generic-library/bzip2
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

bzip2-1.0.6

Browse Source
This commit is contained in:
Gabi Davar 2014-06-04 11:33:57 +03:00
commit faaacf5bed
56 changed files with 120106 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

327
CHANGES Normal file
View File

@ -0,0 +1,327 @@
------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------
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.
0.9.5a
~~~~~~
Major change: add a fallback sorting algorithm (blocksort.c)
to give reasonable behaviour even for very repetitive inputs.
Nuked --repetitive-best and --repetitive-fast since they are
no longer useful.
Minor changes: mostly a whole bunch of small changes/
bugfixes in the driver (bzip2.c). Changes pertaining to the
user interface are:
allow decompression of symlink'd files to stdout
decompress/test files even without .bz2 extension
give more accurate error messages for I/O errors
when compressing/decompressing to stdout, don't catch control-C
read flags from BZIP2 and BZIP environment variables
decline to break hard links to a file unless forced with -f
allow -c flag even with no filenames
preserve file ownerships as far as possible
make -s -1 give the expected block size (100k)
add a flag -q --quiet to suppress nonessential warnings
stop decoding flags after --, so files beginning in - can be handled
resolved inconsistent naming: bzcat or bz2cat ?
bzip2 --help now returns 0
Programming-level changes are:
fixed syntax error in GET_LL4 for Borland C++ 5.02
let bzBuffToBuffDecompress return BZ_DATA_ERROR{_MAGIC}
fix overshoot of mode-string end in bzopen_or_bzdopen
wrapped bzlib.h in #ifdef __cplusplus ... extern "C" { ... }
close file handles under all error conditions
added minor mods so it compiles with DJGPP out of the box
fixed Makefile so it doesn't give problems with BSD make
fix uninitialised memory reads in dlltest.c
0.9.5b
~~~~~~
Open stdin/stdout in binary mode for DJGPP.
0.9.5c
~~~~~~
Changed BZ_N_OVERSHOOT to be ... + 2 instead of ... + 1. The + 1
version could cause the sorted order to be wrong in some extremely
obscure cases. Also changed setting of quadrant in blocksort.c.
0.9.5d
~~~~~~
The only functional change is to make bzlibVersion() in the library
return the correct string. This has no effect whatsoever on the
functioning of the bzip2 program or library. Added a couple of casts
so the library compiles without warnings at level 3 in MS Visual
Studio 6.0. Included a Y2K statement in the file Y2K_INFO. All other
changes are minor documentation changes.
1.0
~~~
Several minor bugfixes and enhancements:
* Large file support. The library uses 64-bit counters to
count the volume of data passing through it. bzip2.c
is now compiled with -D_FILE_OFFSET_BITS=64 to get large
file support from the C library. -v correctly prints out
file sizes greater than 4 gigabytes. All these changes have
been made without assuming a 64-bit platform or a C compiler
which supports 64-bit ints, so, except for the C library
aspect, they are fully portable.
* Decompression robustness. The library/program should be
robust to any corruption of compressed data, detecting and
handling _all_ corruption, instead of merely relying on
the CRCs. What this means is that the program should
never crash, given corrupted data, and the library should
always return BZ_DATA_ERROR.
* Fixed an obscure race-condition bug only ever observed on
Solaris, in which, if you were very unlucky and issued
control-C at exactly the wrong time, both input and output
files would be deleted.
* Don't run out of file handles on test/decompression when
large numbers of files have invalid magic numbers.
* Avoid library namespace pollution. Prefix all exported
symbols with BZ2_.
* Minor sorting enhancements from my DCC2000 paper.
* Advance the version number to 1.0, so as to counteract the
(false-in-this-case) impression some people have that programs
with version numbers less than 1.0 are in some way, experimental,
pre-release versions.
* Create an initial Makefile-libbz2_so to build a shared library.
Yes, I know I should really use libtool et al ...
* Make the program exit with 2 instead of 0 when decompression
fails due to a bad magic number (ie, an invalid bzip2 header).
Also exit with 1 (as the manual claims :-) whenever a diagnostic
message would have been printed AND the corresponding operation
is aborted, for example
bzip2: Output file xx already exists.
When a diagnostic message is printed but the operation is not
aborted, for example
bzip2: Can't guess original name for wurble -- using wurble.out
then the exit value 0 is returned, unless some other problem is
also detected.
I think it corresponds more closely to what the manual claims now.
1.0.1
~~~~~
* Modified dlltest.c so it uses the new BZ2_ naming scheme.
* Modified makefile-msc to fix minor build probs on Win2k.
* Updated README.COMPILATION.PROBLEMS.
There are no functionality changes or bug fixes relative to version
1.0.0. This is just a documentation update + a fix for minor Win32
build problems. For almost everyone, upgrading from 1.0.0 to 1.0.1 is
utterly pointless. Don't bother.
1.0.2
~~~~~
A bug fix release, addressing various minor issues which have appeared
in the 18 or so months since 1.0.1 was released. Most of the fixes
are to do with file-handling or documentation bugs. To the best of my
knowledge, there have been no data-loss-causing bugs reported in the
compression/decompression engine of 1.0.0 or 1.0.1.
Note that this release does not improve the rather crude build system
for Unix platforms. The general plan here is to autoconfiscate/
libtoolise 1.0.2 soon after release, and release the result as 1.1.0
or perhaps 1.2.0. That, however, is still just a plan at this point.
Here are the changes in 1.0.2. Bug-reporters and/or patch-senders in
parentheses.
* Fix an infinite segfault loop in 1.0.1 when a directory is
encountered in -f (force) mode.
(Trond Eivind Glomsrod, Nicholas Nethercote, Volker Schmidt)
* Avoid double fclose() of output file on certain I/O error paths.
(Solar Designer)
* Don't fail with internal error 1007 when fed a long stream (> 48MB)
of byte 251. Also print useful message suggesting that 1007s may be
caused by bad memory.
(noticed by Juan Pedro Vallejo, fixed by me)
* Fix uninitialised variable silly bug in demo prog dlltest.c.
(Jorj Bauer)
* Remove 512-MB limitation on recovered file size for bzip2recover
on selected platforms which support 64-bit ints. At the moment
all GCC supported platforms, and Win32.
(me, Alson van der Meulen)
* Hard-code header byte values, to give correct operation on platforms
using EBCDIC as their native character set (IBM's OS/390).
(Leland Lucius)
* Copy file access times correctly.
(Marty Leisner)
* Add distclean and check targets to Makefile.
(Michael Carmack)
* Parameterise use of ar and ranlib in Makefile. Also add $(LDFLAGS).
(Rich Ireland, Bo Thorsen)
* Pass -p (create parent dirs as needed) to mkdir during make install.
(Jeremy Fusco)
* Dereference symlinks when copying file permissions in -f mode.
(Volker Schmidt)
* Majorly simplify implementation of uInt64_qrm10.
(Bo Lindbergh)
* Check the input file still exists before deleting the output one,
when aborting in cleanUpAndFail().
(Joerg Prante, Robert Linden, Matthias Krings)
Also a bunch of patches courtesy of Philippe Troin, the Debian maintainer
of bzip2:
* Wrapper scripts (with manpages): bzdiff, bzgrep, bzmore.
* Spelling changes and minor enhancements in bzip2.1.
* Avoid race condition between creating the output file and setting its
interim permissions safely, by using fopen_output_safely().
No changes to bzip2recover since there is no issue with file
permissions there.
* do not print senseless report with -v when compressing an empty
file.
* bzcat -f works on non-bzip2 files.
* do not try to escape shell meta-characters on unix (the shell takes
care of these).
* added --fast and --best aliases for -1 -9 for gzip compatibility.
1.0.3 (15 Feb 05)
~~~~~~~~~~~~~~~~~
Fixes some minor bugs since the last version, 1.0.2.
* Further robustification against corrupted compressed data.
There are currently no known bitstreams which can cause the
decompressor to crash, loop or access memory which does not
belong to it. If you are using bzip2 or the library to
decompress bitstreams from untrusted sources, an upgrade
to 1.0.3 is recommended. This fixes CAN-2005-1260.
* The documentation has been converted to XML, from which html
and pdf can be derived.
* Various minor bugs in the documentation have been fixed.
* Fixes for various compilation warnings with newer versions of
gcc, and on 64-bit platforms.
* The BZ_NO_STDIO cpp symbol was not properly observed in 1.0.2.
This has been fixed.
1.0.4 (20 Dec 06)
~~~~~~~~~~~~~~~~~
Fixes some minor bugs since the last version, 1.0.3.
* Fix file permissions race problem (CAN-2005-0953).
* Avoid possible segfault in BZ2_bzclose. From Coverity's NetBSD
scan.
* 'const'/prototype cleanups in the C code.
* Change default install location to /usr/local, and handle multiple
'make install's without error.
* Sanitise file names more carefully in bzgrep. Fixes CAN-2005-0758
to the extent that applies to bzgrep.
* Use 'mktemp' rather than 'tempfile' in bzdiff.
* Tighten up a couple of assertions in blocksort.c following automated
analysis.
* Fix minor doc/comment bugs.
1.0.5 (10 Dec 07)
~~~~~~~~~~~~~~~~~
Security fix only. Fixes CERT-FI 20469 as it applies to bzip2.
1.0.6 (6 Sept 10)
~~~~~~~~~~~~~~~~~
* Security fix for CVE-2010-0405. This was reported by Mikolaj
Izdebski.
* Make the documentation build on Ubuntu 10.04

42
LICENSE Normal file
View File

@ -0,0 +1,42 @@
--------------------------------------------------------------------------
This program, "bzip2", the associated library "libbzip2", and all
documentation, are copyright (C) 1996-2010 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, jseward@bzip.org
bzip2/libbzip2 version 1.0.6 of 6 September 2010
--------------------------------------------------------------------------

217
Makefile Normal file
View File

@ -0,0 +1,217 @@
# ------------------------------------------------------------------
# This file is part of bzip2/libbzip2, a program and library for
# lossless, block-sorting data compression.
#
# bzip2/libbzip2 version 1.0.6 of 6 September 2010
# Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
#
# Please read the WARNING, DISCLAIMER and PATENTS sections in the
# README file.
#
# This program is released under the terms of the license contained
# in the file LICENSE.
# ------------------------------------------------------------------
SHELL=/bin/sh
# To assist in cross-compiling
CC=gcc
AR=ar
RANLIB=ranlib
LDFLAGS=
BIGFILES=-D_FILE_OFFSET_BITS=64
CFLAGS=-Wall -Winline -O2 -g $(BIGFILES)
# Where you want it installed when you do 'make install'
PREFIX=/usr/local
OBJS= blocksort.o \
huffman.o \
crctable.o \
randtable.o \
compress.o \
decompress.o \
bzlib.o
all: libbz2.a bzip2 bzip2recover test
bzip2: libbz2.a bzip2.o
$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2 bzip2.o -L. -lbz2
bzip2recover: bzip2recover.o
$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2recover bzip2recover.o
libbz2.a: $(OBJS)
rm -f libbz2.a
$(AR) cq libbz2.a $(OBJS)
@if ( test -f $(RANLIB) -o -f /usr/bin/ranlib -o \
-f /bin/ranlib -o -f /usr/ccs/bin/ranlib ) ; then \
echo $(RANLIB) libbz2.a ; \
$(RANLIB) libbz2.a ; \
fi
check: test
test: bzip2
@cat words1
./bzip2 -1 < sample1.ref > sample1.rb2
./bzip2 -2 < sample2.ref > sample2.rb2
./bzip2 -3 < sample3.ref > sample3.rb2
./bzip2 -d < sample1.bz2 > sample1.tst
./bzip2 -d < sample2.bz2 > sample2.tst
./bzip2 -ds < sample3.bz2 > sample3.tst
cmp sample1.bz2 sample1.rb2
cmp sample2.bz2 sample2.rb2
cmp sample3.bz2 sample3.rb2
cmp sample1.tst sample1.ref
cmp sample2.tst sample2.ref
cmp sample3.tst sample3.ref
@cat words3
install: bzip2 bzip2recover
if ( test ! -d $(PREFIX)/bin ) ; then mkdir -p $(PREFIX)/bin ; fi
if ( test ! -d $(PREFIX)/lib ) ; then mkdir -p $(PREFIX)/lib ; fi
if ( test ! -d $(PREFIX)/man ) ; then mkdir -p $(PREFIX)/man ; fi
if ( test ! -d $(PREFIX)/man/man1 ) ; then mkdir -p $(PREFIX)/man/man1 ; fi
if ( test ! -d $(PREFIX)/include ) ; then mkdir -p $(PREFIX)/include ; fi
cp -f bzip2 $(PREFIX)/bin/bzip2
cp -f bzip2 $(PREFIX)/bin/bunzip2
cp -f bzip2 $(PREFIX)/bin/bzcat
cp -f bzip2recover $(PREFIX)/bin/bzip2recover
chmod a+x $(PREFIX)/bin/bzip2
chmod a+x $(PREFIX)/bin/bunzip2
chmod a+x $(PREFIX)/bin/bzcat
chmod a+x $(PREFIX)/bin/bzip2recover
cp -f bzip2.1 $(PREFIX)/man/man1
chmod a+r $(PREFIX)/man/man1/bzip2.1
cp -f bzlib.h $(PREFIX)/include
chmod a+r $(PREFIX)/include/bzlib.h
cp -f libbz2.a $(PREFIX)/lib
chmod a+r $(PREFIX)/lib/libbz2.a
cp -f bzgrep $(PREFIX)/bin/bzgrep
ln -s -f $(PREFIX)/bin/bzgrep $(PREFIX)/bin/bzegrep
ln -s -f $(PREFIX)/bin/bzgrep $(PREFIX)/bin/bzfgrep
chmod a+x $(PREFIX)/bin/bzgrep
cp -f bzmore $(PREFIX)/bin/bzmore
ln -s -f $(PREFIX)/bin/bzmore $(PREFIX)/bin/bzless
chmod a+x $(PREFIX)/bin/bzmore
cp -f bzdiff $(PREFIX)/bin/bzdiff
ln -s -f $(PREFIX)/bin/bzdiff $(PREFIX)/bin/bzcmp
chmod a+x $(PREFIX)/bin/bzdiff
cp -f bzgrep.1 bzmore.1 bzdiff.1 $(PREFIX)/man/man1
chmod a+r $(PREFIX)/man/man1/bzgrep.1
chmod a+r $(PREFIX)/man/man1/bzmore.1
chmod a+r $(PREFIX)/man/man1/bzdiff.1
echo ".so man1/bzgrep.1" > $(PREFIX)/man/man1/bzegrep.1
echo ".so man1/bzgrep.1" > $(PREFIX)/man/man1/bzfgrep.1
echo ".so man1/bzmore.1" > $(PREFIX)/man/man1/bzless.1
echo ".so man1/bzdiff.1" > $(PREFIX)/man/man1/bzcmp.1
clean:
rm -f *.o libbz2.a bzip2 bzip2recover \
sample1.rb2 sample2.rb2 sample3.rb2 \
sample1.tst sample2.tst sample3.tst
blocksort.o: blocksort.c
@cat words0
$(CC) $(CFLAGS) -c blocksort.c
huffman.o: huffman.c
$(CC) $(CFLAGS) -c huffman.c
crctable.o: crctable.c
$(CC) $(CFLAGS) -c crctable.c
randtable.o: randtable.c
$(CC) $(CFLAGS) -c randtable.c
compress.o: compress.c
$(CC) $(CFLAGS) -c compress.c
decompress.o: decompress.c
$(CC) $(CFLAGS) -c decompress.c
bzlib.o: bzlib.c
$(CC) $(CFLAGS) -c bzlib.c
bzip2.o: bzip2.c
$(CC) $(CFLAGS) -c bzip2.c
bzip2recover.o: bzip2recover.c
$(CC) $(CFLAGS) -c bzip2recover.c
distclean: clean
rm -f manual.ps manual.html manual.pdf
DISTNAME=bzip2-1.0.6
dist: check manual
rm -f $(DISTNAME)
ln -s -f . $(DISTNAME)
tar cvf $(DISTNAME).tar \
$(DISTNAME)/blocksort.c \
$(DISTNAME)/huffman.c \
$(DISTNAME)/crctable.c \
$(DISTNAME)/randtable.c \
$(DISTNAME)/compress.c \
$(DISTNAME)/decompress.c \
$(DISTNAME)/bzlib.c \
$(DISTNAME)/bzip2.c \
$(DISTNAME)/bzip2recover.c \
$(DISTNAME)/bzlib.h \
$(DISTNAME)/bzlib_private.h \
$(DISTNAME)/Makefile \
$(DISTNAME)/LICENSE \
$(DISTNAME)/bzip2.1 \
$(DISTNAME)/bzip2.1.preformatted \
$(DISTNAME)/bzip2.txt \
$(DISTNAME)/words0 \
$(DISTNAME)/words1 \
$(DISTNAME)/words2 \
$(DISTNAME)/words3 \
$(DISTNAME)/sample1.ref \
$(DISTNAME)/sample2.ref \
$(DISTNAME)/sample3.ref \
$(DISTNAME)/sample1.bz2 \
$(DISTNAME)/sample2.bz2 \
$(DISTNAME)/sample3.bz2 \
$(DISTNAME)/dlltest.c \
$(DISTNAME)/manual.html \
$(DISTNAME)/manual.pdf \
$(DISTNAME)/manual.ps \
$(DISTNAME)/README \
$(DISTNAME)/README.COMPILATION.PROBLEMS \
$(DISTNAME)/README.XML.STUFF \
$(DISTNAME)/CHANGES \
$(DISTNAME)/libbz2.def \
$(DISTNAME)/libbz2.dsp \
$(DISTNAME)/dlltest.dsp \
$(DISTNAME)/makefile.msc \
$(DISTNAME)/unzcrash.c \
$(DISTNAME)/spewG.c \
$(DISTNAME)/mk251.c \
$(DISTNAME)/bzdiff \
$(DISTNAME)/bzdiff.1 \
$(DISTNAME)/bzmore \
$(DISTNAME)/bzmore.1 \
$(DISTNAME)/bzgrep \
$(DISTNAME)/bzgrep.1 \
$(DISTNAME)/Makefile-libbz2_so \
$(DISTNAME)/bz-common.xsl \
$(DISTNAME)/bz-fo.xsl \
$(DISTNAME)/bz-html.xsl \
$(DISTNAME)/bzip.css \
$(DISTNAME)/entities.xml \
$(DISTNAME)/manual.xml \
$(DISTNAME)/format.pl \
$(DISTNAME)/xmlproc.sh
gzip -v $(DISTNAME).tar
# For rebuilding the manual from sources on my SuSE 9.1 box
MANUAL_SRCS= bz-common.xsl bz-fo.xsl bz-html.xsl bzip.css \
entities.xml manual.xml
manual: manual.html manual.ps manual.pdf
manual.ps: $(MANUAL_SRCS)
./xmlproc.sh -ps manual.xml
manual.pdf: $(MANUAL_SRCS)
./xmlproc.sh -pdf manual.xml
manual.html: $(MANUAL_SRCS)
./xmlproc.sh -html manual.xml

59
Makefile-libbz2_so Normal file
View File

@ -0,0 +1,59 @@
# This Makefile builds a shared version of the library,
# libbz2.so.1.0.6, with soname libbz2.so.1.0,
# at least on x86-Linux (RedHat 7.2),
# with gcc-2.96 20000731 (Red Hat Linux 7.1 2.96-98).
# Please see the README file for some important info
# about building the library like this.
# ------------------------------------------------------------------
# This file is part of bzip2/libbzip2, a program and library for
# lossless, block-sorting data compression.
#
# bzip2/libbzip2 version 1.0.6 of 6 September 2010
# Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
#
# Please read the WARNING, DISCLAIMER and PATENTS sections in the
# README file.
#
# This program is released under the terms of the license contained
# in the file LICENSE.
# ------------------------------------------------------------------
SHELL=/bin/sh
CC=gcc
BIGFILES=-D_FILE_OFFSET_BITS=64
CFLAGS=-fpic -fPIC -Wall -Winline -O2 -g $(BIGFILES)
OBJS= blocksort.o \
huffman.o \
crctable.o \
randtable.o \
compress.o \
decompress.o \
bzlib.o
all: $(OBJS)
$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.6 $(OBJS)
$(CC) $(CFLAGS) -o bzip2-shared bzip2.c libbz2.so.1.0.6
rm -f libbz2.so.1.0
ln -s libbz2.so.1.0.6 libbz2.so.1.0
clean:
rm -f $(OBJS) bzip2.o libbz2.so.1.0.6 libbz2.so.1.0 bzip2-shared
blocksort.o: blocksort.c
$(CC) $(CFLAGS) -c blocksort.c
huffman.o: huffman.c
$(CC) $(CFLAGS) -c huffman.c
crctable.o: crctable.c
$(CC) $(CFLAGS) -c crctable.c
randtable.o: randtable.c
$(CC) $(CFLAGS) -c randtable.c
compress.o: compress.c
$(CC) $(CFLAGS) -c compress.c
decompress.o: decompress.c
$(CC) $(CFLAGS) -c decompress.c
bzlib.o: bzlib.c
$(CC) $(CFLAGS) -c bzlib.c

215
README Normal file
View File

@ -0,0 +1,215 @@
This is the README for bzip2/libzip2.
This version is fully compatible with the previous public releases.
------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in this file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------
Complete documentation is available in Postscript form (manual.ps),
PDF (manual.pdf) or html (manual.html). A plain-text version of the
manual page is available as bzip2.txt.
HOW TO BUILD -- UNIX
Type 'make'. This builds the library libbz2.a and then the programs
bzip2 and bzip2recover. Six self-tests are run. If the self-tests
complete ok, carry on to installation:
To install in /usr/local/bin, /usr/local/lib, /usr/local/man and
/usr/local/include, type
make install
To install somewhere else, eg, /xxx/yyy/{bin,lib,man,include}, type
make install PREFIX=/xxx/yyy
If you are (justifiably) paranoid and want to see what 'make install'
is going to do, you can first do
make -n install or
make -n install PREFIX=/xxx/yyy respectively.
The -n instructs make to show the commands it would execute, but not
actually execute them.
HOW TO BUILD -- UNIX, shared library libbz2.so.
Do 'make -f Makefile-libbz2_so'. This Makefile seems to work for
Linux-ELF (RedHat 7.2 on an x86 box), with gcc. I make no claims
that it works for any other platform, though I suspect it probably
will work for most platforms employing both ELF and gcc.
bzip2-shared, a client of the shared library, is also built, but not
self-tested. So I suggest you also build using the normal Makefile,
since that conducts a self-test. A second reason to prefer the
version statically linked to the library is that, on x86 platforms,
building shared objects makes a valuable register (%ebx) unavailable
to gcc, resulting in a slowdown of 10%-20%, at least for bzip2.
Important note for people upgrading .so's from 0.9.0/0.9.5 to version
1.0.X. All the functions in the library have been renamed, from (eg)
bzCompress to BZ2_bzCompress, to avoid namespace pollution.
Unfortunately this means that the libbz2.so created by
Makefile-libbz2_so will not work with any program which used an older
version of the library. I do encourage library clients to make the
effort to upgrade to use version 1.0, since it is both faster and more
robust than previous versions.
HOW TO BUILD -- Windows 95, NT, DOS, Mac, etc.
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 the master web site (http://www.bzip.org). Look there. However
(FWIW), bzip2-1.0.X is very standard ANSI C and should compile
unmodified with MS Visual C. If you have difficulties building, you
might want to read README.COMPILATION.PROBLEMS.
At least using MS Visual C++ 6, you can build from the unmodified
sources by issuing, in a command shell:
nmake -f makefile.msc
(you may need to first run the MSVC-provided script VCVARS32.BAT
so as to set up paths to the MSVC tools correctly).
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.
Please read and be aware of the following:
WARNING:
This program and library (attempts to) compress data by
performing several non-trivial transformations on it.
Unless you are 100% familiar with *all* the algorithms
contained herein, and with the consequences of modifying them,
you should NOT meddle with the compression or decompression
machinery. Incorrect changes can and very likely *will*
lead to disastrous loss of data.
DISCLAIMER:
I TAKE NO RESPONSIBILITY FOR ANY LOSS OF DATA ARISING FROM THE
USE OF THIS PROGRAM/LIBRARY, HOWSOEVER CAUSED.
Every compression of a file implies an assumption that the
compressed file can be decompressed to reproduce the original.
Great efforts in design, coding and testing have been made to
ensure that this program works correctly. However, the complexity
of the algorithms, and, in particular, the presence of various
special cases in the code which occur with very low but non-zero
probability make it impossible to rule out the possibility of bugs
remaining in the program. DO NOT COMPRESS ANY DATA WITH THIS
PROGRAM UNLESS YOU ARE PREPARED TO ACCEPT THE POSSIBILITY, HOWEVER
SMALL, THAT THE DATA WILL NOT BE RECOVERABLE.
That is not to say this program is inherently unreliable.
Indeed, I very much hope the opposite is true. bzip2/libbzip2
has been carefully constructed and extensively tested.
PATENTS:
To the best of my knowledge, bzip2/libbzip2 does not use any
patented algorithms. However, I do not have the resources
to carry out a patent search. Therefore I cannot give any
guarantee of the above statement.
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)
WHAT'S NEW IN 0.9.5 ?
* Compression speed is much less sensitive to the input
data than in previous versions. Specifically, the very
slow performance caused by repetitive data is fixed.
* Many small improvements in file and flag handling.
* A Y2K statement.
WHAT'S NEW IN 1.0.0 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.2 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.3 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.4 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.5 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.6 ?
See the CHANGES file.
I hope you find bzip2 useful. Feel free to contact me at
jseward@bzip.org
if you have any suggestions or queries. Many people mailed me with
comments, suggestions and patches after the releases of bzip-0.15,
bzip-0.21, and bzip2 versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1,
1.0.2 and 1.0.3, and the changes in bzip2 are largely a result of this
feedback. I thank you for your comments.
bzip2's "home" is http://www.bzip.org/
Julian Seward
jseward@bzip.org
Cambridge, UK.
18 July 1996 (version 0.15)
25 August 1996 (version 0.21)
7 August 1997 (bzip2, version 0.1)
29 August 1997 (bzip2, version 0.1pl2)
23 August 1998 (bzip2, version 0.9.0)
8 June 1999 (bzip2, version 0.9.5)
4 Sept 1999 (bzip2, version 0.9.5d)
5 May 2000 (bzip2, version 1.0pre8)
30 December 2001 (bzip2, version 1.0.2pre1)
15 February 2005 (bzip2, version 1.0.3)
20 December 2006 (bzip2, version 1.0.4)
10 December 2007 (bzip2, version 1.0.5)
6 Sept 2010 (bzip2, version 1.0.6)

58
README.COMPILATION.PROBLEMS Normal file
View File

@ -0,0 +1,58 @@
------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------
bzip2-1.0.6 should compile without problems on the vast majority of
platforms. Using the supplied Makefile, I've built and tested it
myself for x86-linux and amd64-linux. With makefile.msc, Visual C++
6.0 and nmake, you can build a native Win32 version too. Large file
support seems to work correctly on at least on amd64-linux.
When I say "large file" I mean a file of size 2,147,483,648 (2^31)
bytes or above. Many older OSs can't handle files above this size,
but many newer ones can. Large files are pretty huge -- most files
you'll encounter are not Large Files.
Early versions of bzip2 (0.1, 0.9.0, 0.9.5) compiled on a wide variety
of platforms without difficulty, and I hope this version will continue
in that tradition. However, in order to support large files, I've had
to include the define -D_FILE_OFFSET_BITS=64 in the Makefile. This
can cause problems.
The technique of adding -D_FILE_OFFSET_BITS=64 to get large file
support is, as far as I know, the Recommended Way to get correct large
file support. For more details, see the Large File Support
Specification, published by the Large File Summit, at
http://ftp.sas.com/standards/large.file
As a general comment, if you get compilation errors which you think
are related to large file support, try removing the above define from
the Makefile, ie, delete the line
BIGFILES=-D_FILE_OFFSET_BITS=64
from the Makefile, and do 'make clean ; make'. This will give you a
version of bzip2 without large file support, which, for most
applications, is probably not a problem.
Alternatively, try some of the platform-specific hints listed below.
You can use the spewG.c program to generate huge files to test bzip2's
large file support, if you are feeling paranoid. Be aware though that
any compilation problems which affect bzip2 will also affect spewG.c,
alas.
AIX: I have reports that for large file support, you need to specify
-D_LARGE_FILES rather than -D_FILE_OFFSET_BITS=64. I have not tested
this myself.

45
README.XML.STUFF Normal file
View File

@ -0,0 +1,45 @@
----------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
----------------------------------------------------------------
The script xmlproc.sh takes an xml file as input,
and processes it to create .pdf, .html or .ps output.
It uses format.pl, a perl script to format <pre> blocks nicely,
and add CDATA tags so writers do not have to use eg. &lt;
The file "entities.xml" must be edited to reflect current
version, year, etc.
Usage:
./xmlproc.sh -v manual.xml
Validates an xml file to ensure no dtd-compliance errors
./xmlproc.sh -html manual.xml
Output: manual.html
./xmlproc.sh -pdf manual.xml
Output: manual.pdf
./xmlproc.sh -ps manual.xml
Output: manual.ps
Notum bene:
- pdfxmltex barfs if given a filename with an underscore in it
- xmltex won't work yet - there's a bug in passivetex
which we are all waiting for Sebastian to fix.
So we are going the xml -> pdf -> ps route for the time being,
using pdfxmltex.

1094
blocksort.c Normal file
View File

File diff suppressed because it is too large Load Diff

39
bz-common.xsl Normal file
View File

@ -0,0 +1,39 @@
<?xml version="1.0"?> <!-- -*- sgml -*- -->
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<!-- we like '1.2 Title' -->
<xsl:param name="section.autolabel" select="'1'"/>
<xsl:param name="section.label.includes.component.label" select="'1'"/>
<!-- Do not put 'Chapter' at the start of eg 'Chapter 1. Doing This' -->
<xsl:param name="local.l10n.xml" select="document('')"/>
<l:i18n xmlns:l="http://docbook.sourceforge.net/xmlns/l10n/1.0">
<l:l10n language="en">
<l:context name="title-numbered">
<l:template name="chapter" text="%n.&#160;%t"/>
</l:context>
</l:l10n>
</l:i18n>
<!-- don't generate sub-tocs for qanda sets -->
<xsl:param name="generate.toc">
set toc,title
book toc,title,figure,table,example,equation
chapter toc,title
section toc
sect1 toc
sect2 toc
sect3 toc
sect4 nop
sect5 nop
qandaset toc
qandadiv nop
appendix toc,title
article/appendix nop
article toc,title
preface toc,title
reference toc,title
</xsl:param>
</xsl:stylesheet>

276
bz-fo.xsl Normal file
View File

@ -0,0 +1,276 @@
<?xml version="1.0" encoding="UTF-8"?> <!-- -*- sgml -*- -->
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:fo="http://www.w3.org/1999/XSL/Format" version="1.0">
<xsl:import href="http://docbook.sourceforge.net/release/xsl/current/fo/docbook.xsl"/>
<xsl:import href="bz-common.xsl"/>
<!-- set indent = yes while debugging, then change to NO -->
<xsl:output method="xml" indent="yes"/>
<!-- ensure only passivetex extensions are on -->
<xsl:param name="stylesheet.result.type" select="'fo'"/>
<!-- fo extensions: PDF bookmarks and index terms -->
<xsl:param name="use.extensions" select="'1'"/>
<xsl:param name="xep.extensions" select="0"/>
<xsl:param name="fop.extensions" select="0"/>
<xsl:param name="saxon.extensions" select="0"/>
<xsl:param name="passivetex.extensions" select="1"/>
<xsl:param name="tablecolumns.extension" select="'1'"/>
<!-- ensure we are using single sided -->
<xsl:param name="double.sided" select="'0'"/>
<!-- insert cross references to page numbers -->
<xsl:param name="insert.xref.page.number" select="1"/>
<!-- <?custom-pagebreak?> inserts a page break at this point -->
<xsl:template match="processing-instruction('custom-pagebreak')">
<fo:block break-before='page'/>
</xsl:template>
<!-- show links in color -->
<xsl:attribute-set name="xref.properties">
<xsl:attribute name="color">blue</xsl:attribute>
</xsl:attribute-set>
<!-- make pre listings indented a bit + a bg colour -->
<xsl:template match="programlisting | screen">
<fo:block start-indent="0.25in" wrap-option="no-wrap"
white-space-collapse="false" text-align="start"
font-family="monospace" background-color="#f2f2f9"
linefeed-treatment="preserve"
xsl:use-attribute-sets="normal.para.spacing">
<xsl:apply-templates/>
</fo:block>
</xsl:template>
<!-- make verbatim output prettier -->
<xsl:template match="literallayout">
<fo:block start-indent="0.25in" wrap-option="no-wrap"
white-space-collapse="false" text-align="start"
font-family="monospace" background-color="#edf7f4"
linefeed-treatment="preserve"
space-before="0em" space-after="0em">
<xsl:apply-templates/>
</fo:block>
</xsl:template>
<!-- workaround bug in passivetex fo output for itemizedlist -->
<xsl:template match="itemizedlist/listitem">
<xsl:variable name="id">
<xsl:call-template name="object.id"/></xsl:variable>
<xsl:variable name="itemsymbol">
<xsl:call-template name="list.itemsymbol">
<xsl:with-param name="node" select="parent::itemizedlist"/>
</xsl:call-template>
</xsl:variable>
<xsl:variable name="item.contents">
<fo:list-item-label end-indent="label-end()">
<fo:block>
<xsl:choose>
<xsl:when test="$itemsymbol='disc'">&#x2022;</xsl:when>
<xsl:when test="$itemsymbol='bullet'">&#x2022;</xsl:when>
<xsl:otherwise>&#x2022;</xsl:otherwise>
</xsl:choose>
</fo:block>
</fo:list-item-label>
<fo:list-item-body start-indent="body-start()">
<xsl:apply-templates/> <!-- removed extra block wrapper -->
</fo:list-item-body>
</xsl:variable>
<xsl:choose>
<xsl:when test="parent::*/@spacing = 'compact'">
<fo:list-item id="{$id}"
xsl:use-attribute-sets="compact.list.item.spacing">
<xsl:copy-of select="$item.contents"/>
</fo:list-item>
</xsl:when>
<xsl:otherwise>
<fo:list-item id="{$id}" xsl:use-attribute-sets="list.item.spacing">
<xsl:copy-of select="$item.contents"/>
</fo:list-item>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<!-- workaround bug in passivetex fo output for orderedlist -->
<xsl:template match="orderedlist/listitem">
<xsl:variable name="id">
<xsl:call-template name="object.id"/></xsl:variable>
<xsl:variable name="item.contents">
<fo:list-item-label end-indent="label-end()">
<fo:block>
<xsl:apply-templates select="." mode="item-number"/>
</fo:block>
</fo:list-item-label>
<fo:list-item-body start-indent="body-start()">
<xsl:apply-templates/> <!-- removed extra block wrapper -->
</fo:list-item-body>
</xsl:variable>
<xsl:choose>
<xsl:when test="parent::*/@spacing = 'compact'">
<fo:list-item id="{$id}"
xsl:use-attribute-sets="compact.list.item.spacing">
<xsl:copy-of select="$item.contents"/>
</fo:list-item>
</xsl:when>
<xsl:otherwise>
<fo:list-item id="{$id}" xsl:use-attribute-sets="list.item.spacing">
<xsl:copy-of select="$item.contents"/>
</fo:list-item>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<!-- workaround bug in passivetex fo output for variablelist -->
<xsl:param name="variablelist.as.blocks" select="1"/>
<xsl:template match="varlistentry" mode="vl.as.blocks">
<xsl:variable name="id">
<xsl:call-template name="object.id"/></xsl:variable>
<fo:block id="{$id}" xsl:use-attribute-sets="list.item.spacing"
keep-together.within-column="always"
keep-with-next.within-column="always">
<xsl:apply-templates select="term"/>
</fo:block>
<fo:block start-indent="0.5in" end-indent="0in"
space-after.minimum="0.2em"
space-after.optimum="0.4em"
space-after.maximum="0.6em">
<fo:block>
<xsl:apply-templates select="listitem"/>
</fo:block>
</fo:block>
</xsl:template>
<!-- workaround bug in footers: force right-align w/two 80|30 cols -->
<xsl:template name="footer.table">
<xsl:param name="pageclass" select="''"/>
<xsl:param name="sequence" select="''"/>
<xsl:param name="gentext-key" select="''"/>
<xsl:choose>
<xsl:when test="$pageclass = 'index'">
<xsl:attribute name="margin-left">0pt</xsl:attribute>
</xsl:when>
</xsl:choose>
<xsl:variable name="candidate">
<fo:table table-layout="fixed" width="100%">
<fo:table-column column-number="1" column-width="80%"/>
<fo:table-column column-number="2" column-width="20%"/>
<fo:table-body>
<fo:table-row height="14pt">
<fo:table-cell text-align="left" display-align="after">
<xsl:attribute name="relative-align">baseline</xsl:attribute>
<fo:block>
<fo:block> </fo:block><!-- empty cell -->
</fo:block>
</fo:table-cell>
<fo:table-cell text-align="center" display-align="after">
<xsl:attribute name="relative-align">baseline</xsl:attribute>
<fo:block>
<xsl:call-template name="footer.content">
<xsl:with-param name="pageclass" select="$pageclass"/>
<xsl:with-param name="sequence" select="$sequence"/>
<xsl:with-param name="position" select="'center'"/>
<xsl:with-param name="gentext-key" select="$gentext-key"/>
</xsl:call-template>
</fo:block>
</fo:table-cell>
</fo:table-row>
</fo:table-body>
</fo:table>
</xsl:variable>
<!-- Really output a footer? -->
<xsl:choose>
<xsl:when test="$pageclass='titlepage' and $gentext-key='book'
and $sequence='first'">
<!-- no, book titlepages have no footers at all -->
</xsl:when>
<xsl:when test="$sequence = 'blank' and $footers.on.blank.pages = 0">
<!-- no output -->
</xsl:when>
<xsl:otherwise>
<xsl:copy-of select="$candidate"/>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<!-- fix bug in headers: force right-align w/two 40|60 cols -->
<xsl:template name="header.table">
<xsl:param name="pageclass" select="''"/>
<xsl:param name="sequence" select="''"/>
<xsl:param name="gentext-key" select="''"/>
<xsl:choose>
<xsl:when test="$pageclass = 'index'">
<xsl:attribute name="margin-left">0pt</xsl:attribute>
</xsl:when>
</xsl:choose>
<xsl:variable name="candidate">
<fo:table table-layout="fixed" width="100%">
<xsl:call-template name="head.sep.rule">
<xsl:with-param name="pageclass" select="$pageclass"/>
<xsl:with-param name="sequence" select="$sequence"/>
<xsl:with-param name="gentext-key" select="$gentext-key"/>
</xsl:call-template>
<fo:table-column column-number="1" column-width="40%"/>
<fo:table-column column-number="2" column-width="60%"/>
<fo:table-body>
<fo:table-row height="14pt">
<fo:table-cell text-align="left" display-align="before">
<xsl:attribute name="relative-align">baseline</xsl:attribute>
<fo:block>
<fo:block> </fo:block><!-- empty cell -->
</fo:block>
</fo:table-cell>
<fo:table-cell text-align="center" display-align="before">
<xsl:attribute name="relative-align">baseline</xsl:attribute>
<fo:block>
<xsl:call-template name="header.content">
<xsl:with-param name="pageclass" select="$pageclass"/>
<xsl:with-param name="sequence" select="$sequence"/>
<xsl:with-param name="position" select="'center'"/>
<xsl:with-param name="gentext-key" select="$gentext-key"/>
</xsl:call-template>
</fo:block>
</fo:table-cell>
</fo:table-row>
</fo:table-body>
</fo:table>
</xsl:variable>
<!-- Really output a header? -->
<xsl:choose>
<xsl:when test="$pageclass = 'titlepage' and $gentext-key = 'book'
and $sequence='first'">
<!-- no, book titlepages have no headers at all -->
</xsl:when>
<xsl:when test="$sequence = 'blank' and $headers.on.blank.pages = 0">
<!-- no output -->
</xsl:when>
<xsl:otherwise>
<xsl:copy-of select="$candidate"/>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<!-- Bug-fix for Suse 10 PassiveTex version -->
<!-- Precompute attribute values 'cos PassiveTex is too stupid: -->
<xsl:attribute-set name="component.title.properties">
<xsl:attribute name="keep-with-next.within-column">always</xsl:attribute>
<xsl:attribute name="space-before.optimum">
<xsl:value-of select="concat($body.font.master, 'pt')"/>
</xsl:attribute>
<xsl:attribute name="space-before.minimum">
<xsl:value-of select="$body.font.master * 0.8"/>
<xsl:text>pt</xsl:text>
</xsl:attribute>
<xsl:attribute name="space-before.maximum">
<xsl:value-of select="$body.font.master * 1.2"/>
<xsl:text>pt</xsl:text>
</xsl:attribute>
<xsl:attribute name="hyphenate">false</xsl:attribute>
</xsl:attribute-set>
</xsl:stylesheet>

20
bz-html.xsl Normal file
View File

@ -0,0 +1,20 @@
<?xml version="1.0"?> <!-- -*- sgml -*- -->
<!DOCTYPE xsl:stylesheet [ <!ENTITY bz-css SYSTEM "./bzip.css"> ]>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:import href="http://docbook.sourceforge.net/release/xsl/current/html/docbook.xsl"/>
<xsl:import href="bz-common.xsl"/>
<!-- use 8859-1 encoding -->
<xsl:output method="html" encoding="ISO-8859-1" indent="yes"/>
<!-- we include the css directly when generating one large file -->
<xsl:template name="user.head.content">
<style type="text/css" media="screen">
<xsl:text>&bz-css;</xsl:text>
</style>
</xsl:template>
</xsl:stylesheet>

76
bzdiff Normal file
View File

@ -0,0 +1,76 @@
#!/bin/sh
# sh is buggy on RS/6000 AIX 3.2. Replace above line with #!/bin/ksh
# Bzcmp/diff wrapped for bzip2,
# adapted from zdiff by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
# Bzcmp and bzdiff are used to invoke the cmp or the diff pro-
# gram on compressed files. All options specified are passed
# directly to cmp or diff. If only 1 file is specified, then
# the files compared are file1 and an uncompressed file1.gz.
# If two files are specified, then they are uncompressed (if
# necessary) and fed to cmp or diff. The exit status from cmp
# or diff is preserved.
PATH="/usr/bin:/bin:$PATH"; export PATH
prog=`echo $0 | sed 's|.*/||'`
case "$prog" in
*cmp) comp=${CMP-cmp} ;;
*) comp=${DIFF-diff} ;;
esac
OPTIONS=
FILES=
for ARG
do
case "$ARG" in
-*) OPTIONS="$OPTIONS $ARG";;
*) if test -f "$ARG"; then
FILES="$FILES $ARG"
else
echo "${prog}: $ARG not found or not a regular file"
exit 1
fi ;;
esac
done
if test -z "$FILES"; then
echo "Usage: $prog [${comp}_options] file [file]"
exit 1
fi
tmp=`mktemp ${TMPDIR:-/tmp}/bzdiff.XXXXXXXXXX` || {
echo 'cannot create a temporary file' >&2
exit 1
}
set $FILES
if test $# -eq 1; then
FILE=`echo "$1" | sed 's/.bz2$//'`
bzip2 -cd "$FILE.bz2" | $comp $OPTIONS - "$FILE"
STAT="$?"
elif test $# -eq 2; then
case "$1" in
*.bz2)
case "$2" in
*.bz2)
F=`echo "$2" | sed 's|.*/||;s|.bz2$||'`
bzip2 -cdfq "$2" > $tmp
bzip2 -cdfq "$1" | $comp $OPTIONS - $tmp
STAT="$?"
/bin/rm -f $tmp;;
*) bzip2 -cdfq "$1" | $comp $OPTIONS - "$2"
STAT="$?";;
esac;;
*) case "$2" in
*.bz2)
bzip2 -cdfq "$2" | $comp $OPTIONS "$1" -
STAT="$?";;
*) $comp $OPTIONS "$1" "$2"
STAT="$?";;
esac;;
esac
exit "$STAT"
else
echo "Usage: $prog [${comp}_options] file [file]"
exit 1
fi

47
bzdiff.1 Normal file
View File

@ -0,0 +1,47 @@
\"Shamelessly copied from zmore.1 by Philippe Troin <phil@fifi.org>
\"for Debian GNU/Linux
.TH BZDIFF 1
.SH NAME
bzcmp, bzdiff \- compare bzip2 compressed files
.SH SYNOPSIS
.B bzcmp
[ cmp_options ] file1
[ file2 ]
.br
.B bzdiff
[ diff_options ] file1
[ file2 ]
.SH DESCRIPTION
.I Bzcmp
and
.I bzdiff
are used to invoke the
.I cmp
or the
.I diff
program on bzip2 compressed files. All options specified are passed
directly to
.I cmp
or
.IR diff "."
If only 1 file is specified, then the files compared are
.I file1
and an uncompressed
.IR file1 ".bz2."
If two files are specified, then they are uncompressed if necessary and fed to
.I cmp
or
.IR diff "."
The exit status from
.I cmp
or
.I diff
is preserved.
.SH "SEE ALSO"
cmp(1), diff(1), bzmore(1), bzless(1), bzgrep(1), bzip2(1)
.SH BUGS
Messages from the
.I cmp
or
.I diff
programs refer to temporary filenames instead of those specified.

75
bzgrep Normal file
View File

@ -0,0 +1,75 @@
#!/bin/sh
# Bzgrep wrapped for bzip2,
# adapted from zgrep by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
## zgrep notice:
## zgrep -- a wrapper around a grep program that decompresses files as needed
## Adapted from a version sent by Charles Levert <charles@comm.polymtl.ca>
PATH="/usr/bin:$PATH"; export PATH
prog=`echo $0 | sed 's|.*/||'`
case "$prog" in
*egrep) grep=${EGREP-egrep} ;;
*fgrep) grep=${FGREP-fgrep} ;;
*) grep=${GREP-grep} ;;
esac
pat=""
while test $# -ne 0; do
case "$1" in
-e | -f) opt="$opt $1"; shift; pat="$1"
if test "$grep" = grep; then # grep is buggy with -e on SVR4
grep=egrep
fi;;
-A | -B) opt="$opt $1 $2"; shift;;
-*) opt="$opt $1";;
*) if test -z "$pat"; then
pat="$1"
else
break;
fi;;
esac
shift
done
if test -z "$pat"; then
echo "grep through bzip2 files"
echo "usage: $prog [grep_options] pattern [files]"
exit 1
fi
list=0
silent=0
op=`echo "$opt" | sed -e 's/ //g' -e 's/-//g'`
case "$op" in
*l*) list=1
esac
case "$op" in
*h*) silent=1
esac
if test $# -eq 0; then
bzip2 -cdfq | $grep $opt "$pat"
exit $?
fi
res=0
for i do
if test -f "$i"; then :; else if test -f "$i.bz2"; then i="$i.bz2"; fi; fi
if test $list -eq 1; then
bzip2 -cdfq "$i" | $grep $opt "$pat" 2>&1 > /dev/null && echo $i
r=$?
elif test $# -eq 1 -o $silent -eq 1; then
bzip2 -cdfq "$i" | $grep $opt "$pat"
r=$?
else
j=${i//\\/\\\\}
j=${j//|/\\|}
j=${j//&/\\&}
j=`printf "%s" "$j" | tr '\n' ' '`
bzip2 -cdfq "$i" | $grep $opt "$pat" | sed "s|^|${j}:|"
r=$?
fi
test "$r" -ne 0 && res="$r"
done
exit $res

56
bzgrep.1 Normal file
View File

@ -0,0 +1,56 @@
\"Shamelessly copied from zmore.1 by Philippe Troin <phil@fifi.org>
\"for Debian GNU/Linux
.TH BZGREP 1
.SH NAME
bzgrep, bzfgrep, bzegrep \- search possibly bzip2 compressed files for a regular expression
.SH SYNOPSIS
.B bzgrep
[ grep_options ]
.BI [\ -e\ ] " pattern"
.IR filename ".\|.\|."
.br
.B bzegrep
[ egrep_options ]
.BI [\ -e\ ] " pattern"
.IR filename ".\|.\|."
.br
.B bzfgrep
[ fgrep_options ]
.BI [\ -e\ ] " pattern"
.IR filename ".\|.\|."
.SH DESCRIPTION
.IR Bzgrep
is used to invoke the
.I grep
on bzip2-compressed files. All options specified are passed directly to
.I grep.
If no file is specified, then the standard input is decompressed
if necessary and fed to grep.
Otherwise the given files are uncompressed if necessary and fed to
.I grep.
.PP
If
.I bzgrep
is invoked as
.I bzegrep
or
.I bzfgrep
then
.I egrep
or
.I fgrep
is used instead of
.I grep.
If the GREP environment variable is set,
.I bzgrep
uses it as the
.I grep
program to be invoked. For example:
for sh: GREP=fgrep bzgrep string files
for csh: (setenv GREP fgrep; bzgrep string files)
.SH AUTHOR
Charles Levert (charles@comm.polymtl.ca). Adapted to bzip2 by Philippe
Troin <phil@fifi.org> for Debian GNU/Linux.
.SH "SEE ALSO"
grep(1), egrep(1), fgrep(1), bzdiff(1), bzmore(1), bzless(1), bzip2(1)

74
bzip.css Normal file
View File

@ -0,0 +1,74 @@
/* Colours:
#74240f dark brown h1, h2, h3, h4
#336699 medium blue links
#339999 turquoise link hover colour
#202020 almost black general text
#761596 purple md5sum text
#626262 dark gray pre border
#eeeeee very light gray pre background
#f2f2f9 very light blue nav table background
#3366cc medium blue nav table border
*/
a, a:link, a:visited, a:active { color: #336699; }
a:hover { color: #339999; }
body { font: 80%/126% sans-serif; }
h1, h2, h3, h4 { color: #74240f; }
dt { color: #336699; font-weight: bold }
dd {
margin-left: 1.5em;
padding-bottom: 0.8em;
}
/* -- ruler -- */
div.hr_blue {
height: 3px;
background:#ffffff url("/images/hr_blue.png") repeat-x; }
div.hr_blue hr { display:none; }
/* release styles */
#release p { margin-top: 0.4em; }
#release .md5sum { color: #761596; }
/* ------ styles for docs|manuals|howto ------ */
/* -- lists -- */
ul {
margin: 0px 4px 16px 16px;
padding: 0px;
list-style: url("/images/li-blue.png");
}
ul li {
margin-bottom: 10px;
}
ul ul {
list-style-type: none;
list-style-image: none;
margin-left: 0px;
}
/* header / footer nav tables */
table.nav {
border: solid 1px #3366cc;
background: #f2f2f9;
background-color: #f2f2f9;
margin-bottom: 0.5em;
}
/* don't have underlined links in chunked nav menus */
table.nav a { text-decoration: none; }
table.nav a:hover { text-decoration: underline; }
table.nav td { font-size: 85%; }
code, tt, pre { font-size: 120%; }
code, tt { color: #761596; }
div.literallayout, pre.programlisting, pre.screen {
color: #000000;
padding: 0.5em;
background: #eeeeee;
border: 1px solid #626262;
background-color: #eeeeee;
margin: 4px 0px 4px 0px;
}

454
bzip2.1 Normal file
View File

@ -0,0 +1,454 @@
.PU
.TH bzip2 1
.SH NAME
bzip2, bunzip2 \- a block-sorting file compressor, v1.0.6
.br
bzcat \- decompresses files to stdout
.br
bzip2recover \- recovers data from damaged bzip2 files
.SH SYNOPSIS
.ll +8
.B bzip2
.RB [ " \-cdfkqstvzVL123456789 " ]
[
.I "filenames \&..."
]
.ll -8
.br
.B bunzip2
.RB [ " \-fkvsVL " ]
[
.I "filenames \&..."
]
.br
.B bzcat
.RB [ " \-s " ]
[
.I "filenames \&..."
]
.br
.B bzip2recover
.I "filename"
.SH DESCRIPTION
.I 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, and approaches the performance of the PPM
family of statistical compressors.
The command-line options are deliberately very similar to
those of
.I GNU gzip,
but they are not identical.
.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".
Each compressed file
has the same modification date, permissions, and, when possible,
ownership as the corresponding original, so that these properties can
be correctly restored at decompression time. File name handling is
naive in the sense that there is no mechanism for preserving original
file names, permissions, ownerships or dates in filesystems which lack
these concepts, or have serious file name length restrictions, such as
MS-DOS.
.I bzip2
and
.I bunzip2
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
compresses from standard
input to standard output. In this case,
.I bzip2
will decline to
write compressed output to a terminal, as this would be entirely
incomprehensible and therefore pointless.
.I bunzip2
(or
.I bzip2 \-d)
decompresses all
specified files. Files which were not created by
.I bzip2
will be detected and ignored, and a warning issued.
.I bzip2
attempts to guess the filename for the decompressed file
from that of the compressed file as follows:
filename.bz2 becomes filename
filename.bz becomes filename
filename.tbz2 becomes filename.tar
filename.tbz becomes filename.tar
anyothername becomes anyothername.out
If the file does not end in one of the recognised endings,
.I .bz2,
.I .bz,
.I .tbz2
or
.I .tbz,
.I bzip2
complains that it cannot
guess the name of the original file, and uses the original name
with
.I .out
appended.
As with compression, 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. 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.
.I bzip2
will read arguments from the environment variables
.I BZIP2
and
.I BZIP,
in that order, and will process them
before any arguments read from the command line. This gives a
convenient way to supply default arguments.
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 compression mechanism has a constant
overhead in the region of 50 bytes. Random data (including the output
of most file compressors) is coded at about 8.05 bits per byte, giving
an expansion of around 0.5%.
As a self-check for your protection,
.I
bzip2
uses 32-bit CRCs to
make sure that the decompressed version of a file is identical to the
original. This guards against corruption of the compressed data, and
against undetected bugs in
.I bzip2
(hopefully very unlikely). The
chances of data corruption going undetected is microscopic, about one
chance in four billion for each file processed. Be aware, though, that
the check occurs upon decompression, so it can only tell you that
something is wrong. It can't help you
recover the original uncompressed
data. You can use
.I bzip2recover
to try to recover data from
damaged files.
Return values: 0 for a normal exit, 1 for environmental problems (file
not found, invalid flags, I/O errors, &c), 2 to indicate a corrupt
compressed file, 3 for an internal consistency error (eg, bug) which
caused
.I bzip2
to panic.
.SH OPTIONS
.TP
.B \-c --stdout
Compress or decompress to standard output.
.TP
.B \-d --decompress
Force decompression.
.I bzip2,
.I bunzip2
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 \-z --compress
The complement to \-d: forces compression, regardless of the
invocation 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.
.TP
.B \-f --force
Force overwrite of output files. Normally,
.I bzip2
will not overwrite
existing output files. Also forces
.I bzip2
to break hard links
to files, which it otherwise wouldn't do.
bzip2 normally declines to decompress files which don't have the
correct magic header bytes. If forced (-f), however, it will pass
such files through unmodified. This is how GNU gzip behaves.
.TP
.B \-k --keep
Keep (don't delete) input files during compression
or decompression.
.TP
.B \-s --small
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 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 below.
.TP
.B \-q --quiet
Suppress non-essential warning messages. Messages pertaining to
I/O errors and other critical events will not be suppressed.
.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 -V --version
Display the software version, license terms and conditions.
.TP
.B \-1 (or \-\-fast) to \-9 (or \-\-best)
Set the block size to 100 k, 200 k .. 900 k when compressing. Has no
effect when decompressing. See MEMORY MANAGEMENT below.
The \-\-fast and \-\-best aliases are primarily for GNU gzip
compatibility. In particular, \-\-fast doesn't make things
significantly faster.
And \-\-best merely selects the default behaviour.
.TP
.B \--
Treats all subsequent arguments as file names, even if they start
with a dash. This is so you can handle files with names beginning
with a dash, for example: bzip2 \-- \-myfilename.
.TP
.B \--repetitive-fast --repetitive-best
These flags are redundant in versions 0.9.5 and above. They provided
some coarse control over the behaviour of the sorting algorithm in
earlier versions, which was sometimes useful. 0.9.5 and above have an
improved algorithm which renders these flags irrelevant.
.SH MEMORY MANAGEMENT
.I bzip2
compresses large files in blocks. The block size affects
both the compression ratio achieved, and the amount of memory needed for
compression and decompression. The flags \-1 through \-9
specify the block size to be 100,000 bytes through 900,000 bytes (the
default) respectively. At decompression time, the block size used for
compression is read from the header of the compressed file, and
.I 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.
Compression and decompression requirements,
in bytes, can be estimated as:
Compression: 400k + ( 8 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
.I bzip2
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,
.I bunzip2
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 amount of memory, about 2300
kbytes. Decompression speed is also halved, so you should use this
option only where necessary. The relevant flag is -s.
In general, try and use the largest block size memory constraints allow,
since that maximises the compression achieved. Compression and
decompression speed are virtually unaffected by block size.
Another significant point applies to files which fit in a single block
-- that means most files you'd encounter using a large block size. The
amount of real memory touched is proportional to the size of the file,
since the file is smaller than a block. For example, compressing a file
20,000 bytes long with the flag -9 will cause the compressor to
allocate around 7600k of memory, but only touch 400k + 20000 * 8 = 560
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 size for 14 files of
the Calgary Text Compression Corpus totalling 3,141,622 bytes. This
column gives some feel for how compression varies with block size.
These figures tend to understate the advantage of larger block sizes for
larger files, since the Corpus is dominated by smaller files.
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
-1 1200k 500k 350k 914704
-2 2000k 900k 600k 877703
-3 2800k 1300k 850k 860338
-4 3600k 1700k 1100k 846899
-5 4400k 2100k 1350k 845160
-6 5200k 2500k 1600k 838626
-7 6100k 2900k 1850k 834096
-8 6800k 3300k 2100k 828642
-9 7600k 3700k 2350k 828642
.SH RECOVERING DATA FROM DAMAGED FILES
.I bzip2
compresses files in blocks, usually 900kbytes long. Each
block is handled independently. If a media or transmission error causes
a multi-block .bz2
file to become damaged, it may be possible to
recover data from the undamaged blocks in the file.
The compressed representation of each block is delimited by a 48-bit
pattern, which makes it possible to find the block boundaries with
reasonable certainty. Each block also carries its own 32-bit CRC, so
damaged blocks can be distinguished from undamaged ones.
.I bzip2recover
is a simple program whose purpose is to search for
blocks in .bz2 files, and write each block out into its own .bz2
file. You can then use
.I bzip2
\-t
to test the
integrity of the resulting files, and decompress those which are
undamaged.
.I bzip2recover
takes a single argument, the name of the damaged file,
and writes a number of files "rec00001file.bz2",
"rec00002file.bz2", etc, containing the extracted blocks.
The output filenames are designed so that the use of
wildcards in subsequent processing -- for example,
"bzip2 -dc rec*file.bz2 > recovered_data" -- processes the files in
the correct order.
.I bzip2recover
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 minimise
any potential data loss through media or transmission errors,
you might consider compressing with a smaller
block size.
.SH PERFORMANCE NOTES
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 more slowly than normal. Versions 0.9.5 and above fare much
better than previous versions in this respect. The ratio between
worst-case and average-case compression time is in the region of 10:1.
For previous versions, this figure was more like 100:1. You can use the
\-vvvv option to monitor progress in great detail, if you want.
Decompression speed is unaffected by these phenomena.
.I bzip2
usually allocates several megabytes of memory to operate
in, and then charges all over it in a fairly random fashion. This means
that performance, both for compressing and decompressing, is largely
determined by the speed at which your machine can service cache misses.
Because of this, small changes to the code to reduce the miss rate have
been observed to give disproportionately large performance improvements.
I imagine
.I bzip2
will perform best on machines with very large caches.
.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 1.0.6 of
.I bzip2.
Compressed data created by this version is entirely forwards and
backwards compatible with the previous public releases, versions
0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1, 1.0.2 and above, but with the following
exception: 0.9.0 and above can correctly decompress multiple
concatenated compressed files. 0.1pl2 cannot do this; it will stop
after decompressing just the first file in the stream.
.I bzip2recover
versions prior to 1.0.2 used 32-bit integers to represent
bit positions in compressed files, so they could not handle compressed
files more than 512 megabytes long. Versions 1.0.2 and above use
64-bit ints on some platforms which support them (GNU supported
targets, and Windows). To establish whether or not bzip2recover was
built with such a limitation, run it without arguments. In any event
you can build yourself an unlimited version if you can recompile it
with MaybeUInt64 set to be an unsigned 64-bit integer.
.SH AUTHOR
Julian Seward, jsewardbzip.org.
http://www.bzip.org
The ideas embodied in
.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 the original
.I bzip,
and many refinements), and Alistair Moffat, Radford Neal and Ian Witten
(for the arithmetic 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. Bela Lubkin encouraged me to improve the
worst-case compression performance.
Donna Robinson XMLised the documentation.
The bz* scripts are derived from those of GNU gzip.
Many people sent patches, helped
with portability problems, lent machines, gave advice and were generally
helpful.

399
bzip2.1.preformatted Normal file
View File

@ -0,0 +1,399 @@
bzip2(1) bzip2(1)
NNAAMMEE
bzip2, bunzip2 − a block‐sorting file compressor, v1.0.6
bzcat − decompresses files to stdout
bzip2recover − recovers data from damaged bzip2 files
SSYYNNOOPPSSIISS
bbzziipp22 [ −−ccddffkkqqssttvvzzVVLL112233445566778899 ] [ _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
sorting text compression algorithm, and Huffman coding.
Compression is generally considerably better than that
achieved by more conventional LZ77/LZ78‐based compressors,
and approaches the performance of the PPM family of sta­
tistical compressors.
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
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, per­
missions, and, when possible, ownership as the correspond­
ing original, so that these properties can be correctly
restored at decompression time. File name handling is
naive in the sense that there is no mechanism for preserv­
ing original file names, permissions, ownerships or dates
in filesystems which lack these concepts, 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 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
will decline to write compressed output to a terminal, as
this would be entirely incomprehensible and therefore
pointless.
_b_u_n_z_i_p_2 (or _b_z_i_p_2 _−_d_) decompresses all specified files.
Files which were not created by _b_z_i_p_2 will be detected and
ignored, and a warning issued. _b_z_i_p_2 attempts to guess
the filename for the decompressed file from that of the
compressed file as follows:
filename.bz2 becomes filename
filename.bz becomes filename
filename.tbz2 becomes filename.tar
filename.tbz becomes filename.tar
anyothername becomes anyothername.out
If the file does not end in one of the recognised endings,
_._b_z_2_, _._b_z_, _._t_b_z_2 or _._t_b_z_, _b_z_i_p_2 complains that it cannot
guess the name of the original file, and uses the original
name with _._o_u_t appended.
As with compression, supplying no filenames causes decom­
pression from standard input to standard output.
_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
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.
_b_z_i_p_2 will read arguments from the environment variables
_B_Z_I_P_2 and _B_Z_I_P_, in that order, and will process them
before any arguments read from the command line. This
gives a convenient way to supply default arguments.
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
compression mechanism has a constant overhead in the
region of 50 bytes. Random data (including the output of
most file compressors) is coded at about 8.05 bits per
byte, giving an expansion of around 0.5%.
As a self‐check for your protection, _b_z_i_p_2 uses 32‐bit
CRCs to make sure that the decompressed version of a file
is identical to the original. This guards against corrup­
tion of the compressed data, and against undetected bugs
in _b_z_i_p_2 (hopefully very unlikely). The chances of data
corruption going undetected is microscopic, about one
chance in four billion for each file processed. Be aware,
though, that the check occurs upon decompression, so it
can only tell you that something is wrong. It can’t help
you recover the original uncompressed data. You can use
_b_z_i_p_2_r_e_c_o_v_e_r to try to recover data from damaged files.
Return values: 0 for a normal exit, 1 for environmental
problems (file not found, invalid flags, I/O errors, &c),
2 to indicate a corrupt compressed file, 3 for an internal
consistency error (eg, bug) which caused _b_z_i_p_2 to panic.
OOPPTTIIOONNSS
−−cc ‐‐‐‐ssttddoouutt
Compress or decompress to standard output.
−−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,
regardless of the invocation 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.
−−ff ‐‐‐‐ffoorrccee
Force overwrite of output files. Normally, _b_z_i_p_2
will not overwrite existing output files. Also
forces _b_z_i_p_2 to break hard links to files, which it
otherwise wouldn’t do.
bzip2 normally declines to decompress files which
don’t have the correct magic header bytes. If
forced (‐f), however, it will pass such files
through unmodified. This is how GNU gzip behaves.
−−kk ‐‐‐‐kkeeeepp
Keep (don’t delete) input files during compression
or decompression.
−−ss ‐‐‐‐ssmmaallll
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
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 below.
−−qq ‐‐‐‐qquuiieett
Suppress non‐essential warning messages. Messages
pertaining to I/O errors and other critical events
will not be suppressed.
−−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 ((oorr −−−−ffaasstt)) ttoo −−99 ((oorr −−−−bbeesstt))
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
See MEMORY MANAGEMENT below. The −−fast and −−best
aliases are primarily for GNU gzip compatibility.
In particular, −−fast doesn’t make things signifi­
cantly faster. And −−best merely selects the
default behaviour.
−−‐‐ Treats all subsequent arguments as file names, even
if they start with a dash. This is so you can han­
dle files with names beginning with a dash, for
example: bzip2 −‐ −myfilename.
−−‐‐rreeppeettiittiivvee‐‐ffaasstt ‐‐‐‐rreeppeettiittiivvee‐‐bbeesstt
These flags are redundant in versions 0.9.5 and
above. They provided some coarse control over the
behaviour of the sorting algorithm in earlier ver­
sions, which was sometimes useful. 0.9.5 and above
have an improved algorithm which renders these
flags irrelevant.
MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
_b_z_i_p_2 compresses large files in blocks. The block size
affects both the compression ratio achieved, and the
amount of memory needed for compression and decompression.
The flags −1 through −9 specify the block size to be
100,000 bytes through 900,000 bytes (the default) respec­
tively. At decompression time, the block size used for
compression is read from the header of the compressed
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.
Compression and decompression requirements, in bytes, can
be estimated as:
Compression: 400k + ( 8 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 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
sion speed is also halved, so you should use this option
only where necessary. The relevant flag is ‐s.
In general, try and use the largest block size memory con­
straints allow, since that maximises the compression
achieved. Compression and decompression speed are virtu­
ally unaffected by block size.
Another significant point applies to files which fit in a
single block ‐‐ that means most files you’d encounter
using a large block size. The amount of real memory
touched is proportional to the size of the file, since the
file is smaller than a block. For example, compressing a
file 20,000 bytes long with the flag ‐9 will cause the
compressor to allocate around 7600k of memory, but only
touch 400k + 20000 * 8 = 560 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 size for 14 files of the Calgary Text Compres­
sion Corpus totalling 3,141,622 bytes. This column gives
some feel for how compression varies with block size.
These figures tend to understate the advantage of larger
block sizes for larger files, since the Corpus is domi­
nated by smaller files.
Compress Decompress Decompress Corpus
Flag usage usage ‐s usage Size
‐1 1200k 500k 350k 914704
‐2 2000k 900k 600k 877703
‐3 2800k 1300k 850k 860338
‐4 3600k 1700k 1100k 846899
‐5 4400k 2100k 1350k 845160
‐6 5200k 2500k 1600k 838626
‐7 6100k 2900k 1850k 834096
‐8 6800k 3300k 2100k 828642
‐9 7600k 3700k 2350k 828642
RREECCOOVVEERRIINNGG DDAATTAA FFRROOMM DDAAMMAAGGEEDD FFIILLEESS
_b_z_i_p_2 compresses files in blocks, usually 900kbytes long.
Each block is handled independently. If a media or trans­
mission error causes a multi‐block .bz2 file to become
damaged, it may be possible to recover data from the
undamaged blocks in the file.
The compressed representation of each block is delimited
by a 48‐bit pattern, which makes it possible to find the
block boundaries with reasonable certainty. Each block
also carries its own 32‐bit CRC, so damaged blocks can be
distinguished from undamaged ones.
_b_z_i_p_2_r_e_c_o_v_e_r is a simple program whose purpose is to
search for blocks in .bz2 files, and write each block out
into its own .bz2 file. You can then use _b_z_i_p_2 −t to test
the integrity of the resulting files, and decompress those
which are undamaged.
_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
"rec00001file.bz2", "rec00002file.bz2", etc, containing
the extracted blocks. The output filenames are
designed so that the use of wildcards in subsequent pro­
cessing ‐‐ for example, "bzip2 ‐dc rec*file.bz2 > recov­
ered_data" ‐‐ processes the files in the correct 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 more
slowly than normal. Versions 0.9.5 and above fare much
better than previous versions in this respect. The ratio
between worst‐case and average‐case compression time is in
the region of 10:1. For previous versions, this figure
was more like 100:1. You can use the −vvvv option to mon­
itor progress in great detail, if you want.
Decompression speed is unaffected by these phenomena.
_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
pressing and decompressing, is largely determined by the
speed at which your machine can service cache misses.
Because of this, small changes to the code to reduce the
miss rate have been observed to give disproportionately
large performance improvements. I imagine _b_z_i_p_2 will per­
form best on machines with very large caches.
CCAAVVEEAATTSS
I/O error messages are not as helpful as they could be.
_b_z_i_p_2 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 1.0.6 of _b_z_i_p_2_. Com­
pressed data created by this version is entirely forwards
and backwards compatible with the previous public
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1,
1.0.2 and above, but with the following exception: 0.9.0
and above can correctly decompress multiple concatenated
compressed files. 0.1pl2 cannot do this; it will stop
after decompressing just the first file in the stream.
_b_z_i_p_2_r_e_c_o_v_e_r versions prior to 1.0.2 used 32‐bit integers
to represent bit positions in compressed files, so they
could not handle compressed files more than 512 megabytes
long. Versions 1.0.2 and above use 64‐bit ints on some
platforms which support them (GNU supported targets, and
Windows). To establish whether or not bzip2recover was
built with such a limitation, run it without arguments.
In any event you can build yourself an unlimited version
if you can recompile it with MaybeUInt64 set to be an
unsigned 64‐bit integer.
AAUUTTHHOORR
Julian Seward, jsewardbzip.org.
http://www.bzip.org
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. Donna Robinson XMLised the docu­
mentation. The bz* scripts are derived from those of GNU
gzip. Many people sent patches, helped with portability
problems, lent machines, gave advice and were generally
helpful.
bzip2(1)

2034
bzip2.c Normal file
View File

File diff suppressed because it is too large Load Diff

391
bzip2.txt Normal file
View File

@ -0,0 +1,391 @@
NAME
bzip2, bunzip2 - a block-sorting file compressor, v1.0.6
bzcat - decompresses files to stdout
bzip2recover - recovers data from damaged bzip2 files
SYNOPSIS
bzip2 [ -cdfkqstvzVL123456789 ] [ filenames ... ]
bunzip2 [ -fkvsVL ] [ filenames ... ]
bzcat [ -s ] [ filenames ... ]
bzip2recover filename
DESCRIPTION
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,
and approaches the performance of the PPM family of sta-
tistical compressors.
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-
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, per-
missions, and, when possible, ownership as the correspond-
ing original, so that these properties can be correctly
restored at decompression time. File name handling is
naive in the sense that there is no mechanism for preserv-
ing original file names, permissions, ownerships or dates
in filesystems which lack these concepts, or have serious
file name length restrictions, such as MS-DOS.
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
will decline to write compressed output to a terminal, as
this would be entirely incomprehensible and therefore
pointless.
bunzip2 (or bzip2 -d) decompresses all specified files.
Files which were not created by bzip2 will be detected and
ignored, and a warning issued. bzip2 attempts to guess
the filename for the decompressed file from that of the
compressed file as follows:
filename.bz2 becomes filename
filename.bz becomes filename
filename.tbz2 becomes filename.tar
filename.tbz becomes filename.tar
anyothername becomes anyothername.out
If the file does not end in one of the recognised endings,
.bz2, .bz, .tbz2 or .tbz, bzip2 complains that it cannot
guess the name of the original file, and uses the original
name with .out appended.
As with compression, supplying no filenames causes decom-
pression 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. 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.
bzip2 will read arguments from the environment variables
BZIP2 and BZIP, in that order, and will process them
before any arguments read from the command line. This
gives a convenient way to supply default arguments.
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
compression mechanism has a constant overhead in the
region of 50 bytes. Random data (including the output of
most file compressors) is coded at about 8.05 bits per
byte, giving an expansion of around 0.5%.
As a self-check for your protection, bzip2 uses 32-bit
CRCs to make sure that the decompressed version of a file
is identical to the original. This guards against corrup-
tion of the compressed data, and against undetected bugs
in bzip2 (hopefully very unlikely). The chances of data
corruption going undetected is microscopic, about one
chance in four billion for each file processed. Be aware,
though, that the check occurs upon decompression, so it
can only tell you that something is wrong. It can't help
you recover the original uncompressed data. You can use
bzip2recover to try to recover data from damaged files.
Return values: 0 for a normal exit, 1 for environmental
problems (file not found, invalid flags, I/O errors, &c),
2 to indicate a corrupt compressed file, 3 for an internal
consistency error (eg, bug) which caused bzip2 to panic.
OPTIONS
-c --stdout
Compress or decompress to standard output.
-d --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.
-z --compress
The complement to -d: forces compression,
regardless of the invocation 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.
-f --force
Force overwrite of output files. Normally, bzip2
will not overwrite existing output files. Also
forces bzip2 to break hard links to files, which it
otherwise wouldn't do.
bzip2 normally declines to decompress files which
don't have the correct magic header bytes. If
forced (-f), however, it will pass such files
through unmodified. This is how GNU gzip behaves.
-k --keep
Keep (don't delete) input files during compression
or decompression.
-s --small
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
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 below.
-q --quiet
Suppress non-essential warning messages. Messages
pertaining to I/O errors and other critical events
will not be suppressed.
-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 -V --version
Display the software version, license terms and
conditions.
-1 (or --fast) to -9 (or --best)
Set the block size to 100 k, 200 k .. 900 k when
compressing. Has no effect when decompressing.
See MEMORY MANAGEMENT below. The --fast and --best
aliases are primarily for GNU gzip compatibility.
In particular, --fast doesn't make things signifi-
cantly faster. And --best merely selects the
default behaviour.
-- Treats all subsequent arguments as file names, even
if they start with a dash. This is so you can han-
dle files with names beginning with a dash, for
example: bzip2 -- -myfilename.
--repetitive-fast --repetitive-best
These flags are redundant in versions 0.9.5 and
above. They provided some coarse control over the
behaviour of the sorting algorithm in earlier ver-
sions, which was sometimes useful. 0.9.5 and above
have an improved algorithm which renders these
flags irrelevant.
MEMORY MANAGEMENT
bzip2 compresses large files in blocks. The block size
affects both the compression ratio achieved, and the
amount of memory needed for compression and decompression.
The flags -1 through -9 specify the block size to be
100,000 bytes through 900,000 bytes (the default) respec-
tively. At decompression time, the block size used for
compression is read from the header of the compressed
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.
Compression and decompression requirements, in bytes, can
be estimated as:
Compression: 400k + ( 8 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 bzip2 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,
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-
sion speed is also halved, so you should use this option
only where necessary. The relevant flag is -s.
In general, try and use the largest block size memory con-
straints allow, since that maximises the compression
achieved. Compression and decompression speed are virtu-
ally unaffected by block size.
Another significant point applies to files which fit in a
single block -- that means most files you'd encounter
using a large block size. The amount of real memory
touched is proportional to the size of the file, since the
file is smaller than a block. For example, compressing a
file 20,000 bytes long with the flag -9 will cause the
compressor to allocate around 7600k of memory, but only
touch 400k + 20000 * 8 = 560 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 size for 14 files of the Calgary Text Compres-
sion Corpus totalling 3,141,622 bytes. This column gives
some feel for how compression varies with block size.
These figures tend to understate the advantage of larger
block sizes for larger files, since the Corpus is domi-
nated by smaller files.
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
-1 1200k 500k 350k 914704
-2 2000k 900k 600k 877703
-3 2800k 1300k 850k 860338
-4 3600k 1700k 1100k 846899
-5 4400k 2100k 1350k 845160
-6 5200k 2500k 1600k 838626
-7 6100k 2900k 1850k 834096
-8 6800k 3300k 2100k 828642
-9 7600k 3700k 2350k 828642
RECOVERING DATA FROM DAMAGED FILES
bzip2 compresses files in blocks, usually 900kbytes long.
Each block is handled independently. If a media or trans-
mission error causes a multi-block .bz2 file to become
damaged, it may be possible to recover data from the
undamaged blocks in the file.
The compressed representation of each block is delimited
by a 48-bit pattern, which makes it possible to find the
block boundaries with reasonable certainty. Each block
also carries its own 32-bit CRC, so damaged blocks can be
distinguished from undamaged ones.
bzip2recover is a simple program whose purpose is to
search for blocks in .bz2 files, and write each block out
into its own .bz2 file. You can then use bzip2 -t to test
the integrity of the resulting files, and decompress those
which are undamaged.
bzip2recover takes a single argument, the name of the dam-
aged file, and writes a number of files
"rec00001file.bz2", "rec00002file.bz2", etc, containing
the extracted blocks. The output filenames are
designed so that the use of wildcards in subsequent pro-
cessing -- for example, "bzip2 -dc rec*file.bz2 > recov-
ered_data" -- processes the files in the correct order.
bzip2recover 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.
PERFORMANCE NOTES
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 more
slowly than normal. Versions 0.9.5 and above fare much
better than previous versions in this respect. The ratio
between worst-case and average-case compression time is in
the region of 10:1. For previous versions, this figure
was more like 100:1. You can use the -vvvv option to mon-
itor progress in great detail, if you want.
Decompression speed is unaffected by these phenomena.
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-
pressing and decompressing, is largely determined by the
speed at which your machine can service cache misses.
Because of this, small changes to the code to reduce the
miss rate have been observed to give disproportionately
large performance improvements. I imagine bzip2 will per-
form best on machines with very large caches.
CAVEATS
I/O error messages are not as helpful as they could be.
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 1.0.6 of bzip2. Com-
pressed data created by this version is entirely forwards
and backwards compatible with the previous public
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1,
1.0.2 and above, but with the following exception: 0.9.0
and above can correctly decompress multiple concatenated
compressed files. 0.1pl2 cannot do this; it will stop
after decompressing just the first file in the stream.
bzip2recover versions prior to 1.0.2 used 32-bit integers
to represent bit positions in compressed files, so they
could not handle compressed files more than 512 megabytes
long. Versions 1.0.2 and above use 64-bit ints on some
platforms which support them (GNU supported targets, and
Windows). To establish whether or not bzip2recover was
built with such a limitation, run it without arguments.
In any event you can build yourself an unlimited version
if you can recompile it with MaybeUInt64 set to be an
unsigned 64-bit integer.
AUTHOR
Julian Seward, jsewardbzip.org.
http://www.bzip.org
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. Donna Robinson XMLised the docu-
mentation. The bz* scripts are derived from those of GNU
gzip. Many people sent patches, helped with portability
problems, lent machines, gave advice and were generally
helpful.

514
bzip2recover.c Normal file
View File

@ -0,0 +1,514 @@
/*-----------------------------------------------------------*/
/*--- Block recoverer program for bzip2 ---*/
/*--- bzip2recover.c ---*/
/*-----------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
/* This program is a complete hack and should be rewritten properly.
It isn't very complicated. */
#include <stdio.h>
#include <errno.h>
#include <stdlib.h>
#include <string.h>
/* This program records bit locations in the file to be recovered.
That means that if 64-bit ints are not supported, we will not
be able to recover .bz2 files over 512MB (2^32 bits) long.
On GNU supported platforms, we take advantage of the 64-bit
int support to circumvent this problem. Ditto MSVC.
This change occurred in version 1.0.2; all prior versions have
the 512MB limitation.
*/
#ifdef __GNUC__
typedef unsigned long long int MaybeUInt64;
# define MaybeUInt64_FMT "%Lu"
#else
#ifdef _MSC_VER
typedef unsigned __int64 MaybeUInt64;
# define MaybeUInt64_FMT "%I64u"
#else
typedef unsigned int MaybeUInt64;
# define MaybeUInt64_FMT "%u"
#endif
#endif
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)
#define BZ_MAX_FILENAME 2000
Char inFileName[BZ_MAX_FILENAME];
Char outFileName[BZ_MAX_FILENAME];
Char progName[BZ_MAX_FILENAME];
MaybeUInt64 bytesOut = 0;
MaybeUInt64 bytesIn = 0;
/*---------------------------------------------------*/
/*--- Header bytes ---*/
/*---------------------------------------------------*/
#define BZ_HDR_B 0x42 /* 'B' */
#define BZ_HDR_Z 0x5a /* 'Z' */
#define BZ_HDR_h 0x68 /* 'h' */
#define BZ_HDR_0 0x30 /* '0' */
/*---------------------------------------------------*/
/*--- I/O errors ---*/
/*---------------------------------------------------*/
/*---------------------------------------------*/
static void readError ( void )
{
fprintf ( stderr,
"%s: I/O error reading `%s', possible reason follows.\n",
progName, inFileName );
perror ( progName );
fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
progName );
exit ( 1 );
}
/*---------------------------------------------*/
static void writeError ( void )
{
fprintf ( stderr,
"%s: I/O error reading `%s', possible reason follows.\n",
progName, inFileName );
perror ( progName );
fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
progName );
exit ( 1 );
}
/*---------------------------------------------*/
static void mallocFail ( Int32 n )
{
fprintf ( stderr,
"%s: malloc failed on request for %d bytes.\n",
progName, n );
fprintf ( stderr, "%s: warning: output file(s) may be incomplete.\n",
progName );
exit ( 1 );
}
/*---------------------------------------------*/
static void tooManyBlocks ( Int32 max_handled_blocks )
{
fprintf ( stderr,
"%s: `%s' appears to contain more than %d blocks\n",
progName, inFileName, max_handled_blocks );
fprintf ( stderr,
"%s: and cannot be handled. To fix, increase\n",
progName );
fprintf ( stderr,
"%s: BZ_MAX_HANDLED_BLOCKS in bzip2recover.c, and recompile.\n",
progName );
exit ( 1 );
}
/*---------------------------------------------------*/
/*--- Bit stream I/O ---*/
/*---------------------------------------------------*/
typedef
struct {
FILE* handle;
Int32 buffer;
Int32 buffLive;
Char mode;
}
BitStream;
/*---------------------------------------------*/
static BitStream* bsOpenReadStream ( FILE* stream )
{
BitStream *bs = malloc ( sizeof(BitStream) );
if (bs == NULL) mallocFail ( sizeof(BitStream) );
bs->handle = stream;
bs->buffer = 0;
bs->buffLive = 0;
bs->mode = 'r';
return bs;
}
/*---------------------------------------------*/
static BitStream* bsOpenWriteStream ( FILE* stream )
{
BitStream *bs = malloc ( sizeof(BitStream) );
if (bs == NULL) mallocFail ( sizeof(BitStream) );
bs->handle = stream;
bs->buffer = 0;
bs->buffLive = 0;
bs->mode = 'w';
return bs;
}
/*---------------------------------------------*/
static void bsPutBit ( BitStream* bs, Int32 bit )
{
if (bs->buffLive == 8) {
Int32 retVal = putc ( (UChar) bs->buffer, bs->handle );
if (retVal == EOF) writeError();
bytesOut++;
bs->buffLive = 1;
bs->buffer = bit & 0x1;
} else {
bs->buffer = ( (bs->buffer << 1) | (bit & 0x1) );
bs->buffLive++;
};
}
/*---------------------------------------------*/
/*--
Returns 0 or 1, or 2 to indicate EOF.
--*/
static Int32 bsGetBit ( BitStream* bs )
{
if (bs->buffLive > 0) {
bs->buffLive --;
return ( ((bs->buffer) >> (bs->buffLive)) & 0x1 );
} else {
Int32 retVal = getc ( bs->handle );
if ( retVal == EOF ) {
if (errno != 0) readError();
return 2;
}
bs->buffLive = 7;
bs->buffer = retVal;
return ( ((bs->buffer) >> 7) & 0x1 );
}
}
/*---------------------------------------------*/
static void bsClose ( BitStream* bs )
{
Int32 retVal;
if ( bs->mode == 'w' ) {
while ( bs->buffLive < 8 ) {
bs->buffLive++;
bs->buffer <<= 1;
};
retVal = putc ( (UChar) (bs->buffer), bs->handle );
if (retVal == EOF) writeError();
bytesOut++;
retVal = fflush ( bs->handle );
if (retVal == EOF) writeError();
}
retVal = fclose ( bs->handle );
if (retVal == EOF) {
if (bs->mode == 'w') writeError(); else readError();
}
free ( bs );
}
/*---------------------------------------------*/
static void bsPutUChar ( BitStream* bs, UChar c )
{
Int32 i;
for (i = 7; i >= 0; i--)
bsPutBit ( bs, (((UInt32) c) >> i) & 0x1 );
}
/*---------------------------------------------*/
static void bsPutUInt32 ( BitStream* bs, UInt32 c )
{
Int32 i;
for (i = 31; i >= 0; i--)
bsPutBit ( bs, (c >> i) & 0x1 );
}
/*---------------------------------------------*/
static Bool endsInBz2 ( Char* name )
{
Int32 n = strlen ( name );
if (n <= 4) return False;
return
(name[n-4] == '.' &&
name[n-3] == 'b' &&
name[n-2] == 'z' &&
name[n-1] == '2');
}
/*---------------------------------------------------*/
/*--- ---*/
/*---------------------------------------------------*/
/* This logic isn't really right when it comes to Cygwin. */
#ifdef _WIN32
# define BZ_SPLIT_SYM '\\' /* path splitter on Windows platform */
#else
# define BZ_SPLIT_SYM '/' /* path splitter on Unix platform */
#endif
#define BLOCK_HEADER_HI 0x00003141UL
#define BLOCK_HEADER_LO 0x59265359UL
#define BLOCK_ENDMARK_HI 0x00001772UL
#define BLOCK_ENDMARK_LO 0x45385090UL
/* Increase if necessary. However, a .bz2 file with > 50000 blocks
would have an uncompressed size of at least 40GB, so the chances
are low you'll need to up this.
*/
#define BZ_MAX_HANDLED_BLOCKS 50000
MaybeUInt64 bStart [BZ_MAX_HANDLED_BLOCKS];
MaybeUInt64 bEnd [BZ_MAX_HANDLED_BLOCKS];
MaybeUInt64 rbStart[BZ_MAX_HANDLED_BLOCKS];
MaybeUInt64 rbEnd [BZ_MAX_HANDLED_BLOCKS];
Int32 main ( Int32 argc, Char** argv )
{
FILE* inFile;
FILE* outFile;
BitStream* bsIn, *bsWr;
Int32 b, wrBlock, currBlock, rbCtr;
MaybeUInt64 bitsRead;
UInt32 buffHi, buffLo, blockCRC;
Char* p;
strcpy ( progName, argv[0] );
inFileName[0] = outFileName[0] = 0;
fprintf ( stderr,
"bzip2recover 1.0.6: extracts blocks from damaged .bz2 files.\n" );
if (argc != 2) {
fprintf ( stderr, "%s: usage is `%s damaged_file_name'.\n",
progName, progName );
switch (sizeof(MaybeUInt64)) {
case 8:
fprintf(stderr,
"\trestrictions on size of recovered file: None\n");
break;
case 4:
fprintf(stderr,
"\trestrictions on size of recovered file: 512 MB\n");
fprintf(stderr,
"\tto circumvent, recompile with MaybeUInt64 as an\n"
"\tunsigned 64-bit int.\n");
break;
default:
fprintf(stderr,
"\tsizeof(MaybeUInt64) is not 4 or 8 -- "
"configuration error.\n");
break;
}
exit(1);
}
if (strlen(argv[1]) >= BZ_MAX_FILENAME-20) {
fprintf ( stderr,
"%s: supplied filename is suspiciously (>= %d chars) long. Bye!\n",
progName, (int)strlen(argv[1]) );
exit(1);
}
strcpy ( inFileName, argv[1] );
inFile = fopen ( inFileName, "rb" );
if (inFile == NULL) {
fprintf ( stderr, "%s: can't read `%s'\n", progName, inFileName );
exit(1);
}
bsIn = bsOpenReadStream ( inFile );
fprintf ( stderr, "%s: searching for block boundaries ...\n", progName );
bitsRead = 0;
buffHi = buffLo = 0;
currBlock = 0;
bStart[currBlock] = 0;
rbCtr = 0;
while (True) {
b = bsGetBit ( bsIn );
bitsRead++;
if (b == 2) {
if (bitsRead >= bStart[currBlock] &&
(bitsRead - bStart[currBlock]) >= 40) {
bEnd[currBlock] = bitsRead-1;
if (currBlock > 0)
fprintf ( stderr, " block %d runs from " MaybeUInt64_FMT
" to " MaybeUInt64_FMT " (incomplete)\n",
currBlock, bStart[currBlock], bEnd[currBlock] );
} else
currBlock--;
break;
}
buffHi = (buffHi << 1) | (buffLo >> 31);
buffLo = (buffLo << 1) | (b & 1);
if ( ( (buffHi & 0x0000ffff) == BLOCK_HEADER_HI
&& buffLo == BLOCK_HEADER_LO)
||
( (buffHi & 0x0000ffff) == BLOCK_ENDMARK_HI
&& buffLo == BLOCK_ENDMARK_LO)
) {
if (bitsRead > 49) {
bEnd[currBlock] = bitsRead-49;
} else {
bEnd[currBlock] = 0;
}
if (currBlock > 0 &&
(bEnd[currBlock] - bStart[currBlock]) >= 130) {
fprintf ( stderr, " block %d runs from " MaybeUInt64_FMT
" to " MaybeUInt64_FMT "\n",
rbCtr+1, bStart[currBlock], bEnd[currBlock] );
rbStart[rbCtr] = bStart[currBlock];
rbEnd[rbCtr] = bEnd[currBlock];
rbCtr++;
}
if (currBlock >= BZ_MAX_HANDLED_BLOCKS)
tooManyBlocks(BZ_MAX_HANDLED_BLOCKS);
currBlock++;
bStart[currBlock] = bitsRead;
}
}
bsClose ( bsIn );
/*-- identified blocks run from 1 to rbCtr inclusive. --*/
if (rbCtr < 1) {
fprintf ( stderr,
"%s: sorry, I couldn't find any block boundaries.\n",
progName );
exit(1);
};
fprintf ( stderr, "%s: splitting into blocks\n", progName );
inFile = fopen ( inFileName, "rb" );
if (inFile == NULL) {
fprintf ( stderr, "%s: can't open `%s'\n", progName, inFileName );
exit(1);
}
bsIn = bsOpenReadStream ( inFile );
/*-- placate gcc's dataflow analyser --*/
blockCRC = 0; bsWr = 0;
bitsRead = 0;
outFile = NULL;
wrBlock = 0;
while (True) {
b = bsGetBit(bsIn);
if (b == 2) break;
buffHi = (buffHi << 1) | (buffLo >> 31);
buffLo = (buffLo << 1) | (b & 1);
if (bitsRead == 47+rbStart[wrBlock])
blockCRC = (buffHi << 16) | (buffLo >> 16);
if (outFile != NULL && bitsRead >= rbStart[wrBlock]
&& bitsRead <= rbEnd[wrBlock]) {
bsPutBit ( bsWr, b );
}
bitsRead++;
if (bitsRead == rbEnd[wrBlock]+1) {
if (outFile != NULL) {
bsPutUChar ( bsWr, 0x17 ); bsPutUChar ( bsWr, 0x72 );
bsPutUChar ( bsWr, 0x45 ); bsPutUChar ( bsWr, 0x38 );
bsPutUChar ( bsWr, 0x50 ); bsPutUChar ( bsWr, 0x90 );
bsPutUInt32 ( bsWr, blockCRC );
bsClose ( bsWr );
}
if (wrBlock >= rbCtr) break;
wrBlock++;
} else
if (bitsRead == rbStart[wrBlock]) {
/* Create the output file name, correctly handling leading paths.
(31.10.2001 by Sergey E. Kusikov) */
Char* split;
Int32 ofs, k;
for (k = 0; k < BZ_MAX_FILENAME; k++)
outFileName[k] = 0;
strcpy (outFileName, inFileName);
split = strrchr (outFileName, BZ_SPLIT_SYM);
if (split == NULL) {
split = outFileName;
} else {
++split;
}
/* Now split points to the start of the basename. */
ofs = split - outFileName;
sprintf (split, "rec%5d", wrBlock+1);
for (p = split; *p != 0; p++) if (*p == ' ') *p = '0';
strcat (outFileName, inFileName + ofs);
if ( !endsInBz2(outFileName)) strcat ( outFileName, ".bz2" );
fprintf ( stderr, " writing block %d to `%s' ...\n",
wrBlock+1, outFileName );
outFile = fopen ( outFileName, "wb" );
if (outFile == NULL) {
fprintf ( stderr, "%s: can't write `%s'\n",
progName, outFileName );
exit(1);
}
bsWr = bsOpenWriteStream ( outFile );
bsPutUChar ( bsWr, BZ_HDR_B );
bsPutUChar ( bsWr, BZ_HDR_Z );
bsPutUChar ( bsWr, BZ_HDR_h );
bsPutUChar ( bsWr, BZ_HDR_0 + 9 );
bsPutUChar ( bsWr, 0x31 ); bsPutUChar ( bsWr, 0x41 );
bsPutUChar ( bsWr, 0x59 ); bsPutUChar ( bsWr, 0x26 );
bsPutUChar ( bsWr, 0x53 ); bsPutUChar ( bsWr, 0x59 );
}
}
fprintf ( stderr, "%s: finished\n", progName );
return 0;
}
/*-----------------------------------------------------------*/
/*--- end bzip2recover.c ---*/
/*-----------------------------------------------------------*/

1572
bzlib.c Normal file
View File

File diff suppressed because it is too large Load Diff

282
bzlib.h Normal file
View File

@ -0,0 +1,282 @@
/*-------------------------------------------------------------*/
/*--- Public header file for the library. ---*/
/*--- bzlib.h ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#ifndef _BZLIB_H
#define _BZLIB_H
#ifdef __cplusplus
extern "C" {
#endif
#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)
#define BZ_CONFIG_ERROR (-9)
typedef
struct {
char *next_in;
unsigned int avail_in;
unsigned int total_in_lo32;
unsigned int total_in_hi32;
char *next_out;
unsigned int avail_out;
unsigned int total_out_lo32;
unsigned int total_out_hi32;
void *state;
void *(*bzalloc)(void *,int,int);
void (*bzfree)(void *,void *);
void *opaque;
}
bz_stream;
#ifndef BZ_IMPORT
#define BZ_EXPORT
#endif
#ifndef BZ_NO_STDIO
/* Need a definitition for FILE */
#include <stdio.h>
#endif
#ifdef _WIN32
# 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(BZ2_bzCompressInit) (
bz_stream* strm,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN int BZ_API(BZ2_bzCompress) (
bz_stream* strm,
int action
);
BZ_EXTERN int BZ_API(BZ2_bzCompressEnd) (
bz_stream* strm
);
BZ_EXTERN int BZ_API(BZ2_bzDecompressInit) (
bz_stream *strm,
int verbosity,
int small
);
BZ_EXTERN int BZ_API(BZ2_bzDecompress) (
bz_stream* strm
);
BZ_EXTERN int BZ_API(BZ2_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(BZ2_bzReadOpen) (
int* bzerror,
FILE* f,
int verbosity,
int small,
void* unused,
int nUnused
);
BZ_EXTERN void BZ_API(BZ2_bzReadClose) (
int* bzerror,
BZFILE* b
);
BZ_EXTERN void BZ_API(BZ2_bzReadGetUnused) (
int* bzerror,
BZFILE* b,
void** unused,
int* nUnused
);
BZ_EXTERN int BZ_API(BZ2_bzRead) (
int* bzerror,
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN BZFILE* BZ_API(BZ2_bzWriteOpen) (
int* bzerror,
FILE* f,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN void BZ_API(BZ2_bzWrite) (
int* bzerror,
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN void BZ_API(BZ2_bzWriteClose) (
int* bzerror,
BZFILE* b,
int abandon,
unsigned int* nbytes_in,
unsigned int* nbytes_out
);
BZ_EXTERN void BZ_API(BZ2_bzWriteClose64) (
int* bzerror,
BZFILE* b,
int abandon,
unsigned int* nbytes_in_lo32,
unsigned int* nbytes_in_hi32,
unsigned int* nbytes_out_lo32,
unsigned int* nbytes_out_hi32
);
#endif
/*-- Utility functions --*/
BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffCompress) (
char* dest,
unsigned int* destLen,
char* source,
unsigned int sourceLen,
int blockSize100k,
int verbosity,
int workFactor
);
BZ_EXTERN int BZ_API(BZ2_bzBuffToBuffDecompress) (
char* dest,
unsigned int* destLen,
char* source,
unsigned int sourceLen,
int small,
int verbosity
);
/*--
Code contributed by Yoshioka Tsuneo (tsuneo@rr.iij4u.or.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(BZ2_bzlibVersion) (
void
);
#ifndef BZ_NO_STDIO
BZ_EXTERN BZFILE * BZ_API(BZ2_bzopen) (
const char *path,
const char *mode
);
BZ_EXTERN BZFILE * BZ_API(BZ2_bzdopen) (
int fd,
const char *mode
);
BZ_EXTERN int BZ_API(BZ2_bzread) (
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN int BZ_API(BZ2_bzwrite) (
BZFILE* b,
void* buf,
int len
);
BZ_EXTERN int BZ_API(BZ2_bzflush) (
BZFILE* b
);
BZ_EXTERN void BZ_API(BZ2_bzclose) (
BZFILE* b
);
BZ_EXTERN const char * BZ_API(BZ2_bzerror) (
BZFILE *b,
int *errnum
);
#endif
#ifdef __cplusplus
}
#endif
#endif
/*-------------------------------------------------------------*/
/*--- end bzlib.h ---*/
/*-------------------------------------------------------------*/

509
bzlib_private.h Normal file
View File

@ -0,0 +1,509 @@
/*-------------------------------------------------------------*/
/*--- Private header file for the library. ---*/
/*--- bzlib_private.h ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#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 "1.0.6, 6-Sept-2010"
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 BZ2_bz__AssertH__fail ( int errcode );
#define AssertH(cond,errcode) \
{ if (!(cond)) BZ2_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) do { } while (0)
#define VPrintf0(zf) do { } while (0)
#define VPrintf1(zf,za1) do { } while (0)
#define VPrintf2(zf,za1,za2) do { } while (0)
#define VPrintf3(zf,za1,za2,za3) do { } while (0)
#define VPrintf4(zf,za1,za2,za3,za4) do { } while (0)
#define VPrintf5(zf,za1,za2,za3,za4,za5) do { } while (0)
#endif
#define BZALLOC(nnn) (strm->bzalloc)(strm->opaque,(nnn),1)
#define BZFREE(ppp) (strm->bzfree)(strm->opaque,(ppp))
/*-- Header bytes. --*/
#define BZ_HDR_B 0x42 /* 'B' */
#define BZ_HDR_Z 0x5a /* 'Z' */
#define BZ_HDR_h 0x68 /* 'h' */
#define BZ_HDR_0 0x30 /* '0' */
/*-- 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 BZ2_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 = BZ2_rNums[s->rTPos]; \
s->rTPos++; \
if (s->rTPos == 512) s->rTPos = 0; \
} \
s->rNToGo--;
/*-- Stuff for doing CRCs. --*/
extern UInt32 BZ2_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) ^ \
BZ2_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_N_RADIX 2
#define BZ_N_QSORT 12
#define BZ_N_SHELL 18
#define BZ_N_OVERSHOOT (BZ_N_RADIX + BZ_N_QSORT + BZ_N_SHELL + 2)
/*-- 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 */
UInt32* arr1;
UInt32* arr2;
UInt32* ftab;
Int32 origPtr;
/* aliases for arr1 and arr2 */
UInt32* ptr;
UChar* block;
UInt16* mtfv;
UChar* zbits;
/* for deciding when to use the fallback sorting algorithm */
Int32 workFactor;
/* 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 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];
/* second dimension: only 3 needed; 4 makes index calculations faster */
UInt32 len_pack[BZ_MAX_ALPHA_SIZE][4];
}
EState;
/*-- externs for compression. --*/
extern void
BZ2_blockSort ( EState* );
extern void
BZ2_compressBlock ( EState*, Bool );
extern void
BZ2_bsInitWrite ( EState* );
extern void
BZ2_hbAssignCodes ( Int32*, UChar*, Int32, Int32, Int32 );
extern void
BZ2_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) \
/* c_tPos is unsigned, hence test < 0 is pointless. */ \
if (s->tPos >= (UInt32)100000 * (UInt32)s->blockSize100k) return True; \
s->tPos = s->tt[s->tPos]; \
cccc = (UChar)(s->tPos & 0xff); \
s->tPos >>= 8;
#define BZ_GET_FAST_C(cccc) \
/* c_tPos is unsigned, hence test < 0 is pointless. */ \
if (c_tPos >= (UInt32)100000 * (UInt32)ro_blockSize100k) return True; \
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) \
/* c_tPos is unsigned, hence test < 0 is pointless. */ \
if (s->tPos >= (UInt32)100000 * (UInt32)s->blockSize100k) return True; \
cccc = BZ2_indexIntoF ( s->tPos, s->cftab ); \
s->tPos = GET_LL(s->tPos);
/*-- externs for decompression. --*/
extern Int32
BZ2_indexIntoF ( Int32, Int32* );
extern Int32
BZ2_decompress ( DState* );
extern void
BZ2_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 ---*/
/*-------------------------------------------------------------*/

61
bzmore Normal file
View File

@ -0,0 +1,61 @@
#!/bin/sh
# Bzmore wrapped for bzip2,
# adapted from zmore by Philippe Troin <phil@fifi.org> for Debian GNU/Linux.
PATH="/usr/bin:$PATH"; export PATH
prog=`echo $0 | sed 's|.*/||'`
case "$prog" in
*less) more=less ;;
*) more=more ;;
esac
if test "`echo -n a`" = "-n a"; then
# looks like a SysV system:
n1=''; n2='\c'
else
n1='-n'; n2=''
fi
oldtty=`stty -g 2>/dev/null`
if stty -cbreak 2>/dev/null; then
cb='cbreak'; ncb='-cbreak'
else
# 'stty min 1' resets eof to ^a on both SunOS and SysV!
cb='min 1 -icanon'; ncb='icanon eof ^d'
fi
if test $? -eq 0 -a -n "$oldtty"; then
trap 'stty $oldtty 2>/dev/null; exit' 0 2 3 5 10 13 15
else
trap 'stty $ncb echo 2>/dev/null; exit' 0 2 3 5 10 13 15
fi
if test $# = 0; then
if test -t 0; then
echo usage: $prog files...
else
bzip2 -cdfq | eval $more
fi
else
FIRST=1
for FILE
do
if test $FIRST -eq 0; then
echo $n1 "--More--(Next file: $FILE)$n2"
stty $cb -echo 2>/dev/null
ANS=`dd bs=1 count=1 2>/dev/null`
stty $ncb echo 2>/dev/null
echo " "
if test "$ANS" = 'e' -o "$ANS" = 'q'; then
exit
fi
fi
if test "$ANS" != 's'; then
echo "------> $FILE <------"
bzip2 -cdfq "$FILE" | eval $more
fi
if test -t; then
FIRST=0
fi
done
fi

152
bzmore.1 Normal file
View File

@ -0,0 +1,152 @@
.\"Shamelessly copied from zmore.1 by Philippe Troin <phil@fifi.org>
.\"for Debian GNU/Linux
.TH BZMORE 1
.SH NAME
bzmore, bzless \- file perusal filter for crt viewing of bzip2 compressed text
.SH SYNOPSIS
.B bzmore
[ name ... ]
.br
.B bzless
[ name ... ]
.SH NOTE
In the following description,
.I bzless
and
.I less
can be used interchangeably with
.I bzmore
and
.I more.
.SH DESCRIPTION
.I Bzmore
is a filter which allows examination of compressed or plain text files
one screenful at a time on a soft-copy terminal.
.I bzmore
works on files compressed with
.I bzip2
and also on uncompressed files.
If a file does not exist,
.I bzmore
looks for a file of the same name with the addition of a .bz2 suffix.
.PP
.I Bzmore
normally pauses after each screenful, printing --More--
at the bottom of the screen.
If the user then types a carriage return, one more line is displayed.
If the user hits a space,
another screenful is displayed. Other possibilities are enumerated later.
.PP
.I Bzmore
looks in the file
.I /etc/termcap
to determine terminal characteristics,
and to determine the default window size.
On a terminal capable of displaying 24 lines,
the default window size is 22 lines.
Other sequences which may be typed when
.I bzmore
pauses, and their effects, are as follows (\fIi\fP is an optional integer
argument, defaulting to 1) :
.PP
.IP \fIi\|\fP<space>
display
.I i
more lines, (or another screenful if no argument is given)
.PP
.IP ^D
display 11 more lines (a ``scroll'').
If
.I i
is given, then the scroll size is set to \fIi\|\fP.
.PP
.IP d
same as ^D (control-D)
.PP
.IP \fIi\|\fPz
same as typing a space except that \fIi\|\fP, if present, becomes the new
window size. Note that the window size reverts back to the default at the
end of the current file.
.PP
.IP \fIi\|\fPs
skip \fIi\|\fP lines and print a screenful of lines
.PP
.IP \fIi\|\fPf
skip \fIi\fP screenfuls and print a screenful of lines
.PP
.IP "q or Q"
quit reading the current file; go on to the next (if any)
.PP
.IP "e or q"
When the prompt --More--(Next file:
.IR file )
is printed, this command causes bzmore to exit.
.PP
.IP s
When the prompt --More--(Next file:
.IR file )
is printed, this command causes bzmore to skip the next file and continue.
.PP
.IP =
Display the current line number.
.PP
.IP \fIi\|\fP/expr
search for the \fIi\|\fP-th occurrence of the regular expression \fIexpr.\fP
If the pattern is not found,
.I bzmore
goes on to the next file (if any).
Otherwise, a screenful is displayed, starting two lines before the place
where the expression was found.
The user's erase and kill characters may be used to edit the regular
expression.
Erasing back past the first column cancels the search command.
.PP
.IP \fIi\|\fPn
search for the \fIi\|\fP-th occurrence of the last regular expression entered.
.PP
.IP !command
invoke a shell with \fIcommand\|\fP.
The character `!' in "command" are replaced with the
previous shell command. The sequence "\\!" is replaced by "!".
.PP
.IP ":q or :Q"
quit reading the current file; go on to the next (if any)
(same as q or Q).
.PP
.IP .
(dot) repeat the previous command.
.PP
The commands take effect immediately, i.e., it is not necessary to
type a carriage return.
Up to the time when the command character itself is given,
the user may hit the line kill character to cancel the numerical
argument being formed.
In addition, the user may hit the erase character to redisplay the
--More-- message.
.PP
At any time when output is being sent to the terminal, the user can
hit the quit key (normally control\-\\).
.I Bzmore
will stop sending output, and will display the usual --More--
prompt.
The user may then enter one of the above commands in the normal manner.
Unfortunately, some output is lost when this is done, due to the
fact that any characters waiting in the terminal's output queue
are flushed when the quit signal occurs.
.PP
The terminal is set to
.I noecho
mode by this program so that the output can be continuous.
What you type will thus not show on your terminal, except for the / and !
commands.
.PP
If the standard output is not a teletype, then
.I bzmore
acts just like
.I bzcat,
except that a header is printed before each file.
.SH FILES
.DT
/etc/termcap Terminal data base
.SH "SEE ALSO"
more(1), less(1), bzip2(1), bzdiff(1), bzgrep(1)

672
compress.c Normal file
View File

@ -0,0 +1,672 @@
/*-------------------------------------------------------------*/
/*--- Compression machinery (not incl block sorting) ---*/
/*--- compress.c ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
/* 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 BZ2_bsInitWrite ( EState* s )
{
s->bsLive = 0;
s->bsBuff = 0;
}
/*---------------------------------------------------*/
static
void bsFinishWrite ( EState* s )
{
while (s->bsLive > 0) {
s->zbits[s->numZ] = (UChar)(s->bsBuff >> 24);
s->numZ++;
s->bsBuff <<= 8;
s->bsLive -= 8;
}
}
/*---------------------------------------------------*/
#define bsNEEDW(nz) \
{ \
while (s->bsLive >= 8) { \
s->zbits[s->numZ] \
= (UChar)(s->bsBuff >> 24); \
s->numZ++; \
s->bsBuff <<= 8; \
s->bsLive -= 8; \
} \
}
/*---------------------------------------------------*/
static
__inline__
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;
Int32 zPend;
Int32 wr;
Int32 EOB;
/*
After sorting (eg, here),
s->arr1 [ 0 .. s->nblock-1 ] holds sorted order,
and
((UChar*)s->arr2) [ 0 .. s->nblock-1 ]
holds the original block data.
The first thing to do is generate the MTF values,
and put them in
((UInt16*)s->arr1) [ 0 .. s->nblock-1 ].
Because there are strictly fewer or equal MTF values
than block values, ptr values in this area are overwritten
with MTF values only when they are no longer needed.
The final compressed bitstream is generated into the
area starting at
(UChar*) (&((UChar*)s->arr2)[s->nblock])
These storage aliases are set up in bzCompressInit(),
except for the last one, which is arranged in
compressBlock().
*/
UInt32* ptr = s->ptr;
UChar* block = s->block;
UInt16* mtfv = s->mtfv;
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 = ptr[i]-1; if (j < 0) j += s->nblock;
ll_i = s->unseqToSeq[block[j]];
AssertD ( ll_i < s->nInUse, "generateMTFValues(2a)" );
if (yy[0] == ll_i) {
zPend++;
} else {
if (zPend > 0) {
zPend--;
while (True) {
if (zPend & 1) {
mtfv[wr] = BZ_RUNB; wr++;
s->mtfFreq[BZ_RUNB]++;
} else {
mtfv[wr] = BZ_RUNA; wr++;
s->mtfFreq[BZ_RUNA]++;
}
if (zPend < 2) break;
zPend = (zPend - 2) / 2;
};
zPend = 0;
}
{
register UChar rtmp;
register UChar* ryy_j;
register UChar rll_i;
rtmp = yy[1];
yy[1] = yy[0];
ryy_j = &(yy[1]);
rll_i = ll_i;
while ( rll_i != rtmp ) {
register UChar rtmp2;
ryy_j++;
rtmp2 = rtmp;
rtmp = *ryy_j;
*ryy_j = rtmp2;
};
yy[0] = rtmp;
j = ryy_j - &(yy[0]);
mtfv[wr] = j+1; wr++; s->mtfFreq[j+1]++;
}
}
}
if (zPend > 0) {
zPend--;
while (True) {
if (zPend & 1) {
mtfv[wr] = BZ_RUNB; wr++;
s->mtfFreq[BZ_RUNB]++;
} else {
mtfv[wr] = BZ_RUNA; wr++;
s->mtfFreq[BZ_RUNA]++;
}
if (zPend < 2) break;
zPend = (zPend - 2) / 2;
};
zPend = 0;
}
mtfv[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];
UInt16* mtfv = s->mtfv;
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;
/*---
Set up an auxiliary length table which is used to fast-track
the common case (nGroups == 6).
---*/
if (nGroups == 6) {
for (v = 0; v < alphaSize; v++) {
s->len_pack[v][0] = (s->len[1][v] << 16) | s->len[0][v];
s->len_pack[v][1] = (s->len[3][v] << 16) | s->len[2][v];
s->len_pack[v][2] = (s->len[5][v] << 16) | s->len[4][v];
}
}
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 && 50 == ge-gs+1) {
/*--- fast track the common case ---*/
register UInt32 cost01, cost23, cost45;
register UInt16 icv;
cost01 = cost23 = cost45 = 0;
# define BZ_ITER(nn) \
icv = mtfv[gs+(nn)]; \
cost01 += s->len_pack[icv][0]; \
cost23 += s->len_pack[icv][1]; \
cost45 += s->len_pack[icv][2]; \
BZ_ITER(0); BZ_ITER(1); BZ_ITER(2); BZ_ITER(3); BZ_ITER(4);
BZ_ITER(5); BZ_ITER(6); BZ_ITER(7); BZ_ITER(8); BZ_ITER(9);
BZ_ITER(10); BZ_ITER(11); BZ_ITER(12); BZ_ITER(13); BZ_ITER(14);
BZ_ITER(15); BZ_ITER(16); BZ_ITER(17); BZ_ITER(18); BZ_ITER(19);
BZ_ITER(20); BZ_ITER(21); BZ_ITER(22); BZ_ITER(23); BZ_ITER(24);
BZ_ITER(25); BZ_ITER(26); BZ_ITER(27); BZ_ITER(28); BZ_ITER(29);
BZ_ITER(30); BZ_ITER(31); BZ_ITER(32); BZ_ITER(33); BZ_ITER(34);
BZ_ITER(35); BZ_ITER(36); BZ_ITER(37); BZ_ITER(38); BZ_ITER(39);
BZ_ITER(40); BZ_ITER(41); BZ_ITER(42); BZ_ITER(43); BZ_ITER(44);
BZ_ITER(45); BZ_ITER(46); BZ_ITER(47); BZ_ITER(48); BZ_ITER(49);
# undef BZ_ITER
cost[0] = cost01 & 0xffff; cost[1] = cost01 >> 16;
cost[2] = cost23 & 0xffff; cost[3] = cost23 >> 16;
cost[4] = cost45 & 0xffff; cost[5] = cost45 >> 16;
} else {
/*--- slow version which correctly handles all situations ---*/
for (i = gs; i <= ge; i++) {
UInt16 icv = mtfv[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.
--*/
if (nGroups == 6 && 50 == ge-gs+1) {
/*--- fast track the common case ---*/
# define BZ_ITUR(nn) s->rfreq[bt][ mtfv[gs+(nn)] ]++
BZ_ITUR(0); BZ_ITUR(1); BZ_ITUR(2); BZ_ITUR(3); BZ_ITUR(4);
BZ_ITUR(5); BZ_ITUR(6); BZ_ITUR(7); BZ_ITUR(8); BZ_ITUR(9);
BZ_ITUR(10); BZ_ITUR(11); BZ_ITUR(12); BZ_ITUR(13); BZ_ITUR(14);
BZ_ITUR(15); BZ_ITUR(16); BZ_ITUR(17); BZ_ITUR(18); BZ_ITUR(19);
BZ_ITUR(20); BZ_ITUR(21); BZ_ITUR(22); BZ_ITUR(23); BZ_ITUR(24);
BZ_ITUR(25); BZ_ITUR(26); BZ_ITUR(27); BZ_ITUR(28); BZ_ITUR(29);
BZ_ITUR(30); BZ_ITUR(31); BZ_ITUR(32); BZ_ITUR(33); BZ_ITUR(34);
BZ_ITUR(35); BZ_ITUR(36); BZ_ITUR(37); BZ_ITUR(38); BZ_ITUR(39);
BZ_ITUR(40); BZ_ITUR(41); BZ_ITUR(42); BZ_ITUR(43); BZ_ITUR(44);
BZ_ITUR(45); BZ_ITUR(46); BZ_ITUR(47); BZ_ITUR(48); BZ_ITUR(49);
# undef BZ_ITUR
} else {
/*--- slow version which correctly handles all situations ---*/
for (i = gs; i <= ge; i++)
s->rfreq[bt][ mtfv[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.
--*/
/* maxLen was changed from 20 to 17 in bzip2-1.0.3. See
comment in huffman.c for details. */
for (t = 0; t < nGroups; t++)
BZ2_hbMakeCodeLengths ( &(s->len[t][0]), &(s->rfreq[t][0]),
alphaSize, 17 /*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 > 17 /*20*/ ), 3004 );
AssertH ( !(minLen < 1), 3005 );
BZ2_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;
AssertH ( s->selector[selCtr] < nGroups, 3006 );
if (nGroups == 6 && 50 == ge-gs+1) {
/*--- fast track the common case ---*/
UInt16 mtfv_i;
UChar* s_len_sel_selCtr
= &(s->len[s->selector[selCtr]][0]);
Int32* s_code_sel_selCtr
= &(s->code[s->selector[selCtr]][0]);
# define BZ_ITAH(nn) \
mtfv_i = mtfv[gs+(nn)]; \
bsW ( s, \
s_len_sel_selCtr[mtfv_i], \
s_code_sel_selCtr[mtfv_i] )
BZ_ITAH(0); BZ_ITAH(1); BZ_ITAH(2); BZ_ITAH(3); BZ_ITAH(4);
BZ_ITAH(5); BZ_ITAH(6); BZ_ITAH(7); BZ_ITAH(8); BZ_ITAH(9);
BZ_ITAH(10); BZ_ITAH(11); BZ_ITAH(12); BZ_ITAH(13); BZ_ITAH(14);
BZ_ITAH(15); BZ_ITAH(16); BZ_ITAH(17); BZ_ITAH(18); BZ_ITAH(19);
BZ_ITAH(20); BZ_ITAH(21); BZ_ITAH(22); BZ_ITAH(23); BZ_ITAH(24);
BZ_ITAH(25); BZ_ITAH(26); BZ_ITAH(27); BZ_ITAH(28); BZ_ITAH(29);
BZ_ITAH(30); BZ_ITAH(31); BZ_ITAH(32); BZ_ITAH(33); BZ_ITAH(34);
BZ_ITAH(35); BZ_ITAH(36); BZ_ITAH(37); BZ_ITAH(38); BZ_ITAH(39);
BZ_ITAH(40); BZ_ITAH(41); BZ_ITAH(42); BZ_ITAH(43); BZ_ITAH(44);
BZ_ITAH(45); BZ_ITAH(46); BZ_ITAH(47); BZ_ITAH(48); BZ_ITAH(49);
# undef BZ_ITAH
} else {
/*--- slow version which correctly handles all situations ---*/
for (i = gs; i <= ge; i++) {
bsW ( s,
s->len [s->selector[selCtr]] [mtfv[i]],
s->code [s->selector[selCtr]] [mtfv[i]] );
}
}
gs = ge+1;
selCtr++;
}
AssertH( selCtr == nSelectors, 3007 );
if (s->verbosity >= 3)
VPrintf1( "codes %d\n", s->numZ-nBytes );
}
/*---------------------------------------------------*/
void BZ2_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%08x, "
"combined CRC = 0x%08x, size = %d\n",
s->blockNo, s->blockCRC, s->combinedCRC, s->nblock );
BZ2_blockSort ( s );
}
s->zbits = (UChar*) (&((UChar*)s->arr2)[s->nblock]);
/*-- If this is the first block, create the stream header. --*/
if (s->blockNo == 1) {
BZ2_bsInitWrite ( s );
bsPutUChar ( s, BZ_HDR_B );
bsPutUChar ( s, BZ_HDR_Z );
bsPutUChar ( s, BZ_HDR_h );
bsPutUChar ( s, (UChar)(BZ_HDR_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 (non-)randomisation.
As of version 0.9.5, we use a better sorting algorithm
which makes randomisation unnecessary. So always set
the randomised bit to 'no'. Of course, the decoder
still needs to be able to handle randomised blocks
so as to maintain backwards compatibility with
older versions of bzip2.
--*/
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) {
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%08x\n ", s->combinedCRC );
bsFinishWrite ( s );
}
}
/*-------------------------------------------------------------*/
/*--- end compress.c ---*/
/*-------------------------------------------------------------*/

104
crctable.c Normal file
View File

@ -0,0 +1,104 @@
/*-------------------------------------------------------------*/
/*--- Table for doing CRCs ---*/
/*--- crctable.c ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#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 BZ2_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 ---*/
/*-------------------------------------------------------------*/

646
decompress.c Normal file
View File

@ -0,0 +1,646 @@
/*-------------------------------------------------------------*/
/*--- Decompression machinery ---*/
/*--- decompress.c ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#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_lo32++; \
if (s->strm->total_in_lo32 == 0) \
s->strm->total_in_hi32++; \
}
#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++; \
if (groupNo >= nSelectors) \
RETURN(BZ_DATA_ERROR); \
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 (1) { \
if (zn > 20 /* the longest code */) \
RETURN(BZ_DATA_ERROR); \
if (zvec <= gLimit[zn]) break; \
zn++; \
GET_BIT(label2, zj); \
zvec = (zvec << 1) | zj; \
}; \
if (zvec - gBase[zn] < 0 \
|| zvec - gBase[zn] >= BZ_MAX_ALPHA_SIZE) \
RETURN(BZ_DATA_ERROR); \
lval = gPerm[zvec - gBase[zn]]; \
}
/*---------------------------------------------------*/
Int32 BZ2_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 != BZ_HDR_B) RETURN(BZ_DATA_ERROR_MAGIC);
GET_UCHAR(BZ_X_MAGIC_2, uc);
if (uc != BZ_HDR_Z) RETURN(BZ_DATA_ERROR_MAGIC);
GET_UCHAR(BZ_X_MAGIC_3, uc)
if (uc != BZ_HDR_h) RETURN(BZ_DATA_ERROR_MAGIC);
GET_BITS(BZ_X_MAGIC_4, s->blockSize100k, 8)
if (s->blockSize100k < (BZ_HDR_0 + 1) ||
s->blockSize100k > (BZ_HDR_0 + 9)) RETURN(BZ_DATA_ERROR_MAGIC);
s->blockSize100k -= BZ_HDR_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);
if (s->origPtr < 0)
RETURN(BZ_DATA_ERROR);
if (s->origPtr > 10 + 100000*s->blockSize100k)
RETURN(BZ_DATA_ERROR);
/*--- 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 );
if (s->nInUse == 0) RETURN(BZ_DATA_ERROR);
alphaSize = s->nInUse+2;
/*--- Now the selectors ---*/
GET_BITS(BZ_X_SELECTOR_1, nGroups, 3);
if (nGroups < 2 || nGroups > 6) RETURN(BZ_DATA_ERROR);
GET_BITS(BZ_X_SELECTOR_2, nSelectors, 15);
if (nSelectors < 1) RETURN(BZ_DATA_ERROR);
for (i = 0; i < nSelectors; i++) {
j = 0;
while (True) {
GET_BIT(BZ_X_SELECTOR_3, uc);
if (uc == 0) break;
j++;
if (j >= nGroups) 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];
}
BZ2_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 {
/* Check that N doesn't get too big, so that es doesn't
go negative. The maximum value that can be
RUNA/RUNB encoded is equal to the block size (post
the initial RLE), viz, 900k, so bounding N at 2
million should guard against overflow without
rejecting any legitimate inputs. */
if (N >= 2*1024*1024) RETURN(BZ_DATA_ERROR);
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) {
if (nblock >= nblockMAX) RETURN(BZ_DATA_ERROR);
s->ll16[nblock] = (UInt16)uc;
nblock++;
es--;
}
else
while (es > 0) {
if (nblock >= nblockMAX) RETURN(BZ_DATA_ERROR);
s->tt[nblock] = (UInt32)uc;
nblock++;
es--;
};
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;
}
}
/* Now we know what nblock is, we can do a better sanity
check on s->origPtr.
*/
if (s->origPtr < 0 || s->origPtr >= nblock)
RETURN(BZ_DATA_ERROR);
/*-- Set up cftab to facilitate generation of T^(-1) --*/
/* Check: unzftab entries in range. */
for (i = 0; i <= 255; i++) {
if (s->unzftab[i] < 0 || s->unzftab[i] > nblock)
RETURN(BZ_DATA_ERROR);
}
/* Actually generate cftab. */
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];
/* Check: cftab entries in range. */
for (i = 0; i <= 256; i++) {
if (s->cftab[i] < 0 || s->cftab[i] > nblock) {
/* s->cftab[i] can legitimately be == nblock */
RETURN(BZ_DATA_ERROR);
}
}
/* Check: cftab entries non-descending. */
for (i = 1; i <= 256; i++) {
if (s->cftab[i-1] > s->cftab[i]) {
RETURN(BZ_DATA_ERROR);
}
}
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" );
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 ---*/
/*-------------------------------------------------------------*/

175
dlltest.c Normal file
View File

@ -0,0 +1,175 @@
/*
minibz2
libbz2.dll test program.
by Yoshioka Tsuneo (tsuneo@rr.iij4u.or.jp)
This file is Public Domain. Welcome any email to me.
usage: minibz2 [-d] [-{1,2,..9}] [[srcfilename] destfilename]
*/
#define BZ_IMPORT
#include <stdio.h>
#include <stdlib.h>
#include "bzlib.h"
#ifdef _WIN32
#include <io.h>
#endif
#ifdef _WIN32
#define BZ2_LIBNAME "libbz2-1.0.2.DLL"
#include <windows.h>
static int BZ2DLLLoaded = 0;
static HINSTANCE BZ2DLLhLib;
int BZ2DLLLoadLibrary(void)
{
HINSTANCE hLib;
if(BZ2DLLLoaded==1){return 0;}
hLib=LoadLibrary(BZ2_LIBNAME);
if(hLib == NULL){
fprintf(stderr,"Can't load %s\n",BZ2_LIBNAME);
return -1;
}
BZ2_bzlibVersion=GetProcAddress(hLib,"BZ2_bzlibVersion");
BZ2_bzopen=GetProcAddress(hLib,"BZ2_bzopen");
BZ2_bzdopen=GetProcAddress(hLib,"BZ2_bzdopen");
BZ2_bzread=GetProcAddress(hLib,"BZ2_bzread");
BZ2_bzwrite=GetProcAddress(hLib,"BZ2_bzwrite");
BZ2_bzflush=GetProcAddress(hLib,"BZ2_bzflush");
BZ2_bzclose=GetProcAddress(hLib,"BZ2_bzclose");
BZ2_bzerror=GetProcAddress(hLib,"BZ2_bzerror");
if (!BZ2_bzlibVersion || !BZ2_bzopen || !BZ2_bzdopen
|| !BZ2_bzread || !BZ2_bzwrite || !BZ2_bzflush
|| !BZ2_bzclose || !BZ2_bzerror) {
fprintf(stderr,"GetProcAddress failed.\n");
return -1;
}
BZ2DLLLoaded=1;
BZ2DLLhLib=hLib;
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]");
}
int main(int argc,char *argv[])
{
int decompress = 0;
int level = 9;
char *fn_r = NULL;
char *fn_w = NULL;
#ifdef _WIN32
if(BZ2DLLLoadLibrary()<0){
fprintf(stderr,"Loading of %s failed. Giving up.\n", BZ2_LIBNAME);
exit(1);
}
printf("Loading of %s succeeded. Library version is %s.\n",
BZ2_LIBNAME, BZ2_bzlibVersion() );
#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 = NULL;
FILE *fp_w = NULL;
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((fn_r == NULL && (BZ2fp_r = BZ2_bzdopen(fileno(stdin),"rb"))==NULL)
|| (fn_r != NULL && (BZ2fp_r = BZ2_bzopen(fn_r,"rb"))==NULL)){
printf("can't bz2openstream\n");
exit(1);
}
while((len=BZ2_bzread(BZ2fp_r,buff,0x1000))>0){
fwrite(buff,1,len,fp_w);
}
BZ2_bzclose(BZ2fp_r);
if(fp_w != stdout) fclose(fp_w);
}else{
BZFILE *BZ2fp_w = NULL;
FILE *fp_r = NULL;
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 = BZ2_bzdopen(fileno(stdout),mode))==NULL)
|| (fn_w !=NULL && (BZ2fp_w = BZ2_bzopen(fn_w,mode))==NULL)){
printf("can't bz2openstream\n");
exit(1);
}
while((len=fread(buff,1,0x1000,fp_r))>0){
BZ2_bzwrite(BZ2fp_w,buff,len);
}
BZ2_bzclose(BZ2fp_w);
if(fp_r!=stdin)fclose(fp_r);
}
}
#ifdef _WIN32
BZ2DLLFreeLibrary();
#endif
return 0;
}

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

9
entities.xml Normal file
View File

@ -0,0 +1,9 @@
<!-- misc. strings -->
<!ENTITY bz-url "http://www.bzip.org">
<!ENTITY bz-email "jseward@bzip.org">
<!ENTITY bz-lifespan "1996-2010">
<!ENTITY bz-version "1.0.6">
<!ENTITY bz-date "6 September 2010">
<!ENTITY manual-title "bzip2 Manual">

68
format.pl Normal file
View File

@ -0,0 +1,68 @@
#!/usr/bin/perl -w
#
# ------------------------------------------------------------------
# This file is part of bzip2/libbzip2, a program and library for
# lossless, block-sorting data compression.
#
# bzip2/libbzip2 version 1.0.6 of 6 September 2010
# Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
#
# Please read the WARNING, DISCLAIMER and PATENTS sections in the
# README file.
#
# This program is released under the terms of the license contained
# in the file LICENSE.
# ------------------------------------------------------------------
#
use strict;
# get command line values:
if ( $#ARGV !=1 ) {
die "Usage: $0 xml_infile xml_outfile\n";
}
my $infile = shift;
# check infile exists
die "Can't find file \"$infile\""
unless -f $infile;
# check we can read infile
if (! -r $infile) {
die "Can't read input $infile\n";
}
# check we can open infile
open( INFILE,"<$infile" ) or
die "Can't input $infile $!";
#my $outfile = 'fmt-manual.xml';
my $outfile = shift;
#print "Infile: $infile, Outfile: $outfile\n";
# check we can write to outfile
open( OUTFILE,">$outfile" ) or
die "Can't output $outfile $! for writing";
my ($prev, $curr, $str);
$prev = ''; $curr = '';
while ( <INFILE> ) {
print OUTFILE $prev;
$prev = $curr;
$curr = $_;
$str = '';
if ( $prev =~ /<programlisting>$|<screen>$/ ) {
chomp $prev;
$curr = join( '', $prev, "<![CDATA[", $curr );
$prev = '';
next;
}
elsif ( $curr =~ /<\/programlisting>|<\/screen>/ ) {
chomp $prev;
$curr = join( '', $prev, "]]>", $curr );
$prev = '';
next;
}
}
print OUTFILE $curr;
close INFILE;
close OUTFILE;
exit;

205
huffman.c Normal file
View File

@ -0,0 +1,205 @@
/*-------------------------------------------------------------*/
/*--- Huffman coding low-level stuff ---*/
/*--- huffman.c ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#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 BZ2_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;
/* 17 Oct 04: keep-going condition for the following loop used
to be 'i < alphaSize', which missed the last element,
theoretically leading to the possibility of the compressor
looping. However, this count-scaling step is only needed if
one of the generated Huffman code words is longer than
maxLen, which up to and including version 1.0.2 was 20 bits,
which is extremely unlikely. In version 1.0.3 maxLen was
changed to 17 bits, which has minimal effect on compression
ratio, but does mean this scaling step is used from time to
time, enough to verify that it works.
This means that bzip2-1.0.3 and later will only produce
Huffman codes with a maximum length of 17 bits. However, in
order to preserve backwards compatibility with bitstreams
produced by versions pre-1.0.3, the decompressor must still
handle lengths of up to 20. */
for (i = 1; i <= alphaSize; i++) {
j = weight[i] >> 8;
j = 1 + (j / 2);
weight[i] = j << 8;
}
}
}
/*---------------------------------------------------*/
void BZ2_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 BZ2_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 ---*/
/*-------------------------------------------------------------*/

27
libbz2.def Normal file
View File

@ -0,0 +1,27 @@
LIBRARY LIBBZ2
DESCRIPTION "libbzip2: library for data compression"
EXPORTS
BZ2_bzCompressInit
BZ2_bzCompress
BZ2_bzCompressEnd
BZ2_bzDecompressInit
BZ2_bzDecompress
BZ2_bzDecompressEnd
BZ2_bzReadOpen
BZ2_bzReadClose
BZ2_bzReadGetUnused
BZ2_bzRead
BZ2_bzWriteOpen
BZ2_bzWrite
BZ2_bzWriteClose
BZ2_bzWriteClose64
BZ2_bzBuffToBuffCompress
BZ2_bzBuffToBuffDecompress
BZ2_bzlibVersion
BZ2_bzopen
BZ2_bzdopen
BZ2_bzread
BZ2_bzwrite
BZ2_bzflush
BZ2_bzclose
BZ2_bzerror

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

63
makefile.msc Normal file
View File

@ -0,0 +1,63 @@
# Makefile for Microsoft Visual C++ 6.0
# usage: nmake -f makefile.msc
# K.M. Syring (syring@gsf.de)
# Fixed up by JRS for bzip2-0.9.5d release.
CC=cl
CFLAGS= -DWIN32 -MD -Ox -D_FILE_OFFSET_BITS=64 -nologo
OBJS= blocksort.obj \
huffman.obj \
crctable.obj \
randtable.obj \
compress.obj \
decompress.obj \
bzlib.obj
all: lib bzip2 test
bzip2: lib
$(CC) $(CFLAGS) -o bzip2 bzip2.c libbz2.lib setargv.obj
$(CC) $(CFLAGS) -o bzip2recover bzip2recover.c
lib: $(OBJS)
lib /out:libbz2.lib $(OBJS)
test: bzip2
type words1
.\\bzip2 -1 < sample1.ref > sample1.rb2
.\\bzip2 -2 < sample2.ref > sample2.rb2
.\\bzip2 -3 < sample3.ref > sample3.rb2
.\\bzip2 -d < sample1.bz2 > sample1.tst
.\\bzip2 -d < sample2.bz2 > sample2.tst
.\\bzip2 -ds < sample3.bz2 > sample3.tst
@echo All six of the fc's should find no differences.
@echo If fc finds an error on sample3.bz2, this could be
@echo because WinZip's 'TAR file smart CR/LF conversion'
@echo is too clever for its own good. Disable this option.
@echo The correct size for sample3.ref is 120,244. If it
@echo is 150,251, WinZip has messed it up.
fc sample1.bz2 sample1.rb2
fc sample2.bz2 sample2.rb2
fc sample3.bz2 sample3.rb2
fc sample1.tst sample1.ref
fc sample2.tst sample2.ref
fc sample3.tst sample3.ref
clean:
del *.obj
del libbz2.lib
del bzip2.exe
del bzip2recover.exe
del sample1.rb2
del sample2.rb2
del sample3.rb2
del sample1.tst
del sample2.tst
del sample3.tst
.c.obj:
$(CC) $(CFLAGS) -c $*.c -o $*.obj

2540
manual.html Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
manual.pdf Normal file
View File

Binary file not shown.

72843
manual.ps Normal file
View File

File diff suppressed because it is too large Load Diff

2964
manual.xml Normal file
View File

File diff suppressed because it is too large Load Diff

31
mk251.c Normal file
View File

@ -0,0 +1,31 @@
/* Spew out a long sequence of the byte 251. When fed to bzip2
versions 1.0.0 or 1.0.1, causes it to die with internal error
1007 in blocksort.c. This assertion misses an extremely rare
case, which is fixed in this version (1.0.2) and above.
*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#include <stdio.h>
int main ()
{
int i;
for (i = 0; i < 48500000 ; i++)
putchar(251);
return 0;
}

84
randtable.c Normal file
View File

@ -0,0 +1,84 @@
/*-------------------------------------------------------------*/
/*--- Table for randomising repetitive blocks ---*/
/*--- randtable.c ---*/
/*-------------------------------------------------------------*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#include "bzlib_private.h"
/*---------------------------------------------*/
Int32 BZ2_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 ---*/
/*-------------------------------------------------------------*/

BIN
sample1.bz2 Normal file
View File

Binary file not shown.

BIN
sample1.ref Normal file
View File

Binary file not shown.

BIN
sample2.bz2 Normal file
View File

Binary file not shown.

BIN
sample2.ref Normal file
View File

Binary file not shown.

BIN
sample3.bz2 Normal file
View File

Binary file not shown.

30007
sample3.ref Normal file
View File

File diff suppressed because it is too large Load Diff

54
spewG.c Normal file
View File

@ -0,0 +1,54 @@
/* spew out a thoroughly gigantic file designed so that bzip2
can compress it reasonably rapidly. This is to help test
support for large files (> 2GB) in a reasonable amount of time.
I suggest you use the undocumented --exponential option to
bzip2 when compressing the resulting file; this saves a bit of
time. Note: *don't* bother with --exponential when compressing
Real Files; it'll just waste a lot of CPU time :-)
(but is otherwise harmless).
*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#define _FILE_OFFSET_BITS 64
#include <stdio.h>
#include <stdlib.h>
/* The number of megabytes of junk to spew out (roughly) */
#define MEGABYTES 5000
#define N_BUF 1000000
char buf[N_BUF];
int main ( int argc, char** argv )
{
int ii, kk, p;
srandom(1);
setbuffer ( stdout, buf, N_BUF );
for (kk = 0; kk < MEGABYTES * 515; kk+=3) {
p = 25+random()%50;
for (ii = 0; ii < p; ii++)
printf ( "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa" );
for (ii = 0; ii < p-1; ii++)
printf ( "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb" );
for (ii = 0; ii < p+1; ii++)
printf ( "ccccccccccccccccccccccccccccccccccccc" );
}
fflush(stdout);
return 0;
}

141
unzcrash.c Normal file
View File

@ -0,0 +1,141 @@
/* A test program written to test robustness to decompression of
corrupted data. Usage is
unzcrash filename
and the program will read the specified file, compress it (in memory),
and then repeatedly decompress it, each time with a different bit of
the compressed data inverted, so as to test all possible one-bit errors.
This should not cause any invalid memory accesses. If it does,
I want to know about it!
PS. As you can see from the above description, the process is
incredibly slow. A file of size eg 5KB will cause it to run for
many hours.
*/
/* ------------------------------------------------------------------
This file is part of bzip2/libbzip2, a program and library for
lossless, block-sorting data compression.
bzip2/libbzip2 version 1.0.6 of 6 September 2010
Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
Please read the WARNING, DISCLAIMER and PATENTS sections in the
README file.
This program is released under the terms of the license contained
in the file LICENSE.
------------------------------------------------------------------ */
#include <stdio.h>
#include <assert.h>
#include "bzlib.h"
#define M_BLOCK 1000000
typedef unsigned char uchar;
#define M_BLOCK_OUT (M_BLOCK + 1000000)
uchar inbuf[M_BLOCK];
uchar outbuf[M_BLOCK_OUT];
uchar zbuf[M_BLOCK + 600 + (M_BLOCK / 100)];
int nIn, nOut, nZ;
static char *bzerrorstrings[] = {
"OK"
,"SEQUENCE_ERROR"
,"PARAM_ERROR"
,"MEM_ERROR"
,"DATA_ERROR"
,"DATA_ERROR_MAGIC"
,"IO_ERROR"
,"UNEXPECTED_EOF"
,"OUTBUFF_FULL"
,"???" /* for future */
,"???" /* for future */
,"???" /* for future */
,"???" /* for future */
,"???" /* for future */
,"???" /* for future */
};
void flip_bit ( int bit )
{
int byteno = bit / 8;
int bitno = bit % 8;
uchar mask = 1 << bitno;
//fprintf ( stderr, "(byte %d bit %d mask %d)",
// byteno, bitno, (int)mask );
zbuf[byteno] ^= mask;
}
int main ( int argc, char** argv )
{
FILE* f;
int r;
int bit;
int i;
if (argc != 2) {
fprintf ( stderr, "usage: unzcrash filename\n" );
return 1;
}
f = fopen ( argv[1], "r" );
if (!f) {
fprintf ( stderr, "unzcrash: can't open %s\n", argv[1] );
return 1;
}
nIn = fread ( inbuf, 1, M_BLOCK, f );
fprintf ( stderr, "%d bytes read\n", nIn );
nZ = M_BLOCK;
r = BZ2_bzBuffToBuffCompress (
zbuf, &nZ, inbuf, nIn, 9, 0, 30 );
assert (r == BZ_OK);
fprintf ( stderr, "%d after compression\n", nZ );
for (bit = 0; bit < nZ*8; bit++) {
fprintf ( stderr, "bit %d ", bit );
flip_bit ( bit );
nOut = M_BLOCK_OUT;
r = BZ2_bzBuffToBuffDecompress (
outbuf, &nOut, zbuf, nZ, 0, 0 );
fprintf ( stderr, " %d %s ", r, bzerrorstrings[-r] );
if (r != BZ_OK) {
fprintf ( stderr, "\n" );
} else {
if (nOut != nIn) {
fprintf(stderr, "nIn/nOut mismatch %d %d\n", nIn, nOut );
return 1;
} else {
for (i = 0; i < nOut; i++)
if (inbuf[i] != outbuf[i]) {
fprintf(stderr, "mismatch at %d\n", i );
return 1;
}
if (i == nOut) fprintf(stderr, "really ok!\n" );
}
}
flip_bit ( bit );
}
#if 0
assert (nOut == nIn);
for (i = 0; i < nOut; i++) {
if (inbuf[i] != outbuf[i]) {
fprintf ( stderr, "difference at %d !\n", i );
return 1;
}
}
#endif
fprintf ( stderr, "all ok\n" );
return 0;
}

9
words0 Normal file
View File

@ -0,0 +1,9 @@
If compilation produces errors, or a large number of warnings,
please read README.COMPILATION.PROBLEMS -- you might be able to
adjust the flags in this Makefile to improve matters.
Also in README.COMPILATION.PROBLEMS are some hints that may help
if your build produces an executable which is unable to correctly
handle so-called 'large files' -- files of size 2GB or more.

4
words1 Normal file
View File

@ -0,0 +1,4 @@
Doing 6 tests (3 compress, 3 uncompress) ...
If there's a problem, things might stop at this point.

5
words2 Normal file
View File

@ -0,0 +1,5 @@
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@bzip.org).

30
words3 Normal file
View File

@ -0,0 +1,30 @@
If you got this far and the 'cmp's didn't complain, it looks
like you're in business.
To install in /usr/local/bin, /usr/local/lib, /usr/local/man and
/usr/local/include, type
make install
To install somewhere else, eg, /xxx/yyy/{bin,lib,man,include}, type
make install PREFIX=/xxx/yyy
If you are (justifiably) paranoid and want to see what 'make install'
is going to do, you can first do
make -n install or
make -n install PREFIX=/xxx/yyy respectively.
The -n instructs make to show the commands it would execute, but
not actually execute them.
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), PDF form (manual.pdf),
and HTML form (manual.html).
You can also do "bzip2 --help" to see some helpful information.
"bzip2 -L" displays the software license.

114
xmlproc.sh Normal file
View File

@ -0,0 +1,114 @@
#!/bin/bash
# see the README file for usage etc.
#
# ------------------------------------------------------------------
# This file is part of bzip2/libbzip2, a program and library for
# lossless, block-sorting data compression.
#
# bzip2/libbzip2 version 1.0.6 of 6 September 2010
# Copyright (C) 1996-2010 Julian Seward <jseward@bzip.org>
#
# Please read the WARNING, DISCLAIMER and PATENTS sections in the
# README file.
#
# This program is released under the terms of the license contained
# in the file LICENSE.
# ----------------------------------------------------------------
usage() {
echo '';
echo 'Usage: xmlproc.sh -[option] <filename.xml>';
echo 'Specify a target from:';
echo '-v verify xml file conforms to dtd';
echo '-html output in html format (single file)';
echo '-ps output in postscript format';
echo '-pdf output in pdf format';
exit;
}
if test $# -ne 2; then
usage
fi
# assign the variable for the output type
action=$1; shift
# assign the output filename
xmlfile=$1; shift
# and check user input it correct
if !(test -f $xmlfile); then
echo "No such file: $xmlfile";
exit;
fi
# some other stuff we will use
OUT=output
xsl_fo=bz-fo.xsl
xsl_html=bz-html.xsl
basename=$xmlfile
basename=${basename//'.xml'/''}
fofile="${basename}.fo"
htmlfile="${basename}.html"
pdffile="${basename}.pdf"
psfile="${basename}.ps"
xmlfmtfile="${basename}.fmt"
# first process the xmlfile with CDATA tags
./format.pl $xmlfile $xmlfmtfile
# so the shell knows where the catalogs live
export XML_CATALOG_FILES=/etc/xml/catalog
# post-processing tidy up
cleanup() {
echo "Cleaning up: $@"
while [ $# != 0 ]
do
arg=$1; shift;
echo " deleting $arg";
rm $arg
done
}
case $action in
-v)
flags='--noout --xinclude --noblanks --postvalid'
dtd='--dtdvalid http://www.oasis-open.org/docbook/xml/4.2/docbookx.dtd'
xmllint $flags $dtd $xmlfmtfile 2> $OUT
egrep 'error' $OUT
rm $OUT
;;
-html)
echo "Creating $htmlfile ..."
xsltproc --nonet --xinclude -o $htmlfile $xsl_html $xmlfmtfile
cleanup $xmlfmtfile
;;
-pdf)
echo "Creating $pdffile ..."
xsltproc --nonet --xinclude -o $fofile $xsl_fo $xmlfmtfile
pdfxmltex $fofile >$OUT </dev/null
pdfxmltex $fofile >$OUT </dev/null
pdfxmltex $fofile >$OUT </dev/null
cleanup $OUT $xmlfmtfile *.aux *.fo *.log *.out
;;
-ps)
echo "Creating $psfile ..."
xsltproc --nonet --xinclude -o $fofile $xsl_fo $xmlfmtfile
pdfxmltex $fofile >$OUT </dev/null
pdfxmltex $fofile >$OUT </dev/null
pdfxmltex $fofile >$OUT </dev/null
pdftops $pdffile $psfile
cleanup $OUT $xmlfmtfile $pdffile *.aux *.fo *.log *.out
# passivetex is broken, so we can't go this route yet.
# xmltex $fofile >$OUT </dev/null
# xmltex $fofile >$OUT </dev/null
# xmltex $fofile >$OUT </dev/null
# dvips -R -q -o bzip-manual.ps *.dvi
;;
*)
usage
;;
esac