mclang/mclangc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

merge into: mclang:c_rwr
Branches Tags
mclang:main
mclang:asm-main
mclang:c_rwr
mclang:main-v2
mclang:dev
mclang:stable
...
pull from: mclang:main
Branches Tags
mclang:asm-main
mclang:c_rwr
mclang:main-v2
mclang:dev
mclang:main
mclang:stable

No commits in common. "c_rwr" and "main" have entirely different histories.
c_rwr ... main

83 changed files with 7922 additions and 2042 deletions
Show Stats Expand all files Collapse all files

236
.clang-format
View File

@ -1,236 +0,0 @@
---
Language: Cpp
# BasedOnStyle: LLVM
AccessModifierOffset: -4
AlignAfterOpenBracket: Align
AlignArrayOfStructures: None
AlignConsecutiveAssignments:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: true
AlignConsecutiveBitFields:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignConsecutiveDeclarations:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignConsecutiveMacros:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignConsecutiveShortCaseStatements:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCaseColons: false
AlignEscapedNewlines: Left
AlignOperands: Align
AlignTrailingComments:
Kind: Always
OverEmptyLines: 0
AllowAllArgumentsOnNextLine: true
AllowAllParametersOfDeclarationOnNextLine: true
AllowShortBlocksOnASingleLine: Never
AllowShortCaseLabelsOnASingleLine: false
AllowShortEnumsOnASingleLine: true
AllowShortFunctionsOnASingleLine: All
AllowShortIfStatementsOnASingleLine: WithoutElse
AllowShortLambdasOnASingleLine: All
AllowShortLoopsOnASingleLine: false
AlwaysBreakAfterDefinitionReturnType: None
AlwaysBreakAfterReturnType: None
AlwaysBreakBeforeMultilineStrings: false
AlwaysBreakTemplateDeclarations: Yes
AttributeMacros:
- __capability
BinPackArguments: true
BinPackParameters: true
BitFieldColonSpacing: Both
BraceWrapping:
AfterCaseLabel: false
AfterClass: false
AfterControlStatement: Never
AfterEnum: false
AfterExternBlock: false
AfterFunction: false
AfterNamespace: false
AfterObjCDeclaration: false
AfterStruct: false
AfterUnion: false
BeforeCatch: false
BeforeElse: false
BeforeLambdaBody: false
BeforeWhile: false
IndentBraces: false
SplitEmptyFunction: true
SplitEmptyRecord: true
SplitEmptyNamespace: true
BreakAfterAttributes: Never
BreakAfterJavaFieldAnnotations: false
BreakArrays: true
BreakBeforeBinaryOperators: None
BreakBeforeConceptDeclarations: Always
BreakBeforeBraces: Attach
BreakBeforeInlineASMColon: OnlyMultiline
BreakBeforeTernaryOperators: true
BreakConstructorInitializers: BeforeColon
BreakInheritanceList: BeforeColon
BreakStringLiterals: true
ColumnLimit: 160
CommentPragmas: '^ IWYU pragma:'
CompactNamespaces: false
ConstructorInitializerIndentWidth: 4
ContinuationIndentWidth: 4
Cpp11BracedListStyle: true
DerivePointerAlignment: false
DisableFormat: false
EmptyLineAfterAccessModifier: Never
EmptyLineBeforeAccessModifier: LogicalBlock
ExperimentalAutoDetectBinPacking: false
FixNamespaceComments: true
ForEachMacros:
- foreach
- Q_FOREACH
- BOOST_FOREACH
IfMacros:
- KJ_IF_MAYBE
IncludeBlocks: Preserve
IncludeCategories:
- Regex: '^"(llvm|llvm-c|clang|clang-c)/'
Priority: 2
SortPriority: 0
CaseSensitive: false
- Regex: '^(<|"(gtest|gmock|isl|json)/)'
Priority: 3
SortPriority: 0
CaseSensitive: false
- Regex: '.*'
Priority: 1
SortPriority: 0
CaseSensitive: false
IncludeIsMainRegex: '(Test)?$'
IncludeIsMainSourceRegex: ''
IndentAccessModifiers: false
IndentCaseBlocks: false
IndentCaseLabels: false
IndentExternBlock: AfterExternBlock
IndentGotoLabels: true
IndentPPDirectives: None
IndentRequiresClause: true
IndentWidth: 4
IndentWrappedFunctionNames: false
InsertBraces: true
InsertNewlineAtEOF: false
InsertTrailingCommas: None
IntegerLiteralSeparator:
Binary: 0
BinaryMinDigits: 0
Decimal: 0
DecimalMinDigits: 0
Hex: 0
HexMinDigits: 0
JavaScriptQuotes: Leave
JavaScriptWrapImports: true
KeepEmptyLinesAtTheStartOfBlocks: true
KeepEmptyLinesAtEOF: false
LambdaBodyIndentation: Signature
LineEnding: DeriveLF
MacroBlockBegin: ''
MacroBlockEnd: ''
MaxEmptyLinesToKeep: 1
NamespaceIndentation: All
ObjCBinPackProtocolList: Auto
ObjCBlockIndentWidth: 2
ObjCBreakBeforeNestedBlockParam: true
ObjCSpaceAfterProperty: false
ObjCSpaceBeforeProtocolList: true
PackConstructorInitializers: BinPack
PenaltyBreakAssignment: 2
PenaltyBreakBeforeFirstCallParameter: 19
PenaltyBreakComment: 300
PenaltyBreakFirstLessLess: 120
PenaltyBreakOpenParenthesis: 0
PenaltyBreakString: 1000
PenaltyBreakTemplateDeclaration: 10
PenaltyExcessCharacter: 1000000
PenaltyIndentedWhitespace: 0
PenaltyReturnTypeOnItsOwnLine: 60
PointerAlignment: Left
PPIndentWidth: -1
QualifierAlignment: Leave
ReferenceAlignment: Pointer
ReflowComments: true
RemoveBracesLLVM: false
RemoveParentheses: Leave
RemoveSemicolon: false
RequiresClausePosition: OwnLine
RequiresExpressionIndentation: OuterScope
SeparateDefinitionBlocks: Always
ShortNamespaceLines: 1
SortIncludes: CaseSensitive
SortJavaStaticImport: Before
SortUsingDeclarations: LexicographicNumeric
SpaceAfterCStyleCast: false
SpaceAfterLogicalNot: false
SpaceAfterTemplateKeyword: true
SpaceAroundPointerQualifiers: Default
SpaceBeforeAssignmentOperators: true
SpaceBeforeCaseColon: false
SpaceBeforeCpp11BracedList: false
SpaceBeforeCtorInitializerColon: true
SpaceBeforeInheritanceColon: true
SpaceBeforeJsonColon: false
SpaceBeforeParens: ControlStatements
SpaceBeforeParensOptions:
AfterControlStatements: true
AfterForeachMacros: true
AfterFunctionDefinitionName: false
AfterFunctionDeclarationName: false
AfterIfMacros: true
AfterOverloadedOperator: false
AfterRequiresInClause: false
AfterRequiresInExpression: false
BeforeNonEmptyParentheses: false
SpaceBeforeRangeBasedForLoopColon: true
SpaceBeforeSquareBrackets: false
SpaceInEmptyBlock: false
SpacesBeforeTrailingComments: 1
SpacesInAngles: Never
SpacesInContainerLiterals: true
SpacesInLineCommentPrefix:
Minimum: 1
Maximum: -1
SpacesInParens: Never
SpacesInParensOptions:
InCStyleCasts: false
InConditionalStatements: false
InEmptyParentheses: false
Other: false
SpacesInSquareBrackets: false
Standard: Latest
StatementAttributeLikeMacros:
- Q_EMIT
StatementMacros:
- Q_UNUSED
- QT_REQUIRE_VERSION
TabWidth: 4
UseTab: Never
VerilogBreakBetweenInstancePorts: true
WhitespaceSensitiveMacros:
- BOOST_PP_STRINGIZE
- CF_SWIFT_NAME
- NS_SWIFT_NAME
- PP_STRINGIZE
- STRINGIZE
...

15
.editorconfig
View File

@ -1,15 +0,0 @@
# EditorConfig is awesome: https://EditorConfig.org
# top-most EditorConfig file
root = true
[{Makefile, *.mk}]
indent_style = tab
[*.{c,cpp,h,hpp}]
indent_style = space
indent_size = 4
end_of_line = lf
charset = utf-8
trim_trailing_whitespace = false
insert_final_newline = false

26
.github/workflows/rust.yml vendored Normal file
View File

@ -0,0 +1,26 @@
name: Rust
on:
push:
branches: [ "main" ]
pull_request:
branches: [ "main" ]
env:
CARGO_TERM_COLOR: always
jobs:
build:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- name: Build
run: cargo build --release --verbose
- name: Run cargo tests
run: cargo test --release --verbose
- name: Run lang tests
run: ./target/release/mcl_test_dev -m test
- name: Check formatting with clippy
run: cargo clippy -- -W clippy::pedantic -A clippy::struct-excessive-bools -A clippy::too_many_lines -A clippy::similar_names

50
.gitignore vendored
View File

@ -1,36 +1,18 @@
# Prerequisites
*.d
/target
/*
# Compiled Object files
*.slo
*.lo
*.o
*.obj
# files
!/.gitignore
!/cargo.lock
!/cargo.toml
!/README.md
# Precompiled Headers
*.gch
*.pch
# Compiled Dynamic libraries
*.so
*.dylib
*.dll
# Fortran module files
*.mod
*.smod
# Compiled Static libraries
*.lai
*.la
*.a
*.lib
# Executables
*.exe
*.out
*.app
.cache/clangd/index
build
temp.c
compile_commands.json
# folders
!/.github
!/editor
!/examples
!/include
!/playground
!/src
!/tests
!/tools

336
Cargo.lock generated Normal file
View File

@ -0,0 +1,336 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "anyhow"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "080e9890a082662b09c1ad45f567faeeb47f22b5fb23895fbe1e651e718e25ca"
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "cc"
version = "1.0.79"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
[[package]]
name = "clap"
version = "4.1.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3d7ae14b20b94cb02149ed21a86c423859cbe18dc7ed69845cace50e52b40a5"
dependencies = [
"bitflags",
"clap_derive",
"clap_lex",
"is-terminal",
"once_cell",
"strsim",
"termcolor",
]
[[package]]
name = "clap_derive"
version = "4.1.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "44bec8e5c9d09e439c4335b1af0abaab56dcf3b94999a936e1bb47b9134288f0"
dependencies = [
"heck",
"proc-macro-error",
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "clap_lex"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "350b9cf31731f9957399229e9b2adc51eeabdfbe9d71d9a0552275fd12710d09"
dependencies = [
"os_str_bytes",
]
[[package]]
name = "errno"
version = "0.2.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f639046355ee4f37944e44f60642c6f3a7efa3cf6b78c78a0d989a8ce6c396a1"
dependencies = [
"errno-dragonfly",
"libc",
"winapi",
]
[[package]]
name = "errno-dragonfly"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf"
dependencies = [
"cc",
"libc",
]
[[package]]
name = "heck"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
[[package]]
name = "hermit-abi"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fed44880c466736ef9a5c5b5facefb5ed0785676d0c02d612db14e54f0d84286"
[[package]]
name = "io-lifetimes"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfa919a82ea574332e2de6e74b4c36e74d41982b335080fa59d4ef31be20fdf3"
dependencies = [
"libc",
"windows-sys",
]
[[package]]
name = "is-terminal"
version = "0.4.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "21b6b32576413a8e69b90e952e4a026476040d81017b80445deda5f2d3921857"
dependencies = [
"hermit-abi",
"io-lifetimes",
"rustix",
"windows-sys",
]
[[package]]
name = "libc"
version = "0.2.140"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "99227334921fae1a979cf0bfdfcc6b3e5ce376ef57e16fb6fb3ea2ed6095f80c"
[[package]]
name = "linux-raw-sys"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f051f77a7c8e6957c0696eac88f26b0117e54f52d3fc682ab19397a8812846a4"
[[package]]
name = "mclangc"
version = "0.1.0"
dependencies = [
"anyhow",
"clap",
]
[[package]]
name = "once_cell"
version = "1.17.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b7e5500299e16ebb147ae15a00a942af264cf3688f47923b8fc2cd5858f23ad3"
[[package]]
name = "os_str_bytes"
version = "6.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee"
[[package]]
name = "proc-macro-error"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c"
dependencies = [
"proc-macro-error-attr",
"proc-macro2",
"quote",
"syn",
"version_check",
]
[[package]]
name = "proc-macro-error-attr"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869"
dependencies = [
"proc-macro2",
"quote",
"version_check",
]
[[package]]
name = "proc-macro2"
version = "1.0.51"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5d727cae5b39d21da60fa540906919ad737832fe0b1c165da3a34d6548c849d6"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rustix"
version = "0.36.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fd5c6ff11fecd55b40746d1995a02f2eb375bf8c00d192d521ee09f42bef37bc"
dependencies = [
"bitflags",
"errno",
"io-lifetimes",
"libc",
"linux-raw-sys",
"windows-sys",
]
[[package]]
name = "strsim"
version = "0.10.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
[[package]]
name = "syn"
version = "1.0.109"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "termcolor"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6"
dependencies = [
"winapi-util",
]
[[package]]
name = "unicode-ident"
version = "1.0.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e5464a87b239f13a63a501f2701565754bae92d243d4bb7eb12f6d57d2269bf4"
[[package]]
name = "version_check"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
dependencies = [
"winapi",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "windows-sys"
version = "0.45.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
dependencies = [
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e2522491fbfcd58cc84d47aeb2958948c4b8982e9a2d8a2a35bbaed431390e7"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8c9864e83243fdec7fc9c5444389dcbbfd258f745e7853198f365e3c4968a608"
[[package]]
name = "windows_aarch64_msvc"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4c8b1b673ffc16c47a9ff48570a9d85e25d265735c503681332589af6253c6c7"
[[package]]
name = "windows_i686_gnu"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "de3887528ad530ba7bdbb1faa8275ec7a1155a45ffa57c37993960277145d640"
[[package]]
name = "windows_i686_msvc"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bf4d1122317eddd6ff351aa852118a2418ad4214e6613a50e0191f7004372605"
[[package]]
name = "windows_x86_64_gnu"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1040f221285e17ebccbc2591ffdc2d44ee1f9186324dd3e84e99ac68d699c45"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "628bfdf232daa22b0d64fdb62b09fcc36bb01f05a3939e20ab73aaf9470d0463"
[[package]]
name = "windows_x86_64_msvc"
version = "0.42.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "447660ad36a13288b1db4d4248e857b510e8c3a225c822ba4fb748c0aafecffd"

13
Cargo.toml Normal file
View File

@ -0,0 +1,13 @@
[package]
name = "mclangc"
description="The McLang Programming language compiler"
version = "0.1.0"
edition = "2021"
authors=[
"MCorange <mcorangecodes@gmail.com> (https://mcorangehq.xyz/)"
]
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
anyhow = "1.0.79"
clap = { version = "4.1.8", features = ["derive"] }

674
LICENSE
View File

@ -1,674 +0,0 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<https://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<https://www.gnu.org/licenses/why-not-lgpl.html>.

40
Makefile
View File

@ -1,40 +0,0 @@
BIN=mclangc
CC_FLAGS = -Isrc/include -std=c23
CXX_FLAGS = -Isrc/include -Ilib/ -std=c++23 -fmodules-ts
LD_FLAGS = -lm
CC=gcc
CXX=g++
LD=gcc
AR=ar
LIBS=
include lib/make.mk
cxx_sources=$(wildcard src/*.cpp)
c_sources=$(wildcard src/*.c)
objects=$(patsubst src/%.cpp,build/obj/%.cpp.o,$(cxx_sources)) $(patsubst src/%.c,build/obj/%.c.o,$(c_sources)) $(LIBS)
all: build/$(BIN) compile_commands.json
@rm -r build/obj
keep: build/$(BIN)
clean:
rm -r build/obj/
build/$(BIN): $(objects)
$(LD) -o $@ $^ $(LD_FLAGS)
build/obj/%.cpp.o: */%.cpp
@mkdir -p $(dir $@)
$(CXX) -c -o $@ $< $(CXX_FLAGS)
build/obj/%.c.o: */%.c
@mkdir -p $(dir $@)
$(CC) -c -o $@ $< $(CC_FLAGS)
compile_commands.json:
compiledb -n make

32
README.md
View File

@ -1,3 +1,31 @@
# C/C++ template
# mclang rev2
made specifically for xor64 org
This is the second revision of [MCLang](https://github.com/mc-lang/mclang) now written in rust!
## Goals
✅ - relatevely usable by normal programmers
✅ - speed comparable to unoptimised C (sometimes)
✅ - static typing
❌ - self hosted (maybe better if not? Since rust is fast asf)
❌ - multiplatform (~~windows~~, linux and mac)
✅ - interop with other languages
❌ - package manager
❌ - installer
## Documentation
The docs are currently are just made in MarkDown.
You can find the docs [here](/docs/index.md)
## Cheatsheet
Usefull things that i search for a lot in the sourcecode so i added them here
add them in reverse order in mclang
Syscall arg order: \[rax ,rdi ,rsi ,rdx ,r10 ,r8 ,r9\]
## Credits
[MCotange](https://github.com/MCorange99) - The one and only me, the creator and current maintainer or mclang rev1 and rev2

2
editor/vscode/.gitignore vendored Normal file
View File

@ -0,0 +1,2 @@
**/*.log
**/node_modules/

17
editor/vscode/.vscode/launch.json vendored Normal file
View File

@ -0,0 +1,17 @@
// A launch configuration that launches the extension inside a new window
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
{
"version": "0.2.0",
"configurations": [
{
"name": "Extension",
"type": "extensionHost",
"request": "launch",
"args": [
"--extensionDevelopmentPath=${workspaceFolder}"
]
}
]
}

4
editor/vscode/.vscodeignore Normal file
View File

@ -0,0 +1,4 @@
.vscode/**
.vscode-test/**
.gitignore
vsc-extension-quickstart.md

9
editor/vscode/CHANGELOG.md Normal file
View File

@ -0,0 +1,9 @@
# Change Log
All notable changes to the "mclang" extension will be documented in this file.
Check [Keep a Changelog](http://keepachangelog.com/) for recommendations on how to structure this file.
## [Unreleased]
- Initial release

0
editor/vscode/LICENSE Normal file
View File

17
editor/vscode/README.md Normal file
View File

@ -0,0 +1,17 @@
# mclang README
Code highlghting for mclang 1 and 2
## Known Issues
None
## Release Notes
Users appreciate release notes as you update your extension.
### 1.0.0
Initial release of mclang
**Enjoy!**

30
editor/vscode/language-configuration.json Normal file
View File

@ -0,0 +1,30 @@
{
"comments": {
// symbol used for single line comment. Remove this entry if your language does not support line comments
"lineComment": "//",
// symbols used for start and end a block comment. Remove this entry if your language does not support block comments
"blockComment": [ "/*", "*/" ]
},
// symbols used as brackets
"brackets": [
["{", "}"],
["[", "]"],
["(", ")"]
],
// symbols that are auto closed when typing
"autoClosingPairs": [
["{", "}"],
["[", "]"],
["(", ")"],
["\"", "\""],
["'", "'"]
],
// symbols that can be used to surround a selection
"surroundingPairs": [
["{", "}"],
["[", "]"],
["(", ")"],
["\"", "\""],
["'", "'"]
]
}

BIN
editor/vscode/mclang-0.0.3.vsix Normal file
View File

Binary file not shown.

42
editor/vscode/package.json Normal file
View File

@ -0,0 +1,42 @@
{
"name": "mclang",
"displayName": "mclang",
"description": "Code highlighting for mclang",
"version": "0.0.3",
"repository": {
"type": "git",
"url": "git@github.com:mc-lang/mclang2.git"
},
"engines": {
"vscode": "^1.54.0"
},
"categories": [
"Programming Languages"
],
"contributes": {
"languages": [
{
"id": "mclang",
"aliases": [
"MCLang",
"mclang"
],
"extensions": [
".mcl"
],
"configuration": "./language-configuration.json"
}
],
"grammars": [
{
"language": "mclang",
"scopeName": "source.mcl",
"path": "./syntaxes/mclang.tmLanguage.json"
}
]
},
"dependencies": {
"generator-code": "^1.7.4",
"@vscode/vsce": "^2.15.0"
}
}

147
editor/vscode/syntaxes/mclang.tmLanguage.json Normal file
View File

@ -0,0 +1,147 @@
{
"name": "MCLang",
"fileTypes": [
"mcl"
],
"scopeName": "source.mcl",
"patterns": [
{
"include": "#errors"
},
{
"include": "#keywords"
},
{
"include": "#definitions"
},
{
"include": "#placeholders"
},
{
"include": "#strings"
},
{
"include": "#comments"
},
{
"include": "#intrinsics"
},
{
"include": "#constants-and-special-vars"
}
],
"repository": {
"errors": {
"patterns": [
{
"name": "invalid.illegal",
"match": "(?<=^|\\s)(?:const|memory)\\s+(end)(?:$|\\s)"
},
{
"name": "invalid.illegal",
"match": "(?<=^|\\s)(?:fn)\\s+(done)(?:$|\\s)"
},
{
"name": "invalid.illegal",
"match": "(?<=^|\\s)(memory|const)\\s+\\S*(\\s+|$)end(?:\n|\\s)"
},
{
"name": "invalid.illegal",
"match": "(?<=^|\\s)(inline)\\s+(?!fn(\\s|$))"
}
]
},
"keywords": {
"patterns": [
{
"name": "keyword.declaration.mclang",
"match": "(?<=\\s|^)(macro|memory|fn|const|in|inline|include|assert|offset|addr-of|call-like|reset|let|peek|with|returns)(?:\\s|$)"
},
{
"name": "keyword.control.mclang",
"match": "(?<=\\s|^)(if|else|elif|end|done|then|while|do|if\\*)(?:\\s|$)"
}
]
},
"definitions": {
"patterns": [
{
"name": "support.class.mclang",
"match": "(?<=(macro|memory|fn|const)\\s+)(\\S*)"
},
{
"name": "support.class.mclang",
"match": "(?<=(let|peek)\\s+)\\S+.*(?=\\s+(in))"
}
]
},
"placeholders": {
"patterns": [
{
"name": "markup.italic.mclang",
"match": "(?<=(\\s|^))_[\\S]*_(?:(\\s|$))"
}
]
},
"strings": {
"patterns": [
{
"name": "string.quoted.double.mclang",
"begin": "\"",
"end": "\"",
"patterns": [
{
"name": "constant.character.escape.mclang",
"match": "\\\\."
}
]
},
{
"name": "string.quoted.single.mclang",
"begin": "'",
"end": "'",
"patterns": [
{
"name": "constant.character.escape.mclang",
"match": "\\\\."
}
]
}
]
},
"comments": {
"patterns": [
{
"name": "constant.other.character-class.regexp",
"match": "(?://\\s*)(TODO(O*)|FIXME).*"
},
{
"name": "comment.line.double-slash.mclang",
"match": "(//(?!\\s?(TODO(O*)|FIXME)(\\s|:|$)).*|//\\s*)"
}
]
},
"intrinsics": {
"patterns": [
{
"name": "variable.name.source.mclang",
"match": "(?<=^|\\s)(\\+|-|\\*|int|ptr|bool|addr|any|void|max|divmod|_dbg_print|=|>|<|>=|<=|!=|>>|<<|\\||&|not|dup|swap|drop|over|rot|argc|argv|here|syscall0|syscall1|syscall2|syscall3|syscall4|syscall5|syscall6|\\?\\?\\?)(?=>$|\\s)"
}
]
},
"constants-and-special-vars": {
"patterns": [
{
"name": "constant.numeric.mclang",
"match": "\\b((0(x|X)[0-9a-fA-F]*)|(([0-9]+\\.?[0-9]*)|(\\.[0-9]+))((e|E)(\\+|-)?[0-9]+)?)\\b(?!\\$)"
},
{
"name": "entity.name.function.mclang",
"match": "(?<=^|\\s)(NULL|true|false|cast(ptr)|cast(int)|cast(bool)|sizeof\\(u64\\)|sizeof\\(u32\\)|sizeof\\(ptr\\)|sizeof\\(bool\\)|sizeof\\(int\\)|sizeof\\(addr\\)|STDIN|STDOUT|STDERR|@ptr|@@ptr|@bool|@int|@addr|!bool|!ptr|!int|!addr|AT_FDCWD|O_RDONLY|O_WRONLY|O_RDWR|O_CREAT|O_TRUNC|O_NONBLOCK|F_SETFL|F_GETFL|EAGAIN|CLOCK_MONOTONIC|TIMER_ABSTIME|MAP_PRIVATE|MAP_ANONYMOUS|PROT_READ|PROT_WRITE|SIGQUIT|timespec\\.tv_sec|timespec\\.tv_nsec|sizeof\\(timespec\\)|ptr\\+|ptr-|ptr!=|ptr=|ptr<|\\+ptr|ptr-diff|sizeof\\(stat\\)|stat\\.st_dev|stat\\.st_ino|stat\\.st_mode|stat\\.st_nlink|stat\\.st_uid|stat\\.st_gid|stat\\.st_rdev|stat\\.st_size|@stat\\.st_size|stat\\.st_blksize|stat\\.st_blocks|stat\\.st_atim|stat\\.st_mtim|stat\\.st_ctim|sizeof\\(stat\\.st_dev\\)|sizeof\\(stat\\.st_ino\\)|sizeof\\(stat\\.st_mode\\)|sizeof\\(stat\\.st_nlink\\)|sizeof\\(stat\\.st_uid\\)|sizeof\\(stat\\.st_gid\\)|sizeof\\(stat\\.st_rdev\\)|sizeof\\(stat\\.st_size\\)|sizeof\\(stat\\.st_blksize\\)|sizeof\\(stat\\.st_blocks\\)|sizeof\\(stat\\.st_atim\\)|sizeof\\(stat\\.st_mtim\\)|sizeof\\(stat\\.st_ctim\\)|write|read|openat|fstat|stat|close|exit|mmap|clock_nanosleep|clock_gettime|fork|getpid|execve|wait4|rename|fcntl|kill|dup2|/|%|mod|div|imod|idiv|emod|nth_argv|lnot|land|lor|inc64-by|inc64|dec64|inc32|dec32|inc8|dec8|swap64|cstrlen|cstreq|cstr-to-str|fputs|puts|eputs|WIFSTOPPED|WIFCONTINUED|WIFSIGNALED|WTERMSIG|WIFEXITED|WEXITSTATUS|offsetof\\(Str\\.count\\)|offsetof\\(Str\\.data\\)|sizeof\\(Str\\)|Str\\.count|Str\\.data|@Str\\.count|@Str\\.data|!Str\\.count|!Str\\.data|@Str|!Str|str-chop-one-left|str-chop-one-right|\\?space|str-trim-left|str-chop-by-predicate|str-chop-by-delim|str-starts-with|\\?str-empty|streq|\\?digit|isdigit|\\?alpha|isalpha|\\?alnum|isalnum|try-parse-int|PUTU_BUFFER_CAP|fputu|fput0u|putu|put0u|eputu|memcpy|memset|srand|RAND_A|RAND_C|rand|getenv|TMP_CAP|tmp-clean|tmp-end|tmp-rewind|tmp-alloc|tmp-str-to-cstr|tmp-append|tmp-append-ptr|execvp|append-item|tmp-utos|map-file|\\?file-exist|\\?shell-safe-char|\\?shell-safe-str|shell-escape|timeit/from-here|1e9|timeit/to-here|str-rfind|dirname|putch|remove-ext|cmd-echoed)(?:\\s|$)"
}
]
}
}
}

29
editor/vscode/vsc-extension-quickstart.md Normal file
View File

@ -0,0 +1,29 @@
# Welcome to your VS Code Extension
## What's in the folder
* This folder contains all of the files necessary for your extension.
* `package.json` - this is the manifest file in which you declare your language support and define the location of the grammar file that has been copied into your extension.
* `syntaxes/mclang.tmLanguage.json` - this is the Text mate grammar file that is used for tokenization.
* `language-configuration.json` - this is the language configuration, defining the tokens that are used for comments and brackets.
## Get up and running straight away
* Make sure the language configuration settings in `language-configuration.json` are accurate.
* Press `F5` to open a new window with your extension loaded.
* Create a new file with a file name suffix matching your language.
* Verify that syntax highlighting works and that the language configuration settings are working.
## Make changes
* You can relaunch the extension from the debug toolbar after making changes to the files listed above.
* You can also reload (`Ctrl+R` or `Cmd+R` on Mac) the VS Code window with your extension to load your changes.
## Add more language features
* To add features such as IntelliSense, hovers and validators check out the VS Code extenders documentation at https://code.visualstudio.com/docs
## Install your extension
* To start using your extension with Visual Studio Code copy it into the `<user home>/.vscode/extensions` folder and restart Code.
* To share your extension with the world, read on https://code.visualstudio.com/docs about publishing an extension.

1784
editor/vscode/yarn.lock Normal file
View File

File diff suppressed because it is too large Load Diff

3
examples/.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
/*
!/.gitignore
!/*.mcl

4
examples/hello_world.mcl Normal file
View File

@ -0,0 +1,4 @@
include "std.mcl"
"Henlo World! :3\n" puts

39
examples/rule110.mcl Executable file
View File

@ -0,0 +1,39 @@
include "std.mcl"
macro BOARD_SIZE 100 end
mem BOARD_SIZE 2 - + 1 @8
0 while dup BOARD_SIZE 2 - < do
0 while dup BOARD_SIZE < do
dup mem + !8 if
dup mem + BOARD_SIZE + '*' @8
else
dup mem + BOARD_SIZE + ' ' @8
end
1 +
end
mem + BOARD_SIZE + '\n' @8
BOARD_SIZE 1 + mem BOARD_SIZE + puts
// pattern
mem !8 1 shl
mem 1 + !8
bor
1 while dup BOARD_SIZE 2 - < do
swap 1 shl 7 band
over mem + 1 + !8 bor
2dup 110 swap shr 1 band
swap mem + swap @8
swap
1 +
end
drop drop
1 +
end
drop

5
examples/seq_100.mcl Normal file
View File

@ -0,0 +1,5 @@
0 while dup 100 < do
dup print
1 +
end

1
include/compat.mcl Normal file
View File

@ -0,0 +1 @@
// todo: add some sort of macrow

29
include/fs.mcl Normal file
View File

@ -0,0 +1,29 @@
const FS_O_RDONLY 0 end
const FS_O_WRONLY 1 end
const FS_O_RDWR 2 end
const FS_O_APPEND 1024 end // append to existing file
const FS_O_TRUNC 512 end // if file exists, ovewrite it (careful!)
const FS_O_CREAT 64 end // create file if it doesn’t exist
const FS_O_ASYNC 8192 end // use signal-driven IO
const FS_O_CLOEXEC 524288 end // use close-on-exec (avoid race conditions and lock contentions)
const FS_O_DIRECT 16384 end // bypass cache (slower)
const FS_O_DIRECTORY 65536 end // fail if pathname isn’t a directory
const FS_O_DSYNC 4096 end // ensure output is sent to hardware and metadata written before return
const FS_O_EXCL 128 end // ensure creation of file
const FS_O_LARGEFILE 0 end // allows use of file sizes represented by off64_t
const FS_O_NOATIME 262144 end // do not increment access time upon open
const FS_O_NOCTTY 256 end // if pathname is a terminal device, don’t become controlling terminal
const FS_O_NOFOLLOW 131072 end // fail if pathname is symbolic link
const FS_O_NONBLOCK 2048 end // if possible, open file with non-blocking IO
const FS_O_NDELAY 2048 end // same as O_NONBLOCK
const FS_O_PATH 2097152 end // open descriptor for obtaining permissions and status of a file but does not allow read/write operations
const FS_O_SYNC 1052672 end // wait for IO to complete before returning
const FS_O_TMPFILE 4259840 end // create an unnamed, unreachable (via any other open call) temporary file
fn fs_read_to_string with int ptr returns int ptr then
done

20
include/int.mcl Normal file
View File

@ -0,0 +1,20 @@
const NULL 0 end
const false 0 end
const true 1 end
inline fn div with int int returns int then divmod drop done
inline fn mod with int int returns int then divmod swap drop done
inline fn dup2 with any any returns any any any any then over over done
inline fn drop2 with any any returns void then drop drop done
const sizeof(u64) 8 end
const sizeof(u32) 4 end
const sizeof(u16) 2 end
const sizeof(u8) 1 end
const u64 8 end
const u32 4 end
const u16 2 end
const u8 1 end

61
include/io.mcl Normal file
View File

@ -0,0 +1,61 @@
// Write to a file descriptor using the SYS_write syscall
// args: [buff_size, buff_ptr, fd]
// @arg buff_size: Int - number of bytes to write
// @arg buff_ptr: Ptr - pointer to the buffer to write
// @arg fd: Int - file descriptor
// @ret Int
inline fn fwrite with int ptr int returns int then
SYS_write syscall3
done
// Write to a file descriptor using the SYS_write syscall
// args: [buff_size, buff_ptr, fd]
// @arg buff_size: Int - number of bytes to write
// @arg buff_ptr: Ptr - pointer to the buffer to write
// @arg fd: Int - file descriptor
// @ret Int
inline fn fread with int ptr int returns int then
SYS_read syscall3
done
// Write to a file descriptor using the SYS_write syscall
// args: [buff_ptr, flags, mode]
// @arg buff_ptr: Ptr - File to open
// @arg flags: Int - Flags
// @arg mode: Int - Mode
// @ret Int - Fd
inline fn fopen with int ptr int returns int then
SYS_open syscall3
done
// Print a string to STDOUT
// args: [str_size, str_ptr]
// @arg buff_size: Int - number of bytes to write
// @arg buff_ptr: Ptr - pointer to the buffer to write
// @ret NULL
inline fn puts with int ptr returns void then
STDOUT fwrite drop
done
// Print a string to STDERR
// args: [str_size, str_ptr]
// @arg buff_size: Int - number of bytes to write
// @arg buff_ptr: Ptr - pointer to the buffer to write
// @ret NULL
inline fn eputs with int ptr returns void then
STDOUT fwrite drop
done
// TODO: make putc, eputc, putd, and eputd after we make local mem
// Exit the program with exit_code
// args: [exit_code]
// @arg exit_code: Int
// @ret NULL/NEVER
inline fn exit with int returns void then
SYS_exit syscall1 drop
done

322
include/linux.mcl Normal file
View File

@ -0,0 +1,322 @@
// file descriptors
const STDIN 0 end
const STDOUT 1 end
const STDERR 2 end
// syscalls
const SYS_read 0 end
const SYS_write 1 end
const SYS_open 2 end
const SYS_close 3 end
const SYS_stat 4 end
const SYS_fstat 5 end
const SYS_lstat 6 end
const SYS_poll 7 end
const SYS_lseek 8 end
const SYS_mmap 9 end
const SYS_mprotect 10 end
const SYS_munmap 11 end
const SYS_brk 12 end
const SYS_rt_sigaction 13 end
const SYS_rt_sigprocmask 14 end
const SYS_rt_sigreturn 15 end
const SYS_ioctl 16 end
const SYS_pread64 17 end
const SYS_pwrite64 18 end
const SYS_readv 19 end
const SYS_writev 20 end
const SYS_access 21 end
const SYS_pipe 22 end
const SYS_select 23 end
const SYS_sched_yield 24 end
const SYS_mremap 25 end
const SYS_msync 26 end
const SYS_mincore 27 end
const SYS_madvise 28 end
const SYS_shmget 29 end
const SYS_shmat 30 end
const SYS_shmctl 31 end
const SYS_dup 32 end
const SYS_dup2 33 end
const SYS_pause 34 end
const SYS_nanosleep 35 end
const SYS_getitimer 36 end
const SYS_alarm 37 end
const SYS_setitimer 38 end
const SYS_getpid 39 end
const SYS_sendfile 40 end
const SYS_socket 41 end
const SYS_connect 42 end
const SYS_accept 43 end
const SYS_sendto 44 end
const SYS_recvfrom 45 end
const SYS_sendmsg 46 end
const SYS_recvmsg 47 end
const SYS_shutdown 48 end
const SYS_bind 49 end
const SYS_listen 50 end
const SYS_getsockname 51 end
const SYS_getpeername 52 end
const SYS_socketpair 53 end
const SYS_setsockopt 54 end
const SYS_getsockopt 55 end
const SYS_clone 56 end
const SYS_fork 57 end
const SYS_vfork 58 end
const SYS_execve 59 end
const SYS_exit 60 end
const SYS_wait4 61 end
const SYS_kill 62 end
const SYS_uname 63 end
const SYS_semget 64 end
const SYS_semop 65 end
const SYS_semctl 66 end
const SYS_shmdt 67 end
const SYS_msgget 68 end
const SYS_msgsnd 69 end
const SYS_msgrcv 70 end
const SYS_msgctl 71 end
const SYS_fcntl 72 end
const SYS_flock 73 end
const SYS_fsync 74 end
const SYS_fdatasync 75 end
const SYS_truncate 76 end
const SYS_ftruncate 77 end
const SYS_getdents 78 end
const SYS_getcwd 79 end
const SYS_chdir 80 end
const SYS_fchdir 81 end
const SYS_rename 82 end
const SYS_mkdir 83 end
const SYS_rmdir 84 end
const SYS_creat 85 end
const SYS_link 86 end
const SYS_unlink 87 end
const SYS_symlink 88 end
const SYS_readlink 89 end
const SYS_chmod 90 end
const SYS_fchmod 91 end
const SYS_chown 92 end
const SYS_fchown 93 end
const SYS_lchown 94 end
const SYS_umask 95 end
const SYS_gettimeofday 96 end
const SYS_getrlimit 97 end
const SYS_getrusage 98 end
const SYS_sysinfo 99 end
const SYS_times 100 end
const SYS_ptrace 101 end
const SYS_getuid 102 end
const SYS_syslog 103 end
const SYS_getgid 104 end
const SYS_setuid 105 end
const SYS_setgid 106 end
const SYS_geteuid 107 end
const SYS_getegid 108 end
const SYS_setpgid 109 end
const SYS_getppid 110 end
const SYS_getpgrp 111 end
const SYS_setsid 112 end
const SYS_setreuid 113 end
const SYS_setregid 114 end
const SYS_getgroups 115 end
const SYS_setgroups 116 end
const SYS_setresuid 117 end
const SYS_getresuid 118 end
const SYS_setresgid 119 end
const SYS_getresgid 120 end
const SYS_getpgid 121 end
const SYS_setfsuid 122 end
const SYS_setfsgid 123 end
const SYS_getsid 124 end
const SYS_capget 125 end
const SYS_capset 126 end
const SYS_rt_sigpending 127 end
const SYS_rt_sigtimedwait 128 end
const SYS_rt_sigqueueinfo 129 end
const SYS_rt_sigsuspend 130 end
const SYS_sigaltstack 131 end
const SYS_utime 132 end
const SYS_mknod 133 end
const SYS_uselib 134 end
const SYS_personality 135 end
const SYS_ustat 136 end
const SYS_statfs 137 end
const SYS_fstatfs 138 end
const SYS_sysfs 139 end
const SYS_getpriority 140 end
const SYS_setpriority 141 end
const SYS_sched_setparam 142 end
const SYS_sched_getparam 143 end
const SYS_sched_setscheduler 144 end
const SYS_sched_getscheduler 145 end
const SYS_sched_get_priority_max 146 end
const SYS_sched_get_priority_min 147 end
const SYS_sched_rr_get_interval 148 end
const SYS_mlock 149 end
const SYS_munlock 150 end
const SYS_mlockall 151 end
const SYS_munlockall 152 end
const SYS_vhangup 153 end
const SYS_modify_ldt 154 end
const SYS_pivot_root 155 end
const SYS__sysctl 156 end
const SYS_prctl 157 end
const SYS_arch_prctl 158 end
const SYS_adjtimex 159 end
const SYS_setrlimit 160 end
const SYS_chroot 161 end
const SYS_sync 162 end
const SYS_acct 163 end
const SYS_settimeofday 164 end
const SYS_mount 165 end
const SYS_umount2 166 end
const SYS_swapon 167 end
const SYS_swapoff 168 end
const SYS_reboot 169 end
const SYS_sethostname 170 end
const SYS_setdomainname 171 end
const SYS_iopl 172 end
const SYS_ioperm 173 end
const SYS_create_module 174 end
const SYS_init_module 175 end
const SYS_delete_module 176 end
const SYS_get_kernel_syms 177 end
const SYS_query_module 178 end
const SYS_quotactl 179 end
const SYS_nfsservctl 180 end
const SYS_getpmsg 181 end
const SYS_putpmsg 182 end
const SYS_afs_syscall 183 end
const SYS_tuxcall 184 end
const SYS_security 185 end
const SYS_gettid 186 end
const SYS_readahead 187 end
const SYS_setxattr 188 end
const SYS_lsetxattr 189 end
const SYS_fsetxattr 190 end
const SYS_getxattr 191 end
const SYS_lgetxattr 192 end
const SYS_fgetxattr 193 end
const SYS_listxattr 194 end
const SYS_llistxattr 195 end
const SYS_flistxattr 196 end
const SYS_removexattr 197 end
const SYS_lremovexattr 198 end
const SYS_fremovexattr 199 end
const SYS_tkill 200 end
const SYS_time 201 end
const SYS_futex 202 end
const SYS_sched_setaffinity 203 end
const SYS_sched_getaffinity 204 end
const SYS_set_thread_area 205 end
const SYS_io_setup 206 end
const SYS_io_destroy 207 end
const SYS_io_getevents 208 end
const SYS_io_submit 209 end
const SYS_io_cancel 210 end
const SYS_get_thread_area 211 end
const SYS_lookup_dcookie 212 end
const SYS_epoll_create 213 end
const SYS_epoll_ctl_old 214 end
const SYS_epoll_wait_old 215 end
const SYS_remap_file_pages 216 end
const SYS_getdents64 217 end
const SYS_set_tid_address 218 end
const SYS_restart_syscall 219 end
const SYS_semtimedop 220 end
const SYS_fadvise64 221 end
const SYS_timer_create 222 end
const SYS_timer_settime 223 end
const SYS_timer_gettime 224 end
const SYS_timer_getoverrun 225 end
const SYS_timer_delete 226 end
const SYS_clock_settime 227 end
const SYS_clock_gettime 228 end
const SYS_clock_getres 229 end
const SYS_clock_nanosleep 230 end
const SYS_exit_group 231 end
const SYS_epoll_wait 232 end
const SYS_epoll_ctl 233 end
const SYS_tgkill 234 end
const SYS_utimes 235 end
const SYS_vserver 236 end
const SYS_mbind 237 end
const SYS_set_mempolicy 238 end
const SYS_get_mempolicy 239 end
const SYS_mq_open 240 end
const SYS_mq_unlink 241 end
const SYS_mq_timedsend 242 end
const SYS_mq_timedreceive 243 end
const SYS_mq_notify 244 end
const SYS_mq_getsetattr 245 end
const SYS_kexec_load 246 end
const SYS_waitid 247 end
const SYS_add_key 248 end
const SYS_request_key 249 end
const SYS_keyctl 250 end
const SYS_ioprio_set 251 end
const SYS_ioprio_get 252 end
const SYS_inotify_init 253 end
const SYS_inotify_add_watch 254 end
const SYS_inotify_rm_watch 255 end
const SYS_migrate_pages 256 end
const SYS_openat 257 end
const SYS_mkdirat 258 end
const SYS_mknodat 259 end
const SYS_fchownat 260 end
const SYS_futimesat 261 end
const SYS_newfstatat 262 end
const SYS_unlinkat 263 end
const SYS_renameat 264 end
const SYS_linkat 265 end
const SYS_symlinkat 266 end
const SYS_readlinkat 267 end
const SYS_fchmodat 268 end
const SYS_faccessat 269 end
const SYS_pselect6 270 end
const SYS_ppoll 271 end
const SYS_unshare 272 end
const SYS_set_robust_list 273 end
const SYS_get_robust_list 274 end
const SYS_splice 275 end
const SYS_tee 276 end
const SYS_sync_file_range 277 end
const SYS_vmsplice 278 end
const SYS_move_pages 279 end
const SYS_utimensat 280 end
const SYS_epoll_pwait 281 end
const SYS_signalfd 282 end
const SYS_timerfd_create 283 end
const SYS_eventfd 284 end
const SYS_fallocate 285 end
const SYS_timerfd_settime 286 end
const SYS_timerfd_gettime 287 end
const SYS_accept4 288 end
const SYS_signalfd4 289 end
const SYS_eventfd2 290 end
const SYS_epoll_create1 291 end
const SYS_dup3 292 end
const SYS_pipe2 293 end
const SYS_inotify_init1 294 end
const SYS_preadv 295 end
const SYS_pwritev 296 end
const SYS_rt_tgsigqueueinfo 297 end
const SYS_perf_event_open 298 end
const SYS_recvmmsg 299 end
const SYS_fanotify_init 300 end
const SYS_fanotify_mark 301 end
const SYS_prlimit64 302 end
const SYS_name_to_handle_at 303 end
const SYS_open_by_handle_at 304 end
const SYS_clock_adjtime 305 end
const SYS_syncfs 306 end
const SYS_sendmmsg 307 end
const SYS_setns 308 end
const SYS_getcpu 309 end
const SYS_process_vm_readv 310 end
const SYS_process_vm_writev 311 end
const SYS_kcmp 312 end
const SYS_finit_module 313 end

1
include/mem.mcl Normal file
View File

@ -0,0 +1 @@

6
include/std.mcl Normal file
View File

@ -0,0 +1,6 @@
include "linux.mcl"
include "io.mcl"
include "util.mcl"
include "int.mcl"
include "fs.mcl"
include "compat.mcl"

5
include/string.mcl Normal file
View File

@ -0,0 +1,5 @@
fn cstr_len with ptr returns int then
dup while dup load8 '\0' != do 1 + end swap -
done

15
include/util.mcl Normal file
View File

@ -0,0 +1,15 @@
// Assert implementation
// args: [condition, str_len, str_ptr]
// @arg condition: Bool
// @arg str_len: Int
// @arg str_ptr: Ptr
// @ret NULL/NEVER
fn assert with bool int ptr returns void then
rot
if else
"Assert failed: \"" eputs eputs
"\". Exiting!\n" eputs
1 exit
end
done

23
lib/make.mk
View File

@ -1,23 +0,0 @@
#? Sample library build recipe:
#? Prefferably put this in the lib directory
#? The onlu thing needed for root makefile, you can build it another way if u want
# LIBS += bin/lib/libmc.a
#
# libmc_src = $(wildcard lib/libmc/src/*.c)
# libmc_obj = $(patsubst lib/libmc/src/%.c,bin/lib/libmc/%.c.o,$(libmc_src))
#
# bin/lib/libmc.a: $(libmc_obj)
# @mkdir -p $(dir $@)
# ar rcs $@ $^
#
# bin/lib/libmc/%.c.o: lib/libmc/src/%.c
# @mkdir -p $(dir $@)
# $(CC) -c -o $@ $<

4
playground/.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
/*
!/.gitignore
!/*.mcl
!/mclangc

13
playground/mclangc Executable file
View File

@ -0,0 +1,13 @@
#!/usr/bin/bash
#? This is just a passthrough for the compiled mclangc binary for ease of use
#? It also compiles mclangc every time its ran
pushd ../ > /dev/null
cargo build --release -q
popd > /dev/null
../target/release/mclangc -I../include ${@:1}

35
playground/test.mcl Normal file
View File

@ -0,0 +1,35 @@
include "std.mcl"
struct StatDef do
val -> u32
val2 -> i8
end
alloc Stat StatDef end
fn main with int ptr returns void then
// p l
"Hello!\n" puts
Stat.val 69 write32
Stat.val read32 _dbg_print
Stat.__size read32 _dbg_print
// memory fd 4 end
// NULL
// FS_O_RDWR
// c"/home/mcorange/@Projects/rust/programming_languages/mclang/mclangc/playground/test.mcl"
// fopen
// dup _dbg_print
// fd swap write32
done

171
src/bin/mcl_test_dev.rs Normal file
View File

@ -0,0 +1,171 @@
use std::path::{PathBuf, Path};
use std::process::Stdio;
use std::{process, fs};
use clap::Parser;
use anyhow::{Result, bail};
pub mod color {
#![allow(dead_code)]
pub const NONE: &str = "\x1b[0m";
pub const RESET: &str = "\x1b[0m";
pub const BRIGHT: &str = "\x1b[1m";
pub const DIM: &str = "\x1b[2m";
pub const UNDERSCORE: &str = "\x1b[4m";
pub const BLINK: &str = "\x1b[5m";
pub const REVERSE: &str = "\x1b[7m";
pub const HIDDEN: &str = "\x1b[8m";
pub const FG_BLACK: &str = "\x1b[30m";
pub const FG_RED: &str = "\x1b[31m";
pub const FG_GREEN: &str = "\x1b[32m";
pub const FG_YELLOW: &str = "\x1b[33m";
pub const FG_BLUE: &str = "\x1b[34m";
pub const FG_MAGENTA: &str = "\x1b[35m";
pub const FG_CYAN: &str = "\x1b[36m";
pub const FG_WHITE: &str = "\x1b[37m";
pub const BG_BLACK: &str = "\x1b[40m";
pub const BG_RED: &str = "\x1b[41m";
pub const BG_GREEN: &str = "\x1b[42m";
pub const BG_YELLOW: &str = "\x1b[43m";
pub const BG_BLUE: &str = "\x1b[44m";
pub const BG_MAGENTA: &str = "\x1b[45m";
pub const BG_CYAN: &str = "\x1b[46m";
pub const BG_WHITE: &str = "\x1b[47m";
}
#[allow(dead_code)]
#[derive(Debug)]
struct TestOutput {
stdout: String,
stderr: String,
stdin: String,
status: i32
}
fn run_test<P: Into<PathBuf> + std::convert::AsRef<std::ffi::OsStr>>(f_in: PathBuf, f_out: &PathBuf, compiler: P, compile_mode: bool, stdin: String) -> Result<TestOutput> {
let mut command = process::Command::new(compiler);
command.stdout(Stdio::piped());
command.stderr(Stdio::piped());
if compile_mode {
command.arg("-cqr");
} else {
command.arg("-sq");
}
command.arg("-i");
command.arg(f_in);
command.arg("-o");
command.arg(f_out);
let child = command.spawn()?;
let out = child.wait_with_output()?;
let stdout = out.stdout.iter().map(|c| {
char::from_u32(u32::from(*c)).expect("Failed to parse stdout char").to_string()
}).collect::<String>();
let stderr = out.stderr.iter().map(|c| {
char::from_u32(u32::from(*c)).expect("Failed to parse stderr char").to_string()
}).collect::<String>();
Ok(TestOutput {
stdout,
stderr,
stdin,
status: out.status.code().unwrap()
})
}
fn run_tests(args: Args) -> Result<()>{
let files = fs::read_dir(args.input)?;
for file in files {
let file = file?;
let f_name = file.file_name().to_string_lossy().to_string();
let f_out = PathBuf::from(&args.output).join(f_name);
let intp = run_test(file.path(), &f_out, &args.compiler_path, false, String::new())?;
let comp = run_test(file.path(), &f_out, &args.compiler_path, true, String::new())?;
compare_results(&intp, &comp, &file.path())?;
}
Ok(())
}
fn compare_results(intp: &TestOutput, comp: &TestOutput, f_in: &Path) -> Result<()> {
if intp.stdout != comp.stdout {
println!("{b}[ {r}ERR{rs}{b} ]{rs} {f} compiled and interpreted stdout versions differ", r=color::FG_RED, rs=color::RESET, b=color::BRIGHT, f=f_in.display());
println!("compiled:\n{}", comp.stdout);
println!("interpreted:\n{}", intp.stdout);
bail!("Testing failed");
}
if intp.stderr != comp.stderr {
println!("{b}[ {r}ERR{rs}{b} ]{rs} {f} compiled and interpreted stderr versions differ", r=color::FG_RED, rs=color::RESET, b=color::BRIGHT, f=f_in.display());
println!("compiled:\n{}", comp.stderr);
println!("interpreted:\n{}", intp.stderr);
bail!("Testing failed");
}
if intp.status != comp.status {
println!("{b}[ {r}ERR{rs}{b} ]{rs} {f} compiled and interpreted status codes differ", r=color::FG_RED, rs=color::RESET, b=color::BRIGHT, f=f_in.display());
println!("compiled:\n{}", comp.status);
println!("interpreted:\n{}", intp.status);
bail!("Testing failed");
}
println!("{b}[ {g}OK{rs}{b} ]{rs} {f} ", g=color::FG_GREEN, rs=color::RESET, b=color::BRIGHT, f=f_in.display());
Ok(())
}
#[derive(Parser, Debug, Clone)]
#[command(author, version, about, long_about = None)]
struct Args {
/// Mode, allowed modes: test, record
#[arg(long, short)]
mode: String,
/// Use compile mode
#[arg(long, short)]
compile: bool,
/// Use interpret mode
#[arg(long, short='s')]
interpret: bool,
/// Output folder
#[arg(long, short, default_value_t=String::from("./target/mcl_test_dev"))]
output: String,
/// Input folder
#[arg(long, short, default_value_t=String::from("./tests"))]
input: String,
/// Compiler path
#[arg(long, short, default_value_t=String::from("./target/release/mclangc"))]
compiler_path: String
}
fn main() -> Result<()> {
let args = Args::parse();
fs::create_dir_all(&args.output)?;
match args.mode.as_str() {
"test" => run_tests(args),
"record" => todo!("Implement test result recording"),
s => {
eprintln!("Unknown mode '{s}'");
bail!("Bad subcommand");
}
}?;
Ok(())
}

72
src/cliargs.c
View File

@ -1,72 +0,0 @@
#include "cliargs.h"
#include "dyn_arr.h"
#include <bits/getopt_core.h>
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
void print_help(char*);
void print_version(char*);
DEFINE_DA_IMPL(string, char*);
cliargs_t* parse_cliargs(int argc, char** argv) {
int optidx = 0;
int opt;
char* progname = argv[0];
if (argc <= 1) {
print_help(progname);
}
cliargs_t* cliargs = malloc(sizeof(cliargs_t));
assert(cliargs && "Out of memory");
while ((opt = getopt_long(argc, argv, "hvo:d", cli_options, &optidx)) != -1) {
switch (opt) {
case 'h':
print_help(progname);
break;
case 'v':
print_version(progname);
break;
case 'o':
cliargs->output = optarg;
break;
case 'd':
cliargs->debug = true;
break;
default: /* '?' */
print_help(progname);
exit(EXIT_FAILURE);
}
}
for (int i = optind; i < argc; i++) {
mcl_da_string_push(&cliargs->input, argv[i]);
}
return cliargs;
}
void print_help(char* progname) {
printf(
"Usage: %s [-v|--version] [-h|--help] [-d|--debug] [-o|--output OUTPUT] [INPUT]\n"
" --version, -v - Prints the current version\n"
" --help, -h - Shows this text\n"
" --debug, -d - Prints extra information\n"
" --output, -o - Output file for compilation\n"
"\n"
"%s Copyright (C) 2024 MCorange<mcorange@mcorangehq.xyz>\n"
"This program comes with ABSOLUTELY NO WARRANTY.\n"
"This is free software, and you are welcome to redistribute it\n"
"under certain conditions\n"
, progname, progname);
exit(0);
}
void print_version(char* progname) {
printf("%s: The very epic compiler %s\n", progname, MCL_VERSION);
exit(0);
}

93
src/compile/commands.rs Normal file
View File

@ -0,0 +1,93 @@
use std::path::{PathBuf, Path};
use std::process::{Command, Stdio};
use anyhow::Result;
use crate::{info, error};
pub fn linux_x86_64_compile_and_link(of_a: &Path, of_o: &Path, of_c: &Path, quiet: bool) -> Result<()> {
let nasm_args = [
"-felf64",
of_a.to_str().unwrap(),
"-o",
of_o.to_str().unwrap()
];
let ld_args = [
of_o.to_str().unwrap(),
"-o",
of_c.to_str().unwrap()
];
let mut proc = if cfg!(target_os = "windows") {
return Ok(());
} else {
let ret = Command::new("nasm")
.args(nasm_args)
.stdout(Stdio::inherit())
.stderr(Stdio::inherit())
.spawn();
if ret.is_err() {
error!("Nasm not installed")
}
ret?
};
if !quiet {
info!("running 'nasm {}'", nasm_args.join(" "));
}
let exit = proc.wait()?;
if !quiet {
info!("nasm process exited with code {}", exit);
}
let mut proc2 = if cfg!(target_os = "windows") {
return Ok(());
} else {
Command::new("ld")
.args(ld_args)
.stdout(Stdio::inherit())
.stderr(Stdio::inherit())
.spawn()?
};
if !quiet {
info!("running 'ld {}'", ld_args.join(" "));
}
let exit2 = proc2.wait()?;
if !quiet {
info!("ld process exited with code {}", exit2);
}
Ok(())
}
pub fn linux_x86_64_run(bin: &Path, args: &[String], quiet: bool) -> Result<i32> {
let bin = PathBuf::from(
format!("./{}", bin.to_string_lossy())
);
let mut proc = if cfg!(target_os = "windows") {
return Ok(0);
} else {
Command::new(bin.clone())
.args(args)
.stdout(Stdio::inherit())
.stderr(Stdio::inherit())
.spawn()?
};
// println!("{}", quiet);
if !quiet {
info!("running {} {}", bin.to_string_lossy(), args.join(" "));
}
let exit = proc.wait()?;
if !quiet {
info!("{} process exited with code {}", bin.to_string_lossy(), exit);
}
Ok(exit.code().unwrap_or(0))
}

536
src/compile/linux_x86_64.rs Normal file
View File

@ -0,0 +1,536 @@
use std::{fs, path::PathBuf, io::{Write, BufWriter}, collections::HashMap};
use crate::{definitions::*, Args, warn, lerror};
use crate::compile::commands::linux_x86_64_compile_and_link;
use crate::definitions::InstructionType;
use super::{commands::linux_x86_64_run, Constant, Memory, Function};
use anyhow::{Result, bail};
pub fn compile(program: &Program, args: &Args) -> Result<i32>{
let debug = args.get_opt_level()? < 1;
let mut of_c = PathBuf::from(&args.out_file);
let (mut of_o, mut of_a) = if args.out_file == *crate::DEFAULT_OUT_FILE {
let of_o = PathBuf::from("/tmp/mclang_comp.o");
let of_a = PathBuf::from("/tmp/mclang_comp.nasm");
(of_o, of_a)
} else {
let of_o = PathBuf::from(&args.out_file);
let of_a = PathBuf::from(&args.out_file);
(of_o, of_a)
};
of_c.set_extension("");
of_o.set_extension("o");
of_a.set_extension("nasm");
let mut should_push_ret = false;
let file = fs::File::create(&of_a)?;
let mut writer = BufWriter::new(&file);
let mut memories: Vec<Memory> = Vec::new();
let mut constants: HashMap<String, Constant> = HashMap::new();
let mut functions: Vec<Function> = Vec::new();
let mut alloced_structs: Vec<(String, String)> = Vec::new();
// println!("{}", tokens.len());
let mut strings: Vec<String> = Vec::new();
writeln!(writer, "BITS 64")?;
writeln!(writer, "segment .text")?;
writeln!(writer, "{}", super::MACRO_DEFINITIONS)?;
writeln!(writer, "{}", super::DBG_PRINT)?;
if !crate::config::ENABLE_EXPORTED_FUNCTIONS && !args.lib_mode {
writeln!(writer, "global _start")?;
writeln!(writer, "_start:")?;
writeln!(writer, " lea rbp, [rel ret_stack]")?;
writeln!(writer, " call main")?;
writeln!(writer, " jmp end")?;
}
let mut ti = 0;
while ti < program.ops.len() {
let token = &program.ops[ti];
if debug {
writeln!(writer, "addr_{ti}:")?;
if token.typ == OpType::Instruction(InstructionType::PushInt) {
writeln!(writer, " ;; -- {:?} {}", token.typ, token.value)?;
} else if token.typ == OpType::Instruction(InstructionType::PushStr) {
writeln!(writer, " ;; -- {:?} {}", token.typ, token.text.escape_debug())?;
} else {
writeln!(writer, " ;; -- {:?}", token.typ)?;
}
} else {
if ti > 0 {
if program.ops[ti-1].typ == OpType::Keyword(KeywordType::Else) ||
program.ops[ti-1].typ == OpType::Keyword(KeywordType::End){
writeln!(writer, "addr_{ti}:")?;
}
}
if ti + 1 < program.ops.len() && program.ops[ti+1].typ == OpType::Keyword(KeywordType::End) {
writeln!(writer, "addr_{ti}:")?;
}
if let OpType::Keyword(keyword) = &token.typ {
match keyword {
&KeywordType::End |
&KeywordType::While => {
writeln!(writer, "addr_{ti}:")?;
}
_ => ()
}
}
}
match token.typ.clone() {
// stack
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => {
writeln!(writer, " OP_PushInt {}", token.value)?;
ti += 1;
},
InstructionType::PushStr => {
writeln!(writer, " OP_PushStr {}, str_{}", token.text.len(), strings.len())?;
strings.push(token.text.clone());
ti += 1;
}
InstructionType::PushCStr => {
writeln!(writer, " OP_PushCStr str_{}", strings.len())?;
strings.push(token.text.clone());
ti += 1;
}
InstructionType::Drop => {
writeln!(writer, " OP_Drop")?;
ti += 1;
},
InstructionType::Print => {
writeln!(writer, " OP_Print")?;
ti += 1;
},
InstructionType::Dup => {
writeln!(writer, " OP_Dup")?;
ti += 1;
},
InstructionType::Rot => {
writeln!(writer, " OP_Rot")?;
ti += 1;
},
InstructionType::Swap => {
writeln!(writer, " OP_Swap")?;
ti += 1;
},
InstructionType::Over => {
writeln!(writer, " OP_Over")?;
ti += 1;
},
InstructionType::Read8 => {
writeln!(writer, " OP_Load8")?;
ti += 1;
}
InstructionType::Write8 => {
writeln!(writer, " OP_Store8")?;
ti += 1;
}
InstructionType::Read32 => {
writeln!(writer, " OP_Load32")?;
ti += 1;
}
InstructionType::Write32 => {
writeln!(writer, " OP_Store32")?;
ti += 1;
}
InstructionType::Read64 => {
writeln!(writer, " OP_Load64")?;
ti += 1;
}
InstructionType::Write64 => {
writeln!(writer, " OP_Store64")?;
ti += 1;
}
// math
InstructionType::Plus => {
writeln!(writer, " OP_Plus")?;
ti += 1;
},
InstructionType::Minus => {
writeln!(writer, " OP_Minus")?;
ti += 1;
},
InstructionType::Equals => {
writeln!(writer, " OP_Equals")?;
ti += 1;
},
InstructionType::Lt => {
writeln!(writer, " OP_Lt")?;
ti += 1;
},
InstructionType::Gt => {
writeln!(writer, " OP_Gt")?;
ti += 1;
},
InstructionType::NotEquals => {
writeln!(writer, " OP_NotEquals")?;
ti += 1;
},
InstructionType::Le => {
writeln!(writer, " OP_Le")?;
ti += 1;
},
InstructionType::Ge => {
writeln!(writer, " OP_Ge")?;
ti += 1;
},
InstructionType::Band => {
writeln!(writer, " OP_Band")?;
ti += 1;
},
InstructionType::Bor => {
writeln!(writer, " OP_Bor")?;
ti += 1;
},
InstructionType::Shr => {
writeln!(writer, " OP_Shr")?;
ti += 1;
},
InstructionType::Shl => {
writeln!(writer, " OP_Shl")?;
ti += 1;
},
InstructionType::DivMod => {
writeln!(writer, " OP_DivMod")?;
ti += 1;
},
InstructionType::Mul => {
writeln!(writer, " OP_Mul")?;
ti += 1;
},
InstructionType::Syscall0 => {
writeln!(writer, " OP_Syscall0")?;
ti += 1;
},
InstructionType::Syscall1 => {
writeln!(writer, " OP_Syscall1")?;
ti += 1;
},
InstructionType::Syscall2 => {
writeln!(writer, " OP_Syscall2")?;
ti += 1;
},
InstructionType::Syscall3 => {
writeln!(writer, " OP_Syscall3")?;
ti += 1;
},
InstructionType::Syscall4 => {
writeln!(writer, " OP_Syscall4")?;
ti += 1;
},
InstructionType::Syscall5 => {
writeln!(writer, " OP_Syscall5")?;
ti += 1;
},
InstructionType::Syscall6 => {
writeln!(writer, " OP_Syscall6")?;
ti += 1;
},
InstructionType::MemUse => {
writeln!(writer, " OP_MemUse {}", token.addr.unwrap())?;
ti += 1;
},
InstructionType::None => {
println!("{token:?}");
unreachable!()
},
InstructionType::FnCall => {
writeln!(writer, " OP_FnCall {}", token.text)?;
ti += 1;
},
InstructionType::Return => {
// Experimental feature exported functions
if crate::config::ENABLE_EXPORTED_FUNCTIONS && should_push_ret {
writeln!(writer, " pop rdx")?;
should_push_ret = false;
}
writeln!(writer, " sub rbp, 8")?;
writeln!(writer, " mov rbx, qword [rbp]")?;
writeln!(writer, " push rbx")?;
writeln!(writer, " ret")?;
ti += 1;
},
InstructionType::CastBool |
InstructionType::CastPtr |
InstructionType::CastInt |
InstructionType::CastVoid |
InstructionType::TypeBool |
InstructionType::TypePtr |
InstructionType::TypeInt |
InstructionType::TypeVoid |
InstructionType::TypeAny |
InstructionType::Returns |
InstructionType::With => {
ti += 1;
}
InstructionType::ConstUse => {
writeln!(writer, " OP_ConstUse {}", token.text)?;
let mut c = constants.get(&token.text).unwrap().clone();
c.used = true;
constants.remove(&token.text);
constants.insert(token.text.clone(), c);
ti += 1;
},
InstructionType::StructUse => {
writeln!(writer, " OP_StructUse {}", token.text)?;
ti += 1;
},
}
}
OpType::Keyword(keyword) => {
match keyword {
// block
KeywordType::If |
KeywordType::Do => {
writeln!(writer, " pop rax")?;
writeln!(writer, " test rax, rax")?;
writeln!(writer, " jz addr_{}", token.jmp)?;
ti += 1;
}
KeywordType::Else => {
writeln!(writer, " jmp addr_{}", token.jmp)?;
ti += 1;
},
KeywordType::While => {
ti += 1;
}
KeywordType::End => {
if ti + 1 != token.jmp {
writeln!(writer, " jmp addr_{}", token.jmp)?;
}
ti += 1;
},
KeywordType::Memory => {
memories.push(Memory { size: token.value, loc: token.loc.clone(), id: token.addr.unwrap() });
ti += 1;
}
KeywordType::ConstantDef => {
// TODO: after we add c style strings add supoort for them in constants
let a = args.get_opt_level()? < 1;
let c = Constant{
loc: token.loc.clone(),
name: token.text.clone(),
value_i: Some(token.value),
value_s: None,
used: a,
};
constants.insert(token.text.clone(), c);
ti += 1;
},
KeywordType::FunctionDef => {
writeln!(writer, "{}:", token.text)?;
writeln!(writer, " pop rbx")?;
writeln!(writer, " mov qword [rbp], rbx")?;
writeln!(writer, " add rbp, 8")?;
functions.push(Function { loc: token.loc.clone(), name: token.text.clone(), exter: false});
ti += 1;
},
KeywordType::FunctionDone => {
if crate::config::ENABLE_EXPORTED_FUNCTIONS && should_push_ret {
writeln!(writer, " pop rdx")?;
should_push_ret = false;
}
writeln!(writer, " sub rbp, 8")?;
writeln!(writer, " mov rbx, qword [rbp]")?;
writeln!(writer, " push rbx")?;
writeln!(writer, " ret")?;
ti += 1;
}
KeywordType::FunctionThen => ti += 1,
KeywordType::FunctionDefExported => {
if !crate::config::ENABLE_EXPORTED_FUNCTIONS {
lerror!(&token.loc, "Experimental feature 'exported functions' is not enabled");
bail!("");
}
writeln!(writer, "global {}", token.text)?;
writeln!(writer, "{}:", token.text)?;
writeln!(writer, " pop rbx")?;
writeln!(writer, " mov qword [rbp], rbx")?;
writeln!(writer, " add rbp, 8")?;
warn!("External functions are highly experimental and should be treated as such");
if token.types.0 == 0 {
writeln!(writer, " ; no arguments")?;
} else {
if token.types.0 >= 1 {
writeln!(writer, " push rdi")?;
}
if token.types.0 >= 2 {
writeln!(writer, " push rsi")?;
}
if token.types.0 >= 3 {
writeln!(writer, " push rdx")?;
}
if token.types.0 >= 4 {
writeln!(writer, " push rcx")?;
}
if token.types.0 >= 5 {
writeln!(writer, " push r8")?;
}
if token.types.0 >= 6 {
writeln!(writer, " push r9")?;
}
if token.types.0 >= 7 {
lerror!(&token.loc, "More than 6 arguments in an external function is not supported");
bail!("");
}
}
if token.types.1 == 1 {
should_push_ret = true;
} else if token.types.1 > 1 {
lerror!(&token.loc, "More than 1 return arguments in an external function is not supported");
bail!("");
}
functions.push(Function { loc: token.loc.clone(), name: token.text.clone(), exter: false});
ti += 1;
},
KeywordType::Function |
KeywordType::Include |
KeywordType::Inline |
KeywordType::Export |
KeywordType::Struct |
KeywordType::Constant => unreachable!(),
}
}
OpType::Internal(t) => {
match t {
InternalType::StructAlloc{name} => {
alloced_structs.push((name, token.text.clone()));
ti += 1;
},
InternalType::Arrow => panic!("{t:?}"),
}
},
}
}
writeln!(writer, "addr_{ti}:")?;
if !crate::config::ENABLE_EXPORTED_FUNCTIONS && !args.lib_mode {
writeln!(writer, "end:")?;
writeln!(writer, " mov rax, 60")?;
writeln!(writer, " mov rdi, 0")?;
writeln!(writer, " syscall")?;
}
writeln!(writer, "segment .data")?;
for (i, s) in strings.iter().enumerate() {
let s_chars = s.chars().map(|c| (c as u32).to_string()).collect::<Vec<String>>();
let s_list = s_chars.join(",");
writeln!(writer, " str_{}: db {} ; {}", i, s_list, s.escape_default())?;
}
for (_, c) in constants {
if !c.used {
continue;
}
if let Some(v) = &c.value_i {
writeln!(writer, " const_{}: dq {}", c.name, v)?;
} else if let Some(_v) = &c.value_s {
todo!();
} else {
unreachable!();
}
}
writeln!(writer, "segment .bss")?;
for m in memories {
writeln!(writer, " mem_{}: resb {}", m.id, m.size)?;
}
for s in alloced_structs {
let Some(st) = program.struct_defs.get(&s.0) else {
// TODO: Make better error
panic!("Couldn find struct in struct defs");
};
let name = &s.1;
let mut st_size = 0;
writeln!(writer, " struct_{name}:")?;
for f in &st.fields {
let size = f.1.get_size();
writeln!(writer, " struct_{name}.{}: resb {}", f.0, size)?;
st_size += size;
}
writeln!(writer, " struct_{name}.__size: db {}", st_size)?;
}
writeln!(writer, " ret_stack: resq 256")?;
// for t in tokens {
// println!("{t:?}");
// }
writer.flush()?;
pre_compile_steps(
String::from_utf8_lossy(writer.buffer()).to_string().as_str(),
functions
)?;
linux_x86_64_compile_and_link(&of_a, &of_o, &of_c, args.quiet);
if args.run {
let c = linux_x86_64_run(&of_c, &[], args.quiet)?;
return Ok(c);
}
Ok(0)
}
fn pre_compile_steps(_code: &str, functions: Vec<Function>) -> Result<()> {
let mut has_main = false;
for func in functions {
if func.name == "main" {
has_main = true;
}
}
if !has_main {
crate::errors::missing_main_fn();
bail!("");
}
Ok(())
}

362
src/compile/mod.rs Normal file
View File

@ -0,0 +1,362 @@
use crate::definitions::Loc;
pub mod linux_x86_64;
pub mod commands;
#[derive(Debug, Clone)]
pub struct Constant {
pub loc: Loc,
pub name: String,
pub value_i: Option<usize>,
pub value_s: Option<String>,
pub used: bool
// extern: bool
}
#[derive(Debug, Clone)]
pub struct Memory {
pub size: usize,
pub loc: Loc,
pub id: usize
}
#[derive(Debug, Clone)]
pub struct Function {
pub loc: Loc,
pub name: String,
pub exter: bool,
}
const DBG_PRINT: &'static str = "
_dbg_print:
mov r9, -3689348814741910323
sub rsp, 40
mov BYTE [rsp+31], 10
lea rcx, [rsp+30]
.L2:
mov rax, rdi
lea r8, [rsp+32]
mul r9
mov rax, rdi
sub r8, rcx
shr rdx, 3
lea rsi, [rdx+rdx*4]
add rsi, rsi
sub rax, rsi
add eax, 48
mov BYTE [rcx], al
mov rax, rdi
mov rdi, rdx
mov rdx, rcx
sub rcx, 1
cmp rax, 9
ja .L2
lea rax, [rsp+32]
mov edi, 1
sub rdx, rax
xor eax, eax
lea rsi, [rsp+32+rdx]
mov rdx, r8
mov rax, 1
syscall
add rsp, 40
ret
";
const MACRO_DEFINITIONS: &'static str = "\
%macro OP_PushInt 1
mov rax, %1
push rax
%endmacro
; str_len, str_id
%macro OP_PushStr 2
mov rax, %1
push rax
mov rax, %2
push rax
%endmacro
; str_id
%macro OP_PushCStr 1
push rax
mov rax, %1
push rax
%endmacro
%macro OP_Drop 0
pop rax
%endmacro
%macro OP_Print 0
pop rdi
call _dbg_print
%endmacro
%macro OP_Dup 0
pop rax
push rax
push rax
%endmacro
%macro OP_Rot 0
pop rax
pop rbx
pop rcx
push rbx
push rax
push rcx
%endmacro
%macro OP_Swap 0
pop rax
pop rbx
push rax
push rbx
%endmacro
%macro OP_Over 0
pop rax
pop rbx
push rbx
push rax
push rbx
%endmacro
%macro OP_Load8 0
pop rax
xor rbx, rbx
mov bl, byte [rax]
push rbx
%endmacro
%macro OP_Store8 0
pop rbx
pop rax
mov byte [rax], bl
%endmacro
%macro OP_Load32 0
pop rax
xor rbx, rbx
mov ebx, dword [rax]
push rbx
%endmacro
%macro OP_Store32 0
pop rbx
pop rax
mov dword[rax], ebx
%endmacro
%macro OP_Load64 0
pop rax
xor rbx, rbx
mov rbx, qword [rax]
push rbx
%endmacro
%macro OP_Store64 0
pop rbx
pop rax
mov qword [rax], rbx
%endmacro
%macro OP_Plus 0
pop rax
pop rbx
add rax, rbx
push rax
%endmacro
%macro OP_Minus 0
pop rax
pop rbx
sub rbx, rax
push rbx
%endmacro
%macro OP_Equals 0
mov rcx, 0
mov rdx, 1
pop rax
pop rbx
cmp rax, rbx
cmove rcx, rdx
push rcx
%endmacro
%macro OP_Lt 0
mov rcx, 0
mov rdx, 1
pop rbx
pop rax
cmp rax, rbx
cmovl rcx, rdx
push rcx
%endmacro
%macro OP_Gt 0
mov rcx, 0
mov rdx, 1
pop rbx
pop rax
cmp rax, rbx
cmovg rcx, rdx
push rcx
%endmacro
%macro OP_NotEquals 0
mov rcx, 1
mov rdx, 0
pop rax
pop rbx
cmp rax, rbx
cmove rcx, rdx
push rcx
%endmacro
%macro OP_Le 0
mov rcx, 0
mov rdx, 1
pop rbx
pop rax
cmp rax, rbx
cmovle rcx, rdx
push rcx
%endmacro
%macro OP_Ge 0
mov rcx, 0
mov rdx, 1
pop rbx
pop rax
cmp rax, rbx
cmovge rcx, rdx
push rcx
%endmacro
%macro OP_Band 0
pop rax
pop rbx
and rbx, rax
push rbx
%endmacro
%macro OP_Bor 0
pop rax
pop rbx
or rbx, rax
push rbx
%endmacro
%macro OP_Shr 0
pop rcx
pop rbx
shr rbx, cl
push rbx
%endmacro
%macro OP_Shl 0
pop rcx
pop rbx
shl rbx, cl
push rbx
%endmacro
%macro OP_DivMod 0
xor rdx, rdx
pop rbx
pop rax
div rbx
push rax
push rdx
%endmacro
%macro OP_Mul 0
pop rax
pop rbx
mul rbx
push rax
%endmacro
%macro OP_Syscall0 0
pop rax
syscall
push rax
%endmacro
%macro OP_Syscall1 0
pop rax
pop rdi
syscall
push rax
%endmacro
%macro OP_Syscall2 0
pop rax
pop rdi
pop rsi
syscall
push rax
%endmacro
%macro OP_Syscall3 0
pop rax
pop rdi
pop rsi
pop rdx
syscall
push rax
%endmacro
%macro OP_Syscall4 0
pop rax
pop rdi
pop rsi
pop rdx
pop r10
syscall
push rax
%endmacro
%macro OP_Syscall5 0
pop rax
pop rdi
pop rsi
pop rdx
pop r10
pop r8
syscall
push rax
%endmacro
%macro OP_Syscall6 0
pop rax
pop rdi
pop rsi
pop rdx
pop r10
pop r8
pop r9
syscall
push rax
%endmacro
%macro OP_MemUse 1
push mem_%1
%endmacro
%macro OP_FnCall 1
call %1
%endmacro
%macro OP_ConstUse 1
mov rax, qword [const_%1]
push rax
%endmacro
%macro OP_StructUse 1
push struct_%1
%endmacro
";

16
src/config.rs Normal file
View File

@ -0,0 +1,16 @@
/**
* Prints out extra information
*/
pub const DEV_MODE: bool = true;
pub const DEFAULT_OUT_FILE: &str = "a.out";
pub const DEFAULT_INCLUDES: [&str;2] = [
"./include",
"~/.mclang/include",
];
/**
* Experimental options
*/
pub const ENABLE_EXPORTED_FUNCTIONS: bool = false;

283
src/constants.rs Normal file
View File

@ -0,0 +1,283 @@
#[derive(Debug, Clone, PartialEq)]
pub enum InstructionType {
// stack
PushInt,
PushStr,
PushCStr,
Drop,
Print,
Dup,
Rot, // a b c => b c a
Over, // a b => a b a
Swap, // a b => b a
// math
Minus,
Plus,
Equals,
Gt,
Lt,
Ge,
Le,
NotEquals,
Band, // &
Bor, // |
Shr, // >>
Shl, // <<
DivMod, // /
Mul,
// mem
Read8,
Write8,
Read32,
Write32,
Read64,
Write64,
// syscalls
Syscall0,
Syscall1,
Syscall2,
Syscall3,
Syscall4,
Syscall5,
Syscall6,
CastBool,
CastPtr,
CastInt,
CastVoid,
// typing
TypeBool,
TypePtr,
TypeInt,
TypeVoid,
// TypeStr,
TypeAny,
Returns,
With,
FnCall,
MemUse,
ConstUse,
Return,
None // Used for macros and any other non built in word definitions
}
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum KeywordType {
If,
Else,
End,
While,
Do,
Include,
Memory,
Constant,
ConstantDef,
Function,
FunctionDef,
FunctionDefExported,
FunctionThen,
FunctionDone,
Inline,
Export,
Struct
}
#[derive(Debug, Clone, PartialEq)]
pub enum OpType {
Keyword(KeywordType),
Instruction(InstructionType)
}
#[derive(Debug, Clone)]
pub struct Operator{
pub typ: OpType,
pub tok_typ: TokenType,
pub value: usize,
pub text: String, //? only used for OpType::PushStr
pub addr: Option<usize>, //? only used for OpType::PushStr
pub jmp: usize,
pub loc: Loc,
pub types: (usize, usize)
}
impl Operator {
pub fn new(typ: OpType, tok_typ: TokenType, value: usize, text: String, file: String, row: usize, col: usize) -> Self {
Self {
typ,
value,
jmp: 0,
addr: None,
text,
loc: (file, row, col),
tok_typ,
types: (0, 0)
}
}
pub fn set_addr(&mut self, addr: usize) -> Self {
self.addr = Some(addr);
(*self).clone()
}
// pub fn set_types(&mut self, args: usize, rets: usize) -> Self {
// self.types = (args, rets);
// (*self).clone()
// }
}
impl OpType {
pub fn human(&self) -> String {
match (*self).clone() {
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => "Number",
InstructionType::PushStr => "String",
InstructionType::PushCStr => "CString",
InstructionType::Print => "_dbg_print",
InstructionType::Dup => "dup",
InstructionType::Drop => "drop",
InstructionType::Rot => "rot",
InstructionType::Over => "over",
InstructionType::Swap => "swap",
InstructionType::Plus => "+",
InstructionType::Minus => "-",
InstructionType::Equals => "=",
InstructionType::Gt => ">",
InstructionType::Lt => "<",
InstructionType::NotEquals => "!=",
InstructionType::Le => "<=",
InstructionType::Ge => ">=",
InstructionType::Band => "band",
InstructionType::Bor => "bor",
InstructionType::Shr => "shr",
InstructionType::Shl => "shl",
InstructionType::DivMod => "divmod",
InstructionType::Mul => "*",
InstructionType::Read8 => "read8",
InstructionType::Write8 => "write8",
InstructionType::Read32 => "read32",
InstructionType::Write32 => "write32",
InstructionType::Read64 => "read64",
InstructionType::Write64 => "write64",
InstructionType::Syscall0 => "syscall0",
InstructionType::Syscall1 => "syscall1",
InstructionType::Syscall2 => "syscall2",
InstructionType::Syscall3 => "syscall3",
InstructionType::Syscall4 => "syscall4",
InstructionType::Syscall5 => "syscall5",
InstructionType::Syscall6 => "syscall6",
InstructionType::CastBool => "cast(bool",
InstructionType::CastPtr => "cast(ptr)",
InstructionType::CastInt => "cast(int)",
InstructionType::CastVoid => "cast(void)",
InstructionType::None => "None",
InstructionType::MemUse => "Memory use (internal)",
InstructionType::FnCall => "Function Call (Internal)",
InstructionType::ConstUse => "Constant Use (Internal)",
InstructionType::Return => "return",
InstructionType::TypeBool => "bool",
InstructionType::TypePtr => "ptr",
InstructionType::TypeInt => "int",
InstructionType::TypeVoid => "void",
InstructionType::Returns => "returns",
InstructionType::With => "with",
InstructionType::TypeAny => "any",
}
}
OpType::Keyword(keyword) => {
match keyword {
KeywordType::If => "if",
KeywordType::Else => "else",
KeywordType::End => "end",
KeywordType::While => "while",
KeywordType::Do => "do",
KeywordType::Include => "include",
KeywordType::Memory => "memory",
KeywordType::Function => "fn",
KeywordType::Constant => "const",
KeywordType::FunctionThen => "then",
KeywordType::FunctionDone => "done",
KeywordType::ConstantDef => "constant Definition (internal)",
KeywordType::FunctionDef => "function definition (internal)",
KeywordType::FunctionDefExported => "extern function definition (internal)",
KeywordType::Inline => "inline",
KeywordType::Export => "export",
KeywordType::Struct => "struct",
}
}
}.to_string()
}
}
#[derive(Debug, Clone)]
pub struct Token {
pub file: String,
pub line: usize,
pub col: usize,
pub text: String,
pub typ: TokenType,
pub value: Option<usize>, //* only used for Memories
pub addr: Option<usize>, //* only used for Memories
pub op_typ: OpType //* only used for Memories
}
#[derive(Debug, Clone, PartialEq, Copy)]
pub enum TokenType {
Word,
Int,
String,
CString,
Char
}
impl Token {
pub fn loc(&self) -> Loc {
(
self.file.clone(),
self.line,
self.col
)
}
}
impl TokenType {
pub fn human(self) -> String {
match self {
TokenType::Word => "Word",
TokenType::Int => "Int",
TokenType::String => "String",
TokenType::CString => "CString",
TokenType::Char => "Char"
}.to_string()
}
}
pub type Loc = (String, usize, usize);
#[derive(Debug, PartialEq, Clone)]
pub enum Types {
Bool,
Ptr,
Int,
Void,
Any
// U8,
// U16,
// U32,
// U64,
// todo: add signed numbers since we dont have them yet lol
}

392
src/definitions/mod.rs Normal file
View File

@ -0,0 +1,392 @@
use std::collections::HashMap;
use anyhow::{Result, bail};
#[derive(Debug, Clone, PartialEq)]
pub enum InstructionType {
// stack
PushInt,
PushStr,
PushCStr,
Drop,
Print,
Dup,
Rot, // a b c => b c a
Over, // a b => a b a
Swap, // a b => b a
// math
Minus,
Plus,
Equals,
Gt,
Lt,
Ge,
Le,
NotEquals,
Band, // &
Bor, // |
Shr, // >>
Shl, // <<
DivMod, // /
Mul,
// mem
Read8,
Write8,
Read32,
Write32,
Read64,
Write64,
// syscalls
Syscall0,
Syscall1,
Syscall2,
Syscall3,
Syscall4,
Syscall5,
Syscall6,
CastBool,
CastPtr,
CastInt,
CastVoid,
// typing
TypeBool,
TypePtr,
TypeInt,
TypeVoid,
// TypeStr,
TypeAny,
Returns,
With,
FnCall,
MemUse,
ConstUse,
StructUse,
Return,
None // Used for macros and any other non built in word definitions
}
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum KeywordType {
If,
Else,
End,
While,
Do,
Include,
Memory,
Constant,
ConstantDef,
Function,
FunctionDef,
FunctionDefExported,
FunctionThen,
FunctionDone,
Inline,
Export,
Struct,
}
#[derive(Debug, Clone, PartialEq)]
pub enum InternalType {
Arrow,
StructAlloc {
name: String
}
}
#[derive(Debug, Clone, PartialEq)]
pub enum OpType {
Keyword(KeywordType),
Instruction(InstructionType),
Internal(InternalType)
}
#[derive(Debug, Clone)]
pub struct Operator{
pub typ: OpType,
pub tok_typ: TokenType,
pub value: usize,
pub text: String, //? only used for OpType::PushStr
pub addr: Option<usize>, //? only used for OpType::PushStr
pub jmp: usize,
pub loc: Loc,
pub types: (usize, usize)
}
impl Operator {
pub fn new(typ: OpType, tok_typ: TokenType, value: usize, text: String, file: String, row: usize, col: usize) -> Self {
Self {
typ,
value,
jmp: 0,
addr: None,
text,
loc: (file, row, col),
tok_typ,
types: (0, 0)
}
}
pub fn set_addr(&mut self, addr: usize) -> Self {
self.addr = Some(addr);
(*self).clone()
}
// pub fn set_types(&mut self, args: usize, rets: usize) -> Self {
// self.types = (args, rets);
// (*self).clone()
// }
}
impl OpType {
pub fn human(&self) -> String {
match (*self).clone() {
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => "Number",
InstructionType::PushStr => "String",
InstructionType::PushCStr => "CString",
InstructionType::Print => "_dbg_print",
InstructionType::Dup => "dup",
InstructionType::Drop => "drop",
InstructionType::Rot => "rot",
InstructionType::Over => "over",
InstructionType::Swap => "swap",
InstructionType::Plus => "+",
InstructionType::Minus => "-",
InstructionType::Equals => "=",
InstructionType::Gt => ">",
InstructionType::Lt => "<",
InstructionType::NotEquals => "!=",
InstructionType::Le => "<=",
InstructionType::Ge => ">=",
InstructionType::Band => "band",
InstructionType::Bor => "bor",
InstructionType::Shr => "shr",
InstructionType::Shl => "shl",
InstructionType::DivMod => "divmod",
InstructionType::Mul => "*",
InstructionType::Read8 => "read8",
InstructionType::Write8 => "write8",
InstructionType::Read32 => "read32",
InstructionType::Write32 => "write32",
InstructionType::Read64 => "read64",
InstructionType::Write64 => "write64",
InstructionType::Syscall0 => "syscall0",
InstructionType::Syscall1 => "syscall1",
InstructionType::Syscall2 => "syscall2",
InstructionType::Syscall3 => "syscall3",
InstructionType::Syscall4 => "syscall4",
InstructionType::Syscall5 => "syscall5",
InstructionType::Syscall6 => "syscall6",
InstructionType::CastBool => "cast(bool",
InstructionType::CastPtr => "cast(ptr)",
InstructionType::CastInt => "cast(int)",
InstructionType::CastVoid => "cast(void)",
InstructionType::None => "None",
InstructionType::MemUse => "Memory use (internal)",
InstructionType::FnCall => "Function Call (Internal)",
InstructionType::ConstUse => "Constant Use (Internal)",
InstructionType::StructUse => "Struct Use (Internal)",
InstructionType::Return => "return",
InstructionType::TypeBool => "bool",
InstructionType::TypePtr => "ptr",
InstructionType::TypeInt => "int",
InstructionType::TypeVoid => "void",
InstructionType::Returns => "returns",
InstructionType::With => "with",
InstructionType::TypeAny => "any",
}
}
OpType::Keyword(keyword) => {
match keyword {
KeywordType::If => "if",
KeywordType::Else => "else",
KeywordType::End => "end",
KeywordType::While => "while",
KeywordType::Do => "do",
KeywordType::Include => "include",
KeywordType::Memory => "memory",
KeywordType::Function => "fn",
KeywordType::Constant => "const",
KeywordType::FunctionThen => "then",
KeywordType::FunctionDone => "done",
KeywordType::ConstantDef => "constant Definition (internal)",
KeywordType::FunctionDef => "function definition (internal)",
KeywordType::FunctionDefExported => "extern function definition (internal)",
KeywordType::Inline => "inline",
KeywordType::Export => "export",
KeywordType::Struct => "struct",
}
}
OpType::Internal(t) => {
match t {
InternalType::Arrow => "->",
InternalType::StructAlloc{..} => "Struct alloc ( internal )",
}
},
}.to_string()
}
}
#[derive(Debug, Clone)]
pub struct Token {
pub file: String,
pub line: usize,
pub col: usize,
pub text: String,
pub typ: TokenType,
pub value: Option<usize>, //* only used for Memories
pub addr: Option<usize>, //* only used for Memories
pub op_typ: OpType //* only used for Memories
}
#[derive(Debug, Clone, PartialEq, Copy)]
pub enum TokenType {
Word,
Int,
String,
CString,
Char
}
impl Token {
pub fn loc(&self) -> Loc {
(
self.file.clone(),
self.line,
self.col
)
}
}
impl TokenType {
pub fn human(self) -> String {
match self {
TokenType::Word => "Word",
TokenType::Int => "Int",
TokenType::String => "String",
TokenType::CString => "CString",
TokenType::Char => "Char"
}.to_string()
}
}
pub type Loc = (String, usize, usize);
#[derive(Debug, PartialEq, Clone)]
pub enum Types {
Any,
Bool,
Ptr,
Void,
U8,
U16,
U32,
U64,
I8,
I16,
I32,
I64,
#[allow(dead_code)] //TODO: Implement custom types
Custom{
size: u64 // in bytes
},
// todo: add signed numbers since we dont have them yet lol
}
impl Types {
pub fn get_size(&self) -> u64 {
match *self {
Types::Any => 0, // any cant be a known size
Types::Void => 0,
Types::Bool => 1,
Types::U8 |
Types::I8 => 1,
Types::U16 |
Types::I16 => 2,
Types::U32 |
Types::I32 => 4,
Types::Ptr |
Types::U64 |
Types::I64 => 8,
Types::Custom { size } => size,
}
}
pub fn from_string<S: Into<String> + std::fmt::Display>(s: &S) -> Result<Self> {
match s.to_string().as_str() {
"any" => Ok(Types::Any),
"void" => Ok(Types::Void),
"bool" => Ok(Types::Bool),
"u8" => Ok(Types::U8),
"i8" => Ok(Types::I8),
"u16" => Ok(Types::U16),
"i16" => Ok(Types::I16),
"u32" => Ok(Types::U32),
"i32" => Ok(Types::I32),
"ptr" => Ok(Types::Ptr),
"u64" => Ok(Types::U64),
"i64" => Ok(Types::I64),
_ => bail!("Unknown type {s}")
}
}
}
#[derive(Debug, Clone)]
pub struct Function {
pub loc: Loc,
pub name: String,
pub inline: bool,
pub tokens: Option<Vec<Operator>>
}
#[derive(Debug, Clone)]
pub struct Constant {
pub loc: Loc,
pub name: String
}
#[derive(Debug, Clone)]
pub struct Memory {
pub loc: Loc,
pub id: usize
}
#[derive(Debug, Clone)]
pub struct StructDef {
pub loc: Loc,
pub name: String,
pub fields: Vec<(String, Types)>
}
pub type Functions = HashMap<String, Function>;
pub type Memories = HashMap<String, Memory>;
pub type Constants = HashMap<String, Constant>;
pub type StructDefs = HashMap<String, StructDef>;
#[derive(Debug, Clone)]
pub struct Program {
pub ops: Vec<Operator>,
pub functions: Functions,
pub memories: Memories,
pub constants: Constants,
pub struct_defs: StructDefs,
pub struct_allocs: HashMap<String, String>
}

18
src/errors/mod.rs Normal file
View File

@ -0,0 +1,18 @@
use crate::{error, help, code_block};
pub fn missing_main_fn() {
error!("Main function not found, please create one lol");
help!("Heres a basic main function with code that prints hello world:\n{}",
code_block!(
concat!(
"include \"std.mcl\"\n",
"\n",
"fn main with void retuns void then\n",
" \"Hello world!\\n\" puts\n",
"done\n"
)
)
);
}

61
src/include/ast.h
View File

@ -1,61 +0,0 @@
#ifndef _H_MCL_AST
#define _H_MCL_AST
#include "loc.h"
#include "dyn_arr.h"
DEFINE_DA(ast_node, void*);
typedef enum ast_type_e {
AT_BIN_ADD,
AT_BIN_SUB,
AT_BIN_DIV,
AT_BIN_MUL,
AT_UN_DEREF,
AT_UN_XOR,
AT_FUNC,
AT_ASSIGN,
AT_EXPR,
} ast_type_t;
typedef struct ast_ident_s {
char* name;
loc_t loc;
} ast_ident_t;
typedef struct type_s {
ast_ident_t name;
struct type_s* inner;
} type_t;
typedef struct ast_node_s {
ast_type_t* type;
loc_t loc;
} ast_node_t;
typedef struct ast_program_s {
mcl_da_ast_node_t body;
loc_t loc;
} ast_program_t;
typedef struct ast_func_param_s {
ast_ident_t name;
type_t type;
} ast_func_param_t;
DEFINE_DA(func_param, ast_func_param_t);
typedef struct ast_func_decl_s {
ast_type_t* type;
loc_t loc;
ast_ident_t id;
mcl_da_func_param_t params;
mcl_da_ast_node_t body;
} ast_func_decl_t;
#endif

33
src/include/cliargs.h
View File

@ -1,33 +0,0 @@
#ifndef _H_MCL_CLIARGS
#define _H_MCL_CLIARGS
#include <getopt.h>
#include <string.h>
#include "dyn_arr.h"
#ifndef MCL_VERSION
#define MCL_VERSION "0.0.1"
#endif
DEFINE_DA(string, char*)
static struct option cli_options[] = {
{"help", no_argument, 0, 'h'},
{"version", no_argument, 0, 'v'},
{"output", required_argument, 0, 'o'},
{"debug", no_argument, 0, 'd'},
{0,0,0,0}
};
typedef struct cliargs_s {
bool help;
bool version;
bool debug;
char* output;
mcl_da_string_t input;
} cliargs_t;
cliargs_t* parse_cliargs(int argc, char** argv);
#endif

121
src/include/dyn_arr.h
View File

@ -1,121 +0,0 @@
#ifndef _H_MCL_DYN_ARR
#define _H_MCL_DYN_ARR
#include <stdio.h>
#define DEFINE_DA(name, type) \
typedef struct mcl_da_##name##_s { \
type* items; \
size_t count; \
size_t capacity; \
} mcl_da_##name##_t; \
type* mcl_da_##name##_pop(mcl_da_##name##_t* da); \
type* mcl_da_##name##_peek(mcl_da_##name##_t* da); \
type* mcl_da_##name##_pop_front(mcl_da_##name##_t* da); \
type* mcl_da_##name##_peek_front(mcl_da_##name##_t* da); \
void mcl_da_##name##_push(mcl_da_##name##_t* da, type item); \
void mcl_da_##name##_free(mcl_da_##name##_t* da);
#define DEFINE_DA_IMPL(name, type) \
type* mcl_da_##name##_pop(mcl_da_##name##_t* da) { \
if (da->capacity <= 0 || da->count <= 0) \
return NULL; \
if (da->count < da->capacity / 2) { \
da->capacity /= 2; \
da->items = realloc(da->items, \
da->capacity * sizeof(type)); \
assert(da->items && "Out of memory"); \
} \
return &da->items[(da->count--) - 1]; \
} \
void mcl_da_##name##_push(mcl_da_##name##_t* da, type item) { \
if (da->capacity <= da->count) { \
if (da->capacity == 0) { \
da->capacity = 8; \
} else { \
da->capacity *= 2; \
} \
da->items = realloc(da->items, \
da->capacity * sizeof(type)); \
assert(da->items && "Out of memory"); \
} \
da->items[da->count++] = item; \
} \
type* mcl_da_##name##_pop_front(mcl_da_##name##_t* da) { \
if (da->capacity <= 0 || da->count <= 0) \
return NULL; \
if (da->count < da->capacity / 2) { \
da->capacity /= 2; \
da->items = realloc(da->items, \
da->capacity * sizeof(type)); \
assert(da->items && "Out of memory"); \
} \
type* item = malloc(sizeof(type)); \
type* temp = malloc(sizeof(type) * da->count); \
*item = da->items[0]; \
memcpy(temp, &da->items[1], sizeof(type) * da->count); \
memcpy(da->items, temp, sizeof(type) * --da->count); \
free(temp); \
return item; \
} \
type* mcl_da_##name##_peek(mcl_da_##name##_t* da) { \
if (da->count < 1) return NULL; \
return &da->items[da->count - 1]; \
} \
type* mcl_da_##name##_peek_front(mcl_da_##name##_t* da) { \
return &da->items[0]; \
} \
void mc_da_##name##_free(mcl_da_##name##_t* da) { \
free(da->items); \
}
//#define DEFINE_PTR_DA(name, type) \
//typedef struct mcl_ptr_da_##name##_s { \
// type** items; \
// size_t count; \
// size_t capacity; \
//} mcl_ptr_da_##name##_t; \
//type* mcl_da_##name##_pop(mcl_da_##name##_t* da); \
//void mcl_da_##name##_push(mcl_da_##name##_t* da, type* item);
//
//
//#define DEFINE_PTR_DA_IMPL(type) \
//type* mcl_ptr_da_##name##_pop(mcl_da_##name##_t* da) { \
// if (da->capacity <= 0 || da->count <= 0) \
// return NULL; \
// if (da->count < da->capacity / 2) { \
// da->capacity /= 2; \
// da->items = realloc(da->items, \
// da->capacity * sizeof(type*)); \
// assert(da->items && "Out of memory"); \
// } \
// return da->items[(da->count--) - 1]; \
//} \
//void mcl_ptr_da_##name##_push(mcl_da_##name##_t* da, type* item) { \
// if (da->capacity <= da->count) { \
// if (da->capacity == 0) { \
// da->capacity = 8; \
// } else { \
// da->capacity *= 2; \
// } \
// da->items = realloc(da->items, \
// da->capacity * sizeof(type*)); \
// assert(da->items && "Out of memory"); \
// } \
// da->items[da->count++] = item; \
//} \
//void mc_ptr_da_##name##_free(mcl_da_##name##_* da) { \
// free(da->items); \
//}
#define MCL_DA_FOR_IN(type, da, item, body) do { \
type item; \
for (int i = 0; i < (da)->count; i++) { \
item = ((da)->items)[i]; \
body \
} \
} while (0)
#endif

6
src/include/errors.h
View File

@ -1,6 +0,0 @@
#ifndef _H_MCL_ERRORS
#define _H_MCL_ERRORS
const char* FUNC_DECL_EXMPL = "To define a function follow this example: \nmain :: fn(argc: i32, argv: string[]) {\n ...\n}";
#endif

11
src/include/loc.h
View File

@ -1,11 +0,0 @@
#ifndef _H_MCL_LOC
#define _H_MCL_LOC
#include <stdio.h>
typedef struct loc_s {
char* file;
size_t col;
size_t line;
} loc_t;
#endif

46
src/include/logger.h
View File

@ -1,46 +0,0 @@
#ifndef _H_MCL_LOG
#define _H_MCL_LOG
#include "loc.h"
#ifdef _LOG_COLORS
#define RESET "\x1b[0m"
#define BRIGHT "\x1b[1m"
#define DIM "\x1b[2m"
#define UNDERSCORE "\x1b[4m"
#define BLINK "\x1b[5m"
#define REVERSE "\x1b[7m"
#define HIDDEN "\x1b[8m"
#define FG_BLACK "\x1b[30m"
#define FG_RED "\x1b[31m"
#define FG_GREEN "\x1b[32m"
#define FG_YELLOW "\x1b[33m"
#define FG_BLUE "\x1b[34m"
#define FG_MAGENTA "\x1b[35m"
#define FG_CYAN "\x1b[36m"
#define FG_WHITE "\x1b[37m"
#define BG_BLACK "\x1b[40m"
#define BG_RED "\x1b[41m"
#define BG_GREEN "\x1b[42m"
#define BG_YELLOW "\x1b[43m"
#define BG_BLUE "\x1b[44m"
#define BG_MAGENTA "\x1b[45m"
#define BG_CYAN "\x1b[46m"
#define BG_WHITE "\x1b[47m"
#endif
typedef enum log_level_e {
ERROR = 0,
WARN,
HELP,
INFO,
DEBUG,
} log_level_t;
static log_level_t FILTER_LEVEL = INFO;
void mcl_log(log_level_t level, const char* fmt, ...);
void mcl_log_loc(log_level_t level, loc_t* loc, const char* fmt, ...);
#endif

10
src/include/parser.h
View File

@ -1,10 +0,0 @@
#ifndef _H_MCL_PARSER
#define _H_MCL_PARSER
#include "tokeniser.h"
#include "ast.h"
ast_program_t* parse(mcl_da_token_t* tokens);
#endif

50
src/include/token.h
View File

@ -1,50 +0,0 @@
#ifndef _H_MCL_TOKEN
#define _H_MCL_TOKEN
#include "loc.h"
typedef enum token_type_e {
TT_IDENT, // identifier
TT_STR, // "*"
TT_CHR, // '*'
TT_CURLY_R, // }
TT_CURLY_L, // {
TT_BRACK_R, // ]
TT_BRACK_L, // [
TT_PAREN_R, // )
TT_PAREN_L, // (
TT_COLON, // :
TT_SEMI, // ;
TT_COMMA, // ,
TT_DOT, // .
TT_AMP, // &
TT_STAR, // *
TT_PLUS, // +
TT_DASH, // -
TT_FSLASH, // /
TT_BAR, // |
TT_EQ, // =
TT_LT, // <
TT_GT, // >
TT_KW_FN,
TT_KW_RETURN,
TT_KW_IF,
TT_KW_ELSE,
TT_KW_FOR,
TT_KW_WHILE,
TT_KW_STRUCT,
TT_KW_ENUM,
TT_KW_BREAK,
TT_KW_CONTINUE,
} token_type_t;
typedef struct token_s {
token_type_t type;
char* text;
loc_t loc;
} token_t;
char* token_to_string(token_t* tt);
#endif

20
src/include/tokeniser.h
View File

@ -1,20 +0,0 @@
#ifndef _H_MCL_TOKENSIER
#define _H_MCL_TOKENSIER
#include <stdlib.h>
#include <assert.h>
#include "dyn_arr.h"
#include "loc.h"
#include "token.h"
DEFINE_DA(token, token_t)
typedef struct tokeniser_s {
mcl_da_token_t tokens;
loc_t loc;
} tokeniser_t;
tokeniser_t* tokenise(char* file);
#endif

442
src/interpret/linux_x86_64/mod.rs Normal file
View File

@ -0,0 +1,442 @@
use std::collections::HashMap;
use crate::{constants::{OpType, Loc, InstructionType, KeywordType, Operator}, lerror, error};
// use crate::util::logger;
use color_eyre::Result;
use eyre::eyre;
use super::{Memory, Function, Constant};
mod syscalls;
fn stack_pop(stack: &mut Vec<usize>, pos: &Loc) -> Result<usize> {
if let Some(i) = stack.pop() { Ok(i) } else {
lerror!(&pos.clone(), "Stack underflow");
Err(eyre!("Stack underflow"))
}
}
pub fn run(ops: &[crate::constants::Operator]) -> Result<i32>{
let mut stack: Vec<usize> = Vec::new();
let mut mem: Vec<u64> = vec![0; crate::MEM_SZ + crate::STRING_SZ];
let mut string_idx = 0;
let prerunned = pre_run(ops);
let functions = prerunned.functions;
let constants = prerunned.constants;
let memories = prerunned.memories;
let mut ret_stack: Vec<usize> = Vec::new();
// for token in &tokens {
// println!("{{typ: \"{:?}\", val: {}, jmp: {}}}", token.typ, token.value, token.jmp);
// }
// jump to main func
let mut ip = if let Some(i) = functions.get("main") {i.id} else {
crate::errors::missing_main_fn();
return Err(eyre!(""));
};
while ip < ops.len() {
let op = &ops[ip];
let pos = op.loc.clone();
match op.typ.clone() {
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => {
stack.push(op.value);
ip += 1;
},
InstructionType::PushStr => {
if op.addr.is_none() {
stack.push(op.text.len()); // string len
stack.push(string_idx + crate::MEM_SZ);
for c in op.text.bytes() {
mem[crate::MEM_SZ + string_idx] = u64::from(c);
string_idx += 1;
}
} else {
stack.push(op.text.len());
if let Some(addr) = op.addr {
stack.push(addr);
}
}
ip += 1;
},
InstructionType::PushCStr => {
if op.addr.is_none() {
stack.push(string_idx + crate::MEM_SZ);
for c in op.text.bytes() {
mem[crate::MEM_SZ + string_idx] = u64::from(c);
string_idx += 1;
}
} else {
if let Some(addr) = op.addr {
stack.push(addr);
}
}
ip += 1;
},
InstructionType::Drop => {
stack.pop();
ip += 1;
},
InstructionType::Dup => {
let a = stack_pop(&mut stack, &pos)?;
stack.push(a);
stack.push(a);
ip += 1;
},
InstructionType::Rot => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
let c = stack_pop(&mut stack, &pos)?;
stack.push(b);
stack.push(a);
stack.push(c);
ip += 1;
}
InstructionType::Swap => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(a);
stack.push(b);
ip += 1;
}
InstructionType::Over => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b);
stack.push(a);
stack.push(b);
ip += 1;
}
InstructionType::Print => {
let a = stack_pop(&mut stack, &pos)?;
println!("{a}");
// let _ = io::stdout().flush();
ip += 1;
},
#[allow(clippy::cast_possible_truncation)]
InstructionType::Read8 |
InstructionType::Read32 |
InstructionType::Read64 => {
let a = stack_pop(&mut stack, &pos)?;
if a > crate::MEM_SZ + crate::STRING_SZ {
lerror!(&op.loc, "Invalid memory address {a}");
return Ok(1);
}
let byte = mem[a];
stack.push(byte as usize);
ip += 1;
}
#[allow(clippy::cast_possible_truncation)]
InstructionType::Write8 => {
let val = stack_pop(&mut stack, &pos)?;
let addr = stack_pop(&mut stack, &pos)?;
if addr > crate::MEM_SZ {
lerror!(&op.loc, "Invalid memory address {addr}");
return Ok(1);
}
mem[addr] = u64::from(val as u8);
ip += 1;
}
#[allow(clippy::cast_possible_truncation)]
InstructionType::Write32 => {
let val = stack_pop(&mut stack, &pos)?;
let addr = stack_pop(&mut stack, &pos)?;
if addr > crate::MEM_SZ {
lerror!(&op.loc, "Invalid memory address {addr}");
return Ok(1);
}
mem[addr] = u64::from(val as u32);
ip += 1;
}
#[allow(clippy::cast_possible_truncation)]
InstructionType::Write64 => {
let val = stack_pop(&mut stack, &pos)?;
let addr = stack_pop(&mut stack, &pos)?;
if addr > crate::MEM_SZ {
lerror!(&op.loc, "Invalid memory address {addr}");
return Ok(1);
}
mem[addr] = val as u64;
ip += 1;
}
// math
InstructionType::Plus => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b + a);
ip += 1;
},
InstructionType::Minus => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b - a);
ip += 1;
},
InstructionType::Equals => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b == a));
ip += 1;
},
InstructionType::Gt => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b > a));
ip += 1;
},
InstructionType::Lt => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b < a));
ip += 1;
},
InstructionType::NotEquals => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b != a));
ip += 1;
},
InstructionType::Ge => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b >= a));
ip += 1;
},
InstructionType::Le => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(usize::from(b <= a));
ip += 1;
},
InstructionType::Band => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(a & b);
ip += 1;
}
InstructionType::Bor => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(a | b);
ip += 1;
}
InstructionType::Shr => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b >> a);
ip += 1;
}
InstructionType::Shl => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b << a);
ip += 1;
}
InstructionType::DivMod => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b / a);
stack.push(b % a);
ip += 1;
}
InstructionType::Mul => {
let a = stack_pop(&mut stack, &pos)?;
let b = stack_pop(&mut stack, &pos)?;
stack.push(b * a);
ip += 1;
}
InstructionType::Syscall0 => {
todo!();
// ti += 1;
},
InstructionType::Syscall1 => {
todo!();
// ti += 1;
},
InstructionType::Syscall2 => {
todo!();
// ti += 1;
},
InstructionType::Syscall3 => {
let rax = stack_pop(&mut stack, &pos)?;
let rdi = stack_pop(&mut stack, &pos)?;
let rsi = stack_pop(&mut stack, &pos)?;
let rdx = stack_pop(&mut stack, &pos)?;
// println!("yes");
let ret = match rax {
1 => syscalls::sys_write(rax, rdi, rsi, rdx, &mem),
0 => 0, //? temp, so clippy doesnt complain
_ => {
error!("Syscall(3) #{} is not implemented", rax);
return Err(eyre!("Syscall not implemented"));
}
};
stack.push(ret);
// println!("{}", stack.len());
ip += 1;
},
InstructionType::Syscall4 => {
todo!();
// ti += 1;
},
InstructionType::Syscall5 => {
todo!();
// ti += 1;
},
InstructionType::Syscall6 => {
todo!();
// ti += 1;
},
InstructionType::MemUse => {
let m = memories.get(&op.addr.unwrap()).unwrap();
stack.push(m.id);
ip += 1;
},
InstructionType::FnCall => {
ret_stack.push(ip);
let f = functions.get(&op.text).unwrap();
ip = f.id;
}
InstructionType::Return => {
ip = ret_stack.pop().unwrap();
ip += 1;
}
InstructionType::ConstUse => {
let a = constants.get(&op.text).unwrap();
if let Some(i) = a.value_i {
stack.push(i);
} else if let Some(_s) = a.value_s.clone() {
unimplemented!();
}
ip += 1;
},
InstructionType::CastBool |
InstructionType::CastPtr |
InstructionType::CastInt |
InstructionType::CastVoid |
InstructionType::TypeBool |
InstructionType::TypePtr |
InstructionType::TypeInt |
InstructionType::TypeVoid |
InstructionType::TypeAny |
InstructionType::Returns |
InstructionType::With => ip += 1,
InstructionType::None => unreachable!(),
}
}
OpType::Keyword(k) => {
match k {
// blocks
KeywordType::If => {
let a = stack_pop(&mut stack, &pos)?;
if a == 0 {
// println!("If({ti}) => t: {:?} j: {}", tokens[token.jmp as usize].typ, token.jmp);
ip = op.jmp;
} else {
ip += 1;
}
},
KeywordType::Else | KeywordType::End => {
ip = op.jmp;
}
KeywordType::Do => {
let a = stack.pop().unwrap();
if a == 0 {
ip = op.jmp;
} else {
ip += 1;
}
}
KeywordType::While | //* exept this one, this one should just skip over
KeywordType::Memory |
KeywordType::FunctionDef |
KeywordType::FunctionDefExported |
KeywordType::ConstantDef => {
//? Disabled since we now pre run the whole program
// constants.insert(op.text.clone(), Constant { loc: op.loc.clone(), name: op.text.clone(), value_i: Some(op.value), value_s: None, used: false });
ip += 1;
},
KeywordType::FunctionDone => {
if let Some(i) = ret_stack.pop() {
ip = i + 1;
} else {
break;
}
},
KeywordType::FunctionThen => ip += 1,
KeywordType::Constant |
KeywordType::Function |
KeywordType::Inline |
KeywordType::Export |
KeywordType::Include => unreachable!(),
}
}
}
}
Ok(0)
}
pub struct Defineds {
pub memories: HashMap<usize, Memory>,
pub functions: HashMap<String, Function>,
pub constants: HashMap<String, Constant>
}
pub fn pre_run(ops: &[Operator]) -> Defineds {
let mut defineds = Defineds{
memories: HashMap::new(),
functions: HashMap::new(),
constants: HashMap::new(),
};
for (ip, op) in ops.iter().enumerate() {
match op.typ {
OpType::Keyword(KeywordType::Memory) => {
defineds.memories.insert(op.addr.unwrap(), Memory { size: op.value, loc: op.loc.clone(), id: op.addr.unwrap() });
},
OpType::Keyword(KeywordType::FunctionDefExported) => {
}
OpType::Keyword(KeywordType::FunctionDef) => {
defineds.functions.insert(op.text.clone(), Function { loc: op.loc.clone(), name: op.text.clone(), id: ip });
},
OpType::Keyword(KeywordType::ConstantDef) => {
defineds.constants.insert(op.text.clone(), Constant { loc: op.loc.clone(), name: op.text.clone(), value_i: Some(op.value), value_s: None, used: false });
},
_ => ()
}
}
defineds
}

22
src/interpret/linux_x86_64/syscalls.rs Normal file
View File

@ -0,0 +1,22 @@
#[allow(clippy::cast_possible_truncation)]
pub fn sys_write(sys_n: usize, fd: usize, buff: usize, count: usize, mem: &Vec<u64> ) -> usize {
let mem = (*mem).clone();
// println!("{:?}", &mem[buff..(buff + count)]);
// return 0 ;
let s = &mem[buff..(buff + count)].iter().map(|i| {
char::from_u32(u32::from(*i as u8)).unwrap_or('_').to_string()
}).collect::<String>();
match fd {
1 => {
print!("{s}");
},
2 => {
eprint!("{s}");
},
_ => panic!("Unknown file {fd}")
};
let _ = std::io::Write::flush(&mut std::io::stdout());
let _ = std::io::Write::flush(&mut std::io::stderr());
sys_n
}

27
src/interpret/mod.rs Normal file
View File

@ -0,0 +1,27 @@
use crate::constants::Loc;
pub mod linux_x86_64;
#[derive(Debug, Clone)]
pub struct Constant {
pub loc: Loc,
pub name: String,
pub value_i: Option<usize>,
pub value_s: Option<String>,
pub used: bool
// extern: bool
}
#[derive(Debug, Clone)]
pub struct Memory {
pub size: usize,
pub loc: Loc,
pub id: usize
}
#[derive(Debug, Clone)]
pub struct Function {
pub loc: Loc,
pub name: String,
pub id: usize
}

147
src/lexer.rs Normal file
View File

@ -0,0 +1,147 @@
use crate::{definitions::{Token, TokenType}, Args};
fn lex_word(s: String, tok_type: TokenType) -> (TokenType, String) {
match s {
s if s.parse::<u64>().is_ok() && tok_type == TokenType::Word => { // negative numbers not yet implemented
(TokenType::Int, s)
},
s if tok_type == TokenType::Word => {
(TokenType::Word, s)
},
s if tok_type == TokenType::String => {
(TokenType::String, s)
}
s if tok_type == TokenType::CString => {
(TokenType::CString, s)
}
s if tok_type == TokenType::Char => {
(TokenType::Char, s)
}
_ => unreachable!()
}
}
pub fn find_col<F>(text: &str, mut col: usize, predicate: F) -> usize where F: Fn(char, char) -> bool {
let mut last = '\0';
while col < text.len() && !predicate(text.chars().nth(col).unwrap(), last) {
last = text.chars().nth(col).unwrap();
col += 1;
}
col
}
// TODO: Implement multiline strings
fn lex_line(text: &str) -> Vec<(usize, String, TokenType)> {
let mut tokens: Vec<(usize, String, TokenType)> = Vec::new();
let mut col = find_col(text, 0, |x, _| !x.is_whitespace());
let mut col_end: usize = 0;
while col_end < text.to_string().len() {
if (text.len() - col) < 1 {
return tokens;
}
if &text[col..=col] == "\"" {
col_end = find_col(text, col + 1, |x, x2| x == '"' && x2 != '\\');
let t = &text[(col + 1)..col_end];
let t = t.replace("\\n", "\n")
.replace("\\t", "\t")
.replace("\\r", "\r")
.replace("\\\'", "\'")
.replace("\\\"", "\"")
.replace("\\0", "\0");
if !t.is_empty() {
tokens.push((col, t.to_string(), TokenType::String));
}
col = find_col(text, col_end + 1, |x, _| !x.is_whitespace());
} else if &text[col..=col] == "'"{
col_end = find_col(text, col + 1, |x, x2| x == '\'' && x2 != '\\');
let t = &text[(col + 1)..col_end];
let t = t.replace("\\n", "\n")
.replace("\\t", "\t")
.replace("\\r", "\r")
.replace("\\\'", "\'")
.replace("\\\"", "\"")
.replace("\\0", "\0");
if !t.is_empty() {
tokens.push((col, t.to_string(), TokenType::Char));
}
col = find_col(text, col_end + 1, |x, _| !x.is_whitespace());
} else {
if &text[col..=col] == "c" && text.len() - 1 + col > 0 && &text[col+1..=col+1] == "\"" {
col_end = find_col(text, col + 2, |x, x2| x == '"' && x2 != '\\');
let t = &text[(col + 2)..col_end];
let mut t = t.replace("\\n", "\n")
.replace("\\t", "\t")
.replace("\\r", "\r")
.replace("\\\'", "\'")
.replace("\\\"", "\"")
.replace("\\0", "\0");
if !t.is_empty() {
t.push('\0');
tokens.push((col, t.to_string(), TokenType::CString));
}
col = find_col(text, col_end + 1, |x, _| !x.is_whitespace());
} else {
col_end = find_col(text, col, |x, _| x.is_whitespace());
let t = &text[col..col_end];
if t == "//" {
return tokens;
}
if !t.is_empty() {
tokens.push((col, t.to_string(), TokenType::Word));
}
col = find_col(text, col_end, |x, _| !x.is_whitespace());
}
}
}
tokens
}
pub fn lex(code: &str, file: &str, _args: &Args) -> Vec<Token> {
let lines: Vec<(usize, &str)> = code
.split(['\n', '\r'])
.enumerate()
.collect();
let lines: Vec<(usize, String)> = lines.iter().map(|i| (i.0, i.1.to_string())).collect();
let mut tokens: Vec<Token> = Vec::new();
for (row, line) in lines {
let lt = lex_line(&line);
for (col, tok, tok_type) in lt {
let (tok_type, tok) = lex_word(tok, tok_type);
let t = Token{
file: file.to_string(),
line: row + 1,
col,
text: tok,
typ: tok_type,
value: None,
addr: None,
op_typ: crate::definitions::OpType::Instruction(crate::definitions::InstructionType::None)
};
tokens.push(t);
}
}
// println!("{}", tokens.len());
// for token in tokens.clone() {
// println!("tok: {:?}", token.text);
// }
tokens
}

16
src/loc.c
View File

@ -1,16 +0,0 @@
#include "loc.h"
#include <stdlib.h>
#include <string.h>
// NEEDS to be freed
char* loc_str(loc_t* loc) {
size_t len = ( (20*2) + // 2 max lens of u64 int as strings
strlen(loc->file) + // file path length
2 // 2 colons
);
char* buf = malloc(sizeof(char)*len);
snprintf(buf, len, "%s:%zu:%zu", loc->file, loc->line, loc->col);
return buf;
}

44
src/logger.c
View File

@ -1,44 +0,0 @@
#include <stdarg.h>
#include <stdio.h>
#define _LOG_COLORS
#include "logger.h"
#include "loc.h"
void mcl_log(log_level_t level, const char *fmt, ...) {
va_list args;
va_start(args, fmt);
char* prefix;
switch (level) {
case ERROR: prefix = BRIGHT FG_RED "ERROR" RESET; break;
case WARN: prefix = BRIGHT FG_YELLOW "WARN" RESET; break;
case HELP: prefix = BRIGHT FG_CYAN "HELP" RESET; break;
case INFO: prefix = BRIGHT FG_GREEN "INFO" RESET; break;
case DEBUG: prefix = BRIGHT FG_BLUE "DEBUG" RESET; break;
}
printf("%s: ", prefix);
vprintf(fmt, args);
puts("");
va_end(args);
}
void mcl_log_loc(log_level_t level, loc_t* loc, const char *fmt, ...) {
va_list args;
va_start(args, fmt);
char* prefix;
switch (level) {
case ERROR: prefix = BRIGHT FG_RED "ERROR" RESET; break;
case WARN: prefix = BRIGHT FG_YELLOW "WARN" RESET; break;
case HELP: prefix = BRIGHT FG_CYAN "HELP" RESET; break;
case INFO: prefix = BRIGHT FG_GREEN "INFO" RESET; break;
case DEBUG: prefix = BRIGHT FG_BLUE "DEBUG" RESET; break;
}
printf(BRIGHT"%s"RESET":"BRIGHT"%zu"RESET":"BRIGHT"%zu"RESET": ", loc->file, loc->line, loc->col);
printf("%s: ", prefix);
vprintf(fmt, args);
puts("");
va_end(args);
}

34
src/main.c
View File

@ -1,34 +0,0 @@
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include "cliargs.h"
#include "dyn_arr.h"
#include "token.h"
#include "tokeniser.h"
#include "parser.h"
#include "logger.h"
int main(int argc, char** argv) {
cliargs_t* cliargs = parse_cliargs(argc, argv);
mcl_log(DEBUG, "Output file: %s", cliargs->output);
MCL_DA_FOR_IN(char*, &cliargs->input, file, {
mcl_log(DEBUG, "Input file: %s", file);
tokeniser_t* tokeniser = tokenise(file);
if (!tokeniser) {
mcl_log(ERROR, "Failed to tokenise");
return 1;
}
MCL_DA_FOR_IN(token_t, &tokeniser->tokens, token, {
printf("%s:%zu:%zu: %s\n",
token.loc.file,
token.loc.line,
token.loc.col,
token_to_string(&token));
});
//ast_program_t* prog = parse(&tokeniser->tokens);
});
return 0;
}

127
src/main.rs Normal file
View File

@ -0,0 +1,127 @@
#![allow(clippy::wildcard_imports)]
#![allow(clippy::too_many_lines)]
mod definitions;
mod util;
mod compile;
mod parser;
mod lexer;
mod preprocessor;
mod typechecker;
mod precompiler;
mod config;
mod errors;
pub mod test;
use config::*;
use std::{fs, collections::HashMap};
use clap::Parser;
use anyhow::{Result, bail};
#[derive(Parser, Debug, Clone)]
#[command(author=env!("CARGO_PKG_AUTHORS"), version=env!("CARGO_PKG_VERSION"), about=env!("CARGO_PKG_DESCRIPTION"), long_about=env!("CARGO_PKG_DESCRIPTION"))]
pub struct Args {
/// Input source file
in_file: String,
/// Output compiled file
#[arg(long, short, default_value_t=String::from(DEFAULT_OUT_FILE))]
out_file: String,
/// Interpert
#[arg(long, short='s')]
interpret: bool,
/// Run the compiled executable
#[arg(long, short)]
run: bool,
/// Dont print any output exept the actual running codes output
#[arg(long, short)]
quiet: bool,
/// Add an include directory [default: ["./include", "~/.mclang/include"]]
#[arg(long, short='I')]
include: Vec<String>,
/// Unsafe mode, disables typechecking
#[arg(long="unsafe", default_value_t = false)]
unsaf: bool,
/// Optimisation level, available levels: 'D': debug, '0': No optimisations
#[arg(long, short='O', default_value_t=String::from("0"))]
optimisation: String,
// disables the main function
#[arg(long="lib")]
lib_mode: bool
//#[arg(long, short='F')]
//features: Vec<String>,
}
impl Args {
/// Get optimisation level
/// 0 => no optimisations
/// 1 => slight optimisations, mostly size ones
/// # Errors
///
/// Throws when the opt level is not known
pub fn get_opt_level(&self) -> Result<usize>{
match self.optimisation.as_str() {
"D" | "d" => Ok(0),
"0" | "" => Ok(1),
o => {
error!("Unknown optimisation level {o}");
bail!("")
}
}
}
}
fn main() -> Result<()>{
let args = Args::parse();
let Ok(code) = fs::read_to_string(&args.in_file) else {
error!("Failed to read file {}, exiting!", &args.in_file);
return Ok(());
};
let tokens = lexer::lex(&code, args.in_file.as_str(), &args);
let mut parser = parser::Parser::new(tokens, &args, None);
let program = match parser.parse(){
Ok(t) => t,
Err(e) => {
error!("Parsing failed, exiting!");
if crate::DEV_MODE {
return Err(e)
}
return Ok(());
}
};
match typechecker::typecheck(program.ops.clone(), &args, None, HashMap::new(), HashMap::new()) {
Ok(_) => (),
Err(e) => {
error!("Typechecking failed, exiting!");
if crate::DEV_MODE {
return Err(e);
}
return Ok(());
}
};
let c =match compile::linux_x86_64::compile(&program, &args) {
Ok(c) => c,
Err(e) => {
error!("Compilation failed, exiting!");
println!("{e}");
1
}
};
std::process::exit(c);
}

111
src/parser.c
View File

@ -1,111 +0,0 @@
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "parser.h"
#include "ast.h"
#include "token.h"
#include "tokeniser.h"
#include "errors.h"
#include "dyn_arr.h"
#include "logger.h"
DEFINE_DA_IMPL(ast_node, void*);
DEFINE_DA_IMPL(func_param, ast_func_param_t);
token_t* expect_token(mcl_da_token_t* tks, token_t t);
token_t* try_token(mcl_da_token_t* tks, token_t t);
token_t* expect_token_err(mcl_da_token_t* tks, token_t t);
ast_func_decl_t* parse_func(mcl_da_token_t* tokens, ast_ident_t name);
ast_program_t* parse(mcl_da_token_t* tokens) {
ast_program_t* prog = malloc(sizeof(ast_program_t));
assert(prog && "Out of mem");
token_t* tok = NULL;
while ((tok=mcl_da_token_pop_front(tokens)) != NULL) {
switch(tok->type) {
case TT_IDENT: {
// printf("IDENT: %s\n", tok->text);
if (!expect_token_err(tokens, (token_t){.type=TT_COLON })) return NULL;
if (!expect_token_err(tokens, (token_t){.type=TT_COLON })) return NULL;
token_t* type = mcl_da_token_pop_front(tokens);
if (type->type == TT_KW_FN) {
ast_ident_t name = {
.name = tok->text,
.loc = tok->loc
};
mcl_da_ast_node_push(&prog->body, parse_func(tokens, name));
} else if (type->type == TT_KW_STRUCT) {
} else if (type->type == TT_KW_ENUM) {
}
return NULL;
} break;
}
// mcl_da_ast_node_push(prog->body, );
}
return prog;
}
ast_func_decl_t* parse_func(mcl_da_token_t* tokens, ast_ident_t name) {
ast_func_decl_t* func = malloc(sizeof(ast_func_decl_t));
// parse args
if (!expect_token_err(tokens, (token_t){.type=TT_PAREN_L})) return NULL;
while (!try_token(tokens, (token_t){.type=TT_PAREN_R})) {
// Name
token_t* arg_name = expect_token_err(tokens,(token_t){.type=TT_IDENT});
if (!arg_name) return NULL;
if (!expect_token_err(tokens, (token_t){.type=TT_COLON})) return NULL;
// Type
token_t* type = expect_token_err(tokens, (token_t){.type=TT_IDENT});
if (!type) return NULL;
ast_func_param_t param = {
.name = { .name = arg_name->text, .loc = arg_name->loc },
.type = { .name = { .name = type->text, .loc = type->loc}, .inner=NULL},
};
mcl_da_func_param_push(&func->params, param);
if (!try_token(tokens, (token_t){.type=TT_COMMA})) {
if (!expect_token_err(tokens, (token_t){.type=TT_PAREN_R})) return NULL;
}
}
// parse body
return func;
}
token_t* expect_token(mcl_da_token_t* tks, token_t t) {
token_t* _tok_ = mcl_da_token_pop_front(tks);
if (_tok_->type != t.type) {
return NULL;
}
return _tok_;
}
token_t* try_token(mcl_da_token_t* tks, token_t t) {
token_t* _tok_ = mcl_da_token_peek_front(tks);
if (_tok_->type != t.type) {
return NULL;
}
return _tok_;
}
token_t* expect_token_err(mcl_da_token_t* tks, token_t t) {
token_t* _tok_ = mcl_da_token_pop_front(tks);
if (_tok_->type != t.type) {
mcl_log(ERROR, "Expected %s", token_to_string(&t));
mcl_log_loc(INFO, &_tok_->loc, "Got %s", token_to_string(_tok_));
return NULL;
}
return _tok_;
}

229
src/parser.rs Normal file
View File

@ -0,0 +1,229 @@
use std::ops::Deref;
use crate::{definitions::{Operator, OpType, Token, TokenType, Loc, KeywordType, InstructionType, InternalType, Program}, lerror, preprocessor::Preprocessor, Args};
use anyhow::{Result, bail};
pub fn cross_ref(mut program: Vec<Operator>) -> Result<Vec<Operator>> {
let mut stack: Vec<usize> = Vec::new();
for ip in 0..program.len() {
let op = &program.clone()[ip];
// println!("{op:?}");
match op.typ {
// OpType::Keyword(KeywordType::FunctionDef) |
OpType::Keyword(KeywordType::If | KeywordType::While) => {
stack.push(ip);
}
OpType::Keyword(KeywordType::Else) => {
let Some(if_ip) = stack.pop() else {
lerror!(&op.loc, "Unclosed-if else block");
bail!("Cross referencing")
};
if program[if_ip].typ != OpType::Keyword(KeywordType::If) {
lerror!(&op.clone().loc,"'else' can only close 'if' blocks");
bail!("Bad block")
}
program[if_ip].jmp = ip + 1;
stack.push(ip);
},
OpType::Keyword(KeywordType::End) => {
let Some(block_ip) = stack.pop() else {
lerror!(&op.loc, "Unclosed if, if-else, while-do, function, memory, or constant");
bail!("Cross referencing")
};
match &program[block_ip].typ {
OpType::Keyword(KeywordType::If | KeywordType::Else) => {
program[block_ip].jmp = ip;
program[ip].jmp = ip + 1;
}
OpType::Keyword(KeywordType::Do) => {
program[ip].jmp = program[block_ip].jmp;
program[block_ip].jmp = ip + 1;
}
OpType::Keyword(KeywordType::Memory | KeywordType::Constant) => (),
a => {
println!("{a:?}");
lerror!(&op.clone().loc,"'end' can only close if, if-else, while-do, function, memory, or constant blocks");
bail!("")
}
}
}
OpType::Keyword(KeywordType::Do) => {
let Some(block_ip) = stack.pop() else {
lerror!(&op.loc, "Unclosed while-do block");
bail!("Cross referencing")
};
program[ip].jmp = block_ip;
stack.push(ip);
}
_ => ()
}
}
if !stack.is_empty() {
// println!("{:?}", stack);
let i = stack.pop().expect("Empy stack");
lerror!(&program[i].clone().loc,"Unclosed block, {:?}", program[i].clone());
bail!("Unclosed block")
}
Ok(program.clone())
}
pub struct Parser<'a> {
tokens: Vec<Token>,
pub preprocessor: Preprocessor<'a>,
#[allow(dead_code)]
args: &'a Args
}
impl<'a> Parser<'a> {
pub fn new(file: Vec<Token>, args: &'a Args, p: Option<Preprocessor<'a>>) -> Self {
let pre = if let Some(p) = p {p} else {
Preprocessor::new(Vec::new(), args)
};
Self{
tokens: file,
preprocessor: pre,
args
}
}
pub fn parse(&mut self) -> Result<Program> {
let mut tokens = Vec::new();
for token in &self.tokens {
if token.text.is_empty() {
continue;
}
let pos = (token.file.clone(), token.line, token.col);
match token.typ {
TokenType::Word => {
let word_type = if token.op_typ == OpType::Instruction(InstructionType::MemUse) {
OpType::Instruction(InstructionType::MemUse)
} else {
lookup_word(&token.text, &pos)
};
tokens.push(Operator::new(word_type, token.typ, token.value.unwrap_or(0), token.text.clone(), token.file.clone(), token.line, token.col).set_addr(token.addr.unwrap_or(0)));
},
TokenType::Int => {// negative numbers not yet implemented
tokens.push(Operator::new(OpType::Instruction(InstructionType::PushInt), token.typ, token.text.parse::<usize>()?, String::new(), token.file.clone(), token.line, token.col));
},
TokenType::String => {
tokens.push(Operator::new(OpType::Instruction(InstructionType::PushStr), token.typ, 0, token.text.clone(), token.file.clone(), token.line, token.col));
},
TokenType::CString => {
tokens.push(Operator::new(OpType::Instruction(InstructionType::PushCStr), token.typ, 0, token.text.clone(), token.file.clone(), token.line, token.col));
},
TokenType::Char => {
let c = token.text.clone();
if c.len() != 1 {
lerror!(&token.loc(), "Chars can only be of lenght 1, got {}", c.len());
bail!("")
}
tokens.push(Operator::new(OpType::Instruction(InstructionType::PushInt), token.typ, token.text.chars().next().unwrap() as usize, String::new(), token.file.clone(), token.line, token.col));
}
};
}
self.preprocessor.program.ops = tokens;
let mut t = self.preprocessor.preprocess()?.get_program();
t.ops = cross_ref(t.ops)?;
Ok(t)
}
}
pub fn lookup_word<P: Deref<Target = Loc>>(s: &str, _pos: P) -> OpType {
let n = s.parse::<usize>();
if n.is_ok() {
return OpType::Instruction(InstructionType::PushInt);
}
match s {
//stack
"_dbg_print" => OpType::Instruction(InstructionType::Print),
"dup" => OpType::Instruction(InstructionType::Dup),
"drop" => OpType::Instruction(InstructionType::Drop),
"rot" => OpType::Instruction(InstructionType::Rot),
"over" => OpType::Instruction(InstructionType::Over),
"swap" => OpType::Instruction(InstructionType::Swap),
// comp and math
"+" => OpType::Instruction(InstructionType::Plus),
"-" => OpType::Instruction(InstructionType::Minus),
"=" => OpType::Instruction(InstructionType::Equals),
"!=" => OpType::Instruction(InstructionType::NotEquals),
">" => OpType::Instruction(InstructionType::Gt),
"<" => OpType::Instruction(InstructionType::Lt),
">=" => OpType::Instruction(InstructionType::Ge),
"<=" => OpType::Instruction(InstructionType::Le),
"band" => OpType::Instruction(InstructionType::Band),
"bor" => OpType::Instruction(InstructionType::Bor),
"shr" => OpType::Instruction(InstructionType::Shr),
"shl" => OpType::Instruction(InstructionType::Shl),
"divmod" => OpType::Instruction(InstructionType::DivMod),
"*" => OpType::Instruction(InstructionType::Mul),
// mem
"read8" => OpType::Instruction(InstructionType::Read8),
"write8" => OpType::Instruction(InstructionType::Write8),
"read32" => OpType::Instruction(InstructionType::Read32),
"write32" => OpType::Instruction(InstructionType::Write32),
"read64" => OpType::Instruction(InstructionType::Read64),
"write64" => OpType::Instruction(InstructionType::Write64),
"syscall0" => OpType::Instruction(InstructionType::Syscall0),
"syscall1" => OpType::Instruction(InstructionType::Syscall1),
"syscall2" => OpType::Instruction(InstructionType::Syscall2),
"syscall3" => OpType::Instruction(InstructionType::Syscall3),
"syscall4" => OpType::Instruction(InstructionType::Syscall4),
"syscall5" => OpType::Instruction(InstructionType::Syscall5),
"syscall6" => OpType::Instruction(InstructionType::Syscall6),
"cast(bool)" => OpType::Instruction(InstructionType::CastBool),
"cast(ptr)" => OpType::Instruction(InstructionType::CastPtr),
"cast(int)" => OpType::Instruction(InstructionType::CastInt),
"cast(void)" => OpType::Instruction(InstructionType::CastVoid),
// block
"if" => OpType::Keyword(KeywordType::If),
"else" => OpType::Keyword(KeywordType::Else),
"end" => OpType::Keyword(KeywordType::End),
"while" => OpType::Keyword(KeywordType::While),
"do" => OpType::Keyword(KeywordType::Do),
"include" => OpType::Keyword(KeywordType::Include),
"memory" => OpType::Keyword(KeywordType::Memory),
"const" => OpType::Keyword(KeywordType::Constant),
"fn" => OpType::Keyword(KeywordType::Function),
"then" => OpType::Keyword(KeywordType::FunctionThen),
"done" => OpType::Keyword(KeywordType::FunctionDone),
"inline" => OpType::Keyword(KeywordType::Inline),
"export" => OpType::Keyword(KeywordType::Export),
"struct" => OpType::Keyword(KeywordType::Struct),
"return" => OpType::Instruction(InstructionType::Return),
"returns" => OpType::Instruction(InstructionType::Returns),
"bool" => OpType::Instruction(InstructionType::TypeBool),
"int" => OpType::Instruction(InstructionType::TypeInt),
"ptr" => OpType::Instruction(InstructionType::TypePtr),
"void" => OpType::Instruction(InstructionType::TypeVoid),
"any" => OpType::Instruction(InstructionType::TypeAny),
"with" => OpType::Instruction(InstructionType::With),
"->" => OpType::Internal(InternalType::Arrow),
_ => OpType::Instruction(InstructionType::None)
}
}

147
src/precompiler.rs Normal file
View File

@ -0,0 +1,147 @@
use anyhow::{Result, bail};
use crate::{definitions::{ OpType, InstructionType, Loc, Operator}, lerror};
fn stack_pop(stack: &mut Vec<usize>, loc: &Loc) -> Result<usize> {
if let Some(i) = stack.pop() { Ok(i) } else {
lerror!(&loc.clone(), "Stack underflow");
bail!("Stack underflow")
}
}
pub fn precompile(tokens: &Vec<Operator>) -> Result<Vec<usize>>{
let mut stack: Vec<usize> = Vec::new();
for token in tokens.iter() {
match token.typ.clone() {
OpType::Instruction(i) => {
let loc = token.loc.clone();
match i {
InstructionType::PushInt => {
stack.push(token.value);
},
InstructionType::Plus => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b + a);
},
InstructionType::Minus => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b - a);
},
InstructionType::Equals => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b == a));
},
InstructionType::Gt => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b > a));
},
InstructionType::Lt => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b < a));
},
InstructionType::NotEquals => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b != a));
},
InstructionType::Ge => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b >= a));
},
InstructionType::Le => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(usize::from(b <= a));
},
InstructionType::Band => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(a & b);
}
InstructionType::Bor => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(a | b);
}
InstructionType::Shr => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b >> a);
}
InstructionType::Shl => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b << a);
}
InstructionType::DivMod => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b / a);
stack.push(b % a);
}
InstructionType::Mul => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b * a);
}
InstructionType::Drop => {
stack.pop();
},
InstructionType::Dup => {
let a = stack_pop(&mut stack, &loc)?;
stack.push(a);
stack.push(a);
},
InstructionType::Rot => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
let c = stack_pop(&mut stack, &loc)?;
stack.push(b);
stack.push(a);
stack.push(c);
}
InstructionType::Swap => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(a);
stack.push(b);
}
InstructionType::Over => {
let a = stack_pop(&mut stack, &loc)?;
let b = stack_pop(&mut stack, &loc)?;
stack.push(b);
stack.push(a);
stack.push(b);
}
_ => {
lerror!(&token.loc, "Unsupported precompiler instruction {:?}", i);
dbg!(tokens);
bail!("");
}
}
}
OpType::Keyword(_) => {
lerror!(&token.loc, "Unsupported precompiler keyword {:?}", token.typ);
dbg!(tokens);
bail!("");
}
OpType::Internal(t) => panic!("{t:?}"),
}
}
Ok(stack)
}

754
src/preprocessor.rs Normal file
View File

@ -0,0 +1,754 @@
use std::collections::HashMap;
use std::path::{PathBuf, Path};
use anyhow::{Result, bail};
use crate::definitions::*;
use crate::lexer::lex;
use crate::precompiler::precompile;
use crate::{lerror, Args, warn, linfo, parser};
use crate::parser::lookup_word;
#[derive(Debug, Clone)]
pub struct Preprocessor<'a> {
pub program: Program,
in_function: Option<String>,
args: &'a Args,
f_inline: bool,
f_export: bool,
}
impl<'a> Preprocessor<'a> {
pub fn new(prog: Vec<Operator>, args: &'a Args) -> Self {
Self {
args,
program: Program {
ops: prog,
functions: HashMap::new(),
memories: HashMap::new(),
constants: HashMap::new(),
struct_defs: HashMap::new(),
struct_allocs: HashMap::new()
},
in_function: None,
f_inline: false,
f_export: false,
}
}
pub fn preprocess(&mut self) -> Result<&mut Preprocessor<'a>>{
// println!("pre: has do tokens: {:?}", self.program.iter().map(|t| if t.typ == OpType::Keyword(KeywordType::Do) {Some(t)} else {None} ).collect::<Vec<Option<&Operator>>>());
let mut program: Vec<Operator> = Vec::new();
let mut rtokens = self.program.ops.clone();
rtokens.reverse();
while !rtokens.is_empty() {
let mut op = rtokens.pop().unwrap();
// println!("{token:?}");
let op_type = op.typ.clone();
match op_type {
OpType::Keyword(KeywordType::Include) => self.handle_include(&mut rtokens, &mut op)?,
OpType::Keyword(KeywordType::Memory) => self.handle_memory(&mut rtokens, &mut op, &mut program)?,
OpType::Keyword(KeywordType::Function) => self.handle_function(&mut rtokens, &mut op, &mut program)?,
OpType::Keyword(KeywordType::Constant) => self.handle_constant(&mut rtokens, &mut op, &mut program)?,
OpType::Keyword(KeywordType::Struct) => self.handle_struct(&mut rtokens, &mut op, &mut program)?,
OpType::Keyword(KeywordType::Inline) => {
if self.f_export {
lerror!(&op.loc, "Function is already marked as exported, function cannot be inline and exported at the same time");
bail!("");
} else if self.f_inline {
lerror!(&op.loc, "Function is already marked as inline, remove this inline Keyword");
bail!("");
} else {
self.f_inline = true;
}
}
OpType::Keyword(KeywordType::Export) => {
if !crate::config::ENABLE_EXPORTED_FUNCTIONS {
lerror!(&op.loc, "Experimental feature Exported functions not enabled");
bail!("");
}
if self.f_inline {
lerror!(&op.loc, "Function is already marked as inline, function cannot be inline and exported at the same time");
bail!("");
} else if self.f_export {
lerror!(&op.loc, "Function is already marked as extern, remove this extern Keyword");
bail!("");
} else {
self.f_export = true;
}
}
_ => {
program.push(op);
}
}
}
self.program.ops = program;
// println!("has do tokens: {:?}", self.program.iter().map(|t| if t.typ == OpType::Keyword(KeywordType::Do) {Some(t)} else {None} ).collect::<Vec<Option<&Operator>>>());
//* Feel free to fix this horrifying shit
//* i wanna kms
let mut times = 0;
// dbg!(program.clone());
while self.program.ops.iter().map(|f| {
if f.tok_typ == TokenType::Word {
match f.typ {
OpType::Instruction(InstructionType::FnCall) |
OpType::Instruction(InstructionType::MemUse) |
OpType::Instruction(InstructionType::StructUse) |
OpType::Keyword(KeywordType::FunctionDef) |
OpType::Keyword(KeywordType::FunctionDefExported)|
OpType::Keyword(KeywordType::ConstantDef) |
OpType::Internal(InternalType::StructAlloc{..}) |
OpType::Instruction(InstructionType::ConstUse) => OpType::Instruction(InstructionType::PushInt),
_ => {
lookup_word(&f.text, &f.loc)
}
}
} else {
OpType::Instruction(InstructionType::PushInt) // i hate myself, this is a randomly picked optype so its happy and works
}
}).collect::<Vec<OpType>>().contains(&OpType::Instruction(InstructionType::None)){
if times >= 50 {
warn!("File import depth maxed out, if the program crashes try reducing the import depth, good luck youll need it");
break
}
self.expand()?;
times += 1;
}
Ok(self)
}
fn handle_include(&mut self, rtokens: &mut Vec<Operator>, op: &mut Operator) -> Result<()> {
if rtokens.is_empty() {
lerror!(&op.loc, "Include path not found, expected {} but found nothing", TokenType::String.human());
bail!("");
}
let include_path = rtokens.pop().unwrap();
if include_path.tok_typ != TokenType::String {
lerror!(&include_path.loc, "Bad include path, expected {} but found {}", TokenType::String.human(), include_path.typ.human());
bail!("");
}
let mut in_paths = self.args.include.clone();
in_paths.append(&mut crate::DEFAULT_INCLUDES.to_vec().clone().iter().map(|f| (*f).to_string()).collect::<Vec<String>>());
let mut include_code = String::new();
let mut pth = PathBuf::new();
if include_path.text.chars().next().unwrap() == '.' {
let p = Path::new(include_path.loc.0.as_str());
let p = p.parent().unwrap();
let p = p.join(&include_path.text);
pth = p.clone();
include_code = std::fs::read_to_string(p)?;
} else {
for path in in_paths {
let p = PathBuf::from(path);
let p = p.join(&include_path.text);
pth = p.clone();
if p.exists() {
include_code = std::fs::read_to_string(p)?;
break;
}
}
}
if include_code.is_empty() {
lerror!(&include_path.loc, "Include file in path '{}' was not found or is empty", include_path.text);
bail!("");
}
let a = pth.to_str().unwrap().to_string();
let code = lex(&include_code, a.as_str(), self.args);
let mut p = parser::Parser::new(code, self.args, Some(self.clone()));
let mut code = p.parse()?;
self.set_constants(p.preprocessor.get_constants());
self.set_functions(p.preprocessor.get_functions());
self.set_memories(p.preprocessor.get_memories());
code.ops.reverse();
rtokens.append(&mut code.ops);
Ok(())
}
fn handle_memory(&mut self, rtokens: &mut Vec<Operator>, op: &mut Operator, program: &mut Vec<Operator>) -> Result<()> {
if rtokens.is_empty() {
lerror!(&op.loc, "Memory name not found, expected {} but found nothing", TokenType::String.human());
bail!("");
}
let name = rtokens.pop().unwrap();
self.is_word_available(&name, KeywordType::Memory)?;
let mut code: Vec<Operator> = Vec::new();
let mut depth = 0;
while !rtokens.is_empty() {
let t = rtokens.pop().unwrap();
let typ = t.typ.clone();
if typ == OpType::Keyword(KeywordType::End) && depth == 0 {
break;
} else if typ == OpType::Keyword(KeywordType::End) && depth != 0 {
depth -= 1;
code.push(t);
} else if typ == OpType::Keyword(KeywordType::If) || typ == OpType::Keyword(KeywordType::Do) {
code.push(t);
depth += 1;
} else {
code.push(t);
}
}
let res = precompile(&code)?;
if res.len() != 1 {
lerror!(&op.loc, "Expected 1 number, got {:?}", res);
bail!("");
}
op.value = res[0];
op.addr = Some(self.program.memories.len());
program.push(op.clone());
self.program.memories.insert(name.text, Memory { loc: op.loc.clone(), id: self.program.memories.len() });
Ok(())
}
fn handle_function(&mut self, rtokens: &mut Vec<Operator>, op: &mut Operator, program: &mut Vec<Operator>) -> Result<()> {
if rtokens.is_empty() {
lerror!(&op.loc, "Function name not found, expected {} but found nothing", TokenType::Word.human());
bail!("");
}
let mut name = rtokens.pop().unwrap();
if let '0'..='9' = name.text.chars().next().unwrap() {
lerror!(&name.loc, "Function name starts with a number which is not allowed");
bail!("");
}
// let mut should_warn = false;
for c in name.text.clone().chars() {
match c {
'a'..='z' |
'A'..='Z' |
'0'..='9' |
'-' | '_' => (),
'(' | ')' => {
name.text = name.text.clone().replace('(', "__OP_PAREN__").replace(')', "__CL_PAREN__");
}
_ => {
lerror!(&name.loc, "Function name contains '{c}', which is unsupported");
bail!("");
}
}
}
// if should_warn {
//TODO: add -W option in cli args to enable more warnings
//lwarn!(&function_name.loc, "Function name contains '(' or ')', this character is not supported but will be replaced with '__OP_PAREN__' or '__CL_PAREN__' respectively ");
// }
self.is_word_available(&name, KeywordType::Function)?;
if self.f_inline {
self.f_inline = false;
let mut prog: Vec<Operator> = Vec::new();
let mut depth = -1;
while !rtokens.is_empty() {
let op = rtokens.pop().unwrap();
match op.typ.clone() {
OpType::Instruction(i) => {
match i {
InstructionType::TypeAny |
InstructionType::TypeBool |
InstructionType::TypeInt |
InstructionType::TypePtr |
InstructionType::With |
InstructionType::Returns |
InstructionType::TypeVoid => {
if depth >= 0 {
prog.push(op);
}
},
_ => prog.push(op)
}
}
OpType::Keyword(k) => {
match k {
KeywordType::Inline |
KeywordType::Include => {
todo!("make error")
},
KeywordType::FunctionThen => {
if depth >= 0 {
prog.push(op);
}
depth += 1;
},
KeywordType::FunctionDone => {
if depth == 0 {
break;
}
depth -= 1;
},
_ => prog.push(op)
}
}
_ => prog.push(op)
}
}
let mut pre = self.clone();
pre.program.ops = prog;
if name.text.chars().next().unwrap() == '.' {
pre.in_function = Some(name.text[1..].to_string());
}
pre.preprocess()?;
prog = pre.get_ops();
self.program.functions.insert(name.text.clone(), Function{
loc: name.loc.clone(),
name: name.text.clone(),
inline: true,
tokens: Some(prog)
});
} else if self.f_export {
self.f_export = false;
self.program.functions.insert(name.text.clone(), Function{
loc: name.loc.clone(),
name: name.text.clone(),
inline: false,
tokens: None
});
let mut a: Vec<Operator> = Vec::new();
let mut fn_def = op.clone();
a.push(rtokens.pop().unwrap());
let mut ret = false;
while !rtokens.is_empty() {
let op = rtokens.pop().unwrap();
// println!("{:?}",op);
a.push(op.clone());
if op.typ == OpType::Instruction(InstructionType::Returns) {
ret = true;
}
if op.typ == OpType::Keyword(KeywordType::FunctionThen) {
break;
}
if op.typ == OpType::Instruction(InstructionType::TypeBool) ||
op.typ == OpType::Instruction(InstructionType::TypeInt) ||
op.typ == OpType::Instruction(InstructionType::TypePtr) {
if ret {
fn_def.types.1 += 1;
} else {
fn_def.types.0 += 1;
}
}
}
fn_def.typ = OpType::Keyword(KeywordType::FunctionDefExported);
fn_def.text = name.text;
// fn_def.set_types(args, rets);
// println!("{:?}", fn_def.types);
program.push(fn_def);
program.append(&mut a);
} else {
self.program.functions.insert(name.text.clone(), Function{
loc: name.loc.clone(),
name: name.text.clone(),
inline: false,
tokens: None
});
let mut fn_def = op.clone();
fn_def.typ = OpType::Keyword(KeywordType::FunctionDef);
fn_def.text = name.text;
// println!("{:?}", token);
program.push(fn_def);
}
Ok(())
}
fn handle_constant(&mut self, rtokens: &mut Vec<Operator>, op: &mut Operator, program: &mut Vec<Operator>) -> Result<()> {
let Some(mut name) = rtokens.pop() else {
lerror!(&op.loc, "Constant name not found, expected {} but found nothing", TokenType::Word.human());
bail!("");
};
if let '0'..='9' | '.' = name.text.chars().next().unwrap() {
lerror!(&name.loc, "Constant name starts with a number or dot which is not allowed");
bail!("");
}
for c in name.text.clone().chars() {
match c {
'a'..='z' |
'A'..='Z' |
'0'..='9' |
'-' | '_' => (),
'(' | ')' => {
// should_warn = true;
name.text = name.text.clone().replace('(', "__OP_PAREN__").replace(')', "__CL_PAREN__");
}
_ => {
lerror!(&name.loc, "Constant name contains '{c}', which is unsupported");
bail!("");
}
}
}
// if should_warn {
//TODO: add -W option in cli args to enable more warnings
//lwarn!(&name.loc, "Constant name contains '(' or ')', this character is not supported but will be replaced with '__OP_PAREN__' or '__CL_PAREN__' respectively ");
// }
self.is_word_available(&name, KeywordType::Constant)?;
self.program.constants.insert(name.text.clone(), Constant{
loc: name.loc.clone(),
name: name.text.clone(),
});
// println!("{:?}", self.program.constants);
let mut const_def = op.clone();
const_def.typ = OpType::Keyword(KeywordType::ConstantDef);
const_def.text = name.text;
let item = rtokens.pop().unwrap();
if item.tok_typ == TokenType::Int {
const_def.value = item.value;
} else {
lerror!(&op.loc, "For now only {:?} is allowed in constants", TokenType::Int);
bail!("");
}
let posibly_end = rtokens.pop();
// println!("end: {posibly_end:?}");
if posibly_end.is_none() || posibly_end.unwrap().typ != OpType::Keyword(KeywordType::End) {
lerror!(&op.loc, "Constant was not closed with an 'end' instruction, expected 'end' but found nothing");
bail!("");
}
// token.value =
program.push(const_def);
Ok(())
}
fn handle_struct(&mut self, rtokens: &mut Vec<Operator>, op: &mut Operator, program: &mut Vec<Operator>) -> Result<()> {
let Some(name) = rtokens.pop() else {
lerror!(&op.loc, "Struct name not found, expected {} but found nothing", TokenType::Word.human());
bail!("");
};
if let '0'..='9' | '.' = name.text.chars().next().unwrap() {
lerror!(&name.loc, "Struct name starts with a number or dot which is not allowed");
bail!("");
}
self.is_word_available(&name, KeywordType::Struct)?;
if let Some(kw_do) = rtokens.pop() {
if kw_do.typ != OpType::Keyword(KeywordType::Do) {
lerror!(&name.loc, "Expected keyword 'do' but found {:?}", kw_do.typ);
bail!("");
}
} else {
lerror!(&name.loc, "Expected keyword 'do' but found nothing");
bail!("");
}
let mut structure = StructDef{
loc: name.loc,
name: name.text,
fields: vec![],
};
loop {
let fl_name = rtokens.pop().unwrap();
if fl_name.typ == OpType::Keyword(KeywordType::End) {
break;
}
if let '0'..='9' = fl_name.text.chars().next().unwrap() {
lerror!(&fl_name.loc, "Struct field name starts with a number which is not allowed");
bail!("");
}
// let mut should_warn = false;
for c in fl_name.text.clone().chars() {
match c {
'a'..='z' |
'A'..='Z' |
'0'..='9' |
'_' => (),
_ => {
lerror!(&fl_name.loc, "Struct field name contains '{c}', which is unsupported");
bail!("");
}
}
}
if let Some(arrow) = rtokens.pop() {
if arrow.typ != OpType::Internal(InternalType::Arrow) {
lerror!(&arrow.loc, "Expected '->' but found {:?}", arrow.typ);
bail!("");
}
} else {
lerror!(&fl_name.loc, "Expected '->' but found nothing");
bail!("");
}
let Some(typ) = rtokens.pop() else {
lerror!(&fl_name.loc, "Expected a type but found nothing");
bail!("");
};
let Ok(typ) = Types::from_string(&typ.text) else {
lerror!(&typ.loc, "Expected a type but found {:?}", typ.text);
bail!("");
};
structure.fields.push((fl_name.text, typ));
}
self.program.struct_defs.insert(structure.name.clone(), structure.clone());
if let Some(def_name) = rtokens.pop() {
if def_name.typ == OpType::Instruction(InstructionType::None){
let mut def = def_name.clone();
def.typ = OpType::Internal(InternalType::StructAlloc {
name: structure.name.clone()
});
self.program.struct_allocs.insert(def_name.text, structure.name);
program.push(def);
} else {
rtokens.push(def_name);
}
}
Ok(())
}
pub fn expand(&mut self) -> Result<()> {
let mut program: Vec<Operator> = Vec::new();
// println!("{:?}", self.program.functions);
let mut rtokens = self.program.ops.clone();
rtokens.reverse();
'main_loop: while !rtokens.is_empty() {
let op = rtokens.pop().unwrap();
let op_type = op.typ.clone();
if op.tok_typ == TokenType::Word {
match op_type {
OpType::Instruction(InstructionType::None) => {
let m = self.program.functions.get(&op.text.clone().replace('(', "__OP_PAREN__").replace(')', "__CL_PAREN__"));
let mem = self.program.memories.get(&op.text);
let cons = self.program.constants.get(&op.text.clone().replace('(', "__OP_PAREN__").replace(')', "__CL_PAREN__"));
if let Some(m) = m {
if m.inline {
program.append(&mut m.tokens.clone().unwrap());
} else {
let mut t = op.clone();
t.typ = OpType::Instruction(InstructionType::FnCall);
t.text = m.name.clone();
program.push(t.clone());
}
// println!("##### {:?}", t);
} else if let Some(mem) = mem {
let mut t = op.clone();
t.addr = Some(mem.id);
t.typ = OpType::Instruction(InstructionType::MemUse);
program.push(t);
} else if let Some(cons) = cons {
let mut t = op.clone();
t.text = cons.name.clone();
t.typ = OpType::Instruction(InstructionType::ConstUse);
program.push(t);
} else {
let mut t = op.clone();
let parts = op.text.split('.').map(|f| f.to_string()).collect::<Vec<String>>();
let alc = self.program.struct_allocs.get(&parts[0]);
if let Some(alc) = alc {
if let Some(def) = self.program.struct_defs.get(alc) {
// if def.fields.iter().for_each(|f| f.0 == parts[1])
println!("{:?}", def.fields);
if def.fields.iter().find(|f| f.0 == parts[1]).is_some() || parts.len() < 2{
t.typ = OpType::Instruction(InstructionType::StructUse);
program.push(t);
continue 'main_loop;
}
}
}
lerror!(&op.loc, "Preprocess: Unknown word '{}'", op.text.clone());
bail!("");
}
}
_ => {
program.push(op.clone());
}
}
} else {
program.push(op.clone());
}
// if op.typ == OpType::Keyword(KeywordType::Do) {
// println!("expand: {:?}", op);
// program.push(op.clone());
// }
}
// println!("expand: has do tokens: {:?}", program.iter().map(|t| if t.typ == OpType::Keyword(KeywordType::Do) {Some(t)} else {None} ).collect::<Vec<Option<&Operator>>>());
self.program.ops = program;
// println!("{:#?}", self.program);
// println!("{:?}", self.program.last().unwrap());
Ok(())
}
pub fn get_ops(&mut self) -> Vec<Operator> {
self.program.ops.clone()
}
pub fn is_word_available(&self, word: &Operator, typ: KeywordType) -> Result<bool> {
match typ {
KeywordType::Memory |
KeywordType::Constant |
KeywordType::Struct |
KeywordType::Function => (),
_ => panic!()
}
if word.tok_typ != TokenType::Word {
lerror!(&word.loc, "Bad {typ:?}, expected {} but found {}", TokenType::Word.human(), word.typ.human());
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
let w = lookup_word(&word.text, &word.loc);
if w != OpType::Instruction(InstructionType::None) {
lerror!(&word.loc, "Bad {typ:?}, {typ:?} definition cannot be builtin word, got {:?}", word.text);
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
let m = self.program.memories.get(&word.text);
if let Some(m) = m {
if typ == KeywordType::Memory {
lerror!(&word.loc, "Memories cannot be redefined, got {}", word.text);
linfo!(&m.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
lerror!(&word.loc, "{typ:?} cannot replace memory, got {}", word.text);
linfo!(&m.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
let f = self.program.functions.get(&word.text);
if let Some(f) = f {
if typ == KeywordType::Function {
lerror!(&word.loc, "Functions cannot be redefined, got {}", word.text);
linfo!(&f.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
lerror!(&word.loc, "{typ:?} cannot replace function, got {}", word.text);
linfo!(&f.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
let c = self.program.constants.get(&word.text);
if let Some(c) = c {
if typ == KeywordType::Constant {
lerror!(&word.loc, "Constants cannot be redefined, got {}", word.text);
linfo!(&c.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
lerror!(&word.loc, "{typ:?} cannot replace constant, got {}", word.text);
linfo!(&c.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
let s = self.program.struct_defs.get(&word.text);
if let Some(s) = s {
if typ == KeywordType::Constant {
lerror!(&word.loc, "Structs cannot be redefined, got {}", word.text);
linfo!(&s.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
lerror!(&word.loc, "{typ:?} cannot replace struct, got {}", word.text);
linfo!(&s.loc, "first definition here");
if crate::DEV_MODE {println!("{word:?}")}
bail!("");
}
Ok(true)
}
pub fn set_functions(&mut self, f: Functions) {
self.program.functions = f;
}
pub fn set_constants(&mut self, f: Constants) {
self.program.constants = f;
}
pub fn set_memories(&mut self, f: Memories) {
self.program.memories = f;
}
pub fn get_functions(&mut self) -> Functions {
self.program.functions.clone()
}
pub fn get_constants(&mut self) -> Constants {
self.program.constants.clone()
}
pub fn get_memories(&mut self) -> Memories{
self.program.memories.clone()
}
pub fn get_program(&mut self) -> Program {
self.program.clone()
}
}

125
src/token.c
View File

@ -1,125 +0,0 @@
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include "token.h"
char* escape_str(char* str);
char* token_to_string(token_t* t) {
char* buf = {0};
int len = 0;
switch(t->type) {
case TT_IDENT:
// printf("IDENT\n");
len = strlen(t->text)+10;
buf = malloc(len);
snprintf(buf, len, "IDENT(\"%s\")", escape_str(t->text));
return buf;
case TT_STR:
// printf("STR\n");
len = strlen(t->text)+10;
buf = malloc(len);
snprintf(buf, len, "STR(\"%s\")", t->text);
buf = escape_str(t->text);
return buf;
case TT_CHR:
// printf("CHR\n");
buf = malloc(10);
snprintf(buf, 10, "CHAR('%c')", *t->text);
return buf;
case TT_CURLY_R:
return "}";
case TT_CURLY_L:
return "{";
case TT_BRACK_R:
return "]";
case TT_BRACK_L:
return "[";
case TT_PAREN_R:
return ")";
case TT_PAREN_L:
return "(";
case TT_COLON:
return ":";
case TT_SEMI:
return ";";
case TT_COMMA:
return ",";
case TT_DOT:
return ".";
case TT_AMP:
return "&";
case TT_STAR:
return "*";
case TT_PLUS:
return "+";
case TT_DASH:
return "-";
case TT_FSLASH:
return "/";
case TT_BAR:
return "|";
case TT_EQ:
return "=";
case TT_LT:
return "<";
case TT_GT:
return ">";
case TT_KW_FN:
return "KEYWORD(fn)";
case TT_KW_RETURN:
return "KEYWORD(return)";
case TT_KW_IF:
return "KEYWORD(if)";
case TT_KW_ELSE:
return "KEYWORD(else)";
case TT_KW_FOR:
return "KEYWORD(for)";
case TT_KW_WHILE:
return "KEYWORD(while)";
case TT_KW_STRUCT:
return "KEYWORD(struct)";
case TT_KW_ENUM:
return "KEYWORD(enum)";
case TT_KW_BREAK:
return "KEYWORD(break)";
case TT_KW_CONTINUE:
return "KEYWORD(continue)";
}
}
char* escape_str(char* str) {
// First, determine the length of the new string
size_t new_length = 0;
for (const char* p = str; *p != '\0'; ++p) {
if (*p == '\n' || *p == '\r') {
new_length += 2; // Each '\n' or '\r' becomes two characters: '\\' and 'n' or 'r'
} else {
new_length += 1;
}
}
// Allocate memory for the new string
char* new_str = (char*)malloc(new_length + 1); // +1 for the null terminator
if (new_str == NULL) {
fprintf(stderr, "Memory allocation failed\n");
exit(EXIT_FAILURE);
}
// Replace '\n' with "\\n" and '\r' with "\\r"
char* q = new_str;
for (const char* p = str; *p != '\0'; ++p) {
if (*p == '\n') {
*q++ = '\\';
*q++ = 'n';
} else if (*p == '\r') {
*q++ = '\\';
*q++ = 'r';
} else {
*q++ = *p;
}
}
*q = '\0'; // Null-terminate the new string
return new_str;
}

255
src/tokeniser.c
View File

@ -1,255 +0,0 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "tokeniser.h"
#include "dyn_arr.h"
#include "logger.h"
#include "token.h"
DEFINE_DA_IMPL(token, token_t)
#define TZ_TOK_PUSH(_loc, _type, _text) mcl_da_token_push(&tz->tokens, (token_t){.loc = (_loc), .type = (_type), .text=(_text)})
static struct {
char* k;
token_type_t v;
} KEYWORDS[] = {
{"fn", TT_KW_FN },
{"return", TT_KW_RETURN},
{"for", TT_KW_FOR},
{"if", TT_KW_IF},
{"else", TT_KW_ELSE},
{"enum", TT_KW_ENUM},
{"struct", TT_KW_STRUCT},
{"while", TT_KW_WHILE},
{"break", TT_KW_BREAK},
{"continue", TT_KW_CONTINUE}
};
tokeniser_t* tokenise(char* file) {
tokeniser_t* tz = malloc(sizeof(tokeniser_t));
tz->loc.file = file;
tz->loc.line = 1;
tz->loc.col = 1;
FILE* f = fopen(file, "r");
if (!f) {
printf("Could not open file %s\n", file);
return NULL;
}
char c;
while ((c = fgetc(f)) != EOF) {
switch(c) {
case '\t':
case '\r':
case ' ':{
tz->loc.col += 1;
} break;
case '\n': {
tz->loc.col = 1;
tz->loc.line++;
} break;
case '"': {
loc_t loc = tz->loc;
int size = 256;
int i = 0;
char* buf = malloc(size * sizeof(char));
while ((c = fgetc(f)) != EOF) {
tz->loc.col++;
if (size <= strlen(buf) - 1) {
buf = realloc(buf, size *= 2);
}
if (c == '\n') {
mcl_log_loc(ERROR, &tz->loc, "No newlines in strings");
return NULL;
}
if (c == '"') break;
if (c == '\\') {
switch (c = fgetc(f)) {
case 'n': c = '\n'; break;
case '\\': break;
}
}
buf[i++] = c;
}
TZ_TOK_PUSH(loc, TT_STR, buf);
} break;
case '\'': {
loc_t loc = tz->loc;
bool escape = false;
char c = fgetc(f);
tz->loc.col += 1;
char* buf = malloc(1 * sizeof(char));
if (c == '\\') {
c = fgetc(f);
tz->loc.col += 1;
switch (c) {
case 'n': *buf = '\n'; break;
default:
mcl_log_loc(ERROR, &tz->loc, "Unknown escape: \\%c\n", c);
return NULL;
}
} else {
tz->loc.col += 1;
*buf = c;
}
c = fgetc(f);
if (c != '\'') {
mcl_log_loc(ERROR, &tz->loc, "Expected \"'\" found \"%c\"", c);
return NULL;
}
TZ_TOK_PUSH(loc, TT_CHR, buf);
}
case 'a': case 'A':
case 'b': case 'B':
case 'c': case 'C':
case 'd': case 'D':
case 'e': case 'E':
case 'f': case 'F':
case 'g': case 'G':
case 'h': case 'H':
case 'i': case 'I':
case 'j': case 'J':
case 'k': case 'K':
case 'l': case 'L':
case 'm': case 'M':
case 'n': case 'N':
case 'o': case 'O':
case 'p': case 'P':
case 'q': case 'Q':
case 'r': case 'R':
case 's': case 'S':
case 't': case 'T':
case 'u': case 'U':
case 'v': case 'V':
case 'w': case 'W':
case 'y': case 'Y':
case 'z': case 'Z':
case '_': {
loc_t loc = tz->loc;
int size = 256;
int i = 1;
char* buf = malloc(size * sizeof(char));
buf[0] = c;
while ((c = fgetc(f)) != EOF) {
if (!( (c >= 'A' && c <= 'Z') ||
(c >= 'a' && c <= 'z') ||
(c >= '0' && c <= '9') ||
(c == '_')
)) {
tz->loc.col++;
ungetc(c, f);
break;
};
if (size <= strlen(buf) - 1) {
buf = realloc(buf, size *= 2);
}
tz->loc.col++;
buf[i++] = c;
}
bool found = false;
for (int i = 0; i < sizeof(KEYWORDS)/sizeof(KEYWORDS[0]); i++) {
if (strcmp(buf, KEYWORDS[i].k) == 0) {
TZ_TOK_PUSH(loc, KEYWORDS[i].v, NULL);
found = true;
}
}
if (!found) TZ_TOK_PUSH(loc, TT_IDENT, buf);
} break;
case '}': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '{': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_L, NULL);
tz->loc.col++;
} break;
case ']': {
TZ_TOK_PUSH(tz->loc, TT_BRACK_R, NULL);
tz->loc.col++;
} break;
case '[': {
TZ_TOK_PUSH(tz->loc, TT_BRACK_L, NULL);
tz->loc.col++;
} break;
case ')': {
TZ_TOK_PUSH(tz->loc, TT_PAREN_R, NULL);
tz->loc.col++;
} break;
case '(': {
TZ_TOK_PUSH(tz->loc, TT_PAREN_L, NULL);
tz->loc.col++;
} break;
case ':': {
TZ_TOK_PUSH(tz->loc, TT_COLON, NULL);
tz->loc.col++;
} break;
case ';': {
TZ_TOK_PUSH(tz->loc, TT_SEMI, NULL);
tz->loc.col++;
} break;
case ',': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '.': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '&': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '*': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '+': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '-': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '/': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '|': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '=': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '<': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
case '>': {
TZ_TOK_PUSH(tz->loc, TT_CURLY_R, NULL);
tz->loc.col++;
} break;
}
}
return tz;
}

408
src/typechecker.rs Normal file
View File

@ -0,0 +1,408 @@
use std::collections::HashMap;
use crate::{definitions::{Operator, Types, OpType, KeywordType, InstructionType, Loc}, Args, lerror, warn};
use anyhow::{Result, bail};
#[allow(dead_code)]
#[derive(Debug, Clone)]
pub struct Function {
loc: Loc,
args: Vec<Types>,
returns: Vec<Types>,
}
#[derive(Debug, Clone)]
pub struct Constant {
#[allow(dead_code)]
loc: Loc,
types: Vec<Types>,
}
impl Function {
#[allow(dead_code)]
pub fn default() -> Self {
Self {
args: Vec::new(),
returns: Vec::new(),
loc: (String::new(), 0, 0)
}
}
}
type Functions = HashMap<String, Function>;
type Constants = HashMap<String, Constant>;
pub fn typecheck(ops: Vec<Operator>, args: &Args, init_types: Option<Vec<Types>>, funcs: HashMap<String, Function>, consts: HashMap<String, Constant>) -> Result<(Vec<Types>, Functions, Constants)>{
if args.unsaf {
if !args.quiet {
warn!("Unsafe mode enabled, disabling typechecker, goodluck");
}
return Ok((Vec::new(), HashMap::new(), HashMap::new()));
}
let mut functions: HashMap<String, Function> = funcs;
let mut constants: HashMap<String, Constant> = consts;
// let mut in_function: (String, Function, Loc) = (String::new(), Function::default(), (String::new(), 0, 0));
let mut stack: Vec<Types> = if let Some(i) = init_types {i} else {Vec::new()};
let mut stack_snapshots: Vec<Vec<Types>> = Vec::new();
let mut rtokens = ops;
rtokens.reverse();
// println!("{:#?}", ops);
while !rtokens.is_empty() {
let op = rtokens.pop().unwrap();
// println!("{:?}", stack.clone());
// println!("{:?}", op);
// println!("{}", ops.len());
match op.typ.clone() {
OpType::Keyword(keyword) => {
match keyword {
KeywordType::If |
KeywordType::Do => {
stack_pop(&mut stack, &op, &[Types::Bool])?;
},
KeywordType::FunctionDefExported |
KeywordType::FunctionDef => {
let name = op.text.clone();
// println!("{:?}", name);
if let Some(p) = rtokens.pop() {
if p.typ != OpType::Instruction(InstructionType::With){
lerror!(&op.loc, "Expected {:?}, got {:?}", OpType::Instruction(InstructionType::With), p.typ);
bail!("");
}
} else {
lerror!(&op.loc, "Expected {:?}, got nothing", OpType::Instruction(InstructionType::With));
bail!("");
}
let mut p = rtokens.pop();
let mut func = Function {
args: Vec::new(),
returns: Vec::new(),
loc: op.loc
};
let mut return_args = false;
while p.as_ref().is_some() {
let op = p.as_ref().unwrap();
if op.typ == OpType::Instruction(InstructionType::TypeBool) ||
op.typ == OpType::Instruction(InstructionType::TypeInt) ||
op.typ == OpType::Instruction(InstructionType::TypePtr) ||
op.typ == OpType::Instruction(InstructionType::TypeAny) ||
op.typ == OpType::Instruction(InstructionType::TypeVoid) {
let t = if op.typ == OpType::Instruction(InstructionType::TypeInt) {
Types::U64
} else if op.typ == OpType::Instruction(InstructionType::TypeBool) {
Types::Bool
} else if op.typ == OpType::Instruction(InstructionType::TypePtr) {
Types::Ptr
} else if op.typ == OpType::Instruction(InstructionType::TypeVoid) {
if return_args {
func.returns = vec![Types::Void];
} else {
func.args = vec![Types::Void];
return_args = true;
continue;
}
Types::Void
} else if op.typ == OpType::Instruction(InstructionType::TypeAny) {
Types::Any
} else {
panic!()
};
if return_args {
func.returns.push(t);
} else {
func.args.push(t);
}
}
if op.typ == OpType::Instruction(InstructionType::Returns) {
return_args = true;
}
if op.typ == OpType::Keyword(KeywordType::FunctionThen) {
break;
}
p = rtokens.pop();
};
let mut code: Vec<Operator> = Vec::new();
while !rtokens.is_empty() {
let op = rtokens.pop().unwrap();
if op.typ == OpType::Keyword(KeywordType::FunctionDone) {
break;
}
code.push(op);
}
let ts = if func.args.clone() == vec![Types::Void] {
Vec::new()
} else {
func.args.clone()
};
if ts.contains(&Types::Void) {
continue;
}
functions.insert(name.clone(), func.clone());
let (ret_typs, _, _) = typecheck(code, args, Some(ts.clone()), functions.clone(), constants.clone())?;
if ret_typs != func.returns && !func.returns.contains(&Types::Void){
lerror!(&func.loc, "Expected {:?}, but got {:?}", func.returns, ret_typs);
bail!("");
}
if !func.args.contains(&Types::Void) {
stack.append(&mut func.args);
}
stack_snapshots.push(stack.clone());
}
KeywordType::Else |
KeywordType::End |
KeywordType::While |
KeywordType::Include |
KeywordType::Constant |
KeywordType::Memory => (),
KeywordType::ConstantDef => {
// println!("defined constant");
constants.insert(op.text, Constant { loc: op.loc.clone(), types: vec![Types::U64] });
},
KeywordType::FunctionThen |
KeywordType::FunctionDone |
KeywordType::Inline |
KeywordType::Export |
KeywordType::Function => {
println!("{:?}", op);
unreachable!()
},
KeywordType::Struct => todo!(),
}
},
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => {
stack.push(Types::U64);
},
InstructionType::PushStr => {
stack.push(Types::U64);
stack.push(Types::Ptr);
},
InstructionType::PushCStr => {
stack.push(Types::U64);
stack.push(Types::Ptr);
},
InstructionType::Drop => {
stack_pop(&mut stack, &op, &[Types::Any])?;
},
InstructionType::Print => {
stack_pop(&mut stack, &op, &[Types::U64])?;
},
InstructionType::Dup => {
let a = stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(a);
},
InstructionType::Rot => {
let a = stack_pop(&mut stack, &op, &[Types::Any])?;
let b = stack_pop(&mut stack, &op, &[Types::Any])?;
let c = stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(b);
stack.push(a);
stack.push(c);
},
InstructionType::Over => {
let a = stack_pop(&mut stack, &op, &[Types::Any])?;
let b = stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(b.clone());
stack.push(a);
stack.push(b);
},
InstructionType::Swap => {
let a = stack_pop(&mut stack, &op, &[Types::Any])?;
let b = stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(a);
stack.push(b);
},
InstructionType::Minus |
InstructionType::Plus |
InstructionType::Band |
InstructionType::Bor |
InstructionType::Shr |
InstructionType::Shl |
InstructionType::Mul => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::U64])?;
stack.push(Types::U64);
},
InstructionType::Equals |
InstructionType::Gt |
InstructionType::Lt |
InstructionType::Ge |
InstructionType::Le |
InstructionType::NotEquals => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::U64])?;
stack.push(Types::Bool);
},
InstructionType::DivMod => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::U64])?;
stack.push(Types::U64);
stack.push(Types::U64);
},
InstructionType::Read8 |
InstructionType::Read32 |
InstructionType::Read64 => {
stack_pop(&mut stack, &op, &[Types::Ptr])?;
stack.push(Types::U64);
},
InstructionType::Write8 |
InstructionType::Write32 |
InstructionType::Write64 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Ptr])?;
},
InstructionType::Syscall0 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack.push(Types::U64);
},
InstructionType::Syscall1 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::Syscall2 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::Syscall3 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::Syscall4 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::Syscall5 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::Syscall6 => {
stack_pop(&mut stack, &op, &[Types::U64])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::CastBool => {
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::Bool);
},
InstructionType::CastPtr => {
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::Ptr);
},
InstructionType::CastInt => {
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::U64);
},
InstructionType::CastVoid => {
stack_pop(&mut stack, &op, &[Types::Any])?;
stack.push(Types::Any);
},
InstructionType::MemUse => {
stack.push(Types::Ptr);
},
InstructionType::FnCall => {
stack_snapshots.push(stack.clone());
let f = if let Some(f) = functions.get(&op.text) {f} else {
lerror!(&op.loc, "Could not find function {}", op.text);
bail!("");
};
// in_function = (op.text.clone(), f.clone(), op.loc.clone());
let mut s = stack.clone();
let mut a = f.args.clone();
// s.reverse();
a.reverse();
for t in a{
if let Some(s2) = s.pop(){
if t != s2 {
lerror!(&op.loc, "Expected {:?}, but got {:?}", t, s2);
bail!("");
}
} else {
lerror!(&op.loc, "Expected {:?}, but got nothing", t);
bail!("");
}
}
}
InstructionType::Return |
InstructionType::None |
InstructionType::TypeBool |
InstructionType::TypePtr |
InstructionType::TypeInt |
InstructionType::TypeVoid |
InstructionType::TypeAny |
InstructionType::Returns |
InstructionType::With => (),
InstructionType::ConstUse => {
// println!("{constants:?}");
let mut c = constants.get(&op.text).unwrap().clone();
stack.append(&mut c.types);
},
InstructionType::StructUse => todo!(),
}
},
OpType::Internal(t) => panic!("{t:?}"),
}
}
Ok((stack, functions, constants))
}
fn stack_pop(v: &mut Vec<Types>, op: &Operator, t: &[Types]) -> Result<Types> {
if v.is_empty() {
lerror!(&op.loc, "Expected {:?}, but got nothing", t);
bail!("");
}
let r = v.pop().unwrap();
if !t.contains(&r) && t[0] != Types::Any {
lerror!(&op.loc, "Expected {:?}, but got {:?}", t, r);
bail!("");
}
Ok(r)
}

392
src/types.rs Normal file
View File

@ -0,0 +1,392 @@
use std::collections::{HashMap, HashSet};
use eyre::bail;
#[derive(Debug, Clone, PartialEq)]
pub enum InstructionType {
// stack
PushInt,
PushStr,
PushCStr,
Drop,
Print,
Dup,
Rot, // a b c => b c a
Over, // a b => a b a
Swap, // a b => b a
// math
Minus,
Plus,
Equals,
Gt,
Lt,
Ge,
Le,
NotEquals,
Band, // &
Bor, // |
Shr, // >>
Shl, // <<
DivMod, // /
Mul,
// mem
Read8,
Write8,
Read32,
Write32,
Read64,
Write64,
// syscalls
Syscall0,
Syscall1,
Syscall2,
Syscall3,
Syscall4,
Syscall5,
Syscall6,
CastBool,
CastPtr,
CastInt,
CastVoid,
// typing
TypeBool,
TypePtr,
TypeInt,
TypeVoid,
// TypeStr,
TypeAny,
Returns,
With,
FnCall,
MemUse,
ConstUse,
Return,
None // Used for macros and any other non built in word definitions
}
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum KeywordType {
If,
Else,
End,
While,
Do,
Include,
Memory,
Constant,
ConstantDef,
Function,
FunctionDef,
FunctionDefExported,
FunctionThen,
FunctionDone,
Inline,
Export,
Struct,
}
#[derive(Debug, Clone, Copy, PartialEq)]
pub enum InternalType {
Arrow
}
#[derive(Debug, Clone, PartialEq)]
pub enum OpType {
Keyword(KeywordType),
Instruction(InstructionType),
Internal(InternalType)
}
#[derive(Debug, Clone)]
pub struct Operator{
pub typ: OpType,
pub tok_typ: TokenType,
pub value: usize,
pub text: String, //? only used for OpType::PushStr
pub addr: Option<usize>, //? only used for OpType::PushStr
pub jmp: usize,
pub loc: Loc,
pub types: (usize, usize)
}
impl Operator {
pub fn new(typ: OpType, tok_typ: TokenType, value: usize, text: String, file: String, row: usize, col: usize) -> Self {
Self {
typ,
value,
jmp: 0,
addr: None,
text,
loc: (file, row, col),
tok_typ,
types: (0, 0)
}
}
pub fn set_addr(&mut self, addr: usize) -> Self {
self.addr = Some(addr);
(*self).clone()
}
// pub fn set_types(&mut self, args: usize, rets: usize) -> Self {
// self.types = (args, rets);
// (*self).clone()
// }
}
impl OpType {
pub fn human(&self) -> String {
match (*self).clone() {
OpType::Instruction(instruction) => {
match instruction {
InstructionType::PushInt => "Number",
InstructionType::PushStr => "String",
InstructionType::PushCStr => "CString",
InstructionType::Print => "_dbg_print",
InstructionType::Dup => "dup",
InstructionType::Drop => "drop",
InstructionType::Rot => "rot",
InstructionType::Over => "over",
InstructionType::Swap => "swap",
InstructionType::Plus => "+",
InstructionType::Minus => "-",
InstructionType::Equals => "=",
InstructionType::Gt => ">",
InstructionType::Lt => "<",
InstructionType::NotEquals => "!=",
InstructionType::Le => "<=",
InstructionType::Ge => ">=",
InstructionType::Band => "band",
InstructionType::Bor => "bor",
InstructionType::Shr => "shr",
InstructionType::Shl => "shl",
InstructionType::DivMod => "divmod",
InstructionType::Mul => "*",
InstructionType::Read8 => "read8",
InstructionType::Write8 => "write8",
InstructionType::Read32 => "read32",
InstructionType::Write32 => "write32",
InstructionType::Read64 => "read64",
InstructionType::Write64 => "write64",
InstructionType::Syscall0 => "syscall0",
InstructionType::Syscall1 => "syscall1",
InstructionType::Syscall2 => "syscall2",
InstructionType::Syscall3 => "syscall3",
InstructionType::Syscall4 => "syscall4",
InstructionType::Syscall5 => "syscall5",
InstructionType::Syscall6 => "syscall6",
InstructionType::CastBool => "cast(bool",
InstructionType::CastPtr => "cast(ptr)",
InstructionType::CastInt => "cast(int)",
InstructionType::CastVoid => "cast(void)",
InstructionType::None => "None",
InstructionType::MemUse => "Memory use (internal)",
InstructionType::FnCall => "Function Call (Internal)",
InstructionType::ConstUse => "Constant Use (Internal)",
InstructionType::Return => "return",
InstructionType::TypeBool => "bool",
InstructionType::TypePtr => "ptr",
InstructionType::TypeInt => "int",
InstructionType::TypeVoid => "void",
InstructionType::Returns => "returns",
InstructionType::With => "with",
InstructionType::TypeAny => "any",
}
}
OpType::Keyword(keyword) => {
match keyword {
KeywordType::If => "if",
KeywordType::Else => "else",
KeywordType::End => "end",
KeywordType::While => "while",
KeywordType::Do => "do",
KeywordType::Include => "include",
KeywordType::Memory => "memory",
KeywordType::Function => "fn",
KeywordType::Constant => "const",
KeywordType::FunctionThen => "then",
KeywordType::FunctionDone => "done",
KeywordType::ConstantDef => "constant Definition (internal)",
KeywordType::FunctionDef => "function definition (internal)",
KeywordType::FunctionDefExported => "extern function definition (internal)",
KeywordType::Inline => "inline",
KeywordType::Export => "export",
KeywordType::Struct => "struct",
}
}
OpType::Internal(t) => panic!("{t:?}"),
}.to_string()
}
}
#[derive(Debug, Clone)]
pub struct Token {
pub file: String,
pub line: usize,
pub col: usize,
pub text: String,
pub typ: TokenType,
pub value: Option<usize>, //* only used for Memories
pub addr: Option<usize>, //* only used for Memories
pub op_typ: OpType //* only used for Memories
}
#[derive(Debug, Clone, PartialEq, Copy)]
pub enum TokenType {
Word,
Int,
String,
CString,
Char
}
impl Token {
pub fn loc(&self) -> Loc {
(
self.file.clone(),
self.line,
self.col
)
}
}
impl TokenType {
pub fn human(self) -> String {
match self {
TokenType::Word => "Word",
TokenType::Int => "Int",
TokenType::String => "String",
TokenType::CString => "CString",
TokenType::Char => "Char"
}.to_string()
}
}
pub type Loc = (String, usize, usize);
#[derive(Debug, PartialEq, Clone)]
pub enum Types {
Any,
Bool,
Ptr,
Void,
U8,
U16,
U32,
U64,
I8,
I16,
I32,
I64,
Custom{
size: u64 // in bytes
},
// todo: add signed numbers since we dont have them yet lol
}
impl Types {
pub fn get_size(&self) -> u64 {
match *self {
Types::Any => 0, // any cant be a known size
Types::Void => 0,
Types::Bool => 1,
Types::U8 |
Types::I8 => 1,
Types::U16 |
Types::I16 => 2,
Types::U32 |
Types::I32 => 4,
Types::Ptr |
Types::U64 |
Types::I64 => 8,
Types::Custom { size } => size,
}
}
}
impl TryInto<Types> for &str {
type Error = color_eyre::eyre::Error;
fn try_into(self) -> Result<Types, Self::Error> {
match self {
"Any" => Ok(Types::Any),
"Void" => Ok(Types::Void),
"Bool" => Ok(Types::Bool),
"U8" => Ok(Types::U8),
"I8" => Ok(Types::I8),
"U16" => Ok(Types::U16),
"I16" => Ok(Types::I16),
"U32" => Ok(Types::U32),
"I32" => Ok(Types::I32),
"Ptr" => Ok(Types::Ptr),
"U64" => Ok(Types::U64),
"I64" => Ok(Types::I64),
_ => bail!("Unknown type {self}")
}
}
}
impl TryInto<Types> for String {
type Error = color_eyre::eyre::Error;
fn try_into(self) -> Result<Types, Self::Error> {
self.into()
}
}
#[derive(Debug, Clone)]
pub struct Function {
pub loc: Loc,
pub name: String,
pub inline: bool,
pub tokens: Option<Vec<Operator>>
}
#[derive(Debug, Clone)]
pub struct Constant {
pub loc: Loc,
pub name: String
}
#[derive(Debug, Clone)]
pub struct Memory {
pub loc: Loc,
pub id: usize
}
#[derive(Debug, Clone)]
pub struct StructDef {
pub loc: Loc,
pub name: String,
pub fields: HashSet<(String, Types)>
}
pub type Functions = HashMap<String, Function>;
pub type Memories = HashMap<String, Memory>;
pub type Constants = HashMap<String, Constant>;
pub type StructDefs = HashMap<String, StructDef>;
#[derive(Debug, Clone)]
pub struct Program {
pub ops: Vec<Operator>,
pub functions: Functions,
pub memories: Memories,
pub constants: Constants,
pub struct_defs: StructDefs
}

29
src/types/common/loc.rs Normal file
View File

@ -0,0 +1,29 @@
pub struct Loc {
pub ln: usize,
pub col: usize,
pub file: String
}
impl Loc {
pub fn new(file: String, ln: usize, col: usize) -> Self {
Self {
ln,
col,
file,
}
}
}
impl ToString for Loc {
fn to_string(&self) -> String {
format!("{}:{}:{}", self.file, self.ln, self.col)
}
}
impl Into<String> for Loc {
fn into(self) -> String {
self.to_string()
}
}

4
src/types/common/mod.rs Normal file
View File

@ -0,0 +1,4 @@
mod loc;
pub use loc::*;

4
src/types/mod.rs Normal file
View File

@ -0,0 +1,4 @@
pub mod common;
pub mod token;

65
src/types/token.rs Normal file
View File

@ -0,0 +1,65 @@
use super::common::Loc;
struct Token {
loc: Loc,
typ: TokenType,
val: TokenValue
}
pub enum TokenValue {
Int(usize),
Str(String)
}
pub enum TokenType {
DbgPrint,
Keyword(TokenKeyword),
Syscall(u8),
//? Literal
PushInt,
PushStr,
//? Stack manipulation
Dup,
Rot, // a b c => b c a
Over, // a b => a b a
Swap, // a b => b a
//? Math
Plus,
Minus,
Mul,
Div,
Mod,
//? Logical
And,
Or,
Eq,
Gt,
Lt,
Ge,
Le,
Ne,
//? Bitwise
Shr,
Shl,
Bor,
Band,
}
pub enum TokenKeyword {
Function,
If,
Else,
End,
Done,
Macro,
While,
Do
}

117
src/util.rs Normal file
View File

@ -0,0 +1,117 @@
// use color_eyre::Result;
pub mod color {
#![allow(dead_code)]
pub const NONE: &str = "\x1b[0m";
pub const RESET: &str = "\x1b[0m";
pub const BRIGHT: &str = "\x1b[1m";
pub const DIM: &str = "\x1b[2m";
pub const UNDERSCORE: &str = "\x1b[4m";
pub const BLINK: &str = "\x1b[5m";
pub const REVERSE: &str = "\x1b[7m";
pub const HIDDEN: &str = "\x1b[8m";
pub const FG_BLACK: &str = "\x1b[30m";
pub const FG_RED: &str = "\x1b[31m";
pub const FG_GREEN: &str = "\x1b[32m";
pub const FG_YELLOW: &str = "\x1b[33m";
pub const FG_BLUE: &str = "\x1b[34m";
pub const FG_MAGENTA: &str = "\x1b[35m";
pub const FG_CYAN: &str = "\x1b[36m";
pub const FG_WHITE: &str = "\x1b[37m";
pub const BG_BLACK: &str = "\x1b[40m";
pub const BG_RED: &str = "\x1b[41m";
pub const BG_GREEN: &str = "\x1b[42m";
pub const BG_YELLOW: &str = "\x1b[43m";
pub const BG_BLUE: &str = "\x1b[44m";
pub const BG_MAGENTA: &str = "\x1b[45m";
pub const BG_CYAN: &str = "\x1b[46m";
pub const BG_WHITE: &str = "\x1b[47m";
}
pub mod logger {
#![allow(dead_code)]
use std::ops::Deref;
use crate::{util::color, definitions::Loc};
pub fn error(msg: &str) {
println!("{red}error{r}: {msg}", red=color::FG_RED, r=color::RESET);
}
pub fn warn(msg: &str) {
println!("{yellow}warn{r}: {msg}", yellow=color::FG_YELLOW, r=color::RESET);
}
pub fn info(msg: &str) {
println!("{green}info{r}: {msg}", green=color::FG_GREEN, r=color::RESET);
}
pub fn note(msg: &str) {
println!("{blue}note{r}: {msg}", blue=color::FG_BLUE, r=color::RESET);
}
pub fn lerror<P: Deref<Target = Loc>>(loc: P, msg: &str) {
println!("{f}:{r}:{c} {red}error{rs}: {msg}", red=color::FG_RED, rs=color::RESET, f=loc.0, r=loc.1, c=loc.2);
}
pub fn lwarn<P: Deref<Target = Loc>>(loc: P, msg: &str) {
println!("{f}:{r}:{c} {yellow}warn{rs}: {msg}", yellow=color::FG_YELLOW, rs=color::RESET, f=loc.0, r=loc.1, c=loc.2);
}
pub fn linfo<P: Deref<Target = Loc>>(loc: P, msg: &str) {
println!("{f}:{r}:{c} {green}info{rs}: {msg}", green=color::FG_GREEN, rs=color::RESET, f=loc.0, r=loc.1, c=loc.2);
}
pub fn lnote<P: Deref<Target = Loc>>(loc: P, msg: &str) {
println!("{f}:{r}:{c} {blue}note{rs}: {msg}", blue=color::FG_BLUE, rs=color::RESET, f=loc.0, r=loc.1, c=loc.2);
}
pub fn help(msg: &str) {
println!("{blue}help{r}: {msg}", blue=color::FG_CYAN, r=color::RESET);
}
pub fn code_block(code: &str) -> String {
let mut ret = String::new();
let lines = code.lines();
for (i, line) in lines.enumerate() {
use std::fmt::Write;
writeln!(ret, "{}{} | {}{}",color::FG_BLUE, i + 1, line, color::RESET).unwrap();
}
ret
}
pub mod macros {
#[macro_export] macro_rules! error { ($($arg:tt)*) => { $crate::util::logger::error(std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! warn { ($($arg:tt)*) => { $crate::util::logger::warn( std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! info { ($($arg:tt)*) => { $crate::util::logger::info( std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! note { ($($arg:tt)*) => { $crate::util::logger::note( std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! lerror { ($dst:expr, $($arg:tt)*) => { $crate::util::logger::lerror($dst, std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! lwarn { ($dst:expr, $($arg:tt)*) => { $crate::util::logger::lwarn($dst, std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! linfo { ($dst:expr, $($arg:tt)*) => { $crate::util::logger::linfo($dst, std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! lnote { ($dst:expr, $($arg:tt)*) => { $crate::util::logger::lnote($dst, std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! help { ($($arg:tt)*) => { $crate::util::logger::help( std::format_args!($($arg)*).to_string().as_str()) }; }
#[macro_export] macro_rules! code_block { ($($arg:tt)*) => { $crate::util::logger::code_block( std::format_args!($($arg)*).to_string().as_str()) }; }
}
}
// pub trait StringExtra{
// fn find_idx(&self, pat: char, start: u32) -> Result<u32, ()>;
// }
// impl StringExtra for String {
// fn find_idx(&self, pat: char, start: u32) -> Result<u32, ()> {
// let mut col = start;
// for c in (*self).chars() {
// if c == pat {
// return Ok(col);
// }
// col += 1;
// }
// Err(())
// }
// }

13
test.mcl
View File

@ -1,6 +1,13 @@
include "std.mcl"
fn main with int ptr returns void then
// p l
"Hello!\n" puts
main :: fn(argc: i32, argv: string -> i32 {
println!("Hello world!\n");
}
// memory fd 4 end
// c"./test.mcl" FS_O_SYNC 0 fopen
// dup _dbg_print
// fd swap write32
done

1
tests/fail_unknown_word.mcl Normal file
View File

@ -0,0 +1 @@
gftdesd5ryutfgyhibugtf6r4

7
tests/math.mcl Normal file
View File

@ -0,0 +1,7 @@
34 35 + print
800 380 - print
10 5 * print
40 5 / print

4
tools/.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
/*
!/.gitignore
!/*.c
!/build_tools.sh

3
tools/build_tools.sh Normal file
View File

@ -0,0 +1,3 @@
#!/usr/bin/bash
gcc intcnv.c -o intcnv

47
tools/intcnv.c Normal file
View File

@ -0,0 +1,47 @@
#include<stdio.h>
#include <stdlib.h>
#include <string.h>
int main(int argc, char** argv) {
if (argc < 3) {
printf("Usage: intcnv i32 134\n");
return 1;
}
const char* typ = argv[1];
__uint64_t num = atoi(argv[2]);
if (strcmp(typ, "u8") == 0) {
__uint8_t num2 = (__uint8_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "i8") == 0) {
__int8_t num2 = (__int8_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "u16") == 0) {
__uint16_t num2 = (__uint16_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "i16") == 0) {
__int16_t num2 = (__int16_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "u32") == 0) {
__uint32_t num2 = (__uint32_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "i32") == 0) {
__int32_t num2 = (__int32_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "u64") == 0) {
__uint64_t num2 = (__uint64_t)num;
printf("%d\n", num2);
}
if (strcmp(typ, "i64") == 0) {
__int64_t num2 = (__int64_t)num;
printf("%d\n", num2);
}
}