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

bzip2-1.0.3

Browse Source
This commit is contained in:
Julian Seward 2005-02-15 22:13:13 +01:00
parent 099d844292
commit 4d540bfc95
30 changed files with 3946 additions and 2635 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
CHANGES
View File

@ -251,3 +251,25 @@ of bzip2:
* 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.
* 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.

7
LICENSE
View File

@ -1,6 +1,7 @@
This program, "bzip2" and associated library "libbzip2", are
copyright (C) 1996-2002 Julian R Seward. All rights reserved.
This program, "bzip2", the associated library "libbzip2", and all
documentation, are copyright (C) 1996-2005 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
@ -35,5 +36,5 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
bzip2/libbzip2 version 1.0.2 of 30 December 2001
bzip2/libbzip2 version 1.0.3 of 15 February 2005

51
Makefile
View File

@ -7,9 +7,8 @@ AR=ar
RANLIB=ranlib
LDFLAGS=
# Suitably paranoid flags to avoid bugs in gcc-2.7
BIGFILES=-D_FILE_OFFSET_BITS=64
CFLAGS=-Wall -Winline -O2 -fomit-frame-pointer -fno-strength-reduce $(BIGFILES)
CFLAGS=-Wall -Winline -O -g $(BIGFILES)
# Where you want it installed when you do 'make install'
PREFIX=/usr
@ -96,7 +95,6 @@ install: bzip2 bzip2recover
echo ".so man1/bzmore.1" > $(PREFIX)/man/man1/bzless.1
echo ".so man1/bzdiff.1" > $(PREFIX)/man/man1/bzcmp.1
distclean: clean
clean:
rm -f *.o libbz2.a bzip2 bzip2recover \
sample1.rb2 sample2.rb2 sample3.rb2 \
@ -122,8 +120,12 @@ bzip2.o: bzip2.c
bzip2recover.o: bzip2recover.c
$(CC) $(CFLAGS) -c bzip2recover.c
DISTNAME=bzip2-1.0.2
tarfile:
distclean: clean
rm -f manual.ps manual.html manual.pdf
DISTNAME=bzip2-1.0.3
dist: check manual
rm -f $(DISTNAME)
ln -sf . $(DISTNAME)
tar cvf $(DISTNAME).tar \
@ -139,9 +141,6 @@ tarfile:
$(DISTNAME)/bzlib.h \
$(DISTNAME)/bzlib_private.h \
$(DISTNAME)/Makefile \
$(DISTNAME)/manual.texi \
$(DISTNAME)/manual.ps \
$(DISTNAME)/manual.pdf \
$(DISTNAME)/LICENSE \
$(DISTNAME)/bzip2.1 \
$(DISTNAME)/bzip2.1.preformatted \
@ -157,9 +156,12 @@ tarfile:
$(DISTNAME)/sample2.bz2 \
$(DISTNAME)/sample3.bz2 \
$(DISTNAME)/dlltest.c \
$(DISTNAME)/*.html \
$(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 \
@ -175,18 +177,29 @@ tarfile:
$(DISTNAME)/bzmore.1 \
$(DISTNAME)/bzgrep \
$(DISTNAME)/bzgrep.1 \
$(DISTNAME)/Makefile-libbz2_so
$(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 RedHat 7.2 box
manual: manual.ps manual.pdf manual.html
# For rebuilding the manual from sources on my SuSE 9.1 box
manual.ps: manual.texi
tex manual.texi
dvips -o manual.ps manual.dvi
MANUAL_SRCS= bz-common.xsl bz-fo.xsl bz-html.xsl bzip.css \
entities.xml manual.xml
manual.pdf: manual.ps
ps2pdf manual.ps
manual: manual.html manual.ps manual.pdf
manual.html: manual.texi
texi2html -split_chapter manual.texi
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

12
Makefile-libbz2_so
View File

@ -1,6 +1,6 @@
# This Makefile builds a shared version of the library,
# libbz2.so.1.0.2, with soname libbz2.so.1.0,
# libbz2.so.1.0.3, 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
@ -9,7 +9,7 @@
SHELL=/bin/sh
CC=gcc
BIGFILES=-D_FILE_OFFSET_BITS=64
CFLAGS=-fpic -fPIC -Wall -Winline -O2 -fomit-frame-pointer -fno-strength-reduce $(BIGFILES)
CFLAGS=-fpic -fPIC -Wall -Winline -O -g
OBJS= blocksort.o \
huffman.o \
@ -20,13 +20,13 @@ OBJS= blocksort.o \
bzlib.o
all: $(OBJS)
$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.2 $(OBJS)
$(CC) $(CFLAGS) -o bzip2-shared bzip2.c libbz2.so.1.0.2
$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.3 $(OBJS)
$(CC) $(CFLAGS) -o bzip2-shared bzip2.c libbz2.so.1.0.3
rm -f libbz2.so.1.0
ln -s libbz2.so.1.0.2 libbz2.so.1.0
ln -s libbz2.so.1.0.3 libbz2.so.1.0
clean:
rm -f $(OBJS) bzip2.o libbz2.so.1.0.2 libbz2.so.1.0 bzip2-shared
rm -f $(OBJS) bzip2.o libbz2.so.1.0.3 libbz2.so.1.0 bzip2-shared
blocksort.o: blocksort.c
$(CC) $(CFLAGS) -c blocksort.c

38
README
View File

@ -1,15 +1,15 @@
This is the README for bzip2, a block-sorting file compressor, version
1.0.2. This version is fully compatible with the previous public
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0 and 1.0.1.
1.0.3. This version is fully compatible with the previous public
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1 and 1.0.2.
bzip2-1.0.2 is distributed under a BSD-style license. For details,
bzip2-1.0.3 is distributed under a BSD-style license. For details,
see the file LICENSE.
Complete documentation is available in Postscript form (manual.ps),
PDF (manual.pdf, amazingly enough) or html (manual_toc.html). A
plain-text version of the manual page is available as bzip2.txt.
A statement about Y2K issues is now included in the file Y2K_INFO.
PDF (manual.pdf) or html (manual.html). A plain-text version of the
manual page is available as bzip2.txt. A statement about Y2K issues
is now included in the file Y2K_INFO.
HOW TO BUILD -- UNIX
@ -78,8 +78,7 @@ importance. To validate bzip2, I used a modified version of Mark
Nelson's churn program. Churn is an automated test driver which
recursively traverses a directory structure, using bzip2 to compress
and then decompress each file it encounters, and checking that the
decompressed data is the same as the original. There are more details
in Section 4 of the user guide.
decompressed data is the same as the original.
@ -119,9 +118,9 @@ DISCLAIMER:
PATENTS:
To the best of my knowledge, bzip2 does not use any patented
algorithms. However, I do not have the resources available to
carry out a full patent search. Therefore I cannot give any
guarantee of the above statement.
algorithms. However, I do not have the resources to carry out
a patent search. Therefore I cannot give any guarantee of the
above statement.
End of legalities.
@ -153,22 +152,26 @@ WHAT'S NEW IN 1.0.2 ?
See the CHANGES file.
WHAT'S NEW IN 1.0.3 ?
See the CHANGES file.
I hope you find bzip2 useful. Feel free to contact me at
jseward@acm.org
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 and 1.0.1,
and the changes in bzip2 are largely a result of this feedback.
bzip-0.21, and bzip2 versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1 and
1.0.2, and the changes in bzip2 are largely a result of this feedback.
I thank you for your comments.
At least for the time being, bzip2's "home" is (or can be reached via)
http://sources.redhat.com/bzip2.
http://www.bzip.org
Julian Seward
jseward@acm.org
jseward@bzip.org
Cambridge, UK (and what a great town this is!)
Cambridge, UK.
18 July 1996 (version 0.15)
25 August 1996 (version 0.21)
@ -179,3 +182,4 @@ Cambridge, UK (and what a great town this is!)
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)

103
README.COMPILATION.PROBLEMS
View File

@ -1,11 +1,10 @@
bzip2-1.0 should compile without problems on the vast majority of
bzip2-1.0.3 should compile without problems on the vast majority of
platforms. Using the supplied Makefile, I've built and tested it
myself for x86-linux, sparc-solaris, alpha-linux, x86-cygwin32 and
alpha-tru64unix. 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 alpha-tru64unix and x86-cygwin32 (on Windows
2000).
myself for x86-linux and x86_64-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 alpha-tru64unix and
x86-cygwin32 (on Windows 2000).
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,
@ -22,7 +21,7 @@ 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://www.sas.com/standard/large.file/
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
@ -38,93 +37,3 @@ 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.
Known problems as of 1.0pre8:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
* HP/UX 10.20 and 11.00, using gcc (2.7.2.3 and 2.95.2): A large
number of warnings appear, including the following:
/usr/include/sys/resource.h: In function `getrlimit':
/usr/include/sys/resource.h:168:
warning: implicit declaration of function `__getrlimit64'
/usr/include/sys/resource.h: In function `setrlimit':
/usr/include/sys/resource.h:170:
warning: implicit declaration of function `__setrlimit64'
This would appear to be a problem with large file support, header
files and gcc. gcc may or may not give up at this point. If it
fails, you might be able to improve matters by adding
-D__STDC_EXT__=1
to the BIGFILES variable in the Makefile (ie, change its definition
to
BIGFILES=-D_FILE_OFFSET_BITS=64 -D__STDC_EXT__=1
Even if gcc does produce a binary which appears to work (ie passes
its self-tests), you might want to test it to see if it works properly
on large files.
* HP/UX 10.20 and 11.00, using HP's cc compiler.
No specific problems for this combination, except that you'll need to
specify the -Ae flag, and zap the gcc-specific stuff
-Wall -Winline -O2 -fomit-frame-pointer -fno-strength-reduce.
You should retain -D_FILE_OFFSET_BITS=64 in order to get large
file support -- which is reported to work ok for this HP/UX + cc
combination.
* SunOS 4.1.X.
Amazingly, there are still people out there using this venerable old
banger. I shouldn't be too rude -- I started life on SunOS, and
it was a pretty darn good OS, way back then. Anyway:
SunOS doesn't seem to have strerror(), so you'll have to use
perror(), perhaps by doing adding this (warning: UNTESTED CODE):
char* strerror ( int errnum )
{
if (errnum < 0 || errnum >= sys_nerr)
return "Unknown error";
else
return sys_errlist[errnum];
}
Or you could comment out the relevant calls to strerror; they're
not mission-critical. Or you could upgrade to Solaris. Ha ha ha!
(what?? you think I've got Bad Attitude?)
* Making a shared library on Solaris. (Not really a compilation
problem, but many people ask ...)
Firstly, if you have Solaris 8, either you have libbz2.so already
on your system, or you can install it from the Solaris CD.
Secondly, be aware that there are potential naming conflicts
between the .so file supplied with Solaris 8, and the .so file
which Makefile-libbz2_so will make. Makefile-libbz2_so creates
a .so which has the names which I intend to be "official" as
of version 1.0.0 and onwards. Unfortunately, the .so in
Solaris 8 appeared before I decided on the final names, so
the two libraries are incompatible. We have since communicated
and I hope that the problems will have been solved in the next
version of Solaris, whenever that might appear.
All that said: you might be able to get somewhere
by finding the line in Makefile-libbz2_so which says
$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.2 $(OBJS)
and replacing with
$(CC) -G -shared -o libbz2.so.1.0.2 -h libbz2.so.1.0 $(OBJS)
If gcc objects to the combination -fpic -fPIC, get rid of
the second one, leaving just "-fpic".
That's the end of the currently known compilation problems.

31
README.XML.STUFF Normal file
View File

@ -0,0 +1,31 @@
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.

4
blocksort.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:

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>

257
bz-fo.xsl Normal file
View File

@ -0,0 +1,257 @@
<?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>
</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>

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;
}

17
bzip2.1
View File

@ -1,7 +1,7 @@
.PU
.TH bzip2 1
.SH NAME
bzip2, bunzip2 \- a block-sorting file compressor, v1.0.2
bzip2, bunzip2 \- a block-sorting file compressor, v1.0.3
.br
bzcat \- decompresses files to stdout
.br
@ -405,19 +405,19 @@ I/O error messages are not as helpful as they could be.
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 1.0.2 of
This manual page pertains to version 1.0.3 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 and 1.0.1, but with the following
0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1 and 1.0.2, 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 this one, 1.0.2, used 32-bit integers to represent
bit positions in compressed files, so it could not handle compressed
files more than 512 megabytes long. Version 1.0.2 and above uses
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
@ -427,9 +427,9 @@ with MaybeUInt64 set to be an unsigned 64-bit integer.
.SH AUTHOR
Julian Seward, jseward@acm.org.
Julian Seward, jsewardbzip.org.
http://sources.redhat.com/bzip2
http://www.bzip.org
The ideas embodied in
.I bzip2
@ -447,6 +447,7 @@ 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

247
bzip2.1.preformatted
View File

@ -3,43 +3,43 @@ bzip2(1) bzip2(1)
NNAAMMEE
bzip2, bunzip2 - a block-sorting file compressor, v1.0.2
bzcat - decompresses files to stdout
bzip2recover - recovers data from damaged bzip2 files
bzip2, bunzip2 − a block‐sorting file compressor, v1.0.3
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 _._._. ]
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
_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
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
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
_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
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
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.
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.
files. If you want this to happen, specify the −f flag.
If no file names are specified, _b_z_i_p_2 compresses from
standard input to standard output. In this case, _b_z_i_p_2
@ -47,7 +47,7 @@ DDEESSCCRRIIPPTTIIOONN
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.
_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
@ -64,26 +64,26 @@ DDEESSCCRRIIPPTTIIOONN
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
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
_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
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
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
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
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
_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
@ -99,15 +99,15 @@ DDEESSCCRRIIPPTTIIOONN
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
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
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
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.
@ -118,41 +118,41 @@ DDEESSCCRRIIPPTTIIOONN
OOPPTTIIOONNSS
--cc ----ssttddoouutt
−−cc ‐‐‐‐ssttddoouutt
Compress or decompress to standard output.
--dd ----ddeeccoommpprreessss
−−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,
−−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
−−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
−−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.
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
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
−−kk ‐‐‐‐kkeeeepp
Keep (don’t delete) input files during compression
or decompression.
--ss ----ssmmaallll
−−ss ‐‐‐‐ssmmaallll
Reduce memory usage, for compression, decompression
and testing. Files are decompressed and tested
using a modified algorithm which only requires 2.5
@ -160,46 +160,46 @@ OOPPTTIIOONNSS
decompressed in 2300k of memory, albeit at about
half the normal speed.
During compression, -s selects a block size of
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
megabytes or less), use −s for everything. See
MEMORY MANAGEMENT below.
--qq ----qquuiieett
Suppress non-essential warning messages. Messages
−−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
−−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
−−LL ‐‐‐‐lliicceennssee ‐‐VV ‐‐‐‐vveerrssiioonn
Display the software version, license terms and
conditions.
--11 ((oorr ----ffaasstt)) ttoo --99 ((oorr ----bbeesstt))
−−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
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
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
−−‐‐ 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.
example: bzip2 −‐ −myfilename.
----rreeppeettiittiivvee--ffaasstt ----rreeppeettiittiivvee--bbeesstt
−−‐‐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
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.
@ -209,13 +209,13 @@ 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
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
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
@ -238,21 +238,21 @@ MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
_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
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.
only where necessary. The relevant flag is ‐s.
In general, try and use the largest block size memory con­
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
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
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
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 +
@ -260,59 +260,59 @@ MMEEMMOORRYY MMAANNAAGGEEMMEENNTT
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
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
block sizes for larger files, since the Corpus is domi­
nated by smaller files.
Compress Decompress Decompress Corpus
Flag usage usage -s usage Size
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
‐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
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
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
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
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
_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.
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
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.
@ -324,21 +324,21 @@ PPEERRFFOORRMMAANNCCEE NNOOTTEESS
..." (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
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
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
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
large performance improvements. I imagine _b_z_i_p_2 will per­
form best on machines with very large caches.
@ -348,50 +348,51 @@ CCAAVVEEAATTSS
but the details of what the problem is sometimes seem
rather misleading.
This manual page pertains to version 1.0.2 of _b_z_i_p_2_. Com­
This manual page pertains to version 1.0.3 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 and 1.0.1,
but with the following exception: 0.9.0 and above can cor­
rectly decompress multiple concatenated compressed files.
0.1pl2 cannot do this; it will stop after decompressing
just the first file in the stream.
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1 and
1.0.2, 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 decom­
pressing just the first file in the stream.
_b_z_i_p_2_r_e_c_o_v_e_r versions prior to this one, 1.0.2, used
32-bit integers to represent bit positions in compressed
files, so it could not handle compressed files more than
512 megabytes long. Version 1.0.2 and above uses 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.
_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, jseward@acm.org.
Julian Seward, jsewardbzip.org.
http://sources.redhat.com/bzip2
http://www.bzip.org
The ideas embodied in _b_z_i_p_2 are due to (at least) the fol­
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
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
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. 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.
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.

20
bzip2.c
View File

@ -7,7 +7,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -41,7 +41,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -525,6 +525,7 @@ Bool uncompressStream ( FILE *zStream, FILE *stream )
UChar obuf[5000];
UChar unused[BZ_MAX_UNUSED];
Int32 nUnused;
void* unusedTmpV;
UChar* unusedTmp;
nUnused = 0;
@ -554,9 +555,10 @@ Bool uncompressStream ( FILE *zStream, FILE *stream )
}
if (bzerr != BZ_STREAM_END) goto errhandler;
BZ2_bzReadGetUnused ( &bzerr, bzf, (void**)(&unusedTmp), &nUnused );
BZ2_bzReadGetUnused ( &bzerr, bzf, &unusedTmpV, &nUnused );
if (bzerr != BZ_OK) panic ( "decompress:bzReadGetUnused" );
unusedTmp = (UChar*)unusedTmpV;
for (i = 0; i < nUnused; i++) unused[i] = unusedTmp[i];
BZ2_bzReadClose ( &bzerr, bzf );
@ -639,6 +641,7 @@ Bool testStream ( FILE *zStream )
UChar obuf[5000];
UChar unused[BZ_MAX_UNUSED];
Int32 nUnused;
void* unusedTmpV;
UChar* unusedTmp;
nUnused = 0;
@ -662,9 +665,10 @@ Bool testStream ( FILE *zStream )
}
if (bzerr != BZ_STREAM_END) goto errhandler;
BZ2_bzReadGetUnused ( &bzerr, bzf, (void**)(&unusedTmp), &nUnused );
BZ2_bzReadGetUnused ( &bzerr, bzf, &unusedTmpV, &nUnused );
if (bzerr != BZ_OK) panic ( "test:bzReadGetUnused" );
unusedTmp = (UChar*)unusedTmpV;
for (i = 0; i < nUnused; i++) unused[i] = unusedTmp[i];
BZ2_bzReadClose ( &bzerr, bzf );
@ -828,7 +832,7 @@ void panic ( Char* s )
"\n%s: PANIC -- internal consistency error:\n"
"\t%s\n"
"\tThis is a BUG. Please report it to me at:\n"
"\tjseward@acm.org\n",
"\tjseward@bzip.org\n",
progName, s );
showFileNames();
cleanUpAndFail( 3 );
@ -908,7 +912,7 @@ void mySIGSEGVorSIGBUScatcher ( IntNative n )
" The user's manual, Section 4.3, has more info on (1) and (2).\n"
" \n"
" If you suspect this is a bug in bzip2, or are unsure about (1)\n"
" or (2), feel free to report it to me at: jseward@acm.org.\n"
" or (2), feel free to report it to me at: jseward@bzip.org.\n"
" Section 4.3 of the user's manual describes the info a useful\n"
" bug report should have. If the manual is available on your\n"
" system, please try and read it before mailing me. If you don't\n"
@ -931,7 +935,7 @@ void mySIGSEGVorSIGBUScatcher ( IntNative n )
" The user's manual, Section 4.3, has more info on (2) and (3).\n"
" \n"
" If you suspect this is a bug in bzip2, or are unsure about (2)\n"
" or (3), feel free to report it to me at: jseward@acm.org.\n"
" or (3), feel free to report it to me at: jseward@bzip.org.\n"
" Section 4.3 of the user's manual describes the info a useful\n"
" bug report should have. If the manual is available on your\n"
" system, please try and read it before mailing me. If you don't\n"
@ -1674,7 +1678,7 @@ void license ( void )
"bzip2, a block-sorting file compressor. "
"Version %s.\n"
" \n"
" Copyright (C) 1996-2002 by Julian Seward.\n"
" Copyright (C) 1996-2005 by Julian Seward.\n"
" \n"
" This program is free software; you can redistribute it and/or modify\n"
" it under the terms set out in the LICENSE file, which is included\n"

117
bzip2.txt
View File

@ -1,6 +1,6 @@
NAME
bzip2, bunzip2 - a block-sorting file compressor, v1.0.2
bzip2, bunzip2 - a block-sorting file compressor, v1.0.3
bzcat - decompresses files to stdout
bzip2recover - recovers data from damaged bzip2 files
@ -17,20 +17,20 @@ DESCRIPTION
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
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
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
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
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.
@ -61,23 +61,23 @@ DESCRIPTION
guess the name of the original file, and uses the original
name with .out appended.
As with compression, supplying no filenames causes decom­
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
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
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
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
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
@ -98,7 +98,7 @@ DESCRIPTION
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
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
@ -171,7 +171,7 @@ OPTIONS
-v --verbose
Verbose mode -- show the compression ratio for each
file processed. Further -v's increase the ver­
file processed. Further -v's increase the ver-
bosity level, spewing out lots of information which
is primarily of interest for diagnostic purposes.
@ -184,19 +184,19 @@ OPTIONS
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
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
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
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.
@ -207,7 +207,7 @@ MEMORY MANAGEMENT
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
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
@ -235,13 +235,13 @@ MEMORY MANAGEMENT
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
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
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
achieved. Compression and decompression speed are virtu-
ally unaffected by block size.
Another significant point applies to files which fit in a
@ -257,11 +257,11 @@ MEMORY MANAGEMENT
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
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
block sizes for larger files, since the Corpus is domi-
nated by smaller files.
Compress Decompress Decompress Corpus
@ -280,7 +280,7 @@ MEMORY MANAGEMENT
RECOVERING DATA FROM DAMAGED FILES
bzip2 compresses files in blocks, usually 900kbytes long.
Each block is handled independently. If a media or trans­
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.
@ -297,19 +297,19 @@ RECOVERING DATA FROM DAMAGED FILES
the integrity of the resulting files, and decompress those
which are undamaged.
bzip2recover takes a single argument, the name of the dam­
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
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
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.
@ -323,19 +323,19 @@ PERFORMANCE NOTES
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
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
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
large performance improvements. I imagine bzip2 will per-
form best on machines with very large caches.
@ -345,46 +345,47 @@ CAVEATS
but the details of what the problem is sometimes seem
rather misleading.
This manual page pertains to version 1.0.2 of bzip2. Com­
This manual page pertains to version 1.0.3 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 and 1.0.1,
but with the following exception: 0.9.0 and above can cor­
rectly decompress multiple concatenated compressed files.
0.1pl2 cannot do this; it will stop after decompressing
just the first file in the stream.
releases, versions 0.1pl2, 0.9.0, 0.9.5, 1.0.0, 1.0.1 and
1.0.2, 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 decom-
pressing just the first file in the stream.
bzip2recover versions prior to this one, 1.0.2, used
32-bit integers to represent bit positions in compressed
files, so it could not handle compressed files more than
512 megabytes long. Version 1.0.2 and above uses 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.
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, jseward@acm.org.
Julian Seward, jsewardbzip.org.
http://sources.redhat.com/bzip2
http://www.bzip.org
The ideas embodied in bzip2 are due to (at least) the fol­
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
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
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
for faster sorting algorithms, so as to speed up compres-
sion. Bela Lubkin encouraged me to improve the worst-case
compression performance. 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.
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.

12
bzip2recover.c
View File

@ -7,9 +7,9 @@
/*--
This program is bzip2recover, a program to attempt data
salvage from damaged files created by the accompanying
bzip2-1.0 program.
bzip2-1.0.3 program.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -43,8 +43,8 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
bzip2/libbzip2 version 1.0 of 21 March 2000
jseward@bzip.org
bzip2/libbzip2 version 1.0.3 of 15 February 2005
--*/
/*--
@ -345,7 +345,7 @@ Int32 main ( Int32 argc, Char** argv )
inFileName[0] = outFileName[0] = 0;
fprintf ( stderr,
"bzip2recover 1.0.2: extracts blocks from damaged .bz2 files.\n" );
"bzip2recover 1.0.3: extracts blocks from damaged .bz2 files.\n" );
if (argc != 2) {
fprintf ( stderr, "%s: usage is `%s damaged_file_name'.\n",
@ -374,7 +374,7 @@ Int32 main ( Int32 argc, Char** argv )
if (strlen(argv[1]) >= BZ_MAX_FILENAME-20) {
fprintf ( stderr,
"%s: supplied filename is suspiciously (>= %d chars) long. Bye!\n",
progName, strlen(argv[1]) );
progName, (int)strlen(argv[1]) );
exit(1);
}

55
bzlib.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -88,12 +88,12 @@ void BZ2_bz__AssertH__fail ( int errcode )
fprintf(stderr,
"\n\nbzip2/libbzip2: internal error number %d.\n"
"This is a bug in bzip2/libbzip2, %s.\n"
"Please report it to me at: jseward@acm.org. If this happened\n"
"Please report it to me at: jseward@bzip.org. If this happened\n"
"when you were using some program which uses libbzip2 as a\n"
"component, you should also report this bug to the author(s)\n"
"of that program. Please make an effort to report this bug;\n"
"timely and accurate bug reports eventually lead to higher\n"
"quality software. Thanks. Julian Seward, 30 December 2001.\n\n",
"quality software. Thanks. Julian Seward, 15 February 2005.\n\n",
errcode,
BZ2_bzlibVersion()
);
@ -574,8 +574,11 @@ int BZ_API(BZ2_bzDecompressInit)
/*---------------------------------------------------*/
/* Return True iff data corruption is discovered.
Returns False if there is no problem.
*/
static
void unRLE_obuf_to_output_FAST ( DState* s )
Bool unRLE_obuf_to_output_FAST ( DState* s )
{
UChar k1;
@ -584,7 +587,7 @@ void unRLE_obuf_to_output_FAST ( DState* s )
while (True) {
/* try to finish existing run */
while (True) {
if (s->strm->avail_out == 0) return;
if (s->strm->avail_out == 0) return False;
if (s->state_out_len == 0) break;
*( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
@ -596,8 +599,11 @@ void unRLE_obuf_to_output_FAST ( DState* s )
}
/* can a new run be started? */
if (s->nblock_used == s->save_nblock+1) return;
if (s->nblock_used == s->save_nblock+1) return False;
/* Only caused by corrupt data stream? */
if (s->nblock_used > s->save_nblock+1)
return True;
s->state_out_len = 1;
s->state_out_ch = s->k0;
@ -667,6 +673,10 @@ void unRLE_obuf_to_output_FAST ( DState* s )
cs_avail_out--;
}
}
/* Only caused by corrupt data stream? */
if (c_nblock_used > s_save_nblockPP)
return True;
/* can a new run be started? */
if (c_nblock_used == s_save_nblockPP) {
c_state_out_len = 0; goto return_notr;
@ -712,6 +722,7 @@ void unRLE_obuf_to_output_FAST ( DState* s )
s->strm->avail_out = cs_avail_out;
/* end save */
}
return False;
}
@ -732,8 +743,11 @@ __inline__ Int32 BZ2_indexIntoF ( Int32 indx, Int32 *cftab )
/*---------------------------------------------------*/
/* Return True iff data corruption is discovered.
Returns False if there is no problem.
*/
static
void unRLE_obuf_to_output_SMALL ( DState* s )
Bool unRLE_obuf_to_output_SMALL ( DState* s )
{
UChar k1;
@ -742,7 +756,7 @@ void unRLE_obuf_to_output_SMALL ( DState* s )
while (True) {
/* try to finish existing run */
while (True) {
if (s->strm->avail_out == 0) return;
if (s->strm->avail_out == 0) return False;
if (s->state_out_len == 0) break;
*( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
@ -754,8 +768,11 @@ void unRLE_obuf_to_output_SMALL ( DState* s )
}
/* can a new run be started? */
if (s->nblock_used == s->save_nblock+1) return;
if (s->nblock_used == s->save_nblock+1) return False;
/* Only caused by corrupt data stream? */
if (s->nblock_used > s->save_nblock+1)
return True;
s->state_out_len = 1;
s->state_out_ch = s->k0;
@ -788,7 +805,7 @@ void unRLE_obuf_to_output_SMALL ( DState* s )
while (True) {
/* try to finish existing run */
while (True) {
if (s->strm->avail_out == 0) return;
if (s->strm->avail_out == 0) return False;
if (s->state_out_len == 0) break;
*( (UChar*)(s->strm->next_out) ) = s->state_out_ch;
BZ_UPDATE_CRC ( s->calculatedBlockCRC, s->state_out_ch );
@ -800,7 +817,11 @@ void unRLE_obuf_to_output_SMALL ( DState* s )
}
/* can a new run be started? */
if (s->nblock_used == s->save_nblock+1) return;
if (s->nblock_used == s->save_nblock+1) return False;
/* Only caused by corrupt data stream? */
if (s->nblock_used > s->save_nblock+1)
return True;
s->state_out_len = 1;
s->state_out_ch = s->k0;
@ -830,6 +851,7 @@ void unRLE_obuf_to_output_SMALL ( DState* s )
/*---------------------------------------------------*/
int BZ_API(BZ2_bzDecompress) ( bz_stream *strm )
{
Bool corrupt;
DState* s;
if (strm == NULL) return BZ_PARAM_ERROR;
s = strm->state;
@ -840,12 +862,13 @@ int BZ_API(BZ2_bzDecompress) ( bz_stream *strm )
if (s->state == BZ_X_IDLE) return BZ_SEQUENCE_ERROR;
if (s->state == BZ_X_OUTPUT) {
if (s->smallDecompress)
unRLE_obuf_to_output_SMALL ( s ); else
unRLE_obuf_to_output_FAST ( s );
corrupt = unRLE_obuf_to_output_SMALL ( s ); else
corrupt = unRLE_obuf_to_output_FAST ( s );
if (corrupt) return BZ_DATA_ERROR;
if (s->nblock_used == s->save_nblock+1 && s->state_out_len == 0) {
BZ_FINALISE_CRC ( s->calculatedBlockCRC );
if (s->verbosity >= 3)
VPrintf2 ( " {0x%x, 0x%x}", s->storedBlockCRC,
VPrintf2 ( " {0x%08x, 0x%08x}", s->storedBlockCRC,
s->calculatedBlockCRC );
if (s->verbosity >= 2) VPrintf0 ( "]" );
if (s->calculatedBlockCRC != s->storedBlockCRC)
@ -863,7 +886,7 @@ int BZ_API(BZ2_bzDecompress) ( bz_stream *strm )
Int32 r = BZ2_decompress ( s );
if (r == BZ_STREAM_END) {
if (s->verbosity >= 3)
VPrintf2 ( "\n combined CRCs: stored = 0x%x, computed = 0x%x",
VPrintf2 ( "\n combined CRCs: stored = 0x%08x, computed = 0x%08x",
s->storedCombinedCRC, s->calculatedCombinedCRC );
if (s->calculatedCombinedCRC != s->storedCombinedCRC)
return BZ_DATA_ERROR;

6
bzlib.h
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -110,8 +110,10 @@ typedef
#define BZ_EXPORT
#endif
#ifndef BZ_NO_STDIO
/* Need a definitition for FILE */
#include <stdio.h>
#endif
#ifdef _WIN32
# include <windows.h>

6
bzlib_private.h
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -76,7 +76,7 @@
/*-- General stuff. --*/
#define BZ_VERSION "1.0.2, 30-Dec-2001"
#define BZ_VERSION "1.0.3, 15-Feb-2005"
typedef char Char;
typedef unsigned char Bool;

16
compress.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -488,9 +488,11 @@ void sendMTFValues ( EState* s )
/*--
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, 20 );
alphaSize, 17 /*20*/ );
}
@ -527,7 +529,7 @@ void sendMTFValues ( EState* s )
if (s->len[t][i] > maxLen) maxLen = s->len[t][i];
if (s->len[t][i] < minLen) minLen = s->len[t][i];
}
AssertH ( !(maxLen > 20), 3004 );
AssertH ( !(maxLen > 17 /*20*/ ), 3004 );
AssertH ( !(minLen < 1), 3005 );
BZ2_hbAssignCodes ( &(s->code[t][0]), &(s->len[t][0]),
minLen, maxLen, alphaSize );
@ -651,8 +653,8 @@ void BZ2_compressBlock ( EState* s, Bool is_last_block )
if (s->blockNo > 1) s->numZ = 0;
if (s->verbosity >= 2)
VPrintf4( " block %d: crc = 0x%8x, "
"combined CRC = 0x%8x, size = %d\n",
VPrintf4( " block %d: crc = 0x%08x, "
"combined CRC = 0x%08x, size = %d\n",
s->blockNo, s->blockCRC, s->combinedCRC, s->nblock );
BZ2_blockSort ( s );
@ -703,7 +705,7 @@ void BZ2_compressBlock ( EState* s, Bool is_last_block )
bsPutUChar ( s, 0x50 ); bsPutUChar ( s, 0x90 );
bsPutUInt32 ( s, s->combinedCRC );
if (s->verbosity >= 2)
VPrintf1( " final combined CRC = 0x%x\n ", s->combinedCRC );
VPrintf1( " final combined CRC = 0x%08x\n ", s->combinedCRC );
bsFinishWrite ( s );
}
}

4
crctable.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:

20
decompress.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -524,17 +524,23 @@ Int32 BZ2_decompress ( DState* s )
if (s->origPtr < 0 || s->origPtr >= nblock)
RETURN(BZ_DATA_ERROR);
/*-- Set up cftab to facilitate generation of T^(-1) --*/
s->cftab[0] = 0;
for (i = 1; i <= 256; i++) s->cftab[i] = s->unzftab[i-1];
for (i = 1; i <= 256; i++) s->cftab[i] += s->cftab[i-1];
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);
}
}
s->state_out_len = 0;
s->state_out_ch = 0;
BZ_INITIALISE_CRC ( s->calculatedBlockCRC );
s->state = BZ_X_OUTPUT;
if (s->verbosity >= 2) VPrintf0 ( "rt+rld" );
/*-- Set up cftab to facilitate generation of T^(-1) --*/
s->cftab[0] = 0;
for (i = 1; i <= 256; i++) s->cftab[i] = s->unzftab[i-1];
for (i = 1; i <= 256; i++) s->cftab[i] += s->cftab[i-1];
if (s->smallDecompress) {
/*-- Make a copy of cftab, used in generation of T --*/

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 "1996-2005">
<!ENTITY bz-version "1.0.3">
<!ENTITY bz-date "15 February 2005">
<!ENTITY manual-title "bzip2 Manual">

53
format.pl Executable file
View File

@ -0,0 +1,53 @@
#!/usr/bin/perl -w
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;

23
huffman.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:
@ -162,7 +162,24 @@ void BZ2_hbMakeCodeLengths ( UChar *len,
if (! tooLong) break;
for (i = 1; i < alphaSize; i++) {
/* 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;

2243
manual.texi
View File

File diff suppressed because it is too large Load Diff

2966
manual.xml Normal file
View File

File diff suppressed because it is too large Load Diff

4
randtable.c
View File

@ -8,7 +8,7 @@
This file is a part of bzip2 and/or libbzip2, a program and
library for lossless, block-sorting data compression.
Copyright (C) 1996-2002 Julian R Seward. All rights reserved.
Copyright (C) 1996-2005 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
@ -42,7 +42,7 @@
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Julian Seward, Cambridge, UK.
jseward@acm.org
jseward@bzip.org
bzip2/libbzip2 version 1.0 of 21 March 2000
This program is based on (at least) the work of:

99
xmlproc.sh Executable file
View File

@ -0,0 +1,99 @@
#!/bin/bash
# see the README in this directory for usage etc.
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