[+] Initial commit

[+] Win32 patches
[+] liblzma build json
[+] .gitignore
[-] Non-public domain code

ABOUT-NLS

@@ -0,0 +1 @@
+<https://www.gnu.org/software/gettext/manual/html_node/Users.html>

AUTHORS

@@ -0,0 +1,39 @@
+
+Authors of XZ Utils
+===================
+
+    XZ Utils is developed and maintained by Lasse Collin
+    <lasse.collin@tukaani.org> and Jia Tan <jiat0218@gmail.com>.
+
+    Major parts of liblzma are based on code written by Igor Pavlov,
+    specifically the LZMA SDK <https://7-zip.org/sdk.html>. Without
+    this code, XZ Utils wouldn't exist.
+
+    The SHA-256 implementation in liblzma is based on the code found from
+    7-Zip <https://7-zip.org/>, which has a modified version of the SHA-256
+    code found from Crypto++ <https://www.cryptopp.com/>. The SHA-256 code
+    in Crypto++ was written by Kevin Springle and Wei Dai.
+
+    Some scripts have been adapted from gzip. The original versions
+    were written by Jean-loup Gailly, Charles Levert, and Paul Eggert.
+    Andrew Dudman helped adapting the scripts and their man pages for
+    XZ Utils.
+
+    The initial version of the threaded .xz decompressor was written
+    by Sebastian Andrzej Siewior.
+
+    The initial version of the .lz (lzip) decoder was written
+    by Michał Górny.
+
+    CLMUL-accelerated CRC code was contributed by Ilya Kurdyukov.
+
+    Other authors:
+      - Jonathan Nieder
+      - Joachim Henke
+
+    The GNU Autotools-based build system contains files from many authors,
+    which I'm not trying to list here.
+
+    Several people have contributed fixes or reported bugs. Most of them
+    are mentioned in the file THANKS.
+

COPYING

@@ -0,0 +1,49 @@
+
+XZ Utils Licensing
+==================
+
+    Different licenses apply to different files in this package. Here
+    is a rough summary of which licenses apply to which parts of this
+    package (but check the individual files to be sure!):
+
+      - liblzma is in the public domain.
+
+
+      - All the documentation in the doc directory and most of the
+        XZ Utils specific documentation files in other directories
+        are in the public domain.
+
+      - Translated messages are in the public domain.
+
+      - Test files and test code in the tests directory, and debugging
+        utilities in the debug directory are in the public domain.
+
+      - The extra directory may contain public domain files, and files
+        that are under various free software licenses.
+
+    You can do whatever you want with the files that have been put into
+    the public domain. If you find public domain legally problematic,
+    take the previous sentence as a license grant. If you still find
+    the lack of copyright legally problematic, you have too many
+    lawyers.
+
+    As usual, this software is provided "as is", without any warranty.
+
+    If you copy significant amounts of public domain code from XZ Utils
+    into your project, acknowledging this somewhere in your software is
+    polite (especially if it is proprietary, non-free software), but
+    naturally it is not legally required. Here is an example of a good
+    notice to put into "about box" or into documentation:
+
+        This software includes code from XZ Utils <https://tukaani.org/xz/>.
+
+
+    Note that the toolchain (compiler, linker etc.) may add some code
+    pieces that are copyrighted. Thus, it is possible that e.g. liblzma
+    binary wouldn't actually be in the public domain in its entirety
+    even though it contains no copyrighted code from the XZ Utils source
+    package.
+
+    If you have questions, don't hesitate to ask the author(s) for more
+    information.
+

PACKAGERS

@@ -0,0 +1,233 @@
+
+Information to packagers of XZ Utils
+====================================
+
+    0. Preface
+    1. Package naming
+    2. Package description
+    3. License
+    4. configure options
+    5. Additional documentation
+    6. Extra files
+    7. Installing XZ Utils and LZMA Utils in parallel
+    8. Example
+
+
+0. Preface
+----------
+
+    This document is meant for people who create and maintain XZ Utils
+    packages for operating system distributions. The focus is on GNU/Linux
+    systems, but most things apply to other systems too.
+
+    While the standard "configure && make DESTDIR=$PKG install" should
+    give a pretty good package, there are some details which packagers
+    may want to tweak.
+
+    Packagers should also read the INSTALL file.
+
+
+1. Package naming
+-----------------
+
+    The preferred name for the XZ Utils package is "xz", because that's
+    the name of the upstream tarball. Naturally you may have good reasons
+    to use some other name; I won't get angry about it. ;-) It's just nice
+    to be able to point people to the correct package name without asking
+    what distro they have.
+
+    If your distro policy is to split things into small pieces, here is
+    one suggestion:
+
+        xz              xz, xzdec, scripts (xzdiff, xzgrep, etc.), docs
+        xz-lzma         lzma, unlzma, lzcat, lzgrep etc. symlinks and
+                        lzmadec binary for compatibility with LZMA Utils
+        liblzma         liblzma.so.*
+        liblzma-devel   liblzma.so, liblzma.a, API headers
+
+
+2. Package description
+----------------------
+
+    Here is a suggestion which you may use as the package description.
+    If you can use only one-line description, pick only the first line.
+    Naturally, feel free to use some other description if you find it
+    better, and maybe send it to me too.
+
+        Library and command line tools for XZ and LZMA compressed files
+
+        XZ Utils provide a general purpose data compression library
+        and command line tools. The native file format is the .xz
+        format, but also the legacy .lzma format is supported. The .xz
+        format supports multiple compression algorithms, of which LZMA2
+        is currently the primary algorithm. With typical files, XZ Utils
+        create about 30 % smaller files than gzip.
+
+    If you are splitting XZ Utils into multiple packages, here are some
+    suggestions for package descriptions:
+
+    xz:
+
+        Command line tools for XZ and LZMA compressed files
+
+        This package includes the xz compression tool and other command
+        line tools from XZ Utils. xz has command line syntax similar to
+        that of gzip. The native file format is the .xz format, but also
+        the legacy .lzma format is supported. The .xz format supports
+        multiple compression algorithms, of which LZMA2 is currently the
+        primary algorithm. With typical files, XZ Utils create about 30 %
+        smaller files than gzip.
+
+        Note that this package doesn't include the files needed for
+        LZMA Utils 4.32.x compatibility. Install also the xz-lzma
+        package to make XZ Utils emulate LZMA Utils 4.32.x.
+
+    xz-lzma:
+
+        LZMA Utils emulation with XZ Utils
+
+        This package includes executables and symlinks to make
+        XZ Utils emulate lzma, unlzma, lzcat, and other command
+        line tools found from the legacy LZMA Utils 4.32.x package.
+
+    liblzma:
+
+        Library for XZ and LZMA compressed files
+
+        liblzma is a general purpose data compression library with
+        an API similar to that of zlib. liblzma supports multiple
+        algorithms, of which LZMA2 is currently the primary algorithm.
+        The native file format is .xz, but also the legacy .lzma
+        format and raw streams (no headers at all) are supported.
+
+        This package includes the shared library.
+
+    liblzma-devel:
+
+        Library for XZ and LZMA compressed files
+
+        This package includes the API headers, static library, and
+        other development files related to liblzma.
+
+
+3. License
+----------
+
+    If the package manager supports a license field, you probably should
+    put GPLv2+ there (GNU GPL v2 or later). The interesting parts of
+    XZ Utils are in the public domain, but some less important files
+    ending up into the binary package are under GPLv2+. So it is simplest
+    to just say GPLv2+ if you cannot specify "public domain and GPLv2+".
+
+    If you split XZ Utils into multiple packages as described earlier
+    in this file, liblzma and liblzma-dev packages will contain only
+    public domain code (from XZ Utils at least; compiler or linker may
+    add some third-party code, which may be copyrighted).
+
+
+4. configure options
+--------------------
+
+    Unless you are building a package for a distribution that is meant
+    only for embedded systems, don't use the following configure options:
+
+        --enable-debug
+        --enable-encoders (*)
+        --enable-decoders
+        --enable-match-finders
+        --enable-checks
+        --enable-small (*)
+        --disable-threads (*)
+        --disable-microlzma (*)
+        --disable-lzip-decoder (*)
+
+    (*) These are OK when building xzdec and lzmadec as described
+        in INSTALL.
+
+    xzdec and lzmadec don't provide any functionality that isn't already
+    available in the xz tool. Shipping xzdec and lzmadec without size
+    optimization and statically-linked liblzma isn't very useful. Doing
+    that would give users the xzdec man page, which may make it easier
+    for people to find out that such tools exists, but the executables
+    wouldn't have any advantage over the full-featured xz.
+
+
+5. Additional documentation
+---------------------------
+
+    "make install" copies some additional documentation to $docdir
+    (--docdir in configure). There is a copy of the GNU GPL v2, which
+    can be replaced with a symlink if your distro ships with shared
+    copies of the common license texts.
+
+    liblzma API is currently only documented using Doxygen tags in the
+    API headers. It hasn't been tested much how good results Doxygen
+    is able to make from the tags (e.g. Doxyfile might need tweaking,
+    the tagging may need to be improved etc.), so it might be simpler
+    to just let people read docs directly from the .h files for now,
+    and also save quite a bit in package size at the same time.
+
+
+6. Extra files
+--------------
+
+    The "extra" directory contains some small extra tools or other files.
+    The exact set of extra files can vary between XZ Utils releases. The
+    extra files have only limited use or they are too dangerous to be
+    put directly to $bindir (7z2lzma.sh is a good example, since it can
+    silently create corrupt output if certain conditions are not met).
+
+    If you feel like it, you may copy the extra directory under the doc
+    directory (e.g. /usr/share/doc/xz/extra). Maybe some people will find
+    them useful. However, most people needing these tools probably are
+    able to find them from the source package too.
+
+    The "debug" directory contains some tools that are useful only when
+    hacking on XZ Utils. Don't package these tools.
+
+
+7. Installing XZ Utils and LZMA Utils in parallel
+-------------------------------------------------
+
+    XZ Utils and LZMA Utils 4.32.x can be installed in parallel by
+    omitting the compatibility symlinks (lzma, unlzma, lzcat, lzgrep etc.)
+    from the XZ Utils package. It's probably a good idea to still package
+    the symlinks into a separate package so that users may choose if they
+    want to use XZ Utils or LZMA Utils for handling .lzma files.
+
+
+8. Example
+----------
+
+    Here is an example for i686 GNU/Linux that
+      - links xz and lzmainfo against shared liblzma;
+      - links size-optimized xzdec and lzmadec against static liblzma
+        while avoiding libpthread dependency;
+      - includes only shared liblzma in the final package; and
+      - copies also the "extra" directory to the package.
+
+    PKG=/tmp/xz-pkg
+    tar xf xz-x.y.z.tar.gz
+    cd xz-x.y.z
+    ./configure \
+            --prefix=/usr \
+            --disable-static \
+            --disable-xzdec \
+            --disable-lzmadec \
+            CFLAGS='-march=i686 -mtune=generic -O2'
+    make
+    make DESTDIR=$PKG install-strip
+    make clean
+    ./configure \
+            --prefix=/usr \
+            --disable-shared \
+            --disable-nls \
+            --disable-encoders \
+            --enable-small \
+            --disable-threads \
+            CFLAGS='-march=i686 -mtune=generic -Os'
+    make -C src/liblzma
+    make -C src/xzdec
+    make -C src/xzdec DESTDIR=$PKG install-strip
+    cp -a extra $PKG/usr/share/doc/xz
+

README

@@ -0,0 +1,303 @@
+
+XZ Utils
+========
+
+    0. Overview
+    1. Documentation
+       1.1. Overall documentation
+       1.2. Documentation for command-line tools
+       1.3. Documentation for liblzma
+    2. Version numbering
+    3. Reporting bugs
+    4. Translations
+    5. Other implementations of the .xz format
+    6. Contact information
+
+
+0. Overview
+-----------
+
+    XZ Utils provide a general-purpose data-compression library plus
+    command-line tools. The native file format is the .xz format, but
+    also the legacy .lzma format is supported. The .xz format supports
+    multiple compression algorithms, which are called "filters" in the
+    context of XZ Utils. The primary filter is currently LZMA2. With
+    typical files, XZ Utils create about 30 % smaller files than gzip.
+
+    To ease adapting support for the .xz format into existing applications
+    and scripts, the API of liblzma is somewhat similar to the API of the
+    popular zlib library. For the same reason, the command-line tool xz
+    has a command-line syntax similar to that of gzip.
+
+    When aiming for the highest compression ratio, the LZMA2 encoder uses
+    a lot of CPU time and may use, depending on the settings, even
+    hundreds of megabytes of RAM. However, in fast modes, the LZMA2 encoder
+    competes with bzip2 in compression speed, RAM usage, and compression
+    ratio.
+
+    LZMA2 is reasonably fast to decompress. It is a little slower than
+    gzip, but a lot faster than bzip2. Being fast to decompress means
+    that the .xz format is especially nice when the same file will be
+    decompressed very many times (usually on different computers), which
+    is the case e.g. when distributing software packages. In such
+    situations, it's not too bad if the compression takes some time,
+    since that needs to be done only once to benefit many people.
+
+    With some file types, combining (or "chaining") LZMA2 with an
+    additional filter can improve the compression ratio. A filter chain may
+    contain up to four filters, although usually only one or two are used.
+    For example, putting a BCJ (Branch/Call/Jump) filter before LZMA2
+    in the filter chain can improve compression ratio of executable files.
+
+    Since the .xz format allows adding new filter IDs, it is possible that
+    some day there will be a filter that is, for example, much faster to
+    compress than LZMA2 (but probably with worse compression ratio).
+    Similarly, it is possible that some day there is a filter that will
+    compress better than LZMA2.
+
+    XZ Utils supports multithreaded compression. XZ Utils doesn't support
+    multithreaded decompression yet. It has been planned though and taken
+    into account when designing the .xz file format. In the future, files
+    that were created in threaded mode can be decompressed in threaded
+    mode too.
+
+
+1. Documentation
+----------------
+
+1.1. Overall documentation
+
+    README              This file
+
+    INSTALL.generic     Generic install instructions for those not familiar
+                        with packages using GNU Autotools
+    INSTALL             Installation instructions specific to XZ Utils
+    PACKAGERS           Information to packagers of XZ Utils
+
+    COPYING             XZ Utils copyright and license information
+    COPYING.GPLv2       GNU General Public License version 2
+    COPYING.GPLv3       GNU General Public License version 3
+    COPYING.LGPLv2.1    GNU Lesser General Public License version 2.1
+
+    AUTHORS             The main authors of XZ Utils
+    THANKS              Incomplete list of people who have helped making
+                        this software
+    NEWS                User-visible changes between XZ Utils releases
+    ChangeLog           Detailed list of changes (commit log)
+    TODO                Known bugs and some sort of to-do list
+
+    Note that only some of the above files are included in binary
+    packages.
+
+
+1.2. Documentation for command-line tools
+
+    The command-line tools are documented as man pages. In source code
+    releases (and possibly also in some binary packages), the man pages
+    are also provided in plain text (ASCII only) and PDF formats in the
+    directory "doc/man" to make the man pages more accessible to those
+    whose operating system doesn't provide an easy way to view man pages.
+
+
+1.3. Documentation for liblzma
+
+    The liblzma API headers include short docs about each function
+    and data type as Doxygen tags. These docs should be quite OK as
+    a quick reference.
+
+    There are a few example/tutorial programs that should help in
+    getting started with liblzma. In the source package the examples
+    are in "doc/examples" and in binary packages they may be under
+    "examples" in the same directory as this README.
+
+    Since the liblzma API has similarities to the zlib API, some people
+    may find it useful to read the zlib docs and tutorial too:
+
+        http://zlib.net/manual.html
+        http://zlib.net/zlib_how.html
+
+
+2. Version numbering
+--------------------
+
+    The version number format of XZ Utils is X.Y.ZS:
+
+      - X is the major version. When this is incremented, the library
+        API and ABI break.
+
+      - Y is the minor version. It is incremented when new features
+        are added without breaking the existing API or ABI. An even Y
+        indicates a stable release and an odd Y indicates unstable
+        (alpha or beta version).
+
+      - Z is the revision. This has a different meaning for stable and
+        unstable releases:
+
+          * Stable: Z is incremented when bugs get fixed without adding
+            any new features. This is intended to be convenient for
+            downstream distributors that want bug fixes but don't want
+            any new features to minimize the risk of introducing new bugs.
+
+          * Unstable: Z is just a counter. API or ABI of features added
+            in earlier unstable releases having the same X.Y may break.
+
+      - S indicates stability of the release. It is missing from the
+        stable releases, where Y is an even number. When Y is odd, S
+        is either "alpha" or "beta" to make it very clear that such
+        versions are not stable releases. The same X.Y.Z combination is
+        not used for more than one stability level, i.e. after X.Y.Zalpha,
+        the next version can be X.Y.(Z+1)beta but not X.Y.Zbeta.
+
+
+3. Reporting bugs
+-----------------
+
+    Naturally it is easiest for me if you already know what causes the
+    unexpected behavior. Even better if you have a patch to propose.
+    However, quite often the reason for unexpected behavior is unknown,
+    so here are a few things to do before sending a bug report:
+
+      1. Try to create a small example how to reproduce the issue.
+
+      2. Compile XZ Utils with debugging code using configure switches
+         --enable-debug and, if possible, --disable-shared. If you are
+         using GCC, use CFLAGS='-O0 -ggdb3'. Don't strip the resulting
+         binaries.
+
+      3. Turn on core dumps. The exact command depends on your shell;
+         for example in GNU bash it is done with "ulimit -c unlimited",
+         and in tcsh with "limit coredumpsize unlimited".
+
+      4. Try to reproduce the suspected bug. If you get "assertion failed"
+         message, be sure to include the complete message in your bug
+         report. If the application leaves a coredump, get a backtrace
+         using gdb:
+           $ gdb /path/to/app-binary   # Load the app to the debugger.
+           (gdb) core core   # Open the coredump.
+           (gdb) bt   # Print the backtrace. Copy & paste to bug report.
+           (gdb) quit   # Quit gdb.
+
+    Report your bug via email or IRC (see Contact information below).
+    Don't send core dump files or any executables. If you have a small
+    example file(s) (total size less than 256 KiB), please include
+    it/them as an attachment. If you have bigger test files, put them
+    online somewhere and include a URL to the file(s) in the bug report.
+
+    Always include the exact version number of XZ Utils in the bug report.
+    If you are using a snapshot from the git repository, use "git describe"
+    to get the exact snapshot version. If you are using XZ Utils shipped
+    in an operating system distribution, mention the distribution name,
+    distribution version, and exact xz package version; if you cannot
+    repeat the bug with the code compiled from unpatched source code,
+    you probably need to report a bug to your distribution's bug tracking
+    system.
+
+
+4. Translations
+---------------
+
+    The xz command line tool and all man pages can be translated.
+    The translations are handled via the Translation Project. If you
+    wish to help translating xz, please join the Translation Project:
+
+        https://translationproject.org/html/translators.html
+
+    Below are notes and testing instructions specific to xz
+    translations.
+
+    Testing can be done by installing xz into a temporary directory:
+
+        ./configure --disable-shared --prefix=/tmp/xz-test
+        # <Edit the .po file in the po directory.>
+        make -C po update-po
+        make install
+        bash debug/translation.bash | less
+        bash debug/translation.bash | less -S  # For --list outputs
+
+    Repeat the above as needed (no need to re-run configure though).
+
+    Note especially the following:
+
+      - The output of --help and --long-help must look nice on
+        an 80-column terminal. It's OK to add extra lines if needed.
+
+      - In contrast, don't add extra lines to error messages and such.
+        They are often preceded with e.g. a filename on the same line,
+        so you have no way to predict where to put a \n. Let the terminal
+        do the wrapping even if it looks ugly. Adding new lines will be
+        even uglier in the generic case even if it looks nice in a few
+        limited examples.
+
+      - Be careful with column alignment in tables and table-like output
+        (--list, --list --verbose --verbose, --info-memory, --help, and
+        --long-help):
+
+          * All descriptions of options in --help should start in the
+            same column (but it doesn't need to be the same column as
+            in the English messages; just be consistent if you change it).
+            Check that both --help and --long-help look OK, since they
+            share several strings.
+
+          * --list --verbose and --info-memory print lines that have
+            the format "Description:   %s". If you need a longer
+            description, you can put extra space between the colon
+            and %s. Then you may need to add extra space to other
+            strings too so that the result as a whole looks good (all
+            values start at the same column).
+
+          * The columns of the actual tables in --list --verbose --verbose
+            should be aligned properly. Abbreviate if necessary. It might
+            be good to keep at least 2 or 3 spaces between column headings
+            and avoid spaces in the headings so that the columns stand out
+            better, but this is a matter of opinion. Do what you think
+            looks best.
+
+      - Be careful to put a period at the end of a sentence when the
+        original version has it, and don't put it when the original
+        doesn't have it. Similarly, be careful with \n characters
+        at the beginning and end of the strings.
+
+      - Read the TRANSLATORS comments that have been extracted from the
+        source code and included in xz.pot. Some comments suggest
+        testing with a specific command which needs an .xz file. You
+        may use e.g. any tests/files/good-*.xz. However, these test
+        commands are included in translations.bash output, so reading
+        translations.bash output carefully can be enough.
+
+      - If you find language problems in the original English strings,
+        feel free to suggest improvements. Ask if something is unclear.
+
+      - The translated messages should be understandable (sometimes this
+        may be a problem with the original English messages too). Don't
+        make a direct word-by-word translation from English especially if
+        the result doesn't sound good in your language.
+
+    Thanks for your help!
+
+
+5. Other implementations of the .xz format
+------------------------------------------
+
+    7-Zip and the p7zip port of 7-Zip support the .xz format starting
+    from the version 9.00alpha.
+
+        http://7-zip.org/
+        http://p7zip.sourceforge.net/
+
+    XZ Embedded is a limited implementation written for use in the Linux
+    kernel, but it is also suitable for other embedded use.
+
+        https://tukaani.org/xz/embedded.html
+
+
+6. Contact information
+----------------------
+
+    If you have questions, bug reports, patches etc. related to XZ Utils,
+    the project maintainers Lasse Collin and Jia Tan can be reached via
+    <xz@tukaani.org>.
+
+    You might find Lasse also from #tukaani on Libera Chat (IRC).
+    The nick is Larhzu. The channel tends to be pretty quiet,
+    so just ask your question and someone might wake up.
+

THANKS

@@ -0,0 +1,163 @@
+
+Thanks
+======
+
+Some people have helped more, some less, but nevertheless everyone's help
+has been important. :-) In alphabetical order:
+  - Mark Adler
+  - H. Peter Anvin
+  - Jeff Bastian
+  - Nelson H. F. Beebe
+  - Karl Beldan
+  - Karl Berry
+  - Anders F. Björklund
+  - Emmanuel Blot
+  - Melanie Blower
+  - Alexander Bluhm
+  - Martin Blumenstingl
+  - Ben Boeckel
+  - Jakub Bogusz
+  - Adam Borowski
+  - Maarten Bosmans
+  - Trent W. Buck
+  - Kevin R. Bulgrien
+  - James Buren
+  - David Burklund
+  - Daniel Mealha Cabrita
+  - Milo Casagrande
+  - Marek Černocký
+  - Tomer Chachamu
+  - Vitaly Chikunov
+  - Antoine Cœur
+  - Gabi Davar
+  - İhsan Doğan
+  - Chris Donawa
+  - Andrew Dudman
+  - Markus Duft
+  - İsmail Dönmez
+  - Paul Eggert
+  - Robert Elz
+  - Gilles Espinasse
+  - Denis Excoffier
+  - Michael Felt
+  - Michael Fox
+  - Mike Frysinger
+  - Daniel Richard G.
+  - Tomasz Gajc
+  - Bjarni Ingi Gislason
+  - John Paul Adrian Glaubitz
+  - Bill Glessner
+  - Michał Górny
+  - Jason Gorski
+  - Juan Manuel Guerrero
+  - Diederik de Haas
+  - Joachim Henke
+  - Christian Hesse
+  - Vincenzo Innocente
+  - Peter Ivanov
+  - Nicholas Jackson
+  - Sam James
+  - Hajin Jang
+  - Jouk Jansen
+  - Jun I Jin
+  - Kiyoshi Kanazawa
+  - Per Øyvind Karlsen
+  - Iouri Kharon
+  - Thomas Klausner
+  - Richard Koch
+  - Ville Koskinen
+  - Jan Kratochvil
+  - Christian Kujau
+  - Stephan Kulow
+  - Ilya Kurdyukov
+  - Peter Lawler
+  - James M Leddy
+  - Vincent Lefevre
+  - Hin-Tak Leung
+  - Andraž 'ruskie' Levstik
+  - Cary Lewis
+  - Wim Lewis
+  - Xin Li
+  - Eric Lindblad
+  - Lorenzo De Liso
+  - H.J. Lu
+  - Bela Lubkin
+  - Gregory Margo
+  - Julien Marrec
+  - Ed Maste
+  - Martin Matuška
+  - Ivan A. Melnikov
+  - Jim Meyering
+  - Arkadiusz Miskiewicz
+  - Nathan Moinvaziri
+  - Étienne Mollier
+  - Conley Moorhous
+  - Rafał Mużyło
+  - Adrien Nader
+  - Evan Nemerson
+  - Hongbo Ni
+  - Jonathan Nieder
+  - Andre Noll
+  - Peter O'Gorman
+  - Daniel Packard
+  - Filip Palian
+  - Peter Pallinger
+  - Rui Paulo
+  - Igor Pavlov
+  - Diego Elio Pettenò
+  - Elbert Pol
+  - Mikko Pouru
+  - Rich Prohaska
+  - Trần Ngọc Quân
+  - Pavel Raiskup
+  - Ole André Vadla Ravnås
+  - Eric S. Raymond
+  - Robert Readman
+  - Bernhard Reutner-Fischer
+  - Markus Rickert
+  - Cristian Rodríguez
+  - Christian von Roques
+  - Boud Roukema
+  - Torsten Rupp
+  - Stephen Sachs
+  - Jukka Salmi
+  - Alexandre Sauvé
+  - Benno Schulenberg
+  - Andreas Schwab
+  - Bhargava Shastry
+  - Dan Shechter
+  - Stuart Shelton
+  - Sebastian Andrzej Siewior
+  - Ville Skyttä
+  - Brad Smith
+  - Bruce Stark
+  - Pippijn van Steenhoven
+  - Jonathan Stott
+  - Dan Stromberg
+  - Jia Tan
+  - Vincent Torri
+  - Paul Townsend
+  - Mohammed Adnène Trojette
+  - Alexey Tourbin
+  - Loganaden Velvindron
+  - Patrick J. Volkerding
+  - Martin Väth
+  - Adam Walling
+  - Jeffrey Walton
+  - Christian Weisgerber
+  - Dan Weiss
+  - Bert Wesarg
+  - Fredrik Wikstrom
+  - Jim Wilcoxson
+  - Ralf Wildenhues
+  - Charles Wilson
+  - Lars Wirzenius
+  - Pilorz Wojciech
+  - Ryan Young
+  - Andreas Zieringer
+
+Also thanks to all the people who have participated in the Tukaani project.
+
+I have probably forgot to add some names to the above list. Sorry about
+that and thanks for your help.
+

TODO

@@ -0,0 +1,109 @@
+
+XZ Utils To-Do List
+===================
+
+Known bugs
+----------
+
+    The test suite is too incomplete.
+
+    If the memory usage limit is less than about 13 MiB, xz is unable to
+    automatically scale down the compression settings enough even though
+    it would be  possible by switching from BT2/BT3/BT4 match finder to
+    HC3/HC4.
+
+    XZ Utils compress some files significantly worse than LZMA Utils.
+    This is due to faster compression presets used by XZ Utils, and
+    can often be worked around by using "xz --extreme". With some files
+    --extreme isn't enough though: it's most likely with files that
+    compress extremely well, so going from compression ratio of 0.003
+    to 0.004 means big relative increase in the compressed file size.
+
+    xz doesn't quote unprintable characters when it displays file names
+    given on the command line.
+
+    tuklib_exit() doesn't block signals => EINTR is possible.
+
+    SIGTSTP is not handled. If xz is stopped, the estimated remaining
+    time and calculated (de)compression speed won't make sense in the
+    progress indicator (xz --verbose).
+
+    If liblzma has created threads and fork() gets called, liblzma
+    code will break in the child process unless it calls exec() and
+    doesn't touch liblzma.
+
+
+Missing features
+----------------
+
+    Add support for storing metadata in .xz files. A preliminary
+    idea is to create a new Stream type for metadata. When both
+    metadata and data are wanted in the same .xz file, two or more
+    Streams would be concatenated.
+
+    The state stored in lzma_stream should be cloneable, which would
+    be mostly useful when using a preset dictionary in LZMA2, but
+    it may have other uses too. Compare to deflateCopy() in zlib.
+
+    Support LZMA_FINISH in raw decoder to indicate end of LZMA1 and
+    other streams that don't have an end of payload marker.
+
+    Adjust dictionary size when the input file size is known.
+    Maybe do this only if an option is given.
+
+    xz doesn't support copying extended attributes, access control
+    lists etc. from source to target file.
+
+    Multithreaded compression:
+      - Reduce memory usage of the current method.
+      - Implement threaded match finders.
+      - Implement pigz-style threading in LZMA2.
+
+    Buffer-to-buffer coding could use less RAM (especially when
+    decompressing LZMA1 or LZMA2).
+
+    I/O library is not implemented (similar to gzopen() in zlib).
+    It will be a separate library that supports uncompressed, .gz,
+    .bz2, .lzma, and .xz files.
+
+    Support changing lzma_options_lzma.mode with lzma_filters_update().
+
+    Support LZMA_FULL_FLUSH for lzma_stream_decoder() to stop at
+    Block and Stream boundaries.
+
+    lzma_strerror() to convert lzma_ret to human readable form?
+    This is tricky, because the same error codes are used with
+    slightly different meanings, and this cannot be fixed anymore.
+
+    Make it possible to adjust LZMA2 options in the middle of a Block
+    so that the encoding speed vs. compression ratio can be optimized
+    when the compressed data is streamed over network.
+
+    Improved BCJ filters. The current filters are small but they aren't
+    so great when compressing binary packages that contain various file
+    types. Specifically, they make things worse if there are static
+    libraries or Linux kernel modules. The filtering could also be
+    more effective (without getting overly complex), for example,
+    streamable variant BCJ2 from 7-Zip could be implemented.
+
+    Filter that autodetects specific data types in the input stream
+    and applies appropriate filters for the corrects parts of the input.
+    Perhaps combine this with the BCJ filter improvement point above.
+
+    Long-range LZ77 method as a separate filter or as a new LZMA2
+    match finder.
+
+
+Documentation
+-------------
+
+    More tutorial programs are needed for liblzma.
+
+    Document the LZMA1 and LZMA2 algorithms.
+
+
+Miscellaneous
+------------
+
+    Try to get the media type for .xz registered at IANA.
+

config.h.in

@@ -0,0 +1,601 @@
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Define if building universal (internal helper macro) */
+#undef AC_APPLE_UNIVERSAL_BUILD
+
+/* How many MiB of RAM to assume if the real amount cannot be determined. */
+#undef ASSUME_RAM
+
+/* Define to 1 if translation of program messages to the user's native
+   language is requested. */
+#undef ENABLE_NLS
+
+/* Define to 1 if bswap_16 is available. */
+#undef HAVE_BSWAP_16
+
+/* Define to 1 if bswap_32 is available. */
+#undef HAVE_BSWAP_32
+
+/* Define to 1 if bswap_64 is available. */
+#undef HAVE_BSWAP_64
+
+/* Define to 1 if you have the <byteswap.h> header file. */
+#undef HAVE_BYTESWAP_H
+
+/* Define to 1 if Capsicum is available. */
+#undef HAVE_CAPSICUM
+
+/* Define to 1 if the system has the type `CC_SHA256_CTX'. */
+#undef HAVE_CC_SHA256_CTX
+
+/* Define to 1 if you have the `CC_SHA256_Init' function. */
+#undef HAVE_CC_SHA256_INIT
+
+/* Define to 1 if you have the Mac OS X function
+   CFLocaleCopyPreferredLanguages in the CoreFoundation framework. */
+#undef HAVE_CFLOCALECOPYPREFERREDLANGUAGES
+
+/* Define to 1 if you have the Mac OS X function CFPreferencesCopyAppValue in
+   the CoreFoundation framework. */
+#undef HAVE_CFPREFERENCESCOPYAPPVALUE
+
+/* Define to 1 if crc32 integrity check is enabled. */
+#undef HAVE_CHECK_CRC32
+
+/* Define to 1 if crc64 integrity check is enabled. */
+#undef HAVE_CHECK_CRC64
+
+/* Define to 1 if sha256 integrity check is enabled. */
+#undef HAVE_CHECK_SHA256
+
+/* Define to 1 if you have the `clock_gettime' function. */
+#undef HAVE_CLOCK_GETTIME
+
+/* Define to 1 if `CLOCK_MONOTONIC' is declared in <time.h>. */
+#undef HAVE_CLOCK_MONOTONIC
+
+/* Define to 1 if you have the <CommonCrypto/CommonDigest.h> header file. */
+#undef HAVE_COMMONCRYPTO_COMMONDIGEST_H
+
+/* Define to 1 if you have the <cpuid.h> header file. */
+#undef HAVE_CPUID_H
+
+/* Define if the GNU dcgettext() function is already present or preinstalled.
+   */
+#undef HAVE_DCGETTEXT
+
+/* Define to 1 if any of HAVE_DECODER_foo have been defined. */
+#undef HAVE_DECODERS
+
+/* Define to 1 if arm decoder is enabled. */
+#undef HAVE_DECODER_ARM
+
+/* Define to 1 if arm64 decoder is enabled. */
+#undef HAVE_DECODER_ARM64
+
+/* Define to 1 if armthumb decoder is enabled. */
+#undef HAVE_DECODER_ARMTHUMB
+
+/* Define to 1 if delta decoder is enabled. */
+#undef HAVE_DECODER_DELTA
+
+/* Define to 1 if ia64 decoder is enabled. */
+#undef HAVE_DECODER_IA64
+
+/* Define to 1 if lzma1 decoder is enabled. */
+#undef HAVE_DECODER_LZMA1
+
+/* Define to 1 if lzma2 decoder is enabled. */
+#undef HAVE_DECODER_LZMA2
+
+/* Define to 1 if powerpc decoder is enabled. */
+#undef HAVE_DECODER_POWERPC
+
+/* Define to 1 if sparc decoder is enabled. */
+#undef HAVE_DECODER_SPARC
+
+/* Define to 1 if x86 decoder is enabled. */
+#undef HAVE_DECODER_X86
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#undef HAVE_DLFCN_H
+
+/* Define to 1 if any of HAVE_ENCODER_foo have been defined. */
+#undef HAVE_ENCODERS
+
+/* Define to 1 if arm encoder is enabled. */
+#undef HAVE_ENCODER_ARM
+
+/* Define to 1 if arm64 encoder is enabled. */
+#undef HAVE_ENCODER_ARM64
+
+/* Define to 1 if armthumb encoder is enabled. */
+#undef HAVE_ENCODER_ARMTHUMB
+
+/* Define to 1 if delta encoder is enabled. */
+#undef HAVE_ENCODER_DELTA
+
+/* Define to 1 if ia64 encoder is enabled. */
+#undef HAVE_ENCODER_IA64
+
+/* Define to 1 if lzma1 encoder is enabled. */
+#undef HAVE_ENCODER_LZMA1
+
+/* Define to 1 if lzma2 encoder is enabled. */
+#undef HAVE_ENCODER_LZMA2
+
+/* Define to 1 if powerpc encoder is enabled. */
+#undef HAVE_ENCODER_POWERPC
+
+/* Define to 1 if sparc encoder is enabled. */
+#undef HAVE_ENCODER_SPARC
+
+/* Define to 1 if x86 encoder is enabled. */
+#undef HAVE_ENCODER_X86
+
+/* Define to 1 if you have the <fcntl.h> header file. */
+#undef HAVE_FCNTL_H
+
+/* Define to 1 if __attribute__((__constructor__)) is supported for functions.
+   */
+#undef HAVE_FUNC_ATTRIBUTE_CONSTRUCTOR
+
+/* Define to 1 if you have the `futimens' function. */
+#undef HAVE_FUTIMENS
+
+/* Define to 1 if you have the `futimes' function. */
+#undef HAVE_FUTIMES
+
+/* Define to 1 if you have the `futimesat' function. */
+#undef HAVE_FUTIMESAT
+
+/* Define to 1 if you have the <getopt.h> header file. */
+#undef HAVE_GETOPT_H
+
+/* Define to 1 if you have the `getopt_long' function. */
+#undef HAVE_GETOPT_LONG
+
+/* Define if the GNU gettext() function is already present or preinstalled. */
+#undef HAVE_GETTEXT
+
+/* Define if you have the iconv() function and it works. */
+#undef HAVE_ICONV
+
+/* Define to 1 if you have the <immintrin.h> header file. */
+#undef HAVE_IMMINTRIN_H
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#undef HAVE_INTTYPES_H
+
+/* Define to 1 if you have the <limits.h> header file. */
+#undef HAVE_LIMITS_H
+
+/* Define to 1 if .lz (lzip) decompression support is enabled. */
+#undef HAVE_LZIP_DECODER
+
+/* Define to 1 if mbrtowc and mbstate_t are properly declared. */
+#undef HAVE_MBRTOWC
+
+/* Define to 1 to enable bt2 match finder. */
+#undef HAVE_MF_BT2
+
+/* Define to 1 to enable bt3 match finder. */
+#undef HAVE_MF_BT3
+
+/* Define to 1 to enable bt4 match finder. */
+#undef HAVE_MF_BT4
+
+/* Define to 1 to enable hc3 match finder. */
+#undef HAVE_MF_HC3
+
+/* Define to 1 to enable hc4 match finder. */
+#undef HAVE_MF_HC4
+
+/* Define to 1 if you have the <minix/config.h> header file. */
+#undef HAVE_MINIX_CONFIG_H
+
+/* Define to 1 if getopt.h declares extern int optreset. */
+#undef HAVE_OPTRESET
+
+/* Define to 1 if you have the `pledge' function. */
+#undef HAVE_PLEDGE
+
+/* Define to 1 if you have the `posix_fadvise' function. */
+#undef HAVE_POSIX_FADVISE
+
+/* Define to 1 if `program_invocation_name' is declared in <errno.h>. */
+#undef HAVE_PROGRAM_INVOCATION_NAME
+
+/* Define to 1 if you have the `pthread_condattr_setclock' function. */
+#undef HAVE_PTHREAD_CONDATTR_SETCLOCK
+
+/* Have PTHREAD_PRIO_INHERIT. */
+#undef HAVE_PTHREAD_PRIO_INHERIT
+
+/* Define to 1 if you have the `SHA256Init' function. */
+#undef HAVE_SHA256INIT
+
+/* Define to 1 if the system has the type `SHA256_CTX'. */
+#undef HAVE_SHA256_CTX
+
+/* Define to 1 if you have the <sha256.h> header file. */
+#undef HAVE_SHA256_H
+
+/* Define to 1 if you have the `SHA256_Init' function. */
+#undef HAVE_SHA256_INIT
+
+/* Define to 1 if the system has the type `SHA2_CTX'. */
+#undef HAVE_SHA2_CTX
+
+/* Define to 1 if you have the <sha2.h> header file. */
+#undef HAVE_SHA2_H
+
+/* Define to 1 if optimizing for size. */
+#undef HAVE_SMALL
+
+/* Define to 1 if stdbool.h conforms to C99. */
+#undef HAVE_STDBOOL_H
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#undef HAVE_STDINT_H
+
+/* Define to 1 if you have the <stdio.h> header file. */
+#undef HAVE_STDIO_H
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#undef HAVE_STDLIB_H
+
+/* Define to 1 if you have the <strings.h> header file. */
+#undef HAVE_STRINGS_H
+
+/* Define to 1 if you have the <string.h> header file. */
+#undef HAVE_STRING_H
+
+/* Define to 1 if `st_atimensec' is a member of `struct stat'. */
+#undef HAVE_STRUCT_STAT_ST_ATIMENSEC
+
+/* Define to 1 if `st_atimespec.tv_nsec' is a member of `struct stat'. */
+#undef HAVE_STRUCT_STAT_ST_ATIMESPEC_TV_NSEC
+
+/* Define to 1 if `st_atim.st__tim.tv_nsec' is a member of `struct stat'. */
+#undef HAVE_STRUCT_STAT_ST_ATIM_ST__TIM_TV_NSEC
+
+/* Define to 1 if `st_atim.tv_nsec' is a member of `struct stat'. */
+#undef HAVE_STRUCT_STAT_ST_ATIM_TV_NSEC
+
+/* Define to 1 if `st_uatime' is a member of `struct stat'. */
+#undef HAVE_STRUCT_STAT_ST_UATIME
+
+/* Define to 1 to if GNU/Linux-specific details are unconditionally wanted for
+   symbol versioning. Define to 2 to if these are wanted only if also PIC is
+   defined (allows building both shared and static liblzma at the same time
+   with Libtool if neither --with-pic nor --without-pic is used). This define
+   must be used together with liblzma_linux.map. */
+#undef HAVE_SYMBOL_VERSIONS_LINUX
+
+/* Define to 1 if you have the <sys/byteorder.h> header file. */
+#undef HAVE_SYS_BYTEORDER_H
+
+/* Define to 1 if you have the <sys/capsicum.h> header file. */
+#undef HAVE_SYS_CAPSICUM_H
+
+/* Define to 1 if you have the <sys/endian.h> header file. */
+#undef HAVE_SYS_ENDIAN_H
+
+/* Define to 1 if you have the <sys/param.h> header file. */
+#undef HAVE_SYS_PARAM_H
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#undef HAVE_SYS_STAT_H
+
+/* Define to 1 if you have the <sys/time.h> header file. */
+#undef HAVE_SYS_TIME_H
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#undef HAVE_SYS_TYPES_H
+
+/* Define to 1 if the system has the type `uintptr_t'. */
+#undef HAVE_UINTPTR_T
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#undef HAVE_UNISTD_H
+
+/* Define to 1 if _mm_set_epi64x and _mm_clmulepi64_si128 are usable. See
+   configure.ac for details. */
+#undef HAVE_USABLE_CLMUL
+
+/* Define to 1 if you have the `utime' function. */
+#undef HAVE_UTIME
+
+/* Define to 1 if you have the `utimes' function. */
+#undef HAVE_UTIMES
+
+/* Define to 1 or 0, depending whether the compiler supports simple visibility
+   declarations. */
+#undef HAVE_VISIBILITY
+
+/* Define to 1 if you have the <wchar.h> header file. */
+#undef HAVE_WCHAR_H
+
+/* Define to 1 if you have the `wcwidth' function. */
+#undef HAVE_WCWIDTH
+
+/* Define to 1 if the system has the type `_Bool'. */
+#undef HAVE__BOOL
+
+/* Define to 1 if you have the `_futime' function. */
+#undef HAVE__FUTIME
+
+/* Define to 1 if _mm_movemask_epi8 is available. */
+#undef HAVE__MM_MOVEMASK_EPI8
+
+/* Define to 1 if the GNU C extension __builtin_assume_aligned is supported.
+   */
+#undef HAVE___BUILTIN_ASSUME_ALIGNED
+
+/* Define to 1 if the GNU C extensions __builtin_bswap16/32/64 are supported.
+   */
+#undef HAVE___BUILTIN_BSWAPXX
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#undef LT_OBJDIR
+
+/* Define to 1 when using POSIX threads (pthreads). */
+#undef MYTHREAD_POSIX
+
+/* Define to 1 when using Windows Vista compatible threads. This uses features
+   that are not available on Windows XP. */
+#undef MYTHREAD_VISTA
+
+/* Define to 1 when using Windows 95 (and thus XP) compatible threads. This
+   avoids use of features that were added in Windows Vista. */
+#undef MYTHREAD_WIN95
+
+/* Define to 1 to disable debugging code. */
+#undef NDEBUG
+
+/* Name of package */
+#undef PACKAGE
+
+/* Define to the address where bug reports for this package should be sent. */
+#undef PACKAGE_BUGREPORT
+
+/* Define to the full name of this package. */
+#undef PACKAGE_NAME
+
+/* Define to the full name and version of this package. */
+#undef PACKAGE_STRING
+
+/* Define to the one symbol short name of this package. */
+#undef PACKAGE_TARNAME
+
+/* Define to the home page for this package. */
+#undef PACKAGE_URL
+
+/* Define to the version of this package. */
+#undef PACKAGE_VERSION
+
+/* Define to necessary symbol if this constant uses a non-standard name on
+   your system. */
+#undef PTHREAD_CREATE_JOINABLE
+
+/* The size of `size_t', as computed by sizeof. */
+#undef SIZEOF_SIZE_T
+
+/* Define to 1 if all of the C90 standard headers exist (not just the ones
+   required in a freestanding environment). This macro is provided for
+   backward compatibility; new code need not use it. */
+#undef STDC_HEADERS
+
+/* Define to 1 if the number of available CPU cores can be detected with
+   cpuset(2). */
+#undef TUKLIB_CPUCORES_CPUSET
+
+/* Define to 1 if the number of available CPU cores can be detected with
+   pstat_getdynamic(). */
+#undef TUKLIB_CPUCORES_PSTAT_GETDYNAMIC
+
+/* Define to 1 if the number of available CPU cores can be detected with
+   sched_getaffinity() */
+#undef TUKLIB_CPUCORES_SCHED_GETAFFINITY
+
+/* Define to 1 if the number of available CPU cores can be detected with
+   sysconf(_SC_NPROCESSORS_ONLN) or sysconf(_SC_NPROC_ONLN). */
+#undef TUKLIB_CPUCORES_SYSCONF
+
+/* Define to 1 if the number of available CPU cores can be detected with
+   sysctl(). */
+#undef TUKLIB_CPUCORES_SYSCTL
+
+/* Define to 1 if the system supports fast unaligned access to 16-bit, 32-bit,
+   and 64-bit integers. */
+#undef TUKLIB_FAST_UNALIGNED_ACCESS
+
+/* Define to 1 if the amount of physical memory can be detected with
+   _system_configuration.physmem. */
+#undef TUKLIB_PHYSMEM_AIX
+
+/* Define to 1 if the amount of physical memory can be detected with
+   getinvent_r(). */
+#undef TUKLIB_PHYSMEM_GETINVENT_R
+
+/* Define to 1 if the amount of physical memory can be detected with
+   getsysinfo(). */
+#undef TUKLIB_PHYSMEM_GETSYSINFO
+
+/* Define to 1 if the amount of physical memory can be detected with
+   pstat_getstatic(). */
+#undef TUKLIB_PHYSMEM_PSTAT_GETSTATIC
+
+/* Define to 1 if the amount of physical memory can be detected with
+   sysconf(_SC_PAGESIZE) and sysconf(_SC_PHYS_PAGES). */
+#undef TUKLIB_PHYSMEM_SYSCONF
+
+/* Define to 1 if the amount of physical memory can be detected with sysctl().
+   */
+#undef TUKLIB_PHYSMEM_SYSCTL
+
+/* Define to 1 if the amount of physical memory can be detected with Linux
+   sysinfo(). */
+#undef TUKLIB_PHYSMEM_SYSINFO
+
+/* Define to 1 to use unsafe type punning, e.g. char *x = ...; *(int *)x =
+   123; which violates strict aliasing rules and thus is undefined behavior
+   and might result in broken code. */
+#undef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+
+/* Enable extensions on AIX 3, Interix.  */
+#ifndef _ALL_SOURCE
+# undef _ALL_SOURCE
+#endif
+/* Enable general extensions on macOS.  */
+#ifndef _DARWIN_C_SOURCE
+# undef _DARWIN_C_SOURCE
+#endif
+/* Enable general extensions on Solaris.  */
+#ifndef __EXTENSIONS__
+# undef __EXTENSIONS__
+#endif
+/* Enable GNU extensions on systems that have them.  */
+#ifndef _GNU_SOURCE
+# undef _GNU_SOURCE
+#endif
+/* Enable X/Open compliant socket functions that do not require linking
+   with -lxnet on HP-UX 11.11.  */
+#ifndef _HPUX_ALT_XOPEN_SOCKET_API
+# undef _HPUX_ALT_XOPEN_SOCKET_API
+#endif
+/* Identify the host operating system as Minix.
+   This macro does not affect the system headers' behavior.
+   A future release of Autoconf may stop defining this macro.  */
+#ifndef _MINIX
+# undef _MINIX
+#endif
+/* Enable general extensions on NetBSD.
+   Enable NetBSD compatibility extensions on Minix.  */
+#ifndef _NETBSD_SOURCE
+# undef _NETBSD_SOURCE
+#endif
+/* Enable OpenBSD compatibility extensions on NetBSD.
+   Oddly enough, this does nothing on OpenBSD.  */
+#ifndef _OPENBSD_SOURCE
+# undef _OPENBSD_SOURCE
+#endif
+/* Define to 1 if needed for POSIX-compatible behavior.  */
+#ifndef _POSIX_SOURCE
+# undef _POSIX_SOURCE
+#endif
+/* Define to 2 if needed for POSIX-compatible behavior.  */
+#ifndef _POSIX_1_SOURCE
+# undef _POSIX_1_SOURCE
+#endif
+/* Enable POSIX-compatible threading on Solaris.  */
+#ifndef _POSIX_PTHREAD_SEMANTICS
+# undef _POSIX_PTHREAD_SEMANTICS
+#endif
+/* Enable extensions specified by ISO/IEC TS 18661-5:2014.  */
+#ifndef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
+# undef __STDC_WANT_IEC_60559_ATTRIBS_EXT__
+#endif
+/* Enable extensions specified by ISO/IEC TS 18661-1:2014.  */
+#ifndef __STDC_WANT_IEC_60559_BFP_EXT__
+# undef __STDC_WANT_IEC_60559_BFP_EXT__
+#endif
+/* Enable extensions specified by ISO/IEC TS 18661-2:2015.  */
+#ifndef __STDC_WANT_IEC_60559_DFP_EXT__
+# undef __STDC_WANT_IEC_60559_DFP_EXT__
+#endif
+/* Enable extensions specified by ISO/IEC TS 18661-4:2015.  */
+#ifndef __STDC_WANT_IEC_60559_FUNCS_EXT__
+# undef __STDC_WANT_IEC_60559_FUNCS_EXT__
+#endif
+/* Enable extensions specified by ISO/IEC TS 18661-3:2015.  */
+#ifndef __STDC_WANT_IEC_60559_TYPES_EXT__
+# undef __STDC_WANT_IEC_60559_TYPES_EXT__
+#endif
+/* Enable extensions specified by ISO/IEC TR 24731-2:2010.  */
+#ifndef __STDC_WANT_LIB_EXT2__
+# undef __STDC_WANT_LIB_EXT2__
+#endif
+/* Enable extensions specified by ISO/IEC 24747:2009.  */
+#ifndef __STDC_WANT_MATH_SPEC_FUNCS__
+# undef __STDC_WANT_MATH_SPEC_FUNCS__
+#endif
+/* Enable extensions on HP NonStop.  */
+#ifndef _TANDEM_SOURCE
+# undef _TANDEM_SOURCE
+#endif
+/* Enable X/Open extensions.  Define to 500 only if necessary
+   to make mbstate_t available.  */
+#ifndef _XOPEN_SOURCE
+# undef _XOPEN_SOURCE
+#endif
+
+
+/* Version number of package */
+#undef VERSION
+
+/* Define WORDS_BIGENDIAN to 1 if your processor stores words with the most
+   significant byte first (like Motorola and SPARC, unlike Intel). */
+#if defined AC_APPLE_UNIVERSAL_BUILD
+# if defined __BIG_ENDIAN__
+#  define WORDS_BIGENDIAN 1
+# endif
+#else
+# ifndef WORDS_BIGENDIAN
+#  undef WORDS_BIGENDIAN
+# endif
+#endif
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+#undef _FILE_OFFSET_BITS
+
+/* Define for large files, on AIX-style hosts. */
+#undef _LARGE_FILES
+
+/* Define for Solaris 2.5.1 so the uint32_t typedef from <sys/synch.h>,
+   <pthread.h>, or <semaphore.h> is not used. If the typedef were allowed, the
+   #define below would cause a syntax error. */
+#undef _UINT32_T
+
+/* Define for Solaris 2.5.1 so the uint64_t typedef from <sys/synch.h>,
+   <pthread.h>, or <semaphore.h> is not used. If the typedef were allowed, the
+   #define below would cause a syntax error. */
+#undef _UINT64_T
+
+/* Define for Solaris 2.5.1 so the uint8_t typedef from <sys/synch.h>,
+   <pthread.h>, or <semaphore.h> is not used. If the typedef were allowed, the
+   #define below would cause a syntax error. */
+#undef _UINT8_T
+
+/* Define to rpl_ if the getopt replacement functions and variables should be
+   used. */
+#undef __GETOPT_PREFIX
+
+/* Define to the type of a signed integer type of width exactly 32 bits if
+   such a type exists and the standard includes do not define it. */
+#undef int32_t
+
+/* Define to the type of a signed integer type of width exactly 64 bits if
+   such a type exists and the standard includes do not define it. */
+#undef int64_t
+
+/* Define to the type of an unsigned integer type of width exactly 16 bits if
+   such a type exists and the standard includes do not define it. */
+#undef uint16_t
+
+/* Define to the type of an unsigned integer type of width exactly 32 bits if
+   such a type exists and the standard includes do not define it. */
+#undef uint32_t
+
+/* Define to the type of an unsigned integer type of width exactly 64 bits if
+   such a type exists and the standard includes do not define it. */
+#undef uint64_t
+
+/* Define to the type of an unsigned integer type of width exactly 8 bits if
+   such a type exists and the standard includes do not define it. */
+#undef uint8_t
+
+/* Define to the type of an unsigned integer type wide enough to hold a
+   pointer, if such a type exists, and if the system does not define it. */
+#undef uintptr_t

debug/README

@@ -0,0 +1,17 @@
+
+Debug tools
+-----------
+
+    This directory contains a few tiny programs that may be helpful when
+    debugging XZ Utils.
+
+    These tools are not meant to be installed. Often one needs to edit
+    the source code a little to make the programs do the wanted things.
+    If you don't know how these programs could help you, it is likely
+    that they really are useless to you.
+
+    These aren't intended to be used as example programs. They take some
+    shortcuts here and there, which correct programs should not do. Many
+    possible errors (especially I/O errors) are ignored. Don't report
+    bugs or send patches to fix this kind of bugs.
+

debug/crc32.c

@@ -0,0 +1,39 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       crc32.c
+/// \brief      Primitive CRC32 calculation tool
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include "lzma.h"
+#include <stdio.h>
+
+
+int
+main(void)
+{
+	uint32_t crc = 0;
+
+	do {
+		uint8_t buf[BUFSIZ];
+		const size_t size = fread(buf, 1, sizeof(buf), stdin);
+		crc = lzma_crc32(buf, size, crc);
+	} while (!ferror(stdin) && !feof(stdin));
+
+	//printf("%08" PRIX32 "\n", crc);
+
+	// I want it little endian so it's easy to work with hex editor.
+	printf("%02" PRIX32 " ", crc & 0xFF);
+	printf("%02" PRIX32 " ", (crc >> 8) & 0xFF);
+	printf("%02" PRIX32 " ", (crc >> 16) & 0xFF);
+	printf("%02" PRIX32 " ", crc >> 24);
+	printf("\n");
+
+	return 0;
+}

debug/full_flush.c

@@ -0,0 +1,103 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       full_flush.c
+/// \brief      Encode files using LZMA_FULL_FLUSH
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include "lzma.h"
+#include <stdio.h>
+
+#define CHUNK 64
+
+
+static lzma_stream strm = LZMA_STREAM_INIT;
+static FILE *file_in;
+
+
+static void
+encode(size_t size, lzma_action action)
+{
+	uint8_t in[CHUNK];
+	uint8_t out[CHUNK];
+	lzma_ret ret;
+
+	do {
+		if (strm.avail_in == 0 && size > 0) {
+			const size_t amount = my_min(size, CHUNK);
+			strm.avail_in = fread(in, 1, amount, file_in);
+			strm.next_in = in;
+			size -= amount; // Intentionally not using avail_in.
+		}
+
+		strm.next_out = out;
+		strm.avail_out = CHUNK;
+
+		ret = lzma_code(&strm, size == 0 ? action : LZMA_RUN);
+
+		if (ret != LZMA_OK && ret != LZMA_STREAM_END) {
+			fprintf(stderr, "%s:%u: %s: ret == %d\n",
+					__FILE__, __LINE__, __func__, ret);
+			exit(1);
+		}
+
+		fwrite(out, 1, CHUNK - strm.avail_out, stdout);
+
+	} while (size > 0 || strm.avail_out == 0);
+
+	if ((action == LZMA_RUN && ret != LZMA_OK)
+			|| (action != LZMA_RUN && ret != LZMA_STREAM_END)) {
+		fprintf(stderr, "%s:%u: %s: ret == %d\n",
+				__FILE__, __LINE__, __func__, ret);
+		exit(1);
+	}
+}
+
+
+int
+main(int argc, char **argv)
+{
+	file_in = argc > 1 ? fopen(argv[1], "rb") : stdin;
+
+
+	// Config
+	lzma_options_lzma opt_lzma;
+	if (lzma_lzma_preset(&opt_lzma, 1)) {
+		fprintf(stderr, "preset failed\n");
+		exit(1);
+	}
+	lzma_filter filters[LZMA_FILTERS_MAX + 1];
+	filters[0].id = LZMA_FILTER_LZMA2;
+	filters[0].options = &opt_lzma;
+	filters[1].id = LZMA_VLI_UNKNOWN;
+
+	// Init
+	if (lzma_stream_encoder(&strm, filters, LZMA_CHECK_CRC32) != LZMA_OK) {
+		fprintf(stderr, "init failed\n");
+		exit(1);
+	}
+
+// 	if (lzma_easy_encoder(&strm, 1)) {
+// 		fprintf(stderr, "init failed\n");
+// 		exit(1);
+// 	}
+
+	// Encoding
+	encode(0, LZMA_FULL_FLUSH);
+	encode(6, LZMA_FULL_FLUSH);
+	encode(0, LZMA_FULL_FLUSH);
+	encode(7, LZMA_FULL_FLUSH);
+	encode(0, LZMA_FULL_FLUSH);
+	encode(0, LZMA_FINISH);
+
+	// Clean up
+	lzma_end(&strm);
+
+	return 0;
+}

debug/hex2bin.c

@@ -0,0 +1,53 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       hex2bin.c
+/// \brief      Converts hexadecimal input strings to binary
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include <stdio.h>
+#include <ctype.h>
+
+
+static int
+getbin(int x)
+{
+	if (x >= '0' && x <= '9')
+		return x - '0';
+
+	if (x >= 'A' && x <= 'F')
+		return x - 'A' + 10;
+
+	return x - 'a' + 10;
+}
+
+
+int
+main(void)
+{
+	while (true) {
+		int byte = getchar();
+		if (byte == EOF)
+			return 0;
+		if (!isxdigit(byte))
+			continue;
+
+		const int digit = getchar();
+		if (digit == EOF || !isxdigit(digit)) {
+			fprintf(stderr, "Invalid input\n");
+			return 1;
+		}
+
+		byte = (getbin(byte) << 4) | getbin(digit);
+		if (putchar(byte) == EOF) {
+			perror(NULL);
+			return 1;
+		}
+	}
+}

debug/known_sizes.c

@@ -0,0 +1,129 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       known_sizes.c
+/// \brief      Encodes .lzma Stream with sizes known in Block Header
+///
+/// The input file is encoded in RAM, and the known Compressed Size
+/// and/or Uncompressed Size values are stored in the Block Header.
+/// As of writing there's no such Stream encoder in liblzma.
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include "lzma.h"
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/unistd.h>
+#include <stdio.h>
+
+
+// Support file sizes up to 1 MiB. We use this for output space too, so files
+// close to 1 MiB had better compress at least a little or we have a buffer
+// overflow.
+#define BUFFER_SIZE (1U << 20)
+
+
+int
+main(void)
+{
+	// Allocate the buffers.
+	uint8_t *in = malloc(BUFFER_SIZE);
+	uint8_t *out = malloc(BUFFER_SIZE);
+	if (in == NULL || out == NULL)
+		return 1;
+
+	// Fill the input buffer.
+	const size_t in_size = fread(in, 1, BUFFER_SIZE, stdin);
+
+	// Filter setup
+	lzma_options_lzma opt_lzma;
+	if (lzma_lzma_preset(&opt_lzma, 1))
+		return 1;
+
+	lzma_filter filters[] = {
+		{
+			.id = LZMA_FILTER_LZMA2,
+			.options = &opt_lzma
+		},
+		{
+			.id = LZMA_VLI_UNKNOWN
+		}
+	};
+
+	lzma_block block = {
+		.check = LZMA_CHECK_CRC32,
+		.compressed_size = BUFFER_SIZE, // Worst case reserve
+		.uncompressed_size = in_size,
+		.filters = filters,
+	};
+
+	lzma_stream strm = LZMA_STREAM_INIT;
+	if (lzma_block_encoder(&strm, &block) != LZMA_OK)
+		return 1;
+
+	// Reserve space for Stream Header and Block Header. We need to
+	// calculate the size of the Block Header first.
+	if (lzma_block_header_size(&block) != LZMA_OK)
+		return 1;
+
+	size_t out_size = LZMA_STREAM_HEADER_SIZE + block.header_size;
+
+	strm.next_in = in;
+	strm.avail_in = in_size;
+	strm.next_out = out + out_size;
+	strm.avail_out = BUFFER_SIZE - out_size;
+
+	if (lzma_code(&strm, LZMA_FINISH) != LZMA_STREAM_END)
+		return 1;
+
+	out_size += strm.total_out;
+
+	if (lzma_block_header_encode(&block, out + LZMA_STREAM_HEADER_SIZE)
+			!= LZMA_OK)
+		return 1;
+
+	lzma_index *idx = lzma_index_init(NULL);
+	if (idx == NULL)
+		return 1;
+
+	if (lzma_index_append(idx, NULL, block.header_size + strm.total_out,
+			strm.total_in) != LZMA_OK)
+		return 1;
+
+	if (lzma_index_encoder(&strm, idx) != LZMA_OK)
+		return 1;
+
+	if (lzma_code(&strm, LZMA_RUN) != LZMA_STREAM_END)
+		return 1;
+
+	out_size += strm.total_out;
+
+	lzma_end(&strm);
+
+	lzma_index_end(idx, NULL);
+
+	// Encode the Stream Header and Stream Footer. backwards_size is
+	// needed only for the Stream Footer.
+	lzma_stream_flags sf = {
+		.backward_size = strm.total_out,
+		.check = block.check,
+	};
+
+	if (lzma_stream_header_encode(&sf, out) != LZMA_OK)
+		return 1;
+
+	if (lzma_stream_footer_encode(&sf, out + out_size) != LZMA_OK)
+		return 1;
+
+	out_size += LZMA_STREAM_HEADER_SIZE;
+
+	// Write out the file.
+	fwrite(out, 1, out_size, stdout);
+
+	return 0;
+}

debug/memusage.c

@@ -0,0 +1,51 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       memusage.c
+/// \brief      Calculates memory usage using lzma_memory_usage()
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include "lzma.h"
+#include <stdio.h>
+
+int
+main(void)
+{
+	lzma_options_lzma lzma = {
+		.dict_size = (1U << 30) + (1U << 29),
+		.lc = 3,
+		.lp = 0,
+		.pb = 2,
+		.preset_dict = NULL,
+		.preset_dict_size = 0,
+		.mode = LZMA_MODE_NORMAL,
+		.nice_len = 48,
+		.mf = LZMA_MF_BT4,
+		.depth = 0,
+	};
+
+/*
+	lzma_options_filter filters[] = {
+		{ LZMA_FILTER_LZMA1,
+			(lzma_options_lzma *)&lzma_preset_lzma[6 - 1] },
+		{ UINT64_MAX, NULL }
+	};
+*/
+	lzma_filter filters[] = {
+		{ LZMA_FILTER_LZMA1, &lzma },
+		{ UINT64_MAX, NULL }
+	};
+
+	printf("Encoder: %10" PRIu64 " B\n",
+			lzma_raw_encoder_memusage(filters));
+	printf("Decoder: %10" PRIu64 " B\n",
+			lzma_raw_decoder_memusage(filters));
+
+	return 0;
+}

debug/repeat.c

@@ -0,0 +1,36 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       repeat.c
+/// \brief      Repeats given string given times
+///
+/// This program can be useful when debugging run-length encoder in
+/// the Subblock filter, especially the condition when repeat count
+/// doesn't fit into 28-bit integer.
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include <stdio.h>
+
+
+int
+main(int argc, char **argv)
+{
+	if (argc != 3) {
+		fprintf(stderr, "Usage: %s COUNT STRING\n", argv[0]);
+		exit(1);
+	}
+
+	unsigned long long count = strtoull(argv[1], NULL, 10);
+	const size_t size = strlen(argv[2]);
+
+	while (count-- != 0)
+		fwrite(argv[2], 1, size, stdout);
+
+	return !!(ferror(stdout) || fclose(stdout));
+}

debug/sync_flush.c

@@ -0,0 +1,125 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       sync_flush.c
+/// \brief      Encode files using LZMA_SYNC_FLUSH
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "sysdefs.h"
+#include "lzma.h"
+#include <stdio.h>
+
+#define CHUNK 64
+
+
+static lzma_stream strm = LZMA_STREAM_INIT;
+static FILE *file_in;
+
+
+static void
+encode(size_t size, lzma_action action)
+{
+	uint8_t in[CHUNK];
+	uint8_t out[CHUNK];
+	lzma_ret ret;
+
+	do {
+		if (strm.avail_in == 0 && size > 0) {
+			const size_t amount = my_min(size, CHUNK);
+			strm.avail_in = fread(in, 1, amount, file_in);
+			strm.next_in = in;
+			size -= amount; // Intentionally not using avail_in.
+		}
+
+		strm.next_out = out;
+		strm.avail_out = CHUNK;
+
+		ret = lzma_code(&strm, size == 0 ? action : LZMA_RUN);
+
+		if (ret != LZMA_OK && ret != LZMA_STREAM_END) {
+			fprintf(stderr, "%s:%u: %s: ret == %d\n",
+					__FILE__, __LINE__, __func__, ret);
+			exit(1);
+		}
+
+		fwrite(out, 1, CHUNK - strm.avail_out, stdout);
+
+	} while (size > 0 || strm.avail_out == 0);
+
+	if ((action == LZMA_RUN && ret != LZMA_OK)
+			|| (action != LZMA_RUN && ret != LZMA_STREAM_END)) {
+		fprintf(stderr, "%s:%u: %s: ret == %d\n",
+				__FILE__, __LINE__, __func__, ret);
+		exit(1);
+	}
+}
+
+
+int
+main(int argc, char **argv)
+{
+	file_in = argc > 1 ? fopen(argv[1], "rb") : stdin;
+
+	// Config
+	lzma_options_lzma opt_lzma = {
+		.dict_size = 1U << 16,
+		.lc = LZMA_LC_DEFAULT,
+		.lp = LZMA_LP_DEFAULT,
+		.pb = LZMA_PB_DEFAULT,
+		.preset_dict = NULL,
+		.mode = LZMA_MODE_NORMAL,
+		.nice_len = 32,
+		.mf = LZMA_MF_HC3,
+		.depth = 0,
+	};
+
+	lzma_options_delta opt_delta = {
+		.dist = 16
+	};
+
+	lzma_filter filters[LZMA_FILTERS_MAX + 1];
+	filters[0].id = LZMA_FILTER_LZMA2;
+	filters[0].options = &opt_lzma;
+	filters[1].id = LZMA_VLI_UNKNOWN;
+
+	// Init
+	if (lzma_stream_encoder(&strm, filters, LZMA_CHECK_CRC32) != LZMA_OK) {
+		fprintf(stderr, "init failed\n");
+		exit(1);
+	}
+
+	// Encoding
+	encode(0, LZMA_SYNC_FLUSH);
+	encode(6, LZMA_SYNC_FLUSH);
+	encode(0, LZMA_SYNC_FLUSH);
+	encode(7, LZMA_SYNC_FLUSH);
+	encode(0, LZMA_SYNC_FLUSH);
+	encode(0, LZMA_FINISH);
+
+/*
+	encode(53, LZMA_SYNC_FLUSH);
+	opt_lzma.lc = 2;
+	opt_lzma.lp = 1;
+	opt_lzma.pb = 0;
+	if (lzma_filters_update(&strm, filters) != LZMA_OK) {
+		fprintf(stderr, "update failed\n");
+		exit(1);
+	}
+	encode(404, LZMA_FINISH);
+*/
+
+	// Clean up
+	lzma_end(&strm);
+
+	return 0;
+
+	// Prevent useless warnings so we don't need to have special CFLAGS
+	// to disable -Werror.
+	(void)opt_lzma;
+	(void)opt_delta;
+}

debug/translation.bash

@@ -0,0 +1,100 @@
+#!/bin/bash
+
+###############################################################################
+#
+# Script to check output of some translated messages
+#
+# This should be useful for translators to check that the translated strings
+# look good. This doesn't make xz print all possible strings, but it should
+# cover most of the cases where mistakes can easily happen.
+#
+# Give the path and filename of the xz executable as an argument. If no
+# arguments are given, this script uses ../src/xz/xz (relative to the
+# location of this script).
+#
+# You may want to pipe the output of this script to less -S to view the
+# tables printed by xz --list on a 80-column terminal. On the other hand,
+# viewing the other messages may be better without -S.
+#
+###############################################################################
+#
+# Author: Lasse Collin
+#
+# This file has been put into the public domain.
+# You can do whatever you want with this file.
+#
+###############################################################################
+
+set -e
+
+# If an argument was given, use it to set the location of the xz executable.
+unset XZ
+if [ -n "$1" ]; then
+	XZ=$1
+	[ "x${XZ:0:1}" != "x/" ] && XZ="$PWD/$XZ"
+fi
+
+# Locate top_srcdir and go there.
+top_srcdir="$(cd -- "$(dirname -- "$0")" && cd .. && pwd)"
+cd -- "$top_srcdir"
+
+# If XZ wasn't already set, use the default location.
+XZ=${XZ-"$PWD/src/xz/xz"}
+if [ "$(type -t "$XZ" || true)" != "file" ]; then
+	echo "Give the location of the xz executable as an argument" \
+			"to this script."
+	exit 1
+fi
+XZ=$(type -p -- "$XZ")
+
+# Print the xz version and locale information.
+echo "$XZ --version"
+"$XZ" --version
+echo
+if [ -d .git ] && type git > /dev/null 2>&1; then
+	echo "Source code version in $PWD:"
+	git describe --abbrev=4
+fi
+echo
+locale
+echo
+
+# Make the test files directory the current directory.
+cd tests/files
+
+# Put xz in PATH so that argv[0] stays short.
+PATH=${XZ%/*}:$PATH
+
+# Some of the test commands are error messages and thus don't
+# return successfully.
+set +e
+
+for CMD in \
+	"xz --foobarbaz" \
+	"xz --memlimit=123abcd" \
+	"xz --memlimit=40MiB -6 /dev/null" \
+	"xz --memlimit=0 --info-memory" \
+	"xz --memlimit-compress=1234MiB --memlimit-decompress=50MiB --info-memory" \
+	"xz --verbose --verbose /dev/null | cat" \
+	"xz --lzma2=foobarbaz" \
+	"xz --lzma2=foobarbaz=abcd" \
+	"xz --lzma2=mf=abcd" \
+	"xz --lzma2=preset=foobarbaz" \
+	"xz --lzma2=mf=bt4,nice=2" \
+	"xz --lzma2=nice=50000" \
+	"xz --help" \
+	"xz --long-help" \
+	"xz --list good-*lzma2*" \
+	"xz --list good-1-check*" \
+	"xz --list --verbose good-*lzma2*" \
+	"xz --list --verbose good-1-check*" \
+	"xz --list --verbose --verbose good-*lzma2*" \
+	"xz --list --verbose --verbose good-1-check*" \
+	"xz --list --verbose --verbose unsupported-check.xz"
+do
+	echo "-----------------------------------------------------------"
+	echo
+	echo "\$ $CMD"
+	eval "$CMD"
+	echo
+done 2>&1

doc/examples/00_README.txt

@@ -0,0 +1,31 @@
+
+liblzma example programs
+========================
+
+Introduction
+
+    The examples are written so that the same comments aren't
+    repeated (much) in later files.
+
+    On POSIX systems, the examples should build by just typing "make".
+
+    The examples that use stdin or stdout don't set stdin and stdout
+    to binary mode. On systems where it matters (e.g. Windows) it is
+    possible that the examples won't work without modification.
+
+
+List of examples
+
+    01_compress_easy.c                  Multi-call compression using
+                                        a compression preset
+
+    02_decompress.c                     Multi-call decompression
+
+    03_compress_custom.c                Like 01_compress_easy.c but using
+                                        a custom filter chain
+                                        (x86 BCJ + LZMA2)
+
+    04_compress_easy_mt.c               Multi-threaded multi-call
+                                        compression using a compression
+                                        preset
+

doc/examples/01_compress_easy.c

@@ -0,0 +1,297 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       01_compress_easy.c
+/// \brief      Compress from stdin to stdout in multi-call mode
+///
+/// Usage:      ./01_compress_easy PRESET < INFILE > OUTFILE
+///
+/// Example:    ./01_compress_easy 6 < foo > foo.xz
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <lzma.h>
+
+
+static void
+show_usage_and_exit(const char *argv0)
+{
+	fprintf(stderr, "Usage: %s PRESET < INFILE > OUTFILE\n"
+			"PRESET is a number 0-9 and can optionally be "
+			"followed by `e' to indicate extreme preset\n",
+			argv0);
+	exit(EXIT_FAILURE);
+}
+
+
+static uint32_t
+get_preset(int argc, char **argv)
+{
+	// One argument whose first char must be 0-9.
+	if (argc != 2 || argv[1][0] < '0' || argv[1][0] > '9')
+		show_usage_and_exit(argv[0]);
+
+	// Calculate the preste level 0-9.
+	uint32_t preset = argv[1][0] - '0';
+
+	// If there is a second char, it must be 'e'. It will set
+	// the LZMA_PRESET_EXTREME flag.
+	if (argv[1][1] != '\0') {
+		if (argv[1][1] != 'e' || argv[1][2] != '\0')
+			show_usage_and_exit(argv[0]);
+
+		preset |= LZMA_PRESET_EXTREME;
+	}
+
+	return preset;
+}
+
+
+static bool
+init_encoder(lzma_stream *strm, uint32_t preset)
+{
+	// Initialize the encoder using a preset. Set the integrity to check
+	// to CRC64, which is the default in the xz command line tool. If
+	// the .xz file needs to be decompressed with XZ Embedded, use
+	// LZMA_CHECK_CRC32 instead.
+	lzma_ret ret = lzma_easy_encoder(strm, preset, LZMA_CHECK_CRC64);
+
+	// Return successfully if the initialization went fine.
+	if (ret == LZMA_OK)
+		return true;
+
+	// Something went wrong. The possible errors are documented in
+	// lzma/container.h (src/liblzma/api/lzma/container.h in the source
+	// package or e.g. /usr/include/lzma/container.h depending on the
+	// install prefix).
+	const char *msg;
+	switch (ret) {
+	case LZMA_MEM_ERROR:
+		msg = "Memory allocation failed";
+		break;
+
+	case LZMA_OPTIONS_ERROR:
+		msg = "Specified preset is not supported";
+		break;
+
+	case LZMA_UNSUPPORTED_CHECK:
+		msg = "Specified integrity check is not supported";
+		break;
+
+	default:
+		// This is most likely LZMA_PROG_ERROR indicating a bug in
+		// this program or in liblzma. It is inconvenient to have a
+		// separate error message for errors that should be impossible
+		// to occur, but knowing the error code is important for
+		// debugging. That's why it is good to print the error code
+		// at least when there is no good error message to show.
+		msg = "Unknown error, possibly a bug";
+		break;
+	}
+
+	fprintf(stderr, "Error initializing the encoder: %s (error code %u)\n",
+			msg, ret);
+	return false;
+}
+
+
+static bool
+compress(lzma_stream *strm, FILE *infile, FILE *outfile)
+{
+	// This will be LZMA_RUN until the end of the input file is reached.
+	// This tells lzma_code() when there will be no more input.
+	lzma_action action = LZMA_RUN;
+
+	// Buffers to temporarily hold uncompressed input
+	// and compressed output.
+	uint8_t inbuf[BUFSIZ];
+	uint8_t outbuf[BUFSIZ];
+
+	// Initialize the input and output pointers. Initializing next_in
+	// and avail_in isn't really necessary when we are going to encode
+	// just one file since LZMA_STREAM_INIT takes care of initializing
+	// those already. But it doesn't hurt much and it will be needed
+	// if encoding more than one file like we will in 02_decompress.c.
+	//
+	// While we don't care about strm->total_in or strm->total_out in this
+	// example, it is worth noting that initializing the encoder will
+	// always reset total_in and total_out to zero. But the encoder
+	// initialization doesn't touch next_in, avail_in, next_out, or
+	// avail_out.
+	strm->next_in = NULL;
+	strm->avail_in = 0;
+	strm->next_out = outbuf;
+	strm->avail_out = sizeof(outbuf);
+
+	// Loop until the file has been successfully compressed or until
+	// an error occurs.
+	while (true) {
+		// Fill the input buffer if it is empty.
+		if (strm->avail_in == 0 && !feof(infile)) {
+			strm->next_in = inbuf;
+			strm->avail_in = fread(inbuf, 1, sizeof(inbuf),
+					infile);
+
+			if (ferror(infile)) {
+				fprintf(stderr, "Read error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			// Once the end of the input file has been reached,
+			// we need to tell lzma_code() that no more input
+			// will be coming and that it should finish the
+			// encoding.
+			if (feof(infile))
+				action = LZMA_FINISH;
+		}
+
+		// Tell liblzma do the actual encoding.
+		//
+		// This reads up to strm->avail_in bytes of input starting
+		// from strm->next_in. avail_in will be decremented and
+		// next_in incremented by an equal amount to match the
+		// number of input bytes consumed.
+		//
+		// Up to strm->avail_out bytes of compressed output will be
+		// written starting from strm->next_out. avail_out and next_out
+		// will be incremented by an equal amount to match the number
+		// of output bytes written.
+		//
+		// The encoder has to do internal buffering, which means that
+		// it may take quite a bit of input before the same data is
+		// available in compressed form in the output buffer.
+		lzma_ret ret = lzma_code(strm, action);
+
+		// If the output buffer is full or if the compression finished
+		// successfully, write the data from the output buffer to
+		// the output file.
+		if (strm->avail_out == 0 || ret == LZMA_STREAM_END) {
+			// When lzma_code() has returned LZMA_STREAM_END,
+			// the output buffer is likely to be only partially
+			// full. Calculate how much new data there is to
+			// be written to the output file.
+			size_t write_size = sizeof(outbuf) - strm->avail_out;
+
+			if (fwrite(outbuf, 1, write_size, outfile)
+					!= write_size) {
+				fprintf(stderr, "Write error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			// Reset next_out and avail_out.
+			strm->next_out = outbuf;
+			strm->avail_out = sizeof(outbuf);
+		}
+
+		// Normally the return value of lzma_code() will be LZMA_OK
+		// until everything has been encoded.
+		if (ret != LZMA_OK) {
+			// Once everything has been encoded successfully, the
+			// return value of lzma_code() will be LZMA_STREAM_END.
+			//
+			// It is important to check for LZMA_STREAM_END. Do not
+			// assume that getting ret != LZMA_OK would mean that
+			// everything has gone well.
+			if (ret == LZMA_STREAM_END)
+				return true;
+
+			// It's not LZMA_OK nor LZMA_STREAM_END,
+			// so it must be an error code. See lzma/base.h
+			// (src/liblzma/api/lzma/base.h in the source package
+			// or e.g. /usr/include/lzma/base.h depending on the
+			// install prefix) for the list and documentation of
+			// possible values. Most values listen in lzma_ret
+			// enumeration aren't possible in this example.
+			const char *msg;
+			switch (ret) {
+			case LZMA_MEM_ERROR:
+				msg = "Memory allocation failed";
+				break;
+
+			case LZMA_DATA_ERROR:
+				// This error is returned if the compressed
+				// or uncompressed size get near 8 EiB
+				// (2^63 bytes) because that's where the .xz
+				// file format size limits currently are.
+				// That is, the possibility of this error
+				// is mostly theoretical unless you are doing
+				// something very unusual.
+				//
+				// Note that strm->total_in and strm->total_out
+				// have nothing to do with this error. Changing
+				// those variables won't increase or decrease
+				// the chance of getting this error.
+				msg = "File size limits exceeded";
+				break;
+
+			default:
+				// This is most likely LZMA_PROG_ERROR, but
+				// if this program is buggy (or liblzma has
+				// a bug), it may be e.g. LZMA_BUF_ERROR or
+				// LZMA_OPTIONS_ERROR too.
+				//
+				// It is inconvenient to have a separate
+				// error message for errors that should be
+				// impossible to occur, but knowing the error
+				// code is important for debugging. That's why
+				// it is good to print the error code at least
+				// when there is no good error message to show.
+				msg = "Unknown error, possibly a bug";
+				break;
+			}
+
+			fprintf(stderr, "Encoder error: %s (error code %u)\n",
+					msg, ret);
+			return false;
+		}
+	}
+}
+
+
+extern int
+main(int argc, char **argv)
+{
+	// Get the preset number from the command line.
+	uint32_t preset = get_preset(argc, argv);
+
+	// Initialize a lzma_stream structure. When it is allocated on stack,
+	// it is simplest to use LZMA_STREAM_INIT macro like below. When it
+	// is allocated on heap, using memset(strmptr, 0, sizeof(*strmptr))
+	// works (as long as NULL pointers are represented with zero bits
+	// as they are on practically all computers today).
+	lzma_stream strm = LZMA_STREAM_INIT;
+
+	// Initialize the encoder. If it succeeds, compress from
+	// stdin to stdout.
+	bool success = init_encoder(&strm, preset);
+	if (success)
+		success = compress(&strm, stdin, stdout);
+
+	// Free the memory allocated for the encoder. If we were encoding
+	// multiple files, this would only need to be done after the last
+	// file. See 02_decompress.c for handling of multiple files.
+	//
+	// It is OK to call lzma_end() multiple times or when it hasn't been
+	// actually used except initialized with LZMA_STREAM_INIT.
+	lzma_end(&strm);
+
+	// Close stdout to catch possible write errors that can occur
+	// when pending data is flushed from the stdio buffers.
+	if (fclose(stdout)) {
+		fprintf(stderr, "Write error: %s\n", strerror(errno));
+		success = false;
+	}
+
+	return success ? EXIT_SUCCESS : EXIT_FAILURE;
+}

doc/examples/02_decompress.c

@@ -0,0 +1,287 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       02_decompress.c
+/// \brief      Decompress .xz files to stdout
+///
+/// Usage:      ./02_decompress INPUT_FILES... > OUTFILE
+///
+/// Example:    ./02_decompress foo.xz bar.xz > foobar
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <lzma.h>
+
+
+static bool
+init_decoder(lzma_stream *strm)
+{
+	// Initialize a .xz decoder. The decoder supports a memory usage limit
+	// and a set of flags.
+	//
+	// The memory usage of the decompressor depends on the settings used
+	// to compress a .xz file. It can vary from less than a megabyte to
+	// a few gigabytes, but in practice (at least for now) it rarely
+	// exceeds 65 MiB because that's how much memory is required to
+	// decompress files created with "xz -9". Settings requiring more
+	// memory take extra effort to use and don't (at least for now)
+	// provide significantly better compression in most cases.
+	//
+	// Memory usage limit is useful if it is important that the
+	// decompressor won't consume gigabytes of memory. The need
+	// for limiting depends on the application. In this example,
+	// no memory usage limiting is used. This is done by setting
+	// the limit to UINT64_MAX.
+	//
+	// The .xz format allows concatenating compressed files as is:
+	//
+	//     echo foo | xz > foobar.xz
+	//     echo bar | xz >> foobar.xz
+	//
+	// When decompressing normal standalone .xz files, LZMA_CONCATENATED
+	// should always be used to support decompression of concatenated
+	// .xz files. If LZMA_CONCATENATED isn't used, the decoder will stop
+	// after the first .xz stream. This can be useful when .xz data has
+	// been embedded inside another file format.
+	//
+	// Flags other than LZMA_CONCATENATED are supported too, and can
+	// be combined with bitwise-or. See lzma/container.h
+	// (src/liblzma/api/lzma/container.h in the source package or e.g.
+	// /usr/include/lzma/container.h depending on the install prefix)
+	// for details.
+	lzma_ret ret = lzma_stream_decoder(
+			strm, UINT64_MAX, LZMA_CONCATENATED);
+
+	// Return successfully if the initialization went fine.
+	if (ret == LZMA_OK)
+		return true;
+
+	// Something went wrong. The possible errors are documented in
+	// lzma/container.h (src/liblzma/api/lzma/container.h in the source
+	// package or e.g. /usr/include/lzma/container.h depending on the
+	// install prefix).
+	//
+	// Note that LZMA_MEMLIMIT_ERROR is never possible here. If you
+	// specify a very tiny limit, the error will be delayed until
+	// the first headers have been parsed by a call to lzma_code().
+	const char *msg;
+	switch (ret) {
+	case LZMA_MEM_ERROR:
+		msg = "Memory allocation failed";
+		break;
+
+	case LZMA_OPTIONS_ERROR:
+		msg = "Unsupported decompressor flags";
+		break;
+
+	default:
+		// This is most likely LZMA_PROG_ERROR indicating a bug in
+		// this program or in liblzma. It is inconvenient to have a
+		// separate error message for errors that should be impossible
+		// to occur, but knowing the error code is important for
+		// debugging. That's why it is good to print the error code
+		// at least when there is no good error message to show.
+		msg = "Unknown error, possibly a bug";
+		break;
+	}
+
+	fprintf(stderr, "Error initializing the decoder: %s (error code %u)\n",
+			msg, ret);
+	return false;
+}
+
+
+static bool
+decompress(lzma_stream *strm, const char *inname, FILE *infile, FILE *outfile)
+{
+	// When LZMA_CONCATENATED flag was used when initializing the decoder,
+	// we need to tell lzma_code() when there will be no more input.
+	// This is done by setting action to LZMA_FINISH instead of LZMA_RUN
+	// in the same way as it is done when encoding.
+	//
+	// When LZMA_CONCATENATED isn't used, there is no need to use
+	// LZMA_FINISH to tell when all the input has been read, but it
+	// is still OK to use it if you want. When LZMA_CONCATENATED isn't
+	// used, the decoder will stop after the first .xz stream. In that
+	// case some unused data may be left in strm->next_in.
+	lzma_action action = LZMA_RUN;
+
+	uint8_t inbuf[BUFSIZ];
+	uint8_t outbuf[BUFSIZ];
+
+	strm->next_in = NULL;
+	strm->avail_in = 0;
+	strm->next_out = outbuf;
+	strm->avail_out = sizeof(outbuf);
+
+	while (true) {
+		if (strm->avail_in == 0 && !feof(infile)) {
+			strm->next_in = inbuf;
+			strm->avail_in = fread(inbuf, 1, sizeof(inbuf),
+					infile);
+
+			if (ferror(infile)) {
+				fprintf(stderr, "%s: Read error: %s\n",
+						inname, strerror(errno));
+				return false;
+			}
+
+			// Once the end of the input file has been reached,
+			// we need to tell lzma_code() that no more input
+			// will be coming. As said before, this isn't required
+			// if the LZMA_CONCATENATED flag isn't used when
+			// initializing the decoder.
+			if (feof(infile))
+				action = LZMA_FINISH;
+		}
+
+		lzma_ret ret = lzma_code(strm, action);
+
+		if (strm->avail_out == 0 || ret == LZMA_STREAM_END) {
+			size_t write_size = sizeof(outbuf) - strm->avail_out;
+
+			if (fwrite(outbuf, 1, write_size, outfile)
+					!= write_size) {
+				fprintf(stderr, "Write error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			strm->next_out = outbuf;
+			strm->avail_out = sizeof(outbuf);
+		}
+
+		if (ret != LZMA_OK) {
+			// Once everything has been decoded successfully, the
+			// return value of lzma_code() will be LZMA_STREAM_END.
+			//
+			// It is important to check for LZMA_STREAM_END. Do not
+			// assume that getting ret != LZMA_OK would mean that
+			// everything has gone well or that when you aren't
+			// getting more output it must have successfully
+			// decoded everything.
+			if (ret == LZMA_STREAM_END)
+				return true;
+
+			// It's not LZMA_OK nor LZMA_STREAM_END,
+			// so it must be an error code. See lzma/base.h
+			// (src/liblzma/api/lzma/base.h in the source package
+			// or e.g. /usr/include/lzma/base.h depending on the
+			// install prefix) for the list and documentation of
+			// possible values. Many values listen in lzma_ret
+			// enumeration aren't possible in this example, but
+			// can be made possible by enabling memory usage limit
+			// or adding flags to the decoder initialization.
+			const char *msg;
+			switch (ret) {
+			case LZMA_MEM_ERROR:
+				msg = "Memory allocation failed";
+				break;
+
+			case LZMA_FORMAT_ERROR:
+				// .xz magic bytes weren't found.
+				msg = "The input is not in the .xz format";
+				break;
+
+			case LZMA_OPTIONS_ERROR:
+				// For example, the headers specify a filter
+				// that isn't supported by this liblzma
+				// version (or it hasn't been enabled when
+				// building liblzma, but no-one sane does
+				// that unless building liblzma for an
+				// embedded system). Upgrading to a newer
+				// liblzma might help.
+				//
+				// Note that it is unlikely that the file has
+				// accidentally became corrupt if you get this
+				// error. The integrity of the .xz headers is
+				// always verified with a CRC32, so
+				// unintentionally corrupt files can be
+				// distinguished from unsupported files.
+				msg = "Unsupported compression options";
+				break;
+
+			case LZMA_DATA_ERROR:
+				msg = "Compressed file is corrupt";
+				break;
+
+			case LZMA_BUF_ERROR:
+				// Typically this error means that a valid
+				// file has got truncated, but it might also
+				// be a damaged part in the file that makes
+				// the decoder think the file is truncated.
+				// If you prefer, you can use the same error
+				// message for this as for LZMA_DATA_ERROR.
+				msg = "Compressed file is truncated or "
+						"otherwise corrupt";
+				break;
+
+			default:
+				// This is most likely LZMA_PROG_ERROR.
+				msg = "Unknown error, possibly a bug";
+				break;
+			}
+
+			fprintf(stderr, "%s: Decoder error: "
+					"%s (error code %u)\n",
+					inname, msg, ret);
+			return false;
+		}
+	}
+}
+
+
+extern int
+main(int argc, char **argv)
+{
+	if (argc <= 1) {
+		fprintf(stderr, "Usage: %s FILES...\n", argv[0]);
+		return EXIT_FAILURE;
+	}
+
+	lzma_stream strm = LZMA_STREAM_INIT;
+
+	bool success = true;
+
+	// Try to decompress all files.
+	for (int i = 1; i < argc; ++i) {
+		if (!init_decoder(&strm)) {
+			// Decoder initialization failed. There's no point
+			// to retry it so we need to exit.
+			success = false;
+			break;
+		}
+
+		FILE *infile = fopen(argv[i], "rb");
+
+		if (infile == NULL) {
+			fprintf(stderr, "%s: Error opening the "
+					"input file: %s\n",
+					argv[i], strerror(errno));
+			success = false;
+		} else {
+			success &= decompress(&strm, argv[i], infile, stdout);
+			fclose(infile);
+		}
+	}
+
+	// Free the memory allocated for the decoder. This only needs to be
+	// done after the last file.
+	lzma_end(&strm);
+
+	if (fclose(stdout)) {
+		fprintf(stderr, "Write error: %s\n", strerror(errno));
+		success = false;
+	}
+
+	return success ? EXIT_SUCCESS : EXIT_FAILURE;
+}

doc/examples/03_compress_custom.c

@@ -0,0 +1,193 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       03_compress_custom.c
+/// \brief      Compress in multi-call mode using x86 BCJ and LZMA2
+///
+/// Usage:      ./03_compress_custom < INFILE > OUTFILE
+///
+/// Example:    ./03_compress_custom < foo > foo.xz
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <lzma.h>
+
+
+static bool
+init_encoder(lzma_stream *strm)
+{
+	// Use the default preset (6) for LZMA2.
+	//
+	// The lzma_options_lzma structure and the lzma_lzma_preset() function
+	// are declared in lzma/lzma12.h (src/liblzma/api/lzma/lzma12.h in the
+	// source package or e.g. /usr/include/lzma/lzma12.h depending on
+	// the install prefix).
+	lzma_options_lzma opt_lzma2;
+	if (lzma_lzma_preset(&opt_lzma2, LZMA_PRESET_DEFAULT)) {
+		// It should never fail because the default preset
+		// (and presets 0-9 optionally with LZMA_PRESET_EXTREME)
+		// are supported by all stable liblzma versions.
+		//
+		// (The encoder initialization later in this function may
+		// still fail due to unsupported preset *if* the features
+		// required by the preset have been disabled at build time,
+		// but no-one does such things except on embedded systems.)
+		fprintf(stderr, "Unsupported preset, possibly a bug\n");
+		return false;
+	}
+
+	// Now we could customize the LZMA2 options if we wanted. For example,
+	// we could set the the dictionary size (opt_lzma2.dict_size) to
+	// something else than the default (8 MiB) of the default preset.
+	// See lzma/lzma12.h for details of all LZMA2 options.
+	//
+	// The x86 BCJ filter will try to modify the x86 instruction stream so
+	// that LZMA2 can compress it better. The x86 BCJ filter doesn't need
+	// any options so it will be set to NULL below.
+	//
+	// Construct the filter chain. The uncompressed data goes first to
+	// the first filter in the array, in this case the x86 BCJ filter.
+	// The array is always terminated by setting .id = LZMA_VLI_UNKNOWN.
+	//
+	// See lzma/filter.h for more information about the lzma_filter
+	// structure.
+	lzma_filter filters[] = {
+		{ .id = LZMA_FILTER_X86, .options = NULL },
+		{ .id = LZMA_FILTER_LZMA2, .options = &opt_lzma2 },
+		{ .id = LZMA_VLI_UNKNOWN, .options = NULL },
+	};
+
+	// Initialize the encoder using the custom filter chain.
+	lzma_ret ret = lzma_stream_encoder(strm, filters, LZMA_CHECK_CRC64);
+
+	if (ret == LZMA_OK)
+		return true;
+
+	const char *msg;
+	switch (ret) {
+	case LZMA_MEM_ERROR:
+		msg = "Memory allocation failed";
+		break;
+
+	case LZMA_OPTIONS_ERROR:
+		// We are no longer using a plain preset so this error
+		// message has been edited accordingly compared to
+		// 01_compress_easy.c.
+		msg = "Specified filter chain is not supported";
+		break;
+
+	case LZMA_UNSUPPORTED_CHECK:
+		msg = "Specified integrity check is not supported";
+		break;
+
+	default:
+		msg = "Unknown error, possibly a bug";
+		break;
+	}
+
+	fprintf(stderr, "Error initializing the encoder: %s (error code %u)\n",
+			msg, ret);
+	return false;
+}
+
+
+// This function is identical to the one in 01_compress_easy.c.
+static bool
+compress(lzma_stream *strm, FILE *infile, FILE *outfile)
+{
+	lzma_action action = LZMA_RUN;
+
+	uint8_t inbuf[BUFSIZ];
+	uint8_t outbuf[BUFSIZ];
+
+	strm->next_in = NULL;
+	strm->avail_in = 0;
+	strm->next_out = outbuf;
+	strm->avail_out = sizeof(outbuf);
+
+	while (true) {
+		if (strm->avail_in == 0 && !feof(infile)) {
+			strm->next_in = inbuf;
+			strm->avail_in = fread(inbuf, 1, sizeof(inbuf),
+					infile);
+
+			if (ferror(infile)) {
+				fprintf(stderr, "Read error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			if (feof(infile))
+				action = LZMA_FINISH;
+		}
+
+		lzma_ret ret = lzma_code(strm, action);
+
+		if (strm->avail_out == 0 || ret == LZMA_STREAM_END) {
+			size_t write_size = sizeof(outbuf) - strm->avail_out;
+
+			if (fwrite(outbuf, 1, write_size, outfile)
+					!= write_size) {
+				fprintf(stderr, "Write error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			strm->next_out = outbuf;
+			strm->avail_out = sizeof(outbuf);
+		}
+
+		if (ret != LZMA_OK) {
+			if (ret == LZMA_STREAM_END)
+				return true;
+
+			const char *msg;
+			switch (ret) {
+			case LZMA_MEM_ERROR:
+				msg = "Memory allocation failed";
+				break;
+
+			case LZMA_DATA_ERROR:
+				msg = "File size limits exceeded";
+				break;
+
+			default:
+				msg = "Unknown error, possibly a bug";
+				break;
+			}
+
+			fprintf(stderr, "Encoder error: %s (error code %u)\n",
+					msg, ret);
+			return false;
+		}
+	}
+}
+
+
+extern int
+main(void)
+{
+	lzma_stream strm = LZMA_STREAM_INIT;
+
+	bool success = init_encoder(&strm);
+	if (success)
+		success = compress(&strm, stdin, stdout);
+
+	lzma_end(&strm);
+
+	if (fclose(stdout)) {
+		fprintf(stderr, "Write error: %s\n", strerror(errno));
+		success = false;
+	}
+
+	return success ? EXIT_SUCCESS : EXIT_FAILURE;
+}

doc/examples/04_compress_easy_mt.c

@@ -0,0 +1,206 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       04_compress_easy_mt.c
+/// \brief      Compress in multi-call mode using LZMA2 in multi-threaded mode
+///
+/// Usage:      ./04_compress_easy_mt < INFILE > OUTFILE
+///
+/// Example:    ./04_compress_easy_mt < foo > foo.xz
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <lzma.h>
+
+
+static bool
+init_encoder(lzma_stream *strm)
+{
+	// The threaded encoder takes the options as pointer to
+	// a lzma_mt structure.
+	lzma_mt mt = {
+		// No flags are needed.
+		.flags = 0,
+
+		// Let liblzma determine a sane block size.
+		.block_size = 0,
+
+		// Use no timeout for lzma_code() calls by setting timeout
+		// to zero. That is, sometimes lzma_code() might block for
+		// a long time (from several seconds to even minutes).
+		// If this is not OK, for example due to progress indicator
+		// needing updates, specify a timeout in milliseconds here.
+		// See the documentation of lzma_mt in lzma/container.h for
+		// information how to choose a reasonable timeout.
+		.timeout = 0,
+
+		// Use the default preset (6) for LZMA2.
+		// To use a preset, filters must be set to NULL.
+		.preset = LZMA_PRESET_DEFAULT,
+		.filters = NULL,
+
+		// Use CRC64 for integrity checking. See also
+		// 01_compress_easy.c about choosing the integrity check.
+		.check = LZMA_CHECK_CRC64,
+	};
+
+	// Detect how many threads the CPU supports.
+	mt.threads = lzma_cputhreads();
+
+	// If the number of CPU cores/threads cannot be detected,
+	// use one thread. Note that this isn't the same as the normal
+	// single-threaded mode as this will still split the data into
+	// blocks and use more RAM than the normal single-threaded mode.
+	// You may want to consider using lzma_easy_encoder() or
+	// lzma_stream_encoder() instead of lzma_stream_encoder_mt() if
+	// lzma_cputhreads() returns 0 or 1.
+	if (mt.threads == 0)
+		mt.threads = 1;
+
+	// If the number of CPU cores/threads exceeds threads_max,
+	// limit the number of threads to keep memory usage lower.
+	// The number 8 is arbitrarily chosen and may be too low or
+	// high depending on the compression preset and the computer
+	// being used.
+	//
+	// FIXME: A better way could be to check the amount of RAM
+	// (or available RAM) and use lzma_stream_encoder_mt_memusage()
+	// to determine if the number of threads should be reduced.
+	const uint32_t threads_max = 8;
+	if (mt.threads > threads_max)
+		mt.threads = threads_max;
+
+	// Initialize the threaded encoder.
+	lzma_ret ret = lzma_stream_encoder_mt(strm, &mt);
+
+	if (ret == LZMA_OK)
+		return true;
+
+	const char *msg;
+	switch (ret) {
+	case LZMA_MEM_ERROR:
+		msg = "Memory allocation failed";
+		break;
+
+	case LZMA_OPTIONS_ERROR:
+		// We are no longer using a plain preset so this error
+		// message has been edited accordingly compared to
+		// 01_compress_easy.c.
+		msg = "Specified filter chain is not supported";
+		break;
+
+	case LZMA_UNSUPPORTED_CHECK:
+		msg = "Specified integrity check is not supported";
+		break;
+
+	default:
+		msg = "Unknown error, possibly a bug";
+		break;
+	}
+
+	fprintf(stderr, "Error initializing the encoder: %s (error code %u)\n",
+			msg, ret);
+	return false;
+}
+
+
+// This function is identical to the one in 01_compress_easy.c.
+static bool
+compress(lzma_stream *strm, FILE *infile, FILE *outfile)
+{
+	lzma_action action = LZMA_RUN;
+
+	uint8_t inbuf[BUFSIZ];
+	uint8_t outbuf[BUFSIZ];
+
+	strm->next_in = NULL;
+	strm->avail_in = 0;
+	strm->next_out = outbuf;
+	strm->avail_out = sizeof(outbuf);
+
+	while (true) {
+		if (strm->avail_in == 0 && !feof(infile)) {
+			strm->next_in = inbuf;
+			strm->avail_in = fread(inbuf, 1, sizeof(inbuf),
+					infile);
+
+			if (ferror(infile)) {
+				fprintf(stderr, "Read error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			if (feof(infile))
+				action = LZMA_FINISH;
+		}
+
+		lzma_ret ret = lzma_code(strm, action);
+
+		if (strm->avail_out == 0 || ret == LZMA_STREAM_END) {
+			size_t write_size = sizeof(outbuf) - strm->avail_out;
+
+			if (fwrite(outbuf, 1, write_size, outfile)
+					!= write_size) {
+				fprintf(stderr, "Write error: %s\n",
+						strerror(errno));
+				return false;
+			}
+
+			strm->next_out = outbuf;
+			strm->avail_out = sizeof(outbuf);
+		}
+
+		if (ret != LZMA_OK) {
+			if (ret == LZMA_STREAM_END)
+				return true;
+
+			const char *msg;
+			switch (ret) {
+			case LZMA_MEM_ERROR:
+				msg = "Memory allocation failed";
+				break;
+
+			case LZMA_DATA_ERROR:
+				msg = "File size limits exceeded";
+				break;
+
+			default:
+				msg = "Unknown error, possibly a bug";
+				break;
+			}
+
+			fprintf(stderr, "Encoder error: %s (error code %u)\n",
+					msg, ret);
+			return false;
+		}
+	}
+}
+
+
+extern int
+main(void)
+{
+	lzma_stream strm = LZMA_STREAM_INIT;
+
+	bool success = init_encoder(&strm);
+	if (success)
+		success = compress(&strm, stdin, stdout);
+
+	lzma_end(&strm);
+
+	if (fclose(stdout)) {
+		fprintf(stderr, "Write error: %s\n", strerror(errno));
+		success = false;
+	}
+
+	return success ? EXIT_SUCCESS : EXIT_FAILURE;
+}

doc/examples_old/xz_pipe_comp.c

@@ -0,0 +1,127 @@
+/*
+ * xz_pipe_comp.c
+ * A simple example of pipe-only xz compressor implementation.
+ * version: 2010-07-12 - by Daniel Mealha Cabrita
+ * Not copyrighted -- provided to the public domain.
+ *
+ * Compiling:
+ * Link with liblzma. GCC example:
+ * $ gcc -llzma xz_pipe_comp.c -o xz_pipe_comp
+ *
+ * Usage example:
+ * $ cat some_file | ./xz_pipe_comp > some_file.xz
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <lzma.h>
+
+
+/* COMPRESSION SETTINGS */
+
+/* analogous to xz CLI options: -0 to -9 */
+#define COMPRESSION_LEVEL 6
+
+/* boolean setting, analogous to xz CLI option: -e */
+#define COMPRESSION_EXTREME true
+
+/* see: /usr/include/lzma/check.h LZMA_CHECK_* */
+#define INTEGRITY_CHECK LZMA_CHECK_CRC64
+
+
+/* read/write buffer sizes */
+#define IN_BUF_MAX	4096
+#define OUT_BUF_MAX	4096
+
+/* error codes */
+#define RET_OK			0
+#define RET_ERROR_INIT		1
+#define RET_ERROR_INPUT		2
+#define RET_ERROR_OUTPUT	3
+#define RET_ERROR_COMPRESSION	4
+
+
+/* note: in_file and out_file must be open already */
+int xz_compress (FILE *in_file, FILE *out_file)
+{
+	uint32_t preset = COMPRESSION_LEVEL | (COMPRESSION_EXTREME ? LZMA_PRESET_EXTREME : 0);
+	lzma_check check = INTEGRITY_CHECK;
+	lzma_stream strm = LZMA_STREAM_INIT; /* alloc and init lzma_stream struct */
+	uint8_t in_buf [IN_BUF_MAX];
+	uint8_t out_buf [OUT_BUF_MAX];
+	size_t in_len;	/* length of useful data in in_buf */
+	size_t out_len;	/* length of useful data in out_buf */
+	bool in_finished = false;
+	bool out_finished = false;
+	lzma_action action;
+	lzma_ret ret_xz;
+	int ret;
+
+	ret = RET_OK;
+
+	/* initialize xz encoder */
+	ret_xz = lzma_easy_encoder (&strm, preset, check);
+	if (ret_xz != LZMA_OK) {
+		fprintf (stderr, "lzma_easy_encoder error: %d\n", (int) ret_xz);
+		return RET_ERROR_INIT;
+	}
+
+	while ((! in_finished) && (! out_finished)) {
+		/* read incoming data */
+		in_len = fread (in_buf, 1, IN_BUF_MAX, in_file);
+
+		if (feof (in_file)) {
+			in_finished = true;
+		}
+		if (ferror (in_file)) {
+			in_finished = true;
+			ret = RET_ERROR_INPUT;
+		}
+
+		strm.next_in = in_buf;
+		strm.avail_in = in_len;
+
+		/* if no more data from in_buf, flushes the
+		   internal xz buffers and closes the xz data
+		   with LZMA_FINISH */
+		action = in_finished ? LZMA_FINISH : LZMA_RUN;
+
+		/* loop until there's no pending compressed output */
+		do {
+			/* out_buf is clean at this point */
+			strm.next_out = out_buf;
+			strm.avail_out = OUT_BUF_MAX;
+
+			/* compress data */
+			ret_xz = lzma_code (&strm, action);
+
+			if ((ret_xz != LZMA_OK) && (ret_xz != LZMA_STREAM_END)) {
+				fprintf (stderr, "lzma_code error: %d\n", (int) ret_xz);
+				out_finished = true;
+				ret = RET_ERROR_COMPRESSION;
+			} else {
+				/* write compressed data */
+				out_len = OUT_BUF_MAX - strm.avail_out;
+				fwrite (out_buf, 1, out_len, out_file);
+				if (ferror (out_file)) {
+					out_finished = true;
+					ret = RET_ERROR_OUTPUT;
+				}
+			}
+		} while (strm.avail_out == 0);
+	}
+
+	lzma_end (&strm);
+	return ret;
+}
+
+int main ()
+{
+	int ret;
+
+	ret = xz_compress (stdin, stdout);
+	return ret;
+}
+

doc/examples_old/xz_pipe_decomp.c

@@ -0,0 +1,123 @@
+/*
+ * xz_pipe_decomp.c
+ * A simple example of pipe-only xz decompressor implementation.
+ * version: 2012-06-14 - by Daniel Mealha Cabrita
+ * Not copyrighted -- provided to the public domain.
+ *
+ * Compiling:
+ * Link with liblzma. GCC example:
+ * $ gcc -llzma xz_pipe_decomp.c -o xz_pipe_decomp
+ *
+ * Usage example:
+ * $ cat some_file.xz | ./xz_pipe_decomp > some_file
+ */
+
+#include <stdio.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <lzma.h>
+
+
+/* read/write buffer sizes */
+#define IN_BUF_MAX	4096
+#define OUT_BUF_MAX	4096
+
+/* error codes */
+#define RET_OK			0
+#define RET_ERROR_INIT		1
+#define RET_ERROR_INPUT		2
+#define RET_ERROR_OUTPUT	3
+#define RET_ERROR_DECOMPRESSION	4
+
+
+/* note: in_file and out_file must be open already */
+int xz_decompress (FILE *in_file, FILE *out_file)
+{
+	lzma_stream strm = LZMA_STREAM_INIT; /* alloc and init lzma_stream struct */
+	const uint32_t flags = LZMA_TELL_UNSUPPORTED_CHECK | LZMA_CONCATENATED;
+	const uint64_t memory_limit = UINT64_MAX; /* no memory limit */
+	uint8_t in_buf [IN_BUF_MAX];
+	uint8_t out_buf [OUT_BUF_MAX];
+	size_t in_len;	/* length of useful data in in_buf */
+	size_t out_len;	/* length of useful data in out_buf */
+	bool in_finished = false;
+	bool out_finished = false;
+	lzma_action action;
+	lzma_ret ret_xz;
+	int ret;
+
+	ret = RET_OK;
+
+	/* initialize xz decoder */
+	ret_xz = lzma_stream_decoder (&strm, memory_limit, flags);
+	if (ret_xz != LZMA_OK) {
+		fprintf (stderr, "lzma_stream_decoder error: %d\n", (int) ret_xz);
+		return RET_ERROR_INIT;
+	}
+
+	while ((! in_finished) && (! out_finished)) {
+		/* read incoming data */
+		in_len = fread (in_buf, 1, IN_BUF_MAX, in_file);
+
+		if (feof (in_file)) {
+			in_finished = true;
+		}
+		if (ferror (in_file)) {
+			in_finished = true;
+			ret = RET_ERROR_INPUT;
+		}
+
+		strm.next_in = in_buf;
+		strm.avail_in = in_len;
+
+		/* if no more data from in_buf, flushes the
+		   internal xz buffers and closes the decompressed data
+		   with LZMA_FINISH */
+		action = in_finished ? LZMA_FINISH : LZMA_RUN;
+
+		/* loop until there's no pending decompressed output */
+		do {
+			/* out_buf is clean at this point */
+			strm.next_out = out_buf;
+			strm.avail_out = OUT_BUF_MAX;
+
+			/* decompress data */
+			ret_xz = lzma_code (&strm, action);
+
+			if ((ret_xz != LZMA_OK) && (ret_xz != LZMA_STREAM_END)) {
+				fprintf (stderr, "lzma_code error: %d\n", (int) ret_xz);
+				out_finished = true;
+				ret = RET_ERROR_DECOMPRESSION;
+			} else {
+				/* write decompressed data */
+				out_len = OUT_BUF_MAX - strm.avail_out;
+				fwrite (out_buf, 1, out_len, out_file);
+				if (ferror (out_file)) {
+					out_finished = true;
+					ret = RET_ERROR_OUTPUT;
+				}
+			}
+		} while (strm.avail_out == 0);
+	}
+
+	/* Bug fix (2012-06-14): If no errors were detected, check
+	   that the last lzma_code() call returned LZMA_STREAM_END.
+	   If not, the file is probably truncated. */
+	if ((ret == RET_OK) && (ret_xz != LZMA_STREAM_END)) {
+		fprintf (stderr, "Input truncated or corrupt\n");
+		ret = RET_ERROR_DECOMPRESSION;
+	}
+
+	lzma_end (&strm);
+	return ret;
+}
+
+int main ()
+{
+	int ret;
+
+	ret = xz_decompress (stdin, stdout);
+	return ret;
+}
+

doc/faq.txt

@@ -0,0 +1,244 @@
+
+XZ Utils FAQ
+============
+
+Q:  What do the letters XZ mean?
+
+A:  Nothing. They are just two letters, which come from the file format
+    suffix .xz. The .xz suffix was selected, because it seemed to be
+    pretty much unused. It has no deeper meaning.
+
+
+Q:  What are LZMA and LZMA2?
+
+A:  LZMA stands for Lempel-Ziv-Markov chain-Algorithm. It is the name
+    of the compression algorithm designed by Igor Pavlov for 7-Zip.
+    LZMA is based on LZ77 and range encoding.
+
+    LZMA2 is an updated version of the original LZMA to fix a couple of
+    practical issues. In context of XZ Utils, LZMA is called LZMA1 to
+    emphasize that LZMA is not the same thing as LZMA2. LZMA2 is the
+    primary compression algorithm in the .xz file format.
+
+
+Q:  There are many LZMA related projects. How does XZ Utils relate to them?
+
+A:  7-Zip and LZMA SDK are the original projects. LZMA SDK is roughly
+    a subset of the 7-Zip source tree.
+
+    p7zip is 7-Zip's command-line tools ported to POSIX-like systems.
+
+    LZMA Utils provide a gzip-like lzma tool for POSIX-like systems.
+    LZMA Utils are based on LZMA SDK. XZ Utils are the successor to
+    LZMA Utils.
+
+    There are several other projects using LZMA. Most are more or less
+    based on LZMA SDK. See <https://7-zip.org/links.html>.
+
+
+Q:  Why is liblzma named liblzma if its primary file format is .xz?
+    Shouldn't it be e.g. libxz?
+
+A:  When the designing of the .xz format began, the idea was to replace
+    the .lzma format and use the same .lzma suffix. It would have been
+    quite OK to reuse the suffix when there were very few .lzma files
+    around. However, the old .lzma format became popular before the
+    new format was finished. The new format was renamed to .xz but the
+    name of liblzma wasn't changed.
+
+
+Q:  Do XZ Utils support the .7z format?
+
+A:  No. Use 7-Zip (Windows) or p7zip (POSIX-like systems) to handle .7z
+    files.
+
+
+Q:  I have many .tar.7z files. Can I convert them to .tar.xz without
+    spending hours recompressing the data?
+
+A:  In the "extra" directory, there is a script named 7z2lzma.bash which
+    is able to convert some .7z files to the .lzma format (not .xz). It
+    needs the 7za (or 7z) command from p7zip. The script may silently
+    produce corrupt output if certain assumptions are not met, so
+    decompress the resulting .lzma file and compare it against the
+    original before deleting the original file!
+
+
+Q:  I have many .lzma files. Can I quickly convert them to the .xz format?
+
+A:  For now, no. Since XZ Utils supports the .lzma format, it's usually
+    not too bad to keep the old files in the old format. If you want to
+    do the conversion anyway, you need to decompress the .lzma files and
+    then recompress to the .xz format.
+
+    Technically, there is a way to make the conversion relatively fast
+    (roughly twice the time that normal decompression takes). Writing
+    such a tool would take quite a bit of time though, and would probably
+    be useful to only a few people. If you really want such a conversion
+    tool, contact Lasse Collin and offer some money.
+
+
+Q:  I have installed xz, but my tar doesn't recognize .tar.xz files.
+    How can I extract .tar.xz files?
+
+A:  xz -dc foo.tar.xz | tar xf -
+
+
+Q:  Can I recover parts of a broken .xz file (e.g. a corrupted CD-R)?
+
+A:  It may be possible if the file consists of multiple blocks, which
+    typically is not the case if the file was created in single-threaded
+    mode. There is no recovery program yet.
+
+
+Q:  Is (some part of) XZ Utils patented?
+
+A:  Lasse Collin is not aware of any patents that could affect XZ Utils.
+    However, due to the nature of software patents, it's not possible to
+    guarantee that XZ Utils isn't affected by any third party patent(s).
+
+
+Q:  Where can I find documentation about the file format and algorithms?
+
+A:  The .xz format is documented in xz-file-format.txt. It is a container
+    format only, and doesn't include descriptions of any non-trivial
+    filters.
+
+    Documenting LZMA and LZMA2 is planned, but for now, there is no other
+    documentation than the source code. Before you begin, you should know
+    the basics of LZ77 and range-coding algorithms. LZMA is based on LZ77,
+    but LZMA is a lot more complex. Range coding is used to compress
+    the final bitstream like Huffman coding is used in Deflate.
+
+
+Q:  I cannot find BCJ and BCJ2 filters. Don't they exist in liblzma?
+
+A:  BCJ filter is called "x86" in liblzma. BCJ2 is not included,
+    because it requires using more than one encoded output stream.
+
+
+Q:  I need to use a script that runs "xz -9". On a system with 256 MiB
+    of RAM, xz says that it cannot allocate memory. Can I make the
+    script work without modifying it?
+
+A:  Set a default memory usage limit for compression. You can do it e.g.
+    in a shell initialization script such as ~/.bashrc or /etc/profile:
+
+        XZ_DEFAULTS=--memlimit-compress=150MiB
+        export XZ_DEFAULTS
+
+    xz will then scale the compression settings down so that the given
+    memory usage limit is not reached. This way xz shouldn't run out
+    of memory.
+
+    Check also that memory-related resource limits are high enough.
+    On most systems, "ulimit -a" will show the current resource limits.
+
+
+Q:  How do I create files that can be decompressed with XZ Embedded?
+
+A:  See the documentation in XZ Embedded. In short, something like
+    this is a good start:
+
+        xz --check=crc32 --lzma2=preset=6e,dict=64KiB
+
+    Or if a BCJ filter is needed too, e.g. if compressing
+    a kernel image for PowerPC:
+
+        xz --check=crc32 --powerpc --lzma2=preset=6e,dict=64KiB
+
+    Adjust the dictionary size to get a good compromise between
+    compression ratio and decompressor memory usage. Note that
+    in single-call decompression mode of XZ Embedded, a big
+    dictionary doesn't increase memory usage.
+
+
+Q:  How is multi-threaded compression implemented in XZ Utils?
+
+A:  The simplest method is splitting the uncompressed data into blocks
+    and compressing them in parallel independent from each other.
+    This is currently the only threading method supported in XZ Utils.
+    Since the blocks are compressed independently, they can also be
+    decompressed independently. Together with the index feature in .xz,
+    this allows using threads to create .xz files for random-access
+    reading. This also makes threaded decompression possible.
+
+    The independent blocks method has a couple of disadvantages too. It
+    will compress worse than a single-block method. Often the difference
+    is not too big (maybe 1-2 %) but sometimes it can be too big. Also,
+    the memory usage of the compressor increases linearly when adding
+    threads.
+
+    At least two other threading methods are possible but these haven't
+    been implemented in XZ Utils:
+
+    Match finder parallelization has been in 7-Zip for ages. It doesn't
+    affect compression ratio or memory usage significantly. Among the
+    three threading methods, only this is useful when compressing small
+    files (files that are not significantly bigger than the dictionary).
+    Unfortunately this method scales only to about two CPU cores.
+
+    The third method is pigz-style threading (I use that name, because
+    pigz <https://www.zlib.net/pigz/> uses that method). It doesn't
+    affect compression ratio significantly and scales to many cores.
+    The memory usage scales linearly when threads are added. This isn't
+    significant with pigz, because Deflate uses only a 32 KiB dictionary,
+    but with LZMA2 the memory usage will increase dramatically just like
+    with the independent-blocks method. There is also a constant
+    computational overhead, which may make pigz-method a bit dull on
+    dual-core compared to the parallel match finder method, but with more
+    cores the overhead is not a big deal anymore.
+
+    Combining the threading methods will be possible and also useful.
+    For example, combining match finder parallelization with pigz-style
+    threading or independent-blocks-threading can cut the memory usage
+    by 50 %.
+
+
+Q:  I told xz to use many threads but it is using only one or two
+    processor cores. What is wrong?
+
+A:  Since multi-threaded compression is done by splitting the data into
+    blocks that are compressed individually, if the input file is too
+    small for the block size, then many threads cannot be used. The
+    default block size increases when the compression level is
+    increased. For example, xz -6 uses 8 MiB LZMA2 dictionary and
+    24 MiB blocks, and xz -9 uses 64 MiB LZMA dictionary and 192 MiB
+    blocks. If the input file is 100 MiB, xz -6 can use five threads
+    of which one will finish quickly as it has only 4 MiB to compress.
+    However, for the same file, xz -9 can only use one thread.
+
+    One can adjust block size with --block-size=SIZE but making the
+    block size smaller than LZMA2 dictionary is waste of RAM: using
+    xz -9 with 6 MiB blocks isn't any better than using xz -6 with
+    6 MiB blocks. The default settings use a block size bigger than
+    the LZMA2 dictionary size because this was seen as a reasonable
+    compromise between RAM usage and compression ratio.
+
+    When decompressing, the ability to use threads depends on how the
+    file was created. If it was created in multi-threaded mode then
+    it can be decompressed in multi-threaded mode too if there are
+    multiple blocks in the file.
+
+
+Q:  How do I build a program that needs liblzmadec (lzmadec.h)?
+
+A:  liblzmadec is part of LZMA Utils. XZ Utils has liblzma, but no
+    liblzmadec. The code using liblzmadec should be ported to use
+    liblzma instead. If you cannot or don't want to do that, download
+    LZMA Utils from <https://tukaani.org/lzma/>.
+
+
+Q:  The default build of liblzma is too big. How can I make it smaller?
+
+A:  Give --enable-small to the configure script. Use also appropriate
+    --enable or --disable options to include only those filter encoders
+    and decoders and integrity checks that you actually need. Use
+    CFLAGS=-Os (with GCC) or equivalent to tell your compiler to optimize
+    for size. See INSTALL for information about configure options.
+
+    If the result is still too big, take a look at XZ Embedded. It is
+    a separate project, which provides a limited but significantly
+    smaller XZ decoder implementation than XZ Utils. You can find it
+    at <https://tukaani.org/xz/embedded.html>.
+

doc/history.txt

@@ -0,0 +1,150 @@
+
+History of LZMA Utils and XZ Utils
+==================================
+
+Tukaani distribution
+
+    In 2005, there was a small group working on the Tukaani distribution,
+    which was a Slackware fork. One of the project's goals was to fit the
+    distro on a single 700 MiB ISO-9660 image. Using LZMA instead of gzip
+    helped a lot. Roughly speaking, one could fit data that took 1000 MiB
+    in gzipped form into 700 MiB with LZMA. Naturally, the compression
+    ratio varied across packages, but this was what we got on average.
+
+    Slackware packages have traditionally had .tgz as the filename suffix,
+    which is an abbreviation of .tar.gz. A logical naming for LZMA
+    compressed packages was .tlz, being an abbreviation of .tar.lzma.
+
+    At the end of the year 2007, there was no distribution under the
+    Tukaani project anymore, but development of LZMA Utils was kept going.
+    Still, there were .tlz packages around, because at least Vector Linux
+    (a Slackware based distribution) used LZMA for its packages.
+
+    First versions of the modified pkgtools used the LZMA_Alone tool from
+    Igor Pavlov's LZMA SDK as is. It was fine, because users wouldn't need
+    to interact with LZMA_Alone directly. But people soon wanted to use
+    LZMA for other files too, and the interface of LZMA_Alone wasn't
+    comfortable for those used to gzip and bzip2.
+
+
+First steps of LZMA Utils
+
+    The first version of LZMA Utils (4.22.0) included a shell script called
+    lzmash. It was a wrapper that had a gzip-like command-line interface. It
+    used the LZMA_Alone tool from LZMA SDK to do all the real work. zgrep,
+    zdiff, and related scripts from gzip were adapted to work with LZMA and
+    were part of the first LZMA Utils release too.
+
+    LZMA Utils 4.22.0 included also lzmadec, which was a small (less than
+    10 KiB) decoder-only command-line tool. It was written on top of the
+    decoder-only C code found from the LZMA SDK. lzmadec was convenient in
+    situations where LZMA_Alone (a few hundred KiB) would be too big.
+
+    lzmash and lzmadec were written by Lasse Collin.
+
+
+Second generation
+
+    The lzmash script was an ugly and not very secure hack. The last
+    version of LZMA Utils to use lzmash was 4.27.1.
+
+    LZMA Utils 4.32.0beta1 introduced a new lzma command-line tool written
+    by Ville Koskinen. It was written in C++, and used the encoder and
+    decoder from C++ LZMA SDK with some little modifications. This tool
+    replaced both the lzmash script and the LZMA_Alone command-line tool
+    in LZMA Utils.
+
+    Introducing this new tool caused some temporary incompatibilities,
+    because the LZMA_Alone executable was simply named lzma like the new
+    command-line tool, but they had a completely different command-line
+    interface. The file format was still the same.
+
+    Lasse wrote liblzmadec, which was a small decoder-only library based
+    on the C code found from LZMA SDK. liblzmadec had an API similar to
+    zlib, although there were some significant differences, which made it
+    non-trivial to use it in some applications designed for zlib and
+    libbzip2.
+
+    The lzmadec command-line tool was converted to use liblzmadec.
+
+    Alexandre Sauvé helped converting the build system to use GNU
+    Autotools. This made it easier to test for certain less portable
+    features needed by the new command-line tool.
+
+    Since the new command-line tool never got completely finished (for
+    example, it didn't support the LZMA_OPT environment variable), the
+    intent was to not call 4.32.x stable. Similarly, liblzmadec wasn't
+    polished, but appeared to work well enough, so some people started
+    using it too.
+
+    Because the development of the third generation of LZMA Utils was
+    delayed considerably (3-4 years), the 4.32.x branch had to be kept
+    maintained. It got some bug fixes now and then, and finally it was
+    decided to call it stable, although most of the missing features were
+    never added.
+
+
+File format problems
+
+    The file format used by LZMA_Alone was primitive. It was designed with
+    embedded systems in mind, and thus provided only a minimal set of
+    features. The two biggest problems for non-embedded use were the lack
+    of magic bytes and an integrity check.
+
+    Igor and Lasse started developing a new file format with some help
+    from Ville Koskinen. Also Mark Adler, Mikko Pouru, H. Peter Anvin,
+    and Lars Wirzenius helped with some minor things at some point of the
+    development. Designing the new format took quite a long time (actually,
+    too long a time would be a more appropriate expression). It was mostly
+    because Lasse was quite slow at getting things done due to personal
+    reasons.
+
+    Originally the new format was supposed to use the same .lzma suffix
+    that was already used by the old file format. Switching to the new
+    format wouldn't have caused much trouble when the old format wasn't
+    used by many people. But since the development of the new format took
+    such a long time, the old format got quite popular, and it was decided
+    that the new file format must use a different suffix.
+
+    It was decided to use .xz as the suffix of the new file format. The
+    first stable .xz file format specification was finally released in
+    December 2008. In addition to fixing the most obvious problems of
+    the old .lzma format, the .xz format added some new features like
+    support for multiple filters (compression algorithms), filter chaining
+    (like piping on the command line), and limited random-access reading.
+
+    Currently the primary compression algorithm used in .xz is LZMA2.
+    It is an extension on top of the original LZMA to fix some practical
+    problems: LZMA2 adds support for flushing the encoder, uncompressed
+    chunks, eases stateful decoder implementations, and improves support
+    for multithreading. Since LZMA2 is better than the original LZMA, the
+    original LZMA is not supported in .xz.
+
+
+Transition to XZ Utils
+
+    The early versions of XZ Utils were called LZMA Utils. The first
+    releases were 4.42.0alphas. They dropped the rest of the C++ LZMA SDK.
+    The code was still directly based on LZMA SDK but ported to C and
+    converted from a callback API to a stateful API. Later, Igor Pavlov
+    made a C version of the LZMA encoder too; these ports from C++ to C
+    were independent in LZMA SDK and LZMA Utils.
+
+    The core of the new LZMA Utils was liblzma, a compression library with
+    a zlib-like API. liblzma supported both the old and new file format.
+    The gzip-like lzma command-line tool was rewritten to use liblzma.
+
+    The new LZMA Utils code base was renamed to XZ Utils when the name
+    of the new file format had been decided. The liblzma compression
+    library retained its name though, because changing it would have
+    caused unnecessary breakage in applications already using the early
+    liblzma snapshots.
+
+    The xz command-line tool can emulate the gzip-like lzma tool by
+    creating appropriate symlinks (e.g. lzma -> xz). Thus, practically
+    all scripts using the lzma tool from LZMA Utils will work as is with
+    XZ Utils (and will keep using the old .lzma format). Still, the .lzma
+    format is more or less deprecated. XZ Utils will keep supporting it,
+    but new applications should use the .xz format, and migrating old
+    applications to .xz is often a good idea too.
+

doc/lzma-file-format.txt

@@ -0,0 +1,173 @@
+
+The .lzma File Format
+=====================
+
+        0. Preface
+           0.1. Notices and Acknowledgements
+           0.2. Changes
+        1. File Format
+           1.1. Header
+                1.1.1. Properties
+                1.1.2. Dictionary Size
+                1.1.3. Uncompressed Size
+           1.2. LZMA Compressed Data
+        2. References
+
+
+0. Preface
+
+        This document describes the .lzma file format, which is
+        sometimes also called LZMA_Alone format. It is a legacy file
+        format, which is being or has been replaced by the .xz format.
+        The MIME type of the .lzma format is `application/x-lzma'.
+
+        The most commonly used software to handle .lzma files are
+        LZMA SDK, LZMA Utils, 7-Zip, and XZ Utils. This document
+        describes some of the differences between these implementations
+        and gives hints what subset of the .lzma format is the most
+        portable.
+
+
+0.1. Notices and Acknowledgements
+
+        This file format was designed by Igor Pavlov for use in
+        LZMA SDK. This document was written by Lasse Collin
+        <lasse.collin@tukaani.org> using the documentation found
+        from the LZMA SDK.
+
+        This document has been put into the public domain.
+
+
+0.2. Changes
+
+        Last modified: 2022-07-13 21:00+0300
+
+        Compared to the previous version (2011-04-12 11:55+0300)
+        the section 1.1.3 was modified to allow End of Payload Marker
+        with a known Uncompressed Size.
+
+
+1. File Format
+
+        +-+-+-+-+-+-+-+-+-+-+-+-+-+==========================+
+        |         Header          |   LZMA Compressed Data   |
+        +-+-+-+-+-+-+-+-+-+-+-+-+-+==========================+
+
+        The .lzma format file consist of 13-byte Header followed by
+        the LZMA Compressed Data.
+
+        Unlike the .gz, .bz2, and .xz formats, it is not possible to
+        concatenate multiple .lzma files as is and expect the
+        decompression tool to decode the resulting file as if it were
+        a single .lzma file.
+
+        For example, the command line tools from LZMA Utils and
+        LZMA SDK silently ignore all the data after the first .lzma
+        stream. In contrast, the command line tool from XZ Utils
+        considers the .lzma file to be corrupt if there is data after
+        the first .lzma stream.
+
+
+1.1. Header
+
+        +------------+----+----+----+----+--+--+--+--+--+--+--+--+
+        | Properties |  Dictionary Size  |   Uncompressed Size   |
+        +------------+----+----+----+----+--+--+--+--+--+--+--+--+
+
+
+1.1.1. Properties
+
+        The Properties field contains three properties. An abbreviation
+        is given in parentheses, followed by the value range of the
+        property. The field consists of
+
+            1) the number of literal context bits (lc, [0, 8]);
+            2) the number of literal position bits (lp, [0, 4]); and
+            3) the number of position bits (pb, [0, 4]).
+
+        The properties are encoded using the following formula:
+
+            Properties = (pb * 5 + lp) * 9 + lc
+
+        The following C code illustrates a straightforward way to
+        decode the Properties field:
+
+            uint8_t lc, lp, pb;
+            uint8_t prop = get_lzma_properties();
+            if (prop > (4 * 5 + 4) * 9 + 8)
+                return LZMA_PROPERTIES_ERROR;
+
+            pb = prop / (9 * 5);
+            prop -= pb * 9 * 5;
+            lp = prop / 9;
+            lc = prop - lp * 9;
+
+        XZ Utils has an additional requirement: lc + lp <= 4. Files
+        which don't follow this requirement cannot be decompressed
+        with XZ Utils. Usually this isn't a problem since the most
+        common lc/lp/pb values are 3/0/2. It is the only lc/lp/pb
+        combination that the files created by LZMA Utils can have,
+        but LZMA Utils can decompress files with any lc/lp/pb.
+
+
+1.1.2. Dictionary Size
+
+        Dictionary Size is stored as an unsigned 32-bit little endian
+        integer. Any 32-bit value is possible, but for maximum
+        portability, only sizes of 2^n and 2^n + 2^(n-1) should be
+        used.
+
+        LZMA Utils creates only files with dictionary size 2^n,
+        16 <= n <= 25. LZMA Utils can decompress files with any
+        dictionary size.
+
+        XZ Utils creates and decompresses .lzma files only with
+        dictionary sizes 2^n and 2^n + 2^(n-1). If some other
+        dictionary size is specified when compressing, the value
+        stored in the Dictionary Size field is a rounded up, but the
+        specified value is still used in the actual compression code.
+
+
+1.1.3. Uncompressed Size
+
+        Uncompressed Size is stored as unsigned 64-bit little endian
+        integer. A special value of 0xFFFF_FFFF_FFFF_FFFF indicates
+        that Uncompressed Size is unknown. End of Payload Marker (*)
+        is used if Uncompressed Size is unknown. End of Payload Marker
+        is allowed but rarely used if Uncompressed Size is known.
+        XZ Utils 5.2.5 and older don't support .lzma files that have
+        End of Payload Marker together with a known Uncompressed Size.
+
+        XZ Utils rejects files whose Uncompressed Size field specifies
+        a known size that is 256 GiB or more. This is to reject false
+        positives when trying to guess if the input file is in the
+        .lzma format. When Uncompressed Size is unknown, there is no
+        limit for the uncompressed size of the file.
+
+        (*) Some tools use the term End of Stream (EOS) marker
+            instead of End of Payload Marker.
+
+
+1.2. LZMA Compressed Data
+
+        Detailed description of the format of this field is out of
+        scope of this document.
+
+
+2. References
+
+        LZMA SDK - The original LZMA implementation
+        http://7-zip.org/sdk.html
+
+        7-Zip
+        http://7-zip.org/
+
+        LZMA Utils - LZMA adapted to POSIX-like systems
+        http://tukaani.org/lzma/
+
+        XZ Utils - The next generation of LZMA Utils
+        http://tukaani.org/xz/
+
+        The .xz file format - The successor of the .lzma format
+        http://tukaani.org/xz/xz-file-format.txt
+

doc/man/txt/lzmainfo.txt

@@ -0,0 +1,40 @@
+LZMAINFO(1)                        XZ Utils                        LZMAINFO(1)
+
+
+
+NAME
+       lzmainfo - show information stored in the .lzma file header
+
+SYNOPSIS
+       lzmainfo [--help] [--version] [file...]
+
+DESCRIPTION
+       lzmainfo  shows  information stored in the .lzma file header.  It reads
+       the first 13 bytes from the specified file,  decodes  the  header,  and
+       prints it to standard output in human readable format.  If no files are
+       given or file is -, standard input is read.
+
+       Usually the most interesting information is the uncompressed  size  and
+       the  dictionary  size.  Uncompressed size can be shown only if the file
+       is in the non-streamed .lzma format variant.  The amount of memory  re-
+       quired to decompress the file is a few dozen kilobytes plus the dictio-
+       nary size.
+
+       lzmainfo is included in XZ Utils primarily for  backward  compatibility
+       with LZMA Utils.
+
+EXIT STATUS
+       0      All is good.
+
+       1      An error occurred.
+
+BUGS
+       lzmainfo  uses  MB  while the correct suffix would be MiB (2^20 bytes).
+       This is to keep the output compatible with LZMA Utils.
+
+SEE ALSO
+       xz(1)
+
+
+
+Tukaani                           2013-06-30                       LZMAINFO(1)

doc/man/txt/xzdec.txt

@@ -0,0 +1,80 @@
+XZDEC(1)                           XZ Utils                           XZDEC(1)
+
+
+
+NAME
+       xzdec, lzmadec - Small .xz and .lzma decompressors
+
+SYNOPSIS
+       xzdec [option...]  [file...]
+       lzmadec [option...]  [file...]
+
+DESCRIPTION
+       xzdec is a liblzma-based decompression-only tool for .xz (and only .xz)
+       files.  xzdec is intended to work as a drop-in replacement for xz(1) in
+       the  most  common  situations where a script has been written to use xz
+       --decompress --stdout (and possibly a few other commonly used  options)
+       to decompress .xz files.  lzmadec is identical to xzdec except that lz-
+       madec supports .lzma files instead of .xz files.
+
+       To reduce the size of the  executable,  xzdec  doesn't  support  multi-
+       threading  or  localization,  and doesn't read options from XZ_DEFAULTS
+       and XZ_OPT environment variables.  xzdec doesn't support displaying in-
+       termediate progress information: sending SIGINFO to xzdec does nothing,
+       but sending  SIGUSR1  terminates  the  process  instead  of  displaying
+       progress information.
+
+OPTIONS
+       -d, --decompress, --uncompress
+              Ignored for xz(1) compatibility.  xzdec supports only decompres-
+              sion.
+
+       -k, --keep
+              Ignored for xz(1) compatibility.  xzdec never creates or removes
+              any files.
+
+       -c, --stdout, --to-stdout
+              Ignored for xz(1) compatibility.  xzdec always writes the decom-
+              pressed data to standard output.
+
+       -q, --quiet
+              Specifying this once does nothing since xzdec never displays any
+              warnings or notices.  Specify this twice to suppress errors.
+
+       -Q, --no-warn
+              Ignored for xz(1) compatibility.  xzdec never uses the exit sta-
+              tus 2.
+
+       -h, --help
+              Display a help message and exit successfully.
+
+       -V, --version
+              Display the version number of xzdec and liblzma.
+
+EXIT STATUS
+       0      All was good.
+
+       1      An error occurred.
+
+       xzdec doesn't have any warning messages like xz(1) has, thus  the  exit
+       status 2 is not used by xzdec.
+
+NOTES
+       Use  xz(1)  instead of xzdec or lzmadec for normal everyday use.  xzdec
+       or lzmadec are meant only for situations where it is important to  have
+       a smaller decompressor than the full-featured xz(1).
+
+       xzdec  and  lzmadec are not really that small.  The size can be reduced
+       further by dropping features from liblzma at  compile  time,  but  that
+       shouldn't  usually  be done for executables distributed in typical non-
+       embedded operating system distributions.  If you need a truly small .xz
+       decompressor, consider using XZ Embedded.
+
+SEE ALSO
+       xz(1)
+
+       XZ Embedded: <https://tukaani.org/xz/embedded.html>
+
+
+
+Tukaani                           2017-04-19                          XZDEC(1)

doc/man/txt/xzdiff.txt

@@ -0,0 +1,37 @@
+XZDIFF(1)                          XZ Utils                          XZDIFF(1)
+
+
+
+NAME
+       xzcmp, xzdiff, lzcmp, lzdiff - compare compressed files
+
+SYNOPSIS
+       xzcmp [cmp_options] file1 [file2]
+       xzdiff [diff_options] file1 [file2]
+       lzcmp [cmp_options] file1 [file2]
+       lzdiff [diff_options] file1 [file2]
+
+DESCRIPTION
+       xzcmp  and  xzdiff  invoke  cmp(1)  or diff(1) on files compressed with
+       xz(1), lzma(1), gzip(1), bzip2(1), lzop(1), or  zstd(1).   All  options
+       specified  are  passed directly to cmp(1) or diff(1).  If only one file
+       is specified, then the files compared are file1 (which must have a suf-
+       fix  of  a  supported compression format) and file1 from which the com-
+       pression format suffix has been stripped.  If two files are  specified,
+       then  they  are uncompressed if necessary and fed to cmp(1) or diff(1).
+       The exit status from cmp(1) or diff(1) is preserved unless a decompres-
+       sion error occurs; then exit status is 2.
+
+       The names lzcmp and lzdiff are provided for backward compatibility with
+       LZMA Utils.
+
+SEE ALSO
+       cmp(1), diff(1), xz(1), gzip(1), bzip2(1), lzop(1), zstd(1), zdiff(1)
+
+BUGS
+       Messages from the cmp(1) or diff(1) programs refer to  temporary  file-
+       names instead of those specified.
+
+
+
+Tukaani                           2021-06-04                         XZDIFF(1)

doc/man/txt/xzgrep.txt

@@ -0,0 +1,49 @@
+XZGREP(1)                          XZ Utils                          XZGREP(1)
+
+
+
+NAME
+       xzgrep - search compressed files for a regular expression
+
+SYNOPSIS
+       xzgrep [grep_options] [-e] pattern [file...]
+       xzegrep ...
+       xzfgrep ...
+       lzgrep ...
+       lzegrep ...
+       lzfgrep ...
+
+DESCRIPTION
+       xzgrep  invokes  grep(1)  on  files which may be either uncompressed or
+       compressed with xz(1), lzma(1), gzip(1), bzip2(1), lzop(1), or zstd(1).
+       All options specified are passed directly to grep(1).
+
+       If  no file is specified, then standard input is decompressed if neces-
+       sary and fed to grep(1).  When reading from  standard  input,  gzip(1),
+       bzip2(1), lzop(1), and zstd(1) compressed files are not supported.
+
+       If  xzgrep  is invoked as xzegrep or xzfgrep then grep -E or grep -F is
+       used instead of grep(1).  The same applies to  names  lzgrep,  lzegrep,
+       and  lzfgrep,  which  are provided for backward compatibility with LZMA
+       Utils.
+
+EXIT STATUS
+       0      At least one match was found from at  least  one  of  the  input
+              files.  No errors occurred.
+
+       1      No  matches  were  found from any of the input files.  No errors
+              occurred.
+
+       >1     One or more errors occurred.  It  is  unknown  if  matches  were
+              found.
+
+ENVIRONMENT
+       GREP   If  the GREP environment variable is set, xzgrep uses it instead
+              of grep(1), grep -E, or grep -F.
+
+SEE ALSO
+       grep(1), xz(1), gzip(1), bzip2(1), lzop(1), zstd(1), zgrep(1)
+
+
+
+Tukaani                           2022-07-19                         XZGREP(1)

doc/man/txt/xzless.txt

@@ -0,0 +1,39 @@
+XZLESS(1)                          XZ Utils                          XZLESS(1)
+
+
+
+NAME
+       xzless, lzless - view xz or lzma compressed (text) files
+
+SYNOPSIS
+       xzless [file...]
+       lzless [file...]
+
+DESCRIPTION
+       xzless is a filter that displays text from compressed files to a termi-
+       nal.  It works on files compressed with xz(1) or lzma(1).  If no  files
+       are given, xzless reads from standard input.
+
+       xzless  uses  less(1) to present its output.  Unlike xzmore, its choice
+       of pager cannot be altered by setting an  environment  variable.   Com-
+       mands  are  based  on  both  more(1) and vi(1) and allow back and forth
+       movement and searching.  See the less(1) manual for more information.
+
+       The command named lzless is provided for  backward  compatibility  with
+       LZMA Utils.
+
+ENVIRONMENT
+       LESSMETACHARS
+              A list of characters special to the shell.  Set by xzless unless
+              it is already set in the environment.
+
+       LESSOPEN
+              Set to a command line to invoke the xz(1) decompressor for  pre-
+              processing the input files to less(1).
+
+SEE ALSO
+       less(1), xz(1), xzmore(1), zless(1)
+
+
+
+Tukaani                           2010-09-27                         XZLESS(1)

doc/man/txt/xzmore.txt

@@ -0,0 +1,34 @@
+XZMORE(1)                          XZ Utils                          XZMORE(1)
+
+
+
+NAME
+       xzmore, lzmore - view xz or lzma compressed (text) files
+
+SYNOPSIS
+       xzmore [file...]
+       lzmore [file...]
+
+DESCRIPTION
+       xzmore  is  a  filter which allows examination of xz(1) or lzma(1) com-
+       pressed text files one screenful at a time on a soft-copy terminal.
+
+       To use a pager other than the default more,  set  environment  variable
+       PAGER  to the name of the desired program.  The name lzmore is provided
+       for backward compatibility with LZMA Utils.
+
+       e or q When the prompt --More--(Next file: file) is printed, this  com-
+              mand causes xzmore to exit.
+
+       s      When  the prompt --More--(Next file: file) is printed, this com-
+              mand causes xzmore to skip the next file and continue.
+
+       For list of keyboard commands supported while actually viewing the con-
+       tent of a file, refer to manual of the pager you use, usually more(1).
+
+SEE ALSO
+       more(1), xz(1), xzless(1), zmore(1)
+
+
+
+Tukaani                           2013-06-30                         XZMORE(1)

extra/7z2lzma/7z2lzma.bash

@@ -0,0 +1,115 @@
+#!/bin/bash
+#
+#############################################################################
+#
+# 7z2lzma.bash is very primitive .7z to .lzma converter. The input file must
+# have exactly one LZMA compressed stream, which has been created with the
+# default lc, lp, and pb values. The CRC32 in the .7z archive is not checked,
+# and the script may seem to succeed while it actually created a corrupt .lzma
+# file. You should always try uncompressing both the original .7z and the
+# created .lzma and compare that the output is identical.
+#
+# This script requires basic GNU tools and 7z or 7za tool from p7zip.
+#
+# Last modified: 2009-01-15 14:25+0200
+#
+#############################################################################
+#
+# Author: Lasse Collin <lasse.collin@tukaani.org>
+#
+# This file has been put into the public domain.
+# You can do whatever you want with this file.
+#
+#############################################################################
+
+# You can use 7z or 7za, both will work.
+SEVENZIP=7za
+
+if [ $# != 2 -o -z "$1" -o -z "$2" ]; then
+	echo "Usage: $0 input.7z output.lzma"
+	exit 1
+fi
+
+# Converts an integer variable to little endian binary integer.
+int2bin()
+{
+	local LEN=$1
+	local NUM=$2
+	local HEX=(0 1 2 3 4 5 6 7 8 9 A B C D E F)
+	local I
+	for ((I=0; I < "$LEN"; ++I)); do
+		printf "\\x${HEX[(NUM >> 4) & 0x0F]}${HEX[NUM & 0x0F]}"
+		NUM=$((NUM >> 8))
+	done
+}
+
+# Make sure we get possible errors from pipes.
+set -o pipefail
+
+# Get information about the input file. At least older 7z and 7za versions
+# may return with zero exit status even when an error occurred, so check
+# if the output has any lines beginning with "Error".
+INFO=$("$SEVENZIP" l -slt "$1")
+if [ $? != 0 ] || printf '%s\n' "$INFO" | grep -q ^Error; then
+	printf '%s\n' "$INFO"
+	exit 1
+fi
+
+# Check if the input file has more than one compressed block.
+if printf '%s\n' "$INFO" | grep -q '^Block = 1'; then
+	echo "Cannot convert, because the input file has more than"
+	echo "one compressed block."
+	exit 1
+fi
+
+# Get compressed, uncompressed, and dictionary size.
+CSIZE=$(printf '%s\n' "$INFO" | sed -rn 's|^Packed Size = ([0-9]+$)|\1|p')
+USIZE=$(printf '%s\n' "$INFO" | sed -rn 's|^Size = ([0-9]+$)|\1|p')
+DICT=$(printf '%s\n' "$INFO" | sed -rn 's|^Method = LZMA:([0-9]+[bkm]?)$|\1|p')
+
+if [ -z "$CSIZE" -o -z "$USIZE" -o -z "$DICT" ]; then
+	echo "Parsing output of $SEVENZIP failed. Maybe the file uses some"
+	echo "other compression method than plain LZMA."
+	exit 1
+fi
+
+# The following assumes that the default lc, lp, and pb settings were used.
+# Otherwise the output will be corrupt.
+printf '\x5D' > "$2"
+
+# Dictionary size can be either was power of two, bytes, kibibytes, or
+# mebibytes. We need to convert it to bytes.
+case $DICT in
+	*b)
+		DICT=${DICT%b}
+		;;
+	*k)
+		DICT=${DICT%k}
+		DICT=$((DICT << 10))
+		;;
+	*m)
+		DICT=${DICT%m}
+		DICT=$((DICT << 20))
+		;;
+	*)
+		DICT=$((1 << DICT))
+		;;
+esac
+int2bin 4 "$DICT" >> "$2"
+
+# Uncompressed size
+int2bin 8 "$USIZE" >> "$2"
+
+# Copy the actual compressed data. Using multiple dd commands to avoid
+# copying large amount of data with one-byte block size, which would be
+# annoyingly slow.
+BS=8192
+BIGSIZE=$((CSIZE / BS))
+CSIZE=$((CSIZE % BS))
+{
+	dd of=/dev/null bs=32 count=1 \
+		&& dd bs="$BS" count="$BIGSIZE" \
+		&& dd bs=1 count="$CSIZE"
+} < "$1" >> "$2"
+
+exit $?

extra/scanlzma/scanlzma.c

@@ -0,0 +1,88 @@
+/*
+    scanlzma, scan for lzma compressed data in stdin and echo it to stdout.
+    Copyright (C) 2006 Timo Lindfors
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+*/
+
+/* Usage example:
+
+   $ wget http://www.wifi-shop.cz/Files/produkty/wa2204/wa2204av1.4.1.zip
+   $ unzip wa2204av1.4.1.zip
+   $ gcc scanlzma.c -o scanlzma -Wall
+   $ ./scanlzma 0 < WA2204-FW1.4.1/linux-1.4.bin | lzma -c -d | strings | grep -i "copyright"
+   UpdateDD version 2.5, Copyright (C) 2005 Philipp Benner.
+   Copyright (C) 2005 Philipp Benner.
+   Copyright (C) 2005 Philipp Benner.
+   mawk 1.3%s%s %s, Copyright (C) Michael D. Brennan
+   # Copyright (C) 1998, 1999, 2001  Henry Spencer.
+   ...
+
+*/
+
+
+/* LZMA compressed file format */
+/* --------------------------- */
+/* Offset Size Description */
+/*   0     1   Special LZMA properties for compressed data */
+/*   1     4   Dictionary size (little endian) */
+/*   5     8   Uncompressed size (little endian). -1 means unknown size */
+/*  13         Compressed data */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#define BUFSIZE 4096
+
+int find_lzma_header(unsigned char *buf) {
+	return (buf[0] < 0xE1
+		&& buf[0] == 0x5d
+		&& buf[4] < 0x20
+		&& (memcmp (buf + 10 , "\x00\x00\x00", 3) == 0
+		    || (memcmp (buf + 5, "\xFF\xFF\xFF\xFF\xFF\xFF\xFF\xFF", 8) == 0)));
+}
+
+int main(int argc, char *argv[]) {
+	unsigned char buf[BUFSIZE];
+	int ret, i, numlzma, blocks=0;
+
+	if (argc != 2) {
+		printf("usage: %s numlzma < infile | lzma -c -d > outfile\n"
+		       "where numlzma is index of lzma file to extract, starting from zero.\n",
+		       argv[0]);
+		exit(1);
+	}
+	numlzma = atoi(argv[1]);
+
+	for (;;) {
+		/* Read data. */
+		ret = fread(buf, BUFSIZE, 1, stdin);
+		if (ret != 1)
+			break;
+
+		/* Scan for signature. */
+		for (i = 0; i<BUFSIZE-23; i++) {
+			if (find_lzma_header(buf+i) && numlzma-- <= 0) {
+				fwrite(buf+i, (BUFSIZE-i), 1, stdout);
+				for (;;) {
+					int ch;
+					ch = getchar();
+					if (ch == EOF)
+						exit(0);
+					putchar(ch);
+				}
+			}
+		}
+		blocks++;
+	}
+	return 1;
+}

lib/getopt.in.h

@@ -0,0 +1,226 @@
+/* Declarations for getopt.
+   Copyright (C) 1989-1994,1996-1999,2001,2003,2004,2005,2006,2007
+   Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU Lesser General Public License as published by
+   the Free Software Foundation; either version 2.1, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public License along
+   with this program; if not, write to the Free Software Foundation,
+   Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+#ifndef _GETOPT_H
+
+#ifndef __need_getopt
+# define _GETOPT_H 1
+#endif
+
+/* Standalone applications should #define __GETOPT_PREFIX to an
+   identifier that prefixes the external functions and variables
+   defined in this header.  When this happens, include the
+   headers that might declare getopt so that they will not cause
+   confusion if included after this file.  Then systematically rename
+   identifiers so that they do not collide with the system functions
+   and variables.  Renaming avoids problems with some compilers and
+   linkers.  */
+#if defined __GETOPT_PREFIX && !defined __need_getopt
+# include <stdlib.h>
+# include <stdio.h>
+# include <unistd.h>
+# undef __need_getopt
+# undef getopt
+# undef getopt_long
+# undef getopt_long_only
+# undef optarg
+# undef opterr
+# undef optind
+# undef optopt
+# define __GETOPT_CONCAT(x, y) x ## y
+# define __GETOPT_XCONCAT(x, y) __GETOPT_CONCAT (x, y)
+# define __GETOPT_ID(y) __GETOPT_XCONCAT (__GETOPT_PREFIX, y)
+# define getopt __GETOPT_ID (getopt)
+# define getopt_long __GETOPT_ID (getopt_long)
+# define getopt_long_only __GETOPT_ID (getopt_long_only)
+# define optarg __GETOPT_ID (optarg)
+# define opterr __GETOPT_ID (opterr)
+# define optind __GETOPT_ID (optind)
+# define optopt __GETOPT_ID (optopt)
+#endif
+
+/* Standalone applications get correct prototypes for getopt_long and
+   getopt_long_only; they declare "char **argv".  libc uses prototypes
+   with "char *const *argv" that are incorrect because getopt_long and
+   getopt_long_only can permute argv; this is required for backward
+   compatibility (e.g., for LSB 2.0.1).
+
+   This used to be `#if defined __GETOPT_PREFIX && !defined __need_getopt',
+   but it caused redefinition warnings if both unistd.h and getopt.h were
+   included, since unistd.h includes getopt.h having previously defined
+   __need_getopt.
+
+   The only place where __getopt_argv_const is used is in definitions
+   of getopt_long and getopt_long_only below, but these are visible
+   only if __need_getopt is not defined, so it is quite safe to rewrite
+   the conditional as follows:
+*/
+#if !defined __need_getopt
+# if defined __GETOPT_PREFIX
+#  define __getopt_argv_const /* empty */
+# else
+#  define __getopt_argv_const const
+# endif
+#endif
+
+/* If __GNU_LIBRARY__ is not already defined, either we are being used
+   standalone, or this is the first header included in the source file.
+   If we are being used with glibc, we need to include <features.h>, but
+   that does not exist if we are standalone.  So: if __GNU_LIBRARY__ is
+   not defined, include <ctype.h>, which will pull in <features.h> for us
+   if it's from glibc.  (Why ctype.h?  It's guaranteed to exist and it
+   doesn't flood the namespace with stuff the way some other headers do.)  */
+#if !defined __GNU_LIBRARY__
+# include <ctype.h>
+#endif
+
+#ifndef __THROW
+# ifndef __GNUC_PREREQ
+#  define __GNUC_PREREQ(maj, min) (0)
+# endif
+# if defined __cplusplus && __GNUC_PREREQ (2,8)
+#  define __THROW	throw ()
+# else
+#  define __THROW
+# endif
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* For communication from `getopt' to the caller.
+   When `getopt' finds an option that takes an argument,
+   the argument value is returned here.
+   Also, when `ordering' is RETURN_IN_ORDER,
+   each non-option ARGV-element is returned here.  */
+
+extern char *optarg;
+
+/* Index in ARGV of the next element to be scanned.
+   This is used for communication to and from the caller
+   and for communication between successive calls to `getopt'.
+
+   On entry to `getopt', zero means this is the first call; initialize.
+
+   When `getopt' returns -1, this is the index of the first of the
+   non-option elements that the caller should itself scan.
+
+   Otherwise, `optind' communicates from one call to the next
+   how much of ARGV has been scanned so far.  */
+
+extern int optind;
+
+/* Callers store zero here to inhibit the error message `getopt' prints
+   for unrecognized options.  */
+
+extern int opterr;
+
+/* Set to an option character which was unrecognized.  */
+
+extern int optopt;
+
+#ifndef __need_getopt
+/* Describe the long-named options requested by the application.
+   The LONG_OPTIONS argument to getopt_long or getopt_long_only is a vector
+   of `struct option' terminated by an element containing a name which is
+   zero.
+
+   The field `has_arg' is:
+   no_argument		(or 0) if the option does not take an argument,
+   required_argument	(or 1) if the option requires an argument,
+   optional_argument	(or 2) if the option takes an optional argument.
+
+   If the field `flag' is not NULL, it points to a variable that is set
+   to the value given in the field `val' when the option is found, but
+   left unchanged if the option is not found.
+
+   To have a long-named option do something other than set an `int' to
+   a compiled-in constant, such as set a value from `optarg', set the
+   option's `flag' field to zero and its `val' field to a nonzero
+   value (the equivalent single-letter option character, if there is
+   one).  For long options that have a zero `flag' field, `getopt'
+   returns the contents of the `val' field.  */
+
+struct option
+{
+  const char *name;
+  /* has_arg can't be an enum because some compilers complain about
+     type mismatches in all the code that assumes it is an int.  */
+  int has_arg;
+  int *flag;
+  int val;
+};
+
+/* Names for the values of the `has_arg' field of `struct option'.  */
+
+# define no_argument		0
+# define required_argument	1
+# define optional_argument	2
+#endif	/* need getopt */
+
+
+/* Get definitions and prototypes for functions to process the
+   arguments in ARGV (ARGC of them, minus the program name) for
+   options given in OPTS.
+
+   Return the option character from OPTS just read.  Return -1 when
+   there are no more options.  For unrecognized options, or options
+   missing arguments, `optopt' is set to the option letter, and '?' is
+   returned.
+
+   The OPTS string is a list of characters which are recognized option
+   letters, optionally followed by colons, specifying that that letter
+   takes an argument, to be placed in `optarg'.
+
+   If a letter in OPTS is followed by two colons, its argument is
+   optional.  This behavior is specific to the GNU `getopt'.
+
+   The argument `--' causes premature termination of argument
+   scanning, explicitly telling `getopt' that there are no more
+   options.
+
+   If OPTS begins with `-', then non-option arguments are treated as
+   arguments to the option '\1'.  This behavior is specific to the GNU
+   `getopt'.  If OPTS begins with `+', or POSIXLY_CORRECT is set in
+   the environment, then do not permute arguments.  */
+
+extern int getopt (int ___argc, char *const *___argv, const char *__shortopts)
+       __THROW;
+
+#ifndef __need_getopt
+extern int getopt_long (int ___argc, char *__getopt_argv_const *___argv,
+			const char *__shortopts,
+		        const struct option *__longopts, int *__longind)
+       __THROW;
+extern int getopt_long_only (int ___argc, char *__getopt_argv_const *___argv,
+			     const char *__shortopts,
+		             const struct option *__longopts, int *__longind)
+       __THROW;
+
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+/* Make sure we later can get all the definitions and declarations.  */
+#undef __need_getopt
+
+#endif /* getopt.h */

lib/getopt1.c

@@ -0,0 +1,171 @@
+/* getopt_long and getopt_long_only entry points for GNU getopt.
+   Copyright (C) 1987,88,89,90,91,92,93,94,96,97,98,2004,2006
+     Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU Lesser General Public License as published by
+   the Free Software Foundation; either version 2.1, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public License along
+   with this program; if not, write to the Free Software Foundation,
+   Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+#ifdef _LIBC
+# include <getopt.h>
+#else
+# include <config.h>
+# include "getopt.h"
+#endif
+#include "getopt_int.h"
+
+#include <stdio.h>
+
+/* This needs to come after some library #include
+   to get __GNU_LIBRARY__ defined.  */
+#ifdef __GNU_LIBRARY__
+#include <stdlib.h>
+#endif
+
+#ifndef	NULL
+#define NULL 0
+#endif
+
+int
+getopt_long (int argc, char *__getopt_argv_const *argv, const char *options,
+	     const struct option *long_options, int *opt_index)
+{
+  return _getopt_internal (argc, (char **) argv, options, long_options,
+			   opt_index, 0, 0);
+}
+
+int
+_getopt_long_r (int argc, char **argv, const char *options,
+		const struct option *long_options, int *opt_index,
+		struct _getopt_data *d)
+{
+  return _getopt_internal_r (argc, argv, options, long_options, opt_index,
+			     0, 0, d);
+}
+
+/* Like getopt_long, but '-' as well as '--' can indicate a long option.
+   If an option that starts with '-' (not '--') doesn't match a long option,
+   but does match a short option, it is parsed as a short option
+   instead.  */
+
+int
+getopt_long_only (int argc, char *__getopt_argv_const *argv,
+		  const char *options,
+		  const struct option *long_options, int *opt_index)
+{
+  return _getopt_internal (argc, (char **) argv, options, long_options,
+			   opt_index, 1, 0);
+}
+
+int
+_getopt_long_only_r (int argc, char **argv, const char *options,
+		     const struct option *long_options, int *opt_index,
+		     struct _getopt_data *d)
+{
+  return _getopt_internal_r (argc, argv, options, long_options, opt_index,
+			     1, 0, d);
+}
+
+
+#ifdef TEST
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+  int c;
+  int digit_optind = 0;
+
+  while (1)
+    {
+      int this_option_optind = optind ? optind : 1;
+      int option_index = 0;
+      static struct option long_options[] =
+      {
+	{"add", 1, 0, 0},
+	{"append", 0, 0, 0},
+	{"delete", 1, 0, 0},
+	{"verbose", 0, 0, 0},
+	{"create", 0, 0, 0},
+	{"file", 1, 0, 0},
+	{0, 0, 0, 0}
+      };
+
+      c = getopt_long (argc, argv, "abc:d:0123456789",
+		       long_options, &option_index);
+      if (c == -1)
+	break;
+
+      switch (c)
+	{
+	case 0:
+	  printf ("option %s", long_options[option_index].name);
+	  if (optarg)
+	    printf (" with arg %s", optarg);
+	  printf ("\n");
+	  break;
+
+	case '0':
+	case '1':
+	case '2':
+	case '3':
+	case '4':
+	case '5':
+	case '6':
+	case '7':
+	case '8':
+	case '9':
+	  if (digit_optind != 0 && digit_optind != this_option_optind)
+	    printf ("digits occur in two different argv-elements.\n");
+	  digit_optind = this_option_optind;
+	  printf ("option %c\n", c);
+	  break;
+
+	case 'a':
+	  printf ("option a\n");
+	  break;
+
+	case 'b':
+	  printf ("option b\n");
+	  break;
+
+	case 'c':
+	  printf ("option c with value `%s'\n", optarg);
+	  break;
+
+	case 'd':
+	  printf ("option d with value `%s'\n", optarg);
+	  break;
+
+	case '?':
+	  break;
+
+	default:
+	  printf ("?? getopt returned character code 0%o ??\n", c);
+	}
+    }
+
+  if (optind < argc)
+    {
+      printf ("non-option ARGV-elements: ");
+      while (optind < argc)
+	printf ("%s ", argv[optind++]);
+      printf ("\n");
+    }
+
+  exit (0);
+}
+
+#endif /* TEST */

lib/getopt_int.h

@@ -0,0 +1,131 @@
+/* Internal declarations for getopt.
+   Copyright (C) 1989-1994,1996-1999,2001,2003,2004
+   Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 2, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License along
+   with this program; if not, write to the Free Software Foundation,
+   Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
+
+#ifndef _GETOPT_INT_H
+#define _GETOPT_INT_H	1
+
+extern int _getopt_internal (int ___argc, char **___argv,
+			     const char *__shortopts,
+		             const struct option *__longopts, int *__longind,
+			     int __long_only, int __posixly_correct);
+
+
+/* Reentrant versions which can handle parsing multiple argument
+   vectors at the same time.  */
+
+/* Data type for reentrant functions.  */
+struct _getopt_data
+{
+  /* These have exactly the same meaning as the corresponding global
+     variables, except that they are used for the reentrant
+     versions of getopt.  */
+  int optind;
+  int opterr;
+  int optopt;
+  char *optarg;
+
+  /* Internal members.  */
+
+  /* True if the internal members have been initialized.  */
+  int __initialized;
+
+  /* The next char to be scanned in the option-element
+     in which the last option character we returned was found.
+     This allows us to pick up the scan where we left off.
+
+     If this is zero, or a null string, it means resume the scan
+     by advancing to the next ARGV-element.  */
+  char *__nextchar;
+
+  /* Describe how to deal with options that follow non-option ARGV-elements.
+
+     If the caller did not specify anything,
+     the default is REQUIRE_ORDER if the environment variable
+     POSIXLY_CORRECT is defined, PERMUTE otherwise.
+
+     REQUIRE_ORDER means don't recognize them as options;
+     stop option processing when the first non-option is seen.
+     This is what Unix does.
+     This mode of operation is selected by either setting the environment
+     variable POSIXLY_CORRECT, or using `+' as the first character
+     of the list of option characters, or by calling getopt.
+
+     PERMUTE is the default.  We permute the contents of ARGV as we
+     scan, so that eventually all the non-options are at the end.
+     This allows options to be given in any order, even with programs
+     that were not written to expect this.
+
+     RETURN_IN_ORDER is an option available to programs that were
+     written to expect options and other ARGV-elements in any order
+     and that care about the ordering of the two.  We describe each
+     non-option ARGV-element as if it were the argument of an option
+     with character code 1.  Using `-' as the first character of the
+     list of option characters selects this mode of operation.
+
+     The special argument `--' forces an end of option-scanning regardless
+     of the value of `ordering'.  In the case of RETURN_IN_ORDER, only
+     `--' can cause `getopt' to return -1 with `optind' != ARGC.  */
+
+  enum
+    {
+      REQUIRE_ORDER, PERMUTE, RETURN_IN_ORDER
+    } __ordering;
+
+  /* If the POSIXLY_CORRECT environment variable is set
+     or getopt was called.  */
+  int __posixly_correct;
+
+
+  /* Handle permutation of arguments.  */
+
+  /* Describe the part of ARGV that contains non-options that have
+     been skipped.  `first_nonopt' is the index in ARGV of the first
+     of them; `last_nonopt' is the index after the last of them.  */
+
+  int __first_nonopt;
+  int __last_nonopt;
+
+#if defined _LIBC && defined USE_NONOPTION_FLAGS
+  int __nonoption_flags_max_len;
+  int __nonoption_flags_len;
+# endif
+};
+
+/* The initializer is necessary to set OPTIND and OPTERR to their
+   default values and to clear the initialization flag.  */
+#define _GETOPT_DATA_INITIALIZER	{ 1, 1 }
+
+extern int _getopt_internal_r (int ___argc, char **___argv,
+			       const char *__shortopts,
+			       const struct option *__longopts, int *__longind,
+			       int __long_only, int __posixly_correct,
+			       struct _getopt_data *__data);
+
+extern int _getopt_long_r (int ___argc, char **___argv,
+			   const char *__shortopts,
+			   const struct option *__longopts, int *__longind,
+			   struct _getopt_data *__data);
+
+extern int _getopt_long_only_r (int ___argc, char **___argv,
+				const char *__shortopts,
+				const struct option *__longopts,
+				int *__longind,
+				struct _getopt_data *__data);
+
+#endif /* getopt_int.h */

po/LINGUAS

@@ -0,0 +1,23 @@
+ca
+cs
+da
+de
+eo
+es
+fi
+fr
+hr
+hu
+it
+ko
+pl
+pt
+pt_BR
+ro
+sr
+sv
+tr
+uk
+vi
+zh_CN
+zh_TW

po/Makevars

@@ -0,0 +1,46 @@
+# Makefile variables for PO directory in any package using GNU gettext.
+
+# Usually the message domain is the same as the package name.
+DOMAIN = $(PACKAGE)
+
+# These two variables depend on the location of this directory.
+subdir = po
+top_builddir = ..
+
+# These options get passed to xgettext.
+XGETTEXT_OPTIONS = --keyword=_ --keyword=N_
+
+# This is the copyright holder that gets inserted into the header of the
+# $(DOMAIN).pot file.  Set this to the copyright holder of the surrounding
+# package.  (Note that the msgstr strings, extracted from the package's
+# sources, belong to the copyright holder of the package.)  Translators are
+# expected to transfer the copyright for their translations to this person
+# or entity, or to disclaim their copyright.  The empty string stands for
+# the public domain; in this case the translators are expected to disclaim
+# their copyright.
+COPYRIGHT_HOLDER =
+
+# This is the email address or URL to which the translators shall report
+# bugs in the untranslated strings:
+# - Strings which are not entire sentences, see the maintainer guidelines
+#   in the GNU gettext documentation, section 'Preparing Strings'.
+# - Strings which use unclear terms or require additional context to be
+#   understood.
+# - Strings which make invalid assumptions about notation of date, time or
+#   money.
+# - Pluralisation problems.
+# - Incorrect English spelling.
+# - Incorrect formatting.
+# It can be your email address, or a mailing list address where translators
+# can write to without being subscribed, or the URL of a web page through
+# which the translators can contact you.
+MSGID_BUGS_ADDRESS =
+
+# This is the list of locale categories, beyond LC_MESSAGES, for which the
+# message catalogs shall be used.  It is usually empty.
+EXTRA_LOCALE_CATEGORIES =
+
+# Although you may need slightly wider terminal than 80 chars, it is
+# much nicer to edit the output of --help when this is set.
+XGETTEXT_OPTIONS += --no-wrap
+MSGMERGE += --no-wrap

po/POTFILES.in

@@ -0,0 +1,13 @@
+# List of source files which contain translatable strings.
+src/xz/args.c
+src/xz/coder.c
+src/xz/file_io.c
+src/xz/hardware.c
+src/xz/list.c
+src/xz/main.c
+src/xz/message.c
+src/xz/options.c
+src/xz/signals.c
+src/xz/suffix.c
+src/xz/util.c
+src/common/tuklib_exit.c

po/Rules-quot

@@ -0,0 +1,62 @@
+# Special Makefile rules for English message catalogs with quotation marks.
+#
+# Copyright (C) 2001-2017 Free Software Foundation, Inc.
+# This file, Rules-quot, and its auxiliary files (listed under
+# DISTFILES.common.extra1) are free software; the Free Software Foundation
+# gives unlimited permission to use, copy, distribute, and modify them.
+
+DISTFILES.common.extra1 = quot.sed boldquot.sed en@quot.header en@boldquot.header insert-header.sin Rules-quot
+
+.SUFFIXES: .insert-header .po-update-en
+
+en@quot.po-create:
+	$(MAKE) en@quot.po-update
+en@boldquot.po-create:
+	$(MAKE) en@boldquot.po-update
+
+en@quot.po-update: en@quot.po-update-en
+en@boldquot.po-update: en@boldquot.po-update-en
+
+.insert-header.po-update-en:
+	@lang=`echo $@ | sed -e 's/\.po-update-en$$//'`; \
+	if test "$(PACKAGE)" = "gettext-tools" && test "$(CROSS_COMPILING)" != "yes"; then PATH=`pwd`/../src:$$PATH; GETTEXTLIBDIR=`cd $(top_srcdir)/src && pwd`; export GETTEXTLIBDIR; fi; \
+	tmpdir=`pwd`; \
+	echo "$$lang:"; \
+	ll=`echo $$lang | sed -e 's/@.*//'`; \
+	LC_ALL=C; export LC_ALL; \
+	cd $(srcdir); \
+	if $(MSGINIT) $(MSGINIT_OPTIONS) -i $(DOMAIN).pot --no-translator -l $$lang -o - 2>/dev/null \
+	   | $(SED) -f $$tmpdir/$$lang.insert-header | $(MSGCONV) -t UTF-8 | \
+	   { case `$(MSGFILTER) --version | sed 1q | sed -e 's,^[^0-9]*,,'` in \
+	     '' | 0.[0-9] | 0.[0-9].* | 0.1[0-8] | 0.1[0-8].*) \
+	       $(MSGFILTER) $(SED) -f `echo $$lang | sed -e 's/.*@//'`.sed \
+	       ;; \
+	     *) \
+	       $(MSGFILTER) `echo $$lang | sed -e 's/.*@//'` \
+	       ;; \
+	     esac } 2>/dev/null > $$tmpdir/$$lang.new.po \
+	     ; then \
+	  if cmp $$lang.po $$tmpdir/$$lang.new.po >/dev/null 2>&1; then \
+	    rm -f $$tmpdir/$$lang.new.po; \
+	  else \
+	    if mv -f $$tmpdir/$$lang.new.po $$lang.po; then \
+	      :; \
+	    else \
+	      echo "creation of $$lang.po failed: cannot move $$tmpdir/$$lang.new.po to $$lang.po" 1>&2; \
+	      exit 1; \
+	    fi; \
+	  fi; \
+	else \
+	  echo "creation of $$lang.po failed!" 1>&2; \
+	  rm -f $$tmpdir/$$lang.new.po; \
+	fi
+
+en@quot.insert-header: insert-header.sin
+	sed -e '/^#/d' -e 's/HEADER/en@quot.header/g' $(srcdir)/insert-header.sin > en@quot.insert-header
+
+en@boldquot.insert-header: insert-header.sin
+	sed -e '/^#/d' -e 's/HEADER/en@boldquot.header/g' $(srcdir)/insert-header.sin > en@boldquot.insert-header
+
+mostlyclean: mostlyclean-quot
+mostlyclean-quot:
+	rm -f *.insert-header

po/boldquot.sed

@@ -0,0 +1,10 @@
+s/"\([^"]*\)"/“\1”/g
+s/`\([^`']*\)'/‘\1’/g
+s/ '\([^`']*\)' / ‘\1’ /g
+s/ '\([^`']*\)'$/ ‘\1’/g
+s/^'\([^`']*\)' /‘\1’ /g
+s/“”/""/g
+s/“/“/g
+s/”/”/g
+s/‘/‘/g
+s/’/’/g

po/en@boldquot.header

@@ -0,0 +1,25 @@
+# All this catalog "translates" are quotation characters.
+# The msgids must be ASCII and therefore cannot contain real quotation
+# characters, only substitutes like grave accent (0x60), apostrophe (0x27)
+# and double quote (0x22). These substitutes look strange; see
+# https://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html
+#
+# This catalog translates grave accent (0x60) and apostrophe (0x27) to
+# left single quotation mark (U+2018) and right single quotation mark (U+2019).
+# It also translates pairs of apostrophe (0x27) to
+# left single quotation mark (U+2018) and right single quotation mark (U+2019)
+# and pairs of quotation mark (0x22) to
+# left double quotation mark (U+201C) and right double quotation mark (U+201D).
+#
+# When output to an UTF-8 terminal, the quotation characters appear perfectly.
+# When output to an ISO-8859-1 terminal, the single quotation marks are
+# transliterated to apostrophes (by iconv in glibc 2.2 or newer) or to
+# grave/acute accent (by libiconv), and the double quotation marks are
+# transliterated to 0x22.
+# When output to an ASCII terminal, the single quotation marks are
+# transliterated to apostrophes, and the double quotation marks are
+# transliterated to 0x22.
+#
+# This catalog furthermore displays the text between the quotation marks in
+# bold face, assuming the VT100/XTerm escape sequences.
+#

po/en@quot.header

@@ -0,0 +1,22 @@
+# All this catalog "translates" are quotation characters.
+# The msgids must be ASCII and therefore cannot contain real quotation
+# characters, only substitutes like grave accent (0x60), apostrophe (0x27)
+# and double quote (0x22). These substitutes look strange; see
+# https://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html
+#
+# This catalog translates grave accent (0x60) and apostrophe (0x27) to
+# left single quotation mark (U+2018) and right single quotation mark (U+2019).
+# It also translates pairs of apostrophe (0x27) to
+# left single quotation mark (U+2018) and right single quotation mark (U+2019)
+# and pairs of quotation mark (0x22) to
+# left double quotation mark (U+201C) and right double quotation mark (U+201D).
+#
+# When output to an UTF-8 terminal, the quotation characters appear perfectly.
+# When output to an ISO-8859-1 terminal, the single quotation marks are
+# transliterated to apostrophes (by iconv in glibc 2.2 or newer) or to
+# grave/acute accent (by libiconv), and the double quotation marks are
+# transliterated to 0x22.
+# When output to an ASCII terminal, the single quotation marks are
+# transliterated to apostrophes, and the double quotation marks are
+# transliterated to 0x22.
+#

po/insert-header.sin

@@ -0,0 +1,28 @@
+# Sed script that inserts the file called HEADER before the header entry.
+#
+# Copyright (C) 2001 Free Software Foundation, Inc.
+# Written by Bruno Haible <bruno@clisp.org>, 2001.
+# This file is free software; the Free Software Foundation gives
+# unlimited permission to use, copy, distribute, and modify it.
+#
+# At each occurrence of a line starting with "msgid ", we execute the following
+# commands. At the first occurrence, insert the file. At the following
+# occurrences, do nothing. The distinction between the first and the following
+# occurrences is achieved by looking at the hold space.
+/^msgid /{
+x
+# Test if the hold space is empty.
+s/m/m/
+ta
+# Yes it was empty. First occurrence. Read the file.
+r HEADER
+# Output the file's contents by reading the next line. But don't lose the
+# current line while doing this.
+g
+N
+bb
+:a
+# The hold space was nonempty. Following occurrences. Do nothing.
+x
+:b
+}

po/quot.sed

@@ -0,0 +1,6 @@
+s/"\([^"]*\)"/“\1”/g
+s/`\([^`']*\)'/‘\1’/g
+s/ '\([^`']*\)' / ‘\1’ /g
+s/ '\([^`']*\)'$/ ‘\1’/g
+s/^'\([^`']*\)' /‘\1’ /g
+s/“”/""/g

po/remove-potcdate.sin

@@ -0,0 +1,25 @@
+# Sed script that removes the POT-Creation-Date line in the header entry
+# from a POT file.
+#
+# Copyright (C) 2002 Free Software Foundation, Inc.
+# Copying and distribution of this file, with or without modification,
+# are permitted in any medium without royalty provided the copyright
+# notice and this notice are preserved.  This file is offered as-is,
+# without any warranty.
+#
+# The distinction between the first and the following occurrences of the
+# pattern is achieved by looking at the hold space.
+/^"POT-Creation-Date: .*"$/{
+x
+# Test if the hold space is empty.
+s/P/P/
+ta
+# Yes it was empty. First occurrence. Remove the line.
+g
+d
+bb
+:a
+# The hold space was nonempty. Following occurrences. Do nothing.
+x
+:b
+}