occheung
/
nac3
forked from M-Labs/nac3
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Compare commits

base: occheung:master
Branches Tags
occheung:master
occheung:nested-binop
occheung:kern-return
occheung:nac3ld
occheung:restrict-linkage
occheung:artiq-lld
occheung:option
occheung:polymorphism_fixes
occheung:refactor_anto
M-Labs:master
M-Labs:ndstrides-neo-next
M-Labs:misc/impl-tracert
M-Labs:ndstrides-14-end
M-Labs:ndstrides-13-tests
M-Labs:ndstrides-12-builtins
M-Labs:ndstrides-11-matmul
M-Labs:ndstrides-10-ops
M-Labs:ndstrides-9-subassign
M-Labs:ndstrides-8-transpose
M-Labs:ndstrides-7-broadcasting
M-Labs:ndstrides-6-reshape
M-Labs:ndstrides-5-miscfuncs
M-Labs:ndstrides-4-nparray
M-Labs:ndstrides-3-indexing
M-Labs:ndstrides-2-basic
M-Labs:ndstrides-1-model
M-Labs:ndstrides
M-Labs:refactor_composer
M-Labs:misc/update-pyo3
M-Labs:misc/mold
M-Labs:ndstrides-1-model-lifetime
M-Labs:ndstrides-enhance-irrt
M-Labs:ndstrides-intro
M-Labs:issue-313
M-Labs:refactor-primstore
M-Labs:numpy-anyall
M-Labs:enhance/cargo-test-standalone-demos
M-Labs:issue-136
M-Labs:rpc-obj-as-param
M-Labs:iterators
M-Labs:escape-analysis
M-Labs:refactor_anto
..
compare: occheung:artiq-lld
Branches Tags
occheung:nested-binop
occheung:kern-return
occheung:master
occheung:nac3ld
occheung:restrict-linkage
occheung:artiq-lld
occheung:option
occheung:polymorphism_fixes
occheung:refactor_anto
M-Labs:master
M-Labs:ndstrides-neo-next
M-Labs:misc/impl-tracert
M-Labs:ndstrides-14-end
M-Labs:ndstrides-13-tests
M-Labs:ndstrides-12-builtins
M-Labs:ndstrides-11-matmul
M-Labs:ndstrides-10-ops
M-Labs:ndstrides-9-subassign
M-Labs:ndstrides-8-transpose
M-Labs:ndstrides-7-broadcasting
M-Labs:ndstrides-6-reshape
M-Labs:ndstrides-5-miscfuncs
M-Labs:ndstrides-4-nparray
M-Labs:ndstrides-3-indexing
M-Labs:ndstrides-2-basic
M-Labs:ndstrides-1-model
M-Labs:ndstrides
M-Labs:refactor_composer
M-Labs:misc/update-pyo3
M-Labs:misc/mold
M-Labs:ndstrides-1-model-lifetime
M-Labs:ndstrides-enhance-irrt
M-Labs:ndstrides-intro
M-Labs:issue-313
M-Labs:refactor-primstore
M-Labs:numpy-anyall
M-Labs:enhance/cargo-test-standalone-demos
M-Labs:issue-136
M-Labs:rpc-obj-as-param
M-Labs:iterators
M-Labs:escape-analysis
M-Labs:refactor_anto

1 Commits
master ... artiq-lld

Author SHA1 Message Date
occheung 9573311a0d nac3artiq: generate buffered object 2022-03-22 13:43:09 +08:00
147 changed files with 9495 additions and 39446 deletions
Show Stats Expand all files Collapse all files

32
.clang-format
View File

@ -1,32 +0,0 @@
BasedOnStyle: LLVM
Language: Cpp
Standard: Cpp11
AccessModifierOffset: -1
AlignEscapedNewlines: Left
AlwaysBreakAfterReturnType: None
AlwaysBreakTemplateDeclarations: Yes
AllowAllParametersOfDeclarationOnNextLine: false
AllowShortFunctionsOnASingleLine: Inline
BinPackParameters: false
BreakBeforeBinaryOperators: NonAssignment
BreakBeforeTernaryOperators: true
BreakConstructorInitializers: AfterColon
BreakInheritanceList: AfterColon
ColumnLimit: 120
ConstructorInitializerAllOnOneLineOrOnePerLine: true
ContinuationIndentWidth: 4
DerivePointerAlignment: false
IndentCaseLabels: true
IndentPPDirectives: None
IndentWidth: 4
MaxEmptyLinesToKeep: 1
PointerAlignment: Left
ReflowComments: true
SortIncludes: false
SortUsingDeclarations: true
SpaceAfterTemplateKeyword: false
SpacesBeforeTrailingComments: 2
TabWidth: 4
UseTab: Never

1
.clippy.toml
View File

@ -1 +0,0 @@
doc-valid-idents = ["CPython", "NumPy", ".."]

2
.gitignore vendored
View File

@ -1,4 +1,2 @@
__pycache__
/target
/nac3standalone/demo/linalg/target
nix/windows/msys2

24
.pre-commit-config.yaml
View File

@ -1,24 +0,0 @@
# See https://pre-commit.com for more information
# See https://pre-commit.com/hooks.html for more hooks
default_stages: [commit]
repos:
- repo: local
hooks:
- id: nac3-cargo-fmt
name: nac3 cargo format
entry: nix
language: system
types: [file, rust]
pass_filenames: false
description: Runs cargo fmt on the codebase.
args: [develop, -c, cargo, fmt, --all]
- id: nac3-cargo-clippy
name: nac3 cargo clippy
entry: nix
language: system
types: [file, rust]
pass_filenames: false
description: Runs cargo clippy on the codebase.
args: [develop, -c, cargo, clippy, --tests]

1145
Cargo.lock generated
View File

File diff suppressed because it is too large Load Diff

2
Cargo.toml
View File

@ -1,6 +1,5 @@
[workspace]
members = [
"nac3ld",
"nac3ast",
"nac3parser",
"nac3core",
@ -8,7 +7,6 @@ members = [
"nac3artiq",
"runkernel",
]
resolver = "2"
[profile.release]
debug = true

57
README.md
View File

@ -1,10 +1,5 @@
<div align="center">
![icon](https://git.m-labs.hk/M-Labs/nac3/raw/branch/master/nac3.svg)
</div>
# NAC3
NAC3 is a major, backward-incompatible rewrite of the compiler for the [ARTIQ](https://m-labs.hk/artiq) physics experiment control and data acquisition system. It features greatly improved compilation speeds, a much better type system, and more predictable and transparent operation.
NAC3 has a modular design and its applicability reaches beyond ARTIQ. The ``nac3core`` module does not contain anything specific to ARTIQ, and can be used in any project that requires compiling Python to machine code.
@ -13,7 +8,7 @@ NAC3 has a modular design and its applicability reaches beyond ARTIQ. The ``nac3
## Packaging
NAC3 is packaged using the [Nix](https://nixos.org) Flakes system. Install Nix 2.8+ and enable flakes by adding ``experimental-features = nix-command flakes`` to ``nix.conf`` (e.g. ``~/.config/nix/nix.conf``).
NAC3 is packaged using the [Nix](https://nixos.org) Flakes system. Install Nix 2.4+ and enable flakes by adding ``experimental-features = nix-command flakes`` to ``nix.conf`` (e.g. ``~/.config/nix/nix.conf``).
## Try NAC3
@ -21,21 +16,43 @@ NAC3 is packaged using the [Nix](https://nixos.org) Flakes system. Install Nix 2
After setting up Nix as above, use ``nix shell git+https://github.com/m-labs/artiq.git?ref=nac3`` to get a shell with the NAC3 version of ARTIQ. See the ``examples`` directory in ARTIQ (``nac3`` Git branch) for some samples of NAC3 kernel code.
### Windows
### Windows (work in progress)
Install [MSYS2](https://www.msys2.org/), and open "MSYS2 CLANG64". Edit ``/etc/pacman.conf`` to add:
NAC3 ARTIQ packaging for MSYS2/Windows is not yet complete so installation involves many manual steps. It is also less tested and you may encounter problems.
Install [MSYS2](https://www.msys2.org/) and run the following commands:
```
[artiq]
SigLevel = Optional TrustAll
Server = https://msys2.m-labs.hk/artiq-nac3
pacman -S mingw-w64-x86_64-python-h5py mingw-w64-x86_64-python-pyqt5 mingw-w64-x86_64-python-scipy mingw-w64-x86_64-python-prettytable mingw-w64-x86_64-python-pygit2
pacman -S mingw-w64-x86_64-python-pip
pip install qasync
pip install pyqtgraph
pacman -S patch git
git clone https://github.com/m-labs/sipyco
cd sipyco
git show 20c946aad78872fe60b78d9b57a624d69f3eea47 | patch -p1 -R
python setup.py install
cd ..
git clone -b nac3 https://github.com/m-labs/artiq
cd artiq
python setup.py install
```
Then run the following commands:
Locate a recent build of ``nac3artiq-mingw`` from [Hydra](https://nixbld.m-labs.hk) and download ``nac3artiq.zip``. Then extract the contents in the appropriate location:
```
pacman -Syu
pacman -S mingw-w64-clang-x86_64-artiq
pacman -S unzip
wget https://nixbld.m-labs.hk/build/97899/download/1/nac3artiq.zip # edit the build number
unzip nac3artiq.zip -d C:/msys64/mingw64/lib/python3.9/site-packages
```
Install additional NAC3 dependencies:
```
pacman -S mingw-w64-x86_64-lld
wget https://nixbld.m-labs.hk/build/97899/download/1/mcfgthread-12.dll # edit the build number
cp mcfgthread-12.dll C:/msys64/mingw64/bin
```
And you should be good to go.
## For developers
This repository contains:
@ -43,7 +60,6 @@ This repository contains:
- ``nac3parser``: Python parser (based on RustPython).
- ``nac3core``: Core compiler library, containing type-checking and code generation.
- ``nac3standalone``: Standalone compiler tool (core language only).
- ``nac3ld``: Minimalist RISC-V and ARM linker.
- ``nac3artiq``: Integration with ARTIQ and implementation of ARTIQ-specific extensions to the core language.
- ``runkernel``: Simple program that runs compiled ARTIQ kernels on the host and displays RTIO operations. Useful for testing without hardware.
@ -51,12 +67,3 @@ Use ``nix develop`` in this repository to enter a development shell.
If you are using a different shell than bash you can use e.g. ``nix develop --command fish``.
Build NAC3 with ``cargo build --release``. See the demonstrations in ``nac3artiq`` and ``nac3standalone``.
### Pre-Commit Hooks
You are strongly recommended to use the provided pre-commit hooks to automatically reformat files and check for non-optimal Rust practices using Clippy. Run `pre-commit install` to install the hook and `pre-commit` will automatically run `cargo fmt` and `cargo clippy` for you.
Several things to note:
- If `cargo fmt` or `cargo clippy` returns an error, the pre-commit hook will fail. You should fix all errors before trying to commit again.
- If `cargo fmt` reformats some files, the pre-commit hook will also fail. You should review the changes and, if satisfied, try to commit again.

8
flake.lock
View File

@ -2,16 +2,16 @@
"nodes": {
"nixpkgs": {
"locked": {
"lastModified": 1727348695,
"narHash": "sha256-J+PeFKSDV+pHL7ukkfpVzCOO7mBSrrpJ3svwBFABbhI=",
"lastModified": 1647282937,
"narHash": "sha256-K8Oo6QyFCfiEWTRpQVfzcwI3YNMKlz6Tu8rr+o3rzRQ=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "1925c603f17fc89f4c8f6bf6f631a802ad85d784",
"rev": "64fc73bd74f04d3e10cb4e70e1c65b92337e76db",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixos-unstable",
"ref": "nixos-21.11",
"repo": "nixpkgs",
"type": "github"
}

225
flake.nix
View File

@ -1,57 +1,69 @@
{
description = "The third-generation ARTIQ compiler";
inputs.nixpkgs.url = github:NixOS/nixpkgs/nixos-unstable;
inputs.nixpkgs.url = github:NixOS/nixpkgs/nixos-21.11;
outputs = { self, nixpkgs }:
let
pkgs = import nixpkgs { system = "x86_64-linux"; };
pkgs32 = import nixpkgs { system = "i686-linux"; };
pkgs-mingw = import nixpkgs {
system = "x86_64-linux";
crossSystem = { config = "x86_64-w64-mingw32"; libc = "msvcrt"; };
# work around https://github.com/NixOS/nixpkgs/issues/149593
overlays = [
(self: super: {
openssh = super.openssh.overrideAttrs(oa: { doCheck = false; });
})
];
};
msys2-python-tar = pkgs.fetchurl {
url = "https://mirror.msys2.org/mingw/mingw64/mingw-w64-x86_64-python-3.9.7-4-any.pkg.tar.zst";
sha256 = "0iwlgbk4b457yn9djwqswid55xhyyi35qymz1lfh42xwdpxdm47c";
};
msys2-python = pkgs.stdenvNoCC.mkDerivation {
name = "msys2-python";
src = msys2-python-tar;
buildInputs = [ pkgs.gnutar pkgs.zstd ];
phases = [ "installPhase" ];
installPhase =
''
mkdir $out
tar xf $src -C $out
'';
};
pyo3-mingw-config = pkgs.writeTextFile {
name = "pyo3-mingw-config";
text =
''
implementation=CPython
version=3.9
shared=true
abi3=false
lib_name=python3.9
lib_dir=${msys2-python}/mingw64/lib
pointer_width=64
build_flags=WITH_THREAD
suppress_build_script_link_lines=false
'';
};
in rec {
packages.x86_64-linux = rec {
llvm-nac3 = pkgs.callPackage ./nix/llvm {};
llvm-tools-irrt = pkgs.runCommandNoCC "llvm-tools-irrt" {}
''
mkdir -p $out/bin
ln -s ${pkgs.llvmPackages_14.clang-unwrapped}/bin/clang $out/bin/clang-irrt
ln -s ${pkgs.llvmPackages_14.llvm.out}/bin/llvm-as $out/bin/llvm-as-irrt
'';
demo-linalg-stub = pkgs.rustPlatform.buildRustPackage {
name = "demo-linalg-stub";
src = ./nac3standalone/demo/linalg;
cargoLock = {
lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
};
doCheck = false;
};
demo-linalg-stub32 = pkgs32.rustPlatform.buildRustPackage {
name = "demo-linalg-stub32";
src = ./nac3standalone/demo/linalg;
cargoLock = {
lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
};
doCheck = false;
};
llvm-nac3 = pkgs.callPackage "${self}/llvm" {};
nac3artiq = pkgs.python3Packages.toPythonModule (
pkgs.rustPlatform.buildRustPackage rec {
pkgs.rustPlatform.buildRustPackage {
name = "nac3artiq";
outputs = [ "out" "runkernel" "standalone" ];
src = self;
cargoLock = {
lockFile = ./Cargo.lock;
};
passthru.cargoLock = cargoLock;
nativeBuildInputs = [ pkgs.python3 (pkgs.wrapClangMulti pkgs.llvmPackages_14.clang) llvm-tools-irrt pkgs.llvmPackages_14.llvm.out llvm-nac3 ];
cargoLock = { lockFile = ./Cargo.lock; };
nativeBuildInputs = [ pkgs.python3 pkgs.llvmPackages_13.clang-unwrapped llvm-nac3 ];
buildInputs = [ pkgs.python3 llvm-nac3 ];
checkInputs = [ (pkgs.python3.withPackages(ps: [ ps.numpy ps.scipy ])) ];
checkInputs = [ (pkgs.python3.withPackages(ps: [ ps.numpy ])) ];
checkPhase =
''
echo "Checking nac3standalone demos..."
pushd nac3standalone/demo
patchShebangs .
export DEMO_LINALG_STUB=${demo-linalg-stub}/lib/liblinalg.a
export DEMO_LINALG_STUB32=${demo-linalg-stub32}/lib/liblinalg.a
./check_demos.sh -i686
./check_demos.sh
popd
echo "Running Cargo tests..."
cargoCheckHook
@ -76,22 +88,22 @@
};
# LLVM PGO support
llvm-nac3-instrumented = pkgs.callPackage ./nix/llvm {
stdenv = pkgs.llvmPackages_14.stdenv;
llvm-nac3-instrumented = pkgs.callPackage "${self}/llvm" {
stdenv = pkgs.llvmPackages_13.stdenv;
extraCmakeFlags = [ "-DLLVM_BUILD_INSTRUMENTED=IR" ];
};
nac3artiq-instrumented = pkgs.python3Packages.toPythonModule (
pkgs.rustPlatform.buildRustPackage {
name = "nac3artiq-instrumented";
src = self;
inherit (nac3artiq) cargoLock;
nativeBuildInputs = [ pkgs.python3 packages.x86_64-linux.llvm-tools-irrt llvm-nac3-instrumented ];
cargoLock = { lockFile = ./Cargo.lock; };
nativeBuildInputs = [ pkgs.python3 pkgs.llvmPackages_13.clang-unwrapped llvm-nac3-instrumented ];
buildInputs = [ pkgs.python3 llvm-nac3-instrumented ];
cargoBuildFlags = [ "--package" "nac3artiq" "--features" "init-llvm-profile" ];
doCheck = false;
configurePhase =
''
export CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS="-C link-arg=-L${pkgs.llvmPackages_14.compiler-rt}/lib/linux -C link-arg=-lclang_rt.profile-x86_64"
export CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS="-C link-arg=-L${pkgs.llvmPackages_13.compiler-rt}/lib/linux -C link-arg=-lclang_rt.profile-x86_64"
'';
installPhase =
''
@ -103,51 +115,27 @@
);
nac3artiq-profile = pkgs.stdenvNoCC.mkDerivation {
name = "nac3artiq-profile";
srcs = [
(pkgs.fetchFromGitHub {
owner = "m-labs";
repo = "sipyco";
rev = "939f84f9b5eef7efbf7423c735d1834783b6140e";
sha256 = "sha256-15Nun4EY35j+6SPZkjzZtyH/ncxLS60KuGJjFh5kSTc=";
})
(pkgs.fetchFromGitHub {
owner = "m-labs";
repo = "artiq";
rev = "923ca3377d42c815f979983134ec549dc39d3ca0";
sha256 = "sha256-oJoEeNEeNFSUyh6jXG8Tzp6qHVikeHS0CzfE+mODPgw=";
})
];
buildInputs = [
(python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ps.jsonschema ps.lmdb nac3artiq-instrumented ]))
pkgs.llvmPackages_14.llvm.out
];
src = self;
buildInputs = [ (python3-mimalloc.withPackages(ps: [ ps.numpy nac3artiq-instrumented ])) pkgs.lld_13 pkgs.llvmPackages_13.libllvm ];
phases = [ "buildPhase" "installPhase" ];
buildPhase =
''
srcs=($srcs)
sipyco=''${srcs[0]}
artiq=''${srcs[1]}
export PYTHONPATH=$sipyco:$artiq
python -m artiq.frontend.artiq_ddb_template $artiq/artiq/examples/nac3devices/nac3devices.json > device_db.py
cp $artiq/artiq/examples/nac3devices/nac3devices.py .
python -m artiq.frontend.artiq_compile nac3devices.py
'';
# TODO: get more representative code.
buildPhase = "python $src/nac3artiq/demo/demo.py";
installPhase =
''
mkdir $out
llvm-profdata merge -o $out/llvm.profdata /build/llvm/build/profiles/*
'';
};
llvm-nac3-pgo = pkgs.callPackage ./nix/llvm {
stdenv = pkgs.llvmPackages_14.stdenv;
llvm-nac3-pgo = pkgs.callPackage "${self}/llvm" {
stdenv = pkgs.llvmPackages_13.stdenv;
extraCmakeFlags = [ "-DLLVM_PROFDATA_FILE=${nac3artiq-profile}/llvm.profdata" ];
};
nac3artiq-pgo = pkgs.python3Packages.toPythonModule (
pkgs.rustPlatform.buildRustPackage {
name = "nac3artiq-pgo";
src = self;
inherit (nac3artiq) cargoLock;
nativeBuildInputs = [ pkgs.python3 packages.x86_64-linux.llvm-tools-irrt llvm-nac3-pgo ];
cargoLock = { lockFile = ./Cargo.lock; };
nativeBuildInputs = [ pkgs.python3 pkgs.llvmPackages_13.clang-unwrapped llvm-nac3-pgo ];
buildInputs = [ pkgs.python3 llvm-nac3-pgo ];
cargoBuildFlags = [ "--package" "nac3artiq" ];
cargoTestFlags = [ "--package" "nac3ast" "--package" "nac3parser" "--package" "nac3core" "--package" "nac3artiq" ];
@ -161,52 +149,91 @@
);
};
packages.x86_64-w64-mingw32 = import ./nix/windows { inherit pkgs; };
packages.x86_64-w64-mingw32 = rec {
llvm-nac3 = pkgs-mingw.callPackage "${self}/llvm" { inherit (pkgs) llvmPackages_13; };
nac3artiq = pkgs-mingw.python3Packages.toPythonModule (
pkgs-mingw.rustPlatform.buildRustPackage {
name = "nac3artiq";
src = self;
cargoLock = { lockFile = ./Cargo.lock; };
nativeBuildInputs = [ pkgs.llvmPackages_13.clang-unwrapped pkgs.llvmPackages_13.llvm pkgs.zip ];
buildInputs = [ pkgs-mingw.zlib ];
configurePhase =
''
# Link libstdc++ statically. As usual with cargo, this is an adventure.
cp --no-preserve=mode,ownership -R $CARGO_HOME/cargo-vendor-dir/llvm-sys-130.0.3/ llvm-sys-130.0.3
substituteInPlace llvm-sys-130.0.3/build.rs --replace "cargo:rustc-link-lib=dylib=" "cargo:rustc-link-lib=static="
substituteInPlace llvm-sys-130.0.3/build.rs --replace "fn main() {" "fn main() { println!(\"cargo:rustc-link-search=native=${pkgs-mingw.stdenv.cc.cc}/x86_64-w64-mingw32/lib\");"
chmod 755 $CARGO_HOME/cargo-vendor-dir
rm $CARGO_HOME/cargo-vendor-dir/llvm-sys-130.0.3
mv llvm-sys-130.0.3 $CARGO_HOME/cargo-vendor-dir/llvm-sys-130.0.3
devShells.x86_64-linux.default = pkgs.mkShell {
export PYO3_CONFIG_FILE=${pyo3-mingw-config}
mkdir llvm-cfg
cat << EOF > llvm-cfg/llvm-config
#!${pkgs.bash}/bin/bash
set -e
# Gross hack to work around llvm-config asking for the wrong system libraries.
exec ${llvm-nac3.dev}/bin/llvm-config-native \$@ | ${pkgs.gnused}/bin/sed s/-lrt\ -ldl\ -lpthread\ -lm//
EOF
chmod +x llvm-cfg/llvm-config
export PATH=`pwd`/llvm-cfg:$PATH
export CARGO_TARGET_X86_64_PC_WINDOWS_GNU_RUSTFLAGS="-C link-arg=-lz -C link-arg=-luuid -C link-arg=-lole32 -C link-arg=-lmcfgthread"
'';
cargoBuildFlags = [ "--package" "nac3artiq" ];
doCheck = false;
installPhase =
''
mkdir -p $out $out/nix-support
ln -s target/x86_64-pc-windows-gnu/release/nac3artiq.dll nac3artiq.pyd
zip $out/nac3artiq.zip nac3artiq.pyd
echo file binary-dist $out/nac3artiq.zip >> $out/nix-support/hydra-build-products
'';
dontFixup = true;
meta.platforms = ["x86_64-windows"];
}
);
};
devShell.x86_64-linux = pkgs.mkShell {
name = "nac3-dev-shell";
buildInputs = with pkgs; [
# build dependencies
packages.x86_64-linux.llvm-nac3
(pkgs.wrapClangMulti llvmPackages_14.clang) llvmPackages_14.llvm.out # for running nac3standalone demos
packages.x86_64-linux.llvm-tools-irrt
llvmPackages_13.clang-unwrapped # IRRT
cargo
rustc
# runtime dependencies
lld_14 # for running kernels on the host
(packages.x86_64-linux.python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ]))
lld_13
(packages.x86_64-linux.python3-mimalloc.withPackages(ps: [ ps.numpy ]))
# development tools
cargo-insta
clippy
pre-commit
rustfmt
];
shellHook =
''
export DEMO_LINALG_STUB=${packages.x86_64-linux.demo-linalg-stub}/lib/liblinalg.a
export DEMO_LINALG_STUB32=${packages.x86_64-linux.demo-linalg-stub32}/lib/liblinalg.a
'';
};
devShells.x86_64-linux.msys2 = pkgs.mkShell {
name = "nac3-dev-shell-msys2";
buildInputs = with pkgs; [
curl
pacman
fakeroot
packages.x86_64-w64-mingw32.wine-msys2
];
};
hydraJobs = {
inherit (packages.x86_64-linux) llvm-nac3 nac3artiq nac3artiq-pgo;
llvm-nac3-msys2 = packages.x86_64-w64-mingw32.llvm-nac3;
nac3artiq-msys2 = packages.x86_64-w64-mingw32.nac3artiq;
nac3artiq-msys2-pkg = packages.x86_64-w64-mingw32.nac3artiq-pkg;
inherit (packages.x86_64-linux) llvm-nac3 nac3artiq;
llvm-nac3-mingw = packages.x86_64-w64-mingw32.llvm-nac3;
nac3artiq-mingw = packages.x86_64-w64-mingw32.nac3artiq;
mcfgthreads = pkgs-mingw.stdenvNoCC.mkDerivation {
name = "mcfgthreads-hydra";
phases = [ "installPhase" ];
installPhase =
''
mkdir -p $out $out/nix-support
ln -s ${pkgs-mingw.windows.mcfgthreads}/bin/mcfgthread-12.dll $out/
echo file binary-dist $out/mcfgthread-12.dll >> $out/nix-support/hydra-build-products
'';
};
};
};
nixConfig = {
extra-trusted-public-keys = "nixbld.m-labs.hk-1:5aSRVA5b320xbNvu30tqxVPXpld73bhtOeH6uAjRyHc=";
extra-substituters = "https://nixbld.m-labs.hk";
binaryCachePublicKeys = ["nixbld.m-labs.hk-1:5aSRVA5b320xbNvu30tqxVPXpld73bhtOeH6uAjRyHc="];
binaryCaches = ["https://nixbld.m-labs.hk" "https://cache.nixos.org"];
};
}

0
nix/llvm/TLI-musl.patch → llvm/TLI-musl.patch
View File

21
nix/llvm/default.nix → llvm/default.nix
View File

@ -8,6 +8,7 @@
, ncurses
, zlib
, which
, llvmPackages_13
, debugVersion ? false
, enableManpages ? false
, enableSharedLibraries ? false
@ -17,7 +18,7 @@
let
inherit (lib) optional optionals optionalString;
release_version = "14.0.6";
release_version = "13.0.1";
candidate = ""; # empty or "rcN"
dash-candidate = lib.optionalString (candidate != "") "-${candidate}";
version = "${release_version}${dash-candidate}"; # differentiating these (variables) is important for RCs
@ -34,7 +35,7 @@ in stdenv.mkDerivation (rec {
pname = "llvm";
inherit version;
src = fetch pname "sha256-BQki7KrKV4H99mMeqSvHFRg/IC+dLxUUcibwI0FPYZo=";
src = fetch pname "sha256-7GuA2Cw4SsrS3BkpA6bPLNuv+4ibhL+5janXHmMPyDQ=";
unpackPhase = ''
unpackFile $src
@ -49,12 +50,19 @@ in stdenv.mkDerivation (rec {
buildInputs = [ ];
propagatedBuildInputs = [ ncurses zlib ];
propagatedBuildInputs = optionals (stdenv.buildPlatform == stdenv.hostPlatform) [ ncurses ]
++ [ zlib ];
checkInputs = [ which ];
patches = [
./gnu-install-dirs.patch
# Fix random compiler crashes: https://bugs.llvm.org/show_bug.cgi?id=50611
(fetchpatch {
url = "https://raw.githubusercontent.com/archlinux/svntogit-packages/4764a4f8c920912a2bfd8b0eea57273acfe0d8a8/trunk/no-strict-aliasing-DwarfCompileUnit.patch";
sha256 = "18l6mrvm2vmwm77ckcnbjvh6ybvn72rhrb799d4qzwac4x2ifl7g";
stripLen = 1;
})
./llvm-future-riscv-abi.diff
];
@ -112,9 +120,7 @@ in stdenv.mkDerivation (rec {
"-DLLVM_HOST_TRIPLE=${stdenv.hostPlatform.config}"
"-DLLVM_DEFAULT_TARGET_TRIPLE=${stdenv.hostPlatform.config}"
"-DLLVM_ENABLE_UNWIND_TABLES=OFF"
"-DLLVM_ENABLE_THREADS=ON"
"-DLLVM_INCLUDE_BENCHMARKS=OFF"
"-DLLVM_BUILD_TOOLS=OFF"
"-DLLVM_ENABLE_THREADS=OFF"
"-DLLVM_TARGETS_TO_BUILD=X86;ARM;RISCV"
] ++ optionals enableSharedLibraries [
"-DLLVM_LINK_LLVM_DYLIB=ON"
@ -131,6 +137,7 @@ in stdenv.mkDerivation (rec {
"-DCAN_TARGET_i386=false"
] ++ optionals (stdenv.hostPlatform != stdenv.buildPlatform) [
"-DCMAKE_CROSSCOMPILING=True"
"-DLLVM_TABLEGEN=${llvmPackages_13.tools.llvm}/bin/llvm-tblgen"
(
let
nativeCC = pkgsBuildBuild.targetPackages.stdenv.cc;
@ -147,7 +154,6 @@ in stdenv.mkDerivation (rec {
] ++ extraCmakeFlags;
postBuild = ''
make llvm-config
rm -fR $out
'';
@ -156,7 +162,6 @@ in stdenv.mkDerivation (rec {
'';
postInstall = ''
cp bin/llvm-config $out/bin
mkdir -p $python/share
mv $out/share/opt-viewer $python/share/opt-viewer
moveToOutput "bin/llvm-config*" "$dev"

381
llvm/gnu-install-dirs.patch Normal file
View File

@ -0,0 +1,381 @@
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 135036f509d2..265c36f8211b 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -270,15 +270,21 @@ if (CMAKE_BUILD_TYPE AND
message(FATAL_ERROR "Invalid value for CMAKE_BUILD_TYPE: ${CMAKE_BUILD_TYPE}")
endif()
+include(GNUInstallDirs)
+
set(LLVM_LIBDIR_SUFFIX "" CACHE STRING "Define suffix of library directory name (32/64)" )
-set(LLVM_TOOLS_INSTALL_DIR "bin" CACHE STRING "Path for binary subdirectory (defaults to 'bin')")
+set(LLVM_TOOLS_INSTALL_DIR "${CMAKE_INSTALL_BINDIR}" CACHE STRING
+ "Path for binary subdirectory (defaults to 'bin')")
mark_as_advanced(LLVM_TOOLS_INSTALL_DIR)
set(LLVM_UTILS_INSTALL_DIR "${LLVM_TOOLS_INSTALL_DIR}" CACHE STRING
"Path to install LLVM utilities (enabled by LLVM_INSTALL_UTILS=ON) (defaults to LLVM_TOOLS_INSTALL_DIR)")
mark_as_advanced(LLVM_UTILS_INSTALL_DIR)
+set(LLVM_INSTALL_CMAKE_DIR "${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX}/cmake/llvm" CACHE STRING
+ "Path for CMake subdirectory (defaults to lib/cmake/llvm)" )
+
# They are used as destination of target generators.
set(LLVM_RUNTIME_OUTPUT_INTDIR ${CMAKE_CURRENT_BINARY_DIR}/${CMAKE_CFG_INTDIR}/bin)
set(LLVM_LIBRARY_OUTPUT_INTDIR ${CMAKE_CURRENT_BINARY_DIR}/${CMAKE_CFG_INTDIR}/lib${LLVM_LIBDIR_SUFFIX})
@@ -581,9 +587,9 @@ option (LLVM_ENABLE_SPHINX "Use Sphinx to generate llvm documentation." OFF)
option (LLVM_ENABLE_OCAMLDOC "Build OCaml bindings documentation." ON)
option (LLVM_ENABLE_BINDINGS "Build bindings." ON)
-set(LLVM_INSTALL_DOXYGEN_HTML_DIR "share/doc/llvm/doxygen-html"
+set(LLVM_INSTALL_DOXYGEN_HTML_DIR "${CMAKE_INSTALL_DOCDIR}/${project}/doxygen-html"
CACHE STRING "Doxygen-generated HTML documentation install directory")
-set(LLVM_INSTALL_OCAMLDOC_HTML_DIR "share/doc/llvm/ocaml-html"
+set(LLVM_INSTALL_OCAMLDOC_HTML_DIR "${CMAKE_INSTALL_DOCDIR}/${project}/ocaml-html"
CACHE STRING "OCamldoc-generated HTML documentation install directory")
option (LLVM_BUILD_EXTERNAL_COMPILER_RT
@@ -1048,7 +1054,7 @@ endif()
if (NOT LLVM_INSTALL_TOOLCHAIN_ONLY)
install(DIRECTORY include/llvm include/llvm-c
- DESTINATION include
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
COMPONENT llvm-headers
FILES_MATCHING
PATTERN "*.def"
@@ -1059,7 +1065,7 @@ if (NOT LLVM_INSTALL_TOOLCHAIN_ONLY)
)
install(DIRECTORY ${LLVM_INCLUDE_DIR}/llvm ${LLVM_INCLUDE_DIR}/llvm-c
- DESTINATION include
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
COMPONENT llvm-headers
FILES_MATCHING
PATTERN "*.def"
@@ -1073,13 +1079,13 @@ if (NOT LLVM_INSTALL_TOOLCHAIN_ONLY)
if (LLVM_INSTALL_MODULEMAPS)
install(DIRECTORY include/llvm include/llvm-c
- DESTINATION include
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
COMPONENT llvm-headers
FILES_MATCHING
PATTERN "module.modulemap"
)
install(FILES include/llvm/module.install.modulemap
- DESTINATION include/llvm
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/llvm
COMPONENT llvm-headers
RENAME "module.extern.modulemap"
)
diff --git a/cmake/modules/AddLLVM.cmake b/cmake/modules/AddLLVM.cmake
index 9c2b85374307..5531ceeb2eeb 100644
--- a/cmake/modules/AddLLVM.cmake
+++ b/cmake/modules/AddLLVM.cmake
@@ -818,9 +818,9 @@ macro(add_llvm_library name)
get_target_export_arg(${name} LLVM export_to_llvmexports ${umbrella})
install(TARGETS ${name}
${export_to_llvmexports}
- LIBRARY DESTINATION lib${LLVM_LIBDIR_SUFFIX} COMPONENT ${name}
- ARCHIVE DESTINATION lib${LLVM_LIBDIR_SUFFIX} COMPONENT ${name}
- RUNTIME DESTINATION bin COMPONENT ${name})
+ LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX} COMPONENT ${name}
+ ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX} COMPONENT ${name}
+ RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} COMPONENT ${name})
if (NOT LLVM_ENABLE_IDE)
add_llvm_install_targets(install-${name}
@@ -1036,7 +1036,7 @@ function(process_llvm_pass_plugins)
"set(LLVM_STATIC_EXTENSIONS ${LLVM_STATIC_EXTENSIONS})")
install(FILES
${llvm_cmake_builddir}/LLVMConfigExtensions.cmake
- DESTINATION ${LLVM_INSTALL_PACKAGE_DIR}
+ DESTINATION ${LLVM_INSTALL_CMAKE_DIR}
COMPONENT cmake-exports)
set(ExtensionDef "${LLVM_BINARY_DIR}/include/llvm/Support/Extension.def")
@@ -1250,7 +1250,7 @@ macro(add_llvm_example name)
endif()
add_llvm_executable(${name} ${ARGN})
if( LLVM_BUILD_EXAMPLES )
- install(TARGETS ${name} RUNTIME DESTINATION examples)
+ install(TARGETS ${name} RUNTIME DESTINATION ${CMAKE_INSTALL_DOCDIR}/examples)
endif()
set_target_properties(${name} PROPERTIES FOLDER "Examples")
endmacro(add_llvm_example name)
@@ -1868,7 +1868,7 @@ function(llvm_install_library_symlink name dest type)
set(full_name ${CMAKE_${type}_LIBRARY_PREFIX}${name}${CMAKE_${type}_LIBRARY_SUFFIX})
set(full_dest ${CMAKE_${type}_LIBRARY_PREFIX}${dest}${CMAKE_${type}_LIBRARY_SUFFIX})
- set(output_dir lib${LLVM_LIBDIR_SUFFIX})
+ set(output_dir ${CMAKE_INSTALL_FULL_LIBDIR}${LLVM_LIBDIR_SUFFIX})
if(WIN32 AND "${type}" STREQUAL "SHARED")
set(output_dir bin)
endif()
@@ -1879,7 +1879,7 @@ function(llvm_install_library_symlink name dest type)
endfunction()
-function(llvm_install_symlink name dest)
+function(llvm_install_symlink name dest output_dir)
cmake_parse_arguments(ARG "ALWAYS_GENERATE" "COMPONENT" "" ${ARGN})
foreach(path ${CMAKE_MODULE_PATH})
if(EXISTS ${path}/LLVMInstallSymlink.cmake)
@@ -1902,7 +1902,7 @@ function(llvm_install_symlink name dest)
set(full_dest ${dest}${CMAKE_EXECUTABLE_SUFFIX})
install(SCRIPT ${INSTALL_SYMLINK}
- CODE "install_symlink(${full_name} ${full_dest} ${LLVM_TOOLS_INSTALL_DIR})"
+ CODE "install_symlink(${full_name} ${full_dest} ${output_dir})"
COMPONENT ${component})
if (NOT LLVM_ENABLE_IDE AND NOT ARG_ALWAYS_GENERATE)
@@ -1985,7 +1985,8 @@ function(add_llvm_tool_symlink link_name target)
endif()
if ((TOOL_IS_TOOLCHAIN OR NOT LLVM_INSTALL_TOOLCHAIN_ONLY) AND LLVM_BUILD_TOOLS)
- llvm_install_symlink(${link_name} ${target})
+ GNUInstallDirs_get_absolute_install_dir(output_dir LLVM_TOOLS_INSTALL_DIR)
+ llvm_install_symlink(${link_name} ${target} ${output_dir})
endif()
endif()
endfunction()
@@ -2114,9 +2115,9 @@ function(llvm_setup_rpath name)
# Since BUILD_SHARED_LIBS is only recommended for use by developers,
# hardcode the rpath to build/install lib dir first in this mode.
# FIXME: update this when there is better solution.
- set(_install_rpath "${LLVM_LIBRARY_OUTPUT_INTDIR}" "${CMAKE_INSTALL_PREFIX}/lib${LLVM_LIBDIR_SUFFIX}" ${extra_libdir})
+ set(_install_rpath "${LLVM_LIBRARY_OUTPUT_INTDIR}" "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX}" ${extra_libdir})
elseif(UNIX)
- set(_install_rpath "\$ORIGIN/../lib${LLVM_LIBDIR_SUFFIX}" ${extra_libdir})
+ set(_install_rpath "\$ORIGIN/../${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX}" ${extra_libdir})
if(${CMAKE_SYSTEM_NAME} MATCHES "(FreeBSD|DragonFly)")
set_property(TARGET ${name} APPEND_STRING PROPERTY
LINK_FLAGS " -Wl,-z,origin ")
diff --git a/cmake/modules/AddOCaml.cmake b/cmake/modules/AddOCaml.cmake
index 554046b20edf..4d1ad980641e 100644
--- a/cmake/modules/AddOCaml.cmake
+++ b/cmake/modules/AddOCaml.cmake
@@ -144,9 +144,9 @@ function(add_ocaml_library name)
endforeach()
if( APPLE )
- set(ocaml_rpath "@executable_path/../../../lib${LLVM_LIBDIR_SUFFIX}")
+ set(ocaml_rpath "@executable_path/../../../${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX}")
elseif( UNIX )
- set(ocaml_rpath "\\$ORIGIN/../../../lib${LLVM_LIBDIR_SUFFIX}")
+ set(ocaml_rpath "\\$ORIGIN/../../../${CMAKE_INSTALL_LIBDIR}${LLVM_LIBDIR_SUFFIX}")
endif()
list(APPEND ocaml_flags "-ldopt" "-Wl,-rpath,${ocaml_rpath}")
diff --git a/cmake/modules/AddSphinxTarget.cmake b/cmake/modules/AddSphinxTarget.cmake
index e80c3b5c1cac..482f6d715ef5 100644
--- a/cmake/modules/AddSphinxTarget.cmake
+++ b/cmake/modules/AddSphinxTarget.cmake
@@ -90,7 +90,7 @@ function (add_sphinx_target builder project)
endif()
elseif (builder STREQUAL html)
string(TOUPPER "${project}" project_upper)
- set(${project_upper}_INSTALL_SPHINX_HTML_DIR "share/doc/${project}/html"
+ set(${project_upper}_INSTALL_SPHINX_HTML_DIR "${CMAKE_INSTALL_DOCDIR}/${project}/html"
CACHE STRING "HTML documentation install directory for ${project}")
# '/.' indicates: copy the contents of the directory directly into
diff --git a/cmake/modules/CMakeLists.txt b/cmake/modules/CMakeLists.txt
index 51b6a4fdc284..4adc2acfc074 100644
--- a/cmake/modules/CMakeLists.txt
+++ b/cmake/modules/CMakeLists.txt
@@ -1,6 +1,6 @@
include(LLVMDistributionSupport)
-set(LLVM_INSTALL_PACKAGE_DIR lib${LLVM_LIBDIR_SUFFIX}/cmake/llvm)
+set(LLVM_INSTALL_PACKAGE_DIR ${LLVM_INSTALL_CMAKE_DIR} CACHE STRING "Path for CMake subdirectory (defaults to 'cmake/llvm')")
set(llvm_cmake_builddir "${LLVM_BINARY_DIR}/${LLVM_INSTALL_PACKAGE_DIR}")
# First for users who use an installed LLVM, create the LLVMExports.cmake file.
@@ -109,13 +109,13 @@ foreach(p ${_count})
set(LLVM_CONFIG_CODE "${LLVM_CONFIG_CODE}
get_filename_component(LLVM_INSTALL_PREFIX \"\${LLVM_INSTALL_PREFIX}\" PATH)")
endforeach(p)
-set(LLVM_CONFIG_INCLUDE_DIRS "\${LLVM_INSTALL_PREFIX}/include")
+set(LLVM_CONFIG_INCLUDE_DIRS "\${LLVM_INSTALL_PREFIX}/${CMAKE_INSTALL_INCLUDEDIR}")
set(LLVM_CONFIG_INCLUDE_DIR "${LLVM_CONFIG_INCLUDE_DIRS}")
set(LLVM_CONFIG_MAIN_INCLUDE_DIR "${LLVM_CONFIG_INCLUDE_DIRS}")
-set(LLVM_CONFIG_LIBRARY_DIRS "\${LLVM_INSTALL_PREFIX}/lib\${LLVM_LIBDIR_SUFFIX}")
+set(LLVM_CONFIG_LIBRARY_DIRS "\${LLVM_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}\${LLVM_LIBDIR_SUFFIX}")
set(LLVM_CONFIG_CMAKE_DIR "\${LLVM_INSTALL_PREFIX}/${LLVM_INSTALL_PACKAGE_DIR}")
set(LLVM_CONFIG_BINARY_DIR "\${LLVM_INSTALL_PREFIX}")
-set(LLVM_CONFIG_TOOLS_BINARY_DIR "\${LLVM_INSTALL_PREFIX}/bin")
+set(LLVM_CONFIG_TOOLS_BINARY_DIR "\${LLVM_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}")
# Generate a default location for lit
if (LLVM_INSTALL_UTILS AND LLVM_BUILD_UTILS)
diff --git a/cmake/modules/LLVMInstallSymlink.cmake b/cmake/modules/LLVMInstallSymlink.cmake
index 3e6a2c9a2648..52e14d955c60 100644
--- a/cmake/modules/LLVMInstallSymlink.cmake
+++ b/cmake/modules/LLVMInstallSymlink.cmake
@@ -4,7 +4,7 @@
function(install_symlink name target outdir)
set(DESTDIR $ENV{DESTDIR})
- set(bindir "${DESTDIR}${CMAKE_INSTALL_PREFIX}/${outdir}/")
+ set(bindir "${DESTDIR}${outdir}/")
message(STATUS "Creating ${name}")
diff --git a/docs/CMake.rst b/docs/CMake.rst
index f1ac2c7d4934..c6e1469b5e13 100644
--- a/docs/CMake.rst
+++ b/docs/CMake.rst
@@ -202,7 +202,7 @@ CMake manual, or execute ``cmake --help-variable VARIABLE_NAME``.
**LLVM_LIBDIR_SUFFIX**:STRING
Extra suffix to append to the directory where libraries are to be
installed. On a 64-bit architecture, one could use ``-DLLVM_LIBDIR_SUFFIX=64``
- to install libraries to ``/usr/lib64``.
+ to install libraries to ``/usr/lib64``. See also ``CMAKE_INSTALL_LIBDIR``.
Rarely-used CMake variables
---------------------------
@@ -551,8 +551,8 @@ LLVM-specific variables
**LLVM_INSTALL_DOXYGEN_HTML_DIR**:STRING
The path to install Doxygen-generated HTML documentation to. This path can
- either be absolute or relative to the CMAKE_INSTALL_PREFIX. Defaults to
- `share/doc/llvm/doxygen-html`.
+ either be absolute or relative to the ``CMAKE_INSTALL_PREFIX``. Defaults to
+ `${CMAKE_INSTALL_DOCDIR}/${project}/doxygen-html`.
**LLVM_LINK_LLVM_DYLIB**:BOOL
If enabled, tools will be linked with the libLLVM shared library. Defaults
@@ -792,9 +792,11 @@ the ``cmake`` command or by setting it directly in ``ccmake`` or ``cmake-gui``).
This file is available in two different locations.
-* ``<INSTALL_PREFIX>/lib/cmake/llvm/LLVMConfig.cmake`` where
- ``<INSTALL_PREFIX>`` is the install prefix of an installed version of LLVM.
- On Linux typically this is ``/usr/lib/cmake/llvm/LLVMConfig.cmake``.
+* ``<LLVM_INSTALL_PACKAGE_DIR>LLVMConfig.cmake`` where
+ ``<LLVM_INSTALL_PACKAGE_DIR>`` is the location where LLVM CMake modules are
+ installed as part of an installed version of LLVM. This is typically
+ ``cmake/llvm/`` within the lib directory. On Linux, this is typically
+ ``/usr/lib/cmake/llvm/LLVMConfig.cmake``.
* ``<LLVM_BUILD_ROOT>/lib/cmake/llvm/LLVMConfig.cmake`` where
``<LLVM_BUILD_ROOT>`` is the root of the LLVM build tree. **Note: this is only
diff --git a/examples/Bye/CMakeLists.txt b/examples/Bye/CMakeLists.txt
index bb96edb4b4bf..678c22fb43c8 100644
--- a/examples/Bye/CMakeLists.txt
+++ b/examples/Bye/CMakeLists.txt
@@ -14,6 +14,6 @@ if (NOT WIN32)
BUILDTREE_ONLY
)
- install(TARGETS ${name} RUNTIME DESTINATION examples)
+ install(TARGETS ${name} RUNTIME DESTINATION ${CMAKE_INSTALL_DOCDIR}/examples)
set_target_properties(${name} PROPERTIES FOLDER "Examples")
endif()
diff --git a/include/llvm/CMakeLists.txt b/include/llvm/CMakeLists.txt
index b46319f24fc8..2feabd1954e4 100644
--- a/include/llvm/CMakeLists.txt
+++ b/include/llvm/CMakeLists.txt
@@ -5,5 +5,5 @@ add_subdirectory(Frontend)
# If we're doing an out-of-tree build, copy a module map for generated
# header files into the build area.
if (NOT "${CMAKE_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
- configure_file(module.modulemap.build module.modulemap COPYONLY)
+ configure_file(module.modulemap.build ${LLVM_INCLUDE_DIR}/module.modulemap COPYONLY)
endif (NOT "${CMAKE_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
diff --git a/tools/llvm-config/BuildVariables.inc.in b/tools/llvm-config/BuildVariables.inc.in
index ebe5b73a5c65..70c497be12f5 100644
--- a/tools/llvm-config/BuildVariables.inc.in
+++ b/tools/llvm-config/BuildVariables.inc.in
@@ -23,6 +23,10 @@
#define LLVM_CXXFLAGS "@LLVM_CXXFLAGS@"
#define LLVM_BUILDMODE "@LLVM_BUILDMODE@"
#define LLVM_LIBDIR_SUFFIX "@LLVM_LIBDIR_SUFFIX@"
+#define LLVM_INSTALL_BINDIR "@CMAKE_INSTALL_BINDIR@"
+#define LLVM_INSTALL_LIBDIR "@CMAKE_INSTALL_LIBDIR@"
+#define LLVM_INSTALL_INCLUDEDIR "@CMAKE_INSTALL_INCLUDEDIR@"
+#define LLVM_INSTALL_CMAKEDIR "@LLVM_INSTALL_CMAKE_DIR@"
#define LLVM_TARGETS_BUILT "@LLVM_TARGETS_BUILT@"
#define LLVM_SYSTEM_LIBS "@LLVM_SYSTEM_LIBS@"
#define LLVM_BUILD_SYSTEM "@LLVM_BUILD_SYSTEM@"
diff --git a/tools/llvm-config/llvm-config.cpp b/tools/llvm-config/llvm-config.cpp
index 1a2f04552d13..44fa7d3eec6b 100644
--- a/tools/llvm-config/llvm-config.cpp
+++ b/tools/llvm-config/llvm-config.cpp
@@ -357,12 +357,26 @@ int main(int argc, char **argv) {
("-I" + ActiveIncludeDir + " " + "-I" + ActiveObjRoot + "/include");
} else {
ActivePrefix = CurrentExecPrefix;
- ActiveIncludeDir = ActivePrefix + "/include";
- SmallString<256> path(StringRef(LLVM_TOOLS_INSTALL_DIR));
- sys::fs::make_absolute(ActivePrefix, path);
- ActiveBinDir = std::string(path.str());
- ActiveLibDir = ActivePrefix + "/lib" + LLVM_LIBDIR_SUFFIX;
- ActiveCMakeDir = ActiveLibDir + "/cmake/llvm";
+ {
+ SmallString<256> path(StringRef(LLVM_INSTALL_INCLUDEDIR));
+ sys::fs::make_absolute(ActivePrefix, path);
+ ActiveIncludeDir = std::string(path.str());
+ }
+ {
+ SmallString<256> path(StringRef(LLVM_INSTALL_BINDIR));
+ sys::fs::make_absolute(ActivePrefix, path);
+ ActiveBinDir = std::string(path.str());
+ }
+ {
+ SmallString<256> path(StringRef(LLVM_INSTALL_LIBDIR LLVM_LIBDIR_SUFFIX));
+ sys::fs::make_absolute(ActivePrefix, path);
+ ActiveLibDir = std::string(path.str());
+ }
+ {
+ SmallString<256> path(StringRef(LLVM_INSTALL_CMAKEDIR));
+ sys::fs::make_absolute(ActivePrefix, path);
+ ActiveCMakeDir = std::string(path.str());
+ }
ActiveIncludeOption = "-I" + ActiveIncludeDir;
}
diff --git a/tools/lto/CMakeLists.txt b/tools/lto/CMakeLists.txt
index 0af29ad762c5..37b99b83e35c 100644
--- a/tools/lto/CMakeLists.txt
+++ b/tools/lto/CMakeLists.txt
@@ -33,7 +33,7 @@ add_llvm_library(${LTO_LIBRARY_NAME} ${LTO_LIBRARY_TYPE} INSTALL_WITH_TOOLCHAIN
${SOURCES} DEPENDS intrinsics_gen)
install(FILES ${LLVM_MAIN_INCLUDE_DIR}/llvm-c/lto.h
- DESTINATION include/llvm-c
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/llvm-c
COMPONENT LTO)
if (APPLE)
diff --git a/tools/opt-viewer/CMakeLists.txt b/tools/opt-viewer/CMakeLists.txt
index ead73ec13a8f..250362021f17 100644
--- a/tools/opt-viewer/CMakeLists.txt
+++ b/tools/opt-viewer/CMakeLists.txt
@@ -8,7 +8,7 @@ set (files
foreach (file ${files})
install(PROGRAMS ${file}
- DESTINATION share/opt-viewer
+ DESTINATION ${CMAKE_INSTALL_DATADIR}/opt-viewer
COMPONENT opt-viewer)
endforeach (file)
diff --git a/tools/remarks-shlib/CMakeLists.txt b/tools/remarks-shlib/CMakeLists.txt
index 865436247270..ce1daa62f6ab 100644
--- a/tools/remarks-shlib/CMakeLists.txt
+++ b/tools/remarks-shlib/CMakeLists.txt
@@ -19,7 +19,7 @@ if(LLVM_ENABLE_PIC)
endif()
install(FILES ${LLVM_MAIN_INCLUDE_DIR}/llvm-c/Remarks.h
- DESTINATION include/llvm-c
+ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/llvm-c
COMPONENT Remarks)
if (APPLE)

0
nix/llvm/llvm-future-riscv-abi.diff → llvm/llvm-future-riscv-abi.diff
View File

0
nix/llvm/outputs.patch → llvm/outputs.patch
View File

56
nac3.svg
View File

@ -1,56 +0,0 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<svg
id="a"
width="128"
height="128"
viewBox="0 0 95.99999 95.99999"
version="1.1"
sodipodi:docname="nac3.svg"
inkscape:version="1.1.1 (3bf5ae0d25, 2021-09-20)"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns="http://www.w3.org/2000/svg"
xmlns:svg="http://www.w3.org/2000/svg">
<defs
id="defs11" />
<sodipodi:namedview
id="namedview9"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageshadow="2"
inkscape:pageopacity="0.0"
inkscape:pagecheckerboard="0"
inkscape:document-units="mm"
showgrid="false"
units="px"
width="128px"
inkscape:zoom="5.9448568"
inkscape:cx="60.472441"
inkscape:cy="60.556547"
inkscape:window-width="2560"
inkscape:window-height="1371"
inkscape:window-x="0"
inkscape:window-y="32"
inkscape:window-maximized="1"
inkscape:current-layer="a" />
<rect
x="40.072601"
y="-26.776209"
width="55.668747"
height="55.668747"
transform="matrix(0.71803815,0.69600374,-0.71803815,0.69600374,0,0)"
style="fill:#be211e;stroke:#000000;stroke-width:4.37375px;stroke-linecap:round;stroke-linejoin:round"
id="rect2" />
<line
x1="38.00692"
y1="63.457153"
x2="57.993061"
y2="63.457153"
style="fill:none;stroke:#000000;stroke-width:4.37269px;stroke-linecap:round;stroke-linejoin:round"
id="line4" />
<path
d="m 48.007301,57.843329 c -1.943097,0 -3.877522,-0.41727 -5.686157,-1.246007 -3.218257,-1.474616 -5.650382,-4.075418 -6.849639,-7.323671 -2.065624,-5.588921 -1.192751,-10.226647 2.575258,-13.827 0.611554,-0.584909 1.518048,-0.773041 2.323689,-0.488206 0.80673,0.286405 1.369495,0.998486 1.447563,1.827234 0.237469,2.549302 2.439719,5.917376 4.28414,6.55273 0.396859,0.13506 0.820953,-0.05859 1.097084,-0.35222 0.339254,-0.360754 0.451065,-0.961893 -1.013597,-3.191372 -2.089851,-3.181137 -4.638728,-8.754903 -0.262407,-15.069853 0.494457,-0.713491 1.384673,-1.068907 2.256469,-0.909156 0.871795,0.161332 1.583757,0.806404 1.752251,1.651189 0.716448,3.591862 2.962357,6.151755 5.199306,8.023138 1.935503,1.61861 4.344688,3.867387 5.435687,7.096643 2.283183,6.758017 -1.202511,14.114988 -8.060822,16.494025 -1.467083,0.509226 -2.98513,0.762536 -4.498836,0.762536 z M 39.358865,40.002192 c -0.304711,0.696206 -0.541636,2.080524 -0.56865,2.237454 -0.330316,1.918771 0.168305,3.803963 0.846157,5.539951 0.856828,2.19436 2.437543,3.942467 4.583411,4.925713 2.143691,0.981675 4.554131,1.097816 6.789992,0.322666 4.571485,-1.586549 6.977584,-6.532238 5.363036,-11.02597 v -5.27e-4 C 55.455481,39.447968 54.023463,38.162043 52.221335,36.65432 50.876945,35.529534 49.409662,33.987726 48.417983,32.135555 48.01343,31.37996 47.79547,30.34303 47.76669,29.413263 c -0.187481,0.669514 -0.212441,2.325923 -0.150396,2.93691 0.179209,1.764456 1.333476,3.644546 2.340611,5.171243 1.311568,1.988179 2.72058,6.037272 0.459681,8.367985 -1.54192,1.58953 -4.038511,2.052034 -5.839973,1.38492 -2.398314,-0.888147 -3.942744,-2.690627 -4.941118,-4.768029 -0.121194,-0.25217 -0.532464,-1.174187 -0.276619,-2.5041 z"
id="path6"
style="stroke-width:1.09317" />
</svg>
Side by Side

Before

Width:  |  Height:  |  Size: 3.3 KiB

17
nac3artiq/Cargo.toml
View File

@ -2,20 +2,23 @@
name = "nac3artiq"
version = "0.1.0"
authors = ["M-Labs"]
edition = "2021"
edition = "2018"
[lib]
name = "nac3artiq"
crate-type = ["cdylib"]
[dependencies]
itertools = "0.13"
pyo3 = { version = "0.21", features = ["extension-module", "gil-refs"] }
parking_lot = "0.12"
tempfile = "3.13"
pyo3 = { version = "0.14", features = ["extension-module"] }
parking_lot = "0.11"
tempfile = "3"
nac3parser = { path = "../nac3parser" }
nac3core = { path = "../nac3core" }
nac3ld = { path = "../nac3ld" }
[dependencies.inkwell]
version = "0.1.0-beta.4"
default-features = false
features = ["llvm13-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
[features]
init-llvm-profile = []
no-escape-analysis = ["nac3core/no-escape-analysis"]

6
nac3artiq/demo/demo.py
View File

@ -1,4 +1,10 @@
from min_artiq import *
from numpy import int32, int64
@extern
def output_int(x: int32):
...
@nac3

11
nac3artiq/demo/embedding_map.py
View File

@ -5,7 +5,6 @@ class EmbeddingMap:
self.string_map = {}
self.string_reverse_map = {}
self.function_map = {}
self.attributes_writeback = []
# preallocate exception names
self.preallocate_runtime_exception_names(["RuntimeError",
@ -17,15 +16,7 @@ class EmbeddingMap:
"CacheError",
"SPIError",
"0:ZeroDivisionError",
"0:IndexError",
"0:ValueError",
"0:RuntimeError",
"0:AssertionError",
"0:KeyError",
"0:NotImplementedError",
"0:OverflowError",
"0:IOError",
"0:UnwrapNoneError"])
"0:IndexError"])
def preallocate_runtime_exception_names(self, names):
for i, name in enumerate(names):

24
nac3artiq/demo/list_cmp.py
View File

@ -1,24 +0,0 @@
from min_artiq import *
from numpy import int32
@nac3
class EmptyList:
core: KernelInvariant[Core]
def __init__(self):
self.core = Core()
@rpc
def get_empty(self) -> list[int32]:
return []
@kernel
def run(self):
a: list[int32] = self.get_empty()
if a != []:
raise ValueError
if __name__ == "__main__":
EmptyList().run()

68
nac3artiq/demo/min_artiq.py
View File

@ -10,8 +10,7 @@ from embedding_map import EmbeddingMap
__all__ = [
"Kernel", "KernelInvariant", "virtual", "ConstGeneric",
"Option", "Some", "none", "UnwrapNoneError",
"Kernel", "KernelInvariant", "virtual",
"round64", "floor64", "ceil64",
"extern", "kernel", "portable", "nac3",
"rpc", "ms", "us", "ns",
@ -33,45 +32,6 @@ class KernelInvariant(Generic[T]):
class virtual(Generic[T]):
pass
class Option(Generic[T]):
_nac3_option: T
def __init__(self, v: T):
self._nac3_option = v
def is_none(self):
return self._nac3_option is None
def is_some(self):
return not self.is_none()
def unwrap(self):
if self.is_none():
raise UnwrapNoneError()
return self._nac3_option
def __repr__(self) -> str:
if self.is_none():
return "none"
else:
return "Some({})".format(repr(self._nac3_option))
def __str__(self) -> str:
if self.is_none():
return "none"
else:
return "Some({})".format(str(self._nac3_option))
def Some(v: T) -> Option[T]:
return Option(v)
none = Option(None)
class _ConstGenericMarker:
pass
def ConstGeneric(name, constraint):
return TypeVar(name, _ConstGenericMarker, constraint)
def round64(x):
return round(x)
@ -86,13 +46,7 @@ def ceil64(x):
import device_db
core_arguments = device_db.device_db["core"]["arguments"]
artiq_builtins = {
"none": none,
"virtual": virtual,
"_ConstGenericMarker": _ConstGenericMarker,
"Option": Option,
}
compiler = nac3artiq.NAC3(core_arguments["target"], artiq_builtins)
compiler = nac3artiq.NAC3(core_arguments["target"])
allow_registration = True
# Delay NAC3 analysis until all referenced variables are supposed to exist on the CPython side.
registered_functions = set()
@ -112,15 +66,10 @@ def extern(function):
register_function(function)
return function
def rpc(arg=None, flags={}):
"""Decorates a function or method to be executed on the host interpreter."""
if arg is None:
def inner_decorator(function):
return rpc(function, flags)
return inner_decorator
register_function(arg)
return arg
def rpc(function):
"""Decorates a function declaration defined by the core device runtime."""
register_function(function)
return function
def kernel(function_or_method):
"""Decorates a function or method to be executed on the core device."""
@ -291,10 +240,5 @@ class KernelContextManager:
def __exit__(self):
pass
@nac3
class UnwrapNoneError(Exception):
"""raised when unwrapping a none value"""
artiq_builtin = True
parallel = KernelContextManager()
sequential = KernelContextManager()

26
nac3artiq/demo/str_abi.py
View File

@ -1,26 +0,0 @@
from min_artiq import *
from numpy import ndarray, zeros as np_zeros
@nac3
class StrFail:
core: KernelInvariant[Core]
def __init__(self):
self.core = Core()
@kernel
def hello(self, arg: str):
pass
@kernel
def consume_ndarray(self, arg: ndarray[str, 1]):
pass
def run(self):
self.hello("world")
self.consume_ndarray(np_zeros([10], dtype=str))
if __name__ == "__main__":
StrFail().run()

24
nac3artiq/demo/string_attribute_issue337.py
View File

@ -1,24 +0,0 @@
from min_artiq import *
from numpy import int32
@nac3
class Demo:
core: KernelInvariant[Core]
attr1: KernelInvariant[str]
attr2: KernelInvariant[int32]
def __init__(self):
self.core = Core()
self.attr2 = 32
self.attr1 = "SAMPLE"
@kernel
def run(self):
print_int32(self.attr2)
self.attr1
if __name__ == "__main__":
Demo().run()

40
nac3artiq/demo/support_class_attr_issue102.py
View File

@ -1,40 +0,0 @@
from min_artiq import *
from numpy import int32
@nac3
class Demo:
attr1: KernelInvariant[int32] = 2
attr2: int32 = 4
attr3: Kernel[int32]
@kernel
def __init__(self):
self.attr3 = 8
@nac3
class NAC3Devices:
core: KernelInvariant[Core]
attr4: KernelInvariant[int32] = 16
def __init__(self):
self.core = Core()
@kernel
def run(self):
Demo.attr1 # Supported
# Demo.attr2 # Field not accessible on Kernel
# Demo.attr3 # Only attributes can be accessed in this way
# Demo.attr1 = 2 # Attributes are immutable
self.attr4 # Attributes can be accessed within class
obj = Demo()
obj.attr1 # Attributes can be accessed by class objects
NAC3Devices.attr4 # Attributes accessible for classes without __init__
if __name__ == "__main__":
NAC3Devices().run()

1683
nac3artiq/src/codegen.rs
View File

File diff suppressed because it is too large Load Diff

1114
nac3artiq/src/lib.rs
View File

File diff suppressed because it is too large Load Diff

1257
nac3artiq/src/symbol_resolver.rs
View File

File diff suppressed because it is too large Load Diff

450
nac3artiq/src/timeline.rs
View File

@ -1,23 +1,10 @@
use itertools::Either;
use inkwell::{values::BasicValueEnum, AddressSpace, AtomicOrdering};
use nac3core::codegen::CodeGenContext;
use nac3core::{
codegen::CodeGenContext,
inkwell::{
values::{BasicValueEnum, CallSiteValue},
AddressSpace, AtomicOrdering,
},
};
/// Functions for manipulating the timeline.
pub trait TimeFns {
/// Emits LLVM IR for `now_mu`.
fn emit_now_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>) -> BasicValueEnum<'ctx>;
/// Emits LLVM IR for `at_mu`.
fn emit_at_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, t: BasicValueEnum<'ctx>);
/// Emits LLVM IR for `delay_mu`.
fn emit_delay_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, dt: BasicValueEnum<'ctx>);
fn emit_now_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>) -> BasicValueEnum<'ctx>;
fn emit_at_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>, t: BasicValueEnum<'ctx>);
fn emit_delay_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>, dt: BasicValueEnum<'ctx>);
}
pub struct NowPinningTimeFns64 {}
@ -25,143 +12,141 @@ pub struct NowPinningTimeFns64 {}
// For FPGA design reasons, on VexRiscv with 64-bit data bus, the "now" CSR is split into two 32-bit
// values that are each padded to 64-bits.
impl TimeFns for NowPinningTimeFns64 {
fn emit_now_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>) -> BasicValueEnum<'ctx> {
fn emit_now_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>) -> BasicValueEnum<'ctx> {
let i64_type = ctx.ctx.i64_type();
let i32_type = ctx.ctx.i32_type();
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx
.builder
.build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
.map(BasicValueEnum::into_pointer_value)
.unwrap();
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now.lo.addr")
let now_hiptr =
ctx.builder.build_bitcast(now, i32_type.ptr_type(AddressSpace::Generic), "now_hiptr");
if let BasicValueEnum::PointerValue(now_hiptr) = now_hiptr {
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now_gep")
};
if let (BasicValueEnum::IntValue(now_hi), BasicValueEnum::IntValue(now_lo)) = (
ctx.builder.build_load(now_hiptr, "now_hi"),
ctx.builder.build_load(now_loptr, "now_lo"),
) {
let zext_hi = ctx.builder.build_int_z_extend(now_hi, i64_type, "now_zext_hi");
let shifted_hi = ctx.builder.build_left_shift(
zext_hi,
i64_type.const_int(32, false),
"now_shifted_zext_hi",
);
let zext_lo = ctx.builder.build_int_z_extend(now_lo, i64_type, "now_zext_lo");
ctx.builder.build_or(shifted_hi, zext_lo, "now_or").into()
} else {
unreachable!();
}
} else {
unreachable!();
}
.unwrap();
let now_hi = ctx
.builder
.build_load(now_hiptr, "now.hi")
.map(BasicValueEnum::into_int_value)
.unwrap();
let now_lo = ctx
.builder
.build_load(now_loptr, "now.lo")
.map(BasicValueEnum::into_int_value)
.unwrap();
let zext_hi = ctx.builder.build_int_z_extend(now_hi, i64_type, "").unwrap();
let shifted_hi =
ctx.builder.build_left_shift(zext_hi, i64_type.const_int(32, false), "").unwrap();
let zext_lo = ctx.builder.build_int_z_extend(now_lo, i64_type, "").unwrap();
ctx.builder.build_or(shifted_hi, zext_lo, "now_mu").map(Into::into).unwrap()
}
fn emit_at_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, t: BasicValueEnum<'ctx>) {
fn emit_at_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>, t: BasicValueEnum<'ctx>) {
let i32_type = ctx.ctx.i32_type();
let i64_type = ctx.ctx.i64_type();
let i64_32 = i64_type.const_int(32, false);
let time = t.into_int_value();
let time_hi = ctx
.builder
.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "time.hi").unwrap(),
if let BasicValueEnum::IntValue(time) = t {
let time_hi = ctx.builder.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "now_lshr"),
i32_type,
"",
)
.unwrap();
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "time.lo").unwrap();
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx
.builder
.build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
.map(BasicValueEnum::into_pointer_value)
.unwrap();
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now.lo.addr")
"now_trunc",
);
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "now_trunc");
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx.builder.build_bitcast(
now,
i32_type.ptr_type(AddressSpace::Generic),
"now_bitcast",
);
if let BasicValueEnum::PointerValue(now_hiptr) = now_hiptr {
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now_gep")
};
ctx.builder
.build_store(now_hiptr, time_hi)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
} else {
unreachable!();
}
} else {
unreachable!();
}
.unwrap();
ctx.builder
.build_store(now_hiptr, time_hi)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
}
fn emit_delay_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, dt: BasicValueEnum<'ctx>) {
fn emit_delay_mu<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, 'a>,
dt: BasicValueEnum<'ctx>,
) {
let i64_type = ctx.ctx.i64_type();
let i32_type = ctx.ctx.i32_type();
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx
.builder
.build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
.map(BasicValueEnum::into_pointer_value)
.unwrap();
let now_hiptr =
ctx.builder.build_bitcast(now, i32_type.ptr_type(AddressSpace::Generic), "now_hiptr");
if let BasicValueEnum::PointerValue(now_hiptr) = now_hiptr {
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now_loptr")
};
if let (
BasicValueEnum::IntValue(now_hi),
BasicValueEnum::IntValue(now_lo),
BasicValueEnum::IntValue(dt),
) = (
ctx.builder.build_load(now_hiptr, "now_hi"),
ctx.builder.build_load(now_loptr, "now_lo"),
dt,
) {
let zext_hi = ctx.builder.build_int_z_extend(now_hi, i64_type, "now_zext_hi");
let shifted_hi = ctx.builder.build_left_shift(
zext_hi,
i64_type.const_int(32, false),
"now_shifted_zext_hi",
);
let zext_lo = ctx.builder.build_int_z_extend(now_lo, i64_type, "now_zext_lo");
let now_val = ctx.builder.build_or(shifted_hi, zext_lo, "now_or");
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(2, false)], "now.lo.addr")
}
.unwrap();
let time = ctx.builder.build_int_add(now_val, dt, "now_add");
let time_hi = ctx.builder.build_int_truncate(
ctx.builder.build_right_shift(
time,
i64_type.const_int(32, false),
false,
"now_lshr",
),
i32_type,
"now_trunc",
);
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "now_trunc");
let now_hi = ctx
.builder
.build_load(now_hiptr, "now.hi")
.map(BasicValueEnum::into_int_value)
.unwrap();
let now_lo = ctx
.builder
.build_load(now_loptr, "now.lo")
.map(BasicValueEnum::into_int_value)
.unwrap();
let dt = dt.into_int_value();
let zext_hi = ctx.builder.build_int_z_extend(now_hi, i64_type, "").unwrap();
let shifted_hi =
ctx.builder.build_left_shift(zext_hi, i64_type.const_int(32, false), "").unwrap();
let zext_lo = ctx.builder.build_int_z_extend(now_lo, i64_type, "").unwrap();
let now_val = ctx.builder.build_or(shifted_hi, zext_lo, "now").unwrap();
let time = ctx.builder.build_int_add(now_val, dt, "time").unwrap();
let time_hi = ctx
.builder
.build_int_truncate(
ctx.builder
.build_right_shift(time, i64_type.const_int(32, false), false, "")
.unwrap(),
i32_type,
"time.hi",
)
.unwrap();
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "time.lo").unwrap();
ctx.builder
.build_store(now_hiptr, time_hi)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
.build_store(now_hiptr, time_hi)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
} else {
unreachable!();
}
} else {
unreachable!();
};
}
}
@ -170,115 +155,110 @@ pub static NOW_PINNING_TIME_FNS_64: NowPinningTimeFns64 = NowPinningTimeFns64 {}
pub struct NowPinningTimeFns {}
impl TimeFns for NowPinningTimeFns {
fn emit_now_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>) -> BasicValueEnum<'ctx> {
fn emit_now_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>) -> BasicValueEnum<'ctx> {
let i64_type = ctx.ctx.i64_type();
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_raw = ctx
.builder
.build_load(now.as_pointer_value(), "now")
.map(BasicValueEnum::into_int_value)
.unwrap();
let i64_32 = i64_type.const_int(32, false);
let now_lo = ctx.builder.build_left_shift(now_raw, i64_32, "now.lo").unwrap();
let now_hi = ctx.builder.build_right_shift(now_raw, i64_32, false, "now.hi").unwrap();
ctx.builder.build_or(now_lo, now_hi, "now_mu").map(Into::into).unwrap()
}
fn emit_at_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, t: BasicValueEnum<'ctx>) {
let i32_type = ctx.ctx.i32_type();
let i64_type = ctx.ctx.i64_type();
let i64_32 = i64_type.const_int(32, false);
let time = t.into_int_value();
let time_hi = ctx
.builder
.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "").unwrap(),
i32_type,
"time.hi",
)
.unwrap();
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "now_trunc").unwrap();
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx
.builder
.build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
.map(BasicValueEnum::into_pointer_value)
.unwrap();
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(1, false)], "now.lo.addr")
let now_raw = ctx.builder.build_load(now.as_pointer_value(), "now");
if let BasicValueEnum::IntValue(now_raw) = now_raw {
let i64_32 = i64_type.const_int(32, false);
let now_lo = ctx.builder.build_left_shift(now_raw, i64_32, "now_shl");
let now_hi = ctx.builder.build_right_shift(now_raw, i64_32, false, "now_lshr");
ctx.builder.build_or(now_lo, now_hi, "now_or").into()
} else {
unreachable!();
}
.unwrap();
ctx.builder
.build_store(now_hiptr, time_hi)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
}
fn emit_delay_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, dt: BasicValueEnum<'ctx>) {
fn emit_at_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>, t: BasicValueEnum<'ctx>) {
let i32_type = ctx.ctx.i32_type();
let i64_type = ctx.ctx.i64_type();
let i64_32 = i64_type.const_int(32, false);
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_raw = ctx
.builder
.build_load(now.as_pointer_value(), "")
.map(BasicValueEnum::into_int_value)
.unwrap();
let dt = dt.into_int_value();
let now_lo = ctx.builder.build_left_shift(now_raw, i64_32, "now.lo").unwrap();
let now_hi = ctx.builder.build_right_shift(now_raw, i64_32, false, "now.hi").unwrap();
let now_val = ctx.builder.build_or(now_lo, now_hi, "now_val").unwrap();
let time = ctx.builder.build_int_add(now_val, dt, "time").unwrap();
let time_hi = ctx
.builder
.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "time.hi").unwrap(),
if let BasicValueEnum::IntValue(time) = t {
let time_hi = ctx.builder.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "now_lshr"),
i32_type,
"now_trunc",
)
.unwrap();
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "time.lo").unwrap();
let now_hiptr = ctx
.builder
.build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
.map(BasicValueEnum::into_pointer_value)
.unwrap();
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(1, false)], "now.lo.addr")
);
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "now_trunc");
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_hiptr = ctx.builder.build_bitcast(
now,
i32_type.ptr_type(AddressSpace::Generic),
"now_bitcast",
);
if let BasicValueEnum::PointerValue(now_hiptr) = now_hiptr {
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(1, false)], "now_gep")
};
ctx.builder
.build_store(now_hiptr, time_hi)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
} else {
unreachable!();
}
} else {
unreachable!();
}
}
fn emit_delay_mu<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, 'a>,
dt: BasicValueEnum<'ctx>,
) {
let i32_type = ctx.ctx.i32_type();
let i64_type = ctx.ctx.i64_type();
let i64_32 = i64_type.const_int(32, false);
let now = ctx
.module
.get_global("now")
.unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
let now_raw = ctx.builder.build_load(now.as_pointer_value(), "now");
if let (BasicValueEnum::IntValue(now_raw), BasicValueEnum::IntValue(dt)) = (now_raw, dt) {
let now_lo = ctx.builder.build_left_shift(now_raw, i64_32, "now_shl");
let now_hi = ctx.builder.build_right_shift(now_raw, i64_32, false, "now_lshr");
let now_val = ctx.builder.build_or(now_lo, now_hi, "now_or");
let time = ctx.builder.build_int_add(now_val, dt, "now_add");
let time_hi = ctx.builder.build_int_truncate(
ctx.builder.build_right_shift(time, i64_32, false, "now_lshr"),
i32_type,
"now_trunc",
);
let time_lo = ctx.builder.build_int_truncate(time, i32_type, "now_trunc");
let now_hiptr = ctx.builder.build_bitcast(
now,
i32_type.ptr_type(AddressSpace::Generic),
"now_bitcast",
);
if let BasicValueEnum::PointerValue(now_hiptr) = now_hiptr {
let now_loptr = unsafe {
ctx.builder.build_gep(now_hiptr, &[i32_type.const_int(1, false)], "now_gep")
};
ctx.builder
.build_store(now_hiptr, time_hi)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
} else {
unreachable!();
}
} else {
unreachable!();
}
.unwrap();
ctx.builder
.build_store(now_hiptr, time_hi)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
ctx.builder
.build_store(now_loptr, time_lo)
.unwrap()
.set_atomic_ordering(AtomicOrdering::SequentiallyConsistent)
.unwrap();
}
}
@ -287,18 +267,14 @@ pub static NOW_PINNING_TIME_FNS: NowPinningTimeFns = NowPinningTimeFns {};
pub struct ExternTimeFns {}
impl TimeFns for ExternTimeFns {
fn emit_now_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>) -> BasicValueEnum<'ctx> {
fn emit_now_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>) -> BasicValueEnum<'ctx> {
let now_mu = ctx.module.get_function("now_mu").unwrap_or_else(|| {
ctx.module.add_function("now_mu", ctx.ctx.i64_type().fn_type(&[], false), None)
});
ctx.builder
.build_call(now_mu, &[], "now_mu")
.map(CallSiteValue::try_as_basic_value)
.map(Either::unwrap_left)
.unwrap()
ctx.builder.build_call(now_mu, &[], "now_mu").try_as_basic_value().left().unwrap()
}
fn emit_at_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, t: BasicValueEnum<'ctx>) {
fn emit_at_mu<'ctx, 'a>(&self, ctx: &mut CodeGenContext<'ctx, 'a>, t: BasicValueEnum<'ctx>) {
let at_mu = ctx.module.get_function("at_mu").unwrap_or_else(|| {
ctx.module.add_function(
"at_mu",
@ -306,10 +282,14 @@ impl TimeFns for ExternTimeFns {
None,
)
});
ctx.builder.build_call(at_mu, &[t.into()], "at_mu").unwrap();
ctx.builder.build_call(at_mu, &[t.into()], "at_mu");
}
fn emit_delay_mu<'ctx>(&self, ctx: &mut CodeGenContext<'ctx, '_>, dt: BasicValueEnum<'ctx>) {
fn emit_delay_mu<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, 'a>,
dt: BasicValueEnum<'ctx>,
) {
let delay_mu = ctx.module.get_function("delay_mu").unwrap_or_else(|| {
ctx.module.add_function(
"delay_mu",
@ -317,7 +297,7 @@ impl TimeFns for ExternTimeFns {
None,
)
});
ctx.builder.build_call(delay_mu, &[dt.into()], "delay_mu").unwrap();
ctx.builder.build_call(delay_mu, &[dt.into()], "delay_mu");
}
}

9
nac3ast/Cargo.toml
View File

@ -2,7 +2,7 @@
name = "nac3ast"
version = "0.1.0"
authors = ["RustPython Team", "M-Labs"]
edition = "2021"
edition = "2018"
[features]
default = ["constant-optimization", "fold"]
@ -10,6 +10,7 @@ constant-optimization = ["fold"]
fold = []
[dependencies]
parking_lot = "0.12"
string-interner = "0.17"
fxhash = "0.2"
lazy_static = "1.4.0"
parking_lot = "0.11.1"
string-interner = "0.13.0"
fxhash = "0.2.1"

1088
nac3ast/src/ast_gen.rs
View File

File diff suppressed because it is too large Load Diff

86
nac3ast/src/constant.rs
View File

@ -28,12 +28,12 @@ impl From<bool> for Constant {
}
impl From<i32> for Constant {
fn from(i: i32) -> Constant {
Self::Int(i128::from(i))
Self::Int(i as i128)
}
}
impl From<i64> for Constant {
fn from(i: i64) -> Constant {
Self::Int(i128::from(i))
Self::Int(i as i128)
}
}
@ -50,7 +50,6 @@ pub enum ConversionFlag {
}
impl ConversionFlag {
#[must_use]
pub fn try_from_byte(b: u8) -> Option<Self> {
match b {
b's' => Some(Self::Str),
@ -70,7 +69,6 @@ pub struct ConstantOptimizer {
#[cfg(feature = "constant-optimization")]
impl ConstantOptimizer {
#[inline]
#[must_use]
pub fn new() -> Self {
Self { _priv: () }
}
@ -87,22 +85,33 @@ impl<U> crate::fold::Fold<U> for ConstantOptimizer {
fn fold_expr(&mut self, node: crate::Expr<U>) -> Result<crate::Expr<U>, Self::Error> {
match node.node {
crate::ExprKind::Tuple { elts, ctx } => {
let elts =
elts.into_iter().map(|x| self.fold_expr(x)).collect::<Result<Vec<_>, _>>()?;
let expr =
if elts.iter().all(|e| matches!(e.node, crate::ExprKind::Constant { .. })) {
let tuple = elts
.into_iter()
.map(|e| match e.node {
crate::ExprKind::Constant { value, .. } => value,
_ => unreachable!(),
})
.collect();
crate::ExprKind::Constant { value: Constant::Tuple(tuple), kind: None }
} else {
crate::ExprKind::Tuple { elts, ctx }
};
Ok(crate::Expr { node: expr, custom: node.custom, location: node.location })
let elts = elts
.into_iter()
.map(|x| self.fold_expr(x))
.collect::<Result<Vec<_>, _>>()?;
let expr = if elts
.iter()
.all(|e| matches!(e.node, crate::ExprKind::Constant { .. }))
{
let tuple = elts
.into_iter()
.map(|e| match e.node {
crate::ExprKind::Constant { value, .. } => value,
_ => unreachable!(),
})
.collect();
crate::ExprKind::Constant {
value: Constant::Tuple(tuple),
kind: None,
}
} else {
crate::ExprKind::Tuple { elts, ctx }
};
Ok(crate::Expr {
node: expr,
custom: node.custom,
location: node.location,
})
}
_ => crate::fold::fold_expr(self, node),
}
@ -118,7 +127,7 @@ mod tests {
use crate::fold::Fold;
use crate::*;
let location = Location::new(0, 0, FileName::default());
let location = Location::new(0, 0, Default::default());
let custom = ();
let ast = Located {
location,
@ -129,12 +138,18 @@ mod tests {
Located {
location,
custom,
node: ExprKind::Constant { value: 1.into(), kind: None },
node: ExprKind::Constant {
value: 1.into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant { value: 2.into(), kind: None },
node: ExprKind::Constant {
value: 2.into(),
kind: None,
},
},
Located {
location,
@ -145,17 +160,26 @@ mod tests {
Located {
location,
custom,
node: ExprKind::Constant { value: 3.into(), kind: None },
node: ExprKind::Constant {
value: 3.into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant { value: 4.into(), kind: None },
node: ExprKind::Constant {
value: 4.into(),
kind: None,
},
},
Located {
location,
custom,
node: ExprKind::Constant { value: 5.into(), kind: None },
node: ExprKind::Constant {
value: 5.into(),
kind: None,
},
},
],
},
@ -163,7 +187,9 @@ mod tests {
],
},
};
let new_ast = ConstantOptimizer::new().fold_expr(ast).unwrap_or_else(|e| match e {});
let new_ast = ConstantOptimizer::new()
.fold_expr(ast)
.unwrap_or_else(|e| match e {});
assert_eq!(
new_ast,
Located {
@ -173,7 +199,11 @@ mod tests {
value: Constant::Tuple(vec![
1.into(),
2.into(),
Constant::Tuple(vec![3.into(), 4.into(), 5.into(),])
Constant::Tuple(vec![
3.into(),
4.into(),
5.into(),
])
]),
kind: None
},

9
nac3ast/src/fold_helpers.rs
View File

@ -64,4 +64,11 @@ macro_rules! simple_fold {
};
}
simple_fold!(usize, String, bool, StrRef, constant::Constant, constant::ConversionFlag);
simple_fold!(
usize,
String,
bool,
StrRef,
constant::Constant,
constant::ConversionFlag
);

6
nac3ast/src/impls.rs
View File

@ -2,7 +2,6 @@ use crate::{Constant, ExprKind};
impl<U> ExprKind<U> {
/// Returns a short name for the node suitable for use in error messages.
#[must_use]
pub fn name(&self) -> &'static str {
match self {
ExprKind::BoolOp { .. } | ExprKind::BinOp { .. } | ExprKind::UnaryOp { .. } => {
@ -35,7 +34,10 @@ impl<U> ExprKind<U> {
ExprKind::Starred { .. } => "starred",
ExprKind::Slice { .. } => "slice",
ExprKind::JoinedStr { values } => {
if values.iter().any(|e| matches!(e.node, ExprKind::JoinedStr { .. })) {
if values
.iter()
.any(|e| matches!(e.node, ExprKind::JoinedStr { .. }))
{
"f-string expression"
} else {
"literal"

19
nac3ast/src/lib.rs
View File

@ -1,18 +1,5 @@
#![deny(
future_incompatible,
let_underscore,
nonstandard_style,
rust_2024_compatibility,
clippy::all
)]
#![warn(clippy::pedantic)]
#![allow(
clippy::missing_errors_doc,
clippy::missing_panics_doc,
clippy::module_name_repetitions,
clippy::too_many_lines,
clippy::wildcard_imports
)]
#[macro_use]
extern crate lazy_static;
mod ast_gen;
mod constant;
@ -22,6 +9,6 @@ mod impls;
mod location;
pub use ast_gen::*;
pub use location::{FileName, Location};
pub use location::{Location, FileName};
pub type Suite<U = ()> = Vec<Stmt<U>>;

40
nac3ast/src/location.rs
View File

@ -1,9 +1,8 @@
//! Datatypes to support source location information.
use crate::ast_gen::StrRef;
use std::cmp::Ordering;
use std::fmt;
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
#[derive(Clone, Copy, Debug, PartialEq)]
pub struct FileName(pub StrRef);
impl Default for FileName {
fn default() -> Self {
@ -18,38 +17,16 @@ impl From<String> for FileName {
}
/// A location somewhere in the sourcecode.
#[derive(Clone, Copy, Debug, Default, Eq, PartialEq)]
#[derive(Clone, Copy, Debug, Default, PartialEq)]
pub struct Location {
pub row: usize,
pub column: usize,
pub file: FileName,
pub file: FileName
}
impl fmt::Display for Location {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}:{}:{}", self.file.0, self.row, self.column)
}
}
impl Ord for Location {
fn cmp(&self, other: &Self) -> Ordering {
let file_cmp = self.file.0.to_string().cmp(&other.file.0.to_string());
if file_cmp != Ordering::Equal {
return file_cmp;
}
let row_cmp = self.row.cmp(&other.row);
if row_cmp != Ordering::Equal {
return row_cmp;
}
self.column.cmp(&other.column)
}
}
impl PartialOrd for Location {
fn partial_cmp(&self, other: &Self) -> Option<Ordering> {
Some(self.cmp(other))
write!(f, "{}: line {} column {}", self.file.0, self.row, self.column)
}
}
@ -76,22 +53,23 @@ impl Location {
)
}
}
Visualize { loc: *self, line, desc }
Visualize {
loc: *self,
line,
desc,
}
}
}
impl Location {
#[must_use]
pub fn new(row: usize, column: usize, file: FileName) -> Self {
Location { row, column, file }
}
#[must_use]
pub fn row(&self) -> usize {
self.row
}
#[must_use]
pub fn column(&self) -> usize {
self.column
}

24
nac3core/Cargo.toml
View File

@ -2,30 +2,24 @@
name = "nac3core"
version = "0.1.0"
authors = ["M-Labs"]
edition = "2021"
[features]
no-escape-analysis = []
edition = "2018"
[dependencies]
itertools = "0.13"
crossbeam = "0.8"
indexmap = "2.6"
parking_lot = "0.12"
rayon = "1.10"
itertools = "0.10.1"
crossbeam = "0.8.1"
parking_lot = "0.11.1"
rayon = "1.5.1"
nac3parser = { path = "../nac3parser" }
strum = "0.26"
strum_macros = "0.26"
[dependencies.inkwell]
version = "0.5"
version = "0.1.0-beta.4"
default-features = false
features = ["llvm14-0-prefer-dynamic", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
features = ["llvm13-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
[dev-dependencies]
test-case = "1.2.0"
indoc = "2.0"
indoc = "1.0"
insta = "=1.11.0"
[build-dependencies]
regex = "1.10"
regex = "1"

83
nac3core/build.rs
View File

@ -1,60 +1,34 @@
use regex::Regex;
use std::{
env,
fs::File,
io::Write,
path::Path,
process::{Command, Stdio},
};
use regex::Regex;
fn main() {
let out_dir = env::var("OUT_DIR").unwrap();
let out_dir = Path::new(&out_dir);
let irrt_dir = Path::new("irrt");
let irrt_cpp_path = irrt_dir.join("irrt.cpp");
const FILE: &str = "src/codegen/irrt/irrt.c";
println!("cargo:rerun-if-changed={}", FILE);
/*
* HACK: Sadly, clang doesn't let us emit generic LLVM bitcode.
* Compiling for WASM32 and filtering the output with regex is the closest we can get.
*/
let mut flags: Vec<&str> = vec![
const FLAG: &[&str] = &[
"--target=wasm32",
"-x",
"c++",
"-std=c++20",
"-fno-discard-value-names",
"-fno-exceptions",
"-fno-rtti",
FILE,
"-O3",
"-emit-llvm",
"-S",
"-Wall",
"-Wextra",
"-Wno-implicit-function-declaration",
"-o",
"-",
"-I",
irrt_dir.to_str().unwrap(),
irrt_cpp_path.to_str().unwrap(),
];
match env::var("PROFILE").as_deref() {
Ok("debug") => {
flags.push("-O0");
flags.push("-DIRRT_DEBUG_ASSERT");
}
Ok("release") => {
flags.push("-O3");
}
flavor => panic!("Unknown or missing build flavor {flavor:?}"),
}
// Tell Cargo to rerun if any file under `irrt_dir` (recursive) changes
println!("cargo:rerun-if-changed={}", irrt_dir.to_str().unwrap());
// Compile IRRT and capture the LLVM IR output
let output = Command::new("clang-irrt")
.args(flags)
let output = Command::new("clang")
.args(FLAG)
.output()
.map(|o| {
assert!(o.status.success(), "{}", std::str::from_utf8(&o.stderr).unwrap());
@ -62,23 +36,12 @@ fn main() {
})
.unwrap();
// https://github.com/rust-lang/regex/issues/244
let output = std::str::from_utf8(&output.stdout).unwrap().replace("\r\n", "\n");
let output = std::str::from_utf8(&output.stdout).unwrap();
let mut filtered_output = String::with_capacity(output.len());
// Filter out irrelevant IR
//
// Regex:
// - `(?ms:^define.*?\}$)` captures LLVM `define` blocks
// - `(?m:^declare.*?$)` captures LLVM `declare` lines
// - `(?m:^%.+?=\s*type\s*\{.+?\}$)` captures LLVM `type` declarations
// - `(?m:^@.+?=.+$)` captures global constants
let regex_filter = Regex::new(
r"(?ms:^define.*?\}$)|(?m:^declare.*?$)|(?m:^%.+?=\s*type\s*\{.+?\}$)|(?m:^@.+?=.+$)",
)
.unwrap();
for f in regex_filter.captures_iter(&output) {
assert_eq!(f.len(), 1);
let regex_filter = regex::Regex::new(r"(?ms:^define.*?\}$)|(?m:^declare.*?$)").unwrap();
for f in regex_filter.captures_iter(output) {
assert!(f.len() == 1);
filtered_output.push_str(&f[0]);
filtered_output.push('\n');
}
@ -87,24 +50,12 @@ fn main() {
.unwrap()
.replace_all(&filtered_output, "");
// For debugging
// Doing `DEBUG_DUMP_IRRT=1 cargo build -p nac3core` dumps the LLVM IR generated
const DEBUG_DUMP_IRRT: &str = "DEBUG_DUMP_IRRT";
println!("cargo:rerun-if-env-changed={DEBUG_DUMP_IRRT}");
if env::var(DEBUG_DUMP_IRRT).is_ok() {
let mut file = File::create(out_dir.join("irrt.ll")).unwrap();
file.write_all(output.as_bytes()).unwrap();
let mut file = File::create(out_dir.join("irrt-filtered.ll")).unwrap();
file.write_all(filtered_output.as_bytes()).unwrap();
}
let mut llvm_as = Command::new("llvm-as-irrt")
let mut llvm_as = Command::new("llvm-as")
.stdin(Stdio::piped())
.arg("-o")
.arg(out_dir.join("irrt.bc"))
.arg(Path::new(&env::var("OUT_DIR").unwrap()).join("irrt.bc"))
.spawn()
.unwrap();
llvm_as.stdin.as_mut().unwrap().write_all(filtered_output.as_bytes()).unwrap();
assert!(llvm_as.wait().unwrap().success());
assert!(llvm_as.wait().unwrap().success())
}

6
nac3core/irrt/irrt.cpp
View File

@ -1,6 +0,0 @@
#include "irrt/exception.hpp"
#include "irrt/int_types.hpp"
#include "irrt/list.hpp"
#include "irrt/math.hpp"
#include "irrt/ndarray.hpp"
#include "irrt/slice.hpp"

9
nac3core/irrt/irrt/cslice.hpp
View File

@ -1,9 +0,0 @@
#pragma once
#include "irrt/int_types.hpp"
template<typename SizeT>
struct CSlice {
uint8_t* base;
SizeT len;
};

25
nac3core/irrt/irrt/debug.hpp
View File

@ -1,25 +0,0 @@
#pragma once
// Set in nac3core/build.rs
#ifdef IRRT_DEBUG_ASSERT
#define IRRT_DEBUG_ASSERT_BOOL true
#else
#define IRRT_DEBUG_ASSERT_BOOL false
#endif
#define raise_debug_assert(SizeT, msg, param1, param2, param3) \
raise_exception(SizeT, EXN_ASSERTION_ERROR, "IRRT debug assert failed: " msg, param1, param2, param3)
#define debug_assert_eq(SizeT, lhs, rhs) \
if constexpr (IRRT_DEBUG_ASSERT_BOOL) { \
if ((lhs) != (rhs)) { \
raise_debug_assert(SizeT, "LHS = {0}. RHS = {1}", lhs, rhs, NO_PARAM); \
} \
}
#define debug_assert(SizeT, expr) \
if constexpr (IRRT_DEBUG_ASSERT_BOOL) { \
if (!(expr)) { \
raise_debug_assert(SizeT, "Got false.", NO_PARAM, NO_PARAM, NO_PARAM); \
} \
}

82
nac3core/irrt/irrt/exception.hpp
View File

@ -1,82 +0,0 @@
#pragma once
#include "irrt/cslice.hpp"
#include "irrt/int_types.hpp"
/**
* @brief The int type of ARTIQ exception IDs.
*/
typedef int32_t ExceptionId;
/*
* Set of exceptions C++ IRRT can use.
* Must be synchronized with `setup_irrt_exceptions` in `nac3core/src/codegen/irrt/mod.rs`.
*/
extern "C" {
ExceptionId EXN_INDEX_ERROR;
ExceptionId EXN_VALUE_ERROR;
ExceptionId EXN_ASSERTION_ERROR;
ExceptionId EXN_TYPE_ERROR;
}
/**
* @brief Extern function to `__nac3_raise`
*
* The parameter `err` could be `Exception<int32_t>` or `Exception<int64_t>`. The caller
* must make sure to pass `Exception`s with the correct `SizeT` depending on the `size_t` of the runtime.
*/
extern "C" void __nac3_raise(void* err);
namespace {
/**
* @brief NAC3's Exception struct
*/
template<typename SizeT>
struct Exception {
ExceptionId id;
CSlice<SizeT> filename;
int32_t line;
int32_t column;
CSlice<SizeT> function;
CSlice<SizeT> msg;
int64_t params[3];
};
constexpr int64_t NO_PARAM = 0;
template<typename SizeT>
void _raise_exception_helper(ExceptionId id,
const char* filename,
int32_t line,
const char* function,
const char* msg,
int64_t param0,
int64_t param1,
int64_t param2) {
Exception<SizeT> e = {
.id = id,
.filename = {.base = reinterpret_cast<const uint8_t*>(filename), .len = __builtin_strlen(filename)},
.line = line,
.column = 0,
.function = {.base = reinterpret_cast<const uint8_t*>(function), .len = __builtin_strlen(function)},
.msg = {.base = reinterpret_cast<const uint8_t*>(msg), .len = __builtin_strlen(msg)},
};
e.params[0] = param0;
e.params[1] = param1;
e.params[2] = param2;
__nac3_raise(reinterpret_cast<void*>(&e));
__builtin_unreachable();
}
/**
* @brief Raise an exception with location details (location in the IRRT source files).
* @param SizeT The runtime `size_t` type.
* @param id The ID of the exception to raise.
* @param msg A global constant C-string of the error message.
*
* `param0` to `param2` are optional format arguments of `msg`. They should be set to
* `NO_PARAM` to indicate they are unused.
*/
#define raise_exception(SizeT, id, msg, param0, param1, param2) \
_raise_exception_helper<SizeT>(id, __FILE__, __LINE__, __FUNCTION__, msg, param0, param1, param2)
} // namespace

22
nac3core/irrt/irrt/int_types.hpp
View File

@ -1,22 +0,0 @@
#pragma once
#if __STDC_VERSION__ >= 202000
using int8_t = _BitInt(8);
using uint8_t = unsigned _BitInt(8);
using int32_t = _BitInt(32);
using uint32_t = unsigned _BitInt(32);
using int64_t = _BitInt(64);
using uint64_t = unsigned _BitInt(64);
#else
using int8_t = _ExtInt(8);
using uint8_t = unsigned _ExtInt(8);
using int32_t = _ExtInt(32);
using uint32_t = unsigned _ExtInt(32);
using int64_t = _ExtInt(64);
using uint64_t = unsigned _ExtInt(64);
#endif
// NDArray indices are always `uint32_t`.
using NDIndex = uint32_t;
// The type of an index or a value describing the length of a range/slice is always `int32_t`.
using SliceIndex = int32_t;

75
nac3core/irrt/irrt/list.hpp
View File

@ -1,75 +0,0 @@
#pragma once
#include "irrt/int_types.hpp"
#include "irrt/math_util.hpp"
extern "C" {
// Handle list assignment and dropping part of the list when
// both dest_step and src_step are +1.
// - All the index must *not* be out-of-bound or negative,
// - The end index is *inclusive*,
// - The length of src and dest slice size should already
// be checked: if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest)
SliceIndex __nac3_list_slice_assign_var_size(SliceIndex dest_start,
SliceIndex dest_end,
SliceIndex dest_step,
uint8_t* dest_arr,
SliceIndex dest_arr_len,
SliceIndex src_start,
SliceIndex src_end,
SliceIndex src_step,
uint8_t* src_arr,
SliceIndex src_arr_len,
const SliceIndex size) {
/* if dest_arr_len == 0, do nothing since we do not support extending list */
if (dest_arr_len == 0)
return dest_arr_len;
/* if both step is 1, memmove directly, handle the dropping of the list, and shrink size */
if (src_step == dest_step && dest_step == 1) {
const SliceIndex src_len = (src_end >= src_start) ? (src_end - src_start + 1) : 0;
const SliceIndex dest_len = (dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
if (src_len > 0) {
__builtin_memmove(dest_arr + dest_start * size, src_arr + src_start * size, src_len * size);
}
if (dest_len > 0) {
/* dropping */
__builtin_memmove(dest_arr + (dest_start + src_len) * size, dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size);
}
/* shrink size */
return dest_arr_len - (dest_len - src_len);
}
/* if two range overlaps, need alloca */
uint8_t need_alloca = (dest_arr == src_arr)
&& !(max(dest_start, dest_end) < min(src_start, src_end)
|| max(src_start, src_end) < min(dest_start, dest_end));
if (need_alloca) {
uint8_t* tmp = reinterpret_cast<uint8_t*>(__builtin_alloca(src_arr_len * size));
__builtin_memcpy(tmp, src_arr, src_arr_len * size);
src_arr = tmp;
}
SliceIndex src_ind = src_start;
SliceIndex dest_ind = dest_start;
for (; (src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end); src_ind += src_step, dest_ind += dest_step) {
/* for constant optimization */
if (size == 1) {
__builtin_memcpy(dest_arr + dest_ind, src_arr + src_ind, 1);
} else if (size == 4) {
__builtin_memcpy(dest_arr + dest_ind * 4, src_arr + src_ind * 4, 4);
} else if (size == 8) {
__builtin_memcpy(dest_arr + dest_ind * 8, src_arr + src_ind * 8, 8);
} else {
/* memcpy for var size, cannot overlap after previous alloca */
__builtin_memcpy(dest_arr + dest_ind * size, src_arr + src_ind * size, size);
}
}
/* only dest_step == 1 can we shrink the dest list. */
/* size should be ensured prior to calling this function */
if (dest_step == 1 && dest_end >= dest_start) {
__builtin_memmove(dest_arr + dest_ind * size, dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size);
return dest_arr_len - (dest_end - dest_ind) - 1;
}
return dest_arr_len;
}
} // extern "C"

93
nac3core/irrt/irrt/math.hpp
View File

@ -1,93 +0,0 @@
#pragma once
namespace {
// adapted from GNU Scientific Library: https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
// need to make sure `exp >= 0` before calling this function
template<typename T>
T __nac3_int_exp_impl(T base, T exp) {
T res = 1;
/* repeated squaring method */
do {
if (exp & 1) {
res *= base; /* for n odd */
}
exp >>= 1;
base *= base;
} while (exp);
return res;
}
} // namespace
#define DEF_nac3_int_exp_(T) \
T __nac3_int_exp_##T(T base, T exp) { \
return __nac3_int_exp_impl(base, exp); \
}
extern "C" {
// Putting semicolons here to make clang-format not reformat this into
// a stair shape.
DEF_nac3_int_exp_(int32_t);
DEF_nac3_int_exp_(int64_t);
DEF_nac3_int_exp_(uint32_t);
DEF_nac3_int_exp_(uint64_t);
int32_t __nac3_isinf(double x) {
return __builtin_isinf(x);
}
int32_t __nac3_isnan(double x) {
return __builtin_isnan(x);
}
double tgamma(double arg);
double __nac3_gamma(double z) {
// Handling for denormals
// | x | Python gamma(x) | C tgamma(x) |
// --- | ----------------- | --------------- | ----------- |
// (1) | nan | nan | nan |
// (2) | -inf | -inf | inf |
// (3) | inf | inf | inf |
// (4) | 0.0 | inf | inf |
// (5) | {-1.0, -2.0, ...} | inf | nan |
// (1)-(3)
if (__builtin_isinf(z) || __builtin_isnan(z)) {
return z;
}
double v = tgamma(z);
// (4)-(5)
return __builtin_isinf(v) || __builtin_isnan(v) ? __builtin_inf() : v;
}
double lgamma(double arg);
double __nac3_gammaln(double x) {
// libm's handling of value overflows differs from scipy:
// - scipy: gammaln(-inf) -> -inf
// - libm : lgamma(-inf) -> inf
if (__builtin_isinf(x)) {
return x;
}
return lgamma(x);
}
double j0(double x);
double __nac3_j0(double x) {
// libm's handling of value overflows differs from scipy:
// - scipy: j0(inf) -> nan
// - libm : j0(inf) -> 0.0
if (__builtin_isinf(x)) {
return __builtin_nan("");
}
return j0(x);
}
}

13
nac3core/irrt/irrt/math_util.hpp
View File

@ -1,13 +0,0 @@
#pragma once
namespace {
template<typename T>
const T& max(const T& a, const T& b) {
return a > b ? a : b;
}
template<typename T>
const T& min(const T& a, const T& b) {
return a > b ? b : a;
}
} // namespace

144
nac3core/irrt/irrt/ndarray.hpp
View File

@ -1,144 +0,0 @@
#pragma once
#include "irrt/int_types.hpp"
namespace {
template<typename SizeT>
SizeT __nac3_ndarray_calc_size_impl(const SizeT* list_data, SizeT list_len, SizeT begin_idx, SizeT end_idx) {
__builtin_assume(end_idx <= list_len);
SizeT num_elems = 1;
for (SizeT i = begin_idx; i < end_idx; ++i) {
SizeT val = list_data[i];
__builtin_assume(val > 0);
num_elems *= val;
}
return num_elems;
}
template<typename SizeT>
void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT* dims, SizeT num_dims, NDIndex* idxs) {
SizeT stride = 1;
for (SizeT dim = 0; dim < num_dims; dim++) {
SizeT i = num_dims - dim - 1;
__builtin_assume(dims[i] > 0);
idxs[i] = (index / stride) % dims[i];
stride *= dims[i];
}
}
template<typename SizeT>
SizeT __nac3_ndarray_flatten_index_impl(const SizeT* dims, SizeT num_dims, const NDIndex* indices, SizeT num_indices) {
SizeT idx = 0;
SizeT stride = 1;
for (SizeT i = 0; i < num_dims; ++i) {
SizeT ri = num_dims - i - 1;
if (ri < num_indices) {
idx += stride * indices[ri];
}
__builtin_assume(dims[i] > 0);
stride *= dims[ri];
}
return idx;
}
template<typename SizeT>
void __nac3_ndarray_calc_broadcast_impl(const SizeT* lhs_dims,
SizeT lhs_ndims,
const SizeT* rhs_dims,
SizeT rhs_ndims,
SizeT* out_dims) {
SizeT max_ndims = lhs_ndims > rhs_ndims ? lhs_ndims : rhs_ndims;
for (SizeT i = 0; i < max_ndims; ++i) {
const SizeT* lhs_dim_sz = i < lhs_ndims ? &lhs_dims[lhs_ndims - i - 1] : nullptr;
const SizeT* rhs_dim_sz = i < rhs_ndims ? &rhs_dims[rhs_ndims - i - 1] : nullptr;
SizeT* out_dim = &out_dims[max_ndims - i - 1];
if (lhs_dim_sz == nullptr) {
*out_dim = *rhs_dim_sz;
} else if (rhs_dim_sz == nullptr) {
*out_dim = *lhs_dim_sz;
} else if (*lhs_dim_sz == 1) {
*out_dim = *rhs_dim_sz;
} else if (*rhs_dim_sz == 1) {
*out_dim = *lhs_dim_sz;
} else if (*lhs_dim_sz == *rhs_dim_sz) {
*out_dim = *lhs_dim_sz;
} else {
__builtin_unreachable();
}
}
}
template<typename SizeT>
void __nac3_ndarray_calc_broadcast_idx_impl(const SizeT* src_dims,
SizeT src_ndims,
const NDIndex* in_idx,
NDIndex* out_idx) {
for (SizeT i = 0; i < src_ndims; ++i) {
SizeT src_i = src_ndims - i - 1;
out_idx[src_i] = src_dims[src_i] == 1 ? 0 : in_idx[src_i];
}
}
} // namespace
extern "C" {
uint32_t __nac3_ndarray_calc_size(const uint32_t* list_data, uint32_t list_len, uint32_t begin_idx, uint32_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
}
uint64_t
__nac3_ndarray_calc_size64(const uint64_t* list_data, uint64_t list_len, uint64_t begin_idx, uint64_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
}
void __nac3_ndarray_calc_nd_indices(uint32_t index, const uint32_t* dims, uint32_t num_dims, NDIndex* idxs) {
__nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
}
void __nac3_ndarray_calc_nd_indices64(uint64_t index, const uint64_t* dims, uint64_t num_dims, NDIndex* idxs) {
__nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
}
uint32_t
__nac3_ndarray_flatten_index(const uint32_t* dims, uint32_t num_dims, const NDIndex* indices, uint32_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
}
uint64_t
__nac3_ndarray_flatten_index64(const uint64_t* dims, uint64_t num_dims, const NDIndex* indices, uint64_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
}
void __nac3_ndarray_calc_broadcast(const uint32_t* lhs_dims,
uint32_t lhs_ndims,
const uint32_t* rhs_dims,
uint32_t rhs_ndims,
uint32_t* out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
}
void __nac3_ndarray_calc_broadcast64(const uint64_t* lhs_dims,
uint64_t lhs_ndims,
const uint64_t* rhs_dims,
uint64_t rhs_ndims,
uint64_t* out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
}
void __nac3_ndarray_calc_broadcast_idx(const uint32_t* src_dims,
uint32_t src_ndims,
const NDIndex* in_idx,
NDIndex* out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
}
void __nac3_ndarray_calc_broadcast_idx64(const uint64_t* src_dims,
uint64_t src_ndims,
const NDIndex* in_idx,
NDIndex* out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
}
}

28
nac3core/irrt/irrt/slice.hpp
View File

@ -1,28 +0,0 @@
#pragma once
#include "irrt/int_types.hpp"
extern "C" {
SliceIndex __nac3_slice_index_bound(SliceIndex i, const SliceIndex len) {
if (i < 0) {
i = len + i;
}
if (i < 0) {
return 0;
} else if (i > len) {
return len;
}
return i;
}
SliceIndex __nac3_range_slice_len(const SliceIndex start, const SliceIndex end, const SliceIndex step) {
SliceIndex diff = end - start;
if (diff > 0 && step > 0) {
return ((diff - 1) / step) + 1;
} else if (diff < 0 && step < 0) {
return ((diff + 1) / step) + 1;
} else {
return 0;
}
}
}

2411
nac3core/src/codegen/builtin_fns.rs
View File

File diff suppressed because it is too large Load Diff

1765
nac3core/src/codegen/classes.rs
View File

File diff suppressed because it is too large Load Diff

78
nac3core/src/codegen/concrete_type.rs
View File

@ -1,20 +1,15 @@
use std::collections::HashMap;
use indexmap::IndexMap;
use nac3parser::ast::StrRef;
use crate::{
symbol_resolver::SymbolValue,
toplevel::DefinitionId,
typecheck::{
type_inferencer::PrimitiveStore,
typedef::{
into_var_map, FunSignature, FuncArg, Type, TypeEnum, TypeVar, TypeVarId, Unifier,
},
typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier},
},
};
use nac3parser::ast::StrRef;
use std::collections::HashMap;
pub struct ConcreteTypeStore {
store: Vec<ConcreteTypeEnum>,
}
@ -27,7 +22,6 @@ pub struct ConcreteFuncArg {
pub name: StrRef,
pub ty: ConcreteType,
pub default_value: Option<SymbolValue>,
pub is_vararg: bool,
}
#[derive(Clone, Debug)]
@ -49,12 +43,14 @@ pub enum ConcreteTypeEnum {
TPrimitive(Primitive),
TTuple {
ty: Vec<ConcreteType>,
is_vararg_ctx: bool,
},
TList {
ty: ConcreteType,
},
TObj {
obj_id: DefinitionId,
fields: HashMap<StrRef, (ConcreteType, bool)>,
params: IndexMap<TypeVarId, ConcreteType>,
params: HashMap<u32, ConcreteType>,
},
TVirtual {
ty: ConcreteType,
@ -62,15 +58,11 @@ pub enum ConcreteTypeEnum {
TFunc {
args: Vec<ConcreteFuncArg>,
ret: ConcreteType,
vars: HashMap<TypeVarId, ConcreteType>,
},
TLiteral {
values: Vec<SymbolValue>,
vars: HashMap<u32, ConcreteType>,
},
}
impl ConcreteTypeStore {
#[must_use]
pub fn new() -> ConcreteTypeStore {
ConcreteTypeStore {
store: vec![
@ -88,7 +80,6 @@ impl ConcreteTypeStore {
}
}
#[must_use]
pub fn get(&self, cty: ConcreteType) -> &ConcreteTypeEnum {
&self.store[cty.0]
}
@ -106,16 +97,8 @@ impl ConcreteTypeStore {
.iter()
.map(|arg| ConcreteFuncArg {
name: arg.name,
ty: if arg.is_vararg {
let tuple_ty = unifier
.add_ty(TypeEnum::TTuple { ty: vec![arg.ty], is_vararg_ctx: true });
self.from_unifier_type(unifier, primitives, tuple_ty, cache)
} else {
self.from_unifier_type(unifier, primitives, arg.ty, cache)
},
ty: self.from_unifier_type(unifier, primitives, arg.ty, cache),
default_value: arg.default_value.clone(),
is_vararg: arg.is_vararg,
})
.collect(),
ret: self.from_unifier_type(unifier, primitives, signature.ret, cache),
@ -170,12 +153,14 @@ impl ConcreteTypeStore {
cache.insert(ty, None);
let ty_enum = unifier.get_ty(ty);
let result = match &*ty_enum {
TypeEnum::TTuple { ty, is_vararg_ctx } => ConcreteTypeEnum::TTuple {
TypeEnum::TTuple { ty } => ConcreteTypeEnum::TTuple {
ty: ty
.iter()
.map(|t| self.from_unifier_type(unifier, primitives, *t, cache))
.collect(),
is_vararg_ctx: *is_vararg_ctx,
},
TypeEnum::TList { ty } => ConcreteTypeEnum::TList {
ty: self.from_unifier_type(unifier, primitives, *ty, cache),
},
TypeEnum::TObj { obj_id, fields, params } => ConcreteTypeEnum::TObj {
obj_id: *obj_id,
@ -209,12 +194,9 @@ impl ConcreteTypeStore {
ty: self.from_unifier_type(unifier, primitives, *ty, cache),
},
TypeEnum::TFunc(signature) => {
self.from_signature(unifier, primitives, signature, cache)
self.from_signature(unifier, primitives, &*signature, cache)
}
TypeEnum::TLiteral { values, .. } => {
ConcreteTypeEnum::TLiteral { values: values.clone() }
}
_ => unreachable!("{:?}", ty_enum.get_type_name()),
_ => unreachable!(),
};
let index = if let Some(ConcreteType(index)) = cache.get(&ty).unwrap() {
self.store[*index] = result;
@ -239,7 +221,7 @@ impl ConcreteTypeStore {
return if let Some(ty) = ty {
*ty
} else {
*ty = Some(unifier.get_dummy_var().ty);
*ty = Some(unifier.get_dummy_var().0);
ty.unwrap()
};
}
@ -261,13 +243,15 @@ impl ConcreteTypeStore {
*cache.get_mut(&cty).unwrap() = Some(ty);
return ty;
}
ConcreteTypeEnum::TTuple { ty, is_vararg_ctx } => TypeEnum::TTuple {
ConcreteTypeEnum::TTuple { ty } => TypeEnum::TTuple {
ty: ty
.iter()
.map(|cty| self.to_unifier_type(unifier, primitives, *cty, cache))
.collect(),
is_vararg_ctx: *is_vararg_ctx,
},
ConcreteTypeEnum::TList { ty } => {
TypeEnum::TList { ty: self.to_unifier_type(unifier, primitives, *ty, cache) }
}
ConcreteTypeEnum::TVirtual { ty } => {
TypeEnum::TVirtual { ty: self.to_unifier_type(unifier, primitives, *ty, cache) }
}
@ -279,10 +263,10 @@ impl ConcreteTypeStore {
(*name, (self.to_unifier_type(unifier, primitives, cty.0, cache), cty.1))
})
.collect::<HashMap<_, _>>(),
params: into_var_map(params.iter().map(|(&id, cty)| {
let ty = self.to_unifier_type(unifier, primitives, *cty, cache);
TypeVar { id, ty }
})),
params: params
.iter()
.map(|(id, cty)| (*id, self.to_unifier_type(unifier, primitives, *cty, cache)))
.collect::<HashMap<_, _>>(),
},
ConcreteTypeEnum::TFunc { args, ret, vars } => TypeEnum::TFunc(FunSignature {
args: args
@ -291,18 +275,14 @@ impl ConcreteTypeStore {
name: arg.name,
ty: self.to_unifier_type(unifier, primitives, arg.ty, cache),
default_value: arg.default_value.clone(),
is_vararg: false,
})
.collect(),
ret: self.to_unifier_type(unifier, primitives, *ret, cache),
vars: into_var_map(vars.iter().map(|(&id, cty)| {
let ty = self.to_unifier_type(unifier, primitives, *cty, cache);
TypeVar { id, ty }
})),
vars: vars
.iter()
.map(|(id, cty)| (*id, self.to_unifier_type(unifier, primitives, *cty, cache)))
.collect::<HashMap<_, _>>(),
}),
ConcreteTypeEnum::TLiteral { values, .. } => {
TypeEnum::TLiteral { values: values.clone(), loc: None }
}
};
let result = unifier.add_ty(result);
if let Some(ty) = cache.get(&cty).unwrap() {

3885
nac3core/src/codegen/expr.rs
View File

File diff suppressed because it is too large Load Diff

193
nac3core/src/codegen/extern_fns.rs
View File

@ -1,193 +0,0 @@
use inkwell::{
attributes::{Attribute, AttributeLoc},
values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue},
};
use itertools::Either;
use super::CodeGenContext;
/// Macro to generate extern function
/// Both function return type and function parameter type are `FloatValue`
///
/// Arguments:
/// * `unary/binary`: Whether the extern function requires one (unary) or two (binary) operands
/// * `$fn_name:ident`: The identifier of the rust function to be generated
/// * `$extern_fn:literal`: Name of underlying extern function
///
/// Optional Arguments:
/// * `$(,$attributes:literal)*)`: Attributes linked with the extern function.
/// The default attributes are "mustprogress", "nofree", "nounwind", "willreturn", and "writeonly".
/// These will be used unless other attributes are specified
/// * `$(,$args:ident)*`: Operands of the extern function
/// The data type of these operands will be set to `FloatValue`
///
macro_rules! generate_extern_fn {
("unary", $fn_name:ident, $extern_fn:literal) => {
generate_extern_fn!($fn_name, $extern_fn, arg, "mustprogress", "nofree", "nounwind", "willreturn", "writeonly");
};
("unary", $fn_name:ident, $extern_fn:literal $(,$attributes:literal)*) => {
generate_extern_fn!($fn_name, $extern_fn, arg $(,$attributes)*);
};
("binary", $fn_name:ident, $extern_fn:literal) => {
generate_extern_fn!($fn_name, $extern_fn, arg1, arg2, "mustprogress", "nofree", "nounwind", "willreturn", "writeonly");
};
("binary", $fn_name:ident, $extern_fn:literal $(,$attributes:literal)*) => {
generate_extern_fn!($fn_name, $extern_fn, arg1, arg2 $(,$attributes)*);
};
($fn_name:ident, $extern_fn:literal $(,$args:ident)* $(,$attributes:literal)*) => {
#[doc = concat!("Invokes the [`", stringify!($extern_fn), "`](https://en.cppreference.com/w/c/numeric/math/", stringify!($llvm_name), ") function." )]
pub fn $fn_name<'ctx>(
ctx: &CodeGenContext<'ctx, '_>
$(,$args: FloatValue<'ctx>)*,
name: Option<&str>,
) -> FloatValue<'ctx> {
const FN_NAME: &str = $extern_fn;
let llvm_f64 = ctx.ctx.f64_type();
$(debug_assert_eq!($args.get_type(), llvm_f64);)*
let extern_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let fn_type = llvm_f64.fn_type(&[$($args.get_type().into()),*], false);
let func = ctx.module.add_function(FN_NAME, fn_type, None);
for attr in [$($attributes),*] {
func.add_attribute(
AttributeLoc::Function,
ctx.ctx.create_enum_attribute(Attribute::get_named_enum_kind_id(attr), 0),
);
}
func
});
ctx.builder
.build_call(extern_fn, &[$($args.into()),*], name.unwrap_or_default())
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}
};
}
generate_extern_fn!("unary", call_tan, "tan");
generate_extern_fn!("unary", call_asin, "asin");
generate_extern_fn!("unary", call_acos, "acos");
generate_extern_fn!("unary", call_atan, "atan");
generate_extern_fn!("unary", call_sinh, "sinh");
generate_extern_fn!("unary", call_cosh, "cosh");
generate_extern_fn!("unary", call_tanh, "tanh");
generate_extern_fn!("unary", call_asinh, "asinh");
generate_extern_fn!("unary", call_acosh, "acosh");
generate_extern_fn!("unary", call_atanh, "atanh");
generate_extern_fn!("unary", call_expm1, "expm1");
generate_extern_fn!(
"unary",
call_cbrt,
"cbrt",
"mustprogress",
"nofree",
"nosync",
"nounwind",
"readonly",
"willreturn"
);
generate_extern_fn!("unary", call_erf, "erf", "nounwind");
generate_extern_fn!("unary", call_erfc, "erfc", "nounwind");
generate_extern_fn!("unary", call_j1, "j1", "nounwind");
generate_extern_fn!("binary", call_atan2, "atan2");
generate_extern_fn!("binary", call_hypot, "hypot", "nounwind");
generate_extern_fn!("binary", call_nextafter, "nextafter", "nounwind");
/// Invokes the [`ldexp`](https://en.cppreference.com/w/c/numeric/math/ldexp) function.
pub fn call_ldexp<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
arg: FloatValue<'ctx>,
exp: IntValue<'ctx>,
name: Option<&str>,
) -> FloatValue<'ctx> {
const FN_NAME: &str = "ldexp";
let llvm_f64 = ctx.ctx.f64_type();
let llvm_i32 = ctx.ctx.i32_type();
debug_assert_eq!(arg.get_type(), llvm_f64);
debug_assert_eq!(exp.get_type(), llvm_i32);
let extern_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let fn_type = llvm_f64.fn_type(&[llvm_f64.into(), llvm_i32.into()], false);
let func = ctx.module.add_function(FN_NAME, fn_type, None);
for attr in ["mustprogress", "nofree", "nounwind", "willreturn"] {
func.add_attribute(
AttributeLoc::Function,
ctx.ctx.create_enum_attribute(Attribute::get_named_enum_kind_id(attr), 0),
);
}
func
});
ctx.builder
.build_call(extern_fn, &[arg.into(), exp.into()], name.unwrap_or_default())
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Macro to generate `np_linalg` and `sp_linalg` functions
/// The function takes as input `NDArray` and returns ()
///
/// Arguments:
/// * `$fn_name:ident`: The identifier of the rust function to be generated
/// * `$extern_fn:literal`: Name of underlying extern function
/// * (2/3/4): Number of `NDArray` that function takes as input
///
/// Note:
/// The operands and resulting `NDArray` are both passed as input to the funcion
/// It is the responsibility of caller to ensure that output `NDArray` is properly allocated on stack
/// The function changes the content of the output `NDArray` in-place
macro_rules! generate_linalg_extern_fn {
($fn_name:ident, $extern_fn:literal, 2) => {
generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2);
};
($fn_name:ident, $extern_fn:literal, 3) => {
generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2, mat3);
};
($fn_name:ident, $extern_fn:literal, 4) => {
generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2, mat3, mat4);
};
($fn_name:ident, $extern_fn:literal $(,$input_matrix:ident)*) => {
#[doc = concat!("Invokes the linalg `", stringify!($extern_fn), " function." )]
pub fn $fn_name<'ctx>(
ctx: &mut CodeGenContext<'ctx, '_>
$(,$input_matrix: BasicValueEnum<'ctx>)*,
name: Option<&str>,
){
const FN_NAME: &str = $extern_fn;
let extern_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let fn_type = ctx.ctx.void_type().fn_type(&[$($input_matrix.get_type().into()),*], false);
let func = ctx.module.add_function(FN_NAME, fn_type, None);
for attr in ["mustprogress", "nofree", "nounwind", "willreturn", "writeonly"] {
func.add_attribute(
AttributeLoc::Function,
ctx.ctx.create_enum_attribute(Attribute::get_named_enum_kind_id(attr), 0),
);
}
func
});
ctx.builder.build_call(extern_fn, &[$($input_matrix.into(),)*], name.unwrap_or_default()).unwrap();
}
};
}
generate_linalg_extern_fn!(call_np_linalg_cholesky, "np_linalg_cholesky", 2);
generate_linalg_extern_fn!(call_np_linalg_qr, "np_linalg_qr", 3);
generate_linalg_extern_fn!(call_np_linalg_svd, "np_linalg_svd", 4);
generate_linalg_extern_fn!(call_np_linalg_inv, "np_linalg_inv", 2);
generate_linalg_extern_fn!(call_np_linalg_pinv, "np_linalg_pinv", 2);
generate_linalg_extern_fn!(call_np_linalg_matrix_power, "np_linalg_matrix_power", 3);
generate_linalg_extern_fn!(call_np_linalg_det, "np_linalg_det", 2);
generate_linalg_extern_fn!(call_sp_linalg_lu, "sp_linalg_lu", 3);
generate_linalg_extern_fn!(call_sp_linalg_schur, "sp_linalg_schur", 3);
generate_linalg_extern_fn!(call_sp_linalg_hessenberg, "sp_linalg_hessenberg", 3);

165
nac3core/src/codegen/generator.rs
View File

@ -1,17 +1,15 @@
use inkwell::{
context::Context,
types::{BasicTypeEnum, IntType},
values::{BasicValueEnum, IntValue, PointerValue},
};
use nac3parser::ast::{Expr, Stmt, StrRef};
use super::{bool_to_i1, bool_to_i8, classes::ArraySliceValue, expr::*, stmt::*, CodeGenContext};
use crate::{
codegen::{expr::*, stmt::*, CodeGenContext},
symbol_resolver::ValueEnum,
toplevel::{DefinitionId, TopLevelDef},
typecheck::typedef::{FunSignature, Type},
};
use inkwell::{
context::Context,
types::{BasicTypeEnum, IntType},
values::{BasicValueEnum, PointerValue},
};
use nac3parser::ast::{Expr, Stmt, StrRef};
pub trait CodeGenerator {
/// Return the module name for the code generator.
@ -24,9 +22,9 @@ pub trait CodeGenerator {
/// - fun: Function signature and definition ID.
/// - params: Function parameters. Note that this does not include the object even if the
/// function is a class method.
fn gen_call<'ctx>(
fn gen_call<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
obj: Option<(Type, ValueEnum<'ctx>)>,
fun: (&FunSignature, DefinitionId),
params: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
@ -38,12 +36,12 @@ pub trait CodeGenerator {
}
/// Generate object constructor and returns the constructed object.
/// - signature: Function signature of the constructor.
/// - signature: Function signature of the contructor.
/// - def: Class definition for the constructor class.
/// - params: Function parameters.
fn gen_constructor<'ctx>(
fn gen_constructor<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
signature: &FunSignature,
def: &TopLevelDef,
params: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
@ -59,23 +57,22 @@ pub trait CodeGenerator {
/// - fun: Function signature, definition ID and the substitution key.
/// - params: Function parameters. Note that this does not include the object even if the
/// function is a class method.
///
/// Note that this function should check if the function is generated in another thread (due to
/// possible race condition), see the default implementation for an example.
fn gen_func_instance<'ctx>(
fn gen_func_instance<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
obj: Option<(Type, ValueEnum<'ctx>)>,
fun: (&FunSignature, &mut TopLevelDef, String),
id: usize,
) -> Result<String, String> {
gen_func_instance(ctx, &obj, fun, id)
gen_func_instance(ctx, obj, fun, id)
}
/// Generate the code for an expression.
fn gen_expr<'ctx>(
fn gen_expr<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
expr: &Expr<Option<Type>>,
) -> Result<Option<ValueEnum<'ctx>>, String>
where
@ -86,92 +83,44 @@ pub trait CodeGenerator {
/// Allocate memory for a variable and return a pointer pointing to it.
/// The default implementation places the allocations at the start of the function.
fn gen_var_alloc<'ctx>(
fn gen_var_alloc<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
ty: BasicTypeEnum<'ctx>,
name: Option<&str>,
) -> Result<PointerValue<'ctx>, String> {
gen_var(ctx, ty, name)
}
/// Allocate memory for a variable and return a pointer pointing to it.
/// The default implementation places the allocations at the start of the function.
fn gen_array_var_alloc<'ctx>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ty: BasicTypeEnum<'ctx>,
size: IntValue<'ctx>,
name: Option<&'ctx str>,
) -> Result<ArraySliceValue<'ctx>, String> {
gen_array_var(ctx, ty, size, name)
gen_var(ctx, ty)
}
/// Return a pointer pointing to the target of the expression.
fn gen_store_target<'ctx>(
fn gen_store_target<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
pattern: &Expr<Option<Type>>,
name: Option<&str>,
) -> Result<Option<PointerValue<'ctx>>, String>
) -> Result<PointerValue<'ctx>, String>
where
Self: Sized,
{
gen_store_target(self, ctx, pattern, name)
gen_store_target(self, ctx, pattern)
}
/// Generate code for an assignment expression.
fn gen_assign<'ctx>(
fn gen_assign<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
target: &Expr<Option<Type>>,
value: ValueEnum<'ctx>,
value_ty: Type,
) -> Result<(), String>
where
Self: Sized,
{
gen_assign(self, ctx, target, value, value_ty)
}
/// Generate code for an assignment expression where LHS is a `"target_list"`.
///
/// See <https://docs.python.org/3/reference/simple_stmts.html#assignment-statements>.
fn gen_assign_target_list<'ctx>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
targets: &Vec<Expr<Option<Type>>>,
value: ValueEnum<'ctx>,
value_ty: Type,
) -> Result<(), String>
where
Self: Sized,
{
gen_assign_target_list(self, ctx, targets, value, value_ty)
}
/// Generate code for an item assignment.
///
/// i.e., `target[key] = value`
fn gen_setitem<'ctx>(
&mut self,
ctx: &mut CodeGenContext<'ctx, '_>,
target: &Expr<Option<Type>>,
key: &Expr<Option<Type>>,
value: ValueEnum<'ctx>,
value_ty: Type,
) -> Result<(), String>
where
Self: Sized,
{
gen_setitem(self, ctx, target, key, value, value_ty)
gen_assign(self, ctx, target, value)
}
/// Generate code for a while expression.
/// Return true if the while loop must early return
fn gen_while(
fn gen_while<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
stmt: &Stmt<Option<Type>>,
) -> Result<(), String>
where
@ -180,11 +129,11 @@ pub trait CodeGenerator {
gen_while(self, ctx, stmt)
}
/// Generate code for a for expression.
/// Return true if the for loop must early return
fn gen_for(
/// Generate code for a while expression.
/// Return true if the while loop must early return
fn gen_for<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
stmt: &Stmt<Option<Type>>,
) -> Result<(), String>
where
@ -195,9 +144,9 @@ pub trait CodeGenerator {
/// Generate code for an if expression.
/// Return true if the statement must early return
fn gen_if(
fn gen_if<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
stmt: &Stmt<Option<Type>>,
) -> Result<(), String>
where
@ -206,9 +155,9 @@ pub trait CodeGenerator {
gen_if(self, ctx, stmt)
}
fn gen_with(
fn gen_with<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
stmt: &Stmt<Option<Type>>,
) -> Result<(), String>
where
@ -218,11 +167,10 @@ pub trait CodeGenerator {
}
/// Generate code for a statement
///
/// Return true if the statement must early return
fn gen_stmt(
fn gen_stmt<'ctx, 'a>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
stmt: &Stmt<Option<Type>>,
) -> Result<(), String>
where
@ -230,36 +178,6 @@ pub trait CodeGenerator {
{
gen_stmt(self, ctx, stmt)
}
/// Generates code for a block statement.
fn gen_block<'a, I: Iterator<Item = &'a Stmt<Option<Type>>>>(
&mut self,
ctx: &mut CodeGenContext<'_, '_>,
stmts: I,
) -> Result<(), String>
where
Self: Sized,
{
gen_block(self, ctx, stmts)
}
/// See [`bool_to_i1`].
fn bool_to_i1<'ctx>(
&self,
ctx: &CodeGenContext<'ctx, '_>,
bool_value: IntValue<'ctx>,
) -> IntValue<'ctx> {
bool_to_i1(&ctx.builder, bool_value)
}
/// See [`bool_to_i8`].
fn bool_to_i8<'ctx>(
&self,
ctx: &CodeGenContext<'ctx, '_>,
bool_value: IntValue<'ctx>,
) -> IntValue<'ctx> {
bool_to_i8(&ctx.builder, ctx.ctx, bool_value)
}
}
pub struct DefaultCodeGenerator {
@ -268,20 +186,17 @@ pub struct DefaultCodeGenerator {
}
impl DefaultCodeGenerator {
#[must_use]
pub fn new(name: String, size_t: u32) -> DefaultCodeGenerator {
assert!(matches!(size_t, 32 | 64));
assert!(size_t == 32 || size_t == 64);
DefaultCodeGenerator { name, size_t }
}
}
impl CodeGenerator for DefaultCodeGenerator {
/// Returns the name for this [`CodeGenerator`].
fn get_name(&self) -> &str {
&self.name
}
/// Returns an LLVM integer type representing `size_t`.
fn get_size_type<'ctx>(&self, ctx: &'ctx Context) -> IntType<'ctx> {
// it should be unsigned, but we don't really need unsigned and this could save us from
// having to do a bit cast...

140
nac3core/src/codegen/irrt/irrt.c Normal file
View File

@ -0,0 +1,140 @@
typedef _ExtInt(8) int8_t;
typedef unsigned _ExtInt(8) uint8_t;
typedef _ExtInt(32) int32_t;
typedef unsigned _ExtInt(32) uint32_t;
typedef _ExtInt(64) int64_t;
typedef unsigned _ExtInt(64) uint64_t;
# define MAX(a, b) (a > b ? a : b)
# define MIN(a, b) (a > b ? b : a)
// adapted from GNU Scientific Library: https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
// need to make sure `exp >= 0` before calling this function
#define DEF_INT_EXP(T) T __nac3_int_exp_##T( \
T base, \
T exp \
) { \
T res = (T)1; \
/* repeated squaring method */ \
do { \
if (exp & 1) res *= base; /* for n odd */ \
exp >>= 1; \
base *= base; \
} while (exp); \
return res; \
} \
DEF_INT_EXP(int32_t)
DEF_INT_EXP(int64_t)
DEF_INT_EXP(uint32_t)
DEF_INT_EXP(uint64_t)
int32_t __nac3_slice_index_bound(int32_t i, const int32_t len) {
if (i < 0) {
i = len + i;
}
if (i < 0) {
return 0;
} else if (i > len) {
return len;
}
return i;
}
int32_t __nac3_range_slice_len(const int32_t start, const int32_t end, const int32_t step) {
int32_t diff = end - start;
if (diff > 0 && step > 0) {
return ((diff - 1) / step) + 1;
} else if (diff < 0 && step < 0) {
return ((diff + 1) / step) + 1;
} else {
return 0;
}
}
// Handle list assignment and dropping part of the list when
// both dest_step and src_step are +1.
// - All the index must *not* be out-of-bound or negative,
// - The end index is *inclusive*,
// - The length of src and dest slice size should already
// be checked: if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest)
int32_t __nac3_list_slice_assign_var_size(
int32_t dest_start,
int32_t dest_end,
int32_t dest_step,
uint8_t *dest_arr,
int32_t dest_arr_len,
int32_t src_start,
int32_t src_end,
int32_t src_step,
uint8_t *src_arr,
int32_t src_arr_len,
const int32_t size
) {
/* if dest_arr_len == 0, do nothing since we do not support extending list */
if (dest_arr_len == 0) return dest_arr_len;
/* if both step is 1, memmove directly, handle the dropping of the list, and shrink size */
if (src_step == dest_step && dest_step == 1) {
const int32_t src_len = (src_end >= src_start) ? (src_end - src_start + 1) : 0;
const int32_t dest_len = (dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
if (src_len > 0) {
__builtin_memmove(
dest_arr + dest_start * size,
src_arr + src_start * size,
src_len * size
);
}
if (dest_len > 0) {
/* dropping */
__builtin_memmove(
dest_arr + (dest_start + src_len) * size,
dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size
);
}
/* shrink size */
return dest_arr_len - (dest_len - src_len);
}
/* if two range overlaps, need alloca */
uint8_t need_alloca =
(dest_arr == src_arr)
&& !(
MAX(dest_start, dest_end) < MIN(src_start, src_end)
|| MAX(src_start, src_end) < MIN(dest_start, dest_end)
);
if (need_alloca) {
uint8_t *tmp = alloca(src_arr_len * size);
__builtin_memcpy(tmp, src_arr, src_arr_len * size);
src_arr = tmp;
}
int32_t src_ind = src_start;
int32_t dest_ind = dest_start;
for (;
(src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end);
src_ind += src_step, dest_ind += dest_step
) {
/* for constant optimization */
if (size == 1) {
__builtin_memcpy(dest_arr + dest_ind, src_arr + src_ind, 1);
} else if (size == 4) {
__builtin_memcpy(dest_arr + dest_ind * 4, src_arr + src_ind * 4, 4);
} else if (size == 8) {
__builtin_memcpy(dest_arr + dest_ind * 8, src_arr + src_ind * 8, 8);
} else {
/* memcpy for var size, cannot overlap after previous alloca */
__builtin_memcpy(dest_arr + dest_ind * size, src_arr + src_ind * size, size);
}
}
/* only dest_step == 1 can we shrink the dest list. */
/* size should be ensured prior to calling this function */
if (dest_step == 1 && dest_end >= dest_start) {
__builtin_memmove(
dest_arr + dest_ind * size,
dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size
);
return dest_arr_len - (dest_end - dest_ind) - 1;
}
return dest_arr_len;
}

838
nac3core/src/codegen/irrt/mod.rs
View File

@ -1,30 +1,18 @@
use crate::typecheck::typedef::Type;
use super::{CodeGenContext, CodeGenerator};
use inkwell::{
attributes::{Attribute, AttributeLoc},
context::Context,
memory_buffer::MemoryBuffer,
module::Module,
types::{BasicTypeEnum, IntType},
values::{BasicValue, BasicValueEnum, CallSiteValue, FloatValue, IntValue},
values::{IntValue, PointerValue},
AddressSpace, IntPredicate,
};
use itertools::Either;
use nac3parser::ast::Expr;
use super::{
classes::{
ArrayLikeIndexer, ArrayLikeValue, ArraySliceValue, ListValue, NDArrayValue,
TypedArrayLikeAccessor, TypedArrayLikeAdapter, UntypedArrayLikeAccessor,
},
llvm_intrinsics,
macros::codegen_unreachable,
stmt::gen_for_callback_incrementing,
CodeGenContext, CodeGenerator,
};
use crate::{symbol_resolver::SymbolResolver, typecheck::typedef::Type};
#[must_use]
pub fn load_irrt<'ctx>(ctx: &'ctx Context, symbol_resolver: &dyn SymbolResolver) -> Module<'ctx> {
pub fn load_irrt(ctx: &Context) -> Module {
let bitcode_buf = MemoryBuffer::create_from_memory_range(
include_bytes!(concat!(env!("OUT_DIR"), "/irrt.bc")),
"irrt_bitcode_buffer",
@ -40,33 +28,13 @@ pub fn load_irrt<'ctx>(ctx: &'ctx Context, symbol_resolver: &dyn SymbolResolver)
let function = irrt_mod.get_function(symbol).unwrap();
function.add_attribute(AttributeLoc::Function, ctx.create_enum_attribute(inline_attr, 0));
}
// Initialize all global `EXN_*` exception IDs in IRRT with the [`SymbolResolver`].
let exn_id_type = ctx.i32_type();
let errors = &[
("EXN_INDEX_ERROR", "0:IndexError"),
("EXN_VALUE_ERROR", "0:ValueError"),
("EXN_ASSERTION_ERROR", "0:AssertionError"),
("EXN_TYPE_ERROR", "0:TypeError"),
];
for (irrt_name, symbol_name) in errors {
let exn_id = symbol_resolver.get_string_id(symbol_name);
let exn_id = exn_id_type.const_int(exn_id as u64, false).as_basic_value_enum();
let global = irrt_mod.get_global(irrt_name).unwrap_or_else(|| {
panic!("Exception symbol name '{irrt_name}' should exist in the IRRT LLVM module")
});
global.set_initializer(&exn_id);
}
irrt_mod
}
// repeated squaring method adapted from GNU Scientific Library:
// https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
pub fn integer_power<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
pub fn integer_power<'ctx, 'a>(
ctx: &mut CodeGenContext<'ctx, 'a>,
base: IntValue<'ctx>,
exp: IntValue<'ctx>,
signed: bool,
@ -76,42 +44,23 @@ pub fn integer_power<'ctx, G: CodeGenerator + ?Sized>(
(64, 64, true) => "__nac3_int_exp_int64_t",
(32, 32, false) => "__nac3_int_exp_uint32_t",
(64, 64, false) => "__nac3_int_exp_uint64_t",
_ => codegen_unreachable!(ctx),
_ => unreachable!(),
};
let base_type = base.get_type();
let pow_fun = ctx.module.get_function(symbol).unwrap_or_else(|| {
let fn_type = base_type.fn_type(&[base_type.into(), base_type.into()], false);
ctx.module.add_function(symbol, fn_type, None)
});
// throw exception when exp < 0
let ge_zero = ctx
.builder
.build_int_compare(
IntPredicate::SGE,
exp,
exp.get_type().const_zero(),
"assert_int_pow_ge_0",
)
.unwrap();
ctx.make_assert(
generator,
ge_zero,
"0:ValueError",
"integer power must be positive or zero",
[None, None, None],
ctx.current_loc,
);
// TODO: throw exception when exp < 0
ctx.builder
.build_call(pow_fun, &[base.into(), exp.into()], "call_int_pow")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap()
.try_as_basic_value()
.unwrap_left()
.into_int_value()
}
pub fn calculate_len_for_slice_range<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
pub fn calculate_len_for_slice_range<'ctx, 'a>(
ctx: &mut CodeGenContext<'ctx, 'a>,
start: IntValue<'ctx>,
end: IntValue<'ctx>,
step: IntValue<'ctx>,
@ -123,25 +72,13 @@ pub fn calculate_len_for_slice_range<'ctx, G: CodeGenerator + ?Sized>(
ctx.module.add_function(SYMBOL, fn_t, None)
});
// assert step != 0, throw exception if not
let not_zero = ctx
.builder
.build_int_compare(IntPredicate::NE, step, step.get_type().const_zero(), "range_step_ne")
.unwrap();
ctx.make_assert(
generator,
not_zero,
"0:ValueError",
"step must not be zero",
[None, None, None],
ctx.current_loc,
);
// TODO: assert step != 0, throw exception if not
ctx.builder
.build_call(len_func, &[start.into(), end.into(), step.into()], "calc_len")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.try_as_basic_value()
.left()
.unwrap()
.into_int_value()
}
/// NOTE: the output value of the end index of this function should be compared ***inclusively***,
@ -184,140 +121,95 @@ pub fn calculate_len_for_slice_range<'ctx, G: CodeGenerator + ?Sized>(
/// ,step
/// )
/// ```
pub fn handle_slice_indices<'ctx, G: CodeGenerator>(
pub fn handle_slice_indices<'a, 'ctx, G: CodeGenerator>(
start: &Option<Box<Expr<Option<Type>>>>,
end: &Option<Box<Expr<Option<Type>>>>,
step: &Option<Box<Expr<Option<Type>>>>,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
generator: &mut G,
length: IntValue<'ctx>,
) -> Result<Option<(IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>)>, String> {
list: PointerValue<'ctx>,
) -> Result<(IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>), String> {
// TODO: throw exception when step is 0
let int32 = ctx.ctx.i32_type();
let zero = int32.const_zero();
let one = int32.const_int(1, false);
let length = ctx.builder.build_int_truncate_or_bit_cast(length, int32, "leni32").unwrap();
Ok(Some(match (start, end, step) {
let length = ctx.build_gep_and_load(list, &[zero, one]).into_int_value();
let length = ctx.builder.build_int_truncate_or_bit_cast(length, int32, "leni32");
Ok(match (start, end, step) {
(s, e, None) => (
if let Some(s) = s.as_ref() {
match handle_slice_index_bound(s, ctx, generator, length)? {
Some(v) => v,
None => return Ok(None),
}
} else {
int32.const_zero()
},
s.as_ref().map_or_else(
|| Ok(int32.const_zero()),
|s| handle_slice_index_bound(s, ctx, generator, length),
)?,
{
let e = if let Some(s) = e.as_ref() {
match handle_slice_index_bound(s, ctx, generator, length)? {
Some(v) => v,
None => return Ok(None),
}
} else {
length
};
ctx.builder.build_int_sub(e, one, "final_end").unwrap()
let e = e.as_ref().map_or_else(
|| Ok(length),
|e| handle_slice_index_bound(e, ctx, generator, length),
)?;
ctx.builder.build_int_sub(e, one, "final_end")
},
one,
),
(s, e, Some(step)) => {
let step = if let Some(v) = generator.gen_expr(ctx, step)? {
v.to_basic_value_enum(ctx, generator, ctx.primitives.int32)?.into_int_value()
} else {
return Ok(None);
};
// assert step != 0, throw exception if not
let not_zero = ctx
.builder
.build_int_compare(
IntPredicate::NE,
step,
step.get_type().const_zero(),
"range_step_ne",
)
.unwrap();
ctx.make_assert(
generator,
not_zero,
"0:ValueError",
"slice step cannot be zero",
[None, None, None],
ctx.current_loc,
);
let len_id = ctx.builder.build_int_sub(length, one, "lenmin1").unwrap();
let neg = ctx
.builder
.build_int_compare(IntPredicate::SLT, step, zero, "step_is_neg")
.unwrap();
let step = generator
.gen_expr(ctx, step)?
.unwrap()
.to_basic_value_enum(ctx, generator)?
.into_int_value();
let len_id = ctx.builder.build_int_sub(length, one, "lenmin1");
let neg = ctx.builder.build_int_compare(IntPredicate::SLT, step, zero, "step_is_neg");
(
match s {
Some(s) => {
let Some(s) = handle_slice_index_bound(s, ctx, generator, length)? else {
return Ok(None);
};
let s = handle_slice_index_bound(s, ctx, generator, length)?;
ctx.builder
.build_select(
ctx.builder
.build_and(
ctx.builder
.build_int_compare(
IntPredicate::EQ,
s,
length,
"s_eq_len",
)
.unwrap(),
neg,
"should_minus_one",
)
.unwrap(),
ctx.builder.build_int_sub(s, one, "s_min").unwrap(),
ctx.builder.build_and(
ctx.builder.build_int_compare(
IntPredicate::EQ,
s,
length,
"s_eq_len",
),
neg,
"should_minus_one",
),
ctx.builder.build_int_sub(s, one, "s_min"),
s,
"final_start",
)
.map(BasicValueEnum::into_int_value)
.unwrap()
.into_int_value()
}
None => ctx
.builder
.build_select(neg, len_id, zero, "stt")
.map(BasicValueEnum::into_int_value)
.unwrap(),
None => ctx.builder.build_select(neg, len_id, zero, "stt").into_int_value(),
},
match e {
Some(e) => {
let Some(e) = handle_slice_index_bound(e, ctx, generator, length)? else {
return Ok(None);
};
let e = handle_slice_index_bound(e, ctx, generator, length)?;
ctx.builder
.build_select(
neg,
ctx.builder.build_int_add(e, one, "end_add_one").unwrap(),
ctx.builder.build_int_sub(e, one, "end_sub_one").unwrap(),
ctx.builder.build_int_add(e, one, "end_add_one"),
ctx.builder.build_int_sub(e, one, "end_sub_one"),
"final_end",
)
.map(BasicValueEnum::into_int_value)
.unwrap()
.into_int_value()
}
None => ctx
.builder
.build_select(neg, zero, len_id, "end")
.map(BasicValueEnum::into_int_value)
.unwrap(),
None => ctx.builder.build_select(neg, zero, len_id, "end").into_int_value(),
},
step,
)
}
}))
})
}
/// this function allows index out of range, since python
/// allows index out of range in slice (`a = [1,2,3]; a[1:10] == [2,3]`).
pub fn handle_slice_index_bound<'ctx, G: CodeGenerator>(
pub fn handle_slice_index_bound<'a, 'ctx, G: CodeGenerator>(
i: &Expr<Option<Type>>,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
generator: &mut G,
length: IntValue<'ctx>,
) -> Result<Option<IntValue<'ctx>>, String> {
) -> Result<IntValue<'ctx>, String> {
const SYMBOL: &str = "__nac3_slice_index_bound";
let func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
let i32_t = ctx.ctx.i32_type();
@ -325,35 +217,29 @@ pub fn handle_slice_index_bound<'ctx, G: CodeGenerator>(
ctx.module.add_function(SYMBOL, fn_t, None)
});
let i = if let Some(v) = generator.gen_expr(ctx, i)? {
v.to_basic_value_enum(ctx, generator, i.custom.unwrap())?
} else {
return Ok(None);
};
Ok(Some(
ctx.builder
.build_call(func, &[i.into(), length.into()], "bounded_ind")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap(),
))
let i = generator.gen_expr(ctx, i)?.unwrap().to_basic_value_enum(ctx, generator)?;
Ok(ctx
.builder
.build_call(func, &[i.into(), length.into()], "bounded_ind")
.try_as_basic_value()
.left()
.unwrap()
.into_int_value())
}
/// This function handles 'end' **inclusively**.
/// Order of tuples `assign_idx` and `value_idx` is ('start', 'end', 'step').
/// Order of tuples assign_idx and value_idx is ('start', 'end', 'step').
/// Negative index should be handled before entering this function
pub fn list_slice_assignment<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
pub fn list_slice_assignment<'ctx, 'a>(
ctx: &mut CodeGenContext<'ctx, 'a>,
size_ty: IntType<'ctx>,
ty: BasicTypeEnum<'ctx>,
dest_arr: ListValue<'ctx>,
dest_arr: PointerValue<'ctx>,
dest_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
src_arr: ListValue<'ctx>,
src_arr: PointerValue<'ctx>,
src_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
) {
let size_ty = generator.get_size_type(ctx.ctx);
let int8_ptr = ctx.ctx.i8_type().ptr_type(AddressSpace::default());
let int8_ptr = ctx.ctx.i8_type().ptr_type(AddressSpace::Generic);
let int32 = ctx.ctx.i32_type();
let (fun_symbol, elem_ptr_type) = ("__nac3_list_slice_assign_var_size", int8_ptr);
let slice_assign_fun = {
@ -378,72 +264,26 @@ pub fn list_slice_assignment<'ctx, G: CodeGenerator + ?Sized>(
let zero = int32.const_zero();
let one = int32.const_int(1, false);
let dest_arr_ptr = dest_arr.data().base_ptr(ctx, generator);
let dest_arr_ptr =
ctx.builder.build_pointer_cast(dest_arr_ptr, elem_ptr_type, "dest_arr_ptr_cast").unwrap();
let dest_len = dest_arr.load_size(ctx, Some("dest.len"));
let dest_len = ctx.builder.build_int_truncate_or_bit_cast(dest_len, int32, "srclen32").unwrap();
let src_arr_ptr = src_arr.data().base_ptr(ctx, generator);
let src_arr_ptr =
ctx.builder.build_pointer_cast(src_arr_ptr, elem_ptr_type, "src_arr_ptr_cast").unwrap();
let src_len = src_arr.load_size(ctx, Some("src.len"));
let src_len = ctx.builder.build_int_truncate_or_bit_cast(src_len, int32, "srclen32").unwrap();
let dest_arr_ptr = ctx.build_gep_and_load(dest_arr, &[zero, zero]);
let dest_arr_ptr = ctx.builder.build_pointer_cast(
dest_arr_ptr.into_pointer_value(),
elem_ptr_type,
"dest_arr_ptr_cast",
);
let dest_len = ctx.build_gep_and_load(dest_arr, &[zero, one]).into_int_value();
let dest_len = ctx.builder.build_int_truncate_or_bit_cast(dest_len, int32, "srclen32");
let src_arr_ptr = ctx.build_gep_and_load(src_arr, &[zero, zero]);
let src_arr_ptr = ctx.builder.build_pointer_cast(
src_arr_ptr.into_pointer_value(),
elem_ptr_type,
"src_arr_ptr_cast",
);
let src_len = ctx.build_gep_and_load(src_arr, &[zero, one]).into_int_value();
let src_len = ctx.builder.build_int_truncate_or_bit_cast(src_len, int32, "srclen32");
// index in bound and positive should be done
// assert if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest), and
// TODO: assert if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest), and
// throw exception if not satisfied
let src_end = ctx
.builder
.build_select(
ctx.builder.build_int_compare(IntPredicate::SLT, src_idx.2, zero, "is_neg").unwrap(),
ctx.builder.build_int_sub(src_idx.1, one, "e_min_one").unwrap(),
ctx.builder.build_int_add(src_idx.1, one, "e_add_one").unwrap(),
"final_e",
)
.map(BasicValueEnum::into_int_value)
.unwrap();
let dest_end = ctx
.builder
.build_select(
ctx.builder.build_int_compare(IntPredicate::SLT, dest_idx.2, zero, "is_neg").unwrap(),
ctx.builder.build_int_sub(dest_idx.1, one, "e_min_one").unwrap(),
ctx.builder.build_int_add(dest_idx.1, one, "e_add_one").unwrap(),
"final_e",
)
.map(BasicValueEnum::into_int_value)
.unwrap();
let src_slice_len =
calculate_len_for_slice_range(generator, ctx, src_idx.0, src_end, src_idx.2);
let dest_slice_len =
calculate_len_for_slice_range(generator, ctx, dest_idx.0, dest_end, dest_idx.2);
let src_eq_dest = ctx
.builder
.build_int_compare(IntPredicate::EQ, src_slice_len, dest_slice_len, "slice_src_eq_dest")
.unwrap();
let src_slt_dest = ctx
.builder
.build_int_compare(IntPredicate::SLT, src_slice_len, dest_slice_len, "slice_src_slt_dest")
.unwrap();
let dest_step_eq_one = ctx
.builder
.build_int_compare(
IntPredicate::EQ,
dest_idx.2,
dest_idx.2.get_type().const_int(1, false),
"slice_dest_step_eq_one",
)
.unwrap();
let cond_1 = ctx.builder.build_and(dest_step_eq_one, src_slt_dest, "slice_cond_1").unwrap();
let cond = ctx.builder.build_or(src_eq_dest, cond_1, "slice_cond").unwrap();
ctx.make_assert(
generator,
cond,
"0:ValueError",
"attempt to assign sequence of size {0} to slice of size {1} with step size {2}",
[Some(src_slice_len), Some(dest_slice_len), Some(dest_idx.2)],
ctx.current_loc,
);
let new_len = {
let args = vec![
dest_idx.0.into(), // dest start idx
@ -462,491 +302,29 @@ pub fn list_slice_assignment<'ctx, G: CodeGenerator + ?Sized>(
BasicTypeEnum::IntType(t) => t.size_of(),
BasicTypeEnum::PointerType(t) => t.size_of(),
BasicTypeEnum::StructType(t) => t.size_of().unwrap(),
_ => codegen_unreachable!(ctx),
_ => unreachable!(),
};
ctx.builder.build_int_truncate_or_bit_cast(s, int32, "size").unwrap()
ctx.builder.build_int_truncate_or_bit_cast(s, int32, "size")
}
.into(),
];
ctx.builder
.build_call(slice_assign_fun, args.as_slice(), "slice_assign")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap()
.try_as_basic_value()
.unwrap_left()
.into_int_value()
};
// update length
let need_update =
ctx.builder.build_int_compare(IntPredicate::NE, new_len, dest_len, "need_update").unwrap();
ctx.builder.build_int_compare(IntPredicate::NE, new_len, dest_len, "need_update");
let current = ctx.builder.get_insert_block().unwrap().get_parent().unwrap();
let update_bb = ctx.ctx.append_basic_block(current, "update");
let cont_bb = ctx.ctx.append_basic_block(current, "cont");
ctx.builder.build_conditional_branch(need_update, update_bb, cont_bb).unwrap();
ctx.builder.build_conditional_branch(need_update, update_bb, cont_bb);
ctx.builder.position_at_end(update_bb);
let new_len = ctx.builder.build_int_z_extend_or_bit_cast(new_len, size_ty, "new_len").unwrap();
dest_arr.store_size(ctx, generator, new_len);
ctx.builder.build_unconditional_branch(cont_bb).unwrap();
let dest_len_ptr = unsafe { ctx.builder.build_gep(dest_arr, &[zero, one], "dest_len_ptr") };
let new_len = ctx.builder.build_int_z_extend_or_bit_cast(new_len, size_ty, "new_len");
ctx.builder.build_store(dest_len_ptr, new_len);
ctx.builder.build_unconditional_branch(cont_bb);
ctx.builder.position_at_end(cont_bb);
}
/// Generates a call to `isinf` in IR. Returns an `i1` representing the result.
pub fn call_isinf<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &CodeGenContext<'ctx, '_>,
v: FloatValue<'ctx>,
) -> IntValue<'ctx> {
let intrinsic_fn = ctx.module.get_function("__nac3_isinf").unwrap_or_else(|| {
let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
ctx.module.add_function("__nac3_isinf", fn_type, None)
});
let ret = ctx
.builder
.build_call(intrinsic_fn, &[v.into()], "isinf")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap();
generator.bool_to_i1(ctx, ret)
}
/// Generates a call to `isnan` in IR. Returns an `i1` representing the result.
pub fn call_isnan<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &CodeGenContext<'ctx, '_>,
v: FloatValue<'ctx>,
) -> IntValue<'ctx> {
let intrinsic_fn = ctx.module.get_function("__nac3_isnan").unwrap_or_else(|| {
let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
ctx.module.add_function("__nac3_isnan", fn_type, None)
});
let ret = ctx
.builder
.build_call(intrinsic_fn, &[v.into()], "isnan")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap();
generator.bool_to_i1(ctx, ret)
}
/// Generates a call to `gamma` in IR. Returns an `f64` representing the result.
pub fn call_gamma<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
let llvm_f64 = ctx.ctx.f64_type();
let intrinsic_fn = ctx.module.get_function("__nac3_gamma").unwrap_or_else(|| {
let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
ctx.module.add_function("__nac3_gamma", fn_type, None)
});
ctx.builder
.build_call(intrinsic_fn, &[v.into()], "gamma")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Generates a call to `gammaln` in IR. Returns an `f64` representing the result.
pub fn call_gammaln<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
let llvm_f64 = ctx.ctx.f64_type();
let intrinsic_fn = ctx.module.get_function("__nac3_gammaln").unwrap_or_else(|| {
let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
ctx.module.add_function("__nac3_gammaln", fn_type, None)
});
ctx.builder
.build_call(intrinsic_fn, &[v.into()], "gammaln")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Generates a call to `j0` in IR. Returns an `f64` representing the result.
pub fn call_j0<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
let llvm_f64 = ctx.ctx.f64_type();
let intrinsic_fn = ctx.module.get_function("__nac3_j0").unwrap_or_else(|| {
let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
ctx.module.add_function("__nac3_j0", fn_type, None)
});
ctx.builder
.build_call(intrinsic_fn, &[v.into()], "j0")
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Generates a call to `__nac3_ndarray_calc_size`. Returns an [`IntValue`] representing the
/// calculated total size.
///
/// * `dims` - An [`ArrayLikeIndexer`] containing the size of each dimension.
/// * `range` - The dimension index to begin and end (exclusively) calculating the dimensions for,
/// or [`None`] if starting from the first dimension and ending at the last dimension
/// respectively.
pub fn call_ndarray_calc_size<'ctx, G, Dims>(
generator: &G,
ctx: &CodeGenContext<'ctx, '_>,
dims: &Dims,
(begin, end): (Option<IntValue<'ctx>>, Option<IntValue<'ctx>>),
) -> IntValue<'ctx>
where
G: CodeGenerator + ?Sized,
Dims: ArrayLikeIndexer<'ctx>,
{
let llvm_usize = generator.get_size_type(ctx.ctx);
let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
let ndarray_calc_size_fn_name = match llvm_usize.get_bit_width() {
32 => "__nac3_ndarray_calc_size",
64 => "__nac3_ndarray_calc_size64",
bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
};
let ndarray_calc_size_fn_t = llvm_usize.fn_type(
&[llvm_pusize.into(), llvm_usize.into(), llvm_usize.into(), llvm_usize.into()],
false,
);
let ndarray_calc_size_fn =
ctx.module.get_function(ndarray_calc_size_fn_name).unwrap_or_else(|| {
ctx.module.add_function(ndarray_calc_size_fn_name, ndarray_calc_size_fn_t, None)
});
let begin = begin.unwrap_or_else(|| llvm_usize.const_zero());
let end = end.unwrap_or_else(|| dims.size(ctx, generator));
ctx.builder
.build_call(
ndarray_calc_size_fn,
&[
dims.base_ptr(ctx, generator).into(),
dims.size(ctx, generator).into(),
begin.into(),
end.into(),
],
"",
)
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Generates a call to `__nac3_ndarray_calc_nd_indices`. Returns a [`TypeArrayLikeAdpater`]
/// containing `i32` indices of the flattened index.
///
/// * `index` - The index to compute the multidimensional index for.
/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
/// `NDArray`.
pub fn call_ndarray_calc_nd_indices<'ctx, G: CodeGenerator + ?Sized>(
generator: &G,
ctx: &mut CodeGenContext<'ctx, '_>,
index: IntValue<'ctx>,
ndarray: NDArrayValue<'ctx>,
) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
let llvm_void = ctx.ctx.void_type();
let llvm_i32 = ctx.ctx.i32_type();
let llvm_usize = generator.get_size_type(ctx.ctx);
let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
let ndarray_calc_nd_indices_fn_name = match llvm_usize.get_bit_width() {
32 => "__nac3_ndarray_calc_nd_indices",
64 => "__nac3_ndarray_calc_nd_indices64",
bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
};
let ndarray_calc_nd_indices_fn =
ctx.module.get_function(ndarray_calc_nd_indices_fn_name).unwrap_or_else(|| {
let fn_type = llvm_void.fn_type(
&[llvm_usize.into(), llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into()],
false,
);
ctx.module.add_function(ndarray_calc_nd_indices_fn_name, fn_type, None)
});
let ndarray_num_dims = ndarray.load_ndims(ctx);
let ndarray_dims = ndarray.dim_sizes();
let indices = ctx.builder.build_array_alloca(llvm_i32, ndarray_num_dims, "").unwrap();
ctx.builder
.build_call(
ndarray_calc_nd_indices_fn,
&[
index.into(),
ndarray_dims.base_ptr(ctx, generator).into(),
ndarray_num_dims.into(),
indices.into(),
],
"",
)
.unwrap();
TypedArrayLikeAdapter::from(
ArraySliceValue::from_ptr_val(indices, ndarray_num_dims, None),
Box::new(|_, v| v.into_int_value()),
Box::new(|_, v| v.into()),
)
}
fn call_ndarray_flatten_index_impl<'ctx, G, Indices>(
generator: &G,
ctx: &CodeGenContext<'ctx, '_>,
ndarray: NDArrayValue<'ctx>,
indices: &Indices,
) -> IntValue<'ctx>
where
G: CodeGenerator + ?Sized,
Indices: ArrayLikeIndexer<'ctx>,
{
let llvm_i32 = ctx.ctx.i32_type();
let llvm_usize = generator.get_size_type(ctx.ctx);
let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
debug_assert_eq!(
IntType::try_from(indices.element_type(ctx, generator))
.map(IntType::get_bit_width)
.unwrap_or_default(),
llvm_i32.get_bit_width(),
"Expected i32 value for argument `indices` to `call_ndarray_flatten_index_impl`"
);
debug_assert_eq!(
indices.size(ctx, generator).get_type().get_bit_width(),
llvm_usize.get_bit_width(),
"Expected usize integer value for argument `indices_size` to `call_ndarray_flatten_index_impl`"
);
let ndarray_flatten_index_fn_name = match llvm_usize.get_bit_width() {
32 => "__nac3_ndarray_flatten_index",
64 => "__nac3_ndarray_flatten_index64",
bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
};
let ndarray_flatten_index_fn =
ctx.module.get_function(ndarray_flatten_index_fn_name).unwrap_or_else(|| {
let fn_type = llvm_usize.fn_type(
&[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_usize.into()],
false,
);
ctx.module.add_function(ndarray_flatten_index_fn_name, fn_type, None)
});
let ndarray_num_dims = ndarray.load_ndims(ctx);
let ndarray_dims = ndarray.dim_sizes();
let index = ctx
.builder
.build_call(
ndarray_flatten_index_fn,
&[
ndarray_dims.base_ptr(ctx, generator).into(),
ndarray_num_dims.into(),
indices.base_ptr(ctx, generator).into(),
indices.size(ctx, generator).into(),
],
"",
)
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_int_value))
.map(Either::unwrap_left)
.unwrap();
index
}
/// Generates a call to `__nac3_ndarray_flatten_index`. Returns the flattened index for the
/// multidimensional index.
///
/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
/// `NDArray`.
/// * `indices` - The multidimensional index to compute the flattened index for.
pub fn call_ndarray_flatten_index<'ctx, G, Index>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
ndarray: NDArrayValue<'ctx>,
indices: &Index,
) -> IntValue<'ctx>
where
G: CodeGenerator + ?Sized,
Index: ArrayLikeIndexer<'ctx>,
{
call_ndarray_flatten_index_impl(generator, ctx, ndarray, indices)
}
/// Generates a call to `__nac3_ndarray_calc_broadcast`. Returns a tuple containing the number of
/// dimension and size of each dimension of the resultant `ndarray`.
pub fn call_ndarray_calc_broadcast<'ctx, G: CodeGenerator + ?Sized>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
lhs: NDArrayValue<'ctx>,
rhs: NDArrayValue<'ctx>,
) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
let llvm_usize = generator.get_size_type(ctx.ctx);
let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
32 => "__nac3_ndarray_calc_broadcast",
64 => "__nac3_ndarray_calc_broadcast64",
bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
};
let ndarray_calc_broadcast_fn =
ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
let fn_type = llvm_usize.fn_type(
&[
llvm_pusize.into(),
llvm_usize.into(),
llvm_pusize.into(),
llvm_usize.into(),
llvm_pusize.into(),
],
false,
);
ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
});
let lhs_ndims = lhs.load_ndims(ctx);
let rhs_ndims = rhs.load_ndims(ctx);
let min_ndims = llvm_intrinsics::call_int_umin(ctx, lhs_ndims, rhs_ndims, None);
gen_for_callback_incrementing(
generator,
ctx,
None,
llvm_usize.const_zero(),
(min_ndims, false),
|generator, ctx, _, idx| {
let idx = ctx.builder.build_int_sub(min_ndims, idx, "").unwrap();
let (lhs_dim_sz, rhs_dim_sz) = unsafe {
(
lhs.dim_sizes().get_typed_unchecked(ctx, generator, &idx, None),
rhs.dim_sizes().get_typed_unchecked(ctx, generator, &idx, None),
)
};
let llvm_usize_const_one = llvm_usize.const_int(1, false);
let lhs_eqz = ctx
.builder
.build_int_compare(IntPredicate::EQ, lhs_dim_sz, llvm_usize_const_one, "")
.unwrap();
let rhs_eqz = ctx
.builder
.build_int_compare(IntPredicate::EQ, rhs_dim_sz, llvm_usize_const_one, "")
.unwrap();
let lhs_or_rhs_eqz = ctx.builder.build_or(lhs_eqz, rhs_eqz, "").unwrap();
let lhs_eq_rhs = ctx
.builder
.build_int_compare(IntPredicate::EQ, lhs_dim_sz, rhs_dim_sz, "")
.unwrap();
let is_compatible = ctx.builder.build_or(lhs_or_rhs_eqz, lhs_eq_rhs, "").unwrap();
ctx.make_assert(
generator,
is_compatible,
"0:ValueError",
"operands could not be broadcast together",
[None, None, None],
ctx.current_loc,
);
Ok(())
},
llvm_usize.const_int(1, false),
)
.unwrap();
let max_ndims = llvm_intrinsics::call_int_umax(ctx, lhs_ndims, rhs_ndims, None);
let lhs_dims = lhs.dim_sizes().base_ptr(ctx, generator);
let lhs_ndims = lhs.load_ndims(ctx);
let rhs_dims = rhs.dim_sizes().base_ptr(ctx, generator);
let rhs_ndims = rhs.load_ndims(ctx);
let out_dims = ctx.builder.build_array_alloca(llvm_usize, max_ndims, "").unwrap();
let out_dims = ArraySliceValue::from_ptr_val(out_dims, max_ndims, None);
ctx.builder
.build_call(
ndarray_calc_broadcast_fn,
&[
lhs_dims.into(),
lhs_ndims.into(),
rhs_dims.into(),
rhs_ndims.into(),
out_dims.base_ptr(ctx, generator).into(),
],
"",
)
.unwrap();
TypedArrayLikeAdapter::from(
out_dims,
Box::new(|_, v| v.into_int_value()),
Box::new(|_, v| v.into()),
)
}
/// Generates a call to `__nac3_ndarray_calc_broadcast_idx`. Returns an [`ArrayAllocaValue`]
/// containing the indices used for accessing `array` corresponding to the index of the broadcasted
/// array `broadcast_idx`.
pub fn call_ndarray_calc_broadcast_index<
'ctx,
G: CodeGenerator + ?Sized,
BroadcastIdx: UntypedArrayLikeAccessor<'ctx>,
>(
generator: &mut G,
ctx: &mut CodeGenContext<'ctx, '_>,
array: NDArrayValue<'ctx>,
broadcast_idx: &BroadcastIdx,
) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
let llvm_i32 = ctx.ctx.i32_type();
let llvm_usize = generator.get_size_type(ctx.ctx);
let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
32 => "__nac3_ndarray_calc_broadcast_idx",
64 => "__nac3_ndarray_calc_broadcast_idx64",
bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
};
let ndarray_calc_broadcast_fn =
ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
let fn_type = llvm_usize.fn_type(
&[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_pi32.into()],
false,
);
ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
});
let broadcast_size = broadcast_idx.size(ctx, generator);
let out_idx = ctx.builder.build_array_alloca(llvm_i32, broadcast_size, "").unwrap();
let array_dims = array.dim_sizes().base_ptr(ctx, generator);
let array_ndims = array.load_ndims(ctx);
let broadcast_idx_ptr = unsafe {
broadcast_idx.ptr_offset_unchecked(ctx, generator, &llvm_usize.const_zero(), None)
};
ctx.builder
.build_call(
ndarray_calc_broadcast_fn,
&[array_dims.into(), array_ndims.into(), broadcast_idx_ptr.into(), out_idx.into()],
"",
)
.unwrap();
TypedArrayLikeAdapter::from(
ArraySliceValue::from_ptr_val(out_idx, broadcast_size, None),
Box::new(|_, v| v.into_int_value()),
Box::new(|_, v| v.into()),
)
}

345
nac3core/src/codegen/llvm_intrinsics.rs
View File

@ -1,345 +0,0 @@
use inkwell::{
context::Context,
intrinsics::Intrinsic,
types::{AnyTypeEnum::IntType, FloatType},
values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue, PointerValue},
AddressSpace,
};
use itertools::Either;
use super::CodeGenContext;
/// Returns the string representation for the floating-point type `ft` when used in intrinsic
/// functions.
fn get_float_intrinsic_repr(ctx: &Context, ft: FloatType) -> &'static str {
// Standard LLVM floating-point types
if ft == ctx.f16_type() {
return "f16";
}
if ft == ctx.f32_type() {
return "f32";
}
if ft == ctx.f64_type() {
return "f64";
}
if ft == ctx.f128_type() {
return "f128";
}
// Non-standard floating-point types
if ft == ctx.x86_f80_type() {
return "f80";
}
if ft == ctx.ppc_f128_type() {
return "ppcf128";
}
unreachable!()
}
/// Invokes the [`llvm.va_start`](https://llvm.org/docs/LangRef.html#llvm-va-start-intrinsic)
/// intrinsic.
pub fn call_va_start<'ctx>(ctx: &CodeGenContext<'ctx, '_>, arglist: PointerValue<'ctx>) {
const FN_NAME: &str = "llvm.va_start";
let intrinsic_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let llvm_void = ctx.ctx.void_type();
let llvm_i8 = ctx.ctx.i8_type();
let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
let fn_type = llvm_void.fn_type(&[llvm_p0i8.into()], false);
ctx.module.add_function(FN_NAME, fn_type, None)
});
ctx.builder.build_call(intrinsic_fn, &[arglist.into()], "").unwrap();
}
/// Invokes the [`llvm.va_start`](https://llvm.org/docs/LangRef.html#llvm-va-start-intrinsic)
/// intrinsic.
pub fn call_va_end<'ctx>(ctx: &CodeGenContext<'ctx, '_>, arglist: PointerValue<'ctx>) {
const FN_NAME: &str = "llvm.va_end";
let intrinsic_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let llvm_void = ctx.ctx.void_type();
let llvm_i8 = ctx.ctx.i8_type();
let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
let fn_type = llvm_void.fn_type(&[llvm_p0i8.into()], false);
ctx.module.add_function(FN_NAME, fn_type, None)
});
ctx.builder.build_call(intrinsic_fn, &[arglist.into()], "").unwrap();
}
/// Invokes the [`llvm.stacksave`](https://llvm.org/docs/LangRef.html#llvm-stacksave-intrinsic)
/// intrinsic.
pub fn call_stacksave<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
name: Option<&str>,
) -> PointerValue<'ctx> {
const FN_NAME: &str = "llvm.stacksave";
let intrinsic_fn = Intrinsic::find(FN_NAME)
.and_then(|intrinsic| intrinsic.get_declaration(&ctx.module, &[]))
.unwrap();
ctx.builder
.build_call(intrinsic_fn, &[], name.unwrap_or_default())
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_pointer_value))
.map(Either::unwrap_left)
.unwrap()
}
/// Invokes the
/// [`llvm.stackrestore`](https://llvm.org/docs/LangRef.html#llvm-stackrestore-intrinsic) intrinsic.
///
/// - `ptr`: The pointer storing the address to restore the stack to.
pub fn call_stackrestore<'ctx>(ctx: &CodeGenContext<'ctx, '_>, ptr: PointerValue<'ctx>) {
const FN_NAME: &str = "llvm.stackrestore";
/*
SEE https://github.com/TheDan64/inkwell/issues/496
We want `llvm.stackrestore`, but the following would generate `llvm.stackrestore.p0i8`.
```ignore
let intrinsic_fn = Intrinsic::find(FN_NAME)
.and_then(|intrinsic| intrinsic.get_declaration(&ctx.module, &[llvm_p0i8.into()]))
.unwrap();
```
Temp workaround by manually declaring the intrinsic with the correct function name instead.
*/
let intrinsic_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
let llvm_void = ctx.ctx.void_type();
let llvm_i8 = ctx.ctx.i8_type();
let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
let fn_type = llvm_void.fn_type(&[llvm_p0i8.into()], false);
ctx.module.add_function(FN_NAME, fn_type, None)
});
ctx.builder.build_call(intrinsic_fn, &[ptr.into()], "").unwrap();
}
/// Invokes the [`llvm.memcpy`](https://llvm.org/docs/LangRef.html#llvm-memcpy-intrinsic) intrinsic.
///
/// * `dest` - The pointer to the destination. Must be a pointer to an integer type.
/// * `src` - The pointer to the source. Must be a pointer to an integer type.
/// * `len` - The number of bytes to copy.
/// * `is_volatile` - Whether the `memcpy` operation should be `volatile`.
pub fn call_memcpy<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
dest: PointerValue<'ctx>,
src: PointerValue<'ctx>,
len: IntValue<'ctx>,
is_volatile: IntValue<'ctx>,
) {
const FN_NAME: &str = "llvm.memcpy";
debug_assert!(dest.get_type().get_element_type().is_int_type());
debug_assert!(src.get_type().get_element_type().is_int_type());
debug_assert_eq!(
dest.get_type().get_element_type().into_int_type().get_bit_width(),
src.get_type().get_element_type().into_int_type().get_bit_width(),
);
debug_assert!(matches!(len.get_type().get_bit_width(), 32 | 64));
debug_assert_eq!(is_volatile.get_type().get_bit_width(), 1);
let llvm_dest_t = dest.get_type();
let llvm_src_t = src.get_type();
let llvm_len_t = len.get_type();
let intrinsic_fn = Intrinsic::find(FN_NAME)
.and_then(|intrinsic| {
intrinsic.get_declaration(
&ctx.module,
&[llvm_dest_t.into(), llvm_src_t.into(), llvm_len_t.into()],
)
})
.unwrap();
ctx.builder
.build_call(intrinsic_fn, &[dest.into(), src.into(), len.into(), is_volatile.into()], "")
.unwrap();
}
/// Invokes the `llvm.memcpy` intrinsic.
///
/// Unlike [`call_memcpy`], this function accepts any type of pointer value. If `dest` or `src` is
/// not a pointer to an integer, the pointer(s) will be cast to `i8*` before invoking `memcpy`.
pub fn call_memcpy_generic<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
dest: PointerValue<'ctx>,
src: PointerValue<'ctx>,
len: IntValue<'ctx>,
is_volatile: IntValue<'ctx>,
) {
let llvm_i8 = ctx.ctx.i8_type();
let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
let dest_elem_t = dest.get_type().get_element_type();
let src_elem_t = src.get_type().get_element_type();
let dest = if matches!(dest_elem_t, IntType(t) if t.get_bit_width() == 8) {
dest
} else {
ctx.builder
.build_bit_cast(dest, llvm_p0i8, "")
.map(BasicValueEnum::into_pointer_value)
.unwrap()
};
let src = if matches!(src_elem_t, IntType(t) if t.get_bit_width() == 8) {
src
} else {
ctx.builder
.build_bit_cast(src, llvm_p0i8, "")
.map(BasicValueEnum::into_pointer_value)
.unwrap()
};
call_memcpy(ctx, dest, src, len, is_volatile);
}
/// Macro to find and generate build call for llvm intrinsic (body of llvm intrinsic function)
///
/// Arguments:
/// * `$ctx:ident`: Reference to the current Code Generation Context
/// * `$name:ident`: Optional name to be assigned to the llvm build call (Option<&str>)
/// * `$llvm_name:literal`: Name of underlying llvm intrinsic function
/// * `$map_fn:ident`: Mapping function to be applied on `BasicValue` (`BasicValue` -> Function Return Type).
/// Use `BasicValueEnum::into_int_value` for Integer return type and
/// `BasicValueEnum::into_float_value` for Float return type
/// * `$llvm_ty:ident`: Type of first operand
/// * `,($val:ident)*`: Comma separated list of operands
macro_rules! generate_llvm_intrinsic_fn_body {
($ctx:ident, $name:ident, $llvm_name:literal, $map_fn:expr, $llvm_ty:ident $(,$val:ident)*) => {{
const FN_NAME: &str = concat!("llvm.", $llvm_name);
let intrinsic_fn = Intrinsic::find(FN_NAME).and_then(|intrinsic| intrinsic.get_declaration(&$ctx.module, &[$llvm_ty.into()])).unwrap();
$ctx.builder.build_call(intrinsic_fn, &[$($val.into()),*], $name.unwrap_or_default()).map(CallSiteValue::try_as_basic_value).map(|v| v.map_left($map_fn)).map(Either::unwrap_left).unwrap()
}};
}
/// Macro to generate the llvm intrinsic function using [`generate_llvm_intrinsic_fn_body`].
///
/// Arguments:
/// * `float/int`: Indicates the return and argument type of the function
/// * `$fn_name:ident`: The identifier of the rust function to be generated
/// * `$llvm_name:literal`: Name of underlying llvm intrinsic function.
/// Omit "llvm." prefix from the function name i.e. use "ceil" instead of "llvm.ceil"
/// * `$val:ident`: The operand for unary operations
/// * `$val1:ident`, `$val2:ident`: The operands for binary operations
macro_rules! generate_llvm_intrinsic_fn {
("float", $fn_name:ident, $llvm_name:literal, $val:ident) => {
#[doc = concat!("Invokes the [`", stringify!($llvm_name), "`](https://llvm.org/docs/LangRef.html#llvm-", stringify!($llvm_name), "-intrinsic) intrinsic." )]
pub fn $fn_name<'ctx> (
ctx: &CodeGenContext<'ctx, '_>,
$val: FloatValue<'ctx>,
name: Option<&str>,
) -> FloatValue<'ctx> {
let llvm_ty = $val.get_type();
generate_llvm_intrinsic_fn_body!(ctx, name, $llvm_name, BasicValueEnum::into_float_value, llvm_ty, $val)
}
};
("float", $fn_name:ident, $llvm_name:literal, $val1:ident, $val2:ident) => {
#[doc = concat!("Invokes the [`", stringify!($llvm_name), "`](https://llvm.org/docs/LangRef.html#llvm-", stringify!($llvm_name), "-intrinsic) intrinsic." )]
pub fn $fn_name<'ctx> (
ctx: &CodeGenContext<'ctx, '_>,
$val1: FloatValue<'ctx>,
$val2: FloatValue<'ctx>,
name: Option<&str>,
) -> FloatValue<'ctx> {
debug_assert_eq!($val1.get_type(), $val2.get_type());
let llvm_ty = $val1.get_type();
generate_llvm_intrinsic_fn_body!(ctx, name, $llvm_name, BasicValueEnum::into_float_value, llvm_ty, $val1, $val2)
}
};
("int", $fn_name:ident, $llvm_name:literal, $val1:ident, $val2:ident) => {
#[doc = concat!("Invokes the [`", stringify!($llvm_name), "`](https://llvm.org/docs/LangRef.html#llvm-", stringify!($llvm_name), "-intrinsic) intrinsic." )]
pub fn $fn_name<'ctx> (
ctx: &CodeGenContext<'ctx, '_>,
$val1: IntValue<'ctx>,
$val2: IntValue<'ctx>,
name: Option<&str>,
) -> IntValue<'ctx> {
debug_assert_eq!($val1.get_type().get_bit_width(), $val2.get_type().get_bit_width());
let llvm_ty = $val1.get_type();
generate_llvm_intrinsic_fn_body!(ctx, name, $llvm_name, BasicValueEnum::into_int_value, llvm_ty, $val1, $val2)
}
};
}
/// Invokes the [`llvm.abs`](https://llvm.org/docs/LangRef.html#llvm-abs-intrinsic) intrinsic.
///
/// * `src` - The value for which the absolute value is to be returned.
/// * `is_int_min_poison` - Whether `poison` is to be returned if `src` is `INT_MIN`.
pub fn call_int_abs<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
src: IntValue<'ctx>,
is_int_min_poison: IntValue<'ctx>,
name: Option<&str>,
) -> IntValue<'ctx> {
debug_assert_eq!(is_int_min_poison.get_type().get_bit_width(), 1);
debug_assert!(is_int_min_poison.is_const());
let src_type = src.get_type();
generate_llvm_intrinsic_fn_body!(
ctx,
name,
"abs",
BasicValueEnum::into_int_value,
src_type,
src,
is_int_min_poison
)
}
generate_llvm_intrinsic_fn!("int", call_int_smax, "smax", a, b);
generate_llvm_intrinsic_fn!("int", call_int_smin, "smin", a, b);
generate_llvm_intrinsic_fn!("int", call_int_umax, "umax", a, b);
generate_llvm_intrinsic_fn!("int", call_int_umin, "umin", a, b);
generate_llvm_intrinsic_fn!("int", call_expect, "expect", val, expected_val);
generate_llvm_intrinsic_fn!("float", call_float_sqrt, "sqrt", val);
generate_llvm_intrinsic_fn!("float", call_float_sin, "sin", val);
generate_llvm_intrinsic_fn!("float", call_float_cos, "cos", val);
generate_llvm_intrinsic_fn!("float", call_float_pow, "pow", val, power);
generate_llvm_intrinsic_fn!("float", call_float_exp, "exp", val);
generate_llvm_intrinsic_fn!("float", call_float_exp2, "exp2", val);
generate_llvm_intrinsic_fn!("float", call_float_log, "log", val);
generate_llvm_intrinsic_fn!("float", call_float_log10, "log10", val);
generate_llvm_intrinsic_fn!("float", call_float_log2, "log2", val);
generate_llvm_intrinsic_fn!("float", call_float_fabs, "fabs", src);
generate_llvm_intrinsic_fn!("float", call_float_minnum, "minnum", val, power);
generate_llvm_intrinsic_fn!("float", call_float_maxnum, "maxnum", val, power);
generate_llvm_intrinsic_fn!("float", call_float_copysign, "copysign", mag, sgn);
generate_llvm_intrinsic_fn!("float", call_float_floor, "floor", val);
generate_llvm_intrinsic_fn!("float", call_float_ceil, "ceil", val);
generate_llvm_intrinsic_fn!("float", call_float_round, "round", val);
generate_llvm_intrinsic_fn!("float", call_float_rint, "rint", val);
/// Invokes the [`llvm.powi`](https://llvm.org/docs/LangRef.html#llvm-powi-intrinsic) intrinsic.
pub fn call_float_powi<'ctx>(
ctx: &CodeGenContext<'ctx, '_>,
val: FloatValue<'ctx>,
power: IntValue<'ctx>,
name: Option<&str>,
) -> FloatValue<'ctx> {
const FN_NAME: &str = "llvm.powi";
let llvm_val_t = val.get_type();
let llvm_power_t = power.get_type();
let intrinsic_fn = Intrinsic::find(FN_NAME)
.and_then(|intrinsic| {
intrinsic.get_declaration(&ctx.module, &[llvm_val_t.into(), llvm_power_t.into()])
})
.unwrap();
ctx.builder
.build_call(intrinsic_fn, &[val.into(), power.into()], name.unwrap_or_default())
.map(CallSiteValue::try_as_basic_value)
.map(|v| v.map_left(BasicValueEnum::into_float_value))
.map(Either::unwrap_left)
.unwrap()
}

885
nac3core/src/codegen/mod.rs
View File

File diff suppressed because it is too large Load Diff

2525
nac3core/src/codegen/numpy.rs
View File

File diff suppressed because it is too large Load Diff

2271
nac3core/src/codegen/stmt.rs
View File

File diff suppressed because it is too large Load Diff

239
nac3core/src/codegen/test.rs
View File

@ -1,37 +1,25 @@
use std::{
collections::{HashMap, HashSet},
sync::Arc,
use crate::{
codegen::{
concrete_type::ConcreteTypeStore, CodeGenContext, CodeGenTask, DefaultCodeGenerator,
WithCall, WorkerRegistry,
},
symbol_resolver::{SymbolResolver, ValueEnum},
toplevel::{
composer::TopLevelComposer, DefinitionId, FunInstance, TopLevelContext, TopLevelDef,
},
typecheck::{
type_inferencer::{FunctionData, Inferencer, PrimitiveStore},
typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier},
},
};
use indexmap::IndexMap;
use indoc::indoc;
use inkwell::{
targets::{InitializationConfig, Target},
OptimizationLevel,
};
use nac3parser::{
ast::{fold::Fold, FileName, StrRef},
ast::{fold::Fold, StrRef},
parser::parse_program,
};
use parking_lot::RwLock;
use super::{
classes::{ListType, NDArrayType, ProxyType, RangeType},
concrete_type::ConcreteTypeStore,
CodeGenContext, CodeGenLLVMOptions, CodeGenTargetMachineOptions, CodeGenTask, CodeGenerator,
DefaultCodeGenerator, WithCall, WorkerRegistry,
};
use crate::{
symbol_resolver::{SymbolResolver, ValueEnum},
toplevel::{
composer::{ComposerConfig, TopLevelComposer},
DefinitionId, FunInstance, TopLevelContext, TopLevelDef,
},
typecheck::{
type_inferencer::{FunctionData, IdentifierInfo, Inferencer, PrimitiveStore},
typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier, VarMap},
},
};
use std::collections::{HashMap, HashSet};
use std::sync::Arc;
struct Resolver {
id_to_type: HashMap<StrRef, Type>,
@ -60,31 +48,30 @@ impl SymbolResolver for Resolver {
_: &PrimitiveStore,
str: StrRef,
) -> Result<Type, String> {
self.id_to_type.get(&str).copied().ok_or_else(|| format!("cannot find symbol `{str}`"))
self.id_to_type.get(&str).cloned().ok_or_else(|| format!("cannot find symbol `{}`", str))
}
fn get_symbol_value<'ctx>(
fn get_symbol_value<'ctx, 'a>(
&self,
_: StrRef,
_: &mut CodeGenContext<'ctx, '_>,
_: &mut dyn CodeGenerator,
_: &mut CodeGenContext<'ctx, 'a>,
) -> Option<ValueEnum<'ctx>> {
unimplemented!()
}
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, HashSet<String>> {
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
self.id_to_def
.read()
.get(&id)
.copied()
.ok_or_else(|| HashSet::from([format!("cannot find symbol `{id}`")]))
.cloned()
.ok_or_else(|| format!("cannot find symbol `{}`", id))
}
fn get_string_id(&self, _: &str) -> i32 {
unimplemented!()
}
fn get_exception_id(&self, _tyid: usize) -> usize {
fn get_exception_id(&self, tyid: usize) -> usize {
unimplemented!()
}
}
@ -96,9 +83,9 @@ fn test_primitives() {
d = a if c == 1 else 0
return d
"};
let statements = parse_program(source, FileName::default()).unwrap();
let statements = parse_program(source, Default::default()).unwrap();
let composer = TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 32).0;
let composer: TopLevelComposer = Default::default();
let mut unifier = composer.unifier.clone();
let primitives = composer.primitives_ty;
let top_level = Arc::new(composer.make_top_level_context());
@ -107,27 +94,17 @@ fn test_primitives() {
let resolver = Arc::new(Resolver {
id_to_type: HashMap::new(),
id_to_def: RwLock::new(HashMap::new()),
class_names: HashMap::default(),
class_names: Default::default(),
}) as Arc<dyn SymbolResolver + Send + Sync>;
let threads = vec![DefaultCodeGenerator::new("test".into(), 32).into()];
let signature = FunSignature {
args: vec![
FuncArg {
name: "a".into(),
ty: primitives.int32,
default_value: None,
is_vararg: false,
},
FuncArg {
name: "b".into(),
ty: primitives.int32,
default_value: None,
is_vararg: false,
},
FuncArg { name: "a".into(), ty: primitives.int32, default_value: None },
FuncArg { name: "b".into(), ty: primitives.int32, default_value: None },
],
ret: primitives.int32,
vars: VarMap::new(),
vars: HashMap::new(),
};
let mut store = ConcreteTypeStore::new();
@ -142,13 +119,12 @@ fn test_primitives() {
};
let mut virtual_checks = Vec::new();
let mut calls = HashMap::new();
let mut identifiers: HashMap<_, _> =
["a".into(), "b".into()].map(|id| (id, IdentifierInfo::default())).into();
let mut identifiers: HashSet<_> = ["a".into(), "b".into()].iter().cloned().collect();
let mut inferencer = Inferencer {
top_level: &top_level,
function_data: &mut function_data,
unifier: &mut unifier,
variable_mapping: HashMap::default(),
variable_mapping: Default::default(),
primitives: &primitives,
virtual_checks: &mut virtual_checks,
calls: &mut calls,
@ -172,7 +148,7 @@ fn test_primitives() {
});
let task = CodeGenTask {
subst: Vec::default(),
subst: Default::default(),
symbol_name: "testing".into(),
body: Arc::new(statements),
unifier_index: 0,
@ -204,48 +180,19 @@ fn test_primitives() {
let expected = indoc! {"
; ModuleID = 'test'
source_filename = \"test\"
target datalayout = \"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128\"
target triple = \"x86_64-unknown-linux-gnu\"
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define i32 @testing(i32 %0, i32 %1) local_unnamed_addr #0 !dbg !4 {
define i32 @testing(i32 %0, i32 %1) {
init:
%add = add i32 %1, %0, !dbg !9
%cmp = icmp eq i32 %add, 1, !dbg !10
%. = select i1 %cmp, i32 %0, i32 0, !dbg !11
ret i32 %., !dbg !12
%add = add i32 %0, %1
%cmp = icmp eq i32 %add, 1
%ifexpr = select i1 %cmp, i32 %0, i32 0
ret i32 %ifexpr
}
attributes #0 = { mustprogress nofree norecurse nosync nounwind readnone willreturn }
!llvm.module.flags = !{!0, !1}
!llvm.dbg.cu = !{!2}
!0 = !{i32 2, !\"Debug Info Version\", i32 3}
!1 = !{i32 2, !\"Dwarf Version\", i32 4}
!2 = distinct !DICompileUnit(language: DW_LANG_Python, file: !3, producer: \"NAC3\", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug)
!3 = !DIFile(filename: \"unknown\", directory: \"\")
!4 = distinct !DISubprogram(name: \"testing\", linkageName: \"testing\", scope: null, file: !3, line: 1, type: !5, scopeLine: 1, flags: DIFlagPublic, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !8)
!5 = !DISubroutineType(flags: DIFlagPublic, types: !6)
!6 = !{!7}
!7 = !DIBasicType(name: \"_\", flags: DIFlagPublic)
!8 = !{}
!9 = !DILocation(line: 1, column: 9, scope: !4)
!10 = !DILocation(line: 2, column: 15, scope: !4)
!11 = !DILocation(line: 0, scope: !4)
!12 = !DILocation(line: 3, column: 8, scope: !4)
"}
"}
.trim();
assert_eq!(expected, module.print_to_string().to_str().unwrap().trim());
})));
Target::initialize_all(&InitializationConfig::default());
let llvm_options = CodeGenLLVMOptions {
opt_level: OptimizationLevel::Default,
target: CodeGenTargetMachineOptions::from_host_triple(),
};
let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, &llvm_options, &f);
let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, f);
registry.add_task(task);
registry.wait_tasks_complete(handles);
}
@ -256,28 +203,23 @@ fn test_simple_call() {
a = foo(a)
return a * 2
"};
let statements_1 = parse_program(source_1, FileName::default()).unwrap();
let statements_1 = parse_program(source_1, Default::default()).unwrap();
let source_2 = indoc! { "
return a + 1
"};
let statements_2 = parse_program(source_2, FileName::default()).unwrap();
let statements_2 = parse_program(source_2, Default::default()).unwrap();
let composer = TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 32).0;
let composer: TopLevelComposer = Default::default();
let mut unifier = composer.unifier.clone();
let primitives = composer.primitives_ty;
let top_level = Arc::new(composer.make_top_level_context());
unifier.top_level = Some(top_level.clone());
let signature = FunSignature {
args: vec![FuncArg {
name: "a".into(),
ty: primitives.int32,
default_value: None,
is_vararg: false,
}],
args: vec![FuncArg { name: "a".into(), ty: primitives.int32, default_value: None }],
ret: primitives.int32,
vars: VarMap::new(),
vars: HashMap::new(),
};
let fun_ty = unifier.add_ty(TypeEnum::TFunc(signature.clone()));
let mut store = ConcreteTypeStore::new();
@ -301,7 +243,7 @@ fn test_simple_call() {
let resolver = Resolver {
id_to_type: HashMap::new(),
id_to_def: RwLock::new(HashMap::new()),
class_names: HashMap::default(),
class_names: Default::default(),
};
resolver.add_id_def("foo".into(), DefinitionId(foo_id));
let resolver = Arc::new(resolver) as Arc<dyn SymbolResolver + Send + Sync>;
@ -322,13 +264,12 @@ fn test_simple_call() {
};
let mut virtual_checks = Vec::new();
let mut calls = HashMap::new();
let mut identifiers: HashMap<_, _> =
["a".into(), "foo".into()].map(|id| (id, IdentifierInfo::default())).into();
let mut identifiers: HashSet<_> = ["a".into(), "foo".into()].iter().cloned().collect();
let mut inferencer = Inferencer {
top_level: &top_level,
function_data: &mut function_data,
unifier: &mut unifier,
variable_mapping: HashMap::default(),
variable_mapping: Default::default(),
primitives: &primitives,
virtual_checks: &mut virtual_checks,
calls: &mut calls,
@ -357,11 +298,11 @@ fn test_simple_call() {
&mut *top_level.definitions.read()[foo_id].write()
{
instance_to_stmt.insert(
String::new(),
"".to_string(),
FunInstance {
body: Arc::new(statements_2),
calls: Arc::new(inferencer.calls.clone()),
subst: IndexMap::default(),
subst: Default::default(),
unifier_id: 0,
},
);
@ -377,7 +318,7 @@ fn test_simple_call() {
});
let task = CodeGenTask {
subst: Vec::default(),
subst: Default::default(),
symbol_name: "testing".to_string(),
body: Arc::new(statements_1),
calls: Arc::new(calls1),
@ -391,86 +332,24 @@ fn test_simple_call() {
let expected = indoc! {"
; ModuleID = 'test'
source_filename = \"test\"
target datalayout = \"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128\"
target triple = \"x86_64-unknown-linux-gnu\"
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define i32 @testing(i32 %0) local_unnamed_addr #0 !dbg !5 {
define i32 @testing(i32 %0) {
init:
%add.i = shl i32 %0, 1, !dbg !10
%mul = add i32 %add.i, 2, !dbg !10
ret i32 %mul, !dbg !10
%call = call i32 @foo.0(i32 %0)
%mul = mul i32 %call, 2
ret i32 %mul
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define i32 @foo.0(i32 %0) local_unnamed_addr #0 !dbg !11 {
define i32 @foo.0(i32 %0) {
init:
%add = add i32 %0, 1, !dbg !12
ret i32 %add, !dbg !12
%add = add i32 %0, 1
ret i32 %add
}
attributes #0 = { mustprogress nofree norecurse nosync nounwind readnone willreturn }
!llvm.module.flags = !{!0, !1}
!llvm.dbg.cu = !{!2, !4}
!0 = !{i32 2, !\"Debug Info Version\", i32 3}
!1 = !{i32 2, !\"Dwarf Version\", i32 4}
!2 = distinct !DICompileUnit(language: DW_LANG_Python, file: !3, producer: \"NAC3\", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug)
!3 = !DIFile(filename: \"unknown\", directory: \"\")
!4 = distinct !DICompileUnit(language: DW_LANG_Python, file: !3, producer: \"NAC3\", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug)
!5 = distinct !DISubprogram(name: \"testing\", linkageName: \"testing\", scope: null, file: !3, line: 1, type: !6, scopeLine: 1, flags: DIFlagPublic, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !9)
!6 = !DISubroutineType(flags: DIFlagPublic, types: !7)
!7 = !{!8}
!8 = !DIBasicType(name: \"_\", flags: DIFlagPublic)
!9 = !{}
!10 = !DILocation(line: 2, column: 12, scope: !5)
!11 = distinct !DISubprogram(name: \"foo.0\", linkageName: \"foo.0\", scope: null, file: !3, line: 1, type: !6, scopeLine: 1, flags: DIFlagPublic, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !4, retainedNodes: !9)
!12 = !DILocation(line: 1, column: 12, scope: !11)
"}
"}
.trim();
assert_eq!(expected, module.print_to_string().to_str().unwrap().trim());
})));
Target::initialize_all(&InitializationConfig::default());
let llvm_options = CodeGenLLVMOptions {
opt_level: OptimizationLevel::Default,
target: CodeGenTargetMachineOptions::from_host_triple(),
};
let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, &llvm_options, &f);
let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, f);
registry.add_task(task);
registry.wait_tasks_complete(handles);
}
#[test]
fn test_classes_list_type_new() {
let ctx = inkwell::context::Context::create();
let generator = DefaultCodeGenerator::new(String::new(), 64);
let llvm_i32 = ctx.i32_type();
let llvm_usize = generator.get_size_type(&ctx);
let llvm_list = ListType::new(&generator, &ctx, llvm_i32.into());
assert!(ListType::is_type(llvm_list.as_base_type(), llvm_usize).is_ok());
}
#[test]
fn test_classes_range_type_new() {
let ctx = inkwell::context::Context::create();
let llvm_range = RangeType::new(&ctx);
assert!(RangeType::is_type(llvm_range.as_base_type()).is_ok());
}
#[test]
fn test_classes_ndarray_type_new() {
let ctx = inkwell::context::Context::create();
let generator = DefaultCodeGenerator::new(String::new(), 64);
let llvm_i32 = ctx.i32_type();
let llvm_usize = generator.get_size_type(&ctx);
let llvm_ndarray = NDArrayType::new(&generator, &ctx, llvm_i32.into());
assert!(NDArrayType::is_type(llvm_ndarray.as_base_type(), llvm_usize).is_ok());
}

26
nac3core/src/lib.rs
View File

@ -1,27 +1,5 @@
#![deny(
future_incompatible,
let_underscore,
nonstandard_style,
rust_2024_compatibility,
clippy::all
)]
#![warn(clippy::pedantic)]
#![allow(
dead_code,
clippy::cast_possible_truncation,
clippy::cast_sign_loss,
clippy::enum_glob_use,
clippy::missing_errors_doc,
clippy::missing_panics_doc,
clippy::module_name_repetitions,
clippy::similar_names,
clippy::too_many_lines,
clippy::wildcard_imports
)]
// users of nac3core need to use the same version of these dependencies, so expose them as nac3core::*
pub use inkwell;
pub use nac3parser;
#![warn(clippy::all)]
#![allow(dead_code)]
pub mod codegen;
pub mod symbol_resolver;

451
nac3core/src/symbol_resolver.rs
View File

@ -1,24 +1,23 @@
use std::{
collections::{HashMap, HashSet},
fmt::{Debug, Display},
rc::Rc,
sync::Arc,
};
use inkwell::values::{BasicValueEnum, FloatValue, IntValue, PointerValue, StructValue};
use itertools::{chain, izip, Itertools};
use parking_lot::RwLock;
use nac3parser::ast::{Constant, Expr, Location, StrRef};
use std::fmt::Debug;
use std::sync::Arc;
use std::{collections::HashMap, fmt::Display};
use crate::typecheck::typedef::TypeEnum;
use crate::{
codegen::{CodeGenContext, CodeGenerator},
toplevel::{type_annotation::TypeAnnotation, DefinitionId, TopLevelDef},
codegen::CodeGenContext,
toplevel::{DefinitionId, TopLevelDef},
};
use crate::{
codegen::CodeGenerator,
typecheck::{
type_inferencer::PrimitiveStore,
typedef::{Type, TypeEnum, Unifier, VarMap},
typedef::{Type, Unifier},
},
};
use inkwell::values::{BasicValueEnum, FloatValue, IntValue, PointerValue};
use itertools::{chain, izip};
use nac3parser::ast::{Expr, Location, StrRef};
use parking_lot::RwLock;
#[derive(Clone, PartialEq, Debug)]
pub enum SymbolValue {
@ -30,196 +29,17 @@ pub enum SymbolValue {
Double(f64),
Bool(bool),
Tuple(Vec<SymbolValue>),
OptionSome(Box<SymbolValue>),
OptionNone,
}
impl SymbolValue {
/// Creates a [`SymbolValue`] from a [`Constant`].
///
/// * `constant` - The constant to create the value from.
/// * `expected_ty` - The expected type of the [`SymbolValue`].
pub fn from_constant(
constant: &Constant,
expected_ty: Type,
primitives: &PrimitiveStore,
unifier: &mut Unifier,
) -> Result<Self, String> {
match constant {
Constant::None => {
if unifier.unioned(expected_ty, primitives.option) {
Ok(SymbolValue::OptionNone)
} else {
Err(format!("Expected {expected_ty:?}, but got Option"))
}
}
Constant::Bool(b) => {
if unifier.unioned(expected_ty, primitives.bool) {
Ok(SymbolValue::Bool(*b))
} else {
Err(format!("Expected {expected_ty:?}, but got bool"))
}
}
Constant::Str(s) => {
if unifier.unioned(expected_ty, primitives.str) {
Ok(SymbolValue::Str(s.to_string()))
} else {
Err(format!("Expected {expected_ty:?}, but got str"))
}
}
Constant::Int(i) => {
if unifier.unioned(expected_ty, primitives.int32) {
i32::try_from(*i).map(SymbolValue::I32).map_err(|e| e.to_string())
} else if unifier.unioned(expected_ty, primitives.int64) {
i64::try_from(*i).map(SymbolValue::I64).map_err(|e| e.to_string())
} else if unifier.unioned(expected_ty, primitives.uint32) {
u32::try_from(*i).map(SymbolValue::U32).map_err(|e| e.to_string())
} else if unifier.unioned(expected_ty, primitives.uint64) {
u64::try_from(*i).map(SymbolValue::U64).map_err(|e| e.to_string())
} else {
Err(format!("Expected {}, but got int", unifier.stringify(expected_ty)))
}
}
Constant::Tuple(t) => {
let expected_ty = unifier.get_ty(expected_ty);
let TypeEnum::TTuple { ty, is_vararg_ctx } = expected_ty.as_ref() else {
return Err(format!(
"Expected {:?}, but got Tuple",
expected_ty.get_type_name()
));
};
assert!(*is_vararg_ctx || ty.len() == t.len());
let elems = t
.iter()
.zip(ty)
.map(|(constant, ty)| Self::from_constant(constant, *ty, primitives, unifier))
.collect::<Result<Vec<SymbolValue>, _>>()?;
Ok(SymbolValue::Tuple(elems))
}
Constant::Float(f) => {
if unifier.unioned(expected_ty, primitives.float) {
Ok(SymbolValue::Double(*f))
} else {
Err(format!("Expected {expected_ty:?}, but got float"))
}
}
_ => Err(format!("Unsupported value type {constant:?}")),
}
}
/// Creates a [`SymbolValue`] from a [`Constant`], with its type being inferred from the constant value.
///
/// * `constant` - The constant to create the value from.
pub fn from_constant_inferred(constant: &Constant) -> Result<Self, String> {
match constant {
Constant::None => Ok(SymbolValue::OptionNone),
Constant::Bool(b) => Ok(SymbolValue::Bool(*b)),
Constant::Str(s) => Ok(SymbolValue::Str(s.to_string())),
Constant::Int(i) => {
let i = *i;
if i >= 0 {
i32::try_from(i)
.map(SymbolValue::I32)
.or_else(|_| i64::try_from(i).map(SymbolValue::I64))
.map_err(|_| {
format!("Literal cannot be expressed as any integral type: {i}")
})
} else {
u32::try_from(i)
.map(SymbolValue::U32)
.or_else(|_| u64::try_from(i).map(SymbolValue::U64))
.map_err(|_| {
format!("Literal cannot be expressed as any integral type: {i}")
})
}
}
Constant::Tuple(t) => {
let elems = t
.iter()
.map(Self::from_constant_inferred)
.collect::<Result<Vec<SymbolValue>, _>>()?;
Ok(SymbolValue::Tuple(elems))
}
Constant::Float(f) => Ok(SymbolValue::Double(*f)),
_ => Err(format!("Unsupported value type {constant:?}")),
}
}
/// Returns the [`Type`] representing the data type of this value.
pub fn get_type(&self, primitives: &PrimitiveStore, unifier: &mut Unifier) -> Type {
match self {
SymbolValue::I32(_) => primitives.int32,
SymbolValue::I64(_) => primitives.int64,
SymbolValue::U32(_) => primitives.uint32,
SymbolValue::U64(_) => primitives.uint64,
SymbolValue::Str(_) => primitives.str,
SymbolValue::Double(_) => primitives.float,
SymbolValue::Bool(_) => primitives.bool,
SymbolValue::Tuple(vs) => {
let vs_tys = vs.iter().map(|v| v.get_type(primitives, unifier)).collect::<Vec<_>>();
unifier.add_ty(TypeEnum::TTuple { ty: vs_tys, is_vararg_ctx: false })
}
SymbolValue::OptionSome(_) | SymbolValue::OptionNone => primitives.option,
}
}
/// Returns the [`TypeAnnotation`] representing the data type of this value.
pub fn get_type_annotation(
&self,
primitives: &PrimitiveStore,
unifier: &mut Unifier,
) -> TypeAnnotation {
match self {
SymbolValue::Bool(..)
| SymbolValue::Double(..)
| SymbolValue::I32(..)
| SymbolValue::I64(..)
| SymbolValue::U32(..)
| SymbolValue::U64(..)
| SymbolValue::Str(..) => TypeAnnotation::Primitive(self.get_type(primitives, unifier)),
SymbolValue::Tuple(vs) => {
let vs_tys = vs
.iter()
.map(|v| v.get_type_annotation(primitives, unifier))
.collect::<Vec<_>>();
TypeAnnotation::Tuple(vs_tys)
}
SymbolValue::OptionNone => TypeAnnotation::CustomClass {
id: primitives.option.obj_id(unifier).unwrap(),
params: Vec::default(),
},
SymbolValue::OptionSome(v) => {
let ty = v.get_type_annotation(primitives, unifier);
TypeAnnotation::CustomClass {
id: primitives.option.obj_id(unifier).unwrap(),
params: vec![ty],
}
}
}
}
/// Returns the [`TypeEnum`] representing the data type of this value.
pub fn get_type_enum(
&self,
primitives: &PrimitiveStore,
unifier: &mut Unifier,
) -> Rc<TypeEnum> {
let ty = self.get_type(primitives, unifier);
unifier.get_ty(ty)
}
}
impl Display for SymbolValue {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
match self {
SymbolValue::I32(i) => write!(f, "{i}"),
SymbolValue::I64(i) => write!(f, "int64({i})"),
SymbolValue::U32(i) => write!(f, "uint32({i})"),
SymbolValue::U64(i) => write!(f, "uint64({i})"),
SymbolValue::Str(s) => write!(f, "\"{s}\""),
SymbolValue::Double(d) => write!(f, "{d}"),
SymbolValue::I32(i) => write!(f, "{}", i),
SymbolValue::I64(i) => write!(f, "int64({})", i),
SymbolValue::U32(i) => write!(f, "uint32({})", i),
SymbolValue::U64(i) => write!(f, "uint64({})", i),
SymbolValue::Str(s) => write!(f, "\"{}\"", s),
SymbolValue::Double(d) => write!(f, "{}", d),
SymbolValue::Bool(b) => {
if *b {
write!(f, "True")
@ -228,82 +48,37 @@ impl Display for SymbolValue {
}
}
SymbolValue::Tuple(t) => {
write!(f, "({})", t.iter().map(|v| format!("{v}")).collect::<Vec<_>>().join(", "))
write!(f, "({})", t.iter().map(|v| format!("{}", v)).collect::<Vec<_>>().join(", "))
}
SymbolValue::OptionSome(v) => write!(f, "Some({v})"),
SymbolValue::OptionNone => write!(f, "none"),
}
}
}
impl TryFrom<SymbolValue> for u64 {
type Error = ();
/// Tries to convert a [`SymbolValue`] into a [`u64`], returning [`Err`] if the value is not
/// numeric or if the value cannot be converted into a `u64` without overflow.
fn try_from(value: SymbolValue) -> Result<Self, Self::Error> {
match value {
SymbolValue::I32(v) => u64::try_from(v).map_err(|_| ()),
SymbolValue::I64(v) => u64::try_from(v).map_err(|_| ()),
SymbolValue::U32(v) => Ok(u64::from(v)),
SymbolValue::U64(v) => Ok(v),
_ => Err(()),
}
}
}
impl TryFrom<SymbolValue> for i128 {
type Error = ();
/// Tries to convert a [`SymbolValue`] into a [`i128`], returning [`Err`] if the value is not
/// numeric.
fn try_from(value: SymbolValue) -> Result<Self, Self::Error> {
match value {
SymbolValue::I32(v) => Ok(i128::from(v)),
SymbolValue::I64(v) => Ok(i128::from(v)),
SymbolValue::U32(v) => Ok(i128::from(v)),
SymbolValue::U64(v) => Ok(i128::from(v)),
_ => Err(()),
}
}
}
pub trait StaticValue {
/// Returns a unique identifier for this value.
fn get_unique_identifier(&self) -> u64;
/// Returns the constant object represented by this unique identifier.
fn get_const_obj<'ctx>(
fn get_const_obj<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
generator: &mut dyn CodeGenerator,
) -> BasicValueEnum<'ctx>;
/// Converts this value to a LLVM [`BasicValueEnum`].
fn to_basic_value_enum<'ctx>(
fn to_basic_value_enum<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
generator: &mut dyn CodeGenerator,
expected_ty: Type,
) -> Result<BasicValueEnum<'ctx>, String>;
/// Returns a field within this value.
fn get_field<'ctx>(
fn get_field<'ctx, 'a>(
&self,
name: StrRef,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
) -> Option<ValueEnum<'ctx>>;
/// Returns a single element of this tuple.
fn get_tuple_element<'ctx>(&self, index: u32) -> Option<ValueEnum<'ctx>>;
}
#[derive(Clone)]
pub enum ValueEnum<'ctx> {
/// [`ValueEnum`] representing a static value.
Static(Arc<dyn StaticValue + Send + Sync>),
/// [`ValueEnum`] representing a dynamic value.
Dynamic(BasicValueEnum<'ctx>),
}
@ -331,29 +106,21 @@ impl<'ctx> From<FloatValue<'ctx>> for ValueEnum<'ctx> {
}
}
impl<'ctx> From<StructValue<'ctx>> for ValueEnum<'ctx> {
fn from(v: StructValue<'ctx>) -> Self {
ValueEnum::Dynamic(v.into())
}
}
impl<'ctx> ValueEnum<'ctx> {
/// Converts this [`ValueEnum`] to a [`BasicValueEnum`].
pub fn to_basic_value_enum<'a>(
self,
ctx: &mut CodeGenContext<'ctx, 'a>,
generator: &mut dyn CodeGenerator,
expected_ty: Type,
) -> Result<BasicValueEnum<'ctx>, String> {
match self {
ValueEnum::Static(v) => v.to_basic_value_enum(ctx, generator, expected_ty),
ValueEnum::Static(v) => v.to_basic_value_enum(ctx, generator),
ValueEnum::Dynamic(v) => Ok(v),
}
}
}
pub trait SymbolResolver {
/// Get type of type variable identifier or top-level function type,
// get type of type variable identifier or top-level function type
fn get_symbol_type(
&self,
unifier: &mut Unifier,
@ -362,67 +129,60 @@ pub trait SymbolResolver {
str: StrRef,
) -> Result<Type, String>;
/// Get the top-level definition of identifiers.
fn get_identifier_def(&self, str: StrRef) -> Result<DefinitionId, HashSet<String>>;
// get the top-level definition of identifiers
fn get_identifier_def(&self, str: StrRef) -> Result<DefinitionId, String>;
fn get_symbol_value<'ctx>(
fn get_symbol_value<'ctx, 'a>(
&self,
str: StrRef,
ctx: &mut CodeGenContext<'ctx, '_>,
generator: &mut dyn CodeGenerator,
ctx: &mut CodeGenContext<'ctx, 'a>,
) -> Option<ValueEnum<'ctx>>;
fn get_default_param_value(&self, expr: &Expr) -> Option<SymbolValue>;
fn get_default_param_value(&self, expr: &nac3parser::ast::Expr) -> Option<SymbolValue>;
fn get_string_id(&self, s: &str) -> i32;
fn get_exception_id(&self, tyid: usize) -> usize;
fn handle_deferred_eval(
&self,
_unifier: &mut Unifier,
_top_level_defs: &[Arc<RwLock<TopLevelDef>>],
_primitives: &PrimitiveStore,
) -> Result<(), String> {
Ok(())
}
// handle function call etc.
}
thread_local! {
static IDENTIFIER_ID: [StrRef; 11] = [
static IDENTIFIER_ID: [StrRef; 12] = [
"int32".into(),
"int64".into(),
"float".into(),
"bool".into(),
"None".into(),
"virtual".into(),
"list".into(),
"tuple".into(),
"str".into(),
"Exception".into(),
"uint32".into(),
"uint64".into(),
"Literal".into(),
];
}
/// Converts a type annotation into a [Type].
// convert type annotation into type
pub fn parse_type_annotation<T>(
resolver: &dyn SymbolResolver,
top_level_defs: &[Arc<RwLock<TopLevelDef>>],
unifier: &mut Unifier,
primitives: &PrimitiveStore,
expr: &Expr<T>,
) -> Result<Type, HashSet<String>> {
) -> Result<Type, String> {
use nac3parser::ast::ExprKind::*;
let ids = IDENTIFIER_ID.with(|ids| *ids);
let int32_id = ids[0];
let int64_id = ids[1];
let float_id = ids[2];
let bool_id = ids[3];
let virtual_id = ids[4];
let tuple_id = ids[5];
let str_id = ids[6];
let exn_id = ids[7];
let uint32_id = ids[8];
let uint64_id = ids[9];
let literal_id = ids[10];
let none_id = ids[4];
let virtual_id = ids[5];
let list_id = ids[6];
let tuple_id = ids[7];
let str_id = ids[8];
let exn_id = ids[9];
let uint32_id = ids[10];
let uint64_id = ids[11];
let name_handling = |id: &StrRef, loc: Location, unifier: &mut Unifier| {
if *id == int32_id {
@ -437,39 +197,47 @@ pub fn parse_type_annotation<T>(
Ok(primitives.float)
} else if *id == bool_id {
Ok(primitives.bool)
} else if *id == none_id {
Ok(primitives.none)
} else if *id == str_id {
Ok(primitives.str)
} else if *id == exn_id {
Ok(primitives.exception)
} else {
let obj_id = resolver.get_identifier_def(*id);
if let Ok(obj_id) = obj_id {
let def = top_level_defs[obj_id.0].read();
if let TopLevelDef::Class { fields, methods, type_vars, .. } = &*def {
if !type_vars.is_empty() {
return Err(HashSet::from([format!(
"Unexpected number of type parameters: expected {} but got 0",
type_vars.len()
)]));
match obj_id {
Ok(obj_id) => {
let def = top_level_defs[obj_id.0].read();
if let TopLevelDef::Class { fields, methods, type_vars, .. } = &*def {
if !type_vars.is_empty() {
return Err(format!(
"Unexpected number of type parameters: expected {} but got 0",
type_vars.len()
));
}
let fields = chain(
fields.iter().map(|(k, v, m)| (*k, (*v, *m))),
methods.iter().map(|(k, v, _)| (*k, (*v, false))),
)
.collect();
Ok(unifier.add_ty(TypeEnum::TObj {
obj_id,
fields,
params: Default::default(),
}))
} else {
Err(format!("Cannot use function name as type at {}", loc))
}
let fields = chain(
fields.iter().map(|(k, v, m)| (*k, (*v, *m))),
methods.iter().map(|(k, v, _)| (*k, (*v, false))),
)
.collect();
Ok(unifier.add_ty(TypeEnum::TObj { obj_id, fields, params: VarMap::default() }))
} else {
Err(HashSet::from([format!("Cannot use function name as type at {loc}")]))
}
} else {
let ty =
resolver.get_symbol_type(unifier, top_level_defs, primitives, *id).map_err(
|e| HashSet::from([format!("Unknown type annotation at {loc}: {e}")]),
)?;
if let TypeEnum::TVar { .. } = &*unifier.get_ty(ty) {
Ok(ty)
} else {
Err(HashSet::from([format!("Unknown type annotation {id} at {loc}")]))
Err(_) => {
let ty = resolver
.get_symbol_type(unifier, top_level_defs, primitives, *id)
.map_err(|e| format!("Unknown type annotation at {}: {}", loc, e))?;
if let TypeEnum::TVar { .. } = &*unifier.get_ty(ty) {
Ok(ty)
} else {
Err(format!("Unknown type annotation {} at {}", id, loc))
}
}
}
}
@ -479,6 +247,9 @@ pub fn parse_type_annotation<T>(
if *id == virtual_id {
let ty = parse_type_annotation(resolver, top_level_defs, unifier, primitives, slice)?;
Ok(unifier.add_ty(TypeEnum::TVirtual { ty }))
} else if *id == list_id {
let ty = parse_type_annotation(resolver, top_level_defs, unifier, primitives, slice)?;
Ok(unifier.add_ty(TypeEnum::TList { ty }))
} else if *id == tuple_id {
if let Tuple { elts, .. } = &slice.node {
let ty = elts
@ -487,33 +258,10 @@ pub fn parse_type_annotation<T>(
parse_type_annotation(resolver, top_level_defs, unifier, primitives, elt)
})
.collect::<Result<Vec<_>, _>>()?;
Ok(unifier.add_ty(TypeEnum::TTuple { ty, is_vararg_ctx: false }))
Ok(unifier.add_ty(TypeEnum::TTuple { ty }))
} else {
Err(HashSet::from(["Expected multiple elements for tuple".into()]))
Err("Expected multiple elements for tuple".into())
}
} else if *id == literal_id {
let mut parse_literal = |elt: &Expr<T>| {
let ty = parse_type_annotation(resolver, top_level_defs, unifier, primitives, elt)?;
let ty_enum = &*unifier.get_ty_immutable(ty);
match ty_enum {
TypeEnum::TLiteral { values, .. } => Ok(values.clone()),
_ => Err(HashSet::from([format!(
"Expected literal in type argument for Literal at {}",
elt.location
)])),
}
};
let values = if let Tuple { elts, .. } = &slice.node {
elts.iter().map(&mut parse_literal).collect::<Result<Vec<_>, _>>()?
} else {
vec![parse_literal(slice)?]
}
.into_iter()
.flatten()
.collect_vec();
Ok(unifier.get_fresh_literal(values, Some(slice.location)))
} else {
let types = if let Tuple { elts, .. } = &slice.node {
elts.iter()
@ -529,13 +277,13 @@ pub fn parse_type_annotation<T>(
let def = top_level_defs[obj_id.0].read();
if let TopLevelDef::Class { fields, methods, type_vars, .. } = &*def {
if types.len() != type_vars.len() {
return Err(HashSet::from([format!(
return Err(format!(
"Unexpected number of type parameters: expected {} but got {}",
type_vars.len(),
types.len()
)]));
));
}
let mut subst = VarMap::new();
let mut subst = HashMap::new();
for (var, ty) in izip!(type_vars.iter(), types.iter()) {
let id = if let TypeEnum::TVar { id, .. } = &*unifier.get_ty(*var) {
*id
@ -557,7 +305,7 @@ pub fn parse_type_annotation<T>(
}));
Ok(unifier.add_ty(TypeEnum::TObj { obj_id, fields, params: subst }))
} else {
Err(HashSet::from(["Cannot use function name as type".into()]))
Err("Cannot use function name as type".into())
}
}
};
@ -568,13 +316,10 @@ pub fn parse_type_annotation<T>(
if let Name { id, .. } = &value.node {
subscript_name_handle(id, slice, unifier)
} else {
Err(HashSet::from([format!("unsupported type expression at {}", expr.location)]))
Err(format!("unsupported type expression at {}", expr.location))
}
}
Constant { value, .. } => SymbolValue::from_constant_inferred(value)
.map(|v| unifier.get_fresh_literal(vec![v], Some(expr.location)))
.map_err(|err| HashSet::from([err])),
_ => Err(HashSet::from([format!("unsupported type expression at {}", expr.location)])),
_ => Err(format!("unsupported type expression at {}", expr.location)),
}
}
@ -585,7 +330,7 @@ impl dyn SymbolResolver + Send + Sync {
unifier: &mut Unifier,
primitives: &PrimitiveStore,
expr: &Expr<T>,
) -> Result<Type, HashSet<String>> {
) -> Result<Type, String> {
parse_type_annotation(self, top_level_defs, unifier, primitives, expr)
}
@ -598,13 +343,13 @@ impl dyn SymbolResolver + Send + Sync {
unifier.internal_stringify(
ty,
&mut |id| {
let TopLevelDef::Class { name, .. } = &*top_level_defs[id].read() else {
if let TopLevelDef::Class { name, .. } = &*top_level_defs[id].read() {
name.to_string()
} else {
unreachable!("expected class definition")
};
name.to_string()
}
},
&mut |id| format!("typevar{id}"),
&mut |id| format!("var{}", id),
&mut None,
)
}

3010
nac3core/src/toplevel/builtins.rs
View File

File diff suppressed because it is too large Load Diff

2182
nac3core/src/toplevel/composer.rs
View File

File diff suppressed because it is too large Load Diff

1028
nac3core/src/toplevel/helper.rs
View File

File diff suppressed because it is too large Load Diff

156
nac3core/src/toplevel/mod.rs
View File

@ -3,70 +3,59 @@ use std::{
collections::{HashMap, HashSet},
fmt::Debug,
iter::FromIterator,
ops::{Deref, DerefMut},
sync::Arc,
};
use inkwell::values::BasicValueEnum;
use itertools::Itertools;
use parking_lot::RwLock;
use nac3parser::ast::{self, Expr, Location, Stmt, StrRef};
use super::codegen::CodeGenContext;
use super::typecheck::type_inferencer::PrimitiveStore;
use super::typecheck::typedef::{FunSignature, FuncArg, SharedUnifier, Type, TypeEnum, Unifier};
use crate::{
codegen::{CodeGenContext, CodeGenerator},
codegen::CodeGenerator,
symbol_resolver::{SymbolResolver, ValueEnum},
typecheck::{
type_inferencer::{CodeLocation, PrimitiveStore},
typedef::{
CallId, FunSignature, FuncArg, SharedUnifier, Type, TypeEnum, TypeVarId, Unifier,
VarMap,
},
},
typecheck::{type_inferencer::CodeLocation, typedef::CallId},
};
use composer::*;
use type_annotation::*;
pub mod builtins;
pub mod composer;
pub mod helper;
pub mod numpy;
#[cfg(test)]
mod test;
pub mod type_annotation;
use inkwell::values::BasicValueEnum;
use itertools::{izip, Itertools};
use nac3parser::ast::{self, Location, Stmt, StrRef};
use parking_lot::RwLock;
#[derive(PartialEq, Eq, PartialOrd, Ord, Clone, Copy, Hash, Debug)]
pub struct DefinitionId(pub usize);
type GenCallCallback = dyn for<'ctx, 'a> Fn(
&mut CodeGenContext<'ctx, 'a>,
Option<(Type, ValueEnum<'ctx>)>,
(&FunSignature, DefinitionId),
Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
&mut dyn CodeGenerator,
) -> Result<Option<BasicValueEnum<'ctx>>, String>
+ Send
+ Sync;
pub mod builtins;
pub mod composer;
pub mod helper;
pub mod type_annotation;
use composer::*;
use type_annotation::*;
#[cfg(test)]
mod test;
type GenCallCallback = Box<
dyn for<'ctx, 'a> Fn(
&mut CodeGenContext<'ctx, 'a>,
Option<(Type, ValueEnum<'ctx>)>,
(&FunSignature, DefinitionId),
Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
&mut dyn CodeGenerator,
) -> Result<Option<BasicValueEnum<'ctx>>, String>
+ Send
+ Sync,
>;
pub struct GenCall {
fp: Box<GenCallCallback>,
fp: GenCallCallback,
}
impl GenCall {
#[must_use]
pub fn new(fp: Box<GenCallCallback>) -> GenCall {
pub fn new(fp: GenCallCallback) -> GenCall {
GenCall { fp }
}
/// Creates a dummy instance of [`GenCall`], which invokes [`unreachable!()`] with the given
/// `reason`.
#[must_use]
pub fn create_dummy(reason: String) -> GenCall {
Self::new(Box::new(move |_, _, _, _, _| unreachable!("{reason}")))
}
pub fn run<'ctx>(
pub fn run<'ctx, 'a>(
&self,
ctx: &mut CodeGenContext<'ctx, '_>,
ctx: &mut CodeGenContext<'ctx, 'a>,
obj: Option<(Type, ValueEnum<'ctx>)>,
fun: (&FunSignature, DefinitionId),
args: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
@ -86,85 +75,58 @@ impl Debug for GenCall {
pub struct FunInstance {
pub body: Arc<Vec<Stmt<Option<Type>>>>,
pub calls: Arc<HashMap<CodeLocation, CallId>>,
pub subst: VarMap,
pub subst: HashMap<u32, Type>,
pub unifier_id: usize,
}
#[derive(Debug, Clone)]
pub enum TopLevelDef {
Class {
/// Name for error messages and symbols.
// name for error messages and symbols
name: StrRef,
/// Object ID used for [`TypeEnum`].
// object ID used for TypeEnum
object_id: DefinitionId,
/// type variables bounded to the class.
type_vars: Vec<Type>,
/// Class fields.
///
/// Name and type is mutable.
// class fields
// name, type, is mutable
fields: Vec<(StrRef, Type, bool)>,
/// Class Attributes.
///
/// Name, type, value.
attributes: Vec<(StrRef, Type, ast::Constant)>,
/// Class methods, pointing to the corresponding function definition.
// class methods, pointing to the corresponding function definition.
methods: Vec<(StrRef, Type, DefinitionId)>,
/// Ancestor classes, including itself.
// ancestor classes, including itself.
ancestors: Vec<TypeAnnotation>,
/// Symbol resolver of the module defined the class; [None] if it is built-in type.
// symbol resolver of the module defined the class, none if it is built-in type
resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
/// Constructor type.
// constructor type
constructor: Option<Type>,
/// Definition location.
// definition location
loc: Option<Location>,
},
Function {
/// Prefix for symbol, should be unique globally.
// prefix for symbol, should be unique globally
name: String,
/// Simple name, the same as in method/function definition.
// simple name, the same as in method/function definition
simple_name: StrRef,
/// Function signature.
// function signature.
signature: Type,
/// Instantiated type variable IDs.
var_id: Vec<TypeVarId>,
// instantiated type variable IDs
var_id: Vec<u32>,
/// Function instance to symbol mapping
///
/// * Key: String representation of type variable values, sorted by variable ID in ascending
/// order, including type variables associated with the class.
/// * Value: Function symbol name.
/// Key: string representation of type variable values, sorted by variable ID in ascending
/// order, including type variables associated with the class.
/// Value: function symbol name.
instance_to_symbol: HashMap<String, String>,
/// Function instances to annotated AST mapping
///
/// * Key: String representation of type variable values, sorted by variable ID in ascending
/// order, including type variables associated with the class. Excluding rigid type
/// variables.
///
/// Rigid type variables that would be substituted when the function is instantiated.
/// Key: string representation of type variable values, sorted by variable ID in ascending
/// order, including type variables associated with the class. Excluding rigid type
/// variables.
/// rigid type variables that would be substituted when the function is instantiated.
instance_to_stmt: HashMap<String, FunInstance>,
/// Symbol resolver of the module defined the class.
// symbol resolver of the module defined the class
resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
/// Custom code generation callback.
// custom codegen callback
codegen_callback: Option<Arc<GenCall>>,
/// Definition location.
loc: Option<Location>,
},
Variable {
/// Qualified name of the global variable, should be unique globally.
name: String,
/// Simple name, the same as in method/function definition.
simple_name: StrRef,
/// Type of the global variable.
ty: Type,
/// The declared type of the global variable, or [`None`] if no type annotation is provided.
ty_decl: Option<Expr>,
/// Symbol resolver of the module defined the class.
resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
/// Definition location.
// definition location
loc: Option<Location>,
},
}

84
nac3core/src/toplevel/numpy.rs
View File

@ -1,84 +0,0 @@
use itertools::Itertools;
use super::helper::PrimDef;
use crate::typecheck::{
type_inferencer::PrimitiveStore,
typedef::{Type, TypeEnum, TypeVarId, Unifier, VarMap},
};
/// Creates a `ndarray` [`Type`] with the given type arguments.
///
/// * `dtype` - The element type of the `ndarray`, or [`None`] if the type variable is not
/// specialized.
/// * `ndims` - The number of dimensions of the `ndarray`, or [`None`] if the type variable is not
/// specialized.
pub fn make_ndarray_ty(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
dtype: Option<Type>,
ndims: Option<Type>,
) -> Type {
subst_ndarray_tvars(unifier, primitives.ndarray, dtype, ndims)
}
/// Substitutes type variables in `ndarray`.
///
/// * `dtype` - The element type of the `ndarray`, or [`None`] if the type variable is not
/// specialized.
/// * `ndims` - The number of dimensions of the `ndarray`, or [`None`] if the type variable is not
/// specialized.
pub fn subst_ndarray_tvars(
unifier: &mut Unifier,
ndarray: Type,
dtype: Option<Type>,
ndims: Option<Type>,
) -> Type {
let TypeEnum::TObj { obj_id, params, .. } = &*unifier.get_ty_immutable(ndarray) else {
panic!("Expected `ndarray` to be TObj, but got {}", unifier.stringify(ndarray))
};
debug_assert_eq!(*obj_id, PrimDef::NDArray.id());
if dtype.is_none() && ndims.is_none() {
return ndarray;
}
let tvar_ids = params.iter().map(|(obj_id, _)| *obj_id).collect_vec();
debug_assert_eq!(tvar_ids.len(), 2);
let mut tvar_subst = VarMap::new();
if let Some(dtype) = dtype {
tvar_subst.insert(tvar_ids[0], dtype);
}
if let Some(ndims) = ndims {
tvar_subst.insert(tvar_ids[1], ndims);
}
unifier.subst(ndarray, &tvar_subst).unwrap_or(ndarray)
}
fn unpack_ndarray_tvars(unifier: &mut Unifier, ndarray: Type) -> Vec<(TypeVarId, Type)> {
let TypeEnum::TObj { obj_id, params, .. } = &*unifier.get_ty_immutable(ndarray) else {
panic!("Expected `ndarray` to be TObj, but got {}", unifier.stringify(ndarray))
};
debug_assert_eq!(*obj_id, PrimDef::NDArray.id());
debug_assert_eq!(params.len(), 2);
params
.iter()
.sorted_by_key(|(obj_id, _)| *obj_id)
.map(|(var_id, ty)| (*var_id, *ty))
.collect_vec()
}
/// Unpacks the type variable IDs of `ndarray` into a tuple. The elements of the tuple corresponds
/// to `dtype` (the element type) and `ndims` (the number of dimensions) of the `ndarray`
/// respectively.
pub fn unpack_ndarray_var_ids(unifier: &mut Unifier, ndarray: Type) -> (TypeVarId, TypeVarId) {
unpack_ndarray_tvars(unifier, ndarray).into_iter().map(|v| v.0).collect_tuple().unwrap()
}
/// Unpacks the type variables of `ndarray` into a tuple. The elements of the tuple corresponds to
/// `dtype` (the element type) and `ndims` (the number of dimensions) of the `ndarray` respectively.
pub fn unpack_ndarray_var_tys(unifier: &mut Unifier, ndarray: Type) -> (Type, Type) {
unpack_ndarray_tvars(unifier, ndarray).into_iter().map(|v| v.1).collect_tuple().unwrap()
}

10
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__generic_class.snap
View File

@ -1,12 +1,14 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 540
expression: res_vec
---
[
"Class {\nname: \"Generic_A\",\nancestors: [\"Generic_A[V]\", \"B\"],\nfields: [\"aa\", \"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"foo\", \"fn[[b:T], none]\"), (\"fun\", \"fn[[a:int32], V]\")],\ntype_vars: [\"V\"]\n}\n",
"Function {\nname: \"Generic_A.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"Generic_A.fun\",\nsig: \"fn[[a:int32], V]\",\nvar_id: [TypeVarId(241)]\n}\n",
"Class {\nname: \"B\",\nancestors: [\"B\"],\nfields: [\"aa\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"foo\", \"fn[[b:T], none]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"Generic_A\",\nancestors: [\"{class: Generic_A, params: [\\\"V\\\"]}\", \"{class: B, params: []}\"],\nfields: [\"aa\", \"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"foo\", \"fn[[b:T], none]\"), (\"fun\", \"fn[[a:int32], V]\")],\ntype_vars: [\"V\"]\n}\n",
"Function {\nname: \"Generic_A.__init__\",\nsig: \"fn[[], none]\",\nvar_id: [6]\n}\n",
"Function {\nname: \"Generic_A.fun\",\nsig: \"fn[[a:int32], V]\",\nvar_id: [6, 17]\n}\n",
"Class {\nname: \"B\",\nancestors: [\"{class: B, params: []}\"],\nfields: [\"aa\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"foo\", \"fn[[b:T], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"B.foo\",\nsig: \"fn[[b:T], none]\",\nvar_id: []\n}\n",
]

12
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__inheritance_override.snap
View File

@ -1,15 +1,17 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 540
expression: res_vec
---
[
"Class {\nname: \"A\",\nancestors: [\"A[T]\"],\nfields: [\"a\", \"b\", \"c\"],\nmethods: [(\"__init__\", \"fn[[t:T], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: [\"T\"]\n}\n",
"Class {\nname: \"A\",\nancestors: [\"{class: A, params: [\\\"T\\\"]}\"],\nfields: [\"a\", \"b\", \"c\"],\nmethods: [(\"__init__\", \"fn[[t:T], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: [\"T\"]\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[t:T], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\",\nvar_id: []\n}\n",
"Function {\nname: \"A.foo\",\nsig: \"fn[[c:C], none]\",\nvar_id: []\n}\n",
"Class {\nname: \"B\",\nancestors: [\"B[typevar230]\", \"A[float]\"],\nfields: [\"a\", \"b\", \"c\", \"d\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: [\"typevar230\"]\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"B.fun\",\nsig: \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\",\nvar_id: []\n}\n",
"Class {\nname: \"C\",\nancestors: [\"C\", \"B[bool]\", \"A[float]\"],\nfields: [\"a\", \"b\", \"c\", \"d\", \"e\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"B\",\nancestors: [\"{class: B, params: [\\\"var6\\\"]}\", \"{class: A, params: [\\\"float\\\"]}\"],\nfields: [\"a\", \"b\", \"c\", \"d\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: [\"var6\"]\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: [6]\n}\n",
"Function {\nname: \"B.fun\",\nsig: \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\",\nvar_id: [6]\n}\n",
"Class {\nname: \"C\",\nancestors: [\"{class: C, params: []}\", \"{class: B, params: [\\\"bool\\\"]}\", \"{class: A, params: [\\\"float\\\"]}\"],\nfields: [\"a\", \"b\", \"c\", \"d\", \"e\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:int32, b:T], list[virtual[B[bool]]]]\"), (\"foo\", \"fn[[c:C], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"C.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
]

12
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__list_tuple_generic.snap
View File

@ -1,13 +1,15 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 540
expression: res_vec
---
[
"Function {\nname: \"foo\",\nsig: \"fn[[a:list[int32], b:tuple[T, float]], A[B, bool]]\",\nvar_id: []\n}\n",
"Class {\nname: \"A\",\nancestors: [\"A[T, V]\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[v:V], none]\"), (\"fun\", \"fn[[a:T], V]\")],\ntype_vars: [\"T\", \"V\"]\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[v:V], none]\",\nvar_id: [TypeVarId(243)]\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[a:T], V]\",\nvar_id: [TypeVarId(248)]\n}\n",
"Function {\nname: \"gfun\",\nsig: \"fn[[a:A[list[float], int32]], none]\",\nvar_id: []\n}\n",
"Class {\nname: \"B\",\nancestors: [\"B\"],\nfields: [],\nmethods: [(\"__init__\", \"fn[[], none]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"A\",\nancestors: [\"{class: A, params: [\\\"T\\\", \\\"V\\\"]}\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[v:V], none]\"), (\"fun\", \"fn[[a:T], V]\")],\ntype_vars: [\"T\", \"V\"]\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[v:V], none]\",\nvar_id: [18, 19]\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[a:T], V]\",\nvar_id: [19, 24]\n}\n",
"Function {\nname: \"gfun\",\nsig: \"fn[[a:A[int32, list[float]]], none]\",\nvar_id: []\n}\n",
"Class {\nname: \"B\",\nancestors: [\"{class: B, params: []}\"],\nfields: [],\nmethods: [(\"__init__\", \"fn[[], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
]

12
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__self1.snap
View File

@ -1,13 +1,15 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 540
expression: res_vec
---
[
"Class {\nname: \"A\",\nancestors: [\"A[typevar229, typevar230]\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[a:A[float, bool], b:B], none]\"), (\"fun\", \"fn[[a:A[float, bool]], A[bool, int32]]\")],\ntype_vars: [\"typevar229\", \"typevar230\"]\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[a:A[float, bool], b:B], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[a:A[float, bool]], A[bool, int32]]\",\nvar_id: []\n}\n",
"Class {\nname: \"B\",\nancestors: [\"B\", \"A[int64, bool]\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:A[float, bool]], A[bool, int32]]\"), (\"foo\", \"fn[[b:B], B]\"), (\"bar\", \"fn[[a:A[list[B], int32]], tuple[A[virtual[A[B, int32]], bool], B]]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"A\",\nancestors: [\"{class: A, params: [\\\"var5\\\", \\\"var6\\\"]}\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[a:A[bool, float], b:B], none]\"), (\"fun\", \"fn[[a:A[bool, float]], A[bool, int32]]\")],\ntype_vars: [\"var5\", \"var6\"]\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[a:A[bool, float], b:B], none]\",\nvar_id: [6]\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[a:A[bool, float]], A[bool, int32]]\",\nvar_id: [6]\n}\n",
"Class {\nname: \"B\",\nancestors: [\"{class: B, params: []}\", \"{class: A, params: [\\\"int64\\\", \\\"bool\\\"]}\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[a:A[bool, float]], A[bool, int32]]\"), (\"foo\", \"fn[[b:B], B]\"), (\"bar\", \"fn[[a:A[int32, list[B]]], tuple[A[bool, virtual[A[B, int32]]], B]]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"B.foo\",\nsig: \"fn[[b:B], B]\",\nvar_id: []\n}\n",
"Function {\nname: \"B.bar\",\nsig: \"fn[[a:A[list[B], int32]], tuple[A[virtual[A[B, int32]], bool], B]]\",\nvar_id: []\n}\n",
"Function {\nname: \"B.bar\",\nsig: \"fn[[a:A[int32, list[B]]], tuple[A[bool, virtual[A[B, int32]]], B]]\",\nvar_id: []\n}\n",
]

12
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__simple_class_compose.snap
View File

@ -1,17 +1,19 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 540
expression: res_vec
---
[
"Class {\nname: \"A\",\nancestors: [\"A\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"A\",\nancestors: [\"{class: A, params: []}\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"A.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"A.fun\",\nsig: \"fn[[b:B], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"A.foo\",\nsig: \"fn[[a:T, b:V], none]\",\nvar_id: [TypeVarId(249)]\n}\n",
"Class {\nname: \"B\",\nancestors: [\"B\", \"C\", \"A\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"A.foo\",\nsig: \"fn[[a:T, b:V], none]\",\nvar_id: [25]\n}\n",
"Class {\nname: \"B\",\nancestors: [\"{class: B, params: []}\", \"{class: C, params: []}\", \"{class: A, params: []}\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Class {\nname: \"C\",\nancestors: [\"C\", \"A\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Class {\nname: \"C\",\nancestors: [\"{class: C, params: []}\", \"{class: A, params: []}\"],\nfields: [\"a\"],\nmethods: [(\"__init__\", \"fn[[], none]\"), (\"fun\", \"fn[[b:B], none]\"), (\"foo\", \"fn[[a:T, b:V], none]\")],\ntype_vars: []\n}\n",
"Function {\nname: \"C.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"C.fun\",\nsig: \"fn[[b:B], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"foo\",\nsig: \"fn[[a:A], none]\",\nvar_id: []\n}\n",
"Function {\nname: \"ff\",\nsig: \"fn[[a:T], V]\",\nvar_id: [TypeVarId(257)]\n}\n",
"Function {\nname: \"ff\",\nsig: \"fn[[a:T], V]\",\nvar_id: [33]\n}\n",
]

4
nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__simple_pass_in_class.snap
View File

@ -1,9 +1,9 @@
---
source: nac3core/src/toplevel/test.rs
assertion_line: 549
assertion_line: 541
expression: res_vec
---
[
"Class {\nname: \"A\",\nancestors: [\"A\"],\nfields: [],\nmethods: [],\ntype_vars: []\n}\n",
"Class {\nname: \"A\",\nancestors: [\"{class: A, params: []}\"],\nfields: [],\nmethods: [],\ntype_vars: []\n}\n",
]

214
nac3core/src/toplevel/test.rs
View File

@ -1,23 +1,19 @@
use std::{collections::HashMap, sync::Arc};
use indoc::indoc;
use parking_lot::Mutex;
use test_case::test_case;
use nac3parser::{
ast::{fold::Fold, FileName},
parser::parse_program,
};
use super::{helper::PrimDef, DefinitionId, *};
use crate::{
codegen::CodeGenContext,
symbol_resolver::{SymbolResolver, ValueEnum},
toplevel::DefinitionId,
typecheck::{
type_inferencer::PrimitiveStore,
typedef::{into_var_map, Type, Unifier},
typedef::{Type, Unifier},
},
};
use indoc::indoc;
use nac3parser::{ast::fold::Fold, parser::parse_program};
use parking_lot::Mutex;
use std::{collections::HashMap, sync::Arc};
use test_case::test_case;
use super::*;
struct ResolverInternal {
id_to_type: Mutex<HashMap<StrRef, Type>>,
@ -40,7 +36,7 @@ struct Resolver(Arc<ResolverInternal>);
impl SymbolResolver for Resolver {
fn get_default_param_value(
&self,
_: &ast::Expr,
_: &nac3parser::ast::Expr,
) -> Option<crate::symbol_resolver::SymbolValue> {
unimplemented!()
}
@ -56,33 +52,27 @@ impl SymbolResolver for Resolver {
.id_to_type
.lock()
.get(&str)
.copied()
.ok_or_else(|| format!("cannot find symbol `{str}`"))
.cloned()
.ok_or_else(|| format!("cannot find symbol `{}`", str))
}
fn get_symbol_value<'ctx>(
fn get_symbol_value<'ctx, 'a>(
&self,
_: StrRef,
_: &mut CodeGenContext<'ctx, '_>,
_: &mut dyn CodeGenerator,
_: &mut CodeGenContext<'ctx, 'a>,
) -> Option<ValueEnum<'ctx>> {
unimplemented!()
}
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, HashSet<String>> {
self.0
.id_to_def
.lock()
.get(&id)
.copied()
.ok_or_else(|| HashSet::from(["Unknown identifier".to_string()]))
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
self.0.id_to_def.lock().get(&id).cloned().ok_or("Unknown identifier".to_string())
}
fn get_string_id(&self, _: &str) -> i32 {
unimplemented!()
}
fn get_exception_id(&self, _tyid: usize) -> usize {
fn get_exception_id(&self, tyid: usize) -> usize {
unimplemented!()
}
}
@ -115,41 +105,23 @@ impl SymbolResolver for Resolver {
def __init__(self):
self.c: int32 = 4
self.a: bool = True
"},
"}
];
"register"
)]
fn test_simple_register(source: Vec<&str>) {
let mut composer =
TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 64).0;
let mut composer: TopLevelComposer = Default::default();
for s in source {
let ast = parse_program(s, FileName::default()).unwrap();
let ast = parse_program(s, Default::default()).unwrap();
let ast = ast[0].clone();
composer.register_top_level(ast, None, "", false).unwrap();
composer.register_top_level(ast, None, "".into()).unwrap();
}
}
#[test_case(
indoc! {"
class A:
def foo(self):
pass
a = A()
"};
"register"
)]
fn test_simple_register_without_constructor(source: &str) {
let mut composer =
TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 64).0;
let ast = parse_program(source, FileName::default()).unwrap();
let ast = ast[0].clone();
composer.register_top_level(ast, None, "", true).unwrap();
}
#[test_case(
&[
vec![
indoc! {"
def fun(a: int32) -> int32:
return a
@ -163,36 +135,35 @@ fn test_simple_register_without_constructor(source: &str) {
return 3
"},
],
&[
vec![
"fn[[a:0], 0]",
"fn[[a:2], 4]",
"fn[[b:1], 0]",
],
&[
vec![
"fun",
"foo",
"f"
];
"function compose"
)]
fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
let mut composer =
TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 64).0;
fn test_simple_function_analyze(source: Vec<&str>, tys: Vec<&str>, names: Vec<&str>) {
let mut composer: TopLevelComposer = Default::default();
let internal_resolver = Arc::new(ResolverInternal {
id_to_def: Mutex::default(),
id_to_type: Mutex::default(),
class_names: Mutex::default(),
id_to_def: Default::default(),
id_to_type: Default::default(),
class_names: Default::default(),
});
let resolver =
Arc::new(Resolver(internal_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
for s in source {
let ast = parse_program(s, FileName::default()).unwrap();
let ast = parse_program(s, Default::default()).unwrap();
let ast = ast[0].clone();
let (id, def_id, ty) =
composer.register_top_level(ast, Some(resolver.clone()), "", false).unwrap();
composer.register_top_level(ast, Some(resolver.clone()), "".into()).unwrap();
internal_resolver.add_id_def(id, def_id);
if let Some(ty) = ty {
internal_resolver.add_id_type(id, ty);
@ -218,7 +189,7 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
}
#[test_case(
&[
vec![
indoc! {"
class A():
a: int32
@ -251,11 +222,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&[];
vec![];
"simple class compose"
)]
#[test_case(
&[
vec![
indoc! {"
class Generic_A(Generic[V], B):
a: int64
@ -273,11 +244,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&[];
vec![];
"generic class"
)]
#[test_case(
&[
vec![
indoc! {"
def foo(a: list[int32], b: tuple[T, float]) -> A[B, bool]:
pass
@ -302,11 +273,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&[];
vec![];
"list tuple generic"
)]
#[test_case(
&[
vec![
indoc! {"
class A(Generic[T, V]):
a: A[float, bool]
@ -327,11 +298,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&[];
vec![];
"self1"
)]
#[test_case(
&[
vec![
indoc! {"
class A(Generic[T]):
a: int32
@ -361,11 +332,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&[];
vec![];
"inheritance_override"
)]
#[test_case(
&[
vec![
indoc! {"
class A(Generic[T]):
def __init__(self):
@ -374,11 +345,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&["application of type vars to generic class is not currently supported (at unknown:4:24)"];
vec!["application of type vars to generic class is not currently supported (at unknown: line 4 column 24)"];
"err no type var in generic app"
)]
#[test_case(
&[
vec![
indoc! {"
class A(B):
def __init__(self):
@ -390,11 +361,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&["cyclic inheritance detected"];
vec!["cyclic inheritance detected"];
"cyclic1"
)]
#[test_case(
&[
vec![
indoc! {"
class A(B[bool, int64]):
def __init__(self):
@ -411,30 +382,30 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"},
],
&["cyclic inheritance detected"];
vec!["cyclic inheritance detected"];
"cyclic2"
)]
#[test_case(
&[
vec![
indoc! {"
class A:
pass
"}
],
&["5: Class {\nname: \"A\",\ndef_id: DefinitionId(5),\nancestors: [CustomClassKind { id: DefinitionId(5), params: [] }],\nfields: [],\nmethods: [],\ntype_vars: []\n}"];
vec!["5: Class {\nname: \"A\",\ndef_id: DefinitionId(5),\nancestors: [CustomClassKind { id: DefinitionId(5), params: [] }],\nfields: [],\nmethods: [],\ntype_vars: []\n}"];
"simple pass in class"
)]
#[test_case(
&[indoc! {"
vec![indoc! {"
class A:
def __init__():
pass
"}],
&["__init__ method must have a `self` parameter (at unknown:2:5)"];
vec!["__init__ method must have a `self` parameter (at unknown: line 2 column 5)"];
"err no self_1"
)]
#[test_case(
&[
vec![
indoc! {"
class A(B, Generic[T], C):
def __init__(self):
@ -452,11 +423,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
"}
],
&["a class definition can only have at most one base class declaration and one generic declaration (at unknown:1:24)"];
vec!["a class definition can only have at most one base class declaration and one generic declaration (at unknown: line 1 column 24)"];
"err multiple inheritance"
)]
#[test_case(
&[
vec![
indoc! {"
class A(Generic[T]):
a: int32
@ -477,11 +448,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&["method fun has same name as ancestors' method, but incompatible type"];
vec!["method fun has same name as ancestors' method, but incompatible type"];
"err_incompatible_inheritance_method"
)]
#[test_case(
&[
vec![
indoc! {"
class A(Generic[T]):
a: int32
@ -503,11 +474,11 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&["field `a` has already declared in the ancestor classes"];
vec!["field `a` has already declared in the ancestor classes"];
"err_incompatible_inheritance_field"
)]
#[test_case(
&[
vec![
indoc! {"
class A:
def __init__(self):
@ -520,13 +491,12 @@ fn test_simple_function_analyze(source: &[&str], tys: &[&str], names: &[&str]) {
pass
"}
],
&["duplicate definition of class `A` (at unknown:1:1)"];
vec!["duplicate definition of class `A` (at unknown: line 1 column 1)"];
"class same name"
)]
fn test_analyze(source: &[&str], res: &[&str]) {
fn test_analyze(source: Vec<&str>, res: Vec<&str>) {
let print = false;
let mut composer =
TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 64).0;
let mut composer: TopLevelComposer = Default::default();
let internal_resolver = make_internal_resolver_with_tvar(
vec![
@ -541,15 +511,15 @@ fn test_analyze(source: &[&str], res: &[&str]) {
Arc::new(Resolver(internal_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
for s in source {
let ast = parse_program(s, FileName::default()).unwrap();
let ast = parse_program(s, Default::default()).unwrap();
let ast = ast[0].clone();
let (id, def_id, ty) = {
match composer.register_top_level(ast, Some(resolver.clone()), "", false) {
match composer.register_top_level(ast, Some(resolver.clone()), "".into()) {
Ok(x) => x,
Err(msg) => {
if print {
println!("{msg}");
println!("{}", msg);
} else {
assert_eq!(res[0], msg);
}
@ -565,9 +535,9 @@ fn test_analyze(source: &[&str], res: &[&str]) {
if let Err(msg) = composer.start_analysis(false) {
if print {
println!("{}", msg.iter().sorted().join("\n----------\n"));
println!("{}", msg);
} else {
assert_eq!(res[0], msg.iter().next().unwrap());
assert_eq!(res[0], msg);
}
} else {
// skip 5 to skip primitives
@ -595,7 +565,7 @@ fn test_analyze(source: &[&str], res: &[&str]) {
return fib(n - 1)
"}
],
&[];
vec![];
"simple function"
)]
#[test_case(
@ -628,7 +598,7 @@ fn test_analyze(source: &[&str], res: &[&str]) {
return a.fun() + 2
"}
],
&[];
vec![];
"simple class body"
)]
#[test_case(
@ -653,7 +623,7 @@ fn test_analyze(source: &[&str], res: &[&str]) {
return [a, b]
"}
],
&[];
vec![];
"type var fun"
)]
#[test_case(
@ -674,7 +644,7 @@ fn test_analyze(source: &[&str], res: &[&str]) {
return ret if self.b else self.fun(self.a)
"}
],
&[];
vec![];
"type var class"
)]
#[test_case(
@ -698,13 +668,12 @@ fn test_analyze(source: &[&str], res: &[&str]) {
self.b = True
"}
],
&[];
vec![];
"no_init_inst_check"
)]
fn test_inference(source: Vec<&str>, res: &[&str]) {
fn test_inference(source: Vec<&str>, res: Vec<&str>) {
let print = true;
let mut composer =
TopLevelComposer::new(Vec::new(), Vec::new(), ComposerConfig::default(), 64).0;
let mut composer: TopLevelComposer = Default::default();
let internal_resolver = make_internal_resolver_with_tvar(
vec![
@ -726,15 +695,15 @@ fn test_inference(source: Vec<&str>, res: &[&str]) {
Arc::new(Resolver(internal_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
for s in source {
let ast = parse_program(s, FileName::default()).unwrap();
let ast = parse_program(s, Default::default()).unwrap();
let ast = ast[0].clone();
let (id, def_id, ty) = {
match composer.register_top_level(ast, Some(resolver.clone()), "", false) {
match composer.register_top_level(ast, Some(resolver.clone()), "".into()) {
Ok(x) => x,
Err(msg) => {
if print {
println!("{msg}");
println!("{}", msg);
} else {
assert_eq!(res[0], msg);
}
@ -750,14 +719,16 @@ fn test_inference(source: Vec<&str>, res: &[&str]) {
if let Err(msg) = composer.start_analysis(true) {
if print {
println!("{}", msg.iter().sorted().join("\n----------\n"));
println!("{}", msg);
} else {
assert_eq!(res[0], msg.iter().next().unwrap());
assert_eq!(res[0], msg);
}
} else {
// skip 5 to skip primitives
let mut stringify_folder = TypeToStringFolder { unifier: &mut composer.unifier };
for (def, _) in composer.definition_ast_list.iter().skip(composer.builtin_num) {
for (_i, (def, _)) in
composer.definition_ast_list.iter().skip(composer.builtin_num).enumerate()
{
let def = &*def.read();
if let TopLevelDef::Function { instance_to_stmt, name, .. } = def {
@ -766,7 +737,7 @@ fn test_inference(source: Vec<&str>, res: &[&str]) {
name,
instance_to_stmt.len()
);
for inst in instance_to_stmt {
for inst in instance_to_stmt.iter() {
let ast = &inst.1.body;
for b in ast.iter() {
println!("{:?}", stringify_folder.fold_stmt(b.clone()).unwrap());
@ -784,29 +755,22 @@ fn make_internal_resolver_with_tvar(
unifier: &mut Unifier,
print: bool,
) -> Arc<ResolverInternal> {
let list_elem_tvar = unifier.get_fresh_var(Some("list_elem".into()), None);
let list = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::List.id(),
fields: HashMap::new(),
params: into_var_map([list_elem_tvar]),
});
let res: Arc<ResolverInternal> = ResolverInternal {
id_to_def: Mutex::new(HashMap::from([("list".into(), PrimDef::List.id())])),
id_to_def: Default::default(),
id_to_type: tvars
.into_iter()
.map(|(name, range)| {
(name, {
let tvar = unifier.get_fresh_var_with_range(range.as_slice(), None, None);
let (ty, id) = unifier.get_fresh_var_with_range(range.as_slice(), None, None);
if print {
println!("{}: {:?}, typevar{}", name, tvar.ty, tvar.id);
println!("{}: {:?}, tvar{}", name, ty, id);
}
tvar.ty
ty
})
})
.collect::<HashMap<_, _>>()
.into(),
class_names: Mutex::new(HashMap::from([("list".into(), list)])),
class_names: Default::default(),
}
.into();
if print {
@ -826,8 +790,8 @@ impl<'a> Fold<Option<Type>> for TypeToStringFolder<'a> {
Ok(if let Some(ty) = user {
self.unifier.internal_stringify(
ty,
&mut |id| format!("class{id}"),
&mut |id| format!("typevar{id}"),
&mut |id| format!("class{}", id.to_string()),
&mut |id| format!("tvar{}", id.to_string()),
&mut None,
)
} else {

443
nac3core/src/toplevel/type_annotation.rs
View File

@ -1,12 +1,4 @@
use strum::IntoEnumIterator;
use nac3parser::ast::Constant;
use super::{
helper::{PrimDef, PrimDefDetails},
*,
};
use crate::{symbol_resolver::SymbolValue, typecheck::typedef::VarMap};
use super::*;
#[derive(Clone, Debug)]
pub enum TypeAnnotation {
@ -20,8 +12,7 @@ pub enum TypeAnnotation {
// can only be CustomClassKind
Virtual(Box<TypeAnnotation>),
TypeVar(Type),
/// A `Literal` allowing a subset of literals.
Literal(Vec<Constant>),
List(Box<TypeAnnotation>),
Tuple(Vec<TypeAnnotation>),
}
@ -31,57 +22,44 @@ impl TypeAnnotation {
match self {
Primitive(ty) | TypeVar(ty) => unifier.stringify(*ty),
CustomClass { id, params } => {
let class_name = if let Some(ref top) = unifier.top_level {
if let TopLevelDef::Class { name, .. } = &*top.definitions.read()[id.0].read() {
(*name).into()
} else {
unreachable!()
let class_name = match unifier.top_level {
Some(ref top) => {
if let TopLevelDef::Class { name, .. } =
&*top.definitions.read()[id.0].read()
{
(*name).into()
} else {
format!("def_{}", id.0)
}
}
} else {
format!("class_def_{}", id.0)
None => format!("def_{}", id.0),
};
format!("{}{}", class_name, {
let param_list =
params.iter().map(|p| p.stringify(unifier)).collect_vec().join(", ");
if param_list.is_empty() {
String::new()
} else {
format!("[{param_list}]")
}
})
}
Literal(values) => {
format!("Literal({})", values.iter().map(|v| format!("{v:?}")).join(", "))
}
Virtual(ty) => format!("virtual[{}]", ty.stringify(unifier)),
Tuple(types) => {
format!(
"tuple[{}]",
types.iter().map(|p| p.stringify(unifier)).collect_vec().join(", ")
"{{class: {}, params: {:?}}}",
class_name,
params.iter().map(|p| p.stringify(unifier)).collect_vec()
)
}
Virtual(ty) | List(ty) => ty.stringify(unifier),
Tuple(types) => {
format!("({:?})", types.iter().map(|p| p.stringify(unifier)).collect_vec())
}
}
}
}
/// Parses an AST expression `expr` into a [`TypeAnnotation`].
///
/// * `locked` - A [`HashMap`] containing the IDs of known definitions, mapped to a [`Vec`] of all
/// generic variables associated with the definition.
/// * `type_var` - The type variable associated with the type argument currently being parsed. Pass
/// [`None`] when this function is invoked externally.
pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
pub fn parse_ast_to_type_annotation_kinds<T>(
resolver: &(dyn SymbolResolver + Send + Sync),
top_level_defs: &[Arc<RwLock<TopLevelDef>>],
unifier: &mut Unifier,
primitives: &PrimitiveStore,
expr: &ast::Expr<T>,
// the key stores the type_var of this topleveldef::class, we only need this field here
locked: HashMap<DefinitionId, Vec<Type>, S>,
) -> Result<TypeAnnotation, HashSet<String>> {
locked: HashMap<DefinitionId, Vec<Type>>,
) -> Result<TypeAnnotation, String> {
let name_handle = |id: &StrRef,
unifier: &mut Unifier,
locked: HashMap<DefinitionId, Vec<Type>, S>| {
locked: HashMap<DefinitionId, Vec<Type>>| {
if id == &"int32".into() {
Ok(TypeAnnotation::Primitive(primitives.int32))
} else if id == &"int64".into() {
@ -94,10 +72,12 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
Ok(TypeAnnotation::Primitive(primitives.float))
} else if id == &"bool".into() {
Ok(TypeAnnotation::Primitive(primitives.bool))
} else if id == &"None".into() {
Ok(TypeAnnotation::Primitive(primitives.none))
} else if id == &"str".into() {
Ok(TypeAnnotation::Primitive(primitives.str))
} else if id == &"Exception".into() {
Ok(TypeAnnotation::CustomClass { id: PrimDef::Exception.id(), params: Vec::default() })
Ok(TypeAnnotation::CustomClass { id: DefinitionId(7), params: Default::default() })
} else if let Ok(obj_id) = resolver.get_identifier_def(*id) {
let type_vars = {
let def_read = top_level_defs[obj_id.0].try_read();
@ -105,10 +85,10 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
if let TopLevelDef::Class { type_vars, .. } = &*def_read {
type_vars.clone()
} else {
return Err(HashSet::from([format!(
return Err(format!(
"function cannot be used as a type (at {})",
expr.location
)]));
));
}
} else {
locked.get(&obj_id).unwrap().clone()
@ -116,29 +96,23 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
};
// check param number here
if !type_vars.is_empty() {
return Err(HashSet::from([format!(
return Err(format!(
"expect {} type variable parameter but got 0 (at {})",
type_vars.len(),
expr.location,
)]));
));
}
Ok(TypeAnnotation::CustomClass { id: obj_id, params: vec![] })
} else if let Ok(ty) = resolver.get_symbol_type(unifier, top_level_defs, primitives, *id) {
if let TypeEnum::TVar { .. } = unifier.get_ty(ty).as_ref() {
let var = unifier.get_fresh_var(Some(*id), Some(expr.location)).ty;
let var = unifier.get_fresh_var(Some(*id), Some(expr.location)).0;
unifier.unify(var, ty).unwrap();
Ok(TypeAnnotation::TypeVar(ty))
} else {
Err(HashSet::from([format!(
"`{}` is not a valid type annotation (at {})",
id, expr.location
)]))
Err(format!("`{}` is not a valid type annotation (at {})", id, expr.location))
}
} else {
Err(HashSet::from([format!(
"`{}` is not a valid type annotation (at {})",
id, expr.location
)]))
Err(format!("`{}` is not a valid type annotation (at {})", id, expr.location))
}
};
@ -146,22 +120,20 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
|id: &StrRef,
slice: &ast::Expr<T>,
unifier: &mut Unifier,
mut locked: HashMap<DefinitionId, Vec<Type>, S>| {
if ["virtual".into(), "Generic".into(), "tuple".into(), "Option".into()].contains(id) {
return Err(HashSet::from([format!(
"keywords cannot be class name (at {})",
expr.location
)]));
mut locked: HashMap<DefinitionId, Vec<Type>>| {
if vec!["virtual".into(), "Generic".into(), "list".into(), "tuple".into()].contains(id)
{
return Err(format!("keywords cannot be class name (at {})", expr.location));
}
let obj_id = resolver.get_identifier_def(*id)?;
let type_vars = {
let def_read = top_level_defs[obj_id.0].try_read();
if let Some(def_read) = def_read {
let TopLevelDef::Class { type_vars, .. } = &*def_read else {
if let TopLevelDef::Class { type_vars, .. } = &*def_read {
type_vars.clone()
} else {
unreachable!("must be class here")
};
type_vars.clone()
}
} else {
locked.get(&obj_id).unwrap().clone()
}
@ -174,12 +146,12 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
vec![slice]
};
if type_vars.len() != params_ast.len() {
return Err(HashSet::from([format!(
return Err(format!(
"expect {} type parameters but got {} (at {})",
type_vars.len(),
params_ast.len(),
params_ast[0].location,
)]));
));
}
let result = params_ast
.iter()
@ -203,17 +175,15 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
if no_type_var {
result
} else {
return Err(HashSet::from([
format!(
"application of type vars to generic class is not currently supported (at {})",
params_ast[0].location
),
]));
return Err(format!(
"application of type vars to generic class \
is not currently supported (at {})",
params_ast[0].location
));
}
};
Ok(TypeAnnotation::CustomClass { id: obj_id, params: param_type_infos })
};
match &expr.node {
ast::ExprKind::Name { id, .. } => name_handle(id, unifier, locked),
// virtual
@ -236,10 +206,10 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
Ok(TypeAnnotation::Virtual(def.into()))
}
// option
// list
ast::ExprKind::Subscript { value, slice, .. }
if {
matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"Option".into())
matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"list".into())
} =>
{
let def_ann = parse_ast_to_type_annotation_kinds(
@ -250,13 +220,7 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
slice.as_ref(),
locked,
)?;
let id =
if let TypeEnum::TObj { obj_id, .. } = unifier.get_ty(primitives.option).as_ref() {
*obj_id
} else {
unreachable!()
};
Ok(TypeAnnotation::CustomClass { id, params: vec![def_ann] })
Ok(TypeAnnotation::List(def_ann.into()))
}
// tuple
@ -288,70 +252,16 @@ pub fn parse_ast_to_type_annotation_kinds<T, S: std::hash::BuildHasher + Clone>(
Ok(TypeAnnotation::Tuple(type_annotations))
}
// Literal
ast::ExprKind::Subscript { value, slice, .. }
if {
matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"Literal".into())
} =>
{
let tup_elts = {
if let ast::ExprKind::Tuple { elts, .. } = &slice.node {
elts.as_slice()
} else {
std::slice::from_ref(slice.as_ref())
}
};
let type_annotations = tup_elts
.iter()
.map(|e| match &e.node {
ast::ExprKind::Constant { value, .. } => {
Ok(TypeAnnotation::Literal(vec![value.clone()]))
}
_ => parse_ast_to_type_annotation_kinds(
resolver,
top_level_defs,
unifier,
primitives,
e,
locked.clone(),
),
})
.collect::<Result<Vec<_>, _>>()?
.into_iter()
.flat_map(|type_ann| match type_ann {
TypeAnnotation::Literal(values) => values,
_ => unreachable!(),
})
.collect_vec();
if type_annotations.len() == 1 {
Ok(TypeAnnotation::Literal(type_annotations))
} else {
Err(HashSet::from([format!(
"multiple literal bounds are currently unsupported (at {})",
value.location
)]))
}
}
// custom class
ast::ExprKind::Subscript { value, slice, .. } => {
if let ast::ExprKind::Name { id, .. } = &value.node {
class_name_handle(id, slice, unifier, locked)
} else {
Err(HashSet::from([format!(
"unsupported expression type for class name (at {})",
value.location
)]))
Err(format!("unsupported expression type for class name (at {})", value.location))
}
}
ast::ExprKind::Constant { value, .. } => Ok(TypeAnnotation::Literal(vec![value.clone()])),
_ => Err(HashSet::from([format!(
"unsupported expression for type annotation (at {})",
expr.location
)])),
_ => Err(format!("unsupported expression for type annotation (at {})", expr.location)),
}
}
@ -363,78 +273,39 @@ pub fn get_type_from_type_annotation_kinds(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
ann: &TypeAnnotation,
subst_list: &mut Option<Vec<Type>>,
) -> Result<Type, HashSet<String>> {
) -> Result<Type, String> {
match ann {
TypeAnnotation::CustomClass { id: obj_id, params } => {
let def_read = top_level_defs[obj_id.0].read();
let class_def: &TopLevelDef = &def_read;
let TopLevelDef::Class { fields, methods, type_vars, .. } = class_def else {
unreachable!("should be class def here")
};
let class_def: &TopLevelDef = def_read.deref();
if let TopLevelDef::Class { fields, methods, type_vars, .. } = class_def {
if type_vars.len() != params.len() {
Err(format!(
"unexpected number of type parameters: expected {} but got {}",
type_vars.len(),
params.len()
))
} else {
let param_ty = params
.iter()
.map(|x| {
get_type_from_type_annotation_kinds(
top_level_defs,
unifier,
primitives,
x,
)
})
.collect::<Result<Vec<_>, _>>()?;
if type_vars.len() != params.len() {
return Err(HashSet::from([format!(
"unexpected number of type parameters: expected {} but got {}",
type_vars.len(),
params.len()
)]));
}
let param_ty = params
.iter()
.map(|x| {
get_type_from_type_annotation_kinds(
top_level_defs,
unifier,
primitives,
x,
subst_list,
)
})
.collect::<Result<Vec<_>, _>>()?;
let ty = if let Some(prim_def) = PrimDef::iter().find(|prim| prim.id() == *obj_id) {
// Primitive TopLevelDefs do not contain all fields that are present in their Type
// counterparts, so directly perform subst on the Type instead.
let PrimDefDetails::PrimClass { get_ty_fn, .. } = prim_def.details() else {
unreachable!()
};
let base_ty = get_ty_fn(primitives);
let params =
if let TypeEnum::TObj { params, .. } = &*unifier.get_ty_immutable(base_ty) {
params.clone()
} else {
unreachable!()
};
unifier
.subst(
get_ty_fn(primitives),
&params
.iter()
.zip(param_ty)
.map(|(obj_tv, param)| (*obj_tv.0, param))
.collect(),
)
.unwrap_or(base_ty)
} else {
let subst = {
// check for compatible range
// TODO: if allow type var to be applied(now this disallowed in the parse_to_type_annotation), need more check
let mut result = VarMap::new();
for (tvar, p) in type_vars.iter().zip(param_ty) {
match unifier.get_ty(*tvar).as_ref() {
TypeEnum::TVar {
id,
range,
fields: None,
name,
loc,
is_const_generic: false,
} => {
let subst = {
// check for compatible range
// TODO: if allow type var to be applied(now this disallowed in the parse_to_type_annotation), need more check
let mut result: HashMap<u32, Type> = HashMap::new();
for (tvar, p) in type_vars.iter().zip(param_ty) {
if let TypeEnum::TVar { id, range, fields: None, name, loc } =
unifier.get_ty(*tvar).as_ref()
{
let ok: bool = {
// create a temp type var and unify to check compatibility
p == *tvar || {
@ -443,119 +314,79 @@ pub fn get_type_from_type_annotation_kinds(
*name,
*loc,
);
unifier.unify(temp.ty, p).is_ok()
unifier.unify(temp.0, p).is_ok()
}
};
if ok {
result.insert(*id, p);
} else {
return Err(HashSet::from([format!(
return Err(format!(
"cannot apply type {} to type variable with id {:?}",
unifier.internal_stringify(
p,
&mut |id| format!("class{id}"),
&mut |id| format!("typevar{id}"),
&mut |id| format!("class{}", id),
&mut |id| format!("tvar{}", id),
&mut None
),
*id
)]));
));
}
} else {
unreachable!("must be generic type var")
}
TypeEnum::TVar {
id, range, name, loc, is_const_generic: true, ..
} => {
let ty = range[0];
let ok: bool = {
// create a temp type var and unify to check compatibility
p == *tvar || {
let temp =
unifier.get_fresh_const_generic_var(ty, *name, *loc);
unifier.unify(temp.ty, p).is_ok()
}
};
if ok {
result.insert(*id, p);
} else {
return Err(HashSet::from([format!(
"cannot apply type {} to type variable {}",
unifier.stringify(p),
name.unwrap_or_else(|| format!("typevar{id}").into()),
)]));
}
}
_ => unreachable!("must be generic type var"),
}
}
result
};
// Class Attributes keep a copy with Class Definition and are not added to objects
let mut tobj_fields = methods
.iter()
.map(|(name, ty, _)| {
result
};
let mut tobj_fields = methods
.iter()
.map(|(name, ty, _)| {
let subst_ty = unifier.subst(*ty, &subst).unwrap_or(*ty);
// methods are immutable
(*name, (subst_ty, false))
})
.collect::<HashMap<_, _>>();
tobj_fields.extend(fields.iter().map(|(name, ty, mutability)| {
let subst_ty = unifier.subst(*ty, &subst).unwrap_or(*ty);
// methods are immutable
(*name, (subst_ty, false))
})
.collect::<HashMap<_, _>>();
tobj_fields.extend(fields.iter().map(|(name, ty, mutability)| {
let subst_ty = unifier.subst(*ty, &subst).unwrap_or(*ty);
(*name, (subst_ty, *mutability))
}));
let need_subst = !subst.is_empty();
let ty = unifier.add_ty(TypeEnum::TObj {
obj_id: *obj_id,
fields: tobj_fields,
params: subst,
});
(*name, (subst_ty, *mutability))
}));
if need_subst {
if let Some(wl) = subst_list.as_mut() {
wl.push(ty);
}
Ok(unifier.add_ty(TypeEnum::TObj {
obj_id: *obj_id,
fields: tobj_fields,
params: subst,
}))
}
ty
};
Ok(ty)
} else {
unreachable!("should be class def here")
}
}
TypeAnnotation::Primitive(ty) | TypeAnnotation::TypeVar(ty) => Ok(*ty),
TypeAnnotation::Literal(values) => {
let values = values
.iter()
.map(SymbolValue::from_constant_inferred)
.collect::<Result<Vec<_>, _>>()
.map_err(|err| HashSet::from([err]))?;
let var = unifier.get_fresh_literal(values, None);
Ok(var)
}
TypeAnnotation::Virtual(ty) => {
let ty = get_type_from_type_annotation_kinds(
top_level_defs,
unifier,
primitives,
ty.as_ref(),
subst_list,
)?;
Ok(unifier.add_ty(TypeEnum::TVirtual { ty }))
}
TypeAnnotation::List(ty) => {
let ty = get_type_from_type_annotation_kinds(
top_level_defs,
unifier,
primitives,
ty.as_ref(),
)?;
Ok(unifier.add_ty(TypeEnum::TList { ty }))
}
TypeAnnotation::Tuple(tys) => {
let tys = tys
.iter()
.map(|x| {
get_type_from_type_annotation_kinds(
top_level_defs,
unifier,
primitives,
x,
subst_list,
)
get_type_from_type_annotation_kinds(top_level_defs, unifier, primitives, x)
})
.collect::<Result<Vec<_>, _>>()?;
Ok(unifier.add_ty(TypeEnum::TTuple { ty: tys, is_vararg_ctx: false }))
Ok(unifier.add_ty(TypeEnum::TTuple { ty: tys }))
}
}
}
@ -568,11 +399,10 @@ pub fn get_type_from_type_annotation_kinds(
/// the type of `self` should be similar to `A[T, V]`, where `T`, `V`
/// considered to be type variables associated with the class \
/// \
/// But note that here we do not make a duplication of `T`, `V`, we directly
/// use them as they are in the [`TopLevelDef::Class`] since those in the
/// `TopLevelDef::Class.type_vars` will be substitute later when seeing applications/instantiations
/// But note that here we do not make a duplication of `T`, `V`, we direclty
/// use them as they are in the TopLevelDef::Class since those in the
/// TopLevelDef::Class.type_vars will be substitute later when seeing applications/instantiations
/// the Type of their fields and methods will also be subst when application/instantiation
#[must_use]
pub fn make_self_type_annotation(type_vars: &[Type], object_id: DefinitionId) -> TypeAnnotation {
TypeAnnotation::CustomClass {
id: object_id,
@ -583,25 +413,27 @@ pub fn make_self_type_annotation(type_vars: &[Type], object_id: DefinitionId) ->
/// get all the occurences of type vars contained in a type annotation
/// e.g. `A[int, B[T], V, virtual[C[G]]]` => [T, V, G]
/// this function will not make a duplicate of type var
#[must_use]
pub fn get_type_var_contained_in_type_annotation(ann: &TypeAnnotation) -> Vec<TypeAnnotation> {
let mut result: Vec<TypeAnnotation> = Vec::new();
match ann {
TypeAnnotation::TypeVar(..) => result.push(ann.clone()),
TypeAnnotation::Virtual(ann) => {
result.extend(get_type_var_contained_in_type_annotation(ann.as_ref()));
result.extend(get_type_var_contained_in_type_annotation(ann.as_ref()))
}
TypeAnnotation::CustomClass { params, .. } => {
for p in params {
result.extend(get_type_var_contained_in_type_annotation(p));
}
}
TypeAnnotation::List(ann) => {
result.extend(get_type_var_contained_in_type_annotation(ann.as_ref()))
}
TypeAnnotation::Tuple(anns) => {
for a in anns {
result.extend(get_type_var_contained_in_type_annotation(a));
}
}
TypeAnnotation::Primitive(..) | TypeAnnotation::Literal { .. } => {}
TypeAnnotation::Primitive(..) => {}
}
result
}
@ -616,20 +448,21 @@ pub fn check_overload_type_annotation_compatible(
(TypeAnnotation::Primitive(a), TypeAnnotation::Primitive(b)) => a == b,
(TypeAnnotation::TypeVar(a), TypeAnnotation::TypeVar(b)) => {
let a = unifier.get_ty(*a);
let a = &*a;
let a = a.deref();
let b = unifier.get_ty(*b);
let b = &*b;
let (
let b = b.deref();
if let (
TypeEnum::TVar { id: a, fields: None, .. },
TypeEnum::TVar { id: b, fields: None, .. },
) = (a, b)
else {
{
a == b
} else {
unreachable!("must be type var")
};
a == b
}
}
(TypeAnnotation::Virtual(a), TypeAnnotation::Virtual(b)) => {
(TypeAnnotation::Virtual(a), TypeAnnotation::Virtual(b))
| (TypeAnnotation::List(a), TypeAnnotation::List(b)) => {
check_overload_type_annotation_compatible(a.as_ref(), b.as_ref(), unifier)
}

244
nac3core/src/typecheck/function_check.rs
View File

@ -1,24 +1,14 @@
use std::{
collections::{HashMap, HashSet},
iter::once,
};
use crate::typecheck::typedef::TypeEnum;
use nac3parser::ast::{
self, Constant, Expr, ExprKind,
Operator::{LShift, RShift},
Stmt, StmtKind, StrRef,
};
use super::{
type_inferencer::{DeclarationSource, IdentifierInfo, Inferencer},
typedef::{Type, TypeEnum},
};
use crate::toplevel::helper::PrimDef;
use super::type_inferencer::Inferencer;
use super::typedef::Type;
use nac3parser::ast::{self, Expr, ExprKind, Stmt, StmtKind, StrRef};
use std::{collections::HashSet, iter::once};
impl<'a> Inferencer<'a> {
fn should_have_value(&mut self, expr: &Expr<Option<Type>>) -> Result<(), HashSet<String>> {
fn should_have_value(&mut self, expr: &Expr<Option<Type>>) -> Result<(), String> {
if matches!(expr.custom, Some(ty) if self.unifier.unioned(ty, self.primitives.none)) {
Err(HashSet::from([format!("Error at {}: cannot have value none", expr.location)]))
Err(format!("Error at {}: cannot have value none", expr.location))
} else {
Ok(())
}
@ -27,61 +17,35 @@ impl<'a> Inferencer<'a> {
fn check_pattern(
&mut self,
pattern: &Expr<Option<Type>>,
defined_identifiers: &mut HashMap<StrRef, IdentifierInfo>,
) -> Result<(), HashSet<String>> {
defined_identifiers: &mut HashSet<StrRef>,
) -> Result<(), String> {
match &pattern.node {
ExprKind::Name { id, .. } if id == &"none".into() => {
Err(HashSet::from([format!("cannot assign to a `none` (at {})", pattern.location)]))
}
ExprKind::Name { id, .. } => {
// If `id` refers to a declared symbol, reject this assignment if it is used in the
// context of an (implicit) global variable
if let Some(id_info) = defined_identifiers.get(id) {
if matches!(
id_info.source,
DeclarationSource::Global { is_explicit: Some(false) }
) {
return Err(HashSet::from([format!(
"cannot access local variable '{id}' before it is declared (at {})",
pattern.location
)]));
}
}
if !defined_identifiers.contains_key(id) {
defined_identifiers.insert(*id, IdentifierInfo::default());
if !defined_identifiers.contains(id) {
defined_identifiers.insert(*id);
}
self.should_have_value(pattern)?;
Ok(())
}
ExprKind::List { elts, .. } | ExprKind::Tuple { elts, .. } => {
for elt in elts {
ExprKind::Tuple { elts, .. } => {
for elt in elts.iter() {
self.check_pattern(elt, defined_identifiers)?;
self.should_have_value(elt)?;
}
Ok(())
}
ExprKind::Starred { value, .. } => {
self.check_pattern(value, defined_identifiers)?;
self.should_have_value(value)?;
Ok(())
}
ExprKind::Subscript { value, slice, .. } => {
self.check_expr(value, defined_identifiers)?;
self.should_have_value(value)?;
self.check_expr(slice, defined_identifiers)?;
if let TypeEnum::TTuple { .. } = &*self.unifier.get_ty(value.custom.unwrap()) {
return Err(HashSet::from([format!(
return Err(format!(
"Error at {}: cannot assign to tuple element",
value.location
)]));
));
}
Ok(())
}
ExprKind::Constant { .. } => Err(HashSet::from([format!(
"cannot assign to a constant (at {})",
pattern.location
)])),
_ => self.check_expr(pattern, defined_identifiers),
}
}
@ -89,28 +53,22 @@ impl<'a> Inferencer<'a> {
fn check_expr(
&mut self,
expr: &Expr<Option<Type>>,
defined_identifiers: &mut HashMap<StrRef, IdentifierInfo>,
) -> Result<(), HashSet<String>> {
defined_identifiers: &mut HashSet<StrRef>,
) -> Result<(), String> {
// there are some cases where the custom field is None
if let Some(ty) = &expr.custom {
if !matches!(&expr.node, ExprKind::Constant { value: Constant::Ellipsis, .. })
&& !ty.obj_id(self.unifier).is_some_and(|id| id == PrimDef::List.id())
&& !self.unifier.is_concrete(*ty, &self.function_data.bound_variables)
{
return Err(HashSet::from([format!(
if !self.unifier.is_concrete(*ty, &self.function_data.bound_variables) {
return Err(format!(
"expected concrete type at {} but got {}",
expr.location,
self.unifier.get_ty(*ty).get_type_name()
)]));
));
}
}
match &expr.node {
ExprKind::Name { id, .. } => {
if id == &"none".into() {
return Ok(());
}
self.should_have_value(expr)?;
if !defined_identifiers.contains_key(id) {
if !defined_identifiers.contains(id) {
match self.function_data.resolver.get_symbol_type(
self.unifier,
&self.top_level.definitions.read(),
@ -118,28 +76,13 @@ impl<'a> Inferencer<'a> {
*id,
) {
Ok(_) => {
let is_global = self.is_id_global(*id);
defined_identifiers.insert(
*id,
IdentifierInfo {
source: match is_global {
Some(true) => {
DeclarationSource::Global { is_explicit: Some(false) }
}
Some(false) => {
DeclarationSource::Global { is_explicit: None }
}
None => DeclarationSource::Local,
},
},
);
self.defined_identifiers.insert(*id);
}
Err(e) => {
return Err(HashSet::from([format!(
return Err(format!(
"type error at identifier `{}` ({}) at {}",
id, e, expr.location
)]))
));
}
}
}
@ -147,7 +90,7 @@ impl<'a> Inferencer<'a> {
ExprKind::List { elts, .. }
| ExprKind::Tuple { elts, .. }
| ExprKind::BoolOp { values: elts, .. } => {
for elt in elts {
for elt in elts.iter() {
self.check_expr(elt, defined_identifiers)?;
self.should_have_value(elt)?;
}
@ -156,25 +99,11 @@ impl<'a> Inferencer<'a> {
self.check_expr(value, defined_identifiers)?;
self.should_have_value(value)?;
}
ExprKind::BinOp { left, op, right } => {
ExprKind::BinOp { left, right, .. } => {
self.check_expr(left, defined_identifiers)?;
self.check_expr(right, defined_identifiers)?;
self.should_have_value(left)?;
self.should_have_value(right)?;
// Check whether a bitwise shift has a negative RHS constant value
if *op == LShift || *op == RShift {
if let ExprKind::Constant { value, .. } = &right.node {
let Constant::Int(rhs_val) = value else { unreachable!() };
if *rhs_val < 0 {
return Err(HashSet::from([format!(
"shift count is negative at {}",
right.location
)]));
}
}
}
}
ExprKind::UnaryOp { operand, .. } => {
self.check_expr(operand, defined_identifiers)?;
@ -204,9 +133,11 @@ impl<'a> Inferencer<'a> {
}
ExprKind::Lambda { args, body } => {
let mut defined_identifiers = defined_identifiers.clone();
for arg in &args.args {
for arg in args.args.iter() {
// TODO: should we check the types here?
defined_identifiers.entry(arg.node.arg).or_default();
if !defined_identifiers.contains(&arg.node.arg) {
defined_identifiers.insert(arg.node.arg);
}
}
self.check_expr(body, &mut defined_identifiers)?;
}
@ -240,49 +171,24 @@ impl<'a> Inferencer<'a> {
Ok(())
}
/// Check that the return value is a non-`alloca` type, effectively only allowing primitive types.
///
/// This is a workaround preventing the caller from using a variable `alloca`-ed in the body, which
/// is freed when the function returns.
fn check_return_value_ty(&mut self, ret_ty: Type) -> bool {
if cfg!(feature = "no-escape-analysis") {
true
} else {
match &*self.unifier.get_ty_immutable(ret_ty) {
TypeEnum::TObj { .. } => [
self.primitives.int32,
self.primitives.int64,
self.primitives.uint32,
self.primitives.uint64,
self.primitives.float,
self.primitives.bool,
]
.iter()
.any(|allowed_ty| self.unifier.unioned(ret_ty, *allowed_ty)),
TypeEnum::TTuple { ty, .. } => ty.iter().all(|t| self.check_return_value_ty(*t)),
_ => false,
}
}
}
// check statements for proper identifier def-use and return on all paths
fn check_stmt(
&mut self,
stmt: &Stmt<Option<Type>>,
defined_identifiers: &mut HashMap<StrRef, IdentifierInfo>,
) -> Result<bool, HashSet<String>> {
defined_identifiers: &mut HashSet<StrRef>,
) -> Result<bool, String> {
match &stmt.node {
StmtKind::For { target, iter, body, orelse, .. } => {
self.check_expr(iter, defined_identifiers)?;
self.should_have_value(iter)?;
let mut local_defined_identifiers = defined_identifiers.clone();
for stmt in orelse {
for stmt in orelse.iter() {
self.check_stmt(stmt, &mut local_defined_identifiers)?;
}
let mut local_defined_identifiers = defined_identifiers.clone();
self.check_pattern(target, &mut local_defined_identifiers)?;
self.should_have_value(target)?;
for stmt in body {
for stmt in body.iter() {
self.check_stmt(stmt, &mut local_defined_identifiers)?;
}
Ok(false)
@ -295,11 +201,9 @@ impl<'a> Inferencer<'a> {
let body_returned = self.check_block(body, &mut body_identifiers)?;
let orelse_returned = self.check_block(orelse, &mut orelse_identifiers)?;
for ident in body_identifiers.keys() {
if !defined_identifiers.contains_key(ident)
&& orelse_identifiers.contains_key(ident)
{
defined_identifiers.insert(*ident, IdentifierInfo::default());
for ident in body_identifiers.iter() {
if !defined_identifiers.contains(ident) && orelse_identifiers.contains(ident) {
defined_identifiers.insert(*ident);
}
}
Ok(body_returned && orelse_returned)
@ -314,7 +218,7 @@ impl<'a> Inferencer<'a> {
}
StmtKind::With { items, body, .. } => {
let mut new_defined_identifiers = defined_identifiers.clone();
for item in items {
for item in items.iter() {
self.check_expr(&item.context_expr, defined_identifiers)?;
if let Some(var) = item.optional_vars.as_ref() {
self.check_pattern(var, &mut new_defined_identifiers)?;
@ -326,11 +230,11 @@ impl<'a> Inferencer<'a> {
StmtKind::Try { body, handlers, orelse, finalbody, .. } => {
self.check_block(body, &mut defined_identifiers.clone())?;
self.check_block(orelse, &mut defined_identifiers.clone())?;
for handler in handlers {
for handler in handlers.iter() {
let mut defined_identifiers = defined_identifiers.clone();
let ast::ExcepthandlerKind::ExceptHandler { name, body, .. } = &handler.node;
if let Some(name) = name {
defined_identifiers.insert(*name, IdentifierInfo::default());
defined_identifiers.insert(*name);
}
self.check_block(body, &mut defined_identifiers)?;
}
@ -361,30 +265,6 @@ impl<'a> Inferencer<'a> {
if let Some(value) = value {
self.check_expr(value, defined_identifiers)?;
self.should_have_value(value)?;
// Check that the return value is a non-`alloca` type, effectively only allowing primitive types.
// This is a workaround preventing the caller from using a variable `alloca`-ed in the body, which
// is freed when the function returns.
if let Some(ret_ty) = value.custom {
// Explicitly allow ellipsis as a return value, as the type of the ellipsis is contextually
// inferred and just generates an unconditional assertion
if matches!(
value.node,
ExprKind::Constant { value: Constant::Ellipsis, .. }
) {
return Ok(true);
}
if !self.check_return_value_ty(ret_ty) {
return Err(HashSet::from([
format!(
"return value of type {} must be a primitive or a tuple of primitives at {}",
self.unifier.stringify(ret_ty),
value.location,
),
]));
}
}
}
Ok(true)
}
@ -394,44 +274,6 @@ impl<'a> Inferencer<'a> {
}
Ok(true)
}
StmtKind::Global { names, .. } => {
for id in names {
if let Some(id_info) = defined_identifiers.get(id) {
if id_info.source == DeclarationSource::Local {
return Err(HashSet::from([format!(
"name '{id}' is referenced prior to global declaration at {}",
stmt.location,
)]));
}
continue;
}
match self.function_data.resolver.get_symbol_type(
self.unifier,
&self.top_level.definitions.read(),
self.primitives,
*id,
) {
Ok(_) => {
defined_identifiers.insert(
*id,
IdentifierInfo {
source: DeclarationSource::Global { is_explicit: Some(true) },
},
);
}
Err(e) => {
return Err(HashSet::from([format!(
"type error at identifier `{}` ({}) at {}",
id, e, stmt.location
)]))
}
}
}
Ok(false)
}
// break, raise, etc.
_ => Ok(false),
}
@ -440,12 +282,12 @@ impl<'a> Inferencer<'a> {
pub fn check_block(
&mut self,
block: &[Stmt<Option<Type>>],
defined_identifiers: &mut HashMap<StrRef, IdentifierInfo>,
) -> Result<bool, HashSet<String>> {
defined_identifiers: &mut HashSet<StrRef>,
) -> Result<bool, String> {
let mut ret = false;
for stmt in block {
if ret {
eprintln!("warning: dead code at {}\n", stmt.location);
return Err(format!("dead code at {:?}", stmt.location));
}
if self.check_stmt(stmt, defined_identifiers)? {
ret = true;

755
nac3core/src/typecheck/magic_methods.rs
View File

@ -1,154 +1,69 @@
use std::{cmp::max, collections::HashMap, rc::Rc};
use itertools::{iproduct, Itertools};
use strum::IntoEnumIterator;
use nac3parser::ast::{Cmpop, Operator, StrRef, Unaryop};
use super::{
use crate::typecheck::{
type_inferencer::*,
typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier, VarMap},
};
use crate::{
symbol_resolver::SymbolValue,
toplevel::{
helper::PrimDef,
numpy::{make_ndarray_ty, unpack_ndarray_var_tys},
},
typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier},
};
use nac3parser::ast::{self, StrRef};
use nac3parser::ast::{Cmpop, Operator, Unaryop};
use std::collections::HashMap;
use std::rc::Rc;
/// The variant of a binary operator.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum BinopVariant {
/// The normal variant.
/// For addition, it would be `+`.
Normal,
/// The "Augmented Assigning Operator" variant.
/// For addition, it would be `+=`.
AugAssign,
}
/// A binary operator with its variant.
#[derive(Debug, Clone, Copy)]
pub struct Binop {
/// The base [`Operator`] of this binary operator.
pub base: Operator,
/// The variant of this binary operator.
pub variant: BinopVariant,
}
impl Binop {
/// Make a [`Binop`] of the normal variant from an [`Operator`].
#[must_use]
pub fn normal(base: Operator) -> Self {
Binop { base, variant: BinopVariant::Normal }
}
/// Make a [`Binop`] of the aug assign variant from an [`Operator`].
#[must_use]
pub fn aug_assign(base: Operator) -> Self {
Binop { base, variant: BinopVariant::AugAssign }
}
}
/// Details about an operator (unary, binary, etc...) in Python
#[derive(Debug, Clone, Copy)]
pub struct OpInfo {
/// The method name of the binary operator.
/// For addition, this would be `__add__`, and `__iadd__` if
/// it is the augmented assigning variant.
pub method_name: &'static str,
/// The symbol of the binary operator.
/// For addition, this would be `+`, and `+=` if
/// it is the augmented assigning variant.
pub symbol: &'static str,
}
/// Helper macro to conveniently build an [`OpInfo`].
///
/// Example usage: `make_info("add", "+")` generates `OpInfo { name: "__add__", symbol: "+" }`
macro_rules! make_op_info {
($name:expr, $symbol:expr) => {
OpInfo { method_name: concat!("__", $name, "__"), symbol: $symbol }
};
}
pub trait HasOpInfo {
fn op_info(&self) -> OpInfo;
}
fn try_get_cmpop_info(op: Cmpop) -> Option<OpInfo> {
pub fn binop_name(op: &Operator) -> &'static str {
match op {
Cmpop::Lt => Some(make_op_info!("lt", "<")),
Cmpop::LtE => Some(make_op_info!("le", "<=")),
Cmpop::Gt => Some(make_op_info!("gt", ">")),
Cmpop::GtE => Some(make_op_info!("ge", ">=")),
Cmpop::Eq => Some(make_op_info!("eq", "==")),
Cmpop::NotEq => Some(make_op_info!("ne", "!=")),
Operator::Add => "__add__",
Operator::Sub => "__sub__",
Operator::Div => "__truediv__",
Operator::Mod => "__mod__",
Operator::Mult => "__mul__",
Operator::Pow => "__pow__",
Operator::BitOr => "__or__",
Operator::BitXor => "__xor__",
Operator::BitAnd => "__and__",
Operator::LShift => "__lshift__",
Operator::RShift => "__rshift__",
Operator::FloorDiv => "__floordiv__",
Operator::MatMult => "__matmul__",
}
}
pub fn binop_assign_name(op: &Operator) -> &'static str {
match op {
Operator::Add => "__iadd__",
Operator::Sub => "__isub__",
Operator::Div => "__itruediv__",
Operator::Mod => "__imod__",
Operator::Mult => "__imul__",
Operator::Pow => "__ipow__",
Operator::BitOr => "__ior__",
Operator::BitXor => "__ixor__",
Operator::BitAnd => "__iand__",
Operator::LShift => "__ilshift__",
Operator::RShift => "__irshift__",
Operator::FloorDiv => "__ifloordiv__",
Operator::MatMult => "__imatmul__",
}
}
pub fn unaryop_name(op: &Unaryop) -> &'static str {
match op {
Unaryop::UAdd => "__pos__",
Unaryop::USub => "__neg__",
Unaryop::Not => "__not__",
Unaryop::Invert => "__inv__",
}
}
pub fn comparison_name(op: &Cmpop) -> Option<&'static str> {
match op {
Cmpop::Lt => Some("__lt__"),
Cmpop::LtE => Some("__le__"),
Cmpop::Gt => Some("__gt__"),
Cmpop::GtE => Some("__ge__"),
Cmpop::Eq => Some("__eq__"),
Cmpop::NotEq => Some("__ne__"),
_ => None,
}
}
impl OpInfo {
#[must_use]
pub fn supports_cmpop(op: Cmpop) -> bool {
try_get_cmpop_info(op).is_some()
}
}
impl HasOpInfo for Cmpop {
fn op_info(&self) -> OpInfo {
try_get_cmpop_info(*self).expect("{self:?} is not supported")
}
}
impl HasOpInfo for Binop {
fn op_info(&self) -> OpInfo {
// Helper macro to generate both the normal variant [`OpInfo`] and the
// augmented assigning variant [`OpInfo`] for a binary operator conveniently.
macro_rules! info {
($name:literal, $symbol:literal) => {
(
make_op_info!($name, $symbol),
make_op_info!(concat!("i", $name), concat!($symbol, "=")),
)
};
}
let (normal_variant, aug_assign_variant) = match self.base {
Operator::Add => info!("add", "+"),
Operator::Sub => info!("sub", "-"),
Operator::Div => info!("truediv", "/"),
Operator::Mod => info!("mod", "%"),
Operator::Mult => info!("mul", "*"),
Operator::Pow => info!("pow", "**"),
Operator::BitOr => info!("or", "|"),
Operator::BitXor => info!("xor", "^"),
Operator::BitAnd => info!("and", "&"),
Operator::LShift => info!("lshift", "<<"),
Operator::RShift => info!("rshift", ">>"),
Operator::FloorDiv => info!("floordiv", "//"),
Operator::MatMult => info!("matmul", "@"),
};
match self.variant {
BinopVariant::Normal => normal_variant,
BinopVariant::AugAssign => aug_assign_variant,
}
}
}
impl HasOpInfo for Unaryop {
fn op_info(&self) -> OpInfo {
match self {
Unaryop::UAdd => make_op_info!("pos", "+"),
Unaryop::USub => make_op_info!("neg", "-"),
Unaryop::Not => make_op_info!("not", "not"), // i.e., `not False`, so the symbol is just `not`.
Unaryop::Invert => make_op_info!("inv", "~"),
}
}
}
pub(super) fn with_fields<F>(unifier: &mut Unifier, ty: Type, f: F)
where
F: FnOnce(&mut Unifier, &mut HashMap<StrRef, (Type, bool)>),
@ -168,31 +83,26 @@ where
pub fn impl_binop(
unifier: &mut Unifier,
_store: &PrimitiveStore,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
ops: &[Operator],
ret_ty: Type,
ops: &[ast::Operator],
) {
with_fields(unifier, ty, |unifier, fields| {
let (other_ty, other_var_id) = if other_ty.len() == 1 {
(other_ty[0], None)
} else {
let tvar = unifier.get_fresh_var_with_range(other_ty, Some("N".into()), None);
(tvar.ty, Some(tvar.id))
let (ty, var_id) = unifier.get_fresh_var_with_range(other_ty, Some("N".into()), None);
(ty, Some(var_id))
};
let function_vars = if let Some(var_id) = other_var_id {
vec![(var_id, other_ty)].into_iter().collect::<VarMap>()
vec![(var_id, other_ty)].into_iter().collect::<HashMap<_, _>>()
} else {
VarMap::new()
HashMap::new()
};
let ret_ty = ret_ty.unwrap_or_else(|| unifier.get_fresh_var(None, None).ty);
for (base_op, variant) in iproduct!(ops, [BinopVariant::Normal, BinopVariant::AugAssign]) {
let op = Binop { base: *base_op, variant };
fields.insert(op.op_info().method_name.into(), {
for op in ops {
fields.insert(binop_name(op).into(), {
(
unifier.add_ty(TypeEnum::TFunc(FunSignature {
ret: ret_ty,
@ -201,7 +111,21 @@ pub fn impl_binop(
ty: other_ty,
default_value: None,
name: "other".into(),
is_vararg: false,
}],
})),
false,
)
});
fields.insert(binop_assign_name(op).into(), {
(
unifier.add_ty(TypeEnum::TFunc(FunSignature {
ret: store.none,
vars: function_vars.clone(),
args: vec![FuncArg {
ty: other_ty,
default_value: None,
name: "other".into(),
}],
})),
false,
@ -211,17 +135,15 @@ pub fn impl_binop(
});
}
pub fn impl_unaryop(unifier: &mut Unifier, ty: Type, ret_ty: Option<Type>, ops: &[Unaryop]) {
pub fn impl_unaryop(unifier: &mut Unifier, ty: Type, ret_ty: Type, ops: &[ast::Unaryop]) {
with_fields(unifier, ty, |unifier, fields| {
let ret_ty = ret_ty.unwrap_or_else(|| unifier.get_fresh_var(None, None).ty);
for op in ops {
fields.insert(
op.op_info().method_name.into(),
unaryop_name(op).into(),
(
unifier.add_ty(TypeEnum::TFunc(FunSignature {
ret: ret_ty,
vars: VarMap::new(),
vars: HashMap::new(),
args: vec![],
})),
false,
@ -233,40 +155,23 @@ pub fn impl_unaryop(unifier: &mut Unifier, ty: Type, ret_ty: Option<Type>, ops:
pub fn impl_cmpop(
unifier: &mut Unifier,
_store: &PrimitiveStore,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ops: &[Cmpop],
ret_ty: Option<Type>,
other_ty: Type,
ops: &[ast::Cmpop],
) {
with_fields(unifier, ty, |unifier, fields| {
let (other_ty, other_var_id) = if other_ty.len() == 1 {
(other_ty[0], None)
} else {
let tvar = unifier.get_fresh_var_with_range(other_ty, Some("N".into()), None);
(tvar.ty, Some(tvar.id))
};
let function_vars = if let Some(var_id) = other_var_id {
vec![(var_id, other_ty)].into_iter().collect::<VarMap>()
} else {
VarMap::new()
};
let ret_ty = ret_ty.unwrap_or_else(|| unifier.get_fresh_var(None, None).ty);
for op in ops {
fields.insert(
op.op_info().method_name.into(),
comparison_name(op).unwrap().into(),
(
unifier.add_ty(TypeEnum::TFunc(FunSignature {
ret: ret_ty,
vars: function_vars.clone(),
ret: store.bool,
vars: HashMap::new(),
args: vec![FuncArg {
ty: other_ty,
default_value: None,
name: "other".into(),
is_vararg: false,
}],
})),
false,
@ -276,13 +181,13 @@ pub fn impl_cmpop(
});
}
/// `Add`, `Sub`, `Mult`
/// Add, Sub, Mult
pub fn impl_basic_arithmetic(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
ret_ty: Type,
) {
impl_binop(
unifier,
@ -290,407 +195,94 @@ pub fn impl_basic_arithmetic(
ty,
other_ty,
ret_ty,
&[Operator::Add, Operator::Sub, Operator::Mult],
);
&[ast::Operator::Add, ast::Operator::Sub, ast::Operator::Mult],
)
}
/// `Pow`
/// Pow
pub fn impl_pow(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
ret_ty: Type,
) {
impl_binop(unifier, store, ty, other_ty, ret_ty, &[Operator::Pow]);
impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::Pow])
}
/// `BitOr`, `BitXor`, `BitAnd`
/// BitOr, BitXor, BitAnd
pub fn impl_bitwise_arithmetic(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
impl_binop(
unifier,
store,
ty,
&[ty],
Some(ty),
&[Operator::BitAnd, Operator::BitOr, Operator::BitXor],
);
}
/// `LShift`, `RShift`
pub fn impl_bitwise_shift(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
impl_binop(
unifier,
store,
ty,
&[store.int32, store.uint32],
Some(ty),
&[Operator::LShift, Operator::RShift],
);
&[ast::Operator::BitAnd, ast::Operator::BitOr, ast::Operator::BitXor],
)
}
/// `Div`
pub fn impl_div(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
) {
impl_binop(unifier, store, ty, other_ty, ret_ty, &[Operator::Div]);
/// LShift, RShift
pub fn impl_bitwise_shift(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
impl_binop(unifier, store, ty, &[ty], ty, &[ast::Operator::LShift, ast::Operator::RShift])
}
/// `FloorDiv`
/// Div
pub fn impl_div(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type, other_ty: &[Type]) {
impl_binop(unifier, store, ty, other_ty, store.float, &[ast::Operator::Div])
}
/// FloorDiv
pub fn impl_floordiv(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
ret_ty: Type,
) {
impl_binop(unifier, store, ty, other_ty, ret_ty, &[Operator::FloorDiv]);
impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::FloorDiv])
}
/// `Mod`
/// Mod
pub fn impl_mod(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
ret_ty: Type,
) {
impl_binop(unifier, store, ty, other_ty, ret_ty, &[Operator::Mod]);
impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::Mod])
}
/// [`Operator::MatMult`]
pub fn impl_matmul(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
) {
impl_binop(unifier, store, ty, other_ty, ret_ty, &[Operator::MatMult]);
/// UAdd, USub
pub fn impl_sign(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type) {
impl_unaryop(unifier, ty, ty, &[ast::Unaryop::UAdd, ast::Unaryop::USub])
}
/// `UAdd`, `USub`
pub fn impl_sign(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type, ret_ty: Option<Type>) {
impl_unaryop(unifier, ty, ret_ty, &[Unaryop::UAdd, Unaryop::USub]);
/// Invert
pub fn impl_invert(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type) {
impl_unaryop(unifier, ty, ty, &[ast::Unaryop::Invert])
}
/// `Invert`
pub fn impl_invert(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type, ret_ty: Option<Type>) {
impl_unaryop(unifier, ty, ret_ty, &[Unaryop::Invert]);
/// Not
pub fn impl_not(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
impl_unaryop(unifier, ty, store.bool, &[ast::Unaryop::Not])
}
/// `Not`
pub fn impl_not(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type, ret_ty: Option<Type>) {
impl_unaryop(unifier, ty, ret_ty, &[Unaryop::Not]);
}
/// `Lt`, `LtE`, `Gt`, `GtE`
pub fn impl_comparison(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
) {
/// Lt, LtE, Gt, GtE
pub fn impl_comparison(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type, other_ty: Type) {
impl_cmpop(
unifier,
store,
ty,
other_ty,
&[Cmpop::Lt, Cmpop::Gt, Cmpop::LtE, Cmpop::GtE],
ret_ty,
);
&[ast::Cmpop::Lt, ast::Cmpop::Gt, ast::Cmpop::LtE, ast::Cmpop::GtE],
)
}
/// `Eq`, `NotEq`
pub fn impl_eq(
unifier: &mut Unifier,
store: &PrimitiveStore,
ty: Type,
other_ty: &[Type],
ret_ty: Option<Type>,
) {
impl_cmpop(unifier, store, ty, other_ty, &[Cmpop::Eq, Cmpop::NotEq], ret_ty);
}
/// Returns the expected return type of binary operations with at least one `ndarray` operand.
pub fn typeof_ndarray_broadcast(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
left: Type,
right: Type,
) -> Result<Type, String> {
let is_left_ndarray = left.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
let is_right_ndarray = right.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
assert!(is_left_ndarray || is_right_ndarray);
if is_left_ndarray && is_right_ndarray {
// Perform broadcasting on two ndarray operands.
let (left_ty_dtype, left_ty_ndims) = unpack_ndarray_var_tys(unifier, left);
let (right_ty_dtype, right_ty_ndims) = unpack_ndarray_var_tys(unifier, right);
assert!(unifier.unioned(left_ty_dtype, right_ty_dtype));
let left_ty_ndims = match &*unifier.get_ty_immutable(left_ty_ndims) {
TypeEnum::TLiteral { values, .. } => values.clone(),
_ => unreachable!(),
};
let right_ty_ndims = match &*unifier.get_ty_immutable(right_ty_ndims) {
TypeEnum::TLiteral { values, .. } => values.clone(),
_ => unreachable!(),
};
let res_ndims = left_ty_ndims
.into_iter()
.cartesian_product(right_ty_ndims)
.map(|(left, right)| {
let left_val = u64::try_from(left).unwrap();
let right_val = u64::try_from(right).unwrap();
max(left_val, right_val)
})
.unique()
.map(SymbolValue::U64)
.collect_vec();
let res_ndims = unifier.get_fresh_literal(res_ndims, None);
Ok(make_ndarray_ty(unifier, primitives, Some(left_ty_dtype), Some(res_ndims)))
} else {
let (ndarray_ty, scalar_ty) = if is_left_ndarray { (left, right) } else { (right, left) };
let (ndarray_ty_dtype, _) = unpack_ndarray_var_tys(unifier, ndarray_ty);
if unifier.unioned(ndarray_ty_dtype, scalar_ty) {
Ok(ndarray_ty)
} else {
let (expected_ty, actual_ty) = if is_left_ndarray {
(ndarray_ty_dtype, scalar_ty)
} else {
(scalar_ty, ndarray_ty_dtype)
};
Err(format!(
"Expected right-hand side operand to be {}, got {}",
unifier.stringify(expected_ty),
unifier.stringify(actual_ty),
))
}
}
}
/// Returns the return type given a binary operator and its primitive operands.
pub fn typeof_binop(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
op: Operator,
lhs: Type,
rhs: Type,
) -> Result<Option<Type>, String> {
let op = Binop { base: op, variant: BinopVariant::Normal };
let is_left_list = lhs.obj_id(unifier).is_some_and(|id| id == PrimDef::List.id());
let is_right_list = rhs.obj_id(unifier).is_some_and(|id| id == PrimDef::List.id());
let is_left_ndarray = lhs.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
let is_right_ndarray = rhs.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
Ok(Some(match op.base {
Operator::Add | Operator::Sub | Operator::Mult | Operator::Mod | Operator::FloorDiv => {
if is_left_list || is_right_list {
if ![Operator::Add, Operator::Mult].contains(&op.base) {
return Err(format!(
"Binary operator {} not supported for list",
op.op_info().symbol
));
}
if is_left_list {
lhs
} else {
rhs
}
} else if is_left_ndarray || is_right_ndarray {
typeof_ndarray_broadcast(unifier, primitives, lhs, rhs)?
} else if unifier.unioned(lhs, rhs) {
lhs
} else {
return Ok(None);
}
}
Operator::MatMult => {
// NOTE: NumPy matmul's LHS and RHS must both be ndarrays. Scalars are not allowed.
match (&*unifier.get_ty(lhs), &*unifier.get_ty(rhs)) {
(
TypeEnum::TObj { obj_id: lhs_obj_id, .. },
TypeEnum::TObj { obj_id: rhs_obj_id, .. },
) if *lhs_obj_id == primitives.ndarray.obj_id(unifier).unwrap()
&& *rhs_obj_id == primitives.ndarray.obj_id(unifier).unwrap() =>
{
// LHS and RHS have valid types
}
_ => {
let lhs_str = unifier.stringify(lhs);
let rhs_str = unifier.stringify(rhs);
return Err(format!("ndarray.__matmul__ only accepts ndarray operands, but left operand has type {lhs_str}, and right operand has type {rhs_str}"));
}
}
let (_, lhs_ndims) = unpack_ndarray_var_tys(unifier, lhs);
let lhs_ndims = match &*unifier.get_ty_immutable(lhs_ndims) {
TypeEnum::TLiteral { values, .. } => {
assert_eq!(values.len(), 1);
u64::try_from(values[0].clone()).unwrap()
}
_ => unreachable!(),
};
let (_, rhs_ndims) = unpack_ndarray_var_tys(unifier, rhs);
let rhs_ndims = match &*unifier.get_ty_immutable(rhs_ndims) {
TypeEnum::TLiteral { values, .. } => {
assert_eq!(values.len(), 1);
u64::try_from(values[0].clone()).unwrap()
}
_ => unreachable!(),
};
match (lhs_ndims, rhs_ndims) {
(2, 2) => typeof_ndarray_broadcast(unifier, primitives, lhs, rhs)?,
(lhs, rhs) if lhs == 0 || rhs == 0 => {
return Err(format!(
"Input operand {} does not have enough dimensions (has {lhs}, requires {rhs})",
u8::from(rhs == 0)
))
}
(lhs, rhs) => {
return Err(format!(
"ndarray.__matmul__ on {lhs}D and {rhs}D operands not supported"
))
}
}
}
Operator::Div => {
if is_left_ndarray || is_right_ndarray {
typeof_ndarray_broadcast(unifier, primitives, lhs, rhs)?
} else if unifier.unioned(lhs, rhs) {
primitives.float
} else {
return Ok(None);
}
}
Operator::Pow => {
if is_left_ndarray || is_right_ndarray {
typeof_ndarray_broadcast(unifier, primitives, lhs, rhs)?
} else if [
primitives.int32,
primitives.int64,
primitives.uint32,
primitives.uint64,
primitives.float,
]
.into_iter()
.any(|ty| unifier.unioned(lhs, ty))
{
lhs
} else {
return Ok(None);
}
}
Operator::LShift | Operator::RShift => lhs,
Operator::BitOr | Operator::BitXor | Operator::BitAnd => {
if unifier.unioned(lhs, rhs) {
lhs
} else {
return Ok(None);
}
}
}))
}
pub fn typeof_unaryop(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
op: Unaryop,
operand: Type,
) -> Result<Option<Type>, String> {
let operand_obj_id = operand.obj_id(unifier);
if op == Unaryop::Not
&& operand_obj_id.is_some_and(|id| id == primitives.ndarray.obj_id(unifier).unwrap())
{
return Err(
"The truth value of an array with more than one element is ambiguous".to_string()
);
}
Ok(match op {
Unaryop::Not => match operand_obj_id {
Some(v) if v == PrimDef::NDArray.id() => Some(operand),
Some(_) => Some(primitives.bool),
_ => None,
},
Unaryop::Invert => {
if operand_obj_id.is_some_and(|id| id == PrimDef::Bool.id()) {
Some(primitives.int32)
} else if operand_obj_id.is_some_and(|id| PrimDef::iter().any(|prim| id == prim.id())) {
Some(operand)
} else {
None
}
}
Unaryop::UAdd | Unaryop::USub => {
if operand_obj_id.is_some_and(|id| id == PrimDef::NDArray.id()) {
let (dtype, _) = unpack_ndarray_var_tys(unifier, operand);
if dtype.obj_id(unifier).is_some_and(|id| id == PrimDef::Bool.id()) {
return Err(if op == Unaryop::UAdd {
"The ufunc 'positive' cannot be applied to ndarray[bool, N]".to_string()
} else {
"The numpy boolean negative, the `-` operator, is not supported, use the `~` operator function instead.".to_string()
});
}
Some(operand)
} else if operand_obj_id.is_some_and(|id| id == PrimDef::Bool.id()) {
Some(primitives.int32)
} else if operand_obj_id.is_some_and(|id| PrimDef::iter().any(|prim| id == prim.id())) {
Some(operand)
} else {
None
}
}
})
}
/// Returns the return type given a comparison operator and its primitive operands.
pub fn typeof_cmpop(
unifier: &mut Unifier,
primitives: &PrimitiveStore,
_op: Cmpop,
lhs: Type,
rhs: Type,
) -> Result<Option<Type>, String> {
let is_left_ndarray = lhs.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
let is_right_ndarray = rhs.obj_id(unifier).is_some_and(|id| id == PrimDef::NDArray.id());
Ok(Some(if is_left_ndarray || is_right_ndarray {
let brd = typeof_ndarray_broadcast(unifier, primitives, lhs, rhs)?;
let (_, ndims) = unpack_ndarray_var_tys(unifier, brd);
make_ndarray_ty(unifier, primitives, Some(primitives.bool), Some(ndims))
} else if unifier.unioned(lhs, rhs) {
primitives.bool
} else {
return Ok(None);
}))
/// Eq, NotEq
pub fn impl_eq(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
impl_cmpop(unifier, store, ty, ty, &[ast::Cmpop::Eq, ast::Cmpop::NotEq])
}
pub fn set_primitives_magic_methods(store: &PrimitiveStore, unifier: &mut Unifier) {
@ -701,81 +293,38 @@ pub fn set_primitives_magic_methods(store: &PrimitiveStore, unifier: &mut Unifie
bool: bool_t,
uint32: uint32_t,
uint64: uint64_t,
str: str_t,
list: list_t,
ndarray: ndarray_t,
..
} = *store;
let size_t = store.usize();
/* int ======== */
for t in [int32_t, int64_t, uint32_t, uint64_t] {
let ndarray_int_t = make_ndarray_ty(unifier, store, Some(t), None);
impl_basic_arithmetic(unifier, store, t, &[t, ndarray_int_t], None);
impl_pow(unifier, store, t, &[t, ndarray_int_t], None);
impl_basic_arithmetic(unifier, store, t, &[t], t);
impl_pow(unifier, store, t, &[t], t);
impl_bitwise_arithmetic(unifier, store, t);
impl_bitwise_shift(unifier, store, t);
impl_div(unifier, store, t, &[t, ndarray_int_t], None);
impl_floordiv(unifier, store, t, &[t, ndarray_int_t], None);
impl_mod(unifier, store, t, &[t, ndarray_int_t], None);
impl_invert(unifier, store, t, Some(t));
impl_not(unifier, store, t, Some(bool_t));
impl_comparison(unifier, store, t, &[t, ndarray_int_t], None);
impl_eq(unifier, store, t, &[t, ndarray_int_t], None);
impl_div(unifier, store, t, &[t]);
impl_floordiv(unifier, store, t, &[t], t);
impl_mod(unifier, store, t, &[t], t);
impl_invert(unifier, store, t);
impl_not(unifier, store, t);
impl_comparison(unifier, store, t, t);
impl_eq(unifier, store, t);
}
for t in [int32_t, int64_t] {
impl_sign(unifier, store, t, Some(t));
impl_sign(unifier, store, t);
}
/* float ======== */
let ndarray_float_t = make_ndarray_ty(unifier, store, Some(float_t), None);
let ndarray_int32_t = make_ndarray_ty(unifier, store, Some(int32_t), None);
impl_basic_arithmetic(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_pow(unifier, store, float_t, &[int32_t, float_t, ndarray_int32_t, ndarray_float_t], None);
impl_div(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_floordiv(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_mod(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_sign(unifier, store, float_t, Some(float_t));
impl_not(unifier, store, float_t, Some(bool_t));
impl_comparison(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_eq(unifier, store, float_t, &[float_t, ndarray_float_t], None);
impl_basic_arithmetic(unifier, store, float_t, &[float_t], float_t);
impl_pow(unifier, store, float_t, &[int32_t, float_t], float_t);
impl_div(unifier, store, float_t, &[float_t]);
impl_floordiv(unifier, store, float_t, &[float_t], float_t);
impl_mod(unifier, store, float_t, &[float_t], float_t);
impl_sign(unifier, store, float_t);
impl_not(unifier, store, float_t);
impl_comparison(unifier, store, float_t, float_t);
impl_eq(unifier, store, float_t);
/* bool ======== */
let ndarray_bool_t = make_ndarray_ty(unifier, store, Some(bool_t), None);
impl_invert(unifier, store, bool_t, Some(int32_t));
impl_not(unifier, store, bool_t, Some(bool_t));
impl_sign(unifier, store, bool_t, Some(int32_t));
impl_eq(unifier, store, bool_t, &[bool_t, ndarray_bool_t], None);
/* str ========= */
impl_cmpop(unifier, store, str_t, &[str_t], &[Cmpop::Eq, Cmpop::NotEq], Some(bool_t));
/* list ======== */
impl_binop(unifier, store, list_t, &[list_t], Some(list_t), &[Operator::Add]);
impl_binop(unifier, store, list_t, &[int32_t, int64_t], Some(list_t), &[Operator::Mult]);
impl_cmpop(unifier, store, list_t, &[list_t], &[Cmpop::Eq, Cmpop::NotEq], Some(bool_t));
/* ndarray ===== */
let ndarray_usized_ndims_tvar =
unifier.get_fresh_const_generic_var(size_t, Some("ndarray_ndims".into()), None);
let ndarray_unsized_t =
make_ndarray_ty(unifier, store, None, Some(ndarray_usized_ndims_tvar.ty));
let (ndarray_dtype_t, _) = unpack_ndarray_var_tys(unifier, ndarray_t);
let (ndarray_unsized_dtype_t, _) = unpack_ndarray_var_tys(unifier, ndarray_unsized_t);
impl_basic_arithmetic(
unifier,
store,
ndarray_t,
&[ndarray_unsized_t, ndarray_unsized_dtype_t],
None,
);
impl_pow(unifier, store, ndarray_t, &[ndarray_unsized_t, ndarray_unsized_dtype_t], None);
impl_div(unifier, store, ndarray_t, &[ndarray_t, ndarray_dtype_t], None);
impl_floordiv(unifier, store, ndarray_t, &[ndarray_unsized_t, ndarray_unsized_dtype_t], None);
impl_mod(unifier, store, ndarray_t, &[ndarray_unsized_t, ndarray_unsized_dtype_t], None);
impl_matmul(unifier, store, ndarray_t, &[ndarray_t], Some(ndarray_t));
impl_sign(unifier, store, ndarray_t, Some(ndarray_t));
impl_invert(unifier, store, ndarray_t, Some(ndarray_t));
impl_eq(unifier, store, ndarray_t, &[ndarray_unsized_t, ndarray_unsized_dtype_t], None);
impl_comparison(unifier, store, ndarray_t, &[ndarray_unsized_t, ndarray_unsized_dtype_t], None);
impl_not(unifier, store, bool_t);
impl_eq(unifier, store, bool_t);
}

119
nac3core/src/typecheck/type_error.rs
View File

@ -1,45 +1,24 @@
use std::{collections::HashMap, fmt::Display};
use std::collections::HashMap;
use std::fmt::Display;
use itertools::Itertools;
use crate::typecheck::typedef::TypeEnum;
use nac3parser::ast::{Cmpop, Location, StrRef};
use super::{
magic_methods::{Binop, HasOpInfo},
typedef::{RecordKey, Type, TypeEnum, Unifier},
};
use super::typedef::{RecordKey, Type, Unifier};
use nac3parser::ast::{Location, StrRef};
#[derive(Debug, Clone)]
pub enum TypeErrorKind {
GotMultipleValues {
name: StrRef,
},
TooManyArguments {
expected_min_count: usize,
expected_max_count: usize,
got_count: usize,
},
MissingArgs {
missing_arg_names: Vec<StrRef>,
expected: usize,
got: usize,
},
MissingArgs(String),
UnknownArgName(StrRef),
IncorrectArgType {
name: StrRef,
expected: Type,
got: Type,
},
UnsupportedBinaryOpTypes {
operator: Binop,
lhs_type: Type,
rhs_type: Type,
expected_rhs_type: Type,
},
UnsupportedComparsionOpTypes {
operator: Cmpop,
lhs_type: Type,
rhs_type: Type,
expected_rhs_type: Type,
},
FieldUnificationError {
field: RecordKey,
types: (Type, Type),
@ -55,7 +34,6 @@ pub enum TypeErrorKind {
},
RequiresTypeAnn,
PolymorphicFunctionPointer,
NoSuchAttribute(RecordKey, Type),
}
#[derive(Debug, Clone)]
@ -65,18 +43,15 @@ pub struct TypeError {
}
impl TypeError {
#[must_use]
pub fn new(kind: TypeErrorKind, loc: Option<Location>) -> TypeError {
TypeError { kind, loc }
}
#[must_use]
pub fn at(mut self, loc: Option<Location>) -> TypeError {
self.loc = self.loc.or(loc);
self
}
#[must_use]
pub fn to_display(self, unifier: &Unifier) -> DisplayTypeError {
DisplayTypeError { err: self, unifier }
}
@ -89,8 +64,8 @@ pub struct DisplayTypeError<'a> {
fn loc_to_str(loc: Option<Location>) -> String {
match loc {
Some(loc) => format!("(in {loc})"),
None => String::new(),
Some(loc) => format!("(in {})", loc),
None => "".to_string(),
}
}
@ -99,49 +74,23 @@ impl<'a> Display for DisplayTypeError<'a> {
use TypeErrorKind::*;
let mut notes = Some(HashMap::new());
match &self.err.kind {
GotMultipleValues { name } => {
write!(f, "For multiple values for parameter {name}")
TooManyArguments { expected, got } => {
write!(f, "Too many arguments. Expected {} but got {}", expected, got)
}
TooManyArguments { expected_min_count, expected_max_count, got_count } => {
debug_assert!(expected_min_count <= expected_max_count);
if expected_min_count == expected_max_count {
let expected_count = expected_min_count; // or expected_max_count
write!(f, "Too many arguments. Expected {expected_count} but got {got_count}")
} else {
write!(f, "Too many arguments. Expected {expected_min_count} to {expected_max_count} arguments but got {got_count}")
}
}
MissingArgs { missing_arg_names } => {
let args = missing_arg_names.iter().join(", ");
write!(f, "Missing arguments: {args}")
}
UnsupportedBinaryOpTypes { operator, lhs_type, rhs_type, expected_rhs_type } => {
let op_symbol = operator.op_info().symbol;
let lhs_type_str = self.unifier.stringify_with_notes(*lhs_type, &mut notes);
let rhs_type_str = self.unifier.stringify_with_notes(*rhs_type, &mut notes);
let expected_rhs_type_str =
self.unifier.stringify_with_notes(*expected_rhs_type, &mut notes);
write!(f, "Unsupported operand type(s) for {op_symbol}: '{lhs_type_str}' and '{rhs_type_str}' (right operand should have type {expected_rhs_type_str})")
}
UnsupportedComparsionOpTypes { operator, lhs_type, rhs_type, expected_rhs_type } => {
let op_symbol = operator.op_info().symbol;
let lhs_type_str = self.unifier.stringify_with_notes(*lhs_type, &mut notes);
let rhs_type_str = self.unifier.stringify_with_notes(*rhs_type, &mut notes);
let expected_rhs_type_str =
self.unifier.stringify_with_notes(*expected_rhs_type, &mut notes);
write!(f, "'{op_symbol}' not supported between instances of '{lhs_type_str}' and '{rhs_type_str}' (right operand should have type {expected_rhs_type_str})")
MissingArgs(args) => {
write!(f, "Missing arguments: {}", args)
}
UnknownArgName(name) => {
write!(f, "Unknown argument name: {name}")
write!(f, "Unknown argument name: {}", name)
}
IncorrectArgType { name, expected, got } => {
let expected = self.unifier.stringify_with_notes(*expected, &mut notes);
let got = self.unifier.stringify_with_notes(*got, &mut notes);
write!(f, "Incorrect argument type for parameter {name}. Expected {expected}, but got {got}")
write!(
f,
"Incorrect argument type for {}. Expected {}, but got {}",
name, expected, got
)
}
FieldUnificationError { field, types, loc } => {
let lhs = self.unifier.stringify_with_notes(types.0, &mut notes);
@ -177,23 +126,22 @@ impl<'a> Display for DisplayTypeError<'a> {
);
if let Some(loc) = loc {
result?;
write!(f, " (in {loc})")?;
write!(f, " (in {})", loc)?;
return Ok(());
}
result
}
(
TypeEnum::TTuple { ty: ty1, is_vararg_ctx: is_vararg1 },
TypeEnum::TTuple { ty: ty2, is_vararg_ctx: is_vararg2 },
) if !is_vararg1 && !is_vararg2 && ty1.len() != ty2.len() => {
(TypeEnum::TTuple { ty: ty1 }, TypeEnum::TTuple { ty: ty2 })
if ty1.len() != ty2.len() =>
{
let t1 = self.unifier.stringify_with_notes(*t1, &mut notes);
let t2 = self.unifier.stringify_with_notes(*t2, &mut notes);
write!(f, "Tuple length mismatch: got {t1} and {t2}")
write!(f, "Tuple length mismatch: got {} and {}", t1, t2)
}
_ => {
let t1 = self.unifier.stringify_with_notes(*t1, &mut notes);
let t2 = self.unifier.stringify_with_notes(*t2, &mut notes);
write!(f, "Incompatible types: {t1} and {t2}")
write!(f, "Incompatible types: {} and {}", t1, t2)
}
}
}
@ -202,21 +150,18 @@ impl<'a> Display for DisplayTypeError<'a> {
write!(f, "Cannot assign to an element of a tuple")
} else {
let t = self.unifier.stringify_with_notes(*t, &mut notes);
write!(f, "Cannot assign to field {name} of {t}, which is immutable")
write!(f, "Cannot assign to field {} of {}, which is immutable", name, t)
}
}
NoSuchField(name, t) => {
let t = self.unifier.stringify_with_notes(*t, &mut notes);
write!(f, "`{t}::{name}` field/method does not exist")
}
NoSuchAttribute(name, t) => {
let t = self.unifier.stringify_with_notes(*t, &mut notes);
write!(f, "`{t}::{name}` is not a class attribute")
write!(f, "`{}::{}` field/method does not exist", t, name)
}
TupleIndexOutOfBounds { index, len } => {
write!(
f,
"Tuple index out of bounds. Got {index} but tuple has only {len} elements"
"Tuple index out of bounds. Got {} but tuple has only {} elements",
index, len
)
}
RequiresTypeAnn => {
@ -227,13 +172,13 @@ impl<'a> Display for DisplayTypeError<'a> {
}
}?;
if let Some(loc) = self.err.loc {
write!(f, " at {loc}")?;
write!(f, " at {}", loc)?;
}
let notes = notes.unwrap();
if !notes.is_empty() {
write!(f, "\n\nNotes:")?;
for line in notes.values() {
write!(f, "\n {line}")?;
write!(f, "\n {}", line)?;
}
}
Ok(())

2395
nac3core/src/typecheck/type_inferencer/mod.rs
View File

File diff suppressed because it is too large Load Diff

412
nac3core/src/typecheck/type_inferencer/test.rs
View File

@ -1,19 +1,15 @@
use std::iter::zip;
use indexmap::IndexMap;
use indoc::indoc;
use parking_lot::RwLock;
use test_case::test_case;
use nac3parser::{ast::FileName, parser::parse_program};
use super::super::{magic_methods::with_fields, typedef::*};
use super::*;
use crate::{
codegen::{CodeGenContext, CodeGenerator},
codegen::CodeGenContext,
symbol_resolver::ValueEnum,
toplevel::{helper::PrimDef, DefinitionId, TopLevelDef},
typecheck::{magic_methods::with_fields, typedef::*},
toplevel::{DefinitionId, TopLevelDef},
};
use indoc::indoc;
use itertools::zip;
use nac3parser::parser::parse_program;
use parking_lot::RwLock;
use test_case::test_case;
struct Resolver {
id_to_type: HashMap<StrRef, Type>,
@ -24,7 +20,7 @@ struct Resolver {
impl SymbolResolver for Resolver {
fn get_default_param_value(
&self,
_: &ast::Expr,
_: &nac3parser::ast::Expr,
) -> Option<crate::symbol_resolver::SymbolValue> {
unimplemented!()
}
@ -36,30 +32,26 @@ impl SymbolResolver for Resolver {
_: &PrimitiveStore,
str: StrRef,
) -> Result<Type, String> {
self.id_to_type.get(&str).copied().ok_or_else(|| format!("cannot find symbol `{str}`"))
self.id_to_type.get(&str).cloned().ok_or_else(|| format!("cannot find symbol `{}`", str))
}
fn get_symbol_value<'ctx>(
fn get_symbol_value<'ctx, 'a>(
&self,
_: StrRef,
_: &mut CodeGenContext<'ctx, '_>,
_: &mut dyn CodeGenerator,
_: &mut CodeGenContext<'ctx, 'a>,
) -> Option<ValueEnum<'ctx>> {
unimplemented!()
}
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, HashSet<String>> {
self.id_to_def
.get(&id)
.copied()
.ok_or_else(|| HashSet::from(["Unknown identifier".to_string()]))
fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
self.id_to_def.get(&id).cloned().ok_or("Unknown identifier".to_string())
}
fn get_string_id(&self, _: &str) -> i32 {
unimplemented!()
}
fn get_exception_id(&self, _tyid: usize) -> usize {
fn get_exception_id(&self, tyid: usize) -> usize {
unimplemented!()
}
}
@ -70,7 +62,7 @@ struct TestEnvironment {
pub primitives: PrimitiveStore,
pub id_to_name: HashMap<usize, StrRef>,
pub identifier_mapping: HashMap<StrRef, Type>,
pub virtual_checks: Vec<(Type, Type, Location)>,
pub virtual_checks: Vec<(Type, Type, nac3parser::ast::Location)>,
pub calls: HashMap<CodeLocation, CallId>,
pub top_level: TopLevelContext,
}
@ -80,107 +72,67 @@ impl TestEnvironment {
let mut unifier = Unifier::new();
let int32 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Int32.id(),
obj_id: DefinitionId(0),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
with_fields(&mut unifier, int32, |unifier, fields| {
let add_ty = unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![FuncArg {
name: "other".into(),
ty: int32,
default_value: None,
is_vararg: false,
}],
args: vec![FuncArg { name: "other".into(), ty: int32, default_value: None }],
ret: int32,
vars: VarMap::new(),
vars: HashMap::new(),
}));
fields.insert("__add__".into(), (add_ty, false));
});
let int64 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Int64.id(),
obj_id: DefinitionId(1),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let float = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Float.id(),
obj_id: DefinitionId(2),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let bool = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Bool.id(),
obj_id: DefinitionId(3),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let none = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::None.id(),
obj_id: DefinitionId(4),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let range = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Range.id(),
obj_id: DefinitionId(5),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let str = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Str.id(),
obj_id: DefinitionId(6),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let exception = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Exception.id(),
obj_id: DefinitionId(7),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let uint32 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::UInt32.id(),
obj_id: DefinitionId(8),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let uint64 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::UInt64.id(),
obj_id: DefinitionId(9),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let option = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Option.id(),
fields: HashMap::new(),
params: VarMap::new(),
});
let list_elem_tvar = unifier.get_fresh_var(Some("list_elem".into()), None);
let list = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::List.id(),
fields: HashMap::new(),
params: into_var_map([list_elem_tvar]),
});
let ndarray_dtype_tvar = unifier.get_fresh_var(Some("ndarray_dtype".into()), None);
let ndarray_ndims_tvar =
unifier.get_fresh_const_generic_var(uint64, Some("ndarray_ndims".into()), None);
let ndarray = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::NDArray.id(),
fields: HashMap::new(),
params: into_var_map([ndarray_dtype_tvar, ndarray_ndims_tvar]),
});
let primitives = PrimitiveStore {
int32,
int64,
float,
bool,
none,
range,
str,
exception,
uint32,
uint64,
option,
list,
ndarray,
size_t: 64,
};
unifier.put_primitive_store(&primitives);
let primitives = PrimitiveStore { int32, int64, float, bool, none, range, str, exception, uint32, uint64 };
set_primitives_magic_methods(&primitives, &mut unifier);
let id_to_name: HashMap<_, _> = [
let id_to_name = [
(0, "int32".into()),
(1, "int64".into()),
(2, "float".into()),
@ -190,21 +142,23 @@ impl TestEnvironment {
(6, "str".into()),
(7, "exception".into()),
]
.into();
.iter()
.cloned()
.collect();
let mut identifier_mapping = HashMap::new();
identifier_mapping.insert("None".into(), none);
let resolver = Arc::new(Resolver {
id_to_type: identifier_mapping.clone(),
id_to_def: HashMap::default(),
class_names: HashMap::default(),
id_to_def: Default::default(),
class_names: Default::default(),
}) as Arc<dyn SymbolResolver + Send + Sync>;
TestEnvironment {
top_level: TopLevelContext {
definitions: Arc::default(),
unifiers: Arc::default(),
definitions: Default::default(),
unifiers: Default::default(),
personality_symbol: None,
},
unifier,
@ -226,112 +180,76 @@ impl TestEnvironment {
let mut identifier_mapping = HashMap::new();
let mut top_level_defs: Vec<Arc<RwLock<TopLevelDef>>> = Vec::new();
let int32 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Int32.id(),
obj_id: DefinitionId(0),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
with_fields(&mut unifier, int32, |unifier, fields| {
let add_ty = unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![FuncArg {
name: "other".into(),
ty: int32,
default_value: None,
is_vararg: false,
}],
args: vec![FuncArg { name: "other".into(), ty: int32, default_value: None }],
ret: int32,
vars: VarMap::new(),
vars: HashMap::new(),
}));
fields.insert("__add__".into(), (add_ty, false));
});
let int64 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Int64.id(),
obj_id: DefinitionId(1),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let float = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Float.id(),
obj_id: DefinitionId(2),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let bool = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Bool.id(),
obj_id: DefinitionId(3),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let none = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::None.id(),
obj_id: DefinitionId(4),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let range = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Range.id(),
obj_id: DefinitionId(5),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let str = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Str.id(),
obj_id: DefinitionId(6),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let exception = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Exception.id(),
obj_id: DefinitionId(7),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let uint32 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::UInt32.id(),
obj_id: DefinitionId(8),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
let uint64 = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::UInt64.id(),
obj_id: DefinitionId(9),
fields: HashMap::new(),
params: VarMap::new(),
});
let option = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::Option.id(),
fields: HashMap::new(),
params: VarMap::new(),
});
let list_elem_tvar = unifier.get_fresh_var(Some("list_elem".into()), None);
let list = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::List.id(),
fields: HashMap::new(),
params: into_var_map([list_elem_tvar]),
});
let ndarray = unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::NDArray.id(),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
});
identifier_mapping.insert("None".into(), none);
for (i, name) in [
"int32",
"int64",
"float",
"bool",
"none",
"range",
"str",
"Exception",
"uint32",
"uint64",
"Option",
"list",
"ndarray",
]
.iter()
.enumerate()
for (i, name) in ["int32", "int64", "float", "bool", "none", "range", "str", "Exception"]
.iter()
.enumerate()
{
top_level_defs.push(
RwLock::new(TopLevelDef::Class {
name: (*name).into(),
object_id: DefinitionId(i),
type_vars: Vec::default(),
fields: Vec::default(),
attributes: Vec::default(),
methods: Vec::default(),
ancestors: Vec::default(),
type_vars: Default::default(),
fields: Default::default(),
methods: Default::default(),
ancestors: Default::default(),
resolver: None,
constructor: None,
loc: None,
@ -339,43 +257,25 @@ impl TestEnvironment {
.into(),
);
}
let defs = 12;
let defs = 7;
let primitives = PrimitiveStore {
int32,
int64,
float,
bool,
none,
range,
str,
exception,
uint32,
uint64,
option,
list,
ndarray,
size_t: 64,
};
let primitives = PrimitiveStore { int32, int64, float, bool, none, range, str, exception, uint32, uint64 };
unifier.put_primitive_store(&primitives);
let tvar = unifier.get_dummy_var();
let (v0, id) = unifier.get_dummy_var();
let foo_ty = unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(defs + 1),
fields: [("a".into(), (tvar.ty, true))].into(),
params: into_var_map([tvar]),
fields: [("a".into(), (v0, true))].iter().cloned().collect::<HashMap<_, _>>(),
params: [(id, v0)].iter().cloned().collect::<HashMap<_, _>>(),
});
top_level_defs.push(
RwLock::new(TopLevelDef::Class {
name: "Foo".into(),
object_id: DefinitionId(defs + 1),
type_vars: vec![tvar.ty],
fields: [("a".into(), tvar.ty, true)].into(),
attributes: Vec::default(),
methods: Vec::default(),
ancestors: Vec::default(),
type_vars: vec![v0],
fields: [("a".into(), v0, true)].into(),
methods: Default::default(),
ancestors: Default::default(),
resolver: None,
constructor: None,
loc: None,
@ -388,29 +288,31 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![],
ret: foo_ty,
vars: into_var_map([tvar]),
vars: [(id, v0)].iter().cloned().collect(),
})),
);
let fun = unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![],
ret: int32,
vars: IndexMap::default(),
vars: Default::default(),
}));
let bar = unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(defs + 2),
fields: [("a".into(), (int32, true)), ("b".into(), (fun, true))].into(),
params: IndexMap::default(),
fields: [("a".into(), (int32, true)), ("b".into(), (fun, true))]
.iter()
.cloned()
.collect::<HashMap<_, _>>(),
params: Default::default(),
});
top_level_defs.push(
RwLock::new(TopLevelDef::Class {
name: "Bar".into(),
object_id: DefinitionId(defs + 2),
type_vars: Vec::default(),
type_vars: Default::default(),
fields: [("a".into(), int32, true), ("b".into(), fun, true)].into(),
attributes: Vec::default(),
methods: Vec::default(),
ancestors: Vec::default(),
methods: Default::default(),
ancestors: Default::default(),
resolver: None,
constructor: None,
loc: None,
@ -422,24 +324,26 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![],
ret: bar,
vars: IndexMap::default(),
vars: Default::default(),
})),
);
let bar2 = unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(defs + 3),
fields: [("a".into(), (bool, true)), ("b".into(), (fun, false))].into(),
params: IndexMap::default(),
fields: [("a".into(), (bool, true)), ("b".into(), (fun, false))]
.iter()
.cloned()
.collect::<HashMap<_, _>>(),
params: Default::default(),
});
top_level_defs.push(
RwLock::new(TopLevelDef::Class {
name: "Bar2".into(),
object_id: DefinitionId(defs + 3),
type_vars: Vec::default(),
type_vars: Default::default(),
fields: [("a".into(), bool, true), ("b".into(), fun, false)].into(),
attributes: Vec::default(),
methods: Vec::default(),
ancestors: Vec::default(),
methods: Default::default(),
ancestors: Default::default(),
resolver: None,
constructor: None,
loc: None,
@ -451,10 +355,10 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![],
ret: bar2,
vars: IndexMap::default(),
vars: Default::default(),
})),
);
let class_names: HashMap<_, _> = [("Bar".into(), bar), ("Bar2".into(), bar2)].into();
let class_names = [("Bar".into(), bar), ("Bar2".into(), bar2)].iter().cloned().collect();
let id_to_name = [
"int32".into(),
@ -465,22 +369,18 @@ impl TestEnvironment {
"range".into(),
"str".into(),
"exception".into(),
"uint32".into(),
"uint64".into(),
"option".into(),
"list".into(),
"ndarray".into(),
"Foo".into(),
"Bar".into(),
"Bar2".into(),
]
.into_iter()
.iter()
.enumerate()
.map(|(a, b)| (a, *b))
.collect();
let top_level = TopLevelContext {
definitions: Arc::new(top_level_defs.into()),
unifiers: Arc::default(),
unifiers: Default::default(),
personality_symbol: None,
};
@ -491,7 +391,9 @@ impl TestEnvironment {
("Bar".into(), DefinitionId(defs + 2)),
("Bar2".into(), DefinitionId(defs + 3)),
]
.into(),
.iter()
.cloned()
.collect(),
class_names,
}) as Arc<dyn SymbolResolver + Send + Sync>;
@ -516,11 +418,11 @@ impl TestEnvironment {
top_level: &self.top_level,
function_data: &mut self.function_data,
unifier: &mut self.unifier,
variable_mapping: HashMap::default(),
variable_mapping: Default::default(),
primitives: &mut self.primitives,
virtual_checks: &mut self.virtual_checks,
calls: &mut self.calls,
defined_identifiers: HashMap::default(),
defined_identifiers: Default::default(),
in_handler: false,
}
}
@ -532,7 +434,7 @@ impl TestEnvironment {
c = 1.234
d = True
"},
&[("a", "int32"), ("b", "int64"), ("c", "float"), ("d", "bool")].into(),
[("a", "int32"), ("b", "int64"), ("c", "float"), ("d", "bool")].iter().cloned().collect(),
&[]
; "primitives test")]
#[test_case(indoc! {"
@ -541,7 +443,7 @@ impl TestEnvironment {
c = 1.234
d = b(c)
"},
&[("a", "fn[[x:float, y:float], float]"), ("b", "fn[[x:float], float]"), ("c", "float"), ("d", "float")].into(),
[("a", "fn[[x:float, y:float], float]"), ("b", "fn[[x:float], float]"), ("c", "float"), ("d", "float")].iter().cloned().collect(),
&[]
; "lambda test")]
#[test_case(indoc! {"
@ -550,7 +452,7 @@ impl TestEnvironment {
a = b
c = b(1)
"},
&[("a", "fn[[x:int32], int32]"), ("b", "fn[[x:int32], int32]"), ("c", "int32")].into(),
[("a", "fn[[x:int32], int32]"), ("b", "fn[[x:int32], int32]"), ("c", "int32")].iter().cloned().collect(),
&[]
; "lambda test 2")]
#[test_case(indoc! {"
@ -566,15 +468,15 @@ impl TestEnvironment {
b(123)
"},
&[("a", "fn[[x:bool], bool]"), ("b", "fn[[x:int32], int32]"), ("c", "bool"),
("d", "int32"), ("foo1", "Foo[bool]"), ("foo2", "Foo[int32]")].into(),
[("a", "fn[[x:bool], bool]"), ("b", "fn[[x:int32], int32]"), ("c", "bool"),
("d", "int32"), ("foo1", "Foo[bool]"), ("foo2", "Foo[int32]")].iter().cloned().collect(),
&[]
; "obj test")]
#[test_case(indoc! {"
a = [1, 2, 3]
b = [x + x for x in a]
"},
&[("a", "list[int32]"), ("b", "list[int32]")].into(),
[("a", "list[int32]"), ("b", "list[int32]")].iter().cloned().collect(),
&[]
; "listcomp test")]
#[test_case(indoc! {"
@ -582,26 +484,25 @@ impl TestEnvironment {
b = a.b()
a = virtual(Bar2())
"},
&[("a", "virtual[Bar]"), ("b", "int32")].into(),
[("a", "virtual[Bar]"), ("b", "int32")].iter().cloned().collect(),
&[("Bar", "Bar"), ("Bar2", "Bar")]
; "virtual test")]
#[test_case(indoc! {"
a = [virtual(Bar(), Bar), virtual(Bar2())]
b = [x.b() for x in a]
"},
&[("a", "list[virtual[Bar]]"), ("b", "list[int32]")].into(),
[("a", "list[virtual[Bar]]"), ("b", "list[int32]")].iter().cloned().collect(),
&[("Bar", "Bar"), ("Bar2", "Bar")]
; "virtual list test")]
fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &str)]) {
println!("source:\n{source}");
fn test_basic(source: &str, mapping: HashMap<&str, &str>, virtuals: &[(&str, &str)]) {
println!("source:\n{}", source);
let mut env = TestEnvironment::new();
let id_to_name = std::mem::take(&mut env.id_to_name);
let mut defined_identifiers: HashMap<_, _> =
env.identifier_mapping.keys().copied().map(|id| (id, IdentifierInfo::default())).collect();
defined_identifiers.insert("virtual".into(), IdentifierInfo::default());
let mut defined_identifiers: HashSet<_> = env.identifier_mapping.keys().cloned().collect();
defined_identifiers.insert("virtual".into());
let mut inferencer = env.get_inferencer();
inferencer.defined_identifiers.clone_from(&defined_identifiers);
let statements = parse_program(source, FileName::default()).unwrap();
inferencer.defined_identifiers = defined_identifiers.clone();
let statements = parse_program(source, Default::default()).unwrap();
let statements = statements
.into_iter()
.map(|v| inferencer.fold_stmt(v))
@ -610,37 +511,37 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
inferencer.check_block(&statements, &mut defined_identifiers).unwrap();
for (k, v) in &inferencer.variable_mapping {
for (k, v) in inferencer.variable_mapping.iter() {
let name = inferencer.unifier.internal_stringify(
*v,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
println!("{k}: {name}");
println!("{}: {}", k, name);
}
for (k, v) in mapping {
for (k, v) in mapping.iter() {
let ty = inferencer.variable_mapping.get(&(*k).into()).unwrap();
let name = inferencer.unifier.internal_stringify(
*ty,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
assert_eq!(format!("{k}: {v}"), format!("{k}: {name}"));
assert_eq!(format!("{}: {}", k, v), format!("{}: {}", k, name));
}
assert_eq!(inferencer.virtual_checks.len(), virtuals.len());
for ((a, b, _), (x, y)) in zip(inferencer.virtual_checks.iter(), virtuals) {
let a = inferencer.unifier.internal_stringify(
*a,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
let b = inferencer.unifier.internal_stringify(
*b,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
@ -659,14 +560,14 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
g = a // b
h = a % b
"},
&[("a", "int32"),
[("a", "int32"),
("b", "int32"),
("c", "int32"),
("d", "int32"),
("e", "int32"),
("f", "float"),
("g", "int32"),
("h", "int32")].into()
("h", "int32")].iter().cloned().collect()
; "int32")]
#[test_case(
indoc! {"
@ -682,7 +583,7 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
ii = 3
j = a ** b
"},
&[("a", "float"),
[("a", "float"),
("b", "float"),
("c", "float"),
("d", "float"),
@ -692,7 +593,7 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
("h", "float"),
("i", "float"),
("ii", "int32"),
("j", "float")].into()
("j", "float")].iter().cloned().collect()
; "float"
)]
#[test_case(
@ -710,7 +611,7 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
k = a < b
l = a != b
"},
&[("a", "int64"),
[("a", "int64"),
("b", "int64"),
("c", "int64"),
("d", "int64"),
@ -721,7 +622,7 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
("i", "bool"),
("j", "bool"),
("k", "bool"),
("l", "bool")].into()
("l", "bool")].iter().cloned().collect()
; "int64"
)]
#[test_case(
@ -732,23 +633,22 @@ fn test_basic(source: &str, mapping: &HashMap<&str, &str>, virtuals: &[(&str, &s
d = not a
e = a != b
"},
&[("a", "bool"),
[("a", "bool"),
("b", "bool"),
("c", "bool"),
("d", "bool"),
("e", "bool")].into()
("e", "bool")].iter().cloned().collect()
; "boolean"
)]
fn test_primitive_magic_methods(source: &str, mapping: &HashMap<&str, &str>) {
println!("source:\n{source}");
fn test_primitive_magic_methods(source: &str, mapping: HashMap<&str, &str>) {
println!("source:\n{}", source);
let mut env = TestEnvironment::basic_test_env();
let id_to_name = std::mem::take(&mut env.id_to_name);
let mut defined_identifiers: HashMap<_, _> =
env.identifier_mapping.keys().copied().map(|id| (id, IdentifierInfo::default())).collect();
defined_identifiers.insert("virtual".into(), IdentifierInfo::default());
let mut defined_identifiers: HashSet<_> = env.identifier_mapping.keys().cloned().collect();
defined_identifiers.insert("virtual".into());
let mut inferencer = env.get_inferencer();
inferencer.defined_identifiers.clone_from(&defined_identifiers);
let statements = parse_program(source, FileName::default()).unwrap();
inferencer.defined_identifiers = defined_identifiers.clone();
let statements = parse_program(source, Default::default()).unwrap();
let statements = statements
.into_iter()
.map(|v| inferencer.fold_stmt(v))
@ -757,23 +657,23 @@ fn test_primitive_magic_methods(source: &str, mapping: &HashMap<&str, &str>) {
inferencer.check_block(&statements, &mut defined_identifiers).unwrap();
for (k, v) in &inferencer.variable_mapping {
for (k, v) in inferencer.variable_mapping.iter() {
let name = inferencer.unifier.internal_stringify(
*v,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
println!("{k}: {name}");
println!("{}: {}", k, name);
}
for (k, v) in mapping {
for (k, v) in mapping.iter() {
let ty = inferencer.variable_mapping.get(&(*k).into()).unwrap();
let name = inferencer.unifier.internal_stringify(
*ty,
&mut |v| (*id_to_name.get(&v).unwrap()).into(),
&mut |v| format!("v{v}"),
&mut |v| format!("v{}", v),
&mut None,
);
assert_eq!(format!("{k}: {v}"), format!("{k}: {name}"));
assert_eq!(format!("{}: {}", k, v), format!("{}: {}", k, name));
}
}

1065
nac3core/src/typecheck/typedef/mod.rs
View File

File diff suppressed because it is too large Load Diff

351
nac3core/src/typecheck/typedef/test.rs
View File

@ -1,12 +1,10 @@
use std::collections::HashMap;
use super::super::magic_methods::with_fields;
use super::*;
use indoc::indoc;
use itertools::Itertools;
use std::collections::HashMap;
use test_case::test_case;
use super::*;
use crate::typecheck::magic_methods::with_fields;
impl Unifier {
/// Check whether two types are equal.
fn eq(&mut self, a: Type, b: Type) -> bool {
@ -30,32 +28,32 @@ impl Unifier {
TypeEnum::TVar { fields: Some(map1), .. },
TypeEnum::TVar { fields: Some(map2), .. },
) => self.map_eq2(map1, map2),
(
TypeEnum::TTuple { ty: ty1, is_vararg_ctx: false },
TypeEnum::TTuple { ty: ty2, is_vararg_ctx: false },
) => {
(TypeEnum::TTuple { ty: ty1 }, TypeEnum::TTuple { ty: ty2 }) => {
ty1.len() == ty2.len()
&& ty1.iter().zip(ty2.iter()).all(|(t1, t2)| self.eq(*t1, *t2))
}
(TypeEnum::TVirtual { ty: ty1 }, TypeEnum::TVirtual { ty: ty2 }) => self.eq(*ty1, *ty2),
(TypeEnum::TList { ty: ty1 }, TypeEnum::TList { ty: ty2 })
| (TypeEnum::TVirtual { ty: ty1 }, TypeEnum::TVirtual { ty: ty2 }) => {
self.eq(*ty1, *ty2)
}
(
TypeEnum::TObj { obj_id: id1, params: params1, .. },
TypeEnum::TObj { obj_id: id2, params: params2, .. },
) => id1 == id2 && self.map_eq(params1, params2),
// TLiteral, TCall and TFunc are not yet implemented
// TCall and TFunc are not yet implemented
_ => false,
}
}
fn map_eq<K>(&mut self, map1: &IndexMapping<K>, map2: &IndexMapping<K>) -> bool
fn map_eq<K>(&mut self, map1: &Mapping<K>, map2: &Mapping<K>) -> bool
where
K: std::hash::Hash + Eq + Clone,
K: std::hash::Hash + std::cmp::Eq + std::clone::Clone,
{
if map1.len() != map2.len() {
return false;
}
for (k, v) in map1 {
if !map2.get(k).is_some_and(|v1| self.eq(*v, *v1)) {
for (k, v) in map1.iter() {
if !map2.get(k).map(|v1| self.eq(*v, *v1)).unwrap_or(false) {
return false;
}
}
@ -64,13 +62,13 @@ impl Unifier {
fn map_eq2<K>(&mut self, map1: &Mapping<K, RecordField>, map2: &Mapping<K, RecordField>) -> bool
where
K: std::hash::Hash + Eq + Clone,
K: std::hash::Hash + std::cmp::Eq + std::clone::Clone,
{
if map1.len() != map2.len() {
return false;
}
for (k, v) in map1 {
if !map2.get(k).is_some_and(|v1| self.eq(v.ty, v1.ty)) {
for (k, v) in map1.iter() {
if !map2.get(k).map(|v1| self.eq(v.ty, v1.ty)).unwrap_or(false) {
return false;
}
}
@ -93,7 +91,7 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(0),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
}),
);
type_mapping.insert(
@ -101,7 +99,7 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(1),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
}),
);
type_mapping.insert(
@ -109,25 +107,16 @@ impl TestEnvironment {
unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(2),
fields: HashMap::new(),
params: VarMap::new(),
params: HashMap::new(),
}),
);
let tvar = unifier.get_dummy_var();
let (v0, id) = unifier.get_dummy_var();
type_mapping.insert(
"Foo".into(),
unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(3),
fields: [("a".into(), (tvar.ty, true))].into(),
params: into_var_map([tvar]),
}),
);
let tvar = unifier.get_dummy_var();
type_mapping.insert(
"list".into(),
unifier.add_ty(TypeEnum::TObj {
obj_id: PrimDef::List.id(),
fields: HashMap::new(),
params: into_var_map([tvar]),
fields: [("a".into(), (v0, true))].iter().cloned().collect::<HashMap<_, _>>(),
params: [(id, v0)].iter().cloned().collect::<HashMap<_, _>>(),
}),
);
@ -140,54 +129,34 @@ impl TestEnvironment {
result.0
}
fn internal_parse<'b>(&mut self, typ: &'b str, mapping: &Mapping<String>) -> (Type, &'b str) {
fn internal_parse<'a, 'b>(
&'a mut self,
typ: &'b str,
mapping: &Mapping<String>,
) -> (Type, &'b str) {
// for testing only, so we can just panic when the input is malformed
let end = typ.find(|c| ['[', ',', ']', '='].contains(&c)).unwrap_or(typ.len());
let end = typ.find(|c| ['[', ',', ']', '='].contains(&c)).unwrap_or_else(|| typ.len());
match &typ[..end] {
"list" => {
let mut s = &typ[end..];
assert_eq!(&s[0..1], "[");
let mut ty = Vec::new();
while &s[0..1] != "]" {
let result = self.internal_parse(&s[1..], mapping);
ty.push(result.0);
s = result.1;
}
assert_eq!(ty.len(), 1);
let list_elem_tvar = if let TypeEnum::TObj { params, .. } =
&*self.unifier.get_ty_immutable(self.type_mapping["list"])
{
iter_type_vars(params).next().unwrap()
} else {
unreachable!()
};
(
self.unifier
.subst(
self.type_mapping["list"],
&into_var_map([TypeVar { id: list_elem_tvar.id, ty: ty[0] }]),
)
.unwrap(),
&s[1..],
)
}
"tuple" => {
let mut s = &typ[end..];
assert_eq!(&s[0..1], "[");
assert!(&s[0..1] == "[");
let mut ty = Vec::new();
while &s[0..1] != "]" {
let result = self.internal_parse(&s[1..], mapping);
ty.push(result.0);
s = result.1;
}
(self.unifier.add_ty(TypeEnum::TTuple { ty, is_vararg_ctx: false }), &s[1..])
(self.unifier.add_ty(TypeEnum::TTuple { ty }), &s[1..])
}
"list" => {
assert!(&typ[end..end + 1] == "[");
let (ty, s) = self.internal_parse(&typ[end + 1..], mapping);
assert!(&s[0..1] == "]");
(self.unifier.add_ty(TypeEnum::TList { ty }), &s[1..])
}
"Record" => {
let mut s = &typ[end..];
assert_eq!(&s[0..1], "[");
assert!(&s[0..1] == "[");
let mut fields = HashMap::new();
while &s[0..1] != "]" {
let eq = s.find('=').unwrap();
@ -200,14 +169,14 @@ impl TestEnvironment {
}
x => {
let mut s = &typ[end..];
let ty = mapping.get(x).copied().unwrap_or_else(|| {
let ty = mapping.get(x).cloned().unwrap_or_else(|| {
// mapping should be type variables, type_mapping should be concrete types
// we should not resolve the type of type variables.
let mut ty = *self.type_mapping.get(x).unwrap();
let te = self.unifier.get_ty(ty);
if let TypeEnum::TObj { params, .. } = &*te {
if let TypeEnum::TObj { params, .. } = &*te.as_ref() {
if !params.is_empty() {
assert_eq!(&s[0..1], "[");
assert!(&s[0..1] == "[");
let mut p = Vec::new();
while &s[0..1] != "]" {
let result = self.internal_parse(&s[1..], mapping);
@ -217,7 +186,7 @@ impl TestEnvironment {
s = &s[1..];
ty = self
.unifier
.subst(ty, &params.keys().copied().zip(p).collect())
.subst(ty, &params.keys().cloned().zip(p.into_iter()).collect())
.unwrap_or(ty);
}
}
@ -281,12 +250,12 @@ fn test_unify(
let mut mapping = HashMap::new();
for i in 1..=variable_count {
let v = env.unifier.get_dummy_var();
mapping.insert(format!("v{i}"), v.ty);
mapping.insert(format!("v{}", i), v.0);
}
// unification may have side effect when we do type resolution, so freeze the types
// before doing unification.
let mut pairs = Vec::new();
for (a, b) in &perm {
for (a, b) in perm.iter() {
let t1 = env.parse(a, &mapping);
let t2 = env.parse(b, &mapping);
pairs.push((t1, t2));
@ -294,8 +263,8 @@ fn test_unify(
for (t1, t2) in pairs {
env.unifier.unify(t1, t2).unwrap();
}
for (a, b) in verify_pairs {
println!("{a} = {b}");
for (a, b) in verify_pairs.iter() {
println!("{} = {}", a, b);
let t1 = env.parse(a, &mapping);
let t2 = env.parse(b, &mapping);
println!("a = {}, b = {}", env.unifier.stringify(t1), env.unifier.stringify(t2));
@ -309,7 +278,7 @@ fn test_unify(
("v1", "tuple[int]"),
("v2", "list[int]"),
],
(("v1", "v2"), "Incompatible types: 11[0] and tuple[0]")
(("v1", "v2"), "Incompatible types: list[0] and tuple[0]")
; "type mismatch"
)]
#[test_case(2,
@ -317,7 +286,7 @@ fn test_unify(
("v1", "tuple[int]"),
("v2", "tuple[float]"),
],
(("v1", "v2"), "Incompatible types: tuple[0] and tuple[1]")
(("v1", "v2"), "Incompatible types: 0 and 1")
; "tuple parameter mismatch"
)]
#[test_case(2,
@ -333,35 +302,35 @@ fn test_unify(
("v1", "Record[a=float,b=int]"),
("v2", "Foo[v3]"),
],
(("v1", "v2"), "`3[typevar5]::b` field/method does not exist")
(("v1", "v2"), "`3[var4]::b` field/method does not exist")
; "record obj merge"
)]
/// Test cases for invalid unifications.
fn test_invalid_unification(
variable_count: u32,
unify_pairs: &[(&'static str, &'static str)],
erroneous_pair: ((&'static str, &'static str), &'static str),
errornous_pair: ((&'static str, &'static str), &'static str),
) {
let mut env = TestEnvironment::new();
let mut mapping = HashMap::new();
for i in 1..=variable_count {
let v = env.unifier.get_dummy_var();
mapping.insert(format!("v{i}"), v.ty);
mapping.insert(format!("v{}", i), v.0);
}
// unification may have side effect when we do type resolution, so freeze the types
// before doing unification.
let mut pairs = Vec::new();
for (a, b) in unify_pairs {
for (a, b) in unify_pairs.iter() {
let t1 = env.parse(a, &mapping);
let t2 = env.parse(b, &mapping);
pairs.push((t1, t2));
}
let (t1, t2) =
(env.parse(erroneous_pair.0 .0, &mapping), env.parse(erroneous_pair.0 .1, &mapping));
(env.parse(errornous_pair.0 .0, &mapping), env.parse(errornous_pair.0 .1, &mapping));
for (a, b) in pairs {
env.unifier.unify(a, b).unwrap();
}
assert_eq!(env.unify(t1, t2), Err(erroneous_pair.1.to_string()));
assert_eq!(env.unify(t1, t2), Err(errornous_pair.1.to_string()));
}
#[test]
@ -370,17 +339,23 @@ fn test_recursive_subst() {
let int = *env.type_mapping.get("int").unwrap();
let foo_id = *env.type_mapping.get("Foo").unwrap();
let foo_ty = env.unifier.get_ty(foo_id);
let mapping: HashMap<_, _>;
with_fields(&mut env.unifier, foo_id, |_unifier, fields| {
fields.insert("rec".into(), (foo_id, true));
});
let TypeEnum::TObj { params, .. } = &*foo_ty else { unreachable!() };
let mapping = params.iter().map(|(id, _)| (*id, int)).collect();
if let TypeEnum::TObj { params, .. } = &*foo_ty {
mapping = params.iter().map(|(id, _)| (*id, int)).collect();
} else {
unreachable!()
}
let instantiated = env.unifier.subst(foo_id, &mapping).unwrap();
let instantiated_ty = env.unifier.get_ty(instantiated);
let TypeEnum::TObj { fields, .. } = &*instantiated_ty else { unreachable!() };
assert!(env.unifier.unioned(fields.get(&"a".into()).unwrap().0, int));
assert!(env.unifier.unioned(fields.get(&"rec".into()).unwrap().0, instantiated));
if let TypeEnum::TObj { fields, .. } = &*instantiated_ty {
assert!(env.unifier.unioned(fields.get(&"a".into()).unwrap().0, int));
assert!(env.unifier.unioned(fields.get(&"rec".into()).unwrap().0, instantiated));
} else {
unreachable!()
}
}
#[test]
@ -390,27 +365,36 @@ fn test_virtual() {
let fun = env.unifier.add_ty(TypeEnum::TFunc(FunSignature {
args: vec![],
ret: int,
vars: VarMap::new(),
vars: HashMap::new(),
}));
let bar = env.unifier.add_ty(TypeEnum::TObj {
obj_id: DefinitionId(5),
fields: [("f".into(), (fun, false)), ("a".into(), (int, false))].into(),
params: VarMap::new(),
fields: [("f".into(), (fun, false)), ("a".into(), (int, false))]
.iter()
.cloned()
.collect::<HashMap<StrRef, _>>(),
params: HashMap::new(),
});
let v0 = env.unifier.get_dummy_var().ty;
let v1 = env.unifier.get_dummy_var().ty;
let v0 = env.unifier.get_dummy_var().0;
let v1 = env.unifier.get_dummy_var().0;
let a = env.unifier.add_ty(TypeEnum::TVirtual { ty: bar });
let b = env.unifier.add_ty(TypeEnum::TVirtual { ty: v0 });
let c = env.unifier.add_record([("f".into(), RecordField::new(v1, false, None))].into());
let c = env
.unifier
.add_record([("f".into(), RecordField::new(v1, false, None))].iter().cloned().collect());
env.unifier.unify(a, b).unwrap();
env.unifier.unify(b, c).unwrap();
assert!(env.unifier.eq(v1, fun));
let d = env.unifier.add_record([("a".into(), RecordField::new(v1, true, None))].into());
let d = env
.unifier
.add_record([("a".into(), RecordField::new(v1, true, None))].iter().cloned().collect());
assert_eq!(env.unify(b, d), Err("`virtual[5]::a` field/method does not exist".to_string()));
let d = env.unifier.add_record([("b".into(), RecordField::new(v1, true, None))].into());
let d = env
.unifier
.add_record([("b".into(), RecordField::new(v1, true, None))].iter().cloned().collect());
assert_eq!(env.unify(b, d), Err("`virtual[5]::b` field/method does not exist".to_string()));
}
@ -423,132 +407,85 @@ fn test_typevar_range() {
let int_list = env.parse("list[int]", &HashMap::new());
let float_list = env.parse("list[float]", &HashMap::new());
let list_elem_tvar = if let TypeEnum::TObj { params, .. } =
&*env.unifier.get_ty_immutable(env.type_mapping["list"])
{
iter_type_vars(params).next().unwrap()
} else {
unreachable!()
};
// unification between v and int
// where v in (int, bool)
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).0;
env.unifier.unify(int, v).unwrap();
// unification between v and list[int]
// where v in (int, bool)
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).0;
assert_eq!(
env.unify(int_list, v),
Err("Expected any one of these types: 0, 2, but got 11[0]".to_string())
Err("Expected any one of these types: 0, 2, but got list[0]".to_string())
);
// unification between v and float
// where v in (int, bool)
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).0;
assert_eq!(
env.unify(float, v),
Err("Expected any one of these types: 0, 2, but got 1".to_string())
);
let v1 = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).ty;
let v1_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: v1 }]),
});
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).ty;
let v1 = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).0;
let v1_list = env.unifier.add_ty(TypeEnum::TList { ty: v1 });
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).0;
// unification between v and int
// where v in (int, list[v1]), v1 in (int, bool)
env.unifier.unify(int, v).unwrap();
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).0;
// unification between v and list[int]
// where v in (int, list[v1]), v1 in (int, bool)
env.unifier.unify(int_list, v).unwrap();
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, v1_list], None, None).0;
// unification between v and list[float]
// where v in (int, list[v1]), v1 in (int, bool)
println!("float_list: {}, v: {}", env.unifier.stringify(float_list), env.unifier.stringify(v));
assert_eq!(
env.unify(float_list, v),
Err("Expected any one of these types: 0, 11[typevar6], but got 11[1]\n\nNotes:\n typevar6 ∈ {0, 2}".to_string())
Err("Expected any one of these types: 0, list[var5], but got list[1]\n\nNotes:\n var5 ∈ {0, 2}".to_string())
);
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).ty;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).ty;
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).0;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).0;
env.unifier.unify(a, b).unwrap();
env.unifier.unify(a, float).unwrap();
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).ty;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).ty;
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).0;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).0;
env.unifier.unify(a, b).unwrap();
assert_eq!(env.unify(a, int), Err("Expected any one of these types: 1, but got 0".into()));
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).ty;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).ty;
let a_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: a }]),
});
let a_list = env.unifier.get_fresh_var_with_range(&[a_list], None, None).ty;
let b_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: b }]),
});
let b_list = env.unifier.get_fresh_var_with_range(&[b_list], None, None).ty;
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).0;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).0;
let a_list = env.unifier.add_ty(TypeEnum::TList { ty: a });
let a_list = env.unifier.get_fresh_var_with_range(&[a_list], None, None).0;
let b_list = env.unifier.add_ty(TypeEnum::TList { ty: b });
let b_list = env.unifier.get_fresh_var_with_range(&[b_list], None, None).0;
env.unifier.unify(a_list, b_list).unwrap();
let float_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: float }]),
});
let float_list = env.unifier.add_ty(TypeEnum::TList { ty: float });
env.unifier.unify(a_list, float_list).unwrap();
// previous unifications should not affect a and b
env.unifier.unify(a, int).unwrap();
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).ty;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).ty;
let a_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: a }]),
});
let b_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: b }]),
});
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).0;
let b = env.unifier.get_fresh_var_with_range(&[boolean, float], None, None).0;
let a_list = env.unifier.add_ty(TypeEnum::TList { ty: a });
let b_list = env.unifier.add_ty(TypeEnum::TList { ty: b });
env.unifier.unify(a_list, b_list).unwrap();
let int_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: int }]),
});
let int_list = env.unifier.add_ty(TypeEnum::TList { ty: int });
assert_eq!(
env.unify(a_list, int_list),
Err("Incompatible types: 11[typevar23] and 11[0]\
\n\nNotes:\n typevar23 ∈ {1}"
.into())
Err("Expected any one of these types: 1, but got 0".into())
);
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).ty;
let b = env.unifier.get_dummy_var().ty;
let a_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: a }]),
});
let a_list = env.unifier.get_fresh_var_with_range(&[a_list], None, None).ty;
let b_list = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: b }]),
});
let a = env.unifier.get_fresh_var_with_range(&[int, float], None, None).0;
let b = env.unifier.get_dummy_var().0;
let a_list = env.unifier.add_ty(TypeEnum::TList { ty: a });
let a_list = env.unifier.get_fresh_var_with_range(&[a_list], None, None).0;
let b_list = env.unifier.add_ty(TypeEnum::TList { ty: b });
env.unifier.unify(a_list, b_list).unwrap();
assert_eq!(
env.unify(b, boolean),
@ -559,29 +496,17 @@ fn test_typevar_range() {
#[test]
fn test_rigid_var() {
let mut env = TestEnvironment::new();
let a = env.unifier.get_fresh_rigid_var(None, None).ty;
let b = env.unifier.get_fresh_rigid_var(None, None).ty;
let x = env.unifier.get_dummy_var().ty;
let list_elem_tvar = env.unifier.get_fresh_var(Some("list_elem".into()), None);
let list_a = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: a }]),
});
let list_x = env.unifier.add_ty(TypeEnum::TObj {
obj_id: env.type_mapping["list"].obj_id(&env.unifier).unwrap(),
fields: Mapping::default(),
params: into_var_map([TypeVar { id: list_elem_tvar.id, ty: x }]),
});
let a = env.unifier.get_fresh_rigid_var(None, None).0;
let b = env.unifier.get_fresh_rigid_var(None, None).0;
let x = env.unifier.get_dummy_var().0;
let list_a = env.unifier.add_ty(TypeEnum::TList { ty: a });
let list_x = env.unifier.add_ty(TypeEnum::TList { ty: x });
let int = env.parse("int", &HashMap::new());
let list_int = env.parse("list[int]", &HashMap::new());
assert_eq!(env.unify(a, b), Err("Incompatible types: typevar4 and typevar3".to_string()));
assert_eq!(env.unify(a, b), Err("Incompatible types: var3 and var2".to_string()));
env.unifier.unify(list_a, list_x).unwrap();
assert_eq!(
env.unify(list_x, list_int),
Err("Incompatible types: 11[typevar3] and 11[0]".to_string())
);
assert_eq!(env.unify(list_x, list_int), Err("Incompatible types: 0 and var2".to_string()));
env.unifier.replace_rigid_var(a, int);
env.unifier.unify(list_x, list_int).unwrap();
@ -595,26 +520,16 @@ fn test_instantiation() {
let float = env.parse("float", &HashMap::new());
let list_int = env.parse("list[int]", &HashMap::new());
let list_elem_tvar = if let TypeEnum::TObj { params, .. } =
&*env.unifier.get_ty_immutable(env.type_mapping["list"])
{
iter_type_vars(params).next().unwrap()
} else {
unreachable!()
};
let obj_map: HashMap<_, _> =
[(0usize, "int"), (1, "float"), (2, "bool")].iter().cloned().collect();
let obj_map: HashMap<_, _> = [(0usize, "int"), (1, "float"), (2, "bool"), (11, "list")].into();
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).ty;
let list_v = env
.unifier
.subst(env.type_mapping["list"], &into_var_map([TypeVar { id: list_elem_tvar.id, ty: v }]))
.unwrap();
let v1 = env.unifier.get_fresh_var_with_range(&[list_v, int], None, None).ty;
let v2 = env.unifier.get_fresh_var_with_range(&[list_int, float], None, None).ty;
let t = env.unifier.get_dummy_var().ty;
let tuple = env.unifier.add_ty(TypeEnum::TTuple { ty: vec![v, v1, v2], is_vararg_ctx: false });
let v3 = env.unifier.get_fresh_var_with_range(&[tuple, t], None, None).ty;
let v = env.unifier.get_fresh_var_with_range(&[int, boolean], None, None).0;
let list_v = env.unifier.add_ty(TypeEnum::TList { ty: v });
let v1 = env.unifier.get_fresh_var_with_range(&[list_v, int], None, None).0;
let v2 = env.unifier.get_fresh_var_with_range(&[list_int, float], None, None).0;
let t = env.unifier.get_dummy_var().0;
let tuple = env.unifier.add_ty(TypeEnum::TTuple { ty: vec![v, v1, v2] });
let v3 = env.unifier.get_fresh_var_with_range(&[tuple, t], None, None).0;
// t = TypeVar('t')
// v = TypeVar('v', int, bool)
// v1 = TypeVar('v1', 'list[v]', int)
@ -636,7 +551,7 @@ fn test_instantiation() {
tuple[int, list[bool], list[int]]
tuple[int, list[int], float]
tuple[int, list[int], list[int]]
v6"
v5"
}
.split('\n')
.collect_vec();
@ -645,8 +560,8 @@ fn test_instantiation() {
.map(|ty| {
env.unifier.internal_stringify(
*ty,
&mut |i| (*obj_map.get(&i).unwrap()).to_string(),
&mut |i| format!("v{i}"),
&mut |i| obj_map.get(&i).unwrap().to_string(),
&mut |i| format!("v{}", i),
&mut None,
)
})

59
nac3core/src/typecheck/unification_table.rs
View File

@ -16,10 +16,21 @@ pub struct UnificationTable<V> {
#[derive(Clone, Debug)]
enum Action<V> {
Parent { key: usize, original_parent: usize },
Value { key: usize, original_value: Option<V> },
Rank { key: usize, original_rank: u32 },
Marker { generation: u32 },
Parent {
key: usize,
original_parent: usize,
},
Value {
key: usize,
original_value: Option<V>,
},
Rank {
key: usize,
original_rank: u32,
},
Marker {
generation: u32,
}
}
impl<V> Default for UnificationTable<V> {
@ -30,13 +41,7 @@ impl<V> Default for UnificationTable<V> {
impl<V> UnificationTable<V> {
pub fn new() -> UnificationTable<V> {
UnificationTable {
parents: Vec::new(),
ranks: Vec::new(),
values: Vec::new(),
log: Vec::new(),
generation: 0,
}
UnificationTable { parents: Vec::new(), ranks: Vec::new(), values: Vec::new(), log: Vec::new(), generation: 0 }
}
pub fn new_key(&mut self, v: V) -> UnificationKey {
@ -56,7 +61,7 @@ impl<V> UnificationTable<V> {
if self.ranks[a] < self.ranks[b] {
std::mem::swap(&mut a, &mut b);
}
self.log.push(Action::Parent { key: b, original_parent: self.parents[b] });
self.log.push(Action::Parent { key: b, original_parent: a });
self.parents[b] = a;
if self.ranks[a] == self.ranks[b] {
self.log.push(Action::Rank { key: a, original_rank: self.ranks[a] });
@ -101,7 +106,7 @@ impl<V> UnificationTable<V> {
// a = parent.parent
let a = self.parents[parent];
// root.parent = parent.parent
self.log.push(Action::Parent { key: root, original_parent: self.parents[root] });
self.log.push(Action::Parent { key: root, original_parent: a });
self.parents[root] = a;
root = parent;
// parent = root.parent
@ -120,10 +125,7 @@ impl<V> UnificationTable<V> {
pub fn restore_snapshot(&mut self, snapshot: (usize, u32)) {
let (log_len, generation) = snapshot;
assert!(self.log.len() >= log_len, "snapshot restoration error");
assert!(
matches!(self.log[log_len - 1], Action::Marker { generation: gen } if gen == generation),
"snapshot restoration error"
);
assert!(matches!(self.log[log_len - 1], Action::Marker { generation: gen } if gen == generation), "snapshot restoration error");
for action in self.log.drain(log_len - 1..).rev() {
match action {
Action::Parent { key, original_parent } => {
@ -143,11 +145,8 @@ impl<V> UnificationTable<V> {
pub fn discard_snapshot(&mut self, snapshot: (usize, u32)) {
let (log_len, generation) = snapshot;
assert!(self.log.len() >= log_len, "snapshot discard error");
assert!(
matches!(self.log[log_len - 1], Action::Marker { generation: gen } if gen == generation),
"snapshot discard error"
);
self.log.clear();
assert!(matches!(self.log[log_len - 1], Action::Marker { generation: gen } if generation == gen), "snapshot discard error");
self.log.truncate(log_len - 1);
}
}
@ -160,23 +159,11 @@ where
.enumerate()
.map(|(i, (v, p))| if *p == i { v.as_ref().map(|v| v.as_ref().clone()) } else { None })
.collect();
UnificationTable {
parents: self.parents.clone(),
ranks: self.ranks.clone(),
values,
log: Vec::new(),
generation: 0,
}
UnificationTable { parents: self.parents.clone(), ranks: self.ranks.clone(), values, log: Vec::new(), generation: 0 }
}
pub fn from_send(table: &UnificationTable<V>) -> UnificationTable<Rc<V>> {
let values = table.values.iter().cloned().map(|v| v.map(Rc::new)).collect();
UnificationTable {
parents: table.parents.clone(),
ranks: table.ranks.clone(),
values,
log: Vec::new(),
generation: 0,
}
UnificationTable { parents: table.parents.clone(), ranks: table.ranks.clone(), values, log: Vec::new(), generation: 0 }
}
}

8
nac3ld/Cargo.toml
View File

@ -1,8 +0,0 @@
[package]
name = "nac3ld"
version = "0.1.0"
authors = ["M-Labs"]
edition = "2021"
[dependencies]
byteorder = { version = "1.5", default-features = false }

509
nac3ld/src/dwarf.rs
View File

@ -1,509 +0,0 @@
#![allow(non_camel_case_types, non_upper_case_globals)]
use std::mem;
use byteorder::{ByteOrder, LittleEndian};
pub const DW_EH_PE_omit: u8 = 0xFF;
pub const DW_EH_PE_absptr: u8 = 0x00;
pub const DW_EH_PE_uleb128: u8 = 0x01;
pub const DW_EH_PE_udata2: u8 = 0x02;
pub const DW_EH_PE_udata4: u8 = 0x03;
pub const DW_EH_PE_udata8: u8 = 0x04;
pub const DW_EH_PE_sleb128: u8 = 0x09;
pub const DW_EH_PE_sdata2: u8 = 0x0A;
pub const DW_EH_PE_sdata4: u8 = 0x0B;
pub const DW_EH_PE_sdata8: u8 = 0x0C;
pub const DW_EH_PE_pcrel: u8 = 0x10;
pub const DW_EH_PE_textrel: u8 = 0x20;
pub const DW_EH_PE_datarel: u8 = 0x30;
pub const DW_EH_PE_funcrel: u8 = 0x40;
pub const DW_EH_PE_aligned: u8 = 0x50;
pub const DW_EH_PE_indirect: u8 = 0x80;
pub struct DwarfReader<'a> {
pub slice: &'a [u8],
pub virt_addr: u32,
base_slice: &'a [u8],
base_virt_addr: u32,
}
impl<'a> DwarfReader<'a> {
pub fn new(slice: &[u8], virt_addr: u32) -> DwarfReader {
DwarfReader { slice, virt_addr, base_slice: slice, base_virt_addr: virt_addr }
}
/// Creates a new instance from another instance of [DwarfReader], optionally removing any
/// offsets previously applied to the other instance.
pub fn from_reader(other: &DwarfReader<'a>, reset_offset: bool) -> DwarfReader<'a> {
if reset_offset {
DwarfReader::new(other.base_slice, other.base_virt_addr)
} else {
DwarfReader::new(other.slice, other.virt_addr)
}
}
pub fn offset(&mut self, offset: u32) {
self.slice = &self.slice[offset as usize..];
self.virt_addr = self.virt_addr.wrapping_add(offset);
}
/// ULEB128 and SLEB128 encodings are defined in Section 7.6 - "Variable Length Data" of the
/// [DWARF-4 Manual](https://dwarfstd.org/doc/DWARF4.pdf).
pub fn read_uleb128(&mut self) -> u64 {
let mut shift: usize = 0;
let mut result: u64 = 0;
let mut byte: u8;
loop {
byte = self.read_u8();
result |= u64::from(byte & 0x7F) << shift;
shift += 7;
if byte & 0x80 == 0 {
break;
}
}
result
}
pub fn read_sleb128(&mut self) -> i64 {
let mut shift: u32 = 0;
let mut result: u64 = 0;
let mut byte: u8;
loop {
byte = self.read_u8();
result |= u64::from(byte & 0x7F) << shift;
shift += 7;
if byte & 0x80 == 0 {
break;
}
}
// sign-extend
if shift < u64::BITS && (byte & 0x40) != 0 {
result |= (!0u64) << shift;
}
result as i64
}
pub fn read_u8(&mut self) -> u8 {
let val = self.slice[0];
self.slice = &self.slice[1..];
val
}
}
macro_rules! impl_read_fn {
( $($type: ty, $byteorder_fn: ident);* ) => {
impl<'a> DwarfReader<'a> {
$(
pub fn $byteorder_fn(&mut self) -> $type {
let val = LittleEndian::$byteorder_fn(self.slice);
self.slice = &self.slice[mem::size_of::<$type>()..];
val
}
)*
}
}
}
impl_read_fn!(
u16, read_u16;
u32, read_u32;
u64, read_u64;
i16, read_i16;
i32, read_i32;
i64, read_i64
);
pub struct DwarfWriter<'a> {
pub slice: &'a mut [u8],
pub offset: usize,
}
impl<'a> DwarfWriter<'a> {
pub fn new(slice: &mut [u8]) -> DwarfWriter {
DwarfWriter { slice, offset: 0 }
}
pub fn write_u8(&mut self, data: u8) {
self.slice[self.offset] = data;
self.offset += 1;
}
pub fn write_u32(&mut self, data: u32) {
LittleEndian::write_u32(&mut self.slice[self.offset..], data);
self.offset += 4;
}
}
fn read_encoded_pointer(reader: &mut DwarfReader, encoding: u8) -> Result<usize, ()> {
if encoding == DW_EH_PE_omit {
return Err(());
}
// DW_EH_PE_aligned implies it's an absolute pointer value
// However, we are linking library for 32-bits architecture
// The size of variable should be 4 bytes instead
if encoding == DW_EH_PE_aligned {
let shifted_virt_addr = round_up(reader.virt_addr as usize, mem::size_of::<u32>())?;
let addr_inc = shifted_virt_addr - reader.virt_addr as usize;
reader.slice = &reader.slice[addr_inc..];
reader.virt_addr = shifted_virt_addr as u32;
return Ok(reader.read_u32() as usize);
}
match encoding & 0x0F {
DW_EH_PE_absptr | DW_EH_PE_udata4 => Ok(reader.read_u32() as usize),
DW_EH_PE_uleb128 => Ok(reader.read_uleb128() as usize),
DW_EH_PE_udata2 => Ok(reader.read_u16() as usize),
DW_EH_PE_udata8 => Ok(reader.read_u64() as usize),
DW_EH_PE_sleb128 => Ok(reader.read_sleb128() as usize),
DW_EH_PE_sdata2 => Ok(reader.read_i16() as usize),
DW_EH_PE_sdata4 => Ok(reader.read_i32() as usize),
DW_EH_PE_sdata8 => Ok(reader.read_i64() as usize),
_ => Err(()),
}
}
fn read_encoded_pointer_with_pc(reader: &mut DwarfReader, encoding: u8) -> Result<usize, ()> {
let entry_virt_addr = reader.virt_addr;
let mut result = read_encoded_pointer(reader, encoding)?;
// DW_EH_PE_aligned implies it's an absolute pointer value
if encoding == DW_EH_PE_aligned {
return Ok(result);
}
result = match encoding & 0x70 {
DW_EH_PE_pcrel => result.wrapping_add(entry_virt_addr as usize),
// .eh_frame normally would not have these kinds of relocations
// These would not be supported by a dedicated linker relocation schemes for RISC-V
DW_EH_PE_textrel | DW_EH_PE_datarel | DW_EH_PE_funcrel | DW_EH_PE_aligned => {
unimplemented!()
}
// Other values should be impossible
_ => unreachable!(),
};
if encoding & DW_EH_PE_indirect != 0 {
// There should not be a need for indirect addressing, as assembly code from
// the dynamic library should not be freely moved relative to the EH frame.
unreachable!()
}
Ok(result)
}
#[inline]
fn round_up(unrounded: usize, align: usize) -> Result<usize, ()> {
if align.is_power_of_two() {
Ok((unrounded + align - 1) & !(align - 1))
} else {
Err(())
}
}
/// Minimalistic structure to store everything needed for parsing FDEs to synthesize `.eh_frame_hdr`
/// section.
///
/// Refer to [The Linux Standard Base Core Specification, Generic Part](https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html)
/// for more information.
pub struct EH_Frame<'a> {
reader: DwarfReader<'a>,
}
impl<'a> EH_Frame<'a> {
/// Creates an [EH_Frame] using the bytes in the `.eh_frame` section and its address in the ELF
/// file.
pub fn new(eh_frame_slice: &[u8], eh_frame_addr: u32) -> EH_Frame {
EH_Frame { reader: DwarfReader::new(eh_frame_slice, eh_frame_addr) }
}
/// Returns an [Iterator] over all Call Frame Information (CFI) records.
pub fn cfi_records(&self) -> CFI_Records<'a> {
let reader = DwarfReader::from_reader(&self.reader, true);
let len = reader.slice.len();
CFI_Records { reader, available: len }
}
}
/// A single Call Frame Information (CFI) record.
///
/// From the [specification](https://refspecs.linuxfoundation.org/LSB_5.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html):
///
/// > Each CFI record contains a Common Information Entry (CIE) record followed by 1 or more Frame
/// > Description Entry (FDE) records.
pub struct CFI_Record<'a> {
// It refers to the augmentation data that corresponds to 'R' in the augmentation string
fde_pointer_encoding: u8,
fde_reader: DwarfReader<'a>,
}
impl<'a> CFI_Record<'a> {
pub fn from_reader(cie_reader: &mut DwarfReader<'a>) -> Result<CFI_Record<'a>, ()> {
let length = cie_reader.read_u32();
let fde_reader = match length {
// eh_frame with 0 lengths means the CIE is terminated
0 => panic!("Cannot create an EH_Frame from a termination CIE"),
// length == u32::MAX means that the length is only representable with 64 bits,
// which does not make sense in a system with 32-bit address.
0xFFFF_FFFF => unimplemented!(),
_ => {
let mut fde_reader = DwarfReader::from_reader(cie_reader, false);
fde_reader.offset(length);
fde_reader
}
};
// Routine check on the .eh_frame well-formness, in terms of CIE ID & Version args.
let cie_ptr = cie_reader.read_u32();
assert_eq!(cie_ptr, 0);
assert_eq!(cie_reader.read_u8(), 1);
// Parse augmentation string
// The first character must be 'z', there is no way to proceed otherwise
assert_eq!(cie_reader.read_u8(), b'z');
// Establish a pointer that skips ahead of the string
// Skip code/data alignment factors & return address register along the way as well
// We only tackle the case where 'z' and 'R' are part of the augmentation string, otherwise
// we cannot get the addresses to make .eh_frame_hdr
let mut aug_data_reader = DwarfReader::from_reader(cie_reader, false);
let mut aug_str_len = 0;
loop {
if aug_data_reader.read_u8() == b'\0' {
break;
}
aug_str_len += 1;
}
if aug_str_len == 0 {
unimplemented!();
}
aug_data_reader.read_uleb128(); // Code alignment factor
aug_data_reader.read_sleb128(); // Data alignment factor
aug_data_reader.read_uleb128(); // Return address register
aug_data_reader.read_uleb128(); // Augmentation data length
let mut fde_pointer_encoding = DW_EH_PE_omit;
for _ in 0..aug_str_len {
match cie_reader.read_u8() {
b'L' => {
aug_data_reader.read_u8();
}
b'P' => {
let encoding = aug_data_reader.read_u8();
read_encoded_pointer(&mut aug_data_reader, encoding)?;
}
b'R' => {
fde_pointer_encoding = aug_data_reader.read_u8();
}
// Other characters are not supported
_ => unimplemented!(),
}
}
assert_ne!(fde_pointer_encoding, DW_EH_PE_omit);
Ok(CFI_Record { fde_pointer_encoding, fde_reader })
}
/// Returns a [DwarfReader] initialized to the first Frame Description Entry (FDE) of this CFI
/// record.
pub fn get_fde_reader(&self) -> DwarfReader<'a> {
DwarfReader::from_reader(&self.fde_reader, true)
}
/// Returns an [Iterator] over all Frame Description Entries (FDEs).
pub fn fde_records(&self) -> FDE_Records<'a> {
let reader = self.get_fde_reader();
let len = reader.slice.len();
FDE_Records { pointer_encoding: self.fde_pointer_encoding, reader, available: len }
}
}
/// [Iterator] over Call Frame Information (CFI) records in an
/// [Exception Handling (EH) frame][EH_Frame].
pub struct CFI_Records<'a> {
reader: DwarfReader<'a>,
available: usize,
}
impl<'a> Iterator for CFI_Records<'a> {
type Item = CFI_Record<'a>;
fn next(&mut self) -> Option<Self::Item> {
loop {
if self.available == 0 {
return None;
}
let mut this_reader = DwarfReader::from_reader(&self.reader, false);
// Remove the length of the header and the content from the counter
let length = self.reader.read_u32();
let length = match length {
// eh_frame with 0-length means the CIE is terminated
0 => return None,
0xFFFF_FFFF => unimplemented!("CIE entries larger than 4 bytes not supported"),
other => other,
} as usize;
// Remove the length of the header and the content from the counter
self.available -= length + mem::size_of::<u32>();
let mut next_reader = DwarfReader::from_reader(&self.reader, false);
next_reader.offset(length as u32);
let cie_ptr = self.reader.read_u32();
self.reader = next_reader;
// Skip this record if it is a FDE
if cie_ptr == 0 {
// Rewind back to the start of the CFI Record
return Some(CFI_Record::from_reader(&mut this_reader).ok().unwrap());
}
}
}
}
/// [Iterator] over Frame Description Entries (FDEs) in an
/// [Exception Handling (EH) frame][EH_Frame].
pub struct FDE_Records<'a> {
pointer_encoding: u8,
reader: DwarfReader<'a>,
available: usize,
}
impl<'a> Iterator for FDE_Records<'a> {
type Item = (u32, u32);
fn next(&mut self) -> Option<Self::Item> {
// Parse each FDE to obtain the starting address that the FDE applies to
// Send the FDE offset and the mentioned address to a callback that write up the
// .eh_frame_hdr section
if self.available == 0 {
return None;
}
// Remove the length of the header and the content from the counter
let length = match self.reader.read_u32() {
// eh_frame with 0-length means the CIE is terminated
0 => return None,
0xFFFF_FFFF => unimplemented!("CIE entries larger than 4 bytes not supported"),
other => other,
} as usize;
// Remove the length of the header and the content from the counter
self.available -= length + mem::size_of::<u32>();
let mut next_fde_reader = DwarfReader::from_reader(&self.reader, false);
next_fde_reader.offset(length as u32);
let cie_ptr = self.reader.read_u32();
let next_val = if cie_ptr != 0 {
let pc_begin = read_encoded_pointer_with_pc(&mut self.reader, self.pointer_encoding)
.expect("Failed to read PC Begin");
Some((pc_begin as u32, self.reader.virt_addr))
} else {
None
};
self.reader = next_fde_reader;
next_val
}
}
pub struct EH_Frame_Hdr<'a> {
fde_writer: DwarfWriter<'a>,
eh_frame_hdr_addr: u32,
fdes: Vec<(u32, u32)>,
}
impl<'a> EH_Frame_Hdr<'a> {
/// Create a [EH_Frame_Hdr] object, and write out the fixed fields of `.eh_frame_hdr` to memory.
///
/// Load address is not known at this point.
pub fn new(
eh_frame_hdr_slice: &mut [u8],
eh_frame_hdr_addr: u32,
eh_frame_addr: u32,
) -> EH_Frame_Hdr {
let mut writer = DwarfWriter::new(eh_frame_hdr_slice);
writer.write_u8(1); // version
writer.write_u8(0x1B); // eh_frame_ptr_enc - PC-relative 4-byte signed value
writer.write_u8(0x03); // fde_count_enc - 4-byte unsigned value
writer.write_u8(0x3B); // table_enc - .eh_frame_hdr section-relative 4-byte signed value
let eh_frame_offset = eh_frame_addr.wrapping_sub(
eh_frame_hdr_addr + writer.offset as u32 + ((mem::size_of::<u8>() as u32) * 4),
);
writer.write_u32(eh_frame_offset); // eh_frame_ptr
writer.write_u32(0); // `fde_count`, will be written in finalize_fde
EH_Frame_Hdr { fde_writer: writer, eh_frame_hdr_addr, fdes: Vec::new() }
}
/// The offset of the `fde_count` value relative to the start of the `.eh_frame_hdr` section in
/// bytes.
fn fde_count_offset() -> usize {
8
}
pub fn add_fde(&mut self, init_loc: u32, addr: u32) {
self.fdes.push((
init_loc.wrapping_sub(self.eh_frame_hdr_addr),
addr.wrapping_sub(self.eh_frame_hdr_addr),
));
}
pub fn finalize_fde(mut self) {
self.fdes
.sort_by(|(left_init_loc, _), (right_init_loc, _)| left_init_loc.cmp(right_init_loc));
for (init_loc, addr) in &self.fdes {
self.fde_writer.write_u32(*init_loc);
self.fde_writer.write_u32(*addr);
}
LittleEndian::write_u32(
&mut self.fde_writer.slice[Self::fde_count_offset()..],
self.fdes.len() as u32,
);
}
pub fn size_from_eh_frame(eh_frame: &[u8]) -> usize {
// The virtual address of the EH frame does not matter in this case
// Calculation of size does not involve modifying any headers
let mut reader = DwarfReader::new(eh_frame, 0);
let mut fde_count = 0;
while !reader.slice.is_empty() {
// The original length field should be able to hold the entire value.
// The device memory space is limited to 32-bits addresses anyway.
let entry_length = reader.read_u32();
if entry_length == 0 || entry_length == 0xFFFF_FFFF {
unimplemented!()
}
// This slot stores the CIE ID (for CIE)/CIE Pointer (for FDE).
// This value must be non-zero for FDEs.
let cie_ptr = reader.read_u32();
if cie_ptr != 0 {
fde_count += 1;
}
reader.offset(entry_length - mem::size_of::<u32>() as u32);
}
12 + fde_count * 8
}
}

2893
nac3ld/src/elf.rs
View File

File diff suppressed because it is too large Load Diff

1502
nac3ld/src/lib.rs
View File

File diff suppressed because it is too large Load Diff

14
nac3parser/Cargo.toml
View File

@ -5,20 +5,20 @@ description = "Parser for python code."
authors = [ "RustPython Team", "M-Labs" ]
build = "build.rs"
license = "MIT"
edition = "2021"
edition = "2018"
[build-dependencies]
lalrpop = "0.22"
lalrpop = "0.19.6"
[dependencies]
nac3ast = { path = "../nac3ast" }
lalrpop-util = "0.22"
log = "0.4"
lalrpop-util = "0.19.6"
log = "0.4.1"
unic-emoji-char = "0.9"
unic-ucd-ident = "0.9"
unicode_names2 = "1.3"
phf = { version = "0.11", features = ["macros"] }
ahash = "0.8"
unicode_names2 = "0.4"
phf = { version = "0.9", features = ["macros"] }
ahash = "0.7.2"
[dev-dependencies]
insta = "=1.11.0"

54
nac3parser/src/config_comment_helper.rs
View File

@ -1,17 +1,15 @@
use crate::{
ast::{Ident, Location},
error::*,
token::Tok,
};
use lalrpop_util::ParseError;
use nac3ast::*;
use crate::ast::Ident;
use crate::ast::Location;
use crate::token::Tok;
use crate::error::*;
pub fn make_config_comment(
com_loc: Location,
stmt_loc: Location,
nac3com_above: Vec<(Ident, Tok)>,
nac3com_end: Option<Ident>,
nac3com_end: Option<Ident>
) -> Result<Vec<Ident>, ParseError<Location, Tok, LexicalError>> {
if com_loc.column() != stmt_loc.column() && !nac3com_above.is_empty() {
return Err(ParseError::User {
@ -19,25 +17,24 @@ pub fn make_config_comment(
location: com_loc,
error: LexicalErrorType::OtherError(
format!(
"config comment at top must have the same indentation with what it applies (comment at {com_loc}, statement at {stmt_loc})",
"config comment at top must have the same indentation with what it applies (comment at {}, statement at {})",
com_loc,
stmt_loc,
)
)
}
});
})
};
Ok(nac3com_above
.into_iter()
.map(|(com, _)| com)
.chain(nac3com_end.map_or_else(|| vec![].into_iter(), |com| vec![com].into_iter()))
.collect())
Ok(
nac3com_above
.into_iter()
.map(|(com, _)| com)
.chain(nac3com_end.map_or_else(|| vec![].into_iter(), |com| vec![com].into_iter()))
.collect()
)
}
pub fn handle_small_stmt<U>(
stmts: &mut [Stmt<U>],
nac3com_above: Vec<(Ident, Tok)>,
nac3com_end: Option<Ident>,
com_above_loc: Location,
) -> Result<(), ParseError<Location, Tok, LexicalError>> {
pub fn handle_small_stmt<U>(stmts: &mut [Stmt<U>], nac3com_above: Vec<(Ident, Tok)>, nac3com_end: Option<Ident>, com_above_loc: Location) -> Result<(), ParseError<Location, Tok, LexicalError>> {
if com_above_loc.column() != stmts[0].location.column() && !nac3com_above.is_empty() {
return Err(ParseError::User {
error: LexicalError {
@ -50,12 +47,17 @@ pub fn handle_small_stmt<U>(
)
)
}
});
})
}
apply_config_comments(&mut stmts[0], nac3com_above.into_iter().map(|(com, _)| com).collect());
apply_config_comments(
&mut stmts[0],
nac3com_above
.into_iter()
.map(|(com, _)| com).collect()
);
apply_config_comments(
stmts.last_mut().unwrap(),
nac3com_end.map_or_else(Vec::new, |com| vec![com]),
nac3com_end.map_or_else(Vec::new, |com| vec![com])
);
Ok(())
}
@ -70,7 +72,7 @@ fn apply_config_comments<U>(stmt: &mut Stmt<U>, comments: Vec<Ident>) {
| StmtKind::AnnAssign { config_comment, .. }
| StmtKind::Break { config_comment, .. }
| StmtKind::Continue { config_comment, .. }
| StmtKind::Return { config_comment, .. }
| StmtKind::Return { config_comment, .. }
| StmtKind::Raise { config_comment, .. }
| StmtKind::Import { config_comment, .. }
| StmtKind::ImportFrom { config_comment, .. }
@ -78,8 +80,6 @@ fn apply_config_comments<U>(stmt: &mut Stmt<U>, comments: Vec<Ident>) {
| StmtKind::Nonlocal { config_comment, .. }
| StmtKind::Assert { config_comment, .. } => config_comment.extend(comments),
_ => {
unreachable!("only small statements should call this function")
}
_ => { unreachable!("only small statements should call this function") }
}
}

63
nac3parser/src/error.rs
View File

@ -1,11 +1,12 @@
//! Define internal parse error types
//! The goal is to provide a matching and a safe error API, maksing errors from LALR
use std::error::Error;
use std::fmt;
use lalrpop_util::ParseError as LalrpopError;
use crate::{ast::Location, token::Tok};
use crate::ast::Location;
use crate::token::Tok;
use std::error::Error;
use std::fmt;
/// Represents an error during lexical scanning.
#[derive(Debug, PartialEq)]
@ -36,7 +37,7 @@ impl fmt::Display for LexicalErrorType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
LexicalErrorType::StringError => write!(f, "Got unexpected string"),
LexicalErrorType::FStringError(error) => write!(f, "Got error in f-string: {error}"),
LexicalErrorType::FStringError(error) => write!(f, "Got error in f-string: {}", error),
LexicalErrorType::UnicodeError => write!(f, "Got unexpected unicode"),
LexicalErrorType::NestingError => write!(f, "Got unexpected nesting"),
LexicalErrorType::IndentationError => {
@ -58,13 +59,13 @@ impl fmt::Display for LexicalErrorType {
write!(f, "positional argument follows keyword argument")
}
LexicalErrorType::UnrecognizedToken { tok } => {
write!(f, "Got unexpected token {tok}")
write!(f, "Got unexpected token {}", tok)
}
LexicalErrorType::LineContinuationError => {
write!(f, "unexpected character after line continuation character")
}
LexicalErrorType::Eof => write!(f, "unexpected EOF while parsing"),
LexicalErrorType::OtherError(msg) => write!(f, "{msg}"),
LexicalErrorType::OtherError(msg) => write!(f, "{}", msg),
}
}
}
@ -95,7 +96,7 @@ impl fmt::Display for FStringErrorType {
FStringErrorType::UnopenedRbrace => write!(f, "Unopened '}}'"),
FStringErrorType::ExpectedRbrace => write!(f, "Expected '}}' after conversion flag."),
FStringErrorType::InvalidExpression(error) => {
write!(f, "Invalid expression: {error}")
write!(f, "Invalid expression: {}", error)
}
FStringErrorType::InvalidConversionFlag => write!(f, "Invalid conversion flag"),
FStringErrorType::EmptyExpression => write!(f, "Empty expression"),
@ -143,27 +144,36 @@ pub enum ParseErrorType {
impl From<LalrpopError<Location, Tok, LexicalError>> for ParseError {
fn from(err: LalrpopError<Location, Tok, LexicalError>) -> Self {
match err {
LalrpopError::ExtraToken { token } => {
ParseError { error: ParseErrorType::ExtraToken(token.1), location: token.0 }
}
LalrpopError::User { error } => {
ParseError { error: ParseErrorType::Lexical(error.error), location: error.location }
}
// TODO: Are there cases where this isn't an EOF?
LalrpopError::InvalidToken { location } => ParseError {
error: ParseErrorType::Eof,
location,
},
LalrpopError::ExtraToken { token } => ParseError {
error: ParseErrorType::ExtraToken(token.1),
location: token.0,
},
LalrpopError::User { error } => ParseError {
error: ParseErrorType::Lexical(error.error),
location: error.location,
},
LalrpopError::UnrecognizedToken { token, expected } => {
// Hacky, but it's how CPython does it. See PyParser_AddToken,
// in particular "Only one possible expected token" comment.
let expected = if expected.len() == 1 { Some(expected[0].clone()) } else { None };
let expected = if expected.len() == 1 {
Some(expected[0].clone())
} else {
None
};
ParseError {
error: ParseErrorType::UnrecognizedToken(token.1, expected),
location: token.0,
}
}
LalrpopError::UnrecognizedEof { location, .. }
// TODO: Are there cases where this isn't an EOF?
| LalrpopError::InvalidToken { location } => {
ParseError { error: ParseErrorType::Eof, location }
}
LalrpopError::UnrecognizedEOF { location, .. } => ParseError {
error: ParseErrorType::Eof,
location,
},
}
}
}
@ -178,7 +188,7 @@ impl fmt::Display for ParseErrorType {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match *self {
ParseErrorType::Eof => write!(f, "Got unexpected EOF"),
ParseErrorType::ExtraToken(ref tok) => write!(f, "Got extraneous token: {tok:?}"),
ParseErrorType::ExtraToken(ref tok) => write!(f, "Got extraneous token: {:?}", tok),
ParseErrorType::InvalidToken => write!(f, "Got invalid token"),
ParseErrorType::UnrecognizedToken(ref tok, ref expected) => {
if *tok == Tok::Indent {
@ -186,10 +196,10 @@ impl fmt::Display for ParseErrorType {
} else if expected.as_deref() == Some("Indent") {
write!(f, "expected an indented block")
} else {
write!(f, "Got unexpected token {tok}")
write!(f, "Got unexpected token {}", tok)
}
}
ParseErrorType::Lexical(ref error) => write!(f, "{error}"),
ParseErrorType::Lexical(ref error) => write!(f, "{}", error),
}
}
}
@ -197,7 +207,6 @@ impl fmt::Display for ParseErrorType {
impl Error for ParseErrorType {}
impl ParseErrorType {
#[must_use]
pub fn is_indentation_error(&self) -> bool {
match self {
ParseErrorType::Lexical(LexicalErrorType::IndentationError) => true,
@ -207,11 +216,11 @@ impl ParseErrorType {
_ => false,
}
}
#[must_use]
pub fn is_tab_error(&self) -> bool {
matches!(
self,
ParseErrorType::Lexical(LexicalErrorType::TabError | LexicalErrorType::TabsAfterSpaces)
ParseErrorType::Lexical(LexicalErrorType::TabError)
| ParseErrorType::Lexical(LexicalErrorType::TabsAfterSpaces)
)
}
}

60
nac3parser/src/fstring.rs
View File

@ -1,11 +1,12 @@
use std::{iter, mem, str};
use std::iter;
use std::mem;
use std::str;
use crate::ast::{Constant, ConversionFlag, Expr, ExprKind, Location};
use crate::error::{FStringError, FStringErrorType, ParseError};
use crate::parser::parse_expression;
use self::FStringErrorType::*;
use crate::{
ast::{Constant, ConversionFlag, Expr, ExprKind, Location},
error::{FStringError, FStringErrorType, ParseError},
parser::parse_expression,
};
struct FStringParser<'a> {
chars: iter::Peekable<str::Chars<'a>>,
@ -14,7 +15,10 @@ struct FStringParser<'a> {
impl<'a> FStringParser<'a> {
fn new(source: &'a str, str_location: Location) -> Self {
Self { chars: source.chars().peekable(), str_location }
Self {
chars: source.chars().peekable(),
str_location,
}
}
#[inline]
@ -129,10 +133,10 @@ impl<'a> FStringParser<'a> {
)
} else {
Box::new(self.expr(ExprKind::Constant {
value: spec_expression.clone().into(),
value: spec_expression.to_owned().into(),
kind: None,
}))
});
})
}
'(' | '{' | '[' => {
expression.push(ch);
@ -247,11 +251,17 @@ impl<'a> FStringParser<'a> {
}
if !content.is_empty() {
values.push(self.expr(ExprKind::Constant { value: content.into(), kind: None }));
values.push(self.expr(ExprKind::Constant {
value: content.into(),
kind: None,
}))
}
let s = match values.len() {
0 => self.expr(ExprKind::Constant { value: String::new().into(), kind: None }),
0 => self.expr(ExprKind::Constant {
value: String::new().into(),
kind: None,
}),
1 => values.into_iter().next().unwrap(),
_ => self.expr(ExprKind::JoinedStr { values }),
};
@ -260,14 +270,16 @@ impl<'a> FStringParser<'a> {
}
fn parse_fstring_expr(source: &str) -> Result<Expr, ParseError> {
let fstring_body = format!("({source})");
let fstring_body = format!("({})", source);
parse_expression(&fstring_body)
}
/// Parse an fstring from a string, located at a certain position in the sourcecode.
/// In case of errors, we will get the location and the error returned.
pub fn parse_located_fstring(source: &str, location: Location) -> Result<Expr, FStringError> {
FStringParser::new(source, location).parse().map_err(|error| FStringError { error, location })
FStringParser::new(source, location)
.parse()
.map_err(|error| FStringError { error, location })
}
#[cfg(test)]
@ -281,7 +293,7 @@ mod tests {
#[test]
fn test_parse_fstring() {
let source = "{a}{ b }{{foo}}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -289,7 +301,7 @@ mod tests {
#[test]
fn test_parse_fstring_nested_spec() {
let source = "{foo:{spec}}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -297,7 +309,7 @@ mod tests {
#[test]
fn test_parse_fstring_not_nested_spec() {
let source = "{foo:spec}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -310,7 +322,7 @@ mod tests {
#[test]
fn test_fstring_parse_selfdocumenting_base() {
let src = "{user=}";
let parse_ast = parse_fstring(src).unwrap();
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -318,7 +330,7 @@ mod tests {
#[test]
fn test_fstring_parse_selfdocumenting_base_more() {
let src = "mix {user=} with text and {second=}";
let parse_ast = parse_fstring(src).unwrap();
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -326,7 +338,7 @@ mod tests {
#[test]
fn test_fstring_parse_selfdocumenting_format() {
let src = "{user=:>10}";
let parse_ast = parse_fstring(src).unwrap();
let parse_ast = parse_fstring(&src).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -359,35 +371,35 @@ mod tests {
#[test]
fn test_parse_fstring_not_equals() {
let source = "{1 != 2}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_equals() {
let source = "{42 == 42}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_selfdoc_prec_space() {
let source = "{x =}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_selfdoc_trailing_space() {
let source = "{x= }";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_fstring_yield_expr() {
let source = "{yield}";
let parse_ast = parse_fstring(source).unwrap();
let parse_ast = parse_fstring(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
}

57
nac3parser/src/function.rs
View File

@ -1,11 +1,8 @@
use ahash::RandomState;
use std::collections::HashSet;
use ahash::RandomState;
use crate::{
ast,
error::{LexicalError, LexicalErrorType},
};
use crate::ast;
use crate::error::{LexicalError, LexicalErrorType};
pub struct ArgumentList {
pub args: Vec<ast::Expr>,
@ -57,32 +54,38 @@ pub fn parse_args(func_args: Vec<FunctionArgument>) -> Result<ArgumentList, Lexi
let mut keyword_names = HashSet::with_capacity_and_hasher(func_args.len(), RandomState::new());
for (name, value) in func_args {
if let Some((location, name)) = name {
if let Some(keyword_name) = &name {
if keyword_names.contains(keyword_name) {
match name {
Some((location, name)) => {
if let Some(keyword_name) = &name {
if keyword_names.contains(keyword_name) {
return Err(LexicalError {
error: LexicalErrorType::DuplicateKeywordArgumentError,
location,
});
}
keyword_names.insert(keyword_name.clone());
}
keywords.push(ast::Keyword::new(
location,
ast::KeywordData {
arg: name.map(|name| name.into()),
value: Box::new(value),
},
));
}
None => {
// Allow starred args after keyword arguments.
if !keywords.is_empty() && !is_starred(&value) {
return Err(LexicalError {
error: LexicalErrorType::DuplicateKeywordArgumentError,
location,
error: LexicalErrorType::PositionalArgumentError,
location: value.location,
});
}
keyword_names.insert(keyword_name.clone());
args.push(value);
}
keywords.push(ast::Keyword::new(
location,
ast::KeywordData { arg: name.map(String::into), value: Box::new(value) },
));
} else {
// Allow starred args after keyword arguments.
if !keywords.is_empty() && !is_starred(&value) {
return Err(LexicalError {
error: LexicalErrorType::PositionalArgumentError,
location: value.location,
});
}
args.push(value);
}
}
Ok(ArgumentList { args, keywords })

365
nac3parser/src/lexer.rs
View File

@ -1,16 +1,16 @@
//! This module takes care of lexing python source text.
//!
//! This means source code is translated into separate tokens.
use std::{char, cmp::Ordering, num::IntErrorKind, str::FromStr};
use unic_emoji_char::is_emoji_presentation;
use unic_ucd_ident::{is_xid_continue, is_xid_start};
pub use super::token::Tok;
use crate::{
ast::{FileName, Location},
error::{LexicalError, LexicalErrorType},
};
use crate::ast::{Location, FileName};
use crate::error::{LexicalError, LexicalErrorType};
use std::char;
use std::cmp::Ordering;
use std::str::FromStr;
use std::num::IntErrorKind;
use unic_emoji_char::is_emoji_presentation;
use unic_ucd_ident::{is_xid_continue, is_xid_start};
#[derive(Clone, Copy, PartialEq, Debug, Default)]
struct IndentationLevel {
@ -32,14 +32,20 @@ impl IndentationLevel {
if self.spaces <= other.spaces {
Ok(Ordering::Less)
} else {
Err(LexicalError { location, error: LexicalErrorType::TabError })
Err(LexicalError {
location,
error: LexicalErrorType::TabError,
})
}
}
Ordering::Greater => {
if self.spaces >= other.spaces {
Ok(Ordering::Greater)
} else {
Err(LexicalError { location, error: LexicalErrorType::TabError })
Err(LexicalError {
location,
error: LexicalErrorType::TabError,
})
}
}
Ordering::Equal => Ok(self.spaces.cmp(&other.spaces)),
@ -57,7 +63,7 @@ pub struct Lexer<T: Iterator<Item = char>> {
chr1: Option<char>,
chr2: Option<char>,
location: Location,
config_comment_prefix: Option<&'static str>,
config_comment_prefix: Option<&'static str>
}
pub static KEYWORDS: phf::Map<&'static str, Tok> = phf::phf_map! {
@ -130,7 +136,11 @@ where
T: Iterator<Item = char>,
{
pub fn new(source: T) -> Self {
let mut nlh = NewlineHandler { source, chr0: None, chr1: None };
let mut nlh = NewlineHandler {
source,
chr0: None,
chr1: None,
};
nlh.shift();
nlh.shift();
nlh
@ -159,7 +169,7 @@ where
self.shift();
} else {
// Transform MAC EOL into \n
self.chr0 = Some('\n');
self.chr0 = Some('\n')
}
} else {
break;
@ -179,13 +189,13 @@ where
chars: input,
at_begin_of_line: true,
nesting: 0,
indentation_stack: vec![IndentationLevel::default()],
indentation_stack: vec![Default::default()],
pending: Vec::new(),
chr0: None,
location: start,
chr1: None,
chr2: None,
config_comment_prefix: Some(" nac3:"),
config_comment_prefix: Some(" nac3:")
};
lxr.next_char();
lxr.next_char();
@ -207,9 +217,11 @@ where
let mut saw_f = false;
loop {
// Detect r"", f"", b"" and u""
if !(saw_b || saw_u || saw_f) && matches!(self.chr0, Some('b' | 'B')) {
if !(saw_b || saw_u || saw_f) && matches!(self.chr0, Some('b') | Some('B')) {
saw_b = true;
} else if !(saw_b || saw_r || saw_u || saw_f) && matches!(self.chr0, Some('u' | 'U')) {
} else if !(saw_b || saw_r || saw_u || saw_f)
&& matches!(self.chr0, Some('u') | Some('U'))
{
saw_u = true;
} else if !(saw_r || saw_u) && (self.chr0 == Some('r') || self.chr0 == Some('R')) {
saw_r = true;
@ -275,15 +287,15 @@ where
let end_pos = self.get_pos();
let value = match i128::from_str_radix(&value_text, radix) {
Ok(value) => value,
Err(e) => match e.kind() {
IntErrorKind::PosOverflow | IntErrorKind::NegOverflow => i128::MAX,
_ => {
return Err(LexicalError {
error: LexicalErrorType::OtherError(format!("{e:?}")),
Err(e) => {
match e.kind() {
IntErrorKind::PosOverflow | IntErrorKind::NegOverflow => i128::MAX,
_ => return Err(LexicalError {
error: LexicalErrorType::OtherError(format!("{:?}", e)),
location: start_pos,
})
}),
}
},
}
};
Ok((start_pos, Tok::Int { value }, end_pos))
}
@ -326,7 +338,14 @@ where
if self.chr0 == Some('j') || self.chr0 == Some('J') {
self.next_char();
let end_pos = self.get_pos();
Ok((start_pos, Tok::Complex { real: 0.0, imag: value }, end_pos))
Ok((
start_pos,
Tok::Complex {
real: 0.0,
imag: value,
},
end_pos,
))
} else {
let end_pos = self.get_pos();
Ok((start_pos, Tok::Float { value }, end_pos))
@ -345,7 +364,7 @@ where
let value = value_text.parse::<i128>().ok();
let nonzero = match value {
Some(value) => value != 0i128,
None => true,
None => true
};
if start_is_zero && nonzero {
return Err(LexicalError {
@ -360,7 +379,7 @@ where
/// Consume a sequence of numbers with the given radix,
/// the digits can be decorated with underscores
/// like this: `'1_2_3_4'` == `'1234'`
/// like this: '1_2_3_4' == '1234'
fn radix_run(&mut self, radix: u32) -> String {
let mut value_text = String::new();
@ -393,7 +412,7 @@ where
2 => matches!(c, Some('0'..='1')),
8 => matches!(c, Some('0'..='7')),
10 => matches!(c, Some('0'..='9')),
16 => matches!(c, Some('0'..='9' | 'a'..='f' | 'A'..='F')),
16 => matches!(c, Some('0'..='9') | Some('a'..='f') | Some('A'..='F')),
other => unimplemented!("Radix not implemented: {}", other),
}
}
@ -401,8 +420,8 @@ where
/// Test if we face '[eE][-+]?[0-9]+'
fn at_exponent(&self) -> bool {
match self.chr0 {
Some('e' | 'E') => match self.chr1 {
Some('+' | '-') => matches!(self.chr2, Some('0'..='9')),
Some('e') | Some('E') => match self.chr1 {
Some('+') | Some('-') => matches!(self.chr2, Some('0'..='9')),
Some('0'..='9') => true,
_ => false,
},
@ -414,17 +433,19 @@ where
fn lex_comment(&mut self) -> Option<Spanned> {
self.next_char();
// if possibly nac3 pseudocomment, special handling for `# nac3:`
let (mut prefix, mut is_comment) =
self.config_comment_prefix.map_or_else(|| ("".chars(), false), |v| (v.chars(), true));
let (mut prefix, mut is_comment) = self
.config_comment_prefix
.map_or_else(|| ("".chars(), false), |v| (v.chars(), true));
// for the correct location of config comment
let mut start_loc = self.location;
start_loc.go_left();
loop {
match self.chr0 {
Some('\n') | None => return None,
Some('\n') => return None,
None => return None,
Some(c) => {
if let (true, Some(p)) = (is_comment, prefix.next()) {
is_comment = is_comment && c == p;
is_comment = is_comment && c == p
} else {
// done checking prefix, if is comment then return the spanned
if is_comment {
@ -439,20 +460,22 @@ where
return Some((
start_loc,
Tok::ConfigComment { content: content.trim().into() },
self.location,
self.location
));
}
}
}
}
self.next_char();
}
};
}
fn unicode_literal(&mut self, literal_number: usize) -> Result<char, LexicalError> {
let mut p: u32 = 0u32;
let unicode_error =
LexicalError { error: LexicalErrorType::UnicodeError, location: self.get_pos() };
let unicode_error = LexicalError {
error: LexicalErrorType::UnicodeError,
location: self.get_pos(),
};
for i in 1..=literal_number {
match self.next_char() {
Some(c) => match c.to_digit(16) {
@ -463,8 +486,8 @@ where
}
}
match p {
0xD800..=0xDFFF => Ok(char::REPLACEMENT_CHARACTER),
_ => char::from_u32(p).ok_or(unicode_error),
0xD800..=0xDFFF => Ok(std::char::REPLACEMENT_CHARACTER),
_ => std::char::from_u32(p).ok_or(unicode_error),
}
}
@ -473,7 +496,7 @@ where
octet_content.push(first);
while octet_content.len() < 3 {
if let Some('0'..='7') = self.chr0 {
octet_content.push(self.next_char().unwrap());
octet_content.push(self.next_char().unwrap())
} else {
break;
}
@ -507,8 +530,10 @@ where
}
}
}
unicode_names2::character(&name)
.ok_or(LexicalError { error: LexicalErrorType::UnicodeError, location: start_pos })
unicode_names2::character(&name).ok_or(LexicalError {
error: LexicalErrorType::UnicodeError,
location: start_pos,
})
}
fn lex_string(
@ -541,7 +566,7 @@ where
} else if is_raw {
string_content.push('\\');
if let Some(c) = self.next_char() {
string_content.push(c);
string_content.push(c)
} else {
return Err(LexicalError {
error: LexicalErrorType::StringError,
@ -574,7 +599,7 @@ where
Some('u') if !is_bytes => string_content.push(self.unicode_literal(4)?),
Some('U') if !is_bytes => string_content.push(self.unicode_literal(8)?),
Some('N') if !is_bytes => {
string_content.push(self.parse_unicode_name()?);
string_content.push(self.parse_unicode_name()?)
}
Some(c) => {
string_content.push('\\');
@ -625,15 +650,20 @@ where
let end_pos = self.get_pos();
let tok = if is_bytes {
Tok::Bytes { value: string_content.chars().map(|c| c as u8).collect() }
Tok::Bytes {
value: string_content.chars().map(|c| c as u8).collect(),
}
} else {
Tok::String { value: string_content, is_fstring }
Tok::String {
value: string_content,
is_fstring,
}
};
Ok((start_pos, tok, end_pos))
}
fn is_identifier_start(c: char) -> bool {
fn is_identifier_start(&self, c: char) -> bool {
match c {
'_' | 'a'..='z' | 'A'..='Z' => true,
'+' | '-' | '*' | '/' | '=' | ' ' | '<' | '>' => false,
@ -805,14 +835,18 @@ where
// Check if we have some character:
if let Some(c) = self.chr0 {
// First check identifier:
if Self::is_identifier_start(c) {
if self.is_identifier_start(c) {
let identifier = self.lex_identifier()?;
self.emit(identifier);
} else if is_emoji_presentation(c) {
let tok_start = self.get_pos();
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::Name { name: c.to_string().into() }, tok_end));
self.emit((
tok_start,
Tok::Name { name: c.to_string().into() },
tok_end,
));
} else {
self.consume_character(c)?;
}
@ -865,13 +899,16 @@ where
'=' => {
let tok_start = self.get_pos();
self.next_char();
if let Some('=') = self.chr0 {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::EqEqual, tok_end));
} else {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::Equal, tok_end));
match self.chr0 {
Some('=') => {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::EqEqual, tok_end));
}
_ => {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::Equal, tok_end));
}
}
}
'+' => {
@ -897,13 +934,16 @@ where
}
Some('*') => {
self.next_char();
if let Some('=') = self.chr0 {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleStarEqual, tok_end));
} else {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleStar, tok_end));
match self.chr0 {
Some('=') => {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleStarEqual, tok_end));
}
_ => {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleStar, tok_end));
}
}
}
_ => {
@ -923,13 +963,16 @@ where
}
Some('/') => {
self.next_char();
if let Some('=') = self.chr0 {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleSlashEqual, tok_end));
} else {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleSlash, tok_end));
match self.chr0 {
Some('=') => {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleSlashEqual, tok_end));
}
_ => {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::DoubleSlash, tok_end));
}
}
}
_ => {
@ -1098,13 +1141,16 @@ where
match self.chr0 {
Some('<') => {
self.next_char();
if let Some('=') = self.chr0 {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::LeftShiftEqual, tok_end));
} else {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::LeftShift, tok_end));
match self.chr0 {
Some('=') => {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::LeftShiftEqual, tok_end));
}
_ => {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::LeftShift, tok_end));
}
}
}
Some('=') => {
@ -1124,13 +1170,16 @@ where
match self.chr0 {
Some('>') => {
self.next_char();
if let Some('=') = self.chr0 {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::RightShiftEqual, tok_end));
} else {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::RightShift, tok_end));
match self.chr0 {
Some('=') => {
self.next_char();
let tok_end = self.get_pos();
self.emit((tok_start, Tok::RightShiftEqual, tok_end));
}
_ => {
let tok_end = self.get_pos();
self.emit((tok_start, Tok::RightShift, tok_end));
}
}
}
Some('=') => {
@ -1284,14 +1333,13 @@ where
#[cfg(test)]
mod tests {
use super::{make_tokenizer, NewlineHandler, Tok};
use nac3ast::FileName;
const WINDOWS_EOL: &str = "\r\n";
const MAC_EOL: &str = "\r";
const UNIX_EOL: &str = "\n";
pub fn lex_source(source: &str) -> Vec<Tok> {
let lexer = make_tokenizer(source, FileName::default());
let lexer = make_tokenizer(source, Default::default());
lexer.map(|x| x.unwrap().1).collect()
}
@ -1371,7 +1419,7 @@ class Foo(A, B):
Dedent,
Dedent
]
);
)
}
#[test]
@ -1391,8 +1439,14 @@ class Foo(A, B):
assert_eq!(
tokens,
vec![
Tok::String { value: "\\\\".to_owned(), is_fstring: false },
Tok::String { value: "\\".to_owned(), is_fstring: false },
Tok::String {
value: "\\\\".to_owned(),
is_fstring: false,
},
Tok::String {
value: "\\".to_owned(),
is_fstring: false,
},
Tok::Newline,
]
);
@ -1405,13 +1459,27 @@ class Foo(A, B):
assert_eq!(
tokens,
vec![
Tok::Int { value: 47i128 },
Tok::Int { value: 13i128 },
Tok::Int { value: 0i128 },
Tok::Int { value: 123i128 },
Tok::Int {
value: 47i128,
},
Tok::Int {
value: 13i128,
},
Tok::Int {
value: 0i128,
},
Tok::Int {
value: 123i128,
},
Tok::Float { value: 0.2 },
Tok::Complex { real: 0.0, imag: 2.0 },
Tok::Complex { real: 0.0, imag: 2.2 },
Tok::Complex {
real: 0.0,
imag: 2.0,
},
Tok::Complex {
real: 0.0,
imag: 2.2,
},
Tok::Newline,
]
);
@ -1471,13 +1539,21 @@ class Foo(A, B):
assert_eq!(
tokens,
vec![
Tok::Name { name: String::from("avariable").into() },
Tok::Name {
name: String::from("avariable").into(),
},
Tok::Equal,
Tok::Int { value: 99i128 },
Tok::Int {
value: 99i128
},
Tok::Plus,
Tok::Int { value: 2i128 },
Tok::Int {
value: 2i128
},
Tok::Minus,
Tok::Int { value: 0i128 },
Tok::Int {
value: 0i128
},
Tok::Newline,
]
);
@ -1664,15 +1740,42 @@ class Foo(A, B):
assert_eq!(
tokens,
vec![
Tok::String { value: String::from("double"), is_fstring: false },
Tok::String { value: String::from("single"), is_fstring: false },
Tok::String { value: String::from("can't"), is_fstring: false },
Tok::String { value: String::from("\\\""), is_fstring: false },
Tok::String { value: String::from("\t\r\n"), is_fstring: false },
Tok::String { value: String::from("\\g"), is_fstring: false },
Tok::String { value: String::from("raw\\'"), is_fstring: false },
Tok::String { value: String::from("Đ"), is_fstring: false },
Tok::String { value: String::from("\u{80}\u{0}a"), is_fstring: false },
Tok::String {
value: String::from("double"),
is_fstring: false,
},
Tok::String {
value: String::from("single"),
is_fstring: false,
},
Tok::String {
value: String::from("can't"),
is_fstring: false,
},
Tok::String {
value: String::from("\\\""),
is_fstring: false,
},
Tok::String {
value: String::from("\t\r\n"),
is_fstring: false,
},
Tok::String {
value: String::from("\\g"),
is_fstring: false,
},
Tok::String {
value: String::from("raw\\'"),
is_fstring: false,
},
Tok::String {
value: String::from("Đ"),
is_fstring: false,
},
Tok::String {
value: String::from("\u{80}\u{0}a"),
is_fstring: false,
},
Tok::Newline,
]
);
@ -1727,7 +1830,7 @@ class Foo(A, B):
#[test]
fn test_escape_char_in_byte_literal() {
// backslash does not escape
let source = r#"b"omkmok\Xaa""#;
let source = r##"b"omkmok\Xaa""##;
let tokens = lex_source(source);
let res = vec![111, 109, 107, 109, 111, 107, 92, 88, 97, 97];
assert_eq!(tokens, vec![Tok::Bytes { value: res }, Tok::Newline]);
@ -1737,17 +1840,41 @@ class Foo(A, B):
fn test_raw_byte_literal() {
let source = r"rb'\x1z'";
let tokens = lex_source(source);
assert_eq!(tokens, vec![Tok::Bytes { value: b"\\x1z".to_vec() }, Tok::Newline]);
assert_eq!(
tokens,
vec![
Tok::Bytes {
value: b"\\x1z".to_vec()
},
Tok::Newline
]
);
let source = r"rb'\\'";
let tokens = lex_source(source);
assert_eq!(tokens, vec![Tok::Bytes { value: b"\\\\".to_vec() }, Tok::Newline]);
assert_eq!(
tokens,
vec![
Tok::Bytes {
value: b"\\\\".to_vec()
},
Tok::Newline
]
)
}
#[test]
fn test_escape_octet() {
let source = r"b'\43a\4\1234'";
let source = r##"b'\43a\4\1234'"##;
let tokens = lex_source(source);
assert_eq!(tokens, vec![Tok::Bytes { value: b"#a\x04S4".to_vec() }, Tok::Newline]);
assert_eq!(
tokens,
vec![
Tok::Bytes {
value: b"#a\x04S4".to_vec()
},
Tok::Newline
]
)
}
#[test]
@ -1756,7 +1883,13 @@ class Foo(A, B):
let tokens = lex_source(source);
assert_eq!(
tokens,
vec![Tok::String { value: "\u{2002}".to_owned(), is_fstring: false }, Tok::Newline]
);
vec![
Tok::String {
value: "\u{2002}".to_owned(),
is_fstring: false,
},
Tok::Newline
]
)
}
}

31
nac3parser/src/lib.rs
View File

@ -15,24 +15,6 @@
//!
//! ```
#![deny(
future_incompatible,
let_underscore,
nonstandard_style,
rust_2024_compatibility,
clippy::all
)]
#![warn(clippy::pedantic)]
#![allow(
clippy::enum_glob_use,
clippy::fn_params_excessive_bools,
clippy::missing_errors_doc,
clippy::missing_panics_doc,
clippy::module_name_repetitions,
clippy::too_many_lines,
clippy::wildcard_imports
)]
#[macro_use]
extern crate log;
use lalrpop_util::lalrpop_mod;
@ -45,16 +27,9 @@ pub mod lexer;
pub mod mode;
pub mod parser;
lalrpop_mod!(
#[allow(
future_incompatible,
let_underscore,
nonstandard_style,
rust_2024_compatibility,
unused,
clippy::all,
clippy::pedantic
)]
#[allow(clippy::all)]
#[allow(unused)]
python
);
pub mod config_comment_helper;
pub mod token;
pub mod config_comment_helper;

47
nac3parser/src/parser.rs
View File

@ -7,14 +7,11 @@
use std::iter;
use nac3ast::Location;
use crate::ast::{self, FileName};
use crate::error::ParseError;
use crate::lexer;
pub use crate::mode::Mode;
use crate::{
ast::{self, FileName},
error::ParseError,
lexer, python,
};
use crate::python;
/*
* Parse python code.
@ -66,7 +63,7 @@ pub fn parse_program(source: &str, file: FileName) -> Result<ast::Suite, ParseEr
///
/// ```
pub fn parse_expression(source: &str) -> Result<ast::Expr, ParseError> {
parse(source, Mode::Expression, FileName::default()).map(|top| match top {
parse(source, Mode::Expression, Default::default()).map(|top| match top {
ast::Mod::Expression { body } => *body,
_ => unreachable!(),
})
@ -75,10 +72,12 @@ pub fn parse_expression(source: &str) -> Result<ast::Expr, ParseError> {
// Parse a given source code
pub fn parse(source: &str, mode: Mode, file: FileName) -> Result<ast::Mod, ParseError> {
let lxr = lexer::make_tokenizer(source, file);
let marker_token = (Location::default(), mode.to_marker(), Location::default());
let marker_token = (Default::default(), mode.to_marker(), Default::default());
let tokenizer = iter::once(Ok(marker_token)).chain(lxr);
python::TopParser::new().parse(tokenizer).map_err(ParseError::from)
python::TopParser::new()
.parse(tokenizer)
.map_err(ParseError::from)
}
#[cfg(test)]
@ -87,42 +86,42 @@ mod tests {
#[test]
fn test_parse_empty() {
let parse_ast = parse_program("", FileName::default()).unwrap();
let parse_ast = parse_program("", Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_hello() {
let source = String::from("print('Hello world')");
let parse_ast = parse_program(&source, FileName::default()).unwrap();
let parse_ast = parse_program(&source, Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_print_2() {
let source = String::from("print('Hello world', 2)");
let parse_ast = parse_program(&source, FileName::default()).unwrap();
let parse_ast = parse_program(&source, Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_kwargs() {
let source = String::from("my_func('positional', keyword=2)");
let parse_ast = parse_program(&source, FileName::default()).unwrap();
let parse_ast = parse_program(&source, Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_if_elif_else() {
let source = String::from("if 1: 10\nelif 2: 20\nelse: 30");
let parse_ast = parse_program(&source, FileName::default()).unwrap();
let parse_ast = parse_program(&source, Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_parse_lambda() {
let source = "lambda x, y: x * y"; // lambda(x, y): x * y";
let parse_ast = parse_program(source, FileName::default()).unwrap();
let parse_ast = parse_program(&source, Default::default()).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
@ -130,7 +129,7 @@ mod tests {
fn test_parse_tuples() {
let source = "a, b = 4, 5";
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
insta::assert_debug_snapshot!(parse_program(&source, Default::default()).unwrap());
}
#[test]
@ -141,7 +140,7 @@ class Foo(A, B):
pass
def method_with_default(self, arg='default'):
pass";
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
insta::assert_debug_snapshot!(parse_program(&source, Default::default()).unwrap());
}
#[test]
@ -164,7 +163,7 @@ class Foo(A, B):
let parse_ast = parse_expression(&source).unwrap();
insta::assert_debug_snapshot!(parse_ast);
}
#[test]
fn test_more_comment() {
let source = "\
@ -184,9 +183,9 @@ while i < 2: # nac3: 4
# nac3: if1
if 1: # nac3: if2
3";
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
insta::assert_debug_snapshot!(parse_program(&source, Default::default()).unwrap());
}
#[test]
fn test_sample_comment() {
let source = "\
@ -197,7 +196,7 @@ while test: # nac3: while3
# nac3: simple assign0
a = 3 # nac3: simple assign1
";
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
insta::assert_debug_snapshot!(parse_program(&source, Default::default()).unwrap());
}
#[test]
@ -216,7 +215,7 @@ if a: # nac3: small2
for i in a: # nac3: for1
pass
";
insta::assert_debug_snapshot!(parse_program(source, FileName::default()).unwrap());
insta::assert_debug_snapshot!(parse_program(&source, Default::default()).unwrap());
}
#[test]
@ -225,6 +224,6 @@ for i in a: # nac3: for1
if a: # nac3: something
a = 3
";
assert!(parse_program(source, FileName::default()).is_err());
assert!(parse_program(&source, Default::default()).is_err());
}
}

29
nac3parser/src/token.rs
View File

@ -1,7 +1,6 @@
//! Different token definitions.
//! Loosely based on token.h from CPython source:
use std::fmt::{self, Write};
use crate::ast;
/// Python source code can be tokenized in a sequence of these tokens.
@ -112,23 +111,15 @@ impl fmt::Display for Tok {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
use Tok::*;
match self {
Name { name } => {
write!(f, "'{}'", ast::get_str_from_ref(&ast::get_str_ref_lock(), *name))
}
Int { value } => {
if *value == i128::MAX {
write!(f, "'#OFL#'")
} else {
write!(f, "'{value}'")
}
}
Float { value } => write!(f, "'{value}'"),
Complex { real, imag } => write!(f, "{real}j{imag}"),
Name { name } => write!(f, "'{}'", ast::get_str_from_ref(&ast::get_str_ref_lock(), *name)),
Int { value } => if *value != i128::MAX { write!(f, "'{}'", value) } else { write!(f, "'#OFL#'") },
Float { value } => write!(f, "'{}'", value),
Complex { real, imag } => write!(f, "{}j{}", real, imag),
String { value, is_fstring } => {
if *is_fstring {
write!(f, "f")?;
write!(f, "f")?
}
write!(f, "{value:?}")
write!(f, "{:?}", value)
}
Bytes { value } => {
write!(f, "b\"")?;
@ -138,16 +129,12 @@ impl fmt::Display for Tok {
10 => f.write_str("\\n")?,
13 => f.write_str("\\r")?,
32..=126 => f.write_char(*i as char)?,
_ => write!(f, "\\x{i:02x}")?,
_ => write!(f, "\\x{:02x}", i)?,
}
}
f.write_str("\"")
}
ConfigComment { content } => write!(
f,
"ConfigComment: '{}'",
ast::get_str_from_ref(&ast::get_str_ref_lock(), *content)
),
ConfigComment { content } => write!(f, "ConfigComment: '{}'", ast::get_str_from_ref(&ast::get_str_ref_lock(), *content)),
Newline => f.write_str("Newline"),
Indent => f.write_str("Indent"),
Dedent => f.write_str("Dedent"),

15
nac3standalone/Cargo.toml
View File

@ -2,15 +2,14 @@
name = "nac3standalone"
version = "0.1.0"
authors = ["M-Labs"]
edition = "2021"
[features]
no-escape-analysis = ["nac3core/no-escape-analysis"]
edition = "2018"
[dependencies]
parking_lot = "0.12"
parking_lot = "0.11.1"
nac3parser = { path = "../nac3parser" }
nac3core = { path = "../nac3core" }
[dependencies.clap]
version = "4.5"
features = ["derive"]
[dependencies.inkwell]
version = "0.1.0-beta.4"
default-features = false
features = ["llvm13-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]

4
nac3standalone/demo/.gitignore vendored
View File

@ -1,4 +0,0 @@
*.bc
*.ll
*.o
/demo

68
nac3standalone/demo/check_demo.sh
View File

@ -1,68 +0,0 @@
#!/usr/bin/env bash
set -e
if [ -z "$1" ]; then
echo "No argument supplied"
exit 1
fi
declare -a nac3args
while [ $# -gt 1 ]; do
case "$1" in
--help)
echo "Usage: check_demo.sh [--debug] [-i686] -- [NAC3ARGS...] demo"
exit
;;
--debug)
debug=1
;;
-i686)
i686=1
;;
--)
shift
break
;;
*)
echo "Unrecognized argument \"$1\""
exit 1
;;
esac
shift
done
while [ $# -gt 1 ]; do
nac3args+=("$1")
shift
done
demo="$1"
echo "### Checking $demo..."
echo ">>>>>> Running $demo with the Python interpreter"
./interpret_demo.py "$demo" > interpreted.log
if [ -n "$i686" ]; then
echo "...... Trying NAC3's 32-bit code generator output"
if [ -n "$debug" ]; then
./run_demo.sh --debug -i686 --out run_32.log -- "${nac3args[@]}" "$demo"
else
./run_demo.sh -i686 --out run_32.log -- "${nac3args[@]}" "$demo"
fi
diff -Nau interpreted.log run_32.log
fi
echo "...... Trying NAC3's 64-bit code generator output"
if [ -n "$debug" ]; then
./run_demo.sh --debug --out run_64.log -- "${nac3args[@]}" "$demo"
else
./run_demo.sh --out run_64.log -- "${nac3args[@]}" "$demo"
fi
diff -Nau interpreted.log run_64.log
echo "...... OK"
rm -f interpreted.log \
run_32.log run_64.log

13
nac3standalone/demo/check_demos.sh
View File

@ -2,15 +2,14 @@
set -e
if [ "$1" == "--help" ]; then
echo "Usage: check_demos.sh [CHECKARGS...] [--] [NAC3ARGS...]"
exit
fi
count=0
for demo in src/*.py; do
./check_demo.sh "$@" "$demo"
((count += 1))
echo -n "checking $demo... "
./interpret_demo.py $demo > interpreted.log
./run_demo.sh $demo > run.log
diff -Nau interpreted.log run.log
echo "ok"
let "count+=1"
done
echo "Ran $count demo checks - PASSED"

138
nac3standalone/demo/demo.c
View File

@ -1,138 +0,0 @@
#include <inttypes.h>
#include <math.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
double dbl_nan(void) {
return NAN;
}
double dbl_inf(void) {
return INFINITY;
}
void output_bool(bool x) {
puts(x ? "True" : "False");
}
void output_int32(int32_t x) {
printf("%" PRId32 "\n", x);
}
void output_int64(int64_t x) {
printf("%" PRId64 "\n", x);
}
void output_uint32(uint32_t x) {
printf("%" PRIu32 "\n", x);
}
void output_uint64(uint64_t x) {
printf("%" PRIu64 "\n", x);
}
void output_float64(double x) {
if (isnan(x)) {
puts("nan");
} else {
printf("%f\n", x);
}
}
void output_range(int32_t range[3]) {
printf("range(");
printf("%d, %d", range[0], range[1]);
if (range[2] != 1) {
printf(", %d", range[2]);
}
puts(")");
}
void output_asciiart(int32_t x) {
static const char* chars = " .,-:;i+hHM$*#@ ";
if (x < 0) {
putchar('\n');
} else {
putchar(chars[x]);
}
}
struct cslice {
void* data;
size_t len;
};
void output_int32_list(struct cslice* slice) {
const int32_t* data = (int32_t*)slice->data;
putchar('[');
for (size_t i = 0; i < slice->len; ++i) {
if (i == slice->len - 1) {
printf("%d", data[i]);
} else {
printf("%d, ", data[i]);
}
}
putchar(']');
putchar('\n');
}
void output_str(struct cslice* slice) {
const char* data = (const char*)slice->data;
for (size_t i = 0; i < slice->len; ++i) {
putchar(data[i]);
}
}
void output_strln(struct cslice* slice) {
output_str(slice);
putchar('\n');
}
uint64_t dbg_stack_address(__attribute__((unused)) struct cslice* slice) {
int i;
void* ptr = (void*)&i;
return (uintptr_t)ptr;
}
uint32_t __nac3_personality(uint32_t state, uint32_t exception_object, uint32_t context) {
printf("__nac3_personality(state: %u, exception_object: %u, context: %u)\n", state, exception_object, context);
exit(101);
__builtin_unreachable();
}
// See `struct Exception<'a>` in
// https://github.com/m-labs/artiq/blob/master/artiq/firmware/libeh/eh_artiq.rs
struct Exception {
uint32_t id;
struct cslice file;
uint32_t line;
uint32_t column;
struct cslice function;
struct cslice message;
int64_t param[3];
};
uint32_t __nac3_raise(struct Exception* e) {
printf("__nac3_raise called. Exception details:\n");
printf(" ID: %" PRIu32 "\n", e->id);
printf(" Location: %*s:%" PRIu32 ":%" PRIu32 "\n", (int)e->file.len, (const char*)e->file.data, e->line,
e->column);
printf(" Function: %*s\n", (int)e->function.len, (const char*)e->function.data);
printf(" Message: \"%*s\"\n", (int)e->message.len, (const char*)e->message.data);
printf(" Params: {0}=%" PRId64 ", {1}=%" PRId64 ", {2}=%" PRId64 "\n", e->param[0], e->param[1], e->param[2]);
exit(101);
__builtin_unreachable();
}
void __nac3_end_catch(void) {}
extern int32_t run(void);
int main(void) {
run();
}

Some files were not shown because too many files have changed in this diff Show More