commit 553c87029f12e0aab4c3a4a240b898a76d268975 Author: Augusto Gunsch Date: Mon Jan 4 17:00:48 2021 -0300 Add compiler and vm-translator diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..68b6d45 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,3 @@ +*.h linguist-language=C +*.c linguist-language=C +Makefile -linguist-detectable diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..8728a54 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +jack-compiler +tags diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..52b51a6 --- /dev/null +++ b/Makefile @@ -0,0 +1,8 @@ +FILES = *.c */*.c +LIBRARIES = -lpthread +INCLUDES = -I. -I./parser/ -I./compiler/ -I./vm/ -I./tokenizer/ -I./misc/ +CFLAGS = -std=c99 -Wall +OUTFILE = jackc + +main: ${FILES} + ${CC} ${CFLAGS} ${LIBRARIES} ${INCLUDES} -o ${OUTFILE} ${FILES} diff --git a/README.md b/README.md new file mode 100644 index 0000000..d60c658 --- /dev/null +++ b/README.md @@ -0,0 +1,2 @@ +# jackc +Jack language compiler, but instead of producing ".vm" files, it produces binary ".hack" files straight away
diff --git a/compiler/compiler-expressions.c b/compiler/compiler-expressions.c new file mode 100644 index 0000000..27d4432 --- /dev/null +++ b/compiler/compiler-expressions.c @@ -0,0 +1,226 @@ +#include +#include +#include "compiler-expressions.h" +#include "compiler-util.h" + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +LINE* pushconstant(int n); +LINE* mathopln(char op); +LINE* pushthat(); +int countexpressions(EXPRESSIONLIST* explist); +char* toascii(char c); + +// Dealing with singular terms +LINEBLOCK* compilestrconst(char* str); +LINEBLOCK* compilekeywordconst(SCOPE* s, TERM* t); +LINEBLOCK* compilearrayitem(SCOPE* s, TERM* t); +LINEBLOCK* compilecallln(SCOPE* s, SUBROUTDEC* d, SUBROUTCALL* call); +LINEBLOCK* pushunaryopterm(SCOPE* s, TERM* t); +LINEBLOCK* compileterm(SCOPE* s, TERM* t); + +/* END FORWARD DECLARATIONS */ + + + +// Miscelaneous +LINE* mathopln(char op) { + if(op == '+') + return onetoken("add"); + if(op == '-') + return onetoken("sub"); + if(op == '=') + return onetoken("eq"); + if(op == '>') + return onetoken("gt"); + if(op == '<') + return onetoken("lt"); + if(op == '|') + return onetoken("or"); + if(op == '&') + return onetoken("and"); + if(op == '/') { + char* tokens[] = { "call", "Math.divide", "2" }; + return mkln(tokens); + } + char* tokens[] = { "call", "Math.multiply", "2" }; + return mkln(tokens); +} + +LINE* pushconstant(int n) { + char* tokens[] = { "push", "constant", itoa(n) }; + LINE* ln = mkln(tokens); + free(tokens[2]); + return ln; +} + +LINE* pushthat() { + char* pushthat[] = { "push", "that", "0" }; + return mkln(pushthat); +} + +int countexpressions(EXPRESSIONLIST* explist) { + int i = 0; + while(explist != NULL) { + i++; + explist = explist->next; + } + return i; +} + +char* toascii(char c) { + char* result = (char*)malloc(sizeof(char) * (countplaces(c) + 1)); + sprintf(result, "%i", c); + return result; +} + +// Dealing with singular terms +LINEBLOCK* compilestrconst(char* str) { + if(str[0] == '\0') + return NULL; + + char* pushchar[] = { "push", "constant", toascii(str[0]) }; + LINEBLOCK* blk = mklnblk(mksimpleln(pushchar, strcount(pushchar))); + free(pushchar[2]); + + char* appendchar[] = { "call", "String.appendChar", "2" }; + appendln(blk, mkln(appendchar)); + + int i = 1; + char c; + while(c = str[i], c != '\0') { + pushchar[2] = toascii(c); + appendln(blk, mksimpleln(pushchar, strcount(pushchar))); + free(pushchar[2]); + appendln(blk, mksimpleln(appendchar, strcount(appendchar))); + i++; + } + + char* strsize[] = { "push", "constant", itoa(i) }; + char* mknew[] = { "call", "String.new", "1" }; + appendlnbefore(blk, mkln(mknew)); + appendlnbefore(blk, mkln(strsize)); + free(strsize[2]); + + return blk; +} + +LINE* pushthisadd() { + char* pushthisadd[] = { "push", "pointer", "0" }; + return mkln(pushthisadd); +} + +LINE* pushfalse() { + return pushconstant(0); +} + +LINEBLOCK* pushtrue() { + LINEBLOCK* blk = mklnblk(pushfalse()); + appendln(blk, onetoken("not")); + return blk; +} + +LINEBLOCK* compilekeywordconst(SCOPE* s, TERM* t) { + if(!strcmp(t->string, "this")) return mklnblk(pushthisadd()); + if(!strcmp(t->string, "false")) return mklnblk(pushfalse()); + if(!strcmp(t->string, "true")) return pushtrue(); + return mklnblk(pushconstant(0)); +} + +LINEBLOCK* compilearrayitem(SCOPE* s, TERM* t) { + LINEBLOCK* blk = compileexpression(s, t->array->exp); + appendln(blk, pushvar(s, t->array->name)); + + appendln(blk, onetoken("add")); + + appendln(blk, popthatadd()); + appendln(blk, pushthat()); + + return blk; +} + +LINEBLOCK* compilecallln(SCOPE* s, SUBROUTDEC* d, SUBROUTCALL* call) { + LINE* ln = mkline(3); + + addtoken(ln, ezheapstr("call")); + + addtoken(ln, dotlabel(d->class->name, call->name)); + + int count = countexpressions(call->parameters); + if(d->subroutclass == method) + count++; + addtoken(ln, itoa(count)); + + return mklnblk(ln); +} + +LINEBLOCK* compilesubroutcall(SCOPE* s, SUBROUTCALL* call) { + VAR* v; + SUBROUTDEC* d = getsubroutdecfromcall(s, call, &v); + LINEBLOCK* blk = compilecallln(s, d, call); + + if(call->parameters != NULL) + blk = mergelnblks(compileexplist(s, call->parameters), blk); + + if(d->subroutclass == method) { + if(call->parentname == NULL) + appendlnbefore(blk, pushthisadd()); + else + appendlnbefore(blk, pushvarraw(s, v)); + } + + // void functions always return 0 + // therefore must be thrown away + if(!strcmp(d->type, "void")) { + appendln(blk, poptemp()); + } + + return blk; +} + +LINEBLOCK* pushunaryopterm(SCOPE* s, TERM* t) { + LINEBLOCK* blk = compileexpression(s, t->expression); + LINE* neg; + if(t->unaryop == '-') + neg = onetoken("neg"); + else + neg = onetoken("not"); + appendln(blk, neg); + return blk; +} + +LINEBLOCK* compileterm(SCOPE* s, TERM* t) { + if(t->type == varname) return mklnblk(pushvar(s, t->string)); + if(t->type == intconstant) return mklnblk(pushconstant(t->integer)); + if(t->type == stringconstant) return compilestrconst(t->string); + if(t->type == keywordconstant) return compilekeywordconst(s, t); + if(t->type == arrayitem) return compilearrayitem(s, t); + if(t->type == subroutcall) return compilesubroutcall(s, t->call); + if(t->type == innerexpression) return compileexpression(s, t->expression); + return pushunaryopterm(s, t); +} + +// Dealing with whole expressions +LINEBLOCK* compileexpression(SCOPE* s, TERM* e) { + LINEBLOCK* blk = NULL; + if(e != NULL) { + while(true) { + blk = mergelnblks(blk, compileterm(s, e)); + if(e->next == NULL) + break; + appendln(blk, mathopln(e->op)); + e = e->next; + } + } + return blk; +} + +LINEBLOCK* compileexplist(SCOPE* s, EXPRESSIONLIST* explist) { + LINEBLOCK* head = NULL; + while(explist != NULL) { + head = mergelnblks(head, compileexpression(s, explist->expression)); + explist = explist->next; + } + return head; +} diff --git a/compiler/compiler-expressions.h b/compiler/compiler-expressions.h new file mode 100644 index 0000000..01eccbf --- /dev/null +++ b/compiler/compiler-expressions.h @@ -0,0 +1,15 @@ +#ifndef COMPILER_EXPRESSIONS_H +#define COMPILER_EXPRESSIONS_H +#include "vm-lines.h" +#include "compiler.h" + +/* compiler-expressions + * Functions for dealing and compiling expressions and singular terms. */ + +// Dealing with singular terms +LINEBLOCK* compilesubroutcall(SCOPE* s, SUBROUTCALL* call); + +// Dealing with whole expressions +LINEBLOCK* compileexpression(SCOPE* s, TERM* e); +LINEBLOCK* compileexplist(SCOPE* s, EXPRESSIONLIST* explist); +#endif diff --git a/compiler/compiler-scopes.c b/compiler/compiler-scopes.c new file mode 100644 index 0000000..6f22673 --- /dev/null +++ b/compiler/compiler-scopes.c @@ -0,0 +1,310 @@ +#include +#include +#include +#include +#include "compiler.h" +#include "compiler-scopes.h" +#include "os.h" + +typedef enum { local, staticseg, arg, fieldseg } MEMSEGMENT; +char* memsegnames[] = { "local", "static", "argument", "this" }; + +// Error messages +void doubledeclaration(const char* name, DEBUGINFO* d1, DEBUGINFO* d2); +void ensurenoduplicate(SCOPE* s, char* name); + +// Getters +VAR* getvarinvars(VAR* vars, const char* name); +CLASS* getclass(SCOPE* s, const char* name); +SUBROUTDEC* getsubroutdecfromlist(SUBROUTDEC* start, char* name); +SUBROUTDEC* getmethod(SCOPE* s, VAR* parent, SUBROUTCALL* call); +SUBROUTDEC* getfunction(SCOPE* s, SUBROUTCALL* call); +SUBROUTDEC* getsubroutdecwithparent(SCOPE* s, SUBROUTCALL* call, VAR** varret); +SUBROUTDEC* getsubroutdecwithoutparent(SCOPE* s, SUBROUTCALL* call); +SUBROUTDEC* getsubroutdec(SCOPE* s, const char* name); + +// Scope adding +VAR* mkvar(char* type, char* name, bool primitive, DEBUGINFO* debug, MEMSEGMENT seg, int i); +void addvar(SCOPE* s, VAR** dest, VAR* v); +void addlocalvar(SCOPE* s, VARDEC* v, int* i); +void addstaticvar(SCOPE* s, CLASSVARDEC* v); +void addfield(SCOPE* s, CLASSVARDEC* v, int* i); +void addclassvardec(SCOPE* s, CLASSVARDEC* v, int* i); +void addparameter(SCOPE* s, PARAMETER* p, int* i); + +// Error messages +void doubledeclaration(const char* name, DEBUGINFO* d1, DEBUGINFO* d2) { + eprintf("Double declaration of '%s' at '%s', line %i; previously defined at '%s', line %i\n", + name, d1->file, d1->definedat, d2->file, d2->definedat); + exit(1); +} + +void notdeclared(const char* name, DEBUGINFO* debug) { + eprintf("'%s' not declared; file '%s', line %i\n", name, debug->file, debug->definedat); + exit(1); +} + +void invalidparent(SUBROUTCALL* call) { + eprintf("Invalid subroutine parent '%s'; file '%s', line %i\n", call->parentname, call->debug->file, call->debug->definedat); + exit(1); +} + +void ensurenoduplicate(SCOPE* s, char* name) { + VAR* v = getvar(s, name); + if(v != NULL) + doubledeclaration(name, s->currdebug, v->debug); + + CLASS* c = getclass(s, name); + if(c != NULL) + doubledeclaration(name, s->currdebug, c->debug); + + SUBROUTDEC* sr = getsubroutdec(s, name); + if(sr != NULL) + doubledeclaration(name, s->currdebug, sr->debug); +} + +// Scope handling +SCOPE* mkscope(SCOPE* prev) { + SCOPE* s = (SCOPE*)malloc(sizeof(SCOPE)); + s->previous = prev; + if(prev != NULL) + s->compiler = prev->compiler; + s->localvars = NULL; + s->fields = NULL; + s->staticvars = NULL; + s->parameters = NULL; + s->classes = NULL; + s->subroutines = NULL; + return s; +} + +// Getters +VAR* getvarinvars(VAR* vars, const char* name) { + while(vars != NULL) { + if(!strcmp(vars->name, name)) + return vars; + vars = vars->next; + } + return NULL; +} + +VAR* getvar(SCOPE* s, const char* name) { + VAR* var = getvarinvars(s->localvars, name); + if(var != NULL) + return var; + var = getvarinvars(s->parameters, name); + if(var != NULL) + return var; + var = getvarinvars(s->fields, name); + if(var != NULL) + return var; + var = getvarinvars(s->staticvars, name); + if(var != NULL) + return var; + if(s->previous != NULL) + return getvar(s->previous, name); + return NULL; +} + +CLASS* getclass(SCOPE* s, const char* name) { + CLASS* curr = s->classes; + while(curr != NULL) { + if(!strcmp(curr->name, name)) + return curr; + curr = curr->next; + } + if(s->previous != NULL) + return getclass(s->previous, name); + return getosclass(s->compiler->os, name); +} + +SUBROUTDEC* getsubroutdecfromlist(SUBROUTDEC* start, char* name) { + while(start != NULL) { + if(!strcmp(start->name, name)) + return start; + start = start->next; + } + return NULL; +} + +SUBROUTDEC* getmethod(SCOPE* s, VAR* parent, SUBROUTCALL* call) { + CLASS* c = getclass(s, parent->type); + SUBROUTDEC* d = getsubroutdecfromlist(c->subroutdecs, call->name); + if(d == NULL) + return NULL; + if(d->subroutclass != method) { + eprintf("Calling a function/constructor as if it were a method; file '%s', line %i\n", call->debug->file, call->debug->definedat); + exit(1); + } + return d; +} + +SUBROUTDEC* getfunction(SCOPE* s, SUBROUTCALL* call) { + CLASS* c = getclass(s, call->parentname); + if(c == NULL) + notdeclared(call->parentname, call->debug); + SUBROUTDEC* d = getsubroutdecfromlist(c->subroutdecs, call->name); + if(d == NULL) + return NULL; + if(d->subroutclass == method) { + eprintf("Calling a method as if it were a function; file '%s', line %i\n", call->debug->file, call->debug->definedat); + exit(1); + } + return d; +} + +SUBROUTDEC* getsubroutdecwithparent(SCOPE* s, SUBROUTCALL* call, VAR** varret) { + VAR* parent = getvar(s, call->parentname); + if(parent != NULL) { + if(parent->primitive) { + eprintf("Primitive type does not have subroutines; file '%s', line %i\n", call->debug->file, call->debug->definedat); + exit(1); + } + *varret = parent; + return getmethod(s, parent, call); + } + else + return getfunction(s, call); +} + +SUBROUTDEC* getsubroutdecwithoutparent(SCOPE* s, SUBROUTCALL* call) { + SUBROUTDEC* d = getsubroutdecfromlist(s->currclass->subroutdecs, call->name); + return d; +} + +SUBROUTDEC* getsubroutdecfromcall(SCOPE* s, SUBROUTCALL* call, VAR** varret) { + SUBROUTDEC* d; + *varret = NULL; + if(call->parentname != NULL) { + d = getossubroutdec(s->compiler->os, call); + if(d == NULL) + d = getsubroutdecwithparent(s, call, varret); + } + else { + d = getsubroutdecwithoutparent(s, call); + } + if(d == NULL) + notdeclared(call->name, call->debug); + return d; +} + +SUBROUTDEC* getsubroutdec(SCOPE* s, const char* name) { + SUBROUTDEC* curr = s->subroutines; + while(curr != NULL) { + if(!strcmp(curr->name, name)) + return curr; + curr = curr->next; + } + if(s->previous != NULL) + return getsubroutdec(s->previous, name); + return NULL; +} + +// Scope adding +VAR* mkvar(char* type, char* name, bool primitive, DEBUGINFO* debug, MEMSEGMENT seg, int i) { + VAR* v = (VAR*)malloc(sizeof(VAR)); + v->name = name; + v->type = type; + v->debug = debug; + v->memsegment = memsegnames[seg]; + v->primitive = primitive; + v->index = i; + return v; +} + +void addvar(SCOPE* s, VAR** dest, VAR* v) { + ensurenoduplicate(s, v->name); + + if(!v->primitive) { + CLASS* type = getclass(s, v->type); + if(type == NULL) + notdeclared(v->type, v->debug); + } + + v->next = *dest; + *dest = v; +} + +void addlocalvar(SCOPE* s, VARDEC* v, int* i) { + STRINGLIST* currname = v->names; + while(currname != NULL) { + addvar(s, &(s->localvars), mkvar(v->type, currname->content, v->primitive, v->debug, local, *i)); + currname = currname->next; + (*i)++; + } +} + +void addstaticvar(SCOPE* s, CLASSVARDEC* v) { + STRINGLIST* currname = v->base->names; + pthread_mutex_lock(&(s->compiler->staticmutex)); + static int i = 0; + while(currname != NULL) { + addvar(s, &(s->staticvars), mkvar(v->base->type, currname->content, v->base->primitive, v->base->debug, staticseg, i)); + currname = currname->next; + i++; + } + pthread_mutex_unlock(&(s->compiler->staticmutex)); +} + +void addfield(SCOPE* s, CLASSVARDEC* v, int* i) { + STRINGLIST* currname = v->base->names; + while(currname != NULL) { + addvar(s, &(s->fields), mkvar(v->base->type, currname->content, v->base->primitive, v->base->debug, fieldseg, *i)); + currname = currname->next; + (*i)++; + } +} + +void addclassvardec(SCOPE* s, CLASSVARDEC* v, int* i) { + if(v->type == stat) + addstaticvar(s, v); + else { + addfield(s, v, i); + } +} + +void addparameter(SCOPE* s, PARAMETER* p, int* i) { + addvar(s, &(s->parameters), mkvar(p->type, p->name, p->primitive, p->debug, arg, *i)); + (*i)++; +} + +// Group adding +void addclassvardecs(SCOPE* s, CLASSVARDEC* classvardecs) { + int i = 0; + while(classvardecs != NULL) { + addclassvardec(s, classvardecs, &i); + classvardecs = classvardecs->next; + } +} + +void addlocalvars(SCOPE* s, VARDEC* localvars) { + int i = 0; + while(localvars != NULL) { + addlocalvar(s, localvars, &i); + localvars = localvars->next; + } +} + +void addparameters(SCOPE* s, bool isformethod, PARAMETER* params) { + int i = isformethod ? 1 : 0; + while(params != NULL) { + addparameter(s, params, &i); + params = params->next; + } +} + +void freevars(VAR* v) { + if(v != NULL) { + VAR* next = v->next; + free(v); + freevars(next); + } +} + +void freescope(SCOPE* s) { + freevars(s->fields); + freevars(s->staticvars); + freevars(s->localvars); + freevars(s->parameters); + free(s); +}; diff --git a/compiler/compiler-scopes.h b/compiler/compiler-scopes.h new file mode 100644 index 0000000..1994f77 --- /dev/null +++ b/compiler/compiler-scopes.h @@ -0,0 +1,58 @@ +#ifndef COMPILER_SCOPES_H +#define COMPILER_SCOPES_H +#include "parser-tree.h" +#include "compiler.h" + +/* compiler-scopes + * Tools for dealing with scopes. + * + * They can be used to create, expand and stack scopes, as well as to enforce + * certain semantic rules. */ + +// Data types +typedef struct var { + DEBUGINFO* debug; + char* memsegment; + char* type; + char* name; + int index; + bool primitive; + struct var* next; +} VAR; + +typedef struct scope { + struct compiler* compiler; + DEBUGINFO* currdebug; + CLASS* currclass; + + CLASS* classes; + SUBROUTDEC* subroutines; + + VAR* fields; + VAR* staticvars; + VAR* localvars; + VAR* parameters; + + struct scope* previous; +} SCOPE; + +struct compiler; + +// Group adding +void addclassvardecs(SCOPE* s, CLASSVARDEC* classvardecs); +void addlocalvars(SCOPE* s, VARDEC* localvars); +void addparameters(SCOPE* s, bool isformethod, PARAMETER* params); + +// Scope handling +SCOPE* mkscope(SCOPE* prev); + +// Single type getters +SUBROUTDEC* getsubroutdecfromcall(SCOPE* s, SUBROUTCALL* call, VAR** varret); +CLASS* getclass(SCOPE* s, const char* name); + +// Generic getters +VAR* getvar(SCOPE* s, const char* name); + +// Freeing +void freescope(SCOPE* s); +#endif diff --git a/compiler/compiler-statements.c b/compiler/compiler-statements.c new file mode 100644 index 0000000..f25adcc --- /dev/null +++ b/compiler/compiler-statements.c @@ -0,0 +1,171 @@ +#include +#include +#include "compiler-expressions.h" +#include "compiler-statements.h" +#include "compiler-util.h" + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +LINE* popthat(); +LINE* pushtemp(); +char* mkcondlabel(char* name, int count); + +// Handling individual statements +LINEBLOCK* compileret(SCOPE* s, TERM* e); +LINEBLOCK* compileif(SCOPE* s, IFSTATEMENT* st); +LINEBLOCK* compilewhile(SCOPE* s, CONDSTATEMENT* w); +LINEBLOCK* compilelet(SCOPE* s, LETSTATEMENT* l); +LINEBLOCK* compilestatement(SCOPE* s, STATEMENT* st); + +/* END FORWARD DECLARATIONS */ + + + +// Miscelaneous +LINE* popthat() { + char* popthat[] = { "pop", "that", "0" }; + return mkln(popthat); +} + +LINE* pushtemp() { + char* pushtemp[] = { "push", "temp", "0" }; + return mkln(pushtemp); +} + +char* mkcondlabel(char* name, int count) { + int sz = (strlen(name) + countplaces(count) + 1) * sizeof(char); + char* result = (char*)malloc(sz); + sprintf(result, "%s%i", name, count); + return result; +} + +// Handling individual statements +LINEBLOCK* compileret(SCOPE* s, TERM* e) { + LINE* ret = onetoken("return"); + LINEBLOCK* blk = mklnblk(ret); + + // void subroutdecs return 0 + if(e == NULL) { + char* tokens[] = { "push", "constant", "0" }; + appendlnbefore(blk, mkln(tokens)); + } else + blk = mergelnblks(compileexpression(s, e), blk); + + return blk; +} + +LINEBLOCK* compileif(SCOPE* s, IFSTATEMENT* st) { + LINEBLOCK* blk = compileexpression(s, st->base->expression); + + pthread_mutex_lock(&(s->compiler->ifmutex)); + static int ifcount = 0; + int mycount = ifcount; + ifcount++; + pthread_mutex_unlock(&(s->compiler->ifmutex)); + + char* truelabel = mkcondlabel("IF_TRUE", mycount); + char* ifgoto[] = { "if-goto", truelabel }; + appendln(blk, mkln(ifgoto)); + + char* falselabel = mkcondlabel("IF_FALSE", mycount); + char* gotofalse[] = { "goto", falselabel }; + appendln(blk, mkln(gotofalse)); + + char* truelabelln[] = { "label", truelabel }; + appendln(blk, mkln(truelabelln)); + + blk = mergelnblks(blk, compilestatements(s, st->base->statements)); + + char* endlabel; + bool haselse = st->elsestatements != NULL; + if(haselse) { + endlabel = mkcondlabel("IF_END", mycount); + char* endgoto[] = { "goto", endlabel }; + appendln(blk, mkln(endgoto)); + } + + char* falselabelln[] = { "label", falselabel}; + appendln(blk, mkln(falselabelln)); + + if(haselse) { + blk = mergelnblks(blk, compilestatements(s, st->elsestatements)); + char* endlabelln[] = { "label", endlabel }; + appendln(blk, mkln(endlabelln)); + free(endlabel); + } + + free(falselabel); + free(truelabel); + + return blk; +} + +LINEBLOCK* compilewhile(SCOPE* s, CONDSTATEMENT* w) { + LINEBLOCK* blk = compileexpression(s, w->expression); + + pthread_mutex_lock(&(s->compiler->whilemutex)); + static int whilecount = 0; + int mycount = whilecount; + whilecount++; + pthread_mutex_unlock(&(s->compiler->whilemutex)); + + char* explabel = mkcondlabel("WHILE_EXP", mycount); + char* explabelln[] = { "label", explabel }; + appendlnbefore(blk, mkln(explabelln)); + + appendln(blk, onetoken("not")); + + char* endlabel = mkcondlabel("WHILE_END", mycount); + char* ifgoto[] = { "if-goto", endlabel }; + appendln(blk, mkln(ifgoto)); + + blk = mergelnblks(blk, compilestatements(s, w->statements)); + + char* gotoln[] = { "goto", explabel }; + appendln(blk, mkln(gotoln)); + + char* endlabelln[] = { "label", endlabel }; + appendln(blk, mkln(endlabelln)); + + free(explabel); + free(endlabel); + + return blk; +} + +LINEBLOCK* compilelet(SCOPE* s, LETSTATEMENT* l) { + LINEBLOCK* blk = compileexpression(s, l->expression); + + if(l->arrayind != NULL) { + appendlnbefore(blk, onetoken("add")); + appendlnbefore(blk, pushvar(s, l->varname)); + blk = mergelnblks(compileexpression(s, l->arrayind), blk); + + appendln(blk, poptemp()); + appendln(blk, popthatadd()); + appendln(blk, pushtemp()); + appendln(blk, popthat()); + } + else + appendln(blk, popvar(s, l->varname)); + return blk; +} + +LINEBLOCK* compilestatement(SCOPE* s, STATEMENT* st) { + s->currdebug = st->debug; + if(st->type == dostatement) return compilesubroutcall(s, st->dostatement); + if(st->type == returnstatement) return compileret(s, st->retstatement); + if(st->type == ifstatement) return compileif(s, st->ifstatement); + if(st->type == whilestatement) return compilewhile(s, st->whilestatement); + return compilelet(s, st->letstatement); +} + +LINEBLOCK* compilestatements(SCOPE* s, STATEMENT* sts) { + LINEBLOCK* head = NULL; + while(sts != NULL) { + head = mergelnblks(head, compilestatement(s, sts)); + sts = sts->next; + } + return head; +} diff --git a/compiler/compiler-statements.h b/compiler/compiler-statements.h new file mode 100644 index 0000000..f71273b --- /dev/null +++ b/compiler/compiler-statements.h @@ -0,0 +1,9 @@ +#ifndef COMPILER_STATEMENTS_H +#define COMPILER_STATEMENTS_H +#include "compiler.h" + +/* compiler-statements + * Single function for compiling statements */ + +LINEBLOCK* compilestatements(SCOPE* s, STATEMENT* sts); +#endif diff --git a/compiler/compiler-structure.c b/compiler/compiler-structure.c new file mode 100644 index 0000000..9fa5bb6 --- /dev/null +++ b/compiler/compiler-structure.c @@ -0,0 +1,135 @@ +#include +#include "compiler-statements.h" +#include "compiler-structure.h" +#include "compiler-util.h" + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +int countlocalvars(VARDEC* decs); +int countstrs(STRINGLIST* ls); +int getobjsize(CLASS* c); +LINE* mksubdeclabel(CLASS* c, SUBROUTDEC* sd); + +// Compiling methods +LINEBLOCK* compilefunbody(SCOPE* s, CLASS* cl, SUBROUTBODY* b); +LINEBLOCK* compilefundec(SCOPE* s, CLASS* cl, SUBROUTDEC* f); +LINEBLOCK* compileconstructor(SCOPE* s, CLASS* cl, SUBROUTDEC* con); +LINEBLOCK* compilemethod(SCOPE* s, CLASS* cl, SUBROUTDEC* m); + +/* END FORWARD DECLARATIONS */ + + +// Miscelaneous +int countlocalvars(VARDEC* decs) { + int i = 0; + while(decs != NULL) { + STRINGLIST* curr = decs->names; + while(curr != NULL) { + i++; + curr = curr->next; + } + decs = decs->next; + } + return i; +} + +int countstrs(STRINGLIST* ls) { + int count = 0; + while(ls != NULL) { + count++; + ls = ls->next; + } + return count; +} + +int getobjsize(CLASS* c) { + CLASSVARDEC* curr = c->vardecs; + int count = 0; + while(curr != NULL) { + if(curr->type == field) + count += countstrs(curr->base->names); + curr = curr->next; + } + return count; +} + +LINE* mksubdeclabel(CLASS* c, SUBROUTDEC* sd) { + char* labelstrs[] = { "function", dotlabel(c->name, sd->name), itoa(countlocalvars(sd->body->vardecs)) }; + LINE* label = mkln(labelstrs); + free(labelstrs[1]); + free(labelstrs[2]); + label->next = NULL; + return label; +} + +// Compiling methods +LINEBLOCK* compilefunbody(SCOPE* s, CLASS* cl, SUBROUTBODY* b) { + SCOPE* myscope = mkscope(s); + myscope->currclass = cl; + if(b->vardecs != NULL) + addlocalvars(myscope, b->vardecs); + LINEBLOCK* head = compilestatements(myscope, b->statements); + freescope(myscope); + return head; +} + +LINEBLOCK* compilefundec(SCOPE* s, CLASS* cl, SUBROUTDEC* f) { + LINE* label = mksubdeclabel(cl, f); + + if(f->body->statements != NULL) { + LINEBLOCK* body = compilefunbody(s, cl, f->body); + appendlnbefore(body, label); + return body; + } + else + return mklnblk(label); +} + +LINEBLOCK* compileconstructor(SCOPE* s, CLASS* cl, SUBROUTDEC* con) { + LINE* label = mksubdeclabel(cl, con); + LINEBLOCK* blk = mklnblk(label); + + char* size[] = { "push", "constant", itoa(getobjsize(cl)) }; + char* memalloc[] = { "call", "Memory.alloc", "1" }; + char* poppointer[] = { "pop", "pointer", "0" }; + appendln(blk, mkln(size)); + appendln(blk, mkln(memalloc)); + appendln(blk, mkln(poppointer)); + free(size[2]); + + if(con->body != NULL) + return mergelnblks(blk, compilefunbody(s, cl, con->body)); + else + return blk; +} + +LINEBLOCK* compilemethod(SCOPE* s, CLASS* cl, SUBROUTDEC* m) { + LINE* label = mksubdeclabel(cl, m); + LINEBLOCK* blk = mklnblk(label); + + char* pusharg0[] = { "push", "argument", "0" }; + char* poppointer[] = { "pop", "pointer", "0" }; + appendln(blk, mkln(pusharg0)); + appendln(blk, mkln(poppointer)); + + if(m->body != NULL) + return mergelnblks(blk, compilefunbody(s, cl, m->body)); + else + return blk; +} + +LINEBLOCK* compilesubroutdec(SCOPE* s, CLASS* cl, SUBROUTDEC* sd) { + SCOPE* myscope = mkscope(s); + LINEBLOCK* blk; + if(sd->parameters != NULL) + addparameters(myscope, sd->subroutclass == method, sd->parameters); + if(sd->subroutclass == function) + blk = compilefundec(myscope, cl, sd); + else if(sd->subroutclass == constructor) + blk = compileconstructor(myscope, cl, sd); + else + blk = compilemethod(myscope, cl, sd); + freescope(myscope); + return blk; +} diff --git a/compiler/compiler-structure.h b/compiler/compiler-structure.h new file mode 100644 index 0000000..c23d921 --- /dev/null +++ b/compiler/compiler-structure.h @@ -0,0 +1,9 @@ +#ifndef COMPILER_STRUCTURE_H +#define COMPILER_STRUCTURE_H +#include "compiler.h" + +/* compiler-structure + * Module for dealing with and compiling general program structure. */ + +LINEBLOCK* compilesubroutdec(SCOPE* s, CLASS* cl, SUBROUTDEC* sd); +#endif diff --git a/compiler/compiler-util.c b/compiler/compiler-util.c new file mode 100644 index 0000000..a699e3d --- /dev/null +++ b/compiler/compiler-util.c @@ -0,0 +1,51 @@ +#include +#include "compiler-util.h" + +LINE* opvarraw(SCOPE* s, char* op, VAR* v) { + char* tokens[] = { op, v->memsegment, itoa(v->index) }; + LINE* ln = mksimpleln(tokens, strcount(tokens)); + free(tokens[2]); + return ln; +} + +LINE* opvar(SCOPE* s, char* op, const char* name) { + VAR* v = getvar(s, name); + return opvarraw(s, op, v); +} + +LINE* pushvarraw(SCOPE*s, VAR* v) { + return opvarraw(s, "push", v); +} + +LINE* pushvar(SCOPE* s, const char* name) { + return opvar(s, "push", name); +} + +LINE* popvar(SCOPE* s, const char* name) { + return opvar(s, "pop", name); +} + +LINE* poptemp() { + char* poptemp[] = { "pop", "temp", "0" }; + return mksimpleln(poptemp, strcount(poptemp)); +} + +LINE* popthatadd() { + char* popthatadd[] = { "pop", "pointer", "1" }; + return mksimpleln(popthatadd, strcount(popthatadd)); +} + +LINE* onetoken(char* str) { + LINE* ln = mkline(1); + addtoken(ln, ezheapstr(str)); + ln->next = NULL; + return ln; +} + +LINE* mksimpleln(char** tokens, int count) { + LINE* ln = mkline(count); + for(int i = 0; i < count; i++) + addtoken(ln, ezheapstr(tokens[i])); + ln->next = NULL; + return ln; +} diff --git a/compiler/compiler-util.h b/compiler/compiler-util.h new file mode 100644 index 0000000..01fa4c2 --- /dev/null +++ b/compiler/compiler-util.h @@ -0,0 +1,21 @@ +#ifndef COMPILER_UTIL_H +#define COMPILER_UTIL_H +#include "vm-lines.h" +#include "compiler-scopes.h" +#include "compiler.h" + +/* compiler-util + * Random utilities used in the compiler module. */ + +#define mkln(id) mksimpleln(id, strcount(id)) + +LINE* onetoken(char* str); +LINE* mksimpleln(char** tokens, int count); + +LINE* pushvarraw(SCOPE*s, VAR* v); +LINE* pushvar(SCOPE* s, const char* name); +LINE* popvar(SCOPE* s, const char* name); +LINE* poptemp(); +LINE* popthatadd(); + +#endif diff --git a/compiler/compiler.c b/compiler/compiler.c new file mode 100644 index 0000000..e8e97d7 --- /dev/null +++ b/compiler/compiler.c @@ -0,0 +1,46 @@ +#include +#include "os.h" +#include "compiler-structure.h" +#include "compiler.h" + +/* This should be part of compiler-structure, but since it is used by other modules, + * it will stay here for convenience */ +LINEBLOCK* compileclass(COMPILER* c, CLASS* class) { + SCOPE* topscope = mkscope(c->globalscope); + if(class->vardecs != NULL) + addclassvardecs(topscope, class->vardecs); + if(class->subroutdecs != NULL) + topscope->subroutines = class->subroutdecs; + + LINEBLOCK* output = NULL; + SUBROUTDEC* curr = class->subroutdecs; + while(curr != NULL) { + output = mergelnblks(output, compilesubroutdec(topscope, class, curr)); + curr = curr->next; + } + freescope(topscope); + return output; +} + +COMPILER* mkcompiler(CLASS* classes) { + COMPILER* c = (COMPILER*)malloc(sizeof(COMPILER)); + c->globalscope = mkscope(NULL); + c->globalscope->compiler = c; + c->globalscope->classes = classes; + c->classes = classes; + c->os = mkos(); + pthread_mutex_init(&(c->ifmutex), NULL); + pthread_mutex_init(&(c->whilemutex), NULL); + pthread_mutex_init(&(c->staticmutex), NULL); + return c; +} + +void freecompiler(COMPILER* c) { + pthread_mutex_destroy(&(c->ifmutex)); + pthread_mutex_destroy(&(c->whilemutex)); + pthread_mutex_destroy(&(c->staticmutex)); + // to be continued + freeos(c->os); + freescope(c->globalscope); + free(c); +} diff --git a/compiler/compiler.h b/compiler/compiler.h new file mode 100644 index 0000000..3009896 --- /dev/null +++ b/compiler/compiler.h @@ -0,0 +1,25 @@ +#ifndef COMPILER_H +#define COMPILER_H +#include +#include "parser-tree.h" +#include "vm-lines.h" +#include "compiler-scopes.h" + +/* compiler + * This is the file that should be included in other modules + * that want to compile a class/program. */ + +struct scope; +typedef struct compiler { + pthread_mutex_t ifmutex; + pthread_mutex_t whilemutex; + pthread_mutex_t staticmutex; + CLASS* classes; + CLASS* os; + struct scope* globalscope; +} COMPILER; + +COMPILER* mkcompiler(CLASS* classes); +LINEBLOCK* compileclass(COMPILER* c, CLASS* class); +void freecompiler(COMPILER* c); +#endif diff --git a/main.c b/main.c new file mode 100644 index 0000000..a2ba9b3 --- /dev/null +++ b/main.c @@ -0,0 +1,78 @@ +#include +#include +#include +#include +#include "threads.h" +#include "parser.h" +#include "compiler.h" +#include "io.h" +#include "os.h" + +int main(int argc, char* argv[]) { + if(argc < 2) { + eprintf("Usage: %s {input file(s)}\n", argv[0]); + return 1; + } + + FILELIST* files = getfiles(argv[1]); + FILELIST* curr = files->next; + + COMPILEUNIT* head = (COMPILEUNIT*)malloc(sizeof(COMPILEUNIT)); + + head->file = files; + head->parser = mkparser(tokenize(files->fullname), files->name); + + COMPILEUNIT* currunit = head; + while(curr != NULL) { + COMPILEUNIT* newunit = (COMPILEUNIT*)malloc(sizeof(COMPILEUNIT)); + newunit->file = curr; + newunit->parser = mkparser(tokenize(curr->fullname), curr->name); + currunit->next = newunit; + currunit = newunit; + curr = curr->next; + } + currunit->next = NULL; + + actonunits(head, parseunit); + + CLASS* headclass = head->parsed; + CLASS* currclass = headclass; + currunit = head->next; + while(currunit != NULL) { + currclass->next = currunit->parsed; + currclass = currunit->parsed; + currunit = currunit->next; + } + currclass->next = NULL; + COMPILER* compiler = mkcompiler(headclass); + + currunit = head; + while(currunit != NULL) { + currunit->compiler = compiler; + currunit = currunit->next; + } + + actonunits(head, compileunit); + + actonunits(head, vmtranslateunit); + + currunit = head; + while(currunit != NULL) { + FILE* output = fopen(currunit->file->outname, "w"); + if(output == NULL) { + eprintf("%s", strerror(errno)); + exit(1); + } + + printstrlist(currunit->asmlns, output); + fclose(output); + COMPILEUNIT* next = currunit->next; + freeunit(currunit); + currunit = next; + } + + freecompiler(compiler); + freetree(headclass); + freefilelist(files); + return 0; +} diff --git a/misc/io.c b/misc/io.c new file mode 100644 index 0000000..bf09704 --- /dev/null +++ b/misc/io.c @@ -0,0 +1,180 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include "util.h" +#include "io.h" + +#include +#ifndef PATH_MAX +#ifdef __linux__ +#include +#else +#define PATH_MAX 512 +#endif +#endif + +char* strtail(char* str, int len, int count) { + int index = len - count; + if (index <= 0) return str; + return str + (sizeof(char) * (index)); +} + +char* strhead(char* str, int count) { + return str + (sizeof(char) * count); +} + +char* trimstr(char* str, int len, int end) { + int count = len - end; + char oldchar = str[count]; + str[count] = '\0'; + char* newstr = (char*)malloc(sizeof(char) * (1 + count)); + strcpy(newstr, str); + str[count] = oldchar; + return newstr; +} + +char* getname(char* f, int len) { + int startind = 0; + int endind = len - 1; + bool readsmt = false; + + for(int i = endind; i >= 0; i--) { + if(f[i] == '/') { + if(!readsmt) { + endind = i-1; + f[i] = '\0'; + continue; + } + startind = i+1; + break; + } + readsmt = true; + } + + int sz = sizeof(char)*(endind - startind + 2); + char* startstr = strhead(f, startind); + char* retstr = (char*)malloc(sz); + snprintf(retstr, sz, "%s", startstr); + return retstr; +} + +char* getfullname(char* fname, int fnamelen, char* dirname, int dirlen) { + int sz = sizeof(char)*(fnamelen+dirlen+2); + char* fullname = (char*)malloc(sz); + sprintf(fullname, "%s/%s", dirname, fname); + return fullname; +} + +bool isdotjack(char* f, int len) { + const char* ext = ".jack"; + return strcmp(strtail(f, len, strlen(ext)), ext) == 0; +} + +bool isdir(char* f, int len) { + bool readsmt = false; + for(int i = len-1; i >= 0; i--) { + if(f[i] == '.') { + if(readsmt) + return false; + else + continue; + } + if(f[i] == '/') + return 1; + readsmt = true; + } + return true; +} + +char* getoutname(char* fullname, int len) { + char* trimmed = trimstr(fullname, len, 4); + int sz = sizeof(char) * (len); + char* outname = (char*)malloc(sz); + snprintf(outname, sz, "%sasm", trimmed); + free(trimmed); + return outname; +} + +FILELIST* addfile(FILELIST* l, char* fullname, char* name) { + FILELIST* new = (FILELIST*)malloc(sizeof(FILELIST)); + new->name = name; + new->fullname = fullname; + new->next = l; + new->outname = getoutname(fullname, strlen(fullname)); + return new; +} + +FILELIST* getfilesfromdir(char* dir) { + FILELIST* filelist = NULL; + DIR* d = opendir(dir); + + if(d == NULL) { + eprintf("Error while opening directory '%s': %s\n", dir, strerror(errno)); + exit(errno); + } + + int len = strlen(dir); + struct dirent* thisfile; + while(thisfile = readdir(d), thisfile != NULL) { + int thislen = strlen(thisfile->d_name); + if(isdotjack(thisfile->d_name, thislen)) { + char* fullname = getfullname(thisfile->d_name, thislen, dir, len); + char* name = ezheapstr(thisfile->d_name); + filelist = addfile(filelist, fullname, name); + } + } + + closedir(d); + + if(filelist == NULL) { + eprintf("Directory '%s' doesn't have any .jack file\n", dir); + exit(1); + } + return filelist; +} + +FILELIST* getsinglefile(char* file) { + int len = strlen(file); + if(isdotjack(file, len)){ + char* name = getname(file, len); + char* fullname = heapstr(file, len); + + FILE* input = fopen(fullname, "r"); + if(input == NULL) { + eprintf("Error while reading file '%s': %s\n", file, strerror(errno)); + exit(errno); + } + fclose(input); + + return addfile(NULL, fullname, name); + } + else { + eprintf("Input file must be named like 'Xxx.vm'\n"); + exit(1); + } +} + +FILELIST* getfiles(char* input) { + int inplen = strlen(input); + bool isitdir = isdir(input, inplen); + + if(isitdir) + return getfilesfromdir(input); + else + return getsinglefile(input); +} + +void freefilelist(FILELIST* fs) { + free(fs->name); + free(fs->fullname); + free(fs->outname); + FILELIST* next = fs->next; + free(fs); + if(next != NULL) + freefilelist(next); +} diff --git a/misc/io.h b/misc/io.h new file mode 100644 index 0000000..1e493b3 --- /dev/null +++ b/misc/io.h @@ -0,0 +1,14 @@ +#ifndef IO_H +#define IO_H + +typedef struct flist { + char* name; + char* fullname; + char* outname; + struct flist* next; +} FILELIST; + + +FILELIST* getfiles(char* input); +void freefilelist(FILELIST* fs); +#endif diff --git a/misc/os.c b/misc/os.c new file mode 100644 index 0000000..a91a6d5 --- /dev/null +++ b/misc/os.c @@ -0,0 +1,166 @@ +#include +#include +#include "os.h" +#include "util.h" + +CLASS* mkosclass(CLASS* os, const char* name) { + CLASS* c = (CLASS*)malloc(sizeof(CLASS)); + c->name = ezheapstr(name); + c->subroutdecs = NULL; + c->next = os; + return c; +} + +void adddec(CLASS* c, SUBROUTCLASS subroutclass, char* type, const char* name) { + SUBROUTDEC* dec = (SUBROUTDEC*)malloc(sizeof(SUBROUTDEC)); + dec->class = c; + dec->subroutclass = subroutclass; + dec->name = ezheapstr(name); + dec->type = ezheapstr(type); + dec->next = c->subroutdecs; + c->subroutdecs = dec; +} + +CLASS* mkmath(CLASS* os) { + CLASS* mathclass = mkosclass(os, "Math"); + adddec(mathclass, function, "int", "multiply"); + adddec(mathclass, function, "int", "divide"); + adddec(mathclass, function, "int", "abs"); + adddec(mathclass, function, "int", "min"); + adddec(mathclass, function, "int", "max"); + adddec(mathclass, function, "int", "sqrt"); + return mathclass; +} + +CLASS* mkstringclass(CLASS* os) { + CLASS* strclass = mkosclass(os, "String"); + adddec(strclass, constructor, "String", "new"); + adddec(strclass, method, "int", "dispose"); + adddec(strclass, method, "int", "length"); + adddec(strclass, method, "char", "charAt"); + adddec(strclass, method, "void", "setCharAt"); + adddec(strclass, method, "String", "appendChar"); + adddec(strclass, method, "void", "eraseLastChar"); + adddec(strclass, method, "int", "intValue"); + adddec(strclass, method, "void", "setInt"); + adddec(strclass, function, "char", "backSpace"); + adddec(strclass, function, "char", "doubleQuote"); + adddec(strclass, function, "char", "newLine"); + return strclass; +} + +CLASS* mkarray(CLASS* os) { + CLASS* arrclass = mkosclass(os, "Array"); + adddec(arrclass, function, "Array", "new"); + adddec(arrclass, method, "void", "dispose"); + return arrclass; +} + +CLASS* mkoutput(CLASS* os) { + CLASS* outclass = mkosclass(os, "Output"); + adddec(outclass, function, "void", "moveCursor"); + adddec(outclass, function, "void", "printChar"); + adddec(outclass, function, "void", "printString"); + adddec(outclass, function, "void", "printInt"); + adddec(outclass, function, "void", "println"); + adddec(outclass, function, "void", "backSpace"); + return outclass; +} + +CLASS* mkscreen(CLASS* os) { + CLASS* scrclass = mkosclass(os, "Screen"); + adddec(scrclass, function, "void", "clearScreen"); + adddec(scrclass, function, "void", "setColor"); + adddec(scrclass, function, "void", "drawPixel"); + adddec(scrclass, function, "void", "drawLine"); + adddec(scrclass, function, "void", "drawRectangle"); + adddec(scrclass, function, "void", "drawCircle"); + return scrclass; +} + +CLASS* mkkeyboard(CLASS* os) { + CLASS* kbdclass = mkosclass(os, "Keyboard"); + adddec(kbdclass, function, "char", "keyPressed"); + adddec(kbdclass, function, "char", "readChar"); + adddec(kbdclass, function, "String", "readLine"); + adddec(kbdclass, function, "int", "readInt"); + return kbdclass; +} + +CLASS* mkmemory(CLASS* os) { + CLASS* memclass = mkosclass(os, "Memory"); + adddec(memclass, function, "int", "peek"); + adddec(memclass, function, "void", "poke"); + adddec(memclass, function, "Array", "alloc"); + adddec(memclass, function, "void", "deAlloc"); + return memclass; +} + +CLASS* mksys(CLASS* os) { + CLASS* sysclass = mkosclass(os, "Sys"); + adddec(sysclass, function, "void", "halt"); + adddec(sysclass, function, "void", "error"); + adddec(sysclass, function, "void", "wait"); + return sysclass; +} + +CLASS* mkos() { + CLASS* os = mkmath(NULL); + os = mkstringclass(os); + os = mkarray(os); + os = mkoutput(os); + os = mkscreen(os); + os = mkkeyboard(os); + os = mkmemory(os); + os = mksys(os); + return os; +} + +void freeossubroutdecs(SUBROUTDEC* d) { + free(d->name); + free(d->type); + SUBROUTDEC* next = d->next; + free(d); + if(next != NULL) + freeossubroutdecs(next); +} + +void freeosclasses(CLASS* c) { + freeossubroutdecs(c->subroutdecs); + free(c->name); + CLASS* next = c->next; + free(c); + if(next != NULL) + freeosclasses(next); +} + +void freeos(CLASS* os) { + freeosclasses(os); +} + +SUBROUTDEC* getsubroutdecinclass(CLASS* c, const char* name) { + SUBROUTDEC* curr = c->subroutdecs; + while(curr != NULL) { + if(!strcmp(curr->name, name)) + return curr; + curr = curr->next; + } + return NULL; +} + +CLASS* getosclass(CLASS* os, const char* name) { + CLASS* curr = os; + while(curr != NULL) { + if(!strcmp(curr->name, name)) + return curr; + curr = curr->next; + } + return NULL; +} + +SUBROUTDEC* getossubroutdec(CLASS* os, SUBROUTCALL* call) { + CLASS* c = getosclass(os, call->parentname); + if(c == NULL) + return NULL; + return getsubroutdecinclass(c, call->name); +} diff --git a/misc/os.h b/misc/os.h new file mode 100644 index 0000000..6ca468b --- /dev/null +++ b/misc/os.h @@ -0,0 +1,10 @@ +#ifndef OS_H +#define OS_H +#include "parser-tree.h" + +SUBROUTDEC* getossubroutdec(CLASS* os, SUBROUTCALL* call); +CLASS* getosclass(CLASS* os, const char* name); +CLASS* mkos(); +void freeos(CLASS* os); + +#endif diff --git a/misc/threads.c b/misc/threads.c new file mode 100644 index 0000000..49b1673 --- /dev/null +++ b/misc/threads.c @@ -0,0 +1,102 @@ +#include +#include +#include +#include +#include "threads.h" + +void* parseunit(void* input) { + COMPILEUNIT* unit = (COMPILEUNIT*)input; + + unit->parsed = parse(unit->parser); + + pthread_exit(NULL); +} + +void* compileunit(void* input) { + COMPILEUNIT* unit = (COMPILEUNIT*)input; + + unit->compiled = compileclass(unit->compiler, unit->parsed); + + pthread_exit(NULL); +} + +char* getclassname(char* filename) { + int count = 0; + int len = strlen(filename); + + for(int i = len-1; i >= 0; i--) + if(filename[i] == '.') { + count = i; + break; + } + + int sz = sizeof(char) * (len - count); + char* classname = (char*)malloc(sz); + snprintf(classname, sz, "%s", filename); // legitimately needs to be snprintf + return classname; +} + +void* vmtranslateunit(void* input) { + COMPILEUNIT* unit = (COMPILEUNIT*)input; + + if(unit->compiled == NULL) { + eprintf("Class '%s' is empty; file '%s'\n", unit->parsed->name, unit->file->name); + exit(1); + } + + char* classname = getclassname(unit->file->name); + unit->vmtranslator = mkvmtranslator(classname, unit->compiled); + unit->asmlns = translatevm(unit->vmtranslator); + free(classname); + + pthread_exit(NULL); +} + +void waitthreads(pthread_t* threads, int amount) { + void* status; + int code; + for(int i = 0; i < amount; i++) { + code = pthread_join(threads[i], &status); + if(code) { + eprintf("Error while joining thread %i: %s\n", i, strerror(code)); + exit(code); + } + } +} + +void actonunits(COMPILEUNIT* units, void*(*fun)(void*)) { + pthread_t mythreads[_SC_THREAD_THREADS_MAX]; + pthread_attr_t attr; + pthread_attr_init(&attr); + pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_JOINABLE); + + COMPILEUNIT* curr = units; + + int i; + int code; + do { + i = 0; + while(curr != NULL && i < _SC_THREAD_THREADS_MAX) { + code = pthread_create(&mythreads[i], &attr, fun, curr); + + if(code) { + eprintf("Error while creating thread %i: %s\n", i, strerror(code)); + exit(code); + } + + curr = curr->next; + i++; + } + waitthreads(mythreads, i); + } while(i == _SC_THREAD_THREADS_MAX); + + pthread_attr_destroy(&attr); +} + +void freeunit(COMPILEUNIT* u) { + freeparser(u->parser); + freelnblk(u->compiled); + freestrlist(u->asmlns); + freevmtranslator(u->vmtranslator); + free(u); +} diff --git a/misc/threads.h b/misc/threads.h new file mode 100644 index 0000000..f85bbe9 --- /dev/null +++ b/misc/threads.h @@ -0,0 +1,29 @@ +#ifndef THREADS_H +#define THREADS_H +#include +#include "parser.h" +#include "compiler.h" +#include "io.h" +#include "vm-translator.h" + +/* threads + * Tools for dealing with the compiling pipeline in a parallel way */ + +typedef struct unit { + FILELIST* file; + PARSER* parser; + CLASS* parsed; + COMPILER* compiler; + STRINGLIST* asmlns; + LINEBLOCK* compiled; + VMTRANSLATOR* vmtranslator; + struct unit* next; +} COMPILEUNIT; + +void* parseunit(void* input); +void* compileunit(void* input); +void* vmtranslateunit(void* input); +void waitthreads(pthread_t* threads, int amount); +void actonunits(COMPILEUNIT* units, void*(*fun)(void*)); +void freeunit(COMPILEUNIT* u); +#endif diff --git a/misc/util.c b/misc/util.c new file mode 100644 index 0000000..ad4c566 --- /dev/null +++ b/misc/util.c @@ -0,0 +1,89 @@ +#include +#include +#include "util.h" + +char* heapstr(const char* str, int len) { + int size = sizeof(char) * (len + 1); + char* outstr = (char*)malloc(size); + strcpy(outstr, str); + return outstr; +} + +char* ezheapstr(const char* str) { + return heapstr(str, strlen(str)); +} + +void* copy(void* v, int size) { + void* copy = malloc(size); + memcpy(copy, v, size); + return copy; +} + +int countplaces(int n) { + int places = 1; + int divisor = 1; + if(n < 0) { + n = -n; + places++; + } + while(n / divisor >= 10) { + places++; + divisor *= 10; + } + return places; +} + +char* itoa(int i) { + int size = sizeof(char)*(countplaces(i)+1); + char* a = (char*)malloc(size); + sprintf(a, "%i", i); + return a; +} + +char* dotlabel(char* n1, char* n2) { + int sz = (strlen(n1) + strlen(n2) + 2) * sizeof(char); + char* result = (char*)malloc(sz); + sprintf(result, "%s.%s", n1, n2); + return result; +} + +STRINGLIST* onestr(const char* str) { + STRINGLIST* strlist = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + strlist->content = ezheapstr(str); + strlist->next = NULL; + return strlist; +} + +STRINGLIST* initstrlist(const char** strs, int count) { + STRINGLIST* strlist = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + STRINGLIST* curr = strlist; + for(int i = 0; i < count-1; i++) { + curr->content = ezheapstr(strs[i]); + curr->next = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + curr = curr->next; + } + curr->content = ezheapstr(strs[count-1]); + curr->next = NULL; + return strlist; +} + +void printstrlist(STRINGLIST* strlist, FILE* stream) { + while(strlist != NULL) { + fprintf(stream, "%s\n", strlist->content); + strlist = strlist->next; + } +} + +void freestrlist(STRINGLIST* strlist) { + STRINGLIST* next = strlist->next; + free(strlist); + if(next != NULL) + freestrlist(next); +} + +bool existsinarray(STRINGARRAY* arr, const char* item) { + for(int i = 0; i < arr->size; i++) + if(!strcmp(arr->items[i], item)) + return true; + return false; +} diff --git a/misc/util.h b/misc/util.h new file mode 100644 index 0000000..f43fd84 --- /dev/null +++ b/misc/util.h @@ -0,0 +1,38 @@ +#ifndef UTIL_H +#define UTIL_H +#include +#include + +/* util + * Random utilities. */ + +// Macros +#define eprintf(...) fprintf (stderr, __VA_ARGS__) +#define count(array, type) ((sizeof(array)) / (sizeof(type))) +#define strcount(array) count(array, char*) +#define mkstrlist(name, array) STRINGARRAY name = { .items = array, .size = strcount(array) } + +typedef struct stringlist { + char* content; + struct stringlist* next; +} STRINGLIST; + +typedef struct { + const char** items; + const int size; +} STRINGARRAY; + +char* heapstr(const char* str, int len); +char* ezheapstr(const char* str); +int countplaces(int n); +char* itoa(int i); +void* copy(void* v, int size); +char* dotlabel(char* n1, char* n2); + +STRINGLIST* onestr(const char* str); +STRINGLIST* initstrlist(const char** strs, int count); +void printstrlist(STRINGLIST* strlist, FILE* stream); +void freestrlist(STRINGLIST* strlist); + +bool existsinarray(STRINGARRAY* arr, const char* item); +#endif diff --git a/parser/parser-expressions.c b/parser/parser-expressions.c new file mode 100644 index 0000000..019d447 --- /dev/null +++ b/parser/parser-expressions.c @@ -0,0 +1,247 @@ +#include +#include "util.h" +#include "parser-util.h" +#include "parser-expressions.h" + + const char* keywordsarr[] = { "true", "false", "null", "this" }; + const char* opsarr[] = { "+", "-", "*", "/", "&", "|", "<", ">", "=" }; + mkstrlist(keywordconstants, keywordsarr); +mkstrlist(operators, opsarr); + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +bool isop(TOKEN* t); + +// Parsing methods +TERM* parsetermnullified(PARSER* p); +TERM* parseterm(PARSER* p); +TERM* mkterm(TERMTYPE type); +TERM* parseint(PARSER* p); +TERM* parsestr(PARSER* p); +TERM* parsekeyword(PARSER* p); +TERM* parseunaryopterm(PARSER* p); +TERM* parseinnerexpression(PARSER* p); +TERM* parsecalltermnullified(PARSER* p); +TERM* parsearrayterm(PARSER* p); +TERM* parsevarterm(PARSER* p); +TERM* parseidentifierterm(PARSER* p); +SUBROUTCALL* nullsubroutcall(PARSER* p, SUBROUTCALL* c); +SUBROUTCALL* parsesubroutcallnullified(PARSER* p); + +/* END FORWARD DECLARATIONS */ + +// Miscelaneous +bool isop(TOKEN* t) { + for(int i = 0; i < operators.size; i++) + if(!strcmp(t->token, operators.items[i])) + return true; + return false; +} + +// Parsing methods +TERM* parsetermnullified(PARSER* p) { + TOKENTYPE type = p->current->type; + if(type == integer) return parseint(p); + if(type == string) return parsestr(p); + if(type == keyword) return parsekeyword(p); + if(type == identifier) return parseidentifierterm(p); + if(equals(p, "-") || equals(p, "~")) return parseunaryopterm(p); + if(equals(p, "(")) return parseinnerexpression(p); + return NULL; +} + +TERM* parseterm(PARSER* p) { + TERM* t = parsetermnullified(p); + if(t == NULL) + unexpected(p); + return t; +} + +TERM* mkterm(TERMTYPE type) { + TERM* t = (TERM*)malloc(sizeof(TERM)); + t->type = type; + return t; +} + +TERM* parseint(PARSER* p) { + TERM* t = mkterm(intconstant); + t->integer = atoi(p->current->token); + next(p); + return t; +} + +TERM* parsestr(PARSER* p) { + TERM* t = mkterm(stringconstant); + t->string = p->current->token; + next(p); + return t; +} + +TERM* parsekeyword(PARSER* p) { + TERM* t = mkterm(keywordconstant); + if(!existsinarray(&keywordconstants, p->current->token)) + unexpected(p); + t->string = p->current->token; + next(p); + return t; +} + +TERM* parseunaryopterm(PARSER* p) { + TERM* t = mkterm(unaryopterm); + t->unaryop = p->current->token[0]; + next(p); + t->expression = parseterm(p); + t->expression->next = NULL; + return t; +} + +TERM* parseinnerexpression(PARSER* p) { + TERM* t = mkterm(innerexpression); + next(p); + t->expression = parseexpression(p); + checkcontent(p, ")"); + return t; +} + +TERM* parsecalltermnullified(PARSER* p) { + SUBROUTCALL* call = parsesubroutcallnullified(p); + if(call == NULL) + return NULL; + TERM* t = mkterm(subroutcall); + t->call = call; + return t; +} + +TERM* parsearrayterm(PARSER* p) { + TERM* t = mkterm(arrayitem); + t->array = (ARRAY*)malloc(sizeof(ARRAY)); + t->array->name = p->current->token; + next(p); + checkcontent(p, "["); + t->array->exp = parseexpression(p); + checkcontent(p, "]"); + return t; +} + +TERM* parsevarterm(PARSER* p) { + TERM* t = mkterm(varname); + t->string = p->current->token; + next(p); + return t; +} + +TERM* parseidentifierterm(PARSER* p) { + TERM* t = parsecalltermnullified(p); + if(t == NULL) + if(nextequals(p, "[")) + return parsearrayterm(p); + else + return parsevarterm(p); + else + return t; +} + +TERM* parseexpressionnullified(PARSER* p) { + TERM* head = parsetermnullified(p); + TERM* current = head; + TERM* nextt; + while(isop(p->current)) { + current->op = p->current->token[0]; + next(p); + nextt = parseterm(p); + current->next = nextt; + current = nextt; + } + if(current != NULL) + current->next = NULL; + return head; +} + +TERM* parseexpression(PARSER* p) { + TERM* t = parseexpressionnullified(p); + if(t == NULL) + unexpected(p); + return t; +} + +SUBROUTCALL* nullsubroutcall(PARSER* p, SUBROUTCALL* c) { + free(c->debug); + free(c); + rewindparser(p); + return NULL; +} + +SUBROUTCALL* parsesubroutcallnullified(PARSER* p) { + if(p->current->type != identifier) + return NULL; + + anchorparser(p); + SUBROUTCALL* c = (SUBROUTCALL*)malloc(sizeof(SUBROUTCALL)); + + c->debug = getdebug(p); + + if(nextequals(p, ".")) { + c->parentname = p->current->token; + next(p); + next(p); + } + else + c->parentname = NULL; + + if(p->current->type != identifier) + return nullsubroutcall(p, c); + c->name = p->current->token; + next(p); + + if(differs(p, "(")) + return nullsubroutcall(p, c); + next(p); + + c->parameters = parseexpressionlist(p); + + if(differs(p, ")")) + return nullsubroutcall(p, c); + next(p); + return c; +} + +SUBROUTCALL* parsesubroutcall(PARSER* p) { + SUBROUTCALL* c = (SUBROUTCALL*)malloc(sizeof(SUBROUTCALL)); + c->debug = getdebug(p); + + if(nextequals(p, ".")) { + c->parentname = parseidentifier(p); + next(p); + } + else + c->parentname = NULL; + + c->name = parseidentifier(p); + + checkcontent(p, "("); + + c->parameters = parseexpressionlist(p); + + checkcontent(p, ")"); + return c; +} + +EXPRESSIONLIST* parseexpressionlist(PARSER* p) { + if(!strcmp(p->current->token, ")")) + return NULL; + EXPRESSIONLIST* head = (EXPRESSIONLIST*)malloc(sizeof(EXPRESSIONLIST)); + head->expression = parseexpressionnullified(p); + EXPRESSIONLIST* current = head; + EXPRESSIONLIST* nextls; + while(!strcmp(p->current->token, ",")) { + next(p); + nextls = (EXPRESSIONLIST*)malloc(sizeof(EXPRESSIONLIST)); + nextls->expression = parseexpression(p); + current->next = nextls; + current = nextls; + } + if(current != NULL) + current->next = NULL; + return head; +} diff --git a/parser/parser-expressions.h b/parser/parser-expressions.h new file mode 100644 index 0000000..47803c4 --- /dev/null +++ b/parser/parser-expressions.h @@ -0,0 +1,12 @@ +#ifndef PARSER_EXPRESSIONS_H +#define PARSER_EXPRESSIONS_H +#include "parser.h" + +/* parser-expressions + * Functions for parsing expressions. */ + +TERM* parseexpressionnullified(PARSER* p); +TERM* parseexpression(PARSER* p); +SUBROUTCALL* parsesubroutcall(PARSER* p); +EXPRESSIONLIST* parseexpressionlist(PARSER* p); +#endif diff --git a/parser/parser-statements.c b/parser/parser-statements.c new file mode 100644 index 0000000..5091192 --- /dev/null +++ b/parser/parser-statements.c @@ -0,0 +1,143 @@ +#include +#include "parser-expressions.h" +#include "parser-util.h" +#include "parser-statements.h" + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +STATEMENT* mkstatement(PARSER* p, STATEMENTTYPE t); + +STATEMENT* parsestatementnullified(PARSER* p); +STATEMENT* parselet(PARSER* p); +CONDSTATEMENT* parsecond(PARSER* p); +STATEMENT* parseif(PARSER* p); +STATEMENT* parsewhile(PARSER* p); +STATEMENT* parsedo(PARSER* p); +STATEMENT* parsereturn(PARSER* p); + +/* END FORWARD DECLARATIONS */ + +// Miscelaneous +STATEMENT* mkstatement(PARSER* p, STATEMENTTYPE t) { + STATEMENT* s = (STATEMENT*)malloc(sizeof(STATEMENT)); + s->type = t; + s->debug = getdebug(p); + return s; +} + +// Parsing methods + +// Though nullified, will throw errors if the parsing fails while on-going +STATEMENT* parsestatementnullified(PARSER* p) { + if(equals(p, "let")) return parselet(p); + if(equals(p, "if")) return parseif(p); + if(equals(p, "while")) return parsewhile(p); + if(equals(p, "do")) return parsedo(p); + if(equals(p, "return")) return parsereturn(p); + return NULL; +} + +STATEMENT* parsestatements(PARSER* p) { + STATEMENT* head = parsestatementnullified(p); + STATEMENT* curr = head; + STATEMENT* next; + while(next = parsestatementnullified(p), next != NULL) { + curr->next = next; + curr = next; + } + if(curr != NULL) + curr->next = NULL; + return head; +} + +STATEMENT* parselet(PARSER* p) { + next(p); + STATEMENT* s = mkstatement(p, letstatement); + LETSTATEMENT* letst = (LETSTATEMENT*)malloc(sizeof(LETSTATEMENT)); + + letst->varname = parseidentifier(p); + + if(equals(p, "[")) { + next(p); + letst->arrayind = parseexpression(p); + checkcontent(p, "]"); + } + else + letst->arrayind = NULL; + + checkcontent(p, "="); + + letst->expression = parseexpression(p); + + checkcontent(p, ";"); + + s->type = letstatement; + s->letstatement = letst; + return s; +} + +CONDSTATEMENT* parsecond(PARSER* p) { + checkcontent(p, "("); + + CONDSTATEMENT* st = (CONDSTATEMENT*)malloc(sizeof(CONDSTATEMENT)); + + st->expression = parseexpression(p); + + checkcontent(p, ")"); + checkcontent(p, "{"); + + st->statements = parsestatements(p); + + checkcontent(p, "}"); + return st; +} + +STATEMENT* parseif(PARSER* p) { + next(p); + STATEMENT* s = mkstatement(p, ifstatement); + IFSTATEMENT* ifst = (IFSTATEMENT*)malloc(sizeof(IFSTATEMENT)); + + ifst->base = parsecond(p); + + if(equals(p, "else")) { + next(p); + checkcontent(p, "{"); + ifst->elsestatements = parsestatements(p); + checkcontent(p, "}"); + } + else + ifst->elsestatements = NULL; + + s->type = ifstatement; + s->ifstatement = ifst; + return s; +} + +STATEMENT* parsewhile(PARSER* p) { + next(p); + STATEMENT* s = mkstatement(p, whilestatement); + + s->whilestatement = parsecond(p); + return s; +} + +STATEMENT* parsedo(PARSER* p) { + next(p); + STATEMENT* s = mkstatement(p, dostatement); + + s->dostatement = parsesubroutcall(p); + + checkcontent(p, ";"); + return s; +} + +STATEMENT* parsereturn(PARSER* p) { + next(p); + STATEMENT* s = mkstatement(p, returnstatement); + + s->retstatement = parseexpressionnullified(p); + + checkcontent(p, ";"); + return s; +} diff --git a/parser/parser-statements.h b/parser/parser-statements.h new file mode 100644 index 0000000..06ded24 --- /dev/null +++ b/parser/parser-statements.h @@ -0,0 +1,9 @@ +#ifndef PARSER_STATEMENTS_H +#define PARSER_STATEMENTS_H +#include "parser.h" + +/* parser-statements + * Function for parsing statements. */ + +STATEMENT* parsestatements(PARSER* p); +#endif diff --git a/parser/parser-structure.c b/parser/parser-structure.c new file mode 100644 index 0000000..f9fad32 --- /dev/null +++ b/parser/parser-structure.c @@ -0,0 +1,253 @@ +#include +#include "parser-util.h" +#include "parser-structure.h" +#include "parser-statements.h" + +const char* classvartypesarr[] = { "static", "field" }; +const char* vartypesarr[] = { "int", "char", "boolean" }; +const char* subroutclassesarr[] = { "constructor", "function", "method" }; +mkstrlist(classvartypes, classvartypesarr); +mkstrlist(vartypes, vartypesarr); +mkstrlist(subroutclasses, subroutclassesarr); + +/* BEGIN FORWARD DECLARATIONS */ + +// Miscelaneous +bool isprimitive(TOKEN* tk); +char* parsetype(PARSER* p); +int parsepossibilities(PARSER* p, STRINGARRAY* poss); + +// Parsing methods +CLASS* parseclass(PARSER* p); +CLASSVARTYPE parseclassvartype(PARSER* p); +CLASSVARDEC* parseclassvardec(PARSER* p); +CLASSVARDEC* parseclassvardecs(PARSER* p); +SUBROUTCLASS parsesubroutclass(PARSER* p); +SUBROUTDEC* parsesubroutdec(PARSER* p, CLASS* c); +SUBROUTDEC* parsesubroutdecs(PARSER* p, CLASS* c); +PARAMETER* parseparameter(PARSER* p); +PARAMETER* parseparameters(PARSER* p); +SUBROUTBODY* parsesubroutbody(PARSER* p); +void parsevardeccommon(PARSER* p, VARDEC* v); +VARDEC* parsevardec(PARSER* p); +VARDEC* parsevardecs(PARSER* p); + +/* END FORWARD DECLARATIONS */ + + +// Miscelaneous +bool isprimitive(TOKEN* tk) { + if(tk->type == keyword) + if(existsinarray(&vartypes, tk->token)) + return true; + return false; +} + +char* parsetype(PARSER* p) { + if(p->current->type != identifier && p->current->type != keyword) + unexpected(p); + + char* result = p->current->token; + next(p); + return result; +} + +int parsepossibilities(PARSER* p, STRINGARRAY* poss) { + for(int i = 0; i < poss->size; i++) + if(equals(p, poss->items[i])) + return i; + return -1; +} + +// Parsing methods +CLASS* parseclass(PARSER* p) { + checkcontent(p, "class"); + + CLASS* class = (CLASS*)malloc(sizeof(CLASS)); + + class->debug = getdebug(p); + + class->name = parseidentifier(p); + + checkcontent(p, "{"); + + class->vardecs = parseclassvardecs(p); + + class->subroutdecs = parsesubroutdecs(p, class); + + checkcontent(p, "}"); + + if(p->current != NULL) + unexpected(p); + + return class; +} + +CLASSVARTYPE parseclassvartype(PARSER* p) { + return parsepossibilities(p, &classvartypes); +} + +CLASSVARDEC* parseclassvardec(PARSER* p) { + CLASSVARTYPE classvartype = parseclassvartype(p); + if(classvartype == -1) + return NULL; + next(p); + + CLASSVARDEC* classvardec = (CLASSVARDEC*)malloc(sizeof(CLASSVARDEC)); + classvardec->type = classvartype; + + classvardec->base = (VARDEC*)malloc(sizeof(VARDEC)); + + parsevardeccommon(p, classvardec->base); + + return classvardec; +} + +CLASSVARDEC* parseclassvardecs(PARSER* p) { + CLASSVARDEC* head = parseclassvardec(p); + CLASSVARDEC* curr = head; + CLASSVARDEC* nextc; + while(nextc = parseclassvardec(p), nextc != NULL) { + curr->next = nextc; + curr = nextc; + } + if(curr != NULL) + curr->next = NULL; + return head; +} + +SUBROUTCLASS parsesubroutclass(PARSER* p) { + return parsepossibilities(p, &subroutclasses); +} + +SUBROUTDEC* parsesubroutdec(PARSER* p, CLASS* c) { + SUBROUTCLASS subroutclass = parsesubroutclass(p); + if(subroutclass == -1) + return NULL; + + next(p); + SUBROUTDEC* subroutdec = (SUBROUTDEC*)malloc(sizeof(SUBROUTDEC)); + subroutdec->subroutclass = subroutclass; + + if(differs(p, "void")) + subroutdec->type = parsetype(p); + else { + subroutdec->type = p->current->token; + next(p); + } + + subroutdec->debug = getdebug(p); + + subroutdec->name = parseidentifier(p); + + checkcontent(p, "("); + subroutdec->parameters = parseparameters(p); + checkcontent(p, ")"); + + checkcontent(p, "{"); + subroutdec->body = parsesubroutbody(p); + checkcontent(p, "}"); + + subroutdec->class = c; + + return subroutdec; +} + +SUBROUTDEC* parsesubroutdecs(PARSER* p, CLASS* c) { + SUBROUTDEC* head = parsesubroutdec(p, c); + SUBROUTDEC* curr = head; + SUBROUTDEC* nexts; + while(nexts = parsesubroutdec(p, c), nexts != NULL) { + curr->next = nexts; + curr = nexts; + } + if(curr != NULL) + curr->next = NULL; + return head; +} + +PARAMETER* parseparameter(PARSER* p) { + if(equals(p, ")")) + return NULL; + PARAMETER* param = (PARAMETER*)malloc(sizeof(PARAMETER)); + param->debug = getdebug(p); + param->primitive = isprimitive(p->current); + param->type = parsetype(p); + param->name = parseidentifier(p); + return param; +} + +PARAMETER* parseparameters(PARSER* p) { + PARAMETER* head = parseparameter(p); + PARAMETER* curr = head; + PARAMETER* nextp; + while(equals(p, ",")) { + next(p); + nextp = parseparameter(p); + if(nextp == NULL) + unexpected(p); + curr->next = nextp; + curr = curr->next; + } + if(curr != NULL) + curr->next = NULL; + return head; +} + +SUBROUTBODY* parsesubroutbody(PARSER* p) { + SUBROUTBODY* subroutbody = (SUBROUTBODY*)malloc(sizeof(SUBROUTBODY)); + subroutbody->vardecs = parsevardecs(p); + subroutbody->statements = parsestatements(p); + + return subroutbody; +} + +void parsevardeccommon(PARSER* p, VARDEC* v) { + v->typeclass = p->current->type; + v->primitive = isprimitive(p->current); + v->type = parsetype(p); + + STRINGLIST* currstr = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + v->names = currstr; + + v->debug = getdebug(p); + + v->names->content = parseidentifier(p); + + while(!strcmp(p->current->token, ",")) { + next(p); + STRINGLIST* nextstr = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + nextstr->content = parseidentifier(p); + currstr->next = nextstr; + currstr = nextstr; + } + currstr->next = NULL; + + checkcontent(p, ";"); +} + + +VARDEC* parsevardec(PARSER* p) { + if(strcmp(p->current->token, "var")) + return NULL; + next(p); + + VARDEC* vardec = (VARDEC*)malloc(sizeof(VARDEC)); + + parsevardeccommon(p, vardec); + + return vardec; +} + +VARDEC* parsevardecs(PARSER* p) { + VARDEC* head = parsevardec(p); + VARDEC* curr = head; + VARDEC* nextv; + while(nextv = parsevardec(p), nextv != NULL) { + curr->next = nextv; + curr = nextv; + } + if(curr != NULL) + curr->next = NULL; + return head; +} diff --git a/parser/parser-structure.h b/parser/parser-structure.h new file mode 100644 index 0000000..feb2506 --- /dev/null +++ b/parser/parser-structure.h @@ -0,0 +1,9 @@ +#ifndef PARSER_STRUCTURE_H +#define PARSER_STRUCTURE_H +#include "parser.h" + +/* parser-structure + * Function for parsing a class. */ + +CLASS* parseclass(PARSER* p); +#endif diff --git a/parser/parser-tree.c b/parser/parser-tree.c new file mode 100644 index 0000000..c37c856 --- /dev/null +++ b/parser/parser-tree.c @@ -0,0 +1,141 @@ +#include +#include "parser-tree.h" + +void freeexpression(TERM* e); +void freeexpressionlist(EXPRESSIONLIST* el); +void freestatements(STATEMENT* s); + +void freevardec(VARDEC* v) { + freestrlist(v->names); + free(v->debug); + free(v); +} + +void freevardecs(VARDEC* v) { + VARDEC* next = v->next; + freevardec(v); + if(next != NULL) + freevardecs(next); +} + +void freeparameters(PARAMETER* p) { + free(p->debug); + PARAMETER* next = p->next; + free(p); + if(next != NULL) + freeparameters(next); +} + +void freearray(ARRAY* a) { + freeexpression(a->exp); + free(a); +} + +void freesubroutcall(SUBROUTCALL* call) { + if(call->parameters != NULL) + freeexpressionlist(call->parameters); + free(call->debug); + free(call); +} + +void freeexpression(TERM* e) { + if(e->type == arrayitem) + freearray(e->array); + else if(e->type == innerexpression || e->type == unaryopterm) + freeexpression(e->expression); + else if(e->type == subroutcall) + freesubroutcall(e->call); + TERM* next = e->next; + free(e); + if(next != NULL) + freeexpression(next); +} + +void freeexpressionlist(EXPRESSIONLIST* el) { + freeexpression(el->expression); + EXPRESSIONLIST* next = el->next; + free(el); + if(next != NULL) + freeexpressionlist(next); +} + +void freelet(LETSTATEMENT* l) { + if(l->arrayind != NULL) + freeexpression(l->arrayind); + freeexpression(l->expression); + free(l); +} + +void freecond(CONDSTATEMENT* cond) { + freeexpression(cond->expression); + if(cond->statements != NULL) + freestatements(cond->statements); + free(cond); +} + +void freeif(IFSTATEMENT* st) { + freecond(st->base); + if(st->elsestatements != NULL) + freestatements(st->elsestatements); + free(st); +} + +void freestatements(STATEMENT* s) { + if(s->type == letstatement) + freelet(s->letstatement); + else if(s->type == ifstatement) + freeif(s->ifstatement); + else if(s->type == whilestatement) + freecond(s->whilestatement); + else if(s->type == dostatement) + freesubroutcall(s->dostatement); + else if(s->retstatement != NULL) + freeexpression(s->retstatement); + + free(s->debug); + STATEMENT* next = s->next; + free(s); + if(next != NULL) + freestatements(next); +} + +void freesubroutbody(SUBROUTBODY* b) { + if(b->vardecs != NULL) + freevardecs(b->vardecs); + if(b->statements != NULL) + freestatements(b->statements); + free(b); +} + +void freesubroutdecs(SUBROUTDEC* sr) { + free(sr->debug); + if(sr->parameters != NULL) + freeparameters(sr->parameters); + freesubroutbody(sr->body); + SUBROUTDEC* next = sr->next; + free(sr); + if(next != NULL) + freesubroutdecs(next); +} + +void freeclassvardecs(CLASSVARDEC* cvd) { + freevardec(cvd->base); + CLASSVARDEC* next = cvd->next; + free(cvd); + if(next != NULL) + freeclassvardecs(next); +} + +void freetree(CLASS* c) { + free(c->debug); + + if(c->vardecs != NULL) + freeclassvardecs(c->vardecs); + if(c->subroutdecs != NULL) + freesubroutdecs(c->subroutdecs); + + CLASS* next = c->next; + free(c); + if(next != NULL) + freetree(next); +} diff --git a/parser/parser-tree.h b/parser/parser-tree.h new file mode 100644 index 0000000..cf2207b --- /dev/null +++ b/parser/parser-tree.h @@ -0,0 +1,160 @@ +#ifndef PARSER_TREE_H +#define PARSER_TREE_H +#include +#include "tokenizer.h" +#include "util.h" + +/* parser-tree + * Type definitions for the parsing tree. */ + +/* BEGIN FORWARD DECLARATIONS */ +struct classvardec; +struct parameter; +struct subroutbody; +struct subroutdec; +struct vardec; +struct letstatement; +struct ifstatement; +struct condstatement; +struct subroutcall; +struct term; +struct expressionlist; +/* END FORWARD DECLARATIONS */ + +// Misc +typedef struct { + char* file; + int definedat; +} DEBUGINFO; + +// Program structure + +typedef struct class { + char* name; + struct classvardec* vardecs; + struct subroutdec* subroutdecs; + DEBUGINFO* debug; + struct class* next; +} CLASS; + +typedef enum { + stat, field +} CLASSVARTYPE; + +typedef struct classvardec { + CLASSVARTYPE type; + struct vardec* base; + struct classvardec* next; +} CLASSVARDEC; + +typedef enum { + constructor, function, method +} SUBROUTCLASS; + +typedef struct subroutdec { + SUBROUTCLASS subroutclass; + CLASS* class; + char* type; + char* name; + struct parameter* parameters; + struct subroutbody* body; + DEBUGINFO* debug; + struct subroutdec* next; +} SUBROUTDEC; + +typedef struct parameter { + char* type; + char* name; + bool primitive; + DEBUGINFO* debug; + struct parameter* next; +} PARAMETER; + +typedef struct subroutbody { + struct vardec* vardecs; + struct statement* statements; +} SUBROUTBODY; + +typedef struct vardec { + char* type; + bool primitive; + TOKENTYPE typeclass; + STRINGLIST* names; + DEBUGINFO* debug; + struct vardec* next; +} VARDEC; + +// Statements +typedef enum { + ifstatement, whilestatement, letstatement, dostatement, returnstatement +} STATEMENTTYPE; + +typedef struct statement { + STATEMENTTYPE type; + union { + struct letstatement* letstatement; + struct ifstatement* ifstatement; + struct condstatement* whilestatement; + struct subroutcall* dostatement; + struct term* retstatement; + }; + DEBUGINFO* debug; + struct statement* next; +} STATEMENT; + +typedef struct letstatement { + char* varname; + struct term* arrayind; + struct term* expression; +} LETSTATEMENT; + +typedef struct ifstatement { + struct condstatement* base; + struct statement* elsestatements; +} IFSTATEMENT; + +typedef struct condstatement { + struct term* expression; + struct statement* statements; +} CONDSTATEMENT; + +// Expressions + +typedef enum { + varname, intconstant, stringconstant, keywordconstant, arrayitem, subroutcall, innerexpression, unaryopterm +} TERMTYPE; + +typedef struct { + char* name; + struct term* exp; +} ARRAY; + +typedef struct term { + TERMTYPE type; + union { + char* string; + int integer; + struct subroutcall* call; + struct term* expression; + ARRAY* array; + }; + char op; + char unaryop; + struct term* next; +} TERM; + +typedef struct subroutcall { + char* parentname; + char* name; + struct expressionlist* parameters; + DEBUGINFO* debug; +} SUBROUTCALL; + +typedef struct expressionlist { + TERM* expression; + struct expressionlist* next; +} EXPRESSIONLIST; + + +void freetree(CLASS* c); +#endif diff --git a/parser/parser-util.c b/parser/parser-util.c new file mode 100644 index 0000000..37d528e --- /dev/null +++ b/parser/parser-util.c @@ -0,0 +1,43 @@ +#include +#include "parser-util.h" +#include "util.h" + +const char* tokentypesarr[] = { "keyword", "identifier", "symbol", + "integerConstant", "stringConstant" }; +mkstrlist(tokentypes, tokentypesarr); + +void unexpected(PARSER* p) { + eprintf("Unexpected token '%s' (of type %s); line %i, file '%s'\n", + p->current->token, tokentypes.items[p->current->type], + p->current->definedat, p->file); + exit(1); +} + +void checktype(PARSER* p, TOKENTYPE type) { + if(p->current->type != type) { + eprintf("Unexpected %s; file '%s', line %i\n", + tokentypes.items[p->current->type], p->file, + p->current->definedat); + exit(1); + } +} + +void checkcontent(PARSER* p, const char* content) { + if(differs(p, content)) + unexpected(p); + next(p); +} + +char* parseidentifier(PARSER* p) { + checktype(p, identifier); + char* result = p->current->token; + next(p); + return result; +} + +DEBUGINFO* getdebug(PARSER* p) { + DEBUGINFO* d = (DEBUGINFO*)malloc(sizeof(DEBUGINFO)); + d->file = p->file; + d->definedat = p->current->definedat; + return d; +} diff --git a/parser/parser-util.h b/parser/parser-util.h new file mode 100644 index 0000000..9fe2885 --- /dev/null +++ b/parser/parser-util.h @@ -0,0 +1,21 @@ +#ifndef PARSER_INTERNAL_H +#define PARSER_INTERNAL_H +#include +#include "parser.h" + +/* parser-util + * Random utilities used in the parser module. */ + +#define next(parser) parser->current = p->current->next +#define anchorparser(parser) p->checkpoint = p->current +#define rewindparser(parser) p->current = p->checkpoint +#define differs(parser, str) strcmp(parser->current->token, str) +#define nextdiffers(parser, str) strcmp(parser->current->next->token, str) +#define equals(parser, str) !differs(parser, str) +#define nextequals(parser, str) !nextdiffers(parser, str) + +void unexpected(PARSER* p); +char* parseidentifier(PARSER* p); +void checkcontent(PARSER* p, const char* content); +DEBUGINFO* getdebug(PARSER* p); +#endif diff --git a/parser/parser.c b/parser/parser.c new file mode 100644 index 0000000..8c82f38 --- /dev/null +++ b/parser/parser.c @@ -0,0 +1,23 @@ +#include +#include +#include +#include +#include "parser.h" +#include "parser-structure.h" + +PARSER* mkparser(TOKEN* t, char* file) { + PARSER* parser = (PARSER*)malloc(sizeof(PARSER)); + parser->tokens = t; + parser->current = t; + parser->file = file; + return parser; +} + +CLASS* parse(PARSER* p) { + return parseclass(p); +} + +void freeparser(PARSER* p) { + freetokens(p->tokens); + free(p); +} diff --git a/parser/parser.h b/parser/parser.h new file mode 100644 index 0000000..7a2a2d1 --- /dev/null +++ b/parser/parser.h @@ -0,0 +1,20 @@ +#ifndef PARSER_H +#define PARSER_H +#include "tokenizer.h" +#include "parser-tree.h" + +/* parser + * This is the file that should be included in other modules + * that want to parse a file. */ + +typedef struct { + TOKEN* tokens; + TOKEN* current; + TOKEN* checkpoint; + char* file; +} PARSER; + +PARSER* mkparser(TOKEN* t, char* file); +CLASS* parse(PARSER* p); +void freeparser(PARSER* p); +#endif diff --git a/tokenizer/tokenizer-tables.h b/tokenizer/tokenizer-tables.h new file mode 100644 index 0000000..61eb940 --- /dev/null +++ b/tokenizer/tokenizer-tables.h @@ -0,0 +1,19 @@ +#ifndef TOKENIZER_TABLES_H +#define TOKENIZER_TABLES_H +#include "util.h" + + +const char* keywordsraw[] = { + "class", "constructor", "function", "method", "field", "static", + "var", "int", "char", "boolean", "void", "true", "false", "null", + "this", "let", "do", "if", "else", "while", "return" +}; +mkstrlist(keywords, keywordsraw); + +const char* symbolsraw[] = { + "{", "}", "(", ")", "[", "]", ".", ",", ";", "+", "-", "*", "/", + "&", "|", "<", ">", "=", "~" +}; +mkstrlist(symbols, symbolsraw); + +#endif diff --git a/tokenizer/tokenizer.c b/tokenizer/tokenizer.c new file mode 100644 index 0000000..d9264b4 --- /dev/null +++ b/tokenizer/tokenizer.c @@ -0,0 +1,257 @@ +#include +#include +#include +#include +#include "tokenizer.h" +#include "tokenizer-tables.h" + +// Data types +typedef enum { + common, charsymbol, space +} CHARTYPE; + +typedef struct { + char* str; + int size; + int count; +} STRING; + +// String manipulation +STRING* mkstring(int size); +void append(STRING* s, char c); +void freestr(STRING* str); + +// Token manipulation; +TOKEN* appendtokenraw(TOKEN* curitem, STRING* token, int definedat, TOKENTYPE type); +TOKEN* appendtoken(TOKEN* curitem, STRING* token, char* file, int definedat); +#define mktoken() (TOKEN*)malloc(sizeof(TOKEN)) + +// Char types +CHARTYPE getchartype(unsigned char c); +bool iskeyword(STRING* tk); +bool issymbol(STRING* tk); +bool isint(char* str); +bool isintcons(STRING* tk); +bool isidentifier(STRING* tk); +TOKENTYPE gettokentype(STRING* tk, char* file, int definedat); + +// Stream handling +void skipln(FILE* input); +void skipmultiln(FILE* input, int* lnscount); +bool handlecomment(FILE* input, int* lnscount); +void readstr(FILE* input, STRING* tmp, int definedat); + +// String manipulation +STRING* mkstring(int size) { + STRING* str = (STRING*)malloc(sizeof(STRING)); + str->size = sizeof(char) * size; // initial size + str->str = (char*)malloc(str->size); + str->count = 0; + return str; +} + +void append(STRING* s, char c) { + int targsize = sizeof(char) * (s->count + 1); + if(s->size <= targsize) { + s->size = targsize * 2; + s->str = (char*)realloc(s->str, s->size); + } + + s->str[s->count] = c; + s->count++; +} + +void freestr(STRING* str) { + free(str->str); + free(str); +} + +// Token manipulation; +TOKEN* appendtokenraw(TOKEN* curitem, STRING* token, int definedat, TOKENTYPE type) { + curitem->token = (char*)malloc(sizeof(char)*token->count); + strcpy(curitem->token, token->str); + curitem->definedat = definedat; + curitem->type = type; + TOKEN* nextitem = mktoken(); + curitem->next = nextitem; + token->count = 0; + return nextitem; +} + +void freetokens(TOKEN* t) { + free(t->token); + TOKEN* next = t->next; + free(t); + if(next != NULL) + freetokens(next); +} + +TOKEN* appendtoken(TOKEN* curitem, STRING* token, char* file, int definedat) { + append(token, '\0'); + return appendtokenraw(curitem, token, definedat, gettokentype(token, file, definedat)); +} + +// Char types +CHARTYPE getchartype(unsigned char c) { + if(isspace(c)) return space; + if(isalnum(c) || c == '_' || c == '"') return common; + return charsymbol; +} + +bool iskeyword(STRING* tk) { + return existsinarray(&keywords, tk->str); +} + +bool issymbol(STRING* tk) { + if(tk->count != 2) + return false; + return existsinarray(&symbols, tk->str); +} + +bool isint(char* str) { + int i = 0; + while(str[i] != '\0') { + if(!isdigit(str[i])) + return false; + i++; + } + return true; +} + +bool isintcons(STRING* tk) { + if(!isint(tk->str)) + return false; + int val = atoi(tk->str); + return val >= 0 && val <= 32767; +} + +bool isidentifier(STRING* tk) { + if(isdigit(tk->str[0])) + return false; + + int count = tk->count - 1; + for(int i = 0; i < count; i++) + if(!isalnum(tk->str[i]) && tk->str[i] != '_') + return false; + return true; +} + +TOKENTYPE gettokentype(STRING* tk, char* file, int definedat) { + if(iskeyword(tk)) return keyword; + if(issymbol(tk)) return symbol; + if(isintcons(tk)) return integer; + if(isidentifier(tk)) return identifier; + eprintf("Unexpected token '%s'; file '%s', line %i\n", tk->str, file, definedat); + exit(1); +} + +// Stream handling +void skipln(FILE* input) { + unsigned char c; + while(c = fgetc(input), c != '\0') + if(c == '\n') + break; +} + +void skipmultiln(FILE* input, int* lnscount) { + unsigned char c; + while(c = fgetc(input), c != '\0') + if(c == '\n') + (*lnscount)++; + else if(c == '*') + if(fgetc(input) == '/') + break; +} + +bool handlecomment(FILE* input, int* lnscount) { + unsigned char nextc = fgetc(input); + if(nextc == '/') { + skipln(input); + (*lnscount)++; + return true; + } + else if(nextc == '*') { + unsigned char furtherc = fgetc(input); + if(furtherc == '*') { + skipmultiln(input, lnscount); + return true; + } + ungetc(furtherc, input); + } + ungetc(nextc, input); + return false; +} + +void readstr(FILE* input, STRING* tmp, int definedat) { + unsigned char c; + while(c = fgetc(input), c != '\0') { + if(c == '\n') { + eprintf("Unexpected end of line; line %i", definedat); + exit(1); + } + if(c == '"') + break; + append(tmp, c); + } + append(tmp, '\0'); +} + +TOKEN* tokenize(char* file) { + TOKEN* head = mktoken(); + TOKEN* lastitem = head; + TOKEN* curitem = head; + + STRING* tmptoken = mkstring(200); + CHARTYPE lasttype = space; + CHARTYPE curtype; + + int lnscount = 1; + FILE* input = fopen(file, "r"); + + unsigned char c; + while(!feof(input)) { + c = fgetc(input); + if(c == '\n') + lnscount++; + else if(c == '/' && handlecomment(input, &lnscount)) + continue; + else if(c == '"') { + if(lasttype != space) + curitem = appendtoken(curitem, tmptoken, file, lnscount); + readstr(input, tmptoken, lnscount); + lastitem = curitem; + curitem = appendtokenraw(curitem, tmptoken, lnscount, string); + lasttype = space; + continue; + } + + curtype = getchartype(c); + + if(curtype == common) { + if(lasttype == charsymbol) { + lastitem = curitem; + curitem = appendtoken(curitem, tmptoken, file, lnscount); + } + append(tmptoken, c); + } else { + if(lasttype != space){ + lastitem = curitem; + curitem = appendtoken(curitem, tmptoken, file, lnscount); + } + if(curtype == charsymbol) + append(tmptoken, c); + } + lasttype = curtype; + } + + if(curitem == head) { + eprintf("File '%s' is empty\n", file); + exit(1); + } + + lastitem->next = NULL; + free(curitem); + freestr(tmptoken); + fclose(input); + return head; +} diff --git a/tokenizer/tokenizer.h b/tokenizer/tokenizer.h new file mode 100644 index 0000000..2d2a5f6 --- /dev/null +++ b/tokenizer/tokenizer.h @@ -0,0 +1,21 @@ +#ifndef TOKENIZER_H +#define TOKENIZER_H +#include + +/* tokenizer + * Simple tool that splits a stream into many tokens. */ + +typedef enum { + keyword, identifier, symbol, integer, string +} TOKENTYPE; + +typedef struct token { + char* token; + TOKENTYPE type; + int definedat; + struct token* next; +} TOKEN; + +TOKEN* tokenize(char* filename); +void freetokens(TOKEN* t); +#endif diff --git a/vm/vm-lines.c b/vm/vm-lines.c new file mode 100644 index 0000000..69541f7 --- /dev/null +++ b/vm/vm-lines.c @@ -0,0 +1,75 @@ +#include +#include "vm-lines.h" + +LINE* mkline(int size) { + LINE* ln = (LINE*)malloc(sizeof(LINE)); + ln->tokens = (char**)malloc(sizeof(char*)*size); + ln->count = 0; + return ln; +} + +void addtoken(LINE* ln, char* token) { + ln->tokens[ln->count] = token; + ln->count++; +} + +void println(LINE* ln, FILE* stream) { + for(int i = 0; i < ln->count; i++) { + fprintf(stream, "%s", ln->tokens[i]); + if(i + 1 < ln->count) + fprintf(stream, " "); + } + fprintf(stream, "\n"); +} + +void printlns(LINE* lns, FILE* stream) { + while(lns != NULL) { + println(lns, stream); + lns = lns->next; + } +} + +void freeln(LINE* ln) { + for(int i = 0; i < ln->count; i++) + free(ln->tokens[i]); + free(ln->tokens); + free(ln); +} + +void freelns(LINE* lns) { + LINE* next = lns->next; + freeln(lns); + if(next != NULL) + freelns(next); +} + +void freelnblk(LINEBLOCK* blk) { + freelns(blk->head); + free(blk); +} + +LINEBLOCK* mklnblk(LINE* start) { + LINEBLOCK* blk = (LINEBLOCK*)malloc(sizeof(LINEBLOCK)); + blk->head = start; + blk->tail = start; + return blk; +} + +LINEBLOCK* mergelnblks(LINEBLOCK* head, LINEBLOCK* tail) { + if(head == NULL) + return tail; + head->tail->next = tail->head; + head->tail = tail->tail; + free(tail); + return head; +} + +void appendln(LINEBLOCK* lnblk, LINE* ln) { + lnblk->tail->next = ln; + lnblk->tail = ln; +} + +void appendlnbefore(LINEBLOCK* lnblk, LINE* ln) { + ln->next = lnblk->head; + lnblk->head = ln; +} diff --git a/vm/vm-lines.h b/vm/vm-lines.h new file mode 100644 index 0000000..9503c10 --- /dev/null +++ b/vm/vm-lines.h @@ -0,0 +1,39 @@ +#ifndef VM_LINES_H +#define VM_LINES_H +#include + +/* vm-lines + * Unified standard for the compiler's output and vm-translator's input. + * It is also used by vm-parser when reading .vm files. */ + +// Data types +typedef struct line { + char** tokens; + int count; + struct line* next; +} LINE; + +typedef struct { + LINE* head; + LINE* tail; +} LINEBLOCK; + +// Line manipulation +LINE* mkline(int size); +void addtoken(LINE* ln, char* token); + +// Line printing +void println(LINE* ln, FILE* stream); +void printlns(LINE* lns, FILE* stream); + +// Line freeing +void freeln(LINE* ln); +void freelns(LINE* lns); +void freelnblk(LINEBLOCK* blk); + +// Line block manipulation +LINEBLOCK* mklnblk(LINE* start); +LINEBLOCK* mergelnblks(LINEBLOCK* head, LINEBLOCK* tail); +void appendln(LINEBLOCK* lnblk, LINE* ln); +void appendlnbefore(LINEBLOCK* lnblk, LINE* ln); +#endif diff --git a/vm/vm-templates.h b/vm/vm-templates.h new file mode 100644 index 0000000..d3df959 --- /dev/null +++ b/vm/vm-templates.h @@ -0,0 +1,313 @@ +#ifndef VM_TEMPLATES +#define VM_TEMPLATES +#else +#error vm-templates may only be included once +#endif + +#include "util.h" + +#define mktemplate(name, array) TEMPLATE name = { .items = array, .count = strcount(array) }; + +typedef struct { + char** items; + int count; +} TEMPLATE; + +char* tpushlns[] = { + "", + "", + "", + "", + "A=D+A", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", +}; +mktemplate(tpush, tpushlns); + +char* tpushconslns[] = { + "", + "", + "D=A", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", +}; +mktemplate(tpushcons, tpushconslns); + +char* tpushstatlns[] = { + "", + "", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", +}; +mktemplate(tpushstat, tpushstatlns); + + +mktemplate(tpushtemp, tpushstatlns); +mktemplate(tpushpointer, tpushstatlns); + +char* tpoplns[] = { + "", + "", + "", + "", + "D=D+A", + "@R13", + "M=D", + "@SP", + "AM=M-1", + "D=M", + "@R13", + "A=M", + "M=D" +}; +mktemplate(tpop, tpoplns); + +char* tpopstatlns[] = { + "", + "@SP", + "AM=M-1", + "D=M", + "", + "" +}; +mktemplate(tpopstat, tpopstatlns); + +mktemplate(tpoptemp, tpopstatlns); + +mktemplate(tpoppointer, tpopstatlns); + +char* tarithlns[] = { + "", + "@SP", + "AM=M-1", + "D=M", + "A=A-1", + "" +}; +mktemplate(tarith, tarithlns); + +char* tneglns[] = { + "", + "@SP", + "A=M-1", + "M=-M", +}; +mktemplate(tneg, tneglns); + +char* tnotlns[] = { + "", + "@SP", + "A=M-1", + "M=!M", +}; +mktemplate(tnot, tnotlns); + +char* tcomplns[] = { + "", + "@SP", + "AM=M-1", + "D=M", + "A=A-1", + "D=D-M", + "M=-1", + "", + "", + "@SP", + "A=M-1", + "M=0", + "" +}; +mktemplate(tcomp, tcomplns); + +char* tlabellns[] = { + "", + "" +}; +mktemplate(tlabel, tlabellns); + +char* tgotolns[] = { + "", + "", + "0;JMP" +}; +mktemplate(tgoto, tgotolns); + +char* tifgotolns[] = { + "", + "@SP", + "AM=M-1", + "D=M", + "", + "D;JNE" +}; +mktemplate(tifgoto, tifgotolns); + +char* tcallstartlns[] = { + "", + "", + "D=A", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", +}; +mktemplate(tcallstart, tcallstartlns); + +char* tcallpushlns[] = { + "", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", +}; +mktemplate(tcallpush, tcallpushlns); + +char* tcallsetarglns[] = { + "@SP", + "D=M", + "@LCL", + "M=D", + "", + "D=D-A", + "@ARG", + "M=D" +}; +mktemplate(tcallsetarg, tcallsetarglns); + +char* tcalljmplns[] = { + "", + "0;JMP", + "" +}; +mktemplate(tcalljmp, tcalljmplns); + +char* tframevarslns[] = { + "@LCL", + "@ARG", + "@THIS", + "@THAT" +}; +mktemplate(tframevars, tframevarslns); + +char* tfunctionlns[] = { + "", + "" +}; +mktemplate(tfunction, tfunctionlns); + +char* tfunctionpushlns[] = { + "@SP", + "A=M", + "M=0", + "@SP", + "M=M+1" +}; +mktemplate(tfunctionpush, tfunctionpushlns); + +char* tstartreturnlns[] = { + "", + "@LCL", + "D=M", + "@5", + "A=D-A", + "D=M", + "@R13", + "M=D", + "@SP", + "A=M-1", + "D=M", + "@ARG", + "A=M", + "M=D", + "@ARG", + "D=M+1", + "@SP", + "M=D" +}; +mktemplate(tstartreturn, tstartreturnlns); + +char* tretpoplns[] = { + "@LCL", + "AM=M-1", + "D=M", + "", + "M=D", +}; +mktemplate(tretpop, tretpoplns); + +char* tendreturnlns[] = { + "@R13", + "A=M", + "0;JMP" +}; +mktemplate(tendreturn, tendreturnlns); + +char* tbootstraplns[] = { + "@256", + "D=A", + "@SP", + "M=D", + "@BOOTSTRAP$ret", + "D=A", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", + "@LCL", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", + "@ARG", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", + "@THIS", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", + "@THAT", + "D=M", + "@SP", + "A=M", + "M=D", + "@SP", + "M=M+1", + "@5", + "D=A", + "@SP", + "D=M-D", + "@ARG", + "M=D", + "@SP", + "D=M", + "@LCL", + "M=D", + "@Sys.init", + "0;JMP", + "(BOOTSTRAP$ret)" +}; +mktemplate(tbootstrap, tbootstraplns); diff --git a/vm/vm-translator.c b/vm/vm-translator.c new file mode 100644 index 0000000..20a1b16 --- /dev/null +++ b/vm/vm-translator.c @@ -0,0 +1,471 @@ +#include +#include +#include "vm-templates.h" +#include "vm-translator.h" +#include "util.h" +#define eq(translator, index, str) !strcmp(translator->currln->tokens[index], str) + +typedef struct { + STRINGLIST* head; + STRINGLIST* tail; +} ASMBLK; + +STRINGLIST* asmln(char* content) { + STRINGLIST* ln = (STRINGLIST*)malloc(sizeof(STRINGLIST)); + ln->content = content; + return ln; +} + +void togarbage(VMTRANSLATOR* t, char* str) { + STRINGLIST* garb = asmln(str); + garb->next = t->garbage; + t->garbage = garb; +} + +char* atraw(VMTRANSLATOR* t, char* n, int len) { + int sz = sizeof(char) * (len + 2); + char* atstr = (char*)malloc(sz); + sprintf(atstr, "@%s", n); + togarbage(t, atstr); + return atstr; +} + +char* at(VMTRANSLATOR* t, char* n) { + return atraw(t, n, strlen(n)); +} + +char* atn(VMTRANSLATOR* t, int n) { + char* str = itoa(n); + togarbage(t, str); + return at(t, str); +} + +char* mkstr(VMTRANSLATOR* t, char* str) { + char* heapstr = ezheapstr(str); + togarbage(t, heapstr); + return heapstr; +} + +char* mkpointerind(VMTRANSLATOR* t) { + if(t->currln->tokens[2][0] == 0) + return mkstr(t, "@THIS"); + else + return mkstr(t, "@THAT"); +} + +char* mktempind(VMTRANSLATOR* t) { + int index = atoi(t->currln->tokens[2]); + char* actualind = itoa(index+5); + togarbage(t, actualind); + return at(t, actualind); +} + +char* dotat(VMTRANSLATOR* t, char* name, char* n) { + int sz = sizeof(char) * (strlen(name) + strlen(n) + 3); + char* atstr = (char*)malloc(sz); + sprintf(atstr, "@%s.%s", name, n); + togarbage(t, atstr); + return atstr; +} + +char* comment(VMTRANSLATOR* t) { + int sz = (4 + strlen(t->currln->tokens[0])) * sizeof(char); + for(int i = 1; i < t->currln->count; i++) + sz += (1 + strlen(t->currln->tokens[i])) * sizeof(char); + + char* com = (char*)malloc(sz); + if(t->currln->count == 1) + sprintf(com, "// %s", t->currln->tokens[0]); + else if(t->currln->count == 2) + sprintf(com, "// %s %s", t->currln->tokens[0], + t->currln->tokens[1]); + else if(t->currln->count == 3) + sprintf(com, "// %s %s %s", t->currln->tokens[0], + t->currln->tokens[1], + t->currln->tokens[2]); + + togarbage(t, com); + return com; +} + +char* switchsegment(VMTRANSLATOR* t) { + if(eq(t, 1, "local")) + return mkstr(t, "@LCL"); + if(eq(t, 1, "argument")) + return mkstr(t, "@ARG"); + if(eq(t, 1, "this")) + return mkstr(t, "@THIS"); + return mkstr(t, "@THAT"); +} + +char* mkspeciallab(VMTRANSLATOR* t, char* suffix, int* ind, int* len) { + (*ind)++; + *len = t->classnamelen + countplaces(*ind) + strlen(suffix) + 2; + int sz = ((*len)+1) * sizeof(char); + char* lab = (char*)malloc(sz); + sprintf(lab, "%s$%s.%i", t->classname, suffix, (*ind)); + togarbage(t, lab); + return lab; +} + +char* mkcmplab(VMTRANSLATOR* t, int* len) { + return mkspeciallab(t, "cmp", &(t->cmpind), len); +} + +char* mkretlab(VMTRANSLATOR* t, int* len) { + return mkspeciallab(t, "ret", &(t->retind), len); +} + +char* enclosingparenthesis(VMTRANSLATOR* t, char* content, int len) { + int sz = sizeof(char) * (len + 3); + char* str = (char*)malloc(sz); + sprintf(str, "(%s)", content); + togarbage(t, str); + return str; +} + +char* mklab(VMTRANSLATOR* t) { + int sz = (t->classnamelen + strlen(t->currln->tokens[1]) + 4) * sizeof(char); + char* lab = (char*)malloc(sz); + sprintf(lab, "(%s$%s)", t->classname, t->currln->tokens[1]); + togarbage(t, lab); + return lab; +} + +char* mkgotolab(VMTRANSLATOR* t) { + int sz = sizeof(char) * (t->classnamelen + strlen(t->currln->tokens[1]) + 3); + char* lab = (char*)malloc(sz); + sprintf(lab, "@%s$%s", t->classname, t->currln->tokens[1]); + togarbage(t, lab); + return lab; +} + +ASMBLK* copytemplate(TEMPLATE* t) { + ASMBLK* blk = (ASMBLK*)malloc(sizeof(ASMBLK)); + blk->head = asmln(t->items[0]); + STRINGLIST* curr = blk->head; + for(int i = 1; i < t->count; i++) { + STRINGLIST* newln = asmln(t->items[i]); + curr->next = newln; + curr = newln; + } + curr->next = NULL; + blk->tail = curr; + return blk; +} + +ASMBLK* mkasmlns(VMTRANSLATOR* t, TEMPLATE* tp) { + // instruction comment + tp->items[0] = comment(t); + + return copytemplate(tp); +} + +void mergeasmblks(ASMBLK* a, ASMBLK* b) { + a->tail->next = b->head; + a->tail = b->tail; + free(b); +} + + + +/* START STACK MANIPULATION */ + +ASMBLK* translatepushconst(VMTRANSLATOR* t) { + // @i + tpushcons.items[1] = at(t, t->currln->tokens[2]); + + return mkasmlns(t, &tpushcons); +} + +ASMBLK* translatepushstatic(VMTRANSLATOR* t) { + // @classname.i + tpushstat.items[1] = dotat(t, t->classname, t->currln->tokens[2]); + + return mkasmlns(t, &tpushstat); +} + +ASMBLK* translatepushpointer(VMTRANSLATOR* t) { + // @THIS/@THAT + tpushpointer.items[1] = mkpointerind(t); + + return mkasmlns(t, &tpushpointer); +} + +ASMBLK* translatepushtemp(VMTRANSLATOR* t) { + // @5+i + tpushtemp.items[1] = mktempind(t); + + return mkasmlns(t, &tpushtemp); +} + +void pushpopcommon(VMTRANSLATOR* t, TEMPLATE* tp) { + // @segment + tp->items[1] = switchsegment(t); + + // D=M + tp->items[2] = mkstr(t, "D=M"); + + // @i + tp->items[3] = at(t, t->currln->tokens[2]); +} + +ASMBLK* translatepushgeneric(VMTRANSLATOR* t) { + pushpopcommon(t, &tpush); + + return mkasmlns(t, &tpush); +} + +ASMBLK* translatepush(VMTRANSLATOR* t) { + if(eq(t, 1, "constant")) + return translatepushconst(t); + if(eq(t, 1, "static")) + return translatepushstatic(t); + if(eq(t, 1, "pointer")) + return translatepushpointer(t); + if(eq(t, 1, "temp")) + return translatepushtemp(t); + return translatepushgeneric(t); +} + +ASMBLK* translatepopstatic(VMTRANSLATOR* t) { + // @classname.i + tpopstat.items[tpopstat.count-2] = dotat(t, t->classname, t->currln->tokens[2]); + + // M=D + tpopstat.items[tpopstat.count-1] = mkstr(t, "M=D"); + + return mkasmlns(t, &tpopstat); +} + +ASMBLK* translatepoppointer(VMTRANSLATOR* t) { + // @THIS/@THAT + tpoppointer.items[tpoppointer.count-2] = mkpointerind(t); + + // M=D + tpoppointer.items[tpoppointer.count-1] = mkstr(t, "M=D"); + + return mkasmlns(t, &tpoppointer); +} + +ASMBLK* translatepoptemp(VMTRANSLATOR* t) { + // @5+i + tpoptemp.items[tpoptemp.count-2] = mktempind(t); + + tpoptemp.items[tpoptemp.count-1] = mkstr(t, "M=D"); + + return mkasmlns(t, &tpoptemp); +} + +ASMBLK* translatepopgeneric(VMTRANSLATOR* t) { + pushpopcommon(t, &tpop); + + return mkasmlns(t, &tpop); +} + +ASMBLK* translatepop(VMTRANSLATOR* t) { + if(eq(t, 1, "static")) + return translatepopstatic(t); + if(eq(t, 1, "pointer")) + return translatepoppointer(t); + if(eq(t, 1, "temp")) + return translatepoptemp(t); + return translatepopgeneric(t); +} + +/* END STACK MANIPULATION */ + + +/* BEGIN OPERATIONS */ + +ASMBLK* translatearith(VMTRANSLATOR* t, char* op) { + tarith.items[tarith.count-1] = mkstr(t, op); + + return mkasmlns(t, &tarith); +} + +ASMBLK* translatecomp(VMTRANSLATOR* t, char* op) { + int labellen; + char* label = mkcmplab(t, &labellen); + + // @label + tcomp.items[tcomp.count-6] = atraw(t, label, labellen); + + // D;J(op) + int sz = sizeof(char) * 6; + char* trueop = (char*)malloc(sz); + sprintf(trueop, "D;J%s", op); + tcomp.items[tcomp.count-5] = trueop; + togarbage(t, trueop); + + // (label) + tcomp.items[tcomp.count-1] = enclosingparenthesis(t, label, labellen); + + return mkasmlns(t, &tcomp); +} + +/* END OPERATIONS */ + +ASMBLK* translatelabel(VMTRANSLATOR* t) { + // (classname$label) + tlabel.items[tlabel.count-1] = mklab(t); + + return mkasmlns(t, &tlabel); +} + +ASMBLK* translategoto(VMTRANSLATOR* t) { + // @label + tgoto.items[tgoto.count-2] = mkgotolab(t); + + return mkasmlns(t, &tgoto); +} + +ASMBLK* translateifgoto(VMTRANSLATOR* t) { + // @label + tifgoto.items[tifgoto.count-2] = mkgotolab(t); + + return mkasmlns(t, &tifgoto); +} + +ASMBLK* translatereturn(VMTRANSLATOR* t) { + ASMBLK* blk = mkasmlns(t, &tstartreturn); + + for(int i = tframevars.count-1; i >= 0; i--) { + tretpop.items[tretpop.count-2] = tframevars.items[i]; + mergeasmblks(blk, copytemplate(&tretpop)); + } + + mergeasmblks(blk, copytemplate(&tendreturn)); + return blk; +} + +ASMBLK* translatefunction(VMTRANSLATOR* t) { + t->retind = 0; + t->cmpind = 0; + + // (funcname) + tfunction.items[1] = mklab(t); + ASMBLK* blk = mkasmlns(t, &tfunction); + + // repeat nVars times: + int nlocals = atoi(t->currln->tokens[2]); + + for(int i = 0; i < nlocals; i++) + mergeasmblks(blk, copytemplate(&tfunctionpush)); + + return blk; +} + +ASMBLK* pushframe(VMTRANSLATOR* t, char* retlab, int retlablen, int* framesize) { + tcallstart.items[1] = atraw(t, retlab, retlablen); + + ASMBLK* blk = mkasmlns(t, &tcallstart); + + for(int i = 0; i < tframevars.count; i++) { + tcallpush.items[0] = tframevars.items[i]; + mergeasmblks(blk, copytemplate((&tcallpush))); + } + + *framesize = tframevars.count + 1; + return blk; +} + +ASMBLK* translatecall(VMTRANSLATOR* t) { + // return label + int retlablen; + char* retlab = mkretlab(t, &retlablen); + + // push frame + int framesize; + ASMBLK* blk = pushframe(t, retlab, retlablen, &framesize); + + // setting ARG + int nargs = atoi(t->currln->tokens[2]); + tcallsetarg.items[tcallsetarg.count-4] = atn(t, nargs + framesize); + mergeasmblks(blk, copytemplate(&tcallsetarg)); + + // jmp + tcalljmp.items[tcalljmp.count-3] = at(t, t->currln->tokens[1]); + tcalljmp.items[tcalljmp.count-1] = enclosingparenthesis(t, retlab, retlablen); + mergeasmblks(blk, copytemplate(&tcalljmp)); + + return blk; +} + +ASMBLK* translateln(VMTRANSLATOR* t) { + if(eq(t, 0, "push")) + return translatepush(t); + if(eq(t, 0, "pop")) + return translatepop(t); + + if(eq(t, 0, "add")) + return translatearith(t, "M=D+M"); + if(eq(t, 0, "sub")) + return translatearith(t, "M=M-D"); + if(eq(t, 0, "and")) + return translatearith(t, "M=D&M"); + if(eq(t, 0, "or")) + return translatearith(t, "M=D|M"); + + if(eq(t, 0, "neg")) + return mkasmlns(t, &tneg); + if(eq(t, 0, "not")) + return mkasmlns(t, &tnot); + + if(eq(t, 0, "eq")) + return translatecomp(t, "EQ"); + if(eq(t, 0, "gt")) + return translatecomp(t, "LT"); + if(eq(t, 0, "lt")) + return translatecomp(t, "GT"); + + if(eq(t, 0, "label")) + return translatelabel(t); + if(eq(t, 0, "goto")) + return translategoto(t); + if(eq(t, 0, "if-goto")) + return translateifgoto(t); + + if(eq(t, 0, "return")) + return translatereturn(t); + if(eq(t, 0, "function")) + return translatefunction(t); + return translatecall(t); +} + +STRINGLIST* translatevm(VMTRANSLATOR* t) { + ASMBLK* blk = copytemplate(&tbootstrap); + while(t->currln != NULL) { + mergeasmblks(blk, translateln(t)); + t->currln = t->currln->next; + } + STRINGLIST* output = blk->head; + free(blk); + return output; +} + +VMTRANSLATOR* mkvmtranslator(char* classname, LINEBLOCK* vmlines) { + VMTRANSLATOR* transl = (VMTRANSLATOR*)malloc(sizeof(VMTRANSLATOR)); + transl->currln = vmlines->head; + transl->start = vmlines->head; + transl->garbage = NULL; + transl->retind = 0; + transl->cmpind = 0; + transl->classname = classname; + transl->classnamelen = strlen(classname); + return transl; +} + +void freegarbage(STRINGLIST* garbage) { + if(garbage != NULL) { + free(garbage->content); + STRINGLIST* next = garbage->next; + free(garbage); + freegarbage(next); + } +} + +void freevmtranslator(VMTRANSLATOR* t) { + freegarbage(t->garbage); + free(t); +} diff --git a/vm/vm-translator.h b/vm/vm-translator.h new file mode 100644 index 0000000..9ee994a --- /dev/null +++ b/vm/vm-translator.h @@ -0,0 +1,20 @@ +#ifndef VM_TRANSLATOR +#define VM_TRANSLATOR +#include "vm-lines.h" + +typedef struct { + char* classname; + int classnamelen; + LINE* start; + LINE* currln; + STRINGLIST* garbage; + int cmpind; + int retind; +} VMTRANSLATOR; + + +STRINGLIST* translatevm(VMTRANSLATOR* t); +VMTRANSLATOR* mkvmtranslator(char* classname, LINEBLOCK* vmlines); +void freevmtranslator(VMTRANSLATOR* t); + +#endif