From f86afc6aa8317a9ed84be9f8c719dcc64cbd22d1 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Fri, 6 Nov 2015 12:24:27 +0100 Subject: Adding upstream version 1.0~rc2. Signed-off-by: Daniel Baumann --- AUTHORS | 4 + COPYING | 676 ++++++++++++++++++++++++++++++++++++++++ ChangeLog | 18 ++ INSTALL | 56 ++++ Makefile.in | 108 +++++++ NEWS | 7 + README | 66 ++++ carg_parser.c | 291 +++++++++++++++++ carg_parser.h | 101 ++++++ clzip.h | 262 ++++++++++++++++ configure | 194 ++++++++++++ decoder.c | 234 ++++++++++++++ decoder.h | 393 +++++++++++++++++++++++ doc/clzip.1 | 87 ++++++ doc/clzip.info | 443 ++++++++++++++++++++++++++ doc/clzip.texinfo | 462 +++++++++++++++++++++++++++ encoder.c | 646 ++++++++++++++++++++++++++++++++++++++ encoder.h | 650 ++++++++++++++++++++++++++++++++++++++ main.c | 899 +++++++++++++++++++++++++++++++++++++++++++++++++++++ testsuite/check.sh | 69 ++++ testsuite/test1 | 676 ++++++++++++++++++++++++++++++++++++++++ testsuite/test1.lz | Bin 0 -> 11540 bytes 22 files changed, 6342 insertions(+) create mode 100644 AUTHORS create mode 100644 COPYING create mode 100644 ChangeLog create mode 100644 INSTALL create mode 100644 Makefile.in create mode 100644 NEWS create mode 100644 README create mode 100644 carg_parser.c create mode 100644 carg_parser.h create mode 100644 clzip.h create mode 100755 configure create mode 100644 decoder.c create mode 100644 decoder.h create mode 100644 doc/clzip.1 create mode 100644 doc/clzip.info create mode 100644 doc/clzip.texinfo create mode 100644 encoder.c create mode 100644 encoder.h create mode 100644 main.c create mode 100755 testsuite/check.sh create mode 100644 testsuite/test1 create mode 100644 testsuite/test1.lz diff --git a/AUTHORS b/AUTHORS new file mode 100644 index 0000000..75ec7b3 --- /dev/null +++ b/AUTHORS @@ -0,0 +1,4 @@ +Clzip was written by Antonio Diaz Diaz. + +Clzip implements a simplified version of the LZMA algorithm. +The original LZMA algorithm was designed by Igor Pavlov. diff --git a/COPYING b/COPYING new file mode 100644 index 0000000..4432540 --- /dev/null +++ b/COPYING @@ -0,0 +1,676 @@ + + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + 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. + + + Copyright (C) + + 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 . + +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: + + Copyright (C) + 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 +. + + 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 +. + diff --git a/ChangeLog b/ChangeLog new file mode 100644 index 0000000..cbbcdbd --- /dev/null +++ b/ChangeLog @@ -0,0 +1,18 @@ +2010-02-21 Antonio Diaz Diaz + + * Version 1.0-rc2 released. + * Code cleanup. + * clzip.h: Fixed warnings produced by over-optimization (-O3). + +2010-02-14 Antonio Diaz Diaz + + * Version 1.0-rc1 released. + * Initial release. + * Translated to C from the C++ source for lzip 1.10-rc1 + + +Copyright (C) 2010 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. diff --git a/INSTALL b/INSTALL new file mode 100644 index 0000000..d04ceae --- /dev/null +++ b/INSTALL @@ -0,0 +1,56 @@ +Requirements +------------ +You will need a C compiler. +I use gcc 4.3.4 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 clzip[version].tar.lz | tar -xf - +or + gzip -cd clzip[version].tar.gz | tar -xf - + +This creates the directory ./clzip[version] containing the source from +the main archive. + +2. Change to clzip directory and run configure. + (Try `configure --help' for usage instructions). + + cd clzip[version] + ./configure + +3. Run make. + + make + +4. Optionally, type `make check' to run the tests that come with clzip. + +5. Type `make install' to install the program and any data files and + documentation. + + +Another way +----------- +You can also compile clzip 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) 2010 Antonio Diaz Diaz. + +This file is free documentation: you have unlimited permission to copy, +distribute and modify it. diff --git a/Makefile.in b/Makefile.in new file mode 100644 index 0000000..c256299 --- /dev/null +++ b/Makefile.in @@ -0,0 +1,108 @@ + +DISTNAME = $(pkgname)-$(pkgversion) +INSTALL = install +INSTALL_PROGRAM = $(INSTALL) -p -m 755 +INSTALL_DATA = $(INSTALL) -p -m 644 +INSTALL_DIR = $(INSTALL) -d -m 755 +SHELL = /bin/sh + +objs = carg_parser.o decoder.o encoder.o main.o + + +.PHONY : all install install-info install-man install-strip \ + uninstall uninstall-info uninstall-man \ + doc info man check dist clean distclean + +all : $(progname) + +$(progname) : $(objs) + $(CC) $(LDFLAGS) -o $(progname) $(objs) + +$(progname)_profiled : $(objs) + $(CC) $(LDFLAGS) -pg -o $(progname)_profiled $(objs) + +main.o : main.c + $(CC) $(CPPFLAGS) $(CFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $< + +%.o : %.c + $(CC) $(CPPFLAGS) $(CFLAGS) -c -o $@ $< + +$(objs) : Makefile +carg_parser.o : carg_parser.h +decoder.o : clzip.h decoder.h +encoder.o : clzip.h encoder.h +main.o : carg_parser.h clzip.h decoder.h encoder.h + + +doc : info man + +info : $(VPATH)/doc/$(pkgname).info + +$(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo + cd $(VPATH)/doc && makeinfo $(pkgname).texinfo + +man : $(VPATH)/doc/$(progname).1 + +$(VPATH)/doc/$(progname).1 : $(progname) + help2man -n 'data compressor based on the LZMA algorithm' \ + -o $(VPATH)/doc/$(progname).1 ./$(progname) + +Makefile : $(VPATH)/configure $(VPATH)/Makefile.in + ./config.status + +check : all + @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite + +install : all install-info install-man + if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi + $(INSTALL_PROGRAM) ./$(progname) "$(DESTDIR)$(bindir)/$(progname)" + +install-info : + if [ ! -d "$(DESTDIR)$(infodir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(infodir)" ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(pkgname).info "$(DESTDIR)$(infodir)/$(pkgname).info" + -install-info --info-dir="$(DESTDIR)$(infodir)" $(DESTDIR)$(infodir)/$(pkgname).info + +install-man : + if [ ! -d "$(DESTDIR)$(mandir)/man1" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1" ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(progname).1 "$(DESTDIR)$(mandir)/man1/$(progname).1" + +install-strip : all + $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install + +uninstall : uninstall-info uninstall-man + -rm -f "$(DESTDIR)$(bindir)/$(progname)" + +uninstall-info : + -install-info --info-dir="$(DESTDIR)$(infodir)" --remove "$(DESTDIR)$(infodir)/$(pkgname).info" + -rm -f "$(DESTDIR)$(infodir)/$(pkgname).info" + +uninstall-man : + -rm -f "$(DESTDIR)$(mandir)/man1/$(progname).1" + +dist : doc + 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 \ + $(DISTNAME)/doc/$(progname).1 \ + $(DISTNAME)/doc/$(pkgname).info \ + $(DISTNAME)/doc/$(pkgname).texinfo \ + $(DISTNAME)/testsuite/check.sh \ + $(DISTNAME)/testsuite/test1 \ + $(DISTNAME)/testsuite/test1.lz \ + $(DISTNAME)/*.h \ + $(DISTNAME)/*.c + rm -f $(DISTNAME) + lzip -v -9 $(DISTNAME).tar + +clean : + -rm -f $(progname) $(progname)_profiled $(objs) + +distclean : clean + -rm -f Makefile config.status *.tar *.tar.lz diff --git a/NEWS b/NEWS new file mode 100644 index 0000000..fd8c0ee --- /dev/null +++ b/NEWS @@ -0,0 +1,7 @@ +Changes in version 1.0: + +Initial release. + +Translated to C from the C++ source for lzip 1.10-rc1 + +Compiler warnings produced by over-optimization (-O3) have been fixed. diff --git a/README b/README new file mode 100644 index 0000000..69257c5 --- /dev/null +++ b/README @@ -0,0 +1,66 @@ +Description + +Clzip is a lossless data compressor based on the LZMA algorithm, with +very safe integrity checking and a user interface similar to the one of +gzip or bzip2. Clzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + +Clzip replaces every file given in the command line with a compressed +version of itself, with the name "original_name.lz". Each compressed +file has the same modification date, permissions, and, when possible, +ownership as the corresponding original, so that these properties can be +correctly restored at decompression time. Clzip is able to read from some +types of non regular files if the "--stdout" option is specified. + +If no file names are specified, clzip compresses (or decompresses) from +standard input to standard output. In this case, clzip will decline to +write compressed output to a terminal, as this would be entirely +incomprehensible and therefore pointless. + +Clzip will correctly decompress a file which is the concatenation of two +or more compressed files. The result is the concatenation of the +corresponding uncompressed files. Integrity testing of concatenated +compressed files is also supported. + +Clzip can produce multimember files and safely recover, with lziprecover, +the undamaged members in case of file damage. Clzip can also split the +compressed output in volumes of a given size, even when reading from +standard input. This allows the direct creation of multivolume +compressed tar archives. + +Clzip will automatically use the smallest possible dictionary size +without exceeding the given limit. It is important to appreciate that +the decompression memory requirement is affected at compression time by +the choice of dictionary size limit. + +As a self-check for your protection, clzip stores in the member trailer +the 32-bit CRC of the original data and the size of the original data, +to make sure that the decompressed version of the data is identical to +the original. This guards against corruption of the compressed data, and +against undetected bugs in clzip (hopefully very unlikely). The chances +of data corruption going undetected are microscopic, less than one +chance in 4000 million for each member processed. Be aware, though, that +the check occurs upon decompression, so it can only tell you that +something is wrong. It can't help you recover the original uncompressed +data. + +Clzip implements a simplified version of the LZMA (Lempel-Ziv-Markov +chain-Algorithm) algorithm. The original LZMA algorithm was designed by +Igor Pavlov. + +The high compression of LZMA comes from combining two basic, well-proven +compression ideas: sliding dictionaries (LZ77/78) and markov models (the +thing used by every compression algorithm that uses a range encoder or +similar order-0 entropy coder as its last stage) with segregation of +contexts according to what the bits are used for. + + +Copyright (C) 2010 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. diff --git a/carg_parser.c b/carg_parser.c new file mode 100644 index 0000000..fe3228c --- /dev/null +++ b/carg_parser.c @@ -0,0 +1,291 @@ +/* Arg_parser - A POSIX/GNU command line argument parser. (C version) + Copyright (C) 2006, 2007, 2008, 2009, 2010 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 library. If not, see . + + 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 +#include + +#include "carg_parser.h" + + +/* assure at least a minimum size for buffer `buf' */ +static void * ap_resize_buffer( void * buf, const int min_size ) + { + if( buf ) buf = realloc( buf, min_size ); + else buf = malloc( min_size ); + return buf; + } + + +static char push_back_record( struct Arg_parser * const ap, + const int code, const char * const argument ) + { + const int len = strlen( argument ); + struct ap_Record *p; + void * tmp = ap_resize_buffer( ap->data, ( ap->data_size + 1 ) * sizeof (struct ap_Record) ); + if( !tmp ) return 0; + ap->data = (struct ap_Record *)tmp; + p = &(ap->data[ap->data_size]); + p->code = code; + p->argument = 0; + tmp = ap_resize_buffer( p->argument, len + 1 ); + if( !tmp ) return 0; + p->argument = (char *)tmp; + strncpy( p->argument, argument, len + 1 ); + ++ap->data_size; + return 1; + } + + +static char add_error( struct Arg_parser * const ap, const char * const msg ) + { + const int len = strlen( msg ); + void * tmp = ap_resize_buffer( ap->error, ap->error_size + len + 1 ); + if( !tmp ) return 0; + ap->error = (char *)tmp; + strncpy( ap->error + ap->error_size, msg, len + 1 ); + ap->error_size += len; + return 1; + } + + +static void free_data( struct Arg_parser * const ap ) + { + int i; + for( i = 0; i < ap->data_size; ++i ) free( ap->data[i].argument ); + if( ap->data ) { free( ap->data ); ap->data = 0; } + ap->data_size = 0; + } + + +static char parse_long_option( struct Arg_parser * const ap, + const char * const opt, const char * const arg, + const struct ap_Option options[], + int * const argindp ) + { + unsigned int len; + int index = -1; + int i; + char exact = 0, ambig = 0; + + for( len = 0; opt[len+2] && opt[len+2] != '='; ++len ) ; + + // Test all long options for either exact match or abbreviated matches. + for( i = 0; options[i].code != 0; ++i ) + if( options[i].name && !strncmp( options[i].name, &opt[2], len ) ) + { + if( strlen( options[i].name ) == len ) // Exact match found + { index = i; exact = 1; 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 = 1; // Second or later nonexact match found + } + + if( ambig && !exact ) + { + add_error( ap, "option `" ); add_error( ap, opt ); + add_error( ap, "' is ambiguous" ); + return 1; + } + + if( index < 0 ) // nothing found + { + add_error( ap, "unrecognized option `" ); add_error( ap, opt ); + add_error( ap, "'" ); + return 1; + } + + ++*argindp; + + if( opt[len+2] ) // `--=' syntax + { + if( options[index].has_arg == ap_no ) + { + add_error( ap, "option `--" ); add_error( ap, options[index].name ); + add_error( ap, "' doesn't allow an argument" ); + return 1; + } + if( options[index].has_arg == ap_yes && !opt[len+3] ) + { + add_error( ap, "option `--" ); add_error( ap, options[index].name ); + add_error( ap, "' requires an argument" ); + return 1; + } + return push_back_record( ap, options[index].code, &opt[len+3] ); + } + + if( options[index].has_arg == ap_yes ) + { + if( !arg || !arg[0] ) + { + add_error( ap, "option `--" ); add_error( ap, options[index].name ); + add_error( ap, "' requires an argument" ); + return 1; + } + ++*argindp; + return push_back_record( ap, options[index].code, arg ); + } + + return push_back_record( ap, options[index].code, "" ); + } + + +static char parse_short_option( struct Arg_parser * const ap, + const char * const opt, const char * const arg, + const struct ap_Option options[], + int * const argindp ) + { + int cind = 1; // character index in opt + + while( cind > 0 ) + { + int index = -1; + int i; + const unsigned char code = opt[cind]; + const char code_str[2] = { code, 0 }; + + if( code != 0 ) + for( i = 0; options[i].code; ++i ) + if( code == options[i].code ) + { index = i; break; } + + if( index < 0 ) + { + add_error( ap, "invalid option -- " ); add_error( ap, code_str ); + return 1; + } + + if( opt[++cind] == 0 ) { ++*argindp; cind = 0; } // opt finished + + if( options[index].has_arg != ap_no && cind > 0 && opt[cind] ) + { + if( !push_back_record( ap, code, &opt[cind] ) ) return 0; + ++*argindp; cind = 0; + } + else if( options[index].has_arg == ap_yes ) + { + if( !arg || !arg[0] ) + { + add_error( ap, "option requires an argument -- " ); + add_error( ap, code_str ); + return 1; + } + ++*argindp; cind = 0; + if( !push_back_record( ap, code, arg ) ) return 0; + } + else if( !push_back_record( ap, code, "" ) ) return 0; + } + return 1; + } + + +char ap_init( struct Arg_parser * const ap, + const int argc, const char * const argv[], + const struct ap_Option options[], const char in_order ) + { + const char ** non_options = 0; // skipped non-options + int non_options_size = 0; // number of skipped non-options + int argind = 1; // index in argv + int i; + + ap->data = 0; + ap->error = 0; + ap->data_size = 0; + ap->error_size = 0; + if( argc < 2 || !argv || !options ) return 1; + + 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( ap, opt, arg, options, &argind ) ) return 0; + } + else if( !parse_short_option( ap, opt, arg, options, &argind ) ) return 0; + if( ap->error ) break; + } + else + { + if( !in_order ) + { + void * tmp = ap_resize_buffer( non_options, + ( non_options_size + 1 ) * sizeof *non_options ); + if( !tmp ) return 0; + non_options = (const char **)tmp; + non_options[non_options_size++] = argv[argind++]; + } + else if( !push_back_record( ap, 0, argv[argind++] ) ) return 0; + } + } + if( ap->error ) free_data( ap ); + else + { + for( i = 0; i < non_options_size; ++i ) + if( !push_back_record( ap, 0, non_options[i] ) ) return 0; + while( argind < argc ) + if( !push_back_record( ap, 0, argv[argind++] ) ) return 0; + } + if( non_options ) free( non_options ); + return 1; + } + + +void ap_free( struct Arg_parser * const ap ) + { + free_data( ap ); + if( ap->error ) { free( ap->error ); ap->error = 0; } + ap->error_size = 0; + } + + +const char * ap_error( const struct Arg_parser * const ap ) + { return ap->error; } + + +int ap_arguments( const struct Arg_parser * const ap ) + { return ap->data_size; } + + +int ap_code( const struct Arg_parser * const ap, const int i ) + { + if( i >= 0 && i < ap_arguments( ap ) ) return ap->data[i].code; + else return 0; + } + + +const char * ap_argument( const struct Arg_parser * const ap, const int i ) + { + if( i >= 0 && i < ap_arguments( ap ) ) return ap->data[i].argument; + else return ""; + } diff --git a/carg_parser.h b/carg_parser.h new file mode 100644 index 0000000..3f47d81 --- /dev/null +++ b/carg_parser.h @@ -0,0 +1,101 @@ +/* Arg_parser - A POSIX/GNU command line argument parser. (C version) + Copyright (C) 2006, 2007, 2008, 2009, 2010 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 library. If not, see . + + 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. +*/ + +/* Arg_parser reads the arguments in `argv' and creates a number of + option codes, option arguments and non-option arguments. + + In case of error, `ap_error' returns a non-null pointer to an error + message. + + `options' is an array of `struct ap_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 `ap_init' 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 `-' + (without whitespace), or `--='. +*/ + +#ifdef __cplusplus +extern "C" { +#endif + +enum ap_Has_arg { ap_no, ap_yes, ap_maybe }; + +struct ap_Option + { + int code; // Short option letter or code ( code != 0 ) + const char * name; // Long option name (maybe null) + enum ap_Has_arg has_arg; + }; + + +struct ap_Record + { + int code; + char * argument; + }; + + +struct Arg_parser + { + struct ap_Record * data; + char * error; + int data_size; + int error_size; + }; + + +char ap_init( struct Arg_parser * const ap, + const int argc, const char * const argv[], + const struct ap_Option options[], const char in_order ); + +void ap_free( struct Arg_parser * const ap ); + +const char * ap_error( const struct Arg_parser * const ap ); + + // The number of arguments parsed (may be different from argc) +int ap_arguments( const struct Arg_parser * const ap ); + + // If ap_code( i ) is 0, ap_argument( i ) is a non-option. + // Else ap_argument( i ) is the option's argument (or empty). +int ap_code( const struct Arg_parser * const ap, const int i ); + +const char * ap_argument( const struct Arg_parser * const ap, const int i ); + +#ifdef __cplusplus +} +#endif diff --git a/clzip.h b/clzip.h new file mode 100644 index 0000000..c523660 --- /dev/null +++ b/clzip.h @@ -0,0 +1,262 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ + +#ifndef max + #define max(x,y) ((x) >= (y) ? (x) : (y)) +#endif +#ifndef min + #define min(x,y) ((x) <= (y) ? (x) : (y)) +#endif + +typedef unsigned char State; + +enum { St_states = 12 }; + +static inline bool St_is_char( const State st ) { return st < 7; } + +static inline void St_set_char( State * const st ) + { + static const unsigned char next[St_states] = + {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5}; + *st = next[*st]; + } +static inline void St_set_match( State * const st ) + { + static const unsigned char next[St_states] = + {7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10}; + *st = next[*st]; + } +static inline void St_set_rep( State * const st ) + { + static const unsigned char next[St_states] = + {8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11}; + *st = next[*st]; + } +static inline void St_set_short_rep( State * const st ) + { + static const unsigned char next[St_states] = + {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11}; + *st = next[*st]; + } + +enum { + min_dictionary_bits = 12, + min_dictionary_size = 1 << min_dictionary_bits, + max_dictionary_bits = 29, + max_dictionary_size = 1 << max_dictionary_bits, + literal_context_bits = 3, + pos_state_bits = 2, + pos_states = 1 << pos_state_bits, + pos_state_mask = pos_states - 1, + + dis_slot_bits = 6, + start_dis_model = 4, + end_dis_model = 14, + modeled_distances = 1 << (end_dis_model / 2), + dis_align_bits = 4, + dis_align_size = 1 << dis_align_bits, + + len_low_bits = 3, + len_mid_bits = 3, + len_high_bits = 8, + len_low_symbols = 1 << len_low_bits, + len_mid_symbols = 1 << len_mid_bits, + len_high_symbols = 1 << len_high_bits, + max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols, + + min_match_len = 2, // must be 2 + max_match_len = min_match_len + max_len_symbols - 1, // 273 + min_match_len_limit = 5, + + max_dis_states = 4 }; + +static inline int get_dis_state( int len ) + { + len -= min_match_len; + if( len >= max_dis_states ) len = max_dis_states - 1; + return len; + } + +enum { + bit_model_move_bits = 5, + bit_model_total_bits = 11, + bit_model_total = 1 << bit_model_total_bits }; + +typedef unsigned int Bit_model; + +static inline void Bm_init( Bit_model * const probability ) + { *probability = bit_model_total / 2; } + + +struct Pretty_print + { + const char * name_; + const char * stdin_name; + int longest_name; + bool first_post; + }; + +void Pp_init( struct Pretty_print * const pp, const char * const filenames[], + const int num_filenames ); + +static inline void Pp_set_name( struct Pretty_print * const pp, + const char * const filename ) + { + if( filename && filename[0] && strcmp( filename, "-" ) ) + pp->name_ = filename; + else pp->name_ = pp->stdin_name; + pp->first_post = true; + } + +static inline void Pp_reset( struct Pretty_print * const pp ) + { if( pp->name_ && pp->name_[0] ) pp->first_post = true; } +void Pp_show_msg( struct Pretty_print * const pp, const char * const msg ); + + +typedef uint32_t CRC32[256]; // Table of CRCs of all 8-bit messages. + +extern CRC32 crc32; + +static inline void CRC32_init() + { + 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; } + crc32[n] = c; + } + } + +static inline void CRC32_update_byte( uint32_t * crc, const uint8_t byte ) + { *crc = crc32[(*crc^byte)&0xFF] ^ ( *crc >> 8 ); } +static inline void CRC32_update_buf( uint32_t * crc, const uint8_t * const buffer, + const int size ) + { + for( int i = 0; i < size; ++i ) + *crc = crc32[(*crc^buffer[i])&0xFF] ^ ( *crc >> 8 ); + } + + +typedef uint8_t File_header[6]; // 0-3 magic bytes + // 4 version + // 5 coded_dict_size; + +static inline void Fh_set_magic( File_header header ) + { + const uint8_t magic_string[4] = { 'L', 'Z', 'I', 'P' }; + memcpy( header, magic_string, 4 ); + header[4] = 1; + } + +static inline bool Fh_verify_magic( const File_header header ) + { + const uint8_t magic_string[4] = { 'L', 'Z', 'I', 'P' }; + return ( memcmp( header, magic_string, 4 ) == 0 ); + } + +static inline uint8_t Fh_version( const File_header header ) + { return header[4]; } + +static inline bool Fh_verify_version( const File_header header ) + { return ( header[4] <= 1 ); } + +static inline int Fh_real_bits( const int value ) + { + int bits = 0; + for( int i = 1, mask = 1; mask > 0; ++i, mask <<= 1 ) + if( value & mask ) bits = i; + return bits; + } + +static inline int Fh_get_dictionary_size( const File_header header ) + { + int size = ( 1 << ( header[5] & 0x1F ) ); + if( size > min_dictionary_size && size <= max_dictionary_size ) + size -= ( size / 16 ) * ( ( header[5] >> 5 ) & 0x07 ); + return size; + } + +static inline bool Fh_set_dictionary_size( File_header header, const int size ) + { + if( size >= min_dictionary_size && size <= max_dictionary_size ) + { + header[5] = Fh_real_bits( size - 1 ); + if( size > min_dictionary_size ) + { + const int base_size = 1 << header[5]; + const int wedge = base_size / 16; + for( int i = 7; i >= 1; --i ) + if( base_size - ( i * wedge ) >= size ) + { header[5] |= ( i << 5 ); break; } + } + return true; + } + return false; + } + + +typedef uint8_t File_trailer[20]; + // 0-3 CRC32 of the uncompressed data + // 4-11 size of the uncompressed data + // 12-19 member size including header and trailer + +static inline int Ft_size( const int version ) + { return sizeof (File_trailer) - ( ( version >= 1 ) ? 0 : 8 ); } + +static inline uint32_t Ft_get_data_crc( const File_trailer trailer ) + { + uint32_t tmp = 0; + for( int i = 3; i >= 0; --i ) { tmp <<= 8; tmp += trailer[i]; } + return tmp; + } + +static inline void Ft_set_data_crc( File_trailer trailer, uint32_t crc ) + { for( int i = 0; i <= 3; ++i ) { trailer[i] = (uint8_t)crc; crc >>= 8; } } + +static inline long long Ft_get_data_size( const File_trailer trailer ) + { + long long tmp = 0; + for( int i = 11; i >= 4; --i ) { tmp <<= 8; tmp += trailer[i]; } + return tmp; + } + +static inline void Ft_set_data_size( File_trailer trailer, long long size ) + { + for( int i = 4; i <= 11; ++i ) { trailer[i] = (uint8_t)size; size >>= 8; } + } + +static inline long long Ft_get_member_size( const File_trailer trailer ) + { + long long tmp = 0; + for( int i = 19; i >= 12; --i ) { tmp <<= 8; tmp += trailer[i]; } + return tmp; + } + +static inline void Ft_set_member_size( File_trailer trailer, long long size ) + { + for( int i = 12; i <= 19; ++i ) { trailer[i] = (uint8_t)size; size >>= 8; } + } + + +extern int verbosity; + +void cleanup_and_fail( const int retval ); +void show_error( const char * const msg, const int errcode, const bool help ); +void internal_error( const char * const msg ); +int readblock( const int fd, uint8_t * const buf, const int size ); +int writeblock( const int fd, const uint8_t * const buf, const int size ); diff --git a/configure b/configure new file mode 100755 index 0000000..5ebfe51 --- /dev/null +++ b/configure @@ -0,0 +1,194 @@ +#! /bin/sh +# configure script for Clzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2010 Antonio Diaz Diaz. +# +# This configure script is free software: you have unlimited permission +# to copy, distribute and modify it. +# +# Date of this version: 2010-02-21 + +args= +no_create= +pkgname=clzip +pkgversion=1.0-rc2 +progname=clzip +srctrigger=clzip.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' +infodir='$(datadir)/info' +mandir='$(datadir)/man' +sysconfdir='$(prefix)/etc' +CC= +CPPFLAGS= +CFLAGS='-Wall -W -O2 -std=gnu99' +LDFLAGS= + +# Loop over all args +while [ -n "$1" ] ; 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 [${datadir}]" + echo " --infodir=DIR info files directory [${infodir}]" + echo " --mandir=DIR man pages directory [${mandir}]" + echo " --sysconfdir=DIR read-only single-machine data directory [${sysconfdir}]" + echo " CC=COMPILER C compiler to use [gcc]" + echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" + echo " CFLAGS=OPTIONS command line options for the C compiler [${CFLAGS}]" + 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 ${optarg} | sed -e 's,/$,,'` ;; + --infodir* | --in*) + infodir=`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 ;; + + CC=*) CC=${optarg} ;; + CPPFLAGS=*) CPPFLAGS=${optarg} ;; + CFLAGS=*) CFLAGS=${optarg} ;; + LDFLAGS=*) LDFLAGS=${optarg} ;; + + --* | *=* | *-*-*) ;; + *) + echo "configure: Unrecognized option: \"${option}\"; use --help for usage." 1>&2 + exit 1 ;; + esac +done + +# Find the source files, if location was not specified. +srcdirtext= +if [ -z "${srcdir}" ] ; 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 $0 | sed -e 's,[^/]*$,,;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 ${srcdir} ; pwd`" ] ; then srcdir=. ; fi + +# checking whether we are using GNU C. +if [ -z "${CC}" ] ; 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 + +echo +if [ -z "${no_create}" ] ; 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 $0 ${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 "infodir = ${infodir}" +echo "mandir = ${mandir}" +echo "sysconfdir = ${sysconfdir}" +echo "CC = ${CC}" +echo "CPPFLAGS = ${CPPFLAGS}" +echo "CFLAGS = ${CFLAGS}" +echo "LDFLAGS = ${LDFLAGS}" +rm -f Makefile +cat > Makefile << EOF +# Makefile for Clzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2010 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} +progname = ${progname} +VPATH = ${srcdir} +prefix = ${prefix} +exec_prefix = ${exec_prefix} +bindir = ${bindir} +datadir = ${datadir} +infodir = ${infodir} +mandir = ${mandir} +sysconfdir = ${sysconfdir} +CC = ${CC} +CPPFLAGS = ${CPPFLAGS} +CFLAGS = ${CFLAGS} +LDFLAGS = ${LDFLAGS} +EOF +cat ${srcdir}/Makefile.in >> Makefile + +echo "OK. Now you can run make." diff --git a/decoder.c b/decoder.c new file mode 100644 index 0000000..20799a3 --- /dev/null +++ b/decoder.c @@ -0,0 +1,234 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include + +#include "clzip.h" +#include "decoder.h" + + +bool Ib_read_block( struct Input_buffer * const ibuf ) + { + if( ibuf->at_stream_end ) return false; + ibuf->stream_pos = readblock( ibuf->infd_, ibuf->buffer, Ib_buffer_size ); + if( ibuf->stream_pos != Ib_buffer_size && errno ) + { show_error( "read error", errno, false ); cleanup_and_fail( 1 ); } + ibuf->pos = 0; + ibuf->at_stream_end = ( ibuf->stream_pos < Ib_buffer_size ); + return !Ib_finished( ibuf ); + } + + +void LZd_flush_data( struct LZ_decoder * const decoder ) + { + const int size = decoder->pos - decoder->stream_pos; + if( size > 0 ) + { + CRC32_update_buf( &decoder->crc_, decoder->buffer + decoder->stream_pos, size ); + if( decoder->outfd_ >= 0 && + writeblock( decoder->outfd_, decoder->buffer + decoder->stream_pos, size ) != size ) + { show_error( "write error", errno, false ); cleanup_and_fail( 1 ); } + if( decoder->pos >= decoder->buffer_size ) + { decoder->partial_data_pos += decoder->pos; decoder->pos = 0; } + decoder->stream_pos = decoder->pos; + } + } + + +bool LZd_verify_trailer( struct LZ_decoder * const decoder, + struct Pretty_print * const pp ) + { + bool error = false; + File_trailer trailer; + const int trailer_size = Ft_size( decoder->format_version ); + for( int i = 0; i < trailer_size && !error; ++i ) + { + if( !Rd_finished( &decoder->range_decoder ) ) + trailer[i] = Rd_get_byte( &decoder->range_decoder ); + else + { + error = true; + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "trailer truncated at trailer position %d;" + " some checks may fail.\n", i ); + } + } + } + if( decoder->format_version == 0 ) + Ft_set_member_size( trailer, LZd_member_position( decoder ) ); + if( !Rd_code_is_zero( &decoder->range_decoder ) ) + { + error = true; + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "range_decoder final code is not zero.\n" ); + } + } + if( Ft_get_data_crc( trailer ) != LZd_crc( decoder ) ) + { + error = true; + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "crc mismatch; trailer says %08X, data crc is %08X.\n", + (unsigned int)Ft_get_data_crc( trailer ), + (unsigned int)LZd_crc( decoder ) ); + } + } + if( Ft_get_data_size( trailer ) != LZd_data_position( decoder ) ) + { + error = true; + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "data size mismatch; trailer says %lld, data size is %lld.\n", + Ft_get_data_size( trailer ), LZd_data_position( decoder ) ); + } + } + if( Ft_get_member_size( trailer ) != LZd_member_position( decoder ) ) + { + error = true; + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "member size mismatch; trailer says %lld, member size is %lld.\n", + Ft_get_member_size( trailer ), LZd_member_position( decoder ) ); + } + } + if( !error && verbosity >= 3 ) + fprintf( stderr, "data crc %08X, data size %9lld, member size %8lld. ", + (unsigned int)Ft_get_data_crc( trailer ), + Ft_get_data_size( trailer ), Ft_get_member_size( trailer ) ); + return !error; + } + + + // Return value: 0 = OK, 1 = decoder error, 2 = unexpected EOF, + // 3 = trailer error, 4 = unknown marker found. +int LZd_decode_member( struct LZ_decoder * const decoder, + struct Pretty_print * const pp ) + { + unsigned int rep0 = 0; // rep[0-3] latest four distances + unsigned int rep1 = 0; // used for efficient coding of + unsigned int rep2 = 0; // repeated distances + unsigned int rep3 = 0; + State state = 0; + + while( true ) + { + if( Rd_finished( &decoder->range_decoder ) ) + { LZd_flush_data( decoder ); return 2; } + const int pos_state = LZd_data_position( decoder ) & pos_state_mask; + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_match[state][pos_state] ) == 0 ) + { + const uint8_t prev_byte = LZd_get_byte( decoder, 0 ); + if( St_is_char( state ) ) + LZd_put_byte( decoder, Lid_decode( &decoder->literal_decoder, &decoder->range_decoder, prev_byte ) ); + else + LZd_put_byte( decoder, Lid_decode_matched( &decoder->literal_decoder, &decoder->range_decoder, prev_byte, + LZd_get_byte( decoder, rep0 ) ) ); + St_set_char( &state ); + } + else + { + int len; + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_rep[state] ) == 1 ) + { + len = 0; + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_rep0[state] ) == 0 ) + { + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_len[state][pos_state] ) == 0 ) + { len = 1; St_set_short_rep( &state ); } + } + else + { + unsigned int distance; + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_rep1[state] ) == 0 ) + distance = rep1; + else + { + if( Rd_decode_bit( &decoder->range_decoder, &decoder->bm_rep2[state] ) == 0 ) + distance = rep2; + else { distance = rep3; rep3 = rep2; } + rep2 = rep1; + } + rep1 = rep0; + rep0 = distance; + } + if( len == 0 ) + { + len = min_match_len + Led_decode( &decoder->rep_match_len_decoder, &decoder->range_decoder, pos_state ); + St_set_rep( &state ); + } + } + else + { + unsigned int rep0_saved = rep0; + len = min_match_len + Led_decode( &decoder->len_decoder, &decoder->range_decoder, pos_state ); + const int dis_slot = Rd_decode_tree( &decoder->range_decoder, decoder->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 += Rd_decode_tree_reversed( &decoder->range_decoder, decoder->bm_dis + rep0 - dis_slot, direct_bits ); + else + { + rep0 += Rd_decode( &decoder->range_decoder, direct_bits - dis_align_bits ) << dis_align_bits; + rep0 += Rd_decode_tree_reversed( &decoder->range_decoder, decoder->bm_align, dis_align_bits ); + if( rep0 == 0xFFFFFFFF ) // Marker found + { + rep0 = rep0_saved; + Rd_normalize( &decoder->range_decoder ); + LZd_flush_data( decoder ); + if( len == min_match_len ) // End Of Stream marker + { + if( LZd_verify_trailer( decoder, pp ) ) return 0; else return 3; + } + if( len == min_match_len + 1 ) // Sync Flush marker + { + Rd_reload( &decoder->range_decoder ); continue; + } + if( verbosity >= 0 ) + { + Pp_show_msg( pp, 0 ); + fprintf( stderr, "unsupported marker code `%d'.\n", len ); + } + return 4; + } + if( rep0 >= (unsigned int)decoder->dictionary_size ) + { LZd_flush_data( decoder ); return 1; } + } + } + rep3 = rep2; rep2 = rep1; rep1 = rep0_saved; + St_set_match( &state ); + } + LZd_copy_block( decoder, rep0, len ); + } + } + } diff --git a/decoder.h b/decoder.h new file mode 100644 index 0000000..7df68b9 --- /dev/null +++ b/decoder.h @@ -0,0 +1,393 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ + +enum { Ib_buffer_size = 65536 }; + +struct Input_buffer + { + uint8_t * buffer; + int pos; + int stream_pos; // when reached, a new block must be read + int infd_; // input file descriptor + bool at_stream_end; + }; + +bool Ib_read_block( struct Input_buffer * const ibuf ); + +static inline void Ib_init( struct Input_buffer * const ibuf, const int infd ) + { + ibuf->buffer = (uint8_t *)malloc( Ib_buffer_size ); + if( !ibuf->buffer ) + { + show_error( "not enough memory. Find a machine with more memory", 0, false ); + cleanup_and_fail( 1 ); + } + ibuf->pos = 0; + ibuf->stream_pos = 0; + ibuf->infd_ = infd; + ibuf->at_stream_end = false; + } + +static inline void Ib_free( struct Input_buffer * const ibuf ) + { free( ibuf->buffer ); ibuf->buffer = 0; } + +static inline bool Ib_finished( struct Input_buffer * const ibuf ) + { return ibuf->at_stream_end && ibuf->pos >= ibuf->stream_pos; } + +static inline uint8_t Ib_get_byte( struct Input_buffer * const ibuf ) + { + if( ibuf->pos >= ibuf->stream_pos && !Ib_read_block( ibuf ) ) + return 0; + return ibuf->buffer[ibuf->pos++]; + } + + +struct Range_decoder + { + long long member_pos; + uint32_t code; + uint32_t range; + struct Input_buffer * ibuf; + }; + +static inline uint8_t Rd_get_byte( struct Range_decoder * const range_decoder ) + { + ++range_decoder->member_pos; + return Ib_get_byte( range_decoder->ibuf ); + } + +static inline void Rd_init( struct Range_decoder * const range_decoder, + struct Input_buffer * const buf ) + { + range_decoder->member_pos = sizeof (File_header); + range_decoder->code = 0; + range_decoder->range = 0xFFFFFFFF; + range_decoder->ibuf = buf; + for( int i = 0; i < 5; ++i ) + range_decoder->code = (range_decoder->code << 8) | + Rd_get_byte( range_decoder ); + } + +static inline bool Rd_code_is_zero( struct Range_decoder * const range_decoder ) + { return ( range_decoder->code == 0 ); } +static inline bool Rd_finished( struct Range_decoder * const range_decoder ) + { return Ib_finished( range_decoder->ibuf ); } +static inline long long Rd_member_position( struct Range_decoder * const range_decoder ) + { return range_decoder->member_pos; } + +static inline void Rd_reload( struct Range_decoder * const range_decoder ) + { + range_decoder->code = 0; + range_decoder->range = 0xFFFFFFFF; + for( int i = 0; i < 5; ++i ) + range_decoder->code = (range_decoder->code << 8) | + Rd_get_byte( range_decoder ); + } + +static inline void Rd_normalize( struct Range_decoder * const range_decoder ) + { + if( range_decoder->range <= 0x00FFFFFF ) + { + range_decoder->range <<= 8; + range_decoder->code = (range_decoder->code << 8) | + Rd_get_byte( range_decoder ); + } + } + +static inline int Rd_decode( struct Range_decoder * const range_decoder, + const int num_bits ) + { + int symbol = 0; + for( int i = num_bits; i > 0; --i ) + { + symbol <<= 1; + if( range_decoder->range <= 0x00FFFFFF ) + { + range_decoder->range <<= 7; + range_decoder->code = (range_decoder->code << 8) | + Rd_get_byte( range_decoder ); + if( range_decoder->code >= range_decoder->range ) + { range_decoder->code -= range_decoder->range; symbol |= 1; } + } + else + { + range_decoder->range >>= 1; + if( range_decoder->code >= range_decoder->range ) + { range_decoder->code -= range_decoder->range; symbol |= 1; } + } + } + return symbol; + } + +static inline int Rd_decode_bit( struct Range_decoder * const range_decoder, + Bit_model * const probability ) + { + Rd_normalize( range_decoder ); + const uint32_t bound = ( range_decoder->range >> bit_model_total_bits ) * + *probability; + if( range_decoder->code < bound ) + { + range_decoder->range = bound; + *probability += (bit_model_total - *probability) >> bit_model_move_bits; + return 0; + } + else + { + range_decoder->range -= bound; + range_decoder->code -= bound; + *probability -= *probability >> bit_model_move_bits; + return 1; + } + } + +static inline int Rd_decode_tree( struct Range_decoder * const range_decoder, + Bit_model bm[], const int num_bits ) + { + int model = 1; + for( int i = num_bits; i > 0; --i ) + model = ( model << 1 ) | Rd_decode_bit( range_decoder, &bm[model] ); + return model - (1 << num_bits); + } + +static inline int Rd_decode_tree_reversed( struct Range_decoder * const range_decoder, + Bit_model bm[], const int num_bits ) + { + int model = 1; + int symbol = 0; + for( int i = 0; i < num_bits; ++i ) + { + const int bit = Rd_decode_bit( range_decoder, &bm[model] ); + model <<= 1; + if( bit ) { model |= 1; symbol |= (1 << i); } + } + return symbol; + } + +static inline int Rd_decode_matched( struct Range_decoder * const range_decoder, + Bit_model bm[], const int match_byte ) + { + Bit_model *bm1 = bm + 0x100; + int symbol = 1; + for( int i = 1; i <= 8; ++i ) + { + const int match_bit = ( match_byte << i ) & 0x100; + const int bit = Rd_decode_bit( range_decoder, &bm1[match_bit+symbol] ); + symbol = ( symbol << 1 ) | bit; + if( ( match_bit && !bit ) || ( !match_bit && bit ) ) + { + while( ++i <= 8 ) + symbol = ( symbol << 1 ) | Rd_decode_bit( range_decoder, &bm[symbol] ); + break; + } + } + return symbol & 0xFF; + } + + +struct 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]; + }; + +static inline void Led_init( struct Len_decoder * const len_decoder ) + { + Bm_init( &len_decoder->choice1 ); + Bm_init( &len_decoder->choice2 ); + for( int i = 0; i < pos_states; ++i ) + for( int j = 0; j < len_low_symbols; ++j ) + Bm_init( &len_decoder->bm_low[i][j] ); + for( int i = 0; i < pos_states; ++i ) + for( int j = 0; j < len_mid_symbols; ++j ) + Bm_init( &len_decoder->bm_mid[i][j] ); + for( int i = 0; i < len_high_symbols; ++i ) + Bm_init( &len_decoder->bm_high[i] ); + } + +static inline int Led_decode( struct Len_decoder * const len_decoder, + struct Range_decoder * const range_decoder, + const int pos_state ) + { + if( Rd_decode_bit( range_decoder, &len_decoder->choice1 ) == 0 ) + return Rd_decode_tree( range_decoder, len_decoder->bm_low[pos_state], + len_low_bits ); + if( Rd_decode_bit( range_decoder, &len_decoder->choice2 ) == 0 ) + return len_low_symbols + + Rd_decode_tree( range_decoder, len_decoder->bm_mid[pos_state], + len_mid_bits ); + return len_low_symbols + len_mid_symbols + + Rd_decode_tree( range_decoder, len_decoder->bm_high, len_high_bits ); + } + + +struct Literal_decoder + { + Bit_model bm_literal[1<bm_literal[i][j] ); + } + +static inline int Lid_state( const int prev_byte ) + { return ( prev_byte >> ( 8 - literal_context_bits ) ); } + +static inline uint8_t Lid_decode( struct Literal_decoder * const literal_decoder, + struct Range_decoder * const range_decoder, + const uint8_t prev_byte ) + { return Rd_decode_tree( range_decoder, literal_decoder->bm_literal[Lid_state(prev_byte)], 8 ); } + +static inline uint8_t Lid_decode_matched( struct Literal_decoder * const literal_decoder, + struct Range_decoder * const range_decoder, + const uint8_t prev_byte, + const uint8_t match_byte ) + { return Rd_decode_matched( range_decoder, literal_decoder->bm_literal[Lid_state(prev_byte)], match_byte ); } + + +struct LZ_decoder + { + long long partial_data_pos; + int format_version; + int dictionary_size; + int buffer_size; + uint8_t * buffer; + int pos; + int stream_pos; // first byte not yet written to file + uint32_t crc_; + int outfd_; // output file descriptor + + Bit_model bm_match[St_states][pos_states]; + Bit_model bm_rep[St_states]; + Bit_model bm_rep0[St_states]; + Bit_model bm_rep1[St_states]; + Bit_model bm_rep2[St_states]; + Bit_model bm_len[St_states][pos_states]; + Bit_model bm_dis_slot[max_dis_states][1<pos - distance - 1; + if( i < 0 ) i += decoder->buffer_size; + return decoder->buffer[i]; + } + +static inline void LZd_put_byte( struct LZ_decoder * const decoder, + const uint8_t b ) + { + decoder->buffer[decoder->pos] = b; + if( ++decoder->pos >= decoder->buffer_size ) + LZd_flush_data( decoder ); + } + +static inline void LZd_copy_block( struct LZ_decoder * const decoder, + const int distance, int len ) + { + int i = decoder->pos - distance - 1; + if( i < 0 ) i += decoder->buffer_size; + if( len < decoder->buffer_size - max( decoder->pos, i ) && + len <= abs( decoder->pos - i ) ) + { + memcpy( decoder->buffer + decoder->pos, decoder->buffer + i, len ); + decoder->pos += len; + } + else for( ; len > 0 ; --len ) + { + decoder->buffer[decoder->pos] = decoder->buffer[i]; + if( ++decoder->pos >= decoder->buffer_size ) + LZd_flush_data( decoder ); + if( ++i >= decoder->buffer_size ) i = 0; + } + } + +bool LZd_verify_trailer( struct LZ_decoder * const decoder, + struct Pretty_print * const pp ); + +static inline void LZd_init( struct LZ_decoder * const decoder, + const File_header header, + struct Input_buffer * const ibuf, const int outfd ) + { + decoder->partial_data_pos = 0; + decoder->format_version = Fh_version( header ); + decoder->dictionary_size = Fh_get_dictionary_size( header ); + decoder->buffer_size = max( 65536, decoder->dictionary_size ); + decoder->buffer = (uint8_t *)malloc( decoder->buffer_size ); + if( !decoder->buffer ) + { + show_error( "not enough memory. Find a machine with more memory", 0, false ); + cleanup_and_fail( 1 ); + } + decoder->pos = 0; + decoder->stream_pos = 0; + decoder->crc_ = 0xFFFFFFFF; + decoder->outfd_ = outfd; + + for( int i = 0; i < St_states; ++i ) + { + for( int j = 0; j < pos_states; ++j ) + { + Bm_init( &decoder->bm_match[i][j] ); + Bm_init( &decoder->bm_len[i][j] ); + } + Bm_init( &decoder->bm_rep[i] ); + Bm_init( &decoder->bm_rep0[i] ); + Bm_init( &decoder->bm_rep1[i] ); + Bm_init( &decoder->bm_rep2[i] ); + } + for( int i = 0; i < max_dis_states; ++i ) + for( int j = 0; j < 1<bm_dis_slot[i][j] ); + for( int i = 0; i < modeled_distances-end_dis_model; ++i ) + Bm_init( &decoder->bm_dis[i] ); + for( int i = 0; i < dis_align_size; ++i ) + Bm_init( &decoder->bm_align[i] ); + + Rd_init( &decoder->range_decoder, ibuf ); + Led_init( &decoder->len_decoder ); + Led_init( &decoder->rep_match_len_decoder ); + Lid_init( &decoder->literal_decoder ); + decoder->buffer[decoder->buffer_size-1] = 0; // prev_byte of first_byte + } + +static inline void LZd_free( struct LZ_decoder * const decoder ) + { free( decoder->buffer ); decoder->buffer = 0; } + +static inline uint32_t LZd_crc( struct LZ_decoder * const decoder ) + { return decoder->crc_ ^ 0xFFFFFFFF; } +int LZd_decode_member( struct LZ_decoder * const decoder, + struct Pretty_print * const pp ); + +static inline long long LZd_member_position( struct LZ_decoder * const decoder ) + { return Rd_member_position( &decoder->range_decoder ); } +static inline long long LZd_data_position( struct LZ_decoder * const decoder ) + { return decoder->partial_data_pos + decoder->pos; } diff --git a/doc/clzip.1 b/doc/clzip.1 new file mode 100644 index 0000000..71884aa --- /dev/null +++ b/doc/clzip.1 @@ -0,0 +1,87 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36. +.TH CLZIP "1" "February 2010" "Clzip 1.0-rc2" "User Commands" +.SH NAME +Clzip \- data compressor based on the LZMA algorithm +.SH SYNOPSIS +.B clzip +[\fIoptions\fR] [\fIfiles\fR] +.SH DESCRIPTION +Clzip \- A data compressor based on the LZMA algorithm. +.SH OPTIONS +.TP +\fB\-h\fR, \fB\-\-help\fR +display this help and exit +.TP +\fB\-V\fR, \fB\-\-version\fR +output version information and exit +.TP +\fB\-b\fR, \fB\-\-member\-size=\fR +set member size limit in bytes +.TP +\fB\-c\fR, \fB\-\-stdout\fR +send output to standard output +.TP +\fB\-d\fR, \fB\-\-decompress\fR +decompress +.TP +\fB\-f\fR, \fB\-\-force\fR +overwrite existing output files +.TP +\fB\-k\fR, \fB\-\-keep\fR +keep (don't delete) input files +.TP +\fB\-m\fR, \fB\-\-match\-length=\fR +set match length limit in bytes [80] +.TP +\fB\-o\fR, \fB\-\-output=\fR +if reading stdin, place the output into +.TP +\fB\-q\fR, \fB\-\-quiet\fR +suppress all messages +.TP +\fB\-s\fR, \fB\-\-dictionary\-size=\fR +set dictionary size limit in bytes [8MiB] +.TP +\fB\-S\fR, \fB\-\-volume\-size=\fR +set volume size limit in bytes +.TP +\fB\-t\fR, \fB\-\-test\fR +test compressed file integrity +.TP +\fB\-v\fR, \fB\-\-verbose\fR +be verbose (a 2nd \fB\-v\fR gives more) +.TP +\fB\-1\fR .. \fB\-9\fR +set compression level [default 6] +.TP +\fB\-\-fast\fR +alias for \fB\-1\fR +.TP +\fB\-\-best\fR +alias for \fB\-9\fR +.PP +If no file names are given, clzip compresses or decompresses +from standard input to standard output. +Numbers may be followed by a multiplier: k = kB = 10^3 = 1000, +Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc... +.SH "REPORTING BUGS" +Report bugs to lzip\-bug@nongnu.org +Clzip home page: http://www.nongnu.org/lzip/clzip.html +.SH COPYRIGHT +Copyright \(co 2010 Antonio Diaz Diaz. +License GPLv3+: GNU GPL version 3 or later +.br +This is free software: you are free to change and redistribute it. +There is NO WARRANTY, to the extent permitted by law. +.SH "SEE ALSO" +The full documentation for +.B Clzip +is maintained as a Texinfo manual. If the +.B info +and +.B Clzip +programs are properly installed at your site, the command +.IP +.B info Clzip +.PP +should give you access to the complete manual. diff --git a/doc/clzip.info b/doc/clzip.info new file mode 100644 index 0000000..d4a51b3 --- /dev/null +++ b/doc/clzip.info @@ -0,0 +1,443 @@ +This is clzip.info, produced by makeinfo version 4.13 from +clzip.texinfo. + +INFO-DIR-SECTION Data Compression +START-INFO-DIR-ENTRY +* Clzip: (clzip). Data compressor based on the LZMA algorithm +END-INFO-DIR-ENTRY + + +File: clzip.info, Node: Top, Next: Introduction, Up: (dir) + +Clzip Manual +************ + +This manual is for Clzip (version 1.0-rc2, 21 February 2010). + +* Menu: + +* Introduction:: Purpose and features of clzip +* Algorithm:: How clzip compresses the data +* Invoking Clzip:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Problems:: Reporting bugs +* Concept Index:: Index of concepts + + + Copyright (C) 2010 Antonio Diaz Diaz. + + This manual is free documentation: you have unlimited permission to +copy, distribute and modify it. + + +File: clzip.info, Node: Introduction, Next: Algorithm, Prev: Top, Up: Top + +1 Introduction +************** + +Clzip is a lossless data compressor based on the LZMA algorithm, with +very safe integrity checking and a user interface similar to the one of +gzip or bzip2. Clzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + + Clzip replaces every file given in the command line with a compressed +version of itself, with the name "original_name.lz". Each compressed +file has the same modification date, permissions, and, when possible, +ownership as the corresponding original, so that these properties can be +correctly restored at decompression time. Clzip is able to read from +some types of non regular files if the `--stdout' option is specified. + + If no file names are specified, clzip compresses (or decompresses) +from standard input to standard output. In this case, clzip will +decline to write compressed output to a terminal, as this would be +entirely incomprehensible and therefore pointless. + + Clzip will correctly decompress a file which is the concatenation of +two or more compressed files. The result is the concatenation of the +corresponding uncompressed files. Integrity testing of concatenated +compressed files is also supported. + + Clzip can produce multimember files and safely recover, with +lziprecover, the undamaged members in case of file damage. Clzip can +also split the compressed output in volumes of a given size, even when +reading from standard input. This allows the direct creation of +multivolume compressed tar archives. + + The amount of memory required for compression is about 5 MiB plus 1 +or 2 times the dictionary size limit (1 if input file size is less than +dictionary size limit, else 2) plus 8 times the dictionary size really +used. For decompression is a little more than the dictionary size really +used. Clzip will automatically use the smallest possible dictionary size +without exceeding the given limit. It is important to appreciate that +the decompression memory requirement is affected at compression time by +the choice of dictionary size limit. + + When decompressing, clzip attempts to guess the name for the +decompressed file from that of the compressed file as follows: + +filename.lz becomes filename +filename.tlz becomes filename.tar +anyothername becomes anyothername.out + + As a self-check for your protection, clzip stores in the member +trailer the 32-bit CRC of the original data and the size of the +original data, to make sure that the decompressed version of the data +is identical to the original. This guards against corruption of the +compressed data, and against undetected bugs in clzip (hopefully very +unlikely). The chances of data corruption going undetected are +microscopic, less than one chance in 4000 million for each member +processed. Be aware, though, that the check occurs upon decompression, +so it can only tell you that something is wrong. It can't help you +recover the original uncompressed data. + + 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 clzip to panic. + + +File: clzip.info, Node: Algorithm, Next: Invoking Clzip, Prev: Introduction, Up: Top + +2 Algorithm +*********** + +Clzip implements a simplified version of the LZMA (Lempel-Ziv-Markov +chain-Algorithm) algorithm. The original LZMA algorithm was designed by +Igor Pavlov. + + The high compression of LZMA comes from combining two basic, +well-proven compression ideas: sliding dictionaries (LZ77/78) and +markov models (the thing used by every compression algorithm that uses +a range encoder or similar order-0 entropy coder as its last stage) +with segregation of contexts according to what the bits are used for. + + Clzip is a two stage compressor. The first stage is a Lempel-Ziv +coder, which reduces redundancy by translating chunks of data to their +corresponding distance-length pairs. The second stage is a range encoder +that uses a different probability model for each type of data; +distances, lengths, literal bytes, etc. + + The match finder, part of the LZ coder, is the most important piece +of the LZMA algorithm, as it is in many Lempel-Ziv based algorithms. +Most of clzip's execution time is spent in the match finder, and it has +the greatest influence on the compression ratio. + + Here is how it works, step by step: + + 1) The member header is written to the output stream. + + 2) The first byte is coded literally, because there are no previous +bytes to which the match finder can refer to. + + 3) The main encoder advances to the next byte in the input data and +calls the match finder. + + 4) The match finder fills an array with the minimum distances before +the current byte where a match of a given length can be found. + + 5) Go back to step 3 until a sequence (formed of pairs, repeated +distances and literal bytes) of minimum price has been formed. Where the +price represents the number of output bits produced. + + 6) The range encoder encodes the sequence produced by the main +encoder and sends the produced bytes to the output stream. + + 7) Go back to step 3 until the input data is finished or until the +member or volume size limits are reached. + + 8) The range encoder is flushed. + + 9) The member trailer is written to the output stream. + + 10) If there are more data to compress, go back to step 1. + + +File: clzip.info, Node: Invoking Clzip, Next: File Format, Prev: Algorithm, Up: Top + +3 Invoking Clzip +**************** + +The format for running clzip is: + + clzip [OPTIONS] [FILES] + + Clzip supports the following options: + +`--help' +`-h' + Print an informative help message describing the options and exit. + +`--version' +`-V' + Print the version number of clzip on the standard output and exit. + +`--member-size=SIZE' +`-b SIZE' + Produce a multimember file and set the member size limit to SIZE + bytes. Minimum member size limit is 100kB. Small member size may + degrade compression ratio, so use it only when needed. The default + is to produce single member files. + +`--stdout' +`-c' + Compress or decompress to standard output. Needed when reading + from a named pipe (fifo) or from a device. Use it to recover as + much of the uncompressed data as possible when decompressing a + corrupt file. + +`--decompress' +`-d' + Decompress. + +`--force' +`-f' + Force overwrite of output file. + +`--keep' +`-k' + Keep (don't delete) input files during compression or + decompression. + +`--match-length=LENGTH' +`-m LENGTH' + Set the match length limit in bytes. Valid values range from 5 to + 273. Larger values usually give better compression ratios but + longer compression times. + +`--output=FILE' +`-o FILE' + When reading from standard input and `--stdout' has not been + specified, use `FILE' as the virtual name of the uncompressed + file. This produces a file named `FILE' when decompressing, a file + named `FILE.lz' when compressing, and several files named + `FILE00001.lz', `FILE00002.lz', etc, when compressing and + splitting the output in volumes. + +`--quiet' +`-q' + Quiet operation. Suppress all messages. + +`--dictionary-size=SIZE' +`-s SIZE' + Set the dictionary size limit in bytes. Valid values range from + 4KiB to 512MiB. Clzip will use the smallest possible dictionary + size for each member without exceeding this limit. Note that + dictionary sizes are quantized. If the specified size does not + match one of the valid sizes, it will be rounded upwards. + +`--volume-size=SIZE' +`-S SIZE' + Split the compressed output into several volume files with names + `original_name00001.lz', `original_name00002.lz', etc, and set the + volume size limit to SIZE bytes. Each volume is a complete, maybe + multimember, lzip file. Minimum volume size limit is 100kB. Small + volume size may degrade compression ratio, so use it only when + needed. + +`--test' +`-t' + Check integrity of the specified file(s), but don't decompress + them. This really performs a trial decompression and throws away + the result. Use `-tvv' or `-tvvv' to see information about the + file. + +`--verbose' +`-v' + Verbose mode. Show the compression ratio for each file processed. + Further -v's increase the verbosity level. + +`-1 .. -9' + Set the compression parameters (dictionary size and match length + limit) as shown in the table below. Note that `-9' can be much + slower than `-1'. These options have no effect when decompressing. + + Level Dictionary size Match length limit + -1 1 MiB 10 bytes + -2 1.5 MiB 12 bytes + -3 2 MiB 17 bytes + -4 3 MiB 26 bytes + -5 4 MiB 44 bytes + -6 8 MiB 80 bytes + -7 16 MiB 108 bytes + -8 24 MiB 163 bytes + -9 32 MiB 273 bytes + +`--fast' +`--best' + Aliases for GNU gzip compatibility. + + + + Numbers given as arguments to options may be followed by a multiplier +and an optional `B' for "byte". + + Table of SI and binary prefixes (unit multipliers): + +Prefix Value | Prefix Value +k kilobyte (10^3 = 1000) | Ki kibibyte (2^10 = 1024) +M megabyte (10^6) | Mi mebibyte (2^20) +G gigabyte (10^9) | Gi gibibyte (2^30) +T terabyte (10^12) | Ti tebibyte (2^40) +P petabyte (10^15) | Pi pebibyte (2^50) +E exabyte (10^18) | Ei exbibyte (2^60) +Z zettabyte (10^21) | Zi zebibyte (2^70) +Y yottabyte (10^24) | Yi yobibyte (2^80) + + +File: clzip.info, Node: File Format, Next: Examples, Prev: Invoking Clzip, Up: Top + +4 File 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 file consists of a series of "members" (compressed data sets). +The members simply appear one after another in the file, 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: clzip.info, Node: Examples, Next: Problems, Prev: File Format, Up: Top + +5 A small tutorial with examples +******************************** + +WARNING! If your data is important, give the `--keep' option to clzip +and do not remove the original file until you verify the compressed +file with a command like `clzip -cd file.lz | cmp file -'. + + +Example 1: Replace a regular file with its compressed version file.lz +and show the compression ratio. + + clzip -v file + + +Example 2: Like example 1 but the created file.lz is multimember with a +member size of 1MiB. + + clzip -b 1MiB file + + +Example 3: Compress a whole floppy in /dev/fd0 and send the output to +file.lz. + + clzip -c /dev/fd0 > file.lz + + +Example 4: Create a multivolume compressed tar archive with a volume +size of 1440KiB. + + tar -c some_directory | clzip -S 1440KiB -o volume_name + + +Example 5: Extract a multivolume compressed tar archive. + + clzip -cd volume_name*.lz | tar -xf - + + +Example 6: Create a multivolume compressed backup of a big database file +with a volume size of 650MB, where each volume is a multimember file +with a member size of 32MiB. + + clzip -b 32MiB -S 650MB big_database + + +File: clzip.info, Node: Problems, Next: Concept Index, Prev: Examples, Up: Top + +6 Reporting Bugs +**************** + +There are probably bugs in clzip. 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 clzip, please send electronic mail to +. Include the version number, which you can find +by running `clzip --version'. + + +File: clzip.info, Node: Concept Index, Prev: Problems, Up: Top + +Concept Index +************* + +[index] +* Menu: + +* algorithm: Algorithm. (line 6) +* bugs: Problems. (line 6) +* examples: Examples. (line 6) +* file format: File Format. (line 6) +* getting help: Problems. (line 6) +* introduction: Introduction. (line 6) +* invoking: Invoking Clzip. (line 6) +* options: Invoking Clzip. (line 6) +* usage: Invoking Clzip. (line 6) +* version: Invoking Clzip. (line 6) + + + +Tag Table: +Node: Top226 +Node: Introduction838 +Node: Algorithm4160 +Node: Invoking Clzip6391 +Node: File Format10747 +Node: Examples12703 +Node: Problems13880 +Node: Concept Index14406 + +End Tag Table diff --git a/doc/clzip.texinfo b/doc/clzip.texinfo new file mode 100644 index 0000000..e9e6339 --- /dev/null +++ b/doc/clzip.texinfo @@ -0,0 +1,462 @@ +\input texinfo @c -*-texinfo-*- +@c %**start of header +@setfilename clzip.info +@settitle Clzip Manual +@finalout +@c %**end of header + +@set UPDATED 21 February 2010 +@set VERSION 1.0-rc2 + +@dircategory Data Compression +@direntry +* Clzip: (clzip). Data compressor based on the LZMA algorithm +@end direntry + + +@titlepage +@title Clzip +@subtitle A data compressor based on the LZMA algorithm +@subtitle for Clzip 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 Clzip (version @value{VERSION}, @value{UPDATED}). + +@menu +* Introduction:: Purpose and features of clzip +* Algorithm:: How clzip compresses the data +* Invoking Clzip:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Problems:: Reporting bugs +* Concept Index:: Index of concepts +@end menu + +@sp 1 +Copyright @copyright{} 2010 Antonio Diaz Diaz. + +This manual is free documentation: you have unlimited permission +to copy, distribute and modify it. + + +@node Introduction +@chapter Introduction +@cindex introduction + +Clzip is a lossless data compressor based on the LZMA algorithm, with +very safe integrity checking and a user interface similar to the one of +gzip or bzip2. Clzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + +Clzip replaces every file given in the command line with a compressed +version of itself, with the name "original_name.lz". Each compressed +file has the same modification date, permissions, and, when possible, +ownership as the corresponding original, so that these properties can be +correctly restored at decompression time. Clzip is able to read from some +types of non regular files if the @samp{--stdout} option is specified. + +If no file names are specified, clzip compresses (or decompresses) from +standard input to standard output. In this case, clzip will decline to +write compressed output to a terminal, as this would be entirely +incomprehensible and therefore pointless. + +Clzip will correctly decompress a file which is the concatenation of two +or more compressed files. The result is the concatenation of the +corresponding uncompressed files. Integrity testing of concatenated +compressed files is also supported. + +Clzip can produce multimember files and safely recover, with lziprecover, +the undamaged members in case of file damage. Clzip can also split the +compressed output in volumes of a given size, even when reading from +standard input. This allows the direct creation of multivolume +compressed tar archives. + +The amount of memory required for compression is about 5 MiB plus 1 or 2 +times the dictionary size limit (1 if input file size is less than +dictionary size limit, else 2) plus 8 times the dictionary size really +used. For decompression is a little more than the dictionary size really +used. Clzip will automatically use the smallest possible dictionary size +without exceeding the given limit. It is important to appreciate that +the decompression memory requirement is affected at compression time by +the choice of dictionary size limit. + +When decompressing, clzip attempts to guess the name for the decompressed +file from that of the compressed file as follows: + +@multitable {anyothername} {becomes} {anyothername.out} +@item filename.lz @tab becomes @tab filename +@item filename.tlz @tab becomes @tab filename.tar +@item anyothername @tab becomes @tab anyothername.out +@end multitable + +As a self-check for your protection, clzip stores in the member trailer +the 32-bit CRC of the original data and the size of the original data, +to make sure that the decompressed version of the data is identical to +the original. This guards against corruption of the compressed data, and +against undetected bugs in clzip (hopefully very unlikely). The chances +of data corruption going undetected are microscopic, less than one +chance in 4000 million for each member processed. Be aware, though, that +the check occurs upon decompression, so it can only tell you that +something is wrong. It can't help you recover the original uncompressed +data. + +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 clzip to panic. + + +@node Algorithm +@chapter Algorithm +@cindex algorithm + +Clzip implements a simplified version of the LZMA (Lempel-Ziv-Markov +chain-Algorithm) algorithm. The original LZMA algorithm was designed by +Igor Pavlov. + +The high compression of LZMA comes from combining two basic, well-proven +compression ideas: sliding dictionaries (LZ77/78) and markov models (the +thing used by every compression algorithm that uses a range encoder or +similar order-0 entropy coder as its last stage) with segregation of +contexts according to what the bits are used for. + +Clzip is a two stage compressor. The first stage is a Lempel-Ziv coder, +which reduces redundancy by translating chunks of data to their +corresponding distance-length pairs. The second stage is a range encoder +that uses a different probability model for each type of data; +distances, lengths, literal bytes, etc. + +The match finder, part of the LZ coder, is the most important piece of +the LZMA algorithm, as it is in many Lempel-Ziv based algorithms. Most +of clzip's execution time is spent in the match finder, and it has the +greatest influence on the compression ratio. + +Here is how it works, step by step: + +1) The member header is written to the output stream. + +2) The first byte is coded literally, because there are no previous +bytes to which the match finder can refer to. + +3) The main encoder advances to the next byte in the input data and +calls the match finder. + +4) The match finder fills an array with the minimum distances before the +current byte where a match of a given length can be found. + +5) Go back to step 3 until a sequence (formed of pairs, repeated +distances and literal bytes) of minimum price has been formed. Where the +price represents the number of output bits produced. + +6) The range encoder encodes the sequence produced by the main encoder +and sends the produced bytes to the output stream. + +7) Go back to step 3 until the input data is finished or until the +member or volume size limits are reached. + +8) The range encoder is flushed. + +9) The member trailer is written to the output stream. + +10) If there are more data to compress, go back to step 1. + + +@node Invoking Clzip +@chapter Invoking Clzip +@cindex invoking +@cindex options +@cindex usage +@cindex version + +The format for running clzip is: + +@example +clzip [@var{options}] [@var{files}] +@end example + +Clzip supports the following options: + +@table @samp +@item --help +@itemx -h +Print an informative help message describing the options and exit. + +@item --version +@itemx -V +Print the version number of clzip on the standard output and exit. + +@item --member-size=@var{size} +@itemx -b @var{size} +Produce a multimember file and set the member size limit to @var{size} +bytes. Minimum member size limit is 100kB. Small member size may degrade +compression ratio, so use it only when needed. The default is to produce +single member files. + +@item --stdout +@itemx -c +Compress or decompress to standard output. Needed when reading from a +named pipe (fifo) or from a device. Use it to recover as much of the +uncompressed data as possible when decompressing a corrupt file. + +@item --decompress +@itemx -d +Decompress. + +@item --force +@itemx -f +Force overwrite of output file. + +@item --keep +@itemx -k +Keep (don't delete) input files during compression or decompression. + +@item --match-length=@var{length} +@itemx -m @var{length} +Set the match length limit in bytes. Valid values range from 5 to 273. +Larger values usually give better compression ratios but longer +compression times. + +@item --output=@var{file} +@itemx -o @var{file} +When reading from standard input and @samp{--stdout} has not been +specified, use @samp{@var{file}} as the virtual name of the uncompressed +file. This produces a file named @samp{@var{file}} when decompressing, a +file named @samp{@var{file}.lz} when compressing, and several files +named @samp{@var{file}00001.lz}, @samp{@var{file}00002.lz}, etc, when +compressing and splitting the output in volumes. + +@item --quiet +@itemx -q +Quiet operation. Suppress all messages. + +@item --dictionary-size=@var{size} +@itemx -s @var{size} +Set the dictionary size limit in bytes. Valid values range from 4KiB to +512MiB. Clzip will use the smallest possible dictionary size for each +member without exceeding this limit. Note that dictionary sizes are +quantized. If the specified size does not match one of the valid sizes, +it will be rounded upwards. + +@item --volume-size=@var{size} +@itemx -S @var{size} +Split the compressed output into several volume files with names +@samp{original_name00001.lz}, @samp{original_name00002.lz}, etc, and set +the volume size limit to @var{size} bytes. Each volume is a complete, +maybe multimember, lzip file. Minimum volume size limit is 100kB. Small +volume size may degrade compression ratio, so use it only when needed. + +@item --test +@itemx -t +Check integrity of the specified file(s), but don't decompress them. +This really performs a trial decompression and throws away the result. +Use @samp{-tvv} or @samp{-tvvv} to see information about the file. + +@item --verbose +@itemx -v +Verbose mode. Show the compression ratio for each file processed. +Further -v's increase the verbosity level. + +@item -1 .. -9 +Set the compression parameters (dictionary size and match length limit) +as shown in the table below. Note that @samp{-9} can be much slower than +@samp{-1}. These options have no effect when decompressing. + +@multitable {Level} {Dictionary size} {Match length limit} +@item Level @tab Dictionary size @tab Match length limit +@item -1 @tab 1 MiB @tab 10 bytes +@item -2 @tab 1.5 MiB @tab 12 bytes +@item -3 @tab 2 MiB @tab 17 bytes +@item -4 @tab 3 MiB @tab 26 bytes +@item -5 @tab 4 MiB @tab 44 bytes +@item -6 @tab 8 MiB @tab 80 bytes +@item -7 @tab 16 MiB @tab 108 bytes +@item -8 @tab 24 MiB @tab 163 bytes +@item -9 @tab 32 MiB @tab 273 bytes +@end multitable + +@item --fast +@itemx --best +Aliases for GNU gzip compatibility. + +@end table + +@sp 1 +Numbers given as arguments to options may be followed by a multiplier +and an optional @samp{B} for "byte". + +Table of SI and binary prefixes (unit multipliers): + +@multitable {Prefix} {kilobyte (10^3 = 1000)} {|} {Prefix} {kibibyte (2^10 = 1024)} +@item Prefix @tab Value @tab | @tab Prefix @tab Value +@item k @tab kilobyte (10^3 = 1000) @tab | @tab Ki @tab kibibyte (2^10 = 1024) +@item M @tab megabyte (10^6) @tab | @tab Mi @tab mebibyte (2^20) +@item G @tab gigabyte (10^9) @tab | @tab Gi @tab gibibyte (2^30) +@item T @tab terabyte (10^12) @tab | @tab Ti @tab tebibyte (2^40) +@item P @tab petabyte (10^15) @tab | @tab Pi @tab pebibyte (2^50) +@item E @tab exabyte (10^18) @tab | @tab Ei @tab exbibyte (2^60) +@item Z @tab zettabyte (10^21) @tab | @tab Zi @tab zebibyte (2^70) +@item Y @tab yottabyte (10^24) @tab | @tab Yi @tab yobibyte (2^80) +@end multitable + + +@node File Format +@chapter File Format +@cindex file 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 file consists of a series of "members" (compressed data sets). +The members simply appear one after another in the file, 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 + +WARNING! If your data is important, give the @samp{--keep} option to +clzip and do not remove the original file until you verify the compressed +file with a command like @samp{clzip -cd file.lz | cmp file -}. + +@sp 1 +@noindent +Example 1: Replace a regular file with its compressed version file.lz +and show the compression ratio. + +@example +clzip -v file +@end example + +@sp 1 +@noindent +Example 2: Like example 1 but the created file.lz is multimember with a +member size of 1MiB. + +@example +clzip -b 1MiB file +@end example + +@sp 1 +@noindent +Example 3: Compress a whole floppy in /dev/fd0 and send the output to +file.lz. + +@example +clzip -c /dev/fd0 > file.lz +@end example + +@sp 1 +@noindent +Example 4: Create a multivolume compressed tar archive with a volume +size of 1440KiB. + +@example +tar -c some_directory | clzip -S 1440KiB -o volume_name +@end example + +@sp 1 +@noindent +Example 5: Extract a multivolume compressed tar archive. + +@example +clzip -cd volume_name*.lz | tar -xf - +@end example + +@sp 1 +@noindent +Example 6: Create a multivolume compressed backup of a big database file +with a volume size of 650MB, where each volume is a multimember file +with a member size of 32MiB. + +@example +clzip -b 32MiB -S 650MB big_database +@end example + + +@node Problems +@chapter Reporting Bugs +@cindex bugs +@cindex getting help + +There are probably bugs in clzip. 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 clzip, please send electronic mail to +@email{lzip-bug@@nongnu.org}. Include the version number, which you can +find by running @w{@samp{clzip --version}}. + + +@node Concept Index +@unnumbered Concept Index + +@printindex cp + +@bye diff --git a/encoder.c b/encoder.c new file mode 100644 index 0000000..a46893a --- /dev/null +++ b/encoder.c @@ -0,0 +1,646 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include + +#include "clzip.h" +#include "encoder.h" + + +Dis_slots dis_slots; +Prob_prices prob_prices; + + +bool Mf_read_block( struct Matchfinder * const matchfinder ) + { + const int size = matchfinder->buffer_size - matchfinder->stream_pos; + const int rd = readblock( matchfinder->infd_, matchfinder->buffer + matchfinder->stream_pos, size ); + matchfinder->stream_pos += rd; + if( rd < size ) matchfinder->at_stream_end = true; + return ( rd == size || !errno ); + } + + +void Mf_init( struct Matchfinder * const matchfinder, + const int dict_size, const int len_limit, const int infd ) + { + matchfinder->partial_data_pos = 0; + matchfinder->pos = 0; + matchfinder->cyclic_pos = 0; + matchfinder->stream_pos = 0; + matchfinder->infd_ = infd; + matchfinder->match_len_limit_ = len_limit; + matchfinder->prev_positions = (int32_t *)malloc( mf_num_prev_positions * sizeof (int32_t) ); + if( !matchfinder->prev_positions ) + { + show_error( "not enough memory. Try a smaller dictionary size", 0, false ); + cleanup_and_fail( 1 ); + } + matchfinder->at_stream_end = false; + + const int buffer_size_limit = ( 2 * dict_size ) + mf_before_size + mf_after_size; + matchfinder->buffer_size = max( 65536, dict_size ); + matchfinder->buffer = (uint8_t *)malloc( matchfinder->buffer_size ); + if( !matchfinder->buffer ) + { + show_error( "not enough memory. Try a smaller dictionary size", 0, false ); + cleanup_and_fail( 1 ); + } + if( !Mf_read_block( matchfinder ) ) + { show_error( "read error", errno, false ); cleanup_and_fail( 1 ); } + if( !matchfinder->at_stream_end && matchfinder->buffer_size < buffer_size_limit ) + { + matchfinder->buffer_size = buffer_size_limit; + matchfinder->buffer = (uint8_t *)realloc( matchfinder->buffer, matchfinder->buffer_size * sizeof (uint8_t) ); + if( !matchfinder->buffer ) + { + show_error( "not enough memory. Try a smaller dictionary size", 0, false ); + cleanup_and_fail( 1 ); + } + if( !Mf_read_block( matchfinder ) ) + { show_error( "read error", errno, false ); cleanup_and_fail( 1 ); } + } + if( matchfinder->at_stream_end && matchfinder->stream_pos < dict_size ) + matchfinder->dictionary_size_ = max( min_dictionary_size, matchfinder->stream_pos ); + else matchfinder->dictionary_size_ = dict_size; + matchfinder->pos_limit = matchfinder->buffer_size; + if( !matchfinder->at_stream_end ) matchfinder->pos_limit -= mf_after_size; + matchfinder->prev_pos_tree = (int32_t *)malloc( 2 * matchfinder->dictionary_size_ * sizeof (int32_t) ); + if( !matchfinder->prev_pos_tree ) + { + show_error( "not enough memory. Try a smaller dictionary size", 0, false ); + cleanup_and_fail( 1 ); + } + for( int i = 0; i < mf_num_prev_positions; ++i ) + matchfinder->prev_positions[i] = -1; + } + + +bool Mf_reset( struct Matchfinder * const matchfinder ) + { + const int size = matchfinder->stream_pos - matchfinder->pos; + if( size > 0 ) memmove( matchfinder->buffer, matchfinder->buffer + matchfinder->pos, size ); + matchfinder->partial_data_pos = 0; + matchfinder->stream_pos -= matchfinder->pos; + matchfinder->pos = 0; + matchfinder->cyclic_pos = 0; + for( int i = 0; i < mf_num_prev_positions; ++i ) + matchfinder->prev_positions[i] = -1; + return ( matchfinder->at_stream_end || Mf_read_block( matchfinder ) ); + } + + +bool Mf_move_pos( struct Matchfinder * const matchfinder ) + { + if( ++matchfinder->cyclic_pos >= matchfinder->dictionary_size_ ) + matchfinder->cyclic_pos = 0; + if( ++matchfinder->pos >= matchfinder->pos_limit ) + { + if( matchfinder->pos > matchfinder->stream_pos ) + { matchfinder->pos = matchfinder->stream_pos; return false; } + if( !matchfinder->at_stream_end ) + { + const int offset = matchfinder->pos - matchfinder->dictionary_size_ - mf_before_size; + const int size = matchfinder->stream_pos - offset; + memmove( matchfinder->buffer, matchfinder->buffer + offset, size ); + matchfinder->partial_data_pos += offset; + matchfinder->pos -= offset; + matchfinder->stream_pos -= offset; + for( int i = 0; i < mf_num_prev_positions; ++i ) + if( matchfinder->prev_positions[i] >= 0 ) matchfinder->prev_positions[i] -= offset; + for( int i = 0; i < 2 * matchfinder->dictionary_size_; ++i ) + if( matchfinder->prev_pos_tree[i] >= 0 ) matchfinder->prev_pos_tree[i] -= offset; + return Mf_read_block( matchfinder ); + } + } + return true; + } + + +int Mf_longest_match_len( struct Matchfinder * const matchfinder, + int * const distances ) + { + int len_limit = matchfinder->match_len_limit_; + if( len_limit > Mf_available_bytes( matchfinder ) ) + { + len_limit = Mf_available_bytes( matchfinder ); + if( len_limit < 4 ) return 0; + } + + int maxlen = min_match_len - 1; + const int min_pos = (matchfinder->pos >= matchfinder->dictionary_size_) ? + (matchfinder->pos - matchfinder->dictionary_size_ + 1) : 0; + const uint8_t * const data = matchfinder->buffer + matchfinder->pos; + const int key2 = mf_num_prev_positions4 + mf_num_prev_positions3 + + ( ( (int)data[0] << 8 ) | data[1] ); + const int tmp = crc32[data[0]] ^ data[1] ^ ( (int)data[2] << 8 ); + const int key3 = mf_num_prev_positions4 + ( tmp & ( mf_num_prev_positions3 - 1 ) ); + const int key4 = ( tmp ^ ( crc32[data[3]] << 5 ) ) & + ( mf_num_prev_positions4 - 1 ); + + if( distances ) + { + int np = matchfinder->prev_positions[key2]; + if( np >= min_pos ) + { distances[2] = matchfinder->pos - np - 1; maxlen = 2; } + else distances[2] = 0x7FFFFFFF; + np = matchfinder->prev_positions[key3]; + if( np >= min_pos && matchfinder->buffer[np] == data[0] ) + { distances[3] = matchfinder->pos - np - 1; maxlen = 3; } + else distances[3] = 0x7FFFFFFF; + distances[4] = 0x7FFFFFFF; + } + + matchfinder->prev_positions[key2] = matchfinder->pos; + matchfinder->prev_positions[key3] = matchfinder->pos; + int newpos = matchfinder->prev_positions[key4]; + matchfinder->prev_positions[key4] = matchfinder->pos; + + int idx0 = matchfinder->cyclic_pos << 1; + int idx1 = idx0 + 1; + int len = 0, len0 = 0, len1 = 0; + + for( int count = 16 + ( matchfinder->match_len_limit_ / 2 ); ; ) + { + if( newpos < min_pos || --count < 0 ) + { matchfinder->prev_pos_tree[idx0] = matchfinder->prev_pos_tree[idx1] = -1; break; } + const uint8_t * const newdata = matchfinder->buffer + newpos; + while( len < len_limit && newdata[len] == data[len] ) ++len; + + const int delta = matchfinder->pos - newpos; + if( distances ) while( maxlen < len ) distances[++maxlen] = delta - 1; + + const int newidx = ( matchfinder->cyclic_pos - delta + + ( ( matchfinder->cyclic_pos >= delta ) ? 0 : matchfinder->dictionary_size_ ) ) << 1; + + if( len < len_limit ) + { + if( newdata[len] < data[len] ) + { + matchfinder->prev_pos_tree[idx0] = newpos; + idx0 = newidx + 1; + newpos = matchfinder->prev_pos_tree[idx0]; + len0 = len; if( len1 < len ) len = len1; + } + else + { + matchfinder->prev_pos_tree[idx1] = newpos; + idx1 = newidx; + newpos = matchfinder->prev_pos_tree[idx1]; + len1 = len; if( len0 < len ) len = len0; + } + } + else + { + matchfinder->prev_pos_tree[idx0] = matchfinder->prev_pos_tree[newidx]; + matchfinder->prev_pos_tree[idx1] = matchfinder->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 Lee_encode( struct Len_encoder * const len_encoder, + struct Range_encoder * const range_encoder, + int symbol, const int pos_state ) + { + symbol -= min_match_len; + if( symbol < len_low_symbols ) + { + Re_encode_bit( range_encoder, &len_encoder->choice1, 0 ); + Re_encode_tree( range_encoder, len_encoder->bm_low[pos_state], symbol, len_low_bits ); + } + else + { + Re_encode_bit( range_encoder, &len_encoder->choice1, 1 ); + if( symbol < len_low_symbols + len_mid_symbols ) + { + Re_encode_bit( range_encoder, &len_encoder->choice2, 0 ); + Re_encode_tree( range_encoder, len_encoder->bm_mid[pos_state], symbol - len_low_symbols, len_mid_bits ); + } + else + { + Re_encode_bit( range_encoder, &len_encoder->choice2, 1 ); + Re_encode_tree( range_encoder, len_encoder->bm_high, symbol - len_low_symbols - len_mid_symbols, len_high_bits ); + } + } + if( --len_encoder->counters[pos_state] <= 0 ) + Lee_update_prices( len_encoder, pos_state ); + } + + +void LZe_fill_align_prices( struct LZ_encoder * const encoder ) + { + for( int i = 0; i < dis_align_size; ++i ) + encoder->align_prices[i] = price_symbol_reversed( encoder->bm_align, i, dis_align_bits ); + encoder->align_price_count = dis_align_size; + } + + +void LZe_fill_distance_prices( struct LZ_encoder * const encoder ) + { + for( int dis_state = 0; dis_state < max_dis_states; ++dis_state ) + { + int * const dsp = encoder->dis_slot_prices[dis_state]; + const Bit_model * const bmds = encoder->bm_dis_slot[dis_state]; + int slot = 0; + for( ; slot < end_dis_model && slot < encoder->num_dis_slots; ++slot ) + dsp[slot] = price_symbol( bmds, slot, dis_slot_bits ); + for( ; slot < encoder->num_dis_slots; ++slot ) + dsp[slot] = price_symbol( bmds, slot, dis_slot_bits ) + + (((( slot >> 1 ) - 1 ) - dis_align_bits ) << price_shift ); + + int * const dp = encoder->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 = get_slot( 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( encoder->bm_dis + base - dis_slot, dis - base, direct_bits ); + } + } + } + + +// Return value: ( dis == -1 ) && ( len == 1 ) means literal +int LZe_best_pair_sequence( struct LZ_encoder * const encoder, const int reps[num_rep_distances], + const State state ) + { + int main_len; + if( encoder->longest_match_found > 0 ) // from previous call + { + main_len = encoder->longest_match_found; + encoder->longest_match_found = 0; + } + else main_len = LZe_read_match_distances( encoder ); + + int replens[num_rep_distances]; + int rep_index = 0; + for( int i = 0; i < num_rep_distances; ++i ) + { + replens[i] = Mf_true_match_len( encoder->matchfinder, 0, reps[i] + 1, max_match_len ); + if( replens[i] > replens[rep_index] ) rep_index = i; + } + if( replens[rep_index] >= Mf_match_len_limit( encoder->matchfinder ) ) + { + encoder->trials[0].dis = rep_index; + encoder->trials[0].price = replens[rep_index]; + if( !LZe_move_pos( encoder, replens[rep_index], true ) ) return 0; + return replens[rep_index]; + } + + if( main_len >= Mf_match_len_limit( encoder->matchfinder ) ) + { + encoder->trials[0].dis = encoder->match_distances[Mf_match_len_limit( encoder->matchfinder )] + + num_rep_distances; + encoder->trials[0].price = main_len; + if( !LZe_move_pos( encoder, main_len, true ) ) return 0; + return main_len; + } + + encoder->trials[0].state = state; + for( int i = 0; i < num_rep_distances; ++i ) encoder->trials[0].reps[i] = reps[i]; + + const uint8_t prev_byte = Mf_peek( encoder->matchfinder, -1 ); + const uint8_t cur_byte = Mf_peek( encoder->matchfinder, 0 ); + const uint8_t match_byte = Mf_peek( encoder->matchfinder, -reps[0]-1 ); + unsigned int position = Mf_data_position( encoder->matchfinder ); + const int pos_state = position & pos_state_mask; + + encoder->trials[1].dis = -1; + encoder->trials[1].prev_index = 0; + encoder->trials[1].price = price0( encoder->bm_match[state][pos_state] ); + if( St_is_char( state ) ) + encoder->trials[1].price += Lie_price_symbol( &encoder->literal_encoder, prev_byte, cur_byte ); + else + encoder->trials[1].price += Lie_price_matched( &encoder->literal_encoder, prev_byte, cur_byte, match_byte ); + + const int match_price = price1( encoder->bm_match[state][pos_state] ); + const int rep_match_price = match_price + price1( encoder->bm_rep[state] ); + + if( match_byte == cur_byte ) + Tr_update( &encoder->trials[1], 0, 0, rep_match_price + LZe_price_rep_len1( encoder, state, pos_state ) ); + + if( main_len < min_match_len ) + { + encoder->trials[0].dis = encoder->trials[1].dis; + encoder->trials[0].price = 1; + if( !Mf_move_pos( encoder->matchfinder ) ) return 0; + return 1; + } + + { + const int normal_match_price = match_price + price0( encoder->bm_rep[state] ); + int len = min_match_len; + if( main_len <= replens[rep_index] ) + { + main_len = replens[rep_index]; + for( ; len <= main_len; ++len ) + encoder->trials[len].price = lze_infinite_price; + } + else for( ; len <= main_len; ++len ) + { + encoder->trials[len].dis = encoder->match_distances[len] + num_rep_distances; + encoder->trials[len].prev_index = 0; + encoder->trials[len].price = normal_match_price + + LZe_price_pair( encoder, encoder->match_distances[len], len, pos_state ); + } + } + + for( int rep = 0; rep < num_rep_distances; ++rep ) + { + const int price = rep_match_price + + LZe_price_rep( encoder, rep, state, pos_state ); + for( int len = min_match_len; len <= replens[rep]; ++len ) + Tr_update( &encoder->trials[len], rep, 0, price + + Lee_price( &encoder->rep_match_len_encoder, len, pos_state ) ); + } + + int cur = 0; + int num_trials = main_len; + if( !Mf_move_pos( encoder->matchfinder ) ) return 0; + + while( true ) + { + if( ++cur >= num_trials ) + { + LZe_backward( encoder, cur ); + return cur; + } + const int newlen = LZe_read_match_distances( encoder ); + if( newlen >= Mf_match_len_limit( encoder->matchfinder ) ) + { + encoder->longest_match_found = newlen; + LZe_backward( encoder, cur ); + return cur; + } + + struct Trial * const cur_trial = &encoder->trials[cur]; + const int prev_index = cur_trial->prev_index; + + cur_trial->state = encoder->trials[prev_index].state; + + for( int i = 0; i < num_rep_distances; ++i ) + cur_trial->reps[i] = encoder->trials[prev_index].reps[i]; + if( prev_index == cur - 1 ) + { + if( cur_trial->dis == 0 ) St_set_short_rep( &cur_trial->state ); + else St_set_char( &cur_trial->state ); + } + else + { + if( cur_trial->dis < num_rep_distances ) St_set_rep( &cur_trial->state ); + else St_set_match( &cur_trial->state ); + LZe_mtf_reps( cur_trial->dis, cur_trial->reps ); + } + + const uint8_t prev_byte = Mf_peek( encoder->matchfinder, -1 ); + const uint8_t cur_byte = Mf_peek( encoder->matchfinder, 0 ); + const uint8_t match_byte = Mf_peek( encoder->matchfinder, -cur_trial->reps[0]-1 ); + const int pos_state = ++position & pos_state_mask; + int next_price = cur_trial->price + price0( encoder->bm_match[cur_trial->state][pos_state] ); + if( St_is_char( cur_trial->state ) ) + next_price += Lie_price_symbol( &encoder->literal_encoder, prev_byte, cur_byte ); + else + next_price += Lie_price_matched( &encoder->literal_encoder, prev_byte, cur_byte, match_byte ); + if( !Mf_move_pos( encoder->matchfinder ) ) return 0; + + struct Trial * const next_trial = &encoder->trials[cur+1]; + + Tr_update( next_trial, -1, cur, next_price ); + + const int match_price = cur_trial->price + price1( encoder->bm_match[cur_trial->state][pos_state] ); + const int rep_match_price = match_price + price1( encoder->bm_rep[cur_trial->state] ); + + if( match_byte == cur_byte && next_trial->dis != 0 ) + Tr_update( next_trial, 0, cur, rep_match_price + + LZe_price_rep_len1( encoder, cur_trial->state, pos_state ) ); + + const int len_limit = min( min( max_num_trials - 1 - cur, + Mf_available_bytes( encoder->matchfinder ) ), + Mf_match_len_limit( encoder->matchfinder ) ); + 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 = Mf_ptr_to_current_pos( encoder->matchfinder ) - 1; + while( len < len_limit && data[len] == data[len-dis] ) ++len; + if( len >= min_match_len ) + { + const int price = rep_match_price + + LZe_price_rep( encoder, rep, cur_trial->state, pos_state ); + while( num_trials < cur + len ) + encoder->trials[++num_trials].price = lze_infinite_price; + for( ; len >= min_match_len; --len ) + Tr_update( &encoder->trials[cur+len], rep, cur, price + + Lee_price( &encoder->rep_match_len_encoder, len, pos_state ) ); + } + } + + if( newlen <= len_limit && + ( newlen > min_match_len || + ( newlen == min_match_len && + encoder->match_distances[newlen] < modeled_distances ) ) ) + { + const int normal_match_price = match_price + + price0( encoder->bm_rep[cur_trial->state] ); + while( num_trials < cur + newlen ) + encoder->trials[++num_trials].price = lze_infinite_price; + + for( int len = min_match_len; len <= newlen; ++len ) + Tr_update( &encoder->trials[cur+len], encoder->match_distances[len] + num_rep_distances, + cur, normal_match_price + + LZe_price_pair( encoder, encoder->match_distances[len], len, pos_state ) ); + } + } + } + + + // End Of Stream mark => (dis == 0xFFFFFFFF, len == min_match_len) +void LZe_full_flush( struct LZ_encoder * const encoder, const State state ) + { + const int pos_state = ( Mf_data_position( encoder->matchfinder ) ) & pos_state_mask; + Re_encode_bit( &encoder->range_encoder, &encoder->bm_match[state][pos_state], 1 ); + Re_encode_bit( &encoder->range_encoder, &encoder->bm_rep[state], 0 ); + LZe_encode_pair( encoder, 0xFFFFFFFF, min_match_len, pos_state ); + Re_flush( &encoder->range_encoder ); + File_trailer trailer; + Ft_set_data_crc( trailer, LZe_crc( encoder ) ); + Ft_set_data_size( trailer, Mf_data_position( encoder->matchfinder ) ); + Ft_set_member_size( trailer, LZe_member_position( encoder ) + sizeof (File_trailer) ); + for( unsigned int i = 0; i < sizeof (File_trailer); ++i ) + Re_put_byte( &encoder->range_encoder, trailer[i] ); + Re_flush_data( &encoder->range_encoder ); + } + + +void LZe_init( struct LZ_encoder * const encoder, struct Matchfinder * const mf, + const File_header header, const int outfd ) + { + encoder->longest_match_found = 0; + encoder->crc_ = 0xFFFFFFFF; + + for( int i = 0; i < St_states; ++i ) + { + for( int j = 0; j < pos_states; ++j ) + { + Bm_init( &encoder->bm_match[i][j] ); + Bm_init( &encoder->bm_len[i][j] ); + } + Bm_init( &encoder->bm_rep[i] ); + Bm_init( &encoder->bm_rep0[i] ); + Bm_init( &encoder->bm_rep1[i] ); + Bm_init( &encoder->bm_rep2[i] ); + } + for( int i = 0; i < max_dis_states; ++i ) + for( int j = 0; j < 1<bm_dis_slot[i][j] ); + for( int i = 0; i < modeled_distances-end_dis_model; ++i ) + Bm_init( &encoder->bm_dis[i] ); + for( int i = 0; i < dis_align_size; ++i ) + Bm_init( &encoder->bm_align[i] ); + + encoder->matchfinder = mf; + Re_init( &encoder->range_encoder, outfd ); + Lee_init( &encoder->len_encoder, Mf_match_len_limit( encoder->matchfinder ) ), + Lee_init( &encoder->rep_match_len_encoder, Mf_match_len_limit( encoder->matchfinder ) ), + Lie_init( &encoder->literal_encoder ); + encoder->num_dis_slots = 2 * Fh_real_bits( Mf_dictionary_size( encoder->matchfinder ) - 1 ); + + LZe_fill_align_prices( encoder ); + + for( unsigned int i = 0; i < sizeof (File_header); ++i ) + Re_put_byte( &encoder->range_encoder, header[i] ); + } + + +bool LZe_encode_member( struct LZ_encoder * const encoder, const long long member_size ) + { + if( LZe_member_position( encoder ) != sizeof (File_header) ) + return false; // can be called only once + const long long member_size_limit = + member_size - sizeof (File_trailer) - lze_max_marker_size; + int fill_counter = 0; + int rep_distances[num_rep_distances]; + State state = 0; + for( int i = 0; i < num_rep_distances; ++i ) rep_distances[i] = 0; + + // encode first byte + if( Mf_data_position( encoder->matchfinder ) == 0 && + !Mf_finished( encoder->matchfinder ) ) + { + Re_encode_bit( &encoder->range_encoder, &encoder->bm_match[state][0], 0 ); + const uint8_t prev_byte = 0; + const uint8_t cur_byte = Mf_peek( encoder->matchfinder, 0 ); + Lie_encode( &encoder->literal_encoder, &encoder->range_encoder, prev_byte, cur_byte ); + CRC32_update_byte( &encoder->crc_, cur_byte ); + if( !LZe_move_pos( encoder, 1, false ) ) return false; + } + + while( true ) + { + if( Mf_finished( encoder->matchfinder ) ) + { LZe_full_flush( encoder, state ); return true; } + if( fill_counter <= 0 ) + { LZe_fill_distance_prices( encoder ); fill_counter = 512; } + + int ahead = LZe_best_pair_sequence( encoder, rep_distances, state ); + if( ahead <= 0 ) return false; + fill_counter -= ahead; + + for( int i = 0; ; ) + { + const int pos_state = ( Mf_data_position( encoder->matchfinder ) - ahead ) & pos_state_mask; + int dis = encoder->trials[i].dis; + const int len = encoder->trials[i].price; + + bool bit = ( dis < 0 && len == 1 ); + Re_encode_bit( &encoder->range_encoder, &encoder->bm_match[state][pos_state], !bit ); + if( bit ) + { + const uint8_t prev_byte = Mf_peek( encoder->matchfinder, -ahead-1 ); + const uint8_t cur_byte = Mf_peek( encoder->matchfinder, -ahead ); + if( St_is_char( state ) ) + Lie_encode( &encoder->literal_encoder, &encoder->range_encoder, prev_byte, cur_byte ); + else + { + const uint8_t match_byte = Mf_peek( encoder->matchfinder, -ahead-rep_distances[0]-1 ); + Lie_encode_matched( &encoder->literal_encoder, &encoder->range_encoder, prev_byte, match_byte, cur_byte ); + } + St_set_char( &state ); + } + else + { + LZe_mtf_reps( dis, rep_distances ); + bit = ( dis < num_rep_distances ); + Re_encode_bit( &encoder->range_encoder, &encoder->bm_rep[state], bit ); + if( bit ) + { + bit = ( dis == 0 ); + Re_encode_bit( &encoder->range_encoder, &encoder->bm_rep0[state], !bit ); + if( bit ) + Re_encode_bit( &encoder->range_encoder, &encoder->bm_len[state][pos_state], len > 1 ); + else + { + Re_encode_bit( &encoder->range_encoder, &encoder->bm_rep1[state], dis > 1 ); + if( dis > 1 ) + Re_encode_bit( &encoder->range_encoder, &encoder->bm_rep2[state], dis > 2 ); + } + if( len == 1 ) St_set_short_rep( &state ); + else + { + Lee_encode( &encoder->rep_match_len_encoder, &encoder->range_encoder, len, pos_state ); + St_set_rep( &state ); + } + } + else + { + LZe_encode_pair( encoder, dis - num_rep_distances, len, pos_state ); + St_set_match( &state ); + } + } + for( int j = 0; j < len; ++j ) + CRC32_update_byte( &encoder->crc_, Mf_peek( encoder->matchfinder, j-ahead ) ); + ahead -= len; i += len; + if( LZe_member_position( encoder ) >= member_size_limit ) + { + if( !Mf_dec_pos( encoder->matchfinder, ahead ) ) return false; + LZe_full_flush( encoder, state ); + return true; + } + if( ahead <= 0 ) break; + } + } + } diff --git a/encoder.h b/encoder.h new file mode 100644 index 0000000..fe74f7c --- /dev/null +++ b/encoder.h @@ -0,0 +1,650 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ + +enum { max_num_trials = 1 << 12, + price_shift = 6 }; + +typedef unsigned char Dis_slots[1<<12]; + +extern Dis_slots dis_slots; + +static inline void Dis_slots_init() + { + for( int slot = 0; slot < 4; ++slot ) dis_slots[slot] = slot; + for( int i = 4, size = 2, slot = 4; slot < 24; slot += 2 ) + { + memset( &dis_slots[i], slot, size ); + memset( &dis_slots[i+size], slot + 1, size ); + size <<= 1; + i += size; + } + } + +static inline int get_slot( const uint32_t dis ) + { + if( dis < (1 << 12) ) return dis_slots[dis]; + if( dis < (1 << 23) ) return dis_slots[dis>>11] + 22; + return dis_slots[dis>>22] + 44; + } + + +typedef int Prob_prices[bit_model_total >> 2]; + +extern Prob_prices prob_prices; + +static inline void Prob_prices_init() + { + 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 ) + prob_prices[j] = (i << price_shift) + + ( ((end - j) << price_shift) >> (num_bits - i - 1) ); + } + } + +static inline int get_price( const int probability ) + { return prob_prices[probability >> 2]; } + + +static inline int price0( const Bit_model probability ) + { return get_price( probability ); } + +static inline int price1( const Bit_model probability ) + { return get_price( bit_model_total-probability ); } + +static inline int price_bit( const Bit_model bm, const int bit ) + { if( bit ) return price1( bm ); else return price0( bm ); } + + +static inline int price_symbol( const Bit_model bm[], int symbol, const int num_bits ) + { + symbol |= ( 1 << num_bits ); + int price = 0; + while( symbol > 1 ) + { + const int bit = symbol & 1; + symbol >>= 1; + price += price_bit( bm[symbol], bit ); + } + return price; + } + + +static inline int price_symbol_reversed( const Bit_model bm[], int symbol, + const int num_bits ) + { + 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], bit ); + model = ( model << 1 ) | bit; + } + return price; + } + + +static inline int price_matched( const Bit_model bm[], const int symbol, + const int match_byte ) + { + 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+0x100], bit ); + model = ( model << 1 ) | bit; + if( match_bit != bit ) + { + while( --i >= 0 ) + { + const int bit = ( symbol >> i ) & 1; + price += price_bit( bm[model], bit ); + model = ( model << 1 ) | bit; + } + break; + } + } + return price; + } + + +enum { // bytes to keep in buffer before dictionary + mf_before_size = max_num_trials + 1, + // bytes to keep in buffer after pos + mf_after_size = max_match_len, + mf_num_prev_positions4 = 1 << 20, + mf_num_prev_positions3 = 1 << 18, + mf_num_prev_positions2 = 1 << 16, + mf_num_prev_positions = mf_num_prev_positions4 + mf_num_prev_positions3 + + mf_num_prev_positions2 }; + +struct Matchfinder + { + long long partial_data_pos; + int dictionary_size_; // bytes to keep in buffer before pos + int buffer_size; + uint8_t * buffer; + int pos; + int cyclic_pos; + int stream_pos; // first byte not yet read from file + int pos_limit; // when reached, a new block must be read + int infd_; // input file descriptor + int match_len_limit_; + int32_t * prev_positions; // last seen position of key + int32_t * prev_pos_tree; + bool at_stream_end; // stream_pos shows real end of file + }; + +bool Mf_read_block( struct Matchfinder * const matchfinder ); + +void Mf_init( struct Matchfinder * const matchfinder, + const int dict_size, const int len_limit, const int infd ); + +static inline void Mf_free( struct Matchfinder * const matchfinder ) + { + free( matchfinder->prev_pos_tree ); matchfinder->prev_pos_tree = 0; + free( matchfinder->prev_positions ); matchfinder->prev_positions = 0; + free( matchfinder->buffer ); matchfinder->buffer = 0; + } + +static inline uint8_t Mf_peek( struct Matchfinder * const matchfinder, const int i ) + { return matchfinder->buffer[matchfinder->pos+i]; } +static inline int Mf_available_bytes( struct Matchfinder * const matchfinder ) + { return matchfinder->stream_pos - matchfinder->pos; } +static inline long long Mf_data_position( struct Matchfinder * const matchfinder ) + { return matchfinder->partial_data_pos + matchfinder->pos; } +static inline int Mf_dictionary_size( struct Matchfinder * const matchfinder ) + { return matchfinder->dictionary_size_; } +static inline bool Mf_finished( struct Matchfinder * const matchfinder ) + { return matchfinder->at_stream_end && matchfinder->pos >= matchfinder->stream_pos; } +static inline int Mf_match_len_limit( struct Matchfinder * const matchfinder ) + { return matchfinder->match_len_limit_; } +static inline const uint8_t * Mf_ptr_to_current_pos( struct Matchfinder * const matchfinder ) + { return matchfinder->buffer + matchfinder->pos; } + +static inline bool Mf_dec_pos( struct Matchfinder * const matchfinder, + const int ahead ) + { + if( ahead < 0 || matchfinder->pos < ahead ) return false; + matchfinder->pos -= ahead; + matchfinder->cyclic_pos -= ahead; + if( matchfinder->cyclic_pos < 0 ) + matchfinder->cyclic_pos += matchfinder->dictionary_size_; + return true; + } + +static inline int Mf_true_match_len( struct Matchfinder * const matchfinder, + const int index, const int distance, int len_limit ) + { + if( index + len_limit > Mf_available_bytes( matchfinder ) ) + len_limit = Mf_available_bytes( matchfinder ) - index; + const uint8_t * const data = matchfinder->buffer + matchfinder->pos + index - distance; + int i = 0; + while( i < len_limit && data[i] == data[i+distance] ) ++i; + return i; + } + +bool Mf_reset( struct Matchfinder * const matchfinder ); +bool Mf_move_pos( struct Matchfinder * const matchfinder ); +int Mf_longest_match_len( struct Matchfinder * const matchfinder, + int * const distances ); + + +enum { re_buffer_size = 65536 }; + +struct Range_encoder + { + uint64_t low; + long long partial_member_pos; + uint8_t * buffer; + int pos; + uint32_t range; + int ff_count; + int outfd_; // output file descriptor + uint8_t cache; + }; + +static inline void Re_flush_data( struct Range_encoder * const range_encoder ) + { + if( range_encoder->pos > 0 ) + { + if( range_encoder->outfd_ >= 0 ) + { + const int wr = writeblock( range_encoder->outfd_, range_encoder->buffer, range_encoder->pos ); + if( wr != range_encoder->pos ) + { show_error( "write error", errno, false ); cleanup_and_fail( 1 ); } + } + range_encoder->partial_member_pos += range_encoder->pos; + range_encoder->pos = 0; + } + } + +static inline void Re_put_byte( struct Range_encoder * const range_encoder, + const uint8_t b ) + { + range_encoder->buffer[range_encoder->pos] = b; + if( ++range_encoder->pos >= re_buffer_size ) Re_flush_data( range_encoder ); + } + +static inline void Re_shift_low( struct Range_encoder * const range_encoder ) + { + const uint32_t carry = range_encoder->low >> 32; + if( range_encoder->low < 0xFF000000LL || carry == 1 ) + { + Re_put_byte( range_encoder, range_encoder->cache + carry ); + for( ; range_encoder->ff_count > 0; --range_encoder->ff_count ) + Re_put_byte( range_encoder, 0xFF + carry ); + range_encoder->cache = range_encoder->low >> 24; + } + else ++range_encoder->ff_count; + range_encoder->low = ( range_encoder->low & 0x00FFFFFFLL ) << 8; + } + +static inline void Re_init( struct Range_encoder * const range_encoder, + const int outfd ) + { + range_encoder->low = 0; + range_encoder->partial_member_pos = 0; + range_encoder->buffer = (uint8_t *)malloc( re_buffer_size ); + if( !range_encoder->buffer ) + { + show_error( "not enough memory. Try a smaller dictionary size", 0, false ); + cleanup_and_fail( 1 ); + } + range_encoder->pos = 0; + range_encoder->range = 0xFFFFFFFF; + range_encoder->ff_count = 0; + range_encoder->outfd_ = outfd; + range_encoder->cache = 0; + } + +static inline void Re_free( struct Range_encoder * const range_encoder ) + { free( range_encoder->buffer ); range_encoder->buffer = 0; } + +static inline void Re_flush( struct Range_encoder * const range_encoder ) + { for( int i = 0; i < 5; ++i ) Re_shift_low( range_encoder ); } + +static inline long long Re_member_position( struct Range_encoder * const range_encoder ) + { return range_encoder->partial_member_pos + range_encoder->pos + range_encoder->ff_count; } + +static inline void Re_encode( struct Range_encoder * const range_encoder, + const int symbol, const int num_bits ) + { + for( int i = num_bits - 1; i >= 0; --i ) + { + range_encoder->range >>= 1; + if( (symbol >> i) & 1 ) range_encoder->low += range_encoder->range; + if( range_encoder->range <= 0x00FFFFFF ) + { range_encoder->range <<= 8; Re_shift_low( range_encoder ); } + } + } + +static inline void Re_encode_bit( struct Range_encoder * const range_encoder, + Bit_model * const probability, const int bit ) + { + const uint32_t bound = ( range_encoder->range >> bit_model_total_bits ) * *probability; + if( !bit ) + { + range_encoder->range = bound; + *probability += (bit_model_total - *probability) >> bit_model_move_bits; + } + else + { + range_encoder->low += bound; + range_encoder->range -= bound; + *probability -= *probability >> bit_model_move_bits; + } + if( range_encoder->range <= 0x00FFFFFF ) + { range_encoder->range <<= 8; Re_shift_low( range_encoder ); } + } + +static inline void Re_encode_tree( struct Range_encoder * const range_encoder, + 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 ); + Re_encode_bit( range_encoder, &bm[model], bit ); + model <<= 1; + if( bit ) model |= 1; + } + } + +static inline void Re_encode_tree_reversed( struct Range_encoder * const range_encoder, + 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; + Re_encode_bit( range_encoder, &bm[model], bit ); + model = ( model << 1 ) | bit; + symbol >>= 1; + } + } + +static inline void Re_encode_matched( struct Range_encoder * const range_encoder, + 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; + Re_encode_bit( range_encoder, &bm[(match_bit<<8)+model+0x100], bit ); + model = ( model << 1 ) | bit; + if( match_bit != bit ) + { + while( --i >= 0 ) + { + const int bit = ( symbol >> i ) & 1; + Re_encode_bit( range_encoder, &bm[model], bit ); + model = ( model << 1 ) | bit; + } + break; + } + } + } + + +struct 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]; + int len_symbols; + int counters[pos_states]; + }; + +static inline void Lee_update_prices( struct Len_encoder * const len_encoder, + const int pos_state ) + { + int * const pps = len_encoder->prices[pos_state]; + int price = price0( len_encoder->choice1 ); + int len = 0; + for( ; len < len_low_symbols && len < len_encoder->len_symbols; ++len ) + pps[len] = price + + price_symbol( len_encoder->bm_low[pos_state], len, len_low_bits ); + price = price1( len_encoder->choice1 ); + for( ; len < len_low_symbols + len_mid_symbols && len < len_encoder->len_symbols; ++len ) + pps[len] = price + price0( len_encoder->choice2 ) + + price_symbol( len_encoder->bm_mid[pos_state], len - len_low_symbols, len_mid_bits ); + for( ; len < len_encoder->len_symbols; ++len ) + pps[len] = price + price1( len_encoder->choice2 ) + + price_symbol( len_encoder->bm_high, len - len_low_symbols - len_mid_symbols, len_high_bits ); + len_encoder->counters[pos_state] = len_encoder->len_symbols; + } + +static inline void Lee_init( struct Len_encoder * const len_encoder, + const int len_limit ) + { + Bm_init( &len_encoder->choice1 ); + Bm_init( &len_encoder->choice2 ); + for( int i = 0; i < pos_states; ++i ) + for( int j = 0; j < len_low_symbols; ++j ) + Bm_init( &len_encoder->bm_low[i][j] ); + for( int i = 0; i < pos_states; ++i ) + for( int j = 0; j < len_mid_symbols; ++j ) + Bm_init( &len_encoder->bm_mid[i][j] ); + for( int i = 0; i < len_high_symbols; ++i ) + Bm_init( &len_encoder->bm_high[i] ); + len_encoder->len_symbols = len_limit + 1 - min_match_len; + for( int i = 0; i < pos_states; ++i ) Lee_update_prices( len_encoder, i ); + } + +void Lee_encode( struct Len_encoder * const len_encoder, + struct Range_encoder * const range_encoder, int symbol, + const int pos_state ); + +static inline int Lee_price( struct Len_encoder * const len_encoder, + const int symbol, const int pos_state ) + { return len_encoder->prices[pos_state][symbol - min_match_len]; } + + +struct Literal_encoder + { + Bit_model bm_literal[1<bm_literal[i][j] ); + } + +static inline int Lie_state( const int prev_byte ) + { return ( prev_byte >> ( 8 - literal_context_bits ) ); } + +static inline void Lie_encode( struct Literal_encoder * const literal_encoder, + struct Range_encoder * const range_encoder, + uint8_t prev_byte, uint8_t symbol ) + { Re_encode_tree( range_encoder, literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, 8 ); } + +static inline void Lie_encode_matched( struct Literal_encoder * const literal_encoder, + struct Range_encoder * const range_encoder, + uint8_t prev_byte, uint8_t match_byte, uint8_t symbol ) + { Re_encode_matched( range_encoder, literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, match_byte ); } + +static inline int Lie_price_matched( struct Literal_encoder * const literal_encoder, + uint8_t prev_byte, uint8_t symbol, uint8_t match_byte ) + { return price_matched( literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, match_byte ); } + +static inline int Lie_price_symbol( struct Literal_encoder * const literal_encoder, + uint8_t prev_byte, uint8_t symbol ) + { return price_symbol( literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, 8 ); } + + +enum { lze_dis_align_mask = dis_align_size - 1, + lze_infinite_price = 0x0FFFFFFF, + lze_max_marker_size = 16, + num_rep_distances = 4 }; // must be 4 + +struct Trial + { + State state; + int dis; + int prev_index; // index of prev trial in trials[] + int price; // dual use var; cumulative price, match length + int reps[num_rep_distances]; + }; + +static inline void Tr_update( struct Trial * const trial, + const int d, const int p_i, const int pr ) + { + if( pr < trial->price ) + { trial->dis = d; trial->prev_index = p_i; trial->price = pr; } + } + + +struct LZ_encoder + { + int longest_match_found; + uint32_t crc_; + + Bit_model bm_match[St_states][pos_states]; + Bit_model bm_rep[St_states]; + Bit_model bm_rep0[St_states]; + Bit_model bm_rep1[St_states]; + Bit_model bm_rep2[St_states]; + Bit_model bm_len[St_states][pos_states]; + Bit_model bm_dis_slot[max_dis_states][1<crc_ ^ 0xFFFFFFFF; } + +static inline void LZe_mtf_reps( const int dis, int reps[num_rep_distances] ) + { + 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; + } + } + +static inline int LZe_price_rep_len1( struct LZ_encoder * const encoder, + const State state, const int pos_state ) + { + return price0( encoder->bm_rep0[state] ) + price0( encoder->bm_len[state][pos_state] ); + } + +static inline int LZe_price_rep( struct LZ_encoder * const encoder, const int rep, + const State state, const int pos_state ) + { + if( rep == 0 ) return price0( encoder->bm_rep0[state] ) + + price1( encoder->bm_len[state][pos_state] ); + int price = price1( encoder->bm_rep0[state] ); + if( rep == 1 ) + price += price0( encoder->bm_rep1[state] ); + else + { + price += price1( encoder->bm_rep1[state] ); + price += price_bit( encoder->bm_rep2[state], rep - 2 ); + } + return price; + } + +static inline int LZe_price_pair( struct LZ_encoder * const encoder, const int dis, + const int len, const int pos_state ) + { + if( len <= min_match_len && dis >= modeled_distances ) + return lze_infinite_price; + int price = Lee_price( &encoder->len_encoder, len, pos_state ); + const int dis_state = get_dis_state( len ); + if( dis < modeled_distances ) + price += encoder->dis_prices[dis_state][dis]; + else + price += encoder->dis_slot_prices[dis_state][get_slot( dis )] + + encoder->align_prices[dis & lze_dis_align_mask]; + return price; + } + +static inline void LZe_encode_pair( struct LZ_encoder * const encoder, + const uint32_t dis, const int len, const int pos_state ) + { + Lee_encode( &encoder->len_encoder, &encoder->range_encoder, len, pos_state ); + const int dis_slot = get_slot( dis ); + Re_encode_tree( &encoder->range_encoder, encoder->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 ) + Re_encode_tree_reversed( &encoder->range_encoder, encoder->bm_dis + base - dis_slot, + direct_dis, direct_bits ); + else + { + Re_encode( &encoder->range_encoder, direct_dis >> dis_align_bits, direct_bits - dis_align_bits ); + Re_encode_tree_reversed( &encoder->range_encoder, encoder->bm_align, direct_dis, dis_align_bits ); + if( --encoder->align_price_count <= 0 ) LZe_fill_align_prices( encoder ); + } + } + } + +static inline int LZe_read_match_distances( struct LZ_encoder * const encoder ) + { + int len = Mf_longest_match_len( encoder->matchfinder, encoder->match_distances ); + if( len == Mf_match_len_limit( encoder->matchfinder ) ) + len += Mf_true_match_len( encoder->matchfinder, len, encoder->match_distances[len] + 1, max_match_len - len ); + return len; + } + +static inline bool LZe_move_pos( struct LZ_encoder * const encoder, + int n, bool skip ) + { + while( --n >= 0 ) + { + if( skip ) skip = false; + else Mf_longest_match_len( encoder->matchfinder, 0 ); + if( !Mf_move_pos( encoder->matchfinder ) ) return false; + } + return true; + } + +static inline void LZe_backward( struct LZ_encoder * const encoder, int cur ) + { + int * const dis = &encoder->trials[cur].dis; + while( cur > 0 ) + { + const int prev_index = encoder->trials[cur].prev_index; + struct Trial * const prev_trial = &encoder->trials[prev_index]; + prev_trial->price = cur - prev_index; // len + cur = *dis; *dis = prev_trial->dis; prev_trial->dis = cur; + cur = prev_index; + } + } + +int LZe_best_pair_sequence( struct LZ_encoder * const encoder, + const int reps[num_rep_distances], const State state ); + +void LZe_full_flush( struct LZ_encoder * const encoder, const State state ); + +void LZe_init( struct LZ_encoder * const encoder, struct Matchfinder * const mf, + const File_header header, const int outfd ); + +static inline void LZe_free( struct LZ_encoder * const encoder ) + { + Re_free( &encoder->range_encoder ); + } + +bool LZe_encode_member( struct LZ_encoder * const encoder, const long long member_size ); + +static inline long long LZe_member_position( struct LZ_encoder * const encoder ) + { return Re_member_position( &encoder->range_encoder ); } diff --git a/main.c b/main.c new file mode 100644 index 0000000..3eb7c87 --- /dev/null +++ b/main.c @@ -0,0 +1,899 @@ +/* Clzip - A data compressor based on the LZMA algorithm + Copyright (C) 2010 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 . +*/ +/* + 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 clzip to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "carg_parser.h" +#include "clzip.h" +#include "decoder.h" +#include "encoder.h" + +#if CHAR_BIT != 8 +#error "Environments where CHAR_BIT != 8 are not supported." +#endif + +#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 + + +const char * invocation_name = 0; +const char * const Program_name = "Clzip"; +const char * const program_name = "clzip"; +const char * const program_year = "2010"; + +#ifdef O_BINARY +const int o_binary = O_BINARY; +#else +const int o_binary = 0; +#endif + +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 }; + +char * output_filename = 0; +int outfd = -1; +bool delete_output_on_interrupt = false; + + +// assure at least a minimum size for buffer `buf' +inline void * resize_buffer( void * buf, const int min_size ) + { + if( buf ) buf = realloc( buf, min_size ); + else buf = malloc( min_size ); + return buf; + } + + +static void show_help() + { + printf( "%s - A data compressor based on the LZMA algorithm.\n", Program_name ); + printf( "\nUsage: %s [options] [files]\n", invocation_name ); + printf( "\nOptions:\n" ); + printf( " -h, --help display this help and exit\n" ); + printf( " -V, --version output version information and exit\n" ); + printf( " -b, --member-size= set member size limit in bytes\n" ); + printf( " -c, --stdout send output to standard output\n" ); + printf( " -d, --decompress decompress\n" ); + printf( " -f, --force overwrite existing output files\n" ); + printf( " -k, --keep keep (don't delete) input files\n" ); + printf( " -m, --match-length= set match length limit in bytes [80]\n" ); + printf( " -o, --output= if reading stdin, place the output into \n" ); + printf( " -q, --quiet suppress all messages\n" ); + printf( " -s, --dictionary-size= set dictionary size limit in bytes [8MiB]\n" ); + printf( " -S, --volume-size= set volume size limit in bytes\n" ); + printf( " -t, --test test compressed file integrity\n" ); + printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" ); + printf( " -1 .. -9 set compression level [default 6]\n" ); + printf( " --fast alias for -1\n" ); + printf( " --best alias for -9\n" ); + printf( "If no file names are given, %s compresses or decompresses\n", program_name ); + printf( "from standard input to standard output.\n" ); + printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" ); + printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" ); + printf( "\nReport bugs to lzip-bug@nongnu.org\n" ); + printf( "Clzip home page: http://www.nongnu.org/lzip/clzip.html\n" ); + } + + +static void show_version() + { + printf( "%s %s\n", Program_name, PROGVERSION ); + printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + printf( "License GPLv3+: GNU GPL version 3 or later \n" ); + printf( "This is free software: you are free to change and redistribute it.\n" ); + printf( "There is NO WARRANTY, to the extent permitted by law.\n" ); + } + + +static const char * format_num( long long num, long long limit, + const int set_prefix ) + { + 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 = max( 999LL, 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; + } + + +static long long getnum( const char * const ptr, const int bs, + const long long llimit, const long long ulimit ) + { + errno = 0; + char *tail; + long long result = strtoll( ptr, &tail, 0 ); + if( tail == ptr ) + { + show_error( "bad or missing numerical argument", 0, true ); + 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 ); + 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", 0, false ); + exit( 1 ); + } + return result; + } + + +static int get_dict_size( const char * const arg ) + { + char *tail; + int bits = 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 ); + } + + +static int extension_index( const char * const name ) + { + for( int i = 0; known_extensions[i].from; ++i ) + { + const char * const ext = known_extensions[i].from; + if( strlen( name ) > strlen( ext ) && + strncmp( name + strlen( name ) - strlen( ext ), ext, strlen( ext ) ) == 0 ) + return i; + } + return -1; + } + + +static int open_instream( const char * const name, struct stat * const in_statsp, + const enum Mode program_mode, const int eindex, + const bool force, const bool to_stdout ) + { + int infd = -1; + if( program_mode == m_compress && !force && eindex >= 0 ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: input file `%s' already has `%s' suffix.\n", + program_name, name, known_extensions[eindex].from ); + } + else + { + infd = open( name, O_RDONLY | o_binary ); + if( infd < 0 ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: Can't open input file `%s': %s.\n", + program_name, name, strerror( errno ) ); + } + else + { + const int i = fstat( infd, 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 ) + fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n", + program_name, name, + to_stdout ? "" : " and `--stdout' was not specified" ); + close( infd ); + infd = -1; + } + } + } + return infd; + } + + +static void set_c_outname( const char * const name, const bool multifile ) + { + output_filename = resize_buffer( output_filename, strlen( name ) + 5 + + strlen( known_extensions[0].from ) + 1 ); + strcpy( output_filename, name ); + if( multifile ) strcat( output_filename, "00001" ); + strcat( output_filename, known_extensions[0].from ); + } + + +static void set_d_outname( const char * const name, const int i ) + { + if( i >= 0 ) + { + const char * const from = known_extensions[i].from; + if( strlen( name ) > strlen( from ) ) + { + output_filename = resize_buffer( output_filename, strlen( name ) + + strlen( known_extensions[0].to ) + 1 ); + strcpy( output_filename, name ); + strcpy( output_filename + strlen( name ) - strlen( from ), + known_extensions[i].to ); + return; + } + } + output_filename = resize_buffer( output_filename, strlen( name ) + 4 + 1 ); + strcpy( output_filename, name ); + strcat( output_filename, ".out" ); + if( verbosity >= 0 ) + fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n", + program_name, name, output_filename ); + } + + +static bool open_outstream( const bool force ) + { + int flags = O_CREAT | O_WRONLY | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + outfd = open( output_filename, flags, + S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH ); + if( outfd < 0 ) + { + if( errno == EEXIST ) outfd = -2; else outfd = -1; + if( verbosity >= 0 ) + { + if( outfd == -2 ) + fprintf( stderr, "%s: Output file %s already exists, skipping.\n", + program_name, output_filename ); + else + fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename, strerror( errno ) ); + } + } + return ( outfd >= 0 ); + } + + +static bool check_tty( const int infd, const enum Mode program_mode ) + { + if( program_mode == m_compress && isatty( outfd ) ) + { + 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( infd ) ) + { + show_error( "I won't read compressed data from a terminal.", 0, true ); + return false; + } + return true; + } + + + // Set permissions, owner and times. +static void close_and_set_permissions( const struct stat * const in_statsp ) + { + bool error = false; + if( in_statsp ) + { + if( fchmod( outfd, in_statsp->st_mode ) != 0 ) error = true; + else (void)fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ); + // fchown will in many cases return with EPERM, which can be safely ignored. + } + if( close( outfd ) == 0 ) outfd = -1; + else cleanup_and_fail( 1 ); + delete_output_on_interrupt = false; + if( !in_statsp ) return; + if( !error ) + { + struct utimbuf t; + t.actime = in_statsp->st_atime; + t.modtime = in_statsp->st_mtime; + if( utime( output_filename, &t ) != 0 ) error = true; + } + if( error ) + { + show_error( "I can't change output file attributes.", 0, false ); + cleanup_and_fail( 1 ); + } + } + + +static bool next_filename() + { + const unsigned int len = strlen( known_extensions[0].from ); + if( strlen( output_filename ) >= len + 5 ) // "*00001.lz" + for( int i = strlen( output_filename ) - 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; + } + + +static int compress( const long long member_size, const long long volume_size, + const struct Lzma_options * const encoder_options, const int infd, + struct Pretty_print * const pp, const struct stat * const in_statsp ) + { + if( verbosity >= 1 ) Pp_show_msg( pp, 0 ); + File_header header; + Fh_set_magic( header ); + if( !Fh_set_dictionary_size( header, encoder_options->dictionary_size ) || + encoder_options->match_len_limit < min_match_len_limit || + encoder_options->match_len_limit > max_match_len ) + internal_error( "invalid argument to encoder" ); + + struct Matchfinder matchfinder; + Mf_init( &matchfinder, Fh_get_dictionary_size( header ), + encoder_options->match_len_limit, infd ); + Fh_set_dictionary_size( header, Mf_dictionary_size( &matchfinder ) ); + + long long in_size = 0, out_size = 0, partial_volume_size = 0; + int retval = 0; + while( true ) // encode one member per iteration + { + struct LZ_encoder encoder; + LZe_init( &encoder, &matchfinder, header, outfd ); + const long long size = + min( member_size, volume_size - partial_volume_size ); + if( !LZe_encode_member( &encoder, size ) ) + { Pp_show_msg( pp, 0 ); show_error( "encoder error", 0, false ); + retval = 1; break; } + in_size += Mf_data_position( &matchfinder ); + out_size += LZe_member_position( &encoder ); + partial_volume_size += LZe_member_position( &encoder ); + LZe_free( &encoder ); + if( Mf_finished( &matchfinder ) ) break; + if( partial_volume_size >= volume_size - min_dictionary_size ) + { + partial_volume_size = 0; + if( delete_output_on_interrupt ) + { + close_and_set_permissions( in_statsp ); + if( !next_filename() ) + { Pp_show_msg( pp, 0 ); + show_error( "too many volume files", 0, false ); + retval = 1; break; } + if( !open_outstream( true ) ) { retval = 1; break; } + delete_output_on_interrupt = true; + } + } + if( !Mf_reset( &matchfinder ) ) + { Pp_show_msg( pp, 0 ); show_error( "can't reset matchfinder", 0, false ); + retval = 1; break; } + } + + if( retval == 0 && verbosity >= 1 ) + { + if( in_size <= 0 || out_size <= 0 ) + fprintf( stderr, "no data compressed.\n" ); + else + 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 ); + } + Mf_free( &matchfinder ); + return retval; + } + + +static int decompress( const int infd, struct Pretty_print * const pp, + const bool testing ) + { + struct Input_buffer ibuf; + Ib_init( &ibuf, infd ); + long long partial_file_pos = 0; + int retval = 0; + + for( bool first_member = true; ; first_member = false, Pp_reset( pp ) ) + { + File_header header; + for( unsigned int i = 0; i < sizeof (File_header); ++i ) + header[i] = Ib_get_byte( &ibuf ); + if( Ib_finished( &ibuf ) ) // End Of File + { + if( !first_member ) break; + Pp_show_msg( pp, "error reading member header" ); retval = 1; break; + } + if( !Fh_verify_magic( header ) ) + { + if( !first_member ) break; // trailing garbage + Pp_show_msg( pp, "bad magic number (file not in lzip format)" ); + retval = 2; break; + } + if( !Fh_verify_version( header ) ) + { + if( verbosity >= 0 ) + { Pp_show_msg( pp, 0 ); + fprintf( stderr, "version %d member format not supported, newer %s needed.\n", + Fh_version( header ), program_name ); } + retval = 2; break; + } + if( Fh_get_dictionary_size( header ) < min_dictionary_size || + Fh_get_dictionary_size( header ) > max_dictionary_size ) + { Pp_show_msg( pp, "invalid dictionary size in member header" ); + retval = 2; break; } + + if( verbosity >= 1 ) + { + Pp_show_msg( pp, 0 ); + if( verbosity >= 2 ) + fprintf( stderr, "version %d, dictionary size %7sB. ", + Fh_version( header ), + format_num( Fh_get_dictionary_size( header ), 9999, 0 ) ); + } + struct LZ_decoder decoder; + LZd_init( &decoder, header, &ibuf, outfd ); + + const int result = LZd_decode_member( &decoder, pp ); + partial_file_pos += LZd_member_position( &decoder ); + LZd_free( &decoder ); + if( result != 0 ) + { + if( verbosity >= 0 && result <= 2 ) + { + Pp_show_msg( pp, 0 ); + if( result == 2 ) + fprintf( stderr, "file ends unexpectedly at pos %lld\n", + partial_file_pos ); + else + fprintf( stderr, "decoder error at pos %lld\n", partial_file_pos ); + } + retval = 2; break; + } + if( verbosity >= 1 ) + { if( testing ) fprintf( stderr, "ok\n" ); + else fprintf( stderr, "done\n" ); } + } + Ib_free( &ibuf ); + return retval; + } + + +void signal_handler( int sig ) + { + sig = 0; // keep compiler happy + show_error( "Control-C or similar caught, quitting.", 0, false ); + cleanup_and_fail( 1 ); + } + + +static void set_signals() + { + signal( SIGHUP, signal_handler ); + signal( SIGINT, signal_handler ); + signal( SIGTERM, signal_handler ); + } + + +int verbosity = 0; + + +void Pp_init( struct Pretty_print * const pp, const char * const filenames[], + const int num_filenames ) + { + pp->name_ = 0; + pp->stdin_name = "(stdin)"; + pp->longest_name = 0; + pp->first_post = false; + unsigned int stdin_name_len = strlen( pp->stdin_name ); + + for( int i = 0; i < num_filenames; ++i ) + { + const char * const s = filenames[i]; + const int len = ( !strcmp( s, "-" ) ? stdin_name_len : strlen( s ) ); + if( len > pp->longest_name ) pp->longest_name = len; + } + if( pp->longest_name == 0 ) pp->longest_name = stdin_name_len; + } + + +void Pp_show_msg( struct Pretty_print * const pp, const char * const msg ) + { + if( verbosity >= 0 ) + { + if( pp->first_post ) + { + pp->first_post = false; + fprintf( stderr, " %s: ", pp->name_ ); + const int len = pp->longest_name - strlen( pp->name_ ); + for( int i = 0; i < len; ++i ) fprintf( stderr, " " ); + if( !msg ) fflush( stderr ); + } + if( msg ) fprintf( stderr, "%s.\n", msg ); + } + } + + +void cleanup_and_fail( const int retval ) + { + if( delete_output_on_interrupt ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n", + program_name, output_filename ); + if( outfd >= 0 ) { close( outfd ); outfd = -1; } + if( remove( output_filename ) != 0 ) + show_error( "WARNING: deletion of output file (apparently) failed.", 0, false ); + } + exit( retval ); + } + + +void show_error( const char * const msg, const int errcode, const bool help ) + { + if( verbosity >= 0 ) + { + if( msg && msg[0] != 0 ) + { + fprintf( stderr, "%s: %s", program_name, msg ); + if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) ); + fprintf( stderr, "\n" ); + } + if( help && invocation_name && invocation_name[0] != 0 ) + fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name ); + } + } + + +void internal_error( const char * const msg ) + { + const char * const e = "internal error: "; + char * s = resize_buffer( 0, strlen( e ) + strlen( msg ) + 1 ); + strcpy( s, e ); + strcat( s, msg ); + show_error( s, 0, false ); + free( s ); + exit( 3 ); + } + + +// Returns the number of bytes really read. +// If (returned value < size) and (errno == 0), means EOF was reached. +// +int readblock( const int fd, uint8_t * const buf, const int size ) + { + 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 uint8_t * const buf, const int size ) + { + 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; + } + + +CRC32 crc32; + +int main( const int argc, const char * const argv[] ) + { + // Mapping from gzip/bzip2 style 1..9 compression modes + // to the corresponding LZMA compression modes. + const struct Lzma_options option_mapping[] = + { + { 1 << 20, 10 }, // -1 + { 3 << 19, 12 }, // -2 + { 1 << 21, 17 }, // -3 + { 3 << 20, 26 }, // -4 + { 1 << 22, 44 }, // -5 + { 1 << 23, 80 }, // -6 + { 1 << 24, 108 }, // -7 + { 3 << 23, 163 }, // -8 + { 1 << 25, 273 } }; // -9 + struct Lzma_options encoder_options = option_mapping[5]; // default = "-6" + long long member_size = LLONG_MAX; + long long volume_size = LLONG_MAX; + int infd = -1; + enum Mode program_mode = m_compress; + bool force = false; + bool keep_input_files = false; + bool to_stdout = false; + const char * input_filename = ""; + const char * default_output_filename = ""; + const char ** filenames = 0; + int num_filenames = 0; + invocation_name = argv[0]; + CRC32_init(); + + const struct ap_Option options[] = + { + { '1', "fast", ap_no }, + { '2', 0, ap_no }, + { '3', 0, ap_no }, + { '4', 0, ap_no }, + { '5', 0, ap_no }, + { '6', 0, ap_no }, + { '7', 0, ap_no }, + { '8', 0, ap_no }, + { '9', "best", ap_no }, + { 'b', "member-size", ap_yes }, + { 'c', "stdout", ap_no }, + { 'd', "decompress", ap_no }, + { 'f', "force", ap_no }, + { 'h', "help", ap_no }, + { 'k', "keep", ap_no }, + { 'm', "match-length", ap_yes }, + { 'o', "output", ap_yes }, + { 'q', "quiet", ap_no }, + { 's', "dictionary-size", ap_yes }, + { 'S', "volume-size", ap_yes }, + { 't', "test", ap_no }, + { 'v', "verbose", ap_no }, + { 'V', "version", ap_no }, + { 0 , 0, ap_no } }; + + struct Arg_parser parser; + if( !ap_init( &parser, argc, argv, options, 0 ) ) + { show_error( "Memory exhausted", 0, 0 ); return 1; } + if( ap_error( &parser ) ) // bad option + { show_error( ap_error( &parser ), 0, 1 ); return 1; } + + int argind = 0; + for( ; argind < ap_arguments( &parser ); ++argind ) + { + const int code = ap_code( &parser, argind ); + const char * const arg = ap_argument( &parser, argind ); + if( !code ) break; // no more options + 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, min_match_len_limit, max_match_len ); 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 < ap_arguments( &parser ); ++argind ) + { + if( strcmp( ap_argument( &parser, argind ), "-" ) ) + filenames_given = true; + ++num_filenames; + filenames = resize_buffer( filenames, num_filenames * sizeof (char *) ); + filenames[num_filenames-1] = ap_argument( &parser, argind ); + } + + if( num_filenames == 0 ) + { + ++num_filenames; + filenames = resize_buffer( filenames, sizeof (char *) ); + filenames[num_filenames-1] = "-"; + } + if( !to_stdout && program_mode != m_test && + ( filenames_given || default_output_filename[0] ) ) + set_signals(); + + struct Pretty_print pp; + Pp_init( &pp, filenames, num_filenames ); + if( program_mode == m_test ) + outfd = -1; + else if( program_mode == m_compress ) + { + Dis_slots_init(); + Prob_prices_init(); + } + + output_filename = resize_buffer( output_filename, 1 ); + int retval = 0; + for( int i = 0; i < num_filenames; ++i ) + { + struct stat in_stats; + output_filename[0] = 0; + + if( !filenames[i][0] || !strcmp( filenames[i], "-" ) ) + { + input_filename = ""; + infd = STDIN_FILENO; + if( program_mode != m_test ) + { + if( to_stdout || !default_output_filename[0] ) + outfd = STDOUT_FILENO; + else + { + if( program_mode == m_compress ) + set_c_outname( default_output_filename, volume_size != LLONG_MAX ); + else + { + output_filename = resize_buffer( output_filename, + strlen( default_output_filename ) + 1 ); + strcpy( output_filename, default_output_filename ); + } + if( !open_outstream( force ) ) + { + if( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + else + { + input_filename = filenames[i]; + const int eindex = extension_index( input_filename ); + infd = open_instream( input_filename, &in_stats, program_mode, + eindex, force, to_stdout ); + if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; } + if( program_mode != m_test ) + { + if( to_stdout ) outfd = 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( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + + if( !check_tty( infd, program_mode ) ) return 1; + + if( output_filename[0] && !to_stdout && program_mode != m_test ) + delete_output_on_interrupt = true; + const struct stat * const in_statsp = input_filename[0] ? &in_stats : 0; + Pp_set_name( &pp, input_filename ); + int tmp = 0; + if( program_mode == m_compress ) + tmp = compress( member_size, volume_size, &encoder_options, infd, + &pp, in_statsp ); + else + tmp = decompress( infd, &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 ); + if( input_filename[0] ) + { + close( infd ); infd = -1; + if( !keep_input_files && !to_stdout && program_mode != m_test ) + remove( input_filename ); + } + } + if( outfd >= 0 && close( outfd ) != 0 ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: Can't close stdout: %s.\n", + program_name, strerror( errno ) ); + if( retval < 1 ) retval = 1; + } + free( output_filename ); + free( filenames ); + ap_free( &parser ); + return retval; + } diff --git a/testsuite/check.sh b/testsuite/check.sh new file mode 100755 index 0000000..a57224d --- /dev/null +++ b/testsuite/check.sh @@ -0,0 +1,69 @@ +#! /bin/sh +# check script for Clzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2010 Antonio Diaz Diaz. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +LC_ALL=C +export LC_ALL +objdir=`pwd` +testdir=`cd "$1" ; pwd` +LZIP="${objdir}"/clzip +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 -rf tmp ; fi +mkdir tmp +printf "testing clzip..." +cd "${objdir}"/tmp + +cat "${testdir}"/test1 > in || framework_failure +fail=0 + +"${LZIP}" -cd "${testdir}"/test1.lz > copy || fail=1 +cmp in copy || fail=1 + +for i in s4Ki 1 2 3 4 5 6 7 8 9 ; do + "${LZIP}" -k -$i in || fail=1 + mv -f in.lz copy.lz || fail=1 + printf "garbage" >> copy.lz || fail=1 + "${LZIP}" -df copy.lz || fail=1 + cmp in copy || fail=1 + printf . +done + +for i in s4Ki 1 2 3 4 5 6 7 8 9 ; do + "${LZIP}" -c -$i in > out || fail=1 + printf "g" >> out || fail=1 + "${LZIP}" -cd out > copy || fail=1 + cmp in copy || fail=1 + printf . +done + +for i in s4Ki 1 2 3 4 5 6 7 8 9 ; do + "${LZIP}" -$i < in > out || fail=1 + "${LZIP}" -d < out > copy || fail=1 + cmp in copy || fail=1 + printf . +done + +for i in s4Ki 1 2 3 4 5 6 7 8 9 ; do + "${LZIP}" -f -$i -o out < in || fail=1 + "${LZIP}" -df -o copy < out.lz || fail=1 + cmp in copy || fail=1 + printf . +done + +echo +if [ ${fail} = 0 ] ; then + echo "tests completed successfully." + cd "${objdir}" && rm -r tmp +else + echo "tests failed." +fi +exit ${fail} diff --git a/testsuite/test1 b/testsuite/test1 new file mode 100644 index 0000000..5b244d5 --- /dev/null +++ b/testsuite/test1 @@ -0,0 +1,676 @@ + + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + 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. + + + Copyright (C) + + 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 . + +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: + + Copyright (C) + 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 +. + + 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 +. + diff --git a/testsuite/test1.lz b/testsuite/test1.lz new file mode 100644 index 0000000..a09b1e8 Binary files /dev/null and b/testsuite/test1.lz differ -- cgit v1.2.3