mirrors/bzip2
0
0
Fork 0
mirror of git://sourceware.org/git/bzip2.git synced 2024-11-23 11:43:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

bzip2-0.9.0c

Browse Source
This commit is contained in:
Julian Seward 1998-08-23 22:13:13 +02:00
parent 1eb67a9d8f
commit 977101ad5f
33 changed files with 8337 additions and 4109 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
ALGORITHMS
View File

@ -1,47 +0,0 @@
Bzip2 is not research work, in the sense that it doesn't present any
new ideas. Rather, it's an engineering exercise based on existing
ideas.
Four documents describe essentially all the ideas behind bzip2:
Michael Burrows and D. J. Wheeler:
"A block-sorting lossless data compression algorithm"
10th May 1994.
Digital SRC Research Report 124.
ftp://ftp.digital.com/pub/DEC/SRC/research-reports/SRC-124.ps.gz
Daniel S. Hirschberg and Debra A. LeLewer
"Efficient Decoding of Prefix Codes"
Communications of the ACM, April 1990, Vol 33, Number 4.
You might be able to get an electronic copy of this
from the ACM Digital Library.
David J. Wheeler
Program bred3.c and accompanying document bred3.ps.
This contains the idea behind the multi-table Huffman
coding scheme.
ftp://ftp.cl.cam.ac.uk/pub/user/djw3/
Jon L. Bentley and Robert Sedgewick
"Fast Algorithms for Sorting and Searching Strings"
Available from Sedgewick's web page,
www.cs.princeton.edu/~rs
The following paper gives valuable additional insights into the
algorithm, but is not immediately the basis of any code
used in bzip2.
Peter Fenwick:
Block Sorting Text Compression
Proceedings of the 19th Australasian Computer Science Conference,
Melbourne, Australia. Jan 31 - Feb 2, 1996.
ftp://ftp.cs.auckland.ac.nz/pub/peter-f/ACSC96paper.ps
All three are well written, and make fascinating reading. If you want
to modify bzip2 in any non-trivial way, I strongly suggest you obtain,
read and understand these papers.
I am much indebted to the various authors for their help, support and
advice.

45
CHANGES Normal file
View File

@ -0,0 +1,45 @@
0.9.0
~~~~~
First version.
0.9.0a
~~~~~~
Removed 'ranlib' from Makefile, since most modern Unix-es
don't need it, or even know about it.
0.9.0b
~~~~~~
Fixed a problem with error reporting in bzip2.c. This does not effect
the library in any way. Problem is: versions 0.9.0 and 0.9.0a (of the
program proper) compress and decompress correctly, but give misleading
error messages (internal panics) when an I/O error occurs, instead of
reporting the problem correctly. This shouldn't give any data loss
(as far as I can see), but is confusing.
Made the inline declarations disappear for non-GCC compilers.
0.9.0c
~~~~~~
Fixed some problems in the library pertaining to some boundary cases.
This makes the library behave more correctly in those situations. The
fixes apply only to features (calls and parameters) not used by
bzip2.c, so the non-fixedness of them in previous versions has no
effect on reliability of bzip2.c.
In bzlib.c:
* made zero-length BZ_FLUSH work correctly in bzCompress().
* fixed bzWrite/bzRead to ignore zero-length requests.
* fixed bzread to correctly handle read requests after EOF.
* wrong parameter order in call to bzDecompressInit in
bzBuffToBuffDecompress. Fixed.
In compress.c:
* changed setting of nGroups in sendMTFValues() so as to
do a bit better on small files. This _does_ effect
bzip2.c.

360
LICENSE
View File

@ -1,339 +1,39 @@
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.
This program, "bzip2" and associated library "libbzip2", are
copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Preamble
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
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.
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
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.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
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.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
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.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
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.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
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.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0 of 28 June 1998
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.

46
Makefile
View File

@ -1,30 +1,46 @@
CC = gcc
SH = /bin/sh
CC=gcc
CFLAGS=-Wall -O2 -fomit-frame-pointer -fno-strength-reduce
CFLAGS = -O3 -fomit-frame-pointer -funroll-loops
OBJS= blocksort.o \
huffman.o \
crctable.o \
randtable.o \
compress.o \
decompress.o \
bzlib.o
all: lib bzip2 test
all:
cat words0
$(CC) $(CFLAGS) -o bzip2 bzip2.c
bzip2: lib
$(CC) $(CFLAGS) -c bzip2.c
$(CC) $(CFLAGS) -o bzip2 bzip2.o -L. -lbz2
$(CC) $(CFLAGS) -o bzip2recover bzip2recover.c
rm -f bunzip2
ln -s ./bzip2 ./bunzip2
cat words1
lib: $(OBJS)
rm -f libbz2.a
ar clq libbz2.a $(OBJS)
test: bzip2
@cat words1
./bzip2 -1 < sample1.ref > sample1.rb2
./bzip2 -2 < sample2.ref > sample2.rb2
./bunzip2 < sample1.bz2 > sample1.tst
./bunzip2 < sample2.bz2 > sample2.tst
cat words2
./bzip2 -d < sample1.bz2 > sample1.tst
./bzip2 -d < sample2.bz2 > sample2.tst
@cat words2
cmp sample1.bz2 sample1.rb2
cmp sample2.bz2 sample2.rb2
cmp sample1.tst sample1.ref
cmp sample2.tst sample2.ref
cat words3
@cat words3
clean:
rm -f bzip2 bunzip2 bzip2recover sample*.tst sample*.rb2
rm -f *.o libbz2.a bzip2 bzip2recover sample1.rb2 sample2.rb2 sample1.tst sample2.tst
.c.o: $*.o bzlib.h bzlib_private.h
$(CC) $(CFLAGS) -c $*.c -o $*.o
tarfile:
tar cvf interim.tar *.c *.h Makefile manual.texi manual.ps LICENSE bzip2.1 bzip2.1.preformatted bzip2.txt words1 words2 words3 sample1.ref sample2.ref sample1.bz2 sample2.bz2 *.html README CHANGES libbz2.def libbz2.dsp dlltest.dsp

228
README
View File

@ -1,194 +1,61 @@
GREETINGS!
This is the README for bzip2, my block-sorting file compressor,
version 0.1.
bzip2 is distributed under the GNU General Public License version 2;
for details, see the file LICENSE. Pointers to the algorithms used
are in ALGORITHMS. Instructions for use are in bzip2.1.preformatted.
Please read all of this file carefully.
This is the README for bzip2, a block-sorting file compressor, version
0.9.0. This version is fully compatible with the previous public
release, bzip2-0.1pl2.
HOW TO BUILD
bzip2-0.9.0 is distributed under a BSD-style license. For details,
see the file LICENSE.
-- for UNIX:
Complete documentation is available in Postscript form (manual.ps)
or html (manual_toc.html). A plain-text version of the manual page is
available as bzip2.txt.
Type `make'. (tough, huh? :-)
This creates binaries "bzip2", and "bunzip2",
which is a symbolic link to "bzip2".
HOW TO BUILD -- UNIX
It also runs four compress-decompress tests to make sure
things are working properly. If all goes well, you should be up &
running. Please be sure to read the output from `make'
just to be sure that the tests went ok.
Type `make'.
To install bzip2 properly:
This creates binaries "bzip2" and "bzip2recover".
-- Copy the binary "bzip2" to a publically visible place,
possibly /usr/bin, /usr/common/bin or /usr/local/bin.
It also runs four compress-decompress tests to make sure things are
working properly. If all goes well, you should be up & running.
Please be sure to read the output from `make' just to be sure that the
tests went ok.
-- In that directory, make "bunzip2" be a symbolic link
To install bzip2 properly:
* Copy the binaries "bzip2" and "bzip2recover" to a publically visible
place, possibly /usr/bin or /usr/local/bin.
* In that directory, make "bunzip2" and "bzcat" be symbolic links
to "bzip2".
-- Copy the manual page, bzip2.1, to the relevant place.
* Copy the manual page, bzip2.1, to the relevant place.
Probably the right place is /usr/man/man1/.
-- for Windows 95 and NT:
For a start, do you *really* want to recompile bzip2?
The standard distribution includes a pre-compiled version
for Windows 95 and NT, `bzip2.exe'.
This executable was created with Jacob Navia's excellent
port to Win32 of Chris Fraser & David Hanson's excellent
ANSI C compiler, "lcc". You can get to it at the pages
of the CS department of Princeton University,
www.cs.princeton.edu.
I have not tried to compile this version of bzip2 with
a commercial C compiler such as MS Visual C, as I don't
have one available.
Note that lcc is designed primarily to be portable and
fast. Code quality is a secondary aim, so bzip2.exe
runs perhaps 40% slower than it could if compiled with
a good optimising compiler.
I compiled a previous version of bzip (0.21) with Borland
C 5.0, which worked fine, and with MS VC++ 2.0, which
didn't. Here is an comment from the README for bzip-0.21.
MS VC++ 2.0's optimising compiler has a bug which, at
maximum optimisation, gives an executable which produces
garbage compressed files. Proceed with caution.
I do not know whether or not this happens with later
versions of VC++.
Edit the defines starting at line 86 of bzip.c to
select your platform/compiler combination, and then compile.
Then check that the resulting executable (assumed to be
called bzip.exe) works correctly, using the SELFTEST.BAT file.
Bearing in mind the previous paragraph, the self-test is
important.
Note that the defines which bzip-0.21 had, to support
compilation with VC 2.0 and BC 5.0, are gone. Windows
is not my preferred operating system, and I am, for the
moment, content with the modestly fast executable created
by lcc-win32.
A manual page is supplied, unformatted (bzip2.1),
preformatted (bzip2.1.preformatted), and preformatted
and sanitised for MS-DOS (bzip2.txt).
If you want to program with the library, you'll need to copy libbz2.a
and bzlib.h to /usr/lib and /usr/include respectively.
HOW TO BUILD -- Windows 95, NT, DOS, Mac, etc.
COMPILATION NOTES
bzip2 should work on any 32 or 64-bit machine. It is known to work
[meaning: it has compiled and passed self-tests] on the
following platform-os combinations:
Intel i386/i486 running Linux 2.0.21
Sun Sparcs (various) running SunOS 4.1.4 and Solaris 2.5
Intel i386/i486 running Windows 95 and NT
DEC Alpha running Digital Unix 4.0
Following the release of bzip-0.21, many people mailed me
from around the world to say they had made it work on all sorts
of weird and wonderful machines. Chances are, if you have
a reasonable ANSI C compiler and a 32-bit machine, you can
get it to work.
The #defines starting at around line 82 of bzip2.c supply some
degree of platform-independance. If you configure bzip2 for some
new far-out platform which is not covered by the existing definitions,
please send me the relevant definitions.
I recommend GNU C for compilation. The code is standard ANSI C,
except for the Unix-specific file handling, so any ANSI C compiler
should work. Note however that the many routines marked INLINE
should be inlined by your compiler, else performance will be very
poor. Asking your compiler to unroll loops gives some
small improvement too; for gcc, the relevant flag is
-funroll-loops.
On a 386/486 machines, I'd recommend giving gcc the
-fomit-frame-pointer flag; this liberates another register for
allocation, which measurably improves performance.
I used the abovementioned lcc compiler to develop bzip2.
I would highly recommend this compiler for day-to-day development;
it is fast, reliable, lightweight, has an excellent profiler,
and is generally excellent. And it's fun to retarget, if you're
into that kind of thing.
If you compile bzip2 on a new platform or with a new compiler,
please be sure to run the four compress-decompress tests, either
using the Makefile, or with the test.bat (MSDOS) or test.cmd (OS/2)
files. Some compilers have been seen to introduce subtle bugs
when optimising, so this check is important. Ideally you should
then go on to test bzip2 on a file several megabytes or even
tens of megabytes long, just to be 110% sure. ``Professional
programmers are paranoid programmers.'' (anon).
It's difficult for me to support compilation on all these platforms.
My approach is to collect binaries for these platforms, and put them
on my web page (http://www.muraroa.demon.co.uk). Look there.
VALIDATION
Correct operation, in the sense that a compressed file can always be
decompressed to reproduce the original, is obviously of paramount
importance. To validate bzip2, I used a modified version of
Mark Nelson's churn program. Churn is an automated test driver
which recursively traverses a directory structure, using bzip2 to
compress and then decompress each file it encounters, and checking
that the decompressed data is the same as the original. As test
material, I used several runs over several filesystems of differing
sizes.
Correct operation, in the sense that a compressed file can always be
decompressed to reproduce the original, is obviously of paramount
importance. To validate bzip2, I used a modified version of Mark
Nelson's churn program. Churn is an automated test driver which
recursively traverses a directory structure, using bzip2 to compress
and then decompress each file it encounters, and checking that the
decompressed data is the same as the original. There are more details
in Section 4 of the user guide.
One set of tests was done on my base Linux filesystem,
410 megabytes in 23,000 files. There were several runs over
this filesystem, in various configurations designed to break bzip2.
That filesystem also contained some specially constructed test
files designed to exercise boundary cases in the code.
This included files of zero length, various long, highly repetitive
files, and some files which generate blocks with all values the same.
The other set of tests was done just with the "normal" configuration,
but on a much larger quantity of data.
Tests are:
Linux FS, 410M, 23000 files
As above, with --repetitive-fast
As above, with -1
Low level disk image of a disk containing
Windows NT4.0; 420M in a single huge file
Linux distribution, incl Slackware,
all GNU sources. 1900M in 2300 files.
Approx ~100M compiler sources and related
programming tools, running under Purify.
About 500M of data in 120 files of around
4 M each. This is raw data from a
biomagnetometer (SQUID-based thing).
Overall, total volume of test data is about
3300 megabytes in 25000 files.
The distribution does four tests after building bzip. These tests
include test decompressions of pre-supplied compressed files, so
they not only test that bzip works correctly on the machine it was
built on, but can also decompress files compressed on a different
machine. This guards against unforseen interoperability problems.
Please read and be aware of the following:
@ -234,14 +101,30 @@ PATENTS:
End of legalities.
WHAT'S NEW IN 0.9.0 (as compared to 0.1pl2) ?
* Approx 10% faster compression, 30% faster decompression
* -t (test mode) is a lot quicker
* Can decompress concatenated compressed files
* Programming interface, so programs can directly read/write .bz2 files
* Less restrictive (BSD-style) licensing
* Flag handling more compatible with GNU gzip
* Much more documentation, i.e., a proper user manual
* Hopefully, improved portability (at least of the library)
I hope you find bzip2 useful. Feel free to contact me at
jseward@acm.org
if you have any suggestions or queries. Many people mailed me with
comments, suggestions and patches after the releases of 0.15 and 0.21,
and the changes in bzip2 are largely a result of this feedback.
I thank you for your comments.
comments, suggestions and patches after the releases of bzip-0.15,
bzip-0.21 and bzip2-0.1pl2, and the changes in bzip2 are largely a
result of this feedback. I thank you for your comments.
At least for the time being, bzip2's "home" is
http://www.muraroa.demon.co.uk.
Julian Seward
jseward@acm.org
Manchester, UK
18 July 1996 (version 0.15)
@ -250,4 +133,5 @@ Manchester, UK
Guildford, Surrey, UK
7 August 1997 (bzip2, version 0.1)
29 August 1997 (bzip2, version 0.1pl2)
23 August 1998 (bzip2, version 0.9.0)

16
README.DOS
View File

@ -1,16 +0,0 @@
As of today (3 March 1998) I've removed the
Win95/NT executables from this distribution, sorry.
You can still get an executable from
http://www.muraroa.demon.co.uk, or (as a last
resort) by mailing me at jseward@acm.org.
The reason for this change of packaging is that it
makes it easier for me to fix problems with specific
executables if they are not included in the main
distribution.
J

709
blocksort.c Normal file
View File

@ -0,0 +1,709 @@
/*-------------------------------------------------------------*/
/*--- Block sorting machinery ---*/
/*--- blocksort.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#include "bzlib_private.h"
/*---------------------------------------------*/
/*--
Compare two strings in block. We assume (see
discussion above) that i1 and i2 have a max
offset of 10 on entry, and that the first
bytes of both block and quadrant have been
copied into the "overshoot area", ie
into the subscript range
[nblock .. nblock+NUM_OVERSHOOT_BYTES-1].
--*/
static __inline__ Bool fullGtU ( UChar* block,
UInt16* quadrant,
UInt32 nblock,
Int32* workDone,
Int32 i1,
Int32 i2
)
{
Int32 k;
UChar c1, c2;
UInt16 s1, s2;
AssertD ( i1 != i2, "fullGtU(1)" );
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
i1++; i2++;
k = nblock;
do {
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
s1 = quadrant[i1];
s2 = quadrant[i2];
if (s1 != s2) return (s1 > s2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
s1 = quadrant[i1];
s2 = quadrant[i2];
if (s1 != s2) return (s1 > s2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
s1 = quadrant[i1];
s2 = quadrant[i2];
if (s1 != s2) return (s1 > s2);
i1++; i2++;
c1 = block[i1];
c2 = block[i2];
if (c1 != c2) return (c1 > c2);
s1 = quadrant[i1];
s2 = quadrant[i2];
if (s1 != s2) return (s1 > s2);
i1++; i2++;
if (i1 >= nblock) i1 -= nblock;
if (i2 >= nblock) i2 -= nblock;
k -= 4;
(*workDone)++;
}
while (k >= 0);
return False;
}
/*---------------------------------------------*/
/*--
Knuth's increments seem to work better
than Incerpi-Sedgewick here. Possibly
because the number of elems to sort is
usually small, typically <= 20.
--*/
static Int32 incs[14] = { 1, 4, 13, 40, 121, 364, 1093, 3280,
9841, 29524, 88573, 265720,
797161, 2391484 };
static void simpleSort ( EState* s, Int32 lo, Int32 hi, Int32 d )
{
Int32 i, j, h, bigN, hp;
Int32 v;
UChar* block = s->block;
UInt32* zptr = s->zptr;
UInt16* quadrant = s->quadrant;
Int32* workDone = &(s->workDone);
Int32 nblock = s->nblock;
Int32 workLimit = s->workLimit;
Bool firstAttempt = s->firstAttempt;
bigN = hi - lo + 1;
if (bigN < 2) return;
hp = 0;
while (incs[hp] < bigN) hp++;
hp--;
for (; hp >= 0; hp--) {
h = incs[hp];
i = lo + h;
while (True) {
/*-- copy 1 --*/
if (i > hi) break;
v = zptr[i];
j = i;
while ( fullGtU ( block, quadrant, nblock, workDone,
zptr[j-h]+d, v+d ) ) {
zptr[j] = zptr[j-h];
j = j - h;
if (j <= (lo + h - 1)) break;
}
zptr[j] = v;
i++;
/*-- copy 2 --*/
if (i > hi) break;
v = zptr[i];
j = i;
while ( fullGtU ( block, quadrant, nblock, workDone,
zptr[j-h]+d, v+d ) ) {
zptr[j] = zptr[j-h];
j = j - h;
if (j <= (lo + h - 1)) break;
}
zptr[j] = v;
i++;
/*-- copy 3 --*/
if (i > hi) break;
v = zptr[i];
j = i;
while ( fullGtU ( block, quadrant, nblock, workDone,
zptr[j-h]+d, v+d ) ) {
zptr[j] = zptr[j-h];
j = j - h;
if (j <= (lo + h - 1)) break;
}
zptr[j] = v;
i++;
if (*workDone > workLimit && firstAttempt) return;
}
}
}
/*---------------------------------------------*/
/*--
The following is an implementation of
an elegant 3-way quicksort for strings,
described in a paper "Fast Algorithms for
Sorting and Searching Strings", by Robert
Sedgewick and Jon L. Bentley.
--*/
#define swap(lv1, lv2) \
{ Int32 tmp = lv1; lv1 = lv2; lv2 = tmp; }
static void vswap ( UInt32* zptr, Int32 p1, Int32 p2, Int32 n )
{
while (n > 0) {
swap(zptr[p1], zptr[p2]);
p1++; p2++; n--;
}
}
static UChar med3 ( UChar a, UChar b, UChar c )
{
UChar t;
if (a > b) { t = a; a = b; b = t; };
if (b > c) { t = b; b = c; c = t; };
if (a > b) b = a;
return b;
}
#define min(a,b) ((a) < (b)) ? (a) : (b)
typedef
struct { Int32 ll; Int32 hh; Int32 dd; }
StackElem;
#define push(lz,hz,dz) { stack[sp].ll = lz; \
stack[sp].hh = hz; \
stack[sp].dd = dz; \
sp++; }
#define pop(lz,hz,dz) { sp--; \
lz = stack[sp].ll; \
hz = stack[sp].hh; \
dz = stack[sp].dd; }
#define SMALL_THRESH 20
#define DEPTH_THRESH 10
/*--
If you are ever unlucky/improbable enough
to get a stack overflow whilst sorting,
increase the following constant and try
again. In practice I have never seen the
stack go above 27 elems, so the following
limit seems very generous.
--*/
#define QSORT_STACK_SIZE 1000
static void qSort3 ( EState* s, Int32 loSt, Int32 hiSt, Int32 dSt )
{
Int32 unLo, unHi, ltLo, gtHi, med, n, m;
Int32 sp, lo, hi, d;
StackElem stack[QSORT_STACK_SIZE];
UChar* block = s->block;
UInt32* zptr = s->zptr;
Int32* workDone = &(s->workDone);
Int32 workLimit = s->workLimit;
Bool firstAttempt = s->firstAttempt;
sp = 0;
push ( loSt, hiSt, dSt );
while (sp > 0) {
AssertH ( sp < QSORT_STACK_SIZE, 1001 );
pop ( lo, hi, d );
if (hi - lo < SMALL_THRESH || d > DEPTH_THRESH) {
simpleSort ( s, lo, hi, d );
if (*workDone > workLimit && firstAttempt) return;
continue;
}
med = med3 ( block[zptr[ lo ]+d],
block[zptr[ hi ]+d],
block[zptr[ (lo+hi)>>1 ]+d] );
unLo = ltLo = lo;
unHi = gtHi = hi;
while (True) {
while (True) {
if (unLo > unHi) break;
n = ((Int32)block[zptr[unLo]+d]) - med;
if (n == 0) { swap(zptr[unLo], zptr[ltLo]); ltLo++; unLo++; continue; };
if (n > 0) break;
unLo++;
}
while (True) {
if (unLo > unHi) break;
n = ((Int32)block[zptr[unHi]+d]) - med;
if (n == 0) { swap(zptr[unHi], zptr[gtHi]); gtHi--; unHi--; continue; };
if (n < 0) break;
unHi--;
}
if (unLo > unHi) break;
swap(zptr[unLo], zptr[unHi]); unLo++; unHi--;
}
AssertD ( unHi == unLo-1, "bad termination in qSort3" );
if (gtHi < ltLo) {
push(lo, hi, d+1 );
continue;
}
n = min(ltLo-lo, unLo-ltLo); vswap(zptr, lo, unLo-n, n);
m = min(hi-gtHi, gtHi-unHi); vswap(zptr, unLo, hi-m+1, m);
n = lo + unLo - ltLo - 1;
m = hi - (gtHi - unHi) + 1;
push ( lo, n, d );
push ( n+1, m-1, d+1 );
push ( m, hi, d );
}
}
/*---------------------------------------------*/
#define BIGFREQ(b) (ftab[((b)+1) << 8] - ftab[(b) << 8])
#define SETMASK (1 << 21)
#define CLEARMASK (~(SETMASK))
static void sortMain ( EState* s )
{
Int32 i, j, k, ss, sb;
Int32 runningOrder[256];
Int32 copy[256];
Bool bigDone[256];
UChar c1, c2;
Int32 numQSorted;
UChar* block = s->block;
UInt32* zptr = s->zptr;
UInt16* quadrant = s->quadrant;
Int32* ftab = s->ftab;
Int32* workDone = &(s->workDone);
Int32 nblock = s->nblock;
Int32 workLimit = s->workLimit;
Bool firstAttempt = s->firstAttempt;
/*--
In the various block-sized structures, live data runs
from 0 to last+NUM_OVERSHOOT_BYTES inclusive. First,
set up the overshoot area for block.
--*/
if (s->verbosity >= 4)
VPrintf0( " sort initialise ...\n" );
for (i = 0; i < BZ_NUM_OVERSHOOT_BYTES; i++)
block[nblock+i] = block[i % nblock];
for (i = 0; i < nblock+BZ_NUM_OVERSHOOT_BYTES; i++)
quadrant[i] = 0;
if (nblock <= 4000) {
/*--
Use simpleSort(), since the full sorting mechanism
has quite a large constant overhead.
--*/
if (s->verbosity >= 4) VPrintf0( " simpleSort ...\n" );
for (i = 0; i < nblock; i++) zptr[i] = i;
firstAttempt = False;
*workDone = workLimit = 0;
simpleSort ( s, 0, nblock-1, 0 );
if (s->verbosity >= 4) VPrintf0( " simpleSort done.\n" );
} else {
numQSorted = 0;
for (i = 0; i <= 255; i++) bigDone[i] = False;
if (s->verbosity >= 4) VPrintf0( " bucket sorting ...\n" );
for (i = 0; i <= 65536; i++) ftab[i] = 0;
c1 = block[nblock-1];
for (i = 0; i < nblock; i++) {
c2 = block[i];
ftab[(c1 << 8) + c2]++;
c1 = c2;
}
for (i = 1; i <= 65536; i++) ftab[i] += ftab[i-1];
c1 = block[0];
for (i = 0; i < nblock-1; i++) {
c2 = block[i+1];
j = (c1 << 8) + c2;
c1 = c2;
ftab[j]--;
zptr[ftab[j]] = i;
}
j = (block[nblock-1] << 8) + block[0];
ftab[j]--;
zptr[ftab[j]] = nblock-1;
/*--
Now ftab contains the first loc of every small bucket.
Calculate the running order, from smallest to largest
big bucket.
--*/
for (i = 0; i <= 255; i++) runningOrder[i] = i;
{
Int32 vv;
Int32 h = 1;
do h = 3 * h + 1; while (h <= 256);
do {
h = h / 3;
for (i = h; i <= 255; i++) {
vv = runningOrder[i];
j = i;
while ( BIGFREQ(runningOrder[j-h]) > BIGFREQ(vv) ) {
runningOrder[j] = runningOrder[j-h];
j = j - h;
if (j <= (h - 1)) goto zero;
}
zero:
runningOrder[j] = vv;
}
} while (h != 1);
}
/*--
The main sorting loop.
--*/
for (i = 0; i <= 255; i++) {
/*--
Process big buckets, starting with the least full.
Basically this is a 4-step process in which we call
qSort3 to sort the small buckets [ss, j], but
also make a big effort to avoid the calls if we can.
--*/
ss = runningOrder[i];
/*--
Step 1:
Complete the big bucket [ss] by quicksorting
any unsorted small buckets [ss, j], for j != ss.
Hopefully previous pointer-scanning phases have already
completed many of the small buckets [ss, j], so
we don't have to sort them at all.
--*/
for (j = 0; j <= 255; j++) {
if (j != ss) {
sb = (ss << 8) + j;
if ( ! (ftab[sb] & SETMASK) ) {
Int32 lo = ftab[sb] & CLEARMASK;
Int32 hi = (ftab[sb+1] & CLEARMASK) - 1;
if (hi > lo) {
if (s->verbosity >= 4)
VPrintf4( " qsort [0x%x, 0x%x] done %d this %d\n",
ss, j, numQSorted, hi - lo + 1 );
qSort3 ( s, lo, hi, 2 );
numQSorted += ( hi - lo + 1 );
if (*workDone > workLimit && firstAttempt) return;
}
}
ftab[sb] |= SETMASK;
}
}
/*--
Step 2:
Deal specially with case [ss, ss]. This establishes the
sorted order for [ss, ss] without any comparisons.
A clever trick, cryptically described as steps Q6b and Q6c
in SRC-124 (aka BW94). This makes it entirely practical to
not use a preliminary run-length coder, but unfortunately
we are now stuck with the .bz2 file format.
--*/
{
Int32 put0, get0, put1, get1;
Int32 sbn = (ss << 8) + ss;
Int32 lo = ftab[sbn] & CLEARMASK;
Int32 hi = (ftab[sbn+1] & CLEARMASK) - 1;
UChar ssc = (UChar)ss;
put0 = lo;
get0 = ftab[ss << 8] & CLEARMASK;
put1 = hi;
get1 = (ftab[(ss+1) << 8] & CLEARMASK) - 1;
while (get0 < put0) {
j = zptr[get0]-1; if (j < 0) j += nblock;
c1 = block[j];
if (c1 == ssc) { zptr[put0] = j; put0++; };
get0++;
}
while (get1 > put1) {
j = zptr[get1]-1; if (j < 0) j += nblock;
c1 = block[j];
if (c1 == ssc) { zptr[put1] = j; put1--; };
get1--;
}
ftab[sbn] |= SETMASK;
}
/*--
Step 3:
The [ss] big bucket is now done. Record this fact,
and update the quadrant descriptors. Remember to
update quadrants in the overshoot area too, if
necessary. The "if (i < 255)" test merely skips
this updating for the last bucket processed, since
updating for the last bucket is pointless.
The quadrant array provides a way to incrementally
cache sort orderings, as they appear, so as to
make subsequent comparisons in fullGtU() complete
faster. For repetitive blocks this makes a big
difference (but not big enough to be able to avoid
randomisation for very repetitive data.)
The precise meaning is: at all times:
for 0 <= i < nblock and 0 <= j <= nblock
if block[i] != block[j],
then the relative values of quadrant[i] and
quadrant[j] are meaningless.
else {
if quadrant[i] < quadrant[j]
then the string starting at i lexicographically
precedes the string starting at j
else if quadrant[i] > quadrant[j]
then the string starting at j lexicographically
precedes the string starting at i
else
the relative ordering of the strings starting
at i and j has not yet been determined.
}
--*/
bigDone[ss] = True;
if (i < 255) {
Int32 bbStart = ftab[ss << 8] & CLEARMASK;
Int32 bbSize = (ftab[(ss+1) << 8] & CLEARMASK) - bbStart;
Int32 shifts = 0;
while ((bbSize >> shifts) > 65534) shifts++;
for (j = 0; j < bbSize; j++) {
Int32 a2update = zptr[bbStart + j];
UInt16 qVal = (UInt16)(j >> shifts);
quadrant[a2update] = qVal;
if (a2update < BZ_NUM_OVERSHOOT_BYTES)
quadrant[a2update + nblock] = qVal;
}
AssertH ( ( ((bbSize-1) >> shifts) <= 65535 ), 1002 );
}
/*--
Step 4:
Now scan this big bucket [ss] so as to synthesise the
sorted order for small buckets [t, ss] for all t != ss.
This will avoid doing Real Work in subsequent Step 1's.
--*/
for (j = 0; j <= 255; j++)
copy[j] = ftab[(j << 8) + ss] & CLEARMASK;
for (j = ftab[ss << 8] & CLEARMASK;
j < (ftab[(ss+1) << 8] & CLEARMASK);
j++) {
k = zptr[j]-1; if (k < 0) k += nblock;
c1 = block[k];
if ( ! bigDone[c1] ) {
zptr[copy[c1]] = k;
copy[c1] ++;
}
}
for (j = 0; j <= 255; j++) ftab[(j << 8) + ss] |= SETMASK;
}
if (s->verbosity >= 4)
VPrintf3( " %d pointers, %d sorted, %d scanned\n",
nblock, numQSorted, nblock - numQSorted );
}
}
/*---------------------------------------------*/
static void randomiseBlock ( EState* s )
{
Int32 i;
BZ_RAND_INIT_MASK;
for (i = 0; i < 256; i++) s->inUse[i] = False;
for (i = 0; i < s->nblock; i++) {
BZ_RAND_UPD_MASK;
s->block[i] ^= BZ_RAND_MASK;
s->inUse[s->block[i]] = True;
}
}
/*---------------------------------------------*/
void blockSort ( EState* s )
{
Int32 i;
s->workLimit = s->workFactor * (s->nblock - 1);
s->workDone = 0;
s->blockRandomised = False;
s->firstAttempt = True;
sortMain ( s );
if (s->verbosity >= 3)
VPrintf3( " %d work, %d block, ratio %5.2f\n",
s->workDone, s->nblock-1,
(float)(s->workDone) / (float)(s->nblock-1) );
if (s->workDone > s->workLimit && s->firstAttempt) {
if (s->verbosity >= 2)
VPrintf0( " sorting aborted; randomising block\n" );
randomiseBlock ( s );
s->workLimit = s->workDone = 0;
s->blockRandomised = True;
s->firstAttempt = False;
sortMain ( s );
if (s->verbosity >= 3)
VPrintf3( " %d work, %d block, ratio %f\n",
s->workDone, s->nblock-1,
(float)(s->workDone) / (float)(s->nblock-1) );
}
s->origPtr = -1;
for (i = 0; i < s->nblock; i++)
if (s->zptr[i] == 0)
{ s->origPtr = i; break; };
AssertH( s->origPtr != -1, 1003 );
}
/*-------------------------------------------------------------*/
/*--- end blocksort.c ---*/
/*-------------------------------------------------------------*/

189
bzip2.1
View File

@ -1,21 +1,29 @@
.PU
.TH bzip2 1
.SH NAME
bzip2, bunzip2 \- a block-sorting file compressor, v0.1
bzip2, bunzip2 \- a block-sorting file compressor, v0.9.0
.br
bzcat \- decompresses files to stdout
.br
bzip2recover \- recovers data from damaged bzip2 files
.SH SYNOPSIS
.ll +8
.B bzip2
.RB [ " \-cdfkstvVL123456789 " ]
.RB [ " \-cdfkstvzVL123456789 " ]
[
.I "filenames \&..."
]
.ll -8
.br
.B bunzip2
.RB [ " \-kvsVL " ]
.RB [ " \-fkvsVL " ]
[
.I "filenames \&..."
]
.br
.B bzcat
.RB [ " \-s " ]
[
.I "filenames \&..."
]
@ -24,7 +32,7 @@ bzip2recover \- recovers data from damaged bzip2 files
.I "filename"
.SH DESCRIPTION
.I Bzip2
.I bzip2
compresses files using the Burrows-Wheeler block-sorting
text compression algorithm, and Huffman coding.
Compression is generally considerably
@ -38,7 +46,7 @@ those of
.I GNU Gzip,
but they are not identical.
.I Bzip2
.I bzip2
expects a list of file names to accompany the command-line flags.
Each file is replaced by a compressed version of itself,
with the name "original_name.bz2".
@ -50,11 +58,11 @@ original file names, permissions and dates in filesystems
which lack these concepts, or have serious file name length
restrictions, such as MS-DOS.
.I Bzip2
.I bzip2
and
.I bunzip2
will not overwrite existing files; if you want this to happen,
you should delete them first.
will by default not overwrite existing files;
if you want this to happen, specify the \-f flag.
If no file names are specified,
.I bzip2
@ -64,7 +72,7 @@ In this case,
will decline to write compressed output to a terminal, as
this would be entirely incomprehensible and therefore pointless.
.I Bunzip2
.I bunzip2
(or
.I bzip2 \-d
) decompresses and restores all specified files whose names
@ -73,12 +81,28 @@ Files without this suffix are ignored.
Again, supplying no filenames
causes decompression from standard input to standard output.
.I bunzip2
will correctly decompress a file which is the concatenation
of two or more compressed files. The result is the concatenation
of the corresponding uncompressed files. Integrity testing
(\-t) of concatenated compressed files is also supported.
You can also compress or decompress files to
the standard output by giving the \-c flag.
You can decompress multiple files like this, but you may
only compress a single file this way, since it would otherwise
be difficult to separate out the compressed representations of
the original files.
Multiple files may be compressed and decompressed like this.
The resulting outputs are fed sequentially to stdout.
Compression of multiple files in this manner generates
a stream containing multiple compressed file representations.
Such a stream can be decompressed correctly only by
.I bzip2
version 0.9.0 or later. Earlier versions of
.I bzip2
will stop after decompressing the first file in the stream.
.I bzcat
(or
.I bzip2 \-dc
) decompresses all specified files to the standard output.
Compression is always performed, even if the compressed file is
slightly larger than the original. Files of less than about
@ -132,7 +156,7 @@ Compression and decompression requirements, in bytes, can be estimated as:
Compression: 400k + ( 7 x block size )
Decompression: 100k + ( 5 x block size ), or
Decompression: 100k + ( 4 x block size ), or
.br
100k + ( 2.5 x block size )
@ -147,7 +171,7 @@ choice of block size.
For files compressed with the default 900k block size,
.I bunzip2
will require about 4600 kbytes to decompress.
will require about 3700 kbytes to decompress.
To support decompression of any file on a 4 megabyte machine,
.I bunzip2
has an option to decompress using approximately half this
@ -168,8 +192,8 @@ For example, compressing a file 20,000 bytes long with the flag
\-9
will cause the compressor to allocate around
6700k of memory, but only touch 400k + 20000 * 7 = 540
kbytes of it. Similarly, the decompressor will allocate 4600k but
only touch 100k + 20000 * 5 = 200 kbytes.
kbytes of it. Similarly, the decompressor will allocate 3700k but
only touch 100k + 20000 * 4 = 180 kbytes.
Here is a table which summarises the maximum memory usage for
different block sizes. Also recorded is the total compressed
@ -182,15 +206,15 @@ Corpus is dominated by smaller files.
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
-1 1100k 600k 350k 914704
-2 1800k 1100k 600k 877703
-3 2500k 1600k 850k 860338
-4 3200k 2100k 1100k 846899
-5 3900k 2600k 1350k 845160
-6 4600k 3100k 1600k 838626
-7 5400k 3600k 1850k 834096
-8 6000k 4100k 2100k 828642
-9 6700k 4600k 2350k 828642
-1 1100k 500k 350k 914704
-2 1800k 900k 600k 877703
-3 2500k 1300k 850k 860338
-4 3200k 1700k 1100k 846899
-5 3900k 2100k 1350k 845160
-6 4600k 2500k 1600k 838626
-7 5400k 2900k 1850k 834096
-8 6000k 3300k 2100k 828642
-9 6700k 3700k 2350k 828642
.SH OPTIONS
.TP
@ -201,52 +225,54 @@ stdout.
.TP
.B \-d --decompress
Force decompression.
.I Bzip2
and
.I bzip2,
.I bunzip2
are really the same program, and the decision about whether to
compress or decompress is done on the basis of which name is
and
.I bzcat
are really the same program, and the decision about what actions
to take is done on the basis of which name is
used. This flag overrides that mechanism, and forces
.I bzip2
to decompress.
.TP
.B \-f --compress
.B \-z --compress
The complement to \-d: forces compression, regardless of the invokation
name.
.TP
.B \-t --test
Check integrity of the specified file(s), but don't decompress them.
This really performs a trial decompression and throws away the result,
using the low-memory decompression algorithm (see \-s).
This really performs a trial decompression and throws away the result.
.TP
.B \-f --force
Force overwrite of output files. Normally,
.I bzip2
will not overwrite existing output files.
.TP
.B \-k --keep
Keep (don't delete) input files during compression or decompression.
.TP
.B \-s --small
Reduce memory usage, both for compression and decompression.
Files are decompressed using a modified algorithm which only
Reduce memory usage, for compression, decompression and
testing.
Files are decompressed and tested using a modified algorithm which only
requires 2.5 bytes per block byte. This means any file can be
decompressed in 2300k of memory, albeit somewhat more slowly than
usual.
decompressed in 2300k of memory, albeit at about half the normal
speed.
During compression, -s selects a block size of 200k, which limits
memory use to around the same figure, at the expense of your
compression ratio. In short, if your machine is low on memory
(8 megabytes or less), use -s for everything. See
MEMORY MANAGEMENT above.
.TP
.B \-v --verbose
Verbose mode -- show the compression ratio for each file processed.
Further \-v's increase the verbosity level, spewing out lots of
information which is primarily of interest for diagnostic purposes.
.TP
.B \-L --license
.B \-L --license -V --version
Display the software version, license terms and conditions.
.TP
.B \-V --version
Same as \-L.
.TP
.B \-1 to \-9
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
@ -329,10 +355,6 @@ to compress the latter.
If you do get a file which causes severe slowness in compression,
try making the block size as small as possible, with flag \-1.
Incompressible or virtually-incompressible data may decompress
rather more slowly than one would hope. This is due to
a naive implementation of the move-to-front coder.
.I bzip2
usually allocates several megabytes of memory to operate in,
and then charges all over it in a fairly random fashion. This
@ -346,28 +368,19 @@ I imagine
.I bzip2
will perform best on machines with very large caches.
Test mode (\-t) uses the low-memory decompression algorithm
(\-s). This means test mode does not run as fast as it could;
it could run as fast as the normal decompression machinery.
This could easily be fixed at the cost of some code bloat.
.SH CAVEATS
I/O error messages are not as helpful as they could be.
.I Bzip2
tries hard to detect I/O errors and exit cleanly, but the
details of what the problem is sometimes seem rather misleading.
This manual page pertains to version 0.1 of
This manual page pertains to version 0.9.0 of
.I bzip2.
It may well happen that some future version will
use a different compressed file format. If you try to
decompress, using 0.1, a .bz2 file created with some
future version which uses a different compressed file format,
0.1 will complain that your file "is not a bzip2 file".
If that happens, you should obtain a more recent version
of
.I bzip2
and use that to decompress the file.
Compressed data created by this version is entirely forwards and
backwards compatible with the previous public release, version 0.1pl2,
but with the following exception: 0.9.0 can correctly decompress
multiple concatenated compressed files. 0.1pl2 cannot do this; it
will stop after decompressing just the first file in the stream.
Wildcard expansion for Windows 95 and NT
is flaky.
@ -377,63 +390,25 @@ uses 32-bit integers to represent bit positions in
compressed files, so it cannot handle compressed files
more than 512 megabytes long. This could easily be fixed.
.I bzip2recover
sometimes reports a very small, incomplete final block.
This is spurious and can be safely ignored.
.SH RELATIONSHIP TO bzip-0.21
This program is a descendant of the
.I bzip
program, version 0.21, which I released in August 1996.
The primary difference of
.I bzip2
is its avoidance of the possibly patented algorithms
which were used in 0.21.
.I bzip2
also brings various useful refinements (\-s, \-t),
uses less memory, decompresses significantly faster, and
has support for recovering data from damaged files.
Because
.I bzip2
uses Huffman coding to construct the compressed bitstream,
rather than the arithmetic coding used in 0.21,
the compressed representations generated by the two programs
are incompatible, and they will not interoperate. The change
in suffix from .bz to .bz2 reflects this. It would have been
helpful to at least allow
.I bzip2
to decompress files created by 0.21, but this would
defeat the primary aim of having a patent-free compressor.
For a more precise statement about patent issues in
bzip2, please see the README file in the distribution.
Huffman coding necessarily involves some coding inefficiency
compared to arithmetic coding. This means that
.I bzip2
compresses about 1% worse than 0.21, an unfortunate but
unavoidable fact-of-life. On the other hand, decompression
is approximately 50% faster for the same reason, and the
change in file format gave an opportunity to add data-recovery
features. So it is not all bad.
.SH AUTHOR
Julian Seward, jseward@acm.org.
http://www.muraroa.demon.co.uk
The ideas embodied in
.I bzip
and
.I bzip2
are due to (at least) the following people:
Michael Burrows and David Wheeler (for the block sorting
transformation), David Wheeler (again, for the Huffman coder),
Peter Fenwick (for the structured coding model in 0.21,
Peter Fenwick (for the structured coding model in the original
.I bzip,
and many refinements),
and
Alistair Moffat, Radford Neal and Ian Witten (for the arithmetic
coder in 0.21). I am much indebted for their help, support and advice.
See the file ALGORITHMS in the source distribution for pointers to
coder in the original
.I bzip).
I am much indebted for their help, support and advice.
See the manual in the source distribution for pointers to
sources of documentation.
Christian von Roques encouraged me to look for faster
sorting algorithms, so as to speed up compression.

334
bzip2.1.preformatted
View File

@ -5,18 +5,20 @@ bzip2(1) bzip2(1)
NNAAMMEE
bzip2, bunzip2 - a block-sorting file compressor, v0.1
bzip2, bunzip2 - a block-sorting file compressor, v0.9.0
bzcat - decompresses files to stdout
bzip2recover - recovers data from damaged bzip2 files
SSYYNNOOPPSSIISS
bbzziipp22 [ --ccddffkkssttvvVVLL112233445566778899 ] [ _f_i_l_e_n_a_m_e_s _._._. ]
bbuunnzziipp22 [ --kkvvssVVLL ] [ _f_i_l_e_n_a_m_e_s _._._. ]
bbzziipp22 [ --ccddffkkssttvvzzVVLL112233445566778899 ] [ _f_i_l_e_n_a_m_e_s _._._. ]
bbuunnzziipp22 [ --ffkkvvssVVLL ] [ _f_i_l_e_n_a_m_e_s _._._. ]
bbzzccaatt [ --ss ] [ _f_i_l_e_n_a_m_e_s _._._. ]
bbzziipp22rreeccoovveerr _f_i_l_e_n_a_m_e
DDEESSCCRRIIPPTTIIOONN
_B_z_i_p_2 compresses files using the Burrows-Wheeler block-
_b_z_i_p_2 compresses files using the Burrows-Wheeler block-
sorting text compression algorithm, and Huffman coding.
Compression is generally considerably better than that
achieved by more conventional LZ77/LZ78-based compressors,
@ -26,7 +28,7 @@ DDEESSCCRRIIPPTTIIOONN
The command-line options are deliberately very similar to
those of _G_N_U _G_z_i_p_, but they are not identical.
_B_z_i_p_2 expects a list of file names to accompany the com-
_b_z_i_p_2 expects a list of file names to accompany the com-
mand-line flags. Each file is replaced by a compressed
version of itself, with the name "original_name.bz2".
Each compressed file has the same modification date and
@ -38,8 +40,8 @@ DDEESSCCRRIIPPTTIIOONN
cepts, or have serious file name length restrictions, such
as MS-DOS.
_B_z_i_p_2 and _b_u_n_z_i_p_2 will not overwrite existing files; if
you want this to happen, you should delete them first.
_b_z_i_p_2 and _b_u_n_z_i_p_2 will by default not overwrite existing
files; if you want this to happen, specify the -f flag.
If no file names are specified, _b_z_i_p_2 compresses from
standard input to standard output. In this case, _b_z_i_p_2
@ -47,17 +49,15 @@ DDEESSCCRRIIPPTTIIOONN
this would be entirely incomprehensible and therefore
pointless.
_B_u_n_z_i_p_2 (or _b_z_i_p_2 _-_d ) decompresses and restores all spec-
_b_u_n_z_i_p_2 (or _b_z_i_p_2 _-_d ) decompresses and restores all spec-
ified files whose names end in ".bz2". Files without this
suffix are ignored. Again, supplying no filenames causes
decompression from standard input to standard output.
You can also compress or decompress files to the standard
output by giving the -c flag. You can decompress multiple
files like this, but you may only compress a single file
this way, since it would otherwise be difficult to sepa-
rate out the compressed representations of the original
files.
_b_u_n_z_i_p_2 will correctly decompress a file which is the con-
catenation of two or more compressed files. The result is
the concatenation of the corresponding uncompressed files.
Integrity testing (-t) of concatenated compressed files is
@ -70,6 +70,21 @@ DDEESSCCRRIIPPTTIIOONN
bzip2(1) bzip2(1)
also supported.
You can also compress or decompress files to the standard
output by giving the -c flag. Multiple files may be com-
pressed and decompressed like this. The resulting outputs
are fed sequentially to stdout. Compression of multiple
files in this manner generates a stream containing multi-
ple compressed file representations. Such a stream can be
decompressed correctly only by _b_z_i_p_2 version 0.9.0 or
later. Earlier versions of _b_z_i_p_2 will stop after decom-
pressing the first file in the stream.
_b_z_c_a_t (or _b_z_i_p_2 _-_d_c ) decompresses all specified files to
the standard output.
Compression is always performed, even if the compressed
file is slightly larger than the original. Files of less
than about one hundred bytes tend to get larger, since the
@ -108,22 +123,7 @@ MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
file, and _b_u_n_z_i_p_2 then allocates itself just enough memory
to decompress the file. Since block sizes are stored in
compressed files, it follows that the flags -1 to -9 are
irrelevant to and so ignored during decompression. Com-
pression and decompression requirements, in bytes, can be
estimated as:
Compression: 400k + ( 7 x block size )
Decompression: 100k + ( 5 x block size ), or
100k + ( 2.5 x block size )
Larger block sizes give rapidly diminishing marginal
returns; most of the compression comes from the first two
or three hundred k of block size, a fact worth bearing in
mind when using _b_z_i_p_2 on small machines. It is also
important to appreciate that the decompression memory
requirement is set at compression-time by the choice of
block size.
irrelevant to and so ignored during decompression.
@ -136,8 +136,24 @@ MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
bzip2(1) bzip2(1)
Compression and decompression requirements, in bytes, can
be estimated as:
Compression: 400k + ( 7 x block size )
Decompression: 100k + ( 4 x block size ), or
100k + ( 2.5 x block size )
Larger block sizes give rapidly diminishing marginal
returns; most of the compression comes from the first two
or three hundred k of block size, a fact worth bearing in
mind when using _b_z_i_p_2 on small machines. It is also
important to appreciate that the decompression memory
requirement is set at compression-time by the choice of
block size.
For files compressed with the default 900k block size,
_b_u_n_z_i_p_2 will require about 4600 kbytes to decompress. To
_b_u_n_z_i_p_2 will require about 3700 kbytes to decompress. To
support decompression of any file on a 4 megabyte machine,
_b_u_n_z_i_p_2 has an option to decompress using approximately
half this amount of memory, about 2300 kbytes. Decompres-
@ -157,8 +173,8 @@ bzip2(1) bzip2(1)
file 20,000 bytes long with the flag -9 will cause the
compressor to allocate around 6700k of memory, but only
touch 400k + 20000 * 7 = 540 kbytes of it. Similarly, the
decompressor will allocate 4600k but only touch 100k +
20000 * 5 = 200 kbytes.
decompressor will allocate 3700k but only touch 100k +
20000 * 4 = 180 kbytes.
Here is a table which summarises the maximum memory usage
for different block sizes. Also recorded is the total
@ -172,24 +188,8 @@ bzip2(1) bzip2(1)
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
-1 1100k 600k 350k 914704
-2 1800k 1100k 600k 877703
-3 2500k 1600k 850k 860338
-4 3200k 2100k 1100k 846899
-5 3900k 2600k 1350k 845160
-6 4600k 3100k 1600k 838626
-7 5400k 3600k 1850k 834096
-8 6000k 4100k 2100k 828642
-9 6700k 4600k 2350k 828642
OOPPTTIIOONNSS
--cc ----ssttddoouutt
Compress or decompress to standard output. -c will
decompress multiple files to stdout, but will only
compress a single file to stdout.
-1 1100k 500k 350k 914704
-2 1800k 900k 600k 877703
@ -202,34 +202,52 @@ OOPPTTIIOONNSS
bzip2(1) bzip2(1)
--dd ----ddeeccoommpprreessss
Force decompression. _B_z_i_p_2 and _b_u_n_z_i_p_2 are really
the same program, and the decision about whether to
compress or decompress is done on the basis of
which name is used. This flag overrides that mech-
anism, and forces _b_z_i_p_2 to decompress.
-3 2500k 1300k 850k 860338
-4 3200k 1700k 1100k 846899
-5 3900k 2100k 1350k 845160
-6 4600k 2500k 1600k 838626
-7 5400k 2900k 1850k 834096
-8 6000k 3300k 2100k 828642
-9 6700k 3700k 2350k 828642
--ff ----ccoommpprreessss
OOPPTTIIOONNSS
--cc ----ssttddoouutt
Compress or decompress to standard output. -c will
decompress multiple files to stdout, but will only
compress a single file to stdout.
--dd ----ddeeccoommpprreessss
Force decompression. _b_z_i_p_2_, _b_u_n_z_i_p_2 and _b_z_c_a_t are
really the same program, and the decision about
what actions to take is done on the basis of which
name is used. This flag overrides that mechanism,
and forces _b_z_i_p_2 to decompress.
--zz ----ccoommpprreessss
The complement to -d: forces compression, regard-
less of the invokation name.
--tt ----tteesstt
Check integrity of the specified file(s), but don't
decompress them. This really performs a trial
decompression and throws away the result, using the
low-memory decompression algorithm (see -s).
decompression and throws away the result.
--ff ----ffoorrccee
Force overwrite of output files. Normally, _b_z_i_p_2
will not overwrite existing output files.
--kk ----kkeeeepp
Keep (don't delete) input files during compression
or decompression.
--ss ----ssmmaallll
Reduce memory usage, both for compression and
decompression. Files are decompressed using a mod-
ified algorithm which only requires 2.5 bytes per
block byte. This means any file can be decom-
pressed in 2300k of memory, albeit somewhat more
slowly than usual.
Reduce memory usage, for compression, decompression
and testing. Files are decompressed and tested
using a modified algorithm which only requires 2.5
bytes per block byte. This means any file can be
decompressed in 2300k of memory, albeit at about
half the normal speed.
During compression, -s selects a block size of
200k, which limits memory use to around the same
@ -239,24 +257,6 @@ bzip2(1) bzip2(1)
MEMORY MANAGEMENT above.
--vv ----vveerrbboossee
Verbose mode -- show the compression ratio for each
file processed. Further -v's increase the ver-
bosity level, spewing out lots of information which
is primarily of interest for diagnostic purposes.
--LL ----lliicceennssee
Display the software version, license terms and
conditions.
--VV ----vveerrssiioonn
Same as -L.
--11 ttoo --99
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
See MEMORY MANAGEMENT above.
4
@ -268,6 +268,21 @@ bzip2(1) bzip2(1)
bzip2(1) bzip2(1)
--vv ----vveerrbboossee
Verbose mode -- show the compression ratio for each
file processed. Further -v's increase the ver-
bosity level, spewing out lots of information which
is primarily of interest for diagnostic purposes.
--LL ----lliicceennssee --VV ----vveerrssiioonn
Display the software version, license terms and
conditions.
--11 ttoo --99
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
See MEMORY MANAGEMENT above.
----rreeppeettiittiivvee--ffaasstt
_b_z_i_p_2 injects some small pseudo-random variations
into very repetitive blocks to limit worst-case
@ -306,22 +321,7 @@ RREECCOOVVEERRIINNGG DDAATTAA FFRROOMM DDAAMMAAGGEEDD F
_b_z_i_p_2_r_e_c_o_v_e_r takes a single argument, the name of the dam-
aged file, and writes a number of files "rec0001file.bz2",
"rec0002file.bz2", etc, containing the extracted blocks.
The output filenames are designed so that the use of wild-
cards in subsequent processing -- for example, "bzip2 -dc
rec*file.bz2 > recovered_data" -- lists the files in the
"right" order.
_b_z_i_p_2_r_e_c_o_v_e_r should be of most use dealing with large .bz2
files, as these will contain many blocks. It is clearly
futile to use it on damaged single-block files, since a
damaged block cannot be recovered. If you wish to min-
imise any potential data loss through media or transmis-
sion errors, you might consider compressing with a smaller
block size.
PPEERRFFOORRMMAANNCCEE NNOOTTEESS
The sorting phase of compression gathers together similar
The output filenames are designed so that the use of
@ -334,6 +334,21 @@ PPEERRFFOORRMMAANNCCEE NNOOTTEESS
bzip2(1) bzip2(1)
wildcards in subsequent processing -- for example, "bzip2
-dc rec*file.bz2 > recovered_data" -- lists the files in
the "right" order.
_b_z_i_p_2_r_e_c_o_v_e_r should be of most use dealing with large .bz2
files, as these will contain many blocks. It is clearly
futile to use it on damaged single-block files, since a
damaged block cannot be recovered. If you wish to min-
imise any potential data loss through media or transmis-
sion errors, you might consider compressing with a smaller
block size.
PPEERRFFOORRMMAANNCCEE NNOOTTEESS
The sorting phase of compression gathers together similar
strings in the file. Because of this, files containing
very long runs of repeated symbols, like "aabaabaabaab
..." (repeated several hundred times) may compress
@ -348,10 +363,6 @@ bzip2(1) bzip2(1)
severe slowness in compression, try making the block size
as small as possible, with flag -1.
Incompressible or virtually-incompressible data may decom-
press rather more slowly than one would hope. This is due
to a naive implementation of the move-to-front coder.
_b_z_i_p_2 usually allocates several megabytes of memory to
operate in, and then charges all over it in a fairly ran-
dom fashion. This means that performance, both for com-
@ -362,12 +373,6 @@ bzip2(1) bzip2(1)
large performance improvements. I imagine _b_z_i_p_2 will per-
form best on machines with very large caches.
Test mode (-t) uses the low-memory decompression algorithm
(-s). This means test mode does not run as fast as it
could; it could run as fast as the normal decompression
machinery. This could easily be fixed at the cost of some
code bloat.
CCAAVVEEAATTSS
I/O error messages are not as helpful as they could be.
@ -375,19 +380,14 @@ CCAAVVEEAATTSS
but the details of what the problem is sometimes seem
rather misleading.
This manual page pertains to version 0.1 of _b_z_i_p_2_. It may
well happen that some future version will use a different
compressed file format. If you try to decompress, using
0.1, a .bz2 file created with some future version which
uses a different compressed file format, 0.1 will complain
that your file "is not a bzip2 file". If that happens,
you should obtain a more recent version of _b_z_i_p_2 and use
that to decompress the file.
This manual page pertains to version 0.9.0 of _b_z_i_p_2_. Com-
pressed data created by this version is entirely forwards
and backwards compatible with the previous public release,
version 0.1pl2, but with the following exception: 0.9.0
can correctly decompress multiple concatenated compressed
files. 0.1pl2 cannot do this; it will stop after decom-
pressing just the first file in the stream.
Wildcard expansion for Windows 95 and NT is flaky.
_b_z_i_p_2_r_e_c_o_v_e_r uses 32-bit integers to represent bit posi-
tions in compressed files, so it cannot handle compressed
@ -400,59 +400,31 @@ CCAAVVEEAATTSS
bzip2(1) bzip2(1)
Wildcard expansion for Windows 95 and NT is flaky.
_b_z_i_p_2_r_e_c_o_v_e_r uses 32-bit integers to represent bit posi-
tions in compressed files, so it cannot handle compressed
files more than 512 megabytes long. This could easily be
fixed.
_b_z_i_p_2_r_e_c_o_v_e_r sometimes reports a very small, incomplete
final block. This is spurious and can be safely ignored.
RREELLAATTIIOONNSSHHIIPP TTOO bbzziipp--00..2211
This program is a descendant of the _b_z_i_p program, version
0.21, which I released in August 1996. The primary dif-
ference of _b_z_i_p_2 is its avoidance of the possibly patented
algorithms which were used in 0.21. _b_z_i_p_2 also brings
various useful refinements (-s, -t), uses less memory,
decompresses significantly faster, and has support for
recovering data from damaged files.
Because _b_z_i_p_2 uses Huffman coding to construct the com-
pressed bitstream, rather than the arithmetic coding used
in 0.21, the compressed representations generated by the
two programs are incompatible, and they will not interop-
erate. The change in suffix from .bz to .bz2 reflects
this. It would have been helpful to at least allow _b_z_i_p_2
to decompress files created by 0.21, but this would defeat
the primary aim of having a patent-free compressor.
For a more precise statement about patent issues in bzip2,
please see the README file in the distribution.
Huffman coding necessarily involves some coding ineffi-
ciency compared to arithmetic coding. This means that
_b_z_i_p_2 compresses about 1% worse than 0.21, an unfortunate
but unavoidable fact-of-life. On the other hand, decom-
pression is approximately 50% faster for the same reason,
and the change in file format gave an opportunity to add
data-recovery features. So it is not all bad.
AAUUTTHHOORR
Julian Seward, jseward@acm.org.
http://www.muraroa.demon.co.uk
The ideas embodied in _b_z_i_p and _b_z_i_p_2 are due to (at least)
the following people: Michael Burrows and David Wheeler
(for the block sorting transformation), David Wheeler
(again, for the Huffman coder), Peter Fenwick (for the
structured coding model in 0.21, and many refinements),
and Alistair Moffat, Radford Neal and Ian Witten (for the
arithmetic coder in 0.21). I am much indebted for their
help, support and advice. See the file ALGORITHMS in the
source distribution for pointers to sources of documenta-
tion. Christian von Roques encouraged me to look for
faster sorting algorithms, so as to speed up compression.
Bela Lubkin encouraged me to improve the worst-case com-
pression performance. Many people sent patches, helped
The ideas embodied in _b_z_i_p_2 are due to (at least) the fol-
lowing people: Michael Burrows and David Wheeler (for the
block sorting transformation), David Wheeler (again, for
the Huffman coder), Peter Fenwick (for the structured cod-
ing model in the original _b_z_i_p_, and many refinements), and
Alistair Moffat, Radford Neal and Ian Witten (for the
arithmetic coder in the original _b_z_i_p_)_. I am much
indebted for their help, support and advice. See the man-
ual in the source distribution for pointers to sources of
documentation. Christian von Roques encouraged me to look
for faster sorting algorithms, so as to speed up compres-
sion. Bela Lubkin encouraged me to improve the worst-case
compression performance. Many people sent patches, helped
with portability problems, lent machines, gave advice and
were generally helpful.
@ -460,6 +432,32 @@ AAUUTTHHOORR
7

3381
bzip2.c
View File

File diff suppressed because it is too large Load Diff

282
bzip2.txt
View File

@ -1,22 +1,22 @@
bzip2(1) bzip2(1)
NAME
bzip2, bunzip2 - a block-sorting file compressor, v0.1
bzip2, bunzip2 - a block-sorting file compressor, v0.9.0
bzcat - decompresses files to stdout
bzip2recover - recovers data from damaged bzip2 files
SYNOPSIS
bzip2 [ -cdfkstvVL123456789 ] [ filenames ... ]
bunzip2 [ -kvsVL ] [ filenames ... ]
bzip2 [ -cdfkstvzVL123456789 ] [ filenames ... ]
bunzip2 [ -fkvsVL ] [ filenames ... ]
bzcat [ -s ] [ filenames ... ]
bzip2recover filename
DESCRIPTION
Bzip2 compresses files using the Burrows-Wheeler block-
bzip2 compresses files using the Burrows-Wheeler block-
sorting text compression algorithm, and Huffman coding.
Compression is generally considerably better than that
achieved by more conventional LZ77/LZ78-based compressors,
@ -26,7 +26,7 @@ DESCRIPTION
The command-line options are deliberately very similar to
those of GNU Gzip, but they are not identical.
Bzip2 expects a list of file names to accompany the com-
bzip2 expects a list of file names to accompany the com-
mand-line flags. Each file is replaced by a compressed
version of itself, with the name "original_name.bz2".
Each compressed file has the same modification date and
@ -38,8 +38,8 @@ DESCRIPTION
cepts, or have serious file name length restrictions, such
as MS-DOS.
Bzip2 and bunzip2 will not overwrite existing files; if
you want this to happen, you should delete them first.
bzip2 and bunzip2 will by default not overwrite existing
files; if you want this to happen, specify the -f flag.
If no file names are specified, bzip2 compresses from
standard input to standard output. In this case, bzip2
@ -47,28 +47,29 @@ DESCRIPTION
this would be entirely incomprehensible and therefore
pointless.
Bunzip2 (or bzip2 -d ) decompresses and restores all spec-
bunzip2 (or bzip2 -d ) decompresses and restores all spec-
ified files whose names end in ".bz2". Files without this
suffix are ignored. Again, supplying no filenames causes
decompression from standard input to standard output.
bunzip2 will correctly decompress a file which is the con-
catenation of two or more compressed files. The result is
the concatenation of the corresponding uncompressed files.
Integrity testing (-t) of concatenated compressed files is
also supported.
You can also compress or decompress files to the standard
output by giving the -c flag. You can decompress multiple
files like this, but you may only compress a single file
this way, since it would otherwise be difficult to sepa-
rate out the compressed representations of the original
files.
1
bzip2(1) bzip2(1)
output by giving the -c flag. Multiple files may be com-
pressed and decompressed like this. The resulting outputs
are fed sequentially to stdout. Compression of multiple
files in this manner generates a stream containing multi-
ple compressed file representations. Such a stream can be
decompressed correctly only by bzip2 version 0.9.0 or
later. Earlier versions of bzip2 will stop after decom-
pressing the first file in the stream.
bzcat (or bzip2 -dc ) decompresses all specified files to
the standard output.
Compression is always performed, even if the compressed
file is slightly larger than the original. Files of less
@ -108,13 +109,14 @@ MEMORY MANAGEMENT
file, and bunzip2 then allocates itself just enough memory
to decompress the file. Since block sizes are stored in
compressed files, it follows that the flags -1 to -9 are
irrelevant to and so ignored during decompression. Com-
pression and decompression requirements, in bytes, can be
estimated as:
irrelevant to and so ignored during decompression.
Compression and decompression requirements, in bytes, can
be estimated as:
Compression: 400k + ( 7 x block size )
Decompression: 100k + ( 5 x block size ), or
Decompression: 100k + ( 4 x block size ), or
100k + ( 2.5 x block size )
Larger block sizes give rapidly diminishing marginal
@ -125,19 +127,8 @@ MEMORY MANAGEMENT
requirement is set at compression-time by the choice of
block size.
2
bzip2(1) bzip2(1)
For files compressed with the default 900k block size,
bunzip2 will require about 4600 kbytes to decompress. To
bunzip2 will require about 3700 kbytes to decompress. To
support decompression of any file on a 4 megabyte machine,
bunzip2 has an option to decompress using approximately
half this amount of memory, about 2300 kbytes. Decompres-
@ -157,8 +148,8 @@ bzip2(1) bzip2(1)
file 20,000 bytes long with the flag -9 will cause the
compressor to allocate around 6700k of memory, but only
touch 400k + 20000 * 7 = 540 kbytes of it. Similarly, the
decompressor will allocate 4600k but only touch 100k +
20000 * 5 = 200 kbytes.
decompressor will allocate 3700k but only touch 100k +
20000 * 4 = 180 kbytes.
Here is a table which summarises the maximum memory usage
for different block sizes. Also recorded is the total
@ -172,15 +163,15 @@ bzip2(1) bzip2(1)
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
-1 1100k 600k 350k 914704
-2 1800k 1100k 600k 877703
-3 2500k 1600k 850k 860338
-4 3200k 2100k 1100k 846899
-5 3900k 2600k 1350k 845160
-6 4600k 3100k 1600k 838626
-7 5400k 3600k 1850k 834096
-8 6000k 4100k 2100k 828642
-9 6700k 4600k 2350k 828642
-1 1100k 500k 350k 914704
-2 1800k 900k 600k 877703
-3 2500k 1300k 850k 860338
-4 3200k 1700k 1100k 846899
-5 3900k 2100k 1350k 845160
-6 4600k 2500k 1600k 838626
-7 5400k 2900k 1850k 834096
-8 6000k 3300k 2100k 828642
-9 6700k 3700k 2350k 828642
OPTIONS
@ -189,47 +180,37 @@ OPTIONS
decompress multiple files to stdout, but will only
compress a single file to stdout.
3
bzip2(1) bzip2(1)
-d --decompress
Force decompression. Bzip2 and bunzip2 are really
the same program, and the decision about whether to
compress or decompress is done on the basis of
which name is used. This flag overrides that mech-
anism, and forces bzip2 to decompress.
Force decompression. bzip2, bunzip2 and bzcat are
really the same program, and the decision about
what actions to take is done on the basis of which
name is used. This flag overrides that mechanism,
and forces bzip2 to decompress.
-f --compress
-z --compress
The complement to -d: forces compression, regard-
less of the invokation name.
-t --test
Check integrity of the specified file(s), but don't
decompress them. This really performs a trial
decompression and throws away the result, using the
low-memory decompression algorithm (see -s).
decompression and throws away the result.
-f --force
Force overwrite of output files. Normally, bzip2
will not overwrite existing output files.
-k --keep
Keep (don't delete) input files during compression
or decompression.
-s --small
Reduce memory usage, both for compression and
decompression. Files are decompressed using a mod-
ified algorithm which only requires 2.5 bytes per
block byte. This means any file can be decom-
pressed in 2300k of memory, albeit somewhat more
slowly than usual.
Reduce memory usage, for compression, decompression
and testing. Files are decompressed and tested
using a modified algorithm which only requires 2.5
bytes per block byte. This means any file can be
decompressed in 2300k of memory, albeit at about
half the normal speed.
During compression, -s selects a block size of
200k, which limits memory use to around the same
@ -238,36 +219,21 @@ bzip2(1) bzip2(1)
megabytes or less), use -s for everything. See
MEMORY MANAGEMENT above.
-v --verbose
Verbose mode -- show the compression ratio for each
file processed. Further -v's increase the ver-
bosity level, spewing out lots of information which
is primarily of interest for diagnostic purposes.
-L --license
-L --license -V --version
Display the software version, license terms and
conditions.
-V --version
Same as -L.
-1 to -9
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
See MEMORY MANAGEMENT above.
4
bzip2(1) bzip2(1)
--repetitive-fast
bzip2 injects some small pseudo-random variations
into very repetitive blocks to limit worst-case
@ -278,7 +244,6 @@ bzip2(1) bzip2(1)
would take before resorting to randomisation. This
flag makes it give up much sooner.
--repetitive-best
Opposite of --repetitive-fast; try a lot harder
before resorting to randomisation.
@ -306,10 +271,10 @@ RECOVERING DATA FROM DAMAGED FILES
bzip2recover takes a single argument, the name of the dam-
aged file, and writes a number of files "rec0001file.bz2",
"rec0002file.bz2", etc, containing the extracted blocks.
The output filenames are designed so that the use of wild-
cards in subsequent processing -- for example, "bzip2 -dc
rec*file.bz2 > recovered_data" -- lists the files in the
"right" order.
The output filenames are designed so that the use of
wildcards in subsequent processing -- for example, "bzip2
-dc rec*file.bz2 > recovered_data" -- lists the files in
the "right" order.
bzip2recover should be of most use dealing with large .bz2
files, as these will contain many blocks. It is clearly
@ -322,18 +287,6 @@ RECOVERING DATA FROM DAMAGED FILES
PERFORMANCE NOTES
The sorting phase of compression gathers together similar
5
bzip2(1) bzip2(1)
strings in the file. Because of this, files containing
very long runs of repeated symbols, like "aabaabaabaab
..." (repeated several hundred times) may compress
@ -348,10 +301,6 @@ bzip2(1) bzip2(1)
severe slowness in compression, try making the block size
as small as possible, with flag -1.
Incompressible or virtually-incompressible data may decom-
press rather more slowly than one would hope. This is due
to a naive implementation of the move-to-front coder.
bzip2 usually allocates several megabytes of memory to
operate in, and then charges all over it in a fairly ran-
dom fashion. This means that performance, both for com-
@ -362,12 +311,6 @@ bzip2(1) bzip2(1)
large performance improvements. I imagine bzip2 will per-
form best on machines with very large caches.
Test mode (-t) uses the low-memory decompression algorithm
(-s). This means test mode does not run as fast as it
could; it could run as fast as the normal decompression
machinery. This could easily be fixed at the cost of some
code bloat.
CAVEATS
I/O error messages are not as helpful as they could be.
@ -375,91 +318,38 @@ CAVEATS
but the details of what the problem is sometimes seem
rather misleading.
This manual page pertains to version 0.1 of bzip2. It may
well happen that some future version will use a different
compressed file format. If you try to decompress, using
0.1, a .bz2 file created with some future version which
uses a different compressed file format, 0.1 will complain
that your file "is not a bzip2 file". If that happens,
you should obtain a more recent version of bzip2 and use
that to decompress the file.
This manual page pertains to version 0.9.0 of bzip2. Com-
pressed data created by this version is entirely forwards
and backwards compatible with the previous public release,
version 0.1pl2, but with the following exception: 0.9.0
can correctly decompress multiple concatenated compressed
files. 0.1pl2 cannot do this; it will stop after decom-
pressing just the first file in the stream.
Wildcard expansion for Windows 95 and NT is flaky.
bzip2recover uses 32-bit integers to represent bit posi-
tions in compressed files, so it cannot handle compressed
6
bzip2(1) bzip2(1)
files more than 512 megabytes long. This could easily be
fixed.
bzip2recover sometimes reports a very small, incomplete
final block. This is spurious and can be safely ignored.
RELATIONSHIP TO bzip-0.21
This program is a descendant of the bzip program, version
0.21, which I released in August 1996. The primary dif-
ference of bzip2 is its avoidance of the possibly patented
algorithms which were used in 0.21. bzip2 also brings
various useful refinements (-s, -t), uses less memory,
decompresses significantly faster, and has support for
recovering data from damaged files.
Because bzip2 uses Huffman coding to construct the com-
pressed bitstream, rather than the arithmetic coding used
in 0.21, the compressed representations generated by the
two programs are incompatible, and they will not interop-
erate. The change in suffix from .bz to .bz2 reflects
this. It would have been helpful to at least allow bzip2
to decompress files created by 0.21, but this would defeat
the primary aim of having a patent-free compressor.
For a more precise statement about patent issues in bzip2,
please see the README file in the distribution.
Huffman coding necessarily involves some coding ineffi-
ciency compared to arithmetic coding. This means that
bzip2 compresses about 1% worse than 0.21, an unfortunate
but unavoidable fact-of-life. On the other hand, decom-
pression is approximately 50% faster for the same reason,
and the change in file format gave an opportunity to add
data-recovery features. So it is not all bad.
AUTHOR
Julian Seward, jseward@acm.org.
http://www.muraroa.demon.co.uk
The ideas embodied in bzip and bzip2 are due to (at least)
the following people: Michael Burrows and David Wheeler
(for the block sorting transformation), David Wheeler
(again, for the Huffman coder), Peter Fenwick (for the
structured coding model in 0.21, and many refinements),
and Alistair Moffat, Radford Neal and Ian Witten (for the
arithmetic coder in 0.21). I am much indebted for their
help, support and advice. See the file ALGORITHMS in the
source distribution for pointers to sources of documenta-
tion. Christian von Roques encouraged me to look for
faster sorting algorithms, so as to speed up compression.
Bela Lubkin encouraged me to improve the worst-case com-
pression performance. Many people sent patches, helped
The ideas embodied in bzip2 are due to (at least) the fol-
lowing people: Michael Burrows and David Wheeler (for the
block sorting transformation), David Wheeler (again, for
the Huffman coder), Peter Fenwick (for the structured cod-
ing model in the original bzip, and many refinements), and
Alistair Moffat, Radford Neal and Ian Witten (for the
arithmetic coder in the original bzip). I am much
indebted for their help, support and advice. See the man-
ual in the source distribution for pointers to sources of
documentation. Christian von Roques encouraged me to look
for faster sorting algorithms, so as to speed up compres-
sion. Bela Lubkin encouraged me to improve the worst-case
compression performance. Many people sent patches, helped
with portability problems, lent machines, gave advice and
were generally helpful.
7

115
bzip2recover.c
View File

@ -7,43 +7,63 @@
/*--
This program is bzip2recover, a program to attempt data
salvage from damaged files created by the accompanying
bzip2-0.1 program.
bzip2-0.9.0c program.
Copyright (C) 1996, 1997 by Julian Seward.
Guildford, Surrey, UK
email: jseward@acm.org
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
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.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
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.
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
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.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
The GNU General Public License is contained in the file LICENSE.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
--*/
/*--
This program is a complete hack and should be rewritten
properly. It isn't very complicated.
--*/
#include <stdio.h>
#include <errno.h>
#include <malloc.h>
#include <stdlib.h>
#include <strings.h> /*-- or try string.h --*/
#include <string.h>
#define UInt32 unsigned int
#define Int32 int
#define UChar unsigned char
#define Char char
#define Bool unsigned char
#define True 1
#define False 0
typedef unsigned int UInt32;
typedef int Int32;
typedef unsigned char UChar;
typedef char Char;
typedef unsigned char Bool;
#define True ((Bool)1)
#define False ((Bool)0)
Char inFileName[2000];
@ -191,8 +211,9 @@ void bsClose ( BitStream* bs )
if (retVal == EOF) writeError();
}
retVal = fclose ( bs->handle );
if (retVal == EOF)
if (retVal == EOF) {
if (bs->mode == 'w') writeError(); else readError();
}
free ( bs );
}
@ -248,13 +269,19 @@ Int32 main ( Int32 argc, Char** argv )
UInt32 bitsRead;
UInt32 bStart[20000];
UInt32 bEnd[20000];
UInt32 rbStart[20000];
UInt32 rbEnd[20000];
Int32 rbCtr;
UInt32 buffHi, buffLo, blockCRC;
Char* p;
strcpy ( progName, argv[0] );
inFileName[0] = outFileName[0] = 0;
fprintf ( stderr, "bzip2recover: extracts blocks from damaged .bz2 files.\n" );
fprintf ( stderr, "bzip2recover v0.9.0c: extracts blocks from damaged .bz2 files.\n" );
if (argc != 2) {
fprintf ( stderr, "%s: usage is `%s damaged_file_name'.\n",
@ -278,6 +305,8 @@ Int32 main ( Int32 argc, Char** argv )
currBlock = 0;
bStart[currBlock] = 0;
rbCtr = 0;
while (True) {
b = bsGetBit ( bsIn );
bitsRead++;
@ -303,19 +332,25 @@ Int32 main ( Int32 argc, Char** argv )
if (bitsRead > 49)
bEnd[currBlock] = bitsRead-49; else
bEnd[currBlock] = 0;
if (currBlock > 0)
if (currBlock > 0 &&
(bEnd[currBlock] - bStart[currBlock]) >= 130) {
fprintf ( stderr, " block %d runs from %d to %d\n",
currBlock, bStart[currBlock], bEnd[currBlock] );
rbCtr+1, bStart[currBlock], bEnd[currBlock] );
rbStart[rbCtr] = bStart[currBlock];
rbEnd[rbCtr] = bEnd[currBlock];
rbCtr++;
}
currBlock++;
bStart[currBlock] = bitsRead;
}
}
bsClose ( bsIn );
/*-- identified blocks run from 1 to currBlock inclusive. --*/
/*-- identified blocks run from 1 to rbCtr inclusive. --*/
if (currBlock < 1) {
if (rbCtr < 1) {
fprintf ( stderr,
"%s: sorry, I couldn't find any block boundaries.\n",
progName );
@ -336,23 +371,23 @@ Int32 main ( Int32 argc, Char** argv )
bitsRead = 0;
outFile = NULL;
wrBlock = 1;
wrBlock = 0;
while (True) {
b = bsGetBit(bsIn);
if (b == 2) break;
buffHi = (buffHi << 1) | (buffLo >> 31);
buffLo = (buffLo << 1) | (b & 1);
if (bitsRead == 47+bStart[wrBlock])
if (bitsRead == 47+rbStart[wrBlock])
blockCRC = (buffHi << 16) | (buffLo >> 16);
if (outFile != NULL && bitsRead >= bStart[wrBlock]
&& bitsRead <= bEnd[wrBlock]) {
if (outFile != NULL && bitsRead >= rbStart[wrBlock]
&& bitsRead <= rbEnd[wrBlock]) {
bsPutBit ( bsWr, b );
}
bitsRead++;
if (bitsRead == bEnd[wrBlock]+1) {
if (bitsRead == rbEnd[wrBlock]+1) {
if (outFile != NULL) {
bsPutUChar ( bsWr, 0x17 ); bsPutUChar ( bsWr, 0x72 );
bsPutUChar ( bsWr, 0x45 ); bsPutUChar ( bsWr, 0x38 );
@ -360,18 +395,18 @@ Int32 main ( Int32 argc, Char** argv )
bsPutUInt32 ( bsWr, blockCRC );
bsClose ( bsWr );
}
if (wrBlock >= currBlock) break;
if (wrBlock >= rbCtr) break;
wrBlock++;
} else
if (bitsRead == bStart[wrBlock]) {
if (bitsRead == rbStart[wrBlock]) {
outFileName[0] = 0;
sprintf ( outFileName, "rec%4d", wrBlock );
sprintf ( outFileName, "rec%4d", wrBlock+1 );
for (p = outFileName; *p != 0; p++) if (*p == ' ') *p = '0';
strcat ( outFileName, inFileName );
if ( !endsInBz2(outFileName)) strcat ( outFileName, ".bz2" );
fprintf ( stderr, " writing block %d to `%s' ...\n",
wrBlock, outFileName );
wrBlock+1, outFileName );
outFile = fopen ( outFileName, "wb" );
if (outFile == NULL) {

1512
bzlib.c Normal file
View File

File diff suppressed because it is too large Load Diff

299
bzlib.h Normal file
View File

@ -0,0 +1,299 @@
/*-------------------------------------------------------------*/
/*--- Public header file for the library. ---*/
/*--- bzlib.h ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#ifndef _BZLIB_H
#define _BZLIB_H
#define BZ_RUN 0
#define BZ_FLUSH 1
#define BZ_FINISH 2
#define BZ_OK 0
#define BZ_RUN_OK 1
#define BZ_FLUSH_OK 2
#define BZ_FINISH_OK 3
#define BZ_STREAM_END 4
#define BZ_SEQUENCE_ERROR (-1)
#define BZ_PARAM_ERROR (-2)
#define BZ_MEM_ERROR (-3)
#define BZ_DATA_ERROR (-4)
#define BZ_DATA_ERROR_MAGIC (-5)
#define BZ_IO_ERROR (-6)
#define BZ_UNEXPECTED_EOF (-7)
#define BZ_OUTBUFF_FULL (-8)
typedef
struct {
char *next_in;
unsigned int avail_in;
unsigned int total_in;
char *next_out;
unsigned int avail_out;
unsigned int total_out;
void *state;
void *(*bzalloc)(void *,int,int);
void (*bzfree)(void *,void *);
void *opaque;
}
bz_stream;
#ifndef BZ_IMPORT
#define BZ_EXPORT
#endif
#ifdef _WIN32
# include <stdio.h>
# include <windows.h>
# ifdef small
/* windows.h define small to char */
# undef small
# endif
# ifdef BZ_EXPORT
# define BZ_API(func) WINAPI func
# define BZ_EXTERN extern
# else
/* import windows dll dynamically */
# define BZ_API(func) (WINAPI * func)
# define BZ_EXTERN
# endif
#else
# define BZ_API(func) func
# define BZ_EXTERN extern
#endif
/*-- Core (low-level) library functions --*/
BZ_EXTERN int BZ_API(bzCompressInit) (
bz_stream* strm,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN int BZ_API(bzCompress) (
bz_stream* strm,
int action
);
BZ_EXTERN int BZ_API(bzCompressEnd) (
bz_stream* strm
);
BZ_EXTERN int BZ_API(bzDecompressInit) (
bz_stream *strm,
int verbosity,
int small
);
BZ_EXTERN int BZ_API(bzDecompress) (
bz_stream* strm
);
BZ_EXTERN int BZ_API(bzDecompressEnd) (
bz_stream *strm
);
/*-- High(er) level library functions --*/
#ifndef BZ_NO_STDIO
#define BZ_MAX_UNUSED 5000
typedef void BZFILE;
BZ_EXTERN BZFILE* BZ_API(bzReadOpen) (
int* bzerror,
FILE* f,
int verbosity,
int small,
void* unused,
int nUnused
);
BZ_EXTERN void BZ_API(bzReadClose) (
int* bzerror,
BZFILE* b
);
BZ_EXTERN void BZ_API(bzReadGetUnused) (
int* bzerror,
BZFILE* b,
void** unused,
int* nUnused
);
BZ_EXTERN int BZ_API(bzRead) (
int* bzerror,
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN BZFILE* BZ_API(bzWriteOpen) (
int* bzerror,
FILE* f,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN void BZ_API(bzWrite) (
int* bzerror,
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN void BZ_API(bzWriteClose) (
int* bzerror,
BZFILE* b,
int abandon,
unsigned int* nbytes_in,
unsigned int* nbytes_out
);
#endif
/*-- Utility functions --*/
BZ_EXTERN int BZ_API(bzBuffToBuffCompress) (
char* dest,
unsigned int* destLen,
char* source,
unsigned int sourceLen,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN int BZ_API(bzBuffToBuffDecompress) (
char* dest,
unsigned int* destLen,
char* source,
unsigned int sourceLen,
int small,
int verbosity
);
/*--
Code contributed by Yoshioka Tsuneo
(QWF00133@niftyserve.or.jp/tsuneo-y@is.aist-nara.ac.jp),
to support better zlib compatibility.
This code is not _officially_ part of libbzip2 (yet);
I haven't tested it, documented it, or considered the
threading-safeness of it.
If this code breaks, please contact both Yoshioka and me.
--*/
BZ_EXTERN const char * BZ_API(bzlibVersion) (
void
);
#ifndef BZ_NO_STDIO
BZ_EXTERN BZFILE * BZ_API(bzopen) (
const char *path,
const char *mode
);
BZ_EXTERN BZFILE * BZ_API(bzdopen) (
int fd,
const char *mode
);
BZ_EXTERN int BZ_API(bzread) (
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN int BZ_API(bzwrite) (
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN int BZ_API(bzflush) (
BZFILE* b
);
BZ_EXTERN void BZ_API(bzclose) (
BZFILE* b
);
BZ_EXTERN const char * BZ_API(bzerror) (
BZFILE *b,
int *errnum
);
#endif
#endif
/*-------------------------------------------------------------*/
/*--- end bzlib.h ---*/
/*-------------------------------------------------------------*/

523
bzlib_private.h Normal file
View File

@ -0,0 +1,523 @@
/*-------------------------------------------------------------*/
/*--- Private header file for the library. ---*/
/*--- bzlib_private.h ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#ifndef _BZLIB_PRIVATE_H
#define _BZLIB_PRIVATE_H
#include <stdlib.h>
#ifndef BZ_NO_STDIO
#include <stdio.h>
#include <ctype.h>
#include <string.h>
#endif
#include "bzlib.h"
/*-- General stuff. --*/
#define BZ_VERSION "0.9.0c"
typedef char Char;
typedef unsigned char Bool;
typedef unsigned char UChar;
typedef int Int32;
typedef unsigned int UInt32;
typedef short Int16;
typedef unsigned short UInt16;
#define True ((Bool)1)
#define False ((Bool)0)
#ifndef __GNUC__
#define __inline__ /* */
#endif
#ifndef BZ_NO_STDIO
extern void bz__AssertH__fail ( int errcode );
#define AssertH(cond,errcode) \
{ if (!(cond)) bz__AssertH__fail ( errcode ); }
#if BZ_DEBUG
#define AssertD(cond,msg) \
{ if (!(cond)) { \
fprintf ( stderr, \
"\n\nlibbzip2(debug build): internal error\n\t%s\n", msg );\
exit(1); \
}}
#else
#define AssertD(cond,msg) /* */
#endif
#define VPrintf0(zf) \
fprintf(stderr,zf)
#define VPrintf1(zf,za1) \
fprintf(stderr,zf,za1)
#define VPrintf2(zf,za1,za2) \
fprintf(stderr,zf,za1,za2)
#define VPrintf3(zf,za1,za2,za3) \
fprintf(stderr,zf,za1,za2,za3)
#define VPrintf4(zf,za1,za2,za3,za4) \
fprintf(stderr,zf,za1,za2,za3,za4)
#define VPrintf5(zf,za1,za2,za3,za4,za5) \
fprintf(stderr,zf,za1,za2,za3,za4,za5)
#else
extern void bz_internal_error ( int errcode );
#define AssertH(cond,errcode) \
{ if (!(cond)) bz_internal_error ( errcode ); }
#define AssertD(cond,msg) /* */
#define VPrintf0(zf) /* */
#define VPrintf1(zf,za1) /* */
#define VPrintf2(zf,za1,za2) /* */
#define VPrintf3(zf,za1,za2,za3) /* */
#define VPrintf4(zf,za1,za2,za3,za4) /* */
#define VPrintf5(zf,za1,za2,za3,za4,za5) /* */
#endif
#define BZALLOC(nnn) (strm->bzalloc)(strm->opaque,(nnn),1)
#define BZFREE(ppp) (strm->bzfree)(strm->opaque,(ppp))
/*-- Constants for the back end. --*/
#define BZ_MAX_ALPHA_SIZE 258
#define BZ_MAX_CODE_LEN 23
#define BZ_RUNA 0
#define BZ_RUNB 1
#define BZ_N_GROUPS 6
#define BZ_G_SIZE 50
#define BZ_N_ITERS 4
#define BZ_MAX_SELECTORS (2 + (900000 / BZ_G_SIZE))
/*-- Stuff for randomising repetitive blocks. --*/
extern Int32 rNums[512];
#define BZ_RAND_DECLS \
Int32 rNToGo; \
Int32 rTPos \
#define BZ_RAND_INIT_MASK \
s->rNToGo = 0; \
s->rTPos = 0 \
#define BZ_RAND_MASK ((s->rNToGo == 1) ? 1 : 0)
#define BZ_RAND_UPD_MASK \
if (s->rNToGo == 0) { \
s->rNToGo = rNums[s->rTPos]; \
s->rTPos++; \
if (s->rTPos == 512) s->rTPos = 0; \
} \
s->rNToGo--;
/*-- Stuff for doing CRCs. --*/
extern UInt32 crc32Table[256];
#define BZ_INITIALISE_CRC(crcVar) \
{ \
crcVar = 0xffffffffL; \
}
#define BZ_FINALISE_CRC(crcVar) \
{ \
crcVar = ~(crcVar); \
}
#define BZ_UPDATE_CRC(crcVar,cha) \
{ \
crcVar = (crcVar << 8) ^ \
crc32Table[(crcVar >> 24) ^ \
((UChar)cha)]; \
}
/*-- States and modes for compression. --*/
#define BZ_M_IDLE 1
#define BZ_M_RUNNING 2
#define BZ_M_FLUSHING 3
#define BZ_M_FINISHING 4
#define BZ_S_OUTPUT 1
#define BZ_S_INPUT 2
#define BZ_NUM_OVERSHOOT_BYTES 20
/*-- Structure holding all the compression-side stuff. --*/
typedef
struct {
/* pointer back to the struct bz_stream */
bz_stream* strm;
/* mode this stream is in, and whether inputting */
/* or outputting data */
Int32 mode;
Int32 state;
/* remembers avail_in when flush/finish requested */
UInt32 avail_in_expect;
/* for doing the block sorting */
UChar* block;
UInt16* quadrant;
UInt32* zptr;
UInt16* szptr;
Int32* ftab;
Int32 workDone;
Int32 workLimit;
Int32 workFactor;
Bool firstAttempt;
Bool blockRandomised;
Int32 origPtr;
/* run-length-encoding of the input */
UInt32 state_in_ch;
Int32 state_in_len;
BZ_RAND_DECLS;
/* input and output limits and current posns */
Int32 nblock;
Int32 nblockMAX;
Int32 numZ;
Int32 state_out_pos;
/* map of bytes used in block */
Int32 nInUse;
Bool inUse[256];
UChar unseqToSeq[256];
/* the buffer for bit stream creation */
UInt32 bsBuff;
Int32 bsLive;
/* block and combined CRCs */
UInt32 blockCRC;
UInt32 combinedCRC;
/* misc administratium */
Int32 verbosity;
Int32 blockNo;
Int32 nBlocksRandomised;
Int32 blockSize100k;
/* stuff for coding the MTF values */
Int32 nMTF;
Int32 mtfFreq [BZ_MAX_ALPHA_SIZE];
UChar selector [BZ_MAX_SELECTORS];
UChar selectorMtf[BZ_MAX_SELECTORS];
UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 code [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 rfreq[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
}
EState;
/*-- externs for compression. --*/
extern void
blockSort ( EState* );
extern void
compressBlock ( EState*, Bool );
extern void
bsInitWrite ( EState* );
extern void
hbAssignCodes ( Int32*, UChar*, Int32, Int32, Int32 );
extern void
hbMakeCodeLengths ( UChar*, Int32*, Int32, Int32 );
/*-- states for decompression. --*/
#define BZ_X_IDLE 1
#define BZ_X_OUTPUT 2
#define BZ_X_MAGIC_1 10
#define BZ_X_MAGIC_2 11
#define BZ_X_MAGIC_3 12
#define BZ_X_MAGIC_4 13
#define BZ_X_BLKHDR_1 14
#define BZ_X_BLKHDR_2 15
#define BZ_X_BLKHDR_3 16
#define BZ_X_BLKHDR_4 17
#define BZ_X_BLKHDR_5 18
#define BZ_X_BLKHDR_6 19
#define BZ_X_BCRC_1 20
#define BZ_X_BCRC_2 21
#define BZ_X_BCRC_3 22
#define BZ_X_BCRC_4 23
#define BZ_X_RANDBIT 24
#define BZ_X_ORIGPTR_1 25
#define BZ_X_ORIGPTR_2 26
#define BZ_X_ORIGPTR_3 27
#define BZ_X_MAPPING_1 28
#define BZ_X_MAPPING_2 29
#define BZ_X_SELECTOR_1 30
#define BZ_X_SELECTOR_2 31
#define BZ_X_SELECTOR_3 32
#define BZ_X_CODING_1 33
#define BZ_X_CODING_2 34
#define BZ_X_CODING_3 35
#define BZ_X_MTF_1 36
#define BZ_X_MTF_2 37
#define BZ_X_MTF_3 38
#define BZ_X_MTF_4 39
#define BZ_X_MTF_5 40
#define BZ_X_MTF_6 41
#define BZ_X_ENDHDR_2 42
#define BZ_X_ENDHDR_3 43
#define BZ_X_ENDHDR_4 44
#define BZ_X_ENDHDR_5 45
#define BZ_X_ENDHDR_6 46
#define BZ_X_CCRC_1 47
#define BZ_X_CCRC_2 48
#define BZ_X_CCRC_3 49
#define BZ_X_CCRC_4 50
/*-- Constants for the fast MTF decoder. --*/
#define MTFA_SIZE 4096
#define MTFL_SIZE 16
/*-- Structure holding all the decompression-side stuff. --*/
typedef
struct {
/* pointer back to the struct bz_stream */
bz_stream* strm;
/* state indicator for this stream */
Int32 state;
/* for doing the final run-length decoding */
UChar state_out_ch;
Int32 state_out_len;
Bool blockRandomised;
BZ_RAND_DECLS;
/* the buffer for bit stream reading */
UInt32 bsBuff;
Int32 bsLive;
/* misc administratium */
Int32 blockSize100k;
Bool smallDecompress;
Int32 currBlockNo;
Int32 verbosity;
/* for undoing the Burrows-Wheeler transform */
Int32 origPtr;
UInt32 tPos;
Int32 k0;
Int32 unzftab[256];
Int32 nblock_used;
Int32 cftab[257];
Int32 cftabCopy[257];
/* for undoing the Burrows-Wheeler transform (FAST) */
UInt32 *tt;
/* for undoing the Burrows-Wheeler transform (SMALL) */
UInt16 *ll16;
UChar *ll4;
/* stored and calculated CRCs */
UInt32 storedBlockCRC;
UInt32 storedCombinedCRC;
UInt32 calculatedBlockCRC;
UInt32 calculatedCombinedCRC;
/* map of bytes used in block */
Int32 nInUse;
Bool inUse[256];
Bool inUse16[16];
UChar seqToUnseq[256];
/* for decoding the MTF values */
UChar mtfa [MTFA_SIZE];
Int32 mtfbase[256 / MTFL_SIZE];
UChar selector [BZ_MAX_SELECTORS];
UChar selectorMtf[BZ_MAX_SELECTORS];
UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 limit [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 base [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 perm [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 minLens[BZ_N_GROUPS];
/* save area for scalars in the main decompress code */
Int32 save_i;
Int32 save_j;
Int32 save_t;
Int32 save_alphaSize;
Int32 save_nGroups;
Int32 save_nSelectors;
Int32 save_EOB;
Int32 save_groupNo;
Int32 save_groupPos;
Int32 save_nextSym;
Int32 save_nblockMAX;
Int32 save_nblock;
Int32 save_es;
Int32 save_N;
Int32 save_curr;
Int32 save_zt;
Int32 save_zn;
Int32 save_zvec;
Int32 save_zj;
Int32 save_gSel;
Int32 save_gMinlen;
Int32* save_gLimit;
Int32* save_gBase;
Int32* save_gPerm;
}
DState;
/*-- Macros for decompression. --*/
#define BZ_GET_FAST(cccc) \
s->tPos = s->tt[s->tPos]; \
cccc = (UChar)(s->tPos & 0xff); \
s->tPos >>= 8;
#define BZ_GET_FAST_C(cccc) \
c_tPos = c_tt[c_tPos]; \
cccc = (UChar)(c_tPos & 0xff); \
c_tPos >>= 8;
#define SET_LL4(i,n) \
{ if (((i) & 0x1) == 0) \
s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0xf0) | (n); else \
s->ll4[(i) >> 1] = (s->ll4[(i) >> 1] & 0x0f) | ((n) << 4); \
}
#define GET_LL4(i) \
(((UInt32)(s->ll4[(i) >> 1])) >> (((i) << 2) & 0x4) & 0xF)
#define SET_LL(i,n) \
{ s->ll16[i] = (UInt16)(n & 0x0000ffff); \
SET_LL4(i, n >> 16); \
}
#define GET_LL(i) \
(((UInt32)s->ll16[i]) | (GET_LL4(i) << 16))
#define BZ_GET_SMALL(cccc) \
cccc = indexIntoF ( s->tPos, s->cftab ); \
s->tPos = GET_LL(s->tPos);
/*-- externs for decompression. --*/
extern Int32
indexIntoF ( Int32, Int32* );
extern Int32
decompress ( DState* );
extern void
hbCreateDecodeTables ( Int32*, Int32*, Int32*, UChar*,
Int32, Int32, Int32 );
#endif
/*-- BZ_NO_STDIO seems to make NULL disappear on some platforms. --*/
#ifdef BZ_NO_STDIO
#ifndef NULL
#define NULL 0
#endif
#endif
/*-------------------------------------------------------------*/
/*--- end bzlib_private.h ---*/
/*-------------------------------------------------------------*/

588
compress.c Normal file
View File

@ -0,0 +1,588 @@
/*-------------------------------------------------------------*/
/*--- Compression machinery (not incl block sorting) ---*/
/*--- compress.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0 of 28 June 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
/*--
CHANGES
~~~~~~~
0.9.0 -- original version.
0.9.0a/b -- no changes in this file.
0.9.0c
* changed setting of nGroups in sendMTFValues() so as to
do a bit better on small files
--*/
#include "bzlib_private.h"
/*---------------------------------------------------*/
/*--- Bit stream I/O ---*/
/*---------------------------------------------------*/
/*---------------------------------------------------*/
void bsInitWrite ( EState* s )
{
s->bsLive = 0;
s->bsBuff = 0;
}
/*---------------------------------------------------*/
static
void bsFinishWrite ( EState* s )
{
while (s->bsLive > 0) {
((UChar*)(s->quadrant))[s->numZ] = (UChar)(s->bsBuff >> 24);
s->numZ++;
s->bsBuff <<= 8;
s->bsLive -= 8;
}
}
/*---------------------------------------------------*/
#define bsNEEDW(nz) \
{ \
while (s->bsLive >= 8) { \
((UChar*)(s->quadrant))[s->numZ] \
= (UChar)(s->bsBuff >> 24); \
s->numZ++; \
s->bsBuff <<= 8; \
s->bsLive -= 8; \
} \
}
/*---------------------------------------------------*/
static
void bsW ( EState* s, Int32 n, UInt32 v )
{
bsNEEDW ( n );
s->bsBuff |= (v << (32 - s->bsLive - n));
s->bsLive += n;
}
/*---------------------------------------------------*/
static
void bsPutUInt32 ( EState* s, UInt32 u )
{
bsW ( s, 8, (u >> 24) & 0xffL );
bsW ( s, 8, (u >> 16) & 0xffL );
bsW ( s, 8, (u >> 8) & 0xffL );
bsW ( s, 8, u & 0xffL );
}
/*---------------------------------------------------*/
static
void bsPutUChar ( EState* s, UChar c )
{
bsW( s, 8, (UInt32)c );
}
/*---------------------------------------------------*/
/*--- The back end proper ---*/
/*---------------------------------------------------*/
/*---------------------------------------------------*/
static
void makeMaps_e ( EState* s )
{
Int32 i;
s->nInUse = 0;
for (i = 0; i < 256; i++)
if (s->inUse[i]) {
s->unseqToSeq[i] = s->nInUse;
s->nInUse++;
}
}
/*---------------------------------------------------*/
static
void generateMTFValues ( EState* s )
{
UChar yy[256];
Int32 i, j;
UChar tmp;
UChar tmp2;
Int32 zPend;
Int32 wr;
Int32 EOB;
makeMaps_e ( s );
EOB = s->nInUse+1;
for (i = 0; i <= EOB; i++) s->mtfFreq[i] = 0;
wr = 0;
zPend = 0;
for (i = 0; i < s->nInUse; i++) yy[i] = (UChar) i;
for (i = 0; i < s->nblock; i++) {
UChar ll_i;
AssertD ( wr <= i, "generateMTFValues(1)" );
j = s->zptr[i]-1; if (j < 0) j += s->nblock;
ll_i = s->unseqToSeq[s->block[j]];
AssertD ( ll_i < s->nInUse, "generateMTFValues(2a)" );
j = 0;
tmp = yy[j];
while ( ll_i != tmp ) {
j++;
tmp2 = tmp;
tmp = yy[j];
yy[j] = tmp2;
};
yy[0] = tmp;
if (j == 0) {
zPend++;
} else {
if (zPend > 0) {
zPend--;
while (True) {
switch (zPend % 2) {
case 0: s->szptr[wr] = BZ_RUNA; wr++; s->mtfFreq[BZ_RUNA]++; break;
case 1: s->szptr[wr] = BZ_RUNB; wr++; s->mtfFreq[BZ_RUNB]++; break;
};
if (zPend < 2) break;
zPend = (zPend - 2) / 2;
};
zPend = 0;
}
s->szptr[wr] = j+1; wr++; s->mtfFreq[j+1]++;
}
}
if (zPend > 0) {
zPend--;
while (True) {
switch (zPend % 2) {
case 0: s->szptr[wr] = BZ_RUNA; wr++; s->mtfFreq[BZ_RUNA]++; break;
case 1: s->szptr[wr] = BZ_RUNB; wr++; s->mtfFreq[BZ_RUNB]++; break;
};
if (zPend < 2) break;
zPend = (zPend - 2) / 2;
};
}
s->szptr[wr] = EOB; wr++; s->mtfFreq[EOB]++;
s->nMTF = wr;
}
/*---------------------------------------------------*/
#define BZ_LESSER_ICOST 0
#define BZ_GREATER_ICOST 15
static
void sendMTFValues ( EState* s )
{
Int32 v, t, i, j, gs, ge, totc, bt, bc, iter;
Int32 nSelectors, alphaSize, minLen, maxLen, selCtr;
Int32 nGroups, nBytes;
/*--
UChar len [BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
is a global since the decoder also needs it.
Int32 code[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
Int32 rfreq[BZ_N_GROUPS][BZ_MAX_ALPHA_SIZE];
are also globals only used in this proc.
Made global to keep stack frame size small.
--*/
UInt16 cost[BZ_N_GROUPS];
Int32 fave[BZ_N_GROUPS];
if (s->verbosity >= 3)
VPrintf3( " %d in block, %d after MTF & 1-2 coding, "
"%d+2 syms in use\n",
s->nblock, s->nMTF, s->nInUse );
alphaSize = s->nInUse+2;
for (t = 0; t < BZ_N_GROUPS; t++)
for (v = 0; v < alphaSize; v++)
s->len[t][v] = BZ_GREATER_ICOST;
/*--- Decide how many coding tables to use ---*/
AssertH ( s->nMTF > 0, 3001 );
if (s->nMTF < 200) nGroups = 2; else
if (s->nMTF < 600) nGroups = 3; else
if (s->nMTF < 1200) nGroups = 4; else
if (s->nMTF < 2400) nGroups = 5; else
nGroups = 6;
/*--- Generate an initial set of coding tables ---*/
{
Int32 nPart, remF, tFreq, aFreq;
nPart = nGroups;
remF = s->nMTF;
gs = 0;
while (nPart > 0) {
tFreq = remF / nPart;
ge = gs-1;
aFreq = 0;
while (aFreq < tFreq && ge < alphaSize-1) {
ge++;
aFreq += s->mtfFreq[ge];
}
if (ge > gs
&& nPart != nGroups && nPart != 1
&& ((nGroups-nPart) % 2 == 1)) {
aFreq -= s->mtfFreq[ge];
ge--;
}
if (s->verbosity >= 3)
VPrintf5( " initial group %d, [%d .. %d], "
"has %d syms (%4.1f%%)\n",
nPart, gs, ge, aFreq,
(100.0 * (float)aFreq) / (float)(s->nMTF) );
for (v = 0; v < alphaSize; v++)
if (v >= gs && v <= ge)
s->len[nPart-1][v] = BZ_LESSER_ICOST; else
s->len[nPart-1][v] = BZ_GREATER_ICOST;
nPart--;
gs = ge+1;
remF -= aFreq;
}
}
/*---
Iterate up to BZ_N_ITERS times to improve the tables.
---*/
for (iter = 0; iter < BZ_N_ITERS; iter++) {
for (t = 0; t < nGroups; t++) fave[t] = 0;
for (t = 0; t < nGroups; t++)
for (v = 0; v < alphaSize; v++)
s->rfreq[t][v] = 0;
nSelectors = 0;
totc = 0;
gs = 0;
while (True) {
/*--- Set group start & end marks. --*/
if (gs >= s->nMTF) break;
ge = gs + BZ_G_SIZE - 1;
if (ge >= s->nMTF) ge = s->nMTF-1;
/*--
Calculate the cost of this group as coded
by each of the coding tables.
--*/
for (t = 0; t < nGroups; t++) cost[t] = 0;
if (nGroups == 6) {
register UInt16 cost0, cost1, cost2, cost3, cost4, cost5;
cost0 = cost1 = cost2 = cost3 = cost4 = cost5 = 0;
for (i = gs; i <= ge; i++) {
UInt16 icv = s->szptr[i];
cost0 += s->len[0][icv];
cost1 += s->len[1][icv];
cost2 += s->len[2][icv];
cost3 += s->len[3][icv];
cost4 += s->len[4][icv];
cost5 += s->len[5][icv];
}
cost[0] = cost0; cost[1] = cost1; cost[2] = cost2;
cost[3] = cost3; cost[4] = cost4; cost[5] = cost5;
} else {
for (i = gs; i <= ge; i++) {
UInt16 icv = s->szptr[i];
for (t = 0; t < nGroups; t++) cost[t] += s->len[t][icv];
}
}
/*--
Find the coding table which is best for this group,
and record its identity in the selector table.
--*/
bc = 999999999; bt = -1;
for (t = 0; t < nGroups; t++)
if (cost[t] < bc) { bc = cost[t]; bt = t; };
totc += bc;
fave[bt]++;
s->selector[nSelectors] = bt;
nSelectors++;
/*--
Increment the symbol frequencies for the selected table.
--*/
for (i = gs; i <= ge; i++)
s->rfreq[bt][ s->szptr[i] ]++;
gs = ge+1;
}
if (s->verbosity >= 3) {
VPrintf2 ( " pass %d: size is %d, grp uses are ",
iter+1, totc/8 );
for (t = 0; t < nGroups; t++)
VPrintf1 ( "%d ", fave[t] );
VPrintf0 ( "\n" );
}
/*--
Recompute the tables based on the accumulated frequencies.
--*/
for (t = 0; t < nGroups; t++)
hbMakeCodeLengths ( &(s->len[t][0]), &(s->rfreq[t][0]),
alphaSize, 20 );
}
AssertH( nGroups < 8, 3002 );
AssertH( nSelectors < 32768 &&
nSelectors <= (2 + (900000 / BZ_G_SIZE)),
3003 );
/*--- Compute MTF values for the selectors. ---*/
{
UChar pos[BZ_N_GROUPS], ll_i, tmp2, tmp;
for (i = 0; i < nGroups; i++) pos[i] = i;
for (i = 0; i < nSelectors; i++) {
ll_i = s->selector[i];
j = 0;
tmp = pos[j];
while ( ll_i != tmp ) {
j++;
tmp2 = tmp;
tmp = pos[j];
pos[j] = tmp2;
};
pos[0] = tmp;
s->selectorMtf[i] = j;
}
};
/*--- Assign actual codes for the tables. --*/
for (t = 0; t < nGroups; t++) {
minLen = 32;
maxLen = 0;
for (i = 0; i < alphaSize; i++) {
if (s->len[t][i] > maxLen) maxLen = s->len[t][i];
if (s->len[t][i] < minLen) minLen = s->len[t][i];
}
AssertH ( !(maxLen > 20), 3004 );
AssertH ( !(minLen < 1), 3005 );
hbAssignCodes ( &(s->code[t][0]), &(s->len[t][0]),
minLen, maxLen, alphaSize );
}
/*--- Transmit the mapping table. ---*/
{
Bool inUse16[16];
for (i = 0; i < 16; i++) {
inUse16[i] = False;
for (j = 0; j < 16; j++)
if (s->inUse[i * 16 + j]) inUse16[i] = True;
}
nBytes = s->numZ;
for (i = 0; i < 16; i++)
if (inUse16[i]) bsW(s,1,1); else bsW(s,1,0);
for (i = 0; i < 16; i++)
if (inUse16[i])
for (j = 0; j < 16; j++) {
if (s->inUse[i * 16 + j]) bsW(s,1,1); else bsW(s,1,0);
}
if (s->verbosity >= 3)
VPrintf1( " bytes: mapping %d, ", s->numZ-nBytes );
}
/*--- Now the selectors. ---*/
nBytes = s->numZ;
bsW ( s, 3, nGroups );
bsW ( s, 15, nSelectors );
for (i = 0; i < nSelectors; i++) {
for (j = 0; j < s->selectorMtf[i]; j++) bsW(s,1,1);
bsW(s,1,0);
}
if (s->verbosity >= 3)
VPrintf1( "selectors %d, ", s->numZ-nBytes );
/*--- Now the coding tables. ---*/
nBytes = s->numZ;
for (t = 0; t < nGroups; t++) {
Int32 curr = s->len[t][0];
bsW ( s, 5, curr );
for (i = 0; i < alphaSize; i++) {
while (curr < s->len[t][i]) { bsW(s,2,2); curr++; /* 10 */ };
while (curr > s->len[t][i]) { bsW(s,2,3); curr--; /* 11 */ };
bsW ( s, 1, 0 );
}
}
if (s->verbosity >= 3)
VPrintf1 ( "code lengths %d, ", s->numZ-nBytes );
/*--- And finally, the block data proper ---*/
nBytes = s->numZ;
selCtr = 0;
gs = 0;
while (True) {
if (gs >= s->nMTF) break;
ge = gs + BZ_G_SIZE - 1;
if (ge >= s->nMTF) ge = s->nMTF-1;
for (i = gs; i <= ge; i++) {
AssertH ( s->selector[selCtr] < nGroups, 3006 );
bsW ( s,
s->len [s->selector[selCtr]] [s->szptr[i]],
s->code [s->selector[selCtr]] [s->szptr[i]] );
}
gs = ge+1;
selCtr++;
}
AssertH( selCtr == nSelectors, 3007 );
if (s->verbosity >= 3)
VPrintf1( "codes %d\n", s->numZ-nBytes );
}
/*---------------------------------------------------*/
void compressBlock ( EState* s, Bool is_last_block )
{
if (s->nblock > 0) {
BZ_FINALISE_CRC ( s->blockCRC );
s->combinedCRC = (s->combinedCRC << 1) | (s->combinedCRC >> 31);
s->combinedCRC ^= s->blockCRC;
if (s->blockNo > 1) s->numZ = 0;
if (s->verbosity >= 2)
VPrintf4( " block %d: crc = 0x%8x, "
"combined CRC = 0x%8x, size = %d\n",
s->blockNo, s->blockCRC, s->combinedCRC, s->nblock );
blockSort ( s );
}
/*-- If this is the first block, create the stream header. --*/
if (s->blockNo == 1) {
bsInitWrite ( s );
bsPutUChar ( s, 'B' );
bsPutUChar ( s, 'Z' );
bsPutUChar ( s, 'h' );
bsPutUChar ( s, '0' + s->blockSize100k );
}
if (s->nblock > 0) {
bsPutUChar ( s, 0x31 ); bsPutUChar ( s, 0x41 );
bsPutUChar ( s, 0x59 ); bsPutUChar ( s, 0x26 );
bsPutUChar ( s, 0x53 ); bsPutUChar ( s, 0x59 );
/*-- Now the block's CRC, so it is in a known place. --*/
bsPutUInt32 ( s, s->blockCRC );
/*-- Now a single bit indicating randomisation. --*/
if (s->blockRandomised) {
bsW(s,1,1); s->nBlocksRandomised++;
} else
bsW(s,1,0);
bsW ( s, 24, s->origPtr );
generateMTFValues ( s );
sendMTFValues ( s );
}
/*-- If this is the last block, add the stream trailer. --*/
if (is_last_block) {
if (s->verbosity >= 2 && s->nBlocksRandomised > 0)
VPrintf2 ( " %d block%s needed randomisation\n",
s->nBlocksRandomised,
s->nBlocksRandomised == 1 ? "" : "s" );
bsPutUChar ( s, 0x17 ); bsPutUChar ( s, 0x72 );
bsPutUChar ( s, 0x45 ); bsPutUChar ( s, 0x38 );
bsPutUChar ( s, 0x50 ); bsPutUChar ( s, 0x90 );
bsPutUInt32 ( s, s->combinedCRC );
if (s->verbosity >= 2)
VPrintf1( " final combined CRC = 0x%x\n ", s->combinedCRC );
bsFinishWrite ( s );
}
}
/*-------------------------------------------------------------*/
/*--- end compress.c ---*/
/*-------------------------------------------------------------*/

144
crctable.c Normal file
View File

@ -0,0 +1,144 @@
/*-------------------------------------------------------------*/
/*--- Table for doing CRCs ---*/
/*--- crctable.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#include "bzlib_private.h"
/*--
I think this is an implementation of the AUTODIN-II,
Ethernet & FDDI 32-bit CRC standard. Vaguely derived
from code by Rob Warnock, in Section 51 of the
comp.compression FAQ.
--*/
UInt32 crc32Table[256] = {
/*-- Ugly, innit? --*/
0x00000000L, 0x04c11db7L, 0x09823b6eL, 0x0d4326d9L,
0x130476dcL, 0x17c56b6bL, 0x1a864db2L, 0x1e475005L,
0x2608edb8L, 0x22c9f00fL, 0x2f8ad6d6L, 0x2b4bcb61L,
0x350c9b64L, 0x31cd86d3L, 0x3c8ea00aL, 0x384fbdbdL,
0x4c11db70L, 0x48d0c6c7L, 0x4593e01eL, 0x4152fda9L,
0x5f15adacL, 0x5bd4b01bL, 0x569796c2L, 0x52568b75L,
0x6a1936c8L, 0x6ed82b7fL, 0x639b0da6L, 0x675a1011L,
0x791d4014L, 0x7ddc5da3L, 0x709f7b7aL, 0x745e66cdL,
0x9823b6e0L, 0x9ce2ab57L, 0x91a18d8eL, 0x95609039L,
0x8b27c03cL, 0x8fe6dd8bL, 0x82a5fb52L, 0x8664e6e5L,
0xbe2b5b58L, 0xbaea46efL, 0xb7a96036L, 0xb3687d81L,
0xad2f2d84L, 0xa9ee3033L, 0xa4ad16eaL, 0xa06c0b5dL,
0xd4326d90L, 0xd0f37027L, 0xddb056feL, 0xd9714b49L,
0xc7361b4cL, 0xc3f706fbL, 0xceb42022L, 0xca753d95L,
0xf23a8028L, 0xf6fb9d9fL, 0xfbb8bb46L, 0xff79a6f1L,
0xe13ef6f4L, 0xe5ffeb43L, 0xe8bccd9aL, 0xec7dd02dL,
0x34867077L, 0x30476dc0L, 0x3d044b19L, 0x39c556aeL,
0x278206abL, 0x23431b1cL, 0x2e003dc5L, 0x2ac12072L,
0x128e9dcfL, 0x164f8078L, 0x1b0ca6a1L, 0x1fcdbb16L,
0x018aeb13L, 0x054bf6a4L, 0x0808d07dL, 0x0cc9cdcaL,
0x7897ab07L, 0x7c56b6b0L, 0x71159069L, 0x75d48ddeL,
0x6b93dddbL, 0x6f52c06cL, 0x6211e6b5L, 0x66d0fb02L,
0x5e9f46bfL, 0x5a5e5b08L, 0x571d7dd1L, 0x53dc6066L,
0x4d9b3063L, 0x495a2dd4L, 0x44190b0dL, 0x40d816baL,
0xaca5c697L, 0xa864db20L, 0xa527fdf9L, 0xa1e6e04eL,
0xbfa1b04bL, 0xbb60adfcL, 0xb6238b25L, 0xb2e29692L,
0x8aad2b2fL, 0x8e6c3698L, 0x832f1041L, 0x87ee0df6L,
0x99a95df3L, 0x9d684044L, 0x902b669dL, 0x94ea7b2aL,
0xe0b41de7L, 0xe4750050L, 0xe9362689L, 0xedf73b3eL,
0xf3b06b3bL, 0xf771768cL, 0xfa325055L, 0xfef34de2L,
0xc6bcf05fL, 0xc27dede8L, 0xcf3ecb31L, 0xcbffd686L,
0xd5b88683L, 0xd1799b34L, 0xdc3abdedL, 0xd8fba05aL,
0x690ce0eeL, 0x6dcdfd59L, 0x608edb80L, 0x644fc637L,
0x7a089632L, 0x7ec98b85L, 0x738aad5cL, 0x774bb0ebL,
0x4f040d56L, 0x4bc510e1L, 0x46863638L, 0x42472b8fL,
0x5c007b8aL, 0x58c1663dL, 0x558240e4L, 0x51435d53L,
0x251d3b9eL, 0x21dc2629L, 0x2c9f00f0L, 0x285e1d47L,
0x36194d42L, 0x32d850f5L, 0x3f9b762cL, 0x3b5a6b9bL,
0x0315d626L, 0x07d4cb91L, 0x0a97ed48L, 0x0e56f0ffL,
0x1011a0faL, 0x14d0bd4dL, 0x19939b94L, 0x1d528623L,
0xf12f560eL, 0xf5ee4bb9L, 0xf8ad6d60L, 0xfc6c70d7L,
0xe22b20d2L, 0xe6ea3d65L, 0xeba91bbcL, 0xef68060bL,
0xd727bbb6L, 0xd3e6a601L, 0xdea580d8L, 0xda649d6fL,
0xc423cd6aL, 0xc0e2d0ddL, 0xcda1f604L, 0xc960ebb3L,
0xbd3e8d7eL, 0xb9ff90c9L, 0xb4bcb610L, 0xb07daba7L,
0xae3afba2L, 0xaafbe615L, 0xa7b8c0ccL, 0xa379dd7bL,
0x9b3660c6L, 0x9ff77d71L, 0x92b45ba8L, 0x9675461fL,
0x8832161aL, 0x8cf30badL, 0x81b02d74L, 0x857130c3L,
0x5d8a9099L, 0x594b8d2eL, 0x5408abf7L, 0x50c9b640L,
0x4e8ee645L, 0x4a4ffbf2L, 0x470cdd2bL, 0x43cdc09cL,
0x7b827d21L, 0x7f436096L, 0x7200464fL, 0x76c15bf8L,
0x68860bfdL, 0x6c47164aL, 0x61043093L, 0x65c52d24L,
0x119b4be9L, 0x155a565eL, 0x18197087L, 0x1cd86d30L,
0x029f3d35L, 0x065e2082L, 0x0b1d065bL, 0x0fdc1becL,
0x3793a651L, 0x3352bbe6L, 0x3e119d3fL, 0x3ad08088L,
0x2497d08dL, 0x2056cd3aL, 0x2d15ebe3L, 0x29d4f654L,
0xc5a92679L, 0xc1683bceL, 0xcc2b1d17L, 0xc8ea00a0L,
0xd6ad50a5L, 0xd26c4d12L, 0xdf2f6bcbL, 0xdbee767cL,
0xe3a1cbc1L, 0xe760d676L, 0xea23f0afL, 0xeee2ed18L,
0xf0a5bd1dL, 0xf464a0aaL, 0xf9278673L, 0xfde69bc4L,
0x89b8fd09L, 0x8d79e0beL, 0x803ac667L, 0x84fbdbd0L,
0x9abc8bd5L, 0x9e7d9662L, 0x933eb0bbL, 0x97ffad0cL,
0xafb010b1L, 0xab710d06L, 0xa6322bdfL, 0xa2f33668L,
0xbcb4666dL, 0xb8757bdaL, 0xb5365d03L, 0xb1f740b4L
};
/*-------------------------------------------------------------*/
/*--- end crctable.c ---*/
/*-------------------------------------------------------------*/

636
decompress.c Normal file
View File

@ -0,0 +1,636 @@
/*-------------------------------------------------------------*/
/*--- Decompression machinery ---*/
/*--- decompress.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#include "bzlib_private.h"
/*---------------------------------------------------*/
static
void makeMaps_d ( DState* s )
{
Int32 i;
s->nInUse = 0;
for (i = 0; i < 256; i++)
if (s->inUse[i]) {
s->seqToUnseq[s->nInUse] = i;
s->nInUse++;
}
}
/*---------------------------------------------------*/
#define RETURN(rrr) \
{ retVal = rrr; goto save_state_and_return; };
#define GET_BITS(lll,vvv,nnn) \
case lll: s->state = lll; \
while (True) { \
if (s->bsLive >= nnn) { \
UInt32 v; \
v = (s->bsBuff >> \
(s->bsLive-nnn)) & ((1 << nnn)-1); \
s->bsLive -= nnn; \
vvv = v; \
break; \
} \
if (s->strm->avail_in == 0) RETURN(BZ_OK); \
s->bsBuff \
= (s->bsBuff << 8) | \
((UInt32) \
(*((UChar*)(s->strm->next_in)))); \
s->bsLive += 8; \
s->strm->next_in++; \
s->strm->avail_in--; \
s->strm->total_in++; \
}
#define GET_UCHAR(lll,uuu) \
GET_BITS(lll,uuu,8)
#define GET_BIT(lll,uuu) \
GET_BITS(lll,uuu,1)
/*---------------------------------------------------*/
#define GET_MTF_VAL(label1,label2,lval) \
{ \
if (groupPos == 0) { \
groupNo++; \
groupPos = BZ_G_SIZE; \
gSel = s->selector[groupNo]; \
gMinlen = s->minLens[gSel]; \
gLimit = &(s->limit[gSel][0]); \
gPerm = &(s->perm[gSel][0]); \
gBase = &(s->base[gSel][0]); \
} \
groupPos--; \
zn = gMinlen; \
GET_BITS(label1, zvec, zn); \
while (zvec > gLimit[zn]) { \
zn++; \
GET_BIT(label2, zj); \
zvec = (zvec << 1) | zj; \
}; \
lval = gPerm[zvec - gBase[zn]]; \
}
/*---------------------------------------------------*/
Int32 decompress ( DState* s )
{
UChar uc;
Int32 retVal;
Int32 minLen, maxLen;
bz_stream* strm = s->strm;
/* stuff that needs to be saved/restored */
Int32 i ;
Int32 j;
Int32 t;
Int32 alphaSize;
Int32 nGroups;
Int32 nSelectors;
Int32 EOB;
Int32 groupNo;
Int32 groupPos;
Int32 nextSym;
Int32 nblockMAX;
Int32 nblock;
Int32 es;
Int32 N;
Int32 curr;
Int32 zt;
Int32 zn;
Int32 zvec;
Int32 zj;
Int32 gSel;
Int32 gMinlen;
Int32* gLimit;
Int32* gBase;
Int32* gPerm;
if (s->state == BZ_X_MAGIC_1) {
/*initialise the save area*/
s->save_i = 0;
s->save_j = 0;
s->save_t = 0;
s->save_alphaSize = 0;
s->save_nGroups = 0;
s->save_nSelectors = 0;
s->save_EOB = 0;
s->save_groupNo = 0;
s->save_groupPos = 0;
s->save_nextSym = 0;
s->save_nblockMAX = 0;
s->save_nblock = 0;
s->save_es = 0;
s->save_N = 0;
s->save_curr = 0;
s->save_zt = 0;
s->save_zn = 0;
s->save_zvec = 0;
s->save_zj = 0;
s->save_gSel = 0;
s->save_gMinlen = 0;
s->save_gLimit = NULL;
s->save_gBase = NULL;
s->save_gPerm = NULL;
}
/*restore from the save area*/
i = s->save_i;
j = s->save_j;
t = s->save_t;
alphaSize = s->save_alphaSize;
nGroups = s->save_nGroups;
nSelectors = s->save_nSelectors;
EOB = s->save_EOB;
groupNo = s->save_groupNo;
groupPos = s->save_groupPos;
nextSym = s->save_nextSym;
nblockMAX = s->save_nblockMAX;
nblock = s->save_nblock;
es = s->save_es;
N = s->save_N;
curr = s->save_curr;
zt = s->save_zt;
zn = s->save_zn;
zvec = s->save_zvec;
zj = s->save_zj;
gSel = s->save_gSel;
gMinlen = s->save_gMinlen;
gLimit = s->save_gLimit;
gBase = s->save_gBase;
gPerm = s->save_gPerm;
retVal = BZ_OK;
switch (s->state) {
GET_UCHAR(BZ_X_MAGIC_1, uc);
if (uc != 'B') RETURN(BZ_DATA_ERROR_MAGIC);
GET_UCHAR(BZ_X_MAGIC_2, uc);
if (uc != 'Z') RETURN(BZ_DATA_ERROR_MAGIC);
GET_UCHAR(BZ_X_MAGIC_3, uc)
if (uc != 'h') RETURN(BZ_DATA_ERROR_MAGIC);
GET_BITS(BZ_X_MAGIC_4, s->blockSize100k, 8)
if (s->blockSize100k < '1' ||
s->blockSize100k > '9') RETURN(BZ_DATA_ERROR_MAGIC);
s->blockSize100k -= '0';
if (s->smallDecompress) {
s->ll16 = BZALLOC( s->blockSize100k * 100000 * sizeof(UInt16) );
s->ll4 = BZALLOC(
((1 + s->blockSize100k * 100000) >> 1) * sizeof(UChar)
);
if (s->ll16 == NULL || s->ll4 == NULL) RETURN(BZ_MEM_ERROR);
} else {
s->tt = BZALLOC( s->blockSize100k * 100000 * sizeof(Int32) );
if (s->tt == NULL) RETURN(BZ_MEM_ERROR);
}
GET_UCHAR(BZ_X_BLKHDR_1, uc);
if (uc == 0x17) goto endhdr_2;
if (uc != 0x31) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_BLKHDR_2, uc);
if (uc != 0x41) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_BLKHDR_3, uc);
if (uc != 0x59) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_BLKHDR_4, uc);
if (uc != 0x26) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_BLKHDR_5, uc);
if (uc != 0x53) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_BLKHDR_6, uc);
if (uc != 0x59) RETURN(BZ_DATA_ERROR);
s->currBlockNo++;
if (s->verbosity >= 2)
VPrintf1 ( "\n [%d: huff+mtf ", s->currBlockNo );
s->storedBlockCRC = 0;
GET_UCHAR(BZ_X_BCRC_1, uc);
s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_BCRC_2, uc);
s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_BCRC_3, uc);
s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_BCRC_4, uc);
s->storedBlockCRC = (s->storedBlockCRC << 8) | ((UInt32)uc);
GET_BITS(BZ_X_RANDBIT, s->blockRandomised, 1);
s->origPtr = 0;
GET_UCHAR(BZ_X_ORIGPTR_1, uc);
s->origPtr = (s->origPtr << 8) | ((Int32)uc);
GET_UCHAR(BZ_X_ORIGPTR_2, uc);
s->origPtr = (s->origPtr << 8) | ((Int32)uc);
GET_UCHAR(BZ_X_ORIGPTR_3, uc);
s->origPtr = (s->origPtr << 8) | ((Int32)uc);
/*--- Receive the mapping table ---*/
for (i = 0; i < 16; i++) {
GET_BIT(BZ_X_MAPPING_1, uc);
if (uc == 1)
s->inUse16[i] = True; else
s->inUse16[i] = False;
}
for (i = 0; i < 256; i++) s->inUse[i] = False;
for (i = 0; i < 16; i++)
if (s->inUse16[i])
for (j = 0; j < 16; j++) {
GET_BIT(BZ_X_MAPPING_2, uc);
if (uc == 1) s->inUse[i * 16 + j] = True;
}
makeMaps_d ( s );
alphaSize = s->nInUse+2;
/*--- Now the selectors ---*/
GET_BITS(BZ_X_SELECTOR_1, nGroups, 3);
GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15);
for (i = 0; i < nSelectors; i++) {
j = 0;
while (True) {
GET_BIT(BZ_X_SELECTOR_3, uc);
if (uc == 0) break;
j++;
if (j > 5) RETURN(BZ_DATA_ERROR);
}
s->selectorMtf[i] = j;
}
/*--- Undo the MTF values for the selectors. ---*/
{
UChar pos[BZ_N_GROUPS], tmp, v;
for (v = 0; v < nGroups; v++) pos[v] = v;
for (i = 0; i < nSelectors; i++) {
v = s->selectorMtf[i];
tmp = pos[v];
while (v > 0) { pos[v] = pos[v-1]; v--; }
pos[0] = tmp;
s->selector[i] = tmp;
}
}
/*--- Now the coding tables ---*/
for (t = 0; t < nGroups; t++) {
GET_BITS(BZ_X_CODING_1, curr, 5);
for (i = 0; i < alphaSize; i++) {
while (True) {
if (curr < 1 || curr > 20) RETURN(BZ_DATA_ERROR);
GET_BIT(BZ_X_CODING_2, uc);
if (uc == 0) break;
GET_BIT(BZ_X_CODING_3, uc);
if (uc == 0) curr++; else curr--;
}
s->len[t][i] = curr;
}
}
/*--- Create the Huffman decoding tables ---*/
for (t = 0; t < nGroups; t++) {
minLen = 32;
maxLen = 0;
for (i = 0; i < alphaSize; i++) {
if (s->len[t][i] > maxLen) maxLen = s->len[t][i];
if (s->len[t][i] < minLen) minLen = s->len[t][i];
}
hbCreateDecodeTables (
&(s->limit[t][0]),
&(s->base[t][0]),
&(s->perm[t][0]),
&(s->len[t][0]),
minLen, maxLen, alphaSize
);
s->minLens[t] = minLen;
}
/*--- Now the MTF values ---*/
EOB = s->nInUse+1;
nblockMAX = 100000 * s->blockSize100k;
groupNo = -1;
groupPos = 0;
for (i = 0; i <= 255; i++) s->unzftab[i] = 0;
/*-- MTF init --*/
{
Int32 ii, jj, kk;
kk = MTFA_SIZE-1;
for (ii = 256 / MTFL_SIZE - 1; ii >= 0; ii--) {
for (jj = MTFL_SIZE-1; jj >= 0; jj--) {
s->mtfa[kk] = (UChar)(ii * MTFL_SIZE + jj);
kk--;
}
s->mtfbase[ii] = kk + 1;
}
}
/*-- end MTF init --*/
nblock = 0;
GET_MTF_VAL(BZ_X_MTF_1, BZ_X_MTF_2, nextSym);
while (True) {
if (nextSym == EOB) break;
if (nextSym == BZ_RUNA || nextSym == BZ_RUNB) {
es = -1;
N = 1;
do {
if (nextSym == BZ_RUNA) es = es + (0+1) * N; else
if (nextSym == BZ_RUNB) es = es + (1+1) * N;
N = N * 2;
GET_MTF_VAL(BZ_X_MTF_3, BZ_X_MTF_4, nextSym);
}
while (nextSym == BZ_RUNA || nextSym == BZ_RUNB);
es++;
uc = s->seqToUnseq[ s->mtfa[s->mtfbase[0]] ];
s->unzftab[uc] += es;
if (s->smallDecompress)
while (es > 0) {
s->ll16[nblock] = (UInt16)uc;
nblock++;
es--;
}
else
while (es > 0) {
s->tt[nblock] = (UInt32)uc;
nblock++;
es--;
};
if (nblock > nblockMAX) RETURN(BZ_DATA_ERROR);
continue;
} else {
if (nblock > nblockMAX) RETURN(BZ_DATA_ERROR);
/*-- uc = MTF ( nextSym-1 ) --*/
{
Int32 ii, jj, kk, pp, lno, off;
UInt32 nn;
nn = (UInt32)(nextSym - 1);
if (nn < MTFL_SIZE) {
/* avoid general-case expense */
pp = s->mtfbase[0];
uc = s->mtfa[pp+nn];
while (nn > 3) {
Int32 z = pp+nn;
s->mtfa[(z) ] = s->mtfa[(z)-1];
s->mtfa[(z)-1] = s->mtfa[(z)-2];
s->mtfa[(z)-2] = s->mtfa[(z)-3];
s->mtfa[(z)-3] = s->mtfa[(z)-4];
nn -= 4;
}
while (nn > 0) {
s->mtfa[(pp+nn)] = s->mtfa[(pp+nn)-1]; nn--;
};
s->mtfa[pp] = uc;
} else {
/* general case */
lno = nn / MTFL_SIZE;
off = nn % MTFL_SIZE;
pp = s->mtfbase[lno] + off;
uc = s->mtfa[pp];
while (pp > s->mtfbase[lno]) {
s->mtfa[pp] = s->mtfa[pp-1]; pp--;
};
s->mtfbase[lno]++;
while (lno > 0) {
s->mtfbase[lno]--;
s->mtfa[s->mtfbase[lno]]
= s->mtfa[s->mtfbase[lno-1] + MTFL_SIZE - 1];
lno--;
}
s->mtfbase[0]--;
s->mtfa[s->mtfbase[0]] = uc;
if (s->mtfbase[0] == 0) {
kk = MTFA_SIZE-1;
for (ii = 256 / MTFL_SIZE-1; ii >= 0; ii--) {
for (jj = MTFL_SIZE-1; jj >= 0; jj--) {
s->mtfa[kk] = s->mtfa[s->mtfbase[ii] + jj];
kk--;
}
s->mtfbase[ii] = kk + 1;
}
}
}
}
/*-- end uc = MTF ( nextSym-1 ) --*/
s->unzftab[s->seqToUnseq[uc]]++;
if (s->smallDecompress)
s->ll16[nblock] = (UInt16)(s->seqToUnseq[uc]); else
s->tt[nblock] = (UInt32)(s->seqToUnseq[uc]);
nblock++;
GET_MTF_VAL(BZ_X_MTF_5, BZ_X_MTF_6, nextSym);
continue;
}
}
s->state_out_len = 0;
s->state_out_ch = 0;
BZ_INITIALISE_CRC ( s->calculatedBlockCRC );
s->state = BZ_X_OUTPUT;
if (s->verbosity >= 2) VPrintf0 ( "rt+rld" );
/*-- Set up cftab to facilitate generation of T^(-1) --*/
s->cftab[0] = 0;
for (i = 1; i <= 256; i++) s->cftab[i] = s->unzftab[i-1];
for (i = 1; i <= 256; i++) s->cftab[i] += s->cftab[i-1];
if (s->smallDecompress) {
/*-- Make a copy of cftab, used in generation of T --*/
for (i = 0; i <= 256; i++) s->cftabCopy[i] = s->cftab[i];
/*-- compute the T vector --*/
for (i = 0; i < nblock; i++) {
uc = (UChar)(s->ll16[i]);
SET_LL(i, s->cftabCopy[uc]);
s->cftabCopy[uc]++;
}
/*-- Compute T^(-1) by pointer reversal on T --*/
i = s->origPtr;
j = GET_LL(i);
do {
Int32 tmp = GET_LL(j);
SET_LL(j, i);
i = j;
j = tmp;
}
while (i != s->origPtr);
s->tPos = s->origPtr;
s->nblock_used = 0;
if (s->blockRandomised) {
BZ_RAND_INIT_MASK;
BZ_GET_SMALL(s->k0); s->nblock_used++;
BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK;
} else {
BZ_GET_SMALL(s->k0); s->nblock_used++;
}
} else {
/*-- compute the T^(-1) vector --*/
for (i = 0; i < nblock; i++) {
uc = (UChar)(s->tt[i] & 0xff);
s->tt[s->cftab[uc]] |= (i << 8);
s->cftab[uc]++;
}
s->tPos = s->tt[s->origPtr] >> 8;
s->nblock_used = 0;
if (s->blockRandomised) {
BZ_RAND_INIT_MASK;
BZ_GET_FAST(s->k0); s->nblock_used++;
BZ_RAND_UPD_MASK; s->k0 ^= BZ_RAND_MASK;
} else {
BZ_GET_FAST(s->k0); s->nblock_used++;
}
}
RETURN(BZ_OK);
endhdr_2:
GET_UCHAR(BZ_X_ENDHDR_2, uc);
if (uc != 0x72) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_ENDHDR_3, uc);
if (uc != 0x45) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_ENDHDR_4, uc);
if (uc != 0x38) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_ENDHDR_5, uc);
if (uc != 0x50) RETURN(BZ_DATA_ERROR);
GET_UCHAR(BZ_X_ENDHDR_6, uc);
if (uc != 0x90) RETURN(BZ_DATA_ERROR);
s->storedCombinedCRC = 0;
GET_UCHAR(BZ_X_CCRC_1, uc);
s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_CCRC_2, uc);
s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_CCRC_3, uc);
s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
GET_UCHAR(BZ_X_CCRC_4, uc);
s->storedCombinedCRC = (s->storedCombinedCRC << 8) | ((UInt32)uc);
s->state = BZ_X_IDLE;
RETURN(BZ_STREAM_END);
default: AssertH ( False, 4001 );
}
AssertH ( False, 4002 );
save_state_and_return:
s->save_i = i;
s->save_j = j;
s->save_t = t;
s->save_alphaSize = alphaSize;
s->save_nGroups = nGroups;
s->save_nSelectors = nSelectors;
s->save_EOB = EOB;
s->save_groupNo = groupNo;
s->save_groupPos = groupPos;
s->save_nextSym = nextSym;
s->save_nblockMAX = nblockMAX;
s->save_nblock = nblock;
s->save_es = es;
s->save_N = N;
s->save_curr = curr;
s->save_zt = zt;
s->save_zn = zn;
s->save_zvec = zvec;
s->save_zj = zj;
s->save_gSel = gSel;
s->save_gMinlen = gMinlen;
s->save_gLimit = gLimit;
s->save_gBase = gBase;
s->save_gPerm = gPerm;
return retVal;
}
/*-------------------------------------------------------------*/
/*--- end decompress.c ---*/
/*-------------------------------------------------------------*/

163
dlltest.c Normal file
View File

@ -0,0 +1,163 @@
/*
minibz2
libbz2.dll test program.
by Yoshioka Tsuneo(QWF00133@nifty.ne.jp/tsuneo-y@is.aist-nara.ac.jp)
This file is Public Domain.
welcome any email to me.
usage: minibz2 [-d] [-{1,2,..9}] [[srcfilename] destfilename]
*/
#define BZ_IMPORT
#include "bzlib.h"
#include <stdio.h>
#include <stdlib.h>
#ifdef _WIN32
#include <io.h>
#endif
#ifdef _WIN32
#include <windows.h>
static int BZ2DLLLoaded = 0;
static HINSTANCE BZ2DLLhLib;
int BZ2DLLLoadLibrary(void)
{
HINSTANCE hLib;
if(BZ2DLLLoaded==1){return 0;}
hLib=LoadLibrary("libbz2.dll");
if(hLib == NULL){
puts("Can't load libbz2.dll");
return -1;
}
BZ2DLLLoaded=1;
BZ2DLLhLib=hLib;
bzlibVersion=GetProcAddress(hLib,"bzlibVersion");
bzopen=GetProcAddress(hLib,"bzopen");
bzdopen=GetProcAddress(hLib,"bzdopen");
bzread=GetProcAddress(hLib,"bzread");
bzwrite=GetProcAddress(hLib,"bzwrite");
bzflush=GetProcAddress(hLib,"bzflush");
bzclose=GetProcAddress(hLib,"bzclose");
bzerror=GetProcAddress(hLib,"bzerror");
return 0;
}
int BZ2DLLFreeLibrary(void)
{
if(BZ2DLLLoaded==0){return 0;}
FreeLibrary(BZ2DLLhLib);
BZ2DLLLoaded=0;
}
#endif /* WIN32 */
void usage(void)
{
puts("usage: minibz2 [-d] [-{1,2,..9}] [[srcfilename] destfilename]");
}
void main(int argc,char *argv[])
{
int decompress = 0;
int level = 9;
char *fn_r,*fn_w;
#ifdef _WIN32
if(BZ2DLLLoadLibrary()<0){
puts("can't load dll");
exit(1);
}
#endif
while(++argv,--argc){
if(**argv =='-' || **argv=='/'){
char *p;
for(p=*argv+1;*p;p++){
if(*p=='d'){
decompress = 1;
}else if('1'<=*p && *p<='9'){
level = *p - '0';
}else{
usage();
exit(1);
}
}
}else{
break;
}
}
if(argc>=1){
fn_r = *argv;
argc--;argv++;
}else{
fn_r = NULL;
}
if(argc>=1){
fn_w = *argv;
argc--;argv++;
}else{
fn_w = NULL;
}
{
int len;
char buff[0x1000];
char mode[10];
if(decompress){
BZFILE *BZ2fp_r;
FILE *fp_w;
if(fn_w){
if((fp_w = fopen(fn_w,"wb"))==NULL){
printf("can't open [%s]\n",fn_w);
perror("reason:");
exit(1);
}
}else{
fp_w = stdout;
}
if((BZ2fp_r == NULL && (BZ2fp_r = bzdopen(fileno(stdin),"rb"))==NULL)
|| (BZ2fp_r != NULL && (BZ2fp_r = bzopen(fn_r,"rb"))==NULL)){
printf("can't bz2openstream\n");
exit(1);
}
while((len=bzread(BZ2fp_r,buff,0x1000))>0){
fwrite(buff,1,len,fp_w);
}
bzclose(BZ2fp_r);
if(fp_w != stdout) fclose(fp_w);
}else{
BZFILE *BZ2fp_w;
FILE *fp_r;
if(fn_r){
if((fp_r = fopen(fn_r,"rb"))==NULL){
printf("can't open [%s]\n",fn_r);
perror("reason:");
exit(1);
}
}else{
fp_r = stdin;
}
mode[0]='w';
mode[1] = '0' + level;
mode[2] = '\0';
if((fn_w == NULL && (BZ2fp_w = bzdopen(fileno(stdout),mode))==NULL)
|| (fn_w !=NULL && (BZ2fp_w = bzopen(fn_w,mode))==NULL)){
printf("can't bz2openstream\n");
exit(1);
}
while((len=fread(buff,1,0x1000,fp_r))>0){
bzwrite(BZ2fp_w,buff,len);
}
bzclose(BZ2fp_w);
if(fp_r!=stdin)fclose(fp_r);
}
}
#ifdef _WIN32
BZ2DLLFreeLibrary();
#endif
}

93
dlltest.dsp Normal file
View File

@ -0,0 +1,93 @@
# Microsoft Developer Studio Project File - Name="dlltest" - Package Owner=<4>
# Microsoft Developer Studio Generated Build File, Format Version 5.00
# ** 編集しないでください **
# TARGTYPE "Win32 (x86) Console Application" 0x0103
CFG=dlltest - Win32 Debug
!MESSAGE これは有効なﾒｲｸﾌｧｲﾙではありません。 このﾌﾟﾛｼﾞｪｸﾄをﾋﾞﾙﾄﾞするためには NMAKE を使用してください。
!MESSAGE [ﾒｲｸﾌｧｲﾙのｴｸｽﾎﾟｰﾄ] ｺﾏﾝﾄﾞを使用して実行してください
!MESSAGE
!MESSAGE NMAKE /f "dlltest.mak".
!MESSAGE
!MESSAGE NMAKE の実行時に構成を指定できます
!MESSAGE ｺﾏﾝﾄﾞ ﾗｲﾝ上でﾏｸﾛの設定を定義します。例:
!MESSAGE
!MESSAGE NMAKE /f "dlltest.mak" CFG="dlltest - Win32 Debug"
!MESSAGE
!MESSAGE 選択可能なﾋﾞﾙﾄﾞ ﾓｰﾄﾞ:
!MESSAGE
!MESSAGE "dlltest - Win32 Release" ("Win32 (x86) Console Application" 用)
!MESSAGE "dlltest - Win32 Debug" ("Win32 (x86) Console Application" 用)
!MESSAGE
# Begin Project
# PROP Scc_ProjName ""
# PROP Scc_LocalPath ""
CPP=cl.exe
RSC=rc.exe
!IF "$(CFG)" == "dlltest - Win32 Release"
# PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "Release"
# PROP BASE Intermediate_Dir "Release"
# PROP BASE Target_Dir ""
# PROP Use_MFC 0
# PROP Use_Debug_Libraries 0
# PROP Output_Dir "Release"
# PROP Intermediate_Dir "Release"
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD CPP /nologo /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD BASE RSC /l 0x411 /d "NDEBUG"
# ADD RSC /l 0x411 /d "NDEBUG"
BSC32=bscmake.exe
# ADD BASE BSC32 /nologo
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /machine:I386 /out:"minibz2.exe"
!ELSEIF "$(CFG)" == "dlltest - Win32 Debug"
# PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "dlltest_"
# PROP BASE Intermediate_Dir "dlltest_"
# PROP BASE Target_Dir ""
# PROP Use_MFC 0
# PROP Use_Debug_Libraries 1
# PROP Output_Dir "dlltest_"
# PROP Intermediate_Dir "dlltest_"
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD CPP /nologo /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_CONSOLE" /D "_MBCS" /YX /FD /c
# ADD BASE RSC /l 0x411 /d "_DEBUG"
# ADD RSC /l 0x411 /d "_DEBUG"
BSC32=bscmake.exe
# ADD BASE BSC32 /nologo
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /pdbtype:sept
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:console /debug /machine:I386 /out:"minibz2.exe" /pdbtype:sept
!ENDIF
# Begin Target
# Name "dlltest - Win32 Release"
# Name "dlltest - Win32 Debug"
# Begin Source File
SOURCE=.\bzlib.h
# End Source File
# Begin Source File
SOURCE=.\dlltest.c
# End Source File
# End Target
# End Project

37
howbig.c Normal file
View File

@ -0,0 +1,37 @@
#include <stdio.h>
#include <assert.h>
#include "bzlib.h"
unsigned char ibuff[1000000];
unsigned char obuff[1000000];
void doone ( int n )
{
int i, j, k, q, nobuff;
q = 0;
for (k = 0; k < 1; k++) {
for (i = 0; i < n; i++)
ibuff[i] = ((unsigned long)(random())) & 0xff;
nobuff = 1000000;
j = bzBuffToBuffCompress ( obuff, &nobuff, ibuff, n, 9,0,0 );
assert (j == BZ_OK);
if (nobuff > q) q = nobuff;
}
printf ( "%d %d(%d)\n", n, q, (int)((float)n * 1.01 - (float)q) );
}
int main ( int argc, char** argv )
{
int i;
i = 0;
while (1) {
if (i >= 900000) break;
doone(i);
if ( (int)(1.10 * i) > i )
i = (int)(1.10 * i); else i++;
}
return 0;
}

228
huffman.c Normal file
View File

@ -0,0 +1,228 @@
/*-------------------------------------------------------------*/
/*--- Huffman coding low-level stuff ---*/
/*--- huffman.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#include "bzlib_private.h"
/*---------------------------------------------------*/
#define WEIGHTOF(zz0) ((zz0) & 0xffffff00)
#define DEPTHOF(zz1) ((zz1) & 0x000000ff)
#define MYMAX(zz2,zz3) ((zz2) > (zz3) ? (zz2) : (zz3))
#define ADDWEIGHTS(zw1,zw2) \
(WEIGHTOF(zw1)+WEIGHTOF(zw2)) | \
(1 + MYMAX(DEPTHOF(zw1),DEPTHOF(zw2)))
#define UPHEAP(z) \
{ \
Int32 zz, tmp; \
zz = z; tmp = heap[zz]; \
while (weight[tmp] < weight[heap[zz >> 1]]) { \
heap[zz] = heap[zz >> 1]; \
zz >>= 1; \
} \
heap[zz] = tmp; \
}
#define DOWNHEAP(z) \
{ \
Int32 zz, yy, tmp; \
zz = z; tmp = heap[zz]; \
while (True) { \
yy = zz << 1; \
if (yy > nHeap) break; \
if (yy < nHeap && \
weight[heap[yy+1]] < weight[heap[yy]]) \
yy++; \
if (weight[tmp] < weight[heap[yy]]) break; \
heap[zz] = heap[yy]; \
zz = yy; \
} \
heap[zz] = tmp; \
}
/*---------------------------------------------------*/
void hbMakeCodeLengths ( UChar *len,
Int32 *freq,
Int32 alphaSize,
Int32 maxLen )
{
/*--
Nodes and heap entries run from 1. Entry 0
for both the heap and nodes is a sentinel.
--*/
Int32 nNodes, nHeap, n1, n2, i, j, k;
Bool tooLong;
Int32 heap [ BZ_MAX_ALPHA_SIZE + 2 ];
Int32 weight [ BZ_MAX_ALPHA_SIZE * 2 ];
Int32 parent [ BZ_MAX_ALPHA_SIZE * 2 ];
for (i = 0; i < alphaSize; i++)
weight[i+1] = (freq[i] == 0 ? 1 : freq[i]) << 8;
while (True) {
nNodes = alphaSize;
nHeap = 0;
heap[0] = 0;
weight[0] = 0;
parent[0] = -2;
for (i = 1; i <= alphaSize; i++) {
parent[i] = -1;
nHeap++;
heap[nHeap] = i;
UPHEAP(nHeap);
}
AssertH( nHeap < (BZ_MAX_ALPHA_SIZE+2), 2001 );
while (nHeap > 1) {
n1 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
n2 = heap[1]; heap[1] = heap[nHeap]; nHeap--; DOWNHEAP(1);
nNodes++;
parent[n1] = parent[n2] = nNodes;
weight[nNodes] = ADDWEIGHTS(weight[n1], weight[n2]);
parent[nNodes] = -1;
nHeap++;
heap[nHeap] = nNodes;
UPHEAP(nHeap);
}
AssertH( nNodes < (BZ_MAX_ALPHA_SIZE * 2), 2002 );
tooLong = False;
for (i = 1; i <= alphaSize; i++) {
j = 0;
k = i;
while (parent[k] >= 0) { k = parent[k]; j++; }
len[i-1] = j;
if (j > maxLen) tooLong = True;
}
if (! tooLong) break;
for (i = 1; i < alphaSize; i++) {
j = weight[i] >> 8;
j = 1 + (j / 2);
weight[i] = j << 8;
}
}
}
/*---------------------------------------------------*/
void hbAssignCodes ( Int32 *code,
UChar *length,
Int32 minLen,
Int32 maxLen,
Int32 alphaSize )
{
Int32 n, vec, i;
vec = 0;
for (n = minLen; n <= maxLen; n++) {
for (i = 0; i < alphaSize; i++)
if (length[i] == n) { code[i] = vec; vec++; };
vec <<= 1;
}
}
/*---------------------------------------------------*/
void hbCreateDecodeTables ( Int32 *limit,
Int32 *base,
Int32 *perm,
UChar *length,
Int32 minLen,
Int32 maxLen,
Int32 alphaSize )
{
Int32 pp, i, j, vec;
pp = 0;
for (i = minLen; i <= maxLen; i++)
for (j = 0; j < alphaSize; j++)
if (length[j] == i) { perm[pp] = j; pp++; };
for (i = 0; i < BZ_MAX_CODE_LEN; i++) base[i] = 0;
for (i = 0; i < alphaSize; i++) base[length[i]+1]++;
for (i = 1; i < BZ_MAX_CODE_LEN; i++) base[i] += base[i-1];
for (i = 0; i < BZ_MAX_CODE_LEN; i++) limit[i] = 0;
vec = 0;
for (i = minLen; i <= maxLen; i++) {
vec += (base[i+1] - base[i]);
limit[i] = vec-1;
vec <<= 1;
}
for (i = minLen + 1; i <= maxLen; i++)
base[i] = ((limit[i-1] + 1) << 1) - base[i];
}
/*-------------------------------------------------------------*/
/*--- end huffman.c ---*/
/*-------------------------------------------------------------*/

25
libbz2.def Normal file
View File

@ -0,0 +1,25 @@
LIBRARY LIBBZ2
DESCRIPTION "libbzip2: library for data compression"
EXPORTS
bzCompressInit
bzCompress
bzCompressEnd
bzDecompressInit
bzDecompress
bzDecompressEnd
bzReadOpen
bzReadClose
bzReadGetUnused
bzRead
bzWriteOpen
bzWrite
bzWriteClose
bzBuffToBuffCompress
bzBuffToBuffDecompress
bzlibVersion
bzopen
bzdopen
bzread
bzwrite
bzflush
bzclose

130
libbz2.dsp Normal file
View File

@ -0,0 +1,130 @@
# Microsoft Developer Studio Project File - Name="libbz2" - Package Owner=<4>
# Microsoft Developer Studio Generated Build File, Format Version 5.00
# ** 編集しないでください **
# TARGTYPE "Win32 (x86) Dynamic-Link Library" 0x0102
CFG=libbz2 - Win32 Debug
!MESSAGE これは有効なﾒｲｸﾌｧｲﾙではありません。 このﾌﾟﾛｼﾞｪｸﾄをﾋﾞﾙﾄﾞするためには NMAKE を使用してください。
!MESSAGE [ﾒｲｸﾌｧｲﾙのｴｸｽﾎﾟｰﾄ] ｺﾏﾝﾄﾞを使用して実行してください
!MESSAGE
!MESSAGE NMAKE /f "libbz2.mak".
!MESSAGE
!MESSAGE NMAKE の実行時に構成を指定できます
!MESSAGE ｺﾏﾝﾄﾞ ﾗｲﾝ上でﾏｸﾛの設定を定義します。例:
!MESSAGE
!MESSAGE NMAKE /f "libbz2.mak" CFG="libbz2 - Win32 Debug"
!MESSAGE
!MESSAGE 選択可能なﾋﾞﾙﾄﾞ ﾓｰﾄﾞ:
!MESSAGE
!MESSAGE "libbz2 - Win32 Release" ("Win32 (x86) Dynamic-Link Library" 用)
!MESSAGE "libbz2 - Win32 Debug" ("Win32 (x86) Dynamic-Link Library" 用)
!MESSAGE
# Begin Project
# PROP Scc_ProjName ""
# PROP Scc_LocalPath ""
CPP=cl.exe
MTL=midl.exe
RSC=rc.exe
!IF "$(CFG)" == "libbz2 - Win32 Release"
# PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 0
# PROP BASE Output_Dir "Release"
# PROP BASE Intermediate_Dir "Release"
# PROP BASE Target_Dir ""
# PROP Use_MFC 0
# PROP Use_Debug_Libraries 0
# PROP Output_Dir "Release"
# PROP Intermediate_Dir "Release"
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /FD /c
# ADD CPP /nologo /MT /W3 /GX /O2 /D "WIN32" /D "NDEBUG" /D "_WINDOWS" /YX /FD /c
# ADD BASE MTL /nologo /D "NDEBUG" /mktyplib203 /o NUL /win32
# ADD MTL /nologo /D "NDEBUG" /mktyplib203 /o NUL /win32
# ADD BASE RSC /l 0x411 /d "NDEBUG"
# ADD RSC /l 0x411 /d "NDEBUG"
BSC32=bscmake.exe
# ADD BASE BSC32 /nologo
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /machine:I386 /out:"libbz2.dll"
!ELSEIF "$(CFG)" == "libbz2 - Win32 Debug"
# PROP BASE Use_MFC 0
# PROP BASE Use_Debug_Libraries 1
# PROP BASE Output_Dir "Debug"
# PROP BASE Intermediate_Dir "Debug"
# PROP BASE Target_Dir ""
# PROP Use_MFC 0
# PROP Use_Debug_Libraries 1
# PROP Output_Dir "Debug"
# PROP Intermediate_Dir "Debug"
# PROP Ignore_Export_Lib 0
# PROP Target_Dir ""
# ADD BASE CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /FD /c
# ADD CPP /nologo /MTd /W3 /Gm /GX /Zi /Od /D "WIN32" /D "_DEBUG" /D "_WINDOWS" /YX /FD /c
# ADD BASE MTL /nologo /D "_DEBUG" /mktyplib203 /o NUL /win32
# ADD MTL /nologo /D "_DEBUG" /mktyplib203 /o NUL /win32
# ADD BASE RSC /l 0x411 /d "_DEBUG"
# ADD RSC /l 0x411 /d "_DEBUG"
BSC32=bscmake.exe
# ADD BASE BSC32 /nologo
# ADD BSC32 /nologo
LINK32=link.exe
# ADD BASE LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 /pdbtype:sept
# ADD LINK32 kernel32.lib user32.lib gdi32.lib winspool.lib comdlg32.lib advapi32.lib shell32.lib ole32.lib oleaut32.lib uuid.lib odbc32.lib odbccp32.lib /nologo /subsystem:windows /dll /debug /machine:I386 /out:"libbz2.dll" /pdbtype:sept
!ENDIF
# Begin Target
# Name "libbz2 - Win32 Release"
# Name "libbz2 - Win32 Debug"
# Begin Source File
SOURCE=.\blocksort.c
# End Source File
# Begin Source File
SOURCE=.\bzlib.c
# End Source File
# Begin Source File
SOURCE=.\bzlib.h
# End Source File
# Begin Source File
SOURCE=.\bzlib_private.h
# End Source File
# Begin Source File
SOURCE=.\compress.c
# End Source File
# Begin Source File
SOURCE=.\crctable.c
# End Source File
# Begin Source File
SOURCE=.\decompress.c
# End Source File
# Begin Source File
SOURCE=.\huffman.c
# End Source File
# Begin Source File
SOURCE=.\libbz2.def
# End Source File
# Begin Source File
SOURCE=.\randtable.c
# End Source File
# End Target
# End Project

2100
manual.texi Normal file
View File

File diff suppressed because it is too large Load Diff

124
randtable.c Normal file
View File

@ -0,0 +1,124 @@
/*-------------------------------------------------------------*/
/*--- Table for randomising repetitive blocks ---*/
/*--- randtable.c ---*/
/*-------------------------------------------------------------*/
/*--
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-1998 Julian R Seward. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. The origin of this software must not be misrepresented; you must
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product
documentation would be appreciated but is not required.
3. Altered source versions must be plainly marked as such, and must
not be misrepresented as being the original software.
4. The name of the author may not be used to endorse or promote
products derived from this software without specific prior written
permission.
THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Guildford, Surrey, UK.
jseward@acm.org
bzip2/libbzip2 version 0.9.0c of 18 October 1998
This program is based on (at least) the work of:
Mike Burrows
David Wheeler
Peter Fenwick
Alistair Moffat
Radford Neal
Ian H. Witten
Robert Sedgewick
Jon L. Bentley
For more information on these sources, see the manual.
--*/
#include "bzlib_private.h"
/*---------------------------------------------*/
Int32 rNums[512] = {
619, 720, 127, 481, 931, 816, 813, 233, 566, 247,
985, 724, 205, 454, 863, 491, 741, 242, 949, 214,
733, 859, 335, 708, 621, 574, 73, 654, 730, 472,
419, 436, 278, 496, 867, 210, 399, 680, 480, 51,
878, 465, 811, 169, 869, 675, 611, 697, 867, 561,
862, 687, 507, 283, 482, 129, 807, 591, 733, 623,
150, 238, 59, 379, 684, 877, 625, 169, 643, 105,
170, 607, 520, 932, 727, 476, 693, 425, 174, 647,
73, 122, 335, 530, 442, 853, 695, 249, 445, 515,
909, 545, 703, 919, 874, 474, 882, 500, 594, 612,
641, 801, 220, 162, 819, 984, 589, 513, 495, 799,
161, 604, 958, 533, 221, 400, 386, 867, 600, 782,
382, 596, 414, 171, 516, 375, 682, 485, 911, 276,
98, 553, 163, 354, 666, 933, 424, 341, 533, 870,
227, 730, 475, 186, 263, 647, 537, 686, 600, 224,
469, 68, 770, 919, 190, 373, 294, 822, 808, 206,
184, 943, 795, 384, 383, 461, 404, 758, 839, 887,
715, 67, 618, 276, 204, 918, 873, 777, 604, 560,
951, 160, 578, 722, 79, 804, 96, 409, 713, 940,
652, 934, 970, 447, 318, 353, 859, 672, 112, 785,
645, 863, 803, 350, 139, 93, 354, 99, 820, 908,
609, 772, 154, 274, 580, 184, 79, 626, 630, 742,
653, 282, 762, 623, 680, 81, 927, 626, 789, 125,
411, 521, 938, 300, 821, 78, 343, 175, 128, 250,
170, 774, 972, 275, 999, 639, 495, 78, 352, 126,
857, 956, 358, 619, 580, 124, 737, 594, 701, 612,
669, 112, 134, 694, 363, 992, 809, 743, 168, 974,
944, 375, 748, 52, 600, 747, 642, 182, 862, 81,
344, 805, 988, 739, 511, 655, 814, 334, 249, 515,
897, 955, 664, 981, 649, 113, 974, 459, 893, 228,
433, 837, 553, 268, 926, 240, 102, 654, 459, 51,
686, 754, 806, 760, 493, 403, 415, 394, 687, 700,
946, 670, 656, 610, 738, 392, 760, 799, 887, 653,
978, 321, 576, 617, 626, 502, 894, 679, 243, 440,
680, 879, 194, 572, 640, 724, 926, 56, 204, 700,
707, 151, 457, 449, 797, 195, 791, 558, 945, 679,
297, 59, 87, 824, 713, 663, 412, 693, 342, 606,
134, 108, 571, 364, 631, 212, 174, 643, 304, 329,
343, 97, 430, 751, 497, 314, 983, 374, 822, 928,
140, 206, 73, 263, 980, 736, 876, 478, 430, 305,
170, 514, 364, 692, 829, 82, 855, 953, 676, 246,
369, 970, 294, 750, 807, 827, 150, 790, 288, 923,
804, 378, 215, 828, 592, 281, 565, 555, 710, 82,
896, 831, 547, 261, 524, 462, 293, 465, 502, 56,
661, 821, 976, 991, 658, 869, 905, 758, 745, 193,
768, 550, 608, 933, 378, 286, 215, 979, 792, 961,
61, 688, 793, 644, 986, 403, 106, 366, 905, 644,
372, 567, 466, 434, 645, 210, 389, 550, 919, 135,
780, 773, 635, 389, 707, 100, 626, 958, 165, 504,
920, 176, 193, 713, 857, 265, 203, 50, 668, 108,
645, 990, 626, 197, 510, 357, 358, 850, 858, 364,
936, 638
};
/*-------------------------------------------------------------*/
/*--- end randtable.c ---*/
/*-------------------------------------------------------------*/

9
test.bat
View File

@ -1,9 +0,0 @@
@rem
@rem MSDOS test driver for bzip2
@rem
type words1
.\bzip2 -1 < sample1.ref > sample1.rbz
.\bzip2 -2 < sample2.ref > sample2.rbz
.\bzip2 -dvv < sample1.bz2 > sample1.tst
.\bzip2 -dvv < sample2.bz2 > sample2.tst
type words3sh

9
test.cmd
View File

@ -1,9 +0,0 @@
@rem
@rem OS/2 test driver for bzip2
@rem
type words1
.\bzip2 -1 < sample1.ref > sample1.rbz
.\bzip2 -2 < sample2.ref > sample2.rbz
.\bzip2 -dvv < sample1.bz2 > sample1.tst
.\bzip2 -dvv < sample2.bz2 > sample2.tst
type words3sh

7
words0
View File

@ -1,7 +0,0 @@
***-------------------------------------------------***
***--------- IMPORTANT: READ WHAT FOLLOWS! ---------***
***--------- viz: pay attention :-) ---------***
***-------------------------------------------------***
Compiling bzip2 ...

1
words1
View File

@ -1,5 +1,4 @@
Doing 4 tests (2 compress, 2 uncompress) ...
If there's a problem, things might stop at this point.

1
words2
View File

@ -1,5 +1,4 @@
Checking test results. If any of the four "cmp"s which follow
report any differences, something is wrong. If you can't easily
figure out what, please let me know (jseward@acm.org).

21
words3
View File

@ -1,23 +1,20 @@
If you got this far and the "cmp"s didn't find anything amiss, looks
like you're in business. You should install bzip2 and bunzip2:
like you're in business. You should install bzip2, bunzip2 and bzcat:
copy bzip2 to a public place, maybe /usr/bin.
In that public place, make bunzip2 a symbolic link
to the bzip2 you just copied there.
Copy bzip2 and bzip2recover to a public place, maybe /usr/bin.
In that public place, make bunzip2 and bzcat be
symbolic links to the bzip2 you just copied there.
Put the manual page, bzip2.1, somewhere appropriate;
perhaps in /usr/man/man1.
Complete instructions for use are in the preformatted
manual page, in the file bzip2.1.preformatted.
Instructions for use are in the preformatted manual page, in the file
bzip2.txt. For more detailed documentation, read the full manual.
It is available in Postscript form (manual.ps) and HTML form
(manual_toc.html).
You can also do "bzip2 --help" to see some helpful information.
"bzip2 -L" displays the software license.
Please read the README file carefully.
Finally, note that bzip2 comes with ABSOLUTELY NO WARRANTY.
Happy compressing!
Happy compressing. -- JRS, 30 August 1998.

12
words3sh
View File

@ -1,12 +0,0 @@
If you got this far and the "bzip2 -dvv"s give identical
stored vs computed CRCs, you're probably in business.
Complete instructions for use are in the preformatted manual page,
in the file bzip2.txt.
You can also do "bzip2 --help" to see some helpful information.
"bzip2 -L" displays the software license.
Please read the README file carefully.
Finally, note that bzip2 comes with ABSOLUTELY NO WARRANTY.
Happy compressing!