsid[] = "$Id: trees.c,v 0.11 1993/03/26 14:55:43 jloup Exp $"; +#endif + +/* =========================================================================== + * Constants + */ + +#define MAX_BITS 15 +/* All codes must not exceed MAX_BITS bits */ + +#define MAX_BL_BITS 7 +/* Bit length codes must not exceed MAX_BL_BITS bits */ + +#define LENGTH_CODES 29 +/* number of length codes, not counting the special END_BLOCK code */ + +#define LITERALS 256 +/* number of literal bytes 0..255 */ + +#define END_BLOCK 256 +/* end of block literal code */ + +#define L_CODES (LITERALS+1+LENGTH_CODES) +/* number of Literal or Length codes, including the END_BLOCK code */ + +#define D_CODES 30 +/* number of distance codes */ + +#define BL_CODES 19 +/* number of codes used to transfer the bit lengths */ + + +local int near extra_lbits[LENGTH_CODES] /* extra bits for each length code */ + = {0,0,0,0,0,0,0,0,1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,0}; + +local int near extra_dbits[D_CODES] /* extra bits for each distance code */ + = {0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13}; + +local int near extra_blbits[BL_CODES]/* extra bits for each bit length code */ + = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,3,7}; + +#define STORED_BLOCK 0 +#define STATIC_TREES 1 +#define DYN_TREES 2 +/* The three kinds of block type */ + +#ifndef LIT_BUFSIZE +# ifdef SMALL_MEM +# define LIT_BUFSIZE 0x2000 +# else +# ifdef MEDIUM_MEM +# define LIT_BUFSIZE 0x4000 +# else +# define LIT_BUFSIZE 0x8000 +# endif +# endif +#endif +#ifndef DIST_BUFSIZE +# define DIST_BUFSIZE LIT_BUFSIZE +#endif +/* Sizes of match buffers for literals/lengths and distances. There are + * 4 reasons for limiting LIT_BUFSIZE to 64K: + * - frequencies can be kept in 16 bit counters + * - if compression is not successful for the first block, all input data is + * still in the window so we can still emit a stored block even when input + * comes from standard input. (This can also be done for all blocks if + * LIT_BUFSIZE is not greater than 32K.) + * - if compression is not successful for a file smaller than 64K, we can + * even emit a stored file instead of a stored block (saving 5 bytes). + * - creating new Huffman trees less frequently may not provide fast + * adaptation to changes in the input data statistics. (Take for + * example a binary file with poorly compressible code followed by + * a highly compressible string table.) Smaller buffer sizes give + * fast adaptation but have of course the overhead of transmitting trees + * more frequently. + * - I can't count above 4 + * The current code is general and allows DIST_BUFSIZE < LIT_BUFSIZE (to save + * memory at the expense of compression). Some optimizations would be possible + * if we rely on DIST_BUFSIZE == LIT_BUFSIZE. + */ +#if LIT_BUFSIZE > INBUFSIZ + error cannot overlay l_buf and inbuf +#endif + +#define REP_3_6 16 +/* repeat previous bit length 3-6 times (2 bits of repeat count) */ + +#define REPZ_3_10 17 +/* repeat a zero length 3-10 times (3 bits of repeat count) */ + +#define REPZ_11_138 18 +/* repeat a zero length 11-138 times (7 bits of repeat count) */ + +/* =========================================================================== + * Local data + */ + +/* Data structure describing a single value and its code string. */ +typedef struct ct_data { + union { + ush freq; /* frequency count */ + ush code; /* bit string */ + } fc; + union { + ush dad; /* father node in Huffman tree */ + ush len; /* length of bit string */ + } dl; +} ct_data; + +#define Freq fc.freq +#define Code fc.code +#define Dad dl.dad +#define Len dl.len + +#define HEAP_SIZE (2*L_CODES+1) +/* maximum heap size */ + +local ct_data near dyn_ltree[HEAP_SIZE]; /* literal and length tree */ +local ct_data near dyn_dtree[2*D_CODES+1]; /* distance tree */ + +local ct_data near static_ltree[L_CODES+2]; +/* The static literal tree. Since the bit lengths are imposed, there is no + * need for the L_CODES extra codes used during heap construction. However + * The codes 286 and 287 are needed to build a canonical tree (see ct_init + * below). + */ + +local ct_data near static_dtree[D_CODES]; +/* The static distance tree. (Actually a trivial tree since all codes use + * 5 bits.) + */ + +local ct_data near bl_tree[2*BL_CODES+1]; +/* Huffman tree for the bit lengths */ + +typedef struct tree_desc { + ct_data near *dyn_tree; /* the dynamic tree */ + ct_data near *static_tree; /* corresponding static tree or NULL */ + int near *extra_bits; /* extra bits for each code or NULL */ + int extra_base; /* base index for extra_bits */ + int elems; /* max number of elements in the tree */ + int max_length; /* max bit length for the codes */ + int max_code; /* largest code with non zero frequency */ +} tree_desc; + +local tree_desc near l_desc = +{dyn_ltree, static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS, 0}; + +local tree_desc near d_desc = +{dyn_dtree, static_dtree, extra_dbits, 0, D_CODES, MAX_BITS, 0}; + +local tree_desc near bl_desc = +{bl_tree, (ct_data near *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS, 0}; + + +local ush near bl_count[MAX_BITS+1]; +/* number of codes at each bit length for an optimal tree */ + +local uch near bl_order[BL_CODES] + = {16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15}; +/* The lengths of the bit length codes are sent in order of decreasing + * probability, to avoid transmitting the lengths for unused bit length codes. + */ + +local int near heap[2*L_CODES+1]; /* heap used to build the Huffman trees */ +local int heap_len; /* number of elements in the heap */ +local int heap_max; /* element of largest frequency */ +/* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used. + * The same heap array is used to build all trees. + */ + +local uch near depth[2*L_CODES+1]; +/* Depth of each subtree used as tie breaker for trees of equal frequency */ + +local uch length_code[MAX_MATCH-MIN_MATCH+1]; +/* length code for each normalized match length (0 == MIN_MATCH) */ + +local uch dist_code[512]; +/* distance codes. The first 256 values correspond to the distances + * 3 .. 258, the last 256 values correspond to the top 8 bits of + * the 15 bit distances. + */ + +local int near base_length[LENGTH_CODES]; +/* First normalized length for each code (0 = MIN_MATCH) */ + +local int near base_dist[D_CODES]; +/* First normalized distance for each code (0 = distance of 1) */ + +#define l_buf inbuf +/* DECLARE(uch, l_buf, LIT_BUFSIZE); buffer for literals or lengths */ + +/* DECLARE(ush, d_buf, DIST_BUFSIZE); buffer for distances */ + +local uch near flag_buf[(LIT_BUFSIZE/8)]; +/* flag_buf is a bit array distinguishing literals from lengths in + * l_buf, thus indicating the presence or absence of a distance. + */ + +local unsigned last_lit; /* running index in l_buf */ +local unsigned last_dist; /* running index in d_buf */ +local unsigned last_flags; /* running index in flag_buf */ +local uch flags; /* current flags not yet saved in flag_buf */ +local uch flag_bit; /* current bit used in flags */ +/* bits are filled in flags starting at bit 0 (least significant). + * Note: these flags are overkill in the current code since we don't + * take advantage of DIST_BUFSIZE == LIT_BUFSIZE. + */ + +local ulg opt_len; /* bit length of current block with optimal trees */ +local ulg static_len; /* bit length of current block with static trees */ + +local ulg compressed_len; /* total bit length of compressed file */ + +local ulg input_len; /* total byte length of input file */ +/* input_len is for debugging only since we can get it by other means. */ + +ush *file_type; /* pointer to UNKNOWN, BINARY or ASCII */ +int *file_method; /* pointer to DEFLATE or STORE */ + +#ifdef DEBUG +extern ulg bits_sent; /* bit length of the compressed data */ +extern long isize; /* byte length of input file */ +#endif + +extern long block_start; /* window offset of current block */ +extern unsigned near strstart; /* window offset of current string */ + +/* =========================================================================== + * Local (static) routines in this file. + */ + +local void init_block OF((void)); +local void pqdownheap OF((ct_data near *tree, int k)); +local void gen_bitlen OF((tree_desc near *desc)); +local void gen_codes OF((ct_data near *tree, int max_code)); +local void build_tree OF((tree_desc near *desc)); +local void scan_tree OF((ct_data near *tree, int max_code)); +local void send_tree OF((ct_data near *tree, int max_code)); +local int build_bl_tree OF((void)); +local void send_all_trees OF((int lcodes, int dcodes, int blcodes)); +local void compress_block OF((ct_data near *ltree, ct_data near *dtree)); +local void set_file_type OF((void)); + + +#ifndef DEBUG +# define send_code(c, tree) send_bits(tree[c].Code, tree[c].Len) + /* Send a code of the given tree. c and tree must not have side effects */ + +#else /* DEBUG */ +# define send_code(c, tree) \ + { if (verbose>1) fprintf(stderr,"\ncd %3d ",(c)); \ + send_bits(tree[c].Code, tree[c].Len); } +#endif + +#define d_code(dist) \ + ((dist) < 256 ? dist_code[dist] : dist_code[256+((dist)>>7)]) +/* Mapping from a distance to a distance code. dist is the distance - 1 and + * must not have side effects. dist_code[256] and dist_code[257] are never + * used. + */ + +#define MAX(a,b) (a >= b ? a : b) +/* the arguments must not have side effects */ + +/* =========================================================================== + * Allocate the match buffer, initialize the various tables and save the + * location of the internal file attribute (ascii/binary) and method + * (DEFLATE/STORE). + */ +void ct_init(attr, methodp) + ush *attr; /* pointer to internal file attribute */ + int *methodp; /* pointer to compression method */ +{ + int n; /* iterates over tree elements */ + int bits; /* bit counter */ + int length; /* length value */ + int code; /* code value */ + int dist; /* distance index */ + + file_type = attr; + file_method = methodp; + compressed_len = input_len = 0L; + + if (static_dtree[0].Len != 0) return; /* ct_init already called */ + + /* Initialize the mapping length (0..255) -> length code (0..28) */ + length = 0; + for (code = 0; code < LENGTH_CODES-1; code++) { + base_length[code] = length; + for (n = 0; n < (1<<extra_lbits[code]); n++) { + length_code[length++] = (uch)code; + } + } + Assert (length == 256, "ct_init: length != 256"); + /* Note that the length 255 (match length 258) can be represented + * in two different ways: code 284 + 5 bits or code 285, so we + * overwrite length_code[255] to use the best encoding: + */ + length_code[length-1] = (uch)code; + + /* Initialize the mapping dist (0..32K) -> dist code (0..29) */ + dist = 0; + for (code = 0 ; code < 16; code++) { + base_dist[code] = dist; + for (n = 0; n < (1<<extra_dbits[code]); n++) { + dist_code[dist++] = (uch)code; + } + } + Assert (dist == 256, "ct_init: dist != 256"); + dist >>= 7; /* from now on, all distances are divided by 128 */ + for ( ; code < D_CODES; code++) { + base_dist[code] = dist << 7; + for (n = 0; n < (1<<(extra_dbits[code]-7)); n++) { + dist_code[256 + dist++] = (uch)code; + } + } + Assert (dist == 256, "ct_init: 256+dist != 512"); + + /* Construct the codes of the static literal tree */ + for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; + n = 0; + while (n <= 143) static_ltree[n++].Len = 8, bl_count[8]++; + while (n <= 255) static_ltree[n++].Len = 9, bl_count[9]++; + while (n <= 279) static_ltree[n++].Len = 7, bl_count[7]++; + while (n <= 287) static_ltree[n++].Len = 8, bl_count[8]++; + /* Codes 286 and 287 do not exist, but we must include them in the + * tree construction to get a canonical Huffman tree (longest code + * all ones) + */ + gen_codes((ct_data near *)static_ltree, L_CODES+1); + + /* The static distance tree is trivial: */ + for (n = 0; n < D_CODES; n++) { + static_dtree[n].Len = 5; + static_dtree[n].Code = bi_reverse(n, 5); + } + + /* Initialize the first block of the first file: */ + init_block(); +} + +/* =========================================================================== + * Initialize a new block. + */ +local void init_block() +{ + int n; /* iterates over tree elements */ + + /* Initialize the trees. */ + for (n = 0; n < L_CODES; n++) dyn_ltree[n].Freq = 0; + for (n = 0; n < D_CODES; n++) dyn_dtree[n].Freq = 0; + for (n = 0; n < BL_CODES; n++) bl_tree[n].Freq = 0; + + dyn_ltree[END_BLOCK].Freq = 1; + opt_len = static_len = 0L; + last_lit = last_dist = last_flags = 0; + flags = 0; flag_bit = 1; +} + +#define SMALLEST 1 +/* Index within the heap array of least frequent node in the Huffman tree */ + + +/* =========================================================================== + * Remove the smallest element from the heap and recreate the heap with + * one less element. Updates heap and heap_len. + */ +#define pqremove(tree, top) \ +{\ + top = heap[SMALLEST]; \ + heap[SMALLEST] = heap[heap_len--]; \ + pqdownheap(tree, SMALLEST); \ +} + +/* =========================================================================== + * Compares to subtrees, using the tree depth as tie breaker when + * the subtrees have equal frequency. This minimizes the worst case length. + */ +#define smaller(tree, n, m) \ + (tree[n].Freq < tree[m].Freq || \ + (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m])) + +/* =========================================================================== + * Restore the heap property by moving down the tree starting at node k, + * exchanging a node with the smallest of its two sons if necessary, stopping + * when the heap property is re-established (each father smaller than its + * two sons). + */ +local void pqdownheap(tree, k) + ct_data near *tree; /* the tree to restore */ + int k; /* node to move down */ +{ + int v = heap[k]; + int j = k << 1; /* left son of k */ + while (j <= heap_len) { + /* Set j to the smallest of the two sons: */ + if (j < heap_len && smaller(tree, heap[j+1], heap[j])) j++; + + /* Exit if v is smaller than both sons */ + if (smaller(tree, v, heap[j])) break; + + /* Exchange v with the smallest son */ + heap[k] = heap[j]; k = j; + + /* And continue down the tree, setting j to the left son of k */ + j <<= 1; + } + heap[k] = v; +} + +/* =========================================================================== + * Compute the optimal bit lengths for a tree and update the total bit length + * for the current block. + * IN assertion: the fields freq and dad are set, heap[heap_max] and + * above are the tree nodes sorted by increasing frequency. + * OUT assertions: the field len is set to the optimal bit length, the + * array bl_count contains the frequencies for each bit length. + * The length opt_len is updated; static_len is also updated if stree is + * not null. + */ +local void gen_bitlen(desc) + tree_desc near *desc; /* the tree descriptor */ +{ + ct_data near *tree = desc->dyn_tree; + int near *extra = desc->extra_bits; + int base = desc->extra_base; + int max_code = desc->max_code; + int max_length = desc->max_length; + ct_data near *stree = desc->static_tree; + int h; /* heap index */ + int n, m; /* iterate over the tree elements */ + int bits; /* bit length */ + int xbits; /* extra bits */ + ush f; /* frequency */ + int overflow = 0; /* number of elements with bit length too large */ + + for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; + + /* In a first pass, compute the optimal bit lengths (which may + * overflow in the case of the bit length tree). + */ + tree[heap[heap_max]].Len = 0; /* root of the heap */ + + for (h = heap_max+1; h < HEAP_SIZE; h++) { + n = heap[h]; + bits = tree[tree[n].Dad].Len + 1; + if (bits > max_length) bits = max_length, overflow++; + tree[n].Len = (ush)bits; + /* We overwrite tree[n].Dad which is no longer needed */ + + if (n > max_code) continue; /* not a leaf node */ + + bl_count[bits]++; + xbits = 0; + if (n >= base) xbits = extra[n-base]; + f = tree[n].Freq; + opt_len += (ulg)f * (bits + xbits); + if (stree) static_len += (ulg)f * (stree[n].Len + xbits); + } + if (overflow == 0) return; + + Trace((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: */ + do { + bits = max_length-1; + while (bl_count[bits] == 0) bits--; + bl_count[bits]--; /* move one leaf down the tree */ + bl_count[bits+1] += 2; /* move one overflow item as its brother */ + bl_count[max_length]--; + /* The brother of the overflow item also moves one step up, + * but this does not affect bl_count[max_length] + */ + overflow -= 2; + } while (overflow > 0); + + /* Now recompute all bit lengths, scanning in increasing frequency. + * h is still equal to HEAP_SIZE. (It is simpler to reconstruct all + * lengths instead of fixing only the wrong ones. This idea is taken + * from 'ar' written by Haruhiko Okumura.) + */ + for (bits = max_length; bits != 0; bits--) { + n = bl_count[bits]; + while (n != 0) { + m = heap[--h]; + if (m > max_code) continue; + if (tree[m].Len != (unsigned) bits) { + Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); + opt_len += ((long)bits-(long)tree[m].Len)*(long)tree[m].Freq; + tree[m].Len = (ush)bits; + } + n--; + } + } +} + +/* =========================================================================== + * Generate the codes for a given tree and bit counts (which need not be + * optimal). + * IN assertion: the array bl_count contains the bit length statistics for + * the given tree and the field len is set for all tree elements. + * OUT assertion: the field code is set for all tree elements of non + * zero code length. + */ +local void gen_codes (tree, max_code) + ct_data near *tree; /* the tree to decorate */ + int max_code; /* largest code with non zero frequency */ +{ + ush next_code[MAX_BITS+1]; /* next code value for each bit length */ + ush code = 0; /* running code value */ + int bits; /* bit index */ + int n; /* code index */ + + /* The distribution counts are first used to generate the code values + * without bit reversal. + */ + for (bits = 1; bits <= MAX_BITS; bits++) { + next_code[bits] = code = (code + bl_count[bits-1]) << 1; + } + /* Check that the bit counts in bl_count are consistent. The last code + * must be all ones. + */ + Assert (code + bl_count[MAX_BITS]-1 == (1<<MAX_BITS)-1, + "inconsistent bit counts"); + Tracev((stderr,"\ngen_codes: max_code %d ", max_code)); + + for (n = 0; n <= max_code; n++) { + int len = tree[n].Len; + if (len == 0) continue; + /* Now reverse the bits */ + tree[n].Code = bi_reverse(next_code[len]++, len); + + Tracec(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ", + n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1)); + } +} + +/* =========================================================================== + * Construct one Huffman tree and assigns the code bit strings and lengths. + * Update the total bit length for the current block. + * IN assertion: the field freq is set for all tree elements. + * OUT assertions: the fields len and code are set to the optimal bit length + * and corresponding code. The length opt_len is updated; static_len is + * also updated if stree is not null. The field max_code is set. + */ +local void build_tree(desc) + tree_desc near *desc; /* the tree descriptor */ +{ + ct_data near *tree = desc->dyn_tree; + ct_data near *stree = desc->static_tree; + int elems = desc->elems; + int n, m; /* iterate over heap elements */ + int max_code = -1; /* largest code with non zero frequency */ + int node = elems; /* next internal node of the tree */ + + /* Construct the initial heap, with least frequent element in + * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1]. + * heap[0] is not used. + */ + heap_len = 0, heap_max = HEAP_SIZE; + + for (n = 0; n < elems; n++) { + if (tree[n].Freq != 0) { + heap[++heap_len] = max_code = n; + depth[n] = 0; + } else { + tree[n].Len = 0; + } + } + + /* The pkzip format requires that at least one distance code exists, + * and that at least one bit should be sent even if there is only one + * possible code. So to avoid special checks later on we force at least + * two codes of non zero frequency. + */ + while (heap_len < 2) { + int new = heap[++heap_len] = (max_code < 2 ? ++max_code : 0); + tree[new].Freq = 1; + depth[new] = 0; + opt_len--; if (stree) static_len -= stree[new].Len; + /* new is 0 or 1 so it does not have extra bits */ + } + desc->max_code = max_code; + + /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree, + * establish sub-heaps of increasing lengths: + */ + for (n = heap_len/2; n >= 1; n--) pqdownheap(tree, n); + + /* Construct the Huffman tree by repeatedly combining the least two + * frequent nodes. + */ + do { + pqremove(tree, n); /* n = node of least frequency */ + m = heap[SMALLEST]; /* m = node of next least frequency */ + + heap[--heap_max] = n; /* keep the nodes sorted by frequency */ + heap[--heap_max] = m; + + /* Create a new node father of n and m */ + tree[node].Freq = tree[n].Freq + tree[m].Freq; + depth[node] = (uch) (MAX(depth[n], depth[m]) + 1); + tree[n].Dad = tree[m].Dad = (ush)node; +#ifdef DUMP_BL_TREE + if (tree == bl_tree) { + fprintf(stderr,"\nnode %d(%d), sons %d(%d) %d(%d)", + node, tree[node].Freq, n, tree[n].Freq, m, tree[m].Freq); + } +#endif + /* and insert the new node in the heap */ + heap[SMALLEST] = node++; + pqdownheap(tree, SMALLEST); + + } while (heap_len >= 2); + + heap[--heap_max] = heap[SMALLEST]; + + /* At this point, the fields freq and dad are set. We can now + * generate the bit lengths. + */ + gen_bitlen((tree_desc near *)desc); + + /* The field len is now set, we can generate the bit codes */ + gen_codes ((ct_data near *)tree, max_code); +} + +/* =========================================================================== + * Scan a literal or distance tree to determine the frequencies of the codes + * in the bit length tree. Updates opt_len to take into account the repeat + * counts. (The contribution of the bit length codes will be added later + * during the construction of bl_tree.) + */ +local void scan_tree (tree, max_code) + ct_data near *tree; /* the tree to be scanned */ + int max_code; /* and its largest code of non zero frequency */ +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + if (nextlen == 0) max_count = 138, min_count = 3; + tree[max_code+1].Len = (ush)0xffff; /* guard */ + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + bl_tree[curlen].Freq += count; + } else if (curlen != 0) { + if (curlen != prevlen) bl_tree[curlen].Freq++; + bl_tree[REP_3_6].Freq++; + } else if (count <= 10) { + bl_tree[REPZ_3_10].Freq++; + } else { + bl_tree[REPZ_11_138].Freq++; + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Send a literal or distance tree in compressed form, using the codes in + * bl_tree. + */ +local void send_tree (tree, max_code) + ct_data near *tree; /* the tree to be scanned */ + int max_code; /* and its largest code of non zero frequency */ +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + /* tree[max_code+1].Len = -1; */ /* guard already set */ + if (nextlen == 0) max_count = 138, min_count = 3; + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + do { send_code(curlen, bl_tree); } while (--count != 0); + + } else if (curlen != 0) { + if (curlen != prevlen) { + send_code(curlen, bl_tree); count--; + } + Assert(count >= 3 && count <= 6, " 3_6?"); + send_code(REP_3_6, bl_tree); send_bits(count-3, 2); + + } else if (count <= 10) { + send_code(REPZ_3_10, bl_tree); send_bits(count-3, 3); + + } else { + send_code(REPZ_11_138, bl_tree); send_bits(count-11, 7); + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Construct the Huffman tree for the bit lengths and return the index in + * bl_order of the last bit length code to send. + */ +local int build_bl_tree() +{ + int max_blindex; /* index of last bit length code of non zero freq */ + + /* Determine the bit length frequencies for literal and distance trees */ + scan_tree((ct_data near *)dyn_ltree, l_desc.max_code); + scan_tree((ct_data near *)dyn_dtree, d_desc.max_code); + + /* Build the bit length tree: */ + build_tree((tree_desc near *)(&bl_desc)); + /* opt_len now includes the length of the tree representations, except + * the lengths of the bit lengths codes and the 5+5+4 bits for the counts. + */ + + /* Determine the number of bit length codes to send. The pkzip format + * requires that at least 4 bit length codes be sent. (appnote.txt says + * 3 but the actual value used is 4.) + */ + for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) { + if (bl_tree[bl_order[max_blindex]].Len != 0) break; + } + /* Update opt_len to include the bit length tree and counts */ + opt_len += 3*(max_blindex+1) + 5+5+4; + Tracev((stderr, "\ndyn trees: dyn %ld, stat %ld", opt_len, static_len)); + + return max_blindex; +} + +/* =========================================================================== + * Send the header for a block using dynamic Huffman trees: the counts, the + * lengths of the bit length codes, the literal tree and the distance tree. + * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4. + */ +local void send_all_trees(lcodes, dcodes, blcodes) + int lcodes, dcodes, blcodes; /* number of codes for each tree */ +{ + int rank; /* index in bl_order */ + + Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes"); + Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES, + "too many codes"); + Tracev((stderr, "\nbl counts: ")); + send_bits(lcodes-257, 5); /* not +255 as stated in appnote.txt */ + send_bits(dcodes-1, 5); + send_bits(blcodes-4, 4); /* not -3 as stated in appnote.txt */ + for (rank = 0; rank < blcodes; rank++) { + Tracev((stderr, "\nbl code %2d ", bl_order[rank])); + send_bits(bl_tree[bl_order[rank]].Len, 3); + } + Tracev((stderr, "\nbl tree: sent %ld", bits_sent)); + + send_tree((ct_data near *)dyn_ltree, lcodes-1); /* send the literal tree */ + Tracev((stderr, "\nlit tree: sent %ld", bits_sent)); + + send_tree((ct_data near *)dyn_dtree, dcodes-1); /* send the distance tree */ + Tracev((stderr, "\ndist tree: sent %ld", bits_sent)); +} + +/* =========================================================================== + * Determine the best encoding for the current block: dynamic trees, static + * trees or store, and output the encoded block to the zip file. This function + * returns the total compressed length for the file so far. + */ +ulg flush_block(buf, stored_len, eof) + char *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 */ +{ + ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */ + int max_blindex; /* index of last bit length code of non zero freq */ + + flag_buf[last_flags] = flags; /* Save the flags for the last 8 items */ + + /* Check if the file is ascii or binary */ + if (*file_type == (ush)UNKNOWN) set_file_type(); + + /* Construct the literal and distance trees */ + build_tree((tree_desc near *)(&l_desc)); + Tracev((stderr, "\nlit data: dyn %ld, stat %ld", opt_len, static_len)); + + build_tree((tree_desc near *)(&d_desc)); + Tracev((stderr, "\ndist data: dyn %ld, stat %ld", opt_len, static_len)); + /* At this point, opt_len and static_len are the total bit lengths of + * the compressed block data, excluding the tree representations. + */ + + /* Build the bit length tree for the above two trees, and get the index + * in bl_order of the last bit length code to send. + */ + max_blindex = build_bl_tree(); + + /* Determine the best encoding. Compute first the block length in bytes */ + opt_lenb = (opt_len+3+7)>>3; + static_lenb = (static_len+3+7)>>3; + input_len += stored_len; /* for debugging only */ + + Trace((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u dist %u ", + opt_lenb, opt_len, static_lenb, static_len, stored_len, + last_lit, last_dist)); + + if (static_lenb <= opt_lenb) opt_lenb = static_lenb; + + /* If compression failed and this is the first and last block, + * and if the zip file can be seeked (to rewrite the local header), + * the whole file is transformed into a stored file: + */ +#ifdef FORCE_METHOD + if (level == 1 && eof && compressed_len == 0L) { /* force stored file */ +#else + if (stored_len <= opt_lenb && eof && compressed_len == 0L && seekable()) { +#endif + /* Since LIT_BUFSIZE <= 2*WSIZE, the input data must be there: */ + if (buf == (char*)0) error ("block vanished"); + + copy_block(buf, (unsigned)stored_len, 0); /* without header */ + compressed_len = stored_len << 3; + *file_method = STORED; + +#ifdef FORCE_METHOD + } else if (level == 2 && buf != (char*)0) { /* force stored block */ +#else + } else if (stored_len+4 <= opt_lenb && buf != (char*)0) { + /* 4: two words for the lengths */ +#endif + /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE. + * Otherwise we can't have processed more than WSIZE input bytes since + * the last block flush, because compression would have been + * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to + * transform a block into a stored block. + */ + send_bits((STORED_BLOCK<<1)+eof, 3); /* send block type */ + compressed_len = (compressed_len + 3 + 7) & ~7L; + compressed_len += (stored_len + 4) << 3; + + copy_block(buf, (unsigned)stored_len, 1); /* with header */ + +#ifdef FORCE_METHOD + } else if (level == 3) { /* force static trees */ +#else + } else if (static_lenb == opt_lenb) { +#endif + send_bits((STATIC_TREES<<1)+eof, 3); + compress_block((ct_data near *)static_ltree, (ct_data near *)static_dtree); + compressed_len += 3 + static_len; + } else { + send_bits((DYN_TREES<<1)+eof, 3); + send_all_trees(l_desc.max_code+1, d_desc.max_code+1, max_blindex+1); + compress_block((ct_data near *)dyn_ltree, (ct_data near *)dyn_dtree); + compressed_len += 3 + opt_len; + } + Assert (compressed_len == bits_sent, "bad compressed size"); + init_block(); + + if (eof) { + Assert (input_len == isize, "bad input size"); + bi_windup(); + compressed_len += 7; /* align on byte boundary */ + } + Tracev((stderr,"\ncomprlen %lu(%lu) ", compressed_len>>3, + compressed_len-7*eof)); + + return compressed_len >> 3; +} + +/* =========================================================================== + * Save the match info and tally the frequency counts. Return true if + * the current block must be flushed. + */ +int ct_tally (dist, lc) + int dist; /* distance of matched string */ + int lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */ +{ + l_buf[last_lit++] = (uch)lc; + if (dist == 0) { + /* lc is the unmatched char */ + dyn_ltree[lc].Freq++; + } else { + /* Here, lc is the match length - MIN_MATCH */ + dist--; /* dist = match distance - 1 */ + Assert((ush)dist < (ush)MAX_DIST && + (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) && + (ush)d_code(dist) < (ush)D_CODES, "ct_tally: bad match"); + + dyn_ltree[length_code[lc]+LITERALS+1].Freq++; + dyn_dtree[d_code(dist)].Freq++; + + d_buf[last_dist++] = (ush)dist; + flags |= flag_bit; + } + flag_bit <<= 1; + + /* Output the flags if they fill a byte: */ + if ((last_lit & 7) == 0) { + flag_buf[last_flags++] = flags; + flags = 0, flag_bit = 1; + } + /* Try to guess if it is profitable to stop the current block here */ + if (level > 2 && (last_lit & 0xfff) == 0) { + /* Compute an upper bound for the compressed length */ + ulg out_length = (ulg)last_lit*8L; + ulg in_length = (ulg)strstart-block_start; + int dcode; + for (dcode = 0; dcode < D_CODES; dcode++) { + out_length += (ulg)dyn_dtree[dcode].Freq*(5L+extra_dbits[dcode]); + } + out_length >>= 3; + Trace((stderr,"\nlast_lit %u, last_dist %u, in %ld, out ~%ld(%ld%%) ", + last_lit, last_dist, in_length, out_length, + 100L - out_length*100L/in_length)); + if (last_dist < last_lit/2 && out_length < in_length/2) return 1; + } + return (last_lit == LIT_BUFSIZE-1 || last_dist == DIST_BUFSIZE); + /* We avoid equality with LIT_BUFSIZE because of wraparound at 64K + * on 16 bit machines and because stored blocks are restricted to + * 64K-1 bytes. + */ +} + +/* =========================================================================== + * Send the block data compressed using the given Huffman trees + */ +local void compress_block(ltree, dtree) + ct_data near *ltree; /* literal tree */ + ct_data near *dtree; /* distance tree */ +{ + unsigned dist; /* distance of matched string */ + int lc; /* match length or unmatched char (if dist == 0) */ + unsigned lx = 0; /* running index in l_buf */ + unsigned dx = 0; /* running index in d_buf */ + unsigned fx = 0; /* running index in flag_buf */ + uch flag = 0; /* current flags */ + unsigned code; /* the code to send */ + int extra; /* number of extra bits to send */ + + if (last_lit != 0) do { + if ((lx & 7) == 0) flag = flag_buf[fx++]; + lc = l_buf[lx++]; + if ((flag & 1) == 0) { + send_code(lc, ltree); /* send a literal byte */ + Tracecv(isgraph(lc), (stderr," '%c' ", lc)); + } else { + /* Here, lc is the match length - MIN_MATCH */ + code = length_code[lc]; + send_code(code+LITERALS+1, ltree); /* send the length code */ + extra = extra_lbits[code]; + if (extra != 0) { + lc -= base_length[code]; + send_bits(lc, extra); /* send the extra length bits */ + } + dist = d_buf[dx++]; + /* Here, dist is the match distance - 1 */ + code = d_code(dist); + Assert (code < D_CODES, "bad d_code"); + + send_code(code, dtree); /* send the distance code */ + extra = extra_dbits[code]; + if (extra != 0) { + dist -= base_dist[code]; + send_bits(dist, extra); /* send the extra distance bits */ + } + } /* literal or match pair ? */ + flag >>= 1; + } while (lx < last_lit); + + send_code(END_BLOCK, ltree); +} + +/* =========================================================================== + * Set the file type to ASCII or BINARY, using a crude approximation: + * binary if more than 20% of the bytes are <= 6 or >= 128, ascii otherwise. + * IN assertion: the fields freq of dyn_ltree are set and the total of all + * frequencies does not exceed 64K (to fit in an int on 16 bit machines). + */ +local void set_file_type() +{ + int n = 0; + unsigned ascii_freq = 0; + unsigned bin_freq = 0; + while (n < 7) bin_freq += dyn_ltree[n++].Freq; + while (n < 128) ascii_freq += dyn_ltree[n++].Freq; + while (n < LITERALS) bin_freq += dyn_ltree[n++].Freq; + *file_type = bin_freq > (ascii_freq >> 2) ? BINARY : ASCII; + if (*file_type == BINARY && translate_eol) { + warn("-l used on binary file", ""); + } +} diff --git a/gnu/usr.bin/gzip/unlzw.c b/gnu/usr.bin/gzip/unlzw.c new file mode 100644 index 0000000..0687c1b --- /dev/null +++ b/gnu/usr.bin/gzip/unlzw.c @@ -0,0 +1,369 @@ +/* unlzw.c -- decompress files in LZW format. + * The code in this file is directly derived from the public domain 'compress' + * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies, + * Ken Turkowski, Dave Mack and Peter Jannesen. + * + * This is a temporary version which will be rewritten in some future version + * to accommodate in-memory decompression. + */ + +#ifndef lint +static char rcsid[] = "$Id: unlzw.c,v 0.13 1993/05/27 10:32:55 jloup Exp $"; +#endif + +#include <stdio.h> +#include <sys/types.h> + +#include "tailor.h" + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif +#ifndef NO_FCNTL_H +# include <fcntl.h> +#endif + +#include "gzip.h" +#include "lzw.h" + +typedef unsigned char char_type; +typedef long code_int; +typedef unsigned long count_int; +typedef unsigned short count_short; +typedef unsigned long cmp_code_int; + +#define MAXCODE(n) (1L << (n)) + +#ifndef REGISTERS +# define REGISTERS 2 +#endif +#define REG1 +#define REG2 +#define REG3 +#define REG4 +#define REG5 +#define REG6 +#define REG7 +#define REG8 +#define REG9 +#define REG10 +#define REG11 +#define REG12 +#define REG13 +#define REG14 +#define REG15 +#define REG16 +#if REGISTERS >= 1 +# undef REG1 +# define REG1 register +#endif +#if REGISTERS >= 2 +# undef REG2 +# define REG2 register +#endif +#if REGISTERS >= 3 +# undef REG3 +# define REG3 register +#endif +#if REGISTERS >= 4 +# undef REG4 +# define REG4 register +#endif +#if REGISTERS >= 5 +# undef REG5 +# define REG5 register +#endif +#if REGISTERS >= 6 +# undef REG6 +# define REG6 register +#endif +#if REGISTERS >= 7 +# undef REG7 +# define REG7 register +#endif +#if REGISTERS >= 8 +# undef REG8 +# define REG8 register +#endif +#if REGISTERS >= 9 +# undef REG9 +# define REG9 register +#endif +#if REGISTERS >= 10 +# undef REG10 +# define REG10 register +#endif +#if REGISTERS >= 11 +# undef REG11 +# define REG11 register +#endif +#if REGISTERS >= 12 +# undef REG12 +# define REG12 register +#endif +#if REGISTERS >= 13 +# undef REG13 +# define REG13 register +#endif +#if REGISTERS >= 14 +# undef REG14 +# define REG14 register +#endif +#if REGISTERS >= 15 +# undef REG15 +# define REG15 register +#endif +#if REGISTERS >= 16 +# undef REG16 +# define REG16 register +#endif + +#ifndef BYTEORDER +# define BYTEORDER 0000 +#endif + +#ifndef NOALLIGN +# define NOALLIGN 0 +#endif + + +union bytes { + long word; + struct { +#if BYTEORDER == 4321 + char_type b1; + char_type b2; + char_type b3; + char_type b4; +#else +#if BYTEORDER == 1234 + char_type b4; + char_type b3; + char_type b2; + char_type b1; +#else +# undef BYTEORDER + int dummy; +#endif +#endif + } bytes; +}; + +#if BYTEORDER == 4321 && NOALLIGN == 1 +# define input(b,o,c,n,m){ \ + (c) = (*(long *)(&(b)[(o)>>3])>>((o)&0x7))&(m); \ + (o) += (n); \ + } +#else +# define input(b,o,c,n,m){ \ + REG1 char_type *p = &(b)[(o)>>3]; \ + (c) = ((((long)(p[0]))|((long)(p[1])<<8)| \ + ((long)(p[2])<<16))>>((o)&0x7))&(m); \ + (o) += (n); \ + } +#endif + +#ifndef MAXSEG_64K + /* DECLARE(ush, tab_prefix, (1<<BITS)); -- prefix code */ +# define tab_prefixof(i) tab_prefix[i] +# define clear_tab_prefixof() memzero(tab_prefix, 256); +#else + /* DECLARE(ush, tab_prefix0, (1<<(BITS-1)); -- prefix for even codes */ + /* DECLARE(ush, tab_prefix1, (1<<(BITS-1)); -- prefix for odd codes */ + ush *tab_prefix[2]; +# define tab_prefixof(i) tab_prefix[(i)&1][(i)>>1] +# define clear_tab_prefixof() \ + memzero(tab_prefix0, 128), \ + memzero(tab_prefix1, 128); +#endif +#define de_stack ((char_type *)(&d_buf[DIST_BUFSIZE-1])) +#define tab_suffixof(i) tab_suffix[i] + +int block_mode = BLOCK_MODE; /* block compress mode -C compatible with 2.0 */ + +/* ============================================================================ + * Decompress in to out. This routine adapts to the codes in the + * file building the "string" table on-the-fly; requiring no table to + * be stored in the compressed file. + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets iptr to insize-1 included. + * The magic header has already been checked and skipped. + * bytes_in and bytes_out have been initialized. + */ +int unlzw(in, out) + int in, out; /* input and output file descriptors */ +{ + REG2 char_type *stackp; + REG3 code_int code; + REG4 int finchar; + REG5 code_int oldcode; + REG6 code_int incode; + REG7 long inbits; + REG8 long posbits; + REG9 int outpos; +/* REG10 int insize; (global) */ + REG11 unsigned bitmask; + REG12 code_int free_ent; + REG13 code_int maxcode; + REG14 code_int maxmaxcode; + REG15 int n_bits; + REG16 int rsize; + +#ifdef MAXSEG_64K + tab_prefix[0] = tab_prefix0; + tab_prefix[1] = tab_prefix1; +#endif + maxbits = get_byte(); + block_mode = maxbits & BLOCK_MODE; + if ((maxbits & LZW_RESERVED) != 0) { + WARN((stderr, "\n%s: %s: warning, unknown flags 0x%x\n", + progname, ifname, maxbits & LZW_RESERVED)); + } + maxbits &= BIT_MASK; + maxmaxcode = MAXCODE(maxbits); + + if (maxbits > BITS) { + fprintf(stderr, + "\n%s: %s: compressed with %d bits, can only handle %d bits\n", + progname, ifname, maxbits, BITS); + exit_code = ERROR; + return ERROR; + } + rsize = insize; + maxcode = MAXCODE(n_bits = INIT_BITS)-1; + bitmask = (1<<n_bits)-1; + oldcode = -1; + finchar = 0; + outpos = 0; + posbits = inptr<<3; + + free_ent = ((block_mode) ? FIRST : 256); + + clear_tab_prefixof(); /* Initialize the first 256 entries in the table. */ + + for (code = 255 ; code >= 0 ; --code) { + tab_suffixof(code) = (char_type)code; + } + do { + REG1 int i; + int e; + int o; + + resetbuf: + e = insize-(o = (posbits>>3)); + + for (i = 0 ; i < e ; ++i) { + inbuf[i] = inbuf[i+o]; + } + insize = e; + posbits = 0; + + if (insize < INBUF_EXTRA) { + if ((rsize = read(in, (char*)inbuf+insize, INBUFSIZ)) == EOF) { + read_error(); + } + insize += rsize; + } + inbits = ((rsize != 0) ? ((long)insize - insize%n_bits)<<3 : + ((long)insize<<3)-(n_bits-1)); + + while (inbits > posbits) { + if (free_ent > maxcode) { + posbits = ((posbits-1) + + ((n_bits<<3)-(posbits-1+(n_bits<<3))%(n_bits<<3))); + ++n_bits; + if (n_bits == maxbits) { + maxcode = maxmaxcode; + } else { + maxcode = MAXCODE(n_bits)-1; + } + bitmask = (1<<n_bits)-1; + goto resetbuf; + } + input(inbuf,posbits,code,n_bits,bitmask); + + if (oldcode == -1) { + outbuf[outpos++] = (char_type)(finchar = (int)(oldcode=code)); + continue; + } + if (code == CLEAR && block_mode) { + clear_tab_prefixof(); + free_ent = FIRST - 1; + posbits = ((posbits-1) + + ((n_bits<<3)-(posbits-1+(n_bits<<3))%(n_bits<<3))); + maxcode = MAXCODE(n_bits = INIT_BITS)-1; + bitmask = (1<<n_bits)-1; + goto resetbuf; + } + incode = code; + stackp = de_stack; + + if (code >= free_ent) { /* Special case for KwKwK string. */ + if (code > free_ent) { +#ifdef DEBUG + char_type *p; + + posbits -= n_bits; + p = &inbuf[posbits>>3]; + fprintf(stderr, + "code:%ld free_ent:%ld n_bits:%d insize:%u\n", + code, free_ent, n_bits, insize); + fprintf(stderr, + "posbits:%ld inbuf:%02X %02X %02X %02X %02X\n", + posbits, p[-1],p[0],p[1],p[2],p[3]); +#endif + if (!test && outpos > 0) { + write_buf(out, outbuf, outpos); + } + error("corrupt input. Use zcat to recover some data."); + } + *--stackp = (char_type)finchar; + code = oldcode; + } + + while ((cmp_code_int)code >= (cmp_code_int)256) { + /* Generate output characters in reverse order */ + *--stackp = tab_suffixof(code); + code = tab_prefixof(code); + } + *--stackp = (char_type)(finchar = tab_suffixof(code)); + + /* And put them out in forward order */ + { + REG1 int i; + + if (outpos+(i = (de_stack-stackp)) >= OUTBUFSIZ) { + do { + if (i > OUTBUFSIZ-outpos) i = OUTBUFSIZ-outpos; + + if (i > 0) { + memcpy(outbuf+outpos, stackp, i); + outpos += i; + } + if (outpos >= OUTBUFSIZ) { + if (!test) write_buf(out, outbuf, outpos); + outpos = 0; + } + stackp+= i; + } while ((i = (de_stack-stackp)) > 0); + } else { + memcpy(outbuf+outpos, stackp, i); + outpos += i; + } + } + + if ((code = free_ent) < maxmaxcode) { /* Generate the new entry. */ + + tab_prefixof(code) = (unsigned short)oldcode; + tab_suffixof(code) = (char_type)finchar; + free_ent = code+1; + } + oldcode = incode; /* Remember previous code. */ + } + bytes_in += rsize; + + } while (rsize != 0); + + if (!test && outpos > 0) write_buf(out, outbuf, outpos); + return OK; +} diff --git a/gnu/usr.bin/gzip/unpack.c b/gnu/usr.bin/gzip/unpack.c new file mode 100644 index 0000000..e6cf7ca --- /dev/null +++ b/gnu/usr.bin/gzip/unpack.c @@ -0,0 +1,241 @@ +/* unpack.c -- decompress files in pack format. + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifndef lint +static char rcsid[] = "$Id: unpack.c,v 1.3 1993/05/28 17:56:07 jloup Exp $"; +#endif + +#include <stdio.h> + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#define MIN(a,b) ((a) <= (b) ? (a) : (b)) +/* The arguments must not have side effects. */ + +#define MAX_BITLEN 25 +/* Maximum length of Huffman codes. (Minor modifications to the code + * would be needed to support 32 bits codes, but pack never generates + * more than 24 bits anyway.) + */ + +#define LITERALS 256 +/* Number of literals, excluding the End of Block (EOB) code */ + +#ifdef SMALL_MEM +# define MAX_PEEK 10 +#else +# define MAX_PEEK 12 +#endif +/* Maximum number of 'peek' bits used to optimize traversal of the + * Huffman tree. + */ + +local ulg orig_len; /* original uncompressed length */ +local int max_len; /* maximum bit length of Huffman codes */ + +local uch literal[LITERALS]; +/* The literal bytes present in the Huffman tree. The EOB code is not + * represented. + */ + +local int lit_base[MAX_BITLEN+1]; +/* All literals of a given bit length are contiguous in literal[] and + * have contiguous codes. literal[code+lit_base[len]] is the literal + * for a code of len bits. + */ + +local int leaves [MAX_BITLEN+1]; /* Number of leaves for each bit length */ +local int parents[MAX_BITLEN+1]; /* Number of parents for each bit length */ + +local int peek_bits; /* Number of peek bits currently used */ + +local uch prefix_len[1 << MAX_PEEK]; +/* For each bit pattern b of peek_bits bits, prefix_len[b] is the length + * of the Huffman code starting with a prefix of b (upper bits), or 0 + * if all codes of prefix b have more than peek_bits bits. It is not + * necessary to have a huge table (large MAX_PEEK) because most of the + * codes encountered in the input stream are short codes (by construction). + * So for most codes a single lookup will be necessary. + */ + +local ulg bitbuf; +/* Bits are added on the low part of bitbuf and read from the high part. */ + +local int valid; /* number of valid bits in bitbuf */ +/* all bits above the last valid bit are always zero */ + +/* Set code to the next 'bits' input bits without skipping them. code + * must be the name of a simple variable and bits must not have side effects. + * IN assertions: bits <= 25 (so that we still have room for an extra byte + * when valid is only 24), and mask = (1<<bits)-1. + */ +#define look_bits(code,bits,mask) \ +{ \ + while (valid < (bits)) bitbuf = (bitbuf<<8) | (ulg)get_byte(), valid += 8; \ + code = (bitbuf >> (valid-(bits))) & (mask); \ +} + +/* Skip the given number of bits (after having peeked at them): */ +#define skip_bits(bits) (valid -= (bits)) + +#define clear_bitbuf() (valid = 0, bitbuf = 0) + +/* Local functions */ + +local void read_tree OF((void)); +local void build_tree OF((void)); + +/* =========================================================================== + * Read the Huffman tree. + */ +local void read_tree() +{ + int len; /* bit length */ + int base; /* base offset for a sequence of leaves */ + int n; + + /* Read the original input size, MSB first */ + orig_len = 0; + for (n = 1; n <= 4; n++) orig_len = (orig_len << 8) | (ulg)get_byte(); + + max_len = (int)get_byte(); /* maximum bit length of Huffman codes */ + if (max_len > MAX_BITLEN) { + error("invalid compressed data -- Huffman code > 32 bits"); + } + + /* Get the number of leaves at each bit length */ + n = 0; + for (len = 1; len <= max_len; len++) { + leaves[len] = (int)get_byte(); + n += leaves[len]; + } + if (n > LITERALS) { + error("too many leaves in Huffman tree"); + } + Trace((stderr, "orig_len %ld, max_len %d, leaves %d\n", + orig_len, max_len, n)); + /* There are at least 2 and at most 256 leaves of length max_len. + * (Pack arbitrarily rejects empty files and files consisting of + * a single byte even repeated.) To fit the last leaf count in a + * byte, it is offset by 2. However, the last literal is the EOB + * code, and is not transmitted explicitly in the tree, so we must + * adjust here by one only. + */ + leaves[max_len]++; + + /* Now read the leaves themselves */ + base = 0; + for (len = 1; len <= max_len; len++) { + /* Remember where the literals of this length start in literal[] : */ + lit_base[len] = base; + /* And read the literals: */ + for (n = leaves[len]; n > 0; n--) { + literal[base++] = (uch)get_byte(); + } + } + leaves[max_len]++; /* Now include the EOB code in the Huffman tree */ +} + +/* =========================================================================== + * Build the Huffman tree and the prefix table. + */ +local void build_tree() +{ + int nodes = 0; /* number of nodes (parents+leaves) at current bit length */ + int len; /* current bit length */ + uch *prefixp; /* pointer in prefix_len */ + + for (len = max_len; len >= 1; len--) { + /* The number of parent nodes at this level is half the total + * number of nodes at parent level: + */ + nodes >>= 1; + parents[len] = nodes; + /* Update lit_base by the appropriate bias to skip the parent nodes + * (which are not represented in the literal array): + */ + lit_base[len] -= nodes; + /* Restore nodes to be parents+leaves: */ + nodes += leaves[len]; + } + /* Construct the prefix table, from shortest leaves to longest ones. + * The shortest code is all ones, so we start at the end of the table. + */ + peek_bits = MIN(max_len, MAX_PEEK); + prefixp = &prefix_len[1<<peek_bits]; + for (len = 1; len <= peek_bits; len++) { + int prefixes = leaves[len] << (peek_bits-len); /* may be 0 */ + while (prefixes--) *--prefixp = (uch)len; + } + /* The length of all other codes is unknown: */ + while (prefixp > prefix_len) *--prefixp = 0; +} + +/* =========================================================================== + * Unpack in to out. This routine does not support the old pack format + * with magic header \037\037. + * + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets inptr to insize-1 included. + * The magic header has already been checked. The output buffer is cleared. + */ +int unpack(in, out) + int in, out; /* input and output file descriptors */ +{ + int len; /* Bit length of current code */ + unsigned eob; /* End Of Block code */ + register unsigned peek; /* lookahead bits */ + unsigned peek_mask; /* Mask for peek_bits bits */ + + ifd = in; + ofd = out; + + read_tree(); /* Read the Huffman tree */ + build_tree(); /* Build the prefix table */ + clear_bitbuf(); /* Initialize bit input */ + peek_mask = (1<<peek_bits)-1; + + /* The eob code is the largest code among all leaves of maximal length: */ + eob = leaves[max_len]-1; + Trace((stderr, "eob %d %x\n", max_len, eob)); + + /* Decode the input data: */ + for (;;) { + /* Since eob is the longest code and not shorter than max_len, + * we can peek at max_len bits without having the risk of reading + * beyond the end of file. + */ + look_bits(peek, peek_bits, peek_mask); + len = prefix_len[peek]; + if (len > 0) { + peek >>= peek_bits - len; /* discard the extra bits */ + } else { + /* Code of more than peek_bits bits, we must traverse the tree */ + ulg mask = peek_mask; + len = peek_bits; + do { + len++, mask = (mask<<1)+1; + look_bits(peek, len, mask); + } while (peek < parents[len]); + /* loop as long as peek is a parent node */ + } + /* At this point, peek is the next complete code, of len bits */ + if (peek == eob && len == max_len) break; /* end of file? */ + put_ubyte(literal[peek+lit_base[len]]); + Tracev((stderr,"%02d %04x %c\n", len, peek, + literal[peek+lit_base[len]])); + skip_bits(len); + } /* for (;;) */ + + flush_window(); + Trace((stderr, "bytes_out %ld\n", bytes_out)); + if (orig_len != bytes_out) { + error("invalid compressed data--length error"); + } + return OK; +} diff --git a/gnu/usr.bin/gzip/unzip.c b/gnu/usr.bin/gzip/unzip.c new file mode 100644 index 0000000..a78622a --- /dev/null +++ b/gnu/usr.bin/gzip/unzip.c @@ -0,0 +1,201 @@ +/* unzip.c -- decompress files in gzip or pkzip format. + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + * + * The code in this file is derived from the file funzip.c written + * and put in the public domain by Mark Adler. + */ + +/* + This version can extract files in gzip or pkzip format. + For the latter, only the first entry is extracted, and it has to be + either deflated or stored. + */ + +#ifndef lint +static char rcsid[] = "$Id: unzip.c,v 0.12 1993/05/28 17:56:23 jloup Exp $"; +#endif + +#include <stdio.h> + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +/* PKZIP header definitions */ +#define LOCSIG 0x04034b50L /* four-byte lead-in (lsb first) */ +#define LOCFLG 6 /* offset of bit flag */ +#define CRPFLG 1 /* bit for encrypted entry */ +#define EXTFLG 8 /* bit for extended local header */ +#define LOCHOW 8 /* offset of compression method */ +#define LOCTIM 10 /* file mod time (for decryption) */ +#define LOCCRC 14 /* offset of crc */ +#define LOCSIZ 18 /* offset of compressed size */ +#define LOCLEN 22 /* offset of uncompressed length */ +#define LOCFIL 26 /* offset of file name field length */ +#define LOCEXT 28 /* offset of extra field length */ +#define LOCHDR 30 /* size of local header, including sig */ +#define EXTHDR 16 /* size of extended local header, inc sig */ + + +/* Globals */ + +int decrypt; /* flag to turn on decryption */ +char *key; /* not used--needed to link crypt.c */ +int pkzip = 0; /* set for a pkzip file */ +int ext_header = 0; /* set if extended local header */ + +/* =========================================================================== + * Check zip file and advance inptr to the start of the compressed data. + * Get ofname from the local header if necessary. + */ +int check_zipfile(in) + int in; /* input file descriptors */ +{ + uch *h = inbuf + inptr; /* first local header */ + + ifd = in; + + /* Check validity of local header, and skip name and extra fields */ + inptr += LOCHDR + SH(h + LOCFIL) + SH(h + LOCEXT); + + if (inptr > insize || LG(h) != LOCSIG) { + fprintf(stderr, "\n%s: %s: not a valid zip file\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + method = h[LOCHOW]; + if (method != STORED && method != DEFLATED) { + fprintf(stderr, + "\n%s: %s: first entry not deflated or stored -- use unzip\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + + /* If entry encrypted, decrypt and validate encryption header */ + if ((decrypt = h[LOCFLG] & CRPFLG) != 0) { + fprintf(stderr, "\n%s: %s: encrypted file -- use unzip\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + + /* Save flags for unzip() */ + ext_header = (h[LOCFLG] & EXTFLG) != 0; + pkzip = 1; + + /* Get ofname and time stamp from local header (to be done) */ + return OK; +} + +/* =========================================================================== + * Unzip in to out. This routine works on both gzip and pkzip files. + * + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets inptr to insize-1 included. + * The magic header has already been checked. The output buffer is cleared. + */ +int unzip(in, out) + int in, out; /* input and output file descriptors */ +{ + ulg orig_crc = 0; /* original crc */ + ulg orig_len = 0; /* original uncompressed length */ + int n; + uch buf[EXTHDR]; /* extended local header */ + + ifd = in; + ofd = out; + + updcrc(NULL, 0); /* initialize crc */ + + if (pkzip && !ext_header) { /* crc and length at the end otherwise */ + orig_crc = LG(inbuf + LOCCRC); + orig_len = LG(inbuf + LOCLEN); + } + + /* Decompress */ + if (method == DEFLATED) { + + int res = inflate(); + + if (res == 3) { + error("out of memory"); + } else if (res != 0) { + error("invalid compressed data--format violated"); + } + + } else if (pkzip && method == STORED) { + + register ulg n = LG(inbuf + LOCLEN); + + if (n != LG(inbuf + LOCSIZ) - (decrypt ? RAND_HEAD_LEN : 0)) { + + fprintf(stderr, "len %ld, siz %ld\n", n, LG(inbuf + LOCSIZ)); + error("invalid compressed data--length mismatch"); + } + while (n--) { + uch c = (uch)get_byte(); +#ifdef CRYPT + if (decrypt) zdecode(c); +#endif + put_ubyte(c); + } + flush_window(); + } else { + error("internal error, invalid method"); + } + + /* Get the crc and original length */ + if (!pkzip) { + /* crc32 (see algorithm.doc) + * uncompressed input size modulo 2^32 + */ + for (n = 0; n < 8; n++) { + buf[n] = (uch)get_byte(); /* may cause an error if EOF */ + } + orig_crc = LG(buf); + orig_len = LG(buf+4); + + } else if (ext_header) { /* If extended header, check it */ + /* signature - 4bytes: 0x50 0x4b 0x07 0x08 + * CRC-32 value + * compressed size 4-bytes + * uncompressed size 4-bytes + */ + for (n = 0; n < EXTHDR; n++) { + buf[n] = (uch)get_byte(); /* may cause an error if EOF */ + } + orig_crc = LG(buf+4); + orig_len = LG(buf+12); + } + + /* Validate decompression */ + if (orig_crc != updcrc(outbuf, 0)) { + error("invalid compressed data--crc error"); + } + if (orig_len != bytes_out) { + error("invalid compressed data--length error"); + } + + /* Check if there are more entries in a pkzip file */ + if (pkzip && inptr + 4 < insize && LG(inbuf+inptr) == LOCSIG) { + if (to_stdout) { + WARN((stderr, + "%s: %s has more than one entry--rest ignored\n", + progname, ifname)); + } else { + /* Don't destroy the input zip file */ + fprintf(stderr, + "%s: %s has more than one entry -- unchanged\n", + progname, ifname); + exit_code = ERROR; + ext_header = pkzip = 0; + return ERROR; + } + } + ext_header = pkzip = 0; /* for next file */ + return OK; +} diff --git a/gnu/usr.bin/gzip/util.c b/gnu/usr.bin/gzip/util.c new file mode 100644 index 0000000..dc3695e --- /dev/null +++ b/gnu/usr.bin/gzip/util.c @@ -0,0 +1,419 @@ +/* util.c -- utility functions for gzip support + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifndef lint +static char rcsid[] = "$Id: util.c,v 0.14 1993/05/27 10:31:52 jloup Exp $"; +#endif + +#include <stdio.h> +#include <ctype.h> +#include <errno.h> +#include <sys/types.h> + +#include "tailor.h" + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif +#ifndef NO_FCNTL_H +# include <fcntl.h> +#endif + +#if defined(STDC_HEADERS) || !defined(NO_STDLIB_H) +# include <stdlib.h> +#else + extern int errno; +#endif + +#include "gzip.h" +#include "crypt.h" + +extern ulg crc_32_tab[]; /* crc table, defined below */ + +/* =========================================================================== + * Run a set of bytes through the crc shift register. If s is a NULL + * pointer, then initialize the crc shift register contents instead. + * Return the current crc in either case. + */ +ulg updcrc(s, n) + uch *s; /* pointer to bytes to pump through */ + unsigned n; /* number of bytes in s[] */ +{ + register ulg c; /* temporary variable */ + + static ulg crc = (ulg)0xffffffffL; /* shift register contents */ + + if (s == NULL) { + c = 0xffffffffL; + } else { + c = crc; + if (n) do { + c = crc_32_tab[((int)c ^ (*s++)) & 0xff] ^ (c >> 8); + } while (--n); + } + crc = c; + return c ^ 0xffffffffL; /* (instead of ~c for 64-bit machines) */ +} + +/* =========================================================================== + * Clear input and output buffers + */ +void clear_bufs() +{ + outcnt = 0; + insize = inptr = 0; + bytes_in = bytes_out = 0L; +} + +/* =========================================================================== + * Fill the input buffer. This is called only when the buffer is empty + * and at least one byte is really needed. + */ +int fill_inbuf() +{ + int len; + + /* Read as much as possible */ + insize = 0; + errno = 0; + do { + len = read(ifd, (char*)inbuf+insize, INBUFSIZ-insize); + if (len == 0 || len == EOF) break; + insize += len; + } while (insize < INBUFSIZ); + + if (insize == 0) { + read_error(); + } + bytes_in += (ulg)insize; + inptr = 1; + return inbuf[0]; +} + +/* =========================================================================== + * Write the output buffer outbuf[0..outcnt-1] and update bytes_out. + * (used for the compressed data only) + */ +void flush_outbuf() +{ + if (outcnt == 0) return; + + write_buf(ofd, (char *)outbuf, outcnt); + bytes_out += (ulg)outcnt; + outcnt = 0; +} + +/* =========================================================================== + * Write the output window window[0..outcnt-1] and update crc and bytes_out. + * (Used for the decompressed data only.) + */ +void flush_window() +{ + if (outcnt == 0) return; + updcrc(window, outcnt); + + if (!test) { + write_buf(ofd, (char *)window, outcnt); + } + bytes_out += (ulg)outcnt; + outcnt = 0; +} + +/* =========================================================================== + * Does the same as write(), but also handles partial pipe writes and checks + * for error return. + */ +void write_buf(fd, buf, cnt) + int fd; + voidp buf; + unsigned cnt; +{ + unsigned n; + + while ((n = write(fd, buf, cnt)) != cnt) { + if (n == (unsigned)(-1)) { + write_error(); + } + cnt -= n; + buf = (voidp)((char*)buf+n); + } +} + +/* ======================================================================== + * Put string s in lower case, return s. + */ +char *strlwr(s) + char *s; +{ + char *t; + for (t = s; *t; t++) *t = tolow(*t); + return s; +} + +/* ======================================================================== + * Return the base name of a file (remove any directory prefix and + * any version suffix). For systems with file names that are not + * case sensitive, force the base name to lower case. + */ +char *basename(fname) + char *fname; +{ + char *p; + + if ((p = strrchr(fname, PATH_SEP)) != NULL) fname = p+1; +#ifdef PATH_SEP2 + if ((p = strrchr(fname, PATH_SEP2)) != NULL) fname = p+1; +#endif +#ifdef PATH_SEP3 + if ((p = strrchr(fname, PATH_SEP3)) != NULL) fname = p+1; +#endif +#ifdef SUFFIX_SEP + if ((p = strrchr(fname, SUFFIX_SEP)) != NULL) *p = '\0'; +#endif + if (casemap('A') == 'a') strlwr(fname); + return fname; +} + +#if defined(NO_STRING_H) && !defined(STDC_HEADERS) + +/* Provide missing strspn and strcspn functions. */ + +# ifndef __STDC__ +# define const +# endif + +int strspn OF((const char *s, const char *accept)); +int strcspn OF((const char *s, const char *reject)); + +/* ======================================================================== + * Return the length of the maximum initial segment + * of s which contains only characters in accept. + */ +int strspn(s, accept) + const char *s; + const char *accept; +{ + register const char *p; + register const char *a; + register int count = 0; + + for (p = s; *p != '\0'; ++p) { + for (a = accept; *a != '\0'; ++a) { + if (*p == *a) break; + } + if (*a == '\0') return count; + ++count; + } + return count; +} + +/* ======================================================================== + * Return the length of the maximum inital segment of s + * which contains no characters from reject. + */ +int strcspn(s, reject) + const char *s; + const char *reject; +{ + register int count = 0; + + while (*s != '\0') { + if (strchr(reject, *s++) != NULL) return count; + ++count; + } + return count; +} + +#endif /* NO_STRING_H */ + +/* ======================================================================== + * Add an environment variable (if any) before argv, and update argc. + * Return the expanded environment variable to be freed later, or NULL + * if no options were added to argv. + */ +#define SEPARATOR " \t" /* separators in env variable */ + +char *add_envopt(argcp, argvp, env) + int *argcp; /* pointer to argc */ + char ***argvp; /* pointer to argv */ + char *env; /* name of environment variable */ +{ + char *p; /* running pointer through env variable */ + char **oargv; /* runs through old argv array */ + char **nargv; /* runs through new argv array */ + int oargc = *argcp; /* old argc */ + int nargc = 0; /* number of arguments in env variable */ + + env = (char*)getenv(env); + if (env == NULL) return NULL; + + p = (char*)xmalloc(strlen(env)+1); + env = strcpy(p, env); /* keep env variable intact */ + + for (p = env; *p; nargc++ ) { /* move through env */ + p += strspn(p, SEPARATOR); /* skip leading separators */ + if (*p == '\0') break; + + p += strcspn(p, SEPARATOR); /* find end of word */ + if (*p) *p++ = '\0'; /* mark it */ + } + if (nargc == 0) { + free(env); env = NULL; + return NULL; + } + *argcp += nargc; + /* Allocate the new argv array, with an extra element just in case + * the original arg list did not end with a NULL. + */ + nargv = (char**)calloc(*argcp+1, sizeof(char *)); + if (nargv == NULL) error("out of memory"); + oargv = *argvp; + *argvp = nargv; + + /* Copy the program name first */ + if (oargc-- < 0) error("argc<=0"); + *(nargv++) = *(oargv++); + + /* Then copy the environment args */ + for (p = env; nargc > 0; nargc--) { + p += strspn(p, SEPARATOR); /* skip separators */ + *(nargv++) = p; /* store start */ + while (*p++) ; /* skip over word */ + } + + /* Finally copy the old args and add a NULL (usual convention) */ + while (oargc--) *(nargv++) = *(oargv++); + *nargv = NULL; + return env; +} + +/* ======================================================================== + * Error handlers. + */ +void error(m) + char *m; +{ + fprintf(stderr, "\n%s: %s: %s\n", progname, ifname, m); + abort_gzip(); +} + +void warn(a, b) + char *a, *b; /* message strings juxtaposed in output */ +{ + WARN((stderr, "%s: %s: warning: %s%s\n", progname, ifname, a, b)); +} + +void read_error() +{ + fprintf(stderr, "\n%s: ", progname); + if (errno != 0) { + perror(ifname); + } else { + fprintf(stderr, "%s: unexpected end of file\n", ifname); + } + abort_gzip(); +} + +void write_error() +{ + fprintf(stderr, "\n%s: ", progname); + perror(ofname); + abort_gzip(); +} + +/* ======================================================================== + * Display compression ratio on stderr. + */ +void display_ratio(num, den) + long num; + long den; +{ + long ratio; /* 1000 times the compression ratio */ + + if (den == 0) { + ratio = 0; /* no compression */ + } else if (den < 2147483L) { /* (2**31 -1)/1000 */ + ratio = 1000L*num/den; + } else { + ratio = num/(den/1000L); + } + if (ratio < 0) { + putc('-', stderr); + ratio = -ratio; + } + fprintf(stderr, "%2ld.%ld%%", ratio / 10L, ratio % 10L); +} + + +/* ======================================================================== + * Semi-safe malloc -- never returns NULL. + */ +voidp xmalloc (size) + unsigned size; +{ + voidp cp = (voidp)malloc (size); + + if (cp == NULL) error("out of memory"); + return cp; +} + +/* ======================================================================== + * Table of CRC-32's of all single-byte values (made by makecrc.c) + */ +ulg crc_32_tab[] = { + 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, + 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, + 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, + 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, + 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, + 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, + 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, + 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, + 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, + 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, + 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, + 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, + 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, + 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, + 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, + 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, + 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, + 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, + 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, + 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, + 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, + 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, + 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, + 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, + 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, + 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, + 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, + 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, + 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, + 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, + 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, + 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, + 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, + 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, + 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, + 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, + 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, + 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, + 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, + 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, + 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, + 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, + 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, + 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, + 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, + 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, + 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, + 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, + 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, + 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, + 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, + 0x2d02ef8dL +}; diff --git a/gnu/usr.bin/gzip/zcmp b/gnu/usr.bin/gzip/zcmp new file mode 100644 index 0000000..c21e7ef --- /dev/null +++ b/gnu/usr.bin/gzip/zcmp @@ -0,0 +1,67 @@ +#!/bin/sh + +# Zcmp and zdiff are used to invoke the cmp or the diff pro- +# gram on compressed files. All options specified are passed +# directly to cmp or diff. If only 1 file is specified, then +# the files compared are file1 and an uncompressed file1.gz. +# If two files are specified, then they are uncompressed (if +# necessary) and fed to cmp or diff. The exit status from cmp +# or diff is preserved. + +prog=`echo $0 | sed 's|.*/||'` +case "$prog" in + *cmp) comp=${CMP-cmp} ;; + *) comp=${DIFF-diff} ;; +esac + +OPTIONS= +FILES= +for ARG +do + case "$ARG" in + -*) OPTIONS="$OPTIONS $ARG";; + *) if test -f "$ARG"; then + FILES="$FILES $ARG" + else + echo "${prog}: $ARG not found or not a regular file" + exit 1 + fi ;; + esac +done +if test -z "$FILES"; then + echo "Usage: $prog [${comp}_options] file [file]" + exit 1 +fi +set $FILES +if test $# -eq 1; then + FILE=`echo "$1" | sed 's/[-.][zZtga]*$//'` + gzip -cd "$1" | $comp $OPTIONS - "$FILE" + STAT="$?" + +elif test $# -eq 2; then + case "$1" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + case "$2" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + F=`echo "$2" | sed 's|.*/||;s|[-.][zZtga]*$||'` + gzip -cd "$2" > /tmp/"$F".$$ + gzip -cd "$1" | $comp $OPTIONS - /tmp/"$F".$$ + STAT="$?" + /bin/rm -f /tmp/"$F".$$;; + + *) gzip -cd "$1" | $comp $OPTIONS - "$2" + STAT="$?";; + esac;; + *) case "$2" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + gzip -cd "$2" | $comp $OPTIONS "$1" - + STAT="$?";; + *) $comp $OPTIONS "$1" "$2" + STAT="$?";; + esac;; + esac + exit "$STAT" +else + echo "Usage: $prog [${comp}_options] file [file]" + exit 1 +fi diff --git a/gnu/usr.bin/gzip/zdiff b/gnu/usr.bin/gzip/zdiff new file mode 100644 index 0000000..c21e7ef --- /dev/null +++ b/gnu/usr.bin/gzip/zdiff @@ -0,0 +1,67 @@ +#!/bin/sh + +# Zcmp and zdiff are used to invoke the cmp or the diff pro- +# gram on compressed files. All options specified are passed +# directly to cmp or diff. If only 1 file is specified, then +# the files compared are file1 and an uncompressed file1.gz. +# If two files are specified, then they are uncompressed (if +# necessary) and fed to cmp or diff. The exit status from cmp +# or diff is preserved. + +prog=`echo $0 | sed 's|.*/||'` +case "$prog" in + *cmp) comp=${CMP-cmp} ;; + *) comp=${DIFF-diff} ;; +esac + +OPTIONS= +FILES= +for ARG +do + case "$ARG" in + -*) OPTIONS="$OPTIONS $ARG";; + *) if test -f "$ARG"; then + FILES="$FILES $ARG" + else + echo "${prog}: $ARG not found or not a regular file" + exit 1 + fi ;; + esac +done +if test -z "$FILES"; then + echo "Usage: $prog [${comp}_options] file [file]" + exit 1 +fi +set $FILES +if test $# -eq 1; then + FILE=`echo "$1" | sed 's/[-.][zZtga]*$//'` + gzip -cd "$1" | $comp $OPTIONS - "$FILE" + STAT="$?" + +elif test $# -eq 2; then + case "$1" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + case "$2" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + F=`echo "$2" | sed 's|.*/||;s|[-.][zZtga]*$||'` + gzip -cd "$2" > /tmp/"$F".$$ + gzip -cd "$1" | $comp $OPTIONS - /tmp/"$F".$$ + STAT="$?" + /bin/rm -f /tmp/"$F".$$;; + + *) gzip -cd "$1" | $comp $OPTIONS - "$2" + STAT="$?";; + esac;; + *) case "$2" in + *[-.]gz | *[-.][zZ] | *.t[ga]z) + gzip -cd "$2" | $comp $OPTIONS "$1" - + STAT="$?";; + *) $comp $OPTIONS "$1" "$2" + STAT="$?";; + esac;; + esac + exit "$STAT" +else + echo "Usage: $prog [${comp}_options] file [file]" + exit 1 +fi diff --git a/gnu/usr.bin/gzip/zdiff.1 b/gnu/usr.bin/gzip/zdiff.1 new file mode 100644 index 0000000..44f9137 --- /dev/null +++ b/gnu/usr.bin/gzip/zdiff.1 @@ -0,0 +1,44 @@ +.TH ZDIFF 1 +.SH NAME +zcmp, zdiff \- compare compressed files +.SH SYNOPSIS +.B zcmp +[ cmp_options ] file1 +[ file2 ] +.br +.B zdiff +[ diff_options ] file1 +[ file2 ] +.SH DESCRIPTION +.I Zcmp +and +.I zdiff +are used to invoke the +.I cmp +or the +.I diff +program on compressed files. All options specified are passed directly to +.I cmp +or +.IR diff "." +If only 1 file is specified, then the files compared are +.I file1 +and an uncompressed +.IR file1 ".gz." +If two files are specified, then they are uncompressed if necessary and fed to +.I cmp +or +.IR diff "." +The exit status from +.I cmp +or +.I diff +is preserved. +.SH "SEE ALSO" +cmp(1), diff(1), zmore(1), znew(1), zforce(1), gzip(1), gzexe(1) +.SH BUGS +Messages from the +.I cmp +or +.I diff +programs refer to temporary filenames instead of those specified. diff --git a/gnu/usr.bin/gzip/zforce b/gnu/usr.bin/gzip/zforce new file mode 100644 index 0000000..9fe85ad --- /dev/null +++ b/gnu/usr.bin/gzip/zforce @@ -0,0 +1,39 @@ +#!/bin/sh +# zforce: force a gz extension on all gzip files so that gzip will not +# compress them twice. +# +# This can be useful for files with names truncated after a file transfer. +# 12345678901234 is renamed to 12345678901.gz + +x=`basename $0` +if test $# = 0; then + echo "force a '.gz' extension on all gzip files" + echo usage: $x files... + exit 1 +fi + +res=0 +for i do + if test ! -f "$i" ; then + echo ${x}: $i not a file + res=1 + continue + fi + test `expr "$i" : '.*[.-]z$'` -eq 0 || continue + test `expr "$i" : '.*[.-]gz$'` -eq 0 || continue + test `expr "$i" : '.*[.]t[ag]z$'` -eq 0 || continue + + gzip -t "$i" 2>/dev/null || continue + + if test `expr "$i" : '^............'` -eq 12; then + new=`expr "$i" : '\(.*\)...$`.gz + else + new="$i.gz" + fi + if mv "$i" "$new" 2>/dev/null; then + echo $i -- replaced with $new + continue + fi + res=1; echo ${x}: cannot rename $i to $new +done +exit $res diff --git a/gnu/usr.bin/gzip/zforce.1 b/gnu/usr.bin/gzip/zforce.1 new file mode 100644 index 0000000..e231815 --- /dev/null +++ b/gnu/usr.bin/gzip/zforce.1 @@ -0,0 +1,20 @@ +.TH ZFORCE 1 +.SH NAME +zforce \- force a '.gz' extension on all gzip files +.SH SYNOPSIS +.B zforce +[ name ... ] +.SH DESCRIPTION +.I zforce +forces a .gz extension on all +.I gzip +files so that +.I gzip +will not compress them twice. +This can be useful for files with names truncated after a file transfer. +On systems with a 14 char limitation on file names, the original name +is truncated to make room for the .gz suffix. For example, +12345678901234 is renamed to 12345678901.gz. A file name such as foo.tgz +is left intact. +.SH "SEE ALSO" +gzip(1), znew(1), zmore(1), zcmp(1), gzexe(1) diff --git a/gnu/usr.bin/gzip/zip.c b/gnu/usr.bin/gzip/zip.c new file mode 100644 index 0000000..5bf172f --- /dev/null +++ b/gnu/usr.bin/gzip/zip.c @@ -0,0 +1,118 @@ +/* zip.c -- compress files to the gzip or pkzip format + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifndef lint +static char rcsid[] = "$Id: zip.c,v 0.16 1993/05/28 14:51:17 jloup Exp $"; +#endif + +#include <ctype.h> +#include <stdio.h> +#include <sys/types.h> + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif +#ifndef NO_FCNTL_H +# include <fcntl.h> +#endif + +local ulg crc; /* crc on uncompressed file data */ +long header_bytes; /* number of bytes in gzip header */ + +/* =========================================================================== + * Deflate in to out. + * IN assertions: the input and output buffers are cleared. + * The variables time_stamp and save_orig_name are initialized. + */ +int zip(in, out) + int in, out; /* input and output file descriptors */ +{ + uch flags = 0; /* general purpose bit flags */ + ush attr = 0; /* ascii/binary flag */ + ush deflate_flags = 0; /* pkzip -es, -en or -ex equivalent */ + + ifd = in; + ofd = out; + outcnt = 0; + + /* Write the header to the gzip file. See algorithm.doc for the format */ + + method = DEFLATED; + put_byte(GZIP_MAGIC[0]); /* magic header */ + put_byte(GZIP_MAGIC[1]); + put_byte(DEFLATED); /* compression method */ + + if (save_orig_name) { + flags |= ORIG_NAME; + } + put_byte(flags); /* general flags */ + put_long(time_stamp); + + /* Write deflated file to zip file */ + crc = updcrc(0, 0); + + bi_init(out); + ct_init(&attr, &method); + lm_init(level, &deflate_flags); + + put_byte((uch)deflate_flags); /* extra flags */ + put_byte(OS_CODE); /* OS identifier */ + + if (save_orig_name) { + char *p = basename(ifname); /* Don't save the directory part. */ + do { + put_char(*p); + } while (*p++); + } + header_bytes = (long)outcnt; + + (void)deflate(); + +#if !defined(NO_SIZE_CHECK) && !defined(RECORD_IO) + /* Check input size (but not in VMS -- variable record lengths mess it up) + * and not on MSDOS -- diet in TSR mode reports an incorrect file size) + */ + if (ifile_size != -1L && isize != (ulg)ifile_size) { + Trace((stderr, " actual=%ld, read=%ld ", ifile_size, isize)); + fprintf(stderr, "%s: %s: file size changed while zipping\n", + progname, ifname); + } +#endif + + /* Write the crc and uncompressed size */ + put_long(crc); + put_long(isize); + header_bytes += 2*sizeof(long); + + flush_outbuf(); + return OK; +} + + +/* =========================================================================== + * Read a new buffer from the current input file, perform end-of-line + * translation, and update the crc and input file size. + * IN assertion: size >= 2 (for end-of-line translation) + */ +int file_read(buf, size) + char *buf; + unsigned size; +{ + unsigned len; + + Assert(insize == 0, "inbuf not empty"); + + len = read(ifd, buf, size); + if (len == (unsigned)(-1) || len == 0) return (int)len; + + crc = updcrc((uch*)buf, len); + isize += (ulg)len; + return (int)len; +} diff --git a/gnu/usr.bin/gzip/zmore b/gnu/usr.bin/gzip/zmore new file mode 100644 index 0000000..64f7b1b --- /dev/null +++ b/gnu/usr.bin/gzip/zmore @@ -0,0 +1,42 @@ +#!/bin/sh + +if test "`echo -n a`" = "-n a"; then + # looks like a SysV system: + n1=''; n2='\c' +else + n1='-n'; n2='' +fi +if stty -cbreak 2>/dev/null; then + cb='cbreak'; ncb='-cbreak' +else + # 'stty min 1' resets eof to ^a on both SunOS and SysV! + cb='min 1 -icanon'; ncb='icanon eof ^d' +fi +oldtty=`stty -g` +trap 'stty -g $oldtty 2>/dev/null; exit' 0 2 3 5 10 13 15 + +if test $# = 0; then + gzip -cd | eval ${PAGER-more} +else + FIRST=1 + for FILE + do + if test $FIRST -eq 0; then + echo $n1 "--More--(Next file: $FILE)$n2" + stty $cb -echo 2>/dev/null + ANS=`dd bs=1 count=1 2>/dev/null` + stty $ncb echo 2>/dev/null + echo " " + if test "$ANS" = 'e' -o "$ANS" = 'q'; then + exit + fi + fi + if test "$ANS" != 's'; then + echo "------> $FILE <------" + gzip -cd "$FILE" | eval ${PAGER-more} + fi + if test -t; then + FIRST=0 + fi + done +fi diff --git a/gnu/usr.bin/gzip/zmore.1 b/gnu/usr.bin/gzip/zmore.1 new file mode 100644 index 0000000..08b49fb --- /dev/null +++ b/gnu/usr.bin/gzip/zmore.1 @@ -0,0 +1,134 @@ +.TH ZMORE 1 +.SH NAME +zmore \- file perusal filter for crt viewing of compressed text +.SH SYNOPSIS +.B zmore +[ name ... ] +.SH DESCRIPTION +.I Zmore +is a filter which allows examination of compressed text files +one screenful at a time on a soft-copy terminal. +It normally pauses after each screenful, printing --More-- +at the bottom of the screen. +If the user then types a carriage return, one more line is displayed. +If the user hits a space, +another screenful is displayed. Other possibilities are enumerated later. +.PP +.I Zmore +looks in the file +.I /etc/termcap +to determine terminal characteristics, +and to determine the default window size. +On a terminal capable of displaying 24 lines, +the default window size is 22 lines. +To use a pager other than the default +.I more, +set environment variable PAGER to the name of the desired program, such as +.I less. +.PP +Other sequences which may be typed when +.I zmore +pauses, and their effects, are as follows (\fIi\fP is an optional integer +argument, defaulting to 1) : +.PP +.IP \fIi\|\fP<space> +display +.I i +more lines, (or another screenful if no argument is given) +.PP +.IP ^D +display 11 more lines (a ``scroll''). +If +.I i +is given, then the scroll size is set to \fIi\|\fP. +.PP +.IP d +same as ^D (control-D) +.PP +.IP \fIi\|\fPz +same as typing a space except that \fIi\|\fP, if present, becomes the new +window size. Note that the window size reverts back to the default at the +end of the current file. +.PP +.IP \fIi\|\fPs +skip \fIi\|\fP lines and print a screenful of lines +.PP +.IP \fIi\|\fPf +skip \fIi\fP screenfuls and print a screenful of lines +.PP +.IP "q or Q" +quit reading the current file; go on to the next (if any) +.PP +.IP "e or q" +When the prompt --More--(Next file: +.IR file ) +is printed, this command causes zmore to exit. +.PP +.IP s +When the prompt --More--(Next file: +.IR file ) +is printed, this command causes zmore to skip the next file and continue. +.PP +.IP = +Display the current line number. +.PP +.IP \fIi\|\fP/expr +search for the \fIi\|\fP-th occurrence of the regular expression \fIexpr.\fP +If the pattern is not found, +.I zmore +goes on to the next file (if any). +Otherwise, a screenful is displayed, starting two lines before the place +where the expression was found. +The user's erase and kill characters may be used to edit the regular +expression. +Erasing back past the first column cancels the search command. +.PP +.IP \fIi\|\fPn +search for the \fIi\|\fP-th occurrence of the last regular expression entered. +.PP +.IP !command +invoke a shell with \fIcommand\|\fP. +The character `!' in "command" are replaced with the +previous shell command. The sequence "\\!" is replaced by "!". +.PP +.IP ":q or :Q" +quit reading the current file; go on to the next (if any) +(same as q or Q). +.PP +.IP . +(dot) repeat the previous command. +.PP +The commands take effect immediately, i.e., it is not necessary to +type a carriage return. +Up to the time when the command character itself is given, +the user may hit the line kill character to cancel the numerical +argument being formed. +In addition, the user may hit the erase character to redisplay the +--More-- message. +.PP +At any time when output is being sent to the terminal, the user can +hit the quit key (normally control\-\\). +.I Zmore +will stop sending output, and will display the usual --More-- +prompt. +The user may then enter one of the above commands in the normal manner. +Unfortunately, some output is lost when this is done, due to the +fact that any characters waiting in the terminal's output queue +are flushed when the quit signal occurs. +.PP +The terminal is set to +.I noecho +mode by this program so that the output can be continuous. +What you type will thus not show on your terminal, except for the / and ! +commands. +.PP +If the standard output is not a teletype, then +.I zmore +acts just like +.I zcat, +except that a header is printed before each file. +.SH FILES +.DT +/etc/termcap Terminal data base +.SH "SEE ALSO" +more(1), gzip(1), zcmp(1), znew(1), zforce(1), gzexe(1) diff --git a/gnu/usr.bin/gzip/znew b/gnu/usr.bin/gzip/znew new file mode 100644 index 0000000..fcbc466 --- /dev/null +++ b/gnu/usr.bin/gzip/znew @@ -0,0 +1,140 @@ +#!/bin/sh + +check=0 +pipe=0 +opt= +files= +keep=0 +res=0 +old=0 +new=0 +block=1024 +# block is the disk block size (best guess, need not be exact) + +warn="(does not preserve modes and timestamp)" +tmp=/tmp/zfoo.$$ +echo hi > $tmp.1 +echo hi > $tmp.2 +if test -z "`(${CPMOD-cpmod} $tmp.1 $tmp.2) 2>&1`"; then + cpmod=${CPMOD-cpmod} + warn="" +fi + +if test -z "$cpmod" && ${TOUCH-touch} -r $tmp.1 $tmp.2 2>/dev/null; then + cpmod="${TOUCH-touch}" + cpmodarg="-r" + warn="(does not preserve file modes)" +fi +rm -f $tmp.[12] + +A= +fileno=0 + +for arg +do + case "$arg" in + -*) opt="$opt $arg";; + *) fileno=`expr $fileno + 1` + eval A$fileno=\$arg + A="$A \"\$A$fileno\"" + ;; + esac +done + +if test $fileno -eq 0; then + echo 'recompress .Z files into .gz (gzip) files' + echo usage: `echo $0 | sed 's,^.*/,,'` "[-tv9P]" file.Z... + echo " -t tests the new files before deleting originals" + echo " -v be verbose" + echo " -9 use the slowest compression method (optimal compression)" + echo " -K keep a .Z file when it is smaller than the .gz file" + echo " -P use pipes for the conversion $warn" + exit 1 +fi + +eval set "$A" # the files are now in $1, $2, ... + +opt=`echo "$opt" | sed -e 's/ //g' -e 's/-//g'` +case "$opt" in + *t*) check=1; opt=`echo "$opt" | sed 's/t//g'` +esac +case "$opt" in + *K*) keep=1; opt=`echo "$opt" | sed 's/K//g'` +esac +case "$opt" in + *P*) pipe=1; opt=`echo "$opt" | sed 's/P//g'` +esac +if test -n "$opt"; then + opt="-$opt" +fi + +for i do + n=`echo $i | sed 's/.Z$//'` + if test ! -f "$n.Z" ; then + echo $n.Z not found + res=1; continue + fi + test $keep -eq 1 && old=`wc -c < "$n.Z"` + if test $pipe -eq 1; then + if gzip -d < "$n.Z" | gzip $opt > "$n.gz"; then + # Copy file attributes from old file to new one, if possible. + test -n "$cpmod" && $cpmod $cpmodarg "$n.Z" "$n.gz" 2> /dev/null + else + echo error while recompressing $n.Z + res=1; continue + fi + else + if test $check -eq 1; then + if cp -p "$n.Z" "$n.$$" 2> /dev/null || cp "$n.Z" "$n.$$"; then + : + else + echo cannot backup "$n.Z" + res=1; continue + fi + fi + if gzip -d "$n.Z"; then + : + else + test $check -eq 1 && mv "$n.$$" "$n.Z" + echo error while uncompressing $n.Z + res=1; continue + fi + if gzip $opt "$n"; then + : + else + if test $check -eq 1; then + mv "$n.$$" "$n.Z" && rm -f "$n" + echo error while recompressing $n + else + # compress $n (might be dangerous if disk full) + echo error while recompressing $n, left uncompressed + fi + res=1; continue + fi + fi + test $keep -eq 1 && new=`wc -c < "$n.gz"` + if test $keep -eq 1 -a `expr \( $old + $block - 1 \) / $block` -lt \ + `expr \( $new + $block - 1 \) / $block`; then + if test $pipe -eq 1; then + rm -f "$n.gz" + elif test $check -eq 1; then + mv "$n.$$" "$n.Z" && rm -f "$n.gz" + else + gzip -d "$n.gz" && compress "$n" && rm -f "$n.gz" + fi + echo "$n.Z smaller than $n.gz -- unchanged" + + elif test $check -eq 1; then + if gzip -t "$n.gz" ; then + rm -f "$n.$$" "$n.Z" + else + test $pipe -eq 0 && mv "$n.$$" "$n.Z" + rm -f "$n.gz" + echo error while testing $n.gz, $n.Z unchanged + res=1; continue + fi + elif test $pipe -eq 1; then + rm -f "$n.Z" + fi +done +exit $res diff --git a/gnu/usr.bin/gzip/znew.1 b/gnu/usr.bin/gzip/znew.1 new file mode 100644 index 0000000..644873b --- /dev/null +++ b/gnu/usr.bin/gzip/znew.1 @@ -0,0 +1,36 @@ +.TH ZNEW 1 +.SH NAME +znew \- recompress .Z files to .gz files +.SH SYNOPSIS +.B znew +[ -ftv9PK] [ name.Z ... ] +.SH DESCRIPTION +.I Znew +recompresses files from .Z (compress) format to .gz (gzip) format. +.SH OPTIONS +.B \-f +Force recompression from .Z to .gz format even if a .gz file already exists. +.TP +.B \-t +Tests the new files before deleting originals. +.TP +.B \-v +Verbose. Display the name and percentage reduction for each file compressed. +.TP +.B \-9 +Use the slowest compression method (optimal compression). +.TP +.B \-P +Use pipes for the conversion to reduce disk space usage. +.TP +.B \-K +Keep a .Z file when it is smaller than the .gz file +.SH "SEE ALSO" +gzip(1), zmore(1), zcmp(1), zforce(1), gzexe(1), compress(1) +.SH BUGS +.I Znew +does not maintain the time stamp with the -P option if +.I cpmod(1) +is not available and +.I touch(1) +does not support the -r option. |