├── .gitignore ├── C-Documentation.pdf ├── LICENSE ├── README.md ├── examples ├── Makefile ├── bin │ └── stub └── src │ ├── ex1.c │ ├── ex2.c │ ├── ex3.c │ ├── ex4.c │ ├── ex5.c │ ├── ex6.c │ └── ex7.c └── src ├── .deps ├── error.Po ├── main.Po ├── parser.Po ├── preprocessor.Po ├── scanner.Po ├── symbol.Po └── utils.Po ├── Makefile ├── compiler ├── Makefile ├── drivers │ ├── error │ │ └── make_err.c │ ├── parser │ │ └── get_token.c │ ├── preprocessor │ │ ├── fseek_test.c │ │ ├── get_inc_fname.c │ │ └── get_next_word.c │ ├── scanner │ │ ├── extract_token.c │ │ ├── get_lexeme.c │ │ ├── get_token.c │ │ ├── is_valid_id.c │ │ ├── return_string.c │ │ └── write_token.c │ ├── semantic │ │ └── stub │ ├── symbol │ │ └── is_keyword.c │ └── utils │ │ ├── bsearch.c │ │ ├── fcpeek.c │ │ ├── get_column.c │ │ ├── get_files_from_argv.c │ │ ├── get_filesize.c │ │ ├── getword.c │ │ ├── scan_for_o.c │ │ └── strip_whitesp.c ├── error.c ├── error.h ├── main.c ├── main.h ├── parser.c ├── parser.h ├── preprocessor.c ├── preprocessor.h ├── scanner.c ├── scanner.h ├── symbol.c ├── symbol.h ├── utils.c └── utils.h └── cvm ├── Makefile ├── cvm.c ├── cvm.h └── drivers └── main.c /.gitignore: -------------------------------------------------------------------------------- 1 | 2 | 3 | docs/* 4 | docs/html/* 5 | docs/latex/* 6 | -------------------------------------------------------------------------------- /C-Documentation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/eudisd/c-compiler/9aa5e08fe4217accd4935b8120178e4e0377e0a0/C-Documentation.pdf -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | C Compiler 2 | ========== 3 | By Eudis Duran 4 | -------------- 5 | 6 | ## Compiling 7 | 8 | ### Linux: 9 | 10 | You can build the source with a single command. 11 | Make sure you are in the root src directory, and 12 | type: "make all" This will build both the compiler 13 | and virtual machine. The resulting executables will 14 | be placed in the root binary folder for the project. 15 | The programs are named "c" for the compiler, and "cvm" for 16 | the virtual machine. 17 | 18 | ### Example Programs/Tests 19 | Once you have built the compiler and virtual machine, both 20 | executables are also copied to the bin folder under 'examples.' 21 | The example programs can be built in a similar fasion. 22 | Change directory to examples/ and execute a "make" 23 | call. That will build all the examples for execution. 24 | In this case however, the Makefile will use my C compiler 25 | to build the examples, and will produce VM executables 26 | in the bin folder under the examples folders. 27 | 28 | ### Windows: 29 | Not tested. 30 | 31 | 32 | ## Usage: 33 | To compile a source file, first make sure that it adheres 34 | to the small C subset that is specified in the Documentation 35 | file, as not all of C is implemented yet. 36 | 37 | Once you have checked that off, locate the compiler and VM 38 | executable in the bin directory and change to that directory 39 | through the command line. Assuming you have a test 40 | file, say test.c, you could type in the following to compile 41 | the file: 42 | 43 | ```bash 44 | $ ./c test.c -o test.vm 45 | ``` 46 | 47 | That would compile the c source and produce a virtual machine 48 | bytecode executable. To run that exectuable, type in the 49 | following: 50 | 51 | ```bash 52 | $ ./cvm test.vm 53 | ``` 54 | 55 | That would execute the program. 56 | 57 | You can display a help screen by typing in --help in either of the 58 | program's command line arguments, like so: 59 | 60 | ```bash 61 | $ ./c --help 62 | ``` 63 | 64 | or 65 | 66 | ```bash 67 | $ ./cvm --help 68 | ``` 69 | -------------------------------------------------------------------------------- /examples/Makefile: -------------------------------------------------------------------------------- 1 | # Makefile to build all the examples/tests using my c compiler 2 | # By Eudis Duran 3 | 4 | 5 | EXECS = bin/ex1.vm bin/ex2.vm bin/ex3.vm bin/ex4.vm bin/ex5.vm bin/ex6.vm bin/ex7.vm 6 | 7 | $(EXECS) : $(EXECS) 8 | 9 | bin/ex1.vm: src/ex1.c 10 | bin/c src/ex1.c -o bin/ex1.vm 11 | 12 | bin/ex2.vm: src/ex2.c 13 | bin/c src/ex2.c -o bin/ex2.vm 14 | 15 | bin/ex3.vm: src/ex3.c 16 | bin/c src/ex3.c -o bin/ex3.vm 17 | 18 | bin/ex4.vm: src/ex4.c 19 | bin/c src/ex4.c -o bin/ex4.vm 20 | 21 | bin/ex5.vm: src/ex5.c 22 | bin/c src/ex5.c -o bin/ex5.vm 23 | 24 | bin/ex6.vm: src/ex6.c 25 | bin/c src/ex6.c -o bin/ex6.vm 26 | 27 | bin/ex7.vm: src/ex7.c 28 | bin/c src/ex7.c -o bin/ex7.vm 29 | 30 | 31 | -------------------------------------------------------------------------------- /examples/bin/stub: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/eudisd/c-compiler/9aa5e08fe4217accd4935b8120178e4e0377e0a0/examples/bin/stub -------------------------------------------------------------------------------- /examples/src/ex1.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------*/ 2 | /* This is a simple hello world program */ 3 | /*--------------------------------------*/ 4 | 5 | /* 6 | * By: Eudis Duran 7 | * Spring 2011 8 | */ 9 | 10 | int main() 11 | { 12 | printf("Hello World!"); 13 | } 14 | -------------------------------------------------------------------------------- /examples/src/ex2.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------------------------*/ 2 | /* This test demonstrates declaration of variables. 3 | * So far, only three are available. int, char, and float. 4 | * 5 | * It also demonstrates assignment, and printing. 6 | */ 7 | /*--------------------------------------------------------*/ 8 | 9 | /* 10 | * By: Eudis Duran 11 | * Spring 2011 12 | */ 13 | 14 | int x, y; 15 | float z, w; 16 | char a, b, c; 17 | 18 | int main() 19 | { 20 | x = 1; 21 | printf ("The value of X is: "); 22 | printf(x); 23 | } 24 | -------------------------------------------------------------------------------- /examples/src/ex3.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------------------------*/ 2 | /* This test demonstrates declaration of variables in different 3 | * scopes. In other words, lexical scoping is presented. 4 | * It also shows the conditional if else construct. 5 | */ 6 | /*--------------------------------------------------------*/ 7 | 8 | /* 9 | * By: Eudis Duran 10 | * Spring 2011 11 | */ 12 | 13 | int main() 14 | { 15 | int x; 16 | x = 1; 17 | printf (x); /* This x is different from the one below */ 18 | 19 | if( x == 1 ){ 20 | int x; 21 | x = 2; 22 | printf ("This should execute!"); 23 | printf (x); 24 | } 25 | else { 26 | printf ("This should not!"); 27 | } 28 | } 29 | -------------------------------------------------------------------------------- /examples/src/ex4.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------------------------*/ 2 | /* Here, I demonstrate while and do-while looping constructs. 3 | * I do so, by presenting the iterative fibonacci algorithm, 4 | * and the GCD algorithm for a very small set of numbers. 5 | */ 6 | /*--------------------------------------------------------*/ 7 | 8 | /* 9 | * By: Eudis Duran 10 | * Spring 2011 11 | */ 12 | 13 | 14 | 15 | int main() 16 | { 17 | int fib_total; 18 | 19 | fib_total = 20; 20 | 21 | int i, j, fib; 22 | 23 | i = 0; 24 | j = 1; 25 | 26 | /* f(n) = f(n - 1) + f(n - 2) */ 27 | printf ("Fibonacci Sequence"); 28 | while( fib < fib_total ){ 29 | fib = i + j; 30 | j = i; 31 | i = fib; 32 | printf (fib); 33 | } 34 | 35 | int a, b, c, d; 36 | 37 | a = 6; 38 | b = 6; 39 | 40 | printf ("Greatest Commond Divisisor"); 41 | do { 42 | c = a % b; 43 | a = b; 44 | b = c; 45 | }while( b > 0 ); 46 | 47 | printf ("The GCD is: "); 48 | printf(a); 49 | 50 | } 51 | -------------------------------------------------------------------------------- /examples/src/ex5.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------------------------*/ 2 | /* This source file demonstrates gotos/labels. Branching accross 3 | * scopes is not supported. */ 4 | /*--------------------------------------------------------*/ 5 | 6 | /* 7 | * By: Eudis Duran 8 | * Spring 2011 9 | */ 10 | 11 | 12 | int main() 13 | { 14 | int x; 15 | x = 10; 16 | 17 | /* Goto First, Label Second */ 18 | goto label2; 19 | 20 | printf ("Do not print this"); 21 | 22 | label2: 23 | 24 | x = 5; 25 | printf("Print this: "); 26 | printf(x); 27 | 28 | 29 | /* Label First, Goto Second */ 30 | 31 | int counter; 32 | counter = 0; 33 | 34 | label1: 35 | 36 | printf ("This always gets printed!"); 37 | 38 | if( counter < 10 ){ 39 | counter = counter + 1; 40 | goto label1; 41 | } 42 | 43 | /* Here the loop ends */ 44 | 45 | 46 | } 47 | -------------------------------------------------------------------------------- /examples/src/ex6.c: -------------------------------------------------------------------------------- 1 | /*--------------------------------------------------------*/ 2 | /* This source file demonstrates integer array declaration and 3 | use. */ 4 | /*--------------------------------------------------------*/ 5 | 6 | /* 7 | * By: Eudis Duran 8 | * Spring 2011 9 | */ 10 | 11 | int main() 12 | { 13 | int x, sorted; 14 | x = 20; 15 | 16 | int a[5]; 17 | a[0] = 10; 18 | 19 | /* First we print the original x */ 20 | 21 | printf(x); 22 | 23 | /* Next, we print the newly assigned x */ 24 | 25 | x = a[0]; 26 | printf (x); 27 | 28 | } 29 | -------------------------------------------------------------------------------- /examples/src/ex7.c: -------------------------------------------------------------------------------- 1 | int main() 2 | { 3 | printf("Hello World!"); 4 | } 5 | -------------------------------------------------------------------------------- /src/.deps/error.Po: -------------------------------------------------------------------------------- 1 | error.o: error.c error.h /usr/include/stdio.h /usr/include/features.h \ 2 | /usr/include/bits/predefs.h /usr/include/sys/cdefs.h \ 3 | /usr/include/bits/wordsize.h /usr/include/gnu/stubs.h \ 4 | /usr/include/gnu/stubs-32.h \ 5 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h \ 6 | /usr/include/bits/types.h /usr/include/bits/typesizes.h \ 7 | /usr/include/libio.h /usr/include/_G_config.h /usr/include/wchar.h \ 8 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h \ 9 | /usr/include/bits/stdio_lim.h /usr/include/bits/sys_errlist.h \ 10 | /usr/include/bits/stdio.h /usr/include/bits/stdio2.h \ 11 | /usr/include/stdlib.h /usr/include/bits/waitflags.h \ 12 | /usr/include/bits/waitstatus.h /usr/include/endian.h \ 13 | /usr/include/bits/endian.h /usr/include/bits/byteswap.h \ 14 | /usr/include/sys/types.h /usr/include/time.h /usr/include/sys/select.h \ 15 | /usr/include/bits/select.h /usr/include/bits/sigset.h \ 16 | /usr/include/bits/time.h /usr/include/sys/sysmacros.h \ 17 | /usr/include/bits/pthreadtypes.h /usr/include/alloca.h \ 18 | /usr/include/bits/stdlib.h 19 | 20 | error.h: 21 | 22 | /usr/include/stdio.h: 23 | 24 | /usr/include/features.h: 25 | 26 | /usr/include/bits/predefs.h: 27 | 28 | /usr/include/sys/cdefs.h: 29 | 30 | /usr/include/bits/wordsize.h: 31 | 32 | /usr/include/gnu/stubs.h: 33 | 34 | /usr/include/gnu/stubs-32.h: 35 | 36 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h: 37 | 38 | /usr/include/bits/types.h: 39 | 40 | /usr/include/bits/typesizes.h: 41 | 42 | /usr/include/libio.h: 43 | 44 | /usr/include/_G_config.h: 45 | 46 | /usr/include/wchar.h: 47 | 48 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h: 49 | 50 | /usr/include/bits/stdio_lim.h: 51 | 52 | /usr/include/bits/sys_errlist.h: 53 | 54 | /usr/include/bits/stdio.h: 55 | 56 | /usr/include/bits/stdio2.h: 57 | 58 | /usr/include/stdlib.h: 59 | 60 | /usr/include/bits/waitflags.h: 61 | 62 | /usr/include/bits/waitstatus.h: 63 | 64 | /usr/include/endian.h: 65 | 66 | /usr/include/bits/endian.h: 67 | 68 | /usr/include/bits/byteswap.h: 69 | 70 | /usr/include/sys/types.h: 71 | 72 | /usr/include/time.h: 73 | 74 | /usr/include/sys/select.h: 75 | 76 | /usr/include/bits/select.h: 77 | 78 | /usr/include/bits/sigset.h: 79 | 80 | /usr/include/bits/time.h: 81 | 82 | /usr/include/sys/sysmacros.h: 83 | 84 | /usr/include/bits/pthreadtypes.h: 85 | 86 | /usr/include/alloca.h: 87 | 88 | /usr/include/bits/stdlib.h: 89 | -------------------------------------------------------------------------------- /src/.deps/main.Po: -------------------------------------------------------------------------------- 1 | main.o: main.c main.h /usr/include/stdlib.h /usr/include/features.h \ 2 | /usr/include/bits/predefs.h /usr/include/sys/cdefs.h \ 3 | /usr/include/bits/wordsize.h /usr/include/gnu/stubs.h \ 4 | /usr/include/gnu/stubs-32.h \ 5 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h \ 6 | /usr/include/bits/waitflags.h /usr/include/bits/waitstatus.h \ 7 | /usr/include/endian.h /usr/include/bits/endian.h \ 8 | /usr/include/bits/byteswap.h /usr/include/sys/types.h \ 9 | /usr/include/bits/types.h /usr/include/bits/typesizes.h \ 10 | /usr/include/time.h /usr/include/sys/select.h /usr/include/bits/select.h \ 11 | /usr/include/bits/sigset.h /usr/include/bits/time.h \ 12 | /usr/include/sys/sysmacros.h /usr/include/bits/pthreadtypes.h \ 13 | /usr/include/alloca.h /usr/include/bits/stdlib.h /usr/include/stdio.h \ 14 | /usr/include/libio.h /usr/include/_G_config.h /usr/include/wchar.h \ 15 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h \ 16 | /usr/include/bits/stdio_lim.h /usr/include/bits/sys_errlist.h \ 17 | /usr/include/bits/stdio.h /usr/include/bits/stdio2.h \ 18 | /usr/include/string.h /usr/include/xlocale.h /usr/include/bits/string.h \ 19 | /usr/include/bits/string2.h /usr/include/bits/string3.h \ 20 | /usr/include/malloc.h utils.h 21 | 22 | main.h: 23 | 24 | /usr/include/stdlib.h: 25 | 26 | /usr/include/features.h: 27 | 28 | /usr/include/bits/predefs.h: 29 | 30 | /usr/include/sys/cdefs.h: 31 | 32 | /usr/include/bits/wordsize.h: 33 | 34 | /usr/include/gnu/stubs.h: 35 | 36 | /usr/include/gnu/stubs-32.h: 37 | 38 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h: 39 | 40 | /usr/include/bits/waitflags.h: 41 | 42 | /usr/include/bits/waitstatus.h: 43 | 44 | /usr/include/endian.h: 45 | 46 | /usr/include/bits/endian.h: 47 | 48 | /usr/include/bits/byteswap.h: 49 | 50 | /usr/include/sys/types.h: 51 | 52 | /usr/include/bits/types.h: 53 | 54 | /usr/include/bits/typesizes.h: 55 | 56 | /usr/include/time.h: 57 | 58 | /usr/include/sys/select.h: 59 | 60 | /usr/include/bits/select.h: 61 | 62 | /usr/include/bits/sigset.h: 63 | 64 | /usr/include/bits/time.h: 65 | 66 | /usr/include/sys/sysmacros.h: 67 | 68 | /usr/include/bits/pthreadtypes.h: 69 | 70 | /usr/include/alloca.h: 71 | 72 | /usr/include/bits/stdlib.h: 73 | 74 | /usr/include/stdio.h: 75 | 76 | /usr/include/libio.h: 77 | 78 | /usr/include/_G_config.h: 79 | 80 | /usr/include/wchar.h: 81 | 82 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h: 83 | 84 | /usr/include/bits/stdio_lim.h: 85 | 86 | /usr/include/bits/sys_errlist.h: 87 | 88 | /usr/include/bits/stdio.h: 89 | 90 | /usr/include/bits/stdio2.h: 91 | 92 | /usr/include/string.h: 93 | 94 | /usr/include/xlocale.h: 95 | 96 | /usr/include/bits/string.h: 97 | 98 | /usr/include/bits/string2.h: 99 | 100 | /usr/include/bits/string3.h: 101 | 102 | /usr/include/malloc.h: 103 | 104 | utils.h: 105 | -------------------------------------------------------------------------------- /src/.deps/parser.Po: -------------------------------------------------------------------------------- 1 | parser.o: parser.c parser.h 2 | 3 | parser.h: 4 | -------------------------------------------------------------------------------- /src/.deps/preprocessor.Po: -------------------------------------------------------------------------------- 1 | preprocessor.o: preprocessor.c preprocessor.h 2 | 3 | preprocessor.h: 4 | -------------------------------------------------------------------------------- /src/.deps/scanner.Po: -------------------------------------------------------------------------------- 1 | scanner.o: scanner.c scanner.h 2 | 3 | scanner.h: 4 | -------------------------------------------------------------------------------- /src/.deps/symbol.Po: -------------------------------------------------------------------------------- 1 | symbol.o: symbol.c symbol.h 2 | 3 | symbol.h: 4 | -------------------------------------------------------------------------------- /src/.deps/utils.Po: -------------------------------------------------------------------------------- 1 | utils.o: utils.c utils.h /usr/include/stdio.h /usr/include/features.h \ 2 | /usr/include/bits/predefs.h /usr/include/sys/cdefs.h \ 3 | /usr/include/bits/wordsize.h /usr/include/gnu/stubs.h \ 4 | /usr/include/gnu/stubs-32.h \ 5 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h \ 6 | /usr/include/bits/types.h /usr/include/bits/typesizes.h \ 7 | /usr/include/libio.h /usr/include/_G_config.h /usr/include/wchar.h \ 8 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h \ 9 | /usr/include/bits/stdio_lim.h /usr/include/bits/sys_errlist.h \ 10 | /usr/include/bits/stdio.h /usr/include/bits/stdio2.h \ 11 | /usr/include/stdlib.h /usr/include/bits/waitflags.h \ 12 | /usr/include/bits/waitstatus.h /usr/include/endian.h \ 13 | /usr/include/bits/endian.h /usr/include/bits/byteswap.h \ 14 | /usr/include/sys/types.h /usr/include/time.h /usr/include/sys/select.h \ 15 | /usr/include/bits/select.h /usr/include/bits/sigset.h \ 16 | /usr/include/bits/time.h /usr/include/sys/sysmacros.h \ 17 | /usr/include/bits/pthreadtypes.h /usr/include/alloca.h \ 18 | /usr/include/bits/stdlib.h /usr/include/xlocale.h /usr/include/malloc.h 19 | 20 | utils.h: 21 | 22 | /usr/include/stdio.h: 23 | 24 | /usr/include/features.h: 25 | 26 | /usr/include/bits/predefs.h: 27 | 28 | /usr/include/sys/cdefs.h: 29 | 30 | /usr/include/bits/wordsize.h: 31 | 32 | /usr/include/gnu/stubs.h: 33 | 34 | /usr/include/gnu/stubs-32.h: 35 | 36 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stddef.h: 37 | 38 | /usr/include/bits/types.h: 39 | 40 | /usr/include/bits/typesizes.h: 41 | 42 | /usr/include/libio.h: 43 | 44 | /usr/include/_G_config.h: 45 | 46 | /usr/include/wchar.h: 47 | 48 | /usr/lib/gcc/i686-linux-gnu/4.4.5/include/stdarg.h: 49 | 50 | /usr/include/bits/stdio_lim.h: 51 | 52 | /usr/include/bits/sys_errlist.h: 53 | 54 | /usr/include/bits/stdio.h: 55 | 56 | /usr/include/bits/stdio2.h: 57 | 58 | /usr/include/stdlib.h: 59 | 60 | /usr/include/bits/waitflags.h: 61 | 62 | /usr/include/bits/waitstatus.h: 63 | 64 | /usr/include/endian.h: 65 | 66 | /usr/include/bits/endian.h: 67 | 68 | /usr/include/bits/byteswap.h: 69 | 70 | /usr/include/sys/types.h: 71 | 72 | /usr/include/time.h: 73 | 74 | /usr/include/sys/select.h: 75 | 76 | /usr/include/bits/select.h: 77 | 78 | /usr/include/bits/sigset.h: 79 | 80 | /usr/include/bits/time.h: 81 | 82 | /usr/include/sys/sysmacros.h: 83 | 84 | /usr/include/bits/pthreadtypes.h: 85 | 86 | /usr/include/alloca.h: 87 | 88 | /usr/include/bits/stdlib.h: 89 | 90 | /usr/include/xlocale.h: 91 | 92 | /usr/include/malloc.h: 93 | -------------------------------------------------------------------------------- /src/Makefile: -------------------------------------------------------------------------------- 1 | # General Makefile 2 | 3 | # By Eudis Duran 4 | 5 | .SILENT: 6 | .IGNORE: 7 | 8 | 9 | .PHONY: c cvm all 10 | 11 | c: 12 | make -C "compiler" 13 | 14 | cvm: 15 | make -C "cvm" 16 | 17 | all: 18 | make -C "compiler" 19 | make -C "cvm" 20 | -------------------------------------------------------------------------------- /src/compiler/Makefile: -------------------------------------------------------------------------------- 1 | # C - Compiler Makefile 2 | 3 | CC := gcc 4 | LIBS := -lm 5 | FLAGS := -Wall -O2 -g 6 | 7 | OBJS := main.o error.o parser.o scanner.o symbol.o preprocessor.o utils.o 8 | 9 | TARGET:=c 10 | 11 | $(TARGET) : $(OBJS) 12 | $(CC) $(FLAGS) $(OBJS) -o $(TARGET) $(LIBS) 13 | @echo 14 | @echo "Done Building C Compiler." 15 | @-rm *.o 16 | @-cp ./$(TARGET) ../../bin 17 | @-cp ./$(TARGET) ../../examples/bin 18 | @echo 19 | 20 | main.o : main.c main.h 21 | @echo "(Modified) Compiling Translation Unit: main.c + main.h" 22 | $(CC) -c main.c -o main.o 23 | 24 | error.o : error.c error.h 25 | @echo "(Modified) Compiling Translation Unit: error.c + error.h" 26 | $(CC) -c error.c -o error.o 27 | 28 | parser.o : parser.c parser.h 29 | @echo "(Modified) Compiling Translation Unit: parser.c + parser.h" 30 | $(CC) -c parser.c -o parser.o 31 | 32 | scanner.o : scanner.c scanner.h 33 | @echo "(Modified) Compiling Translation Unit: scanner.c + scanner.h" 34 | $(CC) -c scanner.c -o scanner.o 35 | 36 | symbol.o : symbol.c symbol.h 37 | @echo "(Modified) Compiling Translation Unit: symbol.c + symbol.h" 38 | $(CC) -c symbol.c -o symbol.o 39 | 40 | preprocessor.o : preprocessor.c preprocessor.h 41 | @echo "(Modified) Compiling Translation Unit: preprocessor.c + preprocessor.h" 42 | $(CC) -c preprocessor.c -o preprocessor.o 43 | 44 | utils.o : utils.c utils.h 45 | @echo "(Modified) Compiling Translation Unit: utils.c + utils.h" 46 | $(CC) -c utils.c -o utils.o 47 | 48 | 49 | -------------------------------------------------------------------------------- /src/compiler/drivers/error/make_err.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | int main() 5 | { 6 | adfs; 7 | return 0; 8 | } 9 | -------------------------------------------------------------------------------- /src/compiler/drivers/parser/get_token.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | 6 | char *get_lexeme(FILE *i); 7 | int get_token_name(char *lexeme); 8 | char *get_token_value(char *lexeme); 9 | 10 | int main() 11 | { 12 | char *tk_stream = "<10,20><30,40><50,60>"; 13 | FILE *in = fopen("test.c", "rb"); 14 | 15 | char *token = get_lexeme(in); 16 | 17 | printf("\n\nGet Token: '%s', token_name: %d, token_value: %d\n\n", token, get_token_name(token), get_token_value(token) ); 18 | token = get_lexeme(in); 19 | 20 | printf("\n\nGet Token: '%s', token_name: %d, token_value: %d\n\n", token, get_token_name(token), get_token_value(token) ); 21 | free(token); 22 | 23 | token = get_lexeme(in); 24 | 25 | printf("\n\nGet Token: '%s', token_name: %d, token_value: %d\n\n", token, get_token_name(token), get_token_value(token) ); 26 | token = get_lexeme(in); 27 | 28 | printf("\n\nGet Token: '%s', token_name: %d, token_value: %d\n\n", token, get_token_name(token), get_token_value(token) ); 29 | 30 | 31 | 32 | return 0; 33 | } 34 | 35 | char *get_lexeme(FILE *in) 36 | { 37 | int i=0, j; 38 | char *token; 39 | int pos = ftell(in); 40 | char c = getc(in); 41 | if(c == '<' && c != EOF){ 42 | while( (c = getc(in)) != EOF ){ 43 | i++; 44 | if(c == '>') 45 | break; 46 | 47 | } 48 | } 49 | else { 50 | return NULL; 51 | } 52 | 53 | token = (char*)malloc(sizeof(char)*i + 1); 54 | 55 | fseek(in, pos, SEEK_SET); 56 | 57 | i = 0; 58 | 59 | while( (c = getc(in)) != EOF ){ 60 | token[i] = c; 61 | i++; 62 | if(c == '>') 63 | break; 64 | 65 | } 66 | 67 | token[i] = '\0'; 68 | return token; 69 | } 70 | 71 | char *get_token_value(char *lexeme) 72 | { 73 | if(lexeme == NULL){ 74 | return -1; 75 | } 76 | 77 | int k = 0; 78 | while( lexeme[k] != ',' ){ 79 | k++; 80 | } 81 | 82 | int start = k + 1; 83 | 84 | int end = 0; 85 | 86 | int i = 0; 87 | while(end < strlen(lexeme)){ 88 | if( lexeme[end] == '>' ){ 89 | break; 90 | } 91 | end++; 92 | } 93 | 94 | char *tmp = (char*)malloc(sizeof(char)*(end - start)+1); 95 | int j; 96 | 97 | for(j = 0; j < (end - start + 1); j ++){ 98 | tmp[j] = lexeme[start + j]; 99 | } 100 | tmp[(end - start)] = '\0'; 101 | 102 | int x = atoi(tmp); 103 | free(tmp); 104 | 105 | return x; 106 | } 107 | 108 | int get_token_name(char *lexeme) 109 | { 110 | if(lexeme == NULL){ 111 | return -1; 112 | } 113 | 114 | int start = 1; 115 | 116 | int end = 0; 117 | 118 | int i = 0; 119 | while(end < strlen(lexeme)){ 120 | if( lexeme[end] == ',' ){ 121 | break; 122 | } 123 | end++; 124 | } 125 | 126 | char *tmp = (char*)malloc(sizeof(char)*(end - start)+1); 127 | int j; 128 | 129 | for(j = 0; j < (end - start + 1); j ++){ 130 | tmp[j] = lexeme[start + j]; 131 | } 132 | tmp[(end - start)] = '\0'; 133 | 134 | int x = atoi(tmp); 135 | free(tmp); 136 | 137 | return x; 138 | } 139 | -------------------------------------------------------------------------------- /src/compiler/drivers/preprocessor/fseek_test.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | int main() 5 | { 6 | FILE *f; 7 | f = fopen("tmp.txt", "r"); 8 | 9 | printf("\nI am at: %d\n", (int)ftell(f)); 10 | getc(f); 11 | printf("\nNow I am at: %d\n", (int)ftell(f)); 12 | fseek(f, 1, SEEK_CUR); 13 | printf("\nNow I am back at: %d\n", (int)ftell(f)); 14 | 15 | return 0; 16 | } 17 | -------------------------------------------------------------------------------- /src/compiler/drivers/preprocessor/get_inc_fname.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | #include "../../utils.h" 5 | 6 | char *get_inc_fname(FILE *i); 7 | 8 | int main() 9 | { 10 | char *name; 11 | FILE *f = fopen("tmp.txt", "r"); 12 | name = get_inc_fname(f); 13 | printf("%s\n", name); 14 | return 0; 15 | } 16 | 17 | 18 | char *get_inc_fname(FILE *i) 19 | { 20 | int j = 0; 21 | char c; 22 | char *name; 23 | 24 | int size = 0; 25 | int pos; /**> Used to save the start position of the filestream. 26 | Will be reverted after size is calculated */ 27 | 28 | pos = ftell(i); 29 | printf("Start file-p position: %d\n", (int)ftell(i)); 30 | 31 | while( (c = getc(i)) != EOF ){ /* The 'c' here begins at position 0 of the filename string. */ 32 | 33 | if( c == '<' ){ 34 | c = getc(i); /* Do not count '<' as it's not part of the string 35 | name, so pop it off the stream */ 36 | while( (c != EOF) && (c != '>') ){ 37 | size++; 38 | c = getc(i); 39 | } 40 | break; 41 | } 42 | } 43 | 44 | printf("Size of filename string is: %d\n", size); 45 | printf("Current file-p position: %d\n", (int)ftell(i)); 46 | fseek(i, -(ftell(i)-pos), SEEK_CUR); 47 | printf("Reset the file-p position to: %d\n", (int)ftell(i)); 48 | 49 | name = (char*)malloc(sizeof(char)*size); 50 | 51 | while( (c = getc(i)) != EOF && (j < size) ){ /* The 'c' here begins at position 0 of the filename string. */ 52 | if( c == '<' ){ 53 | c = getc(i); 54 | while( (c != EOF) && (c != '>') ){ 55 | name[j] = c; 56 | j++; 57 | c = getc(i); 58 | } 59 | break; 60 | } 61 | } 62 | 63 | return name; 64 | } 65 | -------------------------------------------------------------------------------- /src/compiler/drivers/preprocessor/get_next_word.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | char *get_next_word(FILE *f); 6 | 7 | int main() 8 | { 9 | FILE *f = fopen("tmp.txt", "r"); 10 | 11 | //printf("%s", get_next_word(f)); 12 | get_next_word(f); 13 | get_next_word(f); 14 | get_next_word(f); 15 | get_next_word(f); 16 | return 0; 17 | } 18 | 19 | 20 | char *get_next_word(FILE *f) 21 | { 22 | char *word; 23 | int get_out = 0; 24 | char c; 25 | int start_pos = ftell(f); 26 | int count = 0; 27 | int last_run = 0; 28 | 29 | while ( (c = getc(f)) != EOF ){ 30 | if(c == ' ' || c == '\t' || c == '\n') 31 | continue; 32 | else { 33 | while(c != EOF){ 34 | if(c != ' ' && c != '\t' && c != '\n'){ 35 | (!last_run)? count++ : count; 36 | printf("%c", c); 37 | c = getc(f); 38 | } 39 | else { 40 | get_out = last_run = 1; 41 | 42 | break; 43 | } 44 | } 45 | if(get_out == 1) { 46 | fseek(f, -count, SEEK_CUR); // Offset by word length amount 47 | if(last_run == 1){ 48 | word = (char*)malloc(sizeof(char)*count); 49 | printf(" :Word Length: %d\n", count); 50 | } 51 | break; 52 | 53 | } 54 | } 55 | } 56 | return "YO"; 57 | } 58 | 59 | 60 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/extract_token.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | #include "../../utils.h" 6 | 7 | int is_valid_id(char *word); 8 | char *extract_token(char *word); 9 | char *return_keyword(char *word); 10 | 11 | int main() 12 | { 13 | //char ar[] = "int;"; 14 | //printf("%c\n", ar[3]); 15 | printf("keyword: '%s'\n\n", extract_token("(int")); 16 | return 0; 17 | } 18 | 19 | char *extract_token(char *word) 20 | { 21 | switch(word[0]){ 22 | case '{': 23 | return "{"; 24 | case '}': 25 | return "}"; 26 | case '(': 27 | return "("; 28 | case ')': 29 | return ")"; 30 | case ']': 31 | return "]"; 32 | case '[': 33 | return "["; 34 | case '.': 35 | return "."; 36 | case '!': 37 | return "!"; 38 | case '~': 39 | return "~"; 40 | /* ~ */ 41 | /* ~= */ 42 | case '+': 43 | return "+"; 44 | /* + */ 45 | /* ++ */ 46 | /* += */ 47 | case '-': 48 | return "-"; 49 | /* - */ 50 | /* -- */ 51 | /* -= */ 52 | case '*': 53 | return "*"; 54 | /* * */ 55 | /* *= */ 56 | case '&': 57 | return "&"; 58 | /* & */ 59 | /* && */ 60 | /* &= */ 61 | case '/': 62 | return "/"; 63 | /* / */ 64 | /* /= */ 65 | case '%': 66 | return "%"; 67 | /* % */ 68 | /* %= */ 69 | case '<': 70 | return "<"; 71 | /* < */ 72 | /* << */ 73 | /* <= */ 74 | /* <<= */ 75 | case '>': 76 | return ">"; 77 | /* > */ 78 | /* >> */ 79 | /* >= */ 80 | /* >>= */ 81 | case '=': 82 | return "="; 83 | /* = */ 84 | /* == */ 85 | case '|': 86 | return "|"; 87 | /* | */ 88 | /* || */ 89 | /* |= */ 90 | case '^': 91 | return "^"; 92 | /* ^ */ 93 | /* ^= */ 94 | case '?': 95 | return "?"; 96 | case ':': 97 | return ":"; 98 | case ';': 99 | return ";"; 100 | /* Constants */ 101 | 102 | case '\'': 103 | return "'"; 104 | /* String Literals */ 105 | /* Questioning if this even belongs here?*/ 106 | case '"': 107 | return "\""; 108 | break; 109 | 110 | default: 111 | return return_keyword(word); 112 | break; 113 | 114 | 115 | } 116 | return NULL; 117 | } 118 | 119 | char *return_keyword(char *word) 120 | { 121 | 122 | size_t size = strlen(word); 123 | int i; 124 | printf("\n"); 125 | for(i = 0; i < size; i++){ 126 | if( !isdigit(word[i]) && !isalpha(word[i]) && word[i] != '_'){ 127 | break; 128 | } 129 | } 130 | /* 'i' is the size of the valid keyword or id */ 131 | char *keyword = (char *)xmalloc(sizeof(char)* i + 1); 132 | 133 | strcpy(keyword, word); 134 | keyword[i] = '\0'; 135 | 136 | return keyword; 137 | 138 | } 139 | 140 | 141 | int is_valid_id(char *word) 142 | { 143 | size_t size = strlen(word); 144 | 145 | int j; 146 | for(j = 0; j < size; j++){ 147 | if( !isalpha(word[j]) && !isdigit(word[j]) && word[j] != '_' ){ 148 | 149 | return 0; 150 | } 151 | 152 | } 153 | 154 | 155 | return size; 156 | } 157 | 158 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/get_lexeme.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | char *get_lexeme(FILE *i); 6 | 7 | int main() 8 | { 9 | FILE *i = fopen("tmp.txt", "r"); 10 | 11 | printf("%s\n\n", get_lexeme(i)); 12 | return 0; 13 | } 14 | 15 | char *get_lexeme(FILE *i) 16 | { 17 | char c; 18 | while ( (c = fget(i)) != '>' ){} 19 | return NULL; 20 | } 21 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/get_token.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include "../../utils.h" 4 | #include "../../scanner.h" 5 | #include 6 | 7 | int parse_tokens(); 8 | 9 | int main() 10 | { 11 | parse_tokens(); 12 | return 0; 13 | } 14 | 15 | 16 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/is_valid_id.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | #include "../../utils.h" 6 | 7 | int is_valid_id(char *word); 8 | 9 | int main() 10 | { 11 | 12 | printf("%d", is_valid_id("int;")); 13 | return 0; 14 | } 15 | 16 | //int is_valid_id(FILE *i) 17 | //{ 18 | // printf("Current File Pos: %d\n", ftell(i)); 19 | // int valid = 0; 20 | // size_t file_pos = ftell(i); /**> Save the current file p. */ 21 | // char *word = getword(i); 22 | // //free(word); 23 | // //word = getword(i); 24 | // 25 | // printf("Current WORD: %s\n", word); 26 | // 27 | // size_t size = strlen(word); 28 | // 29 | // 30 | // printf("Is it valid? "); 31 | // int j; 32 | // for(j = 0; j < size; j++){ 33 | // if( !isalpha(word[j]) && !isdigit(word[j]) && word[j] != '_' ){ 34 | // 35 | // printf("No! (%d)\n", valid); 36 | // valid = 0; 37 | // return 0; 38 | // } 39 | // valid = 1; 40 | // } 41 | // if(valid == 1){ 42 | // printf("YES! (%d)\n", valid); 43 | // //return size; 44 | // } 45 | // 46 | // fseek(i, -(ftell(i) - file_pos), SEEK_CUR); 47 | // free(word); /* Release the resource */ 48 | // printf("Ending File Pos: %d\n", ftell(i)); 49 | // return 0; 50 | //} 51 | 52 | int is_valid_id(char *word) 53 | { 54 | size_t size = strlen(word); 55 | 56 | int j; 57 | for(j = 0; j < size; j++){ 58 | if( !isalpha(word[j]) && !isdigit(word[j]) && word[j] != '_' ){ 59 | 60 | return 0; 61 | } 62 | 63 | } 64 | 65 | 66 | return size; 67 | } 68 | 69 | 70 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/return_string.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | char *return_string(char *word); 6 | 7 | 8 | int main() 9 | { 10 | char *word = "\" \""; 11 | printf("%s\n", word); 12 | printf("String: %s\n", return_string(word)); 13 | return 0; 14 | } 15 | 16 | 17 | char *return_string(char *word) 18 | { 19 | int i, j; 20 | size_t size = strlen(word); 21 | char *tmp; 22 | for(i = 1; i < size; i++){ 23 | if( word[i] == '"' ){ 24 | i++; 25 | break; 26 | } 27 | } 28 | 29 | tmp = (char*)malloc(sizeof(char)*i + 1); 30 | 31 | for(j = 0; j < i; j++){ 32 | tmp[j] = word[j]; 33 | } 34 | 35 | tmp[i] = '\0'; 36 | 37 | 38 | return tmp; 39 | } 40 | -------------------------------------------------------------------------------- /src/compiler/drivers/scanner/write_token.c: -------------------------------------------------------------------------------- 1 | void write_token(FILE *o, char *tk_name, char *tk_value) 2 | { 3 | size_t tk_name_size = strlen(tk_name); 4 | size_t tk_value_size = strlen(tk_value); 5 | 6 | putc('<', o); 7 | fwrite(tk_name, sizeof(char), tk_name_size, o); 8 | putc(',', o); 9 | fwrite(tk_value, sizeof(char), tk_value_size, o); 10 | putc('>', o); 11 | } 12 | -------------------------------------------------------------------------------- /src/compiler/drivers/semantic/stub: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/eudisd/c-compiler/9aa5e08fe4217accd4935b8120178e4e0377e0a0/src/compiler/drivers/semantic/stub -------------------------------------------------------------------------------- /src/compiler/drivers/symbol/is_keyword.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | #define TRUE 1 5 | #define FALSE 0 6 | #define KEYWORD_TOTAL 30 7 | 8 | char *keywords[] = { 9 | "auto", 10 | "break", 11 | "case", 12 | "char", 13 | "const", 14 | "continue", 15 | "default", 16 | "do", 17 | "double", 18 | "else", 19 | "extern", 20 | "float", 21 | "goto", 22 | "int", 23 | "if", 24 | "long", 25 | "register", 26 | "return", 27 | "short", 28 | "signed", 29 | "sizeof", 30 | "static", 31 | "struct", 32 | "switch", 33 | "typedef", 34 | "union", 35 | "unsigned", 36 | "void", 37 | "volatile", 38 | "while" 39 | }; 40 | 41 | int is_keyword(char *lexeme); 42 | 43 | int main(){ 44 | /* Driver: Test All Cases Test Correctly */ 45 | int i = 0; 46 | 47 | 48 | for(i = 0; i < KEYWORD_TOTAL; i++){ 49 | /* These should all print '1' for Answer!*/ 50 | printf("Is %s a keyword? Answer: %d\n", keywords[i], is_keyword(keywords[i])); 51 | } 52 | return 0; 53 | } 54 | 55 | int is_keyword(char *lexeme) 56 | { 57 | switch(lexeme[0]){ 58 | case 'a': 59 | /* auto */ 60 | if( !strcmp(lexeme, "auto") ) 61 | return TRUE; 62 | return FALSE; 63 | case 'b': 64 | /* break */ 65 | if( !strcmp(lexeme, "break") ) 66 | return TRUE; 67 | return FALSE; 68 | case 'c': 69 | /* case */ 70 | /* char */ 71 | /* const */ 72 | /* continue */ 73 | if( !strcmp(lexeme, "case") || 74 | !strcmp(lexeme, "char") || 75 | !strcmp(lexeme, "const") || 76 | !strcmp(lexeme, "continue") 77 | ) 78 | return TRUE; 79 | return FALSE; 80 | case 'd': 81 | /* default */ 82 | /* do */ 83 | /* double */ 84 | if( !strcmp(lexeme, "default")|| 85 | !strcmp(lexeme, "do") || 86 | !strcmp(lexeme, "double") 87 | ) 88 | return TRUE; 89 | return FALSE; 90 | case 'e': 91 | /* else */ 92 | /* enum */ 93 | /* extern */ 94 | if( !strcmp(lexeme, "else") || 95 | !strcmp(lexeme, "enum") || 96 | !strcmp(lexeme, "extern") 97 | ) 98 | return TRUE; 99 | return FALSE; 100 | case 'f': 101 | /* float */ 102 | /* for */ 103 | if( !strcmp(lexeme, "float")|| 104 | !strcmp(lexeme, "for") 105 | ) 106 | return TRUE; 107 | return FALSE; 108 | case 'g': 109 | /* goto */ 110 | if( !strcmp(lexeme, "goto") ) 111 | return TRUE; 112 | return FALSE; 113 | 114 | case 'i': 115 | /* int */ 116 | /* if */ 117 | if( !strcmp(lexeme, "int") || 118 | !strcmp(lexeme, "if") 119 | ) 120 | return TRUE; 121 | return FALSE; 122 | case 'l': 123 | /* long */ 124 | if( !strcmp(lexeme, "long") ) 125 | return TRUE; 126 | return FALSE; 127 | case 'r': 128 | /* register */ 129 | /* return */ 130 | if( !strcmp(lexeme, "register")|| 131 | !strcmp(lexeme, "return") 132 | ) 133 | return TRUE; 134 | return FALSE; 135 | case 's': 136 | /* short */ 137 | /* signed */ 138 | /* sizeof */ 139 | /* static */ 140 | /* struct */ 141 | /* switch */ 142 | if( !strcmp(lexeme, "short") || 143 | !strcmp(lexeme, "signed") || 144 | !strcmp(lexeme, "sizeof") || 145 | !strcmp(lexeme, "static") || 146 | !strcmp(lexeme, "struct") || 147 | !strcmp(lexeme, "switch") 148 | ) 149 | return TRUE; 150 | return FALSE; 151 | case 't': 152 | /* typedef */ 153 | if( !strcmp(lexeme, "typedef") ) 154 | return TRUE; 155 | return FALSE; 156 | case 'u': 157 | /* union */ 158 | /* unsigned */ 159 | if( !strcmp(lexeme, "union") || 160 | !strcmp(lexeme, "unsigned") 161 | ) 162 | return TRUE; 163 | return FALSE; 164 | case 'v': 165 | /* void */ 166 | /* volatile */ 167 | if( !strcmp(lexeme, "void") || 168 | !strcmp(lexeme, "volatile") 169 | ) 170 | return TRUE; 171 | return FALSE; 172 | case 'w': 173 | /* while */ 174 | if( !strcmp(lexeme, "while") ) 175 | return TRUE; 176 | return FALSE; 177 | default: 178 | return FALSE; 179 | } 180 | } 181 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/bsearch.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | int bint_comp(const void *a, const void *b); 5 | 6 | int bfloat_comp(const void *a, const void *b); 7 | 8 | int main() 9 | { 10 | int a[10] = {0,1,2,3,4,5,6,7,8,9}; 11 | double b[10] = {0.1, 0.01, 0.2, 0.022, 0.101, 0.1, 12.3, 10.3, 11.3, 1.1}; 12 | double key = 0.21; 13 | double *item = bsearch(&key, b, 10, sizeof(double), bfloat_comp); 14 | if(!item){ 15 | 16 | } 17 | else { 18 | printf("%f\n", *item); 19 | } 20 | return 0; 21 | } 22 | 23 | int bint_comp(const void *a, const void *b) 24 | { 25 | if ( *(int*)a > *(int*)b ) return 1; 26 | if ( *(int*)a == *(int*)b ) return 0; 27 | if ( *(int*)a < *(int*)b ) return -1; 28 | } 29 | 30 | int bfloat_comp(const void *a, const void *b) 31 | { 32 | if ( *(double*)a > *(double*)b ) return 1; 33 | if ( *(double*)a == *(double*)b ) return 0; 34 | if ( *(double*)a < *(double*)b ) return -1; 35 | } 36 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/fcpeek.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | char fcpeek(FILE *f); 5 | 6 | int main() 7 | { 8 | FILE *f = fopen("tmp.txt", "r"); 9 | printf("Char: %c\n", fcpeek(f)); 10 | printf("Current Pos: %d\n", (long int)ftell(f)); 11 | return 0; 12 | } 13 | 14 | char fcpeek(FILE *f) 15 | { 16 | char c = getc(f); 17 | ungetc(c, f); 18 | return c; 19 | } 20 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/get_column.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include "../../utils.h" 4 | 5 | int get_column(FILE *i); 6 | 7 | int main() 8 | { 9 | FILE *i = fopen("tmp.txt", "r"); 10 | getc(i); 11 | getc(i); 12 | getc(i); 13 | getc(i); 14 | getc(i); 15 | getc(i); 16 | getc(i); 17 | getc(i); 18 | getc(i); 19 | getc(i); 20 | getc(i); 21 | getc(i); 22 | getc(i); 23 | getc(i); 24 | getc(i); 25 | getc(i); 26 | getc(i); 27 | getc(i); 28 | getc(i); 29 | getc(i); 30 | printf("Answer: %d\n", get_column(i)); 31 | return 0; 32 | } 33 | 34 | int get_column(FILE *i){ 35 | int cur_pos = ftell(i); 36 | int offset = 0; 37 | char c = fcpeek(i); 38 | 39 | while( c != '\n' && (ftell(i) > 0) && c != EOF){ 40 | fseek(i, -1, SEEK_CUR); 41 | offset++; 42 | c = fcpeek(i); 43 | } 44 | fseek(i, cur_pos, SEEK_CUR); 45 | return offset; 46 | } 47 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/get_files_from_argv.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | 6 | 7 | char **get_files_from_argv(int argc, char *argv[]); 8 | 9 | int main(int argc, char *argv[]) 10 | { 11 | int i; 12 | char **a = (char**)get_files_from_argv(argc, argv); 13 | 14 | for(i = 1; i < argc; i++){ 15 | printf("%s\n", a[i]); 16 | } 17 | return 0; 18 | } 19 | 20 | char **get_files_from_argv(int argc, char *argv[]) 21 | { 22 | char **files = (char**)malloc(sizeof(char*)*argc); 23 | int i; 24 | size_t size; 25 | 26 | for(i = 1; i < argc; i++){ 27 | size = strlen(argv[i]); 28 | files[i] = (char*)malloc(sizeof(char)*size); 29 | strcpy(files[i], argv[i]); 30 | } 31 | 32 | return files; 33 | } 34 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/get_filesize.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | int get_filesize(char *filename); 5 | 6 | int main() 7 | { 8 | printf("FILESIZE: %d-bytes\n", get_filesize("tmp.txt")); 9 | #if defined(__linux) 10 | system("wc -c tmp.txt"); 11 | #endif 12 | return 0; 13 | } 14 | 15 | int get_filesize(char *filename) 16 | { 17 | FILE *f = fopen(filename, "r"); 18 | fseek(f, 0, SEEK_END); 19 | return ftell(f); 20 | } 21 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/getword.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | #include 5 | 6 | char *getword(FILE *i); 7 | size_t total_newlines; 8 | int main() 9 | { 10 | char *name; 11 | FILE *f = fopen("tmp.txt", "r"); 12 | 13 | printf("%s\n", getword(f)); 14 | /*printf("%s\n", getword(f)); 15 | printf("%s\n", getword(f)); 16 | printf("%s\n", getword(f)); 17 | printf("%s\n", getword(f)); 18 | printf("%s\n", getword(f)); 19 | printf("%s\n", getword(f)); 20 | printf("%s\n", getword(f)); 21 | printf("%s\n", getword(f)); 22 | printf("%s\n", getword(f)); 23 | printf("%s\n", getword(f)); 24 | printf("%s\n", getword(f)); 25 | printf("%s\n", getword(f)); 26 | printf("%s\n", getword(f)); 27 | printf("%s\n", getword(f)); 28 | */ 29 | fclose(f); 30 | return 0; 31 | } 32 | 33 | 34 | char *getword(FILE *i) 35 | { 36 | 37 | int j = 0; 38 | char c; 39 | char *word; 40 | int pos; 41 | size_t size = 0; 42 | 43 | if(fcpeek(i) == EOF){ 44 | return NULL; 45 | } 46 | 47 | pos = ftell(i); 48 | c = getc(i); 49 | if( c == '\n' ){ 50 | //total_newlines++; 51 | } 52 | 53 | /* We first calculate the size of the word */ 54 | while ( (c != EOF) && !isspace(c) ){ 55 | /* Read and count new lines and characters */ 56 | 57 | /* This new section handles the string word input count*/ 58 | if ( c == '\"' ){ 59 | size++; 60 | c = getc(i); 61 | while( c != '\"' ){ 62 | 63 | if( c == '\n' ){ 64 | printf("String error!\n"); 65 | exit(EXIT_FAILURE); 66 | } 67 | 68 | size++; 69 | c = getc(i); 70 | 71 | } 72 | } 73 | size++; 74 | c = getc(i); 75 | if( c == '\n' ){ 76 | //total_newlines++; 77 | } 78 | 79 | } 80 | fseek(i, -(ftell(i) - pos), SEEK_CUR); 81 | 82 | word = (char*)xmalloc(sizeof(char)*size + 1); 83 | 84 | c = getc(i); 85 | 86 | /* Then we copy the word the to malloc'ed space */ 87 | while ( ((c != EOF) && !isspace(c)) && (j < size) ){ 88 | /* This new section handles the new string copy! */ 89 | if ( c == '\"' ){ 90 | word[j] = c; 91 | j++; 92 | c = getc(i); 93 | word[j] = c; 94 | 95 | while( c != '\"' && (j < size) ){ 96 | word[j] = c; 97 | j++; 98 | c = getc(i); 99 | } 100 | } 101 | word[j] = c; 102 | j++; 103 | c = getc(i); 104 | } 105 | word[size] = '\0'; 106 | 107 | 108 | return word; 109 | } 110 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/scan_for_o.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | char *scan_for_o(int argc, char *argv[]) 6 | { 7 | int i; 8 | for(i = 0; i < argc; i++){ 9 | if(strcmp(argv[i], "-o") == 0){ 10 | return argv[i + 1]; 11 | } 12 | } 13 | } 14 | 15 | int main() 16 | { 17 | char *argv[3] = {"program", "-o", "name"}; 18 | 19 | printf("%s", scan_for_o(3, argv)); 20 | return 0; 21 | } 22 | 23 | -------------------------------------------------------------------------------- /src/compiler/drivers/utils/strip_whitesp.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | char *strip_whitesp(char *str); 5 | 6 | int main() 7 | { 8 | char s[] = " crap "; 9 | printf("Before:'%s'\n", s); 10 | 11 | printf("After:'%s'\n", strip_whitesp(s)); 12 | return 0; 13 | } 14 | 15 | char *strip_whitesp(char *str) 16 | { 17 | return NULL; 18 | } 19 | -------------------------------------------------------------------------------- /src/compiler/error.c: -------------------------------------------------------------------------------- 1 | /** \file error.c 2 | \brief 3 | */ 4 | 5 | #include "error.h" 6 | 7 | void error(char* file, int line, int column, char *msg){ 8 | printf("\n%s:%d:%d: error: %s\n", file, line, column, msg); 9 | exit(EXIT_FAILURE); 10 | } 11 | 12 | void warning(char* file, int line, int column, char *msg){ 13 | printf("\n%s:%d:%d: warning: %s\n", file, line, column, msg); 14 | } 15 | 16 | 17 | 18 | 19 | -------------------------------------------------------------------------------- /src/compiler/error.h: -------------------------------------------------------------------------------- 1 | /** \file error.h 2 | \brief Header file containing all of the error handling primatives for the compiler. 3 | These primatives are for error output in terms of the runtime compiler, not the 4 | development environment for this code. 5 | */ 6 | 7 | #ifndef _ERROR_H_ 8 | #define _ERROR_H_ 9 | 10 | #include 11 | #include 12 | 13 | enum { 14 | TYPE_ERR, 15 | TOKEN_ERR, 16 | SYNTAX_ERR, 17 | TYPE_WARN, 18 | TOKEN_WARN, 19 | SYNTAX_WARN 20 | }; 21 | 22 | 23 | size_t lines; 24 | size_t columns; 25 | 26 | /** Prints an error message in standard UNIX(GNU/GCC) format 27 | */ 28 | inline void error(char* file, int line, int column, char *msg); 29 | /** Prints an warning message in standard UNIX(GNU/GCC) format 30 | */ 31 | inline void warning(char* file, int line, int column, char *msg); 32 | 33 | /** Get the line number where the error occurred. 34 | */ 35 | inline int get_line(FILE *i); 36 | 37 | /** Get the column number where the error occurred. 38 | */ 39 | inline int get_column(FILE *i); 40 | 41 | #endif 42 | -------------------------------------------------------------------------------- /src/compiler/main.c: -------------------------------------------------------------------------------- 1 | /** \file main.c 2 | \brief 3 | */ 4 | 5 | #include "main.h" 6 | 7 | size_t total_newlines = 1; 8 | 9 | extern file_struct file; 10 | 11 | symbol_table *string_table; 12 | symbol_table *id_table; 13 | 14 | int so = 0; 15 | 16 | int main(int argc, char *argv[]) 17 | { 18 | char *ofile; /**> Filename of the output file */ 19 | char *infile; /**> Filename of the input file */ 20 | size_t o_name_len; /**> Filesize of the name specifed by the -o flag */ 21 | 22 | /* Initialize some file information */ 23 | strcpy(file.calling_prog, argv[0]); 24 | strcpy(file.default_o, DEFAULT_OUTPUT); 25 | file.cur_line = 0; 26 | file.cur_column = 0; 27 | 28 | switch(argc){ 29 | case 1: 30 | printf("%s: no input files.\n Try --help for more options.\n", file.calling_prog); 31 | break; 32 | case 2: 33 | if(strcmp(argv[1], "--help") == 0){ 34 | usage(); 35 | } 36 | else if(strcmp(argv[1], "--version") == 0){ 37 | version(); 38 | } 39 | else { 40 | /* Initialize File Contents */ 41 | strcpy(file.filename, argv[1]); 42 | 43 | /* No output name specified, we default to unix elf name a.out */ 44 | // run_preprocessor(&file); 45 | 46 | run_scanner(&file); 47 | run_parser(); /* Generates Stack Code */ 48 | } 49 | break; 50 | case 3: 51 | fprintf(stderr, "File input error!\n"); 52 | exit(EXIT_FAILURE); 53 | break; 54 | default: 55 | /* These next few lines handle the -o flag */ 56 | 57 | if( strcmp(argv[1], "-So") == 0 ){ 58 | printf("\n%s\n", argv[2]); 59 | } 60 | o_name_len = strlen((char*)scan_for_o(argc, argv)); 61 | 62 | if(o_name_len > 0){ 63 | ofile = (char*)xmalloc(sizeof(char)*o_name_len); 64 | strcpy(ofile, (char*)scan_for_o(argc, argv)); 65 | 66 | strcpy(file.filename, argv[1]); 67 | strcpy(file.default_o, ofile); 68 | 69 | 70 | run_preprocessor(&file); 71 | 72 | run_scanner(&file); /* Outputs an interim file */ 73 | run_parser(); /* Generates Stack Code */ 74 | 75 | free(ofile); 76 | } 77 | 78 | break; 79 | } 80 | 81 | return EXIT_SUCCESS; 82 | } 83 | 84 | -------------------------------------------------------------------------------- /src/compiler/main.h: -------------------------------------------------------------------------------- 1 | /** \file main.h 2 | \brief 3 | */ 4 | 5 | #ifndef _MAIN_H_ 6 | #define _MAIN_H_ 7 | 8 | #include 9 | #include 10 | #include 11 | #include 12 | 13 | #include "symbol.h" 14 | #include "utils.h" 15 | #include "preprocessor.h" 16 | #include "scanner.h" 17 | 18 | 19 | /* Command Line Options (externals)*/ 20 | 21 | extern int So; 22 | 23 | 24 | #endif 25 | -------------------------------------------------------------------------------- /src/compiler/parser.h: -------------------------------------------------------------------------------- 1 | /** \file parser.h 2 | \brief 3 | */ 4 | 5 | #ifndef _PARSER_H_ 6 | #define _PARSER_H_ 7 | 8 | #include 9 | #include 10 | #include 11 | #include "error.h" 12 | #include "utils.h" 13 | #include "symbol.h" 14 | #include "scanner.h" 15 | 16 | /* Opcodes */ 17 | 18 | #define OP_PUSH 0 19 | #define OP_PUSHI 1 20 | #define OP_POP 2 21 | #define OP_EXCH 3 22 | #define OP_DUP 4 23 | #define OP_ADDF 5 24 | #define OP_ADD 6 25 | #define OP_SUBF 7 26 | #define OP_SUB 8 27 | #define OP_MULF 9 28 | #define OP_MUL 10 29 | #define OP_DIV 11 30 | #define OP_DIVF 12 31 | #define OP_AND 13 32 | #define OP_OR 14 33 | #define OP_EQL 15 34 | #define OP_NEG 16 35 | #define OP_NOT 17 36 | #define OP_LSS 18 37 | #define OP_GTR 19 38 | #define OP_LEQ 20 39 | #define OP_GEQ 21 40 | #define OP_CVI 22 41 | #define OP_CVR 23 42 | #define OP_JMP 24 43 | #define OP_JFALSE 25 44 | #define OP_JTRUE 26 45 | #define OP_HALT 27 46 | #define OP_WRITEINT 28 47 | 48 | #define OP_WRITEFLOAT 29 49 | #define OP_MOD 30 50 | 51 | #define OP_PUSHF 31 52 | #define OP_POPF 32 53 | 54 | #define OP_WRITEINTID 33 55 | #define OP_POPEMPTY 34 56 | #define OP_NOP 35 57 | 58 | #define OP_NEQ 36 59 | #define OP_EQU 37 60 | #define OP_NEGF 38 61 | #define OP_WRITESTRING 39 62 | #define OP_GET 40 63 | #define OP_PUT 41 64 | 65 | /* Type defs */ 66 | typedef unsigned char uchar; 67 | typedef char TYPE; 68 | 69 | typedef union Operand_TAG { 70 | int i; 71 | float f; 72 | } Operand; 73 | 74 | typedef struct Instruction_TAG { 75 | char opcode; /* 8-bit */ 76 | Operand operand; /* 32-bit */ 77 | }Instruction; 78 | 79 | /* Globals */ 80 | static char *cur_token; 81 | static int dp = 0; 82 | 83 | 84 | /* Externals */ 85 | extern file_struct file; 86 | extern symbol_table *string_table; 87 | extern symbol_table *id_table; 88 | 89 | extern symbol_table *stab_stack[]; 90 | 91 | /** Gets a lexeme. _MUST_ be freed after use. 92 | */ 93 | char *get_lexeme(FILE *i); 94 | 95 | /** Given a lexeme, returns the NAME part. _MUST_ be freed after call. 96 | */ 97 | int get_token_name(char *lexeme); 98 | 99 | /** Given a lexeme, returns the NAME part. _MUST_ be freed after call. 100 | */ 101 | int get_token_value(char *lexeme); 102 | 103 | float get_token_value_f(char *lexeme); 104 | 105 | /** 106 | */ 107 | 108 | char* get_token(); 109 | 110 | /** 111 | */ 112 | void match(char *token); 113 | 114 | /** 115 | */ 116 | void matchi(int token); 117 | 118 | /** 119 | */ 120 | char *peek_next_token(); 121 | 122 | 123 | /**** PRODUCTIONS ******/ 124 | 125 | TYPE CProgram(); 126 | 127 | void Declarations(); 128 | void Assignment(); 129 | void MainEntry(); 130 | 131 | int IntDec(); 132 | int FloatDec(); 133 | int CharDec(); 134 | 135 | void Statements(); 136 | void IfStatement(); 137 | void DoWhile(); 138 | void While(); 139 | void Goto(); 140 | void Label(); 141 | void Switch(); 142 | void Case(); 143 | 144 | /* Expression Productions */ 145 | /** 146 | */ 147 | TYPE E(); 148 | 149 | /** 150 | */ 151 | TYPE EPrime(); 152 | 153 | /** 154 | */ 155 | TYPE T(); 156 | 157 | /** 158 | */ 159 | TYPE TPrime(); 160 | 161 | /** 162 | */ 163 | TYPE F(); 164 | 165 | 166 | /** 167 | */ 168 | 169 | TYPE L(); 170 | 171 | /** 172 | */ 173 | TYPE LPrime(); 174 | 175 | #endif 176 | -------------------------------------------------------------------------------- /src/compiler/preprocessor.c: -------------------------------------------------------------------------------- 1 | /** \file preprocessor.c 2 | \brief 3 | */ 4 | 5 | #include "preprocessor.h" 6 | 7 | file_struct file; 8 | 9 | void run_preprocessor(file_struct *file) 10 | { 11 | /* Order of file processing ("data" is the name of the intermediary file"): 12 | ********************************************************************** 13 | * ifilename(open the stream) --> include_headers("data") --> data --> 14 | * remove_comments("data") --> data --> handle_defines("data") --> 15 | * data 16 | */ 17 | 18 | /* We need certain flags to be set here. If they are not set, then we simply use 19 | * the system defaults. These flags deal with the standard directories, among others things. 20 | */ 21 | 22 | int dir_flag = FALSE; 23 | int lib_flag = FALSE; 24 | 25 | 26 | /* set_flags(dir_flag, lib_flag); */ 27 | 28 | if( !dir_flag ){ 29 | sys_inc_dir = (char*)xmalloc(sizeof(char)*strlen(DEFAULT_INC_DIR) + 1); 30 | strcpy(sys_inc_dir, DEFAULT_INC_DIR); 31 | } 32 | if( !lib_flag ){ 33 | sys_lib_dir = (char*)xmalloc(sizeof(char)*strlen(DEFAULT_LIB_DIR) + 1); 34 | strcpy(sys_lib_dir, DEFAULT_LIB_DIR); 35 | } 36 | 37 | 38 | /******************************************************************** 39 | * First we import all included header files into the current working c temp 40 | * file and output an intermediary object file. 41 | ********************************************************************/ 42 | 43 | //include_headers(prog, ifilename, INTERIM_FILENAME); 44 | 45 | /* This same interim file is then used for all subsequent operations, including 46 | feeding it to the compiler (scanner, parser, etc etc). 47 | */ 48 | 49 | 50 | /* After header files are included, we remove all C-Style comments from the tmp file*/ 51 | remove_comments(file); 52 | 53 | /* At this point, we have to handle #defines. There are two types of cases here. 54 | One is a symbolic constant, the other is a macro. I will handle the constant case 55 | first, and leave stubs for macro, as I'm not sure if I'll implement it fully yet 56 | */ 57 | 58 | //handle_defines((char*)prog, "tmp.txt"); 59 | 60 | /* Memory Clean Up */ 61 | 62 | if( !dir_flag ){ 63 | free(sys_inc_dir); 64 | } 65 | if( !lib_flag ){ 66 | free(sys_lib_dir); 67 | } 68 | } 69 | 70 | char *handle_defines(char* prog, char *filename) 71 | { 72 | char c; 73 | int j; 74 | char *def_keyword; 75 | char *def_name; 76 | char *def_value; 77 | 78 | char *def_name_tmp; 79 | int paren_flag = FALSE; 80 | 81 | /* create preprocessor symbol table here */ 82 | symbol_table *defines_stab = create_stab("Preprocessor", MAX_SLOTS); 83 | 84 | FILE *i = fopen(filename, "r"); 85 | 86 | /* This bit handles the defines */ 87 | while( (c = getc(i)) != EOF ){ 88 | if( c == '#' && (tolower(fcpeek(i)) == 'd') ) { 89 | def_keyword = getword(i); 90 | def_name = getword(i); 91 | 92 | /* does the first macro-word have '(' ? */ 93 | /* If so then: */ 94 | /* 95 | if(strchr(def_name, '(')){ 96 | def_name_tmp = getword(i); 97 | while(!strchr(def_name_tmp, ')')){ 98 | strcat(def_name, def_name_tmp); 99 | free(def_name_tmp); 100 | def_name_tmp = getword(i); 101 | } 102 | strcat(def_name, def_name_tmp); 103 | free(def_name_tmp); 104 | }*/ 105 | 106 | def_value = getword(i); 107 | 108 | stab_insert(filename, get_record(def_name, def_value, 't', 0, "Global"), defines_stab ); 109 | 110 | free(def_keyword); 111 | free(def_name); 112 | free(def_value); 113 | } 114 | 115 | 116 | 117 | } 118 | 119 | //print_stab(defines_stab); 120 | /* This bit handles the defines */ 121 | 122 | 123 | 124 | return NULL; 125 | } 126 | 127 | void include_headers(const char *prog, const char *ifilename, const char *ofilename) 128 | { 129 | char c; /**> Top level character stream container. Holds the characters of ifilename. */ 130 | char c_inc; /**> Nested character stream container. Holds the characters of the included files to write. */ 131 | char *inc_fname; /**> This is the stripped include file name. */ 132 | char *inc_keyword; /**> This is for debugging, holds the include keyword file read so far. */ 133 | char *full_filename; /**> This represents the directory (is_it_system?) and filename concatenated. */ 134 | char *fname; 135 | char *file_path; /**> Holds the full pathname.*/ 136 | 137 | int is_it_system = FALSE; /**> (is it system files?) Just a flag to specify system vs. user files. */ 138 | 139 | FILE *includes; /**> Input file stream for all include files to be inserted. */ 140 | 141 | 142 | 143 | FILE *i = fopen(ifilename, "r"); 144 | FILE *o = fopen(ofilename, "w"); 145 | 146 | if(!i) 147 | file_error((char*)prog, "open", (char*)ifilename, "for inserting include headers", "No such file or directory"); 148 | if(!o) 149 | file_error((char*)prog, "write", (char*)ofilename, "for inserting include headers(preproc intermediate file)\n", "Unknown reason."); 150 | 151 | 152 | /* Here we write out the included file to the intermediary preprocessor file */ 153 | while( (c = getc(i)) != EOF ){ 154 | if( c == '\n' ){ 155 | total_newlines++; 156 | } 157 | if(c == '#' && (fcpeek(i) == 'i')){ 158 | 159 | inc_keyword = getword(i); 160 | full_filename = getword(i); 161 | 162 | /* Here, we determine if the include file is a system file, or user defined */ 163 | if(full_filename && full_filename[0] == '<') 164 | is_it_system = TRUE; 165 | else if (full_filename && full_filename[0] == '"') 166 | is_it_system = FALSE; 167 | 168 | inc_fname = (char*)get_inc_fname(full_filename); 169 | /* 170 | printf("%s :\n", inc_keyword); 171 | printf("'%s' :\n", inc_fname); 172 | printf("Is it system file? %s\n\n", ((is_it_system)? "Yes": "No")); 173 | */ 174 | if(is_it_system){ 175 | file_path = (char*)xmalloc(sizeof(char)* (strlen(sys_inc_dir) + strlen(inc_fname) + 1)); 176 | strcpy(file_path, sys_inc_dir); 177 | strcat(file_path, inc_fname); 178 | strcat(file_path, "\0"); 179 | } 180 | else if(!is_it_system){ 181 | file_path = (char*)xmalloc(sizeof(char)* (strlen(sys_inc_dir) + 3)); 182 | strcpy(file_path, "./"); 183 | strcat(file_path, inc_fname); 184 | strcat(file_path, "\0"); 185 | } 186 | 187 | /* 188 | printf("Full Path: %s\n", file_path); 189 | */ 190 | 191 | includes = fopen(file_path, "r"); 192 | 193 | if (!includes){ 194 | file_error((char*)prog, "open", (char*)file_path, "While doing header inclusions", "No such file or directory"); 195 | } 196 | 197 | while ( (c_inc = getc(includes)) != EOF ) { 198 | putc(c_inc, o); 199 | } 200 | 201 | fclose(includes); 202 | 203 | 204 | free(inc_keyword); 205 | free(inc_fname); 206 | //free(fname); 207 | 208 | 209 | c = getc(i); /* We need to pop this off c (since it's the '#' character) from the 210 | * if conditional above. Then it is safe to write out. */ 211 | } 212 | putc(c, o); 213 | } 214 | 215 | 216 | fclose(i); 217 | fclose(o); 218 | } 219 | 220 | char *get_inc_fname(char *n) 221 | { 222 | int i; 223 | size_t size = strlen(n); 224 | char *new_word = (char*)xmalloc(sizeof(char)*(size-2)); /* + 1 for the '\0' terminator */ 225 | 226 | 227 | for(i = 0; i < (size-2); i++){ 228 | new_word[i] = n[i+1]; 229 | 230 | } 231 | 232 | new_word[size-2] = '\0'; 233 | free(n); 234 | return new_word; 235 | } 236 | 237 | 238 | void remove_comments(file_struct *file) 239 | { 240 | 241 | FILE *i = fopen(file->filename, "r"); 242 | FILE *o = fopen(INTERIM_FILENAME, "w"); 243 | 244 | if(!i) 245 | file_error((char*)file->calling_prog, 246 | "open", 247 | (char*)file->filename, 248 | "for removing comments", "No such file or directory."); 249 | if(!o) 250 | file_error((char*)file->calling_prog, 251 | "write", 252 | (char*)file->filename, 253 | "preproc intermediate file", 254 | "Unknown reason(possibly permissions"); 255 | 256 | /* This code handles the multiline comments removal */ 257 | char c, c_tmp; 258 | 259 | while ( (c = getc(i)) != EOF ){ 260 | 261 | if( c == '\n' ){ 262 | total_newlines++; 263 | } 264 | 265 | if(c == '/' && (fcpeek(i) == '*')){ 266 | 267 | c = getc(i); /* Holds '*' */ 268 | c = getc(i); /* Knock that starter '*' off the file discriptor. */ 269 | while( c != EOF ){ 270 | if( c == '\n' ){ 271 | total_newlines++; 272 | } 273 | if( c == '/' && (fcpeek(i) == '*')){ 274 | remove(INTERIM_FILENAME); 275 | error(file->filename, total_newlines, 0, "Cannot nest comments!\n"); 276 | } 277 | if( c == '*' && fcpeek(i) == '/' ) 278 | break; 279 | 280 | c = getc(i); 281 | } 282 | 283 | c = getc(i); /* Pop off the last '*' */ 284 | c = getc(i); /* Pop off the last '/' */ 285 | 286 | /* Why am I doing the below again? Crap, I show really comment my code...*/ 287 | /*if (c == '\n'){ 288 | c = getc(i); 289 | 290 | }*/ 291 | } 292 | putc(c, o); 293 | } 294 | 295 | fclose(i); 296 | fclose(o); 297 | 298 | //remove(file->filename); 299 | //rename("data.tmp", file->filename); 300 | } 301 | 302 | 303 | 304 | -------------------------------------------------------------------------------- /src/compiler/preprocessor.h: -------------------------------------------------------------------------------- 1 | /** \file preprocessor.h 2 | \brief Preprocessor defines all the operations necessary for the first pass in the compiler. 3 | */ 4 | 5 | #ifndef _PREPROCESSOR_H_ 6 | #define _PREPROCESSOR_H_ 7 | 8 | #include 9 | #include 10 | #include 11 | 12 | #include "utils.h" 13 | #include "symbol.h" 14 | 15 | /* First Pass */ 16 | 17 | #define MAX_PREPROC_IDENT 2 18 | 19 | #define PREPROC_DEFINE 0 20 | #define PREPROC_INCLUDE 1 21 | 22 | #define DEFAULT_INC_DIR "/usr/include/" 23 | #define DEFAULT_LIB_DIR "/usr/lib/" 24 | 25 | 26 | /*------------------------- Globals -------------------------*/ 27 | 28 | char *sys_inc_dir; 29 | char *sys_lib_dir; 30 | 31 | extern size_t total_newlines; 32 | extern file_struct file; 33 | 34 | 35 | 36 | 37 | 38 | 39 | /*------------------- Function Prototypes -------------------*/ 40 | 41 | 42 | /** Runs the preprocessor on the specified file. 43 | */ 44 | void run_preporcessor(file_struct *file); 45 | 46 | /** 47 | */ 48 | void include_headers(const char *prog, const char *ifilename, const char *ofilename); 49 | 50 | 51 | /** This gets the next include name from the #include preprocessor directive. 52 | * It is malloced internally. It _MUST_ be freed after each use. 53 | */ 54 | char *get_inc_fname(char *n); 55 | 56 | /** 57 | */ 58 | char *handle_defines(char *prog, char *filename); 59 | 60 | /** Removes all comments from the import source file, and outputs an intermediary file for 61 | * further processing. At the moment, only handles 1 nested level of inclusion. 62 | */ 63 | void remove_comments(file_struct *file); 64 | 65 | 66 | #endif 67 | -------------------------------------------------------------------------------- /src/compiler/scanner.c: -------------------------------------------------------------------------------- 1 | /** \file scanner.c 2 | \brief Contains all lexical analyzer operations. 3 | */ 4 | 5 | #include "scanner.h" 6 | 7 | symbol_table *string_table; 8 | symbol_table *id_table; 9 | 10 | void run_scanner(file_struct *file) 11 | { 12 | char *word; 13 | int _u = 0; 14 | 15 | /* This is wasteful */ 16 | string_table = create_stab("String Literals", MAX_SLOTS); 17 | id_table = create_stab("ID Symbol Table", MAX_SLOTS); 18 | 19 | /* Dispatcher. Suggested by professor Vulis to eliminate comparison overhead 20 | incurred by switch statement! Very nice. 21 | */ 22 | void (*dispatcher[255])(FILE *o, char *word); 23 | 24 | /* Set everything on the dispatcher to the default job */ 25 | 26 | for(_u = 0; _u < 256; _u++) 27 | dispatcher[_u] = &default_; 28 | 29 | dispatcher['a'] = &a; 30 | dispatcher['b'] = &b; 31 | dispatcher['c'] = &c; 32 | dispatcher['d'] = &d; 33 | dispatcher['e'] = &e; 34 | dispatcher['f'] = &f; 35 | dispatcher['g'] = &g; 36 | dispatcher['i'] = &i; 37 | dispatcher['l'] = &l; 38 | dispatcher['r'] = &r; 39 | dispatcher['s'] = &s; 40 | dispatcher['t'] = &t; 41 | dispatcher['u'] = &u; 42 | dispatcher['v'] = &v; 43 | dispatcher['w'] = &w; 44 | dispatcher['p'] = &p; 45 | dispatcher['{'] = &leftbracket; 46 | dispatcher['}'] = &rightbracket; 47 | dispatcher['('] = &leftparen; 48 | dispatcher[')'] = &rightparen; 49 | dispatcher['['] = &left_sqr_bracket; 50 | dispatcher[']'] = &right_sqr_bracket; 51 | dispatcher['.'] = ˙ 52 | dispatcher[','] = , 53 | dispatcher['!'] = &exclamation; 54 | dispatcher['~'] = &tilda; 55 | dispatcher['+'] = + 56 | dispatcher['-'] = − 57 | dispatcher['*'] = &unary_star; 58 | dispatcher['&'] = &ersand; 59 | dispatcher['/'] = &div_; 60 | dispatcher['%'] = &mod; 61 | dispatcher['<'] = &less; 62 | dispatcher['>'] = &greater; 63 | dispatcher['='] = &equal; 64 | dispatcher['|'] = ∨ 65 | dispatcher['^'] = &xor; 66 | dispatcher['?'] = &question; 67 | dispatcher[':'] = : 68 | dispatcher[';'] = &semicolon; 69 | 70 | FILE *i = fopen(INTERIM_FILENAME, "r"); 71 | FILE *o = fopen("tmp", "w"); 72 | 73 | if( i == NULL ){ 74 | error(file->filename, 0, 0, "Could not open file for processing! Exiting"); 75 | } 76 | 77 | /* getword() returns a string, so a NULL signifies that 78 | * nothing useful was retrieved from the input stream 79 | */ 80 | 81 | while( (word = getword(i)) != NULL ){ 82 | dispatcher[word[0]](o, word); 83 | free(word); 84 | } 85 | 86 | fclose(i); 87 | fclose(o); 88 | remove(INTERIM_FILENAME); 89 | rename("tmp", INTERIM_FILENAME); 90 | 91 | } 92 | 93 | void put_lexeme(FILE *o, char *tk_name, char *tk_value) 94 | { 95 | size_t tk_name_size = strlen(tk_name); 96 | size_t tk_value_size = strlen(tk_value); 97 | 98 | putc('<', o); 99 | fwrite(tk_name, sizeof(char), tk_name_size, o); 100 | putc(',', o); 101 | fwrite(tk_value, sizeof(char), tk_value_size, o); 102 | putc('>', o); 103 | } 104 | 105 | void put_ulexeme(FILE *o, char *tk_name) 106 | { 107 | size_t tk_name_size = strlen(tk_name); 108 | 109 | putc('<', o); 110 | fwrite(tk_name, sizeof(char), tk_name_size, o); 111 | putc('>', o); 112 | } 113 | 114 | 115 | /* NOTE TO SELF: Still need to handle the multiple character 116 | * token extractions!! That is, say, '<<' as opposed to '<' 117 | */ 118 | 119 | char *extract_token(char *word) 120 | { 121 | 122 | switch(word[0]){ 123 | case '{': 124 | return copy_alloced("{"); 125 | case '}': 126 | return copy_alloced("}"); 127 | case '(': 128 | return copy_alloced("("); 129 | case ')': 130 | return copy_alloced(")"); 131 | case ']': 132 | return copy_alloced("]"); 133 | case '[': 134 | return copy_alloced("["); 135 | case '.': 136 | return copy_alloced("."); 137 | case ',': 138 | return copy_alloced(","); 139 | case '!': 140 | if (word[1] == '='){ 141 | return copy_alloced("!="); 142 | } 143 | else 144 | return copy_alloced("!"); 145 | case '~': 146 | if (word[1] == '=') 147 | return copy_alloced("~="); 148 | else 149 | return copy_alloced("~"); 150 | case '+': 151 | if (word[1] == '+') 152 | return copy_alloced("++"); 153 | else if (word[1] == '=') 154 | return copy_alloced("+="); 155 | else 156 | return copy_alloced("+"); 157 | case '-': 158 | if (word[1] == '-') 159 | return copy_alloced("--"); 160 | else if (word[1] == '=') 161 | return copy_alloced("-="); 162 | else 163 | return copy_alloced("-"); 164 | case '*': 165 | if(word[1] == '=') 166 | return copy_alloced("*="); 167 | else 168 | return copy_alloced("*"); 169 | 170 | case '&': 171 | if(word[1] == '&') 172 | return copy_alloced("&&"); 173 | else if (word[1] == '=') 174 | return copy_alloced("&="); 175 | else 176 | return copy_alloced("&"); 177 | 178 | case '/': 179 | if(word[0] == '=') 180 | return copy_alloced("/="); 181 | else 182 | return copy_alloced("/"); 183 | 184 | case '%': 185 | if( word[1] == '=' ) 186 | return copy_alloced("%="); 187 | else 188 | return copy_alloced("%"); 189 | 190 | case '<': 191 | if( word[1] == '<' ){ 192 | if (word[2] == '=') 193 | return copy_alloced("<<="); 194 | else 195 | return copy_alloced("<<"); 196 | } 197 | else if (word[1] == '=') 198 | return copy_alloced("<="); 199 | else 200 | return copy_alloced("<"); 201 | 202 | case '>': 203 | if( word[1] == '>' ){ 204 | if (word[2] == '=') 205 | return copy_alloced(">>="); 206 | else 207 | return copy_alloced(">>"); 208 | } 209 | else if (word[1] == '=') 210 | return copy_alloced(">="); 211 | else 212 | return copy_alloced(">"); 213 | 214 | case '=': 215 | if( word[1] == '=' ) 216 | return copy_alloced("=="); 217 | else 218 | return copy_alloced("="); 219 | case '|': 220 | if (word[1] == '|') 221 | return copy_alloced("||"); 222 | else if (word[1] == '=') 223 | return copy_alloced("|="); 224 | else 225 | return copy_alloced("|"); 226 | case '^': 227 | if (word[1] == '=') 228 | return copy_alloced("^="); 229 | else 230 | return copy_alloced("^"); 231 | case '?': 232 | return copy_alloced("?"); 233 | case ':': 234 | return copy_alloced(":"); 235 | case ';': 236 | return copy_alloced(";"); 237 | 238 | /* Constants */ 239 | 240 | case '\'': 241 | return return_char(word); 242 | /* String Literals */ 243 | /* Questioning if this even belongs here?*/ 244 | case '"': 245 | return return_string(word); 246 | break; 247 | 248 | default: 249 | if( isdigit(word[0]) ){ 250 | return return_integral(word); 251 | } 252 | else { 253 | return return_keyword(word); 254 | } 255 | break; 256 | } 257 | return NULL; 258 | } 259 | 260 | char *return_char(char *word) 261 | { 262 | int i, j; 263 | size_t size = strlen(word); 264 | char *tmp; 265 | for(i = 1; i < size; i++){ 266 | if( word[i] == '\'' ){ 267 | i++; 268 | break; 269 | } 270 | } 271 | 272 | tmp = (char*)xmalloc(sizeof(char)*i + 1); 273 | 274 | for(j = 0; j < i; j++){ 275 | tmp[j] = word[j]; 276 | } 277 | 278 | tmp[i] = '\0'; 279 | if(strlen(tmp) > 3){ 280 | error("unknown-file", total_newlines, 0, "Bad character literal!\n"); 281 | } 282 | 283 | return tmp; 284 | } 285 | 286 | char *return_integral(char *word) 287 | { 288 | int i, j; 289 | size_t size = strlen(word); 290 | 291 | for(i = 0; i < size; i++){ 292 | if( !isdigit(word[i]) && word[i] != '.' ){ 293 | break; 294 | } 295 | } 296 | 297 | char *integral = (char*)xmalloc(sizeof(char)* i + 1); 298 | 299 | for(j = 0; j < i; j++){ 300 | integral[j] = word[j]; 301 | } 302 | integral[i] = '\0'; 303 | return integral; 304 | } 305 | 306 | char *return_string(char *word) 307 | { 308 | int i, j; 309 | size_t size = strlen(word); 310 | char *tmp; 311 | 312 | for(i = 1; i < size; i++){ 313 | if( word[i] == '"' ){ 314 | i++; 315 | break; 316 | } 317 | } 318 | tmp = (char*)xmalloc(sizeof(char)*i + 1); 319 | 320 | for(j = 0; j < i; j++){ 321 | tmp[j] = word[j]; 322 | } 323 | tmp[i] = '\0'; 324 | 325 | return tmp; 326 | } 327 | 328 | char *return_keyword(char *word) 329 | { 330 | if (word == NULL){ 331 | return NULL; 332 | } 333 | 334 | size_t size = strlen(word); 335 | int i; 336 | for(i = 0; i < size; i++){ 337 | if( !isdigit(word[i]) && !isalpha(word[i]) && word[i] != '_'){ 338 | break; 339 | } 340 | } 341 | /* 'i' is the size of the valid keyword or id */ 342 | char *keyword = (char *)xmalloc(sizeof(char)* i + 1); 343 | 344 | strcpy(keyword, word); 345 | keyword[i] = '\0'; 346 | 347 | return keyword; 348 | 349 | } 350 | 351 | int is_valid_id(char *word) 352 | { 353 | size_t size = strlen(word); 354 | int is_valid; 355 | int j; 356 | for(j = 0; j < size; j++){ 357 | if( !isalpha(word[j]) && !isdigit(word[j]) && word[j] != '_' ){ 358 | return FALSE; 359 | } 360 | } 361 | return TRUE; 362 | } 363 | 364 | int parse_tokens(FILE *o, char *word) 365 | { 366 | int index; /**> Used for the hash return value */ 367 | size_t n, m; 368 | char *token = extract_token(word); 369 | char *tmp; 370 | size_t tk_size = strlen(token); 371 | size_t word_size = strlen(word); 372 | size_t diff = word_size - tk_size; 373 | size_t upto = tk_size; 374 | 375 | token_package tk; 376 | 377 | while(tk_size > 0){ 378 | tmp = (char*)xmalloc(sizeof(char)*diff + 1); 379 | 380 | for(n = 0, m = upto; n < diff; n++, m++){ 381 | tmp[n] = word[m]; 382 | } 383 | tmp[diff] = '\n'; 384 | 385 | tk = get_sval(token); 386 | 387 | if (tk.type == -1){ 388 | sprintf(tk_buffer0, "%d", tk.val); 389 | put_ulexeme(o, tk_buffer0); 390 | } 391 | else if (tk.type == TK_KEYWORD) { 392 | 393 | // Switching from to only 394 | sprintf(tk_buffer0, "%d", tk.val); 395 | 396 | put_ulexeme(o, tk_buffer0); 397 | } 398 | else if (tk.type == TK_IDENTIFIER) { 399 | 400 | record *rec = (record*)get_record(token, "NULL", 'V', 0, "\0"); 401 | rec->addr = -1; 402 | 403 | index = hash(token, id_table->size); 404 | 405 | if (id_table->table[index].slot != EMPTY_SLOT){ 406 | free(rec); 407 | } 408 | else { 409 | stab_insert("symbol", rec, id_table); 410 | } 411 | 412 | sprintf(tk_buffer0, "%d", TK_IDENTIFIER); 413 | sprintf(tk_buffer1, "%d", index); 414 | put_lexeme(o, tk_buffer0, tk_buffer1); 415 | } 416 | else if (tk.type == TK_STRINGLIT) { 417 | 418 | record *rec = (record*)get_record(token, "NULL", 'S', 0, "\0"); 419 | stab_insert("c-string-literal", rec, string_table); 420 | index = hash(rec->name, string_table->size); 421 | /* If there are any collisions, the we just ignore those. I 422 | * output the slot number of the hash, and the TK_STRINLIT token 423 | */ 424 | 425 | sprintf(tk_buffer0, "%d", TK_STRINGLIT); 426 | sprintf(tk_buffer1, "%d", index); 427 | 428 | put_lexeme(o, tk_buffer0, tk_buffer1); 429 | } 430 | 431 | else if (tk.type == TK_INTLIT) { 432 | sprintf(tk_buffer0, "%d", TK_INTLIT); 433 | sprintf(tk_buffer1, "%d", tk.val); 434 | put_lexeme(o, tk_buffer0, tk_buffer1); 435 | } 436 | else if (tk.type == TK_FLOATLIT) { 437 | sprintf(tk_buffer0, "%d", TK_FLOATLIT); 438 | sprintf(tk_buffer1, "%f", tk.f_val); 439 | put_lexeme(o, tk_buffer0, tk_buffer1); 440 | } 441 | 442 | if(token != NULL){ 443 | free(token); 444 | } 445 | token = extract_token(tmp); 446 | tk_size = strlen(token); 447 | 448 | upto += tk_size; 449 | diff = word_size - upto; 450 | 451 | 452 | /* HUGE BUG HERE, I cannot figure out why it keeps crashing on this free call 453 | I've solved the problem by introducing another bug. There is memory leaking here */ 454 | /* 455 | if(tmp != NULL){ 456 | printf("tmp_value: %x\n", tmp[0]); 457 | 458 | tmp = NULL; 459 | }*/ 460 | free(tmp); 461 | 462 | } 463 | return 0; 464 | 465 | } 466 | 467 | token_package get_sval(char *s) 468 | { 469 | token_package tk; 470 | 471 | if( !strcmp(s, "{") ){ 472 | tk.type = -1; 473 | tk.val = TK_LEFTBRACKET; 474 | } 475 | else if( !strcmp(s, "}") ){ 476 | tk.type = -1; 477 | tk.val = TK_RIGHTBRACKET; 478 | } 479 | else if( !strcmp(s, "(") ){ 480 | tk.type = -1; 481 | tk.val = TK_LEFTPAREN; 482 | } 483 | else if( !strcmp(s, ")") ){ 484 | tk.type = -1; 485 | tk.val = TK_RIGHTPAREN; 486 | } 487 | else if( !strcmp(s, "[") ){ 488 | tk.type = -1; 489 | tk.val = TK_LEFT_SQR_BRACKET; 490 | } 491 | else if( !strcmp(s, "]") ){ 492 | tk.type = -1; 493 | tk.val = TK_RIGHT_SQR_BRACKET; 494 | } 495 | else if( !strcmp(s, ".") ){ 496 | tk.type = -1; 497 | tk.val = TK_DOT; 498 | } 499 | else if( !strcmp(s, "!") ){ 500 | tk.type = -1; 501 | tk.val = TK_UNARY_EXCLAMATION; 502 | } 503 | else if( !strcmp(s, "~") ){ 504 | tk.type = -1; 505 | tk.val = TK_UNARY_TILDA; 506 | } 507 | else if( !strcmp(s, "++") ){ 508 | tk.type = -1; 509 | tk.val = TK_UNARY_PLUSPLUS; 510 | } 511 | else if( !strcmp(s, "--") ){ 512 | tk.type = -1; 513 | tk.val = TK_UNARY_MINUSMINUS; 514 | } 515 | else if( !strcmp(s, "+") ){ 516 | tk.type = -1; 517 | tk.val = TK_PLUS; 518 | } 519 | else if( !strcmp(s, "-") ){ 520 | tk.type = -1; 521 | tk.val = TK_MINUS; 522 | } 523 | else if( !strcmp(s, "*") ){ 524 | tk.type = -1; 525 | tk.val = TK_MULT_STAR; 526 | } 527 | else if( !strcmp(s, "&") ){ 528 | tk.type = -1; 529 | tk.val = TK_UNARY_AMPERSAND; 530 | } 531 | else if( !strcmp(s, "/") ){ 532 | tk.type = -1; 533 | tk.val = TK_DIV; 534 | } 535 | else if( !strcmp(s, "%") ){ 536 | tk.type = -1; 537 | tk.val = TK_MOD; 538 | } 539 | else if( !strcmp(s, "<<") ){ 540 | tk.type = -1; 541 | tk.val = TK_LEFT_SHIFT; 542 | } 543 | else if( !strcmp(s, ">>") ){ 544 | tk.type = -1; 545 | tk.val = TK_RIGHT_SHIFT; 546 | } 547 | else if( !strcmp(s, "<") ){ 548 | tk.type = -1; 549 | tk.val = TK_LESS_LOGIC; 550 | } 551 | else if( !strcmp(s, ">") ){ 552 | tk.type = -1; 553 | tk.val = TK_GREATER_LOGIC; 554 | } 555 | else if( !strcmp(s, ">=") ){ 556 | tk.type = -1; 557 | tk.val = TK_GREATER_EQU_LOGIC; 558 | } 559 | else if( !strcmp(s, "<=") ){ 560 | tk.type = -1; 561 | tk.val = TK_LESS_EQU_LOGIC; 562 | } 563 | else if( !strcmp(s, "==") ){ 564 | tk.type = -1; 565 | tk.val = TK_EQU_EQU_LOGIC; 566 | } 567 | else if( !strcmp(s, "!=") ){ 568 | tk.type = -1; 569 | tk.val = TK_NOT_EQU_LOGIC; 570 | } 571 | else if( !strcmp(s, "^") ){ 572 | tk.type = -1; 573 | tk.val = TK_BIT_XOR; 574 | } 575 | else if( !strcmp(s, "|") ){ 576 | tk.type = -1; 577 | tk.val = TK_BIT_OR; 578 | } 579 | else if( !strcmp(s, "&&") ){ 580 | tk.type = -1; 581 | tk.val = TK_LOGIC_AND; 582 | } 583 | else if( !strcmp(s, "||") ){ 584 | tk.type = -1; 585 | tk.val = TK_LOGIC_OR; 586 | } 587 | else if( !strcmp(s, "?") ){ 588 | tk.type = -1; 589 | tk.val = TK_QUESTION; 590 | } 591 | else if( !strcmp(s, ":") ){ 592 | tk.type = -1; 593 | tk.val = TK_COLON; 594 | } 595 | else if( !strcmp(s, ";") ){ 596 | tk.type = -1; 597 | tk.val = TK_SEMICOLON; 598 | } 599 | else if( !strcmp(s, "=") ){ 600 | tk.type = -1; 601 | tk.val = TK_EQU; 602 | } 603 | else if( !strcmp(s, "+=") ){ 604 | tk.type = -1; 605 | tk.val = TK_PLUS_EQU; 606 | } 607 | else if( !strcmp(s, "-=") ){ 608 | tk.type = -1; 609 | tk.val = TK_MINUS_EQU; 610 | } 611 | else if( !strcmp(s, "*=") ){ 612 | tk.type = -1; 613 | tk.val = TK_STAR_EQU; 614 | } 615 | else if( !strcmp(s, "/=") ){ 616 | tk.type = -1; 617 | tk.val = TK_DIV_EQU; 618 | } 619 | else if( !strcmp(s, "%=") ){ 620 | tk.type = -1; 621 | tk.val = TK_MOD_EQU; 622 | } 623 | else if( !strcmp(s, "&=") ){ 624 | tk.type = -1; 625 | tk.val = TK_AND_EQU; 626 | } 627 | else if( !strcmp(s, "^=") ){ 628 | tk.type = -1; 629 | tk.val = TK_XOR_EQU; 630 | } 631 | else if( !strcmp(s, "|=") ){ 632 | tk.type = -1; 633 | tk.val = TK_OR_EQU; 634 | } 635 | else if( !strcmp(s, "<=") ){ 636 | tk.type = -1; 637 | tk.val = TK_LSHIFT_EQU; 638 | } 639 | else if( !strcmp(s, ">=") ){ 640 | tk.type = -1; 641 | tk.val = TK_RSHIFT_EQU; 642 | } 643 | /*** NEW AND NOT COMPLETE ****/ 644 | else if( !strcmp(s, "<<=") ){ 645 | tk.type = -1; 646 | tk.val = TK_LSHIFT_EQU; 647 | } 648 | else if( !strcmp(s, ">>=") ){ 649 | tk.type = -1; 650 | tk.val = TK_RSHIFT_EQU; 651 | } 652 | 653 | /*** NEW AND NOT COMPLETE END ***/ 654 | else if( !strcmp(s, ",") ){ 655 | tk.type = -1; 656 | tk.val = TK_COMMA; 657 | } 658 | else if( !strcmp(s, "") ){ 659 | tk.type = -1; 660 | tk.val = TK_LEFTPAREN; 661 | } 662 | else if( !strcmp(s, ")") ){ 663 | tk.type = -1; 664 | tk.val = TK_RIGHTPAREN; 665 | } 666 | else if( !strcmp(s, "auto") ){ 667 | tk.type = TK_KEYWORD; 668 | tk.val = TK_AUTO; 669 | } 670 | else if( !strcmp(s, "break") ){ 671 | tk.type = TK_KEYWORD; 672 | tk.val = TK_BREAK; 673 | } 674 | else if( !strcmp(s, "case") ){ 675 | tk.type = TK_KEYWORD; 676 | tk.val = TK_CASE; 677 | } 678 | else if( !strcmp(s, "char") ){ 679 | tk.type = TK_KEYWORD; 680 | tk.val = TK_CHAR; 681 | } 682 | else if( !strcmp(s, "const") ){ 683 | tk.type = TK_KEYWORD; 684 | tk.val = TK_CONST; 685 | } 686 | else if( !strcmp(s, "continue") ){ 687 | tk.type = TK_KEYWORD; 688 | tk.val = TK_CONTINUE; 689 | } 690 | else if( !strcmp(s, "default") ){ 691 | tk.type = TK_KEYWORD; 692 | tk.val = TK_DEFAULT; 693 | } 694 | else if( !strcmp(s, "do") ){ 695 | tk.type = TK_KEYWORD; 696 | tk.val = TK_DO; 697 | } 698 | else if( !strcmp(s, "double") ){ 699 | tk.type = TK_KEYWORD; 700 | tk.val = TK_DOUBLE; 701 | } 702 | else if( !strcmp(s, "else") ){ 703 | tk.type = TK_KEYWORD; 704 | tk.val = TK_ELSE; 705 | } 706 | else if( !strcmp(s, "enum") ){ 707 | tk.type = TK_KEYWORD; 708 | tk.val = TK_ENUM; 709 | } 710 | else if( !strcmp(s, "extern") ){ 711 | tk.type = TK_KEYWORD; 712 | tk.val = TK_EXTERN; 713 | } 714 | else if( !strcmp(s, "float") ){ 715 | tk.type = TK_KEYWORD; 716 | tk.val = TK_FLOAT; 717 | } 718 | else if( !strcmp(s, "for") ){ 719 | tk.type = TK_KEYWORD; 720 | tk.val = TK_FOR; 721 | } 722 | else if( !strcmp(s, "goto") ){ 723 | tk.type = TK_KEYWORD; 724 | tk.val = TK_GOTO; 725 | } 726 | else if( !strcmp(s, "if") ){ 727 | tk.type = TK_KEYWORD; 728 | tk.val = TK_IF; 729 | } 730 | else if( !strcmp(s, "int") ){ 731 | tk.type = TK_KEYWORD; 732 | tk.val = TK_INT; 733 | } 734 | else if( !strcmp(s, "long") ){ 735 | tk.type = TK_KEYWORD; 736 | tk.val = TK_LONG; 737 | } 738 | else if( !strcmp(s, "register") ){ 739 | tk.type = TK_KEYWORD; 740 | tk.val = TK_REGISTER; 741 | } 742 | else if( !strcmp(s, "return") ){ 743 | tk.type = TK_KEYWORD; 744 | tk.val = TK_RETURN; 745 | } 746 | else if( !strcmp(s, "short") ){ 747 | tk.type = TK_KEYWORD; 748 | tk.val = TK_SHORT; 749 | } 750 | else if( !strcmp(s, "signed") ){ 751 | tk.type = TK_KEYWORD; 752 | tk.val = TK_SIGNED; 753 | } 754 | else if( !strcmp(s, "sizeof") ){ 755 | tk.type = TK_KEYWORD; 756 | tk.val = TK_SIZEOF; 757 | } 758 | else if( !strcmp(s, "static") ){ 759 | tk.type = TK_KEYWORD; 760 | tk.val = TK_STATIC; 761 | } 762 | else if( !strcmp(s, "struct") ){ 763 | tk.type = TK_KEYWORD; 764 | tk.val = TK_STRUCT; 765 | } 766 | else if( !strcmp(s, "switch") ){ 767 | tk.type = TK_KEYWORD; 768 | tk.val = TK_SWITCH; 769 | } 770 | else if( !strcmp(s, "typedef") ){ 771 | tk.type = TK_KEYWORD; 772 | tk.val = TK_TYPEDEF; 773 | } 774 | else if( !strcmp(s, "union" ) ){ 775 | tk.type = TK_KEYWORD; 776 | tk.val = TK_UNION; 777 | } 778 | else if( !strcmp(s, "unsigned") ){ 779 | tk.type = TK_KEYWORD; 780 | tk.val = TK_UNSIGNED; 781 | } 782 | else if( !strcmp(s, "void") ){ 783 | tk.type = TK_KEYWORD; 784 | tk.val = TK_VOID; 785 | } 786 | else if( !strcmp(s, "volatile") ){ 787 | tk.type = TK_KEYWORD; 788 | tk.val = TK_VOLATILE; 789 | } 790 | else if( !strcmp(s, "while") ){ 791 | tk.type = TK_KEYWORD; 792 | tk.val = TK_WHILE; 793 | } 794 | else if( !strcmp(s, "printf") ){ 795 | tk.type = TK_KEYWORD; 796 | tk.val = TK_PRINTF; 797 | } 798 | 799 | else { 800 | if( s[0] == '\"'){ 801 | tk.type = TK_STRINGLIT; 802 | tk.val = 0; 803 | } 804 | else if( s[0] == '\''){ 805 | tk.type = TK_INTLIT; 806 | tk.val = extract_char(s); 807 | } 808 | else if( isdigit(s[0]) ){ 809 | int i; 810 | int dot = FALSE; 811 | size_t size = strlen(s); 812 | 813 | for (i = 0; i < size; i++){ 814 | if(s[i] == '.') 815 | dot = TRUE; 816 | else if ( !isdigit(s[i]) ){ 817 | printf("Bad number!!!! Has characters in it\n"); 818 | return tk; 819 | } 820 | } 821 | if(dot == TRUE){ 822 | tk.type = TK_FLOATLIT; 823 | tk.f_val = atof(s); 824 | } 825 | else { 826 | tk.type = TK_INTLIT; 827 | tk.val = atoi(s); 828 | } 829 | } 830 | else { 831 | // Last case, must be a valid id 832 | if( is_valid_id(s) == TRUE){ 833 | tk.type = TK_IDENTIFIER; 834 | tk.val = 0; /* Hash slot */ 835 | } 836 | } 837 | } 838 | return tk; 839 | } 840 | 841 | int extract_char(char *word) 842 | { 843 | /* This looks like it's going to break any minute! */ 844 | size_t size = strlen(word); 845 | char tmp[4]; 846 | sprintf(tmp, "%d", word[1]); 847 | tmp[3] = '\n'; 848 | return atoi(tmp); 849 | } 850 | 851 | /************************* DISPATCH *****************************/ 852 | 853 | void p(FILE *o, char *word) 854 | { 855 | /* printf */ 856 | if( !strcmp(word, "printf") ) { 857 | sprintf(tk_buffer0, "%d", TK_PRINTF); 858 | put_ulexeme(o, tk_buffer0); 859 | } 860 | else { 861 | parse_tokens(o,word); 862 | } 863 | } 864 | 865 | void a(FILE *o, char *word) 866 | { 867 | /* auto */ 868 | if ( !strcmp(word, "auto") ){ 869 | sprintf(tk_buffer0, "%d", TK_AUTO); 870 | put_ulexeme(o, tk_buffer0); 871 | } 872 | else { 873 | parse_tokens(o,word); 874 | } 875 | } 876 | 877 | void b(FILE *o, char *word) 878 | { 879 | /* break */ 880 | if ( !strcmp(word, "break") ){ 881 | sprintf(tk_buffer0, "%d", TK_BREAK); 882 | put_ulexeme(o, tk_buffer0); 883 | } 884 | else { 885 | parse_tokens(o,word); 886 | } 887 | } 888 | void c(FILE *o, char *word) 889 | { 890 | /* case */ 891 | /* char */ 892 | /* const */ 893 | /* continue */ 894 | if( !strcmp(word, "case") ) { 895 | sprintf(tk_buffer0, "%d", TK_CASE); 896 | put_ulexeme(o, tk_buffer0); 897 | } 898 | else if ( !strcmp(word, "char") ){ 899 | sprintf(tk_buffer0, "%d", TK_CHAR); 900 | put_ulexeme(o, tk_buffer0); 901 | 902 | } 903 | else if ( !strcmp(word, "const") ){ 904 | sprintf(tk_buffer0, "%d", TK_CONST); 905 | put_ulexeme(o, tk_buffer0); 906 | } 907 | else if ( !strcmp(word, "continue") ){ 908 | sprintf(tk_buffer0, "%d", TK_CONTINUE); 909 | put_ulexeme(o, tk_buffer0); 910 | } 911 | else { 912 | parse_tokens(o,word); 913 | } 914 | } 915 | void d(FILE *o, char *word) 916 | { 917 | /* default */ 918 | /* do */ 919 | /* double */ 920 | if( !strcmp(word, "default") ) { 921 | sprintf(tk_buffer0, "%d", TK_DEFAULT); 922 | put_ulexeme(o, tk_buffer0); 923 | } 924 | else if ( !strcmp(word, "do") ){ 925 | sprintf(tk_buffer0, "%d", TK_DO); 926 | put_ulexeme(o, tk_buffer0); 927 | } 928 | else if ( !strcmp(word, "double") ){ 929 | sprintf(tk_buffer0, "%d", TK_DOUBLE); 930 | put_ulexeme(o, tk_buffer0); 931 | } 932 | else { 933 | parse_tokens(o,word); 934 | } 935 | } 936 | void e(FILE *o, char *word) 937 | { 938 | /* else */ 939 | /* enum */ 940 | /* extern */ 941 | if( !strcmp(word, "else") ) { 942 | sprintf(tk_buffer0, "%d", TK_ELSE); 943 | put_ulexeme(o, tk_buffer0); 944 | } 945 | else if ( !strcmp(word, "enum") ){ 946 | sprintf(tk_buffer0, "%d", TK_ENUM); 947 | put_ulexeme(o, tk_buffer0); 948 | } 949 | else if ( !strcmp(word, "extern") ){ 950 | sprintf(tk_buffer0, "%d", TK_EXTERN); 951 | put_ulexeme(o, tk_buffer0); 952 | } 953 | else { 954 | parse_tokens(o,word); 955 | } 956 | } 957 | 958 | void f(FILE *o, char *word) 959 | { 960 | /* float */ 961 | /* for */ 962 | if( !strcmp(word, "float") ) { 963 | sprintf(tk_buffer0, "%d", TK_FLOAT); 964 | put_ulexeme(o, tk_buffer0); 965 | } 966 | else if ( !strcmp(word, "for") ){ 967 | sprintf(tk_buffer0, "%d", TK_FOR); 968 | put_ulexeme(o, tk_buffer0); 969 | } 970 | else { 971 | parse_tokens(o,word); 972 | } 973 | } 974 | 975 | void g(FILE *o, char *word) 976 | { 977 | /* goto */ 978 | if( !strcmp(word, "goto") ) { 979 | sprintf(tk_buffer0, "%d", TK_GOTO); 980 | put_ulexeme(o, tk_buffer0); 981 | } 982 | else { 983 | parse_tokens(o,word); 984 | } 985 | } 986 | void i(FILE *o, char *word) 987 | { 988 | /* int */ 989 | /* if */ 990 | 991 | if( !strcmp(word, "int") ) { 992 | sprintf(tk_buffer0, "%d", TK_INT); 993 | put_ulexeme(o, tk_buffer0); 994 | } 995 | else if ( !strcmp(word, "if") ){ 996 | sprintf(tk_buffer0, "%d", TK_IF); 997 | put_ulexeme(o, tk_buffer0); 998 | } 999 | else { 1000 | 1001 | parse_tokens(o,word); 1002 | } 1003 | } 1004 | void l(FILE *o, char *word) 1005 | { 1006 | 1007 | /* long */ 1008 | if( !strcmp(word, "long") ) { 1009 | sprintf(tk_buffer0, "%d", TK_LONG); 1010 | put_ulexeme(o, tk_buffer0); 1011 | } 1012 | else { 1013 | parse_tokens(o,word); 1014 | } 1015 | } 1016 | void r(FILE *o, char *word) 1017 | { 1018 | /* register */ 1019 | /* return */ 1020 | if( !strcmp(word, "register") ) { 1021 | sprintf(tk_buffer0, "%d", TK_REGISTER); 1022 | put_ulexeme(o, tk_buffer0); 1023 | } 1024 | else if ( !strcmp(word, "return") ){ 1025 | sprintf(tk_buffer0, "%d", TK_RETURN); 1026 | put_ulexeme(o, tk_buffer0); 1027 | } 1028 | else { 1029 | parse_tokens(o,word); 1030 | } 1031 | } 1032 | void s(FILE *o, char *word) 1033 | { 1034 | /* short */ 1035 | /* signed */ 1036 | /* sizeof */ 1037 | /* static */ 1038 | /* struct */ 1039 | /* switch */ 1040 | 1041 | if( !strcmp(word, "short") ) { 1042 | sprintf(tk_buffer0, "%d", TK_SHORT); 1043 | put_ulexeme(o, tk_buffer0); 1044 | } 1045 | else if ( !strcmp(word, "signed") ){ 1046 | sprintf(tk_buffer0, "%d", TK_SIGNED); 1047 | put_ulexeme(o, tk_buffer0); 1048 | } 1049 | else if ( !strcmp(word, "sizeof") ){ 1050 | sprintf(tk_buffer0, "%d", TK_SIZEOF); 1051 | put_ulexeme(o, tk_buffer0); 1052 | } 1053 | else if ( !strcmp(word, "static") ){ 1054 | sprintf(tk_buffer0, "%d", TK_STATIC); 1055 | put_ulexeme(o, tk_buffer0); 1056 | } 1057 | else if ( !strcmp(word, "struct") ){ 1058 | sprintf(tk_buffer0, "%d", TK_STRUCT); 1059 | put_ulexeme(o, tk_buffer0); 1060 | } 1061 | else if ( !strcmp(word, "switch") ){ 1062 | sprintf(tk_buffer0, "%d", TK_SWITCH); 1063 | put_ulexeme(o, tk_buffer0); 1064 | } 1065 | else { 1066 | parse_tokens(o,word); 1067 | } 1068 | } 1069 | 1070 | void t(FILE *o, char *word) 1071 | { 1072 | /* typedef */ 1073 | if( !strcmp(word, "typedef") ) { 1074 | sprintf(tk_buffer0, "%d", TK_TYPEDEF); 1075 | put_ulexeme(o, tk_buffer0); 1076 | } 1077 | else { 1078 | parse_tokens(o,word); 1079 | } 1080 | } 1081 | void u(FILE *o, char *word) 1082 | { 1083 | /* union */ 1084 | /* unsigned */ 1085 | if( !strcmp(word, "union") ) { 1086 | sprintf(tk_buffer0, "%d", TK_UNION); 1087 | put_ulexeme(o, tk_buffer0); 1088 | } 1089 | else if ( !strcmp(word, "unsigned") ){ 1090 | sprintf(tk_buffer0, "%d", TK_UNSIGNED); 1091 | put_ulexeme(o, tk_buffer0); 1092 | } 1093 | else { 1094 | parse_tokens(o,word); 1095 | } 1096 | } 1097 | void v(FILE *o, char *word) 1098 | { 1099 | /* void */ 1100 | /* volatile */ 1101 | if( !strcmp(word, "void") ) { 1102 | sprintf(tk_buffer0, "%d", TK_VOID); 1103 | put_ulexeme(o, tk_buffer0); 1104 | } 1105 | else if ( !strcmp(word, "volatile") ){ 1106 | sprintf(tk_buffer0, "%d", TK_VOLATILE); 1107 | put_ulexeme(o, tk_buffer0); 1108 | } 1109 | else { 1110 | parse_tokens(o,word); 1111 | } 1112 | } 1113 | void w(FILE *o, char *word) 1114 | { 1115 | /* while */ 1116 | if( !strcmp(word, "while") ) { 1117 | sprintf(tk_buffer0, "%d", TK_WHILE); 1118 | put_ulexeme(o, tk_buffer0); 1119 | } 1120 | else { 1121 | parse_tokens(o,word); 1122 | } 1123 | 1124 | } 1125 | void leftbracket(FILE *o, char *word) 1126 | { 1127 | if( !strcmp(word, "{") ) { 1128 | sprintf(tk_buffer0, "%d", TK_LEFTBRACKET); 1129 | put_ulexeme(o, tk_buffer0); 1130 | } 1131 | else { 1132 | parse_tokens(o,word); 1133 | } 1134 | } 1135 | void rightbracket(FILE *o, char *word) 1136 | { 1137 | if( !strcmp(word, "}") ) { 1138 | sprintf(tk_buffer0, "%d", TK_RIGHTBRACKET); 1139 | put_ulexeme(o, tk_buffer0); 1140 | } 1141 | else { 1142 | parse_tokens(o,word); 1143 | } 1144 | } 1145 | 1146 | void leftparen(FILE *o, char *word) 1147 | { 1148 | /* ( */ 1149 | /* (casting) */ 1150 | if( !strcmp(word, "(") ) { 1151 | sprintf(tk_buffer0, "%d", TK_LEFTPAREN); 1152 | put_ulexeme(o, tk_buffer0); 1153 | } 1154 | else { 1155 | parse_tokens(o,word); 1156 | } 1157 | } 1158 | void rightparen(FILE *o, char *word) 1159 | { 1160 | if( !strcmp(word, ")") ) { 1161 | sprintf(tk_buffer0, "%d", TK_RIGHTPAREN); 1162 | put_ulexeme(o, tk_buffer0); 1163 | } 1164 | else { 1165 | parse_tokens(o,word); 1166 | } 1167 | } 1168 | void left_sqr_bracket(FILE *o, char *word) 1169 | { 1170 | if( !strcmp(word, "]") ) { 1171 | sprintf(tk_buffer0, "%d", TK_RIGHT_SQR_BRACKET); 1172 | put_ulexeme(o, tk_buffer0); 1173 | } 1174 | else { 1175 | parse_tokens(o,word); 1176 | } 1177 | } 1178 | void right_sqr_bracket(FILE *o, char *word) 1179 | { 1180 | if( !strcmp(word, "[") ) { 1181 | sprintf(tk_buffer0, "%d", TK_LEFT_SQR_BRACKET); 1182 | put_ulexeme(o, tk_buffer0); 1183 | } 1184 | else { 1185 | parse_tokens(o,word); 1186 | } 1187 | } 1188 | void dot(FILE *o, char *word) 1189 | { 1190 | if( !strcmp(word, ".") ) { 1191 | sprintf(tk_buffer0, "%d", TK_DOT); 1192 | put_ulexeme(o, tk_buffer0); 1193 | } 1194 | else { 1195 | parse_tokens(o,word); 1196 | } 1197 | } 1198 | void comma(FILE *o, char *word) 1199 | { 1200 | 1201 | if( !strcmp(word, ",") ) { 1202 | sprintf(tk_buffer0, "%d", TK_COMMA); 1203 | put_ulexeme(o, tk_buffer0); 1204 | } 1205 | else { 1206 | parse_tokens(o,word); 1207 | } 1208 | } 1209 | void exclamation(FILE *o, char *word) 1210 | { 1211 | 1212 | if( !strcmp(word, "!") ) { 1213 | sprintf(tk_buffer0, "%d", TK_UNARY_EXCLAMATION); 1214 | put_ulexeme(o, tk_buffer0); 1215 | } 1216 | else { 1217 | parse_tokens(o,word); 1218 | } 1219 | } 1220 | void tilda(FILE *o, char *word) 1221 | { 1222 | /* ~ */ 1223 | /* ~= */ 1224 | if( !strcmp(word, "~") ) { 1225 | sprintf(tk_buffer0, "%d", TK_UNARY_TILDA); 1226 | put_ulexeme(o, tk_buffer0); 1227 | } 1228 | else { 1229 | parse_tokens(o,word); 1230 | } 1231 | } 1232 | void plus(FILE *o, char *word) 1233 | { 1234 | /* + */ 1235 | /* ++ */ 1236 | /* += */ 1237 | if( !strcmp(word, "+") ) { 1238 | sprintf(tk_buffer0, "%d", TK_PLUS); 1239 | put_ulexeme(o, tk_buffer0); 1240 | } 1241 | else { 1242 | parse_tokens(o,word); 1243 | } 1244 | } 1245 | void minus(FILE *o, char *word) 1246 | { 1247 | /* - */ 1248 | /* -- */ 1249 | /* -= */ 1250 | if( !strcmp(word, "-") ) { 1251 | sprintf(tk_buffer0, "%d", TK_MINUS); 1252 | put_ulexeme(o, tk_buffer0); 1253 | } 1254 | else { 1255 | parse_tokens(o,word); 1256 | } 1257 | } 1258 | void unary_star(FILE *o, char *word) 1259 | { 1260 | /* * */ 1261 | /* Is it a mult? Is it a dereference? is it a pointer? Is it a santactic sugar? 1262 | these are all questions which must be answered here */ 1263 | /* *= */ 1264 | if( !strcmp(word, "*") ) { 1265 | sprintf(tk_buffer0, "%d", TK_MULT_STAR); 1266 | put_ulexeme(o, tk_buffer0); 1267 | } 1268 | else { 1269 | parse_tokens(o,word); 1270 | } 1271 | } 1272 | void ampersand(FILE *o, char *word) 1273 | { 1274 | /* & */ 1275 | /* && */ 1276 | /* &= */ 1277 | if( !strcmp(word, "&") ) { 1278 | sprintf(tk_buffer0, "%d", TK_BIT_AMPERSAND); 1279 | put_ulexeme(o, tk_buffer0); 1280 | } 1281 | else { 1282 | parse_tokens(o,word); 1283 | } 1284 | } 1285 | void div_(FILE *o, char *word) 1286 | { 1287 | /* / */ 1288 | /* /= */ 1289 | if( !strcmp(word, "/") ) { 1290 | sprintf(tk_buffer0, "%d", TK_DIV); 1291 | put_ulexeme(o, tk_buffer0); 1292 | } 1293 | else { 1294 | parse_tokens(o,word); 1295 | } 1296 | } 1297 | void mod(FILE *o, char *word) 1298 | { 1299 | /* % */ 1300 | /* %= */ 1301 | if( !strcmp(word, "%") ) { 1302 | sprintf(tk_buffer0, "%d", TK_MOD); 1303 | put_ulexeme(o, tk_buffer0); 1304 | } 1305 | else { 1306 | parse_tokens(o,word); 1307 | } 1308 | } 1309 | void less(FILE *o, char *word) 1310 | { 1311 | /* < */ 1312 | /* << */ 1313 | /* <= */ 1314 | /* <<= */ 1315 | if( !strcmp(word, "<") ) { 1316 | sprintf(tk_buffer0, "%d", TK_LESS_LOGIC); 1317 | put_ulexeme(o, tk_buffer0); 1318 | } 1319 | else { 1320 | parse_tokens(o,word); 1321 | } 1322 | } 1323 | void greater(FILE *o, char *word) 1324 | { 1325 | /* > */ 1326 | /* >> */ 1327 | /* >= */ 1328 | /* >>= */ 1329 | if( !strcmp(word, ">") ) { 1330 | sprintf(tk_buffer0, "%d", TK_GREATER_LOGIC); 1331 | put_ulexeme(o, tk_buffer0); 1332 | } 1333 | else { 1334 | parse_tokens(o,word); 1335 | } 1336 | } 1337 | void equal(FILE *o, char *word) 1338 | { 1339 | /* = */ 1340 | /* == */ 1341 | if( !strcmp(word, "=") ) { 1342 | sprintf(tk_buffer0, "%d", TK_EQU); 1343 | put_ulexeme(o, tk_buffer0); 1344 | } 1345 | else { 1346 | parse_tokens(o,word); 1347 | } 1348 | } 1349 | void or(FILE *o, char *word) 1350 | { 1351 | /* | */ 1352 | /* || */ 1353 | /* |= */ 1354 | if( !strcmp(word, "|") ) { 1355 | sprintf(tk_buffer0, "%d", TK_BIT_OR); 1356 | put_ulexeme(o, tk_buffer0); 1357 | } 1358 | else { 1359 | parse_tokens(o,word); 1360 | } 1361 | } 1362 | void xor(FILE *o, char *word) 1363 | { 1364 | /* ^ */ 1365 | /* ^= */ 1366 | if( !strcmp(word, "^") ) { 1367 | sprintf(tk_buffer0, "%d", TK_BIT_XOR); 1368 | put_ulexeme(o, tk_buffer0); 1369 | } 1370 | else { 1371 | parse_tokens(o,word); 1372 | } 1373 | } 1374 | 1375 | 1376 | void question(FILE *o, char *word) 1377 | { 1378 | if( !strcmp(word, "?") ) { 1379 | sprintf(tk_buffer0, "%d", TK_QUESTION); 1380 | put_ulexeme(o, tk_buffer0); 1381 | } 1382 | else { 1383 | parse_tokens(o,word); 1384 | } 1385 | } 1386 | void colon(FILE *o, char *word) 1387 | { 1388 | if( !strcmp(word, ":") ) { 1389 | sprintf(tk_buffer0, "%d", TK_COLON); 1390 | put_ulexeme(o, tk_buffer0); 1391 | } 1392 | else { 1393 | parse_tokens(o,word); 1394 | } 1395 | } 1396 | void semicolon(FILE *o, char *word) 1397 | { 1398 | if( !strcmp(word, ";") ) { 1399 | sprintf(tk_buffer0, "%d", TK_SEMICOLON); 1400 | put_ulexeme(o, tk_buffer0); 1401 | } 1402 | else { 1403 | parse_tokens(o,word); 1404 | } 1405 | } 1406 | 1407 | /* Constants */ 1408 | void constant(FILE *o, char *word) 1409 | { 1410 | } 1411 | 1412 | /* String Literals */ 1413 | void stringlit(FILE *o, char *word) 1414 | { 1415 | } 1416 | 1417 | void default_(FILE *o, char *word) 1418 | { 1419 | /* Try To See if it's a identifier, if not: 1420 | ERROR! Given token is not part of the lang def. */ 1421 | parse_tokens(o, word); 1422 | } 1423 | 1424 | 1425 | -------------------------------------------------------------------------------- /src/compiler/scanner.h: -------------------------------------------------------------------------------- 1 | /** \file scanner.h 2 | * \brief Lists the associativity and precedence of all tokens. 3 | * 4 | * This is done in order of precedence, with the defines at the top with the highest. 5 | * 6 | * The defines here are grouped in order of associativity, and listed 7 | * with descending precedence as we go down. 8 | * 9 | * The rest are token values for keywords and the like. 10 | * 11 | * Everything else normally in a header file comes after. 12 | */ 13 | 14 | #ifndef _SCANNER_H_ 15 | #define _SCANNER_H_ 16 | 17 | #include 18 | #include 19 | #include 20 | #include 21 | 22 | #include "utils.h" 23 | #include "symbol.h" 24 | 25 | #define INTLIT_TABLE_MAX 1000 26 | #define FLOATLIT_TABLE_MAX 1000 27 | #define STRINGLIT_TABLE_MAX 1000 28 | 29 | /* Scope */ 30 | #define TK_LEFTBRACKET 0 31 | #define TK_RIGHTBRACKET 1 32 | 33 | /* Left To Right Associativity */ 34 | #define TK_LEFTPAREN 2 35 | #define TK_RIGHTPAREN 3 36 | #define TK_LEFT_SQR_BRACKET 4 37 | #define TK_RIGHT_SQR_BRACKET 5 38 | #define TK_DOT 6 39 | 40 | /* Right To Left Associativity */ 41 | #define TK_UNARY_EXCLAMATION 7 42 | #define TK_UNARY_TILDA 8 43 | #define TK_UNARY_PLUSPLUS 9 44 | #define TK_UNARY_MINUSMINUS 10 45 | #define TK_UNARY_PLUS 11 46 | #define TK_UNARY_MINUS 12 47 | #define TK_UNARY_STAR 13 48 | #define TK_UNARY_AMPERSAND 14 49 | #define TK_UNARY_CASTING 15 50 | #define TK_UNARY_SIZEOF 16 51 | 52 | /* Left To Right Associativity */ 53 | #define TK_MULT_STAR 17 54 | #define TK_DIV 18 55 | #define TK_MOD 19 56 | 57 | /* Left To Right Associativity */ 58 | #define TK_PLUS 20 59 | #define TK_MINUS 21 60 | 61 | /* Left To Right Associativity */ 62 | #define TK_LEFT_SHIFT 22 63 | #define TK_RIGHT_SHIFT 23 64 | 65 | /* Left To Right Associativity */ 66 | #define TK_LESS_LOGIC 24 67 | #define TK_GREATER_LOGIC 25 68 | #define TK_GREATER_EQU_LOGIC 26 69 | #define TK_LESS_EQU_LOGIC 27 70 | 71 | /* Left To Right Associativity */ 72 | #define TK_EQU_EQU_LOGIC 28 73 | #define TK_NOT_EQU_LOGIC 29 74 | 75 | /* Left To Right Associativity */ 76 | #define TK_BIT_AMPERSAND 30 77 | #define TK_BIT_XOR 31 78 | #define TK_BIT_OR 32 79 | 80 | /* Left To Right Associativity */ 81 | #define TK_LOGIC_AND 33 82 | #define TK_LOGIC_OR 34 83 | 84 | /* Left To Right Associativity */ 85 | #define TK_QUESTION 35 86 | #define TK_COLON 36 87 | 88 | /* Right To Left Associativity */ 89 | #define TK_EQU 37 90 | #define TK_PLUS_EQU 38 91 | #define TK_MINUS_EQU 39 92 | #define TK_STAR_EQU 40 93 | #define TK_DIV_EQU 41 94 | #define TK_MOD_EQU 42 95 | #define TK_AND_EQU 43 96 | #define TK_XOR_EQU 44 97 | #define TK_OR_EQU 45 98 | #define TK_LSHIFT_EQU 46 99 | #define TK_RSHIFT_EQU 47 100 | 101 | /* Left To Right Associativity */ 102 | #define TK_COMMA 48 103 | 104 | /* Precedence and Associative Irrelavent */ 105 | 106 | #define TK_KEYWORD 49 107 | #define TK_IDENTIFIER 50 108 | #define TK_CONSTANT 51 109 | #define TK_STRING 52 110 | 111 | /* ************************************* */ 112 | 113 | /* Keywords/Reserved */ 114 | 115 | #define TK_AUTO 53 116 | #define TK_BREAK 54 117 | #define TK_CASE 55 118 | #define TK_CHAR 56 119 | #define TK_CONST 57 120 | #define TK_CONTINUE 58 121 | #define TK_DEFAULT 59 122 | #define TK_DO 60 123 | #define TK_DOUBLE 61 124 | #define TK_ELSE 62 125 | #define TK_ENUM 63 126 | #define TK_EXTERN 64 127 | #define TK_FLOAT 65 128 | #define TK_FOR 66 129 | #define TK_GOTO 67 130 | #define TK_IF 68 131 | #define TK_INT 69 132 | #define TK_LONG 70 133 | #define TK_REGISTER 71 134 | #define TK_RETURN 72 135 | #define TK_SHORT 73 136 | #define TK_SIGNED 74 137 | #define TK_SIZEOF 75 138 | #define TK_STATIC 76 139 | #define TK_STRUCT 77 140 | #define TK_SWITCH 78 141 | #define TK_TYPEDEF 79 142 | #define TK_UNION 80 143 | #define TK_UNSIGNED 81 144 | #define TK_VOID 82 145 | #define TK_VOLATILE 83 146 | #define TK_WHILE 84 147 | 148 | 149 | #define TK_SEMICOLON 85 150 | #define TK_INTLIT 86 /**> need array for this */ 151 | #define TK_STRINGLIT 87 /**> need a symbol table for this */ 152 | #define TK_FLOATLIT 88 /**> need a symbol table for this too. This is for both float and double */ 153 | 154 | #define TK_LABEL 89 155 | #define TK_FUNCTION_CALL 90 156 | 157 | #define TK_PRINTF 91 158 | 159 | 160 | /*-------------------------Typedefs -------------------------*/ 161 | typedef struct token_package_Tag { 162 | int val; 163 | double f_val; 164 | int type; 165 | } token_package; 166 | /*------------------------- Globals -------------------------*/ 167 | 168 | 169 | extern size_t total_newlines; 170 | 171 | static char tk_buffer0[5]; /**> Used to write the interger values of lexemes below as strings (easier). */ 172 | static char tk_buffer1[5]; 173 | 174 | static size_t intlit_t_counter; 175 | static size_t floatlit_t_counter; 176 | static int intlit_table[INTLIT_TABLE_MAX]; 177 | static double floatlit_table[FLOATLIT_TABLE_MAX]; 178 | 179 | extern symbol_table *string_table; /**> This holds all the string literals*/ 180 | extern symbol_table *id_table; /**>This holds all of the identifier names */ 181 | 182 | /* Token Defininitions */ 183 | 184 | /*------------------------- Globals -------------------------*/ 185 | 186 | size_t total_char; /**> Initialize total character count counter */ 187 | size_t total_char_per_line; 188 | size_t total_newlines; /**> Initialize newlines, to ready counter */ 189 | 190 | /*------------------- Function Prototoypes -------------------*/ 191 | 192 | /** High level scanner encapsulator. 193 | */ 194 | void run_scanner(file_struct *file); 195 | 196 | /** Writes a lexeme out to file, given a name-value pair. 197 | */ 198 | void put_lexeme(FILE *o, char *tk_name, char *tk_value); 199 | 200 | /** Writes a unary lexeme out to file, given a name. 201 | */ 202 | void put_ulexeme(FILE *o, char *tk_name); 203 | 204 | /** Tests if the given word is a valid C symbol, or identifier. 205 | * If false, returns 0, if true returns the size of the identifier. 206 | * This is useful because we can use the size to handle the function 207 | * case, in which an identifier can have '(' directly concatenated (no space) 208 | * with the identifier. (i.e. main() vs main () ) 209 | * 210 | * This function also _RESETS_ the file pointer to where it was at 211 | * the beginning of the call. 212 | */ 213 | int is_valid_id(char *word); 214 | 215 | /** 216 | */ 217 | int parse_tokens(FILE *o, char *word); 218 | 219 | /** 220 | */ 221 | char *extract_token(char *word); 222 | /** _MUST_ be freed. 223 | */ 224 | 225 | char *return_char(char *word); 226 | 227 | /** _MUST_ be freed. 228 | */ 229 | char *return_integral(char *word); 230 | 231 | /** _MUST_ be freed. 232 | */ 233 | 234 | char *return_string(char *word); 235 | 236 | /** _MUST_ be freed. 237 | */ 238 | char *return_keyword(char *word); 239 | 240 | /** 241 | */ 242 | int extract_char(char *word); 243 | 244 | /** 245 | */ 246 | token_package get_sval(char *s); 247 | 248 | /* Jobs prototypes */ 249 | 250 | inline static void a(FILE *o, char *word); 251 | inline static void b(FILE *o, char *word); 252 | inline static void c(FILE *o, char *word); 253 | inline static void d(FILE *o, char *word); 254 | inline static void e(FILE *o, char *word); 255 | inline static void f(FILE *o, char *word); 256 | inline static void g(FILE *o, char *word); 257 | inline static void i(FILE *o, char *word); 258 | inline static void l(FILE *o, char *word); 259 | inline static void r(FILE *o, char *word); 260 | inline static void s(FILE *o, char *word); 261 | inline static void t(FILE *o, char *word); 262 | inline static void p(FILE *o, char *word); 263 | inline static void u(FILE *o, char *word); 264 | inline static void v(FILE *o, char *word); 265 | inline static void w(FILE *o, char *word); 266 | inline static void leftbracket(FILE *o, char *word); 267 | inline static void rightbracket(FILE *o, char *word); 268 | inline static void leftparen(FILE *o, char *word); 269 | inline static void rightparen(FILE *o, char *word); 270 | inline static void left_sqr_bracket(FILE *o, char *word); 271 | inline static void right_sqr_bracket(FILE *o, char *word); 272 | inline static void dot(FILE *o, char *word); 273 | inline static void comma(FILE *o, char *word); 274 | inline static void exclamation(FILE *o, char *word); 275 | inline static void tilda(FILE *o, char *word); 276 | inline static void plus(FILE *o, char *word); 277 | inline static void minus(FILE *o, char *word); 278 | inline static void unary_star(FILE *o, char *word); 279 | inline static void ampersand(FILE *o, char *word); 280 | inline static void div_(FILE *o, char *word); 281 | inline static void mod(FILE *o, char *word); 282 | inline static void less(FILE *o, char *word); 283 | inline static void greater(FILE *o, char *word); 284 | inline static void equal(FILE *o, char *word); 285 | inline static void or(FILE *o, char *word); 286 | inline static void xor(FILE *o, char *word); 287 | inline static void question(FILE *o, char *word); 288 | inline static void colon(FILE *o, char *word); 289 | inline static void semicolon(FILE *o, char *word); 290 | inline static void constant(FILE *o, char *word); 291 | inline static void stringlit(FILE *o, char *word); 292 | inline static void default_(FILE *o, char *word); 293 | 294 | 295 | 296 | 297 | 298 | 299 | #endif 300 | -------------------------------------------------------------------------------- /src/compiler/symbol.c: -------------------------------------------------------------------------------- 1 | /** \file symbol.c 2 | \brief Defines all of the symbol table primitives. 3 | */ 4 | 5 | #include "symbol.h" 6 | 7 | void print_stab(symbol_table *stab) 8 | { 9 | int i; 10 | printf("\n\nCurrent Symbol Table: '%s' \n - Status -\n" 11 | "Total Used: %4d\t Size: %4d\t Load Factor: %4.2f\n" 12 | "\n", stab->t_name, (int)stab->in_use, (int)stab->size, stab->load_factor); 13 | printf("-------\t----\t-----\t----\t-----\n" 14 | "Address\tName\tValue\tSlot\tType\tScope\tIsArray\tArray-Size\n"); 15 | for(i = 0; i < stab->size; i++){ 16 | if( stab->table[i].slot != EMPTY_SLOT ){ 17 | printf("%4d\t%s\t%s\t%d\t%c\t%d\t%c\t%d\n", 18 | stab->table[i].addr, stab->table[i].name, 19 | stab->table[i].value, stab->table[i].slot, 20 | stab->table[i].type, 21 | stab->table[i].scope, 22 | stab->table[i].isarray, 23 | stab->table[i].arraysize); 24 | } 25 | } 26 | } 27 | 28 | size_t hash(char *key, size_t limit) 29 | { 30 | int hash_value = 0; 31 | int i = 0; 32 | size_t size = strlen(key); 33 | 34 | for(i = 0; i < size; i++){ 35 | hash_value = 31*hash_value + key[i]; 36 | } 37 | return (size_t)(hash_value%limit); 38 | } 39 | 40 | symbol_table *create_stab(char* t_name, size_t max) 41 | { 42 | int i; 43 | symbol_table *stab = (symbol_table*)xmalloc(sizeof(symbol_table)*1); 44 | 45 | stab->table = (record*)xmalloc(sizeof(record)*max); 46 | stab->in_use = 0; 47 | stab->load_factor = 0; 48 | stab->size = max; 49 | strcpy(stab->t_name, t_name); 50 | 51 | for(i = 0; i < max; i++){ 52 | stab->table[i].addr = -1; 53 | stab->table[i].slot = EMPTY_SLOT; 54 | stab->table[i].seen = 0; 55 | } 56 | 57 | return stab; 58 | } 59 | 60 | void stab_insert(char* filename, record *rec, symbol_table *stab) 61 | { 62 | size_t index = hash(rec->name, stab->size); 63 | rec->slot = index; 64 | 65 | stab->table[index] = *rec; 66 | stab->in_use++; 67 | stab->load_factor = ((float)stab->in_use) / stab->size; 68 | 69 | } 70 | 71 | record *get_record(char *name, char*val, char type, int slot, char *scope) 72 | { 73 | record *rec = (record*)xmalloc(sizeof(record)*1); 74 | 75 | /* NOTE: I have to purge all these allocations in the freeing of the records! */ 76 | 77 | rec->value = (char*)xmalloc(sizeof(char)*strlen(val)); 78 | 79 | strcpy(rec->name, name); 80 | strcpy(rec->value, val); 81 | rec->type = type; 82 | rec->slot = slot; 83 | rec->scope = 0; 84 | 85 | return rec; 86 | } 87 | 88 | int return_value(symbol_table *stab, int target) 89 | { 90 | return 1; 91 | } 92 | 93 | void purge_record(record *rec) 94 | { 95 | } 96 | 97 | void destroy_stab(symbol_table *stab) 98 | { 99 | } 100 | 101 | int is_keyword(char *lexeme) 102 | { 103 | switch(lexeme[0]){ 104 | case 'a': 105 | /* auto */ 106 | if( !strcmp(lexeme, "auto") ) 107 | return TRUE; 108 | return FALSE; 109 | case 'b': 110 | /* break */ 111 | if( !strcmp(lexeme, "break") ) 112 | return TRUE; 113 | return FALSE; 114 | case 'c': 115 | /* case */ 116 | /* char */ 117 | /* const */ 118 | /* continue */ 119 | if( !strcmp(lexeme, "case") || 120 | !strcmp(lexeme, "char") || 121 | !strcmp(lexeme, "const") || 122 | !strcmp(lexeme, "continue") 123 | ) 124 | return TRUE; 125 | return FALSE; 126 | case 'd': 127 | /* default */ 128 | /* do */ 129 | /* double */ 130 | if( !strcmp(lexeme, "default")|| 131 | !strcmp(lexeme, "do") || 132 | !strcmp(lexeme, "double") 133 | ) 134 | return TRUE; 135 | return FALSE; 136 | case 'e': 137 | /* else */ 138 | /* enum */ 139 | /* extern */ 140 | if( !strcmp(lexeme, "else") || 141 | !strcmp(lexeme, "enum") || 142 | !strcmp(lexeme, "extern") 143 | ) 144 | return TRUE; 145 | return FALSE; 146 | case 'f': 147 | /* float */ 148 | /* for */ 149 | if( !strcmp(lexeme, "float")|| 150 | !strcmp(lexeme, "for") 151 | ) 152 | return TRUE; 153 | return FALSE; 154 | case 'g': 155 | /* goto */ 156 | if( !strcmp(lexeme, "goto") ) 157 | return TRUE; 158 | return FALSE; 159 | 160 | case 'i': 161 | /* int */ 162 | /* if */ 163 | if( !strcmp(lexeme, "int") || 164 | !strcmp(lexeme, "if") 165 | ) 166 | return TRUE; 167 | return FALSE; 168 | case 'l': 169 | /* long */ 170 | if( !strcmp(lexeme, "long") ) 171 | return TRUE; 172 | return FALSE; 173 | case 'r': 174 | /* register */ 175 | /* return */ 176 | if( !strcmp(lexeme, "register")|| 177 | !strcmp(lexeme, "return") 178 | ) 179 | return TRUE; 180 | return FALSE; 181 | case 's': 182 | /* short */ 183 | /* signed */ 184 | /* sizeof */ 185 | /* static */ 186 | /* struct */ 187 | /* switch */ 188 | if( !strcmp(lexeme, "short") || 189 | !strcmp(lexeme, "signed") || 190 | !strcmp(lexeme, "sizeof") || 191 | !strcmp(lexeme, "static") || 192 | !strcmp(lexeme, "struct") || 193 | !strcmp(lexeme, "switch") 194 | ) 195 | return TRUE; 196 | return FALSE; 197 | case 't': 198 | /* typedef */ 199 | if( !strcmp(lexeme, "typedef") ) 200 | return TRUE; 201 | return FALSE; 202 | case 'u': 203 | /* union */ 204 | /* unsigned */ 205 | if( !strcmp(lexeme, "union") || 206 | !strcmp(lexeme, "unsigned") 207 | ) 208 | return TRUE; 209 | return FALSE; 210 | case 'v': 211 | /* void */ 212 | /* volatile */ 213 | if( !strcmp(lexeme, "void") || 214 | !strcmp(lexeme, "volatile") 215 | ) 216 | return TRUE; 217 | return FALSE; 218 | case 'w': 219 | /* while */ 220 | if( !strcmp(lexeme, "while") ) 221 | return TRUE; 222 | return FALSE; 223 | default: 224 | return FALSE; 225 | } 226 | } 227 | 228 | 229 | -------------------------------------------------------------------------------- /src/compiler/symbol.h: -------------------------------------------------------------------------------- 1 | /** \file symbol.h 2 | \brief 3 | */ 4 | 5 | #ifndef _SYMBOL_H_ 6 | #define _SYMBOL_H_ 7 | 8 | #include 9 | #include 10 | #include 11 | #include 12 | 13 | #include "utils.h" /* For TRUE and FALSE constants */ 14 | #include "error.h" /* For reporting ID errors, among other things */ 15 | 16 | #define MAX_SLOTS 10000 /**> Total number of identifiers possible in memory */ 17 | #define EMPTY_SLOT -1 /**> This symbolic constant signifies empty slots in the hash map. */ 18 | 19 | typedef struct record_TAG{ 20 | int addr; 21 | char type; 22 | char name[64]; 23 | char *value; 24 | int slot; /**> Either EMPTY_SLOT or NOT_EMPTY */ 25 | char scope; 26 | int seen; 27 | char isarray; 28 | int arraysize; 29 | char *block_info; 30 | }record; 31 | 32 | typedef struct symbol_table_TAG { 33 | /* Public Fields */ 34 | char t_name[32]; /**> Table identifier. */ 35 | double load_factor; /**> Load factor. If it is > 0.5, it is bad. */ 36 | size_t in_use; /**> How many slots are in use for this one symbol table */ 37 | size_t size; /**> Total Size of the symbol talbe */ 38 | record *table; /**> An array of all the records currently in use. */ 39 | 40 | /* Public Methods */ 41 | } symbol_table; 42 | 43 | /** 44 | */ 45 | void print_stab(symbol_table *stab); 46 | 47 | /** 48 | */ 49 | symbol_table *create_stab(char *t_name, size_t max); 50 | 51 | /** 52 | */ 53 | void stab_insert(char* filename, record *rec, symbol_table *stab); 54 | 55 | /** 56 | */ 57 | record *get_record(char *name, char *val, char type, int slot, char *scope); 58 | 59 | /** 60 | */ 61 | void purge_record(record *rec); 62 | 63 | /** 64 | */ 65 | size_t hash(char *key, size_t limit); 66 | 67 | /** 68 | */ 69 | int is_keyword(char *lexeme); 70 | 71 | /** 72 | */ 73 | int return_value(symbol_table *stab, int target); 74 | 75 | #endif 76 | -------------------------------------------------------------------------------- /src/compiler/utils.c: -------------------------------------------------------------------------------- 1 | /** \file utils.c 2 | \brief 3 | */ 4 | 5 | #include "utils.h" 6 | 7 | void usage( void ) 8 | { 9 | printf("Usage: c [options] file...\n" 10 | "Options:\n" 11 | " --help\tPrint help screen description.\n" 12 | " --version\tPrint version number.\n" 13 | " --verbose\tPrint extra information.\n" 14 | " -o \tSpecify an output file name.\n" 15 | " -Sc \tSpecify the size of the Code Segment (Not Implemented Yet).\n" 16 | " -Sd \tSpecify the size of the Data Segment (Not Implemented Yet).\n" 17 | " -Ss \tSpecify String Symbol Table Hash (Not Implemented Yet).\n" 18 | " -Si \tSpecify ID Symbol Table Hash (Not Implemented Yet).\n" 19 | " -So \tPrint VM Assembly to stdout.\n" 20 | "\n" 21 | ); 22 | } 23 | 24 | void version( void ) 25 | { 26 | printf("c (C Compiler) %s %d (release) %d - Build: %d\n" 27 | "Copyright (c) 2011 Eudis Duran\n" 28 | "See LICENSE file for details.\n" 29 | ,VERSION, get_build_date(), RELEASE, BUILD_NUMBER); 30 | 31 | } 32 | 33 | char *scan_for_o(int argc, char *argv[]) 34 | { 35 | int i; 36 | for(i = 0; i < argc; i++){ 37 | if(strcmp(argv[i], "-o") == 0){ 38 | return argv[i + 1]; 39 | } 40 | } 41 | } 42 | 43 | char **get_files_from_argv(int argc, char *argv[]) 44 | { 45 | 46 | } 47 | 48 | int get_filesize(char *filename) 49 | { 50 | FILE *f = fopen(filename, "r"); 51 | fseek(f, 0, SEEK_END); 52 | return ftell(f); 53 | } 54 | 55 | void *xmalloc(int size) 56 | { 57 | register void *value = malloc(size); 58 | if (value == NULL){ 59 | fprintf(stderr, "Virtual Memory Exhausted!\n"); 60 | exit(1); 61 | } 62 | else { 63 | return value; 64 | } 65 | } 66 | 67 | char fcpeek(FILE *f) 68 | { 69 | char c = getc(f); 70 | ungetc(c, f); 71 | return c; 72 | } 73 | 74 | char *getword(FILE *i) 75 | { 76 | 77 | int j = 0; 78 | char c; 79 | char *word; 80 | int pos; 81 | size_t size = 0; 82 | 83 | if(fcpeek(i) == EOF){ 84 | return NULL; 85 | } 86 | 87 | pos = ftell(i); 88 | c = getc(i); 89 | if( c == '\n' ){ 90 | total_newlines++; 91 | } 92 | 93 | /* We first calculate the size of the word */ 94 | while ( (c != EOF) && !isspace(c) ){ 95 | /* Read and count new lines and characters */ 96 | 97 | /* This new section handles the string word input count*/ 98 | if ( c == '\"' ){ 99 | size++; 100 | c = getc(i); 101 | while( c != '\"' ){ 102 | 103 | if( c == '\n' ){ 104 | error("file-not-known(feature-incomplete)", total_newlines, 0, "Badly formatted string! Exiting\n"); 105 | } 106 | 107 | size++; 108 | c = getc(i); 109 | 110 | } 111 | } 112 | size++; 113 | c = getc(i); 114 | if( c == '\n' ){ 115 | total_newlines++; 116 | } 117 | 118 | } 119 | fseek(i, -(ftell(i) - pos), SEEK_CUR); 120 | 121 | word = (char*)xmalloc(sizeof(char)*size + 1); 122 | 123 | c = getc(i); 124 | 125 | /* Then we copy the word the to malloc'ed space */ 126 | while ( ((c != EOF) && !isspace(c)) && (j < size) ){ 127 | /* This new section handles the new string copy! */ 128 | if ( c == '\"' ){ 129 | word[j] = c; 130 | j++; 131 | c = getc(i); 132 | word[j] = c; 133 | 134 | while( c != '\"' && (j < size) ){ 135 | word[j] = c; 136 | j++; 137 | c = getc(i); 138 | } 139 | } 140 | word[j] = c; 141 | j++; 142 | c = getc(i); 143 | } 144 | word[size] = '\0'; 145 | 146 | 147 | return word; 148 | } 149 | 150 | char *wordpeek(FILE *f) 151 | { 152 | return NULL; 153 | } 154 | 155 | void file_error(char *prog, char *do_this, char *ifilename, char *specifics, char *msg) 156 | { 157 | fprintf(stderr, "%s: cannot %s %s (%s):\n" 158 | "%s.\n", prog, do_this, ifilename, specifics, msg); 159 | exit(EXIT_FAILURE); 160 | } 161 | 162 | char *strip_whitesp(char *str) 163 | { 164 | return 0; 165 | } 166 | 167 | 168 | int get_build_date() 169 | { 170 | char buffer[12]; 171 | time_t rtime; 172 | struct tm *timeinfo; 173 | 174 | time( &rtime ); 175 | timeinfo = localtime( &rtime ); 176 | 177 | strftime(buffer, 12, "%Y%m%d", timeinfo); 178 | return atoi(buffer); 179 | } 180 | 181 | char *copy_alloced(char *s) 182 | { 183 | char *t = (char*)xmalloc(sizeof(char)*strlen(s)); 184 | strcpy(t, s); 185 | return t; 186 | } 187 | 188 | 189 | int get_column(FILE *i){ 190 | int cur_pos = ftell(i); 191 | int offset = 0; 192 | char c = fcpeek(i); 193 | 194 | while( c != '\n' && (ftell(i) > 0) && c != EOF){ 195 | fseek(i, -1, SEEK_CUR); 196 | offset++; 197 | c = fcpeek(i); 198 | } 199 | fseek(i, cur_pos, SEEK_CUR); 200 | return offset; 201 | } 202 | 203 | int intlit_comp(const void *a, const void *b) 204 | { 205 | if( *(int*)a > *(int*)b ) return 1; 206 | if( *(int*)a == *(int*)b ) return 0; 207 | if( *(int*)a < *(int*)b ) return -1; 208 | } 209 | 210 | int floatlit_comp(const void *a, const void *b) 211 | { 212 | if( *(double*)a > *(double*)b ) return 1; 213 | if( *(double*)a == *(double*)b ) return 0; 214 | if( *(double*)a < *(double*)b ) return -1; 215 | } 216 | 217 | char *cstr(char *s) 218 | { 219 | char *tmp = (char*)xmalloc(sizeof(char)*strlen(s) + 1); 220 | strcpy(tmp, s); 221 | return tmp; 222 | } 223 | 224 | int token_num(char *token) 225 | { 226 | int i; 227 | for(i = 0; i < strlen(token); i++){ 228 | if(token[i] == ','){ 229 | return 2; 230 | } 231 | } 232 | return 1; 233 | } 234 | 235 | 236 | 237 | 238 | -------------------------------------------------------------------------------- /src/compiler/utils.h: -------------------------------------------------------------------------------- 1 | /** \file utils.h 2 | \brief Interface that holds common functions and housekeeping operations. 3 | */ 4 | 5 | #ifndef _UTILS_H_ 6 | #define _UTILS_H_ 7 | 8 | #include 9 | #include 10 | #include 11 | #include 12 | #include 13 | 14 | #define VERSION "- 0.0.3 -" /**< Holds the current version (semver.org). */ 15 | #define RELEASE 0 /**< Holds the current release candidate number. */ 16 | #define BUILD_NUMBER 201 /**< Holds the current build number. */ 17 | #define BUILD_DATE 20101231 /**< Holds the current build date in Year-Month-Day format. */ 18 | 19 | #define INTERIM_FILENAME "data" 20 | #define DEFAULT_OUTPUT "a.out" 21 | 22 | #define TRUE 1 23 | #define FALSE 0 24 | 25 | #define DEBUG TRUE 26 | 27 | typedef struct file_struct_Tag { 28 | char calling_prog[64]; 29 | char filename[64]; 30 | char default_o[64]; 31 | int cur_line; 32 | int cur_column; 33 | char cur_word[64]; 34 | } file_struct; 35 | 36 | 37 | /* Globals */ 38 | 39 | extern file_struct file; 40 | extern size_t total_newlines; 41 | 42 | 43 | /** Prints usage information and a listing of commands. 44 | */ 45 | inline void usage(void); 46 | /** Prints version information. 47 | */ 48 | inline void version(void); 49 | 50 | /** Scans the program input for the -o flag, and returns its argument. 51 | */ 52 | inline char *scan_for_o(int argc, char *argv[]); 53 | 54 | inline char **get_files_from_argv(int argc, char *argv[]); 55 | 56 | /** Returns the current filesize of a file. It does this by fseeking to the 57 | last byte of the file, and return ftell(). 58 | */ 59 | int get_filesize(char *filename); 60 | 61 | /** Safety wrapper for malloc. Exits on error allocation. */ 62 | void *xmalloc(int size); 63 | 64 | /** Returns the current character pointed to by the file discriptor. Does not 65 | modify the current file pointer 66 | */ 67 | char fcpeek(FILE *f); 68 | 69 | /** Get the next word from the file stream, and increment the file pointer accordingly. 70 | All calls to this function return a malloc'ed string. It _must_ be freed. 71 | */ 72 | char *getword(FILE *i); 73 | 74 | /** Peek the next word from the file stream, and do not increment the file pointer. 75 | All calls to this function return a malloc'ed string. It _must_ be freed. 76 | Further, 77 | */ 78 | 79 | char *wordpeek(FILE *f); 80 | 81 | /** General file error function. 82 | */ 83 | void file_error(char *prog, char *do_this, char *ifilename, char *specifics, char *msg); 84 | 85 | /** 86 | */ 87 | int get_build_date(); 88 | 89 | /** 90 | */ 91 | int get_column(FILE *i); 92 | 93 | 94 | /** 95 | */ 96 | char *copy_alloced(char *s); 97 | 98 | /** 99 | */ 100 | int intlit_comp(const void *a, const void *b); 101 | 102 | /** 103 | */ 104 | int floatlit_comp(const void *a, const void *b); 105 | 106 | /** 107 | */ 108 | char *cstr(char *s); 109 | 110 | /** 111 | */ 112 | int token_num(char *token); 113 | 114 | 115 | 116 | /* Debug Functions */ 117 | 118 | /** 119 | */ 120 | char *strip_whitesp(char *str); 121 | 122 | 123 | 124 | 125 | 126 | #endif 127 | -------------------------------------------------------------------------------- /src/cvm/Makefile: -------------------------------------------------------------------------------- 1 | # C Virtual Machine Makefile 2 | 3 | # By Eudis Duran 4 | 5 | CC := gcc 6 | LIBS := -lm 7 | FLAGS := -Wall -O2 8 | 9 | OBJS := cvm.o 10 | 11 | TARGET:=cvm 12 | 13 | $(TARGET) : $(OBJS) 14 | $(CC) $(FLAGS) $(OBJS) -o $(TARGET) $(LIBS) 15 | @echo 16 | @echo "Done Building C Virtual Machine." 17 | @-rm *.o 18 | @cp cvm ../../examples/bin 19 | @echo 20 | 21 | cvm.o : cvm.c cvm.h 22 | @echo "(Modified) Compiling Translation Unit: cvm.c + cvm.h" 23 | $(CC) -c cvm.c -o cvm.o 24 | 25 | utils.o : ../compiler/utils.c ../compiler/utils.h 26 | @echo "(Modified) Compiling Translation Unit: utils.c + utils.h" 27 | $(CC) -c ../compiler/utils.c -o utils.o 28 | -------------------------------------------------------------------------------- /src/cvm/cvm.c: -------------------------------------------------------------------------------- 1 | #include "cvm.h" 2 | 3 | int main(int argc, char *argv[]) 4 | { 5 | if( argc == 1 ){ 6 | usage(); 7 | } 8 | else if ( argc == 2 ){ 9 | run(argv[1]); 10 | } 11 | return EXIT_SUCCESS; 12 | } 13 | 14 | 15 | void usage() 16 | { 17 | printf("\nC Virtual Machine - By Eudis Duran (Spring 2011 Semester Project)\n" 18 | "\nUsage: cvm \n\n"); 19 | } 20 | 21 | void run(char *program) 22 | { 23 | FILE *i = fopen(program, "rb"); 24 | 25 | short code_count = 0; 26 | short data_count = 0; 27 | short str_data_end = 0; 28 | 29 | if( i == NULL ){ 30 | printf("\nCould not open program file, exiting...\n"); 31 | exit(EXIT_FAILURE); 32 | } 33 | 34 | int cur_pos = ftell(i); 35 | fseek(i, -6, SEEK_END); 36 | 37 | /* Determine Run Time Data Segment Start */ 38 | fread(&str_data_end, sizeof(short), 1, i); 39 | 40 | /* Determine Data Segment size */ 41 | 42 | fread(&data_count, sizeof(short), 1, i); 43 | 44 | /* Determine Code Segment size */ 45 | 46 | fread(&code_count, sizeof(short), 1, i); 47 | 48 | fseek(i, cur_pos, SEEK_SET); 49 | 50 | /* Allocate data array (semi last short holds the code size) */ 51 | 52 | data = (char*)malloc(sizeof(char)* data_count); 53 | fread(data, sizeof(char), data_count, i); 54 | 55 | /* Read in code array (last short holds the code size) */ 56 | 57 | code = (Instruction*)malloc(sizeof(Instruction)* code_count); 58 | fread(code, sizeof(Instruction), code_count, i); 59 | 60 | ip = 0; 61 | sp = 0; 62 | 63 | /* This tests to see if we have any static strings allocated at all! */ 64 | if( str_data_end != 0){ 65 | dp = str_data_end + 1; /* The last byte is the terminating null, we cannot override it 66 | when assigning run time allocation! */ 67 | } 68 | else { 69 | dp = 0; 70 | } 71 | 72 | /* 73 | int j; 74 | printf("code_count: %d, data_count: %d, dp: %d\n", code_count, data_count, dp); 75 | */ 76 | /* 77 | int c; 78 | printf("Code Segment: "); 79 | for(c = 0; c < data_count; c++){ 80 | printf("%x ", data[c]); 81 | }*/ 82 | 83 | int alloc = 0; /**> Used as the base pointer for the static allocations (non-string)*/ 84 | 85 | while( ip < code_count ){ 86 | 87 | switch( code[ip].opcode ){ 88 | case OP_ADD: 89 | stack[sp - 2].i += stack[sp - 1].i; 90 | sp--; 91 | break; 92 | case OP_PUSH: 93 | alloc = code[ip].operand.i; 94 | stack[sp].i = *(int*)(data + (dp + alloc)); 95 | sp++; 96 | break; 97 | case OP_PUSHF: 98 | alloc = code[ip].operand.i; 99 | stack[sp].f = *(float*)(data + (dp + alloc)); 100 | sp++; 101 | break; 102 | case OP_PUSHI: 103 | //printf("Push-i: %d\n", code[ip].operand.i); 104 | stack[sp].i = code[ip].operand.i; 105 | sp++; 106 | //print_stack(sp); 107 | 108 | break; 109 | case OP_POP: 110 | alloc = code[ip].operand.i; 111 | *(int*)(data + (dp + alloc)) = stack[sp - 1].i; 112 | sp--; 113 | break; 114 | case OP_POPEMPTY: 115 | stack[ip - 1].i = 0; 116 | sp--; 117 | break; 118 | case OP_POPF: 119 | alloc = code[ip].operand.i; 120 | *(float*)(data + (dp + alloc)) = stack[sp - 1].f; 121 | sp--; 122 | break; 123 | case OP_EXCH: 124 | break; 125 | case OP_DUP: 126 | stack[sp] = stack[sp - 1]; 127 | sp++; 128 | break; 129 | case OP_ADDF: 130 | stack[sp - 2].f += stack[sp - 1].f; 131 | sp--; 132 | break; 133 | case OP_SUBF: 134 | stack[sp - 2].f -= stack[sp - 1].f; 135 | sp--; 136 | break; 137 | case OP_SUB: 138 | stack[sp - 2].i -= stack[sp - 1].i; 139 | sp--; 140 | 141 | break; 142 | case OP_MULF: 143 | stack[sp - 2].f *= stack[sp - 1].f; 144 | sp--; 145 | break; 146 | case OP_MUL: 147 | stack[sp - 2].i *= stack[sp - 1].i; 148 | sp--; 149 | break; 150 | case OP_DIV: 151 | stack[sp - 2].i /= stack[sp - 1].i; 152 | sp--; 153 | break; 154 | case OP_DIVF: 155 | stack[sp - 2].f /= stack[sp - 1].f; 156 | sp--; 157 | break; 158 | case OP_MOD: 159 | stack[sp - 2].i %= stack[sp - 1].i; 160 | sp--; 161 | break; 162 | case OP_AND: 163 | stack[sp - 2].i = stack[sp - 2].i && stack[sp - 1].i; 164 | sp--; 165 | break; 166 | case OP_OR: 167 | stack[sp - 2].i = stack[sp - 2].i && stack[sp - 1].i; 168 | sp--; 169 | break; 170 | case OP_EQL: 171 | stack[sp - 2].i = stack[sp - 2].i == stack[sp - 1].i; 172 | sp--; 173 | break; 174 | case OP_NEG: 175 | stack[sp - 1].i = -stack[sp - 1].i; 176 | break; 177 | case OP_NEGF: 178 | stack[sp - 1].f = -stack[sp - 1].f; 179 | break; 180 | 181 | case OP_NOT: 182 | stack[sp - 1].i = !stack[sp - 1].i; 183 | break; 184 | case OP_LSS: 185 | stack[sp - 2].i = stack[sp - 2].i < stack[sp - 1].i; 186 | sp--; 187 | break; 188 | case OP_GTR: 189 | stack[sp - 2].i = stack[sp - 2].i > stack[sp - 1].i; 190 | sp--; 191 | break; 192 | case OP_LEQ: 193 | stack[sp - 2].i = stack[sp - 2].i <= stack[sp - 1].i; 194 | sp--; 195 | break; 196 | case OP_GEQ: 197 | stack[sp - 2].i = stack[sp - 2].i >= stack[sp - 1].i; 198 | sp--; 199 | break; 200 | case OP_NEQ: 201 | stack[sp - 2].i = stack[sp - 2].i != stack[sp - 1].i; 202 | sp--; 203 | break; 204 | case OP_EQU: 205 | stack[sp - 2].i = stack[sp - 2].i == stack[sp - 1].i; 206 | sp--; 207 | break; 208 | case OP_CVI: 209 | stack[sp - 1].i = (int)stack[sp - 1].f; 210 | break; 211 | case OP_CVR: 212 | stack[sp - 1].f = (float)stack[sp - 1].i; 213 | break; 214 | case OP_JMP: 215 | /* 216 | printf("IP: %d\n",ip); 217 | printf("code: %d\n", code[ip].opcode); 218 | printf("oper: %d\n", code[ip].operand.i); 219 | printf("TopofStack: %d\n", stack[sp - 1].i); 220 | for(j = 0; j < code_count; j++){ 221 | printf("%d: opcode: %d, operand: %d\n",j, code[j].opcode, code[j].operand.i); 222 | }*/ 223 | ip = code[ip].operand.i - 1; 224 | 225 | break; 226 | case OP_JFALSE: 227 | /* 228 | printf("IP: %d\n",ip); 229 | printf("code: %d\n", code[ip].opcode); 230 | printf("oper: %d\n", code[ip].operand.i); 231 | printf("TopofStack: %d\n", stack[sp - 1].i); 232 | for(j = 0; j < code_count; j++){ 233 | printf("%d: opcode: %d, operand: %d\n",j, code[j].opcode, code[j].operand.i); 234 | }*/ 235 | if( stack[sp - 1].i == 0 ){ 236 | ip = code[ip].operand.i - 1; /* -1 because we increment right after the break here 237 | so we need code to execute one instruction back on 238 | the next VM iteration! */ 239 | } 240 | //sp--; /* If it's false, we rid the result */ 241 | break; 242 | case OP_JTRUE: 243 | if( stack[sp - 1].i != 0 ) 244 | ip = code[ip].operand.i - 1; 245 | break; 246 | case OP_HALT: 247 | exit(-1); 248 | break; 249 | case OP_WRITEINTID: 250 | printf("%d\n", *(int*)(data + code[ip].operand.i)); 251 | break; 252 | case OP_WRITEINT: 253 | printf("%d\n", stack[sp - 1].i); 254 | sp--; 255 | break; 256 | case OP_WRITEFLOAT: 257 | printf("%f\n", stack[sp - 1].f); 258 | sp--; 259 | break; 260 | case OP_NOP: 261 | break; 262 | case OP_WRITESTRING: 263 | 264 | printf("%s", &data[code[ip].operand.i]); 265 | printf("\n"); 266 | 267 | break; 268 | 269 | case OP_GET: 270 | 271 | alloc = code[ip].operand.i; 272 | int addr = stack[sp - 1].i; 273 | stack[sp - 1].i = *(int*)(data + (dp + stack[sp - 1].i)); 274 | 275 | //printf("\nAddress: %d\n", alloc + addr); 276 | //printf("\nValue: %d\n", stack[sp - 1].i); 277 | sp++; 278 | 279 | case OP_PUT: 280 | alloc = code[ip].operand.i; 281 | *(int*)(data + (dp + stack[sp - 2].i)) = stack[sp - 1].i; 282 | sp--; 283 | 284 | default: 285 | break; 286 | } 287 | ip++; 288 | } 289 | /* 290 | printf("Code Segment: "); 291 | for(c = 0; c < data_count; c++){ 292 | printf("%x ", data[c]); 293 | }*/ 294 | } 295 | 296 | void print_stack(int sp) 297 | { 298 | int i; 299 | printf("\nBottom: "); 300 | for(i = 0; i < sp; i++){ 301 | printf("%d < ", stack[i].i); 302 | 303 | } 304 | printf(": Top\n"); 305 | } 306 | -------------------------------------------------------------------------------- /src/cvm/cvm.h: -------------------------------------------------------------------------------- 1 | #ifndef _CVM_H_ 2 | #define _CVM_H_ 3 | 4 | #include 5 | #include 6 | 7 | #include "../compiler/utils.h" 8 | 9 | #define OP_PUSH 0 10 | #define OP_PUSHI 1 11 | #define OP_POP 2 12 | #define OP_EXCH 3 13 | #define OP_DUP 4 14 | #define OP_ADDF 5 15 | #define OP_ADD 6 16 | #define OP_SUBF 7 17 | #define OP_SUB 8 18 | #define OP_MULF 9 19 | #define OP_MUL 10 20 | #define OP_DIV 11 21 | #define OP_DIVF 12 22 | #define OP_AND 13 23 | #define OP_OR 14 24 | #define OP_EQL 15 25 | #define OP_NEG 16 26 | #define OP_NOT 17 27 | #define OP_LSS 18 28 | #define OP_GTR 19 29 | #define OP_LEQ 20 30 | #define OP_GEQ 21 31 | #define OP_CVI 22 32 | #define OP_CVR 23 33 | #define OP_JMP 24 34 | #define OP_JFALSE 25 35 | #define OP_JTRUE 26 36 | #define OP_HALT 27 37 | #define OP_WRITEINT 28 38 | #define OP_WRITEFLOAT 29 39 | #define OP_MOD 30 40 | 41 | #define OP_PUSHF 31 42 | #define OP_POPF 32 43 | 44 | #define OP_WRITEINTID 33 45 | #define OP_POPEMPTY 34 46 | 47 | #define OP_NOP 35 48 | #define OP_NEQ 36 49 | #define OP_EQU 37 50 | #define OP_NEGF 38 51 | 52 | #define OP_WRITESTRING 39 53 | #define OP_GET 40 54 | #define OP_PUT 41 55 | 56 | typedef unsigned char uchar; 57 | typedef unsigned int uint; 58 | typedef union Operand_TAG { 59 | int i; 60 | float f; 61 | } Operand; 62 | 63 | typedef struct Instruction_TAG { 64 | char opcode; /* 8-bit */ 65 | Operand operand; /* 32-bit */ 66 | }Instruction; 67 | 68 | /* Globals */ 69 | 70 | size_t sp; 71 | size_t ip; 72 | size_t bp; 73 | size_t dp; 74 | 75 | Instruction *code; 76 | char *data; 77 | 78 | union stack_TAG { 79 | int i; 80 | float f; 81 | } stack[1024]; /* 1kb for stack */ 82 | 83 | 84 | 85 | void usage(); 86 | 87 | void run(char *program); 88 | 89 | 90 | void print_stack(); 91 | #endif 92 | -------------------------------------------------------------------------------- /src/cvm/drivers/main.c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/eudisd/c-compiler/9aa5e08fe4217accd4935b8120178e4e0377e0a0/src/cvm/drivers/main.c --------------------------------------------------------------------------------