├── .vscode └── settings.json ├── grammar.txt ├── license.md ├── lowfish ├── makefile ├── out.txt ├── readme.md ├── src ├── il │ ├── il.c │ └── il.h ├── lexer │ ├── lexer.c │ └── lexer.h ├── main.c ├── optimizer │ └── optimizer.h ├── parser │ ├── parser.c │ └── parser.h ├── typechecker │ ├── typechecker.c │ └── typechecker.h ├── util.c └── util.h ├── test.lf └── tests ├── few_call.lf ├── fun.lf ├── fun.lf.expected ├── funcall.lf ├── funcall.lf.expected ├── test.py ├── variable.lf ├── variable.lf.expected ├── variable_func_call.lf └── variable_func_call.lf.expected /.vscode/settings.json: -------------------------------------------------------------------------------- 1 | { 2 | "files.associations": { 3 | "typechecker.h": "c", 4 | "array": "c", 5 | "compare": "c", 6 | "functional": "c", 7 | "tuple": "c", 8 | "type_traits": "c", 9 | "utility": "c", 10 | "istream": "c", 11 | "ostream": "c" 12 | } 13 | } -------------------------------------------------------------------------------- /grammar.txt: -------------------------------------------------------------------------------- 1 | grammar lowfish; 2 | 3 | program: (function | struct | enum | (extern SEMI))* EOF; 4 | struct: 5 | 'struct' ID BEGINOFBLOCK (vardecl SEMI)* ENDOFBLOCK | 6 | 'struct' ID (vardecl SEMI)* 'end'; 7 | enum: 8 | 'enum' ID BEGINOFBLOCK (expression SEMI) * ENDOFBLOCK | 9 | 'enum' ID (expression SEMI)* 'end'; 10 | 11 | function: type ID OPENBR vardecl* CLOSEBR block; 12 | block: normal_block | arrow_block; 13 | normal_block: begin line* end; 14 | arrow_block: ARROW (expression | conditional | booleanexpression | vardecl | native) (end | SEMI ); 15 | begin: BEGINOFBLOCK; 16 | end: ENDOFBLOCK; 17 | line: ((expression SEMI) | (conditional) | (booleanexpression SEMI) | (vardecl SEMI) | (native SEMI) ) ('\n')?; 18 | extern: 19 | 'extern' OPENBR STRING CLOSEBR; 20 | asm: 21 | 'asm' OPENBR STRING CLOSEBR; 22 | basic_expression: 23 | 'true' | 24 | 'false'| 25 | STRING | 26 | NUMBER | 27 | ID; 28 | functioncall: 29 | ID args; 30 | args: 31 | OPENBR (expression)? ((COMMA expression)*)? CLOSEBR; 32 | binexpr: 33 | basic_expression PLUS basic_expression | 34 | basic_expression MINUS basic_expression | 35 | basic_expression DIV basic_expression | 36 | basic_expression MUL basic_expression | 37 | basic_expression MOD basic_expression | 38 | basic_expression LOGICALOR basic_expression | 39 | basic_expression XOR basic_expression | 40 | basic_expression LOGICALAND basic_expression | 41 | binexpr PLUS binexpr | 42 | binexpr MINUS binexpr | 43 | binexpr DIV binexpr | 44 | binexpr MUL binexpr | 45 | binexpr MOD binexpr | 46 | binexpr LOGICALOR binexpr | 47 | binexpr XOR binexpr | 48 | binexpr LOGICALAND binexpr; 49 | PLUS: 50 | '+'; 51 | MINUS: 52 | '-'; 53 | DIV: 54 | '/'; 55 | MUL: 56 | '*'; 57 | MOD: 58 | '%'; 59 | LOGICALOR: 60 | '|'; 61 | XOR: 62 | '^'; 63 | LOGICALAND: 64 | '&'; 65 | expression: 66 | basic_expression | 67 | ID index | 68 | expression index | 69 | OPENBR type CLOSEBR expression | 70 | binexpr | 71 | assignment | 72 | 'return' basic_expression 73 | | functioncall; 74 | assignment: 75 | ID equal; 76 | simplebooleanexpr: 77 | expression | 78 | eq | 79 | noteq| 80 | EXCLAMATION expression | 81 | expression MORE expression | 82 | expression LESS expression | 83 | expression MOREEQUAL expression | 84 | expression LESSEQUAL expression; 85 | booleanexpression: 86 | OPENBR booleanexpression CLOSEBR | 87 | simplebooleanexpr | 88 | simplebooleanexpr BOOLNOTEQUAL simplebooleanexpr | 89 | simplebooleanexpr BOOLEQUAL simplebooleanexpr | 90 | EXCLAMATION simplebooleanexpr | 91 | simplebooleanexpr MORE simplebooleanexpr | 92 | simplebooleanexpr LESS simplebooleanexpr | 93 | simplebooleanexpr MOREEQUAL simplebooleanexpr | 94 | simplebooleanexpr LESSEQUAL simplebooleanexpr | 95 | simplebooleanexpr BOOLAND simplebooleanexpr | 96 | simplebooleanexpr BOOLOR simplebooleanexpr; 97 | eq: 98 | expression BOOLEQUAL expression; 99 | noteq: 100 | expression BOOLNOTEQUAL expression; 101 | conditional: 102 | if | 103 | while | 104 | repeat | 105 | for | 106 | unless | 107 | else; 108 | if: 109 | 'if' booleanexpression blo 110 | ck; 111 | while: 112 | 'while' booleanexpression block; 113 | repeat: 114 | 'repeat' expression ARROW expression block; 115 | for: 116 | 'for' (vardecl | ID) COMMA expression ARROW expression block ; 117 | else: 118 | 'else' block | 119 | 'else' conditional; 120 | unless: 121 | 'unless' booleanexpression block ; 122 | 123 | type: (struct ID) | void | i64 | i32 | i16 | i8 | u64 | u32 | u16 | u8 | ptr8 | ptr16 | ptr32 | ptr64; 124 | void: 'void'; 125 | i64: 'i64'; 126 | i32: 'i32'; 127 | i16: 'i16'; 128 | i8: 'i8'; 129 | u64: 'u64'; 130 | u32: 'u32'; 131 | u16: 'u16'; 132 | u8: 'u8'; 133 | ptr64: 'ptr64'; 134 | ptr32: 'ptr32'; 135 | ptr16: 'ptr16'; 136 | ptr8: 'ptr8'; 137 | 138 | equal: 139 | EQUAL basic_expression | 140 | EQUAL expression; 141 | 142 | vardecl: 143 | type ID (equal)? 144 | | type index (EQUAL BEGINOFBLOCK expression COMMA* ENDOFBLOCK)?; 145 | index: 146 | INDEXBROPEN expression INDEXBRCLOSE; 147 | SEMI: 148 | ';'; 149 | COMMENT: '#' ~[\r\n]* -> channel(HIDDEN); 150 | WS: [ \t\r\n]+ -> skip; 151 | ID: [a-zA-Z_][a-zA-Z0-9_]*; 152 | NUMBER: DIGIT+ ('.' DIGIT+)?; 153 | fragment DIGIT: [0-9]; 154 | STRING: '"'(.*?)'"'; 155 | BEGINOFBLOCK: '{'; 156 | ENDOFBLOCK: '}'; 157 | OPENBR: '('; 158 | CLOSEBR: ')' 159 | EQUAL: '='; 160 | BOOLNOTEQUAL: '!='; 161 | BOOLEQUAL: '=='; 162 | EXCLAMATION: '!'; 163 | INDEXBROPEN: '['; 164 | INDEXBRCLOSE: ']'; 165 | MORE: '>'; 166 | ARROW: '->'; 167 | LESS: '<'; 168 | MOREEQUAL: '>='; 169 | LESSEQUAL: '<='; 170 | BOOLOR: '||'; 171 | BOOLAND: '&&'; 172 | LOGICALAND: '&'; 173 | LOGICALOR: '|'; 174 | XOR: '^'; 175 | PLUS: '+'; 176 | MINUS: '-'; 177 | DIV: '/'; 178 | MUL: '*'; -------------------------------------------------------------------------------- /license.md: -------------------------------------------------------------------------------- 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 | -------------------------------------------------------------------------------- /lowfish: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SpaceFishDev/LowFish/22554fc400895ede6119ae804186360241924645/lowfish -------------------------------------------------------------------------------- /makefile: -------------------------------------------------------------------------------- 1 | src := $(wildcard src/*.c) $(wildcard src/lexer/*.c) $(wildcard src/parser/*.c) $(wildcard src/typechecker/*.c) $(wildcard src/il/*.c) 2 | out := lowfish 3 | cflags := -Isrc/ 4 | 5 | all: $(src) 6 | gcc $(src) $(cflags) -o $(out) -std=c99 7 | ./$(out) 8 | debug: $(src) 9 | gcc $(src) $(cflags) -o $(out) -g 10 | gdb ./$(out) 11 | -------------------------------------------------------------------------------- /out.txt: -------------------------------------------------------------------------------- 1 | 2 | { 3 | 4 | { 5 | 6 | { 7 | 8 | } 9 | } 10 | 11 | { 12 | 13 | 14 | 15 | { 16 | 17 | { 18 | 19 | { 20 | 21 | { 22 | 23 | } 24 | } 25 | } 26 | } 27 | } 28 | } 29 | WARNING: UNSAFE FUNCTION DEFINITION FOR 'printf': The type checker is unable to check functions used from extern make sure that you match the argument count and type. 30 | -------------------------------------------------------------------------------- /readme.md: -------------------------------------------------------------------------------- 1 | # Lowfish 2 | Lowfish is a low level compiled programming language. 3 | 4 | ## Features 5 | - types that make sense ie 'i32' or 'ptr32' 6 | - open source, so if you have a complaint and I'm too slow, fix it. 7 | - other stuff 8 | 9 | ### Hello world. 10 | ```c 11 | extern("printf") 12 | i32 main() 13 | { 14 | printf("Hello, World"); 15 | } 16 | ``` 17 | -------------------------------------------------------------------------------- /src/il/il.c: -------------------------------------------------------------------------------- 1 | #include "il.h" 2 | 3 | #include 4 | 5 | #include "../typechecker/typechecker.h" 6 | 7 | node **get_mul(node **list, int *len, node *p) 8 | { 9 | 10 | if (p->type == BASICEXPRESSION) 11 | { 12 | return list; 13 | } 14 | node *op = p; 15 | if (p->type == BINEXPR) 16 | { 17 | op = p->children[0]; 18 | } 19 | if (op->node_token.type == MUL) 20 | { 21 | list[*len] = op; 22 | list = realloc(list, (*len + 1) * sizeof(node *)); 23 | ++len[0]; 24 | } 25 | if (op->n_child == 2) 26 | { 27 | get_mul(list, len, op->children[0]); 28 | get_mul(list, len, op->children[1]); 29 | } 30 | return list; 31 | } 32 | bool continuing = false; 33 | char *visit_node(il_generator *il_gen, node *curr) 34 | { 35 | if (!curr) 36 | { 37 | return ""; 38 | } 39 | if (curr->parent && curr->parent->type == PROGRAM) 40 | { 41 | if (!continuing) 42 | { 43 | continuing = true; 44 | char *res = visit_node(il_gen, curr); 45 | int c = 0; 46 | for (int i = 0; i < curr->parent->n_child; ++i) 47 | { 48 | if (curr->parent->children[i] == curr) 49 | { 50 | c = i; 51 | break; 52 | } 53 | } 54 | c += 1; 55 | if (c >= curr->parent->n_child) 56 | { 57 | return res; 58 | } 59 | char *o = visit_node(il_gen, curr->parent->children[c]); 60 | char *buf = malloc(strlen(res) + strlen(o) + 2); 61 | buf[strlen(res) + strlen(o) + 1] = 0; 62 | strcpy(buf, res); 63 | strcat(buf, "\n"); 64 | strcat(buf, o); 65 | return buf; 66 | } 67 | if (continuing) 68 | { 69 | continuing = false; 70 | } 71 | } 72 | switch (curr->type) 73 | { 74 | case FUNCTION: 75 | { 76 | char *out = malloc(strlen("function ") + 77 | strlen(curr->children[1]->node_token.text)); 78 | sprintf(out, "function %s\n", curr->children[1]->node_token.text); 79 | 80 | node *block = curr->children[2]; 81 | for (int i = 0; i < block->n_child; ++i) 82 | { 83 | char *str = visit_node(il_gen, block->children[i]); 84 | int x = strlen(str); 85 | out = realloc(out, x + strlen(out) + 2); 86 | strcat(out, str); 87 | strcat(out, "\n"); 88 | free(str); 89 | } 90 | 91 | return out; 92 | } 93 | case FUNCTION_CALL: 94 | { 95 | if (curr->n_child > 0) 96 | { 97 | if (curr->children[0]->type == BASICEXPRESSION) 98 | { 99 | char *fmt = "call %s %s"; 100 | char *buff = malloc(400); 101 | sprintf(buff, fmt, curr->node_token.text, curr->children[0]->children[0]->node_token.text); 102 | return buff; 103 | } 104 | } 105 | } 106 | case TOKENNODE: 107 | { 108 | if (curr->node_token.type == MUL) 109 | { 110 | char *left; 111 | char *right; 112 | left = visit_node(il_gen, curr->children[0]); 113 | right = visit_node(il_gen, curr->children[1]); 114 | char *fmt = "%s mul %s"; 115 | char *out = malloc(100); 116 | sprintf(out, fmt, left, right); 117 | free(left); 118 | free(right); 119 | return out; 120 | } 121 | } 122 | case EXTERN: 123 | { 124 | if (curr->children[0]->type == TOKENNODE) 125 | { 126 | char *fmt = "extern %s"; 127 | char *out = malloc(100); 128 | sprintf(out, fmt, curr->children[0]->node_token.text); 129 | return out; 130 | } 131 | } 132 | break; 133 | case BINEXPR: 134 | { 135 | if (curr->n_child > 0) 136 | { 137 | if (curr->children[0]->node_token.type == MUL) 138 | { 139 | char *left; 140 | char *right; 141 | left = visit_node(il_gen, curr->children[0]->children[0]); 142 | right = visit_node(il_gen, curr->children[0]->children[1]); 143 | char *fmt = "%s mul %s"; 144 | char *out = malloc(100); 145 | sprintf(out, fmt, left, right); 146 | free(left); 147 | free(right); 148 | return out; 149 | } 150 | if (curr->children[0]->node_token.type == DIV) 151 | { 152 | char *left; 153 | char *right; 154 | left = visit_node(il_gen, curr->children[0]->children[0]); 155 | right = visit_node(il_gen, curr->children[0]->children[1]); 156 | char *fmt = "%s div %s"; 157 | char *out = malloc(100); 158 | sprintf(out, fmt, left, right); 159 | free(left); 160 | free(right); 161 | return out; 162 | } 163 | int len = 0; 164 | node **multiplications = get_mul(malloc(sizeof(node *)), &len, curr); 165 | if (len == 0) 166 | { 167 | if (curr->children[0]->node_token.type == PLUS) 168 | { 169 | char *left; 170 | char *right; 171 | left = visit_node(il_gen, curr->children[0]->children[0]); 172 | right = visit_node(il_gen, curr->children[0]->children[1]); 173 | char *fmt = "%s add %s"; 174 | char *out = malloc(100); 175 | sprintf(out, fmt, left, right); 176 | free(left); 177 | free(right); 178 | return out; 179 | } 180 | char *left; 181 | char *right; 182 | left = visit_node(il_gen, curr->children[0]->children[0]); 183 | right = visit_node(il_gen, curr->children[0]->children[1]); 184 | char *fmt = "%s sub %s"; 185 | char *out = malloc(100); 186 | sprintf(out, fmt, left, right); 187 | free(left); 188 | free(right); 189 | return out; 190 | } 191 | char *out = malloc(1000); 192 | for (int i = 0; i < len; ++i) 193 | { 194 | char *x = visit_node(il_gen, multiplications[i]); 195 | strcat(out, x); 196 | } 197 | char *str = malloc(100); 198 | char *fmt = " add %s"; 199 | sprintf(str, fmt, visit_node(il_gen, curr->children[0]->children[0])); 200 | strcat(out, str); 201 | free(str); 202 | return out; 203 | } 204 | } 205 | break; 206 | case BASICEXPRESSION: 207 | { 208 | switch (curr->children[0]->node_token.type) 209 | { 210 | case NUMBER: 211 | { 212 | return curr->children[0]->node_token.text; 213 | } 214 | break; 215 | } 216 | } 217 | break; 218 | default: 219 | { 220 | return visit_node(il_gen, curr->children[0]); 221 | } 222 | } 223 | } 224 | 225 | char *generate_il(node *root, typechecker *type_checker) 226 | { 227 | il_generator generator = 228 | (il_generator){root, root, 0, malloc(1), type_checker}; 229 | char *src = visit_node(&generator, root); 230 | generator.src = src; 231 | return generator.src; 232 | } 233 | -------------------------------------------------------------------------------- /src/il/il.h: -------------------------------------------------------------------------------- 1 | #include "../typechecker/typechecker.h" 2 | 3 | typedef struct 4 | { 5 | node *root; 6 | node *current; 7 | size_t length_of_src; 8 | char *src; // generated source code NOT the input source code! 9 | typechecker *type_checker; 10 | int parent_idx; 11 | } il_generator; 12 | #define append_src(_src) \ 13 | il_gen->src = \ 14 | realloc(il_gen->src, il_gen->length_of_src + strlen(_src) + 2); \ 15 | il_gen->length_of_src += strlen(_src) + 1; \ 16 | strcat(il_gen->src, _src); \ 17 | il_gen->src[il_gen->length_of_src - 1] = '\n'; \ 18 | il_gen->src[il_gen->length_of_src] = 0; 19 | #define append_src_no_nl(_src) \ 20 | il_gen->src = \ 21 | realloc(il_gen->src, il_gen->length_of_src + strlen(_src) + 1); \ 22 | il_gen->length_of_src += strlen(_src); \ 23 | strcat(il_gen->src, _src); \ 24 | il_gen->src[il_gen->length_of_src] = 0; 25 | 26 | char *visit_node(il_generator *generator, node *curr); 27 | 28 | char *generate_il(node *root, typechecker *type_checker); 29 | -------------------------------------------------------------------------------- /src/lexer/lexer.c: -------------------------------------------------------------------------------- 1 | #include "lexer.h" 2 | 3 | char *mkstr(char *str) 4 | { 5 | char *new = malloc(strlen(str) + 1); 6 | memset(new, 0, strlen(str) + 1); 7 | strcpy(new, str); 8 | return new; 9 | } 10 | 11 | bool is_digit(char c) { return c >= '0' && c <= '9'; } 12 | 13 | token lex(lexer *Lexer) 14 | { 15 | if (Lexer->pos > strlen(Lexer->src)) 16 | { 17 | return create_token(Lexer->column, Lexer->line, mkstr("\0"), 18 | END_OF_FILE); 19 | } 20 | switch (Lexer->src[Lexer->pos]) 21 | { 22 | case '\0': 23 | { 24 | return create_token(Lexer->column, Lexer->line, mkstr("\0"), 25 | END_OF_FILE); 26 | } 27 | break; 28 | #pragma region SYMBOLS 29 | 30 | case '{': 31 | { 32 | next; 33 | return create_token(Lexer->column, Lexer->line, mkstr("{"), 34 | BEGINOFBLOCK); 35 | } 36 | case '}': 37 | { 38 | next; 39 | return create_token(Lexer->column, Lexer->line, mkstr("}"), 40 | ENDOFBLOCK); 41 | } 42 | case '(': 43 | { 44 | next; 45 | return create_token(Lexer->column, Lexer->line, mkstr("("), OPENBR); 46 | } 47 | case ')': 48 | { 49 | next; 50 | return create_token(Lexer->column, Lexer->line, mkstr(")"), 51 | CLOSEBR); 52 | } 53 | 54 | case '&': 55 | { 56 | next; 57 | if (Lexer->src[Lexer->pos] >= 'a' && 58 | Lexer->src[Lexer->pos] <= 'z' || 59 | Lexer->src[Lexer->pos] >= 'A' && 60 | Lexer->src[Lexer->pos] <= 'Z' || 61 | Lexer->src[Lexer->pos] == '_') 62 | { 63 | size_t start = Lexer->pos; 64 | size_t column = Lexer->column; 65 | size_t line = Lexer->line; 66 | while (Lexer->src[Lexer->pos] >= 'A' && 67 | Lexer->src[Lexer->pos] <= 'Z' || 68 | Lexer->src[Lexer->pos] >= 'a' && 69 | Lexer->src[Lexer->pos] <= 'z' || 70 | Lexer->src[Lexer->pos] == '_' || 71 | is_digit(Lexer->src[Lexer->pos])) 72 | { 73 | next; 74 | } 75 | size_t len = Lexer->pos - start; 76 | char *result = malloc(len + 1); 77 | result[len] = 0; 78 | Lexer->pos = start; 79 | while (Lexer->src[Lexer->pos] >= 'A' && 80 | Lexer->src[Lexer->pos] <= 'Z' || 81 | Lexer->src[Lexer->pos] >= 'a' && 82 | Lexer->src[Lexer->pos] <= 'z' || 83 | Lexer->src[Lexer->pos] == '_' || 84 | is_digit(Lexer->src[Lexer->pos])) 85 | { 86 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 87 | next; 88 | } 89 | return create_token(column, line, result, REF); 90 | } 91 | if (Lexer->src[Lexer->pos] == '&') 92 | { 93 | next; 94 | return create_token(Lexer->column, Lexer->line, mkstr("&&"), 95 | BOOLAND); 96 | } 97 | return create_token(Lexer->column, Lexer->line, mkstr("&"), 98 | LOGICALAND); 99 | } 100 | case '|': 101 | { 102 | next; 103 | if (Lexer->src[Lexer->pos] == '|') 104 | { 105 | next; 106 | return create_token(Lexer->column, Lexer->line, mkstr("||"), 107 | BOOLOR); 108 | } 109 | return create_token(Lexer->column, Lexer->line, mkstr("|"), 110 | LOGICALOR); 111 | } 112 | case '=': 113 | { 114 | next; 115 | if (Lexer->src[Lexer->pos] == '=') 116 | { 117 | next; 118 | return create_token(Lexer->column, Lexer->line, mkstr("=="), 119 | BOOLEQUAL); 120 | } 121 | return create_token(Lexer->column, Lexer->line, mkstr("="), EQUAL); 122 | } 123 | case '!': 124 | { 125 | next; 126 | if (Lexer->src[Lexer->pos] == '=') 127 | { 128 | next; 129 | return create_token(Lexer->column, Lexer->line, mkstr("!="), 130 | BOOLNOTEQUAL); 131 | } 132 | return create_token(Lexer->column, Lexer->line, mkstr("!"), 133 | EXCLAMATION); 134 | } 135 | case ',': 136 | { 137 | next; 138 | return create_token(Lexer->column, Lexer->line, mkstr(","), COMMA); 139 | } 140 | case '[': 141 | { 142 | next; 143 | return create_token(Lexer->column, Lexer->line, mkstr("["), 144 | INDEXBROPEN); 145 | } 146 | case ']': 147 | { 148 | next; 149 | return create_token(Lexer->column, Lexer->line, mkstr("]"), 150 | INDEXBROPEN); 151 | } 152 | case ';': 153 | { 154 | next; 155 | return create_token(Lexer->column, Lexer->line, mkstr(";"), SEMI); 156 | } 157 | case '-': 158 | { 159 | next; 160 | if (is_digit(Lexer->src[Lexer->pos])) 161 | { 162 | char *result; 163 | size_t start = Lexer->pos; 164 | size_t column = Lexer->column; 165 | size_t line = Lexer->line; 166 | 167 | while (is_digit(Lexer->src[Lexer->pos])) 168 | { 169 | next; 170 | } 171 | if (Lexer->src[Lexer->pos] == '.') 172 | { 173 | next; 174 | } 175 | while (is_digit(Lexer->src[Lexer->pos])) 176 | { 177 | next; 178 | } 179 | size_t len = Lexer->pos - start; 180 | result = malloc(len); 181 | result[len] = 0; 182 | Lexer->pos = start; 183 | while (is_digit(Lexer->src[Lexer->pos])) 184 | { 185 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 186 | next; 187 | } 188 | if (Lexer->src[Lexer->pos] == '.') 189 | { 190 | result[Lexer->pos - start] = '.'; 191 | next; 192 | } 193 | while (is_digit(Lexer->src[Lexer->pos])) 194 | { 195 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 196 | next; 197 | } 198 | char *res2 = malloc(len + 2); 199 | memset(res2, 0, len + 2); 200 | sprintf(res2, "-%s", result); 201 | free(result); 202 | return create_token(column, line, res2, NUMBER); 203 | } 204 | if (Lexer->src[Lexer->pos] == '>') 205 | { 206 | next; 207 | return create_token(Lexer->column, Lexer->line, mkstr("->"), 208 | ARROW); 209 | } 210 | return create_token(Lexer->column, Lexer->line, mkstr("-"), MINUS); 211 | } 212 | case '+': 213 | { 214 | next; 215 | return create_token(Lexer->column, Lexer->line, mkstr("+"), PLUS); 216 | } 217 | case '/': 218 | { 219 | next; 220 | return create_token(Lexer->column, Lexer->line, mkstr("/"), DIV); 221 | } 222 | case '*': 223 | { 224 | next; 225 | if (Lexer->src[Lexer->pos] >= 'a' && 226 | Lexer->src[Lexer->pos] <= 'z' || 227 | Lexer->src[Lexer->pos] >= 'A' && 228 | Lexer->src[Lexer->pos] <= 'Z' || 229 | Lexer->src[Lexer->pos] == '_') 230 | { 231 | size_t start = Lexer->pos; 232 | size_t column = Lexer->column; 233 | size_t line = Lexer->line; 234 | while (Lexer->src[Lexer->pos] >= 'A' && 235 | Lexer->src[Lexer->pos] <= 'Z' || 236 | Lexer->src[Lexer->pos] >= 'a' && 237 | Lexer->src[Lexer->pos] <= 'z' || 238 | Lexer->src[Lexer->pos] == '_' || 239 | is_digit(Lexer->src[Lexer->pos])) 240 | { 241 | next; 242 | } 243 | size_t len = Lexer->pos - start; 244 | char *result = malloc(len + 1); 245 | result[len] = 0; 246 | Lexer->pos = start; 247 | while (Lexer->src[Lexer->pos] >= 'A' && 248 | Lexer->src[Lexer->pos] <= 'Z' || 249 | Lexer->src[Lexer->pos] >= 'a' && 250 | Lexer->src[Lexer->pos] <= 'z' || 251 | Lexer->src[Lexer->pos] == '_' || 252 | is_digit(Lexer->src[Lexer->pos])) 253 | { 254 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 255 | next; 256 | } 257 | return create_token(column, line, result, DEREF); 258 | } 259 | return create_token(Lexer->column, Lexer->line, mkstr("*"), MUL); 260 | } 261 | case '>': 262 | { 263 | next; 264 | if (Lexer->src[Lexer->pos] == '=') 265 | { 266 | next; 267 | return create_token(Lexer->column, Lexer->line, mkstr(">="), 268 | MOREEQUAL); 269 | } 270 | return create_token(Lexer->column, Lexer->line, mkstr(">"), MORE); 271 | } 272 | case '<': 273 | { 274 | next; 275 | if (Lexer->src[Lexer->pos] == '=') 276 | { 277 | next; 278 | return create_token(Lexer->column, Lexer->line, mkstr("<="), 279 | MOREEQUAL); 280 | } 281 | return create_token(Lexer->column, Lexer->line, mkstr("<"), MORE); 282 | } 283 | #pragma endregion 284 | #pragma region COMMENT 285 | case '#': 286 | { 287 | next; 288 | while (Lexer->src[Lexer->pos] != '\n' && 289 | Lexer->src[Lexer->pos] != '\r' && 290 | Lexer->src[Lexer->pos] != '#') 291 | { 292 | next; 293 | } 294 | return lex(Lexer); 295 | } 296 | #pragma endregion 297 | #pragma region WS 298 | case '\n': 299 | { 300 | size_t c = Lexer->column; 301 | size_t l = Lexer->line; 302 | ++Lexer->line; 303 | ++Lexer->pos; 304 | Lexer->column = 0; 305 | return lex(Lexer); 306 | } 307 | case ' ': 308 | case '\t': 309 | case '\r': 310 | { 311 | next; 312 | return lex(Lexer); 313 | } 314 | #pragma endregion 315 | #pragma region STRING 316 | case '"': 317 | { 318 | next; 319 | size_t start = Lexer->pos; 320 | size_t column = Lexer->column; 321 | size_t line = Lexer->line; 322 | char *value_of_string; 323 | while (Lexer->src[Lexer->pos] != '"') 324 | { 325 | next; 326 | } 327 | size_t len = Lexer->pos - start; 328 | 329 | value_of_string = malloc(len + 1); 330 | memset(value_of_string, 0, len + 1); 331 | Lexer->pos = start; 332 | while (Lexer->src[Lexer->pos] != '"') 333 | { 334 | value_of_string[Lexer->pos - start] = Lexer->src[Lexer->pos]; 335 | next; 336 | } 337 | char *val = malloc(len + 3); 338 | sprintf(val, "'%s'", value_of_string); 339 | next; 340 | return create_token(column, line, val, STRING); 341 | } 342 | #pragma endregion 343 | } 344 | #pragma region ID 345 | 346 | if ((Lexer->src[Lexer->pos] >= 'A' && Lexer->src[Lexer->pos] <= 'Z') || 347 | (Lexer->src[Lexer->pos] >= 'a' && Lexer->src[Lexer->pos] <= 'z') || 348 | (Lexer->src[Lexer->pos] == '_')) 349 | { 350 | size_t start = Lexer->pos; 351 | size_t column = Lexer->column; 352 | size_t line = Lexer->line; 353 | while (Lexer->src[Lexer->pos] >= 'A' && Lexer->src[Lexer->pos] <= 'Z' || 354 | Lexer->src[Lexer->pos] >= 'a' && Lexer->src[Lexer->pos] <= 'z' || 355 | Lexer->src[Lexer->pos] == '_' || 356 | is_digit(Lexer->src[Lexer->pos])) 357 | { 358 | next; 359 | } 360 | size_t len = Lexer->pos - start; 361 | char *result = malloc(len + 1); 362 | result[len] = 0; 363 | Lexer->pos = start; 364 | while (Lexer->src[Lexer->pos] >= 'A' && Lexer->src[Lexer->pos] <= 'Z' || 365 | Lexer->src[Lexer->pos] >= 'a' && Lexer->src[Lexer->pos] <= 'z' || 366 | Lexer->src[Lexer->pos] == '_' || 367 | is_digit(Lexer->src[Lexer->pos])) 368 | { 369 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 370 | next; 371 | } 372 | if (Lexer->src[Lexer->pos] == ':') 373 | { 374 | next; 375 | return create_token(column, line, result, LABEL); 376 | } 377 | return create_token(column, line, result, ID); 378 | } 379 | #pragma endregion 380 | #pragma region NUMBER 381 | if (is_digit(Lexer->src[Lexer->pos])) 382 | { 383 | char *result; 384 | size_t start = Lexer->pos; 385 | size_t column = Lexer->column; 386 | size_t line = Lexer->line; 387 | 388 | while (is_digit(Lexer->src[Lexer->pos])) 389 | { 390 | next; 391 | } 392 | if (Lexer->src[Lexer->pos] == '.') 393 | { 394 | next; 395 | } 396 | while (is_digit(Lexer->src[Lexer->pos])) 397 | { 398 | next; 399 | } 400 | size_t len = Lexer->pos - start; 401 | result = malloc(len); 402 | result[len] = 0; 403 | Lexer->pos = start; 404 | while (is_digit(Lexer->src[Lexer->pos])) 405 | { 406 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 407 | next; 408 | } 409 | if (Lexer->src[Lexer->pos] == '.') 410 | { 411 | result[Lexer->pos - start] = '.'; 412 | next; 413 | } 414 | while (is_digit(Lexer->src[Lexer->pos])) 415 | { 416 | result[Lexer->pos - start] = Lexer->src[Lexer->pos]; 417 | next; 418 | } 419 | return create_token(column, line, result, NUMBER); 420 | } 421 | #pragma endregion 422 | return create_token(Lexer->column, Lexer->line, mkstr("BAD"), BAD); 423 | } 424 | -------------------------------------------------------------------------------- /src/lexer/lexer.h: -------------------------------------------------------------------------------- 1 | #ifndef LEXER_H 2 | 3 | #define LEXER_H 4 | #include 5 | #include 6 | #include 7 | #include 8 | #include 9 | 10 | #include "../util.h" 11 | 12 | typedef enum 13 | { 14 | STRING, 15 | NUMBER, 16 | ID, 17 | BEGINOFBLOCK, 18 | ENDOFBLOCK, 19 | OPENBR, 20 | CLOSEBR, 21 | EQUAL, 22 | BOOLNOTEQUAL, 23 | BOOLEQUAL, 24 | EXCLAMATION, 25 | INDEXBROPEN, 26 | INDEXBRCLOSE, 27 | MORE, 28 | ARROW, 29 | LESS, 30 | MOREEQUAL, 31 | LESSEQUAL, 32 | BOOLOR, 33 | BOOLAND, 34 | LOGICALAND, 35 | LOGICALOR, 36 | XOR, 37 | PLUS, 38 | MINUS, 39 | DIV, 40 | MUL, 41 | SEMI, 42 | NL, 43 | COMMA, 44 | END_OF_FILE, 45 | BAD, 46 | NOTOKEN, 47 | REF, 48 | DEREF, 49 | LABEL, 50 | } token_type; 51 | 52 | typedef struct 53 | { 54 | uint32_t col, row; 55 | token_type type; 56 | size_t len; 57 | char *text; 58 | int on_stack; 59 | } token; 60 | 61 | #define string_version(x) (#x) 62 | 63 | #define create_token(col, row, text, type) \ 64 | ((token){col, row, type, strlen(text), text}) 65 | 66 | #define token_type_to_string(__type) \ 67 | (((char *[]){ \ 68 | "STRING", "NUMBER", "ID", "BEGINOFBLOCK", \ 69 | "ENDOFBLOCK", "OPENBR", "CLOSEBR", "EQUAL", \ 70 | "BOOLNOTEQUAL", "BOOLEQUAL", "EXCLAMATION", "INDEXBROPEN", \ 71 | "INDEXBRCLOSE", "MORE", "ARROW", "LESS", \ 72 | "MOREEQUAL", "LESSEQUAL", "BOOLOR", "BOOLAND", \ 73 | "LOGICALAND", "LOGICALOR", "XOR", "PLUS", \ 74 | "MINUS", "DIV", "MUL", "SEMI", \ 75 | "NL", "COMMA", "END_OF_FILE", "BAD", \ 76 | "NOTOKEN", "REF", "DEREF", "LABEL"})[__type]) 77 | 78 | typedef struct 79 | { 80 | char *src; 81 | int line; 82 | int column; 83 | int pos; 84 | } lexer; 85 | 86 | #define next \ 87 | ++Lexer->pos; \ 88 | ++Lexer->column 89 | 90 | token lex(lexer *); 91 | 92 | char *read_file(char *path); 93 | 94 | char *mkstr(char *str); 95 | #endif 96 | -------------------------------------------------------------------------------- /src/main.c: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | 4 | #include "il/il.h" 5 | #include "lexer/lexer.h" 6 | #include "parser/parser.h" 7 | #include "typechecker/typechecker.h" 8 | #include "util.h" 9 | // if you're looking for comments... 10 | // about that... 11 | 12 | char *get_output_file(char **argv) 13 | { 14 | while (*argv) 15 | { 16 | if (!strcmp(*argv, "-o")) 17 | { 18 | return *(++argv); 19 | } 20 | ++argv; 21 | } 22 | } 23 | 24 | char *get_input_file(char **argv) 25 | { 26 | char *input = "test.lf"; 27 | while (*argv) 28 | { 29 | if ((*argv)[0] != '-') 30 | { 31 | input = *argv; 32 | break; 33 | } 34 | } 35 | return input; 36 | } 37 | 38 | node *global_tree; 39 | token *global_tokens; 40 | parser *global_parser; 41 | typechecker *global_typechecker; 42 | 43 | int state = 0; 44 | 45 | enum states 46 | { 47 | LEXING, 48 | PARSING, 49 | RESTRUCTURING, 50 | TYPECHECKING, 51 | IL_CREATION, 52 | }; 53 | 54 | void panic_handler(int s) 55 | { 56 | if (s == SIGSEGV) 57 | { 58 | printf("ERROR: An unkown error occurred.\n"); 59 | printf("The error occured at during the '%s' stage.\n", 60 | ((char *[]){"lexing", "parsing", "tree restructuring", 61 | "typechecking", "il creation"})[state]); 62 | printf( 63 | "This error could not be resolved in any way and so the compiler " 64 | "will " 65 | "exit.\n"); 66 | exit(1); 67 | } 68 | } 69 | 70 | int main(int argc, char **argv) 71 | { 72 | signal(SIGSEGV, panic_handler); 73 | ++argv; 74 | char *input_file = read_file(get_input_file(argv)); 75 | 76 | lexer Lexer = (lexer){input_file, 1, 0, 0}; 77 | token *Tokens = malloc(sizeof(token)); 78 | size_t n_token = 1; 79 | for (;;) 80 | { 81 | token T = lex(&Lexer); 82 | printf("TOKEN(%s,%s, %d)\n", T.text, 83 | (T.type <= DEREF) ? (token_type_to_string(T.type)) : "UNK", T.type); 84 | Tokens = realloc(Tokens, n_token * sizeof(token)); 85 | Tokens[n_token - 1] = T; 86 | ++n_token; 87 | if (T.type == BAD || T.type == END_OF_FILE) 88 | { 89 | break; 90 | } 91 | } 92 | ++state; 93 | 94 | free(input_file); 95 | parser *Parser = create_parser(Tokens, n_token - 1); 96 | node *root = parse(Parser); 97 | ++state; 98 | 99 | restructure_parents(root); 100 | ++state; 101 | free(Tokens); 102 | 103 | print_tree(root, 0); 104 | 105 | typechecker *Typechecker = calloc(sizeof(typechecker), 1); 106 | type_check_tree(root, Typechecker); 107 | ++state; 108 | char *il = generate_il(root, Typechecker); 109 | printf("--IL--\n\n%s\n", il); 110 | free_tree(root); 111 | free(Typechecker->functions); 112 | free(Typechecker->variables); 113 | free(Typechecker); 114 | return 0; 115 | } 116 | -------------------------------------------------------------------------------- /src/optimizer/optimizer.h: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /src/parser/parser.c: -------------------------------------------------------------------------------- 1 | #include "parser.h" 2 | 3 | node *append_child_to_x(node *x, node *y) 4 | { 5 | if (!x) 6 | { 7 | x = calloc(sizeof(node), 1); 8 | } 9 | if (!x->children) 10 | { 11 | x->children = malloc(sizeof(node *)); 12 | x->children[0] = y; 13 | x->n_child = 1; 14 | return x; 15 | } 16 | x->children = realloc(x->children, sizeof(node *) * (x->n_child + 1)); 17 | x->children[x->n_child] = y; 18 | ++x->n_child; 19 | return x; 20 | } 21 | 22 | #define append_child(x, y) x = append_child_to_x(x, y) 23 | 24 | void put_error(char *msg, node *Node, token t) 25 | { 26 | if (Node) 27 | printf("ERROR: %s LN: %d COL: %d\n", msg, Node->node_token.row, 28 | Node->node_token.col); 29 | else 30 | printf("ERROR: %s LN: %d COL: %d\n", msg, t.row, t.col); 31 | free(msg); 32 | exit(-1); 33 | } 34 | 35 | bool expect(token_type type, parser *Parser, bool error) 36 | { 37 | if (Parser->tokens[Parser->pos + 1].type == type) 38 | { 39 | return true; 40 | } 41 | if (error) 42 | { 43 | char *msg = "Expected '%s' but got '%s'."; 44 | char *buffer = malloc(1024); 45 | sprintf(buffer, msg, token_type_to_string(type), 46 | token_type_to_string(Parser->tokens[Parser->pos + 1].type)); 47 | put_error(buffer, 0, Parser->tokens[Parser->pos + 1]); 48 | // exits the program so no need to free. 49 | } 50 | return false; 51 | } 52 | 53 | node *create_arbitrary_node(node_type type, node *parent) 54 | { 55 | token node_token = 56 | create_token(0, 0, mkstr(node_type_to_string(type)), NOTOKEN); 57 | node_token.on_stack = true; 58 | node *n = malloc(sizeof(node)); 59 | n->type = type; 60 | n->node_token = node_token; 61 | n->parent = parent; 62 | n->children = malloc(sizeof(void *)); 63 | n->n_child = 0; 64 | return n; 65 | } 66 | 67 | node *create_node(node_type type, token node_token, node *parent) 68 | { 69 | node *n = malloc(sizeof(node)); 70 | n->type = type; 71 | n->node_token = node_token; 72 | n->parent = parent; 73 | n->children = malloc(sizeof(void *)); 74 | n->n_child = 0; 75 | return n; 76 | } 77 | parser *create_parser(token *tokens, size_t n_token) 78 | { 79 | parser *Parser = malloc(sizeof(parser)); 80 | token t = create_token(0, 0, mkstr("PROGRAM"), NOTOKEN); 81 | 82 | t.on_stack = 1; 83 | Parser->root = create_node(PROGRAM, t, 0); 84 | Parser->current_parent = Parser->root; 85 | Parser->pos = 0; 86 | Parser->tokens = tokens; 87 | Parser->n_token = n_token; 88 | return Parser; 89 | } 90 | 91 | #define expect_err(x) \ 92 | expect(x, Parser, true); \ 93 | ++Parser->pos 94 | #define expect_err_no_inc(x) expect(x, Parser, true) 95 | 96 | #define expect_no_err(x) expect(x, Parser, false) 97 | 98 | #define conditional_token(x) \ 99 | !strcmp("if", x.text) || !strcmp("else", x.text) || \ 100 | !strcmp("while", x.text) || !strcmp("for", x.text) 101 | 102 | bool f_is_type(int type, parser *Parser, bool err) 103 | { 104 | if (Parser->tokens[Parser->pos].type == type) 105 | { 106 | return true; 107 | } 108 | if (err) 109 | { 110 | char *msg = "Expected '%s' but got '%s'."; 111 | char *buffer = malloc(1024); 112 | sprintf(buffer, msg, token_type_to_string(type), 113 | token_type_to_string(Parser->tokens[Parser->pos + 1].type)); 114 | put_error(buffer, 0, Parser->tokens[Parser->pos]); 115 | } 116 | return false; 117 | } 118 | #define is_type(x) (f_is_type(x, Parser, false)) 119 | #define is_type_err(x) (f_is_type(x, Parser, true)) 120 | 121 | node *parse_primary(parser *Parser); 122 | 123 | #define type_token(x) \ 124 | ((!strcmp(x.text, "ptr8") || !strcmp(x.text, "ptr") || \ 125 | !strcmp(x.text, "ptr16") || !strcmp(x.text, "ptr32") || \ 126 | !strcmp(x.text, "struct") || !strcmp(x.text, "i32") || \ 127 | !strcmp(x.text, "i16") || !strcmp(x.text, "i8")) || \ 128 | (!strcmp(x.text, "u32") || !strcmp(x.text, "u16") || \ 129 | !strcmp(x.text, "u8"))) 130 | 131 | node *parse_expression(parser *Parser); 132 | node *parse_assignment(parser *Parser, node *parent) 133 | { 134 | node *id = create_node(TOKENNODE, Parser->tokens[Parser->pos], parent); 135 | if (!expect_no_err(EQUAL)) 136 | { 137 | return id; 138 | } 139 | 140 | // safe to assume its an actual assignment 141 | expect_err(EQUAL); 142 | ++Parser->pos; // skip the equal 143 | node *next = parse_primary(Parser); 144 | node *assign = create_arbitrary_node(ASSIGNMENT, parent); 145 | append_child(assign, id); 146 | append_child(assign, next); 147 | --Parser->pos; // go back or weird errors happen?? 148 | return assign; 149 | } 150 | node *parse_function_call(parser *Parser) 151 | { 152 | if (!strcmp("extern", Parser->tokens[Parser->pos].text)) 153 | { 154 | expect_err(OPENBR); 155 | expect_err(STRING); 156 | node *arb = create_arbitrary_node(EXTERN, 0); 157 | node *tok = create_node(TOKENNODE, Parser->tokens[Parser->pos], arb); 158 | append_child(arb, tok); 159 | expect_err(CLOSEBR); 160 | return arb; 161 | } 162 | if (!strcmp("asm", Parser->tokens[Parser->pos].text)) 163 | { 164 | expect_err(OPENBR); 165 | expect_err(STRING); 166 | node *arb = create_arbitrary_node(ASM, 0); 167 | node *tok = create_node(TOKENNODE, Parser->tokens[Parser->pos], arb); 168 | append_child(arb, tok); 169 | expect_err(CLOSEBR); 170 | return arb; 171 | } 172 | node *id_node = create_node(FUNCTION_CALL, Parser->tokens[Parser->pos], 173 | Parser->current_parent); 174 | expect_err(OPENBR); 175 | 176 | ++Parser->pos; 177 | if (!is_type(CLOSEBR)) 178 | { 179 | while (!is_type(CLOSEBR)) 180 | { 181 | if (is_type(COMMA)) ++Parser->pos; 182 | node *next = parse_primary(Parser); 183 | append_child(id_node, next); 184 | } 185 | } 186 | return id_node; 187 | } 188 | node *parse_id(parser *Parser) 189 | { 190 | if (!strcmp("return", Parser->tokens[Parser->pos].text)) 191 | { 192 | expect_err(ID); 193 | return create_node(RETURN, Parser->tokens[Parser->pos++], 0); 194 | } 195 | if (!strcmp("goto", Parser->tokens[Parser->pos].text)) 196 | { 197 | expect_err(ID); 198 | return create_node(GOTO, Parser->tokens[Parser->pos++], 0); 199 | } 200 | if (!expect_no_err(OPENBR) && !type_token(Parser->tokens[Parser->pos])) 201 | { 202 | node *id = create_node(TOKENNODE, Parser->tokens[Parser->pos], 0); 203 | node *assign = parse_assignment(Parser, 0); 204 | node *arb_expr = create_arbitrary_node(BASICEXPRESSION, 0); 205 | if (assign->type != TOKENNODE) 206 | { 207 | assign->parent = arb_expr; 208 | append_child(arb_expr, assign); 209 | return arb_expr; 210 | } 211 | append_child(arb_expr, id); 212 | return arb_expr; 213 | } 214 | else if (type_token(Parser->tokens[Parser->pos])) 215 | { 216 | node *type_node = create_node(TYPE, Parser->tokens[Parser->pos], 0); 217 | expect_err(ID); 218 | if (!strcmp(Parser->tokens[Parser->pos - 1].text, "struct")) 219 | { 220 | // hopefully not a struct definition. (while we're still building 221 | // out the parser) 222 | type_node = create_node( 223 | TYPE, Parser->tokens[Parser->pos + 1], 224 | 0); // we just assume it isnt just for testing purposes. 225 | expect_err(ID); 226 | } 227 | if (!expect_no_err(OPENBR)) 228 | { 229 | node *var_decl = 230 | create_arbitrary_node(VARDECL, Parser->current_parent); 231 | node *id = 232 | create_node(TOKENNODE, Parser->tokens[Parser->pos], var_decl); 233 | type_node->parent = var_decl; 234 | node *assignment = parse_assignment(Parser, var_decl); 235 | if (assignment->type == TOKENNODE) 236 | { 237 | // its not an assignment 238 | append_child(var_decl, type_node); 239 | append_child(var_decl, id); 240 | return var_decl; 241 | } 242 | // safely assume its an assignment 243 | append_child(var_decl, type_node); 244 | append_child(var_decl, assignment); 245 | return var_decl; 246 | } 247 | 248 | // safe to assume its a function declaration. 249 | // which is a problem becuase that should've been handled :(((( 250 | } 251 | else if (expect_no_err(OPENBR)) 252 | { 253 | return parse_function_call(Parser); 254 | } 255 | } 256 | 257 | node *parse_basic_expression(parser *Parser) 258 | { 259 | if (is_type(ID)) 260 | { 261 | node *expr = parse_id(Parser); 262 | return expr; 263 | } 264 | node *arb_expr = create_arbitrary_node(BASICEXPRESSION, 0); 265 | node *expr = create_node(TOKENNODE, Parser->tokens[Parser->pos], arb_expr); 266 | append_child(arb_expr, expr); 267 | return arb_expr; 268 | } 269 | 270 | node *parse_factor(parser *Parser) 271 | { 272 | node *left = parse_basic_expression(Parser); 273 | 274 | while (expect_no_err(DIV) || expect_no_err(MUL) || 275 | expect_no_err(BOOLEQUAL) || expect_no_err(BOOLNOTEQUAL) || 276 | expect_no_err(LESS) || expect_no_err(MORE) || 277 | expect_no_err(MOREEQUAL) || expect_no_err(LESSEQUAL)) 278 | { 279 | ++Parser->pos; 280 | node *operator= 281 | create_node(TOKENNODE, Parser->tokens[Parser->pos], left); 282 | ++Parser->pos; 283 | node *right = parse_basic_expression(Parser); 284 | append_child(operator, left); 285 | append_child(operator, right); 286 | left->parent = operator; 287 | right->parent = operator; 288 | left = operator; 289 | } 290 | 291 | return left; 292 | } 293 | node *parse_primary(parser *Parser) 294 | { 295 | node *left = parse_factor(Parser); 296 | if (left->type == BLOCK) 297 | { 298 | Parser->current_parent = left; 299 | if (expect_no_err(ENDOFBLOCK)) 300 | { 301 | return left; 302 | } 303 | } 304 | while (expect_no_err(PLUS) || expect_no_err(MINUS) || 305 | expect_no_err(BOOLAND) || expect_no_err(BOOLOR)) 306 | { 307 | ++Parser->pos; 308 | node *operator= 309 | create_node(TOKENNODE, Parser->tokens[Parser->pos], left); 310 | ++Parser->pos; 311 | node *right = parse_factor(Parser); 312 | left->parent = operator; 313 | right->parent = operator; 314 | append_child(operator, left); 315 | append_child(operator, right); 316 | left = operator; 317 | } 318 | if (expect_no_err(SEMI)) 319 | { 320 | ++Parser->pos; 321 | } 322 | if (left->n_child != 0 && (left->type == TOKENNODE)) 323 | { 324 | node *binexpr_node = create_arbitrary_node(BINEXPR, 0); 325 | left->parent = binexpr_node; 326 | append_child(binexpr_node, left); 327 | ++Parser->pos; 328 | return binexpr_node; 329 | } 330 | ++Parser->pos; 331 | return left; 332 | } 333 | 334 | node *parse_conditional(parser *Parser) 335 | { 336 | node *cond = create_arbitrary_node(CONDITIONAL, Parser->current_parent); 337 | // Parser->current_parent = cond; 338 | if (!strcmp("if", Parser->tokens[Parser->pos].text)) 339 | { 340 | append_child(Parser->current_parent, cond); 341 | node *arb_if = create_arbitrary_node(IF, cond); 342 | expect_err(OPENBR); 343 | ++Parser->pos; 344 | node *expr = parse_primary(Parser); 345 | ++Parser->pos; 346 | // expect_err( CLOSEBR ); 347 | expr->parent = arb_if; 348 | append_child(cond, arb_if); 349 | append_child(arb_if, expr); 350 | Parser->current_parent = arb_if; 351 | 352 | return parse(Parser); 353 | } 354 | if (!strcmp("while", Parser->tokens[Parser->pos].text)) 355 | { 356 | append_child(Parser->current_parent, cond); 357 | node *arb_while = create_arbitrary_node(WHILE, cond); 358 | expect_err(OPENBR); 359 | ++Parser->pos; 360 | node *expr = parse_primary(Parser); 361 | ++Parser->pos; 362 | // expect_err( CLOSEBR ); 363 | expr->parent = arb_while; 364 | append_child(cond, arb_while); 365 | append_child(arb_while, expr); 366 | Parser->current_parent = arb_while; 367 | 368 | return parse(Parser); 369 | } 370 | if (!strcmp("else", Parser->tokens[Parser->pos].text)) 371 | { 372 | if (expect_no_err(BEGINOFBLOCK)) 373 | { 374 | // normal else 375 | if (Parser->current_parent->n_child && 376 | Parser->current_parent 377 | ->children[Parser->current_parent->n_child - 1] 378 | ->type == CONDITIONAL) 379 | { 380 | node *arb_else = create_arbitrary_node(ELSE, cond); 381 | ++Parser->pos; 382 | append_child( 383 | Parser->current_parent 384 | ->children[Parser->current_parent->n_child - 1], 385 | arb_else); 386 | Parser->current_parent = arb_else; 387 | return parse(Parser); 388 | } 389 | put_error("Floating else statement.", 0, 390 | Parser->tokens[Parser->pos]); 391 | } 392 | // the comment under this explains the current state. 393 | } 394 | // I'll do something when I'm not lazy, for now just a seg fault 395 | } 396 | node *parse_func(parser *Parser) 397 | { 398 | node *type_node = create_node(TYPE, Parser->tokens[Parser->pos - 1], 0); 399 | expect_err(OPENBR); 400 | node *func = create_arbitrary_node(FUNCTION, 0); 401 | node *id = create_node(TOKENNODE, Parser->tokens[Parser->pos - 1], func); 402 | append_child(func, type_node); 403 | append_child(func, id); 404 | ++Parser->pos; 405 | while (!is_type(CLOSEBR)) // eg i32 b( something ) instead of i32 b() 406 | { 407 | if (is_type(COMMA)) ++Parser->pos; 408 | node *next = parse_primary(Parser); 409 | append_child(func, next); 410 | } 411 | --Parser->pos; 412 | expect_err(CLOSEBR); 413 | ++Parser->pos; 414 | append_child(Parser->root, func); 415 | Parser->current_parent = func; 416 | return parse(Parser); 417 | } 418 | node *parse_full_id(parser *Parser) 419 | { 420 | node *arb_expr = create_arbitrary_node(EXPRESSION, Parser->current_parent); 421 | if (conditional_token(Parser->tokens[Parser->pos])) 422 | { 423 | return parse_conditional(Parser); 424 | } 425 | if (type_token(Parser->tokens[Parser->pos])) 426 | { 427 | expect_err(ID); 428 | // make sure its not a var decl 429 | if (!expect_no_err(OPENBR)) 430 | { 431 | --Parser->pos; 432 | node *expr = parse_primary(Parser); 433 | expr->parent = arb_expr; 434 | append_child(arb_expr, expr); 435 | append_child(Parser->current_parent, arb_expr); 436 | return parse(Parser); 437 | } 438 | return parse_func(Parser); 439 | } 440 | node *expr = parse_primary(Parser); 441 | expr->parent = arb_expr; 442 | append_child(arb_expr, expr); 443 | append_child(Parser->current_parent, arb_expr); 444 | return parse(Parser); 445 | } 446 | node *parse_expression(parser *Parser) 447 | { 448 | node *arb_expr = create_arbitrary_node(EXPRESSION, Parser->current_parent); 449 | switch (Parser->tokens[Parser->pos].type) 450 | { 451 | case LABEL: 452 | { 453 | node *parent = Parser->current_parent; 454 | node *n = 455 | create_node(LABEL_NODE, Parser->tokens[Parser->pos], parent); 456 | append_child(parent, n); 457 | ++Parser->pos; 458 | return parse(Parser); 459 | } 460 | case DEREF: 461 | { 462 | node *parent = Parser->current_parent; 463 | node *id = 464 | create_node(TOKENNODE, Parser->tokens[Parser->pos], parent); 465 | if (!expect_no_err(EQUAL)) 466 | { 467 | return id; 468 | } 469 | // safe to assume its an actual assignment 470 | expect_err(EQUAL); 471 | ++Parser->pos; // skip the equal 472 | node *next = parse_primary(Parser); 473 | node *assign = create_arbitrary_node(ASSIGNMENT, parent); 474 | append_child(assign, id); 475 | append_child(assign, next); 476 | --Parser->pos; // go back or weird errors happen?? 477 | append_child(Parser->current_parent, assign); 478 | 479 | return parse(Parser); 480 | } 481 | case ID: 482 | { 483 | return parse_full_id(Parser); 484 | } 485 | case NUMBER: 486 | { 487 | node *expr = parse_primary(Parser); 488 | expr->parent = arb_expr; 489 | append_child(arb_expr, expr); 490 | append_child(Parser->current_parent, arb_expr); 491 | return parse(Parser); 492 | } 493 | case SEMI: 494 | { 495 | ++Parser->pos; 496 | return parse(Parser); 497 | } 498 | case BEGINOFBLOCK: 499 | { 500 | ++Parser->pos; 501 | node *block = create_arbitrary_node(BLOCK, Parser->current_parent); 502 | append_child(Parser->current_parent, block); 503 | Parser->current_parent = block; 504 | return parse(Parser); 505 | } 506 | case ENDOFBLOCK: 507 | { 508 | ++Parser->pos; 509 | node *p = Parser->current_parent; 510 | while (p && p->parent && p->type != BLOCK && 511 | p->type != PROGRAM) //( p && p->parent && p->type != PROGRAM 512 | //&& !( p->type == BLOCK && p->type != 513 | // Parser->current_parent ) ) 514 | { 515 | p = p->parent; 516 | } 517 | Parser->current_parent = p; 518 | return parse(Parser); 519 | } 520 | case COMMA: 521 | { 522 | ++Parser->pos; 523 | return parse(Parser); 524 | } 525 | case END_OF_FILE: 526 | { 527 | return Parser->root; 528 | } 529 | default: 530 | { 531 | char *msg = "Unexpected token '%s'."; 532 | char *buffer = malloc(1024); 533 | sprintf(buffer, msg, Parser->tokens[Parser->pos].text); 534 | put_error(buffer, 0, Parser->tokens[Parser->pos + 1]); 535 | } 536 | } 537 | } 538 | 539 | node *parse(parser *Parser) 540 | { 541 | if (Parser->pos > Parser->n_token) 542 | { 543 | return Parser->root; 544 | } 545 | return parse_expression(Parser); 546 | } 547 | 548 | void print_tree(node *n, int indent) 549 | { 550 | print_n_times(" ", indent); 551 | printf("\n", n->node_token.text, 552 | node_type_to_string(n->type)); 553 | if (n->n_child > 0) 554 | { 555 | print_n_times(" ", indent); 556 | printf("{\n"); 557 | } 558 | ++indent; 559 | for (size_t i = 0; i < n->n_child; ++i) 560 | { 561 | print_tree(n->children[i], indent); 562 | } 563 | if (n->n_child > 0) 564 | { 565 | print_n_times(" ", indent - 1); 566 | printf("}\n"); 567 | } 568 | } 569 | 570 | void free_tree(node *n) 571 | { 572 | for (size_t i = 0; i < n->n_child; ++i) 573 | { 574 | free_tree(n->children[i]); 575 | } 576 | free(n); 577 | } 578 | -------------------------------------------------------------------------------- /src/parser/parser.h: -------------------------------------------------------------------------------- 1 | #ifndef PARSER_H 2 | 3 | #define PARSER_H 4 | 5 | #include 6 | #include 7 | #include 8 | #include 9 | 10 | #include "../lexer/lexer.h" 11 | #include "../util.h" 12 | #define node_type_to_string(x) \ 13 | (((char *[]){ \ 14 | "PROGRAM", \ 15 | "FUNCTION", \ 16 | "TYPE", \ 17 | "TOKEN_NODE", \ 18 | "BLOCK", \ 19 | "NORMALBLOCK", \ 20 | "ARROWBLOCK", \ 21 | "EXTERN", \ 22 | "ASM", \ 23 | "BASICEXPRESSION", \ 24 | "EXPRESSION", \ 25 | "BINEXPR", \ 26 | "FUNCTION_CALL", \ 27 | "VARDECL", \ 28 | "ASSIGNMENT", \ 29 | "CONDITIONAL", \ 30 | "IF", \ 31 | "WHILE", \ 32 | "ELSE", \ 33 | "REFERENCE", \ 34 | "LABEL", \ 35 | "GOTO", \ 36 | "RETURN", \ 37 | })[x]) 38 | #undef next 39 | typedef enum 40 | { 41 | PROGRAM, 42 | FUNCTION, 43 | TYPE, 44 | TOKENNODE, 45 | BLOCK, 46 | NORMALBLOCK, 47 | ARROW_BLOCK, 48 | EXTERN, 49 | ASM, 50 | BASICEXPRESSION, 51 | EXPRESSION, 52 | BINEXPR, 53 | FUNCTION_CALL, 54 | VARDECL, 55 | ASSIGNMENT, 56 | CONDITIONAL, 57 | IF, 58 | WHILE, 59 | ELSE, 60 | REFERENCE, 61 | LABEL_NODE, 62 | GOTO, 63 | RETURN, 64 | } node_type; 65 | 66 | typedef struct node 67 | { 68 | node_type type; 69 | token node_token; 70 | struct node **children; 71 | size_t n_child; 72 | struct node *parent; 73 | } node; 74 | 75 | typedef struct 76 | { 77 | size_t n_token; 78 | token *tokens; 79 | size_t pos; 80 | node *root; 81 | node *current_parent; 82 | } parser; 83 | 84 | parser *create_parser(token *tokens, size_t n_token); 85 | 86 | node *parse(parser *Parser); 87 | node *create_node(node_type type, token node_token, node *parent); 88 | node *create_arbitrary_node(node_type type, node *parent); 89 | void print_tree(node *n, int indent); 90 | void put_error(char *msg, node *Node, token t); 91 | #define append_child(x, y) x = append_child_to_x(x, y) 92 | node *append_child_to_x(node *x, node *y); 93 | 94 | void free_tree(node *n); 95 | 96 | #endif 97 | -------------------------------------------------------------------------------- /src/typechecker/typechecker.c: -------------------------------------------------------------------------------- 1 | #include "typechecker.h" 2 | 3 | #include 4 | #include 5 | #include 6 | bool is_node(node *t, node_type type) 7 | { 8 | assert((t && "T should exist in this situation.")); 9 | return t->type == type; 10 | } 11 | 12 | void restructure_parents(node *tree) 13 | { 14 | if (tree->n_child == 0) 15 | { 16 | return; 17 | } 18 | for (size_t i = 0; i < tree->n_child; ++i) 19 | { 20 | tree->children[i]->parent = tree; 21 | restructure_parents(tree->children[i]); 22 | } 23 | } 24 | 25 | bool has_child_recursive(node *check, node_type type) 26 | { 27 | if (is_node(check, type)) 28 | { 29 | return true; 30 | } 31 | for (size_t i = 0; i < check->n_child; ++i) 32 | { 33 | bool is = has_child_recursive(check->children[i], type); 34 | if (is) 35 | { 36 | return is; 37 | } 38 | } 39 | return false; 40 | } 41 | // gets first instance... 42 | node *get_child_recursive(node *check, node_type type) 43 | { 44 | if (is_node(check, type)) 45 | { 46 | return check; 47 | } 48 | for (size_t i = 0; i < check->n_child; ++i) 49 | { 50 | node *is = get_child_recursive(check->children[i], type); 51 | if (is) 52 | { 53 | return is; 54 | } 55 | } 56 | return 0; 57 | } 58 | 59 | node *get_parent(node *check, node_type type) 60 | { 61 | node *p = check; 62 | while (p) 63 | { 64 | if (p->type == type) 65 | { 66 | return p; 67 | } 68 | p = p->parent; 69 | } 70 | return 0; 71 | } 72 | 73 | function *get_function(typechecker *type_checker, char *title) 74 | { 75 | for (size_t i = 0; i != type_checker->n_func; ++i) 76 | { 77 | if (!strcmp(title, type_checker->functions[i].title)) 78 | { 79 | return type_checker->functions + i; 80 | } 81 | } 82 | return 0; 83 | } 84 | 85 | variable *get_var(typechecker *type_checker, char *title, size_t scope, 86 | function *func) 87 | { 88 | for (size_t i = 0; i != type_checker->n_var; ++i) 89 | { 90 | if (!strcmp(title, type_checker->variables[i].title) && 91 | type_checker->variables[i].scope == scope && 92 | type_checker->variables[i].func->title == func->title) 93 | { 94 | return &type_checker->variables[i]; 95 | } 96 | } 97 | return 0; 98 | } 99 | // big mac of a function name right there. 100 | void put_error_incompatible_types_assignment(char *type_a, char *type_b, 101 | node *n) 102 | { 103 | // dont need to free since put_error kills the program 104 | char *buffer = malloc(1024); 105 | sprintf(buffer, 106 | "Incompatible types used in an assigmnent Type '%s' is assigned to " 107 | "Type '%s'", 108 | type_a, type_b); 109 | put_error(buffer, 0, n->node_token); 110 | } 111 | 112 | bool starts_with(char *a, char *b) 113 | { 114 | if (!a || !b) 115 | { 116 | return false; 117 | } 118 | if (!strcmp(a, b)) 119 | { 120 | return true; 121 | } 122 | if (strlen(a) < strlen(b)) 123 | { 124 | return false; 125 | } 126 | size_t lenb = strlen(b); 127 | char *start_of_a = a; 128 | while (*a) 129 | { 130 | if (*a != *b) 131 | { 132 | return (a - start_of_a == lenb); 133 | } 134 | ++a; 135 | ++b; 136 | } 137 | return false; 138 | } 139 | 140 | void put_error_incompatible_operation(char *operation, char *a, char *b, 141 | node *n) 142 | { 143 | char *buffer = malloc(1024); 144 | sprintf(buffer, "Cannot do operation '%s' on type '%s' with '%s'.", 145 | operation, a, b); 146 | put_error(buffer, 0, n->node_token); 147 | } 148 | // put error frees the string so it gotta be on the heap :( 149 | 150 | node *eval(node *x, node *parent); 151 | 152 | char *get_type_recursive(typechecker *type_checker, node *expr) 153 | { 154 | if (expr->type == BINEXPR) 155 | { 156 | if (expr->children[0]->node_token.text[0] == '=') 157 | { 158 | return mkstr("bool"); 159 | } 160 | } 161 | if (expr->type == BASICEXPRESSION) 162 | { 163 | if (expr->children[0]->node_token.type == ID) 164 | { 165 | node *f = get_parent(expr, FUNCTION); 166 | function *func = 167 | get_function(type_checker, f->children[1]->node_token.text); 168 | variable *v = 169 | get_var(type_checker, expr->children[0]->node_token.text, 170 | type_checker->scope, func); 171 | if (!v) 172 | { 173 | char *buffer = malloc(1024); 174 | sprintf(buffer, "Variable '%s' doesnt exist.", 175 | expr->children[0]->node_token.text); 176 | put_error(buffer, 0, expr->children[0]->node_token); 177 | } 178 | return v->type; 179 | } 180 | if (expr->children[0]->node_token.type == DEREF) 181 | { 182 | node *f = get_parent(expr, FUNCTION); 183 | function *func = 184 | get_function(type_checker, f->children[1]->node_token.text); 185 | variable *v = 186 | get_var(type_checker, expr->children[0]->node_token.text, 187 | type_checker->scope, func); 188 | if (!v) 189 | { 190 | char *buffer = malloc(1024); 191 | sprintf(buffer, "Variable '%s' doesnt exist.", 192 | expr->children[0]->node_token.text); 193 | put_error(buffer, 0, expr->children[0]->node_token); 194 | } 195 | if (!v->pointing_to) 196 | { 197 | char *buffer = malloc(1024); 198 | sprintf(buffer, 199 | "Variable '%s' is not a pointer and cannot be " 200 | "dereferenced.", 201 | expr->children[0]->node_token.text); 202 | put_error(buffer, 0, expr->children[0]->node_token); 203 | } 204 | return v->pointing_to->type; 205 | } 206 | if (expr->children[0]->node_token.type == NUMBER) 207 | { 208 | return mkstr("i32?"); // question mark denotes literal 209 | } 210 | if (expr->children[0]->node_token.type == STRING) 211 | { 212 | if (strlen(expr->children[0]->node_token.text) == 1) 213 | { 214 | return mkstr("u8?"); 215 | } 216 | return mkstr("ptr8"); 217 | } 218 | } 219 | } 220 | 221 | node *eval(node *x, node *parent) 222 | { 223 | if (x->type == BASICEXPRESSION) 224 | { 225 | return x; 226 | } 227 | switch (x->type) 228 | { 229 | case BINEXPR: 230 | { 231 | node *op = x->children[0]; 232 | node *left = op->children[0]; 233 | node *right = op->children[1]; 234 | if (!has_child_recursive(x, BASICEXPRESSION) && 235 | left->type != BASICEXPRESSION || 236 | right->type != BASICEXPRESSION) 237 | { 238 | return x; 239 | } 240 | if (left->type != BASICEXPRESSION) 241 | { 242 | left = eval(left, op); 243 | } 244 | if (right->type != BASICEXPRESSION) 245 | { 246 | right = eval(right, op); 247 | } 248 | left = left->children[0]; 249 | right = right->children[0]; 250 | if (left->node_token.type == ID || right->node_token.type == ID) 251 | { 252 | return x; 253 | } 254 | switch (op->node_token.text[0]) 255 | { 256 | case '+': 257 | { 258 | if (left->node_token.type == NUMBER && 259 | right->node_token.type == NUMBER) 260 | { 261 | int value = atoi(left->node_token.text) + 262 | atoi(right->node_token.text); 263 | char *buf = malloc(32); 264 | sprintf(buf, "%d", value); 265 | node *x = 266 | create_arbitrary_node(BASICEXPRESSION, parent); 267 | node *n = create_node( 268 | TOKENNODE, 269 | create_token(left->node_token.col, 270 | left->node_token.row, buf, NUMBER), 271 | x); 272 | append_child(x, n); 273 | return x; 274 | } 275 | put_error_incompatible_operation( 276 | "+", token_type_to_string(left->node_token.type), 277 | token_type_to_string(right->node_token.type), right); 278 | } 279 | break; 280 | case '-': 281 | { 282 | if (left->node_token.type == NUMBER && 283 | right->node_token.type == NUMBER) 284 | { 285 | int value = atoi(left->node_token.text) - 286 | atoi(right->node_token.text); 287 | char *buf = malloc(32); 288 | sprintf(buf, "%d", value); 289 | node *x = 290 | create_arbitrary_node(BASICEXPRESSION, parent); 291 | node *n = create_node( 292 | TOKENNODE, 293 | create_token(left->node_token.col, 294 | left->node_token.row, buf, NUMBER), 295 | x); 296 | append_child(x, n); 297 | return x; 298 | } 299 | put_error_incompatible_operation( 300 | "-", token_type_to_string(left->node_token.type), 301 | token_type_to_string(right->node_token.type), right); 302 | } 303 | break; 304 | case '/': 305 | { 306 | if (left->node_token.type == NUMBER && 307 | right->node_token.type == NUMBER) 308 | { 309 | if (atoi(right->node_token.text) == 0) 310 | { 311 | put_error(mkstr("Attempt to divide by zero."), 0, 312 | right->node_token); 313 | } 314 | int value = atoi(left->node_token.text) / 315 | atoi(right->node_token.text); 316 | char *buf = malloc(32); 317 | sprintf(buf, "%d", value); 318 | node *x = 319 | create_arbitrary_node(BASICEXPRESSION, parent); 320 | node *n = create_node( 321 | TOKENNODE, 322 | create_token(left->node_token.col, 323 | left->node_token.row, buf, NUMBER), 324 | x); 325 | append_child(x, n); 326 | return x; 327 | } 328 | put_error_incompatible_operation( 329 | "/", token_type_to_string(left->node_token.type), 330 | token_type_to_string(right->node_token.type), right); 331 | } 332 | case '*': 333 | { 334 | if (left->node_token.type == NUMBER && 335 | right->node_token.type == NUMBER) 336 | { 337 | int value = atoi(left->node_token.text) * 338 | atoi(right->node_token.text); 339 | char *buf = malloc(32); 340 | sprintf(buf, "%d", value); 341 | node *x = 342 | create_arbitrary_node(BASICEXPRESSION, parent); 343 | node *n = create_node( 344 | TOKENNODE, 345 | create_token(left->node_token.col, 346 | left->node_token.row, buf, NUMBER), 347 | x); 348 | append_child(x, n); 349 | return x; 350 | } 351 | put_error_incompatible_operation( 352 | "*", token_type_to_string(left->node_token.type), 353 | token_type_to_string(right->node_token.type), right); 354 | } 355 | case '=': 356 | { 357 | if (left->node_token.type == STRING && 358 | right->node_token.type == STRING) 359 | { 360 | char *buf = malloc(32); 361 | sprintf(buf, "%d", 362 | !strcmp(left->node_token.text, 363 | right->node_token.text)); 364 | node *x = 365 | create_arbitrary_node(BASICEXPRESSION, parent); 366 | node *n = create_node( 367 | TOKENNODE, 368 | create_token(left->node_token.col, 369 | left->node_token.row, buf, NUMBER), 370 | x); 371 | append_child(x, n); 372 | return x; 373 | } 374 | if (left->node_token.type == NUMBER && 375 | right->node_token.type == NUMBER) 376 | { 377 | int value = atoi(left->node_token.text) == 378 | atoi(right->node_token.text); 379 | char *buf = malloc(32); 380 | sprintf(buf, "%d", value); 381 | node *x = 382 | create_arbitrary_node(BASICEXPRESSION, parent); 383 | node *n = create_node( 384 | TOKENNODE, 385 | create_token(left->node_token.col, 386 | left->node_token.row, buf, NUMBER), 387 | x); 388 | append_child(x, n); 389 | return x; 390 | } 391 | put_error_incompatible_operation( 392 | "==", token_type_to_string(left->node_token.type), 393 | token_type_to_string(right->node_token.type), right); 394 | } 395 | } 396 | } 397 | default: 398 | return 0; 399 | } 400 | } 401 | 402 | bool type_check_tree(node *current, typechecker *type_checker) 403 | { 404 | start: 405 | if (!current) 406 | { 407 | return true; 408 | } 409 | switch (current->type) 410 | { 411 | case RETURN: 412 | { 413 | node *func_parent = get_parent(current, FUNCTION)->children[1]; 414 | variable *v = get_var( 415 | type_checker, current->node_token.text, type_checker->scope, 416 | get_function(type_checker, func_parent->node_token.text)); 417 | if (!v) 418 | { 419 | char *buffer = malloc(1024); 420 | sprintf(buffer, "Variable '%s' does not exist.\n", 421 | current->node_token.text); 422 | } 423 | if (strcmp(v->type, 424 | get_function(type_checker, func_parent->node_token.text) 425 | ->type)) 426 | { 427 | char *buffer = malloc(1024); 428 | sprintf(buffer, 429 | "Function '%s' expects a return type of '%s' but was " 430 | "given a '%s'.", 431 | func_parent->node_token.text, 432 | get_function(type_checker, func_parent->node_token.text) 433 | ->type, 434 | v->type); 435 | } 436 | } 437 | case LABEL_NODE: 438 | { 439 | bool found = false; 440 | for (size_t i = 0; i < type_checker->n_label; ++i) 441 | { 442 | if (!strcmp(type_checker->labels[i], current->node_token.text)) 443 | { 444 | found = true; 445 | } 446 | } 447 | if (found) 448 | { 449 | char *buffer = malloc(1024); 450 | sprintf(buffer, "Label '%s' already exists.", 451 | current->node_token.text); 452 | put_error(buffer, 0, current->node_token); 453 | } 454 | type_checker->labels = 455 | realloc(type_checker->labels, 456 | (++type_checker->n_label) * sizeof(char *)); 457 | type_checker->labels[type_checker->n_label - 1] = 458 | current->node_token.text; 459 | } 460 | break; 461 | case GOTO: 462 | { 463 | bool found = false; 464 | for (size_t i = 0; i < type_checker->n_label; ++i) 465 | { 466 | if (!strcmp(type_checker->labels[i], current->node_token.text)) 467 | { 468 | found = true; 469 | } 470 | } 471 | if (!found) 472 | { 473 | char *buffer = malloc(1024); 474 | sprintf(buffer, "Label '%s' doesn't exist.", 475 | current->node_token.text); 476 | put_error(buffer, 0, current->node_token); 477 | } 478 | } 479 | break; 480 | case BINEXPR: 481 | { 482 | current = eval(current, current->parent); 483 | if (current->type == BINEXPR) 484 | { 485 | goto end; 486 | } 487 | goto start; 488 | } 489 | break; 490 | case WHILE: 491 | { 492 | char *type = get_type_recursive(type_checker, current->children[0]); 493 | if (!type || (strcmp(type, "i32") && 494 | (!starts_with(type, "i") && !starts_with(type, "u") && 495 | type[strlen(type)] == '?'))) 496 | { 497 | char *buffer = malloc(1024); 498 | sprintf(buffer, 499 | "While loops can only be used using enumerable " 500 | "conditions. You gave a type '%s' but a while loop " 501 | "requires an integer type.", 502 | type); 503 | put_error(buffer, 0, current->children[0]->node_token); 504 | } 505 | } 506 | break; 507 | case EXTERN: 508 | { 509 | for (size_t i = 0; i < type_checker->n_func; ++i) 510 | { 511 | if (!strcmp(type_checker->functions[i].title, 512 | current->children[0]->node_token.text)) 513 | { 514 | char *msg = (char *)malloc(1024); 515 | memset(msg, 0, 1024); 516 | strcat(msg, "Function '"); 517 | strcat(msg, type_checker->functions[i].title); 518 | strcat(msg, "' has been redefined."); 519 | put_error(msg, 0, current->children[1]->node_token); 520 | } 521 | } 522 | // Extern is sort of a black box for the compiler, we have no idea 523 | // what is actually going on, since this links to any non-lowfish 524 | // function. 525 | printf("WARNING: UNSAFE FUNCTION DEFINITION FOR '%s': %s", 526 | current->children[0]->node_token.text, 527 | " The type checker is unable to check functions used from " 528 | "extern make sure that you match the argument count and " 529 | "type.\n"); 530 | type_checker->functions = 531 | realloc(type_checker->functions, 532 | (++type_checker->n_func) * sizeof(function)); 533 | char *buff = calloc(1, strlen(current->children[0]->node_token.text) + 1); 534 | int i = 0; 535 | int n = 0; 536 | for (i = 1; i < strlen(current->children[0]->node_token.text) - 1; ++i) 537 | { 538 | printf("%c\n", current->children[0]->node_token.text[i]); 539 | buff[n] = current->children[0]->node_token.text[i]; 540 | ++n; 541 | } 542 | printf("thing:%d\n", buff); 543 | type_checker->functions[type_checker->n_func - 1] = 544 | (function){buff, "unk", -1}; 545 | } 546 | break; 547 | case FUNCTION: 548 | { 549 | for (size_t i = 0; i < type_checker->n_func; ++i) 550 | { 551 | if (!strcmp(type_checker->functions[i].title, 552 | current->children[1]->node_token.text)) 553 | { 554 | char *msg = (char *)malloc(1024); 555 | memset(msg, 0, 1024); 556 | strcat(msg, "Function '"); 557 | strcat(msg, type_checker->functions[i].title); 558 | strcat(msg, "' has been redefined."); 559 | put_error(msg, 0, current->children[1]->node_token); 560 | } 561 | } 562 | type_checker->functions = 563 | realloc(type_checker->functions, 564 | (++type_checker->n_func) * sizeof(function)); 565 | type_checker->functions[type_checker->n_func - 1] = (function){ 566 | current->children[1]->node_token.text, 567 | current->children[0]->node_token.text, current->n_child - 3}; 568 | } 569 | break; 570 | case FUNCTION_CALL: 571 | { 572 | bool found = false; 573 | size_t index = 0; 574 | for (size_t i = 0; i < type_checker->n_func; ++i) 575 | { 576 | if (!strcmp(type_checker->functions[i].title, 577 | current->node_token.text)) 578 | { 579 | found = true; 580 | index = i; 581 | } 582 | } 583 | if (!found) 584 | { 585 | char *buffer = malloc(1024); 586 | memset(buffer, 0, 1024); 587 | sprintf(buffer, "Function '%s' doesn't exist.", 588 | current->node_token.text); 589 | put_error(buffer, 0, current->node_token); 590 | free(buffer); 591 | } 592 | 593 | if (type_checker->functions[index].n_args == -1) 594 | { 595 | /* 596 | This is done because -1 means the function is externed and I 597 | cant type check it. 598 | */ 599 | goto end; 600 | } 601 | if (current->n_child > type_checker->functions[index].n_args) 602 | { 603 | char *buffer = malloc(1024); 604 | memset(buffer, 0, 1024); 605 | sprintf(buffer, "To many args for Function '%s'.", 606 | current->node_token.text); 607 | put_error(buffer, 0, current->node_token); 608 | free(buffer); 609 | } 610 | if (current->n_child < type_checker->functions[index].n_args) 611 | { 612 | char *buffer = malloc(1024); 613 | memset(buffer, 0, 1024); 614 | sprintf(buffer, "To few args for Function '%s'.", 615 | current->node_token.text); 616 | put_error(buffer, 0, current->node_token); 617 | free(buffer); 618 | } 619 | } 620 | break; 621 | case VARDECL: 622 | { 623 | node *type = get_child_recursive(current, TYPE); 624 | node *title = get_child_recursive(current, TOKENNODE); 625 | node *func = get_parent(current, FUNCTION)->children[1]; 626 | if (!func) 627 | { 628 | printf("HOW IS THIS POSSIBLE???\n"); 629 | exit(9001); // hehe over 9000 630 | } 631 | variable v = 632 | (variable){title->node_token.text, type->node_token.text, 633 | type_checker->scope, 634 | get_function(type_checker, func->node_token.text)}; 635 | if (!type_checker->variables) 636 | { 637 | type_checker->variables = malloc(sizeof(variable)); 638 | *type_checker->variables = v; 639 | type_checker->n_var = 1; 640 | } 641 | else 642 | { 643 | type_checker->variables = 644 | realloc(type_checker->variables, 645 | sizeof(variable) * (type_checker->n_var + 1)); 646 | type_checker->variables[type_checker->n_var] = v; 647 | type_checker->n_var++; 648 | } 649 | } 650 | break; 651 | case ASSIGNMENT: 652 | { 653 | if (current->node_token.type == DEREF) 654 | { 655 | node *title = get_child_recursive(current, TOKENNODE); 656 | node *node_func = get_parent(current, FUNCTION)->children[1]; 657 | function *func = 658 | get_function(type_checker, node_func->node_token.text); 659 | variable *var = get_var(type_checker, title->node_token.text, 660 | type_checker->scope, func); 661 | if (!var) 662 | { 663 | // no need to free because put_error exits the program. 664 | char *buffer = malloc(1024); 665 | sprintf(buffer, 666 | "The variable you are trying to use '%s' does not " 667 | "exist.", 668 | title->node_token.text); 669 | put_error(buffer, 0, title->node_token); 670 | } 671 | if (!var->pointing_to) 672 | { 673 | char *buffer = malloc(1024); 674 | sprintf(buffer, 675 | "Variable '%s' is not a pointer and cannot be " 676 | "dereferenced.", 677 | var->title); 678 | put_error(buffer, 0, title->node_token); 679 | } 680 | } 681 | if (has_child_recursive(current, FUNCTION_CALL)) 682 | { 683 | node *call = get_child_recursive(current, FUNCTION_CALL); 684 | node *title = get_child_recursive(current, TOKENNODE); 685 | node *node_func = get_parent(current, FUNCTION)->children[1]; 686 | function *func = 687 | get_function(type_checker, node_func->node_token.text); 688 | variable *var = get_var(type_checker, title->node_token.text, 689 | type_checker->scope, func); 690 | if (!var) 691 | { 692 | // no need to free because put_error exits the program. 693 | char *buffer = malloc(1024); 694 | sprintf(buffer, 695 | "The variable you are trying to use '%s' does not " 696 | "exist.", 697 | title->node_token.text); 698 | put_error(buffer, 0, title->node_token); 699 | } 700 | if (func) 701 | { 702 | if (var) 703 | { 704 | if (strcmp(var->type, func->type)) 705 | { 706 | put_error_incompatible_types_assignment( 707 | var->type, func->type, 708 | call); // gotta be careful since some tokens 709 | // dont have a line number and column 710 | // stupid me I should've thougth a small 711 | // bit.. 712 | } 713 | } 714 | } 715 | // if the function doesnt exist then later on when the type 716 | // checker actually gets to the function call an error will be 717 | // shown. 718 | } 719 | else if (has_child_recursive( 720 | current, 721 | BASICEXPRESSION)) // remember that damn else if 722 | { 723 | node *basic_expr = 724 | get_child_recursive(current, BASICEXPRESSION)->children[0]; 725 | if (basic_expr->node_token.type == ID) 726 | { 727 | node *title = get_child_recursive(current, TOKENNODE); 728 | node *node_func = 729 | get_parent(current, FUNCTION)->children[1]; 730 | function *func = 731 | get_function(type_checker, node_func->node_token.text); 732 | variable *var = 733 | get_var(type_checker, title->node_token.text, 734 | type_checker->scope, func); 735 | variable *var_get = 736 | get_var(type_checker, basic_expr->node_token.text, 737 | type_checker->scope, func); 738 | if (!var) 739 | { 740 | // no need to free because put_error exits the program. 741 | char *buffer = malloc(1024); 742 | sprintf(buffer, 743 | "The variable you are trying to use '%s' does " 744 | "not exist.", 745 | title->node_token.text); 746 | put_error(buffer, 0, title->node_token); 747 | } 748 | if (!var_get) 749 | { 750 | // no need to free because put_error exits the program. 751 | char *buffer = malloc(1024); 752 | sprintf(buffer, 753 | "The variable you are trying to use '%s' does " 754 | "not exist.", 755 | basic_expr->node_token.text); 756 | put_error(buffer, 0, basic_expr->node_token); 757 | } 758 | if (strcmp(var->type, var_get->type)) 759 | { 760 | put_error_incompatible_types_assignment( 761 | var->type, var_get->type, basic_expr); 762 | } 763 | } 764 | else if (basic_expr->node_token.type == DEREF) 765 | { 766 | node *title = get_child_recursive(current, TOKENNODE); 767 | node *node_func = 768 | get_parent(current, FUNCTION)->children[1]; 769 | function *func = 770 | get_function(type_checker, node_func->node_token.text); 771 | variable *var = 772 | get_var(type_checker, title->node_token.text, 773 | type_checker->scope, func); 774 | variable *var_get = 775 | get_var(type_checker, basic_expr->node_token.text, 776 | type_checker->scope, func); 777 | if (!var) 778 | { 779 | // no need to free because put_error exits the program. 780 | char *buffer = malloc(1024); 781 | sprintf(buffer, 782 | "The variable you are trying to use '%s' does " 783 | "not exist.", 784 | title->node_token.text); 785 | put_error(buffer, 0, title->node_token); 786 | } 787 | if (!var_get) 788 | { 789 | // no need to free because put_error exits the program. 790 | char *buffer = malloc(1024); 791 | sprintf(buffer, 792 | "The variable you are trying to use '%s' does " 793 | "not exist.", 794 | basic_expr->node_token.text); 795 | put_error(buffer, 0, basic_expr->node_token); 796 | } 797 | if (title->node_token.type == DEREF) 798 | { 799 | var = var->pointing_to; 800 | } 801 | if (!var_get->pointing_to) 802 | { 803 | char *buffer = malloc(1024); 804 | sprintf(buffer, 805 | "Variable '%s' is not a pointer and cannot be " 806 | "dereferenced.", 807 | var_get->title); 808 | put_error(buffer, 0, basic_expr->node_token); 809 | } 810 | if (strcmp(var->type, var_get->pointing_to->type)) 811 | { 812 | printf("'%s', '%s'\n", var->type, var_get->type); 813 | put_error_incompatible_types_assignment( 814 | var->type, var_get->pointing_to->type, basic_expr); 815 | } 816 | } 817 | else if (basic_expr->node_token.type == REF) 818 | { 819 | node *title = get_child_recursive(current, TOKENNODE); 820 | node *node_func = 821 | get_parent(current, FUNCTION)->children[1]; 822 | function *func = 823 | get_function(type_checker, node_func->node_token.text); 824 | variable *var = 825 | get_var(type_checker, title->node_token.text, 826 | type_checker->scope, func); 827 | variable *var_get = 828 | get_var(type_checker, basic_expr->node_token.text, 829 | type_checker->scope, func); 830 | if (!var) 831 | { 832 | // no need to free because put_error exits the program. 833 | char *buffer = malloc(1024); 834 | sprintf(buffer, 835 | "The variable you are trying to use '%s' does " 836 | "not exist.", 837 | title->node_token.text); 838 | put_error(buffer, 0, title->node_token); 839 | } 840 | if (!var_get) 841 | { 842 | char *buffer = malloc(1024); 843 | sprintf(buffer, 844 | "The variable you are trying to use '%s' does " 845 | "not exist.", 846 | basic_expr->node_token.text); 847 | put_error(buffer, 0, basic_expr->node_token); 848 | } 849 | if (title->node_token.type == DEREF) 850 | { 851 | var = var->pointing_to; 852 | } 853 | if (var_get->type && (!strcmp("u8", var_get->type) || 854 | !strcmp("i8", var_get->type))) 855 | { 856 | if (strcmp(var->type, "ptr8")) 857 | { 858 | put_error_incompatible_types_assignment( 859 | var->type, "ptr8", basic_expr); 860 | } 861 | var->pointing_to = var_get; 862 | } 863 | 864 | if (var_get->type && (!strcmp("u16", var_get->type) || 865 | !strcmp("i16", var_get->type))) 866 | { 867 | if (strcmp(var->type, "ptr16")) 868 | { 869 | put_error_incompatible_types_assignment( 870 | var->type, "ptr16", basic_expr); 871 | } 872 | var->pointing_to = var_get; 873 | } 874 | 875 | if (var_get->type && (!strcmp("u32", var_get->type) || 876 | !strcmp("i32", var_get->type))) 877 | { 878 | if (strcmp(var->type, "ptr32")) 879 | { 880 | put_error_incompatible_types_assignment( 881 | var->type, "ptr32", basic_expr); 882 | } 883 | var->pointing_to = var_get; 884 | } 885 | 886 | if (starts_with(var_get->type, "ptr")) 887 | { 888 | if (strcmp(var->type, "ptr")) 889 | { 890 | put_error_incompatible_types_assignment( 891 | var->type, "ptr", basic_expr); 892 | } 893 | var->pointing_to = var_get; 894 | } 895 | } 896 | else if (basic_expr->node_token.type == STRING) 897 | { 898 | node *title = get_child_recursive(current, TOKENNODE); 899 | node *node_func = 900 | get_parent(current, FUNCTION)->children[1]; 901 | function *func = 902 | get_function(type_checker, node_func->node_token.text); 903 | variable *var = 904 | get_var(type_checker, title->node_token.text, 905 | type_checker->scope, func); 906 | if (!var) 907 | { 908 | // no need to free because put_error exits the program. 909 | char *buffer = malloc(1024); 910 | sprintf(buffer, 911 | "The variable you are trying to use '%s' does " 912 | "not exist.", 913 | title->node_token.text); 914 | put_error(buffer, 0, title->node_token); 915 | } 916 | if (title->node_token.type == DEREF) 917 | { 918 | var = var->pointing_to; 919 | } 920 | if (strlen(basic_expr->node_token.text) == 1) 921 | { 922 | // "a" is a char or a string 923 | // "aa" is a string, the distinction is multiple 924 | // characters. strings dont exist tho so we use 'ptr8' 925 | // which is alot more descriptive. 926 | if (strcmp(var->type, "u8") && 927 | strcmp(var->type, "i8") && 928 | strcmp(var->type, "ptr8")) 929 | { 930 | put_error_incompatible_types_assignment( 931 | var->type, "u8", basic_expr); 932 | } 933 | } 934 | else if (strcmp(var->type, "ptr8")) 935 | { 936 | put_error_incompatible_types_assignment( 937 | var->type, "ptr8", basic_expr); 938 | } 939 | } 940 | else if (basic_expr->node_token.type == NUMBER) 941 | { 942 | node *title = get_child_recursive(current, TOKENNODE); 943 | node *node_func = 944 | get_parent(current, FUNCTION)->children[1]; 945 | function *func = 946 | get_function(type_checker, node_func->node_token.text); 947 | variable *var = 948 | get_var(type_checker, title->node_token.text, 949 | type_checker->scope, func); 950 | if (title->node_token.type == DEREF) 951 | { 952 | var = var->pointing_to; 953 | } 954 | if (strcmp(var->type, "i32") && strcmp(var->type, "i16") && 955 | strcmp(var->type, "i8") && strcmp(var->type, "u8") && 956 | strcmp(var->type, "u16") && strcmp(var->type, "u32")) 957 | { 958 | put_error_incompatible_types_assignment( 959 | var->type, "i32", basic_expr); 960 | } 961 | } 962 | } 963 | } 964 | break; 965 | } 966 | end: 967 | for (size_t i = 0; i != current->n_child; ++i) 968 | { 969 | type_check_tree(current->children[i], type_checker); 970 | } 971 | return true; 972 | } 973 | -------------------------------------------------------------------------------- /src/typechecker/typechecker.h: -------------------------------------------------------------------------------- 1 | #ifndef TYPE_CHECKER_H 2 | 3 | #define TYPE_CHECKER_H 4 | #include "../parser/parser.h" 5 | 6 | typedef struct 7 | { 8 | char *title; 9 | char *type; 10 | size_t n_args; // -1 means unknown, like for a C function. 11 | } function; 12 | 13 | typedef struct var 14 | { 15 | char *title; 16 | char *type; 17 | size_t scope; 18 | function *func; 19 | struct var *pointing_to; 20 | } variable; 21 | 22 | typedef struct 23 | { 24 | size_t n_func; 25 | function *functions; 26 | size_t n_var; 27 | variable *variables; 28 | size_t n_label; 29 | char **labels; 30 | size_t scope; 31 | } typechecker; 32 | 33 | bool type_check_tree(node *tree, typechecker *type_checker); 34 | void restructure_parents(node *tree); 35 | function *get_function(typechecker *type_checker, char *title); 36 | 37 | variable *get_var(typechecker *type_checker, char *title, size_t scope, 38 | function *func); 39 | char *get_type_recursive(typechecker *type_checker, node *expr); 40 | node *eval(node *x, node *parent); 41 | #endif 42 | -------------------------------------------------------------------------------- /src/util.c: -------------------------------------------------------------------------------- 1 | #include "util.h" 2 | #include 3 | #include 4 | 5 | char *read_file(char *path) 6 | { 7 | FILE *ptr; 8 | char ch; 9 | ptr = fopen(path, "r"); 10 | if (ptr == NULL) 11 | { 12 | printf("Couldn't read file '%s'\n", path); 13 | } 14 | size_t len = 0; 15 | do 16 | { 17 | ch = fgetc(ptr); 18 | ++len; 19 | } while (ch != EOF); 20 | char *output = malloc(len); 21 | size_t i = 0; 22 | fclose(ptr); 23 | ptr = fopen(path, "r"); 24 | while (i < len) 25 | { 26 | output[i] = fgetc(ptr); 27 | ++i; 28 | } 29 | output[len - 1] = 0; 30 | return output; 31 | } 32 | 33 | inline void **append(void **buffer, void *data, size_t len) 34 | { 35 | buffer = realloc(buffer, len + 1); 36 | buffer[len] = data; 37 | return buffer; 38 | } 39 | void print_n_times(char *string, int n) 40 | { 41 | for (int i = 0; i != n; ++i) 42 | { 43 | printf("%s", string); 44 | } 45 | } -------------------------------------------------------------------------------- /src/util.h: -------------------------------------------------------------------------------- 1 | #ifndef UTIL_H 2 | 3 | #define UTIL_H 4 | 5 | #include 6 | #include 7 | #include 8 | #include 9 | 10 | #define true 1 11 | #define false 0 12 | 13 | char *read_file(char *path); 14 | 15 | void **append(void **buffer, void *data, size_t len); 16 | 17 | void print_n_times(char *string, int n); 18 | 19 | #endif 20 | -------------------------------------------------------------------------------- /test.lf: -------------------------------------------------------------------------------- 1 | extern("printf"); 2 | i32 main() 3 | { 4 | printf("Hello, World"); 5 | } -------------------------------------------------------------------------------- /tests/few_call.lf: -------------------------------------------------------------------------------- 1 | i32 x(i32 a) 2 | { 3 | return a; 4 | } 5 | 6 | i32 main() 7 | { 8 | x(); 9 | } 10 | -------------------------------------------------------------------------------- /tests/fun.lf: -------------------------------------------------------------------------------- 1 | i32 main(i32 argc, ptr argv) 2 | { 3 | } 4 | 5 | -------------------------------------------------------------------------------- /tests/fun.lf.expected: -------------------------------------------------------------------------------- 1 | 2 | { 3 | 4 | { 5 | 6 | 7 | 8 | { 9 | 10 | 11 | } 12 | 13 | { 14 | 15 | 16 | } 17 | 18 | } 19 | } 20 | -------------------------------------------------------------------------------- /tests/funcall.lf: -------------------------------------------------------------------------------- 1 | i32 a() 2 | { 3 | i32 x = 0; 4 | return x; 5 | } 6 | i32 b() 7 | { 8 | a(); 9 | } 10 | -------------------------------------------------------------------------------- /tests/funcall.lf.expected: -------------------------------------------------------------------------------- 1 | 2 | { 3 | 4 | { 5 | 6 | 7 | 8 | { 9 | 10 | { 11 | 12 | { 13 | 14 | 15 | { 16 | 17 | 18 | { 19 | 20 | } 21 | } 22 | } 23 | } 24 | 25 | { 26 | 27 | } 28 | } 29 | } 30 | 31 | { 32 | 33 | 34 | 35 | { 36 | 37 | { 38 | 39 | } 40 | } 41 | } 42 | } 43 | 44 | -------------------------------------------------------------------------------- /tests/test.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | def test(a): 4 | os.system(f"./lowfish tests/{a} > out.txt") 5 | f = open('out.txt', 'r') 6 | got = f.read() 7 | f2 = open(f'tests/{a}.expected', 'r') 8 | expected = f.read() 9 | f.close() 10 | f2.close() 11 | return [expected in got, a, got] 12 | 13 | def print_results(x): 14 | print(f'-- Tested file: {x[1]} --') 15 | print(f'-- Succeeded: {x[0]} --') 16 | if x[0] == False: 17 | print(f'-- What We got: \'\n{x[2]}\n\' --') 18 | 19 | dirs = list(filter((lambda a : a.endswith('.lf')), os.listdir('./tests/'))) 20 | results = list(map(test ,dirs)) 21 | list(map(print_results, results)) 22 | 23 | -------------------------------------------------------------------------------- /tests/variable.lf: -------------------------------------------------------------------------------- 1 | i32 main() 2 | { 3 | i32 x = 55; 4 | i8 y = 5; 5 | i32 z = x; 6 | } 7 | -------------------------------------------------------------------------------- /tests/variable.lf.expected: -------------------------------------------------------------------------------- 1 | 2 | { 3 | 4 | { 5 | 6 | 7 | 8 | { 9 | 10 | { 11 | 12 | { 13 | 14 | 15 | { 16 | 17 | 18 | { 19 | 20 | } 21 | } 22 | } 23 | } 24 | 25 | { 26 | 27 | { 28 | 29 | 30 | { 31 | 32 | 33 | { 34 | 35 | } 36 | } 37 | } 38 | } 39 | 40 | { 41 | 42 | { 43 | 44 | 45 | { 46 | 47 | 48 | { 49 | 50 | } 51 | } 52 | } 53 | } 54 | } 55 | } 56 | } 57 | -------------------------------------------------------------------------------- /tests/variable_func_call.lf: -------------------------------------------------------------------------------- 1 | i32 x(i32 a) 2 | { 3 | return a; 4 | } 5 | i32 main() 6 | { 7 | i32 b = 5; 8 | i32 n = x(a); 9 | } 10 | -------------------------------------------------------------------------------- /tests/variable_func_call.lf.expected: -------------------------------------------------------------------------------- 1 | 2 | { 3 | 4 | { 5 | 6 | 7 | 8 | { 9 | 10 | 11 | } 12 | 13 | { 14 | 15 | { 16 | 17 | } 18 | } 19 | } 20 | 21 | { 22 | 23 | 24 | 25 | { 26 | 27 | { 28 | 29 | { 30 | 31 | 32 | { 33 | 34 | 35 | { 36 | 37 | } 38 | } 39 | } 40 | } 41 | 42 | { 43 | 44 | { 45 | 46 | 47 | { 48 | 49 | 50 | { 51 | 52 | { 53 | 54 | } 55 | } 56 | } 57 | } 58 | } 59 | } 60 | } 61 | } 62 | 63 | --------------------------------------------------------------------------------