lzip/lzlib
1
0
Fork 0
Code Issues Activity

Adding upstream version 0.3.

Browse source 
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-20 15:51:30 +01:00
parent 025fe9bbb5
commit 2e28a50fca
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
22 changed files with 5877 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
AUTHORS Normal file
View file

@ -0,0 +1,5 @@
Lzlib was written by Antonio Diaz Diaz.
Lzlib implements a simplified version of the LZMA algorithm. The
original LZMA algorithm was designed by Igor Pavlov.

676
COPYING Normal file
View file

@ -0,0 +1,676 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.

21
ChangeLog Normal file
View file

@ -0,0 +1,21 @@
2009-05-03 Antonio Diaz <ant_diaz@teleline.es>
* Version 0.3 released.
* Lzilib is now built as a shared library (in addition to static).
2009-04-26 Antonio Diaz <ant_diaz@teleline.es>
* Version 0.2 released.
* Fixed a segfault when decompressing trailing garbage.
* Fixed a false positive in LZ_(de)compress_finished.
2009-04-21 Antonio Diaz <ant_diaz@teleline.es>
* Version 0.1 released.
Copyright (C) 2009 Antonio Diaz Diaz.
This file is a collection of facts, and thus it is not copyrightable,
but just in case, I give you unlimited permission to copy, distribute
and modify it.

57
INSTALL Normal file
View file

@ -0,0 +1,57 @@
Requirements
------------
You will need a C++ compiler.
I use gcc 4.3.3 and 3.3.6, but the code should compile with any
standards compliant compiler.
Gcc is available at http://gcc.gnu.org.
Procedure
---------
1. Unpack the archive if you have not done so already:
lzip -cd lzlib[version].tar.lz | tar -xf -
or
gzip -cd lzlib[version].tar.gz | tar -xf -
This creates the directory ./lzlib[version] containing the source from
the main archive.
2. Change to lzlib directory and run configure.
(Try `configure --help' for usage instructions).
cd lzlib[version]
./configure
3. Run make.
make
4. Optionally, type `make check' to run the tests that come with lzlib.
5. Type `make install' to install the library and any data files and
documentation. (You might have to run ldconfig also).
Another way
-----------
You can also compile lzlib into a separate directory. To do this, you
must use a version of `make' that supports the `VPATH' variable, such
as GNU `make'. `cd' to the directory where you want the object files
and executables to go and run the `configure' script. `configure'
automatically checks for the source code in `.', in `..' and in the
directory that `configure' is in.
`configure' recognizes the option `--srcdir=DIR' to control where to
look for the sources. Usually `configure' can determine that directory
automatically.
After running `configure', you can run `make' and `make install' as
explained above.
Copyright (C) 2009 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.

134
Makefile.in Normal file
View file

@ -0,0 +1,134 @@
DISTNAME = $(pkgname)-$(pkgversion)
AR = ar
INSTALL = install
INSTALL_PROGRAM = $(INSTALL) -p -m 755
INSTALL_DATA = $(INSTALL) -p -m 644
LDCONFIG = ldconfig
SHELL = /bin/sh
lib_objs = decoder.o encoder.o lzlib.o
sh_lib_objs = sh_decoder.o sh_encoder.o sh_lzlib.o
objs = arg_parser.o main.o
.PHONY : all doc check install install-info \
uninstall uninstall-info \
dist clean distclean
all : $(progname) $(progname_shared)
$(libname).a: $(lib_objs)
$(AR) -rcs $(libname).a $(lib_objs)
$(libname).so.$(pkgversion) : $(sh_lib_objs)
$(CXX) -shared -Wl,--soname=$(libname).so.$(soversion) -o $(libname).so.$(pkgversion) $(sh_lib_objs)
$(progname) : $(objs) $(libname).a
$(CXX) $(LDFLAGS) -o $(progname) $(objs) $(libname).a
$(progname)_shared : $(objs) $(libname).so.$(pkgversion)
$(CXX) $(LDFLAGS) -o $(progname)_shared $(objs) $(libname).so.$(pkgversion)
$(progname)_profiled : $(objs) $(libname).a
$(CXX) $(LDFLAGS) -pg -o $(progname)_profiled $(objs) $(libname).a
main.o : main.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $<
%.o : %.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
sh_decoder.o : decoder.cc
$(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_decoder.o $<
sh_encoder.o : encoder.cc
$(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_encoder.o $<
sh_lzlib.o : lzlib.cc
$(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_lzlib.o $<
$(lib_objs) : Makefile lzlib.h lzip.h
$(sh_lib_objs) : Makefile lzlib.h lzip.h
decoder.o : decoder.h
encoder.o : encoder.h
lzlib.o : decoder.h encoder.h
sh_decoder.o : decoder.h
sh_encoder.o : encoder.h
sh_lzlib.o : decoder.h encoder.h
arg_parser.o : Makefile arg_parser.h
main.o : Makefile arg_parser.h lzlib.h $(libname).a
doc : info $(VPATH)/doc/$(progname).1
info : $(VPATH)/doc/$(pkgname).info
$(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo
cd $(VPATH)/doc && makeinfo $(pkgname).texinfo
$(VPATH)/doc/$(progname).1 : $(progname)
help2man -o $(VPATH)/doc/$(progname).1 ./$(progname)
Makefile : $(VPATH)/configure $(VPATH)/Makefile.in
./config.status
check : all $(VPATH)/testsuite/check.sh
@$(VPATH)/testsuite/check.sh $(VPATH)/testsuite
install : all install-info
if test ! -d $(DESTDIR)$(includedir) ; then $(INSTALL) -d $(DESTDIR)$(includedir) ; fi
if test ! -d $(DESTDIR)$(libdir) ; then $(INSTALL) -d $(DESTDIR)$(libdir) ; fi
$(INSTALL_DATA) $(VPATH)/$(pkgname).h $(DESTDIR)$(includedir)/$(pkgname).h
$(INSTALL_DATA) ./$(libname).a $(DESTDIR)$(libdir)/$(libname).a
if test -n "$(progname_shared)" ; then \
$(INSTALL_PROGRAM) ./$(libname).so.$(pkgversion) $(DESTDIR)$(libdir)/$(libname).so.$(pkgversion) ; \
if test -a $(DESTDIR)$(libdir)/$(libname).so.$(soversion) ; then \
run_ldconfig=no ; rm -f $(DESTDIR)$(libdir)/$(libname).so.$(soversion) ; \
else run_ldconfig=yes ; \
fi ; \
cd $(DESTDIR)$(libdir) && ln -s $(libname).so.$(pkgversion) $(libname).so.$(soversion) ; \
if test $${run_ldconfig} = yes ; then $(LDCONFIG) $(DESTDIR)$(libdir) ; fi ; \
fi
install-info :
if test ! -d $(DESTDIR)$(infodir) ; then $(INSTALL) -d $(DESTDIR)$(infodir) ; fi
$(INSTALL_DATA) $(VPATH)/doc/$(pkgname).info $(DESTDIR)$(infodir)/$(pkgname).info
-install-info --info-dir=$(DESTDIR)$(infodir) $(DESTDIR)$(infodir)/$(pkgname).info
uninstall : uninstall-info
-rm -f $(DESTDIR)$(includedir)/$(pkgname).h
-rm -f $(DESTDIR)$(libdir)/$(libname).a
-rm -f $(DESTDIR)$(libdir)/$(libname).so.$(soversion)
-rm -f $(DESTDIR)$(libdir)/$(libname).so.$(pkgversion)
uninstall-info :
-install-info --remove $(DESTDIR)$(infodir)/$(pkgname).info $(DESTDIR)$(infodir)/dir
-rm -f $(DESTDIR)$(infodir)/$(pkgname).info
dist :
ln -sf $(VPATH) $(DISTNAME)
tar -cvf $(DISTNAME).tar \
$(DISTNAME)/AUTHORS \
$(DISTNAME)/COPYING \
$(DISTNAME)/ChangeLog \
$(DISTNAME)/INSTALL \
$(DISTNAME)/Makefile.in \
$(DISTNAME)/NEWS \
$(DISTNAME)/README \
$(DISTNAME)/configure \
$(DISTNAME)/doc/$(pkgname).info \
$(DISTNAME)/doc/$(pkgname).texinfo \
$(DISTNAME)/testsuite/COPYING.lz \
$(DISTNAME)/testsuite/check.sh \
$(DISTNAME)/*.h \
$(DISTNAME)/*.cc
rm -f $(DISTNAME)
lzip -v -9 $(DISTNAME).tar
clean :
-rm -f $(progname) $(progname)_profiled $(lib_objs) $(objs) *.a
-rm -f $(progname)_shared $(sh_lib_objs) *.so.$(pkgversion)
distclean : clean
-rm -f Makefile config.status *.tar *.tar.lz

3
NEWS Normal file
View file

@ -0,0 +1,3 @@
Changes in version 0.3:
Lzilib is now built as a shared library (in addition to static).

39
README Normal file
View file

@ -0,0 +1,39 @@
Description
The lzlib compression library provides in-memory LZMA compression and
decompression functions, including integrity checking of the
uncompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
library are declared in the file lzlib.h. An usage example of the
library is given in the file main.cc.
Compression/decompression is done by repeteadly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
Lzlib will correctly decompress a data stream which is the concatenation
of two or more compressed data streams. The result is the concatenation
of the corresponding uncompressed data streams. Integrity testing of
concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not install
any signal handler. The decoder checks the consistency of the compressed
data, so the library should never crash even in case of corrupted input.
Lzlib implements a simplified version of the LZMA (Lempel-Ziv-Markov
chain-Algorithm) algorithm. The original LZMA algorithm was designed by
Igor Pavlov. For a description of the LZMA algorithm, see the Lzip
manual.
Copyright (C) 2009 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.
The file Makefile.in is a data file used by configure to produce the
Makefile. It has the same copyright owner and permissions that this
file.

193
arg_parser.cc Normal file
View file

@ -0,0 +1,193 @@
/* Arg_parser - A POSIX/GNU command line argument parser.
Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz.
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 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <cstring>
#include <string>
#include <vector>
#include "arg_parser.h"
bool Arg_parser::parse_long_option( const char * const opt, const char * const arg,
const Option options[], int & argind )
{
unsigned int len;
int index = -1;
bool exact = false, ambig = false;
for( len = 0; opt[len+2] && opt[len+2] != '='; ++len ) ;
// Test all long options for either exact match or abbreviated matches.
for( int i = 0; options[i].code != 0; ++i )
if( options[i].name && !std::strncmp( options[i].name, &opt[2], len ) )
{
if( std::strlen( options[i].name ) == len ) // Exact match found
{ index = i; exact = true; break; }
else if( index < 0 ) index = i; // First nonexact match found
else if( options[index].code != options[i].code ||
options[index].has_arg != options[i].has_arg )
ambig = true; // Second or later nonexact match found
}
if( ambig && !exact )
{
error_ = "option `"; error_ += opt; error_ += "' is ambiguous";
return false;
}
if( index < 0 ) // nothing found
{
error_ = "unrecognized option `"; error_ += opt; error_ += '\'';
return false;
}
++argind;
data.push_back( Record( options[index].code ) );
if( opt[len+2] ) // `--<long_option>=<argument>' syntax
{
if( options[index].has_arg == no )
{
error_ = "option `--"; error_ += options[index].name;
error_ += "' doesn't allow an argument";
return false;
}
if( options[index].has_arg == yes && !opt[len+3] )
{
error_ = "option `--"; error_ += options[index].name;
error_ += "' requires an argument";
return false;
}
data.back().argument = &opt[len+3];
return true;
}
if( options[index].has_arg == yes )
{
if( !arg || !arg[0] )
{
error_ = "option `--"; error_ += options[index].name;
error_ += "' requires an argument";
return false;
}
++argind; data.back().argument = arg;
return true;
}
return true;
}
bool Arg_parser::parse_short_option( const char * const opt, const char * const arg,
const Option options[], int & argind )
{
int cind = 1; // character index in opt
while( cind > 0 )
{
int index = -1;
const unsigned char c = opt[cind];
if( c != 0 )
for( int i = 0; options[i].code; ++i )
if( c == options[i].code )
{ index = i; break; }
if( index < 0 )
{
error_ = "invalid option -- "; error_ += c;
return false;
}
data.push_back( Record( c ) );
if( opt[++cind] == 0 ) { ++argind; cind = 0; } // opt finished
if( options[index].has_arg != no && cind > 0 && opt[cind] )
{
data.back().argument = &opt[cind]; ++argind; cind = 0;
}
else if( options[index].has_arg == yes )
{
if( !arg || !arg[0] )
{
error_ = "option requires an argument -- "; error_ += c;
return false;
}
data.back().argument = arg; ++argind; cind = 0;
}
}
return true;
}
Arg_parser::Arg_parser( const int argc, const char * const argv[],
const Option options[], const bool in_order )
{
if( argc < 2 || !argv || !options ) return;
std::vector< std::string > non_options; // skipped non-options
int argind = 1; // index in argv
while( argind < argc )
{
const unsigned char ch1 = argv[argind][0];
const unsigned char ch2 = ( ch1 ? argv[argind][1] : 0 );
if( ch1 == '-' && ch2 ) // we found an option
{
const char * const opt = argv[argind];
const char * const arg = (argind + 1 < argc) ? argv[argind+1] : 0;
if( ch2 == '-' )
{
if( !argv[argind][2] ) { ++argind; break; } // we found "--"
else if( !parse_long_option( opt, arg, options, argind ) ) break;
}
else if( !parse_short_option( opt, arg, options, argind ) ) break;
}
else
{
if( !in_order ) non_options.push_back( argv[argind++] );
else { data.push_back( Record() ); data.back().argument = argv[argind++]; }
}
}
if( error_.size() ) data.clear();
else
{
for( unsigned int i = 0; i < non_options.size(); ++i )
{ data.push_back( Record() ); data.back().argument.swap( non_options[i] ); }
while( argind < argc )
{ data.push_back( Record() ); data.back().argument = argv[argind++]; }
}
}
Arg_parser::Arg_parser( const char * const opt, const char * const arg,
const Option options[] )
{
if( !opt || !opt[0] || !options ) return;
if( opt[0] == '-' && opt[1] ) // we found an option
{
int argind = 1; // dummy
if( opt[1] == '-' )
{ if( opt[2] ) parse_long_option( opt, arg, options, argind ); }
else
parse_short_option( opt, arg, options, argind );
if( error_.size() ) data.clear();
}
else { data.push_back( Record() ); data.back().argument = opt; }
}

95
arg_parser.h Normal file
View file

@ -0,0 +1,95 @@
/* Arg_parser - A POSIX/GNU command line argument parser.
Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz.
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 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
/* Arg_parser reads the arguments in `argv' and creates a number of
option codes, option arguments and non-option arguments.
In case of error, `error' returns a non-empty error message.
`options' is an array of `struct Option' terminated by an element
containing a code which is zero. A null name means a short-only
option. A code value outside the unsigned char range means a
long-only option.
Arg_parser normally makes it appear as if all the option arguments
were specified before all the non-option arguments for the purposes
of parsing, even if the user of your program intermixed option and
non-option arguments. If you want the arguments in the exact order
the user typed them, call `Arg_parser' with `in_order' = true.
The argument `--' terminates all options; any following arguments are
treated as non-option arguments, even if they begin with a hyphen.
The syntax for optional option arguments is `-<short_option><argument>'
(without whitespace), or `--<long_option>=<argument>'.
*/
class Arg_parser
{
public:
enum Has_arg { no, yes, maybe };
struct Option
{
int code; // Short option letter or code ( code != 0 )
const char * name; // Long option name (maybe null)
Has_arg has_arg;
};
private:
struct Record
{
int code;
std::string argument;
Record( const int c = 0 ) : code( c ) {}
};
std::string error_;
std::vector< Record > data;
bool parse_long_option( const char * const opt, const char * const arg,
const Option options[], int & argind );
bool parse_short_option( const char * const opt, const char * const arg,
const Option options[], int & argind );
public:
Arg_parser( const int argc, const char * const argv[],
const Option options[], const bool in_order = false );
// Restricted constructor. Parses a single token and argument (if any)
Arg_parser( const char * const opt, const char * const arg,
const Option options[] );
const std::string & error() const throw() { return error_; }
// The number of arguments parsed (may be different from argc)
int arguments() const throw() { return data.size(); }
// If code( i ) is 0, argument( i ) is a non-option.
// Else argument( i ) is the option's argument (or empty).
int code( const int i ) const throw()
{
if( i >= 0 && i < arguments() ) return data[i].code;
else return 0;
}
const std::string & argument( const int i ) const throw()
{
if( i >= 0 && i < arguments() ) return data[i].argument;
else return error_;
}
};

237
configure vendored Executable file
View file

@ -0,0 +1,237 @@
#! /bin/sh
# configure script for Lzlib - A compression library for lzip files
# Copyright (C) 2009 Antonio Diaz Diaz.
#
# This configure script is free software: you have unlimited permission
# to copy, distribute and modify it.
#
# Date of this version: 2009-05-03
invocation_name=$0
args=
no_create=
pkgname=lzlib
pkgversion=0.3
soversion=0
progname=minilzip
progname_shared=${progname}_shared
libname=liblz
srctrigger=${pkgname}.h
# clear some things potentially inherited from environment.
LC_ALL=C
export LC_ALL
srcdir=
prefix=/usr/local
exec_prefix='$(prefix)'
bindir='$(exec_prefix)/bin'
datadir='$(prefix)/share'
includedir='${prefix}/include'
infodir='$(datadir)/info'
libdir='${exec_prefix}/lib'
mandir='$(datadir)/man'
sysconfdir='$(prefix)/etc'
CC=
CXX=
CPPFLAGS=
CFLAGS='-Wall -W -O2'
CXXFLAGS='-Wall -W -O2'
LDFLAGS=
# Loop over all args
while [ x"$1" != x ] ; do
# Get the first arg, and shuffle
option=$1
shift
# Add the argument quoted to args
args="${args} \"${option}\""
# Split out the argument for options that take them
case ${option} in
*=*) optarg=`echo ${option} | sed -e 's,^[^=]*=,,'` ;;
esac
# Process the options
case ${option} in
--help | --he* | -h)
echo "Usage: configure [options]"
echo
echo "Options: [defaults in brackets]"
echo " -h, --help display this help and exit"
echo " -V, --version output version information and exit"
echo " --srcdir=DIR find the sources in DIR [. or ..]"
echo " --prefix=DIR install into DIR [${prefix}]"
echo " --exec-prefix=DIR base directory for arch-dependent files [${exec_prefix}]"
echo " --bindir=DIR user executables directory [${bindir}]"
echo " --datadir=DIR base directory for doc and data [${datadir}]"
echo " --includedir=DIR C header files [${includedir}]"
echo " --infodir=DIR info files directory [${infodir}]"
echo " --libdir=DIR object code libraries [${libdir}]"
echo " --mandir=DIR man pages directory [${mandir}]"
echo " --sysconfdir=DIR read-only single-machine data directory [${sysconfdir}]"
echo " --disable-shared do not build a shared library [enable]"
echo " CC=COMPILER C compiler to use [gcc]"
echo " CXX=COMPILER C++ compiler to use [g++]"
echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]"
echo " CFLAGS=OPTIONS command line options for the C compiler [${CFLAGS}]"
echo " CXXFLAGS=OPTIONS command line options for the C++ compiler [${CXXFLAGS}]"
echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]"
echo
exit 0 ;;
--version | --ve* | -V)
echo "Configure script for ${pkgname} version ${pkgversion}"
exit 0 ;;
--srcdir* | --sr*)
srcdir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--prefix* | --pr*)
prefix=`echo ${optarg} | sed -e 's,/$,,'` ;;
--exec-prefix* | --ex*)
exec_prefix=`echo ${optarg} | sed -e 's,/$,,'` ;;
--bindir* | --bi*)
bindir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--datadir* | --da*)
datadir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--includedir* | --inc*)
includedir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--infodir* | --inf*)
infodir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--libdir* | --li*)
libdir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--mandir* | --ma*)
mandir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--sysconfdir* | --sy*)
sysconfdir=`echo ${optarg} | sed -e 's,/$,,'` ;;
--no-create | --no-c*)
no_create=yes ;;
--disable-shared | --disable-s*)
progname_shared= ;;
CC=*) CC=${optarg} ;;
CXX=*) CXX=${optarg} ;;
CPPFLAGS=*) CPPFLAGS=${optarg} ;;
CFLAGS=*) CFLAGS=${optarg} ;;
CXXFLAGS=*) CXXFLAGS=${optarg} ;;
LDFLAGS=*) LDFLAGS=${optarg} ;;
--build=* | --enable-* | --with-* | --*dir=* | *=* | *-*-*) ;;
*)
echo "configure: Unrecognized option: \"${option}\"; use --help for usage." 1>&2
exit 1 ;;
esac
done
# Find the source files, if location was not specified.
srcdirtext=
if [ x"${srcdir}" = x ] ; then
srcdirtext="or . or .." ; srcdir=.
if [ ! -r ${srcdir}/${srctrigger} ] ; then srcdir=.. ; fi
if [ ! -r ${srcdir}/${srctrigger} ] ; then
## the sed command below emulates the dirname command
srcdir=`echo ${invocation_name} | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'`
fi
fi
if [ ! -r ${srcdir}/${srctrigger} ] ; then
exec 1>&2
echo
echo "configure: Can't find sources in ${srcdir} ${srcdirtext}"
echo "configure: (At least ${srctrigger} is missing)."
exit 1
fi
# Set srcdir to . if that's what it is.
if [ "`pwd`" = "`cd ${srcdir} ; pwd`" ] ; then srcdir=. ; fi
# checking whether we are using GNU C.
if [ x"${CC}" = x ] ; then # Let the user override the test.
if [ -x /bin/gcc ] ||
[ -x /usr/bin/gcc ] ||
[ -x /usr/local/bin/gcc ] ; then
CC="gcc"
else
CC="cc"
fi
fi
# checking whether we are using GNU C++.
if [ x"${CXX}" = x ] ; then # Let the user override the test.
if [ -x /bin/g++ ] ||
[ -x /usr/bin/g++ ] ||
[ -x /usr/local/bin/g++ ] ; then
CXX="g++"
else
CXX="c++"
fi
fi
echo
if [ x${no_create} = x ] ; then
echo "creating config.status"
rm -f config.status
cat > config.status << EOF
#! /bin/sh
# This file was generated automatically by configure. Do not edit.
# Run this file to recreate the current configuration.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
exec /bin/sh ${invocation_name} ${args} --no-create
EOF
chmod +x config.status
fi
echo "creating Makefile"
echo "VPATH = ${srcdir}"
echo "prefix = ${prefix}"
echo "exec_prefix = ${exec_prefix}"
echo "bindir = ${bindir}"
echo "datadir = ${datadir}"
echo "includedir = ${includedir}"
echo "infodir = ${infodir}"
echo "libdir = ${libdir}"
echo "mandir = ${mandir}"
echo "sysconfdir = ${sysconfdir}"
echo "CC = ${CC}"
echo "CXX = ${CXX}"
echo "CPPFLAGS = ${CPPFLAGS}"
echo "CFLAGS = ${CFLAGS}"
echo "CXXFLAGS = ${CXXFLAGS}"
echo "LDFLAGS = ${LDFLAGS}"
rm -f Makefile
cat > Makefile << EOF
# Makefile for Lzlib - A compression library for lzip files
# Copyright (C) 2009 Antonio Diaz Diaz.
# This file was generated automatically by configure. Do not edit.
#
# This Makefile is free software: you have unlimited permission
# to copy, distribute and modify it.
pkgname = ${pkgname}
pkgversion = ${pkgversion}
soversion = ${soversion}
progname = ${progname}
progname_shared = ${progname_shared}
libname = ${libname}
VPATH = ${srcdir}
prefix = ${prefix}
exec_prefix = ${exec_prefix}
bindir = ${bindir}
datadir = ${datadir}
includedir = ${includedir}
infodir = ${infodir}
libdir = ${libdir}
mandir = ${mandir}
sysconfdir = ${sysconfdir}
CC = ${CC}
CXX = ${CXX}
CPPFLAGS = ${CPPFLAGS}
CFLAGS = ${CFLAGS}
CXXFLAGS = ${CXXFLAGS}
LDFLAGS = ${LDFLAGS}
EOF
cat ${srcdir}/Makefile.in >> Makefile
echo "OK. Now you can run make."

207
decoder.cc Normal file
View file

@ -0,0 +1,207 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
#define _FILE_OFFSET_BITS 64
#include <algorithm>
#include <cerrno>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <stdint.h>
#include "lzlib.h"
#include "lzip.h"
#include "decoder.h"
const CRC32 crc32;
int Circular_buffer::read_data( uint8_t * const out_buffer, const int out_size ) throw()
{
int size = 0;
if( get > put )
{
size = std::min( buffer_size - get, out_size );
if( size > 0 )
{
std::memmove( out_buffer, buffer + get, size );
get += size;
if( get >= buffer_size ) get = 0;
}
}
if( get < put )
{
const int size2 = std::min( put - get, out_size - size );
if( size2 > 0 )
{
std::memmove( out_buffer + size, buffer + get, size2 );
get += size2;
size += size2;
}
}
return size;
}
int Circular_buffer::write_data( uint8_t * const in_buffer, const int in_size ) throw()
{
int size = 0;
if( put >= get )
{
size = std::min( buffer_size - put - (get == 0), in_size );
if( size > 0 )
{
std::memmove( buffer + put, in_buffer, size );
put += size;
if( put >= buffer_size ) put = 0;
}
}
if( put < get )
{
const int size2 = std::min( get - put - 1, in_size - size );
if( size2 > 0 )
{
std::memmove( buffer + put, in_buffer + size, size2 );
put += size2;
size += size2;
}
}
return size;
}
bool LZ_decoder::verify_trailer()
{
bool error = false;
File_trailer trailer;
const int trailer_size = trailer.size( format_version );
for( int i = 0; i < trailer_size && !error; ++i )
{
if( range_decoder.finished() ) error = true;
((uint8_t *)&trailer)[i] = range_decoder.get_byte();
}
if( format_version == 0 ) trailer.member_size( member_position() );
if( trailer.data_crc() != crc() ) error = true;
if( trailer.data_size() != data_position() ) error = true;
if( trailer.member_size() != member_position() ) error = true;
return !error;
}
// Return value: 0 = OK, 1 = decoder error, 2 = unexpected EOF,
// 3 = trailer error, 4 = unknown marker found.
int LZ_decoder::decode_member()
{
if( member_finished_ ) return 0;
while( true )
{
if( range_decoder.available_bytes() <= 0 ||
( !range_decoder.at_stream_end() &&
range_decoder.available_bytes() < min_available_bytes ) )
return 0; // need more data
if( free_bytes() < max_match_len ) return 0;
if( range_decoder.finished() ) return 2;
const int pos_state = data_position() & pos_state_mask;
if( range_decoder.decode_bit( bm_match[state()][pos_state] ) == 0 )
{
if( state.is_char() )
prev_byte = literal_decoder.decode( range_decoder, prev_byte );
else
prev_byte = literal_decoder.decode_matched( range_decoder, prev_byte,
get_byte( rep0 ) );
put_byte( prev_byte );
state.set_char();
}
else
{
int len;
if( range_decoder.decode_bit( bm_rep[state()] ) == 1 )
{
len = 0;
if( range_decoder.decode_bit( bm_rep0[state()] ) == 0 )
{
if( range_decoder.decode_bit( bm_len[state()][pos_state] ) == 0 )
{ len = 1; state.set_short_rep(); }
}
else
{
unsigned int distance;
if( range_decoder.decode_bit( bm_rep1[state()] ) == 0 )
distance = rep1;
else
{
if( range_decoder.decode_bit( bm_rep2[state()] ) == 0 )
distance = rep2;
else { distance = rep3; rep3 = rep2; }
rep2 = rep1;
}
rep1 = rep0;
rep0 = distance;
}
if( len == 0 )
{
len = min_match_len + rep_match_len_decoder.decode( range_decoder, pos_state );
state.set_rep();
}
}
else
{
rep3 = rep2; rep2 = rep1; rep1 = rep0;
len = min_match_len + len_decoder.decode( range_decoder, pos_state );
state.set_match();
const int dis_slot = range_decoder.decode_tree( bm_dis_slot[get_dis_state(len)], dis_slot_bits );
if( dis_slot < start_dis_model ) rep0 = dis_slot;
else
{
const int direct_bits = ( dis_slot >> 1 ) - 1;
rep0 = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
if( dis_slot < end_dis_model )
rep0 += range_decoder.decode_tree_reversed( bm_dis + rep0 - dis_slot, direct_bits );
else
{
rep0 += range_decoder.decode( direct_bits - dis_align_bits ) << dis_align_bits;
rep0 += range_decoder.decode_tree_reversed( bm_align, dis_align_bits );
if( rep0 == 0xFFFFFFFF ) // Marker found
{
if( len == min_match_len ) // End Of Stream marker
{
member_finished_ = true;
if( verify_trailer() ) return 0; else return 3;
}
return 4;
}
}
}
}
if( !copy_block( rep0, len ) ) return 1;
prev_byte = get_byte( 0 );
}
}
}

282
decoder.h Normal file
View file

@ -0,0 +1,282 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
const int min_available_bytes = 8 + sizeof( File_trailer );
class Input_buffer : public Circular_buffer
{
bool at_stream_end_;
public:
Input_buffer()
:
Circular_buffer( 65536 + min_available_bytes ),
at_stream_end_( false ) {}
bool at_stream_end() const throw() { return at_stream_end_; }
void finish() throw() { at_stream_end_ = true; }
bool finished() const throw() { return at_stream_end_ && !used_bytes(); }
void purge() throw() { at_stream_end_ = true; Circular_buffer::reset(); }
int write_data( uint8_t * const in_buffer, const int in_size ) throw()
{
if( at_stream_end_ || in_size <= 0 ) return 0;
return Circular_buffer::write_data( in_buffer, in_size );
}
};
class Range_decoder
{
mutable long long member_pos;
uint32_t code;
uint32_t range;
Input_buffer & ibuf;
public:
Range_decoder( const int header_size, Input_buffer & buf )
:
member_pos( header_size ),
code( 0 ),
range( 0xFFFFFFFF ),
ibuf( buf )
{ for( int i = 0; i < 5; ++i ) code = (code << 8) | get_byte(); }
uint8_t get_byte() const
{
++member_pos;
return ibuf.get_byte();
}
bool at_stream_end() const throw() { return ibuf.at_stream_end(); }
int available_bytes() const throw() { return ibuf.used_bytes(); }
bool finished() const throw() { return ibuf.finished(); }
long long member_position() const throw() { return member_pos; }
int decode( const int num_bits )
{
int symbol = 0;
for( int i = num_bits - 1; i >= 0; --i )
{
range >>= 1;
symbol <<= 1;
if( code >= range )
{ code -= range; symbol |= 1; }
if( range <= 0x00FFFFFF )
{ range <<= 8; code = (code << 8) | get_byte(); }
}
return symbol;
}
int decode_bit( Bit_model & bm )
{
int symbol;
const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability;
if( code < bound )
{
range = bound;
bm.probability += (bit_model_total - bm.probability) >> bit_model_move_bits;
symbol = 0;
}
else
{
range -= bound;
code -= bound;
bm.probability -= bm.probability >> bit_model_move_bits;
symbol = 1;
}
if( range <= 0x00FFFFFF )
{ range <<= 8; code = (code << 8) | get_byte(); }
return symbol;
}
int decode_tree( Bit_model bm[], const int num_bits )
{
int model = 1;
for( int i = num_bits; i > 0; --i )
model = ( model << 1 ) | decode_bit( bm[model-1] );
return model - (1 << num_bits);
}
int decode_tree_reversed( Bit_model bm[], const int num_bits )
{
int model = 1;
int symbol = 0;
for( int i = 1; i < (1 << num_bits); i <<= 1 )
{
const int bit = decode_bit( bm[model-1] );
model = ( model << 1 ) | bit;
if( bit ) symbol |= i;
}
return symbol;
}
int decode_matched( Bit_model bm[], const int match_byte )
{
int symbol = 1;
for( int i = 7; i >= 0; --i )
{
const int match_bit = ( match_byte >> i ) & 1;
const int bit = decode_bit( bm[(match_bit<<8)+symbol+0xFF] );
symbol = ( symbol << 1 ) | bit;
if( match_bit != bit ) break;
}
while( symbol < 0x100 )
symbol = ( symbol << 1 ) | decode_bit( bm[symbol-1] );
return symbol & 0xFF;
}
};
class Len_decoder
{
Bit_model choice1;
Bit_model choice2;
Bit_model bm_low[pos_states][len_low_symbols];
Bit_model bm_mid[pos_states][len_mid_symbols];
Bit_model bm_high[len_high_symbols];
public:
int decode( Range_decoder & range_decoder, const int pos_state )
{
if( range_decoder.decode_bit( choice1 ) == 0 )
return range_decoder.decode_tree( bm_low[pos_state], len_low_bits );
if( range_decoder.decode_bit( choice2 ) == 0 )
return len_low_symbols +
range_decoder.decode_tree( bm_mid[pos_state], len_mid_bits );
return len_low_symbols + len_mid_symbols +
range_decoder.decode_tree( bm_high, len_high_bits );
}
};
class Literal_decoder
{
Bit_model bm_literal[1<<literal_context_bits][0x300];
int state( const int prev_byte ) const throw()
{ return ( prev_byte >> ( 8 - literal_context_bits ) ); }
public:
uint8_t decode( Range_decoder & range_decoder, const int prev_byte )
{ return range_decoder.decode_tree( bm_literal[state(prev_byte)], 8 ); }
uint8_t decode_matched( Range_decoder & range_decoder,
const int prev_byte, const int match_byte )
{ return range_decoder.decode_matched( bm_literal[state(prev_byte)], match_byte ); }
};
class LZ_decoder : public Circular_buffer
{
long long partial_data_pos;
const int format_version;
const int dictionary_size;
uint32_t crc_;
bool member_finished_;
unsigned int rep0;
unsigned int rep1;
unsigned int rep2;
unsigned int rep3;
State state;
uint8_t prev_byte;
Bit_model bm_match[State::states][pos_states];
Bit_model bm_rep[State::states];
Bit_model bm_rep0[State::states];
Bit_model bm_rep1[State::states];
Bit_model bm_rep2[State::states];
Bit_model bm_len[State::states][pos_states];
Bit_model bm_dis_slot[max_dis_states][1<<dis_slot_bits];
Bit_model bm_dis[modeled_distances-end_dis_model];
Bit_model bm_align[dis_align_size];
Range_decoder range_decoder;
Len_decoder len_decoder;
Len_decoder rep_match_len_decoder;
Literal_decoder literal_decoder;
// using Circular_buffer::get_byte;
uint8_t get_byte( const int distance ) const throw()
{
int i = put - distance - 1;
if( i < 0 ) i += buffer_size;
return buffer[i];
}
void put_byte( const uint8_t b )
{
crc32.update( crc_, b );
buffer[put] = b;
if( ++put >= buffer_size ) { partial_data_pos += put; put = 0; }
}
bool copy_block( const int distance, int len )
{
if( distance < 0 || distance >= dictionary_size ||
len <= 0 || len > max_match_len ) return false;
int i = put - distance - 1;
if( i < 0 ) i += buffer_size;
for( ; len > 0 ; --len )
{
crc32.update( crc_, buffer[i] );
buffer[put] = buffer[i];
if( ++put >= buffer_size ) { partial_data_pos += put; put = 0; }
if( ++i >= buffer_size ) i = 0;
}
return true;
}
bool verify_trailer();
public:
LZ_decoder( const File_header & header, Input_buffer & ibuf )
:
Circular_buffer( std::max( 65536, header.dictionary_size() ) + max_match_len ),
partial_data_pos( 0 ),
format_version( header.version ),
dictionary_size( header.dictionary_size() ),
crc_( 0xFFFFFFFF ),
member_finished_( false ),
rep0( 0 ),
rep1( 0 ),
rep2( 0 ),
rep3( 0 ),
prev_byte( 0 ),
range_decoder( sizeof header, ibuf ),
literal_decoder() {}
uint32_t crc() const throw() { return crc_ ^ 0xFFFFFFFF; }
int decode_member();
bool member_finished() const throw()
{ return ( member_finished_ && !used_bytes() ); }
long long member_position() const throw()
{ return range_decoder.member_position(); }
long long data_position() const throw()
{ return partial_data_pos + put; }
};

487
doc/lzlib.info Normal file
View file

@ -0,0 +1,487 @@
This is lzlib.info, produced by makeinfo version 4.13 from
lzlib.texinfo.
INFO-DIR-SECTION Data Compression
START-INFO-DIR-ENTRY
* Lzlib: (lzlib). A compression library for lzip files
END-INFO-DIR-ENTRY

File: lzlib.info, Node: Top, Next: Introduction, Up: (dir)
Lzlib
*****
This manual is for Lzlib (version 0.3, 3 May 2009).
* Menu:
* Introduction:: Purpose and features of Lzlib
* Library Version:: Checking library version
* Compression Functions:: Descriptions of the compression functions
* Decompression Functions:: Descriptions of the decompression functions
* Error Codes:: Meaning of codes returned by functions
* Data Format:: Detailed format of the compressed data
* Examples:: A small tutorial with examples
* Problems:: Reporting bugs
* Concept Index:: Index of concepts
Copyright (C) 2009 Antonio Diaz Diaz.
This manual is free documentation: you have unlimited permission to
copy, distribute and modify it.

File: lzlib.info, Node: Introduction, Next: Library Version, Prev: Top, Up: Top
1 Introduction
**************
The lzlib compression library provides in-memory LZMA compression and
decompression functions, including integrity checking of the
uncompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
library are declared in the file `lzlib.h'. An usage example of the
library is given in the file main.cc.
Compression/decompression is done by repeteadly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
Lzlib will correctly decompress a data stream which is the
concatenation of two or more compressed data streams. The result is the
concatenation of the corresponding uncompressed data streams. Integrity
testing of concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not
install any signal handler. The decoder checks the consistency of the
compressed data, so the library should never crash even in case of
corrupted input.
Lzlib implements a simplified version of the LZMA (Lempel-Ziv-Markov
chain-Algorithm) algorithm. The original LZMA algorithm was designed by
Igor Pavlov. For a description of the LZMA algorithm, see the Lzip
manual.

File: lzlib.info, Node: Library Version, Next: Compression Functions, Prev: Introduction, Up: Top
2 Library Version
*****************
-- Function: const char * LZ_version ( void )
Returns the library version as a string.
-- Constant: const char * LZ_version_string
This constant is defined in the header file `lzlib.h'.
The application should compare LZ_version and LZ_version_string for
consistency. If the first character differs, the library code actually
used may be incompatible with the `lzlib.h' header file used by the
application.
if( LZ_version()[0] != LZ_version_string[0] )
error( "bad library version" );

File: lzlib.info, Node: Compression Functions, Next: Decompression Functions, Prev: Library Version, Up: Top
3 Compression Functions
***********************
These are the functions used to compress data. In case of error, all of
them return -1, except `LZ_compress_open' whose return value must be
verified by calling `LZ_compress_errno' before using it.
-- Function: void * LZ_compress_open ( const int DICTIONARY_SIZE,
const int MATCH_LEN_LIMIT, const long long MEMBER_SIZE )
Initializes the internal stream state for compression and returns a
pointer that can only be used as the ENCODER argument for the
other LZ_compress functions.
The returned pointer must be verified by calling
`LZ_compress_errno' before using it. If `LZ_compress_errno' does
not return `LZ_ok', the returned pointer must not be used and
should be freed with `LZ_compress_close' to avoid memory leaks.
DICTIONARY_SIZE sets the dictionary size to be used, in bytes.
Valid values range from 4KiB to 512MiB. Note that dictionary sizes
are quantized. If the specified size does not match one of the
valid sizes, it will be rounded upwards.
MATCH_LEN_LIMIT sets the match length limit in bytes. Valid values
range from 5 to 273. Larger values usually give better compression
ratios but longer compression times.
MEMBER_SIZE sets the member size limit in bytes. Minimum member
size limit is 100kB. Small member size may degrade compression
ratio, so use it only when needed. To produce a single member data
stream, give MEMBER_SIZE a value larger than the amount of data to
be produced, for example LLONG_MAX.
-- Function: int LZ_compress_close ( void * const ENCODER )
Frees all dynamically allocated data structures for this stream.
This function discards any unprocessed input and does not flush
any pending output. After a call to `LZ_compress_close', ENCODER
can no more be used as an argument to any LZ_compress function.
-- Function: int LZ_compress_finish ( void * const ENCODER )
Use this function to tell `lzlib' that all the data for this stream
has already been written (with the `LZ_compress_write' function).
-- Function: int LZ_compress_finish_member ( void * const ENCODER )
Use this function to tell `lzlib' that all the data for the current
member, in a multimember data stream, has already been written
(with the `LZ_compress_write' function).
-- Function: int LZ_compress_restart_member ( void * const ENCODER,
const long long MEMBER_SIZE )
Use this function to start a new member, in a multimember data
stream. Call this function only after
`LZ_compress_member_finished' indicates that the current member
has been fully read (with the `LZ_compress_read' function).
-- Function: int LZ_compress_read ( void * const ENCODER, uint8_t *
const BUFFER, const int SIZE )
The `LZ_compress_read' function reads up to SIZE bytes from the
stream pointed to by ENCODER, storing the results in BUFFER.
The return value is the number of bytes actually read. This might
be less than SIZE; for example, if there aren't that many bytes
left in the stream or if more bytes have to be yet written with the
`LZ_compress_write' function. Note that reading less than SIZE
bytes is not an error.
-- Function: int LZ_compress_write ( void * const ENCODER, uint8_t *
const BUFFER, const int SIZE )
The `LZ_compress_write' function writes up to SIZE bytes from
BUFFER to the stream pointed to by ENCODER.
The return value is the number of bytes actually written. This
might be less than SIZE. Note that writing less than SIZE bytes is
not an error.
-- Function: enum LZ_errno LZ_compress_errno ( void * const ENCODER )
Returns the current error code for ENCODER (*note Error Codes::)
-- Function: int LZ_compress_finished ( void * const ENCODER )
Returns 1 if all the data has been read and `LZ_compress_close' can
be safely called. Otherwise it returns 0.
-- Function: int LZ_compress_member_finished ( void * const ENCODER )
Returns 1 if the current member, in a multimember data stream, has
been fully read and `LZ_compress_restart_member' can be safely
called. Otherwise it returns 0.
-- Function: long long LZ_compress_data_position ( void * const
ENCODER )
Returns the number of input bytes already compressed in the current
member.
-- Function: long long LZ_compress_member_position ( void * const
ENCODER )
Returns the number of compressed bytes already produced, but
perhaps not yet read, in the current member.
-- Function: long long LZ_compress_total_in_size ( void * const
ENCODER )
Returns the total number of input bytes already compressed.
-- Function: long long LZ_compress_total_out_size ( void * const
ENCODER )
Returns the total number of compressed bytes already produced, but
perhaps not yet read.

File: lzlib.info, Node: Decompression Functions, Next: Error Codes, Prev: Compression Functions, Up: Top
4 Decompression Functions
*************************
These are the functions used to decompress data. In case of error, all
of them return -1, except `LZ_decompress_open' whose return value must
be verified by calling `LZ_decompress_errno' before using it.
-- Function: void * LZ_decompress_open ( void )
Initializes the internal stream state for decompression and
returns a pointer that can only be used as the DECODER argument
for the other LZ_decompress functions.
The returned pointer must be verified by calling
`LZ_decompress_errno' before using it. If `LZ_decompress_errno'
does not return `LZ_ok', the returned pointer must not be used and
should be freed with `LZ_decompress_close' to avoid memory leaks.
-- Function: int LZ_decompress_close ( void * const DECODER )
Frees all dynamically allocated data structures for this stream.
This function discards any unprocessed input and does not flush
any pending output. After a call to `LZ_decompress_close', DECODER
can no more be used as an argument to any LZ_decompress function.
-- Function: int LZ_decompress_finish ( void * const DECODER )
Use this function to tell `lzlib' that all the data for this stream
has already been written (with the `LZ_decompress_write' function).
-- Function: int LZ_decompress_read ( void * const DECODER, uint8_t *
const BUFFER, const int SIZE )
The `LZ_decompress_read' function reads up to SIZE bytes from the
stream pointed to by DECODER, storing the results in BUFFER.
The return value is the number of bytes actually read. This might
be less than SIZE; for example, if there aren't that many bytes
left in the stream or if more bytes have to be yet written with the
`LZ_decompress_write' function. Note that reading less than SIZE
bytes is not an error.
-- Function: int LZ_decompress_write ( void * const DECODER, uint8_t *
const BUFFER, const int SIZE )
The `LZ_decompress_write' function writes up to SIZE bytes from
BUFFER to the stream pointed to by DECODER.
The return value is the number of bytes actually written. This
might be less than SIZE. Note that writing less than SIZE bytes is
not an error.
-- Function: enum LZ_errno LZ_decompress_errno ( void * const DECODER )
Returns the current error code for DECODER (*note Error Codes::)
-- Function: int LZ_decompress_finished ( void * const DECODER )
Returns 1 if all the data has been read and `LZ_decompress_close'
can be safely called. Otherwise it returns 0.
-- Function: long long LZ_decompress_data_position ( void * const
DECODER )
Returns the number of decompressed bytes already produced, but
perhaps not yet read, in the current member.
-- Function: long long LZ_decompress_member_position ( void * const
DECODER )
Returns the number of input bytes already decompressed in the
current member.
-- Function: long long LZ_decompress_total_in_size ( void * const
DECODER )
Returns the total number of input bytes already decompressed.
-- Function: long long LZ_decompress_total_out_size ( void * const
DECODER )
Returns the total number of decompressed bytes already produced,
but perhaps not yet read.

File: lzlib.info, Node: Error Codes, Next: Data Format, Prev: Decompression Functions, Up: Top
5 Error Codes
*************
Most library functions return -1 to indicate that they have failed. But
this return value only tells you that an error has occurred. To find out
what kind of error it was, you need to verify the error code by calling
`LZ_(de)compress_errno'.
Library functions do not change the value returned by
`LZ_(de)compress_errno' when they succeed; thus, the value returned by
`LZ_(de)compress_errno' after a successful call is not necessarily
zero, and you should not use `LZ_(de)compress_errno' to determine
whether a call failed. If the call failed, then you can examine
`LZ_(de)compress_errno'.
The error codes are defined in the header file `lzlib.h'.
-- Constant: enum LZ_errno LZ_ok
The value of this constant is 0 and is used to indicate that there
is no error.
-- Constant: enum LZ_errno LZ_bad_argument
At least one of the arguments passed to the library function was
invalid.
-- Constant: enum LZ_errno LZ_mem_error
No memory available. The system cannot allocate more virtual memory
because its capacity is full.
-- Constant: enum LZ_errno LZ_sequence_error
A library function was called in the wrong order. For example
`LZ_compress_restart_member' was called before
`LZ_compress_member_finished' indicates that the current member is
finished.
-- Constant: enum LZ_errno LZ_header_error
Reading of member header failed. If this happens at the end of the
data stream it may indicate trailing garbage.
-- Constant: enum LZ_errno LZ_unexpected_eof
The end of the data stream was reached in the middle of a member.
-- Constant: enum LZ_errno LZ_data_error
The data stream is corrupt.
-- Constant: enum LZ_errno LZ_library_error
A bug was detected in the library. Please, report it (*note
Problems::).

File: lzlib.info, Node: Data Format, Next: Examples, Prev: Error Codes, Up: Top
6 Data Format
*************
In the diagram below, a box like this:
+---+
| | <-- the vertical bars might be missing
+---+
represents one byte; a box like this:
+==============+
| |
+==============+
represents a variable number of bytes.
A lzip data stream consists of a series of "members" (compressed data
sets). The members simply appear one after another in the data stream,
with no additional information before, between, or after them.
Each member has the following structure:
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| ID string | VN | DS | Lzma stream | CRC32 | Data size | Member size |
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
All multibyte values are stored in little endian order.
`ID string'
A four byte string, identifying the member type, with the value
"LZIP".
`VN (version number, 1 byte)'
Just in case something needs to be modified in the future. Valid
values are 0 and 1. Version 0 files have only one member and lack
`Member size'.
`DS (coded dictionary size, 1 byte)'
Bits 4-0 contain the base 2 logarithm of the base dictionary size.
Bits 7-5 contain the number of "wedges" to substract from the base
dictionary size to obtain the dictionary size. The size of a wedge
is (base dictionary size / 16).
Valid values for dictionary size range from 4KiB to 512MiB.
`Lzma stream'
The lzma stream, finished by an end of stream marker. Uses default
values for encoder properties.
`CRC32 (4 bytes)'
CRC of the uncompressed original data.
`Data size (8 bytes)'
Size of the uncompressed original data.
`Member size (8 bytes)'
Total size of the member, including header and trailer. This
facilitates safe recovery of undamaged members from multimember
files.

File: lzlib.info, Node: Examples, Next: Problems, Prev: Data Format, Up: Top
7 A small tutorial with examples
********************************
This chaper shows the order in which the library functions should be
called depending on what kind of data stream you want to compress or
decompress.
Example 1: Normal compression (MEMBER_SIZE > total output).
1) LZ_compress_open
2) LZ_compress_write
3) LZ_compress_read
4) go back to step 2 until all input data has been written
5) LZ_compress_finish
6) LZ_compress_read
7) go back to step 6 until LZ_compress_read returns 0
8) LZ_compress_close
Example 2: Decompression.
1) LZ_decompress_open
2) LZ_decompress_write
3) LZ_decompress_read
4) go back to step 2 until all input data has been written
5) LZ_decompress_finish
6) LZ_decompress_read
7) go back to step 6 until LZ_decompress_read returns 0
8) LZ_decompress_close
Example 3: Multimember compression (MEMBER_SIZE < total output).
1) LZ_compress_open
2) LZ_compress_write
3) LZ_compress_read
4) go back to step 2 until LZ_compress_member_finished returns 1
5) LZ_compress_restart_member
6) go back to step 2 until all input data has been written
7) LZ_compress_finish
8) LZ_compress_read
9) go back to step 8 until LZ_compress_read returns 0
10) LZ_compress_close

File: lzlib.info, Node: Problems, Next: Concept Index, Prev: Examples, Up: Top
8 Reporting Bugs
****************
There are probably bugs in Lzlib. There are certainly errors and
omissions in this manual. If you report them, they will get fixed. If
you don't, no one will ever know about them and they will remain unfixed
for all eternity, if not longer.
If you find a bug in Lzlib, please send electronic mail to
<lzip-bug@nongnu.org>. Include the version number, which you can find
by running `minilzip --version' or in `LZ_version_string' from
`lzlib.h'.

File: lzlib.info, Node: Concept Index, Prev: Problems, Up: Top
Concept Index
*************
[index]
* Menu:
* bugs: Problems. (line 6)
* compression functions: Compression Functions. (line 6)
* data format: Data Format. (line 6)
* decompression functions: Decompression Functions.
(line 6)
* error codes: Error Codes. (line 6)
* examples: Examples. (line 6)
* getting help: Problems. (line 6)
* introduction: Introduction. (line 6)
* library version: Library Version. (line 6)

Tag Table:
Node: Top219
Node: Introduction968
Node: Library Version2428
Node: Compression Functions3085
Node: Decompression Functions8178
Node: Error Codes11616
Node: Data Format13551
Node: Examples15518
Node: Problems16940
Node: Concept Index17510

End Tag Table

535
doc/lzlib.texinfo Normal file
View file

@ -0,0 +1,535 @@
\input texinfo @c -*-texinfo-*-
@c %**start of header
@setfilename lzlib.info
@settitle Lzlib
@finalout
@c %**end of header
@set UPDATED 3 May 2009
@set VERSION 0.3
@dircategory Data Compression
@direntry
* Lzlib: (lzlib). A compression library for lzip files
@end direntry
@titlepage
@title Lzlib
@subtitle A compression library for lzip files
@subtitle for Lzlib version @value{VERSION}, @value{UPDATED}
@author by Antonio Diaz Diaz
@page
@vskip 0pt plus 1filll
@end titlepage
@contents
@node Top
@top
This manual is for Lzlib (version @value{VERSION}, @value{UPDATED}).
@menu
* Introduction:: Purpose and features of Lzlib
* Library Version:: Checking library version
* Compression Functions:: Descriptions of the compression functions
* Decompression Functions:: Descriptions of the decompression functions
* Error Codes:: Meaning of codes returned by functions
* Data Format:: Detailed format of the compressed data
* Examples:: A small tutorial with examples
* Problems:: Reporting bugs
* Concept Index:: Index of concepts
@end menu
@sp 1
Copyright @copyright{} 2009 Antonio Diaz Diaz.
This manual is free documentation: you have unlimited permission
to copy, distribute and modify it.
@node Introduction
@chapter Introduction
@cindex introduction
The lzlib compression library provides in-memory LZMA compression and
decompression functions, including integrity checking of the
uncompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
library are declared in the file @samp{lzlib.h}. An usage example of the
library is given in the file main.cc.
Compression/decompression is done by repeteadly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
Lzlib will correctly decompress a data stream which is the concatenation
of two or more compressed data streams. The result is the concatenation
of the corresponding uncompressed data streams. Integrity testing of
concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not install
any signal handler. The decoder checks the consistency of the compressed
data, so the library should never crash even in case of corrupted input.
Lzlib implements a simplified version of the LZMA (Lempel-Ziv-Markov
chain-Algorithm) algorithm. The original LZMA algorithm was designed by
Igor Pavlov. For a description of the LZMA algorithm, see the Lzip
manual.
@node Library Version
@chapter Library Version
@cindex library version
@deftypefun {const char *} LZ_version ( void )
Returns the library version as a string.
@end deftypefun
@deftypevr Constant {const char *} LZ_version_string
This constant is defined in the header file @samp{lzlib.h}.
@end deftypevr
The application should compare LZ_version and LZ_version_string for
consistency. If the first character differs, the library code actually
used may be incompatible with the @samp{lzlib.h} header file used by the
application.
@example
if( LZ_version()[0] != LZ_version_string[0] )
error( "bad library version" );
@end example
@node Compression Functions
@chapter Compression Functions
@cindex compression functions
These are the functions used to compress data. In case of error, all of
them return -1, except @samp{LZ_compress_open} whose return value must
be verified by calling @samp{LZ_compress_errno} before using it.
@deftypefun {void *} LZ_compress_open ( const int @var{dictionary_size}, const int @var{match_len_limit}, const long long @var{member_size} )
Initializes the internal stream state for compression and returns a
pointer that can only be used as the @var{encoder} argument for the
other LZ_compress functions.
The returned pointer must be verified by calling
@samp{LZ_compress_errno} before using it. If @samp{LZ_compress_errno}
does not return @samp{LZ_ok}, the returned pointer must not be used and
should be freed with @samp{LZ_compress_close} to avoid memory leaks.
@var{dictionary_size} sets the dictionary size to be used, in bytes.
Valid values range from 4KiB to 512MiB. Note that dictionary sizes are
quantized. If the specified size does not match one of the valid sizes,
it will be rounded upwards.
@var{match_len_limit} sets the match length limit in bytes. Valid values
range from 5 to 273. Larger values usually give better compression
ratios but longer compression times.
@var{member_size} sets the member size limit in bytes. Minimum member
size limit is 100kB. Small member size may degrade compression ratio, so
use it only when needed. To produce a single member data stream, give
@var{member_size} a value larger than the amount of data to be produced,
for example LLONG_MAX.
@end deftypefun
@deftypefun int LZ_compress_close ( void * const @var{encoder} )
Frees all dynamically allocated data structures for this stream. This
function discards any unprocessed input and does not flush any pending
output. After a call to @samp{LZ_compress_close}, @var{encoder} can no
more be used as an argument to any LZ_compress function.
@end deftypefun
@deftypefun int LZ_compress_finish ( void * const @var{encoder} )
Use this function to tell @samp{lzlib} that all the data for this stream
has already been written (with the @samp{LZ_compress_write} function).
@end deftypefun
@deftypefun int LZ_compress_finish_member ( void * const @var{encoder} )
Use this function to tell @samp{lzlib} that all the data for the current
member, in a multimember data stream, has already been written (with the
@samp{LZ_compress_write} function).
@end deftypefun
@deftypefun int LZ_compress_restart_member ( void * const @var{encoder}, const long long @var{member_size} )
Use this function to start a new member, in a multimember data stream.
Call this function only after @samp{LZ_compress_member_finished}
indicates that the current member has been fully read (with the
@samp{LZ_compress_read} function).
@end deftypefun
@deftypefun int LZ_compress_read ( void * const @var{encoder}, uint8_t * const @var{buffer}, const int @var{size} )
The @samp{LZ_compress_read} function reads up to @var{size} bytes from
the stream pointed to by @var{encoder}, storing the results in
@var{buffer}.
The return value is the number of bytes actually read. This might be
less than @var{size}; for example, if there aren't that many bytes left
in the stream or if more bytes have to be yet written with the
@samp{LZ_compress_write} function. Note that reading less than
@var{size} bytes is not an error.
@end deftypefun
@deftypefun int LZ_compress_write ( void * const @var{encoder}, uint8_t * const @var{buffer}, const int @var{size} )
The @samp{LZ_compress_write} function writes up to @var{size} bytes from
@var{buffer} to the stream pointed to by @var{encoder}.
The return value is the number of bytes actually written. This might be
less than @var{size}. Note that writing less than @var{size} bytes is
not an error.
@end deftypefun
@deftypefun {enum LZ_errno} LZ_compress_errno ( void * const @var{encoder} )
Returns the current error code for @var{encoder} (@pxref{Error Codes})
@end deftypefun
@deftypefun int LZ_compress_finished ( void * const @var{encoder} )
Returns 1 if all the data has been read and @samp{LZ_compress_close} can
be safely called. Otherwise it returns 0.
@end deftypefun
@deftypefun int LZ_compress_member_finished ( void * const @var{encoder} )
Returns 1 if the current member, in a multimember data stream, has been
fully read and @samp{LZ_compress_restart_member} can be safely called.
Otherwise it returns 0.
@end deftypefun
@deftypefun {long long} LZ_compress_data_position ( void * const @var{encoder} )
Returns the number of input bytes already compressed in the current
member.
@end deftypefun
@deftypefun {long long} LZ_compress_member_position ( void * const @var{encoder} )
Returns the number of compressed bytes already produced, but perhaps not
yet read, in the current member.
@end deftypefun
@deftypefun {long long} LZ_compress_total_in_size ( void * const @var{encoder} )
Returns the total number of input bytes already compressed.
@end deftypefun
@deftypefun {long long} LZ_compress_total_out_size ( void * const @var{encoder} )
Returns the total number of compressed bytes already produced, but
perhaps not yet read.
@end deftypefun
@node Decompression Functions
@chapter Decompression Functions
@cindex decompression functions
These are the functions used to decompress data. In case of error, all
of them return -1, except @samp{LZ_decompress_open} whose return value
must be verified by calling @samp{LZ_decompress_errno} before using it.
@deftypefun {void *} LZ_decompress_open ( void )
Initializes the internal stream state for decompression and returns a
pointer that can only be used as the @var{decoder} argument for the
other LZ_decompress functions.
The returned pointer must be verified by calling
@samp{LZ_decompress_errno} before using it. If
@samp{LZ_decompress_errno} does not return @samp{LZ_ok}, the returned
pointer must not be used and should be freed with
@samp{LZ_decompress_close} to avoid memory leaks.
@end deftypefun
@deftypefun int LZ_decompress_close ( void * const @var{decoder} )
Frees all dynamically allocated data structures for this stream. This
function discards any unprocessed input and does not flush any pending
output. After a call to @samp{LZ_decompress_close}, @var{decoder} can no
more be used as an argument to any LZ_decompress function.
@end deftypefun
@deftypefun int LZ_decompress_finish ( void * const @var{decoder} )
Use this function to tell @samp{lzlib} that all the data for this stream
has already been written (with the @samp{LZ_decompress_write} function).
@end deftypefun
@deftypefun int LZ_decompress_read ( void * const @var{decoder}, uint8_t * const @var{buffer}, const int @var{size} )
The @samp{LZ_decompress_read} function reads up to @var{size} bytes from
the stream pointed to by @var{decoder}, storing the results in
@var{buffer}.
The return value is the number of bytes actually read. This might be
less than @var{size}; for example, if there aren't that many bytes left
in the stream or if more bytes have to be yet written with the
@samp{LZ_decompress_write} function. Note that reading less than
@var{size} bytes is not an error.
@end deftypefun
@deftypefun int LZ_decompress_write ( void * const @var{decoder}, uint8_t * const @var{buffer}, const int @var{size} )
The @samp{LZ_decompress_write} function writes up to @var{size} bytes from
@var{buffer} to the stream pointed to by @var{decoder}.
The return value is the number of bytes actually written. This might be
less than @var{size}. Note that writing less than @var{size} bytes is
not an error.
@end deftypefun
@deftypefun {enum LZ_errno} LZ_decompress_errno ( void * const @var{decoder} )
Returns the current error code for @var{decoder} (@pxref{Error Codes})
@end deftypefun
@deftypefun int LZ_decompress_finished ( void * const @var{decoder} )
Returns 1 if all the data has been read and @samp{LZ_decompress_close}
can be safely called. Otherwise it returns 0.
@end deftypefun
@deftypefun {long long} LZ_decompress_data_position ( void * const @var{decoder} )
Returns the number of decompressed bytes already produced, but perhaps
not yet read, in the current member.
@end deftypefun
@deftypefun {long long} LZ_decompress_member_position ( void * const @var{decoder} )
Returns the number of input bytes already decompressed in the current
member.
@end deftypefun
@deftypefun {long long} LZ_decompress_total_in_size ( void * const @var{decoder} )
Returns the total number of input bytes already decompressed.
@end deftypefun
@deftypefun {long long} LZ_decompress_total_out_size ( void * const @var{decoder} )
Returns the total number of decompressed bytes already produced, but
perhaps not yet read.
@end deftypefun
@node Error Codes
@chapter Error Codes
@cindex error codes
Most library functions return -1 to indicate that they have failed. But
this return value only tells you that an error has occurred. To find out
what kind of error it was, you need to verify the error code by calling
@samp{LZ_(de)compress_errno}.
Library functions do not change the value returned by
@samp{LZ_(de)compress_errno} when they succeed; thus, the value returned
by @samp{LZ_(de)compress_errno} after a successful call is not
necessarily zero, and you should not use @samp{LZ_(de)compress_errno} to
determine whether a call failed. If the call failed, then you can
examine @samp{LZ_(de)compress_errno}.
The error codes are defined in the header file @samp{lzlib.h}.
@deftypevr Constant {enum LZ_errno} LZ_ok
The value of this constant is 0 and is used to indicate that there is no
error.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_bad_argument
At least one of the arguments passed to the library function was
invalid.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_mem_error
No memory available. The system cannot allocate more virtual memory
because its capacity is full.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_sequence_error
A library function was called in the wrong order. For example
@samp{LZ_compress_restart_member} was called before
@samp{LZ_compress_member_finished} indicates that the current member is
finished.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_header_error
Reading of member header failed. If this happens at the end of the data
stream it may indicate trailing garbage.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_unexpected_eof
The end of the data stream was reached in the middle of a member.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_data_error
The data stream is corrupt.
@end deftypevr
@deftypevr Constant {enum LZ_errno} LZ_library_error
A bug was detected in the library. Please, report it (@pxref{Problems}).
@end deftypevr
@node Data Format
@chapter Data Format
@cindex data format
In the diagram below, a box like this:
@verbatim
+---+
| | <-- the vertical bars might be missing
+---+
@end verbatim
represents one byte; a box like this:
@verbatim
+==============+
| |
+==============+
@end verbatim
represents a variable number of bytes.
@sp 1
A lzip data stream consists of a series of "members" (compressed data
sets). The members simply appear one after another in the data stream,
with no additional information before, between, or after them.
Each member has the following structure:
@verbatim
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| ID string | VN | DS | Lzma stream | CRC32 | Data size | Member size |
+--+--+--+--+----+----+=============+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@end verbatim
All multibyte values are stored in little endian order.
@table @samp
@item ID string
A four byte string, identifying the member type, with the value "LZIP".
@item VN (version number, 1 byte)
Just in case something needs to be modified in the future. Valid values
are 0 and 1. Version 0 files have only one member and lack @samp{Member
size}.
@item DS (coded dictionary size, 1 byte)
Bits 4-0 contain the base 2 logarithm of the base dictionary size.@*
Bits 7-5 contain the number of "wedges" to substract from the base
dictionary size to obtain the dictionary size. The size of a wedge is
(base dictionary size / 16).@*
Valid values for dictionary size range from 4KiB to 512MiB.
@item Lzma stream
The lzma stream, finished by an end of stream marker. Uses default values
for encoder properties.
@item CRC32 (4 bytes)
CRC of the uncompressed original data.
@item Data size (8 bytes)
Size of the uncompressed original data.
@item Member size (8 bytes)
Total size of the member, including header and trailer. This facilitates
safe recovery of undamaged members from multimember files.
@end table
@node Examples
@chapter A small tutorial with examples
@cindex examples
This chaper shows the order in which the library functions should be
called depending on what kind of data stream you want to compress or
decompress.
@sp 1
@noindent
Example 1: Normal compression (@var{member_size} > total output).
@example
1) LZ_compress_open
2) LZ_compress_write
3) LZ_compress_read
4) go back to step 2 until all input data has been written
5) LZ_compress_finish
6) LZ_compress_read
7) go back to step 6 until LZ_compress_read returns 0
8) LZ_compress_close
@end example
@sp 1
@noindent
Example 2: Decompression.
@example
1) LZ_decompress_open
2) LZ_decompress_write
3) LZ_decompress_read
4) go back to step 2 until all input data has been written
5) LZ_decompress_finish
6) LZ_decompress_read
7) go back to step 6 until LZ_decompress_read returns 0
8) LZ_decompress_close
@end example
@sp 1
@noindent
Example 3: Multimember compression (@var{member_size} < total output).
@example
1) LZ_compress_open
2) LZ_compress_write
3) LZ_compress_read
4) go back to step 2 until LZ_compress_member_finished returns 1
5) LZ_compress_restart_member
6) go back to step 2 until all input data has been written
7) LZ_compress_finish
8) LZ_compress_read
9) go back to step 8 until LZ_compress_read returns 0
10) LZ_compress_close
@end example
@node Problems
@chapter Reporting Bugs
@cindex bugs
@cindex getting help
There are probably bugs in Lzlib. There are certainly errors and
omissions in this manual. If you report them, they will get fixed. If
you don't, no one will ever know about them and they will remain unfixed
for all eternity, if not longer.
If you find a bug in Lzlib, please send electronic mail to
@email{lzip-bug@@nongnu.org}. Include the version number, which you can
find by running @w{@samp{minilzip --version}} or in
@samp{LZ_version_string} from @samp{lzlib.h}.
@node Concept Index
@unnumbered Concept Index
@printindex cp
@bye

573
encoder.cc Normal file
View file

@ -0,0 +1,573 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
#define _FILE_OFFSET_BITS 64
#include <algorithm>
#include <cerrno>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <stdint.h>
#include "lzlib.h"
#include "lzip.h"
#include "encoder.h"
const Dis_slots dis_slots;
const Prob_prices prob_prices;
int Matchfinder::write_data( uint8_t * const in_buffer, const int in_size ) throw()
{
if( at_stream_end_ ) return 0;
if( pos >= pos_limit )
{
const int offset = pos - dictionary_size_ - max_num_trials;
const int size = stream_pos - offset;
// std::fprintf( stderr, "%6d offset, %5d size, %4d margin.\n",
// offset, size, after_size - ( pos - pos_limit ) );
std::memmove( buffer, buffer + offset, size );
partial_data_pos += offset;
pos -= offset;
stream_pos -= offset;
for( int i = 0; i < num_prev_positions; ++i )
if( prev_positions[i] >= 0 ) prev_positions[i] -= offset;
for( int i = 0; i < 2 * dictionary_size_; ++i )
if( prev_pos_tree[i] >= 0 ) prev_pos_tree[i] -= offset;
}
const int size = std::min( buffer_size - stream_pos, in_size );
if( size > 0 )
{
std::memmove( buffer + stream_pos, in_buffer, size );
stream_pos += size;
}
return size;
}
bool Matchfinder::reset() throw()
{
const int size = stream_pos - pos;
std::memmove( buffer, buffer + pos, size );
partial_data_pos = 0;
stream_pos -= pos;
pos = 0;
cyclic_pos = 0;
for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = -1;
return true;
}
bool Matchfinder::move_pos() throw()
{
if( ++cyclic_pos >= dictionary_size_ ) cyclic_pos = 0;
if( ++pos > stream_pos ) { pos = stream_pos; return false; }
return true;
}
int Matchfinder::longest_match_len( int * const distances ) throw()
{
int len_limit = match_len_limit_;
if( len_limit > available_bytes() )
{
len_limit = available_bytes();
if( len_limit < 4 ) return 0;
}
int maxlen = min_match_len - 1;
const int min_pos = (pos >= dictionary_size_) ?
(pos - dictionary_size_ + 1) : 0;
const uint8_t * const data = buffer + pos;
const int key2 = num_prev_positions4 + num_prev_positions3 +
( ( (int)data[0] << 8 ) | data[1] );
const int tmp = crc32[data[0]] ^ data[1] ^ ( (int)data[2] << 8 );
const int key3 = num_prev_positions4 + ( tmp & ( num_prev_positions3 - 1 ) );
const int key4 = ( tmp ^ ( crc32[data[3]] << 5 ) ) &
( num_prev_positions4 - 1 );
if( distances )
{
int np = prev_positions[key2];
if( np >= min_pos )
{ distances[2] = pos - np - 1; maxlen = 2; }
else distances[2] = 0x7FFFFFFF;
np = prev_positions[key3];
if( np >= min_pos && buffer[np] == data[0] )
{ distances[3] = pos - np - 1; maxlen = 3; }
else distances[3] = 0x7FFFFFFF;
distances[4] = 0x7FFFFFFF;
}
prev_positions[key2] = pos;
prev_positions[key3] = pos;
int newpos = prev_positions[key4];
prev_positions[key4] = pos;
int idx0 = cyclic_pos << 1;
int idx1 = idx0 + 1;
int len0 = 0, len1 = 0;
for( int count = 16 + ( match_len_limit_ / 2 ); ; )
{
if( newpos < min_pos || --count < 0 )
{ prev_pos_tree[idx0] = prev_pos_tree[idx1] = -1; break; }
const uint8_t * const newdata = buffer + newpos;
int len = std::min( len0, len1 );
while( len < len_limit && newdata[len] == data[len] ) ++len;
const int delta = pos - newpos;
if( distances ) while( maxlen < len ) distances[++maxlen] = delta - 1;
const int newidx = ( cyclic_pos - delta +
( ( cyclic_pos >= delta ) ? 0 : dictionary_size_ ) ) << 1;
if( len < len_limit )
{
if( newdata[len] < data[len] )
{
prev_pos_tree[idx0] = newpos;
idx0 = newidx + 1;
newpos = prev_pos_tree[idx0];
len0 = len;
}
else
{
prev_pos_tree[idx1] = newpos;
idx1 = newidx;
newpos = prev_pos_tree[idx1];
len1 = len;
}
}
else
{
prev_pos_tree[idx0] = prev_pos_tree[newidx];
prev_pos_tree[idx1] = prev_pos_tree[newidx+1];
break;
}
}
if( distances )
{
if( distances[3] > distances[4] ) distances[3] = distances[4];
if( distances[2] > distances[3] ) distances[2] = distances[3];
}
return maxlen;
}
void Len_encoder::encode( Range_encoder & range_encoder, int symbol,
const int pos_state )
{
symbol -= min_match_len;
if( symbol < len_low_symbols )
{
range_encoder.encode_bit( choice1, 0 );
range_encoder.encode_tree( bm_low[pos_state], symbol, len_low_bits );
}
else
{
range_encoder.encode_bit( choice1, 1 );
if( symbol < len_low_symbols + len_mid_symbols )
{
range_encoder.encode_bit( choice2, 0 );
range_encoder.encode_tree( bm_mid[pos_state], symbol - len_low_symbols, len_mid_bits );
}
else
{
range_encoder.encode_bit( choice2, 1 );
range_encoder.encode_tree( bm_high, symbol - len_low_symbols - len_mid_symbols, len_high_bits );
}
}
if( --counters[pos_state] <= 0 ) update_prices( pos_state );
}
void LZ_encoder::fill_align_prices() throw()
{
for( int i = 0; i < dis_align_size; ++i )
align_prices[i] = price_symbol_reversed( bm_align, i, dis_align_bits );
align_price_count = dis_align_size;
}
void LZ_encoder::fill_distance_prices() throw()
{
for( int dis_state = 0; dis_state < max_dis_states; ++dis_state )
{
int * dsp = dis_slot_prices[dis_state];
const Bit_model * bmds = bm_dis_slot[dis_state];
int slot = 0;
for( ; slot < end_dis_model && slot < num_dis_slots; ++slot )
dsp[slot] = price_symbol( bmds, slot, dis_slot_bits );
for( ; slot < num_dis_slots; ++slot )
dsp[slot] = price_symbol( bmds, slot, dis_slot_bits ) +
(((( slot >> 1 ) - 1 ) - dis_align_bits ) << price_shift );
int * dp = dis_prices[dis_state];
int dis = 0;
for( ; dis < start_dis_model; ++dis )
dp[dis] = dsp[dis];
for( ; dis < modeled_distances; ++dis )
{
const int dis_slot = dis_slots[dis];
const int direct_bits = ( dis_slot >> 1 ) - 1;
const int base = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
dp[dis] = dsp[dis_slot] +
price_symbol_reversed( bm_dis + base - dis_slot, dis - base, direct_bits );
}
}
}
// Return value: ( dis == -1 ) && ( len == 1 ) means literal
int LZ_encoder::best_pair_sequence( const int reps[num_rep_distances],
const State & state )
{
int main_len;
if( longest_match_found > 0 ) // from previous call
{
main_len = longest_match_found;
longest_match_found = 0;
}
else main_len = read_match_distances();
int replens[num_rep_distances];
int rep_index = 0;
for( int i = 0; i < num_rep_distances; ++i )
{
replens[i] = matchfinder.true_match_len( 0, reps[i] + 1, max_match_len );
if( replens[i] > replens[rep_index] ) rep_index = i;
}
if( replens[rep_index] >= matchfinder.match_len_limit() )
{
trials[0].dis = rep_index;
trials[0].price = replens[rep_index];
if( !move_pos( replens[rep_index], true ) ) return 0;
return replens[rep_index];
}
if( main_len >= matchfinder.match_len_limit() )
{
trials[0].dis = match_distances[matchfinder.match_len_limit()] +
num_rep_distances;
trials[0].price = main_len;
if( !move_pos( main_len, true ) ) return 0;
return main_len;
}
trials[0].state = state;
for( int i = 0; i < num_rep_distances; ++i ) trials[0].reps[i] = reps[i];
const uint8_t cur_byte = matchfinder[0];
const uint8_t match_byte = matchfinder[-reps[0]-1];
unsigned int position = matchfinder.data_position();
const int pos_state = position & pos_state_mask;
trials[1].dis = -1;
trials[1].prev_index = 0;
trials[1].price = price0( bm_match[state()][pos_state] );
if( state.is_char() )
trials[1].price += literal_encoder.price_symbol( matchfinder[-1], cur_byte );
else
trials[1].price += literal_encoder.price_matched( matchfinder[-1], cur_byte, match_byte );
const int match_price = price1( bm_match[state()][pos_state] );
const int rep_match_price = match_price + price1( bm_rep[state()] );
if( match_byte == cur_byte )
trials[1].update( 0, 0, rep_match_price + price_rep_len1( state, pos_state ) );
if( main_len < min_match_len )
{
trials[0].dis = trials[1].dis;
trials[0].price = 1;
if( !matchfinder.move_pos() ) return 0;
return 1;
}
{
const int normal_match_price = match_price + price0( bm_rep[state()] );
int len = min_match_len;
if( main_len <= replens[rep_index] )
{
main_len = replens[rep_index];
for( ; len <= main_len; ++len ) trials[len].price = infinite_price;
}
else for( ; len <= main_len; ++len )
{
trials[len].dis = match_distances[len] + num_rep_distances;
trials[len].prev_index = 0;
trials[len].price = normal_match_price +
price_pair( match_distances[len], len, pos_state );
}
}
for( int rep = 0; rep < num_rep_distances; ++rep )
for( int len = min_match_len; len <= replens[rep]; ++len )
trials[len].update( rep, 0, rep_match_price +
price_rep( rep, len, state, pos_state ) );
int cur = 0;
int num_trials = main_len;
if( !matchfinder.move_pos() ) return 0;
while( true )
{
if( ++cur >= num_trials )
{
backward( cur );
return cur;
}
const int newlen = read_match_distances();
if( newlen >= matchfinder.match_len_limit() )
{
longest_match_found = newlen;
backward( cur );
return cur;
}
Trial & cur_trial = trials[cur];
const int prev_index = cur_trial.prev_index;
cur_trial.state = trials[prev_index].state;
for( int i = 0; i < num_rep_distances; ++i )
cur_trial.reps[i] = trials[prev_index].reps[i];
if( prev_index == cur - 1 )
{
if( cur_trial.dis == 0 ) cur_trial.state.set_short_rep();
else cur_trial.state.set_char();
}
else
{
if( cur_trial.dis < num_rep_distances ) cur_trial.state.set_rep();
else cur_trial.state.set_match();
mtf_reps( cur_trial.dis, cur_trial.reps );
}
const uint8_t cur_byte = matchfinder[0];
const uint8_t match_byte = matchfinder[-cur_trial.reps[0]-1];
const int pos_state = ++position & pos_state_mask;
int next_price = cur_trial.price + price0( bm_match[cur_trial.state()][pos_state] );
if( cur_trial.state.is_char() )
next_price += literal_encoder.price_symbol( matchfinder[-1], cur_byte );
else
next_price += literal_encoder.price_matched( matchfinder[-1], cur_byte, match_byte );
if( !matchfinder.move_pos() ) return 0;
Trial & next_trial = trials[cur+1];
next_trial.update( -1, cur, next_price );
const int match_price = cur_trial.price + price1( bm_match[cur_trial.state()][pos_state] );
const int rep_match_price = match_price + price1( bm_rep[cur_trial.state()] );
if( match_byte == cur_byte && next_trial.dis != 0 )
next_trial.update( 0, cur, rep_match_price +
price_rep_len1( cur_trial.state, pos_state ) );
const int len_limit = std::min( std::min( max_num_trials - 1 - cur,
matchfinder.available_bytes() ), matchfinder.match_len_limit() );
if( len_limit < min_match_len ) continue;
for( int rep = 0; rep < num_rep_distances; ++rep )
{
const int dis = cur_trial.reps[rep] + 1;
int len = 0;
const uint8_t * const data = matchfinder.ptr_to_current_pos() - 1;
while( len < len_limit && data[len] == data[len-dis] ) ++len;
if( len >= min_match_len )
{
while( num_trials < cur + len )
trials[++num_trials].price = infinite_price;
for( ; len >= min_match_len; --len )
trials[cur+len].update( rep, cur, rep_match_price +
price_rep( rep, len, cur_trial.state, pos_state ) );
}
}
if( newlen <= len_limit &&
( newlen > min_match_len ||
( newlen == min_match_len &&
match_distances[newlen] < modeled_distances ) ) )
{
const int normal_match_price = match_price +
price0( bm_rep[cur_trial.state()] );
while( num_trials < cur + newlen )
trials[++num_trials].price = infinite_price;
for( int len = newlen; len >= min_match_len; --len )
trials[cur+len].update( match_distances[len] + num_rep_distances, cur,
normal_match_price +
price_pair( match_distances[len], len, pos_state ) );
}
}
}
// End Of Stream mark => (dis == 0xFFFFFFFF, len == min_match_len)
void LZ_encoder::flush( const State & state )
{
const int pos_state = ( matchfinder.data_position() ) & pos_state_mask;
range_encoder.encode_bit( bm_match[state()][pos_state], 1 );
range_encoder.encode_bit( bm_rep[state()], 0 );
encode_pair( 0xFFFFFFFF, min_match_len, pos_state );
range_encoder.flush();
File_trailer trailer;
trailer.data_crc( crc() );
trailer.data_size( matchfinder.data_position() );
trailer.member_size( range_encoder.member_position() + sizeof trailer );
for( unsigned int i = 0; i < sizeof trailer; ++i )
range_encoder.put_byte( (( uint8_t *)&trailer)[i] );
}
LZ_encoder::LZ_encoder( Matchfinder & mf, const File_header & header,
const long long member_size )
:
member_size_limit( member_size - sizeof( File_trailer ) - 15 ),
longest_match_found( 0 ),
crc_( 0xFFFFFFFF ),
matchfinder( mf ),
range_encoder(),
len_encoder( matchfinder.match_len_limit() ),
rep_match_len_encoder( matchfinder.match_len_limit() ),
literal_encoder(),
num_dis_slots( 2 * File_header::real_bits( matchfinder.dictionary_size() - 1 ) ),
fill_counter( 0 ),
prev_byte( 0 ),
member_finished_( false )
{
for( int i = 0; i < num_rep_distances; ++i ) rep_distances[i] = 0;
fill_align_prices();
for( unsigned int i = 0; i < sizeof header; ++i )
range_encoder.put_byte( (( uint8_t *)&header)[i] );
}
bool LZ_encoder::encode_member()
{
if( member_finished_ ) return true;
if( !matchfinder.finished() && !matchfinder.available_bytes() )
return true; // need at least 1 byte
if( range_encoder.member_position() == sizeof( File_header ) &&
!matchfinder.finished() ) // copy first byte
{
range_encoder.encode_bit( bm_match[state()][0], 0 );
const uint8_t cur_byte = matchfinder[0];
literal_encoder.encode( range_encoder, prev_byte, cur_byte );
prev_byte = cur_byte;
crc32.update( crc_, cur_byte );
if( !move_pos( 1 ) ) return false;
}
while( true )
{
if( matchfinder.finished() )
{ flush( state ); member_finished_ = true; return true; }
if( !matchfinder.available_bytes() ||
( !matchfinder.at_stream_end() &&
matchfinder.available_bytes() < max_num_trials + max_match_len ) )
return true; // need more data
if( range_encoder.free_bytes() < 2 * max_num_trials ) return true;
if( fill_counter <= 0 ) { fill_distance_prices(); fill_counter = 512; }
int ahead = best_pair_sequence( rep_distances, state );
if( ahead <= 0 ) return false;
fill_counter -= ahead;
for( int i = 0; ; )
{
const int pos_state = ( matchfinder.data_position() - ahead ) & pos_state_mask;
int dis = trials[i].dis;
const int len = trials[i].price;
bool bit = ( dis < 0 && len == 1 );
range_encoder.encode_bit( bm_match[state()][pos_state], !bit );
if( bit )
{
const uint8_t cur_byte = matchfinder[-ahead];
if( state.is_char() )
literal_encoder.encode( range_encoder, prev_byte, cur_byte );
else
{
const uint8_t match_byte = matchfinder[-rep_distances[0]-1-ahead];
literal_encoder.encode_matched( range_encoder, prev_byte, match_byte, cur_byte );
}
state.set_char();
prev_byte = cur_byte;
}
else
{
mtf_reps( dis, rep_distances );
bit = ( dis < num_rep_distances );
range_encoder.encode_bit( bm_rep[state()], bit );
if( bit )
{
bit = ( dis == 0 );
range_encoder.encode_bit( bm_rep0[state()], !bit );
if( bit )
range_encoder.encode_bit( bm_len[state()][pos_state], len > 1 );
else
{
range_encoder.encode_bit( bm_rep1[state()], dis > 1 );
if( dis > 1 )
range_encoder.encode_bit( bm_rep2[state()], dis > 2 );
}
if( len == 1 ) state.set_short_rep();
else
{
rep_match_len_encoder.encode( range_encoder, len, pos_state );
state.set_rep();
}
}
else
{
encode_pair( dis - num_rep_distances, len, pos_state );
state.set_match();
}
prev_byte = matchfinder[len-1-ahead];
}
for( int j = 0; j < len; ++j )
crc32.update( crc_, matchfinder[j-ahead] );
ahead -= len; i += len;
if( range_encoder.member_position() >= member_size_limit )
{
if( !matchfinder.dec_pos( ahead ) ) return false;
flush( state );
member_finished_ = true;
return true;
}
if( ahead <= 0 ) break;
}
}
}

608
encoder.h Normal file
View file

@ -0,0 +1,608 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
const int max_num_trials = 1 << 12;
const int price_shift = 6;
class Dis_slots
{
unsigned char data[1<<12];
public:
Dis_slots()
{
for( int slot = 0; slot < 4; ++slot ) data[slot] = slot;
for( int i = 4, size = 2, slot = 4; slot < 24; slot += 2 )
{
std::memset( &data[i], slot, size );
std::memset( &data[i+size], slot + 1, size );
size <<= 1;
i += size;
}
}
int operator[]( const uint32_t dis ) const throw()
{
if( dis < (1 << 12) ) return data[dis];
if( dis < (1 << 23) ) return data[dis>>11] + 22;
return data[dis>>22] + 44;
}
};
extern const Dis_slots dis_slots;
class Prob_prices
{
int data[bit_model_total >> 2];
public:
Prob_prices()
{
const int num_bits = ( bit_model_total_bits - 2 );
for( int i = num_bits - 1; i >= 0; --i )
{
int start = 1 << ( num_bits - i - 1 );
int end = 1 << ( num_bits - i);
for( int j = start; j < end; ++j )
data[j] = (i << price_shift) +
( ((end - j) << price_shift) >> (num_bits - i - 1) );
}
}
int operator[]( const int symbol ) const throw()
{ return data[symbol >> 2]; }
};
extern const Prob_prices prob_prices;
inline int price0( const Bit_model & bm ) throw()
{ return prob_prices[bm.probability]; }
inline int price1( const Bit_model & bm ) throw()
{ return prob_prices[bit_model_total-bm.probability]; }
inline int price_bit( const Bit_model & bm, const int bit ) throw()
{ if( bit ) return price1( bm ); else return price0( bm ); }
inline int price_symbol( const Bit_model bm[], int symbol, const int num_bits ) throw()
{
symbol |= ( 1 << num_bits );
int price = 0;
while( symbol > 1 )
{
const int bit = symbol & 1;
symbol >>= 1;
price += price_bit( bm[symbol-1], bit );
}
return price;
}
inline int price_symbol_reversed( const Bit_model bm[], int symbol,
const int num_bits ) throw()
{
int price = 0;
int model = 1;
for( int i = num_bits; i > 0; --i )
{
const int bit = symbol & 1;
symbol >>= 1;
price += price_bit( bm[model-1], bit );
model = ( model << 1 ) | bit;
}
return price;
}
inline int price_matched( const Bit_model bm[], const int symbol,
const int match_byte ) throw()
{
int price = 0;
int model = 1;
for( int i = 7; i >= 0; --i )
{
const int match_bit = ( match_byte >> i ) & 1;
const int bit = ( symbol >> i ) & 1;
price += price_bit( bm[(match_bit<<8)+model+0xFF], bit );
model = ( model << 1 ) | bit;
if( match_bit != bit )
{
while( --i >= 0 )
{
const int bit = ( symbol >> i ) & 1;
price += price_bit( bm[model-1], bit );
model = ( model << 1 ) | bit;
}
break;
}
}
return price;
}
class Matchfinder
{
enum { num_prev_positions4 = 1 << 20,
num_prev_positions3 = 1 << 18,
num_prev_positions2 = 1 << 16,
num_prev_positions = num_prev_positions4 + num_prev_positions3 +
num_prev_positions2 };
long long partial_data_pos;
const int dictionary_size_; // bytes to keep in buffer before pos
const int after_size; // bytes to keep in buffer after pos
const int buffer_size;
uint8_t * const buffer;
int pos;
int cyclic_pos;
int stream_pos; // first byte not yet read from file
const int pos_limit; // when reached, a new block must be read
const int match_len_limit_;
int32_t * const prev_positions; // last seen position of key
int32_t * prev_pos_tree;
bool at_stream_end_; // stream_pos shows real end of file
public:
Matchfinder( const int dict_size, const int len_limit )
:
partial_data_pos( 0 ),
dictionary_size_( dict_size ),
after_size( max_num_trials + max_match_len ),
buffer_size( ( 2 * std::max( 65536, dictionary_size_ ) ) +
max_num_trials + after_size ),
buffer( new( std::nothrow ) uint8_t[buffer_size] ),
pos( 0 ),
cyclic_pos( 0 ),
stream_pos( 0 ),
pos_limit( buffer_size - after_size ),
match_len_limit_( len_limit ),
prev_positions( new( std::nothrow ) int32_t[num_prev_positions] ),
at_stream_end_( false )
{
prev_pos_tree = new( std::nothrow ) int32_t[2*dictionary_size_];
if( !buffer || !prev_positions || !prev_pos_tree )
{
if( prev_pos_tree ) delete[] prev_pos_tree;
if( prev_positions ) delete[] prev_positions;
if( buffer ) delete[] buffer;
throw std::bad_alloc();
}
for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = -1;
}
~Matchfinder()
{ delete[] prev_pos_tree; delete[] prev_positions; delete[] buffer; }
uint8_t operator[]( const int i ) const throw() { return buffer[pos+i]; }
bool at_stream_end() const throw() { return at_stream_end_; }
int available_bytes() const throw() { return stream_pos - pos; }
long long data_position() const throw() { return partial_data_pos + pos; }
int dictionary_size() const throw() { return dictionary_size_; }
void finish() throw() { at_stream_end_ = true; }
bool finished() const throw() { return at_stream_end_ && pos >= stream_pos; }
int match_len_limit() const throw() { return match_len_limit_; }
const uint8_t * ptr_to_current_pos() const throw() { return buffer + pos; }
bool dec_pos( const int ahead ) throw()
{
if( ahead < 0 || pos < ahead ) return false;
pos -= ahead;
cyclic_pos -= ahead;
if( cyclic_pos < 0 ) cyclic_pos += dictionary_size_;
return true;
}
int true_match_len( const int index, const int distance, int len_limit ) const throw()
{
if( index + len_limit > available_bytes() )
len_limit = available_bytes() - index;
const uint8_t * const data = buffer + pos + index - distance;
int i = 0;
while( i < len_limit && data[i] == data[i+distance] ) ++i;
return i;
}
int write_data( uint8_t * const in_buffer, const int in_size ) throw();
bool reset() throw();
bool move_pos() throw();
int longest_match_len( int * const distances = 0 ) throw();
};
class Range_encoder : public Circular_buffer
{
uint64_t low;
long long partial_member_pos;
uint32_t range;
int ff_count;
uint8_t cache;
void shift_low()
{
const uint32_t carry = low >> 32;
if( low < 0xFF000000 || carry == 1 )
{
put_byte( cache + carry );
for( ; ff_count > 0; --ff_count ) put_byte( 0xFF + carry );
cache = low >> 24;
}
else ++ff_count;
low = ( low & 0x00FFFFFF ) << 8;
}
public:
Range_encoder()
:
Circular_buffer( 65536 + (2 * max_num_trials) ),
low( 0 ),
partial_member_pos( 0 ),
range( 0xFFFFFFFF ),
ff_count( 0 ),
cache( 0 ) {}
int read_data( uint8_t * const out_buffer, const int out_size ) throw()
{
const int size = Circular_buffer::read_data( out_buffer, out_size );
if( size > 0 ) partial_member_pos += size;
return size;
}
void flush() { for( int i = 0; i < 5; ++i ) shift_low(); }
long long member_position() const throw()
{ return partial_member_pos + used_bytes() + ff_count; }
void encode( const int symbol, const int num_bits )
{
for( int i = num_bits - 1; i >= 0; --i )
{
range >>= 1;
if( (symbol >> i) & 1 ) low += range;
if( range <= 0x00FFFFFF ) { range <<= 8; shift_low(); }
}
}
void encode_bit( Bit_model & bm, const int bit )
{
const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability;
if( !bit )
{
range = bound;
bm.probability += (bit_model_total - bm.probability) >> bit_model_move_bits;
}
else
{
low += bound;
range -= bound;
bm.probability -= bm.probability >> bit_model_move_bits;
}
if( range <= 0x00FFFFFF ) { range <<= 8; shift_low(); }
}
void encode_tree( Bit_model bm[], const int symbol, const int num_bits )
{
int mask = ( 1 << ( num_bits - 1 ) );
int model = 1;
for( int i = num_bits; i > 0; --i, mask >>= 1 )
{
const int bit = ( symbol & mask );
encode_bit( bm[model-1], bit );
model <<= 1;
if( bit ) model |= 1;
}
}
void encode_tree_reversed( Bit_model bm[], int symbol, const int num_bits )
{
int model = 1;
for( int i = num_bits; i > 0; --i )
{
const int bit = symbol & 1;
encode_bit( bm[model-1], bit );
model = ( model << 1 ) | bit;
symbol >>= 1;
}
}
void encode_matched( Bit_model bm[], int symbol, int match_byte )
{
int model = 1;
for( int i = 7; i >= 0; --i )
{
const int bit = ( symbol >> i ) & 1;
const int match_bit = ( match_byte >> i ) & 1;
encode_bit( bm[(match_bit<<8)+model+0xFF], bit );
model = ( model << 1 ) | bit;
if( match_bit != bit )
{
while( --i >= 0 )
{
const int bit = ( symbol >> i ) & 1;
encode_bit( bm[model-1], bit );
model = ( model << 1 ) | bit;
}
break;
}
}
}
};
class Len_encoder
{
Bit_model choice1;
Bit_model choice2;
Bit_model bm_low[pos_states][len_low_symbols];
Bit_model bm_mid[pos_states][len_mid_symbols];
Bit_model bm_high[len_high_symbols];
int prices[pos_states][max_len_symbols];
const int len_symbols;
int counters[pos_states];
void update_prices( const int pos_state ) throw()
{
int * const pps = prices[pos_state];
int price = price0( choice1 );
int len = 0;
for( ; len < len_low_symbols && len < len_symbols; ++len )
pps[len] = price +
price_symbol( bm_low[pos_state], len, len_low_bits );
price = price1( choice1 );
for( ; len < len_low_symbols + len_mid_symbols && len < len_symbols; ++len )
pps[len] = price + price0( choice2 ) +
price_symbol( bm_mid[pos_state], len - len_low_symbols, len_mid_bits );
for( ; len < len_symbols; ++len )
pps[len] = price + price1( choice2 ) +
price_symbol( bm_high, len - len_low_symbols - len_mid_symbols, len_high_bits );
counters[pos_state] = len_symbols;
}
public:
Len_encoder( const int len_limit )
: len_symbols( len_limit + 1 - min_match_len )
{
for( int i = 0; i < pos_states; ++i ) update_prices( i );
}
void encode( Range_encoder & range_encoder, int symbol,
const int pos_state );
int price( const int symbol, const int pos_state ) const throw()
{ return prices[pos_state][symbol - min_match_len]; }
};
class Literal_encoder
{
Bit_model bm_literal[1<<literal_context_bits][0x300];
int state( const int prev_byte ) const throw()
{ return ( prev_byte >> ( 8 - literal_context_bits ) ); }
public:
void encode( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t symbol )
{ range_encoder.encode_tree( bm_literal[state(prev_byte)], symbol, 8 ); }
void encode_matched( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t match_byte, uint8_t symbol )
{ range_encoder.encode_matched( bm_literal[state(prev_byte)], symbol, match_byte ); }
int price_matched( uint8_t prev_byte, uint8_t symbol, uint8_t match_byte ) const throw()
{ return ::price_matched( bm_literal[state(prev_byte)], symbol, match_byte ); }
int price_symbol( uint8_t prev_byte, uint8_t symbol ) const throw()
{ return ::price_symbol( bm_literal[state(prev_byte)], symbol, 8 ); }
};
class LZ_encoder
{
enum { dis_align_mask = dis_align_size - 1,
infinite_price = 0x0FFFFFFF,
num_rep_distances = 4 }; // must be 4
struct Trial
{
State state;
int dis;
int prev_index;
int price; // dual use var; cumulative price, match length
int reps[num_rep_distances];
void update( const int d, const int p_i, const int pr ) throw()
{ if( pr < price ) { dis = d; prev_index = p_i; price = pr; } }
};
const long long member_size_limit;
int longest_match_found;
uint32_t crc_;
Bit_model bm_match[State::states][pos_states];
Bit_model bm_rep[State::states];
Bit_model bm_rep0[State::states];
Bit_model bm_rep1[State::states];
Bit_model bm_rep2[State::states];
Bit_model bm_len[State::states][pos_states];
Bit_model bm_dis_slot[max_dis_states][1<<dis_slot_bits];
Bit_model bm_dis[modeled_distances-end_dis_model];
Bit_model bm_align[dis_align_size];
Matchfinder & matchfinder;
Range_encoder range_encoder;
Len_encoder len_encoder;
Len_encoder rep_match_len_encoder;
Literal_encoder literal_encoder;
const int num_dis_slots;
int rep_distances[num_rep_distances];
int match_distances[max_match_len+1];
Trial trials[max_num_trials];
int dis_slot_prices[max_dis_states][2*max_dictionary_bits];
int dis_prices[max_dis_states][modeled_distances];
int align_prices[dis_align_size];
int align_price_count;
int fill_counter;
State state;
uint8_t prev_byte;
bool member_finished_;
void fill_align_prices() throw();
void fill_distance_prices() throw();
uint32_t crc() const throw() { return crc_ ^ 0xFFFFFFFF; }
void mtf_reps( const int dis, int reps[num_rep_distances] ) throw()
{
if( dis >= num_rep_distances )
{
for( int i = num_rep_distances - 1; i > 0; --i ) reps[i] = reps[i-1];
reps[0] = dis - num_rep_distances;
}
else if( dis > 0 )
{
const int distance = reps[dis];
for( int i = dis; i > 0; --i ) reps[i] = reps[i-1];
reps[0] = distance;
}
}
int price_rep_len1( const State & state, const int pos_state ) const throw()
{
return price0( bm_rep0[state()] ) + price0( bm_len[state()][pos_state] );
}
int price_rep( const int rep, const int len, const State & state,
const int pos_state ) const throw()
{
int price = rep_match_len_encoder.price( len, pos_state );
if( rep == 0 )
{
price += price0( bm_rep0[state()] );
price += price1( bm_len[state()][pos_state] );
}
else
{
price += price1( bm_rep0[state()] );
if( rep == 1 )
price += price0( bm_rep1[state()] );
else
{
price += price1( bm_rep1[state()] );
price += price_bit( bm_rep2[state()], rep - 2 );
}
}
return price;
}
int price_pair( const int dis, const int len, const int pos_state ) const throw()
{
if( len <= min_match_len && dis >= modeled_distances )
return infinite_price;
int price = len_encoder.price( len, pos_state );
const int dis_state = get_dis_state( len );
if( dis < modeled_distances )
price += dis_prices[dis_state][dis];
else
price += dis_slot_prices[dis_state][dis_slots[dis]] +
align_prices[dis & dis_align_mask];
return price;
}
void encode_pair( const uint32_t dis, const int len, const int pos_state ) throw()
{
len_encoder.encode( range_encoder, len, pos_state );
const int dis_slot = dis_slots[dis];
range_encoder.encode_tree( bm_dis_slot[get_dis_state(len)], dis_slot, dis_slot_bits );
if( dis_slot >= start_dis_model )
{
const int direct_bits = ( dis_slot >> 1 ) - 1;
const uint32_t base = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
const uint32_t direct_dis = dis - base;
if( dis_slot < end_dis_model )
range_encoder.encode_tree_reversed( bm_dis + base - dis_slot,
direct_dis, direct_bits );
else
{
range_encoder.encode( direct_dis >> dis_align_bits, direct_bits - dis_align_bits );
range_encoder.encode_tree_reversed( bm_align, direct_dis, dis_align_bits );
if( --align_price_count <= 0 ) fill_align_prices();
}
}
}
int read_match_distances() throw()
{
int len = matchfinder.longest_match_len( match_distances );
if( len == matchfinder.match_len_limit() )
len += matchfinder.true_match_len( len, match_distances[len] + 1, max_match_len - len );
return len;
}
bool move_pos( int n, bool skip = false ) throw()
{
while( --n >= 0 )
{
if( skip ) skip = false;
else matchfinder.longest_match_len();
if( !matchfinder.move_pos() ) return false;
}
return true;
}
void backward( int cur )
{
int & dis = trials[cur].dis;
while( cur > 0 )
{
const int prev_index = trials[cur].prev_index;
Trial & prev_trial = trials[prev_index];
std::swap( dis, prev_trial.dis );
prev_trial.price = cur - prev_index; // len
cur = prev_index;
}
}
int best_pair_sequence( const int reps[num_rep_distances],
const State & state );
void flush( const State & state );
public:
LZ_encoder( Matchfinder & mf, const File_header & header,
const long long member_size );
bool encode_member();
void finish_member()
{ if( !member_finished_ ) { flush( state ); member_finished_ = true; } }
bool member_finished() const throw()
{ return member_finished_ && !range_encoder.used_bytes(); }
int read_data( uint8_t * const buffer, const int size ) throw()
{ return range_encoder.read_data( buffer, size ); }
long long member_position() const throw()
{ return range_encoder.member_position(); }
};

276
lzip.h Normal file
View file

@ -0,0 +1,276 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
class State
{
unsigned char st;
public:
enum { states = 12 };
State() throw() : st( 0 ) {}
int operator()() const throw() { return st; }
bool is_char() const throw() { return st < 7; }
void set_char() throw()
{
static const unsigned char next[states] = {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5};
st = next[st];
}
void set_match() throw()
{
static const unsigned char next[states] = {7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10};
st = next[st];
}
void set_rep() throw()
{
static const unsigned char next[states] = {8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11};
st = next[st];
}
void set_short_rep() throw()
{
static const unsigned char next[states] = {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11};
st = next[st];
}
};
const int literal_context_bits = 3;
const int pos_state_bits = 2;
const int pos_states = 1 << pos_state_bits;
const int pos_state_mask = pos_states - 1;
const int dis_slot_bits = 6;
const int start_dis_model = 4;
const int end_dis_model = 14;
const int modeled_distances = 1 << (end_dis_model / 2);
const int dis_align_bits = 4;
const int dis_align_size = 1 << dis_align_bits;
const int len_low_bits = 3;
const int len_mid_bits = 3;
const int len_high_bits = 8;
const int len_low_symbols = 1 << len_low_bits;
const int len_mid_symbols = 1 << len_mid_bits;
const int len_high_symbols = 1 << len_high_bits;
const int max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols;
const int min_match_len = 2; // must be 2
const int max_match_len = min_match_len + max_len_symbols - 1; // 273
const int max_dis_states = 4;
inline int get_dis_state( int len ) throw()
{
len -= min_match_len;
if( len >= max_dis_states ) len = max_dis_states - 1;
return len;
}
const int bit_model_move_bits = 5;
const int bit_model_total_bits = 11;
const int bit_model_total = 1 << bit_model_total_bits;
struct Bit_model
{
unsigned int probability;
Bit_model() throw() : probability( bit_model_total / 2 ) {}
};
class CRC32
{
uint32_t data[256]; // Table of CRCs of all 8-bit messages.
public:
CRC32()
{
for( unsigned int n = 0; n < 256; ++n )
{
unsigned int c = n;
for( int k = 0; k < 8; ++k )
{ if( c & 1 ) c = 0xEDB88320 ^ ( c >> 1 ); else c >>= 1; }
data[n] = c;
}
}
uint32_t operator[]( const uint8_t byte ) const throw() { return data[byte]; }
void update( uint32_t & crc, const uint8_t byte ) const throw()
{ crc = data[(crc^byte)&0xFF] ^ ( crc >> 8 ); }
};
extern const CRC32 crc32;
const char * const magic_string = "LZIP";
struct File_header
{
char magic[4];
uint8_t version;
uint8_t coded_dict_size;
void set_magic() throw()
{ std::memcpy( magic, magic_string, sizeof magic ); version = 1; }
bool verify_magic() const throw()
{
return ( std::memcmp( magic, magic_string, sizeof magic ) == 0 );
}
bool verify_version() const throw()
{
return ( version <= 1 );
}
static int real_bits( const int value ) throw()
{
int bits = 0;
for( int i = 1, mask = 1; mask > 0; ++i, mask <<= 1 )
if( value & mask ) bits = i;
return bits;
}
int dictionary_size() const throw()
{
int size = ( 1 << ( coded_dict_size & 0x1F ) );
if( size > min_dictionary_size && size <= max_dictionary_size )
size -= ( size / 16 ) * ( ( coded_dict_size >> 5 ) & 0x07 );
return size;
}
bool dictionary_size( const int size ) throw()
{
if( size >= min_dictionary_size && size <= max_dictionary_size )
{
coded_dict_size = real_bits( size - 1 );
if( size > min_dictionary_size )
{
const int base_size = 1 << coded_dict_size;
const int wedge = base_size / 16;
for( int i = 7; i >= 1; --i )
if( base_size - ( i * wedge ) >= size )
{ coded_dict_size |= ( i << 5 ); break; }
}
return true;
}
return false;
}
};
struct File_trailer
{
uint8_t data_crc_[4]; // CRC32 of the uncompressed data
uint8_t data_size_[8]; // size of the uncompressed data
uint8_t member_size_[8]; // member size including header and trailer
static int size( const int version )
{ return sizeof( File_trailer ) - ( ( version >= 1 ) ? 0 : 8 ); }
uint32_t data_crc() const throw()
{
uint32_t tmp = 0;
for( int i = 3; i >= 0; --i ) { tmp <<= 8; tmp += data_crc_[i]; }
return tmp;
}
void data_crc( uint32_t crc ) throw()
{
for( int i = 0; i < 4; ++i )
{ data_crc_[i] = (uint8_t)crc; crc >>= 8; }
}
long long data_size() const throw()
{
long long tmp = 0;
for( int i = 7; i >= 0; --i ) { tmp <<= 8; tmp += data_size_[i]; }
return tmp;
}
void data_size( long long size ) throw()
{
for( int i = 0; i < 8; ++i )
{ data_size_[i] = (uint8_t)size; size >>= 8; }
}
long long member_size() const throw()
{
long long tmp = 0;
for( int i = 7; i >= 0; --i ) { tmp <<= 8; tmp += member_size_[i]; }
return tmp;
}
void member_size( long long size ) throw()
{
for( int i = 0; i < 8; ++i )
{ member_size_[i] = (uint8_t)size; size >>= 8; }
}
};
class Circular_buffer
{
protected:
const int buffer_size;
uint8_t * const buffer;
int get;
int put;
void reset() throw() { get = 0; put = 0; }
public:
Circular_buffer( const int buf_size )
:
buffer_size( buf_size + 1 ),
buffer( new uint8_t[buffer_size] ),
get( 0 ),
put( 0 ) {}
~Circular_buffer() { delete[] buffer; }
int used_bytes() const throw()
{ return ( (get <= put) ? 0 : buffer_size ) + put - get; }
int free_bytes() const throw()
{ return ( (get <= put) ? buffer_size : 0 ) - put + get - 1; }
uint8_t get_byte() throw()
{
const uint8_t b = buffer[get];
if( ++get >= buffer_size ) get = 0;
return b;
}
void put_byte( const uint8_t b ) throw()
{
buffer[put] = b;
if( ++put >= buffer_size ) put = 0;
}
int read_data( uint8_t * const out_buffer, const int out_size ) throw();
int write_data( uint8_t * const in_buffer, const int in_size ) throw();
};

406
lzlib.cc Normal file
View file

@ -0,0 +1,406 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
#include <algorithm>
#include <cstring>
#include <vector>
#include <stdint.h>
#include "lzlib.h"
#include "lzip.h"
#include "decoder.h"
#include "encoder.h"
namespace {
struct Encoder
{
long long partial_in_size;
long long partial_out_size;
Matchfinder * matchfinder;
LZ_encoder * lz_encoder;
LZ_errno lz_errno;
const File_header member_header;
Encoder( const File_header & header ) throw()
:
partial_in_size( 0 ),
partial_out_size( 0 ),
matchfinder( 0 ),
lz_encoder( 0 ),
lz_errno( LZ_ok ),
member_header( header )
{}
};
bool verify_encoder( void * const encoder )
{
if( !encoder ) return false;
Encoder & e = *(Encoder *)encoder;
if( !e.matchfinder || !e.lz_encoder )
{ e.lz_errno = LZ_bad_argument; return false; }
return true;
}
struct Decoder
{
long long partial_in_size;
long long partial_out_size;
Input_buffer * ibuf;
LZ_decoder * lz_decoder;
LZ_errno lz_errno;
Decoder() throw()
:
partial_in_size( 0 ),
partial_out_size( 0 ),
ibuf( 0 ),
lz_decoder( 0 ),
lz_errno( LZ_ok )
{}
};
bool verify_decoder( void * const decoder )
{
if( !decoder ) return false;
if( !((Decoder *)decoder)->ibuf )
{ ((Decoder *)decoder)->lz_errno = LZ_bad_argument; return false; }
return true;
}
} // end namespace
const char * LZ_version() { return LZ_version_string; }
void * LZ_compress_open( const int dictionary_size, const int match_len_limit,
const long long member_size )
{
File_header header;
header.set_magic();
const bool error = ( !header.dictionary_size( dictionary_size ) ||
match_len_limit < 5 || match_len_limit > max_match_len );
Encoder * encoder = new( std::nothrow ) Encoder( header );
if( !encoder ) return 0;
Encoder & e = *encoder;
if( error ) e.lz_errno = LZ_bad_argument;
else
{
try {
e.matchfinder = new Matchfinder( header.dictionary_size(), match_len_limit );
}
catch( std::bad_alloc ) { e.matchfinder = 0; }
if( e.matchfinder )
{
try {
e.lz_encoder = new LZ_encoder( *e.matchfinder, header, member_size );
}
catch( std::bad_alloc )
{
delete e.matchfinder;
e.matchfinder = 0;
e.lz_encoder = 0;
}
}
if( !e.lz_encoder ) e.lz_errno = LZ_mem_error;
}
return encoder;
}
int LZ_compress_close( void * const encoder )
{
if( !encoder ) return -1;
Encoder & e = *(Encoder *)encoder;
if( e.lz_encoder ) delete e.lz_encoder;
if( e.matchfinder ) delete e.matchfinder;
delete (Encoder *)encoder;
return 0;
}
int LZ_compress_finish( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
((Encoder *)encoder)->matchfinder->finish();
return 0;
}
int LZ_compress_finish_member( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
((Encoder *)encoder)->lz_encoder->finish_member();
return 0;
}
int LZ_compress_restart_member( void * const encoder,
const long long member_size )
{
if( !verify_encoder( encoder ) ) return -1;
Encoder & e = *(Encoder *)encoder;
if( !e.lz_encoder->member_finished() )
{ e.lz_errno = LZ_sequence_error; return -1; }
e.partial_in_size += e.matchfinder->data_position();
e.partial_out_size += e.lz_encoder->member_position();
if( !e.matchfinder->reset() )
{ e.lz_errno = LZ_library_error; return -1; }
delete e.lz_encoder;
try {
e.lz_encoder = new LZ_encoder( *e.matchfinder, e.member_header, member_size );
}
catch( std::bad_alloc )
{ e.lz_encoder = 0; e.lz_errno = LZ_mem_error; return -1; }
return 0;
}
int LZ_compress_read( void * const encoder, uint8_t * const buffer,
const int size )
{
if( !verify_encoder( encoder ) ) return -1;
Encoder & e = *(Encoder *)encoder;
if( !e.lz_encoder->encode_member() )
{ e.lz_errno = LZ_library_error; return -1; }
return e.lz_encoder->read_data( buffer, size );
}
int LZ_compress_write( void * const encoder, uint8_t * const buffer,
const int size )
{
if( !verify_encoder( encoder ) ) return -1;
return ((Encoder *)encoder)->matchfinder->write_data( buffer, size );
}
enum LZ_errno LZ_compress_errno( void * const encoder )
{
if( !encoder ) return LZ_bad_argument;
return ((Encoder *)encoder)->lz_errno;
}
int LZ_compress_finished( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
Encoder & e = *(Encoder *)encoder;
return ( e.matchfinder->finished() && e.lz_encoder->member_finished() );
}
int LZ_compress_member_finished( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
return ((Encoder *)encoder)->lz_encoder->member_finished();
}
long long LZ_compress_data_position( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
return ((Encoder *)encoder)->matchfinder->data_position();
}
long long LZ_compress_member_position( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
return ((Encoder *)encoder)->lz_encoder->member_position();
}
long long LZ_compress_total_in_size( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
Encoder & e = *(Encoder *)encoder;
return e.partial_in_size + e.matchfinder->data_position();
}
long long LZ_compress_total_out_size( void * const encoder )
{
if( !verify_encoder( encoder ) ) return -1;
Encoder & e = *(Encoder *)encoder;
return e.partial_out_size + e.lz_encoder->member_position();
}
void * LZ_decompress_open()
{
Decoder * decoder = new( std::nothrow ) Decoder();
if( !decoder ) return 0;
try { decoder->ibuf = new Input_buffer(); }
catch( std::bad_alloc )
{ decoder->ibuf = 0; decoder->lz_errno = LZ_mem_error; }
return decoder;
}
int LZ_decompress_close( void * const decoder )
{
if( !decoder ) return -1;
Decoder & d = *(Decoder *)decoder;
if( d.lz_decoder ) delete d.lz_decoder;
if( d.ibuf ) delete d.ibuf;
delete (Decoder *)decoder;
return 0;
}
int LZ_decompress_finish( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
((Decoder *)decoder)->ibuf->finish();
return 0;
}
int LZ_decompress_read( void * const decoder, uint8_t * const buffer,
const int size )
{
if( !verify_decoder( decoder ) ) return -1;
Decoder & d = *(Decoder *)decoder;
if( d.lz_decoder && d.lz_decoder->member_finished() )
{
d.partial_in_size += d.lz_decoder->member_position();
d.partial_out_size += d.lz_decoder->data_position();
delete d.lz_decoder;
d.lz_decoder = 0;
}
if( !d.lz_decoder )
{
if( d.ibuf->used_bytes() < 5 + (int)sizeof( File_header ) )
{
if( !d.ibuf->at_stream_end() || d.ibuf->finished() ) return 0;
d.ibuf->purge();
d.lz_errno = LZ_header_error;
return -1;
}
File_header header;
for( unsigned int i = 0; i < sizeof header; ++i )
((uint8_t *)&header)[i] = d.ibuf->get_byte();
if( !header.verify_magic() || !header.verify_version() ||
header.dictionary_size() < min_dictionary_size ||
header.dictionary_size() > max_dictionary_size )
{
d.ibuf->purge();
d.lz_errno = LZ_header_error;
return -1;
}
try { d.lz_decoder = new LZ_decoder( header, *d.ibuf ); }
catch( std::bad_alloc )
{
d.ibuf->purge();
d.lz_decoder = 0;
d.lz_errno = LZ_mem_error;
return -1;
}
}
const int result = d.lz_decoder->decode_member();
if( result != 0 )
{
if( result == 2 ) d.lz_errno = LZ_unexpected_eof;
else d.lz_errno = LZ_data_error;
return -1;
}
return d.lz_decoder->read_data( buffer, size );
}
int LZ_decompress_write( void * const decoder, uint8_t * const buffer,
const int size )
{
if( !verify_decoder( decoder ) ) return -1;
return ((Decoder *)decoder)->ibuf->write_data( buffer, size );
}
enum LZ_errno LZ_decompress_errno( void * const decoder )
{
if( !decoder ) return LZ_bad_argument;
return ((Decoder *)decoder)->lz_errno;
}
int LZ_decompress_finished( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
Decoder & d = *(Decoder *)decoder;
return ( d.ibuf->finished() &&
( !d.lz_decoder || d.lz_decoder->member_finished() ) );
}
long long LZ_decompress_data_position( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
if( ((Decoder *)decoder)->lz_decoder )
return ((Decoder *)decoder)->lz_decoder->data_position();
else return 0;
}
long long LZ_decompress_member_position( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
if( ((Decoder *)decoder)->lz_decoder )
return ((Decoder *)decoder)->lz_decoder->member_position();
else return 0;
}
long long LZ_decompress_total_in_size( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
Decoder & d = *(Decoder *)decoder;
if( d.lz_decoder )
return d.partial_in_size + d.lz_decoder->member_position();
return d.partial_in_size;
}
long long LZ_decompress_total_out_size( void * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
Decoder & d = *(Decoder *)decoder;
if( d.lz_decoder )
return d.partial_out_size + d.lz_decoder->data_position();
return d.partial_out_size;
}

89
lzlib.h Normal file
View file

@ -0,0 +1,89 @@
/* Lzlib - A compression library for lzip files
Copyright (C) 2009 Antonio Diaz Diaz.
This library 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 3 of the License, or
(at your option) any later version.
This library 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, see <http://www.gnu.org/licenses/>.
As a special exception, you may use this file as part of a free
software library without restriction. Specifically, if other files
instantiate templates or use macros or inline functions from this
file, or you compile this file and link it with other files to
produce an executable, this file does not by itself cause the
resulting executable to be covered by the GNU General Public
License. This exception does not however invalidate any other
reasons why the executable file might be covered by the GNU General
Public License.
*/
#ifdef __cplusplus
extern "C" {
#endif
const char * const LZ_version_string = "0.3";
enum { min_dictionary_bits = 12,
min_dictionary_size = 1 << min_dictionary_bits,
max_dictionary_bits = 29,
max_dictionary_size = 1 << max_dictionary_bits };
enum LZ_errno { LZ_ok = 0, LZ_bad_argument, LZ_mem_error, LZ_sequence_error,
LZ_header_error, LZ_unexpected_eof, LZ_data_error,
LZ_library_error };
const char * LZ_version( void );
void * LZ_compress_open( const int dictionary_size, const int match_len_limit,
const long long member_size );
int LZ_compress_close( void * const encoder );
int LZ_compress_finish( void * const encoder );
int LZ_compress_finish_member( void * const encoder );
int LZ_compress_restart_member( void * const encoder,
const long long member_size );
int LZ_compress_read( void * const encoder, uint8_t * const buffer,
const int size );
int LZ_compress_write( void * const encoder, uint8_t * const buffer,
const int size );
enum LZ_errno LZ_compress_errno( void * const encoder );
int LZ_compress_finished( void * const encoder );
int LZ_compress_member_finished( void * const encoder );
long long LZ_compress_data_position( void * const encoder );
long long LZ_compress_member_position( void * const encoder );
long long LZ_compress_total_in_size( void * const encoder );
long long LZ_compress_total_out_size( void * const encoder );
void * LZ_decompress_open( void );
int LZ_decompress_close( void * const decoder );
int LZ_decompress_finish( void * const decoder );
int LZ_decompress_read( void * const decoder, uint8_t * const buffer,
const int size );
int LZ_decompress_write( void * const decoder, uint8_t * const buffer,
const int size );
enum LZ_errno LZ_decompress_errno( void * const decoder );
int LZ_decompress_finished( void * const decoder );
long long LZ_decompress_data_position( void * const decoder );
long long LZ_decompress_member_position( void * const decoder );
long long LZ_decompress_total_in_size( void * const decoder );
long long LZ_decompress_total_out_size( void * const decoder );
#ifdef __cplusplus
}
#endif

887
main.cc Normal file
View file

@ -0,0 +1,887 @@
/* Minilzip - A test program for the lzlib library
Copyright (C) 2009 Antonio Diaz Diaz.
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 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
/*
Return values: 0 for a normal exit, 1 for environmental problems
(file not found, invalid flags, I/O errors, etc), 2 to indicate a
corrupt or invalid input file, 3 for an internal consistency error
(eg, bug) which caused lzip to panic.
*/
#define _FILE_OFFSET_BITS 64
#include <algorithm>
#include <cerrno>
#include <climits>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <fcntl.h>
#include <stdint.h>
#include <signal.h>
#include <unistd.h>
#include <utime.h>
#include <sys/stat.h>
#include <sys/time.h>
#include "arg_parser.h"
#include "lzlib.h"
#ifndef LLONG_MAX
#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL
#endif
#ifndef LLONG_MIN
#define LLONG_MIN (-LLONG_MAX - 1LL)
#endif
#ifndef ULLONG_MAX
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
#endif
namespace {
const char * invocation_name = 0;
const char * const Program_name = "Minilzip";
const char * const program_name = "minilzip";
const char * const program_year = "2009";
struct { const char * from; const char * to; } const known_extensions[] = {
{ ".lz", "" },
{ ".tlz", ".tar" },
{ 0, 0 } };
struct lzma_options
{
int dictionary_size; // 4KiB..512MiB
int match_len_limit; // 5..273
};
enum Mode { m_compress = 0, m_decompress, m_test };
std::string output_filename;
int outhandle = -1;
int verbosity = 0;
bool delete_output_on_interrupt = false;
class Pretty_print
{
const char * const stdin_name;
const unsigned int stdin_name_len;
unsigned int longest_name;
std::string name_;
mutable bool first_post;
public:
Pretty_print( const std::vector< std::string > & filenames )
: stdin_name( "(stdin)" ), stdin_name_len( std::strlen( stdin_name ) ),
longest_name( 0 ), first_post( false )
{
for( unsigned int i = 0; i < filenames.size(); ++i )
{
const std::string & s = filenames[i];
const unsigned int len = ( ( s == "-" ) ? stdin_name_len : s.size() );
if( len > longest_name ) longest_name = len;
}
if( longest_name == 0 ) longest_name = stdin_name_len;
}
void set_name( const std::string & filename )
{
if( filename.size() && filename != "-" ) name_ = filename;
else name_ = stdin_name;
first_post = true;
}
void reset() const throw() { if( name_.size() ) first_post = true; }
const char * name() const throw() { return name_.c_str(); }
void operator()( const char * const msg = 0 ) const throw();
};
void show_help() throw()
{
std::printf( "%s - A test program for the lzlib library.\n", Program_name );
std::printf( "\nUsage: %s [options] [files]\n", invocation_name );
std::printf( "Options:\n" );
std::printf( " -h, --help display this help and exit\n" );
std::printf( " -V, --version output version information and exit\n" );
std::printf( " -b, --member-size=<n> set member size limit in bytes\n" );
std::printf( " -c, --stdout send output to standard output\n" );
std::printf( " -d, --decompress decompress\n" );
std::printf( " -f, --force overwrite existing output files\n" );
std::printf( " -k, --keep keep (don't delete) input files\n" );
std::printf( " -m, --match-length=<n> set match length limit in bytes [64]\n" );
std::printf( " -o, --output=<file> if reading stdin, place the output into <file>\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -s, --dictionary-size=<n> set dictionary size limit in bytes [8MiB]\n" );
std::printf( " -S, --volume-size=<n> set volume size limit in bytes\n" );
std::printf( " -t, --test test compressed file integrity\n" );
std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" );
std::printf( " -1 .. -9 set compression level [default 6]\n" );
std::printf( " --fast alias for -1\n" );
std::printf( " --best alias for -9\n" );
std::printf( "If no file names are given, %s compresses or decompresses\n", program_name );
std::printf( "from standard input to standard output.\n" );
std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" );
std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" );
std::printf( "\nReport bugs to lzip-bug@nongnu.org\n" );
std::printf( "Lzip home page: http://www.nongnu.org/lzip/lzip.html\n" );
}
void show_version() throw()
{
std::printf( "%s %s\n", Program_name, PROGVERSION );
std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
std::printf( "License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>\n" );
std::printf( "This is free software: you are free to change and redistribute it.\n" );
std::printf( "There is NO WARRANTY, to the extent permitted by law.\n" );
}
void show_error( const char * msg, const int errcode = 0, const bool help = false ) throw()
{
if( verbosity >= 0 )
{
if( msg && msg[0] != 0 )
{
std::fprintf( stderr, "%s: %s", program_name, msg );
if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) );
std::fprintf( stderr, "\n" );
}
if( help && invocation_name && invocation_name[0] != 0 )
std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name );
}
}
void internal_error( const char * msg )
{
std::string s( "internal error: " ); s += msg;
show_error( s.c_str() );
std::exit( 3 );
}
const char * format_num( long long num, long long limit = 9999,
const int set_prefix = 0 ) throw()
{
const char * const si_prefix[8] =
{ "k", "M", "G", "T", "P", "E", "Z", "Y" };
const char * const binary_prefix[8] =
{ "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" };
static bool si = false;
static char buf[16];
if( set_prefix ) si = ( set_prefix > 0 );
const int factor = ( si ) ? 1000 : 1024;
const char * const *prefix = ( si ) ? si_prefix : binary_prefix;
const char *p = "";
limit = std::max( 999LL, std::min( 999999LL, limit ) );
for( int i = 0; i < 8 && ( llabs( num ) > limit ||
( llabs( num ) >= factor && num % factor == 0 ) ); ++i )
{ num /= factor; p = prefix[i]; }
snprintf( buf, sizeof buf, "%lld %s", num, p );
return buf;
}
long long getnum( const char * ptr, const int bs,
const long long llimit = LLONG_MIN + 1,
const long long ulimit = LLONG_MAX ) throw()
{
errno = 0;
char *tail;
long long result = strtoll( ptr, &tail, 0 );
if( tail == ptr )
{
show_error( "bad or missing numerical argument", 0, true );
std::exit( 1 );
}
if( !errno && tail[0] )
{
int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
int exponent = 0;
bool bad_multiplier = false;
switch( tail[0] )
{
case ' ': break;
case 'b': if( bs > 0 ) { factor = bs; exponent = 1; }
else bad_multiplier = true;
break;
case 'Y': exponent = 8; break;
case 'Z': exponent = 7; break;
case 'E': exponent = 6; break;
case 'P': exponent = 5; break;
case 'T': exponent = 4; break;
case 'G': exponent = 3; break;
case 'M': exponent = 2; break;
case 'K': if( factor == 1024 ) exponent = 1; else bad_multiplier = true;
break;
case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true;
break;
default: bad_multiplier = true;
}
if( bad_multiplier )
{
show_error( "bad multiplier in numerical argument", 0, true );
std::exit( 1 );
}
for( int i = 0; i < exponent; ++i )
{
if( LLONG_MAX / factor >= llabs( result ) ) result *= factor;
else { errno = ERANGE; break; }
}
}
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
if( errno )
{
show_error( "numerical argument out of limits" );
std::exit( 1 );
}
return result;
}
int get_dict_size( const char * arg ) throw()
{
char *tail;
int bits = std::strtol( arg, &tail, 0 );
if( bits >= min_dictionary_bits && bits <= max_dictionary_bits && *tail == 0 )
return ( 1 << bits );
return getnum( arg, 0, min_dictionary_size, max_dictionary_size );
}
int extension_index( const std::string & name ) throw()
{
for( int i = 0; known_extensions[i].from; ++i )
{
const std::string ext( known_extensions[i].from );
if( name.size() > ext.size() &&
name.compare( name.size() - ext.size(), ext.size(), ext ) == 0 )
return i;
}
return -1;
}
int open_instream( const std::string & name, struct stat * in_statsp,
const Mode program_mode, const int eindex,
const bool force, const bool to_stdout ) throw()
{
int inhandle = -1;
if( program_mode == m_compress && !force && eindex >= 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: input file `%s' already has `%s' suffix.\n",
program_name, name.c_str(),
known_extensions[eindex].from );
}
else
{
inhandle = open( name.c_str(), O_RDONLY );
if( inhandle < 0 )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n",
program_name, name.c_str(), std::strerror( errno ) );
}
else
{
const int i = fstat( inhandle, in_statsp );
const mode_t & mode = in_statsp->st_mode;
if( i < 0 || !( S_ISREG( mode ) || ( to_stdout &&
( S_ISFIFO( mode ) || S_ISSOCK( mode ) ||
S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n",
program_name, name.c_str(),
to_stdout ? "" : " and `--stdout' was not specified" );
close( inhandle );
inhandle = -1;
}
}
}
return inhandle;
}
void set_c_outname( const std::string & name, const bool multifile ) throw()
{
output_filename = name;
if( multifile ) output_filename += "00001";
output_filename += known_extensions[0].from;
}
void set_d_outname( const std::string & name, const int i ) throw()
{
if( i >= 0 )
{
const std::string from( known_extensions[i].from );
if( name.size() > from.size() )
{
output_filename.assign( name, 0, name.size() - from.size() );
output_filename += known_extensions[i].to;
return;
}
}
output_filename = name; output_filename += ".out";
if( verbosity >= 0 )
std::fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n",
program_name, name.c_str(), output_filename.c_str() );
}
bool open_outstream( const bool force ) throw()
{
if( force )
outhandle = open( output_filename.c_str(), O_CREAT | O_TRUNC | O_WRONLY,
S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH );
else outhandle = open( output_filename.c_str(), O_CREAT | O_EXCL | O_WRONLY,
S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH );
if( outhandle < 0 )
{
if( errno == EEXIST ) outhandle = -2; else outhandle = -1;
if( verbosity >= 0 )
{
if( outhandle == -2 )
std::fprintf( stderr, "%s: Output file %s already exists, skipping.\n",
program_name, output_filename.c_str() );
else
std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n",
program_name, output_filename.c_str(), std::strerror( errno ) );
}
}
return ( outhandle >= 0 );
}
bool check_tty( const int inhandle, const Mode program_mode ) throw()
{
if( program_mode == m_compress && isatty( outhandle ) )
{
show_error( "I won't write compressed data to a terminal.", 0, true );
return false;
}
if( ( program_mode == m_decompress || program_mode == m_test ) &&
isatty( inhandle ) )
{
show_error( "I won't read compressed data from a terminal.", 0, true );
return false;
}
return true;
}
void cleanup_and_fail( const int retval ) throw()
{
if( delete_output_on_interrupt )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n",
program_name, output_filename.c_str() );
if( outhandle >= 0 ) { close( outhandle ); outhandle = -1; }
if( std::remove( output_filename.c_str() ) != 0 )
show_error( "WARNING: deletion of output file (apparently) failed." );
}
std::exit( retval );
}
// Set permissions, owner and times.
void close_and_set_permissions( const struct stat * in_statsp, int * retvalp )
{
int tmp = 0;
if( in_statsp )
{
if( fchmod( outhandle, in_statsp->st_mode ) != 0 ) tmp = 1;
if( !tmp ) (void)fchown( outhandle, in_statsp->st_uid, in_statsp->st_gid );
// fchown will in many cases return with EPERM, which can be safely ignored.
}
if( close( outhandle ) == 0 ) outhandle = -1;
else cleanup_and_fail( 1 );
delete_output_on_interrupt = false;
if( !in_statsp ) return;
if( !tmp )
{
struct utimbuf t;
t.actime = in_statsp->st_atime;
t.modtime = in_statsp->st_mtime;
tmp = utime( output_filename.c_str(), &t );
}
if( tmp )
{
if( tmp > *retvalp ) *retvalp = tmp;
show_error( "I can't change output file attributes." );
cleanup_and_fail( *retvalp );
}
}
bool next_filename()
{
const unsigned int len = std::strlen( known_extensions[0].from );
if( output_filename.size() >= len + 5 ) // "*00001.lz"
for( int i = output_filename.size() - len - 1, j = 0; j < 5; --i, ++j )
{
if( output_filename[i] < '9' ) { ++output_filename[i]; return true; }
else output_filename[i] = '0';
}
return false;
}
// Returns the number of bytes really read.
// If (returned value < size) and (errno == 0), means EOF was reached.
//
int readblock( const int fd, char * buf, const int size ) throw()
{
int rest = size;
errno = 0;
while( rest > 0 )
{
errno = 0;
const int n = read( fd, buf + size - rest, rest );
if( n > 0 ) rest -= n;
else if( n == 0 ) break;
else if( errno != EINTR && errno != EAGAIN ) break;
}
return ( rest > 0 ) ? size - rest : size;
}
// Returns the number of bytes really written.
// If (returned value < size), it is always an error.
//
int writeblock( const int fd, const char * buf, const int size ) throw()
{
int rest = size;
errno = 0;
while( rest > 0 )
{
errno = 0;
const int n = write( fd, buf + size - rest, rest );
if( n > 0 ) rest -= n;
else if( errno && errno != EINTR && errno != EAGAIN ) break;
}
return ( rest > 0 ) ? size - rest : size;
}
int compress( const long long member_size, const long long volume_size,
lzma_options encoder_options, const int inhandle,
const Pretty_print & pp, const struct stat * in_statsp,
int * retvalp )
{
if( verbosity >= 1 ) pp();
void * encoder = LZ_compress_open( encoder_options.dictionary_size,
encoder_options.match_len_limit,
std::min( member_size, volume_size ) );
if( !encoder || LZ_compress_errno( encoder ) != LZ_ok )
{
const bool mem_error = ( LZ_compress_errno( encoder ) == LZ_mem_error );
LZ_compress_close( encoder );
if( mem_error )
{ pp( "not enough memory. Try a smaller dictionary size" ); return 1; }
internal_error( "invalid argument to encoder" );
}
long long partial_volume_size = 0;
const int out_buffer_size = 65536, in_buffer_size = 8 * out_buffer_size;
uint8_t in_buffer[in_buffer_size], out_buffer[out_buffer_size];
int in_pos = 0, in_stream_pos = 0;
while( true )
{
if( in_stream_pos == 0 )
{
in_stream_pos = readblock( inhandle, (char *)in_buffer, in_buffer_size );
if( in_stream_pos == 0 ) LZ_compress_finish( encoder );
}
int in_size = 0;
if( in_pos < in_stream_pos )
{
in_size = LZ_compress_write( encoder, in_buffer + in_pos, in_stream_pos - in_pos );
in_pos += in_size;
if( in_pos >= in_stream_pos ) { in_stream_pos = 0; in_pos = 0; }
}
int out_size = LZ_compress_read( encoder, out_buffer, out_buffer_size );
// std::fprintf( stderr, "%6d in_size, %5d out_size.\n", in_size, out_size );
if( out_size < 0 )
{ pp(); show_error( "read error", errno ); return 1; }
else if( out_size > 0 )
{
const int wr = writeblock( outhandle, (char *)out_buffer, out_size );
if( wr != out_size )
{ pp(); show_error( "write error", errno ); return 1; }
}
else if( in_size == 0 ) internal_error( "library error" );
if( LZ_compress_member_finished( encoder ) )
{
if( LZ_compress_finished( encoder ) == 1 ) break;
partial_volume_size += LZ_compress_member_position( encoder );
if( partial_volume_size >= volume_size - min_dictionary_size )
{
partial_volume_size = 0;
if( delete_output_on_interrupt )
{
close_and_set_permissions( in_statsp, retvalp );
if( !next_filename() )
{ pp(); show_error( "too many volume files" ); return 1; }
if( !open_outstream( true ) ) return 1;
delete_output_on_interrupt = true;
}
}
const long long size =
std::min( member_size, volume_size - partial_volume_size );
if( LZ_compress_restart_member( encoder, size ) < 0 )
{ pp(); show_error( "read error", errno ); return 1; }
}
}
if( verbosity >= 1 )
{
const long long in_size = LZ_compress_total_in_size( encoder );
const long long out_size = LZ_compress_total_out_size( encoder );
if( in_size <= 0 || out_size <= 0 )
std::fprintf( stderr, "no data compressed.\n" );
else
std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, "
"%5.2f%% saved, %lld in, %lld out.\n",
(double)in_size / out_size,
( 8.0 * out_size ) / in_size,
100.0 * ( 1.0 - ( (double)out_size / in_size ) ),
in_size, out_size );
}
LZ_compress_close( encoder );
return 0;
}
int decompress( const int inhandle, const Pretty_print & pp,
const bool testing )
{
void * decoder = LZ_decompress_open();
if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok )
{
LZ_decompress_close( decoder );
pp( "not enough memory. Find a machine with more memory" );
return 1;
}
if( verbosity >= 1 ) pp();
const int in_buffer_size = 65536, out_buffer_size = 8 * in_buffer_size;
uint8_t in_buffer[in_buffer_size], out_buffer[out_buffer_size];
int in_pos = 0, in_stream_pos = 0;
bool finished = false;
while( true )
{
int in_size = 0;
if( !finished )
{
if( in_stream_pos == 0 )
in_stream_pos = readblock( inhandle, (char *)in_buffer, in_buffer_size );
if( in_pos < in_stream_pos )
{
in_size = LZ_decompress_write( decoder, in_buffer + in_pos, in_stream_pos - in_pos );
in_pos += in_size;
}
if( in_pos >= in_stream_pos )
{
if( in_stream_pos < in_buffer_size )
{ finished = true; LZ_decompress_finish( decoder ); }
in_stream_pos = 0; in_pos = 0;
}
}
int out_size = LZ_decompress_read( decoder, out_buffer, out_buffer_size );
// std::fprintf( stderr, "%5d in_size, %6d out_size.\n", in_size, out_size );
if( out_size < 0 )
{
const LZ_errno lz_errno = LZ_decompress_errno( decoder );
if( lz_errno == LZ_header_error )
{
if( LZ_decompress_total_out_size( decoder ) > 0 ) // trailing garbage
break;
pp( "error reading member header" );
return 1;
}
if( lz_errno == LZ_mem_error )
{
pp( "not enough memory. Find a machine with more memory" );
return 1;
}
if( lz_errno == LZ_unexpected_eof )
{
if( verbosity >= 0 )
{ pp();
std::fprintf( stderr, "file ends unexpectedly at pos %lld\n",
LZ_decompress_total_in_size( decoder ) ); }
return 2;
}
pp(); show_error( "read error", errno ); return 1;
}
else if( out_size > 0 )
{
const int wr = writeblock( outhandle, (char *)out_buffer, out_size );
if( wr != out_size )
{ pp(); show_error( "write error", errno ); return 1; }
}
if( LZ_decompress_finished( decoder ) == 1 ) break;
if( finished && in_size == 0 && out_size == 0 )
internal_error( "library error" );
}
if( verbosity >= 1 )
{ if( testing ) std::fprintf( stderr, "ok\n" );
else std::fprintf( stderr, "done\n" ); }
LZ_decompress_close( decoder );
return 0;
}
void signal_handler( const int ) throw()
{
show_error( "Control-C or similar caught, quitting." );
cleanup_and_fail( 0 );
}
void set_signals() throw()
{
signal( SIGTERM, signal_handler );
signal( SIGHUP, signal_handler );
signal( SIGINT, signal_handler );
}
} // end namespace
void Pretty_print::operator()( const char * const msg ) const throw()
{
if( verbosity >= 0 )
{
if( first_post )
{
first_post = false;
std::fprintf( stderr, " %s: ", name_.c_str() );
for( unsigned int i = 0; i < longest_name - name_.size(); ++i )
std::fprintf( stderr, " " );
if( !msg ) std::fflush( stderr );
}
if( msg ) std::fprintf( stderr, "%s.\n", msg );
}
}
int main( const int argc, const char * argv[] )
{
// Mapping from gzip/bzip2 style 1..9 compression modes
// to the corresponding LZMA compression modes.
const lzma_options option_mapping[] =
{
{ 1 << 22, 10 }, // -1
{ 1 << 22, 12 }, // -2
{ 1 << 22, 17 }, // -3
{ 1 << 22, 26 }, // -4
{ 1 << 22, 44 }, // -5
{ 1 << 23, 80 }, // -6
{ 1 << 24, 108 }, // -7
{ 1 << 24, 163 }, // -8
{ 1 << 25, 273 } }; // -9
lzma_options encoder_options = option_mapping[5]; // default = "-6"
long long member_size = LLONG_MAX;
long long volume_size = LLONG_MAX;
int inhandle = -1;
Mode program_mode = m_compress;
bool force = false;
bool keep_input_files = false;
bool to_stdout = false;
std::string input_filename;
std::string default_output_filename;
std::vector< std::string > filenames;
invocation_name = argv[0];
if( LZ_version()[0] != LZ_version_string[0] )
internal_error( "bad library version" );
if( std::strcmp( PROGVERSION, LZ_version_string ) )
internal_error( "bad library version_string" );
const Arg_parser::Option options[] =
{
{ '1', "fast", Arg_parser::no },
{ '2', 0, Arg_parser::no },
{ '3', 0, Arg_parser::no },
{ '4', 0, Arg_parser::no },
{ '5', 0, Arg_parser::no },
{ '6', 0, Arg_parser::no },
{ '7', 0, Arg_parser::no },
{ '8', 0, Arg_parser::no },
{ '9', "best", Arg_parser::no },
{ 'b', "member-size", Arg_parser::yes },
{ 'c', "stdout", Arg_parser::no },
{ 'd', "decompress", Arg_parser::no },
{ 'f', "force", Arg_parser::no },
{ 'h', "help", Arg_parser::no },
{ 'k', "keep", Arg_parser::no },
{ 'm', "match-length", Arg_parser::yes },
{ 'o', "output", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 's', "dictionary-size", Arg_parser::yes },
{ 'S', "volume-size", Arg_parser::yes },
{ 't', "test", Arg_parser::no },
{ 'v', "verbose", Arg_parser::no },
{ 'V', "version", Arg_parser::no },
{ 0 , 0, Arg_parser::no } };
Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 1; }
int argind = 0;
for( ; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) break; // no more options
const char * arg = parser.argument( argind ).c_str();
switch( code )
{
case '1': case '2': case '3':
case '4': case '5': case '6':
case '7': case '8': case '9':
encoder_options = option_mapping[code-'1']; break;
case 'b': member_size = getnum( arg, 0, 100000, LLONG_MAX / 2 ); break;
case 'c': to_stdout = true; break;
case 'd': program_mode = m_decompress; break;
case 'f': force = true; break;
case 'h': show_help(); return 0;
case 'k': keep_input_files = true; break;
case 'm': encoder_options.match_len_limit =
getnum( arg, 0, 5, 273 ); break;
case 'o': default_output_filename = arg; break;
case 'q': verbosity = -1; break;
case 's': encoder_options.dictionary_size = get_dict_size( arg );
break;
case 'S': volume_size = getnum( arg, 0, 100000, LLONG_MAX / 2 ); break;
case 't': program_mode = m_test; break;
case 'v': if( verbosity < 4 ) ++verbosity; break;
case 'V': show_version(); return 0;
default : internal_error( "uncaught option" );
}
}
bool filenames_given = false;
for( ; argind < parser.arguments(); ++argind )
{
if( parser.argument( argind ) != "-" ) filenames_given = true;
filenames.push_back( parser.argument( argind ) );
}
if( filenames.empty() ) filenames.push_back("-");
if( filenames_given ) set_signals();
Pretty_print pp( filenames );
if( program_mode == m_test )
{
output_filename = "/dev/null";
if( !open_outstream( true ) ) return 1;
}
int retval = 0;
for( unsigned int i = 0; i < filenames.size(); ++i )
{
struct stat in_stats;
output_filename.clear();
if( !filenames[i].size() || filenames[i] == "-" )
{
input_filename.clear();
inhandle = STDIN_FILENO;
if( program_mode != m_test )
{
if( to_stdout || !default_output_filename.size() )
outhandle = STDOUT_FILENO;
else
{
if( program_mode == m_compress )
set_c_outname( default_output_filename, volume_size != LLONG_MAX );
else output_filename = default_output_filename;
if( !open_outstream( force ) )
{
if( outhandle == -1 && retval < 1 ) retval = 1;
close( inhandle ); inhandle = -1;
continue;
}
}
}
}
else
{
input_filename = filenames[i];
const int eindex = extension_index( input_filename );
inhandle = open_instream( input_filename, &in_stats, program_mode,
eindex, force, to_stdout );
if( inhandle < 0 ) continue;
if( program_mode != m_test )
{
if( to_stdout ) outhandle = STDOUT_FILENO;
else
{
if( program_mode == m_compress )
set_c_outname( input_filename, volume_size != LLONG_MAX );
else set_d_outname( input_filename, eindex );
if( !open_outstream( force ) )
{
if( outhandle == -1 && retval < 1 ) retval = 1;
close( inhandle ); inhandle = -1;
continue;
}
}
}
}
if( !check_tty( inhandle, program_mode ) ) return 1;
if( output_filename.size() && !to_stdout && program_mode != m_test )
delete_output_on_interrupt = true;
const struct stat * in_statsp = input_filename.size() ? &in_stats : 0;
pp.set_name( input_filename );
int tmp = 0;
if( program_mode == m_compress )
tmp = compress( member_size, volume_size, encoder_options, inhandle,
pp, in_statsp, &retval );
else
tmp = decompress( inhandle, pp, program_mode == m_test );
if( tmp > retval ) retval = tmp;
if( tmp && program_mode != m_test ) cleanup_and_fail( retval );
if( delete_output_on_interrupt )
close_and_set_permissions( in_statsp, &retval );
if( input_filename.size() )
{
close( inhandle ); inhandle = -1;
if( !keep_input_files && !to_stdout && program_mode != m_test )
std::remove( input_filename.c_str() );
}
}
if( outhandle >= 0 ) close( outhandle );
return retval;
}

BIN
testsuite/COPYING.lz Normal file
View file

Binary file not shown.

67
testsuite/check.sh Executable file
View file

@ -0,0 +1,67 @@
#! /bin/sh
# check script for Lzlib - A compression library for lzip files
# Copyright (C) 2009 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
objdir=`pwd`
testdir=`cd "$1" ; pwd`
LZIP="${objdir}"/minilzip
framework_failure() { echo 'failure in testing framework'; exit 1; }
if [ ! -x "${LZIP}" ] ; then
echo "${LZIP}: cannot execute"
exit 1
fi
if [ -d tmp ] ; then rm -r tmp ; fi
mkdir tmp
echo -n "testing minilzip..."
cd "${objdir}"/tmp
cat "${testdir}"/../COPYING > in || framework_failure
fail=0
"${LZIP}" -cd "${testdir}"/COPYING.lz > copy || fail=1
cmp in copy || fail=1
for i in 1 2 3 4 5 6 7 8 9; do
"${LZIP}" -k -$i in || fail=1
mv -f in.lz copy.lz || fail=1
echo -n "garbage" >> copy.lz || fail=1
"${LZIP}" -df copy.lz || fail=1
cmp in copy || fail=1
echo -n .
done
for i in 1 2 3 4 5 6 7 8 9; do
"${LZIP}" -c -$i in > out || fail=1
echo -n "g" >> out || fail=1
"${LZIP}" -cd out > copy || fail=1
cmp in copy || fail=1
echo -n .
done
for i in 1 2 3 4 5 6 7 8 9; do
"${LZIP}" -c -$i < in > out || fail=1
"${LZIP}" -d < out > copy || fail=1
cmp in copy || fail=1
echo -n .
done
for i in 1 2 3 4 5 6 7 8 9; do
"${LZIP}" -f -$i -o out < in || fail=1
"${LZIP}" -df -o copy < out.lz || fail=1
cmp in copy || fail=1
echo -n .
done
echo
if test ${fail} = 0; then
echo "tests completed successfully."
if cd "${objdir}" ; then rm -r tmp ; fi
else
echo "tests failed."
fi
exit ${fail}