├── LICENSE ├── LzmaSpec.cpp ├── LzmaSpec.exe ├── README.md ├── examples ├── a.lzma ├── a.txt ├── a_eos.lzma ├── a_eos_and_size.lzma ├── a_lp1_lc2_pb1.lzma ├── bad_corrupted.lzma ├── bad_eos_incorrect_size.lzma ├── bad_incorrect_size.lzma └── info.txt ├── geo_lzma ├── lzma-specification.txt ├── lzmaSh2.cpp ├── lzmaSh2.exe ├── lzmaSh2a.cpp ├── lzmaSh2a.exe ├── lzmaspec-readme.txt └── test.bat /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /LzmaSpec.cpp: -------------------------------------------------------------------------------- 1 | /* LzmaSpec.c -- LZMA Reference Decoder 2 | 2015-06-14 : Igor Pavlov : Public domain */ 3 | 4 | // This code implements LZMA file decoding according to LZMA specification. 5 | // This code is not optimized for speed. 6 | 7 | #include 8 | 9 | #ifdef _MSC_VER 10 | #pragma warning(disable : 4710) // function not inlined 11 | #pragma warning(disable : 4996) // This function or variable may be unsafe 12 | #endif 13 | 14 | typedef unsigned char Byte; 15 | typedef unsigned short UInt16; 16 | 17 | #ifdef _LZMA_UINT32_IS_ULONG 18 | typedef unsigned long UInt32; 19 | #else 20 | typedef unsigned int UInt32; 21 | #endif 22 | 23 | #if defined(_MSC_VER) || defined(__BORLANDC__) 24 | typedef unsigned __int64 UInt64; 25 | #else 26 | typedef unsigned long long int UInt64; 27 | #endif 28 | 29 | 30 | struct CInputStream 31 | { 32 | FILE *File; 33 | UInt64 Processed; 34 | 35 | void Init() { Processed = 0; } 36 | 37 | Byte ReadByte() 38 | { 39 | int c = getc(File); 40 | if (c < 0) 41 | throw "Unexpected end of file"; 42 | Processed++; 43 | return (Byte)c; 44 | } 45 | }; 46 | 47 | 48 | struct COutStream 49 | { 50 | FILE *File; 51 | UInt64 Processed; 52 | 53 | void Init() { Processed = 0; } 54 | 55 | void WriteByte(Byte b) 56 | { 57 | if (putc(b, File) == EOF) 58 | throw "File writing error"; 59 | Processed++; 60 | } 61 | }; 62 | 63 | 64 | class COutWindow 65 | { 66 | Byte *Buf; 67 | UInt32 Pos; 68 | UInt32 Size; 69 | bool IsFull; 70 | 71 | public: 72 | unsigned TotalPos; 73 | COutStream OutStream; 74 | 75 | COutWindow(): Buf(NULL) {} 76 | ~COutWindow() { delete []Buf; } 77 | 78 | void Create(UInt32 dictSize) 79 | { 80 | Buf = new Byte[dictSize]; 81 | Pos = 0; 82 | Size = dictSize; 83 | IsFull = false; 84 | TotalPos = 0; 85 | } 86 | 87 | void PutByte(Byte b) 88 | { 89 | TotalPos++; 90 | Buf[Pos++] = b; 91 | if (Pos == Size) 92 | { 93 | Pos = 0; 94 | IsFull = true; 95 | } 96 | OutStream.WriteByte(b); 97 | } 98 | 99 | Byte GetByte(UInt32 dist) const 100 | { 101 | return Buf[dist <= Pos ? Pos - dist : Size - dist + Pos]; 102 | } 103 | 104 | void CopyMatch(UInt32 dist, unsigned len) 105 | { 106 | for (; len > 0; len--) 107 | PutByte(GetByte(dist)); 108 | } 109 | 110 | bool CheckDistance(UInt32 dist) const 111 | { 112 | return dist <= Pos || IsFull; 113 | } 114 | 115 | bool IsEmpty() const 116 | { 117 | return Pos == 0 && !IsFull; 118 | } 119 | }; 120 | 121 | 122 | #define kNumBitModelTotalBits 11 123 | #define kNumMoveBits 5 124 | 125 | typedef UInt16 CProb; 126 | 127 | #define PROB_INIT_VAL ((1 << kNumBitModelTotalBits) / 2) 128 | 129 | #define INIT_PROBS(p) \ 130 | { for (unsigned i = 0; i < sizeof(p) / sizeof(p[0]); i++) p[i] = PROB_INIT_VAL; } 131 | 132 | class CRangeDecoder 133 | { 134 | UInt32 Range; 135 | UInt32 Code; 136 | 137 | void Normalize(); 138 | 139 | public: 140 | 141 | CInputStream *InStream; 142 | bool Corrupted; 143 | 144 | bool Init(); 145 | bool IsFinishedOK() const { return Code == 0; } 146 | 147 | UInt32 DecodeDirectBits(unsigned numBits); 148 | unsigned DecodeBit(CProb *prob); 149 | }; 150 | 151 | bool CRangeDecoder::Init() 152 | { 153 | Corrupted = false; 154 | Range = 0xFFFFFFFF; 155 | Code = 0; 156 | 157 | Byte b = InStream->ReadByte(); 158 | 159 | for (int i = 0; i < 4; i++) 160 | Code = (Code << 8) | InStream->ReadByte(); 161 | 162 | if (b != 0 || Code == Range) 163 | Corrupted = true; 164 | return b == 0; 165 | } 166 | 167 | #define kTopValue ((UInt32)1 << 24) 168 | 169 | void CRangeDecoder::Normalize() 170 | { 171 | if (Range < kTopValue) 172 | { 173 | Range <<= 8; 174 | Code = (Code << 8) | InStream->ReadByte(); 175 | } 176 | } 177 | 178 | UInt32 CRangeDecoder::DecodeDirectBits(unsigned numBits) 179 | { 180 | UInt32 res = 0; 181 | do 182 | { 183 | Range >>= 1; 184 | Code -= Range; 185 | UInt32 t = 0 - ((UInt32)Code >> 31); 186 | Code += Range & t; 187 | 188 | if (Code == Range) 189 | Corrupted = true; 190 | 191 | Normalize(); 192 | res <<= 1; 193 | res += t + 1; 194 | } 195 | while (--numBits); 196 | return res; 197 | } 198 | 199 | unsigned CRangeDecoder::DecodeBit(CProb *prob) 200 | { 201 | unsigned v = *prob; 202 | UInt32 bound = (Range >> kNumBitModelTotalBits) * v; 203 | unsigned symbol; 204 | if (Code < bound) 205 | { 206 | v += ((1 << kNumBitModelTotalBits) - v) >> kNumMoveBits; 207 | Range = bound; 208 | symbol = 0; 209 | } 210 | else 211 | { 212 | v -= v >> kNumMoveBits; 213 | Code -= bound; 214 | Range -= bound; 215 | symbol = 1; 216 | } 217 | *prob = (CProb)v; 218 | Normalize(); 219 | return symbol; 220 | } 221 | 222 | 223 | unsigned BitTreeReverseDecode(CProb *probs, unsigned numBits, CRangeDecoder *rc) 224 | { 225 | unsigned m = 1; 226 | unsigned symbol = 0; 227 | for (unsigned i = 0; i < numBits; i++) 228 | { 229 | unsigned bit = rc->DecodeBit(&probs[m]); 230 | m <<= 1; 231 | m += bit; 232 | symbol |= (bit << i); 233 | } 234 | return symbol; 235 | } 236 | 237 | template 238 | class CBitTreeDecoder 239 | { 240 | CProb Probs[(unsigned)1 << NumBits]; 241 | 242 | public: 243 | 244 | void Init() 245 | { 246 | INIT_PROBS(Probs); 247 | } 248 | 249 | unsigned Decode(CRangeDecoder *rc) 250 | { 251 | unsigned m = 1; 252 | for (unsigned i = 0; i < NumBits; i++) 253 | m = (m << 1) + rc->DecodeBit(&Probs[m]); 254 | return m - ((unsigned)1 << NumBits); 255 | } 256 | 257 | unsigned ReverseDecode(CRangeDecoder *rc) 258 | { 259 | return BitTreeReverseDecode(Probs, NumBits, rc); 260 | } 261 | }; 262 | 263 | #define kNumPosBitsMax 4 264 | 265 | #define kNumStates 12 266 | #define kNumLenToPosStates 4 267 | #define kNumAlignBits 4 268 | #define kStartPosModelIndex 4 269 | #define kEndPosModelIndex 14 270 | #define kNumFullDistances (1 << (kEndPosModelIndex >> 1)) 271 | #define kMatchMinLen 2 272 | 273 | class CLenDecoder 274 | { 275 | CProb Choice; 276 | CProb Choice2; 277 | CBitTreeDecoder<3> LowCoder[1 << kNumPosBitsMax]; 278 | CBitTreeDecoder<3> MidCoder[1 << kNumPosBitsMax]; 279 | CBitTreeDecoder<8> HighCoder; 280 | 281 | public: 282 | 283 | void Init() 284 | { 285 | Choice = PROB_INIT_VAL; 286 | Choice2 = PROB_INIT_VAL; 287 | HighCoder.Init(); 288 | for (unsigned i = 0; i < (1 << kNumPosBitsMax); i++) 289 | { 290 | LowCoder[i].Init(); 291 | MidCoder[i].Init(); 292 | } 293 | } 294 | 295 | unsigned Decode(CRangeDecoder *rc, unsigned posState) 296 | { 297 | if (rc->DecodeBit(&Choice) == 0) 298 | return LowCoder[posState].Decode(rc); 299 | if (rc->DecodeBit(&Choice2) == 0) 300 | return 8 + MidCoder[posState].Decode(rc); 301 | return 16 + HighCoder.Decode(rc); 302 | } 303 | }; 304 | 305 | unsigned UpdateState_Literal(unsigned state) 306 | { 307 | if (state < 4) return 0; 308 | else if (state < 10) return state - 3; 309 | else return state - 6; 310 | } 311 | unsigned UpdateState_Match (unsigned state) { return state < 7 ? 7 : 10; } 312 | unsigned UpdateState_Rep (unsigned state) { return state < 7 ? 8 : 11; } 313 | unsigned UpdateState_ShortRep(unsigned state) { return state < 7 ? 9 : 11; } 314 | 315 | #define LZMA_DIC_MIN (1 << 12) 316 | 317 | class CLzmaDecoder 318 | { 319 | public: 320 | CRangeDecoder RangeDec; 321 | COutWindow OutWindow; 322 | 323 | bool markerIsMandatory; 324 | unsigned lc, pb, lp; 325 | UInt32 dictSize; 326 | UInt32 dictSizeInProperties; 327 | 328 | void DecodeProperties(const Byte *properties) 329 | { 330 | unsigned d = properties[0]; 331 | if (d >= (9 * 5 * 5)) 332 | throw "Incorrect LZMA properties"; 333 | lc = d % 9; 334 | d /= 9; 335 | pb = d / 5; 336 | lp = d % 5; 337 | dictSizeInProperties = 0; 338 | for (int i = 0; i < 4; i++) 339 | dictSizeInProperties |= (UInt32)properties[i + 1] << (8 * i); 340 | dictSize = dictSizeInProperties; 341 | if (dictSize < LZMA_DIC_MIN) 342 | dictSize = LZMA_DIC_MIN; 343 | } 344 | 345 | CLzmaDecoder(): LitProbs(NULL) {} 346 | ~CLzmaDecoder() { delete []LitProbs; } 347 | 348 | void Create() 349 | { 350 | OutWindow.Create(dictSize); 351 | CreateLiterals(); 352 | } 353 | 354 | int Decode(bool unpackSizeDefined, UInt64 unpackSize); 355 | 356 | private: 357 | 358 | CProb *LitProbs; 359 | 360 | void CreateLiterals() 361 | { 362 | LitProbs = new CProb[(UInt32)0x300 << (lc + lp)]; 363 | } 364 | 365 | void InitLiterals() 366 | { 367 | UInt32 num = (UInt32)0x300 << (lc + lp); 368 | for (UInt32 i = 0; i < num; i++) 369 | LitProbs[i] = PROB_INIT_VAL; 370 | } 371 | 372 | void DecodeLiteral(unsigned state, UInt32 rep0) 373 | { 374 | unsigned prevByte = 0; 375 | if (!OutWindow.IsEmpty()) 376 | prevByte = OutWindow.GetByte(1); 377 | 378 | unsigned symbol = 1; 379 | unsigned litState = ((OutWindow.TotalPos & ((1 << lp) - 1)) << lc) + (prevByte >> (8 - lc)); 380 | CProb *probs = &LitProbs[(UInt32)0x300 * litState]; 381 | 382 | if (state >= 7) 383 | { 384 | unsigned matchByte = OutWindow.GetByte(rep0 + 1); 385 | do 386 | { 387 | unsigned matchBit = (matchByte >> 7) & 1; 388 | matchByte <<= 1; 389 | unsigned bit = RangeDec.DecodeBit(&probs[((1 + matchBit) << 8) + symbol]); 390 | symbol = (symbol << 1) | bit; 391 | if (matchBit != bit) 392 | break; 393 | } 394 | while (symbol < 0x100); 395 | } 396 | while (symbol < 0x100) 397 | symbol = (symbol << 1) | RangeDec.DecodeBit(&probs[symbol]); 398 | OutWindow.PutByte((Byte)(symbol - 0x100)); 399 | } 400 | 401 | CBitTreeDecoder<6> PosSlotDecoder[kNumLenToPosStates]; 402 | CBitTreeDecoder AlignDecoder; 403 | CProb PosDecoders[1 + kNumFullDistances - kEndPosModelIndex]; 404 | 405 | void InitDist() 406 | { 407 | for (unsigned i = 0; i < kNumLenToPosStates; i++) 408 | PosSlotDecoder[i].Init(); 409 | AlignDecoder.Init(); 410 | INIT_PROBS(PosDecoders); 411 | } 412 | 413 | unsigned DecodeDistance(unsigned len) 414 | { 415 | unsigned lenState = len; 416 | if (lenState > kNumLenToPosStates - 1) 417 | lenState = kNumLenToPosStates - 1; 418 | 419 | unsigned posSlot = PosSlotDecoder[lenState].Decode(&RangeDec); 420 | if (posSlot < 4) 421 | return posSlot; 422 | 423 | unsigned numDirectBits = (unsigned)((posSlot >> 1) - 1); 424 | UInt32 dist = ((2 | (posSlot & 1)) << numDirectBits); 425 | if (posSlot < kEndPosModelIndex) 426 | dist += BitTreeReverseDecode(PosDecoders + dist - posSlot, numDirectBits, &RangeDec); 427 | else 428 | { 429 | dist += RangeDec.DecodeDirectBits(numDirectBits - kNumAlignBits) << kNumAlignBits; 430 | dist += AlignDecoder.ReverseDecode(&RangeDec); 431 | } 432 | return dist; 433 | } 434 | 435 | CProb IsMatch[kNumStates << kNumPosBitsMax]; 436 | CProb IsRep[kNumStates]; 437 | CProb IsRepG0[kNumStates]; 438 | CProb IsRepG1[kNumStates]; 439 | CProb IsRepG2[kNumStates]; 440 | CProb IsRep0Long[kNumStates << kNumPosBitsMax]; 441 | 442 | CLenDecoder LenDecoder; 443 | CLenDecoder RepLenDecoder; 444 | 445 | void Init() 446 | { 447 | InitLiterals(); 448 | InitDist(); 449 | 450 | INIT_PROBS(IsMatch); 451 | INIT_PROBS(IsRep); 452 | INIT_PROBS(IsRepG0); 453 | INIT_PROBS(IsRepG1); 454 | INIT_PROBS(IsRepG2); 455 | INIT_PROBS(IsRep0Long); 456 | 457 | LenDecoder.Init(); 458 | RepLenDecoder.Init(); 459 | } 460 | }; 461 | 462 | 463 | #define LZMA_RES_ERROR 0 464 | #define LZMA_RES_FINISHED_WITH_MARKER 1 465 | #define LZMA_RES_FINISHED_WITHOUT_MARKER 2 466 | 467 | int CLzmaDecoder::Decode(bool unpackSizeDefined, UInt64 unpackSize) 468 | { 469 | if (!RangeDec.Init()) 470 | return LZMA_RES_ERROR; 471 | 472 | Init(); 473 | 474 | UInt32 rep0 = 0, rep1 = 0, rep2 = 0, rep3 = 0; 475 | unsigned state = 0; 476 | 477 | for (;;) 478 | { 479 | if (unpackSizeDefined && unpackSize == 0 && !markerIsMandatory) 480 | if (RangeDec.IsFinishedOK()) 481 | return LZMA_RES_FINISHED_WITHOUT_MARKER; 482 | 483 | unsigned posState = OutWindow.TotalPos & ((1 << pb) - 1); 484 | 485 | if (RangeDec.DecodeBit(&IsMatch[(state << kNumPosBitsMax) + posState]) == 0) 486 | { 487 | if (unpackSizeDefined && unpackSize == 0) 488 | return LZMA_RES_ERROR; 489 | DecodeLiteral(state, rep0); 490 | state = UpdateState_Literal(state); 491 | unpackSize--; 492 | continue; 493 | } 494 | 495 | unsigned len; 496 | 497 | if (RangeDec.DecodeBit(&IsRep[state]) != 0) 498 | { 499 | if (unpackSizeDefined && unpackSize == 0) 500 | return LZMA_RES_ERROR; 501 | if (OutWindow.IsEmpty()) 502 | return LZMA_RES_ERROR; 503 | if (RangeDec.DecodeBit(&IsRepG0[state]) == 0) 504 | { 505 | if (RangeDec.DecodeBit(&IsRep0Long[(state << kNumPosBitsMax) + posState]) == 0) 506 | { 507 | state = UpdateState_ShortRep(state); 508 | OutWindow.PutByte(OutWindow.GetByte(rep0 + 1)); 509 | unpackSize--; 510 | continue; 511 | } 512 | } 513 | else 514 | { 515 | UInt32 dist; 516 | if (RangeDec.DecodeBit(&IsRepG1[state]) == 0) 517 | dist = rep1; 518 | else 519 | { 520 | if (RangeDec.DecodeBit(&IsRepG2[state]) == 0) 521 | dist = rep2; 522 | else 523 | { 524 | dist = rep3; 525 | rep3 = rep2; 526 | } 527 | rep2 = rep1; 528 | } 529 | rep1 = rep0; 530 | rep0 = dist; 531 | } 532 | len = RepLenDecoder.Decode(&RangeDec, posState); 533 | state = UpdateState_Rep(state); 534 | } 535 | else 536 | { 537 | rep3 = rep2; 538 | rep2 = rep1; 539 | rep1 = rep0; 540 | len = LenDecoder.Decode(&RangeDec, posState); 541 | state = UpdateState_Match(state); 542 | rep0 = DecodeDistance(len); 543 | if (rep0 == 0xFFFFFFFF) 544 | return RangeDec.IsFinishedOK() ? 545 | LZMA_RES_FINISHED_WITH_MARKER : 546 | LZMA_RES_ERROR; 547 | 548 | if (unpackSizeDefined && unpackSize == 0) 549 | return LZMA_RES_ERROR; 550 | if (rep0 >= dictSize || !OutWindow.CheckDistance(rep0)) 551 | return LZMA_RES_ERROR; 552 | } 553 | len += kMatchMinLen; 554 | bool isError = false; 555 | if (unpackSizeDefined && unpackSize < len) 556 | { 557 | len = (unsigned)unpackSize; 558 | isError = true; 559 | } 560 | OutWindow.CopyMatch(rep0 + 1, len); 561 | unpackSize -= len; 562 | if (isError) 563 | return LZMA_RES_ERROR; 564 | } 565 | } 566 | 567 | static void Print(const char *s) 568 | { 569 | fputs(s, stdout); 570 | } 571 | 572 | static void PrintError(const char *s) 573 | { 574 | fputs(s, stderr); 575 | } 576 | 577 | 578 | #define CONVERT_INT_TO_STR(charType, tempSize) \ 579 | 580 | void ConvertUInt64ToString(UInt64 val, char *s) 581 | { 582 | char temp[32]; 583 | unsigned i = 0; 584 | while (val >= 10) 585 | { 586 | temp[i++] = (char)('0' + (unsigned)(val % 10)); 587 | val /= 10; 588 | } 589 | *s++ = (char)('0' + (unsigned)val); 590 | while (i != 0) 591 | { 592 | i--; 593 | *s++ = temp[i]; 594 | } 595 | *s = 0; 596 | } 597 | 598 | void PrintUInt64(const char *title, UInt64 v) 599 | { 600 | Print(title); 601 | Print(" : "); 602 | char s[32]; 603 | ConvertUInt64ToString(v, s); 604 | Print(s); 605 | Print(" bytes \n"); 606 | } 607 | 608 | int main2(int numArgs, const char *args[]) 609 | { 610 | Print("\nLZMA Reference Decoder 15.00 : Igor Pavlov : Public domain : 2015-04-16\n"); 611 | if (numArgs == 1) 612 | Print("\nUse: lzmaSpec a.lzma outFile"); 613 | 614 | if (numArgs != 3) 615 | throw "you must specify two parameters"; 616 | 617 | CInputStream inStream; 618 | inStream.File = fopen(args[1], "rb"); 619 | inStream.Init(); 620 | if (inStream.File == 0) 621 | throw "Can't open input file"; 622 | 623 | CLzmaDecoder lzmaDecoder; 624 | lzmaDecoder.OutWindow.OutStream.File = fopen(args[2], "wb+"); 625 | lzmaDecoder.OutWindow.OutStream.Init(); 626 | if (inStream.File == 0) 627 | throw "Can't open output file"; 628 | 629 | Byte header[13]; 630 | int i; 631 | for (i = 0; i < 13; i++) 632 | header[i] = inStream.ReadByte(); 633 | 634 | lzmaDecoder.DecodeProperties(header); 635 | 636 | printf("\nlc=%d, lp=%d, pb=%d", lzmaDecoder.lc, lzmaDecoder.lp, lzmaDecoder.pb); 637 | printf("\nDictionary Size in properties = %u", lzmaDecoder.dictSizeInProperties); 638 | printf("\nDictionary Size for decoding = %u", lzmaDecoder.dictSize); 639 | 640 | UInt64 unpackSize = 0; 641 | bool unpackSizeDefined = false; 642 | for (i = 0; i < 8; i++) 643 | { 644 | Byte b = header[5 + i]; 645 | if (b != 0xFF) 646 | unpackSizeDefined = true; 647 | unpackSize |= (UInt64)b << (8 * i); 648 | } 649 | 650 | lzmaDecoder.markerIsMandatory = !unpackSizeDefined; 651 | 652 | Print("\n"); 653 | if (unpackSizeDefined) 654 | PrintUInt64("Uncompressed Size", unpackSize); 655 | else 656 | Print("End marker is expected\n"); 657 | lzmaDecoder.RangeDec.InStream = &inStream; 658 | 659 | Print("\n"); 660 | 661 | lzmaDecoder.Create(); 662 | 663 | int res = lzmaDecoder.Decode(unpackSizeDefined, unpackSize); 664 | 665 | PrintUInt64("Read ", inStream.Processed); 666 | PrintUInt64("Written ", lzmaDecoder.OutWindow.OutStream.Processed); 667 | 668 | if (res == LZMA_RES_ERROR) 669 | throw "LZMA decoding error"; 670 | else if (res == LZMA_RES_FINISHED_WITHOUT_MARKER) 671 | Print("Finished without end marker"); 672 | else if (res == LZMA_RES_FINISHED_WITH_MARKER) 673 | { 674 | if (unpackSizeDefined) 675 | { 676 | if (lzmaDecoder.OutWindow.OutStream.Processed != unpackSize) 677 | throw "Finished with end marker before than specified size"; 678 | Print("Warning: "); 679 | } 680 | Print("Finished with end marker"); 681 | } 682 | else 683 | throw "Internal Error"; 684 | 685 | Print("\n"); 686 | 687 | if (lzmaDecoder.RangeDec.Corrupted) 688 | { 689 | Print("\nWarning: LZMA stream is corrupted\n"); 690 | } 691 | 692 | return 0; 693 | } 694 | 695 | 696 | int 697 | #ifdef _MSC_VER 698 | __cdecl 699 | #endif 700 | main(int numArgs, const char *args[]) 701 | { 702 | try { return main2(numArgs, args); } 703 | catch (const char *s) 704 | { 705 | PrintError("\nError:\n"); 706 | PrintError(s); 707 | PrintError("\n"); 708 | return 1; 709 | } 710 | catch(...) 711 | { 712 | PrintError("\nError\n"); 713 | return 1; 714 | } 715 | } 716 | -------------------------------------------------------------------------------- /LzmaSpec.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/LzmaSpec.exe -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # lzma_sh 2 | compact lzma decoder 3 | 4 | lzmaSh2a.cpp is a little longer (247 LoC vs 228), but has an explicit state table 5 | and integrated id decoding. 6 | 7 | LzmaSpec.cpp is the "official" demo decoder, 716 LoC 8 | 9 | 10 | -------------------------------------------------------------------------------- /examples/a.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/a.lzma -------------------------------------------------------------------------------- /examples/a.txt: -------------------------------------------------------------------------------- 1 | LZMA decoder test example 2 | ========================= 3 | ! LZMA ! Decoder ! TEST ! 4 | ========================= 5 | ! TEST ! LZMA ! Decoder ! 6 | ========================= 7 | ---- Test Line 1 -------- 8 | ========================= 9 | ---- Test Line 2 -------- 10 | ========================= 11 | === End of test file ==== 12 | ========================= 13 | -------------------------------------------------------------------------------- /examples/a_eos.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/a_eos.lzma -------------------------------------------------------------------------------- /examples/a_eos_and_size.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/a_eos_and_size.lzma -------------------------------------------------------------------------------- /examples/a_lp1_lc2_pb1.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/a_lp1_lc2_pb1.lzma -------------------------------------------------------------------------------- /examples/bad_corrupted.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/bad_corrupted.lzma -------------------------------------------------------------------------------- /examples/bad_eos_incorrect_size.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/bad_eos_incorrect_size.lzma -------------------------------------------------------------------------------- /examples/bad_incorrect_size.lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/examples/bad_incorrect_size.lzma -------------------------------------------------------------------------------- /examples/info.txt: -------------------------------------------------------------------------------- 1 | GOOD archives: 2 | 3 | a.lzma 4 | the stream was compressed with default properties lp=0 lc=3 pb=2 and 64 KiB dictionary 5 | a_eos.lzma 6 | the stream has EOS marker 7 | a_eos_and_size.lzma 8 | the stream has EOS marker and unpack size is defined 9 | a_lp1_lc2_pb1.lzma 10 | the stream was compressed with lp=1 lc=2 pb=1 properties 11 | 12 | 13 | BAD ARCHIVES: 14 | 15 | bad_corrupted.lzma 16 | some bytes in compressed stream were changed 17 | bad_eos_incorrect_size.lzma 18 | the stream has EOS marker and unpack size in header is larger than real uncompressed size 19 | bad_incorrect_size.lzma 20 | the header contains incorrect size (290). The correct size is 327 21 | -------------------------------------------------------------------------------- /geo_lzma: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/geo_lzma -------------------------------------------------------------------------------- /lzma-specification.txt: -------------------------------------------------------------------------------- 1 | LZMA specification (DRAFT version) 2 | ---------------------------------- 3 | 4 | Author: Igor Pavlov 5 | Date: 2015-06-14 6 | 7 | This specification defines the format of LZMA compressed data and lzma file format. 8 | 9 | Notation 10 | -------- 11 | 12 | We use the syntax of C++ programming language. 13 | We use the following types in C++ code: 14 | unsigned - unsigned integer, at least 16 bits in size 15 | int - signed integer, at least 16 bits in size 16 | UInt64 - 64-bit unsigned integer 17 | UInt32 - 32-bit unsigned integer 18 | UInt16 - 16-bit unsigned integer 19 | Byte - 8-bit unsigned integer 20 | bool - boolean type with two possible values: false, true 21 | 22 | 23 | lzma file format 24 | ================ 25 | 26 | The lzma file contains the raw LZMA stream and the header with related properties. 27 | 28 | The files in that format use ".lzma" extension. 29 | 30 | The lzma file format layout: 31 | 32 | Offset Size Description 33 | 34 | 0 1 LZMA model properties (lc, lp, pb) in encoded form 35 | 1 4 Dictionary size (32-bit unsigned integer, little-endian) 36 | 5 8 Uncompressed size (64-bit unsigned integer, little-endian) 37 | 13 Compressed data (LZMA stream) 38 | 39 | LZMA properties: 40 | 41 | name Range Description 42 | 43 | lc [0, 8] the number of "literal context" bits 44 | lp [0, 4] the number of "literal pos" bits 45 | pb [0, 4] the number of "pos" bits 46 | dictSize [0, 2^32 - 1] the dictionary size 47 | 48 | The following code encodes LZMA properties: 49 | 50 | void EncodeProperties(Byte *properties) 51 | { 52 | properties[0] = (Byte)((pb * 5 + lp) * 9 + lc); 53 | Set_UInt32_LittleEndian(properties + 1, dictSize); 54 | } 55 | 56 | If the value of dictionary size in properties is smaller than (1 << 12), 57 | the LZMA decoder must set the dictionary size variable to (1 << 12). 58 | 59 | #define LZMA_DIC_MIN (1 << 12) 60 | 61 | unsigned lc, pb, lp; 62 | UInt32 dictSize; 63 | UInt32 dictSizeInProperties; 64 | 65 | void DecodeProperties(const Byte *properties) 66 | { 67 | unsigned d = properties[0]; 68 | if (d >= (9 * 5 * 5)) 69 | throw "Incorrect LZMA properties"; 70 | lc = d % 9; 71 | d /= 9; 72 | pb = d / 5; 73 | lp = d % 5; 74 | dictSizeInProperties = 0; 75 | for (int i = 0; i < 4; i++) 76 | dictSizeInProperties |= (UInt32)properties[i + 1] << (8 * i); 77 | dictSize = dictSizeInProperties; 78 | if (dictSize < LZMA_DIC_MIN) 79 | dictSize = LZMA_DIC_MIN; 80 | } 81 | 82 | If "Uncompressed size" field contains ones in all 64 bits, it means that 83 | uncompressed size is unknown and there is the "end marker" in stream, 84 | that indicates the end of decoding point. 85 | In opposite case, if the value from "Uncompressed size" field is not 86 | equal to ((2^64) - 1), the LZMA stream decoding must be finished after 87 | specified number of bytes (Uncompressed size) is decoded. And if there 88 | is the "end marker", the LZMA decoder must read that marker also. 89 | 90 | 91 | The new scheme to encode LZMA properties 92 | ---------------------------------------- 93 | 94 | If LZMA compression is used for some another format, it's recommended to 95 | use a new improved scheme to encode LZMA properties. That new scheme was 96 | used in xz format that uses the LZMA2 compression algorithm. 97 | The LZMA2 is a new compression algorithm that is based on the LZMA algorithm. 98 | 99 | The dictionary size in LZMA2 is encoded with just one byte and LZMA2 supports 100 | only reduced set of dictionary sizes: 101 | (2 << 11), (3 << 11), 102 | (2 << 12), (3 << 12), 103 | ... 104 | (2 << 30), (3 << 30), 105 | (2 << 31) - 1 106 | 107 | The dictionary size can be extracted from encoded value with the following code: 108 | 109 | dictSize = (p == 40) ? 0xFFFFFFFF : (((UInt32)2 | ((p) & 1)) << ((p) / 2 + 11)); 110 | 111 | Also there is additional limitation (lc + lp <= 4) in LZMA2 for values of 112 | "lc" and "lp" properties: 113 | 114 | if (lc + lp > 4) 115 | throw "Unsupported properties: (lc + lp) > 4"; 116 | 117 | There are some advantages for LZMA decoder with such (lc + lp) value 118 | limitation. It reduces the maximum size of tables allocated by decoder. 119 | And it reduces the complexity of initialization procedure, that can be 120 | important to keep high speed of decoding of big number of small LZMA streams. 121 | 122 | It's recommended to use that limitation (lc + lp <= 4) for any new format 123 | that uses LZMA compression. Note that the combinations of "lc" and "lp" 124 | parameters, where (lc + lp > 4), can provide significant improvement in 125 | compression ratio only in some rare cases. 126 | 127 | The LZMA properties can be encoded into two bytes in new scheme: 128 | 129 | Offset Size Description 130 | 131 | 0 1 The dictionary size encoded with LZMA2 scheme 132 | 1 1 LZMA model properties (lc, lp, pb) in encoded form 133 | 134 | 135 | The RAM usage 136 | ============= 137 | 138 | The RAM usage for LZMA decoder is determined by the following parts: 139 | 140 | 1) The Sliding Window (from 4 KiB to 4 GiB). 141 | 2) The probability model counter arrays (arrays of 16-bit variables). 142 | 3) Some additional state variables (about 10 variables of 32-bit integers). 143 | 144 | 145 | The RAM usage for Sliding Window 146 | -------------------------------- 147 | 148 | There are two main scenarios of decoding: 149 | 150 | 1) The decoding of full stream to one RAM buffer. 151 | 152 | If we decode full LZMA stream to one output buffer in RAM, the decoder 153 | can use that output buffer as sliding window. So the decoder doesn't 154 | need additional buffer allocated for sliding window. 155 | 156 | 2) The decoding to some external storage. 157 | 158 | If we decode LZMA stream to external storage, the decoder must allocate 159 | the buffer for sliding window. The size of that buffer must be equal 160 | or larger than the value of dictionary size from properties of LZMA stream. 161 | 162 | In this specification we describe the code for decoding to some external 163 | storage. The optimized version of code for decoding of full stream to one 164 | output RAM buffer can require some minor changes in code. 165 | 166 | 167 | The RAM usage for the probability model counters 168 | ------------------------------------------------ 169 | 170 | The size of the probability model counter arrays is calculated with the 171 | following formula: 172 | 173 | size_of_prob_arrays = 1846 + 768 * (1 << (lp + lc)) 174 | 175 | Each probability model counter is 11-bit unsigned integer. 176 | If we use 16-bit integer variables (2-byte integers) for these probability 177 | model counters, the RAM usage required by probability model counter arrays 178 | can be estimated with the following formula: 179 | 180 | RAM = 4 KiB + 1.5 KiB * (1 << (lp + lc)) 181 | 182 | For example, for default LZMA parameters (lp = 0 and lc = 3), the RAM usage is 183 | 184 | RAM_lc3_lp0 = 4 KiB + 1.5 KiB * 8 = 16 KiB 185 | 186 | The maximum RAM state usage is required for decoding the stream with lp = 4 187 | and lc = 8: 188 | 189 | RAM_lc8_lp4 = 4 KiB + 1.5 KiB * 4096 = 6148 KiB 190 | 191 | If the decoder uses LZMA2's limited property condition 192 | (lc + lp <= 4), the RAM usage will be not larger than 193 | 194 | RAM_lc_lp_4 = 4 KiB + 1.5 KiB * 16 = 28 KiB 195 | 196 | 197 | The RAM usage for encoder 198 | ------------------------- 199 | 200 | There are many variants for LZMA encoding code. 201 | These variants have different values for memory consumption. 202 | Note that memory consumption for LZMA Encoder can not be 203 | smaller than memory consumption of LZMA Decoder for same stream. 204 | 205 | The RAM usage required by modern effective implementation of 206 | LZMA Encoder can be estimated with the following formula: 207 | 208 | Encoder_RAM_Usage = 4 MiB + 11 * dictionarySize. 209 | 210 | But there are some modes of the encoder that require less memory. 211 | 212 | 213 | LZMA Decoding 214 | ============= 215 | 216 | The LZMA compression algorithm uses LZ-based compression with Sliding Window 217 | and Range Encoding as entropy coding method. 218 | 219 | 220 | Sliding Window 221 | -------------- 222 | 223 | LZMA uses Sliding Window compression similar to LZ77 algorithm. 224 | 225 | LZMA stream must be decoded to the sequence that consists 226 | of MATCHES and LITERALS: 227 | 228 | - a LITERAL is a 8-bit character (one byte). 229 | The decoder just puts that LITERAL to the uncompressed stream. 230 | 231 | - a MATCH is a pair of two numbers (DISTANCE-LENGTH pair). 232 | The decoder takes one byte exactly "DISTANCE" characters behind 233 | current position in the uncompressed stream and puts it to 234 | uncompressed stream. The decoder must repeat it "LENGTH" times. 235 | 236 | The "DISTANCE" can not be larger than dictionary size. 237 | And the "DISTANCE" can not be larger than the number of bytes in 238 | the uncompressed stream that were decoded before that match. 239 | 240 | In this specification we use cyclic buffer to implement Sliding Window 241 | for LZMA decoder: 242 | 243 | class COutWindow 244 | { 245 | Byte *Buf; 246 | UInt32 Pos; 247 | UInt32 Size; 248 | bool IsFull; 249 | 250 | public: 251 | unsigned TotalPos; 252 | COutStream OutStream; 253 | 254 | COutWindow(): Buf(NULL) {} 255 | ~COutWindow() { delete []Buf; } 256 | 257 | void Create(UInt32 dictSize) 258 | { 259 | Buf = new Byte[dictSize]; 260 | Pos = 0; 261 | Size = dictSize; 262 | IsFull = false; 263 | TotalPos = 0; 264 | } 265 | 266 | void PutByte(Byte b) 267 | { 268 | TotalPos++; 269 | Buf[Pos++] = b; 270 | if (Pos == Size) 271 | { 272 | Pos = 0; 273 | IsFull = true; 274 | } 275 | OutStream.WriteByte(b); 276 | } 277 | 278 | Byte GetByte(UInt32 dist) const 279 | { 280 | return Buf[dist <= Pos ? Pos - dist : Size - dist + Pos]; 281 | } 282 | 283 | void CopyMatch(UInt32 dist, unsigned len) 284 | { 285 | for (; len > 0; len--) 286 | PutByte(GetByte(dist)); 287 | } 288 | 289 | bool CheckDistance(UInt32 dist) const 290 | { 291 | return dist <= Pos || IsFull; 292 | } 293 | 294 | bool IsEmpty() const 295 | { 296 | return Pos == 0 && !IsFull; 297 | } 298 | }; 299 | 300 | 301 | In another implementation it's possible to use one buffer that contains 302 | Sliding Window and the whole data stream after uncompressing. 303 | 304 | 305 | Range Decoder 306 | ------------- 307 | 308 | LZMA algorithm uses Range Encoding (1) as entropy coding method. 309 | 310 | LZMA stream contains just one very big number in big-endian encoding. 311 | LZMA decoder uses the Range Decoder to extract a sequence of binary 312 | symbols from that big number. 313 | 314 | The state of the Range Decoder: 315 | 316 | struct CRangeDecoder 317 | { 318 | UInt32 Range; 319 | UInt32 Code; 320 | InputStream *InStream; 321 | 322 | bool Corrupted; 323 | } 324 | 325 | The notes about UInt32 type for the "Range" and "Code" variables: 326 | 327 | It's possible to use 64-bit (unsigned or signed) integer type 328 | for the "Range" and the "Code" variables instead of 32-bit unsigned, 329 | but some additional code must be used to truncate the values to 330 | low 32-bits after some operations. 331 | 332 | If the programming language does not support 32-bit unsigned integer type 333 | (like in case of JAVA language), it's possible to use 32-bit signed integer, 334 | but some code must be changed. For example, it's required to change the code 335 | that uses comparison operations for UInt32 variables in this specification. 336 | 337 | The Range Decoder can be in some states that can be treated as 338 | "Corruption" in LZMA stream. The Range Decoder uses the variable "Corrupted": 339 | 340 | (Corrupted == false), if the Range Decoder has not detected any corruption. 341 | (Corrupted == true), if the Range Decoder has detected some corruption. 342 | 343 | The reference LZMA Decoder ignores the value of the "Corrupted" variable. 344 | So it continues to decode the stream, even if the corruption can be detected 345 | in the Range Decoder. To provide the full compatibility with output of the 346 | reference LZMA Decoder, another LZMA Decoder implementations must also 347 | ignore the value of the "Corrupted" variable. 348 | 349 | The LZMA Encoder is required to create only such LZMA streams, that will not 350 | lead the Range Decoder to states, where the "Corrupted" variable is set to true. 351 | 352 | The Range Decoder reads first 5 bytes from input stream to initialize 353 | the state: 354 | 355 | bool CRangeDecoder::Init() 356 | { 357 | Corrupted = false; 358 | Range = 0xFFFFFFFF; 359 | Code = 0; 360 | 361 | Byte b = InStream->ReadByte(); 362 | 363 | for (int i = 0; i < 4; i++) 364 | Code = (Code << 8) | InStream->ReadByte(); 365 | 366 | if (b != 0 || Code == Range) 367 | Corrupted = true; 368 | return b == 0; 369 | } 370 | 371 | The LZMA Encoder always writes ZERO in initial byte of compressed stream. 372 | That scheme allows to simplify the code of the Range Encoder in the 373 | LZMA Encoder. If initial byte is not equal to ZERO, the LZMA Decoder must 374 | stop decoding and report error. 375 | 376 | After the last bit of data was decoded by Range Decoder, the value of the 377 | "Code" variable must be equal to 0. The LZMA Decoder must check it by 378 | calling the IsFinishedOK() function: 379 | 380 | bool IsFinishedOK() const { return Code == 0; } 381 | 382 | If there is corruption in data stream, there is big probability that 383 | the "Code" value will be not equal to 0 in the Finish() function. So that 384 | check in the IsFinishedOK() function provides very good feature for 385 | corruption detection. 386 | 387 | The value of the "Range" variable before each bit decoding can not be smaller 388 | than ((UInt32)1 << 24). The Normalize() function keeps the "Range" value in 389 | described range. 390 | 391 | #define kTopValue ((UInt32)1 << 24) 392 | 393 | void CRangeDecoder::Normalize() 394 | { 395 | if (Range < kTopValue) 396 | { 397 | Range <<= 8; 398 | Code = (Code << 8) | InStream->ReadByte(); 399 | } 400 | } 401 | 402 | Notes: if the size of the "Code" variable is larger than 32 bits, it's 403 | required to keep only low 32 bits of the "Code" variable after the change 404 | in Normalize() function. 405 | 406 | If the LZMA Stream is not corrupted, the value of the "Code" variable is 407 | always smaller than value of the "Range" variable. 408 | But the Range Decoder ignores some types of corruptions, so the value of 409 | the "Code" variable can be equal or larger than value of the "Range" variable 410 | for some "Corrupted" archives. 411 | 412 | 413 | LZMA uses Range Encoding only with binary symbols of two types: 414 | 1) binary symbols with fixed and equal probabilities (direct bits) 415 | 2) binary symbols with predicted probabilities 416 | 417 | The DecodeDirectBits() function decodes the sequence of direct bits: 418 | 419 | UInt32 CRangeDecoder::DecodeDirectBits(unsigned numBits) 420 | { 421 | UInt32 res = 0; 422 | do 423 | { 424 | Range >>= 1; 425 | Code -= Range; 426 | UInt32 t = 0 - ((UInt32)Code >> 31); 427 | Code += Range & t; 428 | 429 | if (Code == Range) 430 | Corrupted = true; 431 | 432 | Normalize(); 433 | res <<= 1; 434 | res += t + 1; 435 | } 436 | while (--numBits); 437 | return res; 438 | } 439 | 440 | 441 | The Bit Decoding with Probability Model 442 | --------------------------------------- 443 | 444 | The task of Bit Probability Model is to estimate probabilities of binary 445 | symbols. And then it provides the Range Decoder with that information. 446 | The better prediction provides better compression ratio. 447 | The Bit Probability Model uses statistical data of previous decoded 448 | symbols. 449 | 450 | That estimated probability is presented as 11-bit unsigned integer value 451 | that represents the probability of symbol "0". 452 | 453 | #define kNumBitModelTotalBits 11 454 | 455 | Mathematical probabilities can be presented with the following formulas: 456 | probability(symbol_0) = prob / 2048. 457 | probability(symbol_1) = 1 - Probability(symbol_0) = 458 | = 1 - prob / 2048 = 459 | = (2048 - prob) / 2048 460 | where the "prob" variable contains 11-bit integer probability counter. 461 | 462 | It's recommended to use 16-bit unsigned integer type, to store these 11-bit 463 | probability values: 464 | 465 | typedef UInt16 CProb; 466 | 467 | Each probability value must be initialized with value ((1 << 11) / 2), 468 | that represents the state, where probabilities of symbols 0 and 1 469 | are equal to 0.5: 470 | 471 | #define PROB_INIT_VAL ((1 << kNumBitModelTotalBits) / 2) 472 | 473 | The INIT_PROBS macro is used to initialize the array of CProb variables: 474 | 475 | #define INIT_PROBS(p) \ 476 | { for (unsigned i = 0; i < sizeof(p) / sizeof(p[0]); i++) p[i] = PROB_INIT_VAL; } 477 | 478 | 479 | The DecodeBit() function decodes one bit. 480 | The LZMA decoder provides the pointer to CProb variable that contains 481 | information about estimated probability for symbol 0 and the Range Decoder 482 | updates that CProb variable after decoding. The Range Decoder increases 483 | estimated probability of the symbol that was decoded: 484 | 485 | #define kNumMoveBits 5 486 | 487 | unsigned CRangeDecoder::DecodeBit(CProb *prob) 488 | { 489 | unsigned v = *prob; 490 | UInt32 bound = (Range >> kNumBitModelTotalBits) * v; 491 | unsigned symbol; 492 | if (Code < bound) 493 | { 494 | v += ((1 << kNumBitModelTotalBits) - v) >> kNumMoveBits; 495 | Range = bound; 496 | symbol = 0; 497 | } 498 | else 499 | { 500 | v -= v >> kNumMoveBits; 501 | Code -= bound; 502 | Range -= bound; 503 | symbol = 1; 504 | } 505 | *prob = (CProb)v; 506 | Normalize(); 507 | return symbol; 508 | } 509 | 510 | 511 | The Binary Tree of bit model counters 512 | ------------------------------------- 513 | 514 | LZMA uses a tree of Bit model variables to decode symbol that needs 515 | several bits for storing. There are two versions of such trees in LZMA: 516 | 1) the tree that decodes bits from high bit to low bit (the normal scheme). 517 | 2) the tree that decodes bits from low bit to high bit (the reverse scheme). 518 | 519 | Each binary tree structure supports different size of decoded symbol 520 | (the size of binary sequence that contains value of symbol). 521 | If that size of decoded symbol is "NumBits" bits, the tree structure 522 | uses the array of (2 << NumBits) counters of CProb type. 523 | But only ((2 << NumBits) - 1) items are used by encoder and decoder. 524 | The first item (the item with index equal to 0) in array is unused. 525 | That scheme with unused array's item allows to simplify the code. 526 | 527 | unsigned BitTreeReverseDecode(CProb *probs, unsigned numBits, CRangeDecoder *rc) 528 | { 529 | unsigned m = 1; 530 | unsigned symbol = 0; 531 | for (unsigned i = 0; i < numBits; i++) 532 | { 533 | unsigned bit = rc->DecodeBit(&probs[m]); 534 | m <<= 1; 535 | m += bit; 536 | symbol |= (bit << i); 537 | } 538 | return symbol; 539 | } 540 | 541 | template 542 | class CBitTreeDecoder 543 | { 544 | CProb Probs[(unsigned)1 << NumBits]; 545 | 546 | public: 547 | 548 | void Init() 549 | { 550 | INIT_PROBS(Probs); 551 | } 552 | 553 | unsigned Decode(CRangeDecoder *rc) 554 | { 555 | unsigned m = 1; 556 | for (unsigned i = 0; i < NumBits; i++) 557 | m = (m << 1) + rc->DecodeBit(&Probs[m]); 558 | return m - ((unsigned)1 << NumBits); 559 | } 560 | 561 | unsigned ReverseDecode(CRangeDecoder *rc) 562 | { 563 | return BitTreeReverseDecode(Probs, NumBits, rc); 564 | } 565 | }; 566 | 567 | 568 | LZ part of LZMA 569 | --------------- 570 | 571 | LZ part of LZMA describes details about the decoding of MATCHES and LITERALS. 572 | 573 | 574 | The Literal Decoding 575 | -------------------- 576 | 577 | The LZMA Decoder uses (1 << (lc + lp)) tables with CProb values, where 578 | each table contains 0x300 CProb values: 579 | 580 | CProb *LitProbs; 581 | 582 | void CreateLiterals() 583 | { 584 | LitProbs = new CProb[(UInt32)0x300 << (lc + lp)]; 585 | } 586 | 587 | void InitLiterals() 588 | { 589 | UInt32 num = (UInt32)0x300 << (lc + lp); 590 | for (UInt32 i = 0; i < num; i++) 591 | LitProbs[i] = PROB_INIT_VAL; 592 | } 593 | 594 | To select the table for decoding it uses the context that consists of 595 | (lc) high bits from previous literal and (lp) low bits from value that 596 | represents current position in outputStream. 597 | 598 | If (State > 7), the Literal Decoder also uses "matchByte" that represents 599 | the byte in OutputStream at position the is the DISTANCE bytes before 600 | current position, where the DISTANCE is the distance in DISTANCE-LENGTH pair 601 | of latest decoded match. 602 | 603 | The following code decodes one literal and puts it to Sliding Window buffer: 604 | 605 | void DecodeLiteral(unsigned state, UInt32 rep0) 606 | { 607 | unsigned prevByte = 0; 608 | if (!OutWindow.IsEmpty()) 609 | prevByte = OutWindow.GetByte(1); 610 | 611 | unsigned symbol = 1; 612 | unsigned litState = ((OutWindow.TotalPos & ((1 << lp) - 1)) << lc) + (prevByte >> (8 - lc)); 613 | CProb *probs = &LitProbs[(UInt32)0x300 * litState]; 614 | 615 | if (state >= 7) 616 | { 617 | unsigned matchByte = OutWindow.GetByte(rep0 + 1); 618 | do 619 | { 620 | unsigned matchBit = (matchByte >> 7) & 1; 621 | matchByte <<= 1; 622 | unsigned bit = RangeDec.DecodeBit(&probs[((1 + matchBit) << 8) + symbol]); 623 | symbol = (symbol << 1) | bit; 624 | if (matchBit != bit) 625 | break; 626 | } 627 | while (symbol < 0x100); 628 | } 629 | while (symbol < 0x100) 630 | symbol = (symbol << 1) | RangeDec.DecodeBit(&probs[symbol]); 631 | OutWindow.PutByte((Byte)(symbol - 0x100)); 632 | } 633 | 634 | 635 | The match length decoding 636 | ------------------------- 637 | 638 | The match length decoder returns normalized (zero-based value) 639 | length of match. That value can be converted to real length of the match 640 | with the following code: 641 | 642 | #define kMatchMinLen 2 643 | 644 | matchLen = len + kMatchMinLen; 645 | 646 | The match length decoder can return the values from 0 to 271. 647 | And the corresponded real match length values can be in the range 648 | from 2 to 273. 649 | 650 | The following scheme is used for the match length encoding: 651 | 652 | Binary encoding Binary Tree structure Zero-based match length 653 | sequence (binary + decimal): 654 | 655 | 0 xxx LowCoder[posState] xxx 656 | 1 0 yyy MidCoder[posState] yyy + 8 657 | 1 1 zzzzzzzz HighCoder zzzzzzzz + 16 658 | 659 | LZMA uses bit model variable "Choice" to decode the first selection bit. 660 | 661 | If the first selection bit is equal to 0, the decoder uses binary tree 662 | LowCoder[posState] to decode 3-bit zero-based match length (xxx). 663 | 664 | If the first selection bit is equal to 1, the decoder uses bit model 665 | variable "Choice2" to decode the second selection bit. 666 | 667 | If the second selection bit is equal to 0, the decoder uses binary tree 668 | MidCoder[posState] to decode 3-bit "yyy" value, and zero-based match 669 | length is equal to (yyy + 8). 670 | 671 | If the second selection bit is equal to 1, the decoder uses binary tree 672 | HighCoder to decode 8-bit "zzzzzzzz" value, and zero-based 673 | match length is equal to (zzzzzzzz + 16). 674 | 675 | LZMA uses "posState" value as context to select the binary tree 676 | from LowCoder and MidCoder binary tree arrays: 677 | 678 | unsigned posState = OutWindow.TotalPos & ((1 << pb) - 1); 679 | 680 | The full code of the length decoder: 681 | 682 | class CLenDecoder 683 | { 684 | CProb Choice; 685 | CProb Choice2; 686 | CBitTreeDecoder<3> LowCoder[1 << kNumPosBitsMax]; 687 | CBitTreeDecoder<3> MidCoder[1 << kNumPosBitsMax]; 688 | CBitTreeDecoder<8> HighCoder; 689 | 690 | public: 691 | 692 | void Init() 693 | { 694 | Choice = PROB_INIT_VAL; 695 | Choice2 = PROB_INIT_VAL; 696 | HighCoder.Init(); 697 | for (unsigned i = 0; i < (1 << kNumPosBitsMax); i++) 698 | { 699 | LowCoder[i].Init(); 700 | MidCoder[i].Init(); 701 | } 702 | } 703 | 704 | unsigned Decode(CRangeDecoder *rc, unsigned posState) 705 | { 706 | if (rc->DecodeBit(&Choice) == 0) 707 | return LowCoder[posState].Decode(rc); 708 | if (rc->DecodeBit(&Choice2) == 0) 709 | return 8 + MidCoder[posState].Decode(rc); 710 | return 16 + HighCoder.Decode(rc); 711 | } 712 | }; 713 | 714 | The LZMA decoder uses two instances of CLenDecoder class. 715 | The first instance is for the matches of "Simple Match" type, 716 | and the second instance is for the matches of "Rep Match" type: 717 | 718 | CLenDecoder LenDecoder; 719 | CLenDecoder RepLenDecoder; 720 | 721 | 722 | The match distance decoding 723 | --------------------------- 724 | 725 | LZMA supports dictionary sizes up to 4 GiB minus 1. 726 | The value of match distance (decoded by distance decoder) can be 727 | from 1 to 2^32. But the distance value that is equal to 2^32 is used to 728 | indicate the "End of stream" marker. So real largest match distance 729 | that is used for LZ-window match is (2^32 - 1). 730 | 731 | LZMA uses normalized match length (zero-based length) 732 | to calculate the context state "lenState" do decode the distance value: 733 | 734 | #define kNumLenToPosStates 4 735 | 736 | unsigned lenState = len; 737 | if (lenState > kNumLenToPosStates - 1) 738 | lenState = kNumLenToPosStates - 1; 739 | 740 | The distance decoder returns the "dist" value that is zero-based value 741 | of match distance. The real match distance can be calculated with the 742 | following code: 743 | 744 | matchDistance = dist + 1; 745 | 746 | The state of the distance decoder and the initialization code: 747 | 748 | #define kEndPosModelIndex 14 749 | #define kNumFullDistances (1 << (kEndPosModelIndex >> 1)) 750 | #define kNumAlignBits 4 751 | 752 | CBitTreeDecoder<6> PosSlotDecoder[kNumLenToPosStates]; 753 | CProb PosDecoders[1 + kNumFullDistances - kEndPosModelIndex]; 754 | CBitTreeDecoder AlignDecoder; 755 | 756 | void InitDist() 757 | { 758 | for (unsigned i = 0; i < kNumLenToPosStates; i++) 759 | PosSlotDecoder[i].Init(); 760 | AlignDecoder.Init(); 761 | INIT_PROBS(PosDecoders); 762 | } 763 | 764 | At first stage the distance decoder decodes 6-bit "posSlot" value with bit 765 | tree decoder from PosSlotDecoder array. It's possible to get 2^6=64 different 766 | "posSlot" values. 767 | 768 | unsigned posSlot = PosSlotDecoder[lenState].Decode(&RangeDec); 769 | 770 | The encoding scheme for distance value is shown in the following table: 771 | 772 | posSlot (decimal) / 773 | zero-based distance (binary) 774 | 0 0 775 | 1 1 776 | 2 10 777 | 3 11 778 | 779 | 4 10 x 780 | 5 11 x 781 | 6 10 xx 782 | 7 11 xx 783 | 8 10 xxx 784 | 9 11 xxx 785 | 10 10 xxxx 786 | 11 11 xxxx 787 | 12 10 xxxxx 788 | 13 11 xxxxx 789 | 790 | 14 10 yy zzzz 791 | 15 11 yy zzzz 792 | 16 10 yyy zzzz 793 | 17 11 yyy zzzz 794 | ... 795 | 62 10 yyyyyyyyyyyyyyyyyyyyyyyyyy zzzz 796 | 63 11 yyyyyyyyyyyyyyyyyyyyyyyyyy zzzz 797 | 798 | where 799 | "x ... x" means the sequence of binary symbols encoded with binary tree and 800 | "Reverse" scheme. It uses separated binary tree for each posSlot from 4 to 13. 801 | "y" means direct bit encoded with range coder. 802 | "zzzz" means the sequence of four binary symbols encoded with binary 803 | tree with "Reverse" scheme, where one common binary tree "AlignDecoder" 804 | is used for all posSlot values. 805 | 806 | If (posSlot < 4), the "dist" value is equal to posSlot value. 807 | 808 | If (posSlot >= 4), the decoder uses "posSlot" value to calculate the value of 809 | the high bits of "dist" value and the number of the low bits. 810 | 811 | If (4 <= posSlot < kEndPosModelIndex), the decoder uses bit tree decoders. 812 | (one separated bit tree decoder per one posSlot value) and "Reverse" scheme. 813 | In this implementation we use one CProb array "PosDecoders" that contains 814 | all CProb variables for all these bit decoders. 815 | 816 | if (posSlot >= kEndPosModelIndex), the middle bits are decoded as direct 817 | bits from RangeDecoder and the low 4 bits are decoded with a bit tree 818 | decoder "AlignDecoder" with "Reverse" scheme. 819 | 820 | The code to decode zero-based match distance: 821 | 822 | unsigned DecodeDistance(unsigned len) 823 | { 824 | unsigned lenState = len; 825 | if (lenState > kNumLenToPosStates - 1) 826 | lenState = kNumLenToPosStates - 1; 827 | 828 | unsigned posSlot = PosSlotDecoder[lenState].Decode(&RangeDec); 829 | if (posSlot < 4) 830 | return posSlot; 831 | 832 | unsigned numDirectBits = (unsigned)((posSlot >> 1) - 1); 833 | UInt32 dist = ((2 | (posSlot & 1)) << numDirectBits); 834 | if (posSlot < kEndPosModelIndex) 835 | dist += BitTreeReverseDecode(PosDecoders + dist - posSlot, numDirectBits, &RangeDec); 836 | else 837 | { 838 | dist += RangeDec.DecodeDirectBits(numDirectBits - kNumAlignBits) << kNumAlignBits; 839 | dist += AlignDecoder.ReverseDecode(&RangeDec); 840 | } 841 | return dist; 842 | } 843 | 844 | 845 | 846 | LZMA Decoding modes 847 | ------------------- 848 | 849 | There are 2 types of LZMA streams: 850 | 851 | 1) The stream with "End of stream" marker. 852 | 2) The stream without "End of stream" marker. 853 | 854 | And the LZMA Decoder supports 3 modes of decoding: 855 | 856 | 1) The unpack size is undefined. The LZMA decoder stops decoding after 857 | getting "End of stream" marker. 858 | The input variables for that case: 859 | 860 | markerIsMandatory = true 861 | unpackSizeDefined = false 862 | unpackSize contains any value 863 | 864 | 2) The unpack size is defined and LZMA decoder supports both variants, 865 | where the stream can contain "End of stream" marker or the stream is 866 | finished without "End of stream" marker. The LZMA decoder must detect 867 | any of these situations. 868 | The input variables for that case: 869 | 870 | markerIsMandatory = false 871 | unpackSizeDefined = true 872 | unpackSize contains unpack size 873 | 874 | 3) The unpack size is defined and the LZMA stream must contain 875 | "End of stream" marker 876 | The input variables for that case: 877 | 878 | markerIsMandatory = true 879 | unpackSizeDefined = true 880 | unpackSize contains unpack size 881 | 882 | 883 | The main loop of decoder 884 | ------------------------ 885 | 886 | The main loop of LZMA decoder: 887 | 888 | Initialize the LZMA state. 889 | loop 890 | { 891 | // begin of loop 892 | Check "end of stream" conditions. 893 | Decode Type of MATCH / LITERAL. 894 | If it's LITERAL, decode LITERAL value and put the LITERAL to Window. 895 | If it's MATCH, decode the length of match and the match distance. 896 | Check error conditions, check end of stream conditions and copy 897 | the sequence of match bytes from sliding window to current position 898 | in window. 899 | Go to begin of loop 900 | } 901 | 902 | The reference implementation of LZMA decoder uses "unpackSize" variable 903 | to keep the number of remaining bytes in output stream. So it reduces 904 | "unpackSize" value after each decoded LITERAL or MATCH. 905 | 906 | The following code contains the "end of stream" condition check at the start 907 | of the loop: 908 | 909 | if (unpackSizeDefined && unpackSize == 0 && !markerIsMandatory) 910 | if (RangeDec.IsFinishedOK()) 911 | return LZMA_RES_FINISHED_WITHOUT_MARKER; 912 | 913 | LZMA uses three types of matches: 914 | 915 | 1) "Simple Match" - the match with distance value encoded with bit models. 916 | 917 | 2) "Rep Match" - the match that uses the distance from distance 918 | history table. 919 | 920 | 3) "Short Rep Match" - the match of single byte length, that uses the latest 921 | distance from distance history table. 922 | 923 | The LZMA decoder keeps the history of latest 4 match distances that were used 924 | by decoder. That set of 4 variables contains zero-based match distances and 925 | these variables are initialized with zero values: 926 | 927 | UInt32 rep0 = 0, rep1 = 0, rep2 = 0, rep3 = 0; 928 | 929 | The LZMA decoder uses binary model variables to select type of MATCH or LITERAL: 930 | 931 | #define kNumStates 12 932 | #define kNumPosBitsMax 4 933 | 934 | CProb IsMatch[kNumStates << kNumPosBitsMax]; 935 | CProb IsRep[kNumStates]; 936 | CProb IsRepG0[kNumStates]; 937 | CProb IsRepG1[kNumStates]; 938 | CProb IsRepG2[kNumStates]; 939 | CProb IsRep0Long[kNumStates << kNumPosBitsMax]; 940 | 941 | The decoder uses "state" variable value to select exact variable 942 | from "IsRep", "IsRepG0", "IsRepG1" and "IsRepG2" arrays. 943 | The "state" variable can get the value from 0 to 11. 944 | Initial value for "state" variable is zero: 945 | 946 | unsigned state = 0; 947 | 948 | The "state" variable is updated after each LITERAL or MATCH with one of the 949 | following functions: 950 | 951 | unsigned UpdateState_Literal(unsigned state) 952 | { 953 | if (state < 4) return 0; 954 | else if (state < 10) return state - 3; 955 | else return state - 6; 956 | } 957 | unsigned UpdateState_Match (unsigned state) { return state < 7 ? 7 : 10; } 958 | unsigned UpdateState_Rep (unsigned state) { return state < 7 ? 8 : 11; } 959 | unsigned UpdateState_ShortRep(unsigned state) { return state < 7 ? 9 : 11; } 960 | 961 | The decoder calculates "state2" variable value to select exact variable from 962 | "IsMatch" and "IsRep0Long" arrays: 963 | 964 | unsigned posState = OutWindow.TotalPos & ((1 << pb) - 1); 965 | unsigned state2 = (state << kNumPosBitsMax) + posState; 966 | 967 | The decoder uses the following code flow scheme to select exact 968 | type of LITERAL or MATCH: 969 | 970 | IsMatch[state2] decode 971 | 0 - the Literal 972 | 1 - the Match 973 | IsRep[state] decode 974 | 0 - Simple Match 975 | 1 - Rep Match 976 | IsRepG0[state] decode 977 | 0 - the distance is rep0 978 | IsRep0Long[state2] decode 979 | 0 - Short Rep Match 980 | 1 - Rep Match 0 981 | 1 - 982 | IsRepG1[state] decode 983 | 0 - Rep Match 1 984 | 1 - 985 | IsRepG2[state] decode 986 | 0 - Rep Match 2 987 | 1 - Rep Match 3 988 | 989 | 990 | LITERAL symbol 991 | -------------- 992 | If the value "0" was decoded with IsMatch[state2] decoding, we have "LITERAL" type. 993 | 994 | At first the LZMA decoder must check that it doesn't exceed 995 | specified uncompressed size: 996 | 997 | if (unpackSizeDefined && unpackSize == 0) 998 | return LZMA_RES_ERROR; 999 | 1000 | Then it decodes literal value and puts it to sliding window: 1001 | 1002 | DecodeLiteral(state, rep0); 1003 | 1004 | Then the decoder must update the "state" value and "unpackSize" value; 1005 | 1006 | state = UpdateState_Literal(state); 1007 | unpackSize--; 1008 | 1009 | Then the decoder must go to the begin of main loop to decode next Match or Literal. 1010 | 1011 | 1012 | Simple Match 1013 | ------------ 1014 | 1015 | If the value "1" was decoded with IsMatch[state2] decoding, 1016 | we have the "Simple Match" type. 1017 | 1018 | The distance history table is updated with the following scheme: 1019 | 1020 | rep3 = rep2; 1021 | rep2 = rep1; 1022 | rep1 = rep0; 1023 | 1024 | The zero-based length is decoded with "LenDecoder": 1025 | 1026 | len = LenDecoder.Decode(&RangeDec, posState); 1027 | 1028 | The state is update with UpdateState_Match function: 1029 | 1030 | state = UpdateState_Match(state); 1031 | 1032 | and the new "rep0" value is decoded with DecodeDistance: 1033 | 1034 | rep0 = DecodeDistance(len); 1035 | 1036 | That "rep0" will be used as zero-based distance for current match. 1037 | 1038 | If the value of "rep0" is equal to 0xFFFFFFFF, it means that we have 1039 | "End of stream" marker, so we can stop decoding and check finishing 1040 | condition in Range Decoder: 1041 | 1042 | if (rep0 == 0xFFFFFFFF) 1043 | return RangeDec.IsFinishedOK() ? 1044 | LZMA_RES_FINISHED_WITH_MARKER : 1045 | LZMA_RES_ERROR; 1046 | 1047 | If uncompressed size is defined, LZMA decoder must check that it doesn't 1048 | exceed that specified uncompressed size: 1049 | 1050 | if (unpackSizeDefined && unpackSize == 0) 1051 | return LZMA_RES_ERROR; 1052 | 1053 | Also the decoder must check that "rep0" value is not larger than dictionary size 1054 | and is not larger than the number of already decoded bytes: 1055 | 1056 | if (rep0 >= dictSize || !OutWindow.CheckDistance(rep0)) 1057 | return LZMA_RES_ERROR; 1058 | 1059 | Then the decoder must copy match bytes as described in 1060 | "The match symbols copying" section. 1061 | 1062 | 1063 | Rep Match 1064 | --------- 1065 | 1066 | If the LZMA decoder has decoded the value "1" with IsRep[state] variable, 1067 | we have "Rep Match" type. 1068 | 1069 | At first the LZMA decoder must check that it doesn't exceed 1070 | specified uncompressed size: 1071 | 1072 | if (unpackSizeDefined && unpackSize == 0) 1073 | return LZMA_RES_ERROR; 1074 | 1075 | Also the decoder must return error, if the LZ window is empty: 1076 | 1077 | if (OutWindow.IsEmpty()) 1078 | return LZMA_RES_ERROR; 1079 | 1080 | If the match type is "Rep Match", the decoder uses one of the 4 variables of 1081 | distance history table to get the value of distance for current match. 1082 | And there are 4 corresponding ways of decoding flow. 1083 | 1084 | The decoder updates the distance history with the following scheme 1085 | depending from type of match: 1086 | 1087 | - "Rep Match 0" or "Short Rep Match": 1088 | ; LZMA doesn't update the distance history 1089 | 1090 | - "Rep Match 1": 1091 | UInt32 dist = rep1; 1092 | rep1 = rep0; 1093 | rep0 = dist; 1094 | 1095 | - "Rep Match 2": 1096 | UInt32 dist = rep2; 1097 | rep2 = rep1; 1098 | rep1 = rep0; 1099 | rep0 = dist; 1100 | 1101 | - "Rep Match 3": 1102 | UInt32 dist = rep3; 1103 | rep3 = rep2; 1104 | rep2 = rep1; 1105 | rep1 = rep0; 1106 | rep0 = dist; 1107 | 1108 | Then the decoder decodes exact subtype of "Rep Match" using "IsRepG0", "IsRep0Long", 1109 | "IsRepG1", "IsRepG2". 1110 | 1111 | If the subtype is "Short Rep Match", the decoder updates the state, puts 1112 | the one byte from window to current position in window and goes to next 1113 | MATCH/LITERAL symbol (the begin of main loop): 1114 | 1115 | state = UpdateState_ShortRep(state); 1116 | OutWindow.PutByte(OutWindow.GetByte(rep0 + 1)); 1117 | unpackSize--; 1118 | continue; 1119 | 1120 | In other cases (Rep Match 0/1/2/3), it decodes the zero-based 1121 | length of match with "RepLenDecoder" decoder: 1122 | 1123 | len = RepLenDecoder.Decode(&RangeDec, posState); 1124 | 1125 | Then it updates the state: 1126 | 1127 | state = UpdateState_Rep(state); 1128 | 1129 | Then the decoder must copy match bytes as described in 1130 | "The Match symbols copying" section. 1131 | 1132 | 1133 | The match symbols copying 1134 | ------------------------- 1135 | 1136 | If we have the match (Simple Match or Rep Match 0/1/2/3), the decoder must 1137 | copy the sequence of bytes with calculated match distance and match length. 1138 | If uncompressed size is defined, LZMA decoder must check that it doesn't 1139 | exceed that specified uncompressed size: 1140 | 1141 | len += kMatchMinLen; 1142 | bool isError = false; 1143 | if (unpackSizeDefined && unpackSize < len) 1144 | { 1145 | len = (unsigned)unpackSize; 1146 | isError = true; 1147 | } 1148 | OutWindow.CopyMatch(rep0 + 1, len); 1149 | unpackSize -= len; 1150 | if (isError) 1151 | return LZMA_RES_ERROR; 1152 | 1153 | Then the decoder must go to the begin of main loop to decode next MATCH or LITERAL. 1154 | 1155 | 1156 | 1157 | NOTES 1158 | ----- 1159 | 1160 | This specification doesn't describe the variant of decoder implementation 1161 | that supports partial decoding. Such partial decoding case can require some 1162 | changes in "end of stream" condition checks code. Also such code 1163 | can use additional status codes, returned by decoder. 1164 | 1165 | This specification uses C++ code with templates to simplify describing. 1166 | The optimized version of LZMA decoder doesn't need templates. 1167 | Such optimized version can use just two arrays of CProb variables: 1168 | 1) The dynamic array of CProb variables allocated for the Literal Decoder. 1169 | 2) The one common array that contains all other CProb variables. 1170 | 1171 | 1172 | References: 1173 | 1174 | 1. G. N. N. Martin, Range encoding: an algorithm for removing redundancy 1175 | from a digitized message, Video & Data Recording Conference, 1176 | Southampton, UK, July 24-27, 1979. 1177 | -------------------------------------------------------------------------------- /lzmaSh2.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | typedef unsigned int uint; 4 | typedef unsigned char byte; 5 | typedef unsigned long long qword; 6 | 7 | struct lzma_decode { 8 | 9 | enum { SCALElog=11, SCALE=1<>5) : ((SCALE-P)>>5); } 15 | }; 16 | 17 | FILE *f, *g; 18 | byte get( void ) { return getc(f); } 19 | void put( uint c ) { putc(c,g); } 20 | 21 | uint range, code; 22 | 23 | void rc_Init( void ) { 24 | code = get() | ((get()<<24) | (get()<<16) | (get()<<8) | (get())); 25 | range = 0xFFFFFFFF; 26 | } 27 | 28 | uint rc_Bits( uint l ) { 29 | uint x=0; do { 30 | if( range<0x01000000 ) range<<=8, code=(code<<8) | get(); 31 | range &= ~1; 32 | uint rnew = (range>>1) * 1; 33 | uint bit = code >= rnew; 34 | range = bit ? code-=rnew,range-rnew : rnew; 35 | x += x + bit; 36 | } while( --l!=0 ); 37 | return x; 38 | } 39 | 40 | uint rc_Decode( uint P ) { 41 | if( range<0x01000000 ) range<<=8, code=(code<<8) | get(); 42 | uint rnew = (range >> SCALElog) * P; 43 | uint bit = code >= rnew; 44 | range = bit ? code-=rnew,range-rnew : rnew; 45 | return bit; 46 | } 47 | 48 | uint BIT( Counter& cc ) { 49 | uint bit = rc_Decode(cc.P); 50 | cc.Update( bit ); 51 | return bit; 52 | } 53 | 54 | enum { 55 | kNumLPosBitsMax = 4, 56 | kNumPosBitsMax = 4, kNumPosStatesMax = (1<>1)), 62 | kNumPosSlotBits = 6, kNumLenToPosStates = 4, 63 | kNumAlignBits = 4, kAlignTableSize = (1<>8) | (qword(get())<<56); 96 | rc_Init(); 97 | lc = d % 9; d /= 9; 98 | pb = d / 5; lp = d % 5; 99 | 100 | for( i=0; i<32; i++ ) rbit5[i] = ((i*0x0802&0x22110)|(i*0x8020&0x88440))*0x10101 >> 16+3; 101 | 102 | uint state=0,rep0=1,rep1=1,rep2=1,rep3=1; 103 | uint dicPos = 0, dicBufSize = dictSize; 104 | uint pbMask = (1<>lc8]; 117 | if( state>=kNumLitStates ) { 118 | uint matchbyte = 0x100 + dic[rep0pos()]; 119 | for( sym=1; sym<0x100; ) { 120 | uint mbprefix = (matchbyte<<=1) >> 8; 121 | sym += sym + BIT(cc[1+(mbprefix&1)][sym]); 122 | if( mbprefix!=sym ) break; 123 | } 124 | } else sym=1; 125 | for(; sym<0x100; sym+=sym+BIT(cc[0][sym]) ); 126 | 127 | symstore(sym); 128 | state = (state<4) ? 0 : (state<10) ? state-3 : state-6; 129 | 130 | } else { 131 | 132 | uint f_rep = BIT(c_IsRep[state]); 133 | 134 | if( f_rep==0 ) state += kNumStates; else { 135 | 136 | if( BIT(c_IsRepG0[state])==0 ) { 137 | 138 | if( BIT(c_IsRep0Long[state][posState])==0 ) { 139 | sym = dic[rep0pos()]; symstore(sym); 140 | state = state < kNumLitStates ? 9 : 11; 141 | continue; 142 | } 143 | 144 | } else { 145 | 146 | dist = rep1; 147 | if( BIT(c_IsRepG1[state]) ) { 148 | dist = rep2; 149 | if( BIT(c_IsRepG2[state]) ) dist = rep3, rep3 = rep2; 150 | rep2 = rep1; 151 | } 152 | rep1 = rep0; rep0 = dist; 153 | } 154 | 155 | state = state < kNumLitStates ? 8 : 11; 156 | } 157 | 158 | uint limit, offset; 159 | Counter* clen = 0; 160 | if( BIT(c_LenChoice[f_rep])==0 ) { 161 | clen = &c_LenLow[f_rep][posState][0]; 162 | offset = 0; limit = (1 << kLenNumLowBits); 163 | } else { 164 | if( BIT(c_LenChoice2[f_rep])==0 ) { 165 | clen = &c_LenMid[f_rep][posState][0]; 166 | offset = kLenNumLowSymbols; limit = (1<=kNumStates ) { 176 | Counter (&cpos)[1<=kStartPosModelIndex ) { 180 | uint posSlot = dist; 181 | int numDirectBits = (dist>>1) - 1; // 13/2-1=5 max 182 | dist = (2 | (dist & 1)); 183 | 184 | if( posSlot0; len-- ) { 206 | sym = dic[pos]; symstore(sym); 207 | if( ++pos == dicBufSize ) pos=0; 208 | } 209 | 210 | } // match 211 | 212 | } // for 213 | 214 | } 215 | 216 | }; 217 | 218 | int main( int argc, char** argv ) { 219 | if( argc<3 ) return 1; 220 | FILE* f = fopen( argv[1], "rb" ); if( f==0 ) return 2; 221 | FILE* g = fopen( argv[2], "wb" ); if( g==0 ) return 3; 222 | 223 | static lzma_decode D( f, g ); 224 | 225 | fclose( f ); 226 | fclose( g ); 227 | return 0; 228 | } 229 | -------------------------------------------------------------------------------- /lzmaSh2.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/lzmaSh2.exe -------------------------------------------------------------------------------- /lzmaSh2a.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | typedef unsigned int uint; 4 | typedef unsigned char byte; 5 | typedef unsigned long long qword; 6 | 7 | const byte statemap[][7] = { 8 | { 7, 0, 8, 9, 8, 8, 8, }, 9 | { 7, 0, 8, 9, 8, 8, 8, }, 10 | { 7, 0, 8, 9, 8, 8, 8, }, 11 | { 7, 0, 8, 9, 8, 8, 8, }, 12 | { 7, 1, 8, 9, 8, 8, 8, }, 13 | { 7, 2, 8, 9, 8, 8, 8, }, 14 | { 7, 3, 8, 9, 8, 8, 8, }, 15 | { 10, 4, 11, 11, 11, 11, 11, }, 16 | { 10, 5, 11, 11, 11, 11, 11, }, 17 | { 10, 6, 11, 11, 11, 11, 11, }, 18 | { 10, 4, 11, 11, 11, 11, 11, }, 19 | { 10, 5, 11, 11, 11, 11, 11, }, 20 | }; 21 | 22 | struct lzma_decode { 23 | 24 | enum { SCALElog=11, SCALE=1<>5) : ((SCALE-P)>>5); } 30 | }; 31 | 32 | FILE *f, *g; 33 | byte get( void ) { return getc(f); } 34 | void put( uint c ) { putc(c,g); } 35 | 36 | uint range, code; 37 | 38 | void rc_Init( void ) { 39 | code = get() | ((get()<<24) | (get()<<16) | (get()<<8) | (get())); 40 | range = 0xFFFFFFFF; 41 | } 42 | 43 | uint rc_Bits( uint l ) { 44 | uint x=0; do { 45 | if( range<0x01000000 ) range<<=8, code=(code<<8) | get(); 46 | range &= ~1; 47 | uint rnew = (range>>1) * 1; 48 | uint bit = code >= rnew; 49 | range = bit ? code-=rnew,range-rnew : rnew; 50 | x += x + bit; 51 | } while( --l!=0 ); 52 | return x; 53 | } 54 | 55 | uint rc_Decode( uint P ) { 56 | if( range<0x01000000 ) range<<=8, code=(code<<8) | get(); 57 | uint rnew = (range >> SCALElog) * P; 58 | uint bit = code >= rnew; 59 | range = bit ? code-=rnew,range-rnew : rnew; 60 | return bit; 61 | } 62 | 63 | uint BIT( Counter& cc ) { 64 | uint bit = rc_Decode(cc.P); 65 | cc.Update( bit ); 66 | return bit; 67 | } 68 | 69 | enum { 70 | kNumLPosBitsMax = 4, 71 | kNumPosBitsMax = 4, kNumPosStatesMax = (1<>1)), 77 | kNumPosSlotBits = 6, kNumLenToPosStates = 4, 78 | kNumAlignBits = 4, kAlignTableSize = (1<>8) | (qword(get())<<56); 112 | rc_Init(); 113 | lc = d % 9; d /= 9; 114 | pb = d / 5; lp = d % 5; 115 | 116 | for( i=0; i<32; i++ ) rbit5[i] = ((i*0x0802&0x22110)|(i*0x8020&0x88440))*0x10101 >> 16+3; 117 | 118 | uint state=0,rep0=1,rep1=1,rep2=1,rep3=1; 119 | uint dicPos = 0, dicBufSize = dictSize; 120 | uint pbMask = (1<>lc8]; 143 | 144 | if( state>=kNumLitStates ) { 145 | uint matchbyte = 0x100 + dic[rep0pos()]; 146 | for( sym=1; sym<0x100; ) { 147 | uint mbprefix = (matchbyte<<=1) >> 8; 148 | sym += sym + BIT(cc[1+(mbprefix&1)][sym]); 149 | if( mbprefix!=sym ) break; 150 | } 151 | } else sym=1; 152 | for(; sym<0x100; sym+=sym+BIT(cc[0][sym]) ); 153 | } 154 | 155 | symstore(sym); 156 | 157 | } else { 158 | 159 | uint f_rep = (id!=id_match); 160 | 161 | if( f_rep ) { 162 | if( id!=id_r0 ) { 163 | dist = rep1; 164 | if( id!=id_r1 ) { 165 | dist = rep2; 166 | if( id==id_r3 ) dist = rep3, rep3 = rep2; 167 | rep2 = rep1; 168 | } 169 | rep1 = rep0; rep0 = dist; 170 | } 171 | } 172 | 173 | if( BIT(c_LenChoice[f_rep])==0 ) i_len=0; else 174 | if( BIT(c_LenChoice2[f_rep])==0 ) i_len=1; else i_len=2; 175 | 176 | uint limit, offset; 177 | if( i_len==0 ) { 178 | clen = &c_LenLow[f_rep][posState][0]; 179 | offset = 0; limit = (1 << kLenNumLowBits); 180 | } else { 181 | if( i_len==1 ) { 182 | clen = &c_LenMid[f_rep][posState][0]; 183 | offset = kLenNumLowSymbols; limit = (1<=kStartPosModelIndex ) { 201 | uint posSlot = dist; 202 | int numDirectBits = (dist>>1) - 1; // 13/2-1=5 max 203 | dist = (2 | (dist & 1)); 204 | 205 | if( posSlot0; len-- ) { 225 | sym = dic[pos]; symstore(sym); 226 | if( ++pos == dicBufSize ) pos=0; 227 | } 228 | 229 | } // match 230 | 231 | } // for 232 | 233 | } 234 | 235 | }; 236 | 237 | int main( int argc, char** argv ) { 238 | if( argc<3 ) return 1; 239 | FILE* f = fopen( argv[1], "rb" ); if( f==0 ) return 2; 240 | FILE* g = fopen( argv[2], "wb" ); if( g==0 ) return 3; 241 | 242 | static lzma_decode D( f, g ); 243 | 244 | fclose( f ); 245 | fclose( g ); 246 | return 0; 247 | } 248 | -------------------------------------------------------------------------------- /lzmaSh2a.exe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Shelwien/lzma_sh/0e916adc087e029ad5afd1567bf0ca03a5574a1b/lzmaSh2a.exe -------------------------------------------------------------------------------- /lzmaspec-readme.txt: -------------------------------------------------------------------------------- 1 | LZMA Specification 2 | ------------------ 3 | 4 | This package contains: 5 | 6 | - LZMA Specification 7 | - LZMA Reference Decoder in C++ 8 | - The folder with examples of lzma archives 9 | 10 | Note that LZMA Reference Decoder is not optimized for speed. 11 | You can use LZMA Decoder from LZMA SDK, if you need the code optimized for speed. 12 | 13 | If you see some bug in code or errors in text of specification, 14 | you can send a message to Igor Pavlov in support forum 15 | or via SourceForge email message system: 16 | 17 | http://www.7-zip.org/support.html 18 | 19 | 20 | --- 21 | Igor Pavlov 22 | http://www.7-zip.org 23 | -------------------------------------------------------------------------------- /test.bat: -------------------------------------------------------------------------------- 1 | @echo off 2 | 3 | del 1 2 4 | lzmaSh2.exe geo_lzma 1 5 | lzmaSh2a.exe geo_lzma 2 6 | fc /b 1 2 7 | 8 | --------------------------------------------------------------------------------