From ce537b6151b2105c25d979bf40f445051754b798 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 7 Nov 2015 08:22:08 +0100 Subject: Adding upstream version 1.6~pre1. Signed-off-by: Daniel Baumann --- AUTHORS | 4 + COPYING | 676 ++++++++++++++++++++++++++++++++++++++++ ChangeLog | 101 ++++++ INSTALL | 59 ++++ Makefile.in | 125 ++++++++ NEWS | 9 + README | 66 ++++ arg_parser.cc | 193 ++++++++++++ arg_parser.h | 95 ++++++ configure | 214 +++++++++++++ decoder.cc | 218 +++++++++++++ decoder.h | 272 +++++++++++++++++ doc/lzip.1 | 87 ++++++ doc/lzip.info | 572 ++++++++++++++++++++++++++++++++++ doc/lzip.texinfo | 598 ++++++++++++++++++++++++++++++++++++ encoder.cc | 554 +++++++++++++++++++++++++++++++++ encoder.h | 604 ++++++++++++++++++++++++++++++++++++ lzdiff | 145 +++++++++ lzgrep | 130 ++++++++ lzip.h | 275 +++++++++++++++++ lziprecover.cc | 347 +++++++++++++++++++++ main.cc | 831 ++++++++++++++++++++++++++++++++++++++++++++++++++ testsuite/COPYING.lz | Bin 0 -> 11540 bytes testsuite/check.sh | 67 ++++ testsuite/unzcrash.cc | 85 ++++++ 25 files changed, 6327 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 arg_parser.cc create mode 100644 arg_parser.h create mode 100755 configure create mode 100644 decoder.cc create mode 100644 decoder.h create mode 100644 doc/lzip.1 create mode 100644 doc/lzip.info create mode 100644 doc/lzip.texinfo create mode 100644 encoder.cc create mode 100644 encoder.h create mode 100755 lzdiff create mode 100755 lzgrep create mode 100644 lzip.h create mode 100644 lziprecover.cc create mode 100644 main.cc create mode 100644 testsuite/COPYING.lz create mode 100755 testsuite/check.sh create mode 100644 testsuite/unzcrash.cc diff --git a/AUTHORS b/AUTHORS new file mode 100644 index 0000000..e6d518b --- /dev/null +++ b/AUTHORS @@ -0,0 +1,4 @@ +Lzip was written by Antonio Diaz Diaz. + +Lzip 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..5b244d5 --- /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..daa565b --- /dev/null +++ b/ChangeLog @@ -0,0 +1,101 @@ +2009-04-27 Antonio Diaz + + * Version 1.6-pre1 released. + * Makefile.in: Extra files are now installed by default. + * decoder.cc: Added extra flush calls to improve partial + decompression of corrupt files. + * "--test" no more needs "/dev/null". + +2009-04-12 Antonio Diaz + + * Version 1.5 released. + * lzip.h: Coded dictionary size implemented in File_header. + * Fixed some includes that prevented compilation with GCC 4.4. + * "member_size" and "volume_size" are now accurate limits. + * Compression speed has been improved. + * Implemented bt4 type matchfinder. + * Added chapter "Algorithm" to the manual. + * Lzdiff and lzgrep now accept "-h" for "--help" and + "-V" for "--version". + * Makefile.in: Man page is now installed by default. + +2009-01-24 Antonio Diaz + + * Version 1.4 released. + * Implemented compression of version 1 files. + * Added new option "--member-size". + * Added new option "--volume-size". + * Added new option "--output". + * main.cc: Read from non regular files if "--stdout" is specified. + * Added "lziprecover", a member recoverer program. + * testsuite/unzcrash.cc: Test all 1-byte errors. + +2008-12-21 Antonio Diaz + + * Version 1.3 released. + * This version automatically chooses the smallest possible + dictionary size for each file during compression, saving + memory during decompression. + * Implemented decompression of version 1 files. + * testsuite/check.sh: Replaced "diff -q" with "cmp". + +2008-12-10 Antonio Diaz + + * Version 1.2 released. + * encoder.cc: A 1-byte read outside allocated memory has been fixed. + * lzip.h: Dictionary size limit has been reduced to 512MiB because + setting it to 1GiB causes overflow of a 32 bit integer. + * Added "lzdiff", a diff/cmp wrapper for gzip, bzip2, lzip and + non-compressed files. + * Added "lzgrep", a grep wrapper for gzip, bzip2, lzip and + non-compressed files. + * "make install-info" should now work on Debian and OS X. + +2008-11-17 Antonio Diaz + + * Version 1.1 released. + * Changed short name of option "--dictionary-size" to "-s". + * Changed short name of option "--match-length" to "-m". + * Changed LONG_LONG_MAX to LLONG_MAX. + +2008-10-14 Antonio Diaz + + * Version 1.0 released. + * "-tvv" shows file version and dictionary size. + +2008-09-30 Antonio Diaz + + * Version 0.5 released. + * Decompression is now 1% faster. + +2008-09-23 Antonio Diaz + + * Version 0.4 released. + * Code cleanup for global variable "verbosity". + * Regained the compression ratio of 0.2 with 5% faster speed. + * Fixed compilation on sistems where size_t != unsigned int. + +2008-09-15 Antonio Diaz + + * Version 0.3 released. + * encoder.cc: Compression is now 15% faster, 1% worse. + * main.cc (main): Make "-t" option override "-c". + * main.cc (decompress): Show "done" instead of "ok" when not testing. + * encoder.h: Use trials[] to return the list of pairs. + +2008-09-09 Antonio Diaz + + * Version 0.2 released. + * encoder.cc: Small improvements in compression speed. + * Small documentation changes. + +2008-08-20 Antonio Diaz + + * Version 0.1 released. + + +Copyright (C) 2008, 2009 Antonio Diaz Diaz. + +This file is a collection of facts, and thus it is not copyrightable, +but just in case, I give you unlimited permission to copy, distribute +and modify it. diff --git a/INSTALL b/INSTALL new file mode 100644 index 0000000..7ca2833 --- /dev/null +++ b/INSTALL @@ -0,0 +1,59 @@ +Requirements +------------ +You will need a C++ compiler. +I use gcc 4.3.3 and 3.3.6, but the code should compile with any +standards compliant compiler. +Gcc is available at http://gcc.gnu.org. + + +Procedure +--------- +1. Unpack the archive if you have not done so already: + + lzip -cd lzip[version].tar.lz | tar -xf - +or + gzip -cd lzip[version].tar.gz | tar -xf - + +This creates the directory ./lzip[version] containing the source from +the main archive. + +2. Change to lzip directory and run configure. + (Try `configure --help' for usage instructions). + + cd lzip[version] + ./configure + +3. Run make. + + make + +4. Optionally, type `make check' to run the tests that come with lzip. + +5. Type `make install' to install the program and any data files and + documentation. + +6. Optionally, type `make install-extra' to install the lziprecover + program and the included wrapper scripts (lzdiff, lzgrep). + + +Another way +----------- +You can also compile lzip 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) 2008, 2009 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..644f141 --- /dev/null +++ b/Makefile.in @@ -0,0 +1,125 @@ + +DISTNAME = $(progname)-$(progversion) +INSTALL = install +INSTALL_PROGRAM = $(INSTALL) -p -m 755 +INSTALL_SCRIPT = $(INSTALL) -p -m 755 +INSTALL_DATA = $(INSTALL) -p -m 644 +SHELL = /bin/sh + +objs = arg_parser.o decoder.o encoder.o main.o + + +.PHONY : all doc check install install-info install-man install-extra \ + uninstall uninstall-info uninstall-man uninstall-extra \ + install-strip dist clean distclean + +all : $(progname) lziprecover + +$(progname) : $(objs) + $(CXX) $(LDFLAGS) -o $(progname) $(objs) + +profiled_$(progname) : $(objs) + $(CXX) $(LDFLAGS) -pg -o profiled_$(progname) $(objs) + +lziprecover : arg_parser.o lziprecover.o + $(CXX) $(LDFLAGS) -o lziprecover arg_parser.o lziprecover.o + +main.o : main.cc + $(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(progversion)\" -c -o $@ $< + +lziprecover.o : lziprecover.cc + $(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(progversion)\" -c -o $@ $< + +%.o : %.cc + $(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $< + +$(objs) : Makefile +arg_parser.o : arg_parser.h +decoder.o : lzip.h decoder.h +encoder.o : lzip.h encoder.h +main.o : arg_parser.h lzip.h decoder.h encoder.h +lziprecover.o : arg_parser.h lzip.h Makefile + +doc : info $(VPATH)/doc/$(progname).1 + +info : $(VPATH)/doc/$(progname).info + +$(VPATH)/doc/$(progname).info : $(VPATH)/doc/$(progname).texinfo + cd $(VPATH)/doc && makeinfo $(progname).texinfo + +$(VPATH)/doc/$(progname).1 : $(progname) + help2man -o $(VPATH)/doc/$(progname).1 ./$(progname) + +Makefile : $(VPATH)/configure $(VPATH)/Makefile.in + ./config.status + +check : all $(VPATH)/testsuite/check.sh + @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite + +install : all install-info install-man install-extra + if test ! -d $(DESTDIR)$(bindir) ; then $(INSTALL) -d $(DESTDIR)$(bindir) ; fi + $(INSTALL_PROGRAM) ./$(progname) $(DESTDIR)$(bindir)/$(progname) + +install-info : + if test ! -d $(DESTDIR)$(infodir) ; then $(INSTALL) -d $(DESTDIR)$(infodir) ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(progname).info $(DESTDIR)$(infodir)/$(progname).info + -install-info --info-dir=$(DESTDIR)$(infodir) $(DESTDIR)$(infodir)/$(progname).info + +install-man : + if test ! -d $(DESTDIR)$(mandir)/man1 ; then $(INSTALL) -d $(DESTDIR)$(mandir)/man1 ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(progname).1 $(DESTDIR)$(mandir)/man1/$(progname).1 + +install-extra : lziprecover + if test ! -d $(DESTDIR)$(bindir) ; then $(INSTALL) -d $(DESTDIR)$(bindir) ; fi + $(INSTALL_SCRIPT) $(VPATH)/lzdiff $(DESTDIR)$(bindir)/lzdiff + $(INSTALL_SCRIPT) $(VPATH)/lzgrep $(DESTDIR)$(bindir)/lzgrep + $(INSTALL_PROGRAM) ./lziprecover $(DESTDIR)$(bindir)/lziprecover + +install-strip : all + $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install + +uninstall : uninstall-info uninstall-man uninstall-extra + -rm -f $(DESTDIR)$(bindir)/$(progname) + +uninstall-info : + -install-info --info-dir=$(DESTDIR)$(infodir) --remove $(DESTDIR)$(infodir)/$(progname).info + -rm -f $(DESTDIR)$(infodir)/$(progname).info + +uninstall-man : + -rm -f $(DESTDIR)$(mandir)/man1/$(progname).1 + +uninstall-extra : + -rm -f $(DESTDIR)$(bindir)/lzdiff + -rm -f $(DESTDIR)$(bindir)/lzgrep + -rm -f $(DESTDIR)$(bindir)/lziprecover + +dist : + ln -sf $(VPATH) $(DISTNAME) + tar -cvf $(DISTNAME).tar \ + $(DISTNAME)/AUTHORS \ + $(DISTNAME)/COPYING \ + $(DISTNAME)/ChangeLog \ + $(DISTNAME)/INSTALL \ + $(DISTNAME)/Makefile.in \ + $(DISTNAME)/NEWS \ + $(DISTNAME)/README \ + $(DISTNAME)/configure \ + $(DISTNAME)/doc/$(progname).1 \ + $(DISTNAME)/doc/$(progname).info \ + $(DISTNAME)/doc/$(progname).texinfo \ + $(DISTNAME)/lzdiff \ + $(DISTNAME)/lzgrep \ + $(DISTNAME)/testsuite/COPYING.lz \ + $(DISTNAME)/testsuite/check.sh \ + $(DISTNAME)/testsuite/unzcrash.cc \ + $(DISTNAME)/*.h \ + $(DISTNAME)/*.cc + rm -f $(DISTNAME) + lzip -v -9 $(DISTNAME).tar + +clean : + -rm -f $(progname) profiled_$(progname) $(objs) + -rm -f lziprecover lziprecover.o + +distclean : clean + -rm -f Makefile config.status *.tar *.tar.lz diff --git a/NEWS b/NEWS new file mode 100644 index 0000000..e052c16 --- /dev/null +++ b/NEWS @@ -0,0 +1,9 @@ +Changes in version 1.6: + +Flush calls have been added to decompressor to allow partial recovery +of the uncompressed data when decompressing a corrupt file. + +Lzdiff, lzgrep and lziprecover are now installed by default. + +The dependence of "--test" on the existence of "/dev/null" has been +removed. diff --git a/README b/README new file mode 100644 index 0000000..6e70de3 --- /dev/null +++ b/README @@ -0,0 +1,66 @@ +Description + +Lzip 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. Lzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + +Lzip 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. Lzip is able to read from some +types of non regular files if the "--stdout" option is specified. + +If no file names are specified, lzip compresses (or decompresses) from +standard input to standard output. In this case, lzip will decline to +write compressed output to a terminal, as this would be entirely +incomprehensible and therefore pointless. + +Lzip 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. + +Lzip can produce multimember files and safely recover, with lziprecover, +the undamaged members in case of file damage. Lzip 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. + +Lzip will automatically use the smallest possible dictionary size for +each member 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, lzip 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 lzip (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. + +Lzip 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) 2008, 2009 Antonio Diaz Diaz. + +This file is free documentation: you have unlimited permission to copy, +distribute and modify it. + +The file Makefile.in is a data file used by configure to produce the +Makefile. It has the same copyright owner and permissions that this +file. diff --git a/arg_parser.cc b/arg_parser.cc new file mode 100644 index 0000000..b889e1a --- /dev/null +++ b/arg_parser.cc @@ -0,0 +1,193 @@ +/* Arg_parser - A POSIX/GNU command line argument parser. + Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +#include +#include +#include + +#include "arg_parser.h" + + +bool Arg_parser::parse_long_option( const char * const opt, const char * const arg, + const Option options[], int & argind ) + { + unsigned int len; + int index = -1; + bool exact = false, ambig = false; + + for( len = 0; opt[len+2] && opt[len+2] != '='; ++len ) ; + + // Test all long options for either exact match or abbreviated matches. + for( int i = 0; options[i].code != 0; ++i ) + if( options[i].name && !std::strncmp( options[i].name, &opt[2], len ) ) + { + if( std::strlen( options[i].name ) == len ) // Exact match found + { index = i; exact = true; break; } + else if( index < 0 ) index = i; // First nonexact match found + else if( options[index].code != options[i].code || + options[index].has_arg != options[i].has_arg ) + ambig = true; // Second or later nonexact match found + } + + if( ambig && !exact ) + { + error_ = "option `"; error_ += opt; error_ += "' is ambiguous"; + return false; + } + + if( index < 0 ) // nothing found + { + error_ = "unrecognized option `"; error_ += opt; error_ += '\''; + return false; + } + + ++argind; + data.push_back( Record( options[index].code ) ); + + if( opt[len+2] ) // `--=' syntax + { + if( options[index].has_arg == no ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' doesn't allow an argument"; + return false; + } + if( options[index].has_arg == yes && !opt[len+3] ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' requires an argument"; + return false; + } + data.back().argument = &opt[len+3]; + return true; + } + + if( options[index].has_arg == yes ) + { + if( !arg || !arg[0] ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' requires an argument"; + return false; + } + ++argind; data.back().argument = arg; + return true; + } + + return true; + } + + +bool Arg_parser::parse_short_option( const char * const opt, const char * const arg, + const Option options[], int & argind ) + { + int cind = 1; // character index in opt + + while( cind > 0 ) + { + int index = -1; + const unsigned char c = opt[cind]; + + if( c != 0 ) + for( int i = 0; options[i].code; ++i ) + if( c == options[i].code ) + { index = i; break; } + + if( index < 0 ) + { + error_ = "invalid option -- "; error_ += c; + return false; + } + + data.push_back( Record( c ) ); + if( opt[++cind] == 0 ) { ++argind; cind = 0; } // opt finished + + if( options[index].has_arg != no && cind > 0 && opt[cind] ) + { + data.back().argument = &opt[cind]; ++argind; cind = 0; + } + else if( options[index].has_arg == yes ) + { + if( !arg || !arg[0] ) + { + error_ = "option requires an argument -- "; error_ += c; + return false; + } + data.back().argument = arg; ++argind; cind = 0; + } + } + return true; + } + + +Arg_parser::Arg_parser( const int argc, const char * const argv[], + const Option options[], const bool in_order ) + { + if( argc < 2 || !argv || !options ) return; + + std::vector< std::string > non_options; // skipped non-options + int argind = 1; // index in argv + + while( argind < argc ) + { + const unsigned char ch1 = argv[argind][0]; + const unsigned char ch2 = ( ch1 ? argv[argind][1] : 0 ); + + if( ch1 == '-' && ch2 ) // we found an option + { + const char * const opt = argv[argind]; + const char * const arg = (argind + 1 < argc) ? argv[argind+1] : 0; + if( ch2 == '-' ) + { + if( !argv[argind][2] ) { ++argind; break; } // we found "--" + else if( !parse_long_option( opt, arg, options, argind ) ) break; + } + else if( !parse_short_option( opt, arg, options, argind ) ) break; + } + else + { + if( !in_order ) non_options.push_back( argv[argind++] ); + else { data.push_back( Record() ); data.back().argument = argv[argind++]; } + } + } + if( error_.size() ) data.clear(); + else + { + for( unsigned int i = 0; i < non_options.size(); ++i ) + { data.push_back( Record() ); data.back().argument.swap( non_options[i] ); } + while( argind < argc ) + { data.push_back( Record() ); data.back().argument = argv[argind++]; } + } + } + + +Arg_parser::Arg_parser( const char * const opt, const char * const arg, + const Option options[] ) + { + if( !opt || !opt[0] || !options ) return; + + if( opt[0] == '-' && opt[1] ) // we found an option + { + int argind = 1; // dummy + if( opt[1] == '-' ) + { if( opt[2] ) parse_long_option( opt, arg, options, argind ); } + else + parse_short_option( opt, arg, options, argind ); + if( error_.size() ) data.clear(); + } + else { data.push_back( Record() ); data.back().argument = opt; } + } diff --git a/arg_parser.h b/arg_parser.h new file mode 100644 index 0000000..fa6161b --- /dev/null +++ b/arg_parser.h @@ -0,0 +1,95 @@ +/* Arg_parser - A POSIX/GNU command line argument parser. + Copyright (C) 2006, 2007, 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +/* Arg_parser reads the arguments in `argv' and creates a number of + option codes, option arguments and non-option arguments. + + In case of error, `error' returns a non-empty error message. + + `options' is an array of `struct Option' terminated by an element + containing a code which is zero. A null name means a short-only + option. A code value outside the unsigned char range means a + long-only option. + + Arg_parser normally makes it appear as if all the option arguments + were specified before all the non-option arguments for the purposes + of parsing, even if the user of your program intermixed option and + non-option arguments. If you want the arguments in the exact order + the user typed them, call `Arg_parser' with `in_order' = true. + + The argument `--' terminates all options; any following arguments are + treated as non-option arguments, even if they begin with a hyphen. + + The syntax for optional option arguments is `-' + (without whitespace), or `--='. +*/ + +class Arg_parser + { +public: + enum Has_arg { no, yes, maybe }; + + struct Option + { + int code; // Short option letter or code ( code != 0 ) + const char * name; // Long option name (maybe null) + Has_arg has_arg; + }; + +private: + struct Record + { + int code; + std::string argument; + Record( const int c = 0 ) : code( c ) {} + }; + + std::string error_; + std::vector< Record > data; + + bool parse_long_option( const char * const opt, const char * const arg, + const Option options[], int & argind ); + bool parse_short_option( const char * const opt, const char * const arg, + const Option options[], int & argind ); + +public: + Arg_parser( const int argc, const char * const argv[], + const Option options[], const bool in_order = false ); + + // Restricted constructor. Parses a single token and argument (if any) + Arg_parser( const char * const opt, const char * const arg, + const Option options[] ); + + const std::string & error() const throw() { return error_; } + + // The number of arguments parsed (may be different from argc) + int arguments() const throw() { return data.size(); } + + // If code( i ) is 0, argument( i ) is a non-option. + // Else argument( i ) is the option's argument (or empty). + int code( const int i ) const throw() + { + if( i >= 0 && i < arguments() ) return data[i].code; + else return 0; + } + + const std::string & argument( const int i ) const throw() + { + if( i >= 0 && i < arguments() ) return data[i].argument; + else return error_; + } + }; diff --git a/configure b/configure new file mode 100755 index 0000000..71ff5f3 --- /dev/null +++ b/configure @@ -0,0 +1,214 @@ +#! /bin/sh +# configure script for Lzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2008, 2009 Antonio Diaz Diaz. +# +# This configure script is free software: you have unlimited permission +# to copy, distribute and modify it. +# +# Date of this version: 2009-04-27 + +invocation_name=$0 +args= +no_create= +progname=lzip +progversion=1.6-pre1 +srctrigger=lzip.h + +# clear some things potentially inherited from environment. +LC_ALL=C +export LC_ALL +srcdir= +prefix=/usr/local +exec_prefix='$(prefix)' +bindir='$(exec_prefix)/bin' +datadir='$(prefix)/share' +infodir='$(datadir)/info' +mandir='$(datadir)/man' +sysconfdir='$(prefix)/etc' +CC= +CXX= +CPPFLAGS= +CFLAGS='-Wall -W -O2' +CXXFLAGS='-Wall -W -O2' +LDFLAGS= + +# Loop over all args +while [ x"$1" != x ] ; do + + # Get the first arg, and shuffle + option=$1 + shift + + # Add the argument quoted to args + args="${args} \"${option}\"" + + # Split out the argument for options that take them + case ${option} in + *=*) optarg=`echo ${option} | sed -e 's,^[^=]*=,,'` ;; + esac + + # Process the options + case ${option} in + --help | --he* | -h) + echo "Usage: configure [options]" + echo + echo "Options: [defaults in brackets]" + echo " -h, --help display this help and exit" + echo " -V, --version output version information and exit" + echo " --srcdir=DIR find the sources in DIR [. or ..]" + echo " --prefix=DIR install into DIR [${prefix}]" + echo " --exec-prefix=DIR base directory for arch-dependent files [${exec_prefix}]" + echo " --bindir=DIR user executables directory [${bindir}]" + echo " --datadir=DIR base directory for doc and data [${datadir}]" + echo " --infodir=DIR info files directory [${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 " CXX=COMPILER C++ compiler to use [g++]" + echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" + echo " CFLAGS=OPTIONS command line options for the C compiler [${CFLAGS}]" + echo " CXXFLAGS=OPTIONS command line options for the C++ compiler [${CXXFLAGS}]" + echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]" + echo + exit 0 ;; + --version | --ve* | -V) + echo "Configure script for ${progname} version ${progversion}" + 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=${optarg} ;; + CXX=*) CXX=${optarg} ;; + CPPFLAGS=*) CPPFLAGS=${optarg} ;; + CFLAGS=*) CFLAGS=${optarg} ;; + CXXFLAGS=*) CXXFLAGS=${optarg} ;; + LDFLAGS=*) LDFLAGS=${optarg} ;; + + --build=* | --enable-* | --with-* | --*dir=* | *=* | *-*-*) ;; + *) + echo "configure: Unrecognized option: \"${option}\"; use --help for usage." 1>&2 + exit 1 ;; + esac +done + +# Find the source files, if location was not specified. +srcdirtext= +if [ x"${srcdir}" = x ] ; then + srcdirtext="or . or .." ; srcdir=. + if [ ! -r ${srcdir}/${srctrigger} ] ; then srcdir=.. ; fi + if [ ! -r ${srcdir}/${srctrigger} ] ; then + ## the sed command below emulates the dirname command + srcdir=`echo ${invocation_name} | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'` + fi +fi + +if [ ! -r ${srcdir}/${srctrigger} ] ; then + exec 1>&2 + echo + echo "configure: Can't find sources in ${srcdir} ${srcdirtext}" + echo "configure: (At least ${srctrigger} is missing)." + exit 1 +fi + +# Set srcdir to . if that's what it is. +if [ "`pwd`" = "`cd ${srcdir} ; pwd`" ] ; then srcdir=. ; fi + +# checking whether we are using GNU C. +if [ x"${CC}" = x ] ; then # Let the user override the test. + if [ -x /bin/gcc ] || + [ -x /usr/bin/gcc ] || + [ -x /usr/local/bin/gcc ] ; then + CC="gcc" + else + CC="cc" + fi +fi + +# checking whether we are using GNU C++. +if [ x"${CXX}" = x ] ; then # Let the user override the test. + if [ -x /bin/g++ ] || + [ -x /usr/bin/g++ ] || + [ -x /usr/local/bin/g++ ] ; then + CXX="g++" + else + CXX="c++" + fi +fi + +echo +if [ x${no_create} = x ] ; then + echo "creating config.status" + rm -f config.status + cat > config.status << EOF +#! /bin/sh +# This file was generated automatically by configure. Do not edit. +# Run this file to recreate the current configuration. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +exec /bin/sh ${invocation_name} ${args} --no-create +EOF + chmod +x config.status +fi + +echo "creating Makefile" +echo "VPATH = ${srcdir}" +echo "prefix = ${prefix}" +echo "exec_prefix = ${exec_prefix}" +echo "bindir = ${bindir}" +echo "datadir = ${datadir}" +echo "infodir = ${infodir}" +echo "mandir = ${mandir}" +echo "sysconfdir = ${sysconfdir}" +echo "CC = ${CC}" +echo "CXX = ${CXX}" +echo "CPPFLAGS = ${CPPFLAGS}" +echo "CFLAGS = ${CFLAGS}" +echo "CXXFLAGS = ${CXXFLAGS}" +echo "LDFLAGS = ${LDFLAGS}" +rm -f Makefile +cat > Makefile << EOF +# Makefile for Lzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2008, 2009 Antonio Diaz Diaz. +# This file was generated automatically by configure. Do not edit. +# +# This Makefile is free software: you have unlimited permission +# to copy, distribute and modify it. + +progname = ${progname} +progversion = ${progversion} +VPATH = ${srcdir} +prefix = ${prefix} +exec_prefix = ${exec_prefix} +bindir = ${bindir} +datadir = ${datadir} +infodir = ${infodir} +mandir = ${mandir} +sysconfdir = ${sysconfdir} +CC = ${CC} +CXX = ${CXX} +CPPFLAGS = ${CPPFLAGS} +CFLAGS = ${CFLAGS} +CXXFLAGS = ${CXXFLAGS} +LDFLAGS = ${LDFLAGS} +EOF +cat ${srcdir}/Makefile.in >> Makefile + +echo "OK. Now you can run make." diff --git a/decoder.cc b/decoder.cc new file mode 100644 index 0000000..341740b --- /dev/null +++ b/decoder.cc @@ -0,0 +1,218 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include +#include + +#include "lzip.h" +#include "decoder.h" + + +const CRC32 crc32; + + +bool Input_buffer::read_block() + { + if( at_stream_end ) return false; + stream_pos = readblock( ides_, (char *)buffer, buffer_size ); + if( stream_pos != buffer_size && errno ) throw Error( "read error" ); + pos = 0; + at_stream_end = ( stream_pos < buffer_size ); + return !finished(); + } + + +void LZ_decoder::flush_data() + { + if( !member_finished ) + { + if( odes_ >= 0 ) + { + const int wr = writeblock( odes_, (char *)buffer, pos ); + if( wr != pos ) throw Error( "write error" ); + } + if( pos >= buffer_size ) { partial_data_pos += pos; pos = 0; } + else member_finished = true; + } + } + + +bool LZ_decoder::verify_trailer( const Pretty_print & pp ) const + { + bool error = false; + File_trailer trailer; + const int trailer_size = trailer.size( format_version ); + for( int i = 0; i < trailer_size && !error; ++i ) + { + if( range_decoder.finished() ) + { + error = true; + if( verbosity >= 0 ) + { + pp(); + std::fprintf( stderr, "trailer truncated at trailer position %d;" + " some checks may fail.\n", i ); + } + } + ((uint8_t *)&trailer)[i] = range_decoder.read_byte(); + } + if( format_version == 0 ) trailer.member_size( member_position() ); + if( trailer.data_crc() != crc() ) + { + error = true; + if( verbosity >= 0 ) + { + pp(); + std::fprintf( stderr, "crc mismatch; trailer says %08X, data crc is %08X.\n", + trailer.data_crc(), crc() ); + } + } + if( trailer.data_size() != data_position() ) + { + error = true; + if( verbosity >= 0 ) + { + if( trailer.data_size() >= 0 ) + { pp(); + std::fprintf( stderr, "data size mismatch; trailer says %lld, data size is %lld.\n", + trailer.data_size(), data_position() ); } + else pp( "member trailer is corrupt" ); + } + } + if( trailer.member_size() != member_position() ) + { + error = true; + if( verbosity >= 0 ) + { + if( trailer.member_size() >= 0 ) + { pp(); + std::fprintf( stderr, "member size mismatch; trailer says %lld, member size is %lld.\n", + trailer.member_size(), member_position() ); } + else pp( "member trailer is corrupt" ); + } + } + if( !error && verbosity >= 3 ) + std::fprintf( stderr, "data crc %08X, data size %8lld, member size %8lld. ", + trailer.data_crc(), trailer.data_size(), trailer.member_size() ); + return !error; + } + + + // Return value: 0 = OK, 1 = decoder error, 2 = unexpected EOF, + // 3 = trailer error, 4 = unknown marker found. +int LZ_decoder::decode_member( const Pretty_print & pp ) + { + unsigned int rep0 = 0; + unsigned int rep1 = 0; + unsigned int rep2 = 0; + unsigned int rep3 = 0; + State state; + uint8_t prev_byte = 0; + + while( true ) + { + if( range_decoder.finished() ) { flush_data(); return 2; } + const int pos_state = data_position() & pos_state_mask; + if( range_decoder.decode_bit( bm_match[state()][pos_state] ) == 0 ) + { + if( state.is_char() ) + prev_byte = literal_decoder.decode( range_decoder, prev_byte ); + else + prev_byte = literal_decoder.decode_matched( range_decoder, prev_byte, + get_byte( rep0 ) ); + put_byte( prev_byte ); + state.set_char(); + } + else + { + int len; + if( range_decoder.decode_bit( bm_rep[state()] ) == 1 ) + { + len = 0; + if( range_decoder.decode_bit( bm_rep0[state()] ) == 0 ) + { + if( range_decoder.decode_bit( bm_len[state()][pos_state] ) == 0 ) + { len = 1; state.set_short_rep(); } + } + else + { + unsigned int distance; + if( range_decoder.decode_bit( bm_rep1[state()] ) == 0 ) + distance = rep1; + else + { + if( range_decoder.decode_bit( bm_rep2[state()] ) == 0 ) + distance = rep2; + else { distance = rep3; rep3 = rep2; } + rep2 = rep1; + } + rep1 = rep0; + rep0 = distance; + } + if( len == 0 ) + { + len = min_match_len + rep_match_len_decoder.decode( range_decoder, pos_state ); + state.set_rep(); + } + } + else + { + rep3 = rep2; rep2 = rep1; rep1 = rep0; + len = min_match_len + len_decoder.decode( range_decoder, pos_state ); + state.set_match(); + const int dis_slot = range_decoder.decode_tree( bm_dis_slot[get_dis_state(len)], dis_slot_bits ); + if( dis_slot < start_dis_model ) rep0 = dis_slot; + else + { + const int direct_bits = ( dis_slot >> 1 ) - 1; + rep0 = ( 2 | ( dis_slot & 1 ) ) << direct_bits; + if( dis_slot < end_dis_model ) + rep0 += range_decoder.decode_tree_reversed( bm_dis + rep0 - dis_slot, direct_bits ); + else + { + rep0 += range_decoder.decode( direct_bits - dis_align_bits ) << dis_align_bits; + rep0 += range_decoder.decode_tree_reversed( bm_align, dis_align_bits ); + if( rep0 == 0xFFFFFFFF ) // Marker found + { + if( len == min_match_len ) // End Of Stream marker + { + flush_data(); + if( verify_trailer( pp ) ) return 0; else return 3; + } + if( verbosity >= 0 ) + { + pp(); + std::fprintf( stderr, "unsupported marker code `%d'.\n", len ); + } + flush_data(); + return 4; + } + } + } + } + if( !copy_block( rep0, len ) ) { flush_data(); return 1; } + prev_byte = get_byte( 0 ); + } + } + } diff --git a/decoder.h b/decoder.h new file mode 100644 index 0000000..ab921dd --- /dev/null +++ b/decoder.h @@ -0,0 +1,272 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +class Input_buffer + { + enum { buffer_size = 65536 }; + + uint8_t * const buffer; + int pos; + int stream_pos; // when reached, a new block must be read + const int ides_; + bool at_stream_end; + + bool read_block(); + +public: + Input_buffer( const int ides ) + : + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + stream_pos( 0 ), + ides_( ides ), + at_stream_end( false ) {} + + ~Input_buffer() { delete[] buffer; } + + bool finished() const throw() { return at_stream_end && pos >= stream_pos; } + + uint8_t read_byte() + { + if( pos >= stream_pos && !read_block() ) return 0; + return buffer[pos++]; + } + }; + + +class Range_decoder + { + mutable long long member_pos; + uint32_t code; + uint32_t range; + Input_buffer & ibuf; + +public: + Range_decoder( const int header_size, Input_buffer & buf ) + : + member_pos( header_size ), + code( 0 ), + range( 0xFFFFFFFF ), + ibuf( buf ) + { for( int i = 0; i < 5; ++i ) code = (code << 8) | read_byte(); } + + uint8_t read_byte() const + { + ++member_pos; + return ibuf.read_byte(); + } + + long long member_position() const throw() { return member_pos; } + bool finished() const throw() { return ibuf.finished(); } + + int decode( const int num_bits ) + { + int symbol = 0; + for( int i = num_bits - 1; i >= 0; --i ) + { + range >>= 1; + symbol <<= 1; + if( code >= range ) + { code -= range; symbol |= 1; } + if( range <= 0x00FFFFFF ) + { range <<= 8; code = (code << 8) | read_byte(); } + } + return symbol; + } + + int decode_bit( Bit_model & bm ) + { + int symbol; + const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability; + if( code < bound ) + { + range = bound; + bm.probability += (bit_model_total - bm.probability) >> bit_model_move_bits; + symbol = 0; + } + else + { + range -= bound; + code -= bound; + bm.probability -= bm.probability >> bit_model_move_bits; + symbol = 1; + } + if( range <= 0x00FFFFFF ) + { range <<= 8; code = (code << 8) | read_byte(); } + return symbol; + } + + int decode_tree( Bit_model bm[], const int num_bits ) + { + int model = 1; + for( int i = num_bits; i > 0; --i ) + model = ( model << 1 ) | decode_bit( bm[model-1] ); + return model - (1 << num_bits); + } + + int decode_tree_reversed( Bit_model bm[], const int num_bits ) + { + int model = 1; + int symbol = 0; + for( int i = 1; i < (1 << num_bits); i <<= 1 ) + { + const int bit = decode_bit( bm[model-1] ); + model = ( model << 1 ) | bit; + if( bit ) symbol |= i; + } + return symbol; + } + + int decode_matched( Bit_model bm[], const int match_byte ) + { + int symbol = 1; + for( int i = 7; i >= 0; --i ) + { + const int match_bit = ( match_byte >> i ) & 1; + const int bit = decode_bit( bm[(match_bit<<8)+symbol+0xFF] ); + symbol = ( symbol << 1 ) | bit; + if( match_bit != bit ) break; + } + while( symbol < 0x100 ) + symbol = ( symbol << 1 ) | decode_bit( bm[symbol-1] ); + return symbol & 0xFF; + } + }; + + +class Len_decoder + { + Bit_model choice1; + Bit_model choice2; + Bit_model bm_low[pos_states][len_low_symbols]; + Bit_model bm_mid[pos_states][len_mid_symbols]; + Bit_model bm_high[len_high_symbols]; + +public: + int decode( Range_decoder & range_decoder, const int pos_state ) + { + if( range_decoder.decode_bit( choice1 ) == 0 ) + return range_decoder.decode_tree( bm_low[pos_state], len_low_bits ); + if( range_decoder.decode_bit( choice2 ) == 0 ) + return len_low_symbols + + range_decoder.decode_tree( bm_mid[pos_state], len_mid_bits ); + return len_low_symbols + len_mid_symbols + + range_decoder.decode_tree( bm_high, len_high_bits ); + } + }; + + +class Literal_decoder + { + Bit_model bm_literal[1<> ( 8 - literal_context_bits ) ); } + +public: + uint8_t decode( Range_decoder & range_decoder, const int prev_byte ) + { return range_decoder.decode_tree( bm_literal[state(prev_byte)], 8 ); } + + uint8_t decode_matched( Range_decoder & range_decoder, + const int prev_byte, const int match_byte ) + { return range_decoder.decode_matched( bm_literal[state(prev_byte)], match_byte ); } + }; + + +class LZ_decoder + { + long long partial_data_pos; + const int format_version; + const int buffer_size; + uint8_t * const buffer; + int pos; + uint32_t crc_; + const int odes_; + bool member_finished; + + Bit_model bm_match[State::states][pos_states]; + Bit_model bm_rep[State::states]; + Bit_model bm_rep0[State::states]; + Bit_model bm_rep1[State::states]; + Bit_model bm_rep2[State::states]; + Bit_model bm_len[State::states][pos_states]; + Bit_model bm_dis_slot[max_dis_states][1<= buffer_size ) flush_data(); + } + + bool copy_block( const int distance, int len ) + { + if( distance < 0 || distance >= buffer_size || + len <= 0 || len > max_match_len ) return false; + int newpos = pos - distance - 1; + if( newpos < 0 ) newpos += buffer_size; + for( ; len > 0 ; --len ) + { + crc32.update( crc_, buffer[newpos] ); + buffer[pos] = buffer[newpos]; + if( ++pos >= buffer_size ) flush_data(); + if( ++newpos >= buffer_size ) newpos = 0; + } + return true; + } + + void flush_data(); + bool verify_trailer( const Pretty_print & pp ) const; + +public: + LZ_decoder( const File_header & header, Input_buffer & ibuf, const int odes ) + : + partial_data_pos( 0 ), + format_version( header.version ), + buffer_size( header.dictionary_size() ), + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + crc_( 0xFFFFFFFF ), + odes_( odes ), + member_finished( false ), + range_decoder( sizeof header, ibuf ), + literal_decoder() {} + + ~LZ_decoder() { delete[] buffer; } + + uint32_t crc() const throw() { return crc_ ^ 0xFFFFFFFF; } + int decode_member( const Pretty_print & pp ); + + long long member_position() const throw() + { return range_decoder.member_position(); } + long long data_position() const throw() + { return partial_data_pos + pos; } + }; diff --git a/doc/lzip.1 b/doc/lzip.1 new file mode 100644 index 0000000..a1a7591 --- /dev/null +++ b/doc/lzip.1 @@ -0,0 +1,87 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.36. +.TH LZIP "1" "April 2009" "Lzip 1.6-pre1" "User Commands" +.SH NAME +Lzip \- manual page for Lzip 1.6-pre1 +.SH SYNOPSIS +.B lzip +[\fIoptions\fR] [\fIfiles\fR] +.SH DESCRIPTION +Lzip \- 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, lzip 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 +Lzip home page: http://www.nongnu.org/lzip/lzip.html +.SH COPYRIGHT +Copyright \(co 2009 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 Lzip +is maintained as a Texinfo manual. If the +.B info +and +.B Lzip +programs are properly installed at your site, the command +.IP +.B info Lzip +.PP +should give you access to the complete manual. diff --git a/doc/lzip.info b/doc/lzip.info new file mode 100644 index 0000000..d40f84f --- /dev/null +++ b/doc/lzip.info @@ -0,0 +1,572 @@ +This is lzip.info, produced by makeinfo version 4.13 from lzip.texinfo. + +INFO-DIR-SECTION Data Compression +START-INFO-DIR-ENTRY +* Lzip: (lzip). Data compressor based on the LZMA algorithm +END-INFO-DIR-ENTRY + + +File: lzip.info, Node: Top, Next: Introduction, Up: (dir) + +Lzip +**** + +This manual is for Lzip (version 1.6-pre1, 27 April 2009). + +* Menu: + +* Introduction:: Purpose and features of lzip +* Algorithm:: How lzip compresses the data +* Invoking Lzip:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Lzdiff:: Comparing compressed files +* Lzgrep:: Searching inside compressed files +* Lziprecover:: Recovering data from damaged compressed files +* Problems:: Reporting bugs +* Concept Index:: Index of concepts + + + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This manual is free documentation: you have unlimited permission to +copy, distribute and modify it. + + +File: lzip.info, Node: Introduction, Next: Algorithm, Prev: Top, Up: Top + +1 Introduction +************** + +Lzip 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. Lzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + + Lzip 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. Lzip is able to read from some +types of non regular files if the `--stdout' option is specified. + + If no file names are specified, lzip compresses (or decompresses) +from standard input to standard output. In this case, lzip will decline +to write compressed output to a terminal, as this would be entirely +incomprehensible and therefore pointless. + + Lzip 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. + + Lzip can produce multimember files and safely recover, with +lziprecover, the undamaged members in case of file damage. Lzip 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 2 times the +dictionary size limit plus 8 times the dictionary size really used. For +decompression is a little more than the dictionary size really used. +Lzip will automatically use the smallest possible dictionary size for +each member 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, lzip 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, lzip 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 lzip (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 lzip to panic. + + +File: lzip.info, Node: Algorithm, Next: Invoking Lzip, Prev: Introduction, Up: Top + +2 Algorithm +*********** + +Lzip 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. + + Lzip 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 lzip'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: lzip.info, Node: Invoking Lzip, Next: File Format, Prev: Algorithm, Up: Top + +3 Invoking Lzip +*************** + +The format for running lzip is: + + lzip [OPTIONS] [FILES] + + Lzip supports the following options: + +`--help' +`-h' + Print an informative help message describing the options and exit. + +`--version' +`-V' + Print the version number of lzip 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. Lzip 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 4MiB 10 bytes + -2 4MiB 12 bytes + -3 4MiB 17 bytes + -4 4MiB 26 bytes + -5 4MiB 44 bytes + -6 8MiB 80 bytes + -7 16MiB 108 bytes + -8 16MiB 163 bytes + -9 32MiB 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: lzip.info, Node: File Format, Next: Examples, Prev: Invoking Lzip, 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: lzip.info, Node: Examples, Next: Lzdiff, Prev: File Format, Up: Top + +5 A small tutorial with examples +******************************** + +WARNING! If your data is important, give the `--keep' option to lzip +and do not remove the original file until you verify the compressed +file with a command like `lzip -cd file.lz | cmp file -'. + + +Example 1: Replace a regular file with its compressed version file.lz +and show the compression ratio. + + lzip -v file + + +Example 2: Like example 1 but the created file.lz is multimember with a +member size of 1MiB. + + lzip -b 1MiB file + + +Example 3: Compress a whole floppy in /dev/fd0 and send the output to +file.lz. + + lzip -c /dev/fd0 > file.lz + + +Example 4: Create a multivolume compressed tar archive with a volume +size of 1440KiB. + + tar -c some_directory | lzip -S 1440KiB -o volume_name + + +Example 5: Extract a multivolume compressed tar archive. + + lzip -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. + + lzip -b 32MiB -S 650MB big_database + + +Example 7: Recover the first volume of those created in example 6 from +two copies, `big_database1_00001.lz' and `big_database2_00001.lz', with +member 00007 damaged in the first copy and member 00018 damaged in the +second copy. (Indented lines are lzip error messages). + + lziprecover big_database1_00001.lz + lziprecover big_database2_00001.lz + lzip -t rec*big_database1_00001.lz + rec00007big_database1_00001.lz: crc mismatch + lzip -t rec*big_database2_00001.lz + rec00018big_database1_00001.lz: crc mismatch + cp rec00007big_database2_00001.lz rec00007big_database1_00001.lz + cat rec*big_database1_00001.lz > big_database3_00001.lz + + +File: lzip.info, Node: Lzdiff, Next: Lzgrep, Prev: Examples, Up: Top + +6 Lzdiff +******** + +Lzdiff is a wrapper script around the diff and cmp commands that allows +transparent comparison of any combination of compressed and +non-compressed files. If any given file is compressed, its uncompressed +content is used. The supported compressors are gzip, bzip2 and lzip. + + The format for running lzdiff is: + + lzdiff [OPTIONS] [DIFF_OPTIONS] FILE1 [FILE2] + +Compares FILE1 to FILE2. If FILE2 is omitted, compares FILE1 to the +uncompressed contents of FILE1.[gz|bz2|lz] (depending on the default +compressor selected). DIFF_OPTIONS are passed directly to diff or cmp. +The exit status from diff or cmp is preserved. + + Lzdiff supports the following options: + +`--help' +`-h' + Print an informative help message describing the options and exit. + +`--version' +`-V' + Print the version number of lzdiff on the standard output and exit. + +`--gzip' + Use gzip as default decompressor. + +`--bzip2' + Use bzip2 as default decompressor. + +`--lzip' + Use lzip as default decompressor (default). + +`--diff' + Use diff to compare files (default). + +`--cmp' + Use cmp to compare files. + + + Lzdiff has the limitation that messages from the diff or cmp programs +refer to temporary filenames instead of those specified. + + +File: lzip.info, Node: Lzgrep, Next: Lziprecover, Prev: Lzdiff, Up: Top + +7 Lzgrep +******** + +Lzgrep is a wrapper script around the grep command that allows +transparent search on any combination of compressed and non-compressed +files. If any given file is compressed, its uncompressed content is +used. If a given file does not exist, lzgrep tries the compressed file +name corresponding to the default compressor selected. The supported +compressors are gzip, bzip2 and lzip. + + The format for running lzgrep is: + + lzgrep [OPTIONS] [GREP_OPTIONS] PATTERN [FILES] + +GREP_OPTIONS are passed directly to grep. The exit status from grep is +preserved. + + Lzgrep supports the following options: + +`--help' +`-h' + Print an informative help message describing the options and exit. + +`--version' +`-V' + Print the version number of lzgrep on the standard output and exit. + +`--gzip' + Use gzip as default decompressor. + +`--bzip2' + Use bzip2 as default decompressor. + +`--lzip' + Use lzip as default decompressor (default). + + + +File: lzip.info, Node: Lziprecover, Next: Problems, Prev: Lzgrep, Up: Top + +8 Lziprecover +************* + +Lziprecover is a program that searches for members in .lz files, and +writes each member in its own .lz file. You can then use `lzip -t' to +test the integrity of the resulting files, and decompress those which +are undamaged. + + Lziprecover takes a single argument, the name of the damaged file, +and writes a number of files `rec00001file.lz', `rec00002file.lz', etc, +containing the extracted members. The output filenames are designed so +that the use of wildcards in subsequent processing, for example, +`lzip -dc rec*file.lz > recovered_data', processes the files in the +correct order. + + +File: lzip.info, Node: Problems, Next: Concept Index, Prev: Lziprecover, Up: Top + +9 Reporting Bugs +**************** + +There are probably bugs in lzip. 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 lzip, please send electronic mail to +. Include the version number, which you can find +by running `lzip --version'. + + +File: lzip.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 Lzip. (line 6) +* lzdiff: Lzdiff. (line 6) +* lzgrep: Lzgrep. (line 6) +* lziprecover: Lziprecover. (line 6) +* options: Invoking Lzip. (line 6) +* usage: Invoking Lzip. (line 6) +* version: Invoking Lzip. (line 6) + + + +Tag Table: +Node: Top224 +Node: Introduction967 +Node: Algorithm4208 +Node: Invoking Lzip6434 +Node: File Format10781 +Node: Examples12735 +Node: Lzdiff14568 +Node: Lzgrep15887 +Node: Lziprecover16922 +Node: Problems17619 +Node: Concept Index18144 + +End Tag Table diff --git a/doc/lzip.texinfo b/doc/lzip.texinfo new file mode 100644 index 0000000..f29b29e --- /dev/null +++ b/doc/lzip.texinfo @@ -0,0 +1,598 @@ +\input texinfo @c -*-texinfo-*- +@c %**start of header +@setfilename lzip.info +@settitle Lzip +@finalout +@c %**end of header + +@set UPDATED 27 April 2009 +@set VERSION 1.6-pre1 + +@dircategory Data Compression +@direntry +* Lzip: (lzip). Data compressor based on the LZMA algorithm +@end direntry + + +@titlepage +@title Lzip +@subtitle A data compressor based on the LZMA algorithm +@subtitle for Lzip 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 Lzip (version @value{VERSION}, @value{UPDATED}). + +@menu +* Introduction:: Purpose and features of lzip +* Algorithm:: How lzip compresses the data +* Invoking Lzip:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Lzdiff:: Comparing compressed files +* Lzgrep:: Searching inside compressed files +* Lziprecover:: Recovering data from damaged compressed files +* Problems:: Reporting bugs +* Concept Index:: Index of concepts +@end menu + +@sp 1 +Copyright @copyright{} 2008, 2009 Antonio Diaz Diaz. + +This manual is free documentation: you have unlimited permission +to copy, distribute and modify it. + + +@node Introduction +@chapter Introduction +@cindex introduction + +Lzip 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. Lzip decompresses almost as fast as gzip and compresses +better than bzip2, which makes it well suited for software distribution +and data archiving. + +Lzip 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. Lzip is able to read from some +types of non regular files if the @samp{--stdout} option is specified. + +If no file names are specified, lzip compresses (or decompresses) from +standard input to standard output. In this case, lzip will decline to +write compressed output to a terminal, as this would be entirely +incomprehensible and therefore pointless. + +Lzip 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. + +Lzip can produce multimember files and safely recover, with lziprecover, +the undamaged members in case of file damage. Lzip 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 2 times the +dictionary size limit plus 8 times the dictionary size really used. For +decompression is a little more than the dictionary size really used. +Lzip will automatically use the smallest possible dictionary size for +each member 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, lzip 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, lzip 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 lzip (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 lzip to panic. + + +@node Algorithm +@chapter Algorithm +@cindex algorithm + +Lzip 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. + +Lzip 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 lzip'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 Lzip +@chapter Invoking Lzip +@cindex invoking +@cindex options +@cindex usage +@cindex version + +The format for running lzip is: + +@example +lzip [@var{options}] [@var{files}] +@end example + +Lzip 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 lzip 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. Lzip 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 4MiB @tab 10 bytes +@item -2 @tab 4MiB @tab 12 bytes +@item -3 @tab 4MiB @tab 17 bytes +@item -4 @tab 4MiB @tab 26 bytes +@item -5 @tab 4MiB @tab 44 bytes +@item -6 @tab 8MiB @tab 80 bytes +@item -7 @tab 16MiB @tab 108 bytes +@item -8 @tab 16MiB @tab 163 bytes +@item -9 @tab 32MiB @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 +lzip and do not remove the original file until you verify the compressed +file with a command like @samp{lzip -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 +lzip -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 +lzip -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 +lzip -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 | lzip -S 1440KiB -o volume_name +@end example + +@sp 1 +@noindent +Example 5: Extract a multivolume compressed tar archive. + +@example +lzip -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 +lzip -b 32MiB -S 650MB big_database +@end example + +@sp 1 +@noindent +Example 7: Recover the first volume of those created in example 6 from +two copies, @samp{big_database1_00001.lz} and +@samp{big_database2_00001.lz}, with member 00007 damaged in the first +copy and member 00018 damaged in the second copy. (Indented lines are +lzip error messages). + +@example +lziprecover big_database1_00001.lz +lziprecover big_database2_00001.lz +lzip -t rec*big_database1_00001.lz + rec00007big_database1_00001.lz: crc mismatch +lzip -t rec*big_database2_00001.lz + rec00018big_database1_00001.lz: crc mismatch +cp rec00007big_database2_00001.lz rec00007big_database1_00001.lz +cat rec*big_database1_00001.lz > big_database3_00001.lz +@end example + + +@node Lzdiff +@chapter Lzdiff +@cindex lzdiff + +Lzdiff is a wrapper script around the diff and cmp commands that allows +transparent comparison of any combination of compressed and +non-compressed files. If any given file is compressed, its uncompressed +content is used. The supported compressors are gzip, bzip2 and lzip. + +The format for running lzdiff is: + +@example +lzdiff [@var{options}] [@var{diff_options}] @var{file1} [@var{file2}] +@end example + +@noindent +Compares @var{file1} to @var{file2}. If @var{file2} is omitted, compares +@var{file1} to the uncompressed contents of @var{file1}.[gz|bz2|lz] +(depending on the default compressor selected). @var{diff_options} are +passed directly to diff or cmp. The exit status from diff or cmp is +preserved. + +Lzdiff 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 lzdiff on the standard output and exit. + +@item --gzip +Use gzip as default decompressor. + +@item --bzip2 +Use bzip2 as default decompressor. + +@item --lzip +Use lzip as default decompressor (default). + +@item --diff +Use diff to compare files (default). + +@item --cmp +Use cmp to compare files. + +@end table + +Lzdiff has the limitation that messages from the diff or cmp programs +refer to temporary filenames instead of those specified. + + +@node Lzgrep +@chapter Lzgrep +@cindex lzgrep + +Lzgrep is a wrapper script around the grep command that allows +transparent search on any combination of compressed and non-compressed +files. If any given file is compressed, its uncompressed content is +used. If a given file does not exist, lzgrep tries the compressed file +name corresponding to the default compressor selected. The supported +compressors are gzip, bzip2 and lzip. + +The format for running lzgrep is: + +@example +lzgrep [@var{options}] [@var{grep_options}] @var{pattern} [@var{files}] +@end example + +@noindent +@var{grep_options} are passed directly to grep. The exit status from +grep is preserved. + +Lzgrep 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 lzgrep on the standard output and exit. + +@item --gzip +Use gzip as default decompressor. + +@item --bzip2 +Use bzip2 as default decompressor. + +@item --lzip +Use lzip as default decompressor (default). + +@end table + + +@node Lziprecover +@chapter Lziprecover +@cindex lziprecover + +Lziprecover is a program that searches for members in .lz files, and +writes each member in its own .lz file. You can then use +@w{@samp{lzip -t}} to test the integrity of the resulting files, and +decompress those which are undamaged. + +Lziprecover takes a single argument, the name of the damaged file, and +writes a number of files @samp{rec00001file.lz}, @samp{rec00002file.lz}, +etc, containing the extracted members. The output filenames are designed +so that the use of wildcards in subsequent processing, for example, +@w{@samp{lzip -dc rec*file.lz > recovered_data}}, processes the files in +the correct order. + + +@node Problems +@chapter Reporting Bugs +@cindex bugs +@cindex getting help + +There are probably bugs in lzip. 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 lzip, please send electronic mail to +@email{lzip-bug@@nongnu.org}. Include the version number, which you can +find by running @w{@samp{lzip --version}}. + + +@node Concept Index +@unnumbered Concept Index + +@printindex cp + +@bye diff --git a/encoder.cc b/encoder.cc new file mode 100644 index 0000000..f1a033b --- /dev/null +++ b/encoder.cc @@ -0,0 +1,554 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include +#include + +#include "lzip.h" +#include "encoder.h" + + +Dis_slots dis_slots; +Prob_prices prob_prices; + + +bool Matchfinder::read_block() throw() + { + const int size = buffer_size - stream_pos; + const int rd = readblock( ides_, (char *)buffer + stream_pos, size ); + stream_pos += rd; + if( rd < size ) at_stream_end = true; + return ( rd == size || !errno ); + } + + +bool Matchfinder::reset() throw() + { + const int size = stream_pos - pos; + std::memmove( buffer, buffer + pos, size ); + partial_data_pos = 0; + stream_pos -= pos; + pos = 0; + cyclic_pos = 0; + for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = -1; + return ( at_stream_end || read_block() ); + } + + +bool Matchfinder::move_pos() throw() + { + if( ++cyclic_pos >= dictionary_size_ ) cyclic_pos = 0; + if( ++pos >= pos_limit ) + { + if( !at_stream_end ) + { + const int offset = pos - dictionary_size_ - max_num_trials; + const int size = stream_pos - offset; + std::memmove( buffer, buffer + offset, size ); + partial_data_pos += offset; + pos -= offset; + stream_pos -= offset; + for( int i = 0; i < num_prev_positions; ++i ) + if( prev_positions[i] >= 0 ) prev_positions[i] -= offset; + for( int i = 0; i < 2 * dictionary_size_; ++i ) + if( prev_pos_tree[i] >= 0 ) prev_pos_tree[i] -= offset; + return read_block(); + } + else if( pos > stream_pos ) { pos = stream_pos; return false; } + } + return true; + } + + +int Matchfinder::longest_match_len( int * const distances ) throw() + { + int len_limit = match_len_limit_; + if( len_limit > available_bytes() ) + { + len_limit = available_bytes(); + if( len_limit < 4 ) return 0; + } + + int maxlen = min_match_len - 1; + const int min_pos = (pos >= dictionary_size_) ? + (pos - dictionary_size_ + 1) : 0; + const uint8_t * const data = buffer + pos; + const int key2 = num_prev_positions4 + num_prev_positions3 + + ( ( (int)data[0] << 8 ) | data[1] ); + const int tmp = crc32[data[0]] ^ data[1] ^ ( (int)data[2] << 8 ); + const int key3 = num_prev_positions4 + ( tmp & ( num_prev_positions3 - 1 ) ); + const int key4 = ( tmp ^ ( crc32[data[3]] << 5 ) ) & + ( num_prev_positions4 - 1 ); + + if( distances ) + { + int np = prev_positions[key2]; + if( np >= min_pos ) + { distances[2] = pos - np - 1; maxlen = 2; } + else distances[2] = 0x7FFFFFFF; + np = prev_positions[key3]; + if( np >= min_pos && buffer[np] == data[0] ) + { distances[3] = pos - np - 1; maxlen = 3; } + else distances[3] = 0x7FFFFFFF; + distances[4] = 0x7FFFFFFF; + } + + prev_positions[key2] = pos; + prev_positions[key3] = pos; + int newpos = prev_positions[key4]; + prev_positions[key4] = pos; + + int idx0 = cyclic_pos << 1; + int idx1 = idx0 + 1; + int len0 = 0, len1 = 0; + + for( int count = 16 + ( match_len_limit_ / 2 ); ; ) + { + if( newpos < min_pos || --count < 0 ) + { prev_pos_tree[idx0] = prev_pos_tree[idx1] = -1; break; } + const uint8_t * const newdata = buffer + newpos; + int len = std::min( len0, len1 ); + while( len < len_limit && newdata[len] == data[len] ) ++len; + + const int delta = pos - newpos; + if( distances ) while( maxlen < len ) distances[++maxlen] = delta - 1; + + const int newidx = ( cyclic_pos - delta + + ( ( cyclic_pos >= delta ) ? 0 : dictionary_size_ ) ) << 1; + + if( len < len_limit ) + { + if( newdata[len] < data[len] ) + { + prev_pos_tree[idx0] = newpos; + idx0 = newidx + 1; + newpos = prev_pos_tree[idx0]; + len0 = len; + } + else + { + prev_pos_tree[idx1] = newpos; + idx1 = newidx; + newpos = prev_pos_tree[idx1]; + len1 = len; + } + } + else + { + prev_pos_tree[idx0] = prev_pos_tree[newidx]; + prev_pos_tree[idx1] = prev_pos_tree[newidx+1]; + break; + } + } + if( distances ) + { + if( distances[3] > distances[4] ) distances[3] = distances[4]; + if( distances[2] > distances[3] ) distances[2] = distances[3]; + } + return maxlen; + } + + +void Len_encoder::encode( Range_encoder & range_encoder, int symbol, + const int pos_state ) + { + symbol -= min_match_len; + if( symbol < len_low_symbols ) + { + range_encoder.encode_bit( choice1, 0 ); + range_encoder.encode_tree( bm_low[pos_state], symbol, len_low_bits ); + } + else + { + range_encoder.encode_bit( choice1, 1 ); + if( symbol < len_low_symbols + len_mid_symbols ) + { + range_encoder.encode_bit( choice2, 0 ); + range_encoder.encode_tree( bm_mid[pos_state], symbol - len_low_symbols, len_mid_bits ); + } + else + { + range_encoder.encode_bit( choice2, 1 ); + range_encoder.encode_tree( bm_high, symbol - len_low_symbols - len_mid_symbols, len_high_bits ); + } + } + if( --counters[pos_state] <= 0 ) update_prices( pos_state ); + } + + +void LZ_encoder::fill_align_prices() throw() + { + for( int i = 0; i < dis_align_size; ++i ) + align_prices[i] = price_symbol_reversed( bm_align, i, dis_align_bits ); + align_price_count = dis_align_size; + } + + +void LZ_encoder::fill_distance_prices() throw() + { + for( int dis_state = 0; dis_state < max_dis_states; ++dis_state ) + { + int * dsp = dis_slot_prices[dis_state]; + const Bit_model * bmds = bm_dis_slot[dis_state]; + int slot = 0; + for( ; slot < end_dis_model && slot < num_dis_slots; ++slot ) + dsp[slot] = price_symbol( bmds, slot, dis_slot_bits ); + for( ; slot < num_dis_slots; ++slot ) + dsp[slot] = price_symbol( bmds, slot, dis_slot_bits ) + + (((( slot >> 1 ) - 1 ) - dis_align_bits ) << price_shift ); + + int * dp = dis_prices[dis_state]; + int dis = 0; + for( ; dis < start_dis_model; ++dis ) + dp[dis] = dsp[dis]; + for( ; dis < modeled_distances; ++dis ) + { + const int dis_slot = dis_slots[dis]; + const int direct_bits = ( dis_slot >> 1 ) - 1; + const int base = ( 2 | ( dis_slot & 1 ) ) << direct_bits; + dp[dis] = dsp[dis_slot] + + price_symbol_reversed( bm_dis + base - dis_slot, dis - base, direct_bits ); + } + } + } + + +// Return value: ( dis == -1 ) && ( len == 1 ) means literal +int LZ_encoder::best_pair_sequence( const int reps[num_rep_distances], + const State & state ) + { + int main_len; + if( longest_match_found > 0 ) // from previous call + { + main_len = longest_match_found; + longest_match_found = 0; + } + else main_len = read_match_distances(); + + int replens[num_rep_distances]; + int rep_index = 0; + for( int i = 0; i < num_rep_distances; ++i ) + { + replens[i] = matchfinder.true_match_len( 0, reps[i] + 1, max_match_len ); + if( replens[i] > replens[rep_index] ) rep_index = i; + } + if( replens[rep_index] >= matchfinder.match_len_limit() ) + { + trials[0].dis = rep_index; + trials[0].price = replens[rep_index]; + if( !move_pos( replens[rep_index], true ) ) return 0; + return replens[rep_index]; + } + + if( main_len >= matchfinder.match_len_limit() ) + { + trials[0].dis = match_distances[matchfinder.match_len_limit()] + + num_rep_distances; + trials[0].price = main_len; + if( !move_pos( main_len, true ) ) return 0; + return main_len; + } + + trials[0].state = state; + for( int i = 0; i < num_rep_distances; ++i ) trials[0].reps[i] = reps[i]; + + const uint8_t cur_byte = matchfinder[0]; + const uint8_t match_byte = matchfinder[-reps[0]-1]; + unsigned int position = matchfinder.data_position(); + const int pos_state = position & pos_state_mask; + + trials[1].dis = -1; + trials[1].prev_index = 0; + trials[1].price = price0( bm_match[state()][pos_state] ); + if( state.is_char() ) + trials[1].price += literal_encoder.price_symbol( matchfinder[-1], cur_byte ); + else + trials[1].price += literal_encoder.price_matched( matchfinder[-1], cur_byte, match_byte ); + + const int match_price = price1( bm_match[state()][pos_state] ); + const int rep_match_price = match_price + price1( bm_rep[state()] ); + + if( match_byte == cur_byte ) + trials[1].update( 0, 0, rep_match_price + price_rep_len1( state, pos_state ) ); + + if( main_len < min_match_len ) + { + trials[0].dis = trials[1].dis; + trials[0].price = 1; + if( !matchfinder.move_pos() ) return 0; + return 1; + } + + { + const int normal_match_price = match_price + price0( bm_rep[state()] ); + int len = min_match_len; + if( main_len <= replens[rep_index] ) + { + main_len = replens[rep_index]; + for( ; len <= main_len; ++len ) trials[len].price = infinite_price; + } + else for( ; len <= main_len; ++len ) + { + trials[len].dis = match_distances[len] + num_rep_distances; + trials[len].prev_index = 0; + trials[len].price = normal_match_price + + price_pair( match_distances[len], len, pos_state ); + } + } + + for( int rep = 0; rep < num_rep_distances; ++rep ) + for( int len = min_match_len; len <= replens[rep]; ++len ) + trials[len].update( rep, 0, rep_match_price + + price_rep( rep, len, state, pos_state ) ); + + int cur = 0; + int num_trials = main_len; + if( !matchfinder.move_pos() ) return 0; + + while( true ) + { + if( ++cur >= num_trials ) + { + backward( cur ); + return cur; + } + const int newlen = read_match_distances(); + if( newlen >= matchfinder.match_len_limit() ) + { + longest_match_found = newlen; + backward( cur ); + return cur; + } + + Trial & cur_trial = trials[cur]; + const int prev_index = cur_trial.prev_index; + + cur_trial.state = trials[prev_index].state; + + for( int i = 0; i < num_rep_distances; ++i ) + cur_trial.reps[i] = trials[prev_index].reps[i]; + if( prev_index == cur - 1 ) + { + if( cur_trial.dis == 0 ) cur_trial.state.set_short_rep(); + else cur_trial.state.set_char(); + } + else + { + if( cur_trial.dis < num_rep_distances ) cur_trial.state.set_rep(); + else cur_trial.state.set_match(); + mtf_reps( cur_trial.dis, cur_trial.reps ); + } + + const uint8_t cur_byte = matchfinder[0]; + const uint8_t match_byte = matchfinder[-cur_trial.reps[0]-1]; + const int pos_state = ++position & pos_state_mask; + int next_price = cur_trial.price + price0( bm_match[cur_trial.state()][pos_state] ); + if( cur_trial.state.is_char() ) + next_price += literal_encoder.price_symbol( matchfinder[-1], cur_byte ); + else + next_price += literal_encoder.price_matched( matchfinder[-1], cur_byte, match_byte ); + if( !matchfinder.move_pos() ) return 0; + + Trial & next_trial = trials[cur+1]; + + next_trial.update( -1, cur, next_price ); + + const int match_price = cur_trial.price + price1( bm_match[cur_trial.state()][pos_state] ); + const int rep_match_price = match_price + price1( bm_rep[cur_trial.state()] ); + + if( match_byte == cur_byte && next_trial.dis != 0 ) + next_trial.update( 0, cur, rep_match_price + + price_rep_len1( cur_trial.state, pos_state ) ); + + const int len_limit = std::min( std::min( max_num_trials - 1 - cur, + matchfinder.available_bytes() ), matchfinder.match_len_limit() ); + if( len_limit < min_match_len ) continue; + + for( int rep = 0; rep < num_rep_distances; ++rep ) + { + const int dis = cur_trial.reps[rep] + 1; + int len = 0; + const uint8_t * const data = matchfinder.ptr_to_current_pos() - 1; + while( len < len_limit && data[len] == data[len-dis] ) ++len; + if( len >= min_match_len ) + { + while( num_trials < cur + len ) + trials[++num_trials].price = infinite_price; + for( ; len >= min_match_len; --len ) + trials[cur+len].update( rep, cur, rep_match_price + + price_rep( rep, len, cur_trial.state, pos_state ) ); + } + } + + if( newlen <= len_limit && + ( newlen > min_match_len || + ( newlen == min_match_len && + match_distances[newlen] < modeled_distances ) ) ) + { + const int normal_match_price = match_price + + price0( bm_rep[cur_trial.state()] ); + while( num_trials < cur + newlen ) + trials[++num_trials].price = infinite_price; + + for( int len = newlen; len >= min_match_len; --len ) + trials[cur+len].update( match_distances[len] + num_rep_distances, cur, + normal_match_price + + price_pair( match_distances[len], len, pos_state ) ); + } + } + } + + + // End Of Stream mark => (dis == 0xFFFFFFFF, len == min_match_len) +void LZ_encoder::flush( const State & state ) + { + const int pos_state = ( matchfinder.data_position() ) & pos_state_mask; + range_encoder.encode_bit( bm_match[state()][pos_state], 1 ); + range_encoder.encode_bit( bm_rep[state()], 0 ); + encode_pair( 0xFFFFFFFF, min_match_len, pos_state ); + range_encoder.flush(); + File_trailer trailer; + trailer.data_crc( crc() ); + trailer.data_size( matchfinder.data_position() ); + trailer.member_size( range_encoder.member_position() + sizeof trailer ); + for( unsigned int i = 0; i < sizeof trailer; ++i ) + range_encoder.put_byte( (( uint8_t *)&trailer)[i] ); + range_encoder.flush_data(); + } + + +LZ_encoder::LZ_encoder( Matchfinder & mf, const File_header & header, + const int odes ) + : + longest_match_found( 0 ), + crc_( 0xFFFFFFFF ), + matchfinder( mf ), + range_encoder( odes ), + len_encoder( matchfinder.match_len_limit() ), + rep_match_len_encoder( matchfinder.match_len_limit() ), + literal_encoder(), + num_dis_slots( 2 * File_header::real_bits( matchfinder.dictionary_size() - 1 ) ) + { + fill_align_prices(); + + for( unsigned int i = 0; i < sizeof header; ++i ) + range_encoder.put_byte( (( uint8_t *)&header)[i] ); + } + + +bool LZ_encoder::encode_member( const long long member_size ) + { + if( range_encoder.member_position() != sizeof( File_header ) ) + return false; // can be called only once + const long long member_size_limit = member_size - sizeof( File_trailer ) - 15; + int fill_counter = 0; + int rep_distances[num_rep_distances]; + State state; + uint8_t prev_byte = 0; + for( int i = 0; i < num_rep_distances; ++i ) rep_distances[i] = 0; + + if( !matchfinder.finished() ) // copy first byte + { + range_encoder.encode_bit( bm_match[state()][0], 0 ); + const uint8_t cur_byte = matchfinder[0]; + literal_encoder.encode( range_encoder, prev_byte, cur_byte ); + prev_byte = cur_byte; + crc32.update( crc_, cur_byte ); + if( !move_pos( 1 ) ) return false; + } + + while( true ) + { + if( matchfinder.finished() ) { flush( state ); return true; } + if( fill_counter <= 0 ) { fill_distance_prices(); fill_counter = 512; } + + int ahead = best_pair_sequence( rep_distances, state ); + if( ahead <= 0 ) return false; + fill_counter -= ahead; + + for( int i = 0; ; ) + { + const int pos_state = ( matchfinder.data_position() - ahead ) & pos_state_mask; + int dis = trials[i].dis; + const int len = trials[i].price; + + bool bit = ( dis < 0 && len == 1 ); + range_encoder.encode_bit( bm_match[state()][pos_state], !bit ); + if( bit ) + { + const uint8_t cur_byte = matchfinder[-ahead]; + if( state.is_char() ) + literal_encoder.encode( range_encoder, prev_byte, cur_byte ); + else + { + const uint8_t match_byte = matchfinder[-rep_distances[0]-1-ahead]; + literal_encoder.encode_matched( range_encoder, prev_byte, match_byte, cur_byte ); + } + state.set_char(); + prev_byte = cur_byte; + } + else + { + mtf_reps( dis, rep_distances ); + bit = ( dis < num_rep_distances ); + range_encoder.encode_bit( bm_rep[state()], bit ); + if( bit ) + { + bit = ( dis == 0 ); + range_encoder.encode_bit( bm_rep0[state()], !bit ); + if( bit ) + range_encoder.encode_bit( bm_len[state()][pos_state], len > 1 ); + else + { + range_encoder.encode_bit( bm_rep1[state()], dis > 1 ); + if( dis > 1 ) + range_encoder.encode_bit( bm_rep2[state()], dis > 2 ); + } + if( len == 1 ) state.set_short_rep(); + else + { + rep_match_len_encoder.encode( range_encoder, len, pos_state ); + state.set_rep(); + } + } + else + { + encode_pair( dis - num_rep_distances, len, pos_state ); + state.set_match(); + } + prev_byte = matchfinder[len-1-ahead]; + } + for( int j = 0; j < len; ++j ) + crc32.update( crc_, matchfinder[j-ahead] ); + ahead -= len; i += len; + if( range_encoder.member_position() >= member_size_limit ) + { + if( !matchfinder.dec_pos( ahead ) ) return false; + flush( state ); + return true; + } + if( ahead <= 0 ) break; + } + } + } diff --git a/encoder.h b/encoder.h new file mode 100644 index 0000000..59cebb8 --- /dev/null +++ b/encoder.h @@ -0,0 +1,604 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +const int max_num_trials = 1 << 12; +const int price_shift = 6; + +class Dis_slots + { + unsigned char data[1<<12]; + +public: + void init() throw() + { + for( int slot = 0; slot < 4; ++slot ) data[slot] = slot; + for( int i = 4, size = 2, slot = 4; slot < 24; slot += 2 ) + { + std::memset( &data[i], slot, size ); + std::memset( &data[i+size], slot + 1, size ); + size <<= 1; + i += size; + } + } + + int operator[]( const uint32_t dis ) const throw() + { + if( dis < (1 << 12) ) return data[dis]; + if( dis < (1 << 23) ) return data[dis>>11] + 22; + return data[dis>>22] + 44; + } + }; + +extern Dis_slots dis_slots; + +class Prob_prices + { + int data[bit_model_total >> 2]; + +public: + void init() throw() + { + const int num_bits = ( bit_model_total_bits - 2 ); + for( int i = num_bits - 1; i >= 0; --i ) + { + int start = 1 << ( num_bits - i - 1 ); + int end = 1 << ( num_bits - i); + for( int j = start; j < end; ++j ) + data[j] = (i << price_shift) + + ( ((end - j) << price_shift) >> (num_bits - i - 1) ); + } + } + + int operator[]( const int symbol ) const throw() + { return data[symbol >> 2]; } + }; + +extern Prob_prices prob_prices; + +inline int price0( const Bit_model & bm ) throw() + { return prob_prices[bm.probability]; } + +inline int price1( const Bit_model & bm ) throw() + { return prob_prices[bit_model_total-bm.probability]; } + +inline int price_bit( const Bit_model & bm, const int bit ) throw() + { if( bit ) return price1( bm ); else return price0( bm ); } + +inline int price_symbol( const Bit_model bm[], int symbol, const int num_bits ) throw() + { + symbol |= ( 1 << num_bits ); + int price = 0; + while( symbol > 1 ) + { + const int bit = symbol & 1; + symbol >>= 1; + price += price_bit( bm[symbol-1], bit ); + } + return price; + } + +inline int price_symbol_reversed( const Bit_model bm[], int symbol, + const int num_bits ) throw() + { + int price = 0; + int model = 1; + for( int i = num_bits; i > 0; --i ) + { + const int bit = symbol & 1; + symbol >>= 1; + price += price_bit( bm[model-1], bit ); + model = ( model << 1 ) | bit; + } + return price; + } + +inline int price_matched( const Bit_model bm[], const int symbol, + const int match_byte ) throw() + { + int price = 0; + int model = 1; + + for( int i = 7; i >= 0; --i ) + { + const int match_bit = ( match_byte >> i ) & 1; + const int bit = ( symbol >> i ) & 1; + price += price_bit( bm[(match_bit<<8)+model+0xFF], bit ); + model = ( model << 1 ) | bit; + if( match_bit != bit ) + { + while( --i >= 0 ) + { + const int bit = ( symbol >> i ) & 1; + price += price_bit( bm[model-1], bit ); + model = ( model << 1 ) | bit; + } + break; + } + } + return price; + } + + +class Matchfinder + { + enum { num_prev_positions4 = 1 << 20, + num_prev_positions3 = 1 << 18, + num_prev_positions2 = 1 << 16, + num_prev_positions = num_prev_positions4 + num_prev_positions3 + + num_prev_positions2 }; + + long long partial_data_pos; + int dictionary_size_; // bytes to keep in buffer before pos + const int after_size; // bytes to keep in buffer after pos + const int buffer_size; + uint8_t * const buffer; + int pos; + int cyclic_pos; + int stream_pos; // first byte not yet read from file + const int pos_limit; // when reached, a new block must be read + const int ides_; + const int match_len_limit_; + int32_t * const prev_positions; // last seen position of key + int32_t * prev_pos_tree; + bool at_stream_end; // stream_pos shows real end of file + + bool read_block() throw(); + +public: + Matchfinder( const int dict_size, const int len_limit, const int ides ) + : + partial_data_pos( 0 ), + dictionary_size_( dict_size ), + after_size( max_match_len ), + buffer_size( ( 2 * std::max( 65536, dictionary_size_ ) ) + + max_num_trials + after_size ), + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + cyclic_pos( 0 ), + stream_pos( 0 ), + pos_limit( buffer_size - after_size ), + ides_( ides ), + match_len_limit_( len_limit ), + prev_positions( new int32_t[num_prev_positions] ), + at_stream_end( false ) + { + if( !read_block() ) throw Error( "read error" ); + if( at_stream_end && stream_pos < dictionary_size_ ) + dictionary_size_ = std::max( min_dictionary_size, stream_pos ); + prev_pos_tree = new int32_t[2*dictionary_size_]; + for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = -1; + } + + ~Matchfinder() + { delete[] prev_pos_tree; delete[] prev_positions; delete[] buffer; } + + uint8_t operator[]( const int i ) const throw() { return buffer[pos+i]; } + int available_bytes() const throw() { return stream_pos - pos; } + long long data_position() const throw() { return partial_data_pos + pos; } + int dictionary_size() const throw() { return dictionary_size_; } + bool finished() const throw() { return at_stream_end && pos >= stream_pos; } + int match_len_limit() const throw() { return match_len_limit_; } + const uint8_t * ptr_to_current_pos() const throw() { return buffer + pos; } + + bool dec_pos( const int ahead ) throw() + { + if( ahead < 0 || pos < ahead ) return false; + pos -= ahead; + cyclic_pos -= ahead; + if( cyclic_pos < 0 ) cyclic_pos += dictionary_size_; + return true; + } + + int true_match_len( const int index, const int distance, int len_limit ) const throw() + { + if( index + len_limit > available_bytes() ) + len_limit = available_bytes() - index; + const uint8_t * const data = buffer + pos + index - distance; + int i = 0; + while( i < len_limit && data[i] == data[i+distance] ) ++i; + return i; + } + + bool reset() throw(); + bool move_pos() throw(); + int longest_match_len( int * const distances = 0 ) throw(); + }; + + +class Range_encoder + { + enum { buffer_size = 65536 }; + + uint64_t low; + long long partial_member_pos; + uint8_t * const buffer; + int pos; + uint32_t range; + int ff_count; + const int odes_; + uint8_t cache; + + void shift_low() + { + const uint32_t carry = low >> 32; + if( low < 0xFF000000 || carry == 1 ) + { + put_byte( cache + carry ); + for( ; ff_count > 0; --ff_count ) put_byte( 0xFF + carry ); + cache = low >> 24; + } + else ++ff_count; + low = ( low & 0x00FFFFFF ) << 8; + } + +public: + Range_encoder( const int odes ) + : + low( 0 ), + partial_member_pos( 0 ), + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + range( 0xFFFFFFFF ), + ff_count( 0 ), + odes_( odes ), + cache( 0 ) {} + + ~Range_encoder() { delete[] buffer; } + + void flush_data() + { + if( pos > 0 ) + { + if( odes_ >= 0 ) + { + const int wr = writeblock( odes_, (char *)buffer, pos ); + if( wr != pos ) throw Error( "write error" ); + } + partial_member_pos += pos; + pos = 0; + } + } + + void flush() { for( int i = 0; i < 5; ++i ) shift_low(); } + + long long member_position() const throw() + { return partial_member_pos + pos + ff_count; } + + void put_byte( const uint8_t b ) + { + buffer[pos] = b; + if( ++pos >= buffer_size ) flush_data(); + } + + void encode( const int symbol, const int num_bits ) + { + for( int i = num_bits - 1; i >= 0; --i ) + { + range >>= 1; + if( (symbol >> i) & 1 ) low += range; + if( range <= 0x00FFFFFF ) { range <<= 8; shift_low(); } + } + } + + void encode_bit( Bit_model & bm, const int bit ) + { + const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability; + if( !bit ) + { + range = bound; + bm.probability += (bit_model_total - bm.probability) >> bit_model_move_bits; + } + else + { + low += bound; + range -= bound; + bm.probability -= bm.probability >> bit_model_move_bits; + } + if( range <= 0x00FFFFFF ) { range <<= 8; shift_low(); } + } + + void encode_tree( Bit_model bm[], const int symbol, const int num_bits ) + { + int mask = ( 1 << ( num_bits - 1 ) ); + int model = 1; + for( int i = num_bits; i > 0; --i, mask >>= 1 ) + { + const int bit = ( symbol & mask ); + encode_bit( bm[model-1], bit ); + model <<= 1; + if( bit ) model |= 1; + } + } + + void encode_tree_reversed( Bit_model bm[], int symbol, const int num_bits ) + { + int model = 1; + for( int i = num_bits; i > 0; --i ) + { + const int bit = symbol & 1; + encode_bit( bm[model-1], bit ); + model = ( model << 1 ) | bit; + symbol >>= 1; + } + } + + void encode_matched( Bit_model bm[], int symbol, int match_byte ) + { + int model = 1; + for( int i = 7; i >= 0; --i ) + { + const int bit = ( symbol >> i ) & 1; + const int match_bit = ( match_byte >> i ) & 1; + encode_bit( bm[(match_bit<<8)+model+0xFF], bit ); + model = ( model << 1 ) | bit; + if( match_bit != bit ) + { + while( --i >= 0 ) + { + const int bit = ( symbol >> i ) & 1; + encode_bit( bm[model-1], bit ); + model = ( model << 1 ) | bit; + } + break; + } + } + } + }; + + +class Len_encoder + { + Bit_model choice1; + Bit_model choice2; + Bit_model bm_low[pos_states][len_low_symbols]; + Bit_model bm_mid[pos_states][len_mid_symbols]; + Bit_model bm_high[len_high_symbols]; + int prices[pos_states][max_len_symbols]; + const int len_symbols; + int counters[pos_states]; + + void update_prices( const int pos_state ) throw() + { + int * const pps = prices[pos_state]; + int price = price0( choice1 ); + int len = 0; + for( ; len < len_low_symbols && len < len_symbols; ++len ) + pps[len] = price + + price_symbol( bm_low[pos_state], len, len_low_bits ); + price = price1( choice1 ); + for( ; len < len_low_symbols + len_mid_symbols && len < len_symbols; ++len ) + pps[len] = price + price0( choice2 ) + + price_symbol( bm_mid[pos_state], len - len_low_symbols, len_mid_bits ); + for( ; len < len_symbols; ++len ) + pps[len] = price + price1( choice2 ) + + price_symbol( bm_high, len - len_low_symbols - len_mid_symbols, len_high_bits ); + counters[pos_state] = len_symbols; + } + +public: + Len_encoder( const int len_limit ) + : len_symbols( len_limit + 1 - min_match_len ) + { + for( int i = 0; i < pos_states; ++i ) update_prices( i ); + } + + void encode( Range_encoder & range_encoder, int symbol, + const int pos_state ); + + int price( const int symbol, const int pos_state ) const throw() + { return prices[pos_state][symbol - min_match_len]; } + }; + + +class Literal_encoder + { + Bit_model bm_literal[1<> ( 8 - literal_context_bits ) ); } + +public: + void encode( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t symbol ) + { range_encoder.encode_tree( bm_literal[state(prev_byte)], symbol, 8 ); } + + void encode_matched( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t match_byte, uint8_t symbol ) + { range_encoder.encode_matched( bm_literal[state(prev_byte)], symbol, match_byte ); } + + int price_matched( uint8_t prev_byte, uint8_t symbol, uint8_t match_byte ) const throw() + { return ::price_matched( bm_literal[state(prev_byte)], symbol, match_byte ); } + + int price_symbol( uint8_t prev_byte, uint8_t symbol ) const throw() + { return ::price_symbol( bm_literal[state(prev_byte)], symbol, 8 ); } + }; + + +class LZ_encoder + { + enum { dis_align_mask = dis_align_size - 1, + infinite_price = 0x0FFFFFFF, + num_rep_distances = 4 }; // must be 4 + + struct Trial + { + State state; + int dis; + int prev_index; + int price; // dual use var; cumulative price, match length + int reps[num_rep_distances]; + void update( const int d, const int p_i, const int pr ) throw() + { if( pr < price ) { dis = d; prev_index = p_i; price = pr; } } + }; + + int longest_match_found; + uint32_t crc_; + + Bit_model bm_match[State::states][pos_states]; + Bit_model bm_rep[State::states]; + Bit_model bm_rep0[State::states]; + Bit_model bm_rep1[State::states]; + Bit_model bm_rep2[State::states]; + Bit_model bm_len[State::states][pos_states]; + Bit_model bm_dis_slot[max_dis_states][1<= num_rep_distances ) + { + for( int i = num_rep_distances - 1; i > 0; --i ) reps[i] = reps[i-1]; + reps[0] = dis - num_rep_distances; + } + else if( dis > 0 ) + { + const int distance = reps[dis]; + for( int i = dis; i > 0; --i ) reps[i] = reps[i-1]; + reps[0] = distance; + } + } + + int price_rep_len1( const State & state, const int pos_state ) const throw() + { + return price0( bm_rep0[state()] ) + price0( bm_len[state()][pos_state] ); + } + + int price_rep( const int rep, const int len, const State & state, + const int pos_state ) const throw() + { + int price = rep_match_len_encoder.price( len, pos_state ); + if( rep == 0 ) + { + price += price0( bm_rep0[state()] ); + price += price1( bm_len[state()][pos_state] ); + } + else + { + price += price1( bm_rep0[state()] ); + if( rep == 1 ) + price += price0( bm_rep1[state()] ); + else + { + price += price1( bm_rep1[state()] ); + price += price_bit( bm_rep2[state()], rep - 2 ); + } + } + return price; + } + + int price_pair( const int dis, const int len, const int pos_state ) const throw() + { + if( len <= min_match_len && dis >= modeled_distances ) + return infinite_price; + int price = len_encoder.price( len, pos_state ); + const int dis_state = get_dis_state( len ); + if( dis < modeled_distances ) + price += dis_prices[dis_state][dis]; + else + price += dis_slot_prices[dis_state][dis_slots[dis]] + + align_prices[dis & dis_align_mask]; + return price; + } + + void encode_pair( const uint32_t dis, const int len, const int pos_state ) throw() + { + len_encoder.encode( range_encoder, len, pos_state ); + const int dis_slot = dis_slots[dis]; + range_encoder.encode_tree( bm_dis_slot[get_dis_state(len)], dis_slot, dis_slot_bits ); + + if( dis_slot >= start_dis_model ) + { + const int direct_bits = ( dis_slot >> 1 ) - 1; + const uint32_t base = ( 2 | ( dis_slot & 1 ) ) << direct_bits; + const uint32_t direct_dis = dis - base; + + if( dis_slot < end_dis_model ) + range_encoder.encode_tree_reversed( bm_dis + base - dis_slot, + direct_dis, direct_bits ); + else + { + range_encoder.encode( direct_dis >> dis_align_bits, direct_bits - dis_align_bits ); + range_encoder.encode_tree_reversed( bm_align, direct_dis, dis_align_bits ); + if( --align_price_count <= 0 ) fill_align_prices(); + } + } + } + + int read_match_distances() throw() + { + int len = matchfinder.longest_match_len( match_distances ); + if( len == matchfinder.match_len_limit() ) + len += matchfinder.true_match_len( len, match_distances[len] + 1, max_match_len - len ); + return len; + } + + bool move_pos( int n, bool skip = false ) throw() + { + while( --n >= 0 ) + { + if( skip ) skip = false; + else matchfinder.longest_match_len(); + if( !matchfinder.move_pos() ) return false; + } + return true; + } + + void backward( int cur ) + { + int & dis = trials[cur].dis; + while( cur > 0 ) + { + const int prev_index = trials[cur].prev_index; + Trial & prev_trial = trials[prev_index]; + std::swap( dis, prev_trial.dis ); + prev_trial.price = cur - prev_index; // len + cur = prev_index; + } + } + + int best_pair_sequence( const int reps[num_rep_distances], + const State & state ); + + void flush( const State & state ); + +public: + LZ_encoder( Matchfinder & mf, const File_header & header, const int odes ); + + bool encode_member( const long long member_size ); + + long long member_position() const throw() + { return range_encoder.member_position(); } + }; diff --git a/lzdiff b/lzdiff new file mode 100755 index 0000000..f289a95 --- /dev/null +++ b/lzdiff @@ -0,0 +1,145 @@ +#! /bin/sh +# Lzdiff - Diff/cmp wrapper for compressed files. +# Copyright (C) 2008, 2009 Antonio Diaz Diaz. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +invocation_name=$0 +args= +default_ext=.lz +diff_prog=diff +file1= +file2= + +# Loop over args +while [ x"$1" != x ] ; do + + case "$1" in + --help | --he* | -h) + echo "Lzdiff - Diff/cmp wrapper for compressed files." + echo + echo "Lzdiff is a wrapper script around the diff and cmp commands that allows" + echo "transparent comparison of any combination of compressed and" + echo "non-compressed files. If any given file is compressed, its uncompressed" + echo "content is used. The supported compressors are gzip, bzip2 and lzip." + echo + echo "Usage: ${invocation_name} [OPTIONS] [DIFF_OPTIONS] FILE1 [FILE2]" + echo + echo "Compares FILE1 to FILE2. If FILE2 is omitted, compares FILE1 to the" + echo "uncompressed contents of FILE1.[gz|bz2|lz] (depending on the default" + echo "compressor selected). DIFF_OPTIONS are passed directly to diff or cmp." + echo "The exit status from diff or cmp is preserved." + echo + echo "Options:" + echo " -h, --help display this help and exit" + echo " -V, --version output version information and exit" + echo " --gzip use gzip as default decompressor" + echo " --bzip2 use bzip2 as default decompressor" + echo " --lzip use lzip as default decompressor (default)" + echo " --diff use diff to compare files (default)" + echo " --cmp use cmp to compare files" + exit 0 ;; + --version | --ve* | -V) + echo "Lzdiff 0.3" + echo "Copyright (C) 2009 Antonio Diaz Diaz." + echo "This script is free software: you have unlimited permission" + echo "to copy, distribute and modify it." + exit 0 ;; + --gz*) + default_ext=.gz ;; + --bz*) + default_ext=.bz2 ;; + --lz*) + default_ext=.lz ;; + --diff) + diff_prog=diff ;; + --cmp) + diff_prog=cmp ;; + -) + echo "${invocation_name}: reading from stdin not supported\n" + exit 1 ;; + --) + ;; + -?*) + args="${args} $1" ;; + *) + if test -f "$1"; then + if test -z "${file1}"; then file1="$1" + else + if test -z "${file2}"; then file2="$1" + else + echo "${invocation_name}: Too many files; use --help for usage." 1>&2 + fi + fi + else + echo "${invocation_name}: File \"$1\" not found or not a regular file" 1>&2 + exit 1 + fi ;; + esac + shift +done + +if test -z "${file1}"; then + echo "${invocation_name}: No files given; use --help for usage." 1>&2 + exit 1 +fi + +if test -z "${file2}"; then + case "${file1}" in + *.gz) + file2=`echo "${file1}" | sed 's/.gz$//'` ;; + *.tgz) + file2=`echo "${file1}" | sed 's/tgz$/tar/'` ;; + *.bz2) + file2=`echo "${file1}" | sed 's/.bz2$//'` ;; + *.tbz2) + file2=`echo "${file1}" | sed 's/tbz2$/tar/'` ;; + *.lz) + file2=`echo "${file1}" | sed 's/.lz$//'` ;; + *.tlz) + file2=`echo "${file1}" | sed 's/.tlz$/tar/'` ;; + *) + file2="${file1}"; file1="${file1}${default_ext}" ;; + esac +fi + +prog1= +prog2= +case "${file1}" in +*.gz | *.tgz) prog1=gzip ;; +*.bz2 | *.tbz2) prog1=bzip2 ;; +*.lz | *.tlz) prog1=lzip ;; +esac +case "${file2}" in +*.gz | *.tgz) prog2=gzip ;; +*.bz2 | *.tbz2) prog2=bzip2 ;; +*.lz | *.tlz) prog2=lzip ;; +esac + +retval=0 +if test -n "${prog1}"; then + if test -n "${prog2}"; then + tmp_file=`mktemp "${TMPDIR:-/tmp}"/lzdiff.XXXXXXXXXX` || { + echo 'cannot create a temporary file' 1>&2 + exit 1 + } + ${prog2} -cdfq "${file2}" > "${tmp_file}" || exit 1 + ${prog1} -cdfq "${file1}" | ${diff_prog} ${args} - "${tmp_file}" + retval=$? + rm -f "${tmp_file}" || retval=$? + else + ${prog1} -cdfq "${file1}" | ${diff_prog} ${args} - "${file2}" + retval=$? + fi +else + if test -n "${prog2}"; then + ${prog2} -cdfq "${file2}" | ${diff_prog} ${args} "${file1}" - + retval=$? + else + ${diff_prog} ${args} "${file1}" "${file2}" + retval=$? + fi +fi + +exit ${retval} diff --git a/lzgrep b/lzgrep new file mode 100755 index 0000000..9d9eaeb --- /dev/null +++ b/lzgrep @@ -0,0 +1,130 @@ +#! /bin/sh +# Lzgrep - Grep wrapper for compressed files. +# Copyright (C) 2008, 2009 Antonio Diaz Diaz. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +invocation_name=$0 +args= +default_prog=lzip +have_pat=0 +list=0 +no_name=0 + +# Loop over args until pattern is found +while [ x"$1" != x ] ; do + + case "$1" in + --help | --he* | -h) + echo "Lzgrep - Grep wrapper for compressed files." + echo + echo "Lzgrep is a wrapper script around the grep command that allows" + echo "transparent search on any combination of compressed and non-compressed" + echo "files. If any given file is compressed, its uncompressed content is" + echo "used. If a given file does not exist, lzgrep tries the compressed file" + echo "name corresponding to the default compressor selected. The supported" + echo "compressors are gzip, bzip2 and lzip." + echo + echo "Usage: ${invocation_name} [OPTIONS] [GREP_OPTIONS] PATTERN [FILES]" + echo + echo "GREP_OPTIONS are passed directly to grep." + echo "The exit status from grep is preserved." + echo + echo "Options:" + echo " -h, --help display this help and exit" + echo " -V, --version output version information and exit" + echo " --gzip use gzip as default decompressor" + echo " --bzip2 use bzip2 as default decompressor" + echo " --lzip use lzip as default decompressor (default)" + exit 0 ;; + --version | --ve* | -V) + echo "Lzgrep 0.3" + echo "Copyright (C) 2009 Antonio Diaz Diaz." + echo "This script is free software: you have unlimited permission" + echo "to copy, distribute and modify it." + exit 0 ;; + --gz*) + default_prog=gzip ;; + --bz*) + default_prog=bzip2 ;; + --lz*) + default_prog=lzip ;; + -[drRzZ] | --di* | --exc* | --inc* | --nu* | --rec*) + echo "${invocation_name}: option $1 not supported\n" + exit 1 ;; + -e?* | -f?* | --file=* | --reg*=*) + args="${args} $1"; have_pat=1 ;; + -e | -f | --file | --reg*) + args="${args} $1 $2"; shift; have_pat=1 ;; + --*=*) + args="${args} $1" ;; + -[ABCDm] | --af* | --be* | --binary-* | --con* | --de* | --[lm]a*) + args="${args} $1 $2"; shift ;; + -l | --files-with-*) + args="${args} $1"; list=1 ;; + -h | --no-f*) + args="${args} $1"; no_name=1 ;; + --) + break ;; + -?*) + args="${args} $1" ;; + *) + if test ${have_pat} = 0; then args="${args} $1"; have_pat=1 + else break + fi ;; + esac + shift +done + +if test ${have_pat} = 0; then + echo "${invocation_name}: Pattern not found; use --help for usage." 1>&2 + exit 1 +fi + +if test $# -eq 0; then + ${default_prog} -cdfq | grep ${args} + exit $? +fi + +retval=0 +for i in "$@" ; do + prog="${default_prog} -cdfq" + case "$i" in + *.gz | *.tgz) + prog="gzip -cdfq" ;; + *.bz2 | *.tbz2) + prog="bzip2 -cdfq" ;; + *.lz | *.tlz) + prog="lzip -cdfq" ;; + *) + if test -f "$i"; then prog=cat + else + case ${default_prog} in + gzip) + if test -f "$i.gz"; then i="$i.gz"; fi ;; + bzip2) + if test -f "$i.bz2"; then i="$i.bz2"; fi ;; + lzip) + if test -f "$i.lz"; then i="$i.lz"; fi ;; + esac + fi ;; + esac + if test ${list} -eq 1; then + ${prog} -- "$i" | grep ${args} 2>&1 > /dev/null && echo $i + r=$? + elif test $# -eq 1 -o ${no_name} -eq 1; then + ${prog} -- "$i" | grep ${args} + r=$? + else + j=${i//\\/\\\\} + j=${j//|/\\|} + j=${j//&/\\&} + j=`printf "%s" "$j" | tr '\n' ' '` + ${prog} -- "$i" | grep ${args} | sed "s|^|${j}:|" + r=$? + fi + test "$r" -ne 0 && retval="$r" +done + +exit ${retval} diff --git a/lzip.h b/lzip.h new file mode 100644 index 0000000..89afe96 --- /dev/null +++ b/lzip.h @@ -0,0 +1,275 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ + +class State + { + unsigned char st; + +public: + enum { states = 12 }; + State() throw() : st( 0 ) {} + int operator()() const throw() { return st; } + bool is_char() const throw() { return st < 7; } + + void set_char() throw() + { + static const unsigned char next[states] = {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5}; + st = next[st]; + } + void set_match() throw() + { + static const unsigned char next[states] = {7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10}; + st = next[st]; + } + void set_rep() throw() + { + static const unsigned char next[states] = {8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11}; + st = next[st]; + } + void set_short_rep() throw() + { + static const unsigned char next[states] = {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11}; + st = next[st]; + } + }; + + +const int min_dictionary_bits = 12; +const int min_dictionary_size = 1 << min_dictionary_bits; +const int max_dictionary_bits = 29; +const int max_dictionary_size = 1 << max_dictionary_bits; +const int literal_context_bits = 3; +const int pos_state_bits = 2; +const int pos_states = 1 << pos_state_bits; +const int pos_state_mask = pos_states - 1; + +const int dis_slot_bits = 6; +const int start_dis_model = 4; +const int end_dis_model = 14; +const int modeled_distances = 1 << (end_dis_model / 2); +const int dis_align_bits = 4; +const int dis_align_size = 1 << dis_align_bits; + +const int len_low_bits = 3; +const int len_mid_bits = 3; +const int len_high_bits = 8; +const int len_low_symbols = 1 << len_low_bits; +const int len_mid_symbols = 1 << len_mid_bits; +const int len_high_symbols = 1 << len_high_bits; +const int max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols; + +const int min_match_len = 2; // must be 2 +const int max_match_len = min_match_len + max_len_symbols - 1; // 273 + +const int max_dis_states = 4; + +inline int get_dis_state( int len ) throw() + { + len -= min_match_len; + if( len >= max_dis_states ) len = max_dis_states - 1; + return len; + } + + +const int bit_model_move_bits = 5; +const int bit_model_total_bits = 11; +const int bit_model_total = 1 << bit_model_total_bits; + +struct Bit_model + { + unsigned int probability; + Bit_model() throw() : probability( bit_model_total / 2 ) {} + }; + + +class Pretty_print + { + const char * const stdin_name; + const unsigned int stdin_name_len; + unsigned int longest_name; + std::string name_; + mutable bool first_post; + +public: + Pretty_print( const std::vector< std::string > & filenames ) + : stdin_name( "(stdin)" ), stdin_name_len( std::strlen( stdin_name ) ), + longest_name( 0 ), first_post( false ) + { + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + const std::string & s = filenames[i]; + const unsigned int len = ( ( s == "-" ) ? stdin_name_len : s.size() ); + if( len > longest_name ) longest_name = len; + } + if( longest_name == 0 ) longest_name = stdin_name_len; + } + + void set_name( const std::string & filename ) + { + if( filename.size() && filename != "-" ) name_ = filename; + else name_ = stdin_name; + first_post = true; + } + + void reset() const throw() { if( name_.size() ) first_post = true; } + const char * name() const throw() { return name_.c_str(); } + void operator()( const char * const msg = 0 ) const throw(); + }; + + +class CRC32 + { + uint32_t data[256]; // Table of CRCs of all 8-bit messages. + +public: + CRC32() + { + for( unsigned int n = 0; n < 256; ++n ) + { + unsigned int c = n; + for( int k = 0; k < 8; ++k ) + { if( c & 1 ) c = 0xEDB88320 ^ ( c >> 1 ); else c >>= 1; } + data[n] = c; + } + } + + uint32_t operator[]( const uint8_t byte ) const throw() { return data[byte]; } + void update( uint32_t & crc, const uint8_t byte ) const throw() + { crc = data[(crc^byte)&0xFF] ^ ( crc >> 8 ); } + }; + + +const char * const magic_string = "LZIP"; + +struct File_header + { + char magic[4]; + uint8_t version; + uint8_t coded_dict_size; + + void set_magic() throw() + { std::memcpy( magic, magic_string, sizeof magic ); version = 1; } + + bool verify_magic() const throw() + { + return ( std::memcmp( magic, magic_string, sizeof magic ) == 0 ); + } + + bool verify_version() const throw() + { + return ( version <= 1 ); + } + + static int real_bits( const int value ) throw() + { + int bits = 0; + for( int i = 1, mask = 1; mask > 0; ++i, mask <<= 1 ) + if( value & mask ) bits = i; + return bits; + } + + int dictionary_size() const throw() + { + int size = ( 1 << ( coded_dict_size & 0x1F ) ); + if( size > min_dictionary_size && size <= max_dictionary_size ) + size -= ( size / 16 ) * ( ( coded_dict_size >> 5 ) & 0x07 ); + return size; + } + + bool dictionary_size( const int size ) throw() + { + if( size >= min_dictionary_size && size <= max_dictionary_size ) + { + coded_dict_size = real_bits( size - 1 ); + if( size > min_dictionary_size ) + { + const int base_size = 1 << coded_dict_size; + const int wedge = base_size / 16; + for( int i = 7; i >= 1; --i ) + if( base_size - ( i * wedge ) >= size ) + { coded_dict_size |= ( i << 5 ); break; } + } + return true; + } + return false; + } + }; + + +struct File_trailer + { + uint8_t data_crc_[4]; // CRC32 of the uncompressed data + uint8_t data_size_[8]; // size of the uncompressed data + uint8_t member_size_[8]; // member size including header and trailer + + static int size( const int version ) + { return sizeof( File_trailer ) - ( ( version >= 1 ) ? 0 : 8 ); } + + uint32_t data_crc() const throw() + { + uint32_t tmp = 0; + for( int i = 3; i >= 0; --i ) { tmp <<= 8; tmp += data_crc_[i]; } + return tmp; + } + + void data_crc( uint32_t crc ) throw() + { + for( int i = 0; i < 4; ++i ) + { data_crc_[i] = (uint8_t)crc; crc >>= 8; } + } + + long long data_size() const throw() + { + long long tmp = 0; + for( int i = 7; i >= 0; --i ) { tmp <<= 8; tmp += data_size_[i]; } + return tmp; + } + + void data_size( long long size ) throw() + { + for( int i = 0; i < 8; ++i ) + { data_size_[i] = (uint8_t)size; size >>= 8; } + } + + long long member_size() const throw() + { + long long tmp = 0; + for( int i = 7; i >= 0; --i ) { tmp <<= 8; tmp += member_size_[i]; } + return tmp; + } + + void member_size( long long size ) throw() + { + for( int i = 0; i < 8; ++i ) + { member_size_[i] = (uint8_t)size; size >>= 8; } + } + }; + + +struct Error + { + const char * s; + Error( const char * p ) throw() : s( p ) {} + }; + +extern int verbosity; +extern const CRC32 crc32; + +void show_error( const char * msg, const int errcode = 0, const bool help = false ) throw(); +void internal_error( const char * msg ); +int readblock( const int fd, char * buf, const int size ) throw(); +int writeblock( const int fd, const char * buf, const int size ) throw(); diff --git a/lziprecover.cc b/lziprecover.cc new file mode 100644 index 0000000..bca2744 --- /dev/null +++ b/lziprecover.cc @@ -0,0 +1,347 @@ +/* Lziprecover - Member recoverer program for lzip compressed files + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ +/* + Return values: 0 for a normal exit, 1 for environmental problems + (file not found, invalid flags, I/O errors, etc), 2 to indicate a + corrupt or invalid input file, 3 for an internal consistency error + (eg, bug) which caused lzip to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "arg_parser.h" +#include "lzip.h" + + +namespace { + +const char * invocation_name = 0; +const char * const Program_name = "Lziprecover"; +const char * const program_name = "lziprecover"; +const char * const program_year = "2009"; + + +void show_help() throw() + { + std::printf( "%s - Member recoverer program for lzip compressed files.\n", Program_name ); + std::printf( "\nUsage: %s [options] file\n", invocation_name ); + std::printf( "Options:\n" ); + std::printf( " -h, --help display this help and exit\n" ); + std::printf( " -V, --version output version information and exit\n" ); + std::printf( " -q, --quiet suppress all messages\n" ); + std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" ); + std::printf( "\nReport bugs to lzip-bug@nongnu.org\n"); + } + + +void show_version() throw() + { + std::printf( "%s %s\n", Program_name, PROGVERSION ); + std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + std::printf( "License GPLv3+: GNU GPL version 3 or later \n" ); + std::printf( "This is free software: you are free to change and redistribute it.\n" ); + std::printf( "There is NO WARRANTY, to the extent permitted by law.\n" ); + } + + +int open_instream( const std::string & input_filename ) throw() + { + int ides = open( input_filename.c_str(), O_RDONLY ); + if( ides < 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n", + program_name, input_filename.c_str(), std::strerror( errno ) ); + } + else + { + struct stat in_stats; + const int i = fstat( ides, &in_stats ); + if( i < 0 || !S_ISREG( in_stats.st_mode ) ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: input file `%s' is not a regular file.\n", + program_name, input_filename.c_str() ); + close( ides ); + ides = -1; + } + } + return ides; + } + + +int open_outstream( const std::string & output_filename ) throw() + { + int odes = open( output_filename.c_str(), O_CREAT | O_TRUNC | O_WRONLY, S_IRUSR | S_IWUSR ); + if( odes < 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename.c_str(), std::strerror( errno ) ); + } + return odes; + } + + +bool next_filename( std::string & output_filename ) + { + for( int i = 7; i >= 3; --i ) // "rec00001" + { + if( output_filename[i] < '9' ) { ++output_filename[i]; return true; } + else output_filename[i] = '0'; + } + return false; + } + + +int search_header( const char * buffer, const int size, const int pos, + const long long last_header_pos, + const long long partial_file_pos ) + { + for( int i = pos; i < size; ++i ) + if( buffer[i] == magic_string[0] && buffer[i+1] == magic_string[1] && + buffer[i+2] == magic_string[2] && buffer[i+3] == magic_string[3] ) + { + File_trailer trailer; + for( unsigned int j = 0; j < sizeof trailer; ++j ) + ((char *)&trailer)[j] = buffer[i-(sizeof trailer)+j]; + if( partial_file_pos + i - trailer.member_size() == last_header_pos ) + return i; + } + return -1; + } + + +bool verify_header( const char * buffer, const int pos ) + { + File_header header; + for( unsigned int i = 0; i < sizeof header; ++i ) + ((char *)&header)[i] = buffer[pos+i]; + if( !header.verify_magic() ) + { + show_error( "bad magic number (file not created by lzip).\n" ); + return false; + } + if( header.version == 0 ) + { + show_error( "version 0 member format can't be recovered.\n" ); + return false; + } + if( header.version != 1 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "version %d member format not supported, newer %s needed.\n", + header.version, program_name ); + return false; + } + return true; + } + + +int process_file( const std::string & input_filename, char * & base_buffer ) + { + const int hsize = sizeof( File_header ); + const int tsize = sizeof( File_trailer ); + const int buffer_size = 65536; + const int base_buffer_size = tsize + buffer_size + hsize; + base_buffer = new char[base_buffer_size]; + char * const buffer = base_buffer + tsize; + + const int inhandle = open_instream( input_filename ); + if( inhandle < 0 ) return 1; + int size = readblock( inhandle, buffer, buffer_size + hsize ) - hsize; + bool at_stream_end = ( size < buffer_size ); + if( size != buffer_size && errno ) + { show_error( "read error", errno ); return 1; } + if( size <= tsize ) + { show_error( "file too short" ); return 2; } + if( !verify_header( buffer, 0 ) ) return 2; + + std::string output_filename( "rec00001" ); output_filename += input_filename; + int outhandle = open_outstream( output_filename ); + if( outhandle < 0 ) { close( inhandle ); return 1; } + + long long last_header_pos = 0; + long long partial_file_pos = 0; + int pos = 0; + while( size > 0 ) + { + const int newpos = search_header( buffer, size - hsize, pos + hsize, + last_header_pos, partial_file_pos ); + if( newpos > pos ) + { + const int wr = writeblock( outhandle, buffer + pos, newpos - pos ); + if( wr != newpos - pos ) + { show_error( "write error", errno ); return 1; } + if( close( outhandle ) != 0 ) + { show_error( "error closing output file", errno ); return 1; } + if( !next_filename( output_filename ) ) + { show_error( "too many members in file" ); close( inhandle ); return 1; } + outhandle = open_outstream( output_filename ); + if( outhandle < 0 ) { close( inhandle ); return 1; } + last_header_pos = partial_file_pos + newpos; + pos = newpos; + continue; + } + else + { + if( !at_stream_end ) + { + partial_file_pos += buffer_size; + const int wr = writeblock( outhandle, buffer + pos, buffer_size - pos ); + if( wr != buffer_size - pos ) + { show_error( "write error", errno ); return 1; } + std::memcpy( base_buffer, base_buffer + buffer_size, tsize + hsize ); + pos = 0; + } + else + { + const int wr = writeblock( outhandle, buffer + pos, size + hsize - pos ); + if( wr != size + hsize - pos ) + { show_error( "write error", errno ); return 1; } + break; + } + } + size = readblock( inhandle, buffer + hsize, buffer_size ); + at_stream_end = ( size < buffer_size ); + if( size != buffer_size && errno ) + { show_error( "read error", errno ); return 1; } + } + close( inhandle ); + if( close( outhandle ) != 0 ) + { show_error( "error closing output file", errno ); return 1; } + return 0; + } + +} // end namespace + + +int verbosity = 0; + + +void show_error( const char * msg, const int errcode, const bool help ) throw() + { + if( verbosity >= 0 ) + { + if( msg && msg[0] != 0 ) + { + std::fprintf( stderr, "%s: %s", program_name, msg ); + if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) ); + std::fprintf( stderr, "\n" ); + } + if( help && invocation_name && invocation_name[0] != 0 ) + std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name ); + } + } + + +void internal_error( const char * msg ) + { + std::string s( "internal error: " ); s += msg; + show_error( s.c_str() ); + std::exit( 3 ); + } + + +// Returns the number of bytes really read. +// If (returned value < size) and (errno == 0), means EOF was reached. +// +int readblock( const int fd, char * buf, const int size ) throw() + { + int rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = read( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( n == 0 ) break; + else if( errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +// Returns the number of bytes really written. +// If (returned value < size), it is always an error. +// +int writeblock( const int fd, const char * buf, const int size ) throw() + { + int rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = write( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( errno && errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +int main( const int argc, const char * argv[] ) + { + invocation_name = argv[0]; + + const Arg_parser::Option options[] = + { + { 'h', "help", Arg_parser::no }, + { 'q', "quiet", Arg_parser::no }, + { 'v', "verbose", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + Arg_parser parser( argc, argv, options ); + if( parser.error().size() ) // bad option + { show_error( parser.error().c_str(), 0, true ); return 1; } + + int argind = 0; + for( ; argind < parser.arguments(); ++argind ) + { + const int code = parser.code( argind ); + if( !code ) break; // no more options + switch( code ) + { + case 'h': show_help(); return 0; + case 'q': verbosity = -1; break; + case 'v': if( verbosity < 4 ) ++verbosity; break; + case 'V': show_version(); return 0; + default : internal_error( "uncaught option" ); + } + } + + if( argind + 1 != parser.arguments() ) + { show_error( "you must specify exactly 1 file", 0, true ); return 1; } + + char * base_buffer; + const int retval = process_file( parser.argument( argind ), base_buffer ); + + delete[] base_buffer; + return retval; + } diff --git a/main.cc b/main.cc new file mode 100644 index 0000000..fa91d9d --- /dev/null +++ b/main.cc @@ -0,0 +1,831 @@ +/* Lzip - A data compressor based on the LZMA algorithm + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +*/ +/* + Return values: 0 for a normal exit, 1 for environmental problems + (file not found, invalid flags, I/O errors, etc), 2 to indicate a + corrupt or invalid input file, 3 for an internal consistency error + (eg, bug) which caused lzip to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "arg_parser.h" +#include "lzip.h" +#include "decoder.h" +#include "encoder.h" + +#ifndef LLONG_MAX +#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL +#endif +#ifndef LLONG_MIN +#define LLONG_MIN (-LLONG_MAX - 1LL) +#endif +#ifndef ULLONG_MAX +#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL +#endif + + +namespace { + +const char * invocation_name = 0; +const char * const Program_name = "Lzip"; +const char * const program_name = "lzip"; +const char * const program_year = "2009"; + +struct { const char * from; const char * to; } const known_extensions[] = { + { ".lz", "" }, + { ".tlz", ".tar" }, + { 0, 0 } }; + +struct lzma_options + { + int dictionary_size; // 4KiB..512MiB + int match_len_limit; // 5..273 + }; + +enum Mode { m_compress = 0, m_decompress, m_test }; + +std::string output_filename; +int outhandle = -1; +bool delete_output_on_interrupt = false; + + +void show_help() throw() + { + std::printf( "%s - A data compressor based on the LZMA algorithm.\n", Program_name ); + std::printf( "\nUsage: %s [options] [files]\n", invocation_name ); + std::printf( "Options:\n" ); + std::printf( " -h, --help display this help and exit\n" ); + std::printf( " -V, --version output version information and exit\n" ); + std::printf( " -b, --member-size= set member size limit in bytes\n" ); + std::printf( " -c, --stdout send output to standard output\n" ); + std::printf( " -d, --decompress decompress\n" ); + std::printf( " -f, --force overwrite existing output files\n" ); + std::printf( " -k, --keep keep (don't delete) input files\n" ); + std::printf( " -m, --match-length= set match length limit in bytes [80]\n" ); + std::printf( " -o, --output= if reading stdin, place the output into \n" ); + std::printf( " -q, --quiet suppress all messages\n" ); + std::printf( " -s, --dictionary-size= set dictionary size limit in bytes [8MiB]\n" ); + std::printf( " -S, --volume-size= set volume size limit in bytes\n" ); + std::printf( " -t, --test test compressed file integrity\n" ); + std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" ); + std::printf( " -1 .. -9 set compression level [default 6]\n" ); + std::printf( " --fast alias for -1\n" ); + std::printf( " --best alias for -9\n" ); + std::printf( "If no file names are given, lzip compresses or decompresses\n" ); + std::printf( "from standard input to standard output.\n" ); + std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" ); + std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" ); + std::printf( "\nReport bugs to lzip-bug@nongnu.org\n" ); + std::printf( "Lzip home page: http://www.nongnu.org/lzip/lzip.html\n" ); + } + + +void show_version() throw() + { + std::printf( "%s %s\n", Program_name, PROGVERSION ); + std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + std::printf( "License GPLv3+: GNU GPL version 3 or later \n" ); + std::printf( "This is free software: you are free to change and redistribute it.\n" ); + std::printf( "There is NO WARRANTY, to the extent permitted by law.\n" ); + } + + +const char * format_num( long long num, long long limit = 9999, + const int set_prefix = 0 ) throw() + { + const char * const si_prefix[8] = + { "k", "M", "G", "T", "P", "E", "Z", "Y" }; + const char * const binary_prefix[8] = + { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; + static bool si = false; + static char buf[16]; + + if( set_prefix ) si = ( set_prefix > 0 ); + const int factor = ( si ) ? 1000 : 1024; + const char * const *prefix = ( si ) ? si_prefix : binary_prefix; + const char *p = ""; + limit = std::max( 999LL, std::min( 999999LL, limit ) ); + + for( int i = 0; i < 8 && ( llabs( num ) > limit || + ( llabs( num ) >= factor && num % factor == 0 ) ); ++i ) + { num /= factor; p = prefix[i]; } + snprintf( buf, sizeof buf, "%lld %s", num, p ); + return buf; + } + + +long long getnum( const char * ptr, const int bs, + const long long llimit = LLONG_MIN + 1, + const long long ulimit = LLONG_MAX ) throw() + { + errno = 0; + char *tail; + long long result = strtoll( ptr, &tail, 0 ); + if( tail == ptr ) + { + show_error( "bad or missing numerical argument", 0, true ); + std::exit( 1 ); + } + + if( !errno && tail[0] ) + { + int factor = ( tail[1] == 'i' ) ? 1024 : 1000; + int exponent = 0; + bool bad_multiplier = false; + switch( tail[0] ) + { + case ' ': break; + case 'b': if( bs > 0 ) { factor = bs; exponent = 1; } + else bad_multiplier = true; + break; + case 'Y': exponent = 8; break; + case 'Z': exponent = 7; break; + case 'E': exponent = 6; break; + case 'P': exponent = 5; break; + case 'T': exponent = 4; break; + case 'G': exponent = 3; break; + case 'M': exponent = 2; break; + case 'K': if( factor == 1024 ) exponent = 1; else bad_multiplier = true; + break; + case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true; + break; + default: bad_multiplier = true; + } + if( bad_multiplier ) + { + show_error( "bad multiplier in numerical argument", 0, true ); + std::exit( 1 ); + } + for( int i = 0; i < exponent; ++i ) + { + if( LLONG_MAX / factor >= llabs( result ) ) result *= factor; + else { errno = ERANGE; break; } + } + } + if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE; + if( errno ) + { + show_error( "numerical argument out of limits" ); + std::exit( 1 ); + } + return result; + } + + +int get_dict_size( const char * arg ) throw() + { + char *tail; + int bits = std::strtol( arg, &tail, 0 ); + if( bits >= min_dictionary_bits && bits <= max_dictionary_bits && *tail == 0 ) + return ( 1 << bits ); + return getnum( arg, 0, min_dictionary_size, max_dictionary_size ); + } + + +int extension_index( const std::string & name ) throw() + { + for( int i = 0; known_extensions[i].from; ++i ) + { + const std::string ext( known_extensions[i].from ); + if( name.size() > ext.size() && + name.compare( name.size() - ext.size(), ext.size(), ext ) == 0 ) + return i; + } + return -1; + } + + +int open_instream( const std::string & name, struct stat * in_statsp, + const Mode program_mode, const int eindex, + const bool force, const bool to_stdout ) throw() + { + int inhandle = -1; + if( program_mode == m_compress && !force && eindex >= 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: input file `%s' already has `%s' suffix.\n", + program_name, name.c_str(), + known_extensions[eindex].from ); + } + else + { + inhandle = open( name.c_str(), O_RDONLY ); + if( inhandle < 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n", + program_name, name.c_str(), std::strerror( errno ) ); + } + else + { + const int i = fstat( inhandle, in_statsp ); + const mode_t & mode = in_statsp->st_mode; + if( i < 0 || !( S_ISREG( mode ) || ( to_stdout && + ( S_ISFIFO( mode ) || S_ISSOCK( mode ) || + S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n", + program_name, name.c_str(), + to_stdout ? "" : " and `--stdout' was not specified" ); + close( inhandle ); + inhandle = -1; + } + } + } + return inhandle; + } + + +void set_c_outname( const std::string & name, const bool multifile ) throw() + { + output_filename = name; + if( multifile ) output_filename += "00001"; + output_filename += known_extensions[0].from; + } + + +void set_d_outname( const std::string & name, const int i ) throw() + { + if( i >= 0 ) + { + const std::string from( known_extensions[i].from ); + if( name.size() > from.size() ) + { + output_filename.assign( name, 0, name.size() - from.size() ); + output_filename += known_extensions[i].to; + return; + } + } + output_filename = name; output_filename += ".out"; + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n", + program_name, name.c_str(), output_filename.c_str() ); + } + + +bool open_outstream( const bool force ) throw() + { + if( force ) + outhandle = open( output_filename.c_str(), O_CREAT | O_TRUNC | O_WRONLY, + S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH ); + else outhandle = open( output_filename.c_str(), O_CREAT | O_EXCL | O_WRONLY, + S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH ); + if( outhandle < 0 ) + { + if( errno == EEXIST ) outhandle = -2; else outhandle = -1; + if( verbosity >= 0 ) + { + if( outhandle == -2 ) + std::fprintf( stderr, "%s: Output file %s already exists, skipping.\n", + program_name, output_filename.c_str() ); + else + std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename.c_str(), std::strerror( errno ) ); + } + } + return ( outhandle >= 0 ); + } + + +bool check_tty( const int inhandle, const Mode program_mode ) throw() + { + if( program_mode == m_compress && isatty( outhandle ) ) + { + show_error( "I won't write compressed data to a terminal.", 0, true ); + return false; + } + if( ( program_mode == m_decompress || program_mode == m_test ) && + isatty( inhandle ) ) + { + show_error( "I won't read compressed data from a terminal.", 0, true ); + return false; + } + return true; + } + + +void cleanup_and_fail( const int retval ) throw() + { + if( delete_output_on_interrupt ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n", + program_name, output_filename.c_str() ); + if( outhandle >= 0 ) { close( outhandle ); outhandle = -1; } + if( std::remove( output_filename.c_str() ) != 0 ) + show_error( "WARNING: deletion of output file (apparently) failed." ); + } + std::exit( retval ); + } + + + // Set permissions, owner and times. +void close_and_set_permissions( const struct stat * in_statsp, int * retvalp ) + { + int tmp = 0; + if( in_statsp ) + { + if( fchmod( outhandle, in_statsp->st_mode ) != 0 ) tmp = 1; + if( !tmp ) (void)fchown( outhandle, in_statsp->st_uid, in_statsp->st_gid ); + // fchown will in many cases return with EPERM, which can be safely ignored. + } + if( close( outhandle ) == 0 ) outhandle = -1; + else cleanup_and_fail( 1 ); + delete_output_on_interrupt = false; + if( !in_statsp ) return; + if( !tmp ) + { + struct utimbuf t; + t.actime = in_statsp->st_atime; + t.modtime = in_statsp->st_mtime; + tmp = utime( output_filename.c_str(), &t ); + } + if( tmp ) + { + if( tmp > *retvalp ) *retvalp = tmp; + show_error( "I can't change output file attributes." ); + cleanup_and_fail( *retvalp ); + } + } + + +bool next_filename() + { + const unsigned int len = std::strlen( known_extensions[0].from ); + if( output_filename.size() >= len + 5 ) // "*00001.lz" + for( int i = output_filename.size() - len - 1, j = 0; j < 5; --i, ++j ) + { + if( output_filename[i] < '9' ) { ++output_filename[i]; return true; } + else output_filename[i] = '0'; + } + return false; + } + + +int compress( const long long member_size, const long long volume_size, + lzma_options encoder_options, const int inhandle, + const Pretty_print & pp, const struct stat * in_statsp, + int * retvalp ) + { + if( verbosity >= 1 ) pp(); + File_header header; + header.set_magic(); + if( !header.dictionary_size( encoder_options.dictionary_size ) || + encoder_options.match_len_limit < 5 || + encoder_options.match_len_limit > max_match_len ) + internal_error( "invalid argument to encoder" ); + + try { + Matchfinder matchfinder( header.dictionary_size(), + encoder_options.match_len_limit, inhandle ); + header.dictionary_size( matchfinder.dictionary_size() ); + + long long in_size = 0, out_size = 0, partial_volume_size = 0; + while( true ) + { + LZ_encoder encoder( matchfinder, header, outhandle ); + const long long size = + std::min( member_size, volume_size - partial_volume_size ); + if( !encoder.encode_member( size ) ) + { pp(); show_error( "read error", errno ); return 1; } + in_size += matchfinder.data_position(); + out_size += encoder.member_position(); + if( matchfinder.finished() ) break; + partial_volume_size += encoder.member_position(); + if( partial_volume_size >= volume_size - min_dictionary_size ) + { + partial_volume_size = 0; + if( delete_output_on_interrupt ) + { + close_and_set_permissions( in_statsp, retvalp ); + if( !next_filename() ) + { pp(); show_error( "too many volume files" ); return 1; } + if( !open_outstream( true ) ) return 1; + delete_output_on_interrupt = true; + } + } + if( !matchfinder.reset() ) + { pp(); show_error( "read error", errno ); return 1; } + } + + if( verbosity >= 1 ) + { + if( in_size <= 0 || out_size <= 0 ) + std::fprintf( stderr, "no data compressed.\n" ); + else + std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, " + "%5.2f%% saved, %lld in, %lld out.\n", + (double)in_size / out_size, + ( 8.0 * out_size ) / in_size, + 100.0 * ( 1.0 - ( (double)out_size / in_size ) ), + in_size, out_size ); + } + } + catch( std::bad_alloc ) + { + pp( "not enough memory. Try a smaller dictionary size" ); + return 1; + } + catch( Error e ) { pp(); show_error( e.s, errno ); return 1; } + return 0; + } + + +int decompress( const int inhandle, const Pretty_print & pp, + const bool testing ) + { + try { + Input_buffer ibuf( inhandle ); + long long partial_file_pos = 0; + for( bool first_pass = true; ; first_pass = false, pp.reset() ) + { + File_header header; + for( unsigned int i = 0; i < sizeof header; ++i ) + ((uint8_t *)&header)[i] = ibuf.read_byte(); + if( ibuf.finished() ) + { + if( first_pass ) { pp( "error reading member header" ); return 1; } + else break; + } + if( !header.verify_magic() ) + { + if( !first_pass ) break; + if( verbosity >= 0 ) + { pp(); + std::fprintf( stderr, "bad magic number (file not created by %s).\n", + program_name ); } + return 2; + } + if( !header.verify_version() ) + { + if( verbosity >= 0 ) + { pp(); + std::fprintf( stderr, "version %d member format not supported, newer %s needed.\n", + header.version, program_name ); } + return 2; + } + if( header.dictionary_size() < min_dictionary_size || + header.dictionary_size() > max_dictionary_size ) + { pp( "invalid dictionary size in member header" ); return 2; } + + if( verbosity >= 1 ) + { + pp(); + if( verbosity >= 2 ) + std::fprintf( stderr, "version %d, dictionary size %7sB. ", + header.version, + format_num( header.dictionary_size() ) ); + } + LZ_decoder decoder( header, ibuf, outhandle ); + + const int result = decoder.decode_member( pp ); + partial_file_pos += decoder.member_position(); + if( result != 0 ) + { + if( verbosity >= 0 && result <= 2 ) + { + pp(); + if( result == 2 ) + std::fprintf( stderr, "file ends unexpectedly at pos %lld\n", + partial_file_pos ); + else + std::fprintf( stderr, "decoder error at pos %lld\n", + partial_file_pos ); + } + return 2; + } + if( verbosity >= 1 ) + { if( testing ) std::fprintf( stderr, "ok\n" ); + else std::fprintf( stderr, "done\n" ); } + } + } + catch( std::bad_alloc ) + { + pp( "not enough memory. Find a machine with more memory" ); + return 1; + } + catch( Error e ) { pp(); show_error( e.s, errno ); return 1; } + return 0; + } + + +void signal_handler( const int ) throw() + { + show_error( "Control-C or similar caught, quitting." ); + cleanup_and_fail( 0 ); + } + + +void set_signals() throw() + { + signal( SIGTERM, signal_handler ); + signal( SIGHUP, signal_handler ); + signal( SIGINT, signal_handler ); + } + +} // end namespace + + +int verbosity = 0; + + +void Pretty_print::operator()( const char * const msg ) const throw() + { + if( verbosity >= 0 ) + { + if( first_post ) + { + first_post = false; + std::fprintf( stderr, " %s: ", name_.c_str() ); + for( unsigned int i = 0; i < longest_name - name_.size(); ++i ) + std::fprintf( stderr, " " ); + if( !msg ) std::fflush( stderr ); + } + if( msg ) std::fprintf( stderr, "%s.\n", msg ); + } + } + + +void show_error( const char * msg, const int errcode, const bool help ) throw() + { + if( verbosity >= 0 ) + { + if( msg && msg[0] != 0 ) + { + std::fprintf( stderr, "%s: %s", program_name, msg ); + if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) ); + std::fprintf( stderr, "\n" ); + } + if( help && invocation_name && invocation_name[0] != 0 ) + std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name ); + } + } + + +void internal_error( const char * msg ) + { + std::string s( "internal error: " ); s += msg; + show_error( s.c_str() ); + std::exit( 3 ); + } + + +// Returns the number of bytes really read. +// If (returned value < size) and (errno == 0), means EOF was reached. +// +int readblock( const int fd, char * buf, const int size ) throw() + { + int rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = read( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( n == 0 ) break; + else if( errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +// Returns the number of bytes really written. +// If (returned value < size), it is always an error. +// +int writeblock( const int fd, const char * buf, const int size ) throw() + { + int rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = write( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( errno && errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +int main( const int argc, const char * argv[] ) + { + // Mapping from gzip/bzip2 style 1..9 compression modes + // to the corresponding LZMA compression modes. + const lzma_options option_mapping[] = + { + { 1 << 22, 10 }, // -1 + { 1 << 22, 12 }, // -2 + { 1 << 22, 17 }, // -3 + { 1 << 22, 26 }, // -4 + { 1 << 22, 44 }, // -5 + { 1 << 23, 80 }, // -6 + { 1 << 24, 108 }, // -7 + { 1 << 24, 163 }, // -8 + { 1 << 25, 273 } }; // -9 + lzma_options encoder_options = option_mapping[5]; // default = "-6" + long long member_size = LLONG_MAX; + long long volume_size = LLONG_MAX; + int inhandle = -1; + Mode program_mode = m_compress; + bool force = false; + bool keep_input_files = false; + bool to_stdout = false; + std::string input_filename; + std::string default_output_filename; + std::vector< std::string > filenames; + invocation_name = argv[0]; + + const Arg_parser::Option options[] = + { + { '1', "fast", Arg_parser::no }, + { '2', 0, Arg_parser::no }, + { '3', 0, Arg_parser::no }, + { '4', 0, Arg_parser::no }, + { '5', 0, Arg_parser::no }, + { '6', 0, Arg_parser::no }, + { '7', 0, Arg_parser::no }, + { '8', 0, Arg_parser::no }, + { '9', "best", Arg_parser::no }, + { 'b', "member-size", Arg_parser::yes }, + { 'c', "stdout", Arg_parser::no }, + { 'd', "decompress", Arg_parser::no }, + { 'f', "force", Arg_parser::no }, + { 'h', "help", Arg_parser::no }, + { 'k', "keep", Arg_parser::no }, + { 'm', "match-length", Arg_parser::yes }, + { 'o', "output", Arg_parser::yes }, + { 'q', "quiet", Arg_parser::no }, + { 's', "dictionary-size", Arg_parser::yes }, + { 'S', "volume-size", Arg_parser::yes }, + { 't', "test", Arg_parser::no }, + { 'v', "verbose", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + Arg_parser parser( argc, argv, options ); + if( parser.error().size() ) // bad option + { show_error( parser.error().c_str(), 0, true ); return 1; } + + int argind = 0; + for( ; argind < parser.arguments(); ++argind ) + { + const int code = parser.code( argind ); + if( !code ) break; // no more options + const char * arg = parser.argument( argind ).c_str(); + switch( code ) + { + case '1': case '2': case '3': + case '4': case '5': case '6': + case '7': case '8': case '9': + encoder_options = option_mapping[code-'1']; break; + case 'b': member_size = getnum( arg, 0, 100000, LLONG_MAX / 2 ); break; + case 'c': to_stdout = true; break; + case 'd': program_mode = m_decompress; break; + case 'f': force = true; break; + case 'h': show_help(); return 0; + case 'k': keep_input_files = true; break; + case 'm': encoder_options.match_len_limit = + getnum( arg, 0, 5, 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 < parser.arguments(); ++argind ) + { + if( parser.argument( argind ) != "-" ) filenames_given = true; + filenames.push_back( parser.argument( argind ) ); + } + + if( filenames.empty() ) filenames.push_back("-"); + if( filenames_given ) set_signals(); + + Pretty_print pp( filenames ); + if( program_mode == m_compress ) + { + dis_slots.init(); + prob_prices.init(); + } + else if( program_mode == m_test ) + outhandle = -1; + + int retval = 0; + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + struct stat in_stats; + output_filename.clear(); + + if( !filenames[i].size() || filenames[i] == "-" ) + { + input_filename.clear(); + inhandle = STDIN_FILENO; + if( program_mode != m_test ) + { + if( to_stdout || !default_output_filename.size() ) + outhandle = STDOUT_FILENO; + else + { + if( program_mode == m_compress ) + set_c_outname( default_output_filename, volume_size != LLONG_MAX ); + else output_filename = default_output_filename; + if( !open_outstream( force ) ) + { + if( outhandle == -1 && retval < 1 ) retval = 1; + close( inhandle ); inhandle = -1; + continue; + } + } + } + } + else + { + input_filename = filenames[i]; + const int eindex = extension_index( input_filename ); + inhandle = open_instream( input_filename, &in_stats, program_mode, + eindex, force, to_stdout ); + if( inhandle < 0 ) continue; + if( program_mode != m_test ) + { + if( to_stdout ) outhandle = STDOUT_FILENO; + else + { + if( program_mode == m_compress ) + set_c_outname( input_filename, volume_size != LLONG_MAX ); + else set_d_outname( input_filename, eindex ); + if( !open_outstream( force ) ) + { + if( outhandle == -1 && retval < 1 ) retval = 1; + close( inhandle ); inhandle = -1; + continue; + } + } + } + } + + if( !check_tty( inhandle, program_mode ) ) return 1; + + if( output_filename.size() && !to_stdout && program_mode != m_test ) + delete_output_on_interrupt = true; + const struct stat * in_statsp = input_filename.size() ? &in_stats : 0; + pp.set_name( input_filename ); + int tmp = 0; + if( program_mode == m_compress ) + tmp = compress( member_size, volume_size, encoder_options, inhandle, + pp, in_statsp, &retval ); + else + tmp = decompress( inhandle, pp, program_mode == m_test ); + if( tmp > retval ) retval = tmp; + if( tmp && program_mode != m_test ) cleanup_and_fail( retval ); + + if( delete_output_on_interrupt ) + close_and_set_permissions( in_statsp, &retval ); + if( input_filename.size() ) + { + close( inhandle ); inhandle = -1; + if( !keep_input_files && !to_stdout && program_mode != m_test ) + std::remove( input_filename.c_str() ); + } + } + if( outhandle >= 0 ) close( outhandle ); + return retval; + } diff --git a/testsuite/COPYING.lz b/testsuite/COPYING.lz new file mode 100644 index 0000000..a09b1e8 Binary files /dev/null and b/testsuite/COPYING.lz differ diff --git a/testsuite/check.sh b/testsuite/check.sh new file mode 100755 index 0000000..83ebc6f --- /dev/null +++ b/testsuite/check.sh @@ -0,0 +1,67 @@ +#! /bin/sh +# check script for Lzip - A data compressor based on the LZMA algorithm +# Copyright (C) 2008, 2009 Antonio Diaz Diaz. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +objdir=`pwd` +testdir=`cd "$1" ; pwd` +LZIP="${objdir}"/lzip +framework_failure() { echo 'failure in testing framework'; exit 1; } + +if [ ! -x "${LZIP}" ] ; then + echo "${LZIP}: cannot execute" + exit 1 +fi + +if [ -d tmp ] ; then rm -r tmp ; fi +mkdir tmp +echo -n "testing lzip..." +cd "${objdir}"/tmp + +cat "${testdir}"/../COPYING > in || framework_failure +fail=0 + +"${LZIP}" -cd "${testdir}"/COPYING.lz > copy || fail=1 +cmp in copy || fail=1 + +for i in 1 2 3 4 5 6 7 8 9; do + "${LZIP}" -k -$i in || fail=1 + mv -f in.lz copy.lz || fail=1 + echo -n "garbage" >> copy.lz || fail=1 + "${LZIP}" -df copy.lz || fail=1 + cmp in copy || fail=1 + echo -n . +done + +for i in 1 2 3 4 5 6 7 8 9; do + "${LZIP}" -c -$i in > out || fail=1 + echo -n "g" >> out || fail=1 + "${LZIP}" -cd out > copy || fail=1 + cmp in copy || fail=1 + echo -n . +done + +for i in 1 2 3 4 5 6 7 8 9; do + "${LZIP}" -c -$i < in > out || fail=1 + "${LZIP}" -d < out > copy || fail=1 + cmp in copy || fail=1 + echo -n . +done + +for i in 1 2 3 4 5 6 7 8 9; do + "${LZIP}" -f -$i -o out < in || fail=1 + "${LZIP}" -df -o copy < out.lz || fail=1 + cmp in copy || fail=1 + echo -n . +done + +echo +if test ${fail} = 0; then + echo "tests completed successfully." + if cd "${objdir}" ; then rm -r tmp ; fi +else + echo "tests failed." +fi +exit ${fail} diff --git a/testsuite/unzcrash.cc b/testsuite/unzcrash.cc new file mode 100644 index 0000000..bf44628 --- /dev/null +++ b/testsuite/unzcrash.cc @@ -0,0 +1,85 @@ +/* Unzcrash - A test program written to test robustness to + decompression of corrupted data. + Inspired by unzcrash.c from Julian Seward's bzip2. + Copyright (C) 2008, 2009 Antonio Diaz Diaz. + + This program is free software: you have unlimited permission + to copy, distribute and modify it. + + Usage is: + unzcrash "lzip -tv" filename.lz + + This program reads the specified file and then repeatedly + decompresses it, increasing 256 times each byte of the compressed + data, so as to test all possible one-byte errors. This should not + cause any invalid memory accesses. If it does, please, report it as + a bug. + + Compile this file with the command: + g++ -O2 -Wall -W -o unzcrash testsuite/unzcrash.cc +*/ + +#include +#include +#include +#include +#include + + +int main( const int argc, const char * argv[] ) + { + if( argc < 3 ) + { + std::fprintf( stderr, "Usage: unzcrash \"lzip -tv\" filename.lz\n" ); + return 1; + } + + FILE *f = std::fopen( argv[2], "rb" ); + if( !f ) + { + std::fprintf( stderr, "Can't open file `%s' for reading\n", argv[2] ); + return 1; + } + + const int buffer_size = 1 << 20; + uint8_t buffer[buffer_size]; + const int size = std::fread( buffer, 1, buffer_size, f ); + if( size >= buffer_size ) + { + std::fprintf( stderr, "input file `%s' too big.\n", argv[2] ); + return 1; + } + std::fclose( f ); + + f = popen( argv[1], "w" ); + if( !f ) + { + std::fprintf( stderr, "incorrect parameters or too many files.\n" ); + return 1; + } + const int wr = std::fwrite( buffer, 1, size, f ); + if( wr != size || pclose( f ) != 0 ) + { + std::fprintf( stderr, "Could not run `%s' or other error.\n", argv[1] ); + return 1; + } + + signal( SIGPIPE, SIG_IGN ); + + for( int byte = 0; byte < size; ++byte ) + { + std::fprintf( stderr, "byte %d\n", byte ); + for( int i = 0; i < 255; ++i ) + { + ++buffer[byte]; + f = popen( argv[1], "w" ); + if( !f ) + { std::fprintf( stderr, "Can't open pipe.\n" ); return 1; } + std::fwrite( buffer, 1, size, f ); + pclose( f ); + } + ++buffer[byte]; + } + + return 0; + } -- cgit v1.2.3