diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-19 17:06:04 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-19 17:06:04 +0000 |
| commit | 2f0649f6fe411d7e07c8d56cf8ea56db53536da8 (patch) | |
| tree | 778611fb52176dce1ad06c68e87b2cb348ca0f7b /usr/gzip | |
| parent | Initial commit. (diff) | |
| download | klibc-upstream/2.0.13.tar.xz klibc-upstream/2.0.13.zip | |
Adding upstream version 2.0.13.upstream/2.0.13upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'usr/gzip')
| -rw-r--r-- | usr/gzip/.gitignore | 3 | ||||
| -rw-r--r-- | usr/gzip/COPYING | 339 | ||||
| -rw-r--r-- | usr/gzip/Kbuild | 26 | ||||
| -rw-r--r-- | usr/gzip/README | 144 | ||||
| -rw-r--r-- | usr/gzip/bits.c | 200 | ||||
| -rw-r--r-- | usr/gzip/deflate.c | 759 | ||||
| -rw-r--r-- | usr/gzip/gzip.c | 1215 | ||||
| -rw-r--r-- | usr/gzip/gzip.h | 298 | ||||
| -rw-r--r-- | usr/gzip/inflate.c | 950 | ||||
| -rw-r--r-- | usr/gzip/revision.h | 11 | ||||
| -rw-r--r-- | usr/gzip/tailor.h | 50 | ||||
| -rw-r--r-- | usr/gzip/trees.c | 1075 | ||||
| -rw-r--r-- | usr/gzip/unzip.c | 77 | ||||
| -rw-r--r-- | usr/gzip/util.c | 372 | ||||
| -rw-r--r-- | usr/gzip/zip.c | 110 |
15 files changed, 5629 insertions, 0 deletions
diff --git a/usr/gzip/.gitignore b/usr/gzip/.gitignore new file mode 100644 index 0000000..b665e3f --- /dev/null +++ b/usr/gzip/.gitignore @@ -0,0 +1,3 @@ +gunzip +gzip +zcat diff --git a/usr/gzip/COPYING b/usr/gzip/COPYING new file mode 100644 index 0000000..a43ea21 --- /dev/null +++ b/usr/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/usr/gzip/Kbuild b/usr/gzip/Kbuild new file mode 100644 index 0000000..52c57d0 --- /dev/null +++ b/usr/gzip/Kbuild @@ -0,0 +1,26 @@ +# +# Kbuild file for gzip +# + +# The gzip executable +static-y := gzip +gzip-y := gzip.o util.o unzip.o inflate.o + +# Additional targets +always := gunzip zcat + +# Optional ZIP support +gzip-$(CONFIG_KLIBC_ZIP) += zip.o deflate.o trees.o bits.o +cflags-$(CONFIG_KLIBC_ZIP) += -DSUPPORT_ZIP +EXTRA_KLIBCCFLAGS := $(cflags-y) + +# Additionally linked targets +$(obj)/gunzip $(obj)/zcat: $(obj)/gzip + $(call cmd,ln) + +# Cleaning +targets := gzip gzip.g gunzip zcat + +# Targets to install +install-y := gzip +install-link-y := gunzip=gzip zcat=gzip diff --git a/usr/gzip/README b/usr/gzip/README new file mode 100644 index 0000000..fdd7311 --- /dev/null +++ b/usr/gzip/README @@ -0,0 +1,144 @@ +This is the file README for the gzip distribution, version 1.2.4. + +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.) + +WARNING: on several systems, compiler bugs cause gzip to fail, in +particular when optimization options are on. See the section "Special +targets" at the end of the INSTALL file for a list of known problems. +For all machines, use "make check" to check that gzip was compiled +correctly. Try compiling gzip without any optimization if you have a +problem. + +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 + +If you send me patches for machines I don't have access to, please test them +very carefully. gzip is used for backups, it must be extremely reliable. + +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 package ftp.uu.net:/languages/emacs-lisp/misc/jka-compr19.el.Z +also supports gzip'ed files. + +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 in subdirectory sample +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.gz). +- 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. + gzip386.exe runs much faster but only on 386 and above; it is compiled with + djgpp 1.10 available in directory omnigate.clarkson.edu:/pub/msdos/djgpp. + +A VMS executable is available in ftp.spc.edu:[.macro32.savesets]gzip-1-*.zip +(use [.macro32]unzip.exe to extract). A PRIMOS executable is available +in ftp.lysator.liu.se:/pub/primos/run/gzip.run. +OS/2 executables (16 and 32 bits versions) are available in +ftp.tu-muenchen.de:/pub/comp/os/os2/archiver/gz*-[16,32].zip + +Some ftp servers can automatically make a tar.Z from a tar file. If +you are getting gzip for the first time, you can ask for a tar.Z file +instead of the much larger tar file. + +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.gz 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.gz 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/usr/gzip/bits.c b/usr/gzip/bits.c new file mode 100644 index 0000000..4707a08 --- /dev/null +++ b/usr/gzip/bits.c @@ -0,0 +1,200 @@ +/* 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" + +#ifdef DEBUG +# include <stdio.h> +#endif + +#ifdef RCSID +static char rcsid[] = "$Id: bits.c,v 1.1 2002/08/18 00:59:21 hpa 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)); +/* 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--) { + put_byte(*buf++); + } +} diff --git a/usr/gzip/deflate.c b/usr/gzip/deflate.c new file mode 100644 index 0000000..1db44fd --- /dev/null +++ b/usr/gzip/deflate.c @@ -0,0 +1,759 @@ +/* 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" + +#ifdef RCSID +static char rcsid[] = "$Id: deflate.c,v 1.1 2002/08/18 00:59:21 hpa 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 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 strstart; /* start of string to insert */ + unsigned 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 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. This mechanism is used only for compression + * levels >= 4. + */ +#define max_insert_length max_lazy_match +/* Insert new strings in the hash table only if the match length + * is not greater than this length. This saves time but degrades compression. + * max_insert_length is used only for compression levels <= 3. + */ + +local int compr_level; +/* compression level (1..9) */ + +unsigned 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 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, 8, 4}, /* maximum speed, no lazy matches */ +/* 2 */ {4, 5, 16, 8}, +/* 3 */ {4, 6, 32, 32}, + +/* 4 */ {4, 4, 16, 16}, /* lazy matches */ +/* 5 */ {8, 16, 32, 32}, +/* 6 */ {8, 16, 128, 128}, +/* 7 */ {8, 32, 128, 256}, +/* 8 */ {32, 128, 258, 1024}, +/* 9 */ {32, 258, 258, 4096}}; /* maximum compression */ + +/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4 + * For deflate_fast() (levels <= 3) good is ignored and lazy has a different + * meaning. + */ + +#define EQUAL 0 +/* result of memcmp for equal strings */ + +/* =========================================================================== + * Prototypes for local functions. + */ +local void fill_window OF((void)); +local ulg deflate_fast 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"); + compr_level = pack_level; + + /* Initialize the hash table. */ + memzero((char*)head, HASH_SIZE*sizeof(*head)); + + /* 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. This + * function does not perform lazy evaluationof matches and inserts + * new strings in the dictionary only for unmatched strings or for short + * matches. It is used only for the fast compression options. + */ +local ulg deflate_fast() +{ + 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; + + /* Insert new strings in the hash table only if the match length + * is not too large. This saves time but degrades compression. + */ + if (match_length <= max_insert_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 be emitted as literals. + */ + } while (--match_length != 0); + strstart++; + } else { + strstart += match_length; + match_length = 0; + ins_h = window[strstart]; + UPDATE_HASH(ins_h, window[strstart+1]); +#if MIN_MATCH != 3 + Call UPDATE_HASH() MIN_MATCH-3 more times +#endif + } + } else { + /* No match, output a literal byte */ + Tracevv((stderr,"%c",window[strstart])); + 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 */ +} + +/* =========================================================================== + * 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 + + if (compr_level <= 3) return deflate_fast(); /* optimized for speed */ + + /* 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 */ +} diff --git a/usr/gzip/gzip.c b/usr/gzip/gzip.c new file mode 100644 index 0000000..d0c7e00 --- /dev/null +++ b/usr/gzip/gzip.c @@ -0,0 +1,1215 @@ +/* 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 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. + * + * Using gz on MSDOS would create too many file name conflicts. For + * example, foo.txt -> foo.tgz (.tgz must be reserved as shorthand for + * tar.gz). Similarly, foo.dir and foo.doc would both be mapped to foo.dgz. + * I also considered 12345678.txt -> 12345txt.gz but this truncates the name + * too heavily. There is no ideal solution given the MSDOS 8+3 limitation. + * + * For the meaning of all compilation flags, see comments in Makefile.in. + */ + +#ifdef RCSID +static char rcsid[] = "$Id: gzip.c,v 1.3 2005/02/12 21:03:28 olh Exp $"; +#endif + +#include <ctype.h> +#include <sys/types.h> +#include <signal.h> +#include <sys/stat.h> +#include <errno.h> + +#include "tailor.h" +#include "gzip.h" +#include "revision.h" + +#include <time.h> +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> + +#include <utime.h> + +typedef void (*sig_type) OF((int)); + +#define RW_USER (S_IRUSR | S_IWUSR) /* creation mode for open() */ + +#ifndef MAX_PATH_LEN +# define MAX_PATH_LEN 1024 /* max pathname length */ +#endif + + /* 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); +DECLARE(ush, tab_prefix, 1L<<BITS); + + /* local variables */ + +#ifndef SUPPORT_ZIP +#define decompress 1 +#else +int level = 6; /* compression level */ +#endif + +int to_stdout; /* output to stdout (-c) */ +#ifdef decompress +int decompress_wanted; +#else +int decompress; /* decompress (-d) */ +#define decompress_wanted decompress +#endif +int force; /* don't ask questions, compress links (-f) */ +int no_name = -1; /* don't save or restore the original file name */ +int no_time = -1; /* don't save or restore the original file time */ +int verbose; /* be verbose (-v) */ +int quiet; /* be very quiet (-q) */ +int test; /* test .gz file integrity */ +int foreground; /* set if program run in foreground */ +char *progname; /* program name */ +int method = DEFLATED;/* compression method */ +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 */ +time_t 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 header_bytes; /* number of bytes in gzip header */ +long bytes_in; /* number of input bytes */ +long bytes_out; /* number of output bytes */ +long total_in; /* input bytes for all files */ +long total_out; /* output bytes for all files */ +char ifname[MAX_PATH_LEN]; /* input file name */ +char ofname[MAX_PATH_LEN]; /* output file name */ +int remove_ofname; /* 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 */ + +/* 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 void shorten_name OF((char *name)); +local int get_method OF((void)); +local int check_ofname OF((void)); +local void copy_stat OF((struct stat *ifstat)); +local void do_exit OF((int exitcode)); + int main OF((int argc, char **argv)); +int (*work) OF((int infile, int outfile)) +#ifdef SUPPORT_ZIP + = zip; /* function to call */ +#else + = unzip; +#endif +local void reset_times OF((char *name, struct stat *statb)); + +#define strequ(s1, s2) (strcmp((s1),(s2)) == 0) + +/* ======================================================================== */ +local void usage() +{ + fprintf(stderr, "usage: %s [-cdfhlLnNtvV19] [-S suffix] [file ...]\n", + progname); +} + +/* ======================================================================== */ +local void help() +{ + static char *help_msg[] = { + " -c --stdout write on standard output, keep original files unchanged", + " -d --decompress decompress", + " -f --force force overwrite of output file and compress links", + " -h --help give this help", + " -L --license display software license", +#ifdef UNDOCUMENTED + " -m --no-time do not save or restore the original modification time", + " -M --time save or restore the original modification time", +#endif + " -n --no-name do not save or restore the original name and time stamp", + " -N --name save or restore the original name and time stamp", + " -q --quiet suppress all warnings", + " -S .suf --suffix .suf use suffix .suf on compressed files", + " -t --test test compressed file integrity", + " -v --verbose verbose mode", + " -V --version display version number", +#ifdef SUPPORT_ZIP + " -1 --fast compress faster", + " -9 --best compress better", + " file... files to (de)compress. If none given, use standard input.", +#else + " file... files to decompress. If none given, use standard input.", +#endif + 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: UTIME STDC_HEADERS" +#ifndef SUPPORT_ZIP + " DECOMPRESS_ONLY" +#endif + "\n"); +} + +/* ======================================================================== */ +int main (argc, argv) + int argc; + char **argv; +{ + int file_count; /* number of files to precess */ + int optc; /* current option */ + + progname = basename(argv[0]); + + /* Add options in GZIP environment variable if there is one */ + env = add_envopt(&argc, &argv, OPTIONS_VAR); + if (env != NULL) args = argv; + + foreground = sysv_signal(SIGINT, SIG_IGN) != SIG_IGN; + if (foreground) { + (void) sysv_signal(SIGINT, (sig_type)abort_gzip); + } +#ifdef SIGTERM + if (sysv_signal(SIGTERM, SIG_IGN) != SIG_IGN) { + (void) sysv_signal(SIGTERM, (sig_type)abort_gzip); + } +#endif +#ifdef SIGHUP + if (sysv_signal(SIGHUP, SIG_IGN) != SIG_IGN) { + (void) sysv_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_wanted = 1; + } + if (strequ(progname+1, "cat") /* zcat, pcat, gcat */ + || strequ(progname, "gzcat")) { /* gzcat */ + decompress_wanted = 1; + to_stdout = 1; + } +#endif + + strncpy(z_suffix, Z_SUFFIX, sizeof(z_suffix)-1); + z_len = strlen(z_suffix); + + while ((optc = getopt(argc, argv, "cdfhH?LmMnNqrS:tvV123456789")) != EOF) { + switch (optc) { + case 'c': + to_stdout = 1; break; + case 'd': + decompress_wanted = 1; + break; + case 'f': + force++; break; + case 'h': case 'H': case '?': + help(); do_exit(OK); break; + case 'L': + license(); do_exit(OK); break; + case 'm': /* undocumented, may change later */ + no_time = 1; break; + case 'M': /* undocumented, may change later */ + no_time = 0; break; + case 'n': + no_name = no_time = 1; break; + case 'N': + no_name = no_time = 0; break; + case 'q': + quiet = 1; verbose = 0; break; + case 'S': + z_len = strlen(optarg); + strcpy(z_suffix, optarg); + break; + case 't': + test = to_stdout = 1; + decompress_wanted = 1; + break; + case 'v': + verbose++; quiet = 0; break; + case 'V': + version(); do_exit(OK); break; +#ifdef SUPPORT_ZIP + case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + level = optc - '0'; + break; +#endif + default: + /* Error message already emitted by getopt_long. */ + usage(); + do_exit(ERROR); + } + } /* loop on all arguments */ + +#ifndef SUPPORT_ZIP + if (!decompress_wanted) { + fprintf(stderr, "%s: this version does not support compression\n", + progname); + do_exit(ERROR); + } +#endif + + /* By default, save name and timestamp on compression but do not + * restore them on decompression. + */ + if (no_time < 0) no_time = decompress; + if (no_name < 0) no_name = decompress; + + file_count = argc - optind; + + if ((z_len == 0 && !decompress) || z_len > MAX_SUFFIX) { + fprintf(stderr, "%s: incorrect suffix '%s'\n", + progname, optarg); + do_exit(ERROR); + } + + /* 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); + ALLOC(ush, tab_prefix, 1L<<BITS); + + /* And get to work */ + if (file_count != 0) { + 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); + } + + strcpy(ifname, "stdin"); + strcpy(ofname, "stdout"); + + /* Get the time stamp on the input file. */ + time_stamp = 0; /* time unknown by default */ + + if (!no_time) { + if (fstat(fileno(stdin), &istat) != 0) { + error("fstat(stdin)"); + } + time_stamp = istat.st_mtime; + } + 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(); + 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(); + if (method < 0) return; /* error message already emitted */ + bytes_out = 0; /* required for length check */ + } + + if (verbose) { + if (test) { + fprintf(stderr, " OK\n"); + + } else if (!decompress) { + display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in, stderr); + fprintf(stderr, "\n"); +#ifdef DISPLAY_STDIN_RATIO + } else { + display_ratio(bytes_out-(bytes_in-header_bytes), bytes_out,stderr); + fprintf(stderr, "\n"); +#endif + } + } +} + +/* ======================================================================== + * Compress or decompress the given file + */ +local void treat_file(iname) + char *iname; +{ + /* Accept "-" as synonym for stdin */ + if (strequ(iname, "-")) { + int cflag = to_stdout; + treat_stdin(); + to_stdout = cflag; + return; + } + + /* 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)) { + 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 = no_time ? 0 : istat.st_mtime; + + /* Generate output file name. For -r and (-t or -l), skip files + * without a valid gzip suffix (check done in make_ofname). + */ + if (to_stdout && !test) { + 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, !decompress ? O_RDONLY : O_RDONLY, + 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(); /* 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 (!decompress && save_orig_name && !verbose && !quiet) { + fprintf(stderr, "%s: %s compressed to %s\n", + progname, ifname, ofname); + } + } + /* Keep the name even if not truncated except with --no-name: */ + if (!save_orig_name) save_orig_name = !no_name; + + 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(); + 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,stderr); + } else { + display_ratio(bytes_in-(bytes_out-header_bytes), bytes_in, stderr); + } + 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." + * Sets save_orig_name to true if the file name has been truncated. + * 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 flags = O_WRONLY | O_CREAT | O_EXCL; + + for (;;) { + /* Make sure that ofname is not an existing file */ + 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; + } + close(ofd); + unlink(ofname); + shorten_name(ofname); + } +} + +/* ======================================================================== + * 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 (!to_stdout && !force) { + return lstat(name, sbuf); + } + 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. + * On systems allowing multiple versions of the same file (such as VMS), + * this function removes any version suffix in the given name. + */ +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", + 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); + } + 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; + + 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 (after removing any + * version number for VMS). + */ + s = get_suffix(ifname); + if (s != NULL) { + perror(ifname); /* ifname already has z suffix and does not exist */ + exit_code = ERROR; + return ERROR; + } + ilen = strlen(ifname); + if (strequ(z_suffix, ".gz")) suf++; + + /* Search for all suffixes */ + do { + s = *suf; + strcat(ifname, s); + if (do_stat(ifname, sbuf) == 0) return OK; + ifname[ilen] = '\0'; + } while (*++suf != NULL); + + /* No suffix found, complain using z_suffix: */ + strcat(ifname, z_suffix); + perror(ifname); + exit_code = ERROR; + return ERROR; +} + +/* ======================================================================== + * Generate ofname given ifname. Return OK, or WARNING if file must be skipped. + * Sets save_orig_name to true if the file name has been truncated. + */ +local int make_ofname() +{ + char *suff; /* ofname z suffix */ + + strcpy(ofname, ifname); + /* strip a version number if any and get the gzip suffix if present: */ + suff = get_suffix(ofname); + + if (decompress) { + if (suff == NULL) { + /* Whith -t or -l, try all files (even without .gz suffix) + * except with -r (behave as with just -dr). + */ + if (test) return OK; + + /* Avoid annoying messages with -r */ + if (verbose || !quiet) { + 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 the z suffix */ + } + /* 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 || !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; + 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. + * Updates time_stamp if there is one and --no-time is not used. + * 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() +{ + uch flags; /* compression flags */ + char magic[2]; /* magic header */ + ulg stamp; /* time stamp */ + + /* If --force and --stdout, zcat == cat, so do not complain about + * premature end of file: use try_byte instead of get_byte. + */ + if (force && to_stdout) { + magic[0] = (char)try_byte(); + magic[1] = (char)try_byte(); + /* If try_byte returned EOF, magic[1] == 0xff */ + } else { + magic[0] = (char)get_byte(); + magic[1] = (char)get_byte(); + } + 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) { + + method = (int)get_byte(); + if (method != DEFLATED) { + fprintf(stderr, + "%s: %s: unknown method %d -- get newer version of gzip\n", + progname, ifname, method); + exit_code = ERROR; + return -1; + } + work = unzip; + 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; + } + stamp = (ulg)get_byte(); + stamp |= ((ulg)get_byte()) << 8; + stamp |= ((ulg)get_byte()) << 16; + stamp |= ((ulg)get_byte()) << 24; + if (stamp != 0 && !no_time) time_stamp = stamp; + + (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 (no_name || to_stdout || part_nb > 1) { + /* Discard the old name */ + char c; /* dummy used for NeXTstep 3.0 cc optimizer bug */ + do {c=get_byte();} while (c != 0); + } 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"); + } + } + } /* no_name || 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 (force && to_stdout) { /* pass input unchanged */ + method = STORED; + work = copy; + inptr = 0; + 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: decompression OK, 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; +} + +/* ======================================================================== + * Shorten the given name by one character, or replace a .tar extension + * with .tgz. Truncate the last part of the name which is longer than + * MIN_PART characters: 1234.678.012.gz -> 123.678.012.gz. If the name + * has only parts shorter than MIN_PART truncate the longest part. + * For decompression, just remove the last character of the name. + * + * IN assertion: for compression, the suffix of the given name is z_suffix. + */ +local void shorten_name(name) + char *name; +{ + int len; /* length of name without z_suffix */ + char *trunc = NULL; /* character to be truncated */ + int plen; /* current part length */ + int min_part = MIN_PART; /* current minimum part length */ + char *p; + + len = strlen(name); + if (decompress) { + if (len <= 1) error("name too short"); + name[len-1] = '\0'; + return; + } + p = get_suffix(name); + if (p == NULL) error("can't recover suffix\n"); + *p = '\0'; + save_orig_name = 1; + + /* compress 1234567890.tar to 1234567890.tgz */ + if (len > 4 && strequ(p-4, ".tar")) { + strcpy(p-4, ".tgz"); + return; + } + /* Try keeping short extensions intact: + * 1234.678.012.gz -> 123.678.012.gz + */ + do { + p = strrchr(name, PATH_SEP); + p = p ? p+1 : name; + while (*p) { + plen = strcspn(p, "."); + p += plen; + if (plen > min_part) trunc = p-1; + if (*p) p++; + } + } while (trunc == NULL && --min_part != 0); + + if (trunc != NULL) { + do { + trunc[0] = trunc[1]; + } while (*trunc++); + trunc--; + } else { + trunc = strrchr(name, '.'); + if (trunc == NULL) error("internal error in shorten_name"); + if (trunc[1] == '\0') trunc--; /* force truncation */ + } + strcpy(trunc, z_suffix); +} + +/* ======================================================================== + * 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() +{ + struct stat ostat; /* stat for ofname */ + +#ifdef ENAMETOOLONG + /* Check for strictly conforming Posix systems (which return ENAMETOOLONG + * instead of silently truncating filenames). + */ + errno = 0; + while (stat(ofname, &ostat) != 0) { + if (errno != ENAMETOOLONG) return 0; /* ofname does not exist */ + shorten_name(ofname); + } +#else + if (stat(ofname, &ostat) != 0) return 0; +#endif + /* Check for name truncation on existing file. Do this even on systems + * defining ENAMETOOLONG, because on most systems the strict Posix + * behavior is disabled by default (silent name truncation allowed). + */ + if (!decompress && name_too_long(ofname, &ostat)) { + shorten_name(ofname); + if (stat(ofname, &ostat) != 0) return 0; + } + + /* Check that the input and output files are different (could be + * the same by name truncation or links). + */ + if (same_file(&istat, &ostat)) { + if (strequ(ifname, ofname)) { + fprintf(stderr, "%s: %s: cannot %scompress onto itself\n", + progname, ifname, decompress ? "de" : ""); + } else { + 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) { +#if 0 + 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)? "); + (void)fgets(response, sizeof(response)-1, stdin); + } + if (tolow(*response) != 'y') { + fprintf(stderr, "\tnot overwritten\n"); +#endif + if (exit_code == OK) exit_code = WARNING; + return ERROR; +#if 0 + } +#endif + } + (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; +{ + 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); + } +} + + +/* ======================================================================== + * Copy modes, times, ownership from input file to output file. + * IN assertion: to_stdout is false. + */ +local void copy_stat(ifstat) + struct stat *ifstat; +{ + if (decompress && time_stamp != 0 && ifstat->st_mtime != time_stamp) { + ifstat->st_mtime = time_stamp; + if (verbose > 1) { + fprintf(stderr, "%s: time stamp restored\n", ofname); + } + } + reset_times(ofname, ifstat); + + /* Copy the protection modes */ + if (chmod(ofname, ifstat->st_mode & 07777)) { + WARN((stderr, "%s: ", progname)); + if (!quiet) perror(ofname); + } + + chown(ofname, ifstat->st_uid, ifstat->st_gid); /* Copy ownership */ + + 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); + } +} + +/* ======================================================================== + * Free all dynamically allocated variables and exit with the given code. + */ +local void do_exit(exitcode) + int exitcode; +{ + static int in_exit = 0; + + if (in_exit) exit(exitcode); + in_exit = 1; + if (env != NULL) free(env), env = NULL; + if (args != NULL) free((char*)args), args = NULL; + FREE(inbuf); + FREE(outbuf); + FREE(d_buf); + FREE(window); + FREE(tab_prefix); + exit(exitcode); +} + +/* ======================================================================== + * Signal and error handler. + */ +void abort_gzip() +{ + if (remove_ofname) { + close(ofd); + unlink (ofname); + } + do_exit(ERROR); +} diff --git a/usr/gzip/gzip.h b/usr/gzip/gzip.h new file mode 100644 index 0000000..7cd2fbd --- /dev/null +++ b/usr/gzip/gzip.h @@ -0,0 +1,298 @@ +/* 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 and io functions are used + * too often + */ +#include <stdio.h> +#include <string.h> +#define memzero(s, n) memset ((voidp)(s), 0, (n)) + +#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 +#define LZHED 3 +/* methods 4 to 7 reserved */ +#define DEFLATED 8 +#define MAX_METHODS 9 +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 prefix_len + * unlzh: left+right window c_table inbuf c_len + * 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 time_t 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 PACK_MAGIC "\037\036" /* Magic header for packed files */ +#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 LZH_MAGIC "\037\240" /* Magic header for SCO LZH Compress files*/ +#define PKZIP_MAGIC "\120\113\003\004" /* Magic header for pkzip 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(0)) +#define try_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf(1)) + +/* 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 gzip.c */ +void 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 int copy OF((int in, int out)); +extern ulg updcrc OF((uch *s, unsigned n)); +extern void clear_bufs OF((void)); +extern int fill_inbuf OF((int eof_ok)); +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 void make_simple_name OF((char *name)); +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, FILE *file)); +extern voidp xmalloc OF((unsigned int size)); + + /* in inflate.c */ +extern int inflate OF((void)); + +/* stuff from lzw.h */ +#ifndef BITS +# define BITS 16 +#endif diff --git a/usr/gzip/inflate.c b/usr/gzip/inflate.c new file mode 100644 index 0000000..a540538 --- /dev/null +++ b/usr/gzip/inflate.c @@ -0,0 +1,950 @@ +/* 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. + */ + +#ifdef RCSID +static char rcsid[] = "$Id: inflate.c,v 1.1 2002/08/18 00:59:21 hpa Exp $"; +#endif + +#include <sys/types.h> +#include <stdlib.h> + +#include "tailor.h" +#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(), 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 */ + p++; /* Can't combine with above line (Solaris bug) */ + } 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 ? (unsigned)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/usr/gzip/revision.h b/usr/gzip/revision.h new file mode 100644 index 0000000..736020b --- /dev/null +++ b/usr/gzip/revision.h @@ -0,0 +1,11 @@ +/* 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 "1.2.4" +#define PATCHLEVEL 0 +#define REVDATE "18 Aug 93" + +/* $Id: revision.h,v 1.1 2002/08/18 00:59:21 hpa Exp $ */ diff --git a/usr/gzip/tailor.h b/usr/gzip/tailor.h new file mode 100644 index 0000000..849e589 --- /dev/null +++ b/usr/gzip/tailor.h @@ -0,0 +1,50 @@ +/* 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 1.1 2002/08/18 00:59:21 hpa Exp $ */ + + /* Common defaults */ + +#ifndef OS_CODE +# define OS_CODE 0x03 /* assume Unix */ +#endif + +#define PATH_SEP '/' + +#ifndef casemap +# define casemap(c) (c) +#endif + +#ifndef OPTIONS_VAR +# define OPTIONS_VAR "GZIP" +#endif + +#ifndef Z_SUFFIX +# define Z_SUFFIX ".gz" +#endif + +#define MAX_SUFFIX 30 + +#ifndef MIN_PART +# define MIN_PART 3 + /* keep at least MIN_PART chars between dots in a file name. */ +#endif + +#ifndef RECORD_IO +# define RECORD_IO 0 +#endif + +#ifndef get_char +# define get_char() get_byte() +#endif + +#ifndef put_char +# define put_char(c) put_byte(c) +#endif diff --git a/usr/gzip/trees.c b/usr/gzip/trees.c new file mode 100644 index 0000000..75efc97 --- /dev/null +++ b/usr/gzip/trees.c @@ -0,0 +1,1075 @@ +/* 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 "tailor.h" +#include "gzip.h" + +#ifdef RCSID +static char rcsid[] = "$Id: trees.c,v 1.1 2002/08/18 00:59:21 hpa 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 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 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 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 dyn_ltree[HEAP_SIZE]; /* literal and length tree */ +local ct_data dyn_dtree[2*D_CODES+1]; /* distance tree */ + +local ct_data 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 static_dtree[D_CODES]; +/* The static distance tree. (Actually a trivial tree since all codes use + * 5 bits.) + */ + +local ct_data bl_tree[2*BL_CODES+1]; +/* Huffman tree for the bit lengths */ + +typedef struct tree_desc { + ct_data *dyn_tree; /* the dynamic tree */ + ct_data *static_tree; /* corresponding static tree or NULL */ + int *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 l_desc = +{dyn_ltree, static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS, 0}; + +local tree_desc d_desc = +{dyn_dtree, static_dtree, extra_dbits, 0, D_CODES, MAX_BITS, 0}; + +local tree_desc bl_desc = +{bl_tree, (ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS, 0}; + + +local ush bl_count[MAX_BITS+1]; +/* number of codes at each bit length for an optimal tree */ + +local uch 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 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 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 base_length[LENGTH_CODES]; +/* First normalized length for each code (0 = MIN_MATCH) */ + +local int 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 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 strstart; /* window offset of current string */ + +/* =========================================================================== + * Local (static) routines in this file. + */ + +local void init_block OF((void)); +local void pqdownheap OF((ct_data *tree, int k)); +local void gen_bitlen OF((tree_desc *desc)); +local void gen_codes OF((ct_data *tree, int max_code)); +local void build_tree OF((tree_desc *desc)); +local void scan_tree OF((ct_data *tree, int max_code)); +local void send_tree OF((ct_data *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 *ltree, ct_data *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 *)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 *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 *desc; /* the tree descriptor */ +{ + ct_data *tree = desc->dyn_tree; + int *extra = desc->extra_bits; + int base = desc->extra_base; + int max_code = desc->max_code; + int max_length = desc->max_length; + ct_data *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 *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 *desc; /* the tree descriptor */ +{ + ct_data *tree = desc->dyn_tree; + ct_data *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 *)desc); + + /* The field len is now set, we can generate the bit codes */ + gen_codes ((ct_data *)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 *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 *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 *)dyn_ltree, l_desc.max_code); + scan_tree((ct_data *)dyn_dtree, d_desc.max_code); + + /* Build the bit length tree: */ + build_tree((tree_desc *)(&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 *)dyn_ltree, lcodes-1); /* send the literal tree */ + Tracev((stderr, "\nlit tree: sent %ld", bits_sent)); + + send_tree((ct_data *)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 *)(&l_desc)); + Tracev((stderr, "\nlit data: dyn %ld, stat %ld", opt_len, static_len)); + + build_tree((tree_desc *)(&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 *)static_ltree, (ct_data *)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 *)dyn_ltree, (ct_data *)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 *ltree; /* literal tree */ + ct_data *dtree; /* distance tree */ +{ + unsigned dist; /* distance of matched string */ + int lc; /* match length or unmatched char (if dist == 0) */ + unsigned lx = 0; /* running index in l_buf */ + unsigned 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/usr/gzip/unzip.c b/usr/gzip/unzip.c new file mode 100644 index 0000000..c8e14a3 --- /dev/null +++ b/usr/gzip/unzip.c @@ -0,0 +1,77 @@ +/* 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 format. + Only the first entry is extracted, and it has to be + either deflated or stored. + */ + +#ifdef RCSID +static char rcsid[] = "$Id: unzip.c,v 1.1 2002/08/18 00:59:21 hpa Exp $"; +#endif + +#include "tailor.h" +#include "gzip.h" + +/* =========================================================================== + * Unzip in to out. This routine works on gzip files only. + * + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets inptr to insize-1 included. + * The magic header has already been checked. The output buffer is cleared. + */ +int unzip(in, out) + int in, out; /* input and output file descriptors */ +{ + ulg orig_crc = 0; /* original crc */ + ulg orig_len = 0; /* original uncompressed length */ + int n; + uch buf[8]; /* extended local header */ + + ifd = in; + ofd = out; + + updcrc(NULL, 0); /* initialize crc */ + + /* Decompress */ + if (method == DEFLATED) { + + int res = inflate(); + + if (res == 3) { + error("out of memory"); + } else if (res != 0) { + error("invalid compressed data--format violated"); + } + + } else { + error("internal error, invalid method"); + } + + /* Get the crc and original length */ + /* crc32 (see algorithm.doc) + * uncompressed input size modulo 2^32 + */ + for (n = 0; n < 8; n++) { + buf[n] = (uch)get_byte(); /* may cause an error if EOF */ + } + orig_crc = LG(buf); + orig_len = LG(buf+4); + + /* Validate decompression */ + if (orig_crc != updcrc(outbuf, 0)) { + error("invalid compressed data--crc error"); + } + if (orig_len != (ulg)bytes_out) { + error("invalid compressed data--length error"); + } + + return OK; +} diff --git a/usr/gzip/util.c b/usr/gzip/util.c new file mode 100644 index 0000000..22ff6e5 --- /dev/null +++ b/usr/gzip/util.c @@ -0,0 +1,372 @@ +/* util.c -- utility functions for gzip support + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifdef RCSID +static char rcsid[] = "$Id: util.c,v 1.1 2002/08/18 00:59:21 hpa Exp $"; +#endif + +#include <ctype.h> +#include <errno.h> +#include <sys/types.h> + +#include "tailor.h" + +#include <unistd.h> +#include <fcntl.h> +#include <stdlib.h> + +#include "gzip.h" + +extern ulg crc_32_tab[]; /* crc table, defined below */ + +/* =========================================================================== + * Copy input to output unchanged: zcat == cat with --force. + * IN assertion: insize bytes have already been read in inbuf. + */ +int copy(in, out) + int in, out; /* input and output file descriptors */ +{ + errno = 0; + while (insize != 0 && (int)insize != EOF) { + write_buf(out, (char*)inbuf, insize); + bytes_out += insize; + insize = read(in, (char*)inbuf, INBUFSIZ); + } + if ((int)insize == EOF && errno != 0) { + read_error(); + } + bytes_in = bytes_out; + return OK; +} + +/* =========================================================================== + * 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. + */ +int fill_inbuf(eof_ok) + int eof_ok; /* set if EOF acceptable as a result */ +{ + 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) { + if (eof_ok) return EOF; + 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; + if (casemap('A') == 'a') strlwr(fname); + return fname; +} + +/* ======================================================================== + * 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); + 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 the given stream on 6 characters. + */ +void display_ratio(num, den, file) + long num; + long den; + FILE *file; +{ + long ratio; /* 1000 times the compression ratio */ + char sign; + + 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) { + sign = '-'; + ratio = -ratio; + } else { + sign = ' '; + } + fprintf(file, "%c%2ld.%1ld%%", sign, 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/usr/gzip/zip.c b/usr/gzip/zip.c new file mode 100644 index 0000000..d0394c2 --- /dev/null +++ b/usr/gzip/zip.c @@ -0,0 +1,110 @@ +/* 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. + */ + +#ifdef RCSID +static char rcsid[] = "$Id: zip.c,v 1.1 2002/08/18 00:59:21 hpa Exp $"; +#endif + +#include <ctype.h> +#include <sys/types.h> +#include <unistd.h> +#include <fcntl.h> + +#include "tailor.h" +#include "gzip.h" + +local ulg crc; /* crc on uncompressed file data */ + +/* =========================================================================== + * 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; +} |