diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | COPYING | 676 | ||||
| -rw-r--r-- | ChangeLog | 55 | ||||
| -rw-r--r-- | INSTALL | 57 | ||||
| -rw-r--r-- | Makefile.in | 111 | ||||
| -rw-r--r-- | NEWS | 10 | ||||
| -rw-r--r-- | README | 34 | ||||
| -rw-r--r-- | arg_parser.cc | 203 | ||||
| -rw-r--r-- | arg_parser.h | 105 | ||||
| -rwxr-xr-x | configure | 192 | ||||
| -rw-r--r-- | decoder.cc | 310 | ||||
| -rw-r--r-- | decoder.h | 268 | ||||
| -rw-r--r-- | doc/lziprecover.1 | 71 | ||||
| -rw-r--r-- | doc/lziprecover.info | 368 | ||||
| -rw-r--r-- | doc/lziprecover.texinfo | 397 | ||||
| -rw-r--r-- | lzip.h | 323 | ||||
| -rw-r--r-- | main.cc | 676 | ||||
| -rw-r--r-- | merge.cc | 406 | ||||
| -rw-r--r-- | repair.cc | 114 | ||||
| -rw-r--r-- | split.cc | 176 | ||||
| -rwxr-xr-x | testsuite/check.sh | 103 | ||||
| -rw-r--r-- | testsuite/test.txt | 676 | ||||
| -rw-r--r-- | testsuite/test_bad1.lz | bin | 0 -> 11548 bytes | |||
| -rw-r--r-- | testsuite/test_bad2.lz | bin | 0 -> 11548 bytes | |||
| -rw-r--r-- | testsuite/test_bad3.lz | bin | 0 -> 11548 bytes | |||
| -rw-r--r-- | testsuite/test_bad4.lz | bin | 0 -> 11548 bytes | |||
| -rw-r--r-- | testsuite/test_bad5.lz | bin | 0 -> 11548 bytes | |||
| -rw-r--r-- | testsuite/test_v0.lz | bin | 0 -> 11540 bytes | |||
| -rw-r--r-- | testsuite/test_v1.lz | bin | 0 -> 11548 bytes |
29 files changed, 5332 insertions, 0 deletions
@@ -0,0 +1 @@ +Lziprecover was written by Antonio Diaz Diaz. @@ -0,0 +1,676 @@ + + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/> + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + <program> Copyright (C) <year> <name of author> + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +<http://www.gnu.org/licenses/>. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +<http://www.gnu.org/philosophy/why-not-lgpl.html>. + diff --git a/ChangeLog b/ChangeLog new file mode 100644 index 0000000..15e7746 --- /dev/null +++ b/ChangeLog @@ -0,0 +1,55 @@ +2011-11-12 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 1.13-rc1 released. + * Lziprecover is now distributed in its own package. Until + version 1.12 it was included in the lzip package. + * lziprecover.cc: Renamed to main.cc. + * main.cc: Added decompressor options (-c, -d, -k, -t) so that + a external decompressor is not needed for recovery nor for + "make check". + * New files merge.cc, repair.cc and split.cc. + * merge.cc repair.cc: Remove output file if recovery fails. + * split.cc: Use Boyer-Moore algorithm to search for headers. + * testsuite/check.sh: Use `ln' instead of `cat' for input files. + +2011-04-30 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 1.12 released. + * lziprecover.cc: If `-v' is not specified show errors only. + +2010-09-16 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 1.11 released. + * lziprecover.cc: Added new option `-m, --merge' which tries to + produce a correct file merging the good parts of two or more + damaged copies. + * lziprecover.cc: Added new option `-R, --repair' for repairing + a 1-byte error in single-member files. + * decoder.cc (decode_member): Detect file errors earlier to + improve efficiency of lziprecover's new repair capability. + This change also prevents (harmless) access to uninitialized + memory when decompressing a corrupt file. + * lziprecover.cc: Added new option `-f, --force'. + * lziprecover.cc: Added new option `-o, --output'. + * lziprecover.cc: Added new option `-s, --split' to select the + until now only operation of splitting multimember files. + * lziprecover.cc: If no operation is specified, warn the user + and do nothing. + +2009-06-22 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 1.6 released. + * Added man page for lziprecover. + * testsuite/check.sh: Test lziprecover. + +2009-01-24 Antonio Diaz Diaz <ant_diaz@teleline.es> + + * Version 1.4 released. + * Added `lziprecover', a member recoverer program. + + +Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + +This file is a collection of facts, and thus it is not copyrightable, +but just in case, you have unlimited permission to copy, distribute and +modify it. @@ -0,0 +1,57 @@ +Requirements +------------ +You will need a C++ compiler. +I use gcc 4.3.5 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 lziprecover[version].tar.lz | tar -xf - +or + gzip -cd lziprecover[version].tar.gz | tar -xf - + +This creates the directory ./lziprecover[version] containing the source +from the main archive. + +2. Change to lziprecover directory and run configure. + (Try `configure --help' for usage instructions). + + cd lziprecover[version] + ./configure + +3. Run make. + + make + +4. Optionally, type `make check' to run the tests that come with + lziprecover. + +5. Type `make install' to install the programs and any data files and + documentation. + + +Another way +----------- +You can also compile lziprecover into a separate directory. To do this, +you must use a version of `make' that supports the `VPATH' variable, +such as GNU `make'. `cd' to the directory where you want the object +files and executables to go and run the `configure' script. `configure' +automatically checks for the source code in `.', in `..' and in the +directory that `configure' is in. + +`configure' recognizes the option `--srcdir=DIR' to control where to +look for the sources. Usually `configure' can determine that directory +automatically. + +After running `configure', you can run `make' and `make install' as +explained above. + + +Copyright (C) 2009, 2010, 2011 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..6c12f88 --- /dev/null +++ b/Makefile.in @@ -0,0 +1,111 @@ + +DISTNAME = $(pkgname)-$(pkgversion) +INSTALL = install +INSTALL_PROGRAM = $(INSTALL) -p -m 755 +INSTALL_DATA = $(INSTALL) -p -m 644 +INSTALL_DIR = $(INSTALL) -d -m 755 +SHELL = /bin/sh + +objs = arg_parser.o decoder.o merge.o repair.o split.o main.o + + +.PHONY : all install install-info install-man install-strip \ + uninstall uninstall-info uninstall-man \ + doc info man check dist clean distclean + +all : $(progname) + +$(progname) : $(objs) + $(CXX) $(LDFLAGS) -o $@ $(objs) + +$(progname)_profiled : $(objs) + $(CXX) $(LDFLAGS) -pg -o $@ $(objs) + +main.o : main.cc + $(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $< + +%.o : %.cc + $(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $< + +$(objs) : Makefile +arg_parser.o : arg_parser.h +decoder.o : lzip.h decoder.h +main.o : arg_parser.h lzip.h decoder.h +merge.o : lzip.h decoder.h +repair.o : lzip.h +split.o : lzip.h + + +doc : info man + +info : $(VPATH)/doc/$(pkgname).info + +$(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo + cd $(VPATH)/doc && makeinfo $(pkgname).texinfo + +man : $(VPATH)/doc/$(progname).1 + +$(VPATH)/doc/$(progname).1 : $(progname) + help2man -n 'recovers data from damaged lzip files' \ + -o $@ ./$(progname) + +Makefile : $(VPATH)/configure $(VPATH)/Makefile.in + ./config.status + +check : all + @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite $(pkgversion) + +install : all install-info install-man + if [ ! -d "$(DESTDIR)$(bindir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(bindir)" ; fi + $(INSTALL_PROGRAM) ./$(progname) "$(DESTDIR)$(bindir)/$(progname)" + +install-info : + if [ ! -d "$(DESTDIR)$(infodir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(infodir)" ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(pkgname).info "$(DESTDIR)$(infodir)/$(pkgname).info" + -install-info --info-dir="$(DESTDIR)$(infodir)" $(DESTDIR)$(infodir)/$(pkgname).info + +install-man : + if [ ! -d "$(DESTDIR)$(mandir)/man1" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1" ; fi + $(INSTALL_DATA) $(VPATH)/doc/$(progname).1 "$(DESTDIR)$(mandir)/man1/$(progname).1" + +install-strip : all + $(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install + +uninstall : uninstall-info uninstall-man + -rm -f "$(DESTDIR)$(bindir)/$(progname)" + +uninstall-info : + -install-info --info-dir="$(DESTDIR)$(infodir)" --remove "$(DESTDIR)$(infodir)/$(pkgname).info" + -rm -f "$(DESTDIR)$(infodir)/$(pkgname).info" + +uninstall-man : + -rm -f "$(DESTDIR)$(mandir)/man1/$(progname).1" + +dist : doc + ln -sf $(VPATH) $(DISTNAME) + tar -cvf $(DISTNAME).tar \ + $(DISTNAME)/AUTHORS \ + $(DISTNAME)/COPYING \ + $(DISTNAME)/ChangeLog \ + $(DISTNAME)/INSTALL \ + $(DISTNAME)/Makefile.in \ + $(DISTNAME)/NEWS \ + $(DISTNAME)/README \ + $(DISTNAME)/configure \ + $(DISTNAME)/doc/$(progname).1 \ + $(DISTNAME)/doc/$(pkgname).info \ + $(DISTNAME)/doc/$(pkgname).texinfo \ + $(DISTNAME)/testsuite/check.sh \ + $(DISTNAME)/testsuite/test.txt \ + $(DISTNAME)/testsuite/test_bad[1-5].lz \ + $(DISTNAME)/testsuite/test_v[01].lz \ + $(DISTNAME)/*.h \ + $(DISTNAME)/*.cc + rm -f $(DISTNAME) + lzip -v -9 $(DISTNAME).tar + +clean : + -rm -f $(progname) $(progname)_profiled $(objs) + +distclean : clean + -rm -f Makefile config.status *.tar *.tar.lz @@ -0,0 +1,10 @@ +Changes in version 1.13: + +Lziprecover is now distributed in its own package. Until version 1.12 it +was included in the lzip package. + +Decompressor options (-c, -d, -k, -t) have been implemented in +lziprecover so that a external decompressor is not needed for recovery +nor for "make check". + +"--merge" and "--repair" now remove the output file if recovery fails. @@ -0,0 +1,34 @@ +Description + +Lziprecover is a data recovery tool and decompressor for files in the +lzip compressed data format (.lz) able to repair slightly damaged files, +recover badly damaged files from two or more copies, extract undamaged +members from multi-member files, decompress files and test integrity of +files. + +Lziprecover is able to recover or decompress files produced by any of +the compressors in the lzip family; lzip, plzip, minilzip/lzlib, clzip +and pdlzip. This recovery capability contributes to make the lzip format +one of the best options for long-term data archiving. + +When recovering data, lziprecover takes as arguments the names of the +damaged files and writes zero or more recovered files depending on the +operation selected and whether the recovery succeeded or not. The +damaged files themselves are never modified. + +When decompressing or testing file integrity, lziprecover behaves like +lzip or lunzip. + +If the files are too damaged for lziprecover to repair them, data from +damaged members can be partially recovered writing it to stdout. + +To give you an idea of its possibilities, when merging two copies each +of them with one damaged area affecting 1 percent of the copy, the +probability of obtaining a correct file is about 98 percent. With three +such copies the probability rises to 99.97 percent. For large files with +small errors, the probability approaches 100 percent even with only two +copies. + +If the cause of file corruption is damaged media, the combination +GNU ddrescue + lziprecover is the best option for recovering data from +multiple damaged copies. diff --git a/arg_parser.cc b/arg_parser.cc new file mode 100644 index 0000000..bc4b4a3 --- /dev/null +++ b/arg_parser.cc @@ -0,0 +1,203 @@ +/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) + Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011 Antonio Diaz Diaz. + + This library is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this library. If not, see <http://www.gnu.org/licenses/>. + + As a special exception, you may use this file as part of a free + software library without restriction. Specifically, if other files + instantiate templates or use macros or inline functions from this + file, or you compile this file and link it with other files to + produce an executable, this file does not by itself cause the + resulting executable to be covered by the GNU General Public + License. This exception does not however invalidate any other + reasons why the executable file might be covered by the GNU General + Public License. +*/ + +#include <cstring> +#include <string> +#include <vector> + +#include "arg_parser.h" + + +bool Arg_parser::parse_long_option( const char * const opt, const char * const arg, + const Option options[], int & argind ) + { + unsigned int len; + int index = -1; + bool exact = false, ambig = false; + + for( len = 0; opt[len+2] && opt[len+2] != '='; ++len ) ; + + // Test all long options for either exact match or abbreviated matches. + for( int i = 0; options[i].code != 0; ++i ) + if( options[i].name && !std::strncmp( options[i].name, &opt[2], len ) ) + { + if( std::strlen( options[i].name ) == len ) // Exact match found + { index = i; exact = true; break; } + else if( index < 0 ) index = i; // First nonexact match found + else if( options[index].code != options[i].code || + options[index].has_arg != options[i].has_arg ) + ambig = true; // Second or later nonexact match found + } + + if( ambig && !exact ) + { + error_ = "option `"; error_ += opt; error_ += "' is ambiguous"; + return false; + } + + if( index < 0 ) // nothing found + { + error_ = "unrecognized option `"; error_ += opt; error_ += '\''; + return false; + } + + ++argind; + data.push_back( Record( options[index].code ) ); + + if( opt[len+2] ) // `--<long_option>=<argument>' syntax + { + if( options[index].has_arg == no ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' doesn't allow an argument"; + return false; + } + if( options[index].has_arg == yes && !opt[len+3] ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' requires an argument"; + return false; + } + data.back().argument = &opt[len+3]; + return true; + } + + if( options[index].has_arg == yes ) + { + if( !arg || !arg[0] ) + { + error_ = "option `--"; error_ += options[index].name; + error_ += "' requires an argument"; + return false; + } + ++argind; data.back().argument = arg; + return true; + } + + return true; + } + + +bool Arg_parser::parse_short_option( const char * const opt, const char * const arg, + const Option options[], int & argind ) + { + int cind = 1; // character index in opt + + while( cind > 0 ) + { + int index = -1; + const unsigned char c = opt[cind]; + + if( c != 0 ) + for( int i = 0; options[i].code; ++i ) + if( c == options[i].code ) + { index = i; break; } + + if( index < 0 ) + { + error_ = "invalid option -- "; error_ += c; + return false; + } + + data.push_back( Record( c ) ); + if( opt[++cind] == 0 ) { ++argind; cind = 0; } // opt finished + + if( options[index].has_arg != no && cind > 0 && opt[cind] ) + { + data.back().argument = &opt[cind]; ++argind; cind = 0; + } + else if( options[index].has_arg == yes ) + { + if( !arg || !arg[0] ) + { + error_ = "option requires an argument -- "; error_ += c; + return false; + } + data.back().argument = arg; ++argind; cind = 0; + } + } + return true; + } + + +Arg_parser::Arg_parser( const int argc, const char * const argv[], + const Option options[], const bool in_order ) + { + if( argc < 2 || !argv || !options ) return; + + std::vector< std::string > non_options; // skipped non-options + int argind = 1; // index in argv + + while( argind < argc ) + { + const unsigned char ch1 = argv[argind][0]; + const unsigned char ch2 = ( ch1 ? argv[argind][1] : 0 ); + + if( ch1 == '-' && ch2 ) // we found an option + { + const char * const opt = argv[argind]; + const char * const arg = (argind + 1 < argc) ? argv[argind+1] : 0; + if( ch2 == '-' ) + { + if( !argv[argind][2] ) { ++argind; break; } // we found "--" + else if( !parse_long_option( opt, arg, options, argind ) ) break; + } + else if( !parse_short_option( opt, arg, options, argind ) ) break; + } + else + { + if( !in_order ) non_options.push_back( argv[argind++] ); + else { data.push_back( Record() ); data.back().argument = argv[argind++]; } + } + } + if( error_.size() ) data.clear(); + else + { + for( unsigned int i = 0; i < non_options.size(); ++i ) + { data.push_back( Record() ); data.back().argument.swap( non_options[i] ); } + while( argind < argc ) + { data.push_back( Record() ); data.back().argument = argv[argind++]; } + } + } + + +Arg_parser::Arg_parser( const char * const opt, const char * const arg, + const Option options[] ) + { + if( !opt || !opt[0] || !options ) return; + + if( opt[0] == '-' && opt[1] ) // we found an option + { + int argind = 1; // dummy + if( opt[1] == '-' ) + { if( opt[2] ) parse_long_option( opt, arg, options, argind ); } + else + parse_short_option( opt, arg, options, argind ); + if( error_.size() ) data.clear(); + } + else { data.push_back( Record() ); data.back().argument = opt; } + } diff --git a/arg_parser.h b/arg_parser.h new file mode 100644 index 0000000..d1e5c02 --- /dev/null +++ b/arg_parser.h @@ -0,0 +1,105 @@ +/* Arg_parser - POSIX/GNU command line argument parser. (C++ version) + Copyright (C) 2006, 2007, 2008, 2009, 2010, 2011 Antonio Diaz Diaz. + + This library is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this library. If not, see <http://www.gnu.org/licenses/>. + + As a special exception, you may use this file as part of a free + software library without restriction. Specifically, if other files + instantiate templates or use macros or inline functions from this + file, or you compile this file and link it with other files to + produce an executable, this file does not by itself cause the + resulting executable to be covered by the GNU General Public + License. This exception does not however invalidate any other + reasons why the executable file might be covered by the GNU General + Public License. +*/ + +/* Arg_parser reads the arguments in `argv' and creates a number of + option codes, option arguments and non-option arguments. + + In case of error, `error' returns a non-empty error message. + + `options' is an array of `struct Option' terminated by an element + containing a code which is zero. A null name means a short-only + option. A code value outside the unsigned char range means a + long-only option. + + Arg_parser normally makes it appear as if all the option arguments + were specified before all the non-option arguments for the purposes + of parsing, even if the user of your program intermixed option and + non-option arguments. If you want the arguments in the exact order + the user typed them, call `Arg_parser' with `in_order' = true. + + The argument `--' terminates all options; any following arguments are + treated as non-option arguments, even if they begin with a hyphen. + + The syntax for optional option arguments is `-<short_option><argument>' + (without whitespace), or `--<long_option>=<argument>'. +*/ + +class Arg_parser + { +public: + enum Has_arg { no, yes, maybe }; + + struct Option + { + int code; // Short option letter or code ( code != 0 ) + const char * name; // Long option name (maybe null) + Has_arg has_arg; + }; + +private: + struct Record + { + int code; + std::string argument; + Record( const int c = 0 ) : code( c ) {} + }; + + std::string error_; + std::vector< Record > data; + + bool parse_long_option( const char * const opt, const char * const arg, + const Option options[], int & argind ); + bool parse_short_option( const char * const opt, const char * const arg, + const Option options[], int & argind ); + +public: + Arg_parser( const int argc, const char * const argv[], + const Option options[], const bool in_order = false ); + + // Restricted constructor. Parses a single token and argument (if any) + Arg_parser( const char * const opt, const char * const arg, + const Option options[] ); + + const std::string & error() const throw() { return error_; } + + // The number of arguments parsed (may be different from argc) + int arguments() const throw() { return data.size(); } + + // If code( i ) is 0, argument( i ) is a non-option. + // Else argument( i ) is the option's argument (or empty). + int code( const int i ) const throw() + { + if( i >= 0 && i < arguments() ) return data[i].code; + else return 0; + } + + const std::string & argument( const int i ) const throw() + { + if( i >= 0 && i < arguments() ) return data[i].argument; + else return error_; + } + }; diff --git a/configure b/configure new file mode 100755 index 0000000..43bf621 --- /dev/null +++ b/configure @@ -0,0 +1,192 @@ +#! /bin/sh +# configure script for Lziprecover - Data recovery tool for lzipped files +# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. +# +# This configure script is free software: you have unlimited permission +# to copy, distribute and modify it. + +args= +no_create= +pkgname=lziprecover +pkgversion=1.13-rc1 +progname=lziprecover +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' +CXX= +CPPFLAGS= +CXXFLAGS='-Wall -W -O2' +LDFLAGS= + +# Loop over all args +while [ -n "$1" ] ; do + + # Get the first arg, and shuffle + option=$1 + shift + + # Add the argument quoted to args + args="${args} \"${option}\"" + + # Split out the argument for options that take them + case ${option} in + *=*) optarg=`echo ${option} | sed -e 's,^[^=]*=,,'` ;; + esac + + # Process the options + case ${option} in + --help | --he* | -h) + echo "Usage: configure [options]" + echo + echo "Options: [defaults in brackets]" + echo " -h, --help display this help and exit" + echo " -V, --version output version information and exit" + echo " --srcdir=DIR find the sources in DIR [. or ..]" + echo " --prefix=DIR install into DIR [${prefix}]" + echo " --exec-prefix=DIR base directory for arch-dependent files [${exec_prefix}]" + echo " --bindir=DIR user executables directory [${bindir}]" + echo " --datadir=DIR base directory for doc and data [${datadir}]" + echo " --infodir=DIR info files directory [${infodir}]" + echo " --mandir=DIR man pages directory [${mandir}]" + echo " --sysconfdir=DIR read-only single-machine data directory [${sysconfdir}]" + echo " CXX=COMPILER C++ compiler to use [g++]" + echo " CPPFLAGS=OPTIONS command line options for the preprocessor [${CPPFLAGS}]" + echo " CXXFLAGS=OPTIONS command line options for the C++ compiler [${CXXFLAGS}]" + echo " LDFLAGS=OPTIONS command line options for the linker [${LDFLAGS}]" + echo + exit 0 ;; + --version | --ve* | -V) + echo "Configure script for ${pkgname} version ${pkgversion}" + exit 0 ;; + --srcdir* | --sr*) + srcdir=`echo ${optarg} | sed -e 's,/$,,'` ;; + --prefix* | --pr*) + prefix=`echo ${optarg} | sed -e 's,/$,,'` ;; + --exec-prefix* | --ex*) + exec_prefix=`echo ${optarg} | sed -e 's,/$,,'` ;; + --bindir* | --bi*) + bindir=`echo ${optarg} | sed -e 's,/$,,'` ;; + --datadir* | --da*) + datadir=`echo ${optarg} | sed -e 's,/$,,'` ;; + --infodir* | --inf*) + 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 ;; + + CXX=*) CXX=${optarg} ;; + CPPFLAGS=*) CPPFLAGS=${optarg} ;; + CXXFLAGS=*) CXXFLAGS=${optarg} ;; + LDFLAGS=*) LDFLAGS=${optarg} ;; + + --* | *=* | *-*-*) ;; + *) + echo "configure: Unrecognized option: \"${option}\"; use --help for usage." 1>&2 + exit 1 ;; + esac +done + +# Find the source files, if location was not specified. +srcdirtext= +if [ -z "${srcdir}" ] ; then + srcdirtext="or . or .." ; srcdir=. + if [ ! -r ${srcdir}/${srctrigger} ] ; then srcdir=.. ; fi + if [ ! -r ${srcdir}/${srctrigger} ] ; then + ## the sed command below emulates the dirname command + srcdir=`echo $0 | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'` + fi +fi + +if [ ! -r ${srcdir}/${srctrigger} ] ; then + exec 1>&2 + echo + echo "configure: Can't find sources in ${srcdir} ${srcdirtext}" + echo "configure: (At least ${srctrigger} is missing)." + exit 1 +fi + +# Set srcdir to . if that's what it is. +if [ "`pwd`" = "`cd ${srcdir} ; pwd`" ] ; then srcdir=. ; fi + +# checking whether we are using GNU C++. +if [ -z "${CXX}" ] ; 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 [ -z "${no_create}" ] ; then + echo "creating config.status" + rm -f config.status + cat > config.status << EOF +#! /bin/sh +# This file was generated automatically by configure. Do not edit. +# Run this file to recreate the current configuration. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +exec /bin/sh $0 ${args} --no-create +EOF + chmod +x config.status +fi + +echo "creating Makefile" +echo "VPATH = ${srcdir}" +echo "prefix = ${prefix}" +echo "exec_prefix = ${exec_prefix}" +echo "bindir = ${bindir}" +echo "datadir = ${datadir}" +echo "infodir = ${infodir}" +echo "mandir = ${mandir}" +echo "sysconfdir = ${sysconfdir}" +echo "CXX = ${CXX}" +echo "CPPFLAGS = ${CPPFLAGS}" +echo "CXXFLAGS = ${CXXFLAGS}" +echo "LDFLAGS = ${LDFLAGS}" +rm -f Makefile +cat > Makefile << EOF +# Makefile for Lziprecover - Data recovery tool for lzipped files +# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. +# This file was generated automatically by configure. Do not edit. +# +# This Makefile is free software: you have unlimited permission +# to copy, distribute and modify it. + +pkgname = ${pkgname} +pkgversion = ${pkgversion} +progname = ${progname} +VPATH = ${srcdir} +prefix = ${prefix} +exec_prefix = ${exec_prefix} +bindir = ${bindir} +datadir = ${datadir} +infodir = ${infodir} +mandir = ${mandir} +sysconfdir = ${sysconfdir} +CXX = ${CXX} +CPPFLAGS = ${CPPFLAGS} +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..b9fc3d8 --- /dev/null +++ b/decoder.cc @@ -0,0 +1,310 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <algorithm> +#include <cerrno> +#include <cstdio> +#include <cstdlib> +#include <cstring> +#include <string> +#include <vector> +#include <stdint.h> +#include <unistd.h> + +#include "lzip.h" +#include "decoder.h" + + +const CRC32 crc32; + + +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 ); + } + } + + +// Returns the number of bytes really read. +// If (returned value < size) and (errno == 0), means EOF was reached. +// +int readblock( const int fd, uint8_t * const buf, const int size ) 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 uint8_t * const 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; + } + + +bool Range_decoder::read_block() + { + if( !at_stream_end ) + { + stream_pos = readblock( infd, buffer, buffer_size ); + if( stream_pos != buffer_size && errno ) throw Error( "Read error" ); + at_stream_end = ( stream_pos < buffer_size ); + partial_member_pos += pos; + pos = 0; + } + return pos < stream_pos; + } + + +void LZ_decoder::flush_data() + { + const int size = pos - stream_pos; + if( size > 0 ) + { + crc32.update( crc_, buffer + stream_pos, size ); + if( outfd >= 0 && + writeblock( outfd, buffer + stream_pos, size ) != size ) + throw Error( "Write error" ); + if( pos >= buffer_size ) { partial_data_pos += pos; pos = 0; } + stream_pos = pos; + } + } + + +bool LZ_decoder::verify_trailer( const Pretty_print & pp ) const + { + File_trailer trailer; + const int trailer_size = File_trailer::size( member_version ); + const long long member_size = range_decoder.member_position() + trailer_size; + bool error = false; + + for( int i = 0; i < trailer_size && !error; ++i ) + { + if( !range_decoder.finished() ) + trailer.data[i] = range_decoder.get_byte(); + else + { + error = true; + if( pp.verbosity() >= 0 ) + { + pp(); + std::fprintf( stderr, "Trailer truncated at trailer position %d;" + " some checks may fail.\n", i ); + } + for( ; i < trailer_size; ++i ) trailer.data[i] = 0; + } + } + if( member_version == 0 ) trailer.member_size( member_size ); + if( !range_decoder.code_is_zero() ) + { + error = true; + pp( "Range decoder final code is not zero" ); + } + if( trailer.data_crc() != crc() ) + { + error = true; + if( pp.verbosity() >= 0 ) + { + pp(); + std::fprintf( stderr, "CRC mismatch; trailer says %08X, data CRC is %08X.\n", + (unsigned int)trailer.data_crc(), (unsigned int)crc() ); + } + } + if( trailer.data_size() != data_position() ) + { + error = true; + if( pp.verbosity() >= 0 ) + { + pp(); + std::fprintf( stderr, "Data size mismatch; trailer says %lld, data size is %lld (0x%llX).\n", + trailer.data_size(), data_position(), data_position() ); + } + } + if( trailer.member_size() != member_size ) + { + error = true; + if( pp.verbosity() >= 0 ) + { + pp(); + std::fprintf( stderr, "Member size mismatch; trailer says %lld, member size is %lld (0x%llX).\n", + trailer.member_size(), member_size, member_size ); + } + } + if( !error && pp.verbosity() >= 3 && data_position() > 0 && member_size > 0 ) + std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, %5.2f%% saved. ", + (double)data_position() / member_size, + ( 8.0 * member_size ) / data_position(), + 100.0 * ( 1.0 - ( (double)member_size / data_position() ) ) ); + if( !error && pp.verbosity() >= 4 ) + std::fprintf( stderr, "data CRC %08X, data size %9lld, member size %8lld. ", + (unsigned int)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 ) + { + Bit_model bm_match[State::states][pos_states]; + Bit_model bm_rep[State::states]; + Bit_model bm_rep0[State::states]; + Bit_model bm_rep1[State::states]; + Bit_model bm_rep2[State::states]; + Bit_model bm_len[State::states][pos_states]; + Bit_model bm_dis_slot[max_dis_states][1<<dis_slot_bits]; + Bit_model bm_dis[modeled_distances-end_dis_model+1]; + Bit_model bm_align[dis_align_size]; + + unsigned int rep0 = 0; // rep[0-3] latest four distances + unsigned int rep1 = 0; // used for efficient coding of + unsigned int rep2 = 0; // repeated distances + unsigned int rep3 = 0; + + Len_decoder len_decoder; + Len_decoder rep_match_len_decoder; + Literal_decoder literal_decoder; + State state; + range_decoder.load(); + + 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 ) + { + const uint8_t prev_byte = get_prev_byte(); + if( state.is_char() ) + put_byte( literal_decoder.decode( range_decoder, prev_byte ) ); + else + put_byte( literal_decoder.decode_matched( range_decoder, prev_byte, + get_byte( rep0 ) ) ); + 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()] ) == 1 ) + { + 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; + } + else + { + if( range_decoder.decode_bit( bm_len[state()][pos_state] ) == 0 ) + { state.set_short_rep(); len = 1; } + } + if( len == 0 ) + { + state.set_rep(); + len = min_match_len + rep_match_len_decoder.decode( range_decoder, pos_state ); + } + } + else + { + const unsigned int rep0_saved = rep0; + len = min_match_len + len_decoder.decode( range_decoder, pos_state ); + 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 == 0xFFFFFFFFU ) // Marker found + { + rep0 = rep0_saved; + range_decoder.normalize(); + flush_data(); + if( len == min_match_len ) // End Of Stream marker + { + if( verify_trailer( pp ) ) return 0; else return 3; + } + if( len == min_match_len + 1 ) // Sync Flush marker + { + range_decoder.load(); continue; + } + if( pp.verbosity() >= 0 ) + { + pp(); + std::fprintf( stderr, "Unsupported marker code `%d'.\n", len ); + } + return 4; + } + } + } + rep3 = rep2; rep2 = rep1; rep1 = rep0_saved; + state.set_match(); + if( rep0 >= (unsigned int)dictionary_size || + ( rep0 >= (unsigned int)pos && !partial_data_pos ) ) + { flush_data(); return 1; } + } + copy_block( rep0, len ); + } + } + } diff --git a/decoder.h b/decoder.h new file mode 100644 index 0000000..3b5dc7d --- /dev/null +++ b/decoder.h @@ -0,0 +1,268 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +class Range_decoder + { + enum { buffer_size = 16384 }; + long long partial_member_pos; + uint8_t * const buffer; // input buffer + int pos; // current pos in buffer + int stream_pos; // when reached, a new block must be read + uint32_t code; + uint32_t range; + const int infd; // input file descriptor + bool at_stream_end; + + bool read_block(); + +public: + Range_decoder( const int ifd ) + : + partial_member_pos( 0 ), + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + stream_pos( 0 ), + code( 0 ), + range( 0xFFFFFFFFU ), + infd( ifd ), + at_stream_end( false ) {} + + ~Range_decoder() { delete[] buffer; } + + bool code_is_zero() const throw() { return ( code == 0 ); } + bool finished() { return pos >= stream_pos && !read_block(); } + long long member_position() const throw() + { return partial_member_pos + pos; } + void reset_member_position() throw() + { partial_member_pos = -pos; } + + uint8_t get_byte() + { + if( finished() ) return 0x55; // make code != 0 + return buffer[pos++]; + } + + void load() + { + code = 0; + range = 0xFFFFFFFFU; + for( int i = 0; i < 5; ++i ) code = (code << 8) | get_byte(); + } + + void normalize() + { + if( range <= 0x00FFFFFFU ) + { range <<= 8; code = (code << 8) | get_byte(); } + } + + int decode( const int num_bits ) + { + int symbol = 0; + for( int i = num_bits; i > 0; --i ) + { + symbol <<= 1; + if( range <= 0x00FFFFFFU ) + { + range <<= 7; code = (code << 8) | get_byte(); + if( code >= range ) { code -= range; symbol |= 1; } + } + else + { + range >>= 1; + if( code >= range ) { code -= range; symbol |= 1; } + } + } + return symbol; + } + + int decode_bit( Bit_model & bm ) + { + normalize(); + 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; + return 0; + } + else + { + range -= bound; + code -= bound; + bm.probability -= bm.probability >> bit_model_move_bits; + return 1; + } + } + + 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] ); + 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 = 0; i < num_bits; ++i ) + { + const int bit = decode_bit( bm[model] ); + model <<= 1; + if( bit ) { model |= 1; symbol |= (1 << i); } + } + return symbol; + } + + int decode_matched( Bit_model bm[], const int match_byte ) + { + Bit_model * const bm1 = bm + 0x100; + int symbol = 1; + for( int i = 7; i >= 0; --i ) + { + const int match_bit = ( match_byte >> i ) & 1; + const int bit = decode_bit( bm1[(match_bit<<8)+symbol] ); + symbol = ( symbol << 1 ) | bit; + if( match_bit != bit ) + { + while( --i >= 0 ) + symbol = ( symbol << 1 ) | decode_bit( bm[symbol] ); + break; + } + } + return symbol & 0xFF; + } + }; + + +class Len_decoder + { + Bit_model choice1; + Bit_model choice2; + Bit_model bm_low[pos_states][len_low_symbols]; + Bit_model bm_mid[pos_states][len_mid_symbols]; + Bit_model bm_high[len_high_symbols]; + +public: + int decode( Range_decoder & range_decoder, const int pos_state ) + { + if( range_decoder.decode_bit( choice1 ) == 0 ) + return range_decoder.decode_tree( bm_low[pos_state], len_low_bits ); + if( range_decoder.decode_bit( choice2 ) == 0 ) + return len_low_symbols + + range_decoder.decode_tree( bm_mid[pos_state], len_mid_bits ); + return len_low_symbols + len_mid_symbols + + range_decoder.decode_tree( bm_high, len_high_bits ); + } + }; + + +class Literal_decoder + { + Bit_model bm_literal[1<<literal_context_bits][0x300]; + + int lstate( const int prev_byte ) const throw() + { return ( prev_byte >> ( 8 - literal_context_bits ) ); } + +public: + uint8_t decode( Range_decoder & range_decoder, const uint8_t prev_byte ) + { return range_decoder.decode_tree( bm_literal[lstate(prev_byte)], 8 ); } + + uint8_t decode_matched( Range_decoder & range_decoder, + const uint8_t prev_byte, const uint8_t match_byte ) + { return range_decoder.decode_matched( bm_literal[lstate(prev_byte)], + match_byte ); } + }; + + +class LZ_decoder + { + long long partial_data_pos; + const int dictionary_size; + const int buffer_size; + uint8_t * const buffer; // output buffer + int pos; // current pos in buffer + int stream_pos; // first byte not yet written to file + uint32_t crc_; + const int outfd; // output file descriptor + const int member_version; + Range_decoder & range_decoder; + + void flush_data(); + bool verify_trailer( const Pretty_print & pp ) const; + + uint8_t get_prev_byte() const throw() + { + const int i = ( ( pos > 0 ) ? pos : buffer_size ) - 1; + return buffer[i]; + } + + uint8_t get_byte( const int distance ) const throw() + { + int i = pos - distance - 1; + if( i < 0 ) i += buffer_size; + return buffer[i]; + } + + void put_byte( const uint8_t b ) + { + buffer[pos] = b; + if( ++pos >= buffer_size ) flush_data(); + } + + void copy_block( const int distance, int len ) + { + int i = pos - distance - 1; + if( i < 0 ) i += buffer_size; + if( len < buffer_size - std::max( pos, i ) && len <= std::abs( pos - i ) ) + { + std::memcpy( buffer + pos, buffer + i, len ); + pos += len; + } + else for( ; len > 0; --len ) + { + buffer[pos] = buffer[i]; + if( ++pos >= buffer_size ) flush_data(); + if( ++i >= buffer_size ) i = 0; + } + } + +public: + LZ_decoder( const File_header & header, Range_decoder & rdec, const int ofd ) + : + partial_data_pos( 0 ), + dictionary_size( header.dictionary_size() ), + buffer_size( std::max( 65536, dictionary_size ) ), + buffer( new uint8_t[buffer_size] ), + pos( 0 ), + stream_pos( 0 ), + crc_( 0xFFFFFFFFU ), + outfd( ofd ), + member_version( header.version() ), + range_decoder( rdec ) + { buffer[buffer_size-1] = 0; } // prev_byte of first_byte + + ~LZ_decoder() { delete[] buffer; } + + uint32_t crc() const throw() { return crc_ ^ 0xFFFFFFFFU; } + + long long data_position() const throw() + { return partial_data_pos + pos; } + + int decode_member( const Pretty_print & pp ); + }; diff --git a/doc/lziprecover.1 b/doc/lziprecover.1 new file mode 100644 index 0000000..495de0b --- /dev/null +++ b/doc/lziprecover.1 @@ -0,0 +1,71 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.37.1. +.TH LZIPRECOVER "1" "November 2011" "Lziprecover 1.13-rc1" "User Commands" +.SH NAME +Lziprecover \- recovers data from damaged lzip files +.SH SYNOPSIS +.B lziprecover +[\fIoptions\fR] [\fIfiles\fR] +.SH DESCRIPTION +Lziprecover \- Data recovery tool and decompressor for lzipped files. +.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\-c\fR, \fB\-\-stdout\fR +send decompressed 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\-\-merge\fR +correct errors in file using several copies +.TP +\fB\-o\fR, \fB\-\-output=\fR<file> +place the output into <file> +.TP +\fB\-q\fR, \fB\-\-quiet\fR +suppress all messages +.TP +\fB\-R\fR, \fB\-\-repair\fR +try to repair a small error in file +.TP +\fB\-s\fR, \fB\-\-split\fR +split a multimember file in single\-member files +.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) +.SH "REPORTING BUGS" +Report bugs to lzip\-bug@nongnu.org +.br +Lziprecover home page: http://www.nongnu.org/lzip/lziprecover.html +.SH COPYRIGHT +Copyright \(co 2011 Antonio Diaz Diaz. +License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html> +.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 Lziprecover +is maintained as a Texinfo manual. If the +.B info +and +.B Lziprecover +programs are properly installed at your site, the command +.IP +.B info Lziprecover +.PP +should give you access to the complete manual. diff --git a/doc/lziprecover.info b/doc/lziprecover.info new file mode 100644 index 0000000..4528103 --- /dev/null +++ b/doc/lziprecover.info @@ -0,0 +1,368 @@ +This is lziprecover.info, produced by makeinfo version 4.13 from +lziprecover.texinfo. + +INFO-DIR-SECTION Data Compression +START-INFO-DIR-ENTRY +* Lziprecover: (lziprecover). Data recovery tool for lzipped files +END-INFO-DIR-ENTRY + + +File: lziprecover.info, Node: Top, Next: Introduction, Up: (dir) + +Lziprecover Manual +****************** + +This manual is for Lziprecover (version 1.13-rc1, 12 November 2011). + +* Menu: + +* Introduction:: Purpose and features of lziprecover +* Invoking Lziprecover:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Problems:: Reporting bugs +* Concept Index:: Index of concepts + + + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This manual is free documentation: you have unlimited permission to +copy, distribute and modify it. + + +File: lziprecover.info, Node: Introduction, Next: Invoking Lziprecover, Prev: Top, Up: Top + +1 Introduction +************** + +Lziprecover is a data recovery tool and decompressor for files in the +lzip compressed data format (.lz) able to repair slightly damaged files, +recover badly damaged files from two or more copies, extract undamaged +members from multi-member files, decompress files and test integrity of +files. + + Lziprecover is able to recover or decompress files produced by any of +the compressors in the lzip family; lzip, plzip, minilzip/lzlib, clzip +and pdlzip. This recovery capability contributes to make the lzip format +one of the best options for long-term data archiving. + + When recovering data, lziprecover takes as arguments the names of the +damaged files and writes zero or more recovered files depending on the +operation selected and whether the recovery succeeded or not. The +damaged files themselves are never modified. + + When decompressing or testing file integrity, lziprecover behaves +like lzip or lunzip. + + If the files are too damaged for lziprecover to repair them, data +from damaged members can be partially recovered writing it to stdout as +shown in the following example (the resulting file may contain some +garbage data at the end): + + lziprecover -cd rec00001file.lz > rec00001file + + If the cause of file corruption is damaged media, the combination +GNU ddrescue + lziprecover is the best option for recovering data from +multiple damaged copies. *Note ddrescue-example::, for an example. + + 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 lziprecover to panic. + + +File: lziprecover.info, Node: Invoking Lziprecover, Next: File Format, Prev: Introduction, Up: Top + +2 Invoking Lziprecover +********************** + +The format for running lziprecover is: + + lziprecover [OPTIONS] [FILES] + + Lziprecover supports the following options: + +`-h' +`--help' + Print an informative help message describing the options and exit. + +`-V' +`--version' + Print the version number of lziprecover on the standard output and + exit. + +`-c' +`--stdout' + 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. + +`-d' +`--decompress' + Decompress. + +`-f' +`--force' + Force overwrite of output files. + +`-k' +`--keep' + Keep (don't delete) input files during decompression. + +`-m' +`--merge' + Try to produce a correct file merging the good parts of two or more + damaged copies. The copies must be single-member files. The merge + will fail if the copies have too many damaged areas or if the same + byte is damaged in all copies. If successful, a repaired copy is + written to the file `FILE_fixed.lz'. The exit status is 0 if the + file could be repaired, 2 otherwise. + + To give you an idea of its possibilities, when merging two copies + each of them with one damaged area affecting 1 percent of the + copy, the probability of obtaining a correct file is about 98 + percent. With three such copies the probability rises to 99.97 + percent. For large files with small errors, the probability + approaches 100 percent even with only two copies. + +`-o FILE' +`--output=FILE' + Place the output into `FILE' instead of into `FILE_fixed.lz'. If + splitting, the names of the files produced are in the form + `rec00001FILE', `rec00002FILE', etc. If decompressing from + standard input and `--stdout' has not been specified, use `FILE' + as the name of the decompressed file. + +`-q' +`--quiet' + Quiet operation. Suppress all messages. + +`-R' +`--repair' + Try to repair a small error, affecting only one byte, in a + single-member FILE. If successful, a repaired copy is written to + the file `FILE_fixed.lz'. `FILE' is not modified at all. The exit + status is 0 if the file could be repaired, 2 otherwise. + +`-s' +`--split' + Search for members in `FILE' and write each member in its own + `.lz' file. You can then use `lziprecover -t' to test the + integrity of the resulting files, decompress those which are + undamaged, and try to repair or partially decompress those which + are damaged. + + The names of the files produced are in the form `rec00001FILE.lz', + `rec00002FILE.lz', etc, and are designed so that the use of + wildcards in subsequent processing, for example, + `lziprecover -cd rec*FILE.lz > recovered_data', processes the + files in the correct order. + +`-t' +`--test' + Check integrity of the specified file(s), but don't decompress + them. This really performs a trial decompression and throws away + the result. Use it together with `-v' to see information about + the file. + +`-v' +`--verbose' + Verbose mode. + When decompressing or testing, further -v's (up to 4) increase the + verbosity level, showing status, dictionary size, compression + ratio, trailer contents (CRC, data size, member size), and up to 6 + bytes of trailing garbage (if any). + + + +File: lziprecover.info, Node: File Format, Next: Examples, Prev: Invoking Lziprecover, Up: Top + +3 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 lzip format, 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 are deprecated. They can + contain only one member and lack the `Member size' field. + +`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: lziprecover.info, Node: Examples, Next: Problems, Prev: File Format, Up: Top + +4 A small tutorial with examples +******************************** + +Example 1: Restore a regular file from its compressed version +`file.lz'. If the operation is successful, `file.lz' is removed. + + lziprecover -d file.lz + + +Example 2: Verify the integrity of the compressed file `file.lz' and +show status. + + lziprecover -tv file.lz + + +Example 3: Decompress `file.lz' partially until 10KiB of decompressed +data are produced. + + lziprecover -cd file.lz | dd bs=1024 count=10 + + +Example 4: Decompress `file.lz' partially from decompressed byte 10000 +to decompressed byte 15000 (5000 bytes are produced). + + lziprecover -cd file.lz | dd bs=1000 skip=10 count=5 + + +Example 5: Repair a one-byte corruption in the single-member file +`file.lz'. (Indented lines are abridged error messages from +lziprecover). + + lziprecover -v -R file.lz + Copy of input file repaired successfully. + mv file_fixed.lz file.lz + + +Example 6: Split the multi-member file `file.lz' and write each member +in its own `recXXXXXfile.lz' file. Then use `lziprecover -t' to test +the integrity of the resulting files. + + lziprecover -s file.lz + lziprecover -tv rec*file.lz + + +Example 7: Recover a compressed backup from two copies on CD-ROM (see +the GNU ddrescue manual for details about ddrescue) + + ddrescue -b2048 /dev/cdrom cdimage1 logfile1 + mount -t iso9660 -o loop,ro cdimage1 /mnt/cdimage + cp /mnt/cdimage/backup.tar.lz rescued1.tar.lz + umount /mnt/cdimage + (insert second copy in the CD drive) + ddrescue -b2048 /dev/cdrom cdimage2 logfile2 + mount -t iso9660 -o loop,ro cdimage2 /mnt/cdimage + cp /mnt/cdimage/backup.tar.lz rescued2.tar.lz + umount /mnt/cdimage + lziprecover -m -v -o rescued.tar.lz rescued1.tar.lz rescued2.tar.lz + + +Example 8: Recover the first volume of those created with the command +`lzip -b 32MiB -S 650MB big_db' from two copies, `big_db1_00001.lz' and +`big_db2_00001.lz', with member 00007 damaged in the first copy, member +00018 damaged in the second copy, and member 00012 damaged in both +copies. Two correct copies are produced and compared. + + lziprecover -s big_db1_00001.lz + lziprecover -s big_db2_00001.lz + lziprecover -t rec*big_db1_00001.lz + rec00007big_db1_00001.lz: crc mismatch + rec00012big_db1_00001.lz: crc mismatch + lziprecover -t rec*big_db2_00001.lz + rec00012big_db2_00001.lz: crc mismatch + rec00018big_db2_00001.lz: crc mismatch + lziprecover -m -v rec00012big_db1_00001.lz rec00012big_db2_00001.lz + Input files merged successfully + cp rec00007big_db2_00001.lz rec00007big_db1_00001.lz + cp rec00012big_db1_00001_fixed.lz rec00012big_db1_00001.lz + cp rec00012big_db1_00001_fixed.lz rec00012big_db2_00001.lz + cp rec00018big_db1_00001.lz rec00018big_db2_00001.lz + cat rec*big_db1_00001.lz > big_db3_00001.lz + cat rec*big_db2_00001.lz > big_db4_00001.lz + zcmp big_db3_00001.lz big_db4_00001.lz + + +File: lziprecover.info, Node: Problems, Next: Concept Index, Prev: Examples, Up: Top + +5 Reporting Bugs +**************** + +There are probably bugs in lziprecover. 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 lziprecover, please send electronic mail to +<lzip-bug@nongnu.org>. Include the version number, which you can find +by running `lziprecover --version'. + + +File: lziprecover.info, Node: Concept Index, Prev: Problems, Up: Top + +Concept Index +************* + + +* Menu: + +* bugs: Problems. (line 6) +* examples: Examples. (line 6) +* file format: File Format. (line 6) +* getting help: Problems. (line 6) +* introduction: Introduction. (line 6) +* invoking lziprecover: Invoking Lziprecover. (line 6) + + + +Tag Table: +Node: Top231 +Node: Introduction898 +Node: Invoking Lziprecover2684 +Node: File Format6150 +Node: Examples8156 +Ref: ddrescue-example9409 +Node: Problems11188 +Node: Concept Index11738 + +End Tag Table diff --git a/doc/lziprecover.texinfo b/doc/lziprecover.texinfo new file mode 100644 index 0000000..2447c14 --- /dev/null +++ b/doc/lziprecover.texinfo @@ -0,0 +1,397 @@ +\input texinfo @c -*-texinfo-*- +@c %**start of header +@setfilename lziprecover.info +@settitle Lziprecover Manual +@finalout +@c %**end of header + +@set UPDATED 12 November 2011 +@set VERSION 1.13-rc1 + +@dircategory Data Compression +@direntry +* Lziprecover: (lziprecover). Data recovery tool for lzipped files +@end direntry + + +@ifnothtml +@titlepage +@title Lziprecover +@subtitle Data recovery tool for lzipped files +@subtitle for Lziprecover version @value{VERSION}, @value{UPDATED} +@author by Antonio Diaz Diaz + +@page +@vskip 0pt plus 1filll +@end titlepage + +@contents +@end ifnothtml + +@node Top +@top + +This manual is for Lziprecover (version @value{VERSION}, @value{UPDATED}). + +@menu +* Introduction:: Purpose and features of lziprecover +* Invoking Lziprecover:: Command line interface +* File Format:: Detailed format of the compressed file +* Examples:: A small tutorial with examples +* Problems:: Reporting bugs +* Concept Index:: Index of concepts +@end menu + +@sp 1 +Copyright @copyright{} 2009, 2010, 2011 Antonio Diaz Diaz. + +This manual is free documentation: you have unlimited permission +to copy, distribute and modify it. + + +@node Introduction +@chapter Introduction +@cindex introduction + +Lziprecover is a data recovery tool and decompressor for files in the +lzip compressed data format (.lz) able to repair slightly damaged files, +recover badly damaged files from two or more copies, extract undamaged +members from multi-member files, decompress files and test integrity of +files. + +Lziprecover is able to recover or decompress files produced by any of +the compressors in the lzip family; lzip, plzip, minilzip/lzlib, clzip +and pdlzip. This recovery capability contributes to make the lzip format +one of the best options for long-term data archiving. + +When recovering data, lziprecover takes as arguments the names of the +damaged files and writes zero or more recovered files depending on the +operation selected and whether the recovery succeeded or not. The +damaged files themselves are never modified. + +When decompressing or testing file integrity, lziprecover behaves like +lzip or lunzip. + +If the files are too damaged for lziprecover to repair them, data from +damaged members can be partially recovered writing it to stdout as shown +in the following example (the resulting file may contain some garbage +data at the end): + +@example +lziprecover -cd rec00001file.lz > rec00001file +@end example + +If the cause of file corruption is damaged media, the combination +@w{GNU ddrescue + lziprecover} is the best option for recovering data +from multiple damaged copies. @xref{ddrescue-example}, for an example. + +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 lziprecover to panic. + + +@node Invoking Lziprecover +@chapter Invoking Lziprecover +@cindex invoking lziprecover + +The format for running lziprecover is: + +@example +lziprecover [@var{options}] [@var{files}] +@end example + +Lziprecover supports the following options: + +@table @samp +@item -h +@itemx --help +Print an informative help message describing the options and exit. + +@item -V +@itemx --version +Print the version number of lziprecover on the standard output and exit. + +@item -c +@itemx --stdout +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 -d +@itemx --decompress +Decompress. + +@item -f +@itemx --force +Force overwrite of output files. + +@item -k +@itemx --keep +Keep (don't delete) input files during decompression. + +@item -m +@itemx --merge +Try to produce a correct file merging the good parts of two or more +damaged copies. The copies must be single-member files. The merge will +fail if the copies have too many damaged areas or if the same byte is +damaged in all copies. If successful, a repaired copy is written to the +file @samp{@var{file}_fixed.lz}. The exit status is 0 if the file could +be repaired, 2 otherwise. + +To give you an idea of its possibilities, when merging two copies each +of them with one damaged area affecting 1 percent of the copy, the +probability of obtaining a correct file is about 98 percent. With three +such copies the probability rises to 99.97 percent. For large files with +small errors, the probability approaches 100 percent even with only two +copies. + +@item -o @var{file} +@itemx --output=@var{file} +Place the output into @samp{@var{file}} instead of into +@samp{@var{file}_fixed.lz}. If splitting, the names of the files +produced are in the form @samp{rec00001@var{file}}, +@samp{rec00002@var{file}}, etc. If decompressing from standard input and +@samp{--stdout} has not been specified, use @samp{@var{file}} as the +name of the decompressed file. + +@item -q +@itemx --quiet +Quiet operation. Suppress all messages. + +@item -R +@itemx --repair +Try to repair a small error, affecting only one byte, in a single-member +@var{file}. If successful, a repaired copy is written to the file +@samp{@var{file}_fixed.lz}. @samp{@var{file}} is not modified at all. +The exit status is 0 if the file could be repaired, 2 otherwise. + +@item -s +@itemx --split +Search for members in @samp{@var{file}} and write each member in its own +@samp{.lz} file. You can then use @samp{lziprecover -t} to test the +integrity of the resulting files, decompress those which are undamaged, +and try to repair or partially decompress those which are damaged. + +The names of the files produced are in the form +@samp{rec00001@var{file}.lz}, @samp{rec00002@var{file}.lz}, etc, and are +designed so that the use of wildcards in subsequent processing, for +example, @w{@samp{lziprecover -cd rec*@var{file}.lz > recovered_data}}, +processes the files in the correct order. + +@item -t +@itemx --test +Check integrity of the specified file(s), but don't decompress them. +This really performs a trial decompression and throws away the result. +Use it together with @samp{-v} to see information about the file. + +@item -v +@itemx --verbose +Verbose mode.@* +When decompressing or testing, further -v's (up to 4) increase the +verbosity level, showing status, dictionary size, compression ratio, +trailer contents (CRC, data size, member size), and up to 6 bytes of +trailing garbage (if any). + +@end table + + +@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 lzip format, 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 are deprecated. They can contain only one +member and lack the @samp{Member size} field. + +@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 + +Example 1: Restore a regular file from its compressed version +@samp{file.lz}. If the operation is successful, @samp{file.lz} is +removed. + +@example +lziprecover -d file.lz +@end example + +@sp 1 +@noindent +Example 2: Verify the integrity of the compressed file @samp{file.lz} +and show status. + +@example +lziprecover -tv file.lz +@end example + +@sp 1 +@noindent +Example 3: Decompress @samp{file.lz} partially until 10KiB of +decompressed data are produced. + +@example +lziprecover -cd file.lz | dd bs=1024 count=10 +@end example + +@sp 1 +@noindent +Example 4: Decompress @samp{file.lz} partially from decompressed byte +10000 to decompressed byte 15000 (5000 bytes are produced). + +@example +lziprecover -cd file.lz | dd bs=1000 skip=10 count=5 +@end example + +@sp 1 +@noindent +Example 5: Repair a one-byte corruption in the single-member file +@samp{file.lz}. (Indented lines are abridged error messages from +lziprecover). + +@example +lziprecover -v -R file.lz + Copy of input file repaired successfully. +mv file_fixed.lz file.lz +@end example + +@sp 1 +@noindent +Example 6: Split the multi-member file @samp{file.lz} and write each +member in its own @samp{recXXXXXfile.lz} file. Then use +@w{@samp{lziprecover -t}} to test the integrity of the resulting files. + +@example +lziprecover -s file.lz +lziprecover -tv rec*file.lz +@end example + +@sp 1 +@anchor{ddrescue-example} +@noindent +Example 7: Recover a compressed backup from two copies on CD-ROM (see +the GNU ddrescue manual for details about ddrescue) + +@example +ddrescue -b2048 /dev/cdrom cdimage1 logfile1 +mount -t iso9660 -o loop,ro cdimage1 /mnt/cdimage +cp /mnt/cdimage/backup.tar.lz rescued1.tar.lz +umount /mnt/cdimage + (insert second copy in the CD drive) +ddrescue -b2048 /dev/cdrom cdimage2 logfile2 +mount -t iso9660 -o loop,ro cdimage2 /mnt/cdimage +cp /mnt/cdimage/backup.tar.lz rescued2.tar.lz +umount /mnt/cdimage +lziprecover -m -v -o rescued.tar.lz rescued1.tar.lz rescued2.tar.lz +@end example + +@sp 1 +@noindent +Example 8: Recover the first volume of those created with the command +@w{@code{lzip -b 32MiB -S 650MB big_db}} from two copies, +@samp{big_db1_00001.lz} and @samp{big_db2_00001.lz}, with member 00007 +damaged in the first copy, member 00018 damaged in the second copy, and +member 00012 damaged in both copies. Two correct copies are produced and +compared. + +@example +lziprecover -s big_db1_00001.lz +lziprecover -s big_db2_00001.lz +lziprecover -t rec*big_db1_00001.lz + rec00007big_db1_00001.lz: crc mismatch + rec00012big_db1_00001.lz: crc mismatch +lziprecover -t rec*big_db2_00001.lz + rec00012big_db2_00001.lz: crc mismatch + rec00018big_db2_00001.lz: crc mismatch +lziprecover -m -v rec00012big_db1_00001.lz rec00012big_db2_00001.lz + Input files merged successfully +cp rec00007big_db2_00001.lz rec00007big_db1_00001.lz +cp rec00012big_db1_00001_fixed.lz rec00012big_db1_00001.lz +cp rec00012big_db1_00001_fixed.lz rec00012big_db2_00001.lz +cp rec00018big_db1_00001.lz rec00018big_db2_00001.lz +cat rec*big_db1_00001.lz > big_db3_00001.lz +cat rec*big_db2_00001.lz > big_db4_00001.lz +zcmp big_db3_00001.lz big_db4_00001.lz +@end example + + +@node Problems +@chapter Reporting Bugs +@cindex bugs +@cindex getting help + +There are probably bugs in lziprecover. 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 lziprecover, please send electronic mail to +@email{lzip-bug@@nongnu.org}. Include the version number, which you can +find by running @w{@samp{lziprecover --version}}. + + +@node Concept Index +@unnumbered Concept Index + +@printindex cp + +@bye @@ -0,0 +1,323 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +class State + { + unsigned char st; + +public: + enum { states = 12 }; + State() throw() : st( 0 ) {} + unsigned char 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]; + } + }; + + +enum { + min_dictionary_bits = 12, + min_dictionary_size = 1 << min_dictionary_bits, + max_dictionary_bits = 29, + max_dictionary_size = 1 << max_dictionary_bits, + literal_context_bits = 3, + pos_state_bits = 2, + pos_states = 1 << pos_state_bits, + pos_state_mask = pos_states - 1, + + dis_slot_bits = 6, + start_dis_model = 4, + end_dis_model = 14, + modeled_distances = 1 << (end_dis_model / 2), + dis_align_bits = 4, + dis_align_size = 1 << dis_align_bits, + + len_low_bits = 3, + len_mid_bits = 3, + len_high_bits = 8, + len_low_symbols = 1 << len_low_bits, + len_mid_symbols = 1 << len_mid_bits, + len_high_symbols = 1 << len_high_bits, + max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols, + + min_match_len = 2, // must be 2 + max_match_len = min_match_len + max_len_symbols - 1, // 273 + min_match_len_limit = 5, + + max_dis_states = 4 }; + +inline int get_dis_state( int len ) throw() + { + len -= min_match_len; + if( len >= max_dis_states ) len = max_dis_states - 1; + return len; + } + + +enum { bit_model_move_bits = 5, + bit_model_total_bits = 11, + bit_model_total = 1 << bit_model_total_bits }; + +struct Bit_model + { + unsigned int probability; + Bit_model() throw() : probability( bit_model_total / 2 ) {} + }; + + +class Pretty_print + { + const char * const stdin_name; + unsigned int longest_name; + const int verbosity_; + std::string name_; + mutable bool first_post; + +public: + Pretty_print( const std::vector< std::string > & filenames, const int v ) + : stdin_name( "(stdin)" ), longest_name( 0 ), verbosity_( v ), + first_post( false ) + { + const unsigned int stdin_name_len = std::strlen( stdin_name ); + 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(); } + int verbosity() const throw() { return verbosity_; } + 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 = 0xEDB88320U ^ ( 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 ); } + void update( uint32_t & crc, const uint8_t * const buffer, const int size ) const throw() + { + for( int i = 0; i < size; ++i ) + crc = data[(crc^buffer[i])&0xFF] ^ ( crc >> 8 ); + } + }; + +extern const CRC32 crc32; + + +inline 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; + } + +const uint8_t magic_string[4] = { 'L', 'Z', 'I', 'P' }; + +struct File_header + { + uint8_t data[6]; // 0-3 magic bytes + // 4 version + // 5 coded_dict_size + enum { size = 6 }; + + void set_magic() throw() + { std::memcpy( data, magic_string, 4 ); data[4] = 1; } + + bool verify_magic() const throw() + { return ( std::memcmp( data, magic_string, 4 ) == 0 ); } + + uint8_t version() const throw() { return data[4]; } + bool verify_version() const throw() { return ( data[4] <= 1 ); } + + int dictionary_size() const throw() + { + int sz = ( 1 << ( data[5] & 0x1F ) ); + if( sz > min_dictionary_size && sz <= max_dictionary_size ) + sz -= ( sz / 16 ) * ( ( data[5] >> 5 ) & 0x07 ); + return sz; + } + + bool dictionary_size( const int sz ) throw() + { + if( sz >= min_dictionary_size && sz <= max_dictionary_size ) + { + data[5] = real_bits( sz - 1 ); + if( sz > min_dictionary_size ) + { + const int base_size = 1 << data[5]; + const int wedge = base_size / 16; + for( int i = 7; i >= 1; --i ) + if( base_size - ( i * wedge ) >= sz ) + { data[5] |= ( i << 5 ); break; } + } + return true; + } + return false; + } + }; + + +struct File_trailer + { + uint8_t data[20]; // 0-3 CRC32 of the uncompressed data + // 4-11 size of the uncompressed data + // 12-19 member size including header and trailer + + static int size( const int version = 1 ) + { return ( ( version >= 1 ) ? 20 : 12 ); } + + uint32_t data_crc() const throw() + { + uint32_t tmp = 0; + for( int i = 3; i >= 0; --i ) { tmp <<= 8; tmp += data[i]; } + return tmp; + } + + void data_crc( uint32_t crc ) throw() + { for( int i = 0; i <= 3; ++i ) { data[i] = (uint8_t)crc; crc >>= 8; } } + + long long data_size() const throw() + { + long long tmp = 0; + for( int i = 11; i >= 4; --i ) { tmp <<= 8; tmp += data[i]; } + return tmp; + } + + void data_size( long long sz ) throw() + { + for( int i = 4; i <= 11; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } + } + + long long member_size() const throw() + { + long long tmp = 0; + for( int i = 19; i >= 12; --i ) { tmp <<= 8; tmp += data[i]; } + return tmp; + } + + void member_size( long long sz ) throw() + { + for( int i = 12; i <= 19; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; } + } + }; + + +struct Error + { + const char * const msg; + Error( const char * const s ) throw() : msg( s ) {} + }; + + +#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 + + +// defined in decoder.cc +int readblock( const int fd, uint8_t * const buf, const int size ) throw(); +int writeblock( const int fd, const uint8_t * const buf, const int size ) throw(); + +// defined in main.cc +extern int verbosity; +int open_instream( const std::string & name, struct stat * const in_statsp, + const bool to_stdout, const bool reg_only = false ) throw(); +int open_outstream_rw( const std::string & output_filename, + const bool force ) throw(); +void show_error( const char * const msg, const int errcode = 0, + const bool help = false ) throw(); +void internal_error( const char * const msg ); + +// defined in merge.cc +void cleanup_and_fail( const std::string & output_filename, + const int outfd, const int retval ) throw(); +bool copy_file( const int infd, const int outfd, + const long long size = LLONG_MAX ); +bool try_decompress( const int fd, const long long file_size, + long long * failure_posp = 0 ); +bool verify_header( const File_header & header ); +bool verify_single_member( const int fd, const long long file_size ); +int merge_files( const std::vector< std::string > & filenames, + const std::string & output_filename, const bool force ); + +// defined in repair.cc +int repair_file( const std::string & input_filename, + const std::string & output_filename, const bool force ); + +// defined in split.cc +int split_file( const std::string & input_filename, + const std::string & default_output_filename, const bool force ); @@ -0,0 +1,676 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ +/* + Return values: 0 for a normal exit, 1 for environmental problems + (file not found, invalid flags, I/O errors, etc), 2 to indicate a + corrupt or invalid input file, 3 for an internal consistency error + (eg, bug) which caused lziprecover to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <algorithm> +#include <cerrno> +#include <climits> +#include <csignal> +#include <cstdio> +#include <cstdlib> +#include <cstring> +#include <string> +#include <vector> +#include <fcntl.h> +#include <stdint.h> +#include <unistd.h> +#include <utime.h> +#include <sys/stat.h> +#if defined(__MSVCRT__) +#define S_IRGRP 0 +#define S_IWGRP 0 +#define S_IROTH 0 +#define S_IWOTH 0 +#endif + +#include "arg_parser.h" +#include "lzip.h" +#include "decoder.h" + +#if CHAR_BIT != 8 +#error "Environments where CHAR_BIT != 8 are not supported." +#endif + + +namespace { + +const char * const Program_name = "Lziprecover"; +const char * const program_name = "lziprecover"; +const char * const program_year = "2011"; +const char * invocation_name = 0; + +#ifdef O_BINARY +const int o_binary = O_BINARY; +#else +const int o_binary = 0; +#endif + +struct { const char * from; const char * to; } const known_extensions[] = { + { ".lz", "" }, + { ".tlz", ".tar" }, + { 0, 0 } }; + +enum Mode { m_none, m_decompress, m_generate, m_merge, m_recover, m_repair, + m_split, m_test, m_update }; + +std::string output_filename; +int outfd = -1; +const mode_t usr_rw = S_IRUSR | S_IWUSR; +const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; +mode_t outfd_mode = usr_rw; +bool delete_output_on_interrupt = false; + + +void show_help() throw() + { + std::printf( "%s - Data recovery tool and decompressor for lzipped files.\n", Program_name ); + std::printf( "\nUsage: %s [options] [files]\n", invocation_name ); + std::printf( "\nOptions:\n" + " -h, --help display this help and exit\n" + " -V, --version output version information and exit\n" + " -c, --stdout send decompressed output to standard output\n" + " -d, --decompress decompress\n" + " -f, --force overwrite existing output files\n" +// " -g, --generate-recover-file generate a recover file\n" + " -k, --keep keep (don't delete) input files\n" + " -m, --merge correct errors in file using several copies\n" + " -o, --output=<file> place the output into <file>\n" + " -q, --quiet suppress all messages\n" +// " -r, --recover correct errors in file using a recover file\n" + " -R, --repair try to repair a small error in file\n" + " -s, --split split a multimember file in single-member files\n" + " -t, --test test compressed file integrity\n" +// " -u, --update convert file from version 0 to version 1\n" + " -v, --verbose be verbose (a 2nd -v gives more)\n" + "\nReport bugs to lzip-bug@nongnu.org\n" + "Lziprecover home page: http://www.nongnu.org/lzip/lziprecover.html\n" ); + } + + +void show_version() throw() + { + std::printf( "%s %s\n", Program_name, PROGVERSION ); + std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + std::printf( "License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>\n" + "This is free software: you are free to change and redistribute it.\n" + "There is NO WARRANTY, to the extent permitted by law.\n" ); + } + + +const char * format_num( long long num ) throw() + { + const char * const prefix[8] = + { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; + enum { buf_size = 16, factor = 1024 }; + static char buf[buf_size]; + const char *p = ""; + bool exact = ( num % factor == 0 ); + + for( int i = 0; i < 8 && ( llabs( num ) > 9999 || + ( exact && llabs( num ) >= factor ) ); ++i ) + { num /= factor; if( num % factor != 0 ) exact = false; p = prefix[i]; } + snprintf( buf, buf_size, "%lld %s", num, p ); + return buf; + } + + +void set_mode( Mode & program_mode, const Mode new_mode ) throw() + { + if( program_mode != m_none && program_mode != new_mode ) + { + show_error( "Only one operation can be specified.", 0, true ); + std::exit( 1 ); + } + program_mode = new_mode; + } + + +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; + } + + +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 >= 1 ) + 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() + { + int flags = O_CREAT | O_WRONLY | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + outfd = open( output_filename.c_str(), flags, outfd_mode ); + if( outfd < 0 && verbosity >= 0 ) + { + if( errno == EEXIST ) + 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 ( outfd >= 0 ); + } + + +bool check_tty( const int infd ) throw() + { + if( isatty( infd ) ) + { + 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 ) + { + delete_output_on_interrupt = false; + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n", + program_name, output_filename.c_str() ); + if( outfd >= 0 ) { close( outfd ); outfd = -1; } + if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT ) + 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 * const in_statsp ) + { + bool warning = false; + if( in_statsp ) + { + // fchown will in many cases return with EPERM, which can be safely ignored. + if( ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 && + errno != EPERM ) || + fchmod( outfd, in_statsp->st_mode ) != 0 ) warning = true; + } + if( close( outfd ) != 0 ) cleanup_and_fail( 1 ); + outfd = -1; + delete_output_on_interrupt = false; + if( in_statsp ) + { + struct utimbuf t; + t.actime = in_statsp->st_atime; + t.modtime = in_statsp->st_mtime; + if( utime( output_filename.c_str(), &t ) != 0 ) warning = true; + } + if( warning && verbosity >= 1 ) + show_error( "Can't change output file attributes." ); + } + + +std::string insert_fixed( std::string name ) throw() + { + if( name.size() > 4 && name.compare( name.size() - 4, 4, ".tlz" ) == 0 ) + name.insert( name.size() - 4, "_fixed" ); + else if( name.size() > 3 && name.compare( name.size() - 3, 3, ".lz" ) == 0 ) + name.insert( name.size() - 3, "_fixed" ); + else name += "_fixed.lz"; + return name; + } + + +unsigned char xdigit( const int value ) throw() + { + if( value >= 0 && value <= 9 ) return '0' + value; + if( value >= 10 && value <= 15 ) return 'A' + value - 10; + return 0; + } + + +void show_trailing_garbage( const uint8_t * const data, const int size, + const Pretty_print & pp, const bool all ) throw() + { + std::string garbage_msg; + if( !all ) garbage_msg = "first bytes of "; + garbage_msg += "trailing garbage found = "; + bool text = true; + for( int i = 0; i < size; ++i ) + if( !std::isprint( data[i] ) ) { text = false; break; } + if( text ) + { + garbage_msg += '`'; + garbage_msg.append( (const char *)data, size ); + garbage_msg += '\''; + } + else + { + for( int i = 0; i < size; ++i ) + { + if( i > 0 ) garbage_msg += ' '; + garbage_msg += xdigit( data[i] >> 4 ); + garbage_msg += xdigit( data[i] & 0x0F ); + } + } + pp( garbage_msg.c_str() ); + } + + +int decompress( const int infd, const Pretty_print & pp, const bool testing ) + { + int retval = 0; + + try { + Range_decoder rdec( infd ); + long long partial_file_pos = 0; + for( bool first_member = true; ; first_member = false, pp.reset() ) + { + File_header header; + int size; + rdec.reset_member_position(); + for( size = 0; size < File_header::size && !rdec.finished(); ++size ) + header.data[size] = rdec.get_byte(); + if( rdec.finished() ) // End Of File + { + if( first_member ) + { pp( "Error reading member header" ); retval = 1; } + else if( verbosity >= 4 && size > 0 ) + show_trailing_garbage( header.data, size, pp, true ); + break; + } + if( !header.verify_magic() ) + { + if( first_member ) + { pp( "Bad magic number (file not in lzip format)" ); retval = 2; } + else if( verbosity >= 4 ) + show_trailing_garbage( header.data, size, pp, false ); + break; + } + if( !header.verify_version() ) + { + if( verbosity >= 0 ) + { pp(); + std::fprintf( stderr, "Version %d member format not supported.\n", + header.version() ); } + retval = 2; break; + } + if( header.dictionary_size() < min_dictionary_size || + header.dictionary_size() > max_dictionary_size ) + { pp( "Invalid dictionary size in member header" ); retval = 2; break; } + + if( verbosity >= 2 || ( verbosity == 1 && first_member ) ) + { + pp(); + if( verbosity >= 2 ) + std::fprintf( stderr, "version %d, dictionary size %7sB. ", + header.version(), + format_num( header.dictionary_size() ) ); + } + LZ_decoder decoder( header, rdec, outfd ); + + const int result = decoder.decode_member( pp ); + partial_file_pos += rdec.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 ); + } + retval = 2; break; + } + if( verbosity >= 2 ) + { 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" ); + retval = 1; + } + catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; } + if( verbosity == 1 && retval == 0 ) + { if( testing ) std::fprintf( stderr, "ok\n" ); + else std::fprintf( stderr, "done\n" ); } + return retval; + } + + +extern "C" void signal_handler( int ) throw() + { + show_error( "Control-C or similar caught, quitting." ); + cleanup_and_fail( 1 ); + } + + +void set_signals() throw() + { + std::signal( SIGHUP, signal_handler ); + std::signal( SIGINT, signal_handler ); + std::signal( SIGTERM, signal_handler ); + } + +} // end namespace + + +int verbosity = 0; + + +int open_instream( const std::string & name, struct stat * const in_statsp, + const bool to_stdout, const bool reg_only ) throw() + { + int infd = open( name.c_str(), O_RDONLY | o_binary ); + if( infd < 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( infd, in_statsp ); + const mode_t & mode = in_statsp->st_mode; + const bool can_read = ( i == 0 && !reg_only && + ( S_ISBLK( mode ) || S_ISCHR( mode ) || + S_ISFIFO( mode ) || S_ISSOCK( mode ) ) ); + if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Input file `%s' is not a regular file%s.\n", + program_name, name.c_str(), + ( can_read && !to_stdout ) ? + " and `--stdout' was not specified" : "" ); + close( infd ); + infd = -1; + } + } + return infd; + } + + +int open_outstream_rw( const std::string & output_filename, + const bool force ) throw() + { + int flags = O_CREAT | O_RDWR | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + int outfd = open( output_filename.c_str(), flags, all_rw ); + if( outfd < 0 && verbosity >= 0 ) + { + if( errno == EEXIST ) + std::fprintf( stderr, "%s: Output file `%s' already exists." + " Use `--force' to overwrite it.\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 outfd; + } + + +void show_error( const char * const msg, const int errcode, const bool help ) throw() + { + if( verbosity >= 0 ) + { + if( msg && msg[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] ) + std::fprintf( stderr, "Try `%s --help' for more information.\n", + invocation_name ); + } + } + + +void internal_error( const char * const msg ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: internal error: %s.\n", program_name, msg ); + std::exit( 3 ); + } + + +int main( const int argc, const char * const argv[] ) + { + int infd = -1; + Mode program_mode = m_none; + 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[] = + { + { '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', "merge", Arg_parser::no }, + { 'o', "output", Arg_parser::yes }, + { 'q', "quiet", Arg_parser::no }, + { 'R', "repair", Arg_parser::no }, + { 's', "split", Arg_parser::no }, + { 't', "test", Arg_parser::no }, + { 'v', "verbose", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + const 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 'c': to_stdout = true; break; + case 'd': set_mode( 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': set_mode( program_mode, m_merge ); break; + case 'o': default_output_filename = parser.argument( argind ); break; + case 'q': verbosity = -1; break; + case 'R': set_mode( program_mode, m_repair ); break; + case 's': set_mode( program_mode, m_split ); break; + case 't': set_mode( program_mode, m_test ); break; + case 'v': if( verbosity < 4 ) ++verbosity; break; + case 'V': show_version(); return 0; + default : internal_error( "uncaught option" ); + } + } // end process options + + if( program_mode == m_none ) + { + show_error( "You must specify the operation to be performed.", 0, true ); + return 1; + } + + switch( program_mode ) + { + case m_generate: + case m_recover: + case m_update: + case m_none: internal_error( "invalid operation" ); break; + case m_decompress: break; + case m_merge: + { + std::vector< std::string > filenames; + for( ; argind < parser.arguments(); ++argind ) + filenames.push_back( parser.argument( argind ) ); + if( filenames.size() < 2 ) + { show_error( "You must specify at least 2 files.", 0, true ); return 1; } + if( !default_output_filename.size() ) + default_output_filename = insert_fixed( filenames[0] ); + return merge_files( filenames, default_output_filename, force ); + } break; + case m_repair: + { + if( argind + 1 != parser.arguments() ) + { show_error( "You must specify exactly 1 file.", 0, true ); return 1; } + if( !default_output_filename.size() ) + default_output_filename = insert_fixed( parser.argument( argind ) ); + return repair_file( parser.argument( argind ), default_output_filename, force ); + } break; + case m_split: + { + if( argind + 1 != parser.arguments() ) + { show_error( "You must specify exactly 1 file.", 0, true ); return 1; } + return split_file( parser.argument( argind ), default_output_filename, force ); + } break; + case m_test: break; + } + + 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( !to_stdout && program_mode != m_test && + ( filenames_given || default_output_filename.size() ) ) + set_signals(); + + Pretty_print pp( filenames, verbosity ); + if( program_mode == m_test ) + outfd = -1; + else if( program_mode != m_decompress ) + internal_error( "invalid decompressor operation" ); + + 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(); + infd = STDIN_FILENO; + if( program_mode != m_test ) + { + if( to_stdout || !default_output_filename.size() ) + outfd = STDOUT_FILENO; + else + { + output_filename = default_output_filename; + outfd_mode = all_rw; + if( !open_outstream( force ) ) + { + if( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + else + { + input_filename = filenames[i]; + const int eindex = extension_index( input_filename ); + infd = open_instream( input_filename, &in_stats, to_stdout ); + if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; } + if( program_mode != m_test ) + { + if( to_stdout ) outfd = STDOUT_FILENO; + else + { + set_d_outname( input_filename, eindex ); + outfd_mode = usr_rw; + if( !open_outstream( force ) ) + { + if( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + + if( !check_tty( infd ) ) return 1; + + if( output_filename.size() && !to_stdout && program_mode != m_test ) + delete_output_on_interrupt = true; + const struct stat * const in_statsp = input_filename.size() ? &in_stats : 0; + pp.set_name( input_filename ); + const int tmp = decompress( infd, pp, program_mode == m_test ); + if( tmp > retval ) retval = tmp; + if( tmp && program_mode != m_test ) cleanup_and_fail( retval ); + + if( delete_output_on_interrupt ) + close_and_set_permissions( in_statsp ); + if( input_filename.size() ) + { + close( infd ); infd = -1; + if( !keep_input_files && !to_stdout && program_mode != m_test ) + std::remove( input_filename.c_str() ); + } + } + if( outfd >= 0 && close( outfd ) != 0 ) + { + show_error( "Can't close stdout", errno ); + if( retval < 1 ) retval = 1; + } + return retval; + } diff --git a/merge.cc b/merge.cc new file mode 100644 index 0000000..298d90b --- /dev/null +++ b/merge.cc @@ -0,0 +1,406 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <cerrno> +#include <climits> +#include <cstdio> +#include <cstdlib> +#include <cstring> +#include <string> +#include <vector> +#include <stdint.h> +#include <unistd.h> +#include <sys/stat.h> + +#include "lzip.h" +#include "decoder.h" + + +namespace { + +class Block + { + long long pos_, size_; // pos + size <= LLONG_MAX + +public: + Block( const long long p, const long long s ) throw() + : pos_( p ), size_( s ) {} + + long long pos() const throw() { return pos_; } + long long size() const throw() { return size_; } + long long end() const throw() { return pos_ + size_; } + + void pos( const long long p ) throw() { pos_ = p; } + void size( const long long s ) throw() { size_ = s; } + void shift( Block & b ) throw() { ++size_; ++b.pos_; --b.size_; } + }; + + +bool copy_and_diff_file( const std::vector< int > & infd_vector, + const int outfd, std::vector< Block > & block_vector ) + { + const int buffer_size = 65536; + std::vector< uint8_t * > buffer_vector( infd_vector.size() ); + for( unsigned int i = 0; i < infd_vector.size(); ++i ) + buffer_vector[i] = new uint8_t[buffer_size]; + Block b( 0, 0 ); + long long partial_pos = 0; + int equal_bytes = 0; + bool error = false; + + while( true ) + { + const int rd = readblock( infd_vector[0], buffer_vector[0], buffer_size ); + if( rd != buffer_size && errno ) + { show_error( "Error reading input file", errno ); error = true; break; } + if( rd > 0 ) + { + for( unsigned int i = 1; i < infd_vector.size(); ++i ) + if( readblock( infd_vector[i], buffer_vector[i], rd ) != rd ) + { show_error( "Error reading input file", errno ); + error = true; break; } + if( error ) break; + const int wr = writeblock( outfd, buffer_vector[0], rd ); + if( wr != rd ) + { show_error( "Error writing output file", errno ); + error = true; break; } + for( int i = 0; i < rd; ++i ) + { + while( i < rd && b.pos() == 0 ) + { + for( unsigned int j = 1; j < infd_vector.size(); ++j ) + if( buffer_vector[0][i] != buffer_vector[j][i] ) + { b.pos( partial_pos + i ); break; } // begin block + ++i; + } + while( i < rd && b.pos() > 0 ) + { + ++equal_bytes; + for( unsigned int j = 1; j < infd_vector.size(); ++j ) + if( buffer_vector[0][i] != buffer_vector[j][i] ) + { equal_bytes = 0; break; } + if( equal_bytes >= 2 ) // end block + { + b.size( partial_pos + i - ( equal_bytes - 1 ) - b.pos() ); + block_vector.push_back( b ); + b.pos( 0 ); + equal_bytes = 0; + } + ++i; + } + } + partial_pos += rd; + } + if( rd < buffer_size ) break; // EOF + } + if( b.pos() > 0 ) // finish last block + { + b.size( partial_pos - b.pos() ); + block_vector.push_back( b ); + } + for( unsigned int i = 0; i < infd_vector.size(); ++i ) + delete[] buffer_vector[i]; + return !error; + } + + +int ipow( const unsigned int base, const unsigned int exponent ) throw() + { + int result = 1; + for( unsigned int i = 0; i < exponent; ++i ) + { + if( INT_MAX / base >= (unsigned int)result ) result *= base; + else { result = INT_MAX; break; } + } + return result; + } + + +int open_input_files( const std::vector< std::string > & filenames, + std::vector< int > & infd_vector, long long & isize ) + { + bool identical = false; + for( unsigned int i = 1; i < filenames.size(); ++i ) + if( filenames[0] == filenames[i] ) + { identical = true; break; } + if( !identical ) + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + struct stat in_stats; + ino_t st_ino0 = 0; + dev_t st_dev0 = 0; + infd_vector[i] = open_instream( filenames[i], &in_stats, true, true ); + if( infd_vector[i] < 0 ) return 1; + if( i == 0 ) { st_ino0 = in_stats.st_ino; st_dev0 = in_stats.st_dev; } + else if( st_ino0 == in_stats.st_ino && st_dev0 == in_stats.st_dev ) + { identical = true; break; } + } + if( identical ) { show_error( "Two input files are the same." ); return 1; } + + isize = 0; + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + const long long tmp = lseek( infd_vector[i], 0, SEEK_END ); + if( tmp < 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "File `%s' is not seekable.\n", filenames[i].c_str() ); + return 1; + } + if( i == 0 ) + { + isize = tmp; + if( isize < 36 ) { show_error( "Input file is too short." ); return 2; } + } + else if( isize != tmp ) + { show_error( "Sizes of input files are different." ); return 1; } + } + + for( unsigned int i = 0; i < filenames.size(); ++i ) + if( !verify_single_member( infd_vector[i], isize ) ) + return 2; + + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + if( lseek( infd_vector[i], 0, SEEK_SET ) < 0 ) + { show_error( "Seek error in input file", errno ); return 1; } + if( try_decompress( infd_vector[i], isize ) ) + { + if( verbosity >= 1 ) + std::printf( "File `%s' has no errors. Recovery is not needed.\n", + filenames[i].c_str() ); + return 0; + } + if( lseek( infd_vector[i], 0, SEEK_SET ) < 0 ) + { show_error( "Seek error in input file", errno ); return 1; } + } + return -1; + } + +} // end namespace + + +void cleanup_and_fail( const std::string & output_filename, + const int outfd, const int retval ) throw() + { + if( outfd >= 0 ) close( outfd ); + if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT ) + show_error( "WARNING: deletion of output file (apparently) failed." ); + std::exit( retval ); + } + + +bool copy_file( const int infd, const int outfd, const long long size ) + { + long long rest = size; + const int buffer_size = 65536; + uint8_t * const buffer = new uint8_t[buffer_size]; + bool error = false; + + while( true ) + { + const int block_size = std::min( (long long)buffer_size, rest ); + if( block_size <= 0 ) break; + const int rd = readblock( infd, buffer, block_size ); + if( rd != block_size && errno ) + { show_error( "Error reading input file", errno ); error = true; break; } + if( rd > 0 ) + { + const int wr = writeblock( outfd, buffer, rd ); + if( wr != rd ) + { show_error( "Error writing output file", errno ); + error = true; break; } + rest -= rd; + } + if( rd < block_size ) break; // EOF + } + delete[] buffer; + return !error; + } + + +bool try_decompress( const int fd, const long long file_size, + long long * failure_posp ) + { + try { + Range_decoder rdec( fd ); + File_header header; + rdec.reset_member_position(); + for( int i = 0; i < File_header::size; ++i ) + header.data[i] = rdec.get_byte(); + if( !rdec.finished() && // End Of File + header.verify_magic() && + header.version() == 1 && + header.dictionary_size() >= min_dictionary_size && + header.dictionary_size() <= max_dictionary_size ) + { + LZ_decoder decoder( header, rdec, -1 ); + std::vector< std::string > dummy_filenames; + Pretty_print dummy( dummy_filenames, -1 ); + + if( decoder.decode_member( dummy ) == 0 && + rdec.member_position() == file_size ) return true; + if( failure_posp ) *failure_posp = rdec.member_position(); + } + } + catch( std::bad_alloc ) + { + show_error( "Not enough memory. Find a machine with more memory." ); + std::exit( 1 ); + } + catch( Error e ) {} + return false; + } + + +bool verify_header( const File_header & header ) + { + if( !header.verify_magic() ) + { + show_error( "Bad magic number (file not in lzip format)." ); + return false; + } + if( header.version() == 0 ) + { + show_error( "Version 0 member format can't be recovered." ); + return false; + } + if( header.version() != 1 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "Version %d member format not supported.\n", + header.version() ); + return false; + } + return true; + } + + +bool verify_single_member( const int fd, const long long file_size ) + { + File_header header; + if( lseek( fd, 0, SEEK_SET ) < 0 || + readblock( fd, header.data, File_header::size ) != File_header::size ) + { show_error( "Error reading member header", errno ); return false; } + if( !verify_header( header ) ) return false; + + File_trailer trailer; + if( lseek( fd, -File_trailer::size(), SEEK_END ) < 0 || + readblock( fd, trailer.data, File_trailer::size() ) != File_trailer::size() ) + { show_error( "Error reading member trailer", errno ); return false; } + const long long member_size = trailer.member_size(); + if( member_size != file_size ) + { + if( member_size < file_size && + lseek( fd, -member_size, SEEK_END ) > 0 && + readblock( fd, header.data, File_header::size ) == File_header::size && + verify_header( header ) ) + show_error( "Input file has more than 1 member. Split it first." ); + else + show_error( "Member size in input file trailer is corrupt." ); + return false; + } + return true; + } + + +int merge_files( const std::vector< std::string > & filenames, + const std::string & output_filename, const bool force ) + { + std::vector< int > infd_vector( filenames.size() ); + long long isize = 0; + const int retval = open_input_files( filenames, infd_vector, isize ); + if( retval >= 0 ) return retval; + + const int outfd = open_outstream_rw( output_filename, force ); + if( outfd < 0 ) return 1; + + // vector of data blocks differing among the copies of the input file. + std::vector< Block > block_vector; + if( !copy_and_diff_file( infd_vector, outfd, block_vector ) ) + cleanup_and_fail( output_filename, outfd, 1 ); + + if( !block_vector.size() ) + { show_error( "Input files are identical. Recovery is not possible." ); + cleanup_and_fail( output_filename, outfd, 2 ); } + + const bool single_block = ( block_vector.size() == 1 ); + if( single_block && block_vector[0].size() < 2 ) + { show_error( "Input files have the same byte damaged." + " Try repairing one of them." ); + cleanup_and_fail( output_filename, outfd, 2 ); } + + if( ipow( filenames.size(), block_vector.size() ) >= INT_MAX || + ( single_block && + ipow( filenames.size(), 2 ) >= INT_MAX / block_vector[0].size() ) ) + { show_error( "Input files are too damaged. Recovery is not possible." ); + cleanup_and_fail( output_filename, outfd, 2 ); } + + const int shifts = ( single_block ? block_vector[0].size() - 1 : 1 ); + if( single_block ) + { + Block b( block_vector[0].pos() + 1, block_vector[0].size() - 1 ); + block_vector[0].size( 1 ); + block_vector.push_back( b ); + } + + const int base_variations = ipow( filenames.size(), block_vector.size() ); + const int variations = ( base_variations * shifts ) - 2; + bool done = false; + for( int var = 1; var <= variations; ++var ) + { + if( verbosity >= 1 ) + { + std::printf( "Trying variation %d of %d \r", var, variations ); + std::fflush( stdout ); + } + int tmp = var; + for( unsigned int i = 0; i < block_vector.size(); ++i ) + { + const int infd = infd_vector[tmp % filenames.size()]; + tmp /= filenames.size(); + if( lseek( infd, block_vector[i].pos(), SEEK_SET ) < 0 || + lseek( outfd, block_vector[i].pos(), SEEK_SET ) < 0 || + !copy_file( infd, outfd, block_vector[i].size() ) ) + { show_error( "Error reading output file", errno ); + cleanup_and_fail( output_filename, outfd, 1 ); } + } + if( lseek( outfd, 0, SEEK_SET ) < 0 ) + { show_error( "Seek error in output file", errno ); + cleanup_and_fail( output_filename, outfd, 1 ); } + if( try_decompress( outfd, isize ) ) + { done = true; break; } + if( var % base_variations == 0 ) block_vector[0].shift( block_vector[1] ); + } + if( verbosity >= 1 ) std::printf( "\n" ); + + if( close( outfd ) != 0 ) + { + show_error( "Error closing output file", errno ); + cleanup_and_fail( output_filename, -1, 1 ); + } + if( !done ) + { + show_error( "Some error areas overlap. Can't recover input file." ); + cleanup_and_fail( output_filename, -1, 2 ); + } + if( verbosity >= 1 ) + std::printf( "Input files merged successfully.\n" ); + return 0; + } diff --git a/repair.cc b/repair.cc new file mode 100644 index 0000000..8a92e59 --- /dev/null +++ b/repair.cc @@ -0,0 +1,114 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <cerrno> +#include <climits> +#include <cstdio> +#include <cstring> +#include <string> +#include <vector> +#include <stdint.h> +#include <sys/stat.h> + +#include "lzip.h" + + +int repair_file( const std::string & input_filename, + const std::string & output_filename, const bool force ) + { + struct stat in_stats; + const int infd = open_instream( input_filename, &in_stats, true, true ); + if( infd < 0 ) return 1; + const long long isize = lseek( infd, 0, SEEK_END ); + if( isize < 0 ) + { show_error( "Input file is not seekable", errno ); return 1; } + if( isize < 36 ) + { show_error( "Input file is too short." ); return 2; } + if( !verify_single_member( infd, isize ) ) return 2; + if( lseek( infd, 0, SEEK_SET ) < 0 ) + { show_error( "Seek error in input file", errno ); return 1; } + + long long failure_pos = 0; + if( try_decompress( infd, isize, &failure_pos ) ) + { + if( verbosity >= 1 ) + std::printf( "Input file has no errors. Recovery is not needed.\n" ); + return 0; + } + if( failure_pos >= isize - 8 ) failure_pos = isize - 8 - 1; + if( failure_pos < File_header::size ) + { show_error( "Can't repair error in input file." ); return 2; } + + if( lseek( infd, 0, SEEK_SET ) < 0 ) + { show_error( "Seek error in input file", errno ); return 1; } + + const int outfd = open_outstream_rw( output_filename, force ); + if( outfd < 0 ) { close( infd ); return 1; } + if( !copy_file( infd, outfd ) ) + cleanup_and_fail( output_filename, outfd, 1 ); + + const long long min_pos = + std::max( (long long)File_header::size, failure_pos - 1000 ); + bool done = false; + for( long long pos = failure_pos; pos >= min_pos; --pos ) + { + if( verbosity >= 1 ) + { + std::printf( "Trying position %lld \r", pos ); + std::fflush( stdout ); + } + uint8_t byte; + if( lseek( outfd, pos, SEEK_SET ) < 0 || + readblock( outfd, &byte, 1 ) != 1 ) + { show_error( "Error reading output file", errno ); + cleanup_and_fail( output_filename, outfd, 1 ); } + for( int i = 0; i < 255; ++i ) + { + ++byte; + if( lseek( outfd, pos, SEEK_SET ) < 0 || + writeblock( outfd, &byte, 1 ) != 1 || + lseek( outfd, 0, SEEK_SET ) < 0 ) + { show_error( "Error writing output file", errno ); + cleanup_and_fail( output_filename, outfd, 1 ); } + if( try_decompress( outfd, isize ) ) + { done = true; break; } + } + if( done ) break; + ++byte; + if( lseek( outfd, pos, SEEK_SET ) < 0 || + writeblock( outfd, &byte, 1 ) != 1 ) + { show_error( "Error writing output file", errno ); + cleanup_and_fail( output_filename, outfd, 1 ); } + } + if( verbosity >= 1 ) std::printf( "\n" ); + + if( close( outfd ) != 0 ) + { + show_error( "Error closing output file", errno ); + cleanup_and_fail( output_filename, -1, 1 ); + } + if( !done ) + { + show_error( "Error is larger than 1 byte. Can't repair input file." ); + cleanup_and_fail( output_filename, -1, 2 ); + } + if( verbosity >= 1 ) + std::printf( "Copy of input file repaired successfully.\n" ); + return 0; + } diff --git a/split.cc b/split.cc new file mode 100644 index 0000000..d6538f8 --- /dev/null +++ b/split.cc @@ -0,0 +1,176 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <cerrno> +#include <climits> +#include <cstdio> +#include <cstring> +#include <string> +#include <vector> +#include <stdint.h> +#include <sys/stat.h> + +#include "lzip.h" + + +namespace { + +void first_filename( const std::string & input_filename, + const std::string & default_output_filename, + std::string & output_filename ) + { + if( default_output_filename.size() ) + output_filename = default_output_filename; + else + output_filename = input_filename; + int b = output_filename.size(); + while( b > 0 && output_filename[b-1] != '/' ) --b; + output_filename.insert( b, "rec00001" ); + } + + +bool next_filename( std::string & output_filename ) + { + int b = output_filename.size(); + while( b > 0 && output_filename[b-1] != '/' ) --b; + for( int i = b + 7; i >= b + 3; --i ) // "rec00001" + { + if( output_filename[i] < '9' ) { ++output_filename[i]; return true; } + else output_filename[i] = '0'; + } + return false; + } + + +// Search forward from 'pos' for "LZIP" (Boyer-Moore algorithm) +// Return pos of found string or 'pos+size' if not found. +// +int find_magic( const uint8_t * const buffer, const int pos, const int size ) throw() + { + const unsigned char table[256] = { + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,1,4,4,3,4,4,4,4,4,4,4,4,4,4,4,4,4,2,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4, + 4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4 }; + + for( int i = pos; i <= pos + size - 4; i += table[buffer[i+3]] ) + if( buffer[i] == 'L' && buffer[i+1] == 'Z' && + buffer[i+2] == 'I' && buffer[i+3] == 'P' ) + return i; // magic string found + return pos + size; + } + + +int do_split_file( const std::string & input_filename, uint8_t * & base_buffer, + const std::string & default_output_filename, const bool force ) + { + const int hsize = File_header::size; + const int tsize = File_trailer::size(); + const int buffer_size = 65536; + const int base_buffer_size = tsize + buffer_size + hsize; + base_buffer = new uint8_t[base_buffer_size]; + uint8_t * const buffer = base_buffer + tsize; + + struct stat in_stats; + const int infd = open_instream( input_filename, &in_stats, true, true ); + if( infd < 0 ) return 1; + int size = readblock( infd, 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( "Input file is too short." ); return 2; } + if( !verify_header( *(File_header *)buffer ) ) return 2; + + std::string output_filename; + first_filename( input_filename, default_output_filename, output_filename ); + int outfd = open_outstream_rw( output_filename, force ); + if( outfd < 0 ) { close( infd ); return 1; } + + long long partial_member_size = 0; + while( true ) + { + int pos = 0; + for( int newpos = 1; newpos <= size; ++newpos ) + { + newpos = find_magic( buffer, newpos, size + 4 - newpos ); + if( newpos <= size ) + { + long long member_size = 0; + for( int i = 1; i <= 8; ++i ) + { member_size <<= 8; member_size += base_buffer[tsize+newpos-i]; } + if( partial_member_size + newpos - pos == member_size ) + { // header found + const int wr = writeblock( outfd, buffer + pos, newpos - pos ); + if( wr != newpos - pos ) + { show_error( "Write error", errno ); return 1; } + if( close( outfd ) != 0 ) + { show_error( "Error closing output file", errno ); return 1; } + if( !next_filename( output_filename ) ) + { show_error( "Too many members in file." ); close( infd ); return 1; } + outfd = open_outstream_rw( output_filename, force ); + if( outfd < 0 ) { close( infd ); return 1; } + partial_member_size = 0; + pos = newpos; + } + } + } + + if( at_stream_end ) + { + const int wr = writeblock( outfd, buffer + pos, size + hsize - pos ); + if( wr != size + hsize - pos ) + { show_error( "Write error", errno ); return 1; } + break; + } + if( pos < buffer_size ) + { + partial_member_size += buffer_size - pos; + const int wr = writeblock( outfd, 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 ); + size = readblock( infd, buffer + hsize, buffer_size ); + at_stream_end = ( size < buffer_size ); + if( size != buffer_size && errno ) + { show_error( "Read error", errno ); return 1; } + } + close( infd ); + if( close( outfd ) != 0 ) + { show_error( "Error closing output file", errno ); return 1; } + return 0; + } + +} // end namespace + + +int split_file( const std::string & input_filename, + const std::string & default_output_filename, const bool force ) + { + uint8_t * base_buffer; + const int retval = do_split_file( input_filename, base_buffer, + default_output_filename, force ); + delete[] base_buffer; + return retval; + } diff --git a/testsuite/check.sh b/testsuite/check.sh new file mode 100755 index 0000000..5885ba2 --- /dev/null +++ b/testsuite/check.sh @@ -0,0 +1,103 @@ +#! /bin/sh +# check script for Lziprecover - Data recovery tool for lzipped files +# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz. +# +# This script is free software: you have unlimited permission +# to copy, distribute and modify it. + +LC_ALL=C +export LC_ALL +objdir=`pwd` +testdir=`cd "$1" ; pwd` +LZIPRECOVER="${objdir}"/lziprecover +framework_failure() { echo "failure in testing framework" ; exit 1 ; } + +if [ ! -x "${LZIPRECOVER}" ] ; then + echo "${LZIPRECOVER}: cannot execute" + exit 1 +fi + +if [ -d tmp ] ; then rm -rf tmp ; fi +mkdir tmp +cd "${objdir}"/tmp + +ln "${testdir}"/test.txt in || framework_failure +ln "${testdir}"/test_v1.lz in.lz || framework_failure +cat in.lz in.lz in.lz > in3.lz || framework_failure +for i in 1 2 3 4 5 ; do + ln "${testdir}"/test_bad${i}.lz bad${i}.lz +done +fail=0 + +# Description of test files for lziprecover: +# test_bad1.lz: byte at offset 67 changed from 0xCC to 0x33 +# test_bad2.lz: [ 34- 66) --> copy of bytes [ 68- 100) +# test_bad3.lz: [ 512-1536) --> zeroed; [2560-3584) --> zeroed +# test_bad4.lz: [3072-4096) --> random data; [4608-5632) --> zeroed +# test_bad5.lz: [1024-2048) --> random data; [5120-6144) --> random data + +printf "testing lziprecover-%s..." "$2" + +"${LZIPRECOVER}" -m -o copy.lz bad1.lz bad2.lz bad1.lz -q +if [ $? != 1 ] ; then fail=1 ; printf - ; else printf . ; fi +"${LZIPRECOVER}" -m -o copy.lz bad1.lz bad2.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . +"${LZIPRECOVER}" -m -o copy.lz bad2.lz bad1.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . + +for i in 1 2 ; do + for j in 3 4 5 ; do + "${LZIPRECOVER}" -m -o copy.lz bad${i}.lz bad${j}.lz || fail=1 + "${LZIPRECOVER}" -df copy.lz || fail=1 + cmp in copy || fail=1 + printf . + "${LZIPRECOVER}" -m -o copy.lz bad${j}.lz bad${i}.lz || fail=1 + "${LZIPRECOVER}" -df copy.lz || fail=1 + cmp in copy || fail=1 + printf . + done +done + +"${LZIPRECOVER}" -m -o copy.lz bad3.lz bad4.lz bad5.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . +"${LZIPRECOVER}" -m -o copy.lz bad4.lz bad5.lz bad3.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . +"${LZIPRECOVER}" -m -o copy.lz bad5.lz bad3.lz bad4.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . + +"${LZIPRECOVER}" -R in.lz || fail=1 +printf . +"${LZIPRECOVER}" -R -o copy.lz bad2.lz -q +if [ $? != 2 ] ; then fail=1 ; printf - ; else printf . ; fi +"${LZIPRECOVER}" -R -o copy.lz bad1.lz || fail=1 +"${LZIPRECOVER}" -df copy.lz || fail=1 +cmp in copy || fail=1 +printf . + +cat in3.lz > out || framework_failure +printf "garbage" >> out || fail=1 +"${LZIPRECOVER}" -s out -o out.lz || fail=1 +for i in 1 2 3 ; do + "${LZIPRECOVER}" -cd rec0000${i}out.lz > copy || fail=1 + cmp in copy || fail=1 + printf . +done + +echo +if [ ${fail} = 0 ] ; then + echo "tests completed successfully." + cd "${objdir}" && rm -r tmp +else + echo "tests failed." +fi +exit ${fail} diff --git a/testsuite/test.txt b/testsuite/test.txt new file mode 100644 index 0000000..5b244d5 --- /dev/null +++ b/testsuite/test.txt @@ -0,0 +1,676 @@ +
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ <program> Copyright (C) <year> <name of author>
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
+
diff --git a/testsuite/test_bad1.lz b/testsuite/test_bad1.lz Binary files differnew file mode 100644 index 0000000..0b84883 --- /dev/null +++ b/testsuite/test_bad1.lz diff --git a/testsuite/test_bad2.lz b/testsuite/test_bad2.lz Binary files differnew file mode 100644 index 0000000..cce6a3c --- /dev/null +++ b/testsuite/test_bad2.lz diff --git a/testsuite/test_bad3.lz b/testsuite/test_bad3.lz Binary files differnew file mode 100644 index 0000000..a1676bb --- /dev/null +++ b/testsuite/test_bad3.lz diff --git a/testsuite/test_bad4.lz b/testsuite/test_bad4.lz Binary files differnew file mode 100644 index 0000000..a8f89a3 --- /dev/null +++ b/testsuite/test_bad4.lz diff --git a/testsuite/test_bad5.lz b/testsuite/test_bad5.lz Binary files differnew file mode 100644 index 0000000..73e0142 --- /dev/null +++ b/testsuite/test_bad5.lz diff --git a/testsuite/test_v0.lz b/testsuite/test_v0.lz Binary files differnew file mode 100644 index 0000000..a09b1e8 --- /dev/null +++ b/testsuite/test_v0.lz diff --git a/testsuite/test_v1.lz b/testsuite/test_v1.lz Binary files differnew file mode 100644 index 0000000..f1c79eb --- /dev/null +++ b/testsuite/test_v1.lz |