nac3core: replace paramter with parameter

Co-authored-by: wylited <ds@m-labs.hk>
Co-committed-by: wylited <ds@m-labs.hk>

.gitignore

@@ -1,2 +1,3 @@
 __pycache__
 /target
+windows/msys2

Cargo.toml

@@ -1,6 +1,12 @@
 [workspace]
 members = [
+  "nac3ast",
+  "nac3parser",
   "nac3core",
   "nac3standalone",
-  "nac3embedded",
+  "nac3artiq",
+  "runkernel",
 ]
+
+[profile.release]
+debug = true

README.md

@@ -1,34 +1,55 @@
-# nac3 compiler
+# 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.
+
+**WARNING: NAC3 is currently experimental software and several important features are not implemented yet.**
+
+## Packaging
+
+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
+
+### Linux
+
+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
+
+Install [MSYS2](https://www.msys2.org/), and open "MSYS2 MinGW x64". Edit ``/etc/pacman.conf`` to add:
+```
+[artiq]
+SigLevel = Optional TrustAll
+Server = https://lab.m-labs.hk/msys2
+```
+
+Then run the following commands:
+```
+pacman -Syu
+pacman -S mingw-w64-x86_64-artiq
+```
+
+Install ``lld-msys2`` manually:
+```
+wget https://nixbld.m-labs.hk/build/115527/download/1/ld.lld.exe
+mv ld.lld.exe C:/msys64/mingw64/bin
+```
+
+Note: This build of NAC3 cannot be used with Anaconda Python nor the python.org binaries for Windows. Those Python versions are compiled with Visual Studio (MSVC) and their ABI is incompatible with the GNU ABI used in this build. We have no plans to support Visual Studio nor the MSVC ABI. If you need a MSVC build, please install the requisite bloated spyware from Microsoft and compile NAC3 yourself.
+
+## For developers
 
 This repository contains:
-- nac3core: Core compiler library, containing type-checking, static analysis (in
-    the future) and code generation.
-- nac3embedded: Integration with CPython runtime.
-- nac3standalone: Standalone compiler tool.
-
-The core compiler would know nothing about symbol resolution, host variables
-etc. The nac3embedded/nac3standalone library would provide (implement) the
-symbol resolver to the core compiler for resolving the type and value for
-unknown symbols. The core compiler would only type check classes and functions
-requested by the nac3embedded/nac3standalone lib (the API should allow the
-caller to specify which methods should be compiled). After type checking, the
-compiler would analyse the set of functions/classes that are used and perform
-code generation.
-
-value could be integer values, boolean values, bytes (for memcpy), function ID
-(full name + concrete type)
-
-## Current Plan
-
-Type checking:
-
-- [x] Basic interface for symbol resolver.
-- [x] Track location information in context object (for diagnostics).
-- [ ] Refactor old expression and statement type inference code. (anto)
-- [ ] Error diagnostics utilities. (pca)
-- [ ] Move tests to external files, write scripts for testing. (pca)
-- [ ] Implement function type checking (instantiate bounded type parameters),
-    loop unrolling, type inference for lists with virtual objects. (pca)
-
+- ``nac3ast``: Python abstract syntax tree definition (based on RustPython).
+- ``nac3parser``: Python parser (based on RustPython).
+- ``nac3core``: Core compiler library, containing type-checking and code generation.
+- ``nac3standalone``: Standalone compiler tool (core language only).
+- ``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.
 
+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``.

flake.lock

@@ -0,0 +1,27 @@
+{
+  "nodes": {
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1649619156,
+        "narHash": "sha256-p0q4zpuKMwrzGF+5ZU7Thnpac5TinhDI9jr2mBxhV4w=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "e7d63bd0d50df412f5a1d8acfa3caae75522e347",
+        "type": "github"
+      },
+      "original": {
+        "owner": "NixOS",
+        "ref": "nixos-21.11",
+        "repo": "nixpkgs",
+        "type": "github"
+      }
+    },
+    "root": {
+      "inputs": {
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,154 @@
+{
+  description = "The third-generation ARTIQ compiler";
+
+  inputs.nixpkgs.url = github:NixOS/nixpkgs/nixos-21.11;
+
+  outputs = { self, nixpkgs }:
+    let
+      pkgs = import nixpkgs { system = "x86_64-linux"; };
+    in rec {
+      packages.x86_64-linux = rec {
+        llvm-nac3 = pkgs.callPackage ./nix/llvm {};
+        nac3artiq = pkgs.python3Packages.toPythonModule (
+          pkgs.rustPlatform.buildRustPackage {
+            name = "nac3artiq";
+            outputs = [ "out" "runkernel" "standalone" ];
+            src = self;
+            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 ])) ];
+            checkPhase =
+              ''
+              echo "Checking nac3standalone demos..."
+              pushd nac3standalone/demo
+              patchShebangs .
+              ./check_demos.sh
+              popd
+              echo "Running Cargo tests..."
+              cargoCheckHook
+              '';
+            installPhase =
+              ''
+              PYTHON_SITEPACKAGES=$out/${pkgs.python3Packages.python.sitePackages}
+              mkdir -p $PYTHON_SITEPACKAGES
+              cp target/x86_64-unknown-linux-gnu/release/libnac3artiq.so $PYTHON_SITEPACKAGES/nac3artiq.so
+
+              mkdir -p $runkernel/bin
+              cp target/x86_64-unknown-linux-gnu/release/runkernel $runkernel/bin
+
+              mkdir -p $standalone/bin
+              cp target/x86_64-unknown-linux-gnu/release/nac3standalone $standalone/bin
+              '';
+          }
+        );
+        python3-mimalloc = pkgs.python3 // rec {
+          withMimalloc = pkgs.python3.buildEnv.override({ makeWrapperArgs = [ "--set LD_PRELOAD ${pkgs.mimalloc}/lib/libmimalloc.so" ]; });
+          withPackages = f: let packages = f pkgs.python3.pkgs; in withMimalloc.override { extraLibs = packages; };
+        };
+
+        # LLVM PGO support
+        llvm-nac3-instrumented = pkgs.callPackage ./nix/llvm {
+          stdenv = pkgs.llvmPackages_13.stdenv;
+          extraCmakeFlags = [ "-DLLVM_BUILD_INSTRUMENTED=IR" ];
+        };
+        nac3artiq-instrumented = pkgs.python3Packages.toPythonModule (
+          pkgs.rustPlatform.buildRustPackage {
+            name = "nac3artiq-instrumented";
+            src = self;
+            cargoLock = { lockFile = ./Cargo.lock; };
+            nativeBuildInputs = [ pkgs.python3 pkgs.llvmPackages_13.clang-unwrapped llvm-nac3-instrumented ];
+            buildInputs = [ pkgs.python3 llvm-nac3-instrumented ];
+            cargoBuildFlags = [ "--package" "nac3artiq" "--features" "init-llvm-profile" ];
+            doCheck = false;
+            configurePhase =
+              ''
+              export CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_RUSTFLAGS="-C link-arg=-L${pkgs.llvmPackages_13.compiler-rt}/lib/linux -C link-arg=-lclang_rt.profile-x86_64"
+              '';
+            installPhase =
+              ''
+              TARGET_DIR=$out/${pkgs.python3Packages.python.sitePackages}
+              mkdir -p $TARGET_DIR
+              cp target/x86_64-unknown-linux-gnu/release/libnac3artiq.so $TARGET_DIR/nac3artiq.so
+              '';
+          }
+        );
+        nac3artiq-profile = pkgs.stdenvNoCC.mkDerivation {
+          name = "nac3artiq-profile";
+          src = self;
+          buildInputs = [ (python3-mimalloc.withPackages(ps: [ ps.numpy nac3artiq-instrumented ])) pkgs.lld_13 pkgs.llvmPackages_13.libllvm ];
+          phases = [ "buildPhase" "installPhase" ];
+          # TODO: get more representative code.
+          buildPhase = "python $src/nac3artiq/demo/demo.py";
+          installPhase =
+            ''
+            mkdir $out
+            llvm-profdata merge -o $out/llvm.profdata /build/llvm/build/profiles/*
+            '';
+        };
+        llvm-nac3-pgo = pkgs.callPackage ./nix/llvm {
+          stdenv = pkgs.llvmPackages_13.stdenv;
+          extraCmakeFlags = [ "-DLLVM_PROFDATA_FILE=${nac3artiq-profile}/llvm.profdata" ];
+        };
+        nac3artiq-pgo = pkgs.python3Packages.toPythonModule (
+          pkgs.rustPlatform.buildRustPackage {
+            name = "nac3artiq-pgo";
+            src = self;
+            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" ];
+            installPhase =
+              ''
+              TARGET_DIR=$out/${pkgs.python3Packages.python.sitePackages}
+              mkdir -p $TARGET_DIR
+              cp target/x86_64-unknown-linux-gnu/release/libnac3artiq.so $TARGET_DIR/nac3artiq.so
+              '';
+          }
+        );
+      };
+
+      packages.x86_64-w64-mingw32 = import ./nix/windows { inherit pkgs; };
+
+      devShell.x86_64-linux = pkgs.mkShell {
+        name = "nac3-dev-shell";
+        buildInputs = with pkgs; [
+          # build dependencies
+          packages.x86_64-linux.llvm-nac3
+          llvmPackages_13.clang-unwrapped  # IRRT
+          cargo
+          rustc
+          # runtime dependencies
+          lld_13
+          (packages.x86_64-linux.python3-mimalloc.withPackages(ps: [ ps.numpy ]))
+          # development tools
+          cargo-insta
+          clippy
+          rustfmt
+        ];
+      };
+      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;
+        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;
+        lld-msys2 = packages.x86_64-w64-mingw32.lld;
+      };
+  };
+
+  nixConfig = {
+    binaryCachePublicKeys = ["nixbld.m-labs.hk-1:5aSRVA5b320xbNvu30tqxVPXpld73bhtOeH6uAjRyHc="];
+    binaryCaches = ["https://nixbld.m-labs.hk" "https://cache.nixos.org"];
+  };
+}

nac3artiq/Cargo.toml

@@ -0,0 +1,24 @@
+[package]
+name = "nac3artiq"
+version = "0.1.0"
+authors = ["M-Labs"]
+edition = "2018"
+
+[lib]
+name = "nac3artiq"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = { version = "0.14", features = ["extension-module"] }
+parking_lot = "0.11"
+tempfile = "3"
+nac3parser = { path = "../nac3parser" }
+nac3core = { path = "../nac3core" }
+
+[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 = []

nac3artiq/demo/demo.py

@@ -0,0 +1,26 @@
+from min_artiq import *
+
+
+@nac3
+class Demo:
+    core: KernelInvariant[Core]
+    led0: KernelInvariant[TTLOut]
+    led1: KernelInvariant[TTLOut]
+
+    def __init__(self):
+        self.core = Core()
+        self.led0 = TTLOut(self.core, 18)
+        self.led1 = TTLOut(self.core, 19)
+
+    @kernel
+    def run(self):
+        self.core.reset()
+        while True:
+            with parallel:
+                self.led0.pulse(100.*ms)
+                self.led1.pulse(100.*ms)
+            self.core.delay(100.*ms)
+
+
+if __name__ == "__main__":
+    Demo().run()

nac3artiq/demo/device_db.py

@@ -0,0 +1,16 @@
+# python demo.py
+# artiq_run module.elf
+
+device_db = {
+    "core": {
+        "type": "local",
+        "module": "artiq.coredevice.core",
+        "class": "Core",
+        "arguments": {
+            "host": "kc705",
+            "ref_period": 1e-9,
+            "ref_multiplier": 8,
+            "target": "rv32g"
+        }
+    },
+}

nac3artiq/demo/embedding_map.py

@@ -0,0 +1,59 @@
+class EmbeddingMap:
+    def __init__(self):
+        self.object_inverse_map = {}
+        self.object_map = {}
+        self.string_map = {}
+        self.string_reverse_map = {}
+        self.function_map = {}
+        self.attributes_writeback = []
+
+        # preallocate exception names
+        self.preallocate_runtime_exception_names(["RuntimeError",
+                                          "RTIOUnderflow",
+                                          "RTIOOverflow",
+                                          "RTIODestinationUnreachable",
+                                          "DMAError",
+                                          "I2CError",
+                                          "CacheError",
+                                          "SPIError",
+                                          "0:ZeroDivisionError",
+                                          "0:IndexError",
+                                          "0:UnwrapNoneError"])
+
+    def preallocate_runtime_exception_names(self, names):
+        for i, name in enumerate(names):
+            if ":" not in name:
+                name = "0:artiq.coredevice.exceptions." + name
+            exn_id = self.store_str(name)
+            assert exn_id == i
+
+    def store_function(self, key, fun):
+        self.function_map[key] = fun
+        return key
+
+    def store_object(self, obj):
+        obj_id = id(obj)
+        if obj_id in self.object_inverse_map:
+            return self.object_inverse_map[obj_id]
+        key = len(self.object_map) + 1
+        self.object_map[key] = obj
+        self.object_inverse_map[obj_id] = key
+        return key
+
+    def store_str(self, s):
+        if s in self.string_reverse_map:
+            return self.string_reverse_map[s]
+        key = len(self.string_map)
+        self.string_map[key] = s
+        self.string_reverse_map[s] = key
+        return key
+
+    def retrieve_function(self, key):
+        return self.function_map[key]
+
+    def retrieve_object(self, key):
+        return self.object_map[key]
+
+    def retrieve_str(self, key):
+        return self.string_map[key]
+

nac3artiq/demo/min_artiq.py

@@ -0,0 +1,283 @@
+from inspect import getfullargspec
+from functools import wraps
+from types import SimpleNamespace
+from numpy import int32, int64
+from typing import Generic, TypeVar
+from math import floor, ceil
+
+import nac3artiq
+from embedding_map import EmbeddingMap
+
+
+__all__ = [
+    "Kernel", "KernelInvariant", "virtual",
+    "Option", "Some", "none", "UnwrapNoneError",
+    "round64", "floor64", "ceil64",
+    "extern", "kernel", "portable", "nac3",
+    "rpc", "ms", "us", "ns",
+    "print_int32", "print_int64",
+    "Core", "TTLOut",
+    "parallel", "sequential"
+]
+
+
+T = TypeVar('T')
+
+class Kernel(Generic[T]):
+    pass
+
+class KernelInvariant(Generic[T]):
+    pass
+
+# The virtual class must exist before nac3artiq.NAC3 is created.
+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)
+
+def round64(x):
+    return round(x)
+
+def floor64(x):
+    return floor(x)
+
+def ceil64(x):
+    return ceil(x)
+
+
+import device_db
+core_arguments = device_db.device_db["core"]["arguments"]
+
+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()
+registered_classes = set()
+
+def register_function(fun):
+    assert allow_registration
+    registered_functions.add(fun)
+
+def register_class(cls):
+    assert allow_registration
+    registered_classes.add(cls)
+
+
+def extern(function):
+    """Decorates a function declaration defined by the core device runtime."""
+    register_function(function)
+    return function
+
+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."""
+    register_function(function_or_method)
+    argspec = getfullargspec(function_or_method)
+    if argspec.args and argspec.args[0] == "self":
+        @wraps(function_or_method)
+        def run_on_core(self, *args, **kwargs):
+            fake_method = SimpleNamespace(__self__=self, __name__=function_or_method.__name__)
+            self.core.run(fake_method, *args, **kwargs)
+    else:
+        @wraps(function_or_method)
+        def run_on_core(*args, **kwargs):
+            raise RuntimeError("Kernel functions need explicit core.run()")
+    return run_on_core
+
+
+def portable(function):
+    """Decorates a function or method to be executed on the same device (host/core device) as the caller."""
+    register_function(function)
+    return function
+
+
+def nac3(cls):
+    """
+    Decorates a class to be analyzed by NAC3.
+    All classes containing kernels or portable methods must use this decorator.
+    """
+    register_class(cls)
+    return cls
+
+
+ms = 1e-3
+us = 1e-6
+ns = 1e-9
+
+@extern
+def rtio_init():
+    raise NotImplementedError("syscall not simulated")
+
+
+@extern
+def rtio_get_counter() -> int64:
+    raise NotImplementedError("syscall not simulated")
+
+
+@extern
+def rtio_output(target: int32, data: int32):
+    raise NotImplementedError("syscall not simulated")
+
+
+@extern
+def rtio_input_timestamp(timeout_mu: int64, channel: int32) -> int64:
+    raise NotImplementedError("syscall not simulated")
+
+
+@extern
+def rtio_input_data(channel: int32) -> int32:
+    raise NotImplementedError("syscall not simulated")
+
+
+# These is not part of ARTIQ and only available in runkernel. Defined here for convenience.
+@extern
+def print_int32(x: int32):
+    raise NotImplementedError("syscall not simulated")
+
+
+@extern
+def print_int64(x: int64):
+    raise NotImplementedError("syscall not simulated")
+
+
+@nac3
+class Core:
+    ref_period: KernelInvariant[float]
+
+    def __init__(self):
+        self.ref_period = core_arguments["ref_period"]
+
+    def run(self, method, *args, **kwargs):
+        global allow_registration
+
+        embedding = EmbeddingMap()
+
+        if allow_registration:
+            compiler.analyze(registered_functions, registered_classes)
+            allow_registration = False
+
+        if hasattr(method, "__self__"):
+            obj = method.__self__
+            name = method.__name__
+        else:
+            obj = method
+            name = ""
+
+        compiler.compile_method_to_file(obj, name, args, "module.elf", embedding)
+
+    @kernel
+    def reset(self):
+        rtio_init()
+        at_mu(rtio_get_counter() + int64(125000))
+
+    @kernel
+    def break_realtime(self):
+        min_now = rtio_get_counter() + int64(125000)
+        if now_mu() < min_now:
+            at_mu(min_now)
+
+    @portable
+    def seconds_to_mu(self, seconds: float) -> int64:
+        return int64(round(seconds/self.ref_period))
+
+    @portable
+    def mu_to_seconds(self, mu: int64) -> float:
+        return float(mu)*self.ref_period
+
+    @kernel
+    def delay(self, dt: float):
+        delay_mu(self.seconds_to_mu(dt))
+
+
+@nac3
+class TTLOut:
+    core: KernelInvariant[Core]
+    channel: KernelInvariant[int32]
+    target_o: KernelInvariant[int32]
+
+    def __init__(self, core: Core, channel: int32):
+        self.core = core
+        self.channel = channel
+        self.target_o = channel << 8
+
+    @kernel
+    def output(self):
+        pass
+
+    @kernel
+    def set_o(self, o: bool):
+        rtio_output(self.target_o, 1 if o else 0)
+
+    @kernel
+    def on(self):
+        self.set_o(True)
+
+    @kernel
+    def off(self):
+        self.set_o(False)
+
+    @kernel
+    def pulse_mu(self, duration: int64):
+        self.on()
+        delay_mu(duration)
+        self.off()
+
+    @kernel
+    def pulse(self, duration: float):
+        self.on()
+        self.core.delay(duration)
+        self.off()
+
+@nac3
+class KernelContextManager:
+    @kernel
+    def __enter__(self):
+        pass
+
+    @kernel
+    def __exit__(self):
+        pass
+
+@nac3
+class UnwrapNoneError(Exception):
+    """raised when unwrapping a none value"""
+    artiq_builtin = True
+
+parallel = KernelContextManager()
+sequential = KernelContextManager()

nac3artiq/demo/nac3artiq.so

@@ -0,0 +1 @@
+../../target/release/libnac3artiq.so

nac3artiq/src/codegen.rs

@@ -0,0 +1,575 @@
+use nac3core::{
+    codegen::{
+        expr::gen_call,
+        stmt::{gen_block, gen_with},
+        CodeGenContext, CodeGenerator,
+    },
+    symbol_resolver::ValueEnum,
+    toplevel::{DefinitionId, GenCall},
+    typecheck::typedef::{FunSignature, FuncArg, Type, TypeEnum}
+};
+
+use nac3parser::ast::{Expr, ExprKind, Located, Stmt, StmtKind, StrRef};
+
+use inkwell::{
+    context::Context, module::Linkage, types::IntType, values::BasicValueEnum, AddressSpace,
+};
+
+use pyo3::{PyObject, PyResult, Python, types::{PyDict, PyList}};
+
+use crate::{symbol_resolver::InnerResolver, timeline::TimeFns};
+
+use std::{
+    collections::hash_map::DefaultHasher,
+    collections::HashMap,
+    hash::{Hash, Hasher},
+    sync::Arc,
+};
+
+pub struct ArtiqCodeGenerator<'a> {
+    name: String,
+    size_t: u32,
+    name_counter: u32,
+    start: Option<Expr<Option<Type>>>,
+    end: Option<Expr<Option<Type>>>,
+    timeline: &'a (dyn TimeFns + Sync),
+}
+
+impl<'a> ArtiqCodeGenerator<'a> {
+    pub fn new(
+        name: String,
+        size_t: u32,
+        timeline: &'a (dyn TimeFns + Sync),
+    ) -> ArtiqCodeGenerator<'a> {
+        assert!(size_t == 32 || size_t == 64);
+        ArtiqCodeGenerator { name, size_t, name_counter: 0, start: None, end: None, timeline }
+    }
+}
+
+impl<'b> CodeGenerator for ArtiqCodeGenerator<'b> {
+    fn get_name(&self) -> &str {
+        &self.name
+    }
+
+    fn get_size_type<'ctx>(&self, ctx: &'ctx Context) -> IntType<'ctx> {
+        if self.size_t == 32 {
+            ctx.i32_type()
+        } else {
+            ctx.i64_type()
+        }
+    }
+
+    fn gen_call<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        obj: Option<(Type, ValueEnum<'ctx>)>,
+        fun: (&FunSignature, DefinitionId),
+        params: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
+    ) -> Result<Option<BasicValueEnum<'ctx>>, String> {
+        let result = gen_call(self, ctx, obj, fun, params)?;
+        if let Some(end) = self.end.clone() {
+            let old_end = self.gen_expr(ctx, &end)?.unwrap().to_basic_value_enum(ctx, self, end.custom.unwrap())?;
+            let now = self.timeline.emit_now_mu(ctx);
+            let smax = ctx.module.get_function("llvm.smax.i64").unwrap_or_else(|| {
+                let i64 = ctx.ctx.i64_type();
+                ctx.module.add_function(
+                    "llvm.smax.i64",
+                    i64.fn_type(&[i64.into(), i64.into()], false),
+                    None,
+                )
+            });
+            let max = ctx
+                .builder
+                .build_call(smax, &[old_end.into(), now.into()], "smax")
+                .try_as_basic_value()
+                .left()
+                .unwrap();
+            let end_store = self.gen_store_target(ctx, &end)?;
+            ctx.builder.build_store(end_store, max);
+        }
+        if let Some(start) = self.start.clone() {
+            let start_val = self.gen_expr(ctx, &start)?.unwrap().to_basic_value_enum(ctx, self, start.custom.unwrap())?;
+            self.timeline.emit_at_mu(ctx, start_val);
+        }
+        Ok(result)
+    }
+
+    fn gen_with<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String> {
+        if let StmtKind::With { items, body, .. } = &stmt.node {
+            if items.len() == 1 && items[0].optional_vars.is_none() {
+                let item = &items[0];
+                // Behavior of parallel and sequential:
+                // Each function call (indirectly, can be inside a sequential block) within a parallel
+                // block will update the end variable to the maximum now_mu in the block.
+                // Each function call directly inside a parallel block will reset the timeline after
+                // execution. A parallel block within a sequential block (or not within any block) will
+                // set the timeline to the max now_mu within the block (and the outer max now_mu will also
+                // be updated).
+                //
+                // Implementation: We track the start and end separately.
+                // - If there is a start variable, it indicates that we are directly inside a
+                // parallel block and we have to reset the timeline after every function call.
+                // - If there is a end variable, it indicates that we are (indirectly) inside a
+                // parallel block, and we should update the max end value.
+                if let ExprKind::Name { id, ctx: name_ctx } = &item.context_expr.node {
+                    if id == &"parallel".into() {
+                        let old_start = self.start.take();
+                        let old_end = self.end.take();
+                        let now = if let Some(old_start) = &old_start {
+                            self.gen_expr(ctx, old_start)?.unwrap().to_basic_value_enum(ctx, self, old_start.custom.unwrap())?
+                        } else {
+                            self.timeline.emit_now_mu(ctx)
+                        };
+                        // Emulate variable allocation, as we need to use the CodeGenContext
+                        // HashMap to store our variable due to lifetime limitation
+                        // Note: we should be able to store variables directly if generic
+                        // associative type is used by limiting the lifetime of CodeGenerator to
+                        // the LLVM Context.
+                        // The name is guaranteed to be unique as users cannot use this as variable
+                        // name.
+                        self.start = old_start.clone().map_or_else(
+                            || {
+                                let start = format!("with-{}-start", self.name_counter).into();
+                                let start_expr = Located {
+                                    // location does not matter at this point
+                                    location: stmt.location,
+                                    node: ExprKind::Name { id: start, ctx: name_ctx.clone() },
+                                    custom: Some(ctx.primitives.int64),
+                                };
+                                let start = self.gen_store_target(ctx, &start_expr)?;
+                                ctx.builder.build_store(start, now);
+                                Ok(Some(start_expr)) as Result<_, String>
+                            },
+                            |v| Ok(Some(v)),
+                        )?;
+                        let end = format!("with-{}-end", self.name_counter).into();
+                        let end_expr = Located {
+                            // location does not matter at this point
+                            location: stmt.location,
+                            node: ExprKind::Name { id: end, ctx: name_ctx.clone() },
+                            custom: Some(ctx.primitives.int64),
+                        };
+                        let end = self.gen_store_target(ctx, &end_expr)?;
+                        ctx.builder.build_store(end, now);
+                        self.end = Some(end_expr);
+                        self.name_counter += 1;
+                        gen_block(self, ctx, body.iter())?;
+                        let current = ctx.builder.get_insert_block().unwrap();
+                        // if the current block is terminated, move before the terminator
+                        // we want to set the timeline before reaching the terminator
+                        // TODO: This may be unsound if there are multiple exit paths in the
+                        // block... e.g.
+                        // if ...:
+                        //     return
+                        // Perhaps we can fix this by using actual with block?
+                        let reset_position = if let Some(terminator) = current.get_terminator() {
+                            ctx.builder.position_before(&terminator);
+                            true
+                        } else {
+                            false
+                        };
+                        // set duration
+                        let end_expr = self.end.take().unwrap();
+                        let end_val = self
+                            .gen_expr(ctx, &end_expr)?
+                            .unwrap()
+                            .to_basic_value_enum(ctx, self, end_expr.custom.unwrap())?;
+
+                        // inside a sequential block
+                        if old_start.is_none() {
+                            self.timeline.emit_at_mu(ctx, end_val);
+                        }
+                        // inside a parallel block, should update the outer max now_mu
+                        if let Some(old_end) = &old_end {
+                            let outer_end_val = self
+                                .gen_expr(ctx, old_end)?
+                                .unwrap()
+                                .to_basic_value_enum(ctx, self, old_end.custom.unwrap())?;
+                            let smax =
+                                ctx.module.get_function("llvm.smax.i64").unwrap_or_else(|| {
+                                    let i64 = ctx.ctx.i64_type();
+                                    ctx.module.add_function(
+                                        "llvm.smax.i64",
+                                        i64.fn_type(&[i64.into(), i64.into()], false),
+                                        None,
+                                    )
+                                });
+                            let max = ctx
+                                .builder
+                                .build_call(smax, &[end_val.into(), outer_end_val.into()], "smax")
+                                .try_as_basic_value()
+                                .left()
+                                .unwrap();
+                            let outer_end = self.gen_store_target(ctx, old_end)?;
+                            ctx.builder.build_store(outer_end, max);
+                        }
+                        self.start = old_start;
+                        self.end = old_end;
+                        if reset_position {
+                            ctx.builder.position_at_end(current);
+                        }
+                        return Ok(());
+                    } else if id == &"sequential".into() {
+                        let start = self.start.take();
+                        for stmt in body.iter() {
+                            self.gen_stmt(ctx, stmt)?;
+                            if ctx.is_terminated() {
+                                break;
+                            }
+                        }
+                        self.start = start;
+                        return Ok(());
+                    }
+                }
+            }
+            // not parallel/sequential
+            gen_with(self, ctx, stmt)
+        } else {
+            unreachable!()
+        }
+    }
+}
+
+fn gen_rpc_tag<'ctx, 'a>(
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    ty: Type,
+    buffer: &mut Vec<u8>,
+) -> Result<(), String> {
+    use nac3core::typecheck::typedef::TypeEnum::*;
+
+    let int32 = ctx.primitives.int32;
+    let int64 = ctx.primitives.int64;
+    let float = ctx.primitives.float;
+    let bool = ctx.primitives.bool;
+    let str = ctx.primitives.str;
+    let none = ctx.primitives.none;
+
+    if ctx.unifier.unioned(ty, int32) {
+        buffer.push(b'i');
+    } else if ctx.unifier.unioned(ty, int64) {
+        buffer.push(b'I');
+    } else if ctx.unifier.unioned(ty, float) {
+        buffer.push(b'f');
+    } else if ctx.unifier.unioned(ty, bool) {
+        buffer.push(b'b');
+    } else if ctx.unifier.unioned(ty, str) {
+        buffer.push(b's');
+    } else if ctx.unifier.unioned(ty, none) {
+        buffer.push(b'n');
+    } else {
+        let ty_enum = ctx.unifier.get_ty(ty);
+        match &*ty_enum {
+            TTuple { ty } => {
+                buffer.push(b't');
+                buffer.push(ty.len() as u8);
+                for ty in ty {
+                    gen_rpc_tag(ctx, *ty, buffer)?;
+                }
+            }
+            TList { ty } => {
+                buffer.push(b'l');
+                gen_rpc_tag(ctx, *ty, buffer)?;
+            }
+            _ => return Err(format!("Unsupported type: {:?}", ctx.unifier.stringify(ty))),
+        }
+    }
+    Ok(())
+}
+
+fn rpc_codegen_callback_fn<'ctx, 'a>(
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    obj: Option<(Type, ValueEnum<'ctx>)>,
+    fun: (&FunSignature, DefinitionId),
+    args: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
+    generator: &mut dyn CodeGenerator,
+) -> Result<Option<BasicValueEnum<'ctx>>, String> {
+    let ptr_type = ctx.ctx.i8_type().ptr_type(inkwell::AddressSpace::Generic);
+    let size_type = generator.get_size_type(ctx.ctx);
+    let int8 = ctx.ctx.i8_type();
+    let int32 = ctx.ctx.i32_type();
+    let tag_ptr_type = ctx.ctx.struct_type(&[ptr_type.into(), size_type.into()], false);
+
+    let service_id = int32.const_int(fun.1.0 as u64, false);
+    // -- setup rpc tags
+    let mut tag = Vec::new();
+    if obj.is_some() {
+        tag.push(b'O');
+    }
+    for arg in fun.0.args.iter() {
+        gen_rpc_tag(ctx, arg.ty, &mut tag)?;
+    }
+    tag.push(b':');
+    gen_rpc_tag(ctx, fun.0.ret, &mut tag)?;
+
+    let mut hasher = DefaultHasher::new();
+    tag.hash(&mut hasher);
+    let hash = format!("{}", hasher.finish());
+
+    let tag_ptr = ctx
+        .module
+        .get_global(hash.as_str())
+        .unwrap_or_else(|| {
+            let tag_arr_ptr = ctx.module.add_global(
+                int8.array_type(tag.len() as u32),
+                None,
+                format!("tagptr{}", fun.1 .0).as_str(),
+            );
+            tag_arr_ptr.set_initializer(&int8.const_array(
+                &tag.iter().map(|v| int8.const_int(*v as u64, false)).collect::<Vec<_>>(),
+            ));
+            tag_arr_ptr.set_linkage(Linkage::Private);
+            let tag_ptr = ctx.module.add_global(tag_ptr_type, None, &hash);
+            tag_ptr.set_linkage(Linkage::Private);
+            tag_ptr.set_initializer(&ctx.ctx.const_struct(
+                &[
+                    tag_arr_ptr.as_pointer_value().const_cast(ptr_type).into(),
+                    size_type.const_int(tag.len() as u64, false).into(),
+                ],
+                false,
+            ));
+            tag_ptr
+        })
+        .as_pointer_value();
+
+    let arg_length = args.len() + if obj.is_some() { 1 } else { 0 };
+
+    let stacksave = ctx.module.get_function("llvm.stacksave").unwrap_or_else(|| {
+        ctx.module.add_function("llvm.stacksave", ptr_type.fn_type(&[], false), None)
+    });
+    let stackrestore = ctx.module.get_function("llvm.stackrestore").unwrap_or_else(|| {
+        ctx.module.add_function(
+            "llvm.stackrestore",
+            ctx.ctx.void_type().fn_type(&[ptr_type.into()], false),
+            None,
+        )
+    });
+
+    let stackptr = ctx.builder.build_call(stacksave, &[], "rpc.stack");
+    let args_ptr = ctx.builder.build_array_alloca(
+        ptr_type,
+        ctx.ctx.i32_type().const_int(arg_length as u64, false),
+        "argptr",
+    );
+
+    // -- rpc args handling
+    let mut keys = fun.0.args.clone();
+    let mut mapping = HashMap::new();
+    for (key, value) in args.into_iter() {
+        mapping.insert(key.unwrap_or_else(|| keys.remove(0).name), value);
+    }
+    // default value handling
+    for k in keys.into_iter() {
+        mapping.insert(
+            k.name,
+            ctx.gen_symbol_val(generator, &k.default_value.unwrap(), k.ty).into()
+        );
+    }
+    // reorder the parameters
+    let mut real_params = fun
+        .0
+        .args
+        .iter()
+        .map(|arg| mapping.remove(&arg.name).unwrap().to_basic_value_enum(ctx, generator, arg.ty))
+        .collect::<Result<Vec<_>, _>>()?;
+    if let Some(obj) = obj {
+        if let ValueEnum::Static(obj) = obj.1 {
+            real_params.insert(0, obj.get_const_obj(ctx, generator));
+        } else {
+            // should be an error here...
+            panic!("only host object is allowed");
+        }
+    }
+
+    for (i, arg) in real_params.iter().enumerate() {
+        let arg_slot = ctx.builder.build_alloca(arg.get_type(), &format!("rpc.arg{}", i));
+        ctx.builder.build_store(arg_slot, *arg);
+        let arg_slot = ctx.builder.build_bitcast(arg_slot, ptr_type, "rpc.arg");
+        let arg_ptr = unsafe {
+            ctx.builder.build_gep(
+                args_ptr,
+                &[int32.const_int(i as u64, false)],
+                &format!("rpc.arg{}", i),
+            )
+        };
+        ctx.builder.build_store(arg_ptr, arg_slot);
+    }
+
+    // call
+    let rpc_send = ctx.module.get_function("rpc_send").unwrap_or_else(|| {
+        ctx.module.add_function(
+            "rpc_send",
+            ctx.ctx.void_type().fn_type(
+                &[
+                    int32.into(),
+                    tag_ptr_type.ptr_type(AddressSpace::Generic).into(),
+                    ptr_type.ptr_type(AddressSpace::Generic).into(),
+                ],
+                false,
+            ),
+            None,
+        )
+    });
+    ctx.builder.build_call(
+        rpc_send,
+        &[service_id.into(), tag_ptr.into(), args_ptr.into()],
+        "rpc.send",
+    );
+
+    // reclaim stack space used by arguments
+    ctx.builder.build_call(
+        stackrestore,
+        &[stackptr.try_as_basic_value().unwrap_left().into()],
+        "rpc.stackrestore",
+    );
+
+    // -- receive value:
+    // T result = {
+    //   void *ret_ptr = alloca(sizeof(T));
+    //   void *ptr = ret_ptr;
+    //   loop: int size = rpc_recv(ptr);
+    //   // Non-zero: Provide `size` bytes of extra storage for variable-length data.
+    //   if(size) { ptr = alloca(size); goto loop; }
+    //   else *(T*)ret_ptr
+    // }
+    let rpc_recv = ctx.module.get_function("rpc_recv").unwrap_or_else(|| {
+        ctx.module.add_function("rpc_recv", int32.fn_type(&[ptr_type.into()], false), None)
+    });
+
+    if ctx.unifier.unioned(fun.0.ret, ctx.primitives.none) {
+        ctx.build_call_or_invoke(rpc_recv, &[ptr_type.const_null().into()], "rpc_recv");
+        return Ok(None);
+    }
+
+    let prehead_bb = ctx.builder.get_insert_block().unwrap();
+    let current_function = prehead_bb.get_parent().unwrap();
+    let head_bb = ctx.ctx.append_basic_block(current_function, "rpc.head");
+    let alloc_bb = ctx.ctx.append_basic_block(current_function, "rpc.continue");
+    let tail_bb = ctx.ctx.append_basic_block(current_function, "rpc.tail");
+
+    let ret_ty = ctx.get_llvm_type(generator, fun.0.ret);
+    let need_load = !ret_ty.is_pointer_type();
+    let slot = ctx.builder.build_alloca(ret_ty, "rpc.ret.slot");
+    let slotgen = ctx.builder.build_bitcast(slot, ptr_type, "rpc.ret.ptr");
+    ctx.builder.build_unconditional_branch(head_bb);
+    ctx.builder.position_at_end(head_bb);
+
+    let phi = ctx.builder.build_phi(ptr_type, "rpc.ptr");
+    phi.add_incoming(&[(&slotgen, prehead_bb)]);
+    let alloc_size = ctx
+        .build_call_or_invoke(rpc_recv, &[phi.as_basic_value()], "rpc.size.next")
+        .unwrap()
+        .into_int_value();
+    let is_done = ctx.builder.build_int_compare(
+        inkwell::IntPredicate::EQ,
+        int32.const_zero(),
+        alloc_size,
+        "rpc.done",
+    );
+
+    ctx.builder.build_conditional_branch(is_done, tail_bb, alloc_bb);
+    ctx.builder.position_at_end(alloc_bb);
+
+    let alloc_ptr = ctx.builder.build_array_alloca(ptr_type, alloc_size, "rpc.alloc");
+    let alloc_ptr = ctx.builder.build_bitcast(alloc_ptr, ptr_type, "rpc.alloc.ptr");
+    phi.add_incoming(&[(&alloc_ptr, alloc_bb)]);
+    ctx.builder.build_unconditional_branch(head_bb);
+
+    ctx.builder.position_at_end(tail_bb);
+
+    let result = ctx.builder.build_load(slot, "rpc.result");
+    if need_load {
+        ctx.builder.build_call(
+            stackrestore,
+            &[stackptr.try_as_basic_value().unwrap_left().into()],
+            "rpc.stackrestore",
+        );
+    }
+    Ok(Some(result))
+}
+
+pub fn attributes_writeback<'ctx, 'a>(
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    generator: &mut dyn CodeGenerator,
+    inner_resolver: &InnerResolver,
+    host_attributes: PyObject,
+) -> Result<(), String> {
+    Python::with_gil(|py| -> PyResult<Result<(), String>> {
+        let host_attributes = host_attributes.cast_as::<PyList>(py)?;
+        let top_levels = ctx.top_level.definitions.read();
+        let globals = inner_resolver.global_value_ids.read();
+        let int32 = ctx.ctx.i32_type();
+        let zero = int32.const_zero();
+        let mut values = Vec::new();
+        let mut scratch_buffer = Vec::new();
+        for (_, val) in globals.iter() {
+            let val = val.as_ref(py);
+            let ty = inner_resolver.get_obj_type(py, val, &mut ctx.unifier, &top_levels, &ctx.primitives)?;
+            if let Err(ty) = ty {
+                return Ok(Err(ty))
+            }
+            let ty = ty.unwrap();
+            match &*ctx.unifier.get_ty(ty) {
+                TypeEnum::TObj { fields, obj_id, .. }
+                    if *obj_id != ctx.primitives.option.get_obj_id(&ctx.unifier) =>
+                {
+                    // we only care about primitive attributes
+                    // for non-primitive attributes, they should be in another global
+                    let mut attributes = Vec::new();
+                    let obj = inner_resolver.get_obj_value(py, val, ctx, generator, ty)?.unwrap();
+                    for (name, (field_ty, is_mutable)) in fields.iter() {
+                        if !is_mutable {
+                            continue
+                        }
+                        if gen_rpc_tag(ctx, *field_ty, &mut scratch_buffer).is_ok() {
+                            attributes.push(name.to_string());
+                            let index = ctx.get_attr_index(ty, *name);
+                            values.push((*field_ty, ctx.build_gep_and_load(
+                                            obj.into_pointer_value(),
+                                            &[zero, int32.const_int(index as u64, false)])));
+                        }
+                    }
+                    if !attributes.is_empty() {
+                        let pydict = PyDict::new(py);
+                        pydict.set_item("obj", val)?;
+                        pydict.set_item("fields", attributes)?;
+                        host_attributes.append(pydict)?;
+                    }
+                },
+                TypeEnum::TList { ty: elem_ty } => {
+                    if gen_rpc_tag(ctx, *elem_ty, &mut scratch_buffer).is_ok() {
+                        let pydict = PyDict::new(py);
+                        pydict.set_item("obj", val)?;
+                        host_attributes.append(pydict)?;
+                        values.push((ty, inner_resolver.get_obj_value(py, val, ctx, generator, ty)?.unwrap()));
+                    }
+                },
+                _ => {}
+            }
+        }
+        let fun = FunSignature {
+            args: values.iter().enumerate().map(|(i, (ty, _))| FuncArg {
+                name: i.to_string().into(),
+                ty: *ty,
+                default_value: None
+            }).collect(),
+            ret: ctx.primitives.none,
+            vars: Default::default()
+        };
+        let args: Vec<_> = values.into_iter().map(|(_, val)| (None, ValueEnum::Dynamic(val))).collect();
+        if let Err(e) = rpc_codegen_callback_fn(ctx, None, (&fun, DefinitionId(0)), args, generator) {
+            return Ok(Err(e));
+        }
+        Ok(Ok(()))
+    }).unwrap()?;
+    Ok(())
+}
+
+pub fn rpc_codegen_callback() -> Arc<GenCall> {
+    Arc::new(GenCall::new(Box::new(|ctx, obj, fun, args, generator| {
+        rpc_codegen_callback_fn(ctx, obj, fun, args, generator)
+    })))
+}

nac3artiq/src/kernel.ld

@@ -0,0 +1,56 @@
+/* Force ld to make the ELF header as loadable. */
+PHDRS
+{
+    headers     PT_LOAD FILEHDR PHDRS ;
+    text        PT_LOAD ;
+    data        PT_LOAD ;
+    dynamic     PT_DYNAMIC ;
+    eh_frame    PT_GNU_EH_FRAME ;
+}
+
+SECTIONS
+{
+    /* Push back .text section enough so that ld.lld not complain */
+    . = SIZEOF_HEADERS;
+
+    .text :
+    {
+        *(.text .text.*)
+    } : text
+
+    .rodata :
+    {
+        *(.rodata .rodata.*)
+    }
+
+    .eh_frame :
+    {
+        KEEP(*(.eh_frame))
+    } : text
+
+    .eh_frame_hdr :
+    {
+        KEEP(*(.eh_frame_hdr))
+    } : text : eh_frame
+
+    .data :
+    {
+        *(.data)
+    } : data
+
+    .dynamic :
+    {
+        *(.dynamic)
+    } : data : dynamic
+
+    .bss (NOLOAD) : ALIGN(4)
+    {
+        __bss_start = .;
+        *(.sbss .sbss.* .bss .bss.*);
+        . = ALIGN(4);
+        _end = .;
+    }
+
+    . = ALIGN(0x1000);
+    _sstack_guard = .;
+}

nac3artiq/src/lib.rs

@@ -0,0 +1,922 @@
+use std::collections::{HashMap, HashSet};
+use std::fs;
+use std::process::Command;
+use std::rc::Rc;
+use std::sync::Arc;
+
+use inkwell::{
+    memory_buffer::MemoryBuffer,
+    passes::{PassManager, PassManagerBuilder},
+    targets::*,
+    OptimizationLevel,
+};
+use nac3core::codegen::gen_func_impl;
+use nac3core::toplevel::builtins::get_exn_constructor;
+use nac3core::typecheck::typedef::{TypeEnum, Unifier};
+use nac3parser::{
+    ast::{self, ExprKind, Stmt, StmtKind, StrRef},
+    parser::{self, parse_program},
+};
+use pyo3::prelude::*;
+use pyo3::{exceptions, types::PyBytes, types::PyDict, types::PySet};
+use pyo3::create_exception;
+
+use parking_lot::{Mutex, RwLock};
+
+use nac3core::{
+    codegen::irrt::load_irrt,
+    codegen::{concrete_type::ConcreteTypeStore, CodeGenTask, WithCall, WorkerRegistry},
+    symbol_resolver::SymbolResolver,
+    toplevel::{
+        composer::{ComposerConfig, TopLevelComposer},
+        DefinitionId, GenCall, TopLevelDef,
+    },
+    typecheck::typedef::{FunSignature, FuncArg},
+    typecheck::{type_inferencer::PrimitiveStore, typedef::Type},
+};
+
+use tempfile::{self, TempDir};
+
+use crate::codegen::attributes_writeback;
+use crate::{
+    codegen::{rpc_codegen_callback, ArtiqCodeGenerator},
+    symbol_resolver::{InnerResolver, PythonHelper, Resolver, DeferredEvaluationStore},
+};
+
+mod codegen;
+mod symbol_resolver;
+mod timeline;
+
+use timeline::TimeFns;
+
+#[derive(PartialEq, Clone, Copy)]
+enum Isa {
+    Host,
+    RiscV32G,
+    RiscV32IMA,
+    CortexA9,
+}
+
+#[derive(Clone)]
+pub struct PrimitivePythonId {
+    int: u64,
+    int32: u64,
+    int64: u64,
+    uint32: u64,
+    uint64: u64,
+    float: u64,
+    float64: u64,
+    bool: u64,
+    list: u64,
+    tuple: u64,
+    typevar: u64,
+    none: u64,
+    exception: u64,
+    generic_alias: (u64, u64),
+    virtual_id: u64,
+    option: u64,
+}
+
+type TopLevelComponent = (Stmt, String, PyObject);
+
+// TopLevelComposer is unsendable as it holds the unification table, which is
+// unsendable due to Rc. Arc would cause a performance hit.
+#[pyclass(unsendable, name = "NAC3")]
+struct Nac3 {
+    isa: Isa,
+    time_fns: &'static (dyn TimeFns + Sync),
+    primitive: PrimitiveStore,
+    builtins: Vec<(StrRef, FunSignature, Arc<GenCall>)>,
+    pyid_to_def: Arc<RwLock<HashMap<u64, DefinitionId>>>,
+    primitive_ids: PrimitivePythonId,
+    working_directory: TempDir,
+    top_levels: Vec<TopLevelComponent>,
+    string_store: Arc<RwLock<HashMap<String, i32>>>,
+    exception_ids: Arc<RwLock<HashMap<usize, usize>>>,
+    deferred_eval_store: DeferredEvaluationStore
+}
+
+create_exception!(nac3artiq, CompileError, exceptions::PyException);
+
+impl Nac3 {
+    fn register_module(
+        &mut self,
+        module: PyObject,
+        registered_class_ids: &HashSet<u64>,
+    ) -> PyResult<()> {
+        let (module_name, source_file) = Python::with_gil(|py| -> PyResult<(String, String)> {
+            let module: &PyAny = module.extract(py)?;
+            Ok((module.getattr("__name__")?.extract()?, module.getattr("__file__")?.extract()?))
+        })?;
+
+        let source = fs::read_to_string(&source_file).map_err(|e| {
+            exceptions::PyIOError::new_err(format!("failed to read input file: {}", e))
+        })?;
+        let parser_result = parser::parse_program(&source, source_file.into())
+            .map_err(|e| exceptions::PySyntaxError::new_err(format!("parse error: {}", e)))?;
+
+        for mut stmt in parser_result.into_iter() {
+            let include = match stmt.node {
+                ast::StmtKind::ClassDef {
+                    ref decorator_list, ref mut body, ref mut bases, ..
+                } => {
+                    let nac3_class = decorator_list.iter().any(|decorator| {
+                        if let ast::ExprKind::Name { id, .. } = decorator.node {
+                            id.to_string() == "nac3"
+                        } else {
+                            false
+                        }
+                    });
+                    if !nac3_class {
+                        continue;
+                    }
+                    // Drop unregistered (i.e. host-only) base classes.
+                    bases.retain(|base| {
+                        Python::with_gil(|py| -> PyResult<bool> {
+                            let id_fn = PyModule::import(py, "builtins")?.getattr("id")?;
+                            match &base.node {
+                                ast::ExprKind::Name { id, .. } => {
+                                    if *id == "Exception".into() {
+                                        Ok(true)
+                                    } else {
+                                        let base_obj = module.getattr(py, id.to_string())?;
+                                        let base_id = id_fn.call1((base_obj,))?.extract()?;
+                                        Ok(registered_class_ids.contains(&base_id))
+                                    }
+                                }
+                                _ => Ok(true),
+                            }
+                        })
+                        .unwrap()
+                    });
+                    body.retain(|stmt| {
+                        if let ast::StmtKind::FunctionDef { ref decorator_list, .. } = stmt.node {
+                            decorator_list.iter().any(|decorator| {
+                                if let ast::ExprKind::Name { id, .. } = decorator.node {
+                                    id.to_string() == "kernel"
+                                        || id.to_string() == "portable"
+                                        || id.to_string() == "rpc"
+                                } else {
+                                    false
+                                }
+                            })
+                        } else {
+                            true
+                        }
+                    });
+                    true
+                }
+                ast::StmtKind::FunctionDef { ref decorator_list, .. } => {
+                    decorator_list.iter().any(|decorator| {
+                        if let ast::ExprKind::Name { id, .. } = decorator.node {
+                            let id = id.to_string();
+                            id == "extern" || id == "portable" || id == "kernel" || id == "rpc"
+                        } else {
+                            false
+                        }
+                    })
+                }
+                _ => false,
+            };
+
+            if include {
+                self.top_levels.push((stmt, module_name.clone(), module.clone()));
+            }
+        }
+        Ok(())
+    }
+
+    fn report_modinit(
+        arg_names: &[String],
+        method_name: &str,
+        resolver: Arc<dyn SymbolResolver + Send + Sync>,
+        top_level_defs: &[Arc<RwLock<TopLevelDef>>],
+        unifier: &mut Unifier,
+        primitives: &PrimitiveStore,
+    ) -> Option<String> {
+        let base_ty =
+            match resolver.get_symbol_type(unifier, top_level_defs, primitives, "base".into()) {
+                Ok(ty) => ty,
+                Err(e) => return Some(format!("type error inside object launching kernel: {}", e)),
+            };
+
+        let fun_ty = if method_name.is_empty() {
+            base_ty
+        } else if let TypeEnum::TObj { fields, .. } = &*unifier.get_ty(base_ty) {
+            match fields.get(&(*method_name).into()) {
+                Some(t) => t.0,
+                None => {
+                    return Some(format!(
+                        "object launching kernel does not have method `{}`",
+                        method_name
+                    ))
+                }
+            }
+        } else {
+            return Some("cannot launch kernel by calling a non-callable".into());
+        };
+
+        if let TypeEnum::TFunc(FunSignature { args, .. }) = &*unifier.get_ty(fun_ty) {
+            if arg_names.len() > args.len() {
+                return Some(format!(
+                    "launching kernel function with too many arguments (expect {}, found {})",
+                    args.len(),
+                    arg_names.len(),
+                ));
+            }
+            for (i, FuncArg { ty, default_value, name }) in args.iter().enumerate() {
+                let in_name = match arg_names.get(i) {
+                    Some(n) => n,
+                    None if default_value.is_none() => {
+                        return Some(format!(
+                            "argument `{}` not provided when launching kernel function",
+                            name
+                        ))
+                    }
+                    _ => break,
+                };
+                let in_ty = match resolver.get_symbol_type(
+                    unifier,
+                    top_level_defs,
+                    primitives,
+                    in_name.clone().into(),
+                ) {
+                    Ok(t) => t,
+                    Err(e) => {
+                        return Some(format!(
+                            "type error ({}) at parameter #{} when calling kernel function",
+                            e, i
+                        ))
+                    }
+                };
+                if let Err(e) = unifier.unify(in_ty, *ty) {
+                    return Some(format!(
+                        "type error ({}) at parameter #{} when calling kernel function",
+                        e.to_display(unifier).to_string(),
+                        i
+                    ));
+                }
+            }
+        } else {
+            return Some("cannot launch kernel by calling a non-callable".into());
+        }
+        None
+    }
+}
+
+fn add_exceptions(
+    composer: &mut TopLevelComposer,
+    builtin_def: &mut HashMap<StrRef, DefinitionId>,
+    builtin_ty: &mut HashMap<StrRef, Type>,
+    error_names: &[&str]
+) -> Vec<Type> {
+    let mut types = Vec::new();
+    // note: this is only for builtin exceptions, i.e. the exception name is "0:{exn}"
+    for name in error_names {
+        let def_id = composer.definition_ast_list.len();
+        let (exception_fn, exception_class, exception_cons, exception_type) = get_exn_constructor(
+            name,
+            // class id
+            def_id,
+            // constructor id
+            def_id + 1,
+            &mut composer.unifier,
+            &composer.primitives_ty
+        );
+        composer.definition_ast_list.push((Arc::new(RwLock::new(exception_class)), None));
+        composer.definition_ast_list.push((Arc::new(RwLock::new(exception_fn)), None));
+        builtin_ty.insert((*name).into(), exception_cons);
+        builtin_def.insert((*name).into(), DefinitionId(def_id));
+        types.push(exception_type);
+    }
+    types
+}
+
+#[pymethods]
+impl Nac3 {
+    #[new]
+    fn new(isa: &str, py: Python) -> PyResult<Self> {
+        let isa = match isa {
+            "host" => Isa::Host,
+            "rv32g" => Isa::RiscV32G,
+            "rv32ima" => Isa::RiscV32IMA,
+            "cortexa9" => Isa::CortexA9,
+            _ => return Err(exceptions::PyValueError::new_err("invalid ISA")),
+        };
+        let time_fns: &(dyn TimeFns + Sync) = match isa {
+            Isa::Host => &timeline::EXTERN_TIME_FNS,
+            Isa::RiscV32G => &timeline::NOW_PINNING_TIME_FNS_64,
+            Isa::RiscV32IMA => &timeline::NOW_PINNING_TIME_FNS,
+            Isa::CortexA9 => &timeline::EXTERN_TIME_FNS,
+        };
+        let primitive: PrimitiveStore = TopLevelComposer::make_primitives().0;
+        let builtins = vec![
+            (
+                "now_mu".into(),
+                FunSignature { args: vec![], ret: primitive.int64, vars: HashMap::new() },
+                Arc::new(GenCall::new(Box::new(move |ctx, _, _, _, _| {
+                    Ok(Some(time_fns.emit_now_mu(ctx)))
+                }))),
+            ),
+            (
+                "at_mu".into(),
+                FunSignature {
+                    args: vec![FuncArg {
+                        name: "t".into(),
+                        ty: primitive.int64,
+                        default_value: None,
+                    }],
+                    ret: primitive.none,
+                    vars: HashMap::new(),
+                },
+                Arc::new(GenCall::new(Box::new(move |ctx, _, fun, args, generator| {
+                    let arg_ty = fun.0.args[0].ty;
+                    let arg = args[0].1.clone().to_basic_value_enum(ctx, generator, arg_ty).unwrap();
+                    time_fns.emit_at_mu(ctx, arg);
+                    Ok(None)
+                }))),
+            ),
+            (
+                "delay_mu".into(),
+                FunSignature {
+                    args: vec![FuncArg {
+                        name: "dt".into(),
+                        ty: primitive.int64,
+                        default_value: None,
+                    }],
+                    ret: primitive.none,
+                    vars: HashMap::new(),
+                },
+                Arc::new(GenCall::new(Box::new(move |ctx, _, fun, args, generator| {
+                    let arg_ty = fun.0.args[0].ty;
+                    let arg = args[0].1.clone().to_basic_value_enum(ctx, generator, arg_ty).unwrap();
+                    time_fns.emit_delay_mu(ctx, arg);
+                    Ok(None)
+                }))),
+            ),
+        ];
+
+        let builtins_mod = PyModule::import(py, "builtins").unwrap();
+        let id_fn = builtins_mod.getattr("id").unwrap();
+        let numpy_mod = PyModule::import(py, "numpy").unwrap();
+        let typing_mod = PyModule::import(py, "typing").unwrap();
+        let types_mod = PyModule::import(py, "types").unwrap();
+
+        let get_id = |x| id_fn.call1((x,)).unwrap().extract().unwrap();
+        let get_attr_id = |obj: &PyModule, attr| id_fn.call1((obj.getattr(attr).unwrap(),))
+            .unwrap().extract().unwrap();
+        let primitive_ids = PrimitivePythonId {
+            virtual_id: get_id(
+                            builtins_mod
+                            .getattr("globals")
+                            .unwrap()
+                            .call0()
+                            .unwrap()
+                            .get_item("virtual")
+                            .unwrap(
+                        )),
+            generic_alias: (
+                get_attr_id(typing_mod, "_GenericAlias"),
+                get_attr_id(types_mod, "GenericAlias"),
+            ),
+            none: id_fn
+                .call1((builtins_mod
+                    .getattr("globals")
+                    .unwrap()
+                    .call0()
+                    .unwrap()
+                    .get_item("none")
+                    .unwrap(),))
+                .unwrap()
+                .extract()
+                .unwrap(),
+            typevar: get_attr_id(typing_mod, "TypeVar"),
+            int: get_attr_id(builtins_mod, "int"),
+            int32: get_attr_id(numpy_mod, "int32"),
+            int64: get_attr_id(numpy_mod, "int64"),
+            uint32: get_attr_id(numpy_mod, "uint32"),
+            uint64: get_attr_id(numpy_mod, "uint64"),
+            bool: get_attr_id(builtins_mod, "bool"),
+            float: get_attr_id(builtins_mod, "float"),
+            float64: get_attr_id(numpy_mod, "float64"),
+            list: get_attr_id(builtins_mod, "list"),
+            tuple: get_attr_id(builtins_mod, "tuple"),
+            exception: get_attr_id(builtins_mod, "Exception"),
+            option: id_fn
+                .call1((builtins_mod
+                    .getattr("globals")
+                    .unwrap()
+                    .call0()
+                    .unwrap()
+                    .get_item("Option")
+                    .unwrap(),))
+                .unwrap()
+                .extract()
+                .unwrap(),
+        };
+
+        let working_directory = tempfile::Builder::new().prefix("nac3-").tempdir().unwrap();
+        fs::write(working_directory.path().join("kernel.ld"), include_bytes!("kernel.ld")).unwrap();
+
+        Ok(Nac3 {
+            isa,
+            time_fns,
+            primitive,
+            builtins,
+            primitive_ids,
+            top_levels: Default::default(),
+            pyid_to_def: Default::default(),
+            working_directory,
+            string_store: Default::default(),
+            exception_ids: Default::default(),
+            deferred_eval_store: DeferredEvaluationStore::new(),
+        })
+    }
+
+    fn analyze(&mut self, functions: &PySet, classes: &PySet) -> PyResult<()> {
+        let (modules, class_ids) =
+            Python::with_gil(|py| -> PyResult<(HashMap<u64, PyObject>, HashSet<u64>)> {
+                let mut modules: HashMap<u64, PyObject> = HashMap::new();
+                let mut class_ids: HashSet<u64> = HashSet::new();
+
+                let id_fn = PyModule::import(py, "builtins")?.getattr("id")?;
+                let getmodule_fn = PyModule::import(py, "inspect")?.getattr("getmodule")?;
+
+                for function in functions.iter() {
+                    let module = getmodule_fn.call1((function,))?.extract()?;
+                    modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                }
+                for class in classes.iter() {
+                    let module = getmodule_fn.call1((class,))?.extract()?;
+                    modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                    class_ids.insert(id_fn.call1((class,))?.extract()?);
+                }
+                Ok((modules, class_ids))
+            })?;
+
+        for module in modules.into_values() {
+            self.register_module(module, &class_ids)?;
+        }
+        Ok(())
+    }
+
+    fn compile_method_to_file(
+        &mut self,
+        obj: &PyAny,
+        method_name: &str,
+        args: Vec<&PyAny>,
+        filename: &str,
+        embedding_map: &PyAny,
+        py: Python,
+    ) -> PyResult<()> {
+        let (mut composer, mut builtins_def, mut builtins_ty) = TopLevelComposer::new(
+            self.builtins.clone(),
+            ComposerConfig { kernel_ann: Some("Kernel"), kernel_invariant_ann: "KernelInvariant" },
+        );
+
+        let builtins = PyModule::import(py, "builtins")?;
+        let typings = PyModule::import(py, "typing")?;
+        let id_fn = builtins.getattr("id")?;
+        let issubclass = builtins.getattr("issubclass")?;
+        let exn_class = builtins.getattr("Exception")?;
+        let store_obj = embedding_map.getattr("store_object").unwrap().to_object(py);
+        let store_str = embedding_map.getattr("store_str").unwrap().to_object(py);
+        let store_fun = embedding_map.getattr("store_function").unwrap().to_object(py);
+        let host_attributes = embedding_map.getattr("attributes_writeback").unwrap().to_object(py);
+        let global_value_ids: Arc<RwLock<HashMap<_, _>>> = Arc::new(RwLock::new(HashMap::new()));
+        let helper = PythonHelper {
+            id_fn: builtins.getattr("id").unwrap().to_object(py),
+            len_fn: builtins.getattr("len").unwrap().to_object(py),
+            type_fn: builtins.getattr("type").unwrap().to_object(py),
+            origin_ty_fn: typings.getattr("get_origin").unwrap().to_object(py),
+            args_ty_fn: typings.getattr("get_args").unwrap().to_object(py),
+            store_obj: store_obj.clone(),
+            store_str,
+        };
+
+        let pyid_to_type = Arc::new(RwLock::new(HashMap::<u64, Type>::new()));
+        let exception_names = [
+            "ZeroDivisionError",
+            "IndexError",
+            "ValueError",
+            "RuntimeError",
+            "AssertionError",
+            "KeyError",
+            "NotImplementedError",
+            "OverflowError",
+            "IOError",
+            "UnwrapNoneError",
+        ];
+        add_exceptions(&mut composer, &mut builtins_def, &mut builtins_ty, &exception_names);
+
+        let mut module_to_resolver_cache: HashMap<u64, _> = HashMap::new();
+
+        let mut rpc_ids = vec![];
+        for (stmt, path, module) in self.top_levels.iter() {
+            let py_module: &PyAny = module.extract(py)?;
+            let module_id: u64 = id_fn.call1((py_module,))?.extract()?;
+            let helper = helper.clone();
+            let class_obj;
+            if let StmtKind::ClassDef { name, .. } = &stmt.node {
+                let class = py_module.getattr(name.to_string()).unwrap();
+                if issubclass.call1((class, exn_class)).unwrap().extract().unwrap() &&
+                    class.getattr("artiq_builtin").is_err() {
+                    class_obj = Some(class);
+                } else {
+                    class_obj = None;
+                }
+            } else {
+                class_obj = None;
+            }
+            let (name_to_pyid, resolver) =
+                module_to_resolver_cache.get(&module_id).cloned().unwrap_or_else(|| {
+                    let mut name_to_pyid: HashMap<StrRef, u64> = HashMap::new();
+                    let members: &PyDict =
+                        py_module.getattr("__dict__").unwrap().cast_as().unwrap();
+                    for (key, val) in members.iter() {
+                        let key: &str = key.extract().unwrap();
+                        let val = id_fn.call1((val,)).unwrap().extract().unwrap();
+                        name_to_pyid.insert(key.into(), val);
+                    }
+                    let resolver = Arc::new(Resolver(Arc::new(InnerResolver {
+                        id_to_type: builtins_ty.clone().into(),
+                        id_to_def: builtins_def.clone().into(),
+                        pyid_to_def: self.pyid_to_def.clone(),
+                        pyid_to_type: pyid_to_type.clone(),
+                        primitive_ids: self.primitive_ids.clone(),
+                        global_value_ids: global_value_ids.clone(),
+                        class_names: Default::default(),
+                        name_to_pyid: name_to_pyid.clone(),
+                        module: module.clone(),
+                        id_to_pyval: Default::default(),
+                        id_to_primitive: Default::default(),
+                        field_to_val: Default::default(),
+                        helper,
+                        string_store: self.string_store.clone(),
+                        exception_ids: self.exception_ids.clone(),
+                        deferred_eval_store: self.deferred_eval_store.clone(),
+                    })))
+                        as Arc<dyn SymbolResolver + Send + Sync>;
+                    let name_to_pyid = Rc::new(name_to_pyid);
+                    module_to_resolver_cache
+                        .insert(module_id, (name_to_pyid.clone(), resolver.clone()));
+                    (name_to_pyid, resolver)
+                });
+
+            let (name, def_id, ty) = composer
+                .register_top_level(stmt.clone(), Some(resolver.clone()), path.clone())
+                .map_err(|e| {
+                    CompileError::new_err(format!(
+                        "compilation failed\n----------\n{}",
+                        e
+                    ))
+                })?;
+            if let Some(class_obj) = class_obj {
+                self.exception_ids.write().insert(def_id.0, store_obj.call1(py, (class_obj, ))?.extract(py)?);
+            }
+
+            match &stmt.node {
+                StmtKind::FunctionDef { decorator_list, .. } => {
+                    if decorator_list.iter().any(|decorator| matches!(decorator.node, ExprKind::Name { id, .. } if id == "rpc".into())) {
+                        store_fun.call1(py, (def_id.0.into_py(py), module.getattr(py, name.to_string()).unwrap())).unwrap();
+                        rpc_ids.push((None, def_id));
+                    }
+                }
+                StmtKind::ClassDef { name, body, .. } => {
+                    let class_obj = module.getattr(py, name.to_string()).unwrap();
+                    for stmt in body.iter() {
+                        if let StmtKind::FunctionDef { name, decorator_list, .. } = &stmt.node {
+                            if decorator_list.iter().any(|decorator| matches!(decorator.node, ExprKind::Name { id, .. } if id == "rpc".into())) {
+                                rpc_ids.push((Some((class_obj.clone(), *name)), def_id));
+                            }
+                        }
+                    }
+                }
+                _ => ()
+            }
+
+            let id = *name_to_pyid.get(&name).unwrap();
+            self.pyid_to_def.write().insert(id, def_id);
+            {
+                let mut pyid_to_ty = pyid_to_type.write();
+                if let Some(ty) = ty {
+                    pyid_to_ty.insert(id, ty);
+                }
+            }
+        }
+
+        let id_fun = PyModule::import(py, "builtins")?.getattr("id")?;
+        let mut name_to_pyid: HashMap<StrRef, u64> = HashMap::new();
+        let module = PyModule::new(py, "tmp")?;
+        module.add("base", obj)?;
+        name_to_pyid.insert("base".into(), id_fun.call1((obj,))?.extract()?);
+        let mut arg_names = vec![];
+        for (i, arg) in args.into_iter().enumerate() {
+            let name = format!("tmp{}", i);
+            module.add(&name, arg)?;
+            name_to_pyid.insert(name.clone().into(), id_fun.call1((arg,))?.extract()?);
+            arg_names.push(name);
+        }
+        let synthesized = if method_name.is_empty() {
+            format!("def __modinit__():\n    base({})", arg_names.join(", "))
+        } else {
+            format!("def __modinit__():\n    base.{}({})", method_name, arg_names.join(", "))
+        };
+        let mut synthesized =
+            parse_program(&synthesized, "__nac3_synthesized_modinit__".to_string().into()).unwrap();
+        let inner_resolver = Arc::new(InnerResolver {
+            id_to_type: builtins_ty.clone().into(),
+            id_to_def: builtins_def.clone().into(),
+            pyid_to_def: self.pyid_to_def.clone(),
+            pyid_to_type: pyid_to_type.clone(),
+            primitive_ids: self.primitive_ids.clone(),
+            global_value_ids: global_value_ids.clone(),
+            class_names: Default::default(),
+            id_to_pyval: Default::default(),
+            id_to_primitive: Default::default(),
+            field_to_val: Default::default(),
+            name_to_pyid,
+            module: module.to_object(py),
+            helper,
+            string_store: self.string_store.clone(),
+            exception_ids: self.exception_ids.clone(),
+            deferred_eval_store: self.deferred_eval_store.clone(),
+        });
+        let resolver = Arc::new(Resolver(inner_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
+        let (_, def_id, _) = composer
+            .register_top_level(synthesized.pop().unwrap(), Some(resolver.clone()), "".into())
+            .unwrap();
+
+        let fun_signature =
+            FunSignature { args: vec![], ret: self.primitive.none, vars: HashMap::new() };
+        let mut store = ConcreteTypeStore::new();
+        let mut cache = HashMap::new();
+        let signature =
+            store.from_signature(&mut composer.unifier, &self.primitive, &fun_signature, &mut cache);
+        let signature = store.add_cty(signature);
+
+        if let Err(e) = composer.start_analysis(true) {
+            // report error of __modinit__ separately
+            if !e.contains("__nac3_synthesized_modinit__") {
+                return Err(CompileError::new_err(format!(
+                    "compilation failed\n----------\n{}",
+                    e
+                )));
+            } else {
+                let msg = Self::report_modinit(
+                    &arg_names,
+                    method_name,
+                    resolver.clone(),
+                    &composer.extract_def_list(),
+                    &mut composer.unifier,
+                    &self.primitive,
+                );
+                return Err(CompileError::new_err(msg.unwrap_or(e)));
+            }
+        }
+        let top_level = Arc::new(composer.make_top_level_context());
+
+        {
+            let rpc_codegen = rpc_codegen_callback();
+            let defs = top_level.definitions.read();
+            for (class_data, id) in rpc_ids.iter() {
+                let mut def = defs[id.0].write();
+                match &mut *def {
+                    TopLevelDef::Function { codegen_callback, .. } => {
+                        *codegen_callback = Some(rpc_codegen.clone());
+                    }
+                    TopLevelDef::Class { methods, .. } => {
+                        let (class_def, method_name) = class_data.as_ref().unwrap();
+                        for (name, _, id) in methods.iter() {
+                            if name != method_name {
+                                continue;
+                            }
+                            if let TopLevelDef::Function { codegen_callback, .. } =
+                                &mut *defs[id.0].write()
+                            {
+                                *codegen_callback = Some(rpc_codegen.clone());
+                                store_fun
+                                    .call1(
+                                        py,
+                                        (
+                                            id.0.into_py(py),
+                                            class_def.getattr(py, name.to_string()).unwrap(),
+                                        ),
+                                    )
+                                    .unwrap();
+                            }
+                        }
+                    }
+                }
+            }
+        }
+
+        let instance = {
+            let defs = top_level.definitions.read();
+            let mut definition = defs[def_id.0].write();
+            if let TopLevelDef::Function { instance_to_stmt, instance_to_symbol, .. } =
+                &mut *definition
+            {
+                instance_to_symbol.insert("".to_string(), "__modinit__".into());
+                instance_to_stmt[""].clone()
+            } else {
+                unreachable!()
+            }
+        };
+
+        let task = CodeGenTask {
+            subst: Default::default(),
+            symbol_name: "__modinit__".to_string(),
+            body: instance.body,
+            signature,
+            resolver: resolver.clone(),
+            store,
+            unifier_index: instance.unifier_id,
+            calls: instance.calls,
+            id: 0,
+        };
+
+        let mut store = ConcreteTypeStore::new();
+        let mut cache = HashMap::new();
+        let signature =
+            store.from_signature(&mut composer.unifier, &self.primitive, &fun_signature, &mut cache);
+        let signature = store.add_cty(signature);
+        let attributes_writeback_task = CodeGenTask {
+            subst: Default::default(),
+            symbol_name: "attributes_writeback".to_string(),
+            body: Arc::new(Default::default()),
+            signature,
+            resolver,
+            store,
+            unifier_index: instance.unifier_id,
+            calls: Arc::new(Default::default()),
+            id: 0,
+        };
+        let isa = self.isa;
+        let working_directory = self.working_directory.path().to_owned();
+
+        let membuffers: Arc<Mutex<Vec<Vec<u8>>>> = Default::default();
+
+        let membuffer = membuffers.clone();
+
+        let f = Arc::new(WithCall::new(Box::new(move |module| {
+            let buffer = module.write_bitcode_to_memory();
+            let buffer = buffer.as_slice().into();
+            membuffer.lock().push(buffer);
+        })));
+        let size_t = if self.isa == Isa::Host { 64 } else { 32 };
+        let thread_names: Vec<String> = (0..4).map(|_| "main".to_string()).collect();
+        let threads: Vec<_> = thread_names
+            .iter()
+            .map(|s| Box::new(ArtiqCodeGenerator::new(s.to_string(), size_t, self.time_fns)))
+            .collect();
+
+        let membuffer = membuffers.clone();
+        py.allow_threads(|| {
+            let (registry, handles) = WorkerRegistry::create_workers(threads, top_level.clone(), f);
+            registry.add_task(task);
+            registry.wait_tasks_complete(handles);
+
+            let mut generator = ArtiqCodeGenerator::new("attributes_writeback".to_string(), size_t, self.time_fns);
+            let context = inkwell::context::Context::create();
+            let module = context.create_module("attributes_writeback");
+            let builder = context.create_builder();
+            let (_, module, _) = gen_func_impl(&context, &mut generator, &registry, builder, module,
+                attributes_writeback_task, |generator, ctx| {
+                    attributes_writeback(ctx, generator, inner_resolver.as_ref(), host_attributes)
+                }).unwrap();
+            let buffer = module.write_bitcode_to_memory();
+            let buffer = buffer.as_slice().into();
+            membuffer.lock().push(buffer);
+        });
+
+        let context = inkwell::context::Context::create();
+        let buffers = membuffers.lock();
+        let main = context
+            .create_module_from_ir(MemoryBuffer::create_from_memory_range(&buffers[0], "main"))
+            .unwrap();
+        for buffer in buffers.iter().skip(1) {
+            let other = context
+                .create_module_from_ir(MemoryBuffer::create_from_memory_range(buffer, "main"))
+                .unwrap();
+
+            main.link_in_module(other)
+                .map_err(|err| CompileError::new_err(err.to_string()))?;
+        }
+        let builder = context.create_builder();
+        let modinit_return = main.get_function("__modinit__").unwrap().get_last_basic_block().unwrap().get_terminator().unwrap();
+        builder.position_before(&modinit_return);
+        builder.build_call(main.get_function("attributes_writeback").unwrap(), &[], "attributes_writeback");
+
+        main.link_in_module(load_irrt(&context))
+            .map_err(|err| CompileError::new_err(err.to_string()))?;
+
+        let mut function_iter = main.get_first_function();
+        while let Some(func) = function_iter {
+            if func.count_basic_blocks() > 0 && func.get_name().to_str().unwrap() != "__modinit__" {
+                func.set_linkage(inkwell::module::Linkage::Private);
+            }
+            function_iter = func.get_next_function();
+        }
+
+        let builder = PassManagerBuilder::create();
+        builder.set_optimization_level(OptimizationLevel::Aggressive);
+        let passes = PassManager::create(());
+        builder.set_inliner_with_threshold(255);
+        builder.populate_module_pass_manager(&passes);
+        passes.run_on(&main);
+
+        let (triple, features) = match isa {
+            Isa::Host => (
+                TargetMachine::get_default_triple(),
+                TargetMachine::get_host_cpu_features().to_string(),
+            ),
+            Isa::RiscV32G => {
+                (TargetTriple::create("riscv32-unknown-linux"), "+a,+m,+f,+d".to_string())
+            }
+            Isa::RiscV32IMA => (TargetTriple::create("riscv32-unknown-linux"), "+a,+m".to_string()),
+            Isa::CortexA9 => (
+                TargetTriple::create("armv7-unknown-linux-gnueabihf"),
+                "+dsp,+fp16,+neon,+vfp3".to_string(),
+            ),
+        };
+        let target =
+            Target::from_triple(&triple).expect("couldn't create target from target triple");
+        let target_machine = target
+            .create_target_machine(
+                &triple,
+                "",
+                &features,
+                OptimizationLevel::Default,
+                RelocMode::PIC,
+                CodeModel::Default,
+            )
+            .expect("couldn't create target machine");
+        target_machine
+            .write_to_file(&main, FileType::Object, &working_directory.join("module.o"))
+            .expect("couldn't write module to file");
+
+        let mut linker_args = vec![
+            "-shared".to_string(),
+            "--eh-frame-hdr".to_string(),
+            "-x".to_string(),
+            "-o".to_string(),
+            filename.to_string(),
+            working_directory.join("module.o").to_string_lossy().to_string(),
+        ];
+        if isa != Isa::Host {
+            linker_args.push(
+                "-T".to_string()
+                    + self.working_directory.path().join("kernel.ld").to_str().unwrap(),
+            );
+        }
+
+        #[cfg(not(windows))]
+        let lld_command = "ld.lld";
+        #[cfg(windows)]
+        let lld_command = "ld.lld.exe";
+        if let Ok(linker_status) = Command::new(lld_command).args(linker_args).status() {
+            if !linker_status.success() {
+                return Err(CompileError::new_err("failed to start linker"));
+            }
+        } else {
+            return Err(CompileError::new_err(
+                "linker returned non-zero status code",
+            ));
+        }
+
+        Ok(())
+    }
+
+    fn compile_method_to_mem(
+        &mut self,
+        obj: &PyAny,
+        method_name: &str,
+        args: Vec<&PyAny>,
+        embedding_map: &PyAny,
+        py: Python,
+    ) -> PyResult<PyObject> {
+        let filename_path = self.working_directory.path().join("module.elf");
+        let filename = filename_path.to_str().unwrap();
+        self.compile_method_to_file(obj, method_name, args, filename, embedding_map, py)?;
+        Ok(PyBytes::new(py, &fs::read(filename).unwrap()).into())
+    }
+}
+
+#[cfg(feature = "init-llvm-profile")]
+extern "C" {
+    fn __llvm_profile_initialize();
+}
+
+#[pymodule]
+fn nac3artiq(py: Python, m: &PyModule) -> PyResult<()> {
+    #[cfg(feature = "init-llvm-profile")]
+    unsafe {
+        __llvm_profile_initialize();
+    }
+
+    Target::initialize_all(&InitializationConfig::default());
+    m.add("CompileError", py.get_type::<CompileError>())?;
+    m.add_class::<Nac3>()?;
+    Ok(())
+}

nac3artiq/src/timeline.rs

@@ -0,0 +1,304 @@
+use inkwell::{values::BasicValueEnum, AddressSpace, AtomicOrdering};
+use nac3core::codegen::CodeGenContext;
+
+pub trait TimeFns {
+    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 {}
+
+// 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, '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_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!();
+        }
+    }
+
+    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);
+        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",
+            );
+            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!();
+        }
+    }
+
+    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_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 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");
+
+                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!();
+        };
+    }
+}
+
+pub static NOW_PINNING_TIME_FNS_64: NowPinningTimeFns64 = NowPinningTimeFns64 {};
+
+pub struct NowPinningTimeFns {}
+
+impl TimeFns for NowPinningTimeFns {
+    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");
+        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!();
+        }
+    }
+
+    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);
+        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",
+            );
+            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!();
+        }
+    }
+}
+
+pub static NOW_PINNING_TIME_FNS: NowPinningTimeFns = NowPinningTimeFns {};
+
+pub struct ExternTimeFns {}
+
+impl TimeFns for ExternTimeFns {
+    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").try_as_basic_value().left().unwrap()
+    }
+
+    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",
+                ctx.ctx.void_type().fn_type(&[ctx.ctx.i64_type().into()], false),
+                None,
+            )
+        });
+        ctx.builder.build_call(at_mu, &[t.into()], "at_mu");
+    }
+
+    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",
+                ctx.ctx.void_type().fn_type(&[ctx.ctx.i64_type().into()], false),
+                None,
+            )
+        });
+        ctx.builder.build_call(delay_mu, &[dt.into()], "delay_mu");
+    }
+}
+
+pub static EXTERN_TIME_FNS: ExternTimeFns = ExternTimeFns {};

nac3ast/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "nac3ast"
+version = "0.1.0"
+authors = ["RustPython Team", "M-Labs"]
+edition = "2018"
+
+[features]
+default = ["constant-optimization", "fold"]
+constant-optimization = ["fold"]
+fold = []
+
+[dependencies]
+lazy_static = "1.4.0"
+parking_lot = "0.11.1"
+string-interner = "0.13.0"
+fxhash = "0.2.1"

nac3ast/Python.asdl

@@ -0,0 +1,127 @@
+-- ASDL's 4 builtin types are:
+-- identifier, int, string, constant
+
+module Python
+{
+    mod = Module(stmt* body, type_ignore* type_ignores)
+        | Interactive(stmt* body)
+        | Expression(expr body)
+        | FunctionType(expr* argtypes, expr returns)
+
+    stmt = FunctionDef(identifier name, arguments args,
+                       stmt* body, expr* decorator_list, expr? returns,
+                       string? type_comment, identifier* config_comment)
+          | AsyncFunctionDef(identifier name, arguments args,
+                             stmt* body, expr* decorator_list, expr? returns,
+                             string? type_comment, identifier* config_comment)
+
+          | ClassDef(identifier name,
+             expr* bases,
+             keyword* keywords,
+             stmt* body,
+             expr* decorator_list, identifier* config_comment)
+          | Return(expr? value, identifier* config_comment)
+
+          | Delete(expr* targets, identifier* config_comment)
+          | Assign(expr* targets, expr value, string? type_comment, identifier* config_comment)
+          | AugAssign(expr target, operator op, expr value, identifier* config_comment)
+          -- 'simple' indicates that we annotate simple name without parens
+          | AnnAssign(expr target, expr annotation, expr? value, bool simple, identifier* config_comment)
+
+          -- use 'orelse' because else is a keyword in target languages
+          | For(expr target, expr iter, stmt* body, stmt* orelse, string? type_comment, identifier* config_comment)
+          | AsyncFor(expr target, expr iter, stmt* body, stmt* orelse, string? type_comment, identifier* config_comment)
+          | While(expr test, stmt* body, stmt* orelse, identifier* config_comment)
+          | If(expr test, stmt* body, stmt* orelse, identifier* config_comment)
+          | With(withitem* items, stmt* body, string? type_comment, identifier* config_comment)
+          | AsyncWith(withitem* items, stmt* body, string? type_comment, identifier* config_comment)
+
+          | Raise(expr? exc, expr? cause, identifier* config_comment)
+          | Try(stmt* body, excepthandler* handlers, stmt* orelse, stmt* finalbody, identifier* config_comment)
+          | Assert(expr test, expr? msg, identifier* config_comment)
+
+          | Import(alias* names, identifier* config_comment)
+          | ImportFrom(identifier? module, alias* names, int level, identifier* config_comment)
+
+          | Global(identifier* names, identifier* config_comment)
+          | Nonlocal(identifier* names, identifier* config_comment)
+          | Expr(expr value, identifier* config_comment)
+          | Pass(identifier* config_comment)
+          | Break(identifier* config_comment)
+          | Continue(identifier* config_comment)
+
+          -- col_offset is the byte offset in the utf8 string the parser uses
+          attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
+
+          -- BoolOp() can use left & right?
+    expr = BoolOp(boolop op, expr* values)
+         | NamedExpr(expr target, expr value)
+         | BinOp(expr left, operator op, expr right)
+         | UnaryOp(unaryop op, expr operand)
+         | Lambda(arguments args, expr body)
+         | IfExp(expr test, expr body, expr orelse)
+         | Dict(expr?* keys, expr* values)
+         | Set(expr* elts)
+         | ListComp(expr elt, comprehension* generators)
+         | SetComp(expr elt, comprehension* generators)
+         | DictComp(expr key, expr value, comprehension* generators)
+         | GeneratorExp(expr elt, comprehension* generators)
+         -- the grammar constrains where yield expressions can occur
+         | Await(expr value)
+         | Yield(expr? value)
+         | YieldFrom(expr value)
+         -- need sequences for compare to distinguish between
+         -- x < 4 < 3 and (x < 4) < 3
+         | Compare(expr left, cmpop* ops, expr* comparators)
+         | Call(expr func, expr* args, keyword* keywords)
+         | FormattedValue(expr value, conversion_flag? conversion, expr? format_spec)
+         | JoinedStr(expr* values)
+         | Constant(constant value, string? kind)
+
+         -- the following expression can appear in assignment context
+         | Attribute(expr value, identifier attr, expr_context ctx)
+         | Subscript(expr value, expr slice, expr_context ctx)
+         | Starred(expr value, expr_context ctx)
+         | Name(identifier id, expr_context ctx)
+         | List(expr* elts, expr_context ctx)
+         | Tuple(expr* elts, expr_context ctx)
+
+         -- can appear only in Subscript
+         | Slice(expr? lower, expr? upper, expr? step)
+
+          -- col_offset is the byte offset in the utf8 string the parser uses
+          attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
+
+    expr_context = Load | Store | Del
+
+    boolop = And | Or
+
+    operator = Add | Sub | Mult | MatMult | Div | Mod | Pow | LShift
+                 | RShift | BitOr | BitXor | BitAnd | FloorDiv
+
+    unaryop = Invert | Not | UAdd | USub
+
+    cmpop = Eq | NotEq | Lt | LtE | Gt | GtE | Is | IsNot | In | NotIn
+
+    comprehension = (expr target, expr iter, expr* ifs, bool is_async)
+
+    excepthandler = ExceptHandler(expr? type, identifier? name, stmt* body)
+                    attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
+
+    arguments = (arg* posonlyargs, arg* args, arg? vararg, arg* kwonlyargs,
+                 expr?* kw_defaults, arg? kwarg, expr* defaults)
+
+    arg = (identifier arg, expr? annotation, string? type_comment)
+           attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
+
+    -- keyword arguments supplied to call (NULL identifier for **kwargs)
+    keyword = (identifier? arg, expr value)
+               attributes (int lineno, int col_offset, int? end_lineno, int? end_col_offset)
+
+    -- import name with optional 'as' alias.
+    alias = (identifier name, identifier? asname)
+
+    withitem = (expr context_expr, expr? optional_vars)
+
+    type_ignore = TypeIgnore(int lineno, string tag)
+}

nac3ast/asdl.py

@@ -0,0 +1,385 @@
+#-------------------------------------------------------------------------------
+# Parser for ASDL [1] definition files. Reads in an ASDL description and parses
+# it into an AST that describes it.
+#
+# The EBNF we're parsing here: Figure 1 of the paper [1]. Extended to support
+# modules and attributes after a product. Words starting with Capital letters
+# are terminals. Literal tokens are in "double quotes". Others are
+# non-terminals. Id is either TokenId or ConstructorId.
+#
+# module        ::= "module" Id "{" [definitions] "}"
+# definitions   ::= { TypeId "=" type }
+# type          ::= product | sum
+# product       ::= fields ["attributes" fields]
+# fields        ::= "(" { field, "," } field ")"
+# field         ::= TypeId ["?" | "*"] [Id]
+# sum           ::= constructor { "|" constructor } ["attributes" fields]
+# constructor   ::= ConstructorId [fields]
+#
+# [1] "The Zephyr Abstract Syntax Description Language" by Wang, et. al. See
+#     http://asdl.sourceforge.net/
+#-------------------------------------------------------------------------------
+from collections import namedtuple
+import re
+
+__all__ = [
+    'builtin_types', 'parse', 'AST', 'Module', 'Type', 'Constructor',
+    'Field', 'Sum', 'Product', 'VisitorBase', 'Check', 'check']
+
+# The following classes define nodes into which the ASDL description is parsed.
+# Note: this is a "meta-AST". ASDL files (such as Python.asdl) describe the AST
+# structure used by a programming language. But ASDL files themselves need to be
+# parsed. This module parses ASDL files and uses a simple AST to represent them.
+# See the EBNF at the top of the file to understand the logical connection
+# between the various node types.
+
+builtin_types = {'identifier', 'string', 'int', 'constant', 'bool', 'conversion_flag'}
+
+class AST:
+    def __repr__(self):
+        raise NotImplementedError
+
+class Module(AST):
+    def __init__(self, name, dfns):
+        self.name = name
+        self.dfns = dfns
+        self.types = {type.name: type.value for type in dfns}
+
+    def __repr__(self):
+        return 'Module({0.name}, {0.dfns})'.format(self)
+
+class Type(AST):
+    def __init__(self, name, value):
+        self.name = name
+        self.value = value
+
+    def __repr__(self):
+        return 'Type({0.name}, {0.value})'.format(self)
+
+class Constructor(AST):
+    def __init__(self, name, fields=None):
+        self.name = name
+        self.fields = fields or []
+
+    def __repr__(self):
+        return 'Constructor({0.name}, {0.fields})'.format(self)
+
+class Field(AST):
+    def __init__(self, type, name=None, seq=False, opt=False):
+        self.type = type
+        self.name = name
+        self.seq = seq
+        self.opt = opt
+
+    def __str__(self):
+        if self.seq:
+            extra = "*"
+        elif self.opt:
+            extra = "?"
+        else:
+            extra = ""
+
+        return "{}{} {}".format(self.type, extra, self.name)
+
+    def __repr__(self):
+        if self.seq:
+            extra = ", seq=True"
+        elif self.opt:
+            extra = ", opt=True"
+        else:
+            extra = ""
+        if self.name is None:
+            return 'Field({0.type}{1})'.format(self, extra)
+        else:
+            return 'Field({0.type}, {0.name}{1})'.format(self, extra)
+
+class Sum(AST):
+    def __init__(self, types, attributes=None):
+        self.types = types
+        self.attributes = attributes or []
+
+    def __repr__(self):
+        if self.attributes:
+            return 'Sum({0.types}, {0.attributes})'.format(self)
+        else:
+            return 'Sum({0.types})'.format(self)
+
+class Product(AST):
+    def __init__(self, fields, attributes=None):
+        self.fields = fields
+        self.attributes = attributes or []
+
+    def __repr__(self):
+        if self.attributes:
+            return 'Product({0.fields}, {0.attributes})'.format(self)
+        else:
+            return 'Product({0.fields})'.format(self)
+
+# A generic visitor for the meta-AST that describes ASDL. This can be used by
+# emitters. Note that this visitor does not provide a generic visit method, so a
+# subclass needs to define visit methods from visitModule to as deep as the
+# interesting node.
+# We also define a Check visitor that makes sure the parsed ASDL is well-formed.
+
+class VisitorBase(object):
+    """Generic tree visitor for ASTs."""
+    def __init__(self):
+        self.cache = {}
+
+    def visit(self, obj, *args):
+        klass = obj.__class__
+        meth = self.cache.get(klass)
+        if meth is None:
+            methname = "visit" + klass.__name__
+            meth = getattr(self, methname, None)
+            self.cache[klass] = meth
+        if meth:
+            try:
+                meth(obj, *args)
+            except Exception as e:
+                print("Error visiting %r: %s" % (obj, e))
+                raise
+
+class Check(VisitorBase):
+    """A visitor that checks a parsed ASDL tree for correctness.
+
+    Errors are printed and accumulated.
+    """
+    def __init__(self):
+        super(Check, self).__init__()
+        self.cons = {}
+        self.errors = 0
+        self.types = {}
+
+    def visitModule(self, mod):
+        for dfn in mod.dfns:
+            self.visit(dfn)
+
+    def visitType(self, type):
+        self.visit(type.value, str(type.name))
+
+    def visitSum(self, sum, name):
+        for t in sum.types:
+            self.visit(t, name)
+
+    def visitConstructor(self, cons, name):
+        key = str(cons.name)
+        conflict = self.cons.get(key)
+        if conflict is None:
+            self.cons[key] = name
+        else:
+            print('Redefinition of constructor {}'.format(key))
+            print('Defined in {} and {}'.format(conflict, name))
+            self.errors += 1
+        for f in cons.fields:
+            self.visit(f, key)
+
+    def visitField(self, field, name):
+        key = str(field.type)
+        l = self.types.setdefault(key, [])
+        l.append(name)
+
+    def visitProduct(self, prod, name):
+        for f in prod.fields:
+            self.visit(f, name)
+
+def check(mod):
+    """Check the parsed ASDL tree for correctness.
+
+    Return True if success. For failure, the errors are printed out and False
+    is returned.
+    """
+    v = Check()
+    v.visit(mod)
+
+    for t in v.types:
+        if t not in mod.types and not t in builtin_types:
+            v.errors += 1
+            uses = ", ".join(v.types[t])
+            print('Undefined type {}, used in {}'.format(t, uses))
+    return not v.errors
+
+# The ASDL parser itself comes next. The only interesting external interface
+# here is the top-level parse function.
+
+def parse(filename):
+    """Parse ASDL from the given file and return a Module node describing it."""
+    with open(filename) as f:
+        parser = ASDLParser()
+        return parser.parse(f.read())
+
+# Types for describing tokens in an ASDL specification.
+class TokenKind:
+    """TokenKind is provides a scope for enumerated token kinds."""
+    (ConstructorId, TypeId, Equals, Comma, Question, Pipe, Asterisk,
+     LParen, RParen, LBrace, RBrace) = range(11)
+
+    operator_table = {
+        '=': Equals, ',': Comma,    '?': Question, '|': Pipe,    '(': LParen,
+        ')': RParen, '*': Asterisk, '{': LBrace,   '}': RBrace}
+
+Token = namedtuple('Token', 'kind value lineno')
+
+class ASDLSyntaxError(Exception):
+    def __init__(self, msg, lineno=None):
+        self.msg = msg
+        self.lineno = lineno or '<unknown>'
+
+    def __str__(self):
+        return 'Syntax error on line {0.lineno}: {0.msg}'.format(self)
+
+def tokenize_asdl(buf):
+    """Tokenize the given buffer. Yield Token objects."""
+    for lineno, line in enumerate(buf.splitlines(), 1):
+        for m in re.finditer(r'\s*(\w+|--.*|.)', line.strip()):
+            c = m.group(1)
+            if c[0].isalpha():
+                # Some kind of identifier
+                if c[0].isupper():
+                    yield Token(TokenKind.ConstructorId, c, lineno)
+                else:
+                    yield Token(TokenKind.TypeId, c, lineno)
+            elif c[:2] == '--':
+                # Comment
+                break
+            else:
+                # Operators
+                try:
+                    op_kind = TokenKind.operator_table[c]
+                except KeyError:
+                    raise ASDLSyntaxError('Invalid operator %s' % c, lineno)
+                yield Token(op_kind, c, lineno)
+
+class ASDLParser:
+    """Parser for ASDL files.
+
+    Create, then call the parse method on a buffer containing ASDL.
+    This is a simple recursive descent parser that uses tokenize_asdl for the
+    lexing.
+    """
+    def __init__(self):
+        self._tokenizer = None
+        self.cur_token = None
+
+    def parse(self, buf):
+        """Parse the ASDL in the buffer and return an AST with a Module root.
+        """
+        self._tokenizer = tokenize_asdl(buf)
+        self._advance()
+        return self._parse_module()
+
+    def _parse_module(self):
+        if self._at_keyword('module'):
+            self._advance()
+        else:
+            raise ASDLSyntaxError(
+                'Expected "module" (found {})'.format(self.cur_token.value),
+                self.cur_token.lineno)
+        name = self._match(self._id_kinds)
+        self._match(TokenKind.LBrace)
+        defs = self._parse_definitions()
+        self._match(TokenKind.RBrace)
+        return Module(name, defs)
+
+    def _parse_definitions(self):
+        defs = []
+        while self.cur_token.kind == TokenKind.TypeId:
+            typename = self._advance()
+            self._match(TokenKind.Equals)
+            type = self._parse_type()
+            defs.append(Type(typename, type))
+        return defs
+
+    def _parse_type(self):
+        if self.cur_token.kind == TokenKind.LParen:
+            # If we see a (, it's a product
+            return self._parse_product()
+        else:
+            # Otherwise it's a sum. Look for ConstructorId
+            sumlist = [Constructor(self._match(TokenKind.ConstructorId),
+                                   self._parse_optional_fields())]
+            while self.cur_token.kind  == TokenKind.Pipe:
+                # More constructors
+                self._advance()
+                sumlist.append(Constructor(
+                                self._match(TokenKind.ConstructorId),
+                                self._parse_optional_fields()))
+            return Sum(sumlist, self._parse_optional_attributes())
+
+    def _parse_product(self):
+        return Product(self._parse_fields(), self._parse_optional_attributes())
+
+    def _parse_fields(self):
+        fields = []
+        self._match(TokenKind.LParen)
+        while self.cur_token.kind == TokenKind.TypeId:
+            typename = self._advance()
+            is_seq, is_opt = self._parse_optional_field_quantifier()
+            id = (self._advance() if self.cur_token.kind in self._id_kinds
+                                  else None)
+            fields.append(Field(typename, id, seq=is_seq, opt=is_opt))
+            if self.cur_token.kind == TokenKind.RParen:
+                break
+            elif self.cur_token.kind == TokenKind.Comma:
+                self._advance()
+        self._match(TokenKind.RParen)
+        return fields
+
+    def _parse_optional_fields(self):
+        if self.cur_token.kind == TokenKind.LParen:
+            return self._parse_fields()
+        else:
+            return None
+
+    def _parse_optional_attributes(self):
+        if self._at_keyword('attributes'):
+            self._advance()
+            return self._parse_fields()
+        else:
+            return None
+
+    def _parse_optional_field_quantifier(self):
+        is_seq, is_opt = False, False
+        if self.cur_token.kind == TokenKind.Question:
+            is_opt = True
+            self._advance()
+        if self.cur_token.kind == TokenKind.Asterisk:
+            is_seq = True
+            self._advance()
+        return is_seq, is_opt
+
+    def _advance(self):
+        """ Return the value of the current token and read the next one into
+            self.cur_token.
+        """
+        cur_val = None if self.cur_token is None else self.cur_token.value
+        try:
+            self.cur_token = next(self._tokenizer)
+        except StopIteration:
+            self.cur_token = None
+        return cur_val
+
+    _id_kinds = (TokenKind.ConstructorId, TokenKind.TypeId)
+
+    def _match(self, kind):
+        """The 'match' primitive of RD parsers.
+
+        * Verifies that the current token is of the given kind (kind can
+          be a tuple, in which the kind must match one of its members).
+        * Returns the value of the current token
+        * Reads in the next token
+        """
+        if (isinstance(kind, tuple) and self.cur_token.kind in kind or
+            self.cur_token.kind == kind
+            ):
+            value = self.cur_token.value
+            self._advance()
+            return value
+        else:
+            raise ASDLSyntaxError(
+                'Unmatched {} (found {})'.format(kind, self.cur_token.kind),
+                self.cur_token.lineno)
+
+    def _at_keyword(self, keyword):
+        return (self.cur_token.kind == TokenKind.TypeId and
+                self.cur_token.value == keyword)

nac3ast/asdl_rs.py

@@ -0,0 +1,609 @@
+#! /usr/bin/env python
+"""Generate Rust code from an ASDL description."""
+
+import os
+import sys
+import textwrap
+
+import json
+
+from argparse import ArgumentParser
+from pathlib import Path
+
+import asdl
+
+TABSIZE = 4
+AUTOGEN_MESSAGE = "// File automatically generated by {}.\n\n"
+
+builtin_type_mapping = {
+    'identifier': 'Ident',
+    'string': 'String',
+    'int': 'usize',
+    'constant': 'Constant',
+    'bool': 'bool',
+    'conversion_flag': 'ConversionFlag',
+}
+assert builtin_type_mapping.keys() == asdl.builtin_types
+
+def get_rust_type(name):
+    """Return a string for the C name of the type.
+
+    This function special cases the default types provided by asdl.
+    """
+    if name in asdl.builtin_types:
+        return builtin_type_mapping[name]
+    else:
+        return "".join(part.capitalize() for part in name.split("_"))
+
+def is_simple(sum):
+    """Return True if a sum is a simple.
+
+    A sum is simple if its types have no fields, e.g.
+    unaryop = Invert | Not | UAdd | USub
+    """
+    for t in sum.types:
+        if t.fields:
+            return False
+    return True
+
+def asdl_of(name, obj):
+    if isinstance(obj, asdl.Product) or isinstance(obj, asdl.Constructor):
+        fields = ", ".join(map(str, obj.fields))
+        if fields:
+            fields = "({})".format(fields)
+        return "{}{}".format(name, fields)
+    else:
+        if is_simple(obj):
+            types = " | ".join(type.name for type in obj.types)
+        else:
+            sep = "\n{}| ".format(" " * (len(name) + 1))
+            types = sep.join(
+                asdl_of(type.name, type) for type in obj.types
+            )
+        return "{} = {}".format(name, types)
+
+class EmitVisitor(asdl.VisitorBase):
+    """Visit that emits lines"""
+
+    def __init__(self, file):
+        self.file = file
+        self.identifiers = set()
+        super(EmitVisitor, self).__init__()
+
+    def emit_identifier(self, name):
+        name = str(name)
+        if name in self.identifiers:
+            return
+        self.emit("_Py_IDENTIFIER(%s);" % name, 0)
+        self.identifiers.add(name)
+
+    def emit(self, line, depth):
+        if line:
+            line = (" " * TABSIZE * depth) + line
+        self.file.write(line + "\n")
+
+class TypeInfo:
+    def __init__(self, name):
+        self.name = name
+        self.has_userdata = None
+        self.children = set()
+        self.boxed = False
+
+    def __repr__(self):
+        return f"<TypeInfo: {self.name}>"
+
+    def determine_userdata(self, typeinfo, stack):
+        if self.name in stack:
+            return None
+        stack.add(self.name)
+        for child, child_seq in self.children:
+            if child in asdl.builtin_types:
+                continue
+            childinfo = typeinfo[child]
+            child_has_userdata = childinfo.determine_userdata(typeinfo, stack)
+            if self.has_userdata is None and child_has_userdata is True:
+                self.has_userdata = True
+
+        stack.remove(self.name)
+        return self.has_userdata
+
+class FindUserdataTypesVisitor(asdl.VisitorBase):
+    def __init__(self, typeinfo):
+        self.typeinfo = typeinfo
+        super().__init__()
+
+    def visitModule(self, mod):
+        for dfn in mod.dfns:
+            self.visit(dfn)
+        stack = set()
+        for info in self.typeinfo.values():
+            info.determine_userdata(self.typeinfo, stack)
+
+    def visitType(self, type):
+        self.typeinfo[type.name] = TypeInfo(type.name)
+        self.visit(type.value, type.name)
+
+    def visitSum(self, sum, name):
+        info = self.typeinfo[name]
+        if is_simple(sum):
+            info.has_userdata = False
+        else:
+            if len(sum.types) > 1:
+                info.boxed = True
+            if sum.attributes:
+                # attributes means Located, which has the `custom: U` field
+                info.has_userdata = True
+        for variant in sum.types:
+            self.add_children(name, variant.fields)
+
+    def visitProduct(self, product, name):
+        info = self.typeinfo[name]
+        if product.attributes:
+            # attributes means Located, which has the `custom: U` field
+            info.has_userdata = True
+        if len(product.fields) > 2:
+            info.boxed = True
+        self.add_children(name, product.fields)
+
+    def add_children(self, name, fields):
+        self.typeinfo[name].children.update((field.type, field.seq) for field in fields)
+
+def rust_field(field_name):
+    if field_name == 'type':
+        return 'type_'
+    else:
+        return field_name
+
+class TypeInfoEmitVisitor(EmitVisitor):
+    def __init__(self, file, typeinfo):
+        self.typeinfo = typeinfo
+        super().__init__(file)
+
+    def has_userdata(self, typ):
+        return self.typeinfo[typ].has_userdata
+
+    def get_generics(self, typ, *generics):
+        if self.has_userdata(typ):
+            return [f"<{g}>" for g in generics]
+        else:
+            return ["" for g in generics]
+
+class StructVisitor(TypeInfoEmitVisitor):
+    """Visitor to generate typedefs for AST."""
+
+    def visitModule(self, mod):
+        for dfn in mod.dfns:
+            self.visit(dfn)
+
+    def visitType(self, type, depth=0):
+        self.visit(type.value, type.name, depth)
+
+    def visitSum(self, sum, name, depth):
+        if is_simple(sum):
+            self.simple_sum(sum, name, depth)
+        else:
+            self.sum_with_constructors(sum, name, depth)
+
+    def emit_attrs(self, depth):
+        self.emit("#[derive(Clone, Debug, PartialEq)]", depth)
+
+    def simple_sum(self, sum, name, depth):
+        rustname = get_rust_type(name)
+        self.emit_attrs(depth)
+        self.emit(f"pub enum {rustname} {{", depth)
+        for variant in sum.types:
+            self.emit(f"{variant.name},", depth + 1)
+        self.emit("}", depth)
+        self.emit("", depth)
+
+    def sum_with_constructors(self, sum, name, depth):
+        typeinfo = self.typeinfo[name]
+        generics, generics_applied = self.get_generics(name, "U = ()", "U")
+        enumname = rustname = get_rust_type(name)
+        # all the attributes right now are for location, so if it has attrs we
+        # can just wrap it in Located<>
+        if sum.attributes:
+            enumname = rustname + "Kind"
+        self.emit_attrs(depth)
+        self.emit(f"pub enum {enumname}{generics} {{", depth)
+        for t in sum.types:
+            self.visit(t, typeinfo, depth + 1)
+        self.emit("}", depth)
+        if sum.attributes:
+            self.emit(f"pub type {rustname}<U = ()> = Located<{enumname}{generics_applied}, U>;", depth)
+        self.emit("", depth)
+
+    def visitConstructor(self, cons, parent, depth):
+        if cons.fields:
+            self.emit(f"{cons.name} {{", depth)
+            for f in cons.fields:
+                self.visit(f, parent, "", depth + 1)
+            self.emit("},", depth)
+        else:
+            self.emit(f"{cons.name},", depth)
+
+    def visitField(self, field, parent, vis, depth):
+        typ = get_rust_type(field.type)
+        fieldtype = self.typeinfo.get(field.type)
+        if fieldtype and fieldtype.has_userdata:
+            typ = f"{typ}<U>"
+        # don't box if we're doing Vec<T>, but do box if we're doing Vec<Option<Box<T>>>
+        if fieldtype and fieldtype.boxed and (not field.seq or field.opt):
+            typ = f"Box<{typ}>"
+        if field.opt:
+            typ = f"Option<{typ}>"
+        if field.seq:
+            typ = f"Vec<{typ}>"
+        name = rust_field(field.name)
+        self.emit(f"{vis}{name}: {typ},", depth)
+
+    def visitProduct(self, product, name, depth):
+        typeinfo = self.typeinfo[name]
+        generics, generics_applied = self.get_generics(name, "U = ()", "U")
+        dataname = rustname = get_rust_type(name)
+        if product.attributes:
+            dataname = rustname + "Data"
+        self.emit_attrs(depth)
+        self.emit(f"pub struct {dataname}{generics} {{", depth)
+        for f in product.fields:
+            self.visit(f, typeinfo, "pub ", depth + 1)
+        self.emit("}", depth)
+        if product.attributes:
+            # attributes should just be location info
+            self.emit(f"pub type {rustname}<U = ()> = Located<{dataname}{generics_applied}, U>;", depth);
+        self.emit("", depth)
+
+
+class FoldTraitDefVisitor(TypeInfoEmitVisitor):
+    def visitModule(self, mod, depth):
+        self.emit("pub trait Fold<U> {", depth)
+        self.emit("type TargetU;", depth + 1)
+        self.emit("type Error;", depth + 1)
+        self.emit("fn map_user(&mut self, user: U) -> Result<Self::TargetU, Self::Error>;", depth + 2)
+        for dfn in mod.dfns:
+            self.visit(dfn, depth + 2)
+        self.emit("}", depth)
+
+    def visitType(self, type, depth):
+        name = type.name
+        apply_u, apply_target_u = self.get_generics(name, "U", "Self::TargetU")
+        enumname = get_rust_type(name)
+        self.emit(f"fn fold_{name}(&mut self, node: {enumname}{apply_u}) -> Result<{enumname}{apply_target_u}, Self::Error> {{", depth)
+        self.emit(f"fold_{name}(self, node)", depth + 1)
+        self.emit("}", depth)
+
+
+class FoldImplVisitor(TypeInfoEmitVisitor):
+    def visitModule(self, mod, depth):
+        self.emit("fn fold_located<U, F: Fold<U> + ?Sized, T, MT>(folder: &mut F, node: Located<T, U>, f: impl FnOnce(&mut F, T) -> Result<MT, F::Error>) -> Result<Located<MT, F::TargetU>, F::Error> {", depth)
+        self.emit("Ok(Located { custom: folder.map_user(node.custom)?, location: node.location, node: f(folder, node.node)? })", depth + 1)
+        self.emit("}", depth)
+        for dfn in mod.dfns:
+            self.visit(dfn, depth)
+
+    def visitType(self, type, depth=0):
+        self.visit(type.value, type.name, depth)
+
+    def visitSum(self, sum, name, depth):
+        apply_t, apply_u, apply_target_u = self.get_generics(name, "T", "U", "F::TargetU")
+        enumname = get_rust_type(name)
+        is_located = bool(sum.attributes)
+
+        self.emit(f"impl<T, U> Foldable<T, U> for {enumname}{apply_t} {{", depth)
+        self.emit(f"type Mapped = {enumname}{apply_u};", depth + 1)
+        self.emit("fn fold<F: Fold<T, TargetU = U> + ?Sized>(self, folder: &mut F) -> Result<Self::Mapped, F::Error> {", depth + 1)
+        self.emit(f"folder.fold_{name}(self)", depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("}", depth)
+
+        self.emit(f"pub fn fold_{name}<U, F: Fold<U> + ?Sized>(#[allow(unused)] folder: &mut F, node: {enumname}{apply_u}) -> Result<{enumname}{apply_target_u}, F::Error> {{", depth)
+        if is_located:
+            self.emit("fold_located(folder, node, |folder, node| {", depth)
+            enumname += "Kind"
+        self.emit("match node {", depth + 1)
+        for cons in sum.types:
+            fields_pattern = self.make_pattern(cons.fields)
+            self.emit(f"{enumname}::{cons.name} {{ {fields_pattern} }} => {{", depth + 2)
+            self.gen_construction(f"{enumname}::{cons.name}", cons.fields, depth + 3)
+            self.emit("}", depth + 2)
+        self.emit("}", depth + 1)
+        if is_located:
+            self.emit("})", depth)
+        self.emit("}", depth)
+
+
+    def visitProduct(self, product, name, depth):
+        apply_t, apply_u, apply_target_u = self.get_generics(name, "T", "U", "F::TargetU")
+        structname = get_rust_type(name)
+        is_located = bool(product.attributes)
+
+        self.emit(f"impl<T, U> Foldable<T, U> for {structname}{apply_t} {{", depth)
+        self.emit(f"type Mapped = {structname}{apply_u};", depth + 1)
+        self.emit("fn fold<F: Fold<T, TargetU = U> + ?Sized>(self, folder: &mut F) -> Result<Self::Mapped, F::Error> {", depth + 1)
+        self.emit(f"folder.fold_{name}(self)", depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("}", depth)
+
+        self.emit(f"pub fn fold_{name}<U, F: Fold<U> + ?Sized>(#[allow(unused)] folder: &mut F, node: {structname}{apply_u}) -> Result<{structname}{apply_target_u}, F::Error> {{", depth)
+        if is_located:
+            self.emit("fold_located(folder, node, |folder, node| {", depth)
+            structname += "Data"
+        fields_pattern = self.make_pattern(product.fields)
+        self.emit(f"let {structname} {{ {fields_pattern} }} = node;", depth + 1)
+        self.gen_construction(structname, product.fields, depth + 1)
+        if is_located:
+            self.emit("})", depth)
+        self.emit("}", depth)
+
+    def make_pattern(self, fields):
+        return ",".join(rust_field(f.name) for f in fields)
+
+    def gen_construction(self, cons_path, fields, depth):
+        self.emit(f"Ok({cons_path} {{", depth)
+        for field in fields:
+            name = rust_field(field.name)
+            self.emit(f"{name}: Foldable::fold({name}, folder)?,", depth + 1)
+        self.emit("})", depth)
+
+
+class FoldModuleVisitor(TypeInfoEmitVisitor):
+    def visitModule(self, mod):
+        depth = 0
+        self.emit('#[cfg(feature = "fold")]', depth)
+        self.emit("pub mod fold {", depth)
+        self.emit("use super::*;", depth + 1)
+        self.emit("use crate::fold_helpers::Foldable;", depth + 1)
+        FoldTraitDefVisitor(self.file, self.typeinfo).visit(mod, depth + 1)
+        FoldImplVisitor(self.file, self.typeinfo).visit(mod, depth + 1)
+        self.emit("}", depth)
+
+
+class ClassDefVisitor(EmitVisitor):
+
+    def visitModule(self, mod):
+        for dfn in mod.dfns:
+            self.visit(dfn)
+
+    def visitType(self, type, depth=0):
+        self.visit(type.value, type.name, depth)
+
+    def visitSum(self, sum, name, depth):
+        for cons in sum.types:
+            self.visit(cons, sum.attributes, depth)
+
+    def visitConstructor(self, cons, attrs, depth):
+        self.gen_classdef(cons.name, cons.fields, attrs, depth)
+
+    def visitProduct(self, product, name, depth):
+        self.gen_classdef(name, product.fields, product.attributes, depth)
+
+    def gen_classdef(self, name, fields, attrs, depth):
+        structname = "Node" + name
+        self.emit(f'#[pyclass(module = "_ast", name = {json.dumps(name)}, base = "AstNode")]', depth)
+        self.emit(f"struct {structname};", depth)
+        self.emit("#[pyimpl(flags(HAS_DICT, BASETYPE))]", depth)
+        self.emit(f"impl {structname} {{", depth)
+        self.emit(f"#[extend_class]", depth + 1)
+        self.emit("fn extend_class_with_fields(ctx: &PyContext, class: &PyTypeRef) {", depth + 1)
+        fields = ",".join(f"ctx.new_str({json.dumps(f.name)})" for f in fields)
+        self.emit(f'class.set_str_attr("_fields", ctx.new_list(vec![{fields}]));', depth + 2)
+        attrs = ",".join(f"ctx.new_str({json.dumps(attr.name)})" for attr in attrs)
+        self.emit(f'class.set_str_attr("_attributes", ctx.new_list(vec![{attrs}]));', depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("}", depth)
+
+class ExtendModuleVisitor(EmitVisitor):
+
+    def visitModule(self, mod):
+        depth = 0
+        self.emit("pub fn extend_module_nodes(vm: &VirtualMachine, module: &PyObjectRef) {", depth)
+        self.emit("extend_module!(vm, module, {", depth + 1)
+        for dfn in mod.dfns:
+            self.visit(dfn, depth + 2)
+        self.emit("})", depth + 1)
+        self.emit("}", depth)
+
+    def visitType(self, type, depth):
+        self.visit(type.value, type.name, depth)
+
+    def visitSum(self, sum, name, depth):
+        for cons in sum.types:
+            self.visit(cons, depth)
+
+    def visitConstructor(self, cons, depth):
+        self.gen_extension(cons.name, depth)
+
+    def visitProduct(self, product, name, depth):
+        self.gen_extension(name, depth)
+
+    def gen_extension(self, name, depth):
+        self.emit(f"{json.dumps(name)} => Node{name}::make_class(&vm.ctx),", depth)
+
+
+class TraitImplVisitor(EmitVisitor):
+
+    def visitModule(self, mod):
+        for dfn in mod.dfns:
+            self.visit(dfn)
+
+    def visitType(self, type, depth=0):
+        self.visit(type.value, type.name, depth)
+
+    def visitSum(self, sum, name, depth):
+        enumname = get_rust_type(name)
+        if sum.attributes:
+            enumname += "Kind"
+
+
+        self.emit(f"impl NamedNode for ast::{enumname} {{", depth)
+        self.emit(f"const NAME: &'static str = {json.dumps(name)};", depth + 1)
+        self.emit("}", depth)
+        self.emit(f"impl Node for ast::{enumname} {{", depth)
+        self.emit("fn ast_to_object(self, _vm: &VirtualMachine) -> PyObjectRef {", depth + 1)
+        self.emit("match self {", depth + 2)
+        for variant in sum.types:
+            self.constructor_to_object(variant, enumname, depth + 3)
+        self.emit("}", depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("fn ast_from_object(_vm: &VirtualMachine, _object: PyObjectRef) -> PyResult<Self> {", depth + 1)
+        self.gen_sum_fromobj(sum, name, enumname, depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("}", depth)
+
+    def constructor_to_object(self, cons, enumname, depth):
+        fields_pattern = self.make_pattern(cons.fields)
+        self.emit(f"ast::{enumname}::{cons.name} {{ {fields_pattern} }} => {{", depth)
+        self.make_node(cons.name, cons.fields, depth + 1)
+        self.emit("}", depth)
+
+    def visitProduct(self, product, name, depth):
+        structname = get_rust_type(name)
+        if product.attributes:
+            structname += "Data"
+
+        self.emit(f"impl NamedNode for ast::{structname} {{", depth)
+        self.emit(f"const NAME: &'static str = {json.dumps(name)};", depth + 1)
+        self.emit("}", depth)
+        self.emit(f"impl Node for ast::{structname} {{", depth)
+        self.emit("fn ast_to_object(self, _vm: &VirtualMachine) -> PyObjectRef {", depth + 1)
+        fields_pattern = self.make_pattern(product.fields)
+        self.emit(f"let ast::{structname} {{ {fields_pattern} }} = self;", depth + 2)
+        self.make_node(name, product.fields, depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("fn ast_from_object(_vm: &VirtualMachine, _object: PyObjectRef) -> PyResult<Self> {", depth + 1)
+        self.gen_product_fromobj(product, name, structname, depth + 2)
+        self.emit("}", depth + 1)
+        self.emit("}", depth)
+
+    def make_node(self, variant, fields, depth):
+        lines = []
+        self.emit(f"let _node = AstNode.into_ref_with_type(_vm, Node{variant}::static_type().clone()).unwrap();", depth)
+        if fields:
+            self.emit("let _dict = _node.as_object().dict().unwrap();", depth)
+        for f in fields:
+            self.emit(f"_dict.set_item({json.dumps(f.name)}, {rust_field(f.name)}.ast_to_object(_vm), _vm).unwrap();", depth)
+        self.emit("_node.into_object()", depth)
+
+    def make_pattern(self, fields):
+        return ",".join(rust_field(f.name) for f in fields)
+
+    def gen_sum_fromobj(self, sum, sumname, enumname, depth):
+        if sum.attributes:
+            self.extract_location(sumname, depth)
+
+        self.emit("let _cls = _object.class();", depth)
+        self.emit("Ok(", depth)
+        for cons in sum.types:
+            self.emit(f"if _cls.is(Node{cons.name}::static_type()) {{", depth)
+            self.gen_construction(f"{enumname}::{cons.name}", cons, sumname, depth + 1)
+            self.emit("} else", depth)
+
+        self.emit("{", depth)
+        msg = f'format!("expected some sort of {sumname}, but got {{}}",_vm.to_repr(&_object)?)'
+        self.emit(f"return Err(_vm.new_type_error({msg}));", depth + 1)
+        self.emit("})", depth)
+
+    def gen_product_fromobj(self, product, prodname, structname, depth):
+        if product.attributes:
+            self.extract_location(prodname, depth)
+
+        self.emit("Ok(", depth)
+        self.gen_construction(structname, product, prodname, depth + 1)
+        self.emit(")", depth)
+
+    def gen_construction(self, cons_path, cons, name, depth):
+        self.emit(f"ast::{cons_path} {{", depth)
+        for field in cons.fields:
+            self.emit(f"{rust_field(field.name)}: {self.decode_field(field, name)},", depth + 1)
+        self.emit("}", depth)
+
+    def extract_location(self, typename, depth):
+        row = self.decode_field(asdl.Field('int', 'lineno'), typename)
+        column = self.decode_field(asdl.Field('int', 'col_offset'), typename)
+        self.emit(f"let _location = ast::Location::new({row}, {column});", depth)
+
+    def wrap_located_node(self, depth):
+        self.emit(f"let node = ast::Located::new(_location, node);", depth)
+
+    def decode_field(self, field, typename):
+        name = json.dumps(field.name)
+        if field.opt and not field.seq:
+            return f"get_node_field_opt(_vm, &_object, {name})?.map(|obj| Node::ast_from_object(_vm, obj)).transpose()?"
+        else:
+            return f"Node::ast_from_object(_vm, get_node_field(_vm, &_object, {name}, {json.dumps(typename)})?)?"
+
+class ChainOfVisitors:
+    def __init__(self, *visitors):
+        self.visitors = visitors
+
+    def visit(self, object):
+        for v in self.visitors:
+            v.visit(object)
+            v.emit("", 0)
+
+
+def write_ast_def(mod, typeinfo, f):
+    f.write('pub use crate::location::Location;\n')
+    f.write('pub use crate::constant::*;\n')
+    f.write('\n')
+    f.write('type Ident = String;\n')
+    f.write('\n')
+    StructVisitor(f, typeinfo).emit_attrs(0)
+    f.write('pub struct Located<T, U = ()> {\n')
+    f.write('    pub location: Location,\n')
+    f.write('    pub custom: U,\n')
+    f.write('    pub node: T,\n')
+    f.write('}\n')
+    f.write('\n')
+    f.write('impl<T> Located<T> {\n')
+    f.write('    pub fn new(location: Location, node: T) -> Self {\n')
+    f.write('        Self { location, custom: (), node }\n')
+    f.write('    }\n')
+    f.write('}\n')
+    f.write('\n')
+
+    c = ChainOfVisitors(StructVisitor(f, typeinfo),
+                        FoldModuleVisitor(f, typeinfo))
+    c.visit(mod)
+
+
+def write_ast_mod(mod, f):
+    f.write('use super::*;\n')
+    f.write('\n')
+
+    c = ChainOfVisitors(ClassDefVisitor(f),
+                        TraitImplVisitor(f),
+                        ExtendModuleVisitor(f))
+    c.visit(mod)
+
+def main(input_filename, ast_mod_filename, ast_def_filename, dump_module=False):
+    auto_gen_msg = AUTOGEN_MESSAGE.format("/".join(Path(__file__).parts[-2:]))
+    mod = asdl.parse(input_filename)
+    if dump_module:
+        print('Parsed Module:')
+        print(mod)
+    if not asdl.check(mod):
+        sys.exit(1)
+
+    typeinfo = {}
+    FindUserdataTypesVisitor(typeinfo).visit(mod)
+
+    with ast_def_filename.open("w") as def_file, \
+         ast_mod_filename.open("w") as mod_file:
+        def_file.write(auto_gen_msg)
+        write_ast_def(mod, typeinfo, def_file)
+
+        mod_file.write(auto_gen_msg)
+        write_ast_mod(mod, mod_file)
+
+    print(f"{ast_def_filename}, {ast_mod_filename} regenerated.")
+
+if __name__ == "__main__":
+    parser = ArgumentParser()
+    parser.add_argument("input_file", type=Path)
+    parser.add_argument("-M", "--mod-file", type=Path, required=True)
+    parser.add_argument("-D", "--def-file", type=Path, required=True)
+    parser.add_argument("-d", "--dump-module", action="store_true")
+
+    args = parser.parse_args()
+    main(args.input_file, args.mod_file, args.def_file, args.dump_module)

nac3ast/src/constant.rs

@@ -0,0 +1,213 @@
+#[derive(Clone, Debug, PartialEq)]
+pub enum Constant {
+    None,
+    Bool(bool),
+    Str(String),
+    Bytes(Vec<u8>),
+    Int(i128),
+    Tuple(Vec<Constant>),
+    Float(f64),
+    Complex { real: f64, imag: f64 },
+    Ellipsis,
+}
+
+impl From<String> for Constant {
+    fn from(s: String) -> Constant {
+        Self::Str(s)
+    }
+}
+impl From<Vec<u8>> for Constant {
+    fn from(b: Vec<u8>) -> Constant {
+        Self::Bytes(b)
+    }
+}
+impl From<bool> for Constant {
+    fn from(b: bool) -> Constant {
+        Self::Bool(b)
+    }
+}
+impl From<i32> for Constant {
+    fn from(i: i32) -> Constant {
+        Self::Int(i as i128)
+    }
+}
+impl From<i64> for Constant {
+    fn from(i: i64) -> Constant {
+        Self::Int(i as i128)
+    }
+}
+
+/// Transforms a value prior to formatting it.
+#[derive(Copy, Clone, Debug, PartialEq)]
+#[repr(u8)]
+pub enum ConversionFlag {
+    /// Converts by calling `str(<value>)`.
+    Str = b's',
+    /// Converts by calling `ascii(<value>)`.
+    Ascii = b'a',
+    /// Converts by calling `repr(<value>)`.
+    Repr = b'r',
+}
+
+impl ConversionFlag {
+    pub fn try_from_byte(b: u8) -> Option<Self> {
+        match b {
+            b's' => Some(Self::Str),
+            b'a' => Some(Self::Ascii),
+            b'r' => Some(Self::Repr),
+            _ => None,
+        }
+    }
+}
+
+#[cfg(feature = "constant-optimization")]
+#[derive(Default)]
+pub struct ConstantOptimizer {
+    _priv: (),
+}
+
+#[cfg(feature = "constant-optimization")]
+impl ConstantOptimizer {
+    #[inline]
+    pub fn new() -> Self {
+        Self { _priv: () }
+    }
+}
+
+#[cfg(feature = "constant-optimization")]
+impl<U> crate::fold::Fold<U> for ConstantOptimizer {
+    type TargetU = U;
+    type Error = std::convert::Infallible;
+    #[inline]
+    fn map_user(&mut self, user: U) -> Result<Self::TargetU, Self::Error> {
+        Ok(user)
+    }
+    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,
+                })
+            }
+            _ => crate::fold::fold_expr(self, node),
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    #[cfg(feature = "constant-optimization")]
+    #[test]
+    fn test_constant_opt() {
+        use super::*;
+        use crate::fold::Fold;
+        use crate::*;
+
+        let location = Location::new(0, 0, Default::default());
+        let custom = ();
+        let ast = Located {
+            location,
+            custom,
+            node: ExprKind::Tuple {
+                ctx: ExprContext::Load,
+                elts: vec![
+                    Located {
+                        location,
+                        custom,
+                        node: ExprKind::Constant {
+                            value: 1.into(),
+                            kind: None,
+                        },
+                    },
+                    Located {
+                        location,
+                        custom,
+                        node: ExprKind::Constant {
+                            value: 2.into(),
+                            kind: None,
+                        },
+                    },
+                    Located {
+                        location,
+                        custom,
+                        node: ExprKind::Tuple {
+                            ctx: ExprContext::Load,
+                            elts: vec![
+                                Located {
+                                    location,
+                                    custom,
+                                    node: ExprKind::Constant {
+                                        value: 3.into(),
+                                        kind: None,
+                                    },
+                                },
+                                Located {
+                                    location,
+                                    custom,
+                                    node: ExprKind::Constant {
+                                        value: 4.into(),
+                                        kind: None,
+                                    },
+                                },
+                                Located {
+                                    location,
+                                    custom,
+                                    node: ExprKind::Constant {
+                                        value: 5.into(),
+                                        kind: None,
+                                    },
+                                },
+                            ],
+                        },
+                    },
+                ],
+            },
+        };
+        let new_ast = ConstantOptimizer::new()
+            .fold_expr(ast)
+            .unwrap_or_else(|e| match e {});
+        assert_eq!(
+            new_ast,
+            Located {
+                location,
+                custom,
+                node: ExprKind::Constant {
+                    value: Constant::Tuple(vec![
+                        1.into(),
+                        2.into(),
+                        Constant::Tuple(vec![
+                            3.into(),
+                            4.into(),
+                            5.into(),
+                        ])
+                    ]),
+                    kind: None
+                },
+            }
+        );
+    }
+}

nac3ast/src/fold_helpers.rs

@@ -0,0 +1,74 @@
+use crate::constant;
+use crate::fold::Fold;
+use crate::StrRef;
+
+pub(crate) trait Foldable<T, U> {
+    type Mapped;
+    fn fold<F: Fold<T, TargetU = U> + ?Sized>(
+        self,
+        folder: &mut F,
+    ) -> Result<Self::Mapped, F::Error>;
+}
+
+impl<T, U, X> Foldable<T, U> for Vec<X>
+where
+    X: Foldable<T, U>,
+{
+    type Mapped = Vec<X::Mapped>;
+    fn fold<F: Fold<T, TargetU = U> + ?Sized>(
+        self,
+        folder: &mut F,
+    ) -> Result<Self::Mapped, F::Error> {
+        self.into_iter().map(|x| x.fold(folder)).collect()
+    }
+}
+
+impl<T, U, X> Foldable<T, U> for Option<X>
+where
+    X: Foldable<T, U>,
+{
+    type Mapped = Option<X::Mapped>;
+    fn fold<F: Fold<T, TargetU = U> + ?Sized>(
+        self,
+        folder: &mut F,
+    ) -> Result<Self::Mapped, F::Error> {
+        self.map(|x| x.fold(folder)).transpose()
+    }
+}
+
+impl<T, U, X> Foldable<T, U> for Box<X>
+where
+    X: Foldable<T, U>,
+{
+    type Mapped = Box<X::Mapped>;
+    fn fold<F: Fold<T, TargetU = U> + ?Sized>(
+        self,
+        folder: &mut F,
+    ) -> Result<Self::Mapped, F::Error> {
+        (*self).fold(folder).map(Box::new)
+    }
+}
+
+macro_rules! simple_fold {
+    ($($t:ty),+$(,)?) => {
+        $(impl<T, U> $crate::fold_helpers::Foldable<T, U> for $t {
+            type Mapped = Self;
+            #[inline]
+            fn fold<F: Fold<T, TargetU = U> + ?Sized>(
+                self,
+                _folder: &mut F,
+            ) -> Result<Self::Mapped, F::Error> {
+                Ok(self)
+            }
+        })+
+    };
+}
+
+simple_fold!(
+    usize,
+    String,
+    bool,
+    StrRef,
+    constant::Constant,
+    constant::ConversionFlag
+);

nac3ast/src/impls.rs

@@ -0,0 +1,53 @@
+use crate::{Constant, ExprKind};
+
+impl<U> ExprKind<U> {
+    /// Returns a short name for the node suitable for use in error messages.
+    pub fn name(&self) -> &'static str {
+        match self {
+            ExprKind::BoolOp { .. } | ExprKind::BinOp { .. } | ExprKind::UnaryOp { .. } => {
+                "operator"
+            }
+            ExprKind::Subscript { .. } => "subscript",
+            ExprKind::Await { .. } => "await expression",
+            ExprKind::Yield { .. } | ExprKind::YieldFrom { .. } => "yield expression",
+            ExprKind::Compare { .. } => "comparison",
+            ExprKind::Attribute { .. } => "attribute",
+            ExprKind::Call { .. } => "function call",
+            ExprKind::Constant { value, .. } => match value {
+                Constant::Str(_)
+                | Constant::Int(_)
+                | Constant::Float(_)
+                | Constant::Complex { .. }
+                | Constant::Bytes(_) => "literal",
+                Constant::Tuple(_) => "tuple",
+                Constant::Bool(_) | Constant::None => "keyword",
+                Constant::Ellipsis => "ellipsis",
+            },
+            ExprKind::List { .. } => "list",
+            ExprKind::Tuple { .. } => "tuple",
+            ExprKind::Dict { .. } => "dict display",
+            ExprKind::Set { .. } => "set display",
+            ExprKind::ListComp { .. } => "list comprehension",
+            ExprKind::DictComp { .. } => "dict comprehension",
+            ExprKind::SetComp { .. } => "set comprehension",
+            ExprKind::GeneratorExp { .. } => "generator expression",
+            ExprKind::Starred { .. } => "starred",
+            ExprKind::Slice { .. } => "slice",
+            ExprKind::JoinedStr { values } => {
+                if values
+                    .iter()
+                    .any(|e| matches!(e.node, ExprKind::JoinedStr { .. }))
+                {
+                    "f-string expression"
+                } else {
+                    "literal"
+                }
+            }
+            ExprKind::FormattedValue { .. } => "f-string expression",
+            ExprKind::Name { .. } => "name",
+            ExprKind::Lambda { .. } => "lambda",
+            ExprKind::IfExp { .. } => "conditional expression",
+            ExprKind::NamedExpr { .. } => "named expression",
+        }
+    }
+}

nac3ast/src/lib.rs

@@ -0,0 +1,14 @@
+#[macro_use]
+extern crate lazy_static;
+
+mod ast_gen;
+mod constant;
+#[cfg(feature = "fold")]
+mod fold_helpers;
+mod impls;
+mod location;
+
+pub use ast_gen::*;
+pub use location::{Location, FileName};
+
+pub type Suite<U = ()> = Vec<Stmt<U>>;

nac3ast/src/location.rs

@@ -0,0 +1,94 @@
+//! Datatypes to support source location information.
+use crate::ast_gen::StrRef;
+use std::fmt;
+
+#[derive(Clone, Copy, Debug, PartialEq)]
+pub struct FileName(pub StrRef);
+impl Default for FileName {
+    fn default() -> Self {
+        FileName("unknown".into())
+    }
+}
+
+impl From<String> for FileName {
+    fn from(s: String) -> Self {
+        FileName(s.into())
+    }
+}
+
+/// A location somewhere in the sourcecode.
+#[derive(Clone, Copy, Debug, Default, PartialEq)]
+pub struct Location {
+    pub row: usize,
+    pub column: usize,
+    pub file: FileName
+}
+
+impl fmt::Display for Location {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{}: line {} column {}", self.file.0, self.row, self.column)
+    }
+}
+
+impl Location {
+    pub fn visualize<'a>(
+        &self,
+        line: &'a str,
+        desc: impl fmt::Display + 'a,
+    ) -> impl fmt::Display + 'a {
+        struct Visualize<'a, D: fmt::Display> {
+            loc: Location,
+            line: &'a str,
+            desc: D,
+        }
+        impl<D: fmt::Display> fmt::Display for Visualize<'_, D> {
+            fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+                write!(
+                    f,
+                    "{}\n{}\n{arrow:>pad$}",
+                    self.desc,
+                    self.line,
+                    pad = self.loc.column,
+                    arrow = "↑",
+                )
+            }
+        }
+        Visualize {
+            loc: *self,
+            line,
+            desc,
+        }
+    }
+}
+
+impl Location {
+    pub fn new(row: usize, column: usize, file: FileName) -> Self {
+        Location { row, column, file }
+    }
+
+    pub fn row(&self) -> usize {
+        self.row
+    }
+
+    pub fn column(&self) -> usize {
+        self.column
+    }
+
+    pub fn reset(&mut self) {
+        self.row = 1;
+        self.column = 1;
+    }
+
+    pub fn go_right(&mut self) {
+        self.column += 1;
+    }
+
+    pub fn go_left(&mut self) {
+        self.column -= 1;
+    }
+
+    pub fn newline(&mut self) {
+        self.row += 1;
+        self.column = 1;
+    }
+}

nac3core/Cargo.toml

@@ -5,12 +5,21 @@ authors = ["M-Labs"]
 edition = "2018"
 
 [dependencies]
-num-bigint = "0.3"
-num-traits = "0.2"
-inkwell = { git = "https://github.com/TheDan64/inkwell", branch = "master", features = ["llvm10-0"] }
-rustpython-parser = { git = "https://github.com/RustPython/RustPython", branch = "master" }
-indoc = "1.0"
+itertools = "0.10.1"
+crossbeam = "0.8.1"
+parking_lot = "0.11.1"
+rayon = "1.5.1"
+nac3parser = { path = "../nac3parser" }
+
+[dependencies.inkwell]
+version = "0.1.0-beta.4"
+default-features = false
+features = ["llvm13-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
 
 [dev-dependencies]
 test-case = "1.2.0"
-indoc = "1.0"
+indoc = "1.0"
+insta = "=1.11.0"
+
+[build-dependencies]
+regex = "1"

nac3core/build.rs

@@ -0,0 +1,72 @@
+use regex::Regex;
+use std::{
+    env,
+    fs::File,
+    io::Write,
+    path::Path,
+    process::{Command, Stdio},
+};
+
+fn main() {
+    const FILE: &str = "src/codegen/irrt/irrt.c";
+    println!("cargo:rerun-if-changed={}", FILE);
+    let out_dir = env::var("OUT_DIR").unwrap();
+    let out_path = Path::new(&out_dir);
+
+    /*
+     * 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.
+     */
+
+    const FLAG: &[&str] = &[
+        "--target=wasm32",
+        FILE,
+        "-O3",
+        "-emit-llvm",
+        "-S",
+        "-Wall",
+        "-Wextra",
+        "-o",
+        "-",
+    ];
+    let output = Command::new("clang")
+        .args(FLAG)
+        .output()
+        .map(|o| {
+            assert!(o.status.success(), "{}", std::str::from_utf8(&o.stderr).unwrap());
+            o
+        })
+        .unwrap();
+
+    // https://github.com/rust-lang/regex/issues/244
+    let output = std::str::from_utf8(&output.stdout).unwrap().replace("\r\n", "\n");
+    let mut filtered_output = String::with_capacity(output.len());
+
+    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');
+    }
+
+    let filtered_output = Regex::new("(#\\d+)|(, *![0-9A-Za-z.]+)|(![0-9A-Za-z.]+)|(!\".*?\")")
+        .unwrap()
+        .replace_all(&filtered_output, "");
+
+    println!("cargo:rerun-if-env-changed=DEBUG_DUMP_IRRT");
+    if env::var("DEBUG_DUMP_IRRT").is_ok() {
+        let mut file = File::create(out_path.join("irrt.ll")).unwrap();
+        file.write_all(output.as_bytes()).unwrap();
+        let mut file = File::create(out_path.join("irrt-filtered.ll")).unwrap();
+        file.write_all(filtered_output.as_bytes()).unwrap();
+    }
+
+    let mut llvm_as = Command::new("llvm-as")
+        .stdin(Stdio::piped())
+        .arg("-o")
+        .arg(out_path.join("irrt.bc"))
+        .spawn()
+        .unwrap();
+    llvm_as.stdin.as_mut().unwrap().write_all(filtered_output.as_bytes()).unwrap();
+    assert!(llvm_as.wait().unwrap().success())
+}

nac3core/src/codegen/concrete_type.rs

@@ -0,0 +1,305 @@
+use crate::{
+    symbol_resolver::SymbolValue,
+    toplevel::DefinitionId,
+    typecheck::{
+        type_inferencer::PrimitiveStore,
+        typedef::{FunSignature, FuncArg, Type, TypeEnum, Unifier},
+    },
+};
+
+use nac3parser::ast::StrRef;
+use std::collections::HashMap;
+
+pub struct ConcreteTypeStore {
+    store: Vec<ConcreteTypeEnum>,
+}
+
+#[derive(Copy, Clone, Eq, PartialEq, Hash, Debug)]
+pub struct ConcreteType(usize);
+
+#[derive(Clone, Debug)]
+pub struct ConcreteFuncArg {
+    pub name: StrRef,
+    pub ty: ConcreteType,
+    pub default_value: Option<SymbolValue>,
+}
+
+#[derive(Clone, Debug)]
+pub enum Primitive {
+    Int32,
+    Int64,
+    UInt32,
+    UInt64,
+    Float,
+    Bool,
+    None,
+    Range,
+    Str,
+    Exception,
+}
+
+#[derive(Debug)]
+pub enum ConcreteTypeEnum {
+    TPrimitive(Primitive),
+    TTuple {
+        ty: Vec<ConcreteType>,
+    },
+    TList {
+        ty: ConcreteType,
+    },
+    TObj {
+        obj_id: DefinitionId,
+        fields: HashMap<StrRef, (ConcreteType, bool)>,
+        params: HashMap<u32, ConcreteType>,
+    },
+    TVirtual {
+        ty: ConcreteType,
+    },
+    TFunc {
+        args: Vec<ConcreteFuncArg>,
+        ret: ConcreteType,
+        vars: HashMap<u32, ConcreteType>,
+    },
+}
+
+impl ConcreteTypeStore {
+    pub fn new() -> ConcreteTypeStore {
+        ConcreteTypeStore {
+            store: vec![
+                ConcreteTypeEnum::TPrimitive(Primitive::Int32),
+                ConcreteTypeEnum::TPrimitive(Primitive::Int64),
+                ConcreteTypeEnum::TPrimitive(Primitive::Float),
+                ConcreteTypeEnum::TPrimitive(Primitive::Bool),
+                ConcreteTypeEnum::TPrimitive(Primitive::None),
+                ConcreteTypeEnum::TPrimitive(Primitive::Range),
+                ConcreteTypeEnum::TPrimitive(Primitive::Str),
+                ConcreteTypeEnum::TPrimitive(Primitive::Exception),
+                ConcreteTypeEnum::TPrimitive(Primitive::UInt32),
+                ConcreteTypeEnum::TPrimitive(Primitive::UInt64),
+            ],
+        }
+    }
+
+    pub fn get(&self, cty: ConcreteType) -> &ConcreteTypeEnum {
+        &self.store[cty.0]
+    }
+
+    pub fn from_signature(
+        &mut self,
+        unifier: &mut Unifier,
+        primitives: &PrimitiveStore,
+        signature: &FunSignature,
+        cache: &mut HashMap<Type, Option<ConcreteType>>,
+    ) -> ConcreteTypeEnum {
+        ConcreteTypeEnum::TFunc {
+            args: signature
+                .args
+                .iter()
+                .map(|arg| ConcreteFuncArg {
+                    name: arg.name,
+                    ty: self.from_unifier_type(unifier, primitives, arg.ty, cache),
+                    default_value: arg.default_value.clone(),
+                })
+                .collect(),
+            ret: self.from_unifier_type(unifier, primitives, signature.ret, cache),
+            vars: signature
+                .vars
+                .iter()
+                .map(|(id, ty)| (*id, self.from_unifier_type(unifier, primitives, *ty, cache)))
+                .collect(),
+        }
+    }
+
+    pub fn from_unifier_type(
+        &mut self,
+        unifier: &mut Unifier,
+        primitives: &PrimitiveStore,
+        ty: Type,
+        cache: &mut HashMap<Type, Option<ConcreteType>>,
+    ) -> ConcreteType {
+        let ty = unifier.get_representative(ty);
+        if unifier.unioned(ty, primitives.int32) {
+            ConcreteType(0)
+        } else if unifier.unioned(ty, primitives.int64) {
+            ConcreteType(1)
+        } else if unifier.unioned(ty, primitives.float) {
+            ConcreteType(2)
+        } else if unifier.unioned(ty, primitives.bool) {
+            ConcreteType(3)
+        } else if unifier.unioned(ty, primitives.none) {
+            ConcreteType(4)
+        } else if unifier.unioned(ty, primitives.range) {
+            ConcreteType(5)
+        } else if unifier.unioned(ty, primitives.str) {
+            ConcreteType(6)
+        } else if unifier.unioned(ty, primitives.exception) {
+            ConcreteType(7)
+        } else if unifier.unioned(ty, primitives.uint32) {
+            ConcreteType(8)
+        } else if unifier.unioned(ty, primitives.uint64) {
+            ConcreteType(9)
+        } else if let Some(cty) = cache.get(&ty) {
+            if let Some(cty) = cty {
+                *cty
+            } else {
+                let index = self.store.len();
+                // placeholder
+                self.store.push(ConcreteTypeEnum::TPrimitive(Primitive::Int32));
+                let result = ConcreteType(index);
+                cache.insert(ty, Some(result));
+                result
+            }
+        } else {
+            cache.insert(ty, None);
+            let ty_enum = unifier.get_ty(ty);
+            let result = match &*ty_enum {
+                TypeEnum::TTuple { ty } => ConcreteTypeEnum::TTuple {
+                    ty: ty
+                        .iter()
+                        .map(|t| self.from_unifier_type(unifier, primitives, *t, cache))
+                        .collect(),
+                },
+                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,
+                    fields: fields
+                        .iter()
+                        .filter_map(|(name, ty)| {
+                            // here we should not have type vars, but some partial instantiated
+                            // class methods can still have uninstantiated type vars, so
+                            // filter out all the methods, as this will not affect codegen
+                            if let TypeEnum::TFunc(..) = &*unifier.get_ty(ty.0) {
+                                None
+                            } else {
+                                Some((
+                                    *name,
+                                    (
+                                        self.from_unifier_type(unifier, primitives, ty.0, cache),
+                                        ty.1,
+                                    ),
+                                ))
+                            }
+                        })
+                        .collect(),
+                    params: params
+                        .iter()
+                        .map(|(id, ty)| {
+                            (*id, self.from_unifier_type(unifier, primitives, *ty, cache))
+                        })
+                        .collect(),
+                },
+                TypeEnum::TVirtual { ty } => ConcreteTypeEnum::TVirtual {
+                    ty: self.from_unifier_type(unifier, primitives, *ty, cache),
+                },
+                TypeEnum::TFunc(signature) => {
+                    self.from_signature(unifier, primitives, &*signature, cache)
+                }
+                _ => unreachable!(),
+            };
+            let index = if let Some(ConcreteType(index)) = cache.get(&ty).unwrap() {
+                self.store[*index] = result;
+                *index
+            } else {
+                self.store.push(result);
+                self.store.len() - 1
+            };
+            cache.insert(ty, Some(ConcreteType(index)));
+            ConcreteType(index)
+        }
+    }
+
+    pub fn to_unifier_type(
+        &self,
+        unifier: &mut Unifier,
+        primitives: &PrimitiveStore,
+        cty: ConcreteType,
+        cache: &mut HashMap<ConcreteType, Option<Type>>,
+    ) -> Type {
+        if let Some(ty) = cache.get_mut(&cty) {
+            return if let Some(ty) = ty {
+                *ty
+            } else {
+                *ty = Some(unifier.get_dummy_var().0);
+                ty.unwrap()
+            };
+        }
+        cache.insert(cty, None);
+        let result = match &self.store[cty.0] {
+            ConcreteTypeEnum::TPrimitive(primitive) => {
+                let ty = match primitive {
+                    Primitive::Int32 => primitives.int32,
+                    Primitive::Int64 => primitives.int64,
+                    Primitive::UInt32 => primitives.uint32,
+                    Primitive::UInt64 => primitives.uint64,
+                    Primitive::Float => primitives.float,
+                    Primitive::Bool => primitives.bool,
+                    Primitive::None => primitives.none,
+                    Primitive::Range => primitives.range,
+                    Primitive::Str => primitives.str,
+                    Primitive::Exception => primitives.exception,
+                };
+                *cache.get_mut(&cty).unwrap() = Some(ty);
+                return ty;
+            }
+            ConcreteTypeEnum::TTuple { ty } => TypeEnum::TTuple {
+                ty: ty
+                    .iter()
+                    .map(|cty| self.to_unifier_type(unifier, primitives, *cty, cache))
+                    .collect(),
+            },
+            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) }
+            }
+            ConcreteTypeEnum::TObj { obj_id, fields, params } => TypeEnum::TObj {
+                obj_id: *obj_id,
+                fields: fields
+                    .iter()
+                    .map(|(name, cty)| {
+                        (*name, (self.to_unifier_type(unifier, primitives, cty.0, cache), cty.1))
+                    })
+                    .collect::<HashMap<_, _>>(),
+                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
+                    .iter()
+                    .map(|arg| FuncArg {
+                        name: arg.name,
+                        ty: self.to_unifier_type(unifier, primitives, arg.ty, cache),
+                        default_value: arg.default_value.clone(),
+                    })
+                    .collect(),
+                ret: self.to_unifier_type(unifier, primitives, *ret, cache),
+                vars: vars
+                    .iter()
+                    .map(|(id, cty)| (*id, self.to_unifier_type(unifier, primitives, *cty, cache)))
+                    .collect::<HashMap<_, _>>(),
+            }),
+        };
+        let result = unifier.add_ty(result);
+        if let Some(ty) = cache.get(&cty).unwrap() {
+            unifier.unify(*ty, result).unwrap();
+        }
+        cache.insert(cty, Some(result));
+        result
+    }
+
+    pub fn add_cty(&mut self, cty: ConcreteTypeEnum) -> ConcreteType {
+        self.store.push(cty);
+        ConcreteType(self.store.len() - 1)
+    }
+}
+
+impl Default for ConcreteTypeStore {
+    fn default() -> Self {
+        Self::new()
+    }
+}

nac3core/src/codegen/generator.rs

@@ -0,0 +1,209 @@
+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.
+    fn get_name(&self) -> &str;
+
+    fn get_size_type<'ctx>(&self, ctx: &'ctx Context) -> IntType<'ctx>;
+
+    /// Generate function call and returns the function return value.
+    /// - obj: Optional object for method call.
+    /// - 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, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        obj: Option<(Type, ValueEnum<'ctx>)>,
+        fun: (&FunSignature, DefinitionId),
+        params: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
+    ) -> Result<Option<BasicValueEnum<'ctx>>, String>
+    where
+        Self: Sized,
+    {
+        gen_call(self, ctx, obj, fun, params)
+    }
+
+    /// Generate object constructor and returns the constructed object.
+    /// - signature: Function signature of the constructor.
+    /// - def: Class definition for the constructor class.
+    /// - params: Function parameters.
+    fn gen_constructor<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        signature: &FunSignature,
+        def: &TopLevelDef,
+        params: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
+    ) -> Result<BasicValueEnum<'ctx>, String>
+    where
+        Self: Sized,
+    {
+        gen_constructor(self, ctx, signature, def, params)
+    }
+
+    /// Generate a function instance.
+    /// - obj: Optional object for method call.
+    /// - 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, 'a>(
+        &mut self,
+        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)
+    }
+
+    /// Generate the code for an expression.
+    fn gen_expr<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        expr: &Expr<Option<Type>>,
+    ) -> Result<Option<ValueEnum<'ctx>>, String>
+    where
+        Self: Sized,
+    {
+        gen_expr(self, ctx, expr)
+    }
+
+    /// 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, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        ty: BasicTypeEnum<'ctx>,
+    ) -> Result<PointerValue<'ctx>, String> {
+        gen_var(ctx, ty)
+    }
+
+    /// Return a pointer pointing to the target of the expression.
+    fn gen_store_target<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        pattern: &Expr<Option<Type>>,
+    ) -> Result<PointerValue<'ctx>, String>
+    where
+        Self: Sized,
+    {
+        gen_store_target(self, ctx, pattern)
+    }
+
+    /// Generate code for an assignment expression.
+    fn gen_assign<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        target: &Expr<Option<Type>>,
+        value: ValueEnum<'ctx>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_assign(self, ctx, target, value)
+    }
+
+    /// Generate code for a while expression.
+    /// Return true if the while loop must early return
+    fn gen_while<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_while(self, ctx, stmt)
+    }
+
+    /// 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, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_for(self, ctx, stmt)
+    }
+
+    /// Generate code for an if expression.
+    /// Return true if the statement must early return
+    fn gen_if<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_if(self, ctx, stmt)
+    }
+
+    fn gen_with<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_with(self, ctx, stmt)
+    }
+
+    /// Generate code for a statement
+    /// Return true if the statement must early return
+    fn gen_stmt<'ctx, 'a>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        stmt: &Stmt<Option<Type>>,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_stmt(self, ctx, stmt)
+    }
+}
+
+pub struct DefaultCodeGenerator {
+    name: String,
+    size_t: u32,
+}
+
+impl DefaultCodeGenerator {
+    pub fn new(name: String, size_t: u32) -> DefaultCodeGenerator {
+        assert!(size_t == 32 || size_t == 64);
+        DefaultCodeGenerator { name, size_t }
+    }
+}
+
+impl CodeGenerator for DefaultCodeGenerator {
+    fn get_name(&self) -> &str {
+        &self.name
+    }
+
+    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...
+        if self.size_t == 32 {
+            ctx.i32_type()
+        } else {
+            ctx.i64_type()
+        }
+    }
+}

nac3core/src/codegen/irrt/irrt.c

@@ -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 = __builtin_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;
+}

nac3core/src/codegen/irrt/mod.rs

@@ -0,0 +1,434 @@
+use crate::typecheck::typedef::Type;
+
+use super::{CodeGenContext, CodeGenerator};
+use inkwell::{
+    attributes::{Attribute, AttributeLoc},
+    context::Context,
+    memory_buffer::MemoryBuffer,
+    module::Module,
+    types::BasicTypeEnum,
+    values::{IntValue, PointerValue},
+    AddressSpace, IntPredicate,
+};
+use nac3parser::ast::Expr;
+
+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",
+    );
+    let irrt_mod = Module::parse_bitcode_from_buffer(&bitcode_buf, ctx).unwrap();
+    let inline_attr = Attribute::get_named_enum_kind_id("alwaysinline");
+    for symbol in &[
+        "__nac3_int_exp_int32_t",
+        "__nac3_int_exp_int64_t",
+        "__nac3_range_slice_len",
+        "__nac3_slice_index_bound",
+    ] {
+        let function = irrt_mod.get_function(symbol).unwrap();
+        function.add_attribute(AttributeLoc::Function, ctx.create_enum_attribute(inline_attr, 0));
+    }
+    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, 'a>(
+    generator: &mut dyn CodeGenerator,
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    base: IntValue<'ctx>,
+    exp: IntValue<'ctx>,
+    signed: bool,
+) -> IntValue<'ctx> {
+    let symbol = match (base.get_type().get_bit_width(), exp.get_type().get_bit_width(), signed) {
+        (32, 32, true) => "__nac3_int_exp_int32_t",
+        (64, 64, true) => "__nac3_int_exp_int64_t",
+        (32, 32, false) => "__nac3_int_exp_uint32_t",
+        (64, 64, false) => "__nac3_int_exp_uint64_t",
+        _ => 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",
+    );
+    ctx.make_assert(
+        generator,
+        ge_zero,
+        "0:ValueError",
+        "integer power must be positive or zero",
+        [None, None, None],
+        ctx.current_loc,
+    );
+    ctx.builder
+        .build_call(pow_fun, &[base.into(), exp.into()], "call_int_pow")
+        .try_as_basic_value()
+        .unwrap_left()
+        .into_int_value()
+}
+
+pub fn calculate_len_for_slice_range<'ctx, 'a>(
+    generator: &mut dyn CodeGenerator,
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    start: IntValue<'ctx>,
+    end: IntValue<'ctx>,
+    step: IntValue<'ctx>,
+) -> IntValue<'ctx> {
+    const SYMBOL: &str = "__nac3_range_slice_len";
+    let len_func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
+        let i32_t = ctx.ctx.i32_type();
+        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into(), i32_t.into()], false);
+        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",
+    );
+    ctx.make_assert(
+        generator,
+        not_zero,
+        "0:ValueError",
+        "step must not be zero",
+        [None, None, None],
+        ctx.current_loc,
+    );
+    ctx.builder
+        .build_call(len_func, &[start.into(), end.into(), step.into()], "calc_len")
+        .try_as_basic_value()
+        .left()
+        .unwrap()
+        .into_int_value()
+}
+
+/// NOTE: the output value of the end index of this function should be compared ***inclusively***,
+/// because python allows `a[2::-1]`, whose semantic is `[a[2], a[1], a[0]]`, which is equivalent to
+/// NO numeric slice in python.
+///
+/// equivalent code:
+/// ```pseudo_code
+/// match (start, end, step):
+///     case (s, e, None | Some(step)) if step > 0:
+///         return (
+///             match s:
+///                 case None:
+///                     0
+///                 case Some(s):
+///                     handle_in_bound(s)
+///             ,match e:
+///                 case None:
+///                     length - 1
+///                 case Some(e):
+///                     handle_in_bound(e) - 1
+///             ,step == None ? 1 : step
+///         )
+///     case (s, e, Some(step)) if step < 0:
+///         return (
+///             match s:
+///                 case None:
+///                     length - 1
+///                 case Some(s):
+///                     s = handle_in_bound(s)
+///                     if s == length:
+///                         s - 1
+///                     else:
+///                         s
+///             ,match e:
+///                 case None:
+///                     0
+///                 case Some(e):
+///                     handle_in_bound(e) + 1
+///             ,step
+///         )
+/// ```
+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, 'a>,
+    generator: &mut G,
+    list: PointerValue<'ctx>,
+) -> Result<(IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>), String> {
+    let int32 = ctx.ctx.i32_type();
+    let zero = int32.const_zero();
+    let one = int32.const_int(1, false);
+    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) => (
+            s.as_ref().map_or_else(
+                || Ok(int32.const_zero()),
+                |s| handle_slice_index_bound(s, ctx, generator, length),
+            )?,
+            {
+                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 = generator
+                .gen_expr(ctx, step)?
+                .unwrap()
+                .to_basic_value_enum(ctx, generator, ctx.primitives.int32)?
+                .into_int_value();
+            // 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",
+            );
+            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");
+            let neg = ctx.builder.build_int_compare(IntPredicate::SLT, step, zero, "step_is_neg");
+            (
+                match s {
+                    Some(s) => {
+                        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",
+                                    ),
+                                    neg,
+                                    "should_minus_one",
+                                ),
+                                ctx.builder.build_int_sub(s, one, "s_min"),
+                                s,
+                                "final_start",
+                            )
+                            .into_int_value()
+                    }
+                    None => ctx.builder.build_select(neg, len_id, zero, "stt").into_int_value(),
+                },
+                match e {
+                    Some(e) => {
+                        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"),
+                                ctx.builder.build_int_sub(e, one, "end_sub_one"),
+                                "final_end",
+                            )
+                            .into_int_value()
+                    }
+                    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<'a, 'ctx, G: CodeGenerator>(
+    i: &Expr<Option<Type>>,
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    generator: &mut G,
+    length: IntValue<'ctx>,
+) -> 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();
+        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into()], false);
+        ctx.module.add_function(SYMBOL, fn_t, None)
+    });
+
+    let i = generator.gen_expr(ctx, i)?.unwrap().to_basic_value_enum(ctx, generator, i.custom.unwrap())?;
+    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').
+/// Negative index should be handled before entering this function
+pub fn list_slice_assignment<'ctx, 'a>(
+    generator: &mut dyn CodeGenerator,
+    ctx: &mut CodeGenContext<'ctx, 'a>,
+    ty: BasicTypeEnum<'ctx>,
+    dest_arr: PointerValue<'ctx>,
+    dest_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'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::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 = {
+        let ty_vec = vec![
+            int32.into(),         // dest start idx
+            int32.into(),         // dest end idx
+            int32.into(),         // dest step
+            elem_ptr_type.into(), // dest arr ptr
+            int32.into(),         // dest arr len
+            int32.into(),         // src start idx
+            int32.into(),         // src end idx
+            int32.into(),         // src step
+            elem_ptr_type.into(), // src arr ptr
+            int32.into(),         // src arr len
+            int32.into(),         // size
+        ];
+        ctx.module.get_function(fun_symbol).unwrap_or_else(|| {
+            let fn_t = int32.fn_type(ty_vec.as_slice(), false);
+            ctx.module.add_function(fun_symbol, fn_t, None)
+        })
+    };
+
+    let zero = int32.const_zero();
+    let one = int32.const_int(1, false);
+    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
+    // throw exception if not satisfied
+    let src_end = ctx.builder
+        .build_select(
+            ctx.builder.build_int_compare(
+                inkwell::IntPredicate::SLT,
+                src_idx.2,
+                zero,
+                "is_neg",
+            ),
+            ctx.builder.build_int_sub(src_idx.1, one, "e_min_one"),
+            ctx.builder.build_int_add(src_idx.1, one, "e_add_one"),
+            "final_e",
+        )
+        .into_int_value();
+    let dest_end = ctx.builder
+        .build_select(
+            ctx.builder.build_int_compare(
+                inkwell::IntPredicate::SLT,
+                dest_idx.2,
+                zero,
+                "is_neg",
+            ),
+            ctx.builder.build_int_sub(dest_idx.1, one, "e_min_one"),
+            ctx.builder.build_int_add(dest_idx.1, one, "e_add_one"),
+            "final_e",
+        )
+        .into_int_value();
+    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",
+    );
+    let src_slt_dest = ctx.builder.build_int_compare(
+        IntPredicate::SLT,
+        src_slice_len,
+        dest_slice_len,
+        "slice_src_slt_dest",
+    );
+    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",
+    );
+    let cond_1 = ctx.builder.build_and(dest_step_eq_one, src_slt_dest, "slice_cond_1");
+    let cond = ctx.builder.build_or(src_eq_dest, cond_1, "slice_cond");
+    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
+            dest_idx.1.into(),   // dest end idx
+            dest_idx.2.into(),   // dest step
+            dest_arr_ptr.into(), // dest arr ptr
+            dest_len.into(),     // dest arr len
+            src_idx.0.into(),    // src start idx
+            src_idx.1.into(),    // src end idx
+            src_idx.2.into(),    // src step
+            src_arr_ptr.into(),  // src arr ptr
+            src_len.into(),      // src arr len
+            {
+                let s = match ty {
+                    BasicTypeEnum::FloatType(t) => t.size_of(),
+                    BasicTypeEnum::IntType(t) => t.size_of(),
+                    BasicTypeEnum::PointerType(t) => t.size_of(),
+                    BasicTypeEnum::StructType(t) => t.size_of().unwrap(),
+                    _ => unreachable!(),
+                };
+                ctx.builder.build_int_truncate_or_bit_cast(s, int32, "size")
+            }
+            .into(),
+        ];
+        ctx.builder
+            .build_call(slice_assign_fun, args.as_slice(), "slice_assign")
+            .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");
+    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);
+    ctx.builder.position_at_end(update_bb);
+    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);
+}

nac3core/src/codegen/mod.rs

@@ -0,0 +1,608 @@
+use crate::{
+    symbol_resolver::{StaticValue, SymbolResolver},
+    toplevel::{TopLevelContext, TopLevelDef},
+    typecheck::{
+        type_inferencer::{CodeLocation, PrimitiveStore},
+        typedef::{CallId, FuncArg, Type, TypeEnum, Unifier},
+    },
+};
+use crossbeam::channel::{unbounded, Receiver, Sender};
+use inkwell::{
+    AddressSpace,
+    OptimizationLevel,
+    attributes::{Attribute, AttributeLoc},
+    basic_block::BasicBlock,
+    builder::Builder,
+    context::Context,
+    module::Module,
+    passes::{PassManager, PassManagerBuilder},
+    types::{AnyType, BasicType, BasicTypeEnum},
+    values::{BasicValueEnum, FunctionValue, PhiValue, PointerValue}
+};
+use itertools::Itertools;
+use nac3parser::ast::{Stmt, StrRef, Location};
+use parking_lot::{Condvar, Mutex};
+use std::collections::{HashMap, HashSet};
+use std::sync::{
+    atomic::{AtomicBool, Ordering},
+    Arc,
+};
+use std::thread;
+
+pub mod concrete_type;
+pub mod expr;
+mod generator;
+pub mod irrt;
+pub mod stmt;
+
+#[cfg(test)]
+mod test;
+
+use concrete_type::{ConcreteType, ConcreteTypeEnum, ConcreteTypeStore};
+pub use generator::{CodeGenerator, DefaultCodeGenerator};
+
+#[derive(Default)]
+pub struct StaticValueStore {
+    pub lookup: HashMap<Vec<(usize, u64)>, usize>,
+    pub store: Vec<HashMap<usize, Arc<dyn StaticValue + Send + Sync>>>,
+}
+
+pub type VarValue<'ctx> = (PointerValue<'ctx>, Option<Arc<dyn StaticValue + Send + Sync>>, i64);
+
+pub struct CodeGenContext<'ctx, 'a> {
+    pub ctx: &'ctx Context,
+    pub builder: Builder<'ctx>,
+    pub module: Module<'ctx>,
+    pub top_level: &'a TopLevelContext,
+    pub unifier: Unifier,
+    pub resolver: Arc<dyn SymbolResolver + Send + Sync>,
+    pub static_value_store: Arc<Mutex<StaticValueStore>>,
+    pub var_assignment: HashMap<StrRef, VarValue<'ctx>>,
+    pub type_cache: HashMap<Type, BasicTypeEnum<'ctx>>,
+    pub primitives: PrimitiveStore,
+    pub calls: Arc<HashMap<CodeLocation, CallId>>,
+    pub registry: &'a WorkerRegistry,
+    // const string cache
+    pub const_strings: HashMap<String, BasicValueEnum<'ctx>>,
+    // stores the alloca for variables
+    pub init_bb: BasicBlock<'ctx>,
+    // the first one is the test_bb, and the second one is bb after the loop
+    pub loop_target: Option<(BasicBlock<'ctx>, BasicBlock<'ctx>)>,
+    // unwind target bb
+    pub unwind_target: Option<BasicBlock<'ctx>>,
+    // return target bb, just emit ret if no such target
+    pub return_target: Option<BasicBlock<'ctx>>,
+    pub return_buffer: Option<PointerValue<'ctx>>,
+    // outer catch clauses
+    pub outer_catch_clauses:
+        Option<(Vec<Option<BasicValueEnum<'ctx>>>, BasicBlock<'ctx>, PhiValue<'ctx>)>,
+    pub need_sret: bool,
+    pub current_loc: Location,
+}
+
+impl<'ctx, 'a> CodeGenContext<'ctx, 'a> {
+    pub fn is_terminated(&self) -> bool {
+        self.builder.get_insert_block().unwrap().get_terminator().is_some()
+    }
+}
+
+type Fp = Box<dyn Fn(&Module) + Send + Sync>;
+
+pub struct WithCall {
+    fp: Fp,
+}
+
+impl WithCall {
+    pub fn new(fp: Fp) -> WithCall {
+        WithCall { fp }
+    }
+
+    pub fn run<'ctx>(&self, m: &Module<'ctx>) {
+        (self.fp)(m)
+    }
+}
+
+pub struct WorkerRegistry {
+    sender: Arc<Sender<Option<CodeGenTask>>>,
+    receiver: Arc<Receiver<Option<CodeGenTask>>>,
+    panicked: AtomicBool,
+    task_count: Mutex<usize>,
+    thread_count: usize,
+    wait_condvar: Condvar,
+    top_level_ctx: Arc<TopLevelContext>,
+    static_value_store: Arc<Mutex<StaticValueStore>>,
+}
+
+impl WorkerRegistry {
+    pub fn create_workers<G: CodeGenerator + Send + 'static>(
+        generators: Vec<Box<G>>,
+        top_level_ctx: Arc<TopLevelContext>,
+        f: Arc<WithCall>,
+    ) -> (Arc<WorkerRegistry>, Vec<thread::JoinHandle<()>>) {
+        let (sender, receiver) = unbounded();
+        let task_count = Mutex::new(0);
+        let wait_condvar = Condvar::new();
+
+        // init: 0 to be empty
+        let mut static_value_store: StaticValueStore = Default::default();
+        static_value_store.lookup.insert(Default::default(), 0);
+        static_value_store.store.push(Default::default());
+
+        let registry = Arc::new(WorkerRegistry {
+            sender: Arc::new(sender),
+            receiver: Arc::new(receiver),
+            thread_count: generators.len(),
+            panicked: AtomicBool::new(false),
+            static_value_store: Arc::new(Mutex::new(static_value_store)),
+            task_count,
+            wait_condvar,
+            top_level_ctx,
+        });
+
+        let mut handles = Vec::new();
+        for mut generator in generators.into_iter() {
+            let registry = registry.clone();
+            let registry2 = registry.clone();
+            let f = f.clone();
+            let handle = thread::spawn(move || {
+                registry.worker_thread(generator.as_mut(), f);
+            });
+            let handle = thread::spawn(move || {
+                if let Err(e) = handle.join() {
+                    if let Some(e) = e.downcast_ref::<&'static str>() {
+                        eprintln!("Got an error: {}", e);
+                    } else {
+                        eprintln!("Got an unknown error: {:?}", e);
+                    }
+                    registry2.panicked.store(true, Ordering::SeqCst);
+                    registry2.wait_condvar.notify_all();
+                }
+            });
+            handles.push(handle);
+        }
+        (registry, handles)
+    }
+
+    pub fn wait_tasks_complete(&self, handles: Vec<thread::JoinHandle<()>>) {
+        {
+            let mut count = self.task_count.lock();
+            while *count != 0 {
+                if self.panicked.load(Ordering::SeqCst) {
+                    break;
+                }
+                self.wait_condvar.wait(&mut count);
+            }
+        }
+        for _ in 0..self.thread_count {
+            self.sender.send(None).unwrap();
+        }
+        {
+            let mut count = self.task_count.lock();
+            while *count != self.thread_count {
+                if self.panicked.load(Ordering::SeqCst) {
+                    break;
+                }
+                self.wait_condvar.wait(&mut count);
+            }
+        }
+        for handle in handles {
+            handle.join().unwrap();
+        }
+        if self.panicked.load(Ordering::SeqCst) {
+            panic!("tasks panicked");
+        }
+    }
+
+    pub fn add_task(&self, task: CodeGenTask) {
+        *self.task_count.lock() += 1;
+        self.sender.send(Some(task)).unwrap();
+    }
+
+    fn worker_thread<G: CodeGenerator>(&self, generator: &mut G, f: Arc<WithCall>) {
+        let context = Context::create();
+        let mut builder = context.create_builder();
+        let module = context.create_module(generator.get_name());
+
+        let pass_builder = PassManagerBuilder::create();
+        pass_builder.set_optimization_level(OptimizationLevel::Default);
+        let passes = PassManager::create(&module);
+        pass_builder.populate_function_pass_manager(&passes);
+
+        let mut errors = HashSet::new();
+        while let Some(task) = self.receiver.recv().unwrap() {
+            let tmp_module = context.create_module("tmp");
+            match gen_func(&context, generator, self, builder, tmp_module, task) {
+                Ok(result) => {
+                    builder = result.0;
+                    passes.run_on(&result.2);
+                    module.link_in_module(result.1).unwrap();
+                }
+                Err((old_builder, e)) => {
+                    builder = old_builder;
+                    errors.insert(e);
+                }
+            }
+            *self.task_count.lock() -= 1;
+            self.wait_condvar.notify_all();
+        }
+        if !errors.is_empty() {
+            panic!("Codegen error: {}", errors.into_iter().sorted().join("\n----------\n"));
+        }
+
+        let result = module.verify();
+        if let Err(err) = result {
+            println!("{}", module.print_to_string().to_str().unwrap());
+            println!("{}", err);
+            panic!()
+        }
+        f.run(&module);
+        let mut lock = self.task_count.lock();
+        *lock += 1;
+        self.wait_condvar.notify_all();
+    }
+}
+
+pub struct CodeGenTask {
+    pub subst: Vec<(Type, ConcreteType)>,
+    pub store: ConcreteTypeStore,
+    pub symbol_name: String,
+    pub signature: ConcreteType,
+    pub body: Arc<Vec<Stmt<Option<Type>>>>,
+    pub calls: Arc<HashMap<CodeLocation, CallId>>,
+    pub unifier_index: usize,
+    pub resolver: Arc<dyn SymbolResolver + Send + Sync>,
+    pub id: usize,
+}
+
+fn get_llvm_type<'ctx>(
+    ctx: &'ctx Context,
+    generator: &mut dyn CodeGenerator,
+    unifier: &mut Unifier,
+    top_level: &TopLevelContext,
+    type_cache: &mut HashMap<Type, BasicTypeEnum<'ctx>>,
+    primitives: &PrimitiveStore,
+    ty: Type,
+) -> BasicTypeEnum<'ctx> {
+    use TypeEnum::*;
+    // we assume the type cache should already contain primitive types,
+    // and they should be passed by value instead of passing as pointer.
+    type_cache.get(&unifier.get_representative(ty)).cloned().unwrap_or_else(|| {
+        let ty_enum = unifier.get_ty(ty);
+        let result = match &*ty_enum {
+            TObj { obj_id, fields, .. } => {
+                // check to avoid treating primitives other than Option as classes
+                if obj_id.0 <= 10 {
+                    match (unifier.get_ty(ty).as_ref(), unifier.get_ty(primitives.option).as_ref())
+                    {
+                        (
+                            TypeEnum::TObj { obj_id, params, .. },
+                            TypeEnum::TObj { obj_id: opt_id, .. },
+                        ) if *obj_id == *opt_id => {
+                            return get_llvm_type(
+                                ctx,
+                                generator,
+                                unifier,
+                                top_level,
+                                type_cache,
+                                primitives,
+                                *params.iter().next().unwrap().1,
+                            )
+                            .ptr_type(AddressSpace::Generic)
+                            .into();
+                        }
+                        _ => unreachable!("must be option type"),
+                    }
+                }
+                // a struct with fields in the order of declaration
+                let top_level_defs = top_level.definitions.read();
+                let definition = top_level_defs.get(obj_id.0).unwrap();
+                let ty = if let TopLevelDef::Class { name, fields: fields_list, .. } =
+                    &*definition.read()
+                {
+                    let struct_type = ctx.opaque_struct_type(&name.to_string());
+                    type_cache.insert(unifier.get_representative(ty), struct_type.ptr_type(AddressSpace::Generic).into());
+                    let fields = fields_list
+                        .iter()
+                        .map(|f| {
+                            get_llvm_type(
+                                ctx,
+                                generator,
+                                unifier,
+                                top_level,
+                                type_cache,
+                                primitives,
+                                fields[&f.0].0,
+                            )
+                        })
+                        .collect_vec();
+                    struct_type.set_body(&fields, false);
+                    struct_type.ptr_type(AddressSpace::Generic).into()
+                } else {
+                    unreachable!()
+                };
+                return ty;
+            }
+            TTuple { ty } => {
+                // a struct with fields in the order present in the tuple
+                let fields = ty
+                    .iter()
+                    .map(|ty| get_llvm_type(ctx, generator, unifier, top_level, type_cache, primitives, *ty))
+                    .collect_vec();
+                ctx.struct_type(&fields, false).into()
+            }
+            TList { ty } => {
+                // a struct with an integer and a pointer to an array
+                let element_type =
+                    get_llvm_type(ctx, generator, unifier, top_level, type_cache, primitives, *ty);
+                let fields = [
+                    element_type.ptr_type(AddressSpace::Generic).into(),
+                    generator.get_size_type(ctx).into(),
+                ];
+                ctx.struct_type(&fields, false).ptr_type(AddressSpace::Generic).into()
+            }
+            TVirtual { .. } => unimplemented!(),
+            _ => unreachable!("{}", ty_enum.get_type_name()),
+        };
+        type_cache.insert(unifier.get_representative(ty), result);
+        result
+    })
+}
+
+fn need_sret<'ctx>(ctx: &'ctx Context, ty: BasicTypeEnum<'ctx>) -> bool {
+    fn need_sret_impl<'ctx>(ctx: &'ctx Context, ty: BasicTypeEnum<'ctx>, maybe_large: bool) -> bool {
+        match ty {
+            BasicTypeEnum::IntType(_) | BasicTypeEnum::PointerType(_) => false,
+            BasicTypeEnum::FloatType(_) if maybe_large => false,
+            BasicTypeEnum::StructType(ty) if maybe_large && ty.count_fields() <= 2 =>
+                ty.get_field_types().iter().any(|ty| need_sret_impl(ctx, *ty, false)),
+            _ => true,
+        }
+    }
+    need_sret_impl(ctx, ty, true)
+}
+
+pub fn gen_func_impl<'ctx, G: CodeGenerator, F: FnOnce(&mut G, &mut CodeGenContext) -> Result<(), String>> (
+    context: &'ctx Context,
+    generator: &mut G,
+    registry: &WorkerRegistry,
+    builder: Builder<'ctx>,
+    module: Module<'ctx>,
+    task: CodeGenTask,
+    codegen_function: F
+) -> Result<(Builder<'ctx>, Module<'ctx>, FunctionValue<'ctx>), (Builder<'ctx>, String)> {
+    let top_level_ctx = registry.top_level_ctx.clone();
+    let static_value_store = registry.static_value_store.clone();
+    let (mut unifier, primitives) = {
+        let (unifier, primitives) = &top_level_ctx.unifiers.read()[task.unifier_index];
+        (Unifier::from_shared_unifier(unifier), *primitives)
+    };
+    unifier.top_level = Some(top_level_ctx.clone());
+
+    let mut cache = HashMap::new();
+    for (a, b) in task.subst.iter() {
+        // this should be unification between variables and concrete types
+        // and should not cause any problem...
+        let b = task.store.to_unifier_type(&mut unifier, &primitives, *b, &mut cache);
+        unifier
+            .unify(*a, b)
+            .or_else(|err| {
+                if matches!(&*unifier.get_ty(*a), TypeEnum::TRigidVar { .. }) {
+                    unifier.replace_rigid_var(*a, b);
+                    Ok(())
+                } else {
+                    Err(err)
+                }
+            })
+            .unwrap()
+    }
+
+    // rebuild primitive store with unique representatives
+    let primitives = PrimitiveStore {
+        int32: unifier.get_representative(primitives.int32),
+        int64: unifier.get_representative(primitives.int64),
+        uint32: unifier.get_representative(primitives.uint32),
+        uint64: unifier.get_representative(primitives.uint64),
+        float: unifier.get_representative(primitives.float),
+        bool: unifier.get_representative(primitives.bool),
+        none: unifier.get_representative(primitives.none),
+        range: unifier.get_representative(primitives.range),
+        str: unifier.get_representative(primitives.str),
+        exception: unifier.get_representative(primitives.exception),
+        option: unifier.get_representative(primitives.option),
+    };
+
+    let mut type_cache: HashMap<_, _> = [
+        (primitives.int32, context.i32_type().into()),
+        (primitives.int64, context.i64_type().into()),
+        (primitives.uint32, context.i32_type().into()),
+        (primitives.uint64, context.i64_type().into()),
+        (primitives.float, context.f64_type().into()),
+        (primitives.bool, context.bool_type().into()),
+        (primitives.str, {
+            let str_type = context.opaque_struct_type("str");
+            let fields = [
+                context.i8_type().ptr_type(AddressSpace::Generic).into(),
+                generator.get_size_type(context).into(),
+            ];
+            str_type.set_body(&fields, false);
+            str_type.into()
+        }),
+        (primitives.range, context.i32_type().array_type(3).ptr_type(AddressSpace::Generic).into()),
+    ]
+    .iter()
+    .cloned()
+    .collect();
+    type_cache.insert(primitives.exception, {
+        let exception = context.opaque_struct_type("Exception");
+        let int32 = context.i32_type().into();
+        let int64 = context.i64_type().into();
+        let str_ty = *type_cache.get(&primitives.str).unwrap();
+        let fields = [int32, str_ty, int32, int32, str_ty, str_ty, int64, int64, int64];
+        exception.set_body(&fields, false);
+        exception.ptr_type(AddressSpace::Generic).into()
+    });
+    // NOTE: special handling of option cannot use this type cache since it contains type var,
+    // handled inside get_llvm_type instead
+
+    let (args, ret) = if let ConcreteTypeEnum::TFunc { args, ret, .. } =
+        task.store.get(task.signature)
+    {
+        (
+            args.iter()
+                .map(|arg| FuncArg {
+                    name: arg.name,
+                    ty: task.store.to_unifier_type(&mut unifier, &primitives, arg.ty, &mut cache),
+                    default_value: arg.default_value.clone(),
+                })
+                .collect_vec(),
+            task.store.to_unifier_type(&mut unifier, &primitives, *ret, &mut cache),
+        )
+    } else {
+        unreachable!()
+    };
+    let ret_type = if unifier.unioned(ret, primitives.none) {
+        None
+    } else {
+        Some(get_llvm_type(context, generator, &mut unifier, top_level_ctx.as_ref(), &mut type_cache, &primitives, ret))
+    };
+
+    let has_sret = ret_type.map_or(false, |ty| need_sret(context, ty));
+    let mut params = args
+        .iter()
+        .map(|arg| {
+            get_llvm_type(
+                context,
+                generator,
+                &mut unifier,
+                top_level_ctx.as_ref(),
+                &mut type_cache,
+                &primitives,
+                arg.ty,
+            )
+            .into()
+        })
+        .collect_vec();
+
+    if has_sret {
+        params.insert(0, ret_type.unwrap().ptr_type(AddressSpace::Generic).into());
+    }
+
+    let fn_type = match ret_type {
+        Some(ret_type) if !has_sret => ret_type.fn_type(&params, false),
+        _ => context.void_type().fn_type(&params, false)
+    };
+
+    let symbol = &task.symbol_name;
+    let fn_val =
+        module.get_function(symbol).unwrap_or_else(|| module.add_function(symbol, fn_type, None));
+
+    if let Some(personality) = &top_level_ctx.personality_symbol {
+        let personality = module.get_function(personality).unwrap_or_else(|| {
+            let ty = context.i32_type().fn_type(&[], true);
+            module.add_function(personality, ty, None)
+        });
+        fn_val.set_personality_function(personality);
+    }
+    if has_sret {
+        fn_val.add_attribute(AttributeLoc::Param(0),
+            context.create_type_attribute(Attribute::get_named_enum_kind_id("sret"),
+            ret_type.unwrap().as_any_type_enum()));
+    }
+
+    let init_bb = context.append_basic_block(fn_val, "init");
+    builder.position_at_end(init_bb);
+    let body_bb = context.append_basic_block(fn_val, "body");
+
+    let mut var_assignment = HashMap::new();
+    let offset = if has_sret { 1 } else { 0 };
+    for (n, arg) in args.iter().enumerate() {
+        let param = fn_val.get_nth_param((n as u32) + offset).unwrap();
+        let alloca = builder.build_alloca(
+            get_llvm_type(
+                context,
+                generator,
+                &mut unifier,
+                top_level_ctx.as_ref(),
+                &mut type_cache,
+                &primitives,
+                arg.ty,
+            ),
+            &arg.name.to_string(),
+        );
+        builder.build_store(alloca, param);
+        var_assignment.insert(arg.name, (alloca, None, 0));
+    }
+
+    let return_buffer = if has_sret {
+        Some(fn_val.get_nth_param(0).unwrap().into_pointer_value())
+    } else {
+        fn_type.get_return_type().map(|v| builder.build_alloca(v, "$ret"))
+    };
+
+    let static_values = {
+        let store = registry.static_value_store.lock();
+        store.store[task.id].clone()
+    };
+    for (k, v) in static_values.into_iter() {
+        let (_, static_val, _) = var_assignment.get_mut(&args[k].name).unwrap();
+        *static_val = Some(v);
+    }
+
+    builder.build_unconditional_branch(body_bb);
+    builder.position_at_end(body_bb);
+
+    let mut code_gen_context = CodeGenContext {
+        ctx: context,
+        resolver: task.resolver,
+        top_level: top_level_ctx.as_ref(),
+        calls: task.calls,
+        loop_target: None,
+        return_target: None,
+        return_buffer,
+        unwind_target: None,
+        outer_catch_clauses: None,
+        const_strings: Default::default(),
+        registry,
+        var_assignment,
+        type_cache,
+        primitives,
+        init_bb,
+        builder,
+        module,
+        unifier,
+        static_value_store,
+        need_sret: has_sret,
+        current_loc: Default::default(),
+    };
+
+    let result = codegen_function(generator, &mut code_gen_context);
+
+    // after static analysis, only void functions can have no return at the end.
+    if !code_gen_context.is_terminated() {
+        code_gen_context.builder.build_return(None);
+    }
+
+    let CodeGenContext { builder, module, .. } = code_gen_context;
+    if let Err(e) = result {
+        return Err((builder, e));
+    }
+
+    Ok((builder, module, fn_val))
+}
+
+pub fn gen_func<'ctx, G: CodeGenerator>(
+    context: &'ctx Context,
+    generator: &mut G,
+    registry: &WorkerRegistry,
+    builder: Builder<'ctx>,
+    module: Module<'ctx>,
+    task: CodeGenTask,
+) -> Result<(Builder<'ctx>, Module<'ctx>, FunctionValue<'ctx>), (Builder<'ctx>, String)> {
+    let body = task.body.clone();
+    gen_func_impl(context, generator, registry, builder, module, task, |generator, ctx| {
+        for stmt in body.iter() {
+            generator.gen_stmt(ctx, stmt)?;
+        }
+        Ok(())
+    })
+}

nac3core/src/codegen/test.rs

@@ -0,0 +1,364 @@
+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 indoc::indoc;
+use nac3parser::{
+    ast::{fold::Fold, StrRef},
+    parser::parse_program,
+};
+use parking_lot::RwLock;
+use std::collections::{HashMap, HashSet};
+use std::sync::Arc;
+
+struct Resolver {
+    id_to_type: HashMap<StrRef, Type>,
+    id_to_def: RwLock<HashMap<StrRef, DefinitionId>>,
+    class_names: HashMap<StrRef, Type>,
+}
+
+impl Resolver {
+    pub fn add_id_def(&self, id: StrRef, def: DefinitionId) {
+        self.id_to_def.write().insert(id, def);
+    }
+}
+
+impl SymbolResolver for Resolver {
+    fn get_default_param_value(
+        &self,
+        _: &nac3parser::ast::Expr,
+    ) -> Option<crate::symbol_resolver::SymbolValue> {
+        unimplemented!()
+    }
+
+    fn get_symbol_type(
+        &self,
+        _: &mut Unifier,
+        _: &[Arc<RwLock<TopLevelDef>>],
+        _: &PrimitiveStore,
+        str: StrRef,
+    ) -> Result<Type, String> {
+        self.id_to_type.get(&str).cloned().ok_or_else(|| format!("cannot find symbol `{}`", str))
+    }
+
+    fn get_symbol_value<'ctx, 'a>(
+        &self,
+        _: StrRef,
+        _: &mut CodeGenContext<'ctx, 'a>,
+    ) -> Option<ValueEnum<'ctx>> {
+        unimplemented!()
+    }
+
+    fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
+        self.id_to_def
+            .read()
+            .get(&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 {
+        unimplemented!()
+    }
+}
+
+#[test]
+fn test_primitives() {
+    let source = indoc! { "
+        c = a + b
+        d = a if c == 1 else 0
+        return d
+        "};
+    let statements = parse_program(source, Default::default()).unwrap();
+
+    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 resolver = Arc::new(Resolver {
+        id_to_type: HashMap::new(),
+        id_to_def: RwLock::new(HashMap::new()),
+        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 },
+            FuncArg { name: "b".into(), ty: primitives.int32, default_value: None },
+        ],
+        ret: primitives.int32,
+        vars: HashMap::new(),
+    };
+
+    let mut store = ConcreteTypeStore::new();
+    let mut cache = HashMap::new();
+    let signature = store.from_signature(&mut unifier, &primitives, &signature, &mut cache);
+    let signature = store.add_cty(signature);
+
+    let mut function_data = FunctionData {
+        resolver: resolver.clone(),
+        bound_variables: Vec::new(),
+        return_type: Some(primitives.int32),
+    };
+    let mut virtual_checks = Vec::new();
+    let mut calls = HashMap::new();
+    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: Default::default(),
+        primitives: &primitives,
+        virtual_checks: &mut virtual_checks,
+        calls: &mut calls,
+        defined_identifiers: identifiers.clone(),
+        in_handler: false,
+    };
+    inferencer.variable_mapping.insert("a".into(), inferencer.primitives.int32);
+    inferencer.variable_mapping.insert("b".into(), inferencer.primitives.int32);
+
+    let statements = statements
+        .into_iter()
+        .map(|v| inferencer.fold_stmt(v))
+        .collect::<Result<Vec<_>, _>>()
+        .unwrap();
+
+    inferencer.check_block(&statements, &mut identifiers).unwrap();
+    let top_level = Arc::new(TopLevelContext {
+        definitions: Arc::new(RwLock::new(std::mem::take(&mut *top_level.definitions.write()))),
+        unifiers: Arc::new(RwLock::new(vec![(unifier.get_shared_unifier(), primitives)])),
+        personality_symbol: None,
+    });
+
+    let task = CodeGenTask {
+        subst: Default::default(),
+        symbol_name: "testing".into(),
+        body: Arc::new(statements),
+        unifier_index: 0,
+        calls: Arc::new(calls),
+        resolver,
+        store,
+        signature,
+        id: 0,
+    };
+    let f = Arc::new(WithCall::new(Box::new(|module| {
+        // the following IR is equivalent to
+        // ```
+        // ; ModuleID = 'test.ll'
+        // source_filename = "test"
+        //
+        // ; Function Attrs: norecurse nounwind readnone
+        // define i32 @testing(i32 %0, i32 %1) local_unnamed_addr #0 {
+        // init:
+        //   %add = add i32 %1, %0
+        //   %cmp = icmp eq i32 %add, 1
+        //   %ifexpr = select i1 %cmp, i32 %0, i32 0
+        //   ret i32 %ifexpr
+        // }
+        //
+        // attributes #0 = { norecurse nounwind readnone }
+        // ```
+        // after O2 optimization
+
+        let expected = indoc! {"
+            ; ModuleID = 'test'
+            source_filename = \"test\"
+            
+            define i32 @testing(i32 %0, i32 %1) {
+            init:
+              %add = add i32 %0, %1
+              %cmp = icmp eq i32 %add, 1
+              br i1 %cmp, label %then, label %else
+            
+            then:                                             ; preds = %init
+              br label %cont
+            
+            else:                                             ; preds = %init
+              br label %cont
+            
+            cont:                                             ; preds = %else, %then
+              %if_exp_result.0 = phi i32 [ %0, %then ], [ 0, %else ]
+              ret i32 %if_exp_result.0
+            }
+       "}
+        .trim();
+        assert_eq!(expected, module.print_to_string().to_str().unwrap().trim());
+    })));
+    let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, f);
+    registry.add_task(task);
+    registry.wait_tasks_complete(handles);
+}
+
+#[test]
+fn test_simple_call() {
+    let source_1 = indoc! { "
+        a = foo(a)
+        return a * 2
+        "};
+    let statements_1 = parse_program(source_1, Default::default()).unwrap();
+
+    let source_2 = indoc! { "
+        return a + 1
+        "};
+    let statements_2 = parse_program(source_2, Default::default()).unwrap();
+
+    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 }],
+        ret: primitives.int32,
+        vars: HashMap::new(),
+    };
+    let fun_ty = unifier.add_ty(TypeEnum::TFunc(signature.clone()));
+    let mut store = ConcreteTypeStore::new();
+    let mut cache = HashMap::new();
+    let signature = store.from_signature(&mut unifier, &primitives, &signature, &mut cache);
+    let signature = store.add_cty(signature);
+
+    let foo_id = top_level.definitions.read().len();
+    top_level.definitions.write().push(Arc::new(RwLock::new(TopLevelDef::Function {
+        name: "foo".to_string(),
+        simple_name: "foo".into(),
+        signature: fun_ty,
+        var_id: vec![],
+        instance_to_stmt: HashMap::new(),
+        instance_to_symbol: HashMap::new(),
+        resolver: None,
+        codegen_callback: None,
+        loc: None,
+    })));
+
+    let resolver = Resolver {
+        id_to_type: HashMap::new(),
+        id_to_def: RwLock::new(HashMap::new()),
+        class_names: Default::default(),
+    };
+    resolver.add_id_def("foo".into(), DefinitionId(foo_id));
+    let resolver = Arc::new(resolver) as Arc<dyn SymbolResolver + Send + Sync>;
+
+    if let TopLevelDef::Function { resolver: r, .. } =
+        &mut *top_level.definitions.read()[foo_id].write()
+    {
+        *r = Some(resolver.clone());
+    } else {
+        unreachable!()
+    }
+
+    let threads = vec![DefaultCodeGenerator::new("test".into(), 32).into()];
+    let mut function_data = FunctionData {
+        resolver: resolver.clone(),
+        bound_variables: Vec::new(),
+        return_type: Some(primitives.int32),
+    };
+    let mut virtual_checks = Vec::new();
+    let mut calls = HashMap::new();
+    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: Default::default(),
+        primitives: &primitives,
+        virtual_checks: &mut virtual_checks,
+        calls: &mut calls,
+        defined_identifiers: identifiers.clone(),
+        in_handler: false,
+    };
+    inferencer.variable_mapping.insert("a".into(), inferencer.primitives.int32);
+    inferencer.variable_mapping.insert("foo".into(), fun_ty);
+
+    let statements_1 = statements_1
+        .into_iter()
+        .map(|v| inferencer.fold_stmt(v))
+        .collect::<Result<Vec<_>, _>>()
+        .unwrap();
+
+    let calls1 = inferencer.calls.clone();
+    inferencer.calls.clear();
+
+    let statements_2 = statements_2
+        .into_iter()
+        .map(|v| inferencer.fold_stmt(v))
+        .collect::<Result<Vec<_>, _>>()
+        .unwrap();
+
+    if let TopLevelDef::Function { instance_to_stmt, .. } =
+        &mut *top_level.definitions.read()[foo_id].write()
+    {
+        instance_to_stmt.insert(
+            "".to_string(),
+            FunInstance {
+                body: Arc::new(statements_2),
+                calls: Arc::new(inferencer.calls.clone()),
+                subst: Default::default(),
+                unifier_id: 0,
+            },
+        );
+    } else {
+        unreachable!()
+    }
+
+    inferencer.check_block(&statements_1, &mut identifiers).unwrap();
+    let top_level = Arc::new(TopLevelContext {
+        definitions: Arc::new(RwLock::new(std::mem::take(&mut *top_level.definitions.write()))),
+        unifiers: Arc::new(RwLock::new(vec![(unifier.get_shared_unifier(), primitives)])),
+        personality_symbol: None,
+    });
+
+    let task = CodeGenTask {
+        subst: Default::default(),
+        symbol_name: "testing".to_string(),
+        body: Arc::new(statements_1),
+        calls: Arc::new(calls1),
+        unifier_index: 0,
+        resolver,
+        signature,
+        store,
+        id: 0,
+    };
+    let f = Arc::new(WithCall::new(Box::new(|module| {
+        let expected = indoc! {"
+            ; ModuleID = 'test'
+            source_filename = \"test\"
+
+            define i32 @testing(i32 %0) {
+            init:
+              %call = call i32 @foo.0(i32 %0)
+              %mul = mul i32 %call, 2
+              ret i32 %mul
+            }
+
+            define i32 @foo.0(i32 %0) {
+            init:
+              %add = add i32 %0, 1
+              ret i32 %add
+            }
+       "}
+        .trim();
+        assert_eq!(expected, module.print_to_string().to_str().unwrap().trim());
+    })));
+    let (registry, handles) = WorkerRegistry::create_workers(threads, top_level, f);
+    registry.add_task(task);
+    registry.wait_tasks_complete(handles);
+}

nac3core/src/lib.rs

@@ -1,13 +1,7 @@
 #![warn(clippy::all)]
-#![allow(clippy::clone_double_ref)]
-
-#[cfg(test)]
-extern crate test_case;
-
-extern crate num_bigint;
-extern crate inkwell;
-extern crate rustpython_parser;
-extern crate indoc;
-
-mod typecheck;
+#![allow(dead_code)]
 
+pub mod codegen;
+pub mod symbol_resolver;
+pub mod toplevel;
+pub mod typecheck;

nac3core/src/symbol_resolver.rs

@@ -0,0 +1,380 @@
+use std::fmt::Debug;
+use std::sync::Arc;
+use std::{collections::HashMap, fmt::Display};
+
+use crate::typecheck::typedef::TypeEnum;
+use crate::{
+    codegen::CodeGenContext,
+    toplevel::{DefinitionId, TopLevelDef},
+};
+use crate::{
+    codegen::CodeGenerator,
+    typecheck::{
+        type_inferencer::PrimitiveStore,
+        typedef::{Type, Unifier},
+    },
+};
+use inkwell::values::{BasicValueEnum, FloatValue, IntValue, PointerValue, StructValue};
+use itertools::{chain, izip};
+use nac3parser::ast::{Expr, Location, StrRef};
+use parking_lot::RwLock;
+
+#[derive(Clone, PartialEq, Debug)]
+pub enum SymbolValue {
+    I32(i32),
+    I64(i64),
+    U32(u32),
+    U64(u64),
+    Str(String),
+    Double(f64),
+    Bool(bool),
+    Tuple(Vec<SymbolValue>),
+    OptionSome(Box<SymbolValue>),
+    OptionNone,
+}
+
+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::Bool(b) => {
+                if *b {
+                    write!(f, "True")
+                } else {
+                    write!(f, "False")
+                }
+            }
+            SymbolValue::Tuple(t) => {
+                write!(f, "({})", t.iter().map(|v| format!("{}", v)).collect::<Vec<_>>().join(", "))
+            }
+            SymbolValue::OptionSome(v) => write!(f, "Some({})", v),
+            SymbolValue::OptionNone => write!(f, "none"),
+        }
+    }
+}
+
+pub trait StaticValue {
+    fn get_unique_identifier(&self) -> u64;
+
+    fn get_const_obj<'ctx, 'a>(
+        &self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        generator: &mut dyn CodeGenerator,
+    ) -> BasicValueEnum<'ctx>;
+
+    fn to_basic_value_enum<'ctx, 'a>(
+        &self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        generator: &mut dyn CodeGenerator,
+        expected_ty: Type,
+    ) -> Result<BasicValueEnum<'ctx>, String>;
+
+    fn get_field<'ctx, 'a>(
+        &self,
+        name: StrRef,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+    ) -> Option<ValueEnum<'ctx>>;
+
+    fn get_tuple_element<'ctx>(&self, index: u32) -> Option<ValueEnum<'ctx>>;
+}
+
+#[derive(Clone)]
+pub enum ValueEnum<'ctx> {
+    Static(Arc<dyn StaticValue + Send + Sync>),
+    Dynamic(BasicValueEnum<'ctx>),
+}
+
+impl<'ctx> From<BasicValueEnum<'ctx>> for ValueEnum<'ctx> {
+    fn from(v: BasicValueEnum<'ctx>) -> Self {
+        ValueEnum::Dynamic(v)
+    }
+}
+
+impl<'ctx> From<PointerValue<'ctx>> for ValueEnum<'ctx> {
+    fn from(v: PointerValue<'ctx>) -> Self {
+        ValueEnum::Dynamic(v.into())
+    }
+}
+
+impl<'ctx> From<IntValue<'ctx>> for ValueEnum<'ctx> {
+    fn from(v: IntValue<'ctx>) -> Self {
+        ValueEnum::Dynamic(v.into())
+    }
+}
+
+impl<'ctx> From<FloatValue<'ctx>> for ValueEnum<'ctx> {
+    fn from(v: FloatValue<'ctx>) -> Self {
+        ValueEnum::Dynamic(v.into())
+    }
+}
+
+impl<'ctx> From<StructValue<'ctx>> for ValueEnum<'ctx> {
+    fn from(v: StructValue<'ctx>) -> Self {
+        ValueEnum::Dynamic(v.into())
+    }
+}
+
+impl<'ctx> ValueEnum<'ctx> {
+    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::Dynamic(v) => Ok(v),
+        }
+    }
+}
+
+pub trait SymbolResolver {
+    // get type of type variable identifier or top-level function type
+    fn get_symbol_type(
+        &self,
+        unifier: &mut Unifier,
+        top_level_defs: &[Arc<RwLock<TopLevelDef>>],
+        primitives: &PrimitiveStore,
+        str: StrRef,
+    ) -> Result<Type, String>;
+
+    // get the top-level definition of identifiers
+    fn get_identifier_def(&self, str: StrRef) -> Result<DefinitionId, String>;
+
+    fn get_symbol_value<'ctx, 'a>(
+        &self,
+        str: StrRef,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+    ) -> Option<ValueEnum<'ctx>>;
+
+    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(())
+    }
+}
+
+thread_local! {
+    static IDENTIFIER_ID: [StrRef; 11] = [
+        "int32".into(),
+        "int64".into(),
+        "float".into(),
+        "bool".into(),
+        "virtual".into(),
+        "list".into(),
+        "tuple".into(),
+        "str".into(),
+        "Exception".into(),
+        "uint32".into(),
+        "uint64".into(),
+    ];
+}
+
+// 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, 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 list_id = ids[5];
+    let tuple_id = ids[6];
+    let str_id = ids[7];
+    let exn_id = ids[8];
+    let uint32_id = ids[9];
+    let uint64_id = ids[10];
+
+    let name_handling = |id: &StrRef, loc: Location, unifier: &mut Unifier| {
+        if *id == int32_id {
+            Ok(primitives.int32)
+        } else if *id == int64_id {
+            Ok(primitives.int64)
+        } else if *id == uint32_id {
+            Ok(primitives.uint32)
+        } else if *id == uint64_id {
+            Ok(primitives.uint64)
+        } else if *id == float_id {
+            Ok(primitives.float)
+        } else if *id == bool_id {
+            Ok(primitives.bool)
+        } 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);
+            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))
+                    }
+                }
+                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))
+                    }
+                }
+            }
+        }
+    };
+
+    let subscript_name_handle = |id: &StrRef, slice: &Expr<T>, unifier: &mut Unifier| {
+        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
+                    .iter()
+                    .map(|elt| {
+                        parse_type_annotation(resolver, top_level_defs, unifier, primitives, elt)
+                    })
+                    .collect::<Result<Vec<_>, _>>()?;
+                Ok(unifier.add_ty(TypeEnum::TTuple { ty }))
+            } else {
+                Err("Expected multiple elements for tuple".into())
+            }
+        } else {
+            let types = if let Tuple { elts, .. } = &slice.node {
+                elts.iter()
+                    .map(|v| {
+                        parse_type_annotation(resolver, top_level_defs, unifier, primitives, v)
+                    })
+                    .collect::<Result<Vec<_>, _>>()?
+            } else {
+                vec![parse_type_annotation(resolver, top_level_defs, unifier, primitives, slice)?]
+            };
+
+            let obj_id = resolver.get_identifier_def(*id)?;
+            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(format!(
+                        "Unexpected number of type parameters: expected {} but got {}",
+                        type_vars.len(),
+                        types.len()
+                    ));
+                }
+                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
+                    } else {
+                        unreachable!()
+                    };
+                    subst.insert(id, *ty);
+                }
+                let mut fields = fields
+                    .iter()
+                    .map(|(attr, ty, is_mutable)| {
+                        let ty = unifier.subst(*ty, &subst).unwrap_or(*ty);
+                        (*attr, (ty, *is_mutable))
+                    })
+                    .collect::<HashMap<_, _>>();
+                fields.extend(methods.iter().map(|(attr, ty, _)| {
+                    let ty = unifier.subst(*ty, &subst).unwrap_or(*ty);
+                    (*attr, (ty, false))
+                }));
+                Ok(unifier.add_ty(TypeEnum::TObj { obj_id, fields, params: subst }))
+            } else {
+                Err("Cannot use function name as type".into())
+            }
+        }
+    };
+
+    match &expr.node {
+        Name { id, .. } => name_handling(id, expr.location, unifier),
+        Subscript { value, slice, .. } => {
+            if let Name { id, .. } = &value.node {
+                subscript_name_handle(id, slice, unifier)
+            } else {
+                Err(format!("unsupported type expression at {}", expr.location))
+            }
+        }
+        _ => Err(format!("unsupported type expression at {}", expr.location)),
+    }
+}
+
+impl dyn SymbolResolver + Send + Sync {
+    pub fn parse_type_annotation<T>(
+        &self,
+        top_level_defs: &[Arc<RwLock<TopLevelDef>>],
+        unifier: &mut Unifier,
+        primitives: &PrimitiveStore,
+        expr: &Expr<T>,
+    ) -> Result<Type, String> {
+        parse_type_annotation(self, top_level_defs, unifier, primitives, expr)
+    }
+
+    pub fn get_type_name(
+        &self,
+        top_level_defs: &[Arc<RwLock<TopLevelDef>>],
+        unifier: &mut Unifier,
+        ty: Type,
+    ) -> String {
+        unifier.internal_stringify(
+            ty,
+            &mut |id| {
+                if let TopLevelDef::Class { name, .. } = &*top_level_defs[id].read() {
+                    name.to_string()
+                } else {
+                    unreachable!("expected class definition")
+                }
+            },
+            &mut |id| format!("typevar{}", id),
+            &mut None,
+        )
+    }
+}
+
+impl Debug for dyn SymbolResolver + Send + Sync {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        write!(f, "")
+    }
+}

nac3core/src/toplevel/helper.rs

@@ -0,0 +1,585 @@
+use std::convert::TryInto;
+
+use crate::symbol_resolver::SymbolValue;
+use nac3parser::ast::{Constant, Location};
+
+use super::*;
+
+impl TopLevelDef {
+    pub fn to_string(&self, unifier: &mut Unifier) -> String {
+        match self {
+            TopLevelDef::Class { name, ancestors, fields, methods, type_vars, .. } => {
+                let fields_str = fields
+                    .iter()
+                    .map(|(n, ty, _)| (n.to_string(), unifier.stringify(*ty)))
+                    .collect_vec();
+
+                let methods_str = methods
+                    .iter()
+                    .map(|(n, ty, id)| (n.to_string(), unifier.stringify(*ty), *id))
+                    .collect_vec();
+                format!(
+                    "Class {{\nname: {:?},\nancestors: {:?},\nfields: {:?},\nmethods: {:?},\ntype_vars: {:?}\n}}",
+                    name,
+                    ancestors.iter().map(|ancestor| ancestor.stringify(unifier)).collect_vec(),
+                    fields_str.iter().map(|(a, _)| a).collect_vec(),
+                    methods_str.iter().map(|(a, b, _)| (a, b)).collect_vec(),
+                    type_vars.iter().map(|id| unifier.stringify(*id)).collect_vec(),
+                )
+            }
+            TopLevelDef::Function { name, signature, var_id, .. } => format!(
+                "Function {{\nname: {:?},\nsig: {:?},\nvar_id: {:?}\n}}",
+                name,
+                unifier.stringify(*signature),
+                {
+                    // preserve the order for debug output and test
+                    let mut r = var_id.clone();
+                    r.sort_unstable();
+                    r
+                }
+            ),
+        }
+    }
+}
+
+impl TopLevelComposer {
+    pub fn make_primitives() -> (PrimitiveStore, Unifier) {
+        let mut unifier = Unifier::new();
+        let int32 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(0),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let int64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(1),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let float = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(2),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let bool = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(3),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let none = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(4),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let range = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(5),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let str = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(6),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let exception = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(7),
+            fields: vec![
+                ("__name__".into(), (int32, true)),
+                ("__file__".into(), (int32, true)),
+                ("__line__".into(), (int32, true)),
+                ("__col__".into(), (int32, true)),
+                ("__func__".into(), (str, true)),
+                ("__message__".into(), (str, true)),
+                ("__param0__".into(), (int64, true)),
+                ("__param1__".into(), (int64, true)),
+                ("__param2__".into(), (int64, true)),
+            ]
+            .into_iter()
+            .collect::<HashMap<_, _>>(),
+            params: HashMap::new(),
+        });
+        let uint32 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(8),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let uint64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(9),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+
+        let option_type_var = unifier.get_fresh_var(Some("option_type_var".into()), None);
+        let is_some_type_fun_ty = unifier.add_ty(TypeEnum::TFunc(FunSignature {
+            args: vec![],
+            ret: bool,
+            vars: HashMap::from([(option_type_var.1, option_type_var.0)]),
+        }));
+        let unwrap_fun_ty = unifier.add_ty(TypeEnum::TFunc(FunSignature {
+            args: vec![],
+            ret: option_type_var.0,
+            vars: HashMap::from([(option_type_var.1, option_type_var.0)]),
+        }));
+        let option = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(10),
+            fields: vec![
+                ("is_some".into(), (is_some_type_fun_ty, true)),
+                ("is_none".into(), (is_some_type_fun_ty, true)),
+                ("unwrap".into(), (unwrap_fun_ty, true)),
+            ]
+            .into_iter()
+            .collect::<HashMap<_, _>>(),
+            params: HashMap::from([(option_type_var.1, option_type_var.0)]),
+        });
+
+        let primitives = PrimitiveStore {
+            int32,
+            int64,
+            float,
+            bool,
+            none,
+            range,
+            str,
+            exception,
+            uint32,
+            uint64,
+            option,
+        };
+        crate::typecheck::magic_methods::set_primitives_magic_methods(&primitives, &mut unifier);
+        (primitives, unifier)
+    }
+
+    /// already include the definition_id of itself inside the ancestors vector
+    /// when first registering, the type_vars, fields, methods, ancestors are invalid
+    pub fn make_top_level_class_def(
+        index: usize,
+        resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
+        name: StrRef,
+        constructor: Option<Type>,
+        loc: Option<Location>,
+    ) -> TopLevelDef {
+        TopLevelDef::Class {
+            name,
+            object_id: DefinitionId(index),
+            type_vars: Default::default(),
+            fields: Default::default(),
+            methods: Default::default(),
+            ancestors: Default::default(),
+            constructor,
+            resolver,
+            loc,
+        }
+    }
+
+    /// when first registering, the type is a invalid value
+    pub fn make_top_level_function_def(
+        name: String,
+        simple_name: StrRef,
+        ty: Type,
+        resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
+        loc: Option<Location>,
+    ) -> TopLevelDef {
+        TopLevelDef::Function {
+            name,
+            simple_name,
+            signature: ty,
+            var_id: Default::default(),
+            instance_to_symbol: Default::default(),
+            instance_to_stmt: Default::default(),
+            resolver,
+            codegen_callback: None,
+            loc,
+        }
+    }
+
+    pub fn make_class_method_name(mut class_name: String, method_name: &str) -> String {
+        class_name.push('.');
+        class_name.push_str(method_name);
+        class_name
+    }
+
+    pub fn get_class_method_def_info(
+        class_methods_def: &[(StrRef, Type, DefinitionId)],
+        method_name: StrRef,
+    ) -> Result<(Type, DefinitionId), String> {
+        for (name, ty, def_id) in class_methods_def {
+            if name == &method_name {
+                return Ok((*ty, *def_id));
+            }
+        }
+        Err(format!("no method {} in the current class", method_name))
+    }
+
+    /// get all base class def id of a class, excluding itself. \
+    /// this function should called only after the direct parent is set
+    /// and before all the ancestors are set
+    /// and when we allow single inheritance \
+    /// the order of the returned list is from the child to the deepest ancestor
+    pub fn get_all_ancestors_helper(
+        child: &TypeAnnotation,
+        temp_def_list: &[Arc<RwLock<TopLevelDef>>],
+    ) -> Result<Vec<TypeAnnotation>, String> {
+        let mut result: Vec<TypeAnnotation> = Vec::new();
+        let mut parent = Self::get_parent(child, temp_def_list);
+        while let Some(p) = parent {
+            parent = Self::get_parent(&p, temp_def_list);
+            let p_id = if let TypeAnnotation::CustomClass { id, .. } = &p {
+                *id
+            } else {
+                unreachable!("must be class kind annotation")
+            };
+            // check cycle
+            let no_cycle = result.iter().all(|x| {
+                if let TypeAnnotation::CustomClass { id, .. } = x {
+                    id.0 != p_id.0
+                } else {
+                    unreachable!("must be class kind annotation")
+                }
+            });
+            if no_cycle {
+                result.push(p);
+            } else {
+                return Err("cyclic inheritance detected".into());
+            }
+        }
+        Ok(result)
+    }
+
+    /// should only be called when finding all ancestors, so panic when wrong
+    fn get_parent(
+        child: &TypeAnnotation,
+        temp_def_list: &[Arc<RwLock<TopLevelDef>>],
+    ) -> Option<TypeAnnotation> {
+        let child_id = if let TypeAnnotation::CustomClass { id, .. } = child {
+            *id
+        } else {
+            unreachable!("should be class type annotation")
+        };
+        let child_def = temp_def_list.get(child_id.0).unwrap();
+        let child_def = child_def.read();
+        if let TopLevelDef::Class { ancestors, .. } = &*child_def {
+            if !ancestors.is_empty() {
+                Some(ancestors[0].clone())
+            } else {
+                None
+            }
+        } else {
+            unreachable!("child must be top level class def")
+        }
+    }
+
+    /// get the var_id of a given TVar type
+    pub fn get_var_id(var_ty: Type, unifier: &mut Unifier) -> Result<u32, String> {
+        if let TypeEnum::TVar { id, .. } = unifier.get_ty(var_ty).as_ref() {
+            Ok(*id)
+        } else {
+            Err("not type var".to_string())
+        }
+    }
+
+    pub fn check_overload_function_type(
+        this: Type,
+        other: Type,
+        unifier: &mut Unifier,
+        type_var_to_concrete_def: &HashMap<Type, TypeAnnotation>,
+    ) -> bool {
+        let this = unifier.get_ty(this);
+        let this = this.as_ref();
+        let other = unifier.get_ty(other);
+        let other = other.as_ref();
+        if let (
+            TypeEnum::TFunc(FunSignature { args: this_args, ret: this_ret, .. }),
+            TypeEnum::TFunc(FunSignature { args: other_args, ret: other_ret, .. }),
+        ) = (this, other)
+        {
+            // check args
+            let args_ok = this_args
+                .iter()
+                .map(|FuncArg { name, ty, .. }| (name, type_var_to_concrete_def.get(ty).unwrap()))
+                .zip(other_args.iter().map(|FuncArg { name, ty, .. }| {
+                    (name, type_var_to_concrete_def.get(ty).unwrap())
+                }))
+                .all(|(this, other)| {
+                    if this.0 == &"self".into() && this.0 == other.0 {
+                        true
+                    } else {
+                        this.0 == other.0
+                            && check_overload_type_annotation_compatible(this.1, other.1, unifier)
+                    }
+                });
+
+            // check rets
+            let ret_ok = check_overload_type_annotation_compatible(
+                type_var_to_concrete_def.get(this_ret).unwrap(),
+                type_var_to_concrete_def.get(other_ret).unwrap(),
+                unifier,
+            );
+
+            // return
+            args_ok && ret_ok
+        } else {
+            unreachable!("this function must be called with function type")
+        }
+    }
+
+    pub fn check_overload_field_type(
+        this: Type,
+        other: Type,
+        unifier: &mut Unifier,
+        type_var_to_concrete_def: &HashMap<Type, TypeAnnotation>,
+    ) -> bool {
+        check_overload_type_annotation_compatible(
+            type_var_to_concrete_def.get(&this).unwrap(),
+            type_var_to_concrete_def.get(&other).unwrap(),
+            unifier,
+        )
+    }
+
+    pub fn get_all_assigned_field(stmts: &[ast::Stmt<()>]) -> Result<HashSet<StrRef>, String> {
+        let mut result = HashSet::new();
+        for s in stmts {
+            match &s.node {
+                ast::StmtKind::AnnAssign { target, .. }
+                    if {
+                        if let ast::ExprKind::Attribute { value, .. } = &target.node {
+                            if let ast::ExprKind::Name { id, .. } = &value.node {
+                                id == &"self".into()
+                            } else {
+                                false
+                            }
+                        } else {
+                            false
+                        }
+                    } =>
+                {
+                    return Err(format!(
+                        "redundant type annotation for class fields at {}",
+                        s.location
+                    ))
+                }
+                ast::StmtKind::Assign { targets, .. } => {
+                    for t in targets {
+                        if let ast::ExprKind::Attribute { value, attr, .. } = &t.node {
+                            if let ast::ExprKind::Name { id, .. } = &value.node {
+                                if id == &"self".into() {
+                                    result.insert(*attr);
+                                }
+                            }
+                        }
+                    }
+                }
+                // TODO: do not check for For and While?
+                ast::StmtKind::For { body, orelse, .. }
+                | ast::StmtKind::While { body, orelse, .. } => {
+                    result.extend(Self::get_all_assigned_field(body.as_slice())?);
+                    result.extend(Self::get_all_assigned_field(orelse.as_slice())?);
+                }
+                ast::StmtKind::If { body, orelse, .. } => {
+                    let inited_for_sure = Self::get_all_assigned_field(body.as_slice())?
+                        .intersection(&Self::get_all_assigned_field(orelse.as_slice())?)
+                        .cloned()
+                        .collect::<HashSet<_>>();
+                    result.extend(inited_for_sure);
+                }
+                ast::StmtKind::Try { body, orelse, finalbody, .. } => {
+                    let inited_for_sure = Self::get_all_assigned_field(body.as_slice())?
+                        .intersection(&Self::get_all_assigned_field(orelse.as_slice())?)
+                        .cloned()
+                        .collect::<HashSet<_>>();
+                    result.extend(inited_for_sure);
+                    result.extend(Self::get_all_assigned_field(finalbody.as_slice())?);
+                }
+                ast::StmtKind::With { body, .. } => {
+                    result.extend(Self::get_all_assigned_field(body.as_slice())?);
+                }
+                ast::StmtKind::Pass { .. } => {}
+                ast::StmtKind::Assert { .. } => {}
+                ast::StmtKind::Expr { .. } => {}
+
+                _ => {
+                    unimplemented!()
+                }
+            }
+        }
+        Ok(result)
+    }
+
+    pub fn parse_parameter_default_value(
+        default: &ast::Expr,
+        resolver: &(dyn SymbolResolver + Send + Sync),
+    ) -> Result<SymbolValue, String> {
+        parse_parameter_default_value(default, resolver)
+    }
+
+    pub fn check_default_param_type(
+        val: &SymbolValue,
+        ty: &TypeAnnotation,
+        primitive: &PrimitiveStore,
+        unifier: &mut Unifier,
+    ) -> Result<(), String> {
+        fn type_default_param(
+            val: &SymbolValue,
+            primitive: &PrimitiveStore,
+            unifier: &mut Unifier,
+        ) -> TypeAnnotation {
+            match val {
+                SymbolValue::Bool(..) => TypeAnnotation::Primitive(primitive.bool),
+                SymbolValue::Double(..) => TypeAnnotation::Primitive(primitive.float),
+                SymbolValue::I32(..) => TypeAnnotation::Primitive(primitive.int32),
+                SymbolValue::I64(..) => TypeAnnotation::Primitive(primitive.int64),
+                SymbolValue::U32(..) => TypeAnnotation::Primitive(primitive.uint32),
+                SymbolValue::U64(..) => TypeAnnotation::Primitive(primitive.uint64),
+                SymbolValue::Str(..) => TypeAnnotation::Primitive(primitive.str),
+                SymbolValue::Tuple(vs) => {
+                    let vs_tys = vs
+                        .iter()
+                        .map(|v| type_default_param(v, primitive, unifier))
+                        .collect::<Vec<_>>();
+                    TypeAnnotation::Tuple(vs_tys)
+                }
+                SymbolValue::OptionNone => TypeAnnotation::CustomClass {
+                    id: primitive.option.get_obj_id(unifier),
+                    params: Default::default(),
+                },
+                SymbolValue::OptionSome(v) => {
+                    let ty = type_default_param(v, primitive, unifier);
+                    TypeAnnotation::CustomClass {
+                        id: primitive.option.get_obj_id(unifier),
+                        params: vec![ty],
+                    }
+                }
+            }
+        }
+
+        fn is_compatible(
+            found: &TypeAnnotation,
+            expect: &TypeAnnotation,
+            unifier: &mut Unifier,
+            primitive: &PrimitiveStore,
+        ) -> bool {
+            match (found, expect) {
+                (TypeAnnotation::Primitive(f), TypeAnnotation::Primitive(e)) => {
+                    unifier.unioned(*f, *e)
+                }
+                (
+                    TypeAnnotation::CustomClass { id: f_id, params: f_param },
+                    TypeAnnotation::CustomClass { id: e_id, params: e_param },
+                ) => {
+                    *f_id == *e_id
+                        && *f_id == primitive.option.get_obj_id(unifier)
+                        && (f_param.is_empty()
+                            || (f_param.len() == 1
+                                && e_param.len() == 1
+                                && is_compatible(&f_param[0], &e_param[0], unifier, primitive)))
+                }
+                (TypeAnnotation::Tuple(f), TypeAnnotation::Tuple(e)) => {
+                    f.len() == e.len()
+                        && f.iter()
+                            .zip(e.iter())
+                            .all(|(f, e)| is_compatible(f, e, unifier, primitive))
+                }
+                _ => false,
+            }
+        }
+
+        let found = type_default_param(val, primitive, unifier);
+        if !is_compatible(&found, ty, unifier, primitive) {
+            Err(format!(
+                "incompatible default parameter type, expect {}, found {}",
+                ty.stringify(unifier),
+                found.stringify(unifier),
+            ))
+        } else {
+            Ok(())
+        }
+    }
+}
+
+pub fn parse_parameter_default_value(
+    default: &ast::Expr,
+    resolver: &(dyn SymbolResolver + Send + Sync),
+) -> Result<SymbolValue, String> {
+    fn handle_constant(val: &Constant, loc: &Location) -> Result<SymbolValue, String> {
+        match val {
+            Constant::Int(v) => {
+                if let Ok(v) = (*v).try_into() {
+                    Ok(SymbolValue::I32(v))
+                } else {
+                    Err(format!("integer value out of range at {}", loc))
+                }
+            }
+            Constant::Float(v) => Ok(SymbolValue::Double(*v)),
+            Constant::Bool(v) => Ok(SymbolValue::Bool(*v)),
+            Constant::Tuple(tuple) => Ok(SymbolValue::Tuple(
+                tuple.iter().map(|x| handle_constant(x, loc)).collect::<Result<Vec<_>, _>>()?,
+            )),
+            Constant::None => Err(format!(
+                "`None` is not supported, use `none` for option type instead ({})",
+                loc
+            )),
+            _ => unimplemented!("this constant is not supported at {}", loc),
+        }
+    }
+    match &default.node {
+        ast::ExprKind::Constant { value, .. } => handle_constant(value, &default.location),
+        ast::ExprKind::Call { func, args, .. } if args.len() == 1 => {
+            match &func.node {
+                ast::ExprKind::Name { id, .. } if *id == "int64".into() => match &args[0].node {
+                    ast::ExprKind::Constant { value: Constant::Int(v), .. } => {
+                        let v: Result<i64, _> = (*v).try_into();
+                        match v {
+                            Ok(v) => Ok(SymbolValue::I64(v)),
+                            _ => Err(format!("default param value out of range at {}", default.location)),
+                        }
+                    }
+                    _ => Err(format!("only allow constant integer here at {}", default.location))
+                }
+                ast::ExprKind::Name { id, .. } if *id == "uint32".into() => match &args[0].node {
+                    ast::ExprKind::Constant { value: Constant::Int(v), .. } => {
+                        let v: Result<u32, _> = (*v).try_into();
+                        match v {
+                            Ok(v) => Ok(SymbolValue::U32(v)),
+                            _ => Err(format!("default param value out of range at {}", default.location)),
+                        }
+                    }
+                    _ => Err(format!("only allow constant integer here at {}", default.location))
+                }
+                ast::ExprKind::Name { id, .. } if *id == "uint64".into() => match &args[0].node {
+                    ast::ExprKind::Constant { value: Constant::Int(v), .. } => {
+                        let v: Result<u64, _> = (*v).try_into();
+                        match v {
+                            Ok(v) => Ok(SymbolValue::U64(v)),
+                            _ => Err(format!("default param value out of range at {}", default.location)),
+                        }
+                    }
+                    _ => Err(format!("only allow constant integer here at {}", default.location))
+                }
+                ast::ExprKind::Name { id, .. } if *id == "Some".into() => Ok(
+                    SymbolValue::OptionSome(
+                        Box::new(parse_parameter_default_value(&args[0], resolver)?)
+                    )
+                ),
+                _ => Err(format!("unsupported default parameter at {}", default.location)),
+            }
+        }
+        ast::ExprKind::Tuple { elts, .. } => Ok(SymbolValue::Tuple(elts
+            .iter()
+            .map(|x| parse_parameter_default_value(x, resolver))
+            .collect::<Result<Vec<_>, _>>()?
+        )),
+        ast::ExprKind::Name { id, .. } if id == &"none".into() => Ok(SymbolValue::OptionNone),
+        ast::ExprKind::Name { id, .. } => {
+            resolver.get_default_param_value(default).ok_or_else(
+                || format!(
+                    "`{}` cannot be used as a default parameter at {} \
+                    (not primitive type, option or tuple / not defined?)",
+                    id,
+                    default.location
+                )
+            )
+        }
+        _ => Err(format!(
+            "unsupported default parameter (not primitive type, option or tuple) at {}",
+            default.location
+        ))
+    }
+}

nac3core/src/toplevel/mod.rs

@@ -0,0 +1,138 @@
+use std::{
+    borrow::BorrowMut,
+    collections::{HashMap, HashSet},
+    fmt::Debug,
+    iter::FromIterator,
+    ops::{Deref, DerefMut},
+    sync::Arc,
+};
+
+use super::codegen::CodeGenContext;
+use super::typecheck::type_inferencer::PrimitiveStore;
+use super::typecheck::typedef::{FunSignature, FuncArg, SharedUnifier, Type, TypeEnum, Unifier};
+use crate::{
+    codegen::CodeGenerator,
+    symbol_resolver::{SymbolResolver, ValueEnum},
+    typecheck::{type_inferencer::CodeLocation, typedef::CallId},
+};
+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);
+
+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: GenCallCallback,
+}
+
+impl GenCall {
+    pub fn new(fp: GenCallCallback) -> GenCall {
+        GenCall { fp }
+    }
+
+    pub fn run<'ctx, 'a>(
+        &self,
+        ctx: &mut CodeGenContext<'ctx, 'a>,
+        obj: Option<(Type, ValueEnum<'ctx>)>,
+        fun: (&FunSignature, DefinitionId),
+        args: Vec<(Option<StrRef>, ValueEnum<'ctx>)>,
+        generator: &mut dyn CodeGenerator,
+    ) -> Result<Option<BasicValueEnum<'ctx>>, String> {
+        (self.fp)(ctx, obj, fun, args, generator)
+    }
+}
+
+impl Debug for GenCall {
+    fn fmt(&self, _: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        Ok(())
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct FunInstance {
+    pub body: Arc<Vec<Stmt<Option<Type>>>>,
+    pub calls: Arc<HashMap<CodeLocation, CallId>>,
+    pub subst: HashMap<u32, Type>,
+    pub unifier_id: usize,
+}
+
+#[derive(Debug, Clone)]
+pub enum TopLevelDef {
+    Class {
+        // name for error messages and symbols
+        name: StrRef,
+        // object ID used for TypeEnum
+        object_id: DefinitionId,
+        /// type variables bounded to the class.
+        type_vars: Vec<Type>,
+        // class fields
+        // name, type, is mutable
+        fields: Vec<(StrRef, Type, bool)>,
+        // class methods, pointing to the corresponding function definition.
+        methods: Vec<(StrRef, Type, DefinitionId)>,
+        // ancestor classes, including itself.
+        ancestors: Vec<TypeAnnotation>,
+        // 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: Option<Type>,
+        // definition location
+        loc: Option<Location>,
+    },
+    Function {
+        // prefix for symbol, should be unique globally
+        name: String,
+        // simple name, the same as in method/function definition
+        simple_name: StrRef,
+        // function signature.
+        signature: Type,
+        // 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.
+        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.
+        instance_to_stmt: HashMap<String, FunInstance>,
+        // symbol resolver of the module defined the class
+        resolver: Option<Arc<dyn SymbolResolver + Send + Sync>>,
+        // custom codegen callback
+        codegen_callback: Option<Arc<GenCall>>,
+        // definition location
+        loc: Option<Location>,
+    },
+}
+
+pub struct TopLevelContext {
+    pub definitions: Arc<RwLock<Vec<Arc<RwLock<TopLevelDef>>>>>,
+    pub unifiers: Arc<RwLock<Vec<(SharedUnifier, PrimitiveStore)>>>,
+    pub personality_symbol: Option<String>,
+}

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__generic_class.snap

@@ -0,0 +1,14 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+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: [18]\n}\n",
+    "Class {\nname: \"B\",\nancestors: [\"B\"],\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",
+]

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__inheritance_override.snap

@@ -0,0 +1,17 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+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",
+    "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[typevar7]\", \"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: [\"typevar7\"]\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",
+    "Function {\nname: \"C.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
+]

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__list_tuple_generic.snap

@@ -0,0 +1,15 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+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: [20]\n}\n",
+    "Function {\nname: \"A.fun\",\nsig: \"fn[[a:T], V]\",\nvar_id: [25]\n}\n",
+    "Function {\nname: \"gfun\",\nsig: \"fn[[a:A[int32, list[float]]], none]\",\nvar_id: []\n}\n",
+    "Class {\nname: \"B\",\nancestors: [\"B\"],\nfields: [],\nmethods: [(\"__init__\", \"fn[[], none]\")],\ntype_vars: []\n}\n",
+    "Function {\nname: \"B.__init__\",\nsig: \"fn[[], none]\",\nvar_id: []\n}\n",
+]

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__self1.snap

@@ -0,0 +1,15 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+expression: res_vec
+
+---
+[
+    "Class {\nname: \"A\",\nancestors: [\"A[typevar6, typevar7]\"],\nfields: [\"a\", \"b\"],\nmethods: [(\"__init__\", \"fn[[a:A[bool, float], b:B], none]\"), (\"fun\", \"fn[[a:A[bool, float]], A[bool, int32]]\")],\ntype_vars: [\"typevar6\", \"typevar7\"]\n}\n",
+    "Function {\nname: \"A.__init__\",\nsig: \"fn[[a:A[bool, float], b:B], none]\",\nvar_id: []\n}\n",
+    "Function {\nname: \"A.fun\",\nsig: \"fn[[a:A[bool, float]], 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[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[int32, list[B]]], tuple[A[bool, virtual[A[B, int32]]], B]]\",\nvar_id: []\n}\n",
+]

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__simple_class_compose.snap

@@ -0,0 +1,19 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+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",
+    "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: [26]\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: \"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",
+    "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: [34]\n}\n",
+]

nac3core/src/toplevel/snapshots/nac3core__toplevel__test__test_analyze__simple_pass_in_class.snap

@@ -0,0 +1,9 @@
+---
+source: nac3core/src/toplevel/test.rs
+assertion_line: 549
+expression: res_vec
+
+---
+[
+    "Class {\nname: \"A\",\nancestors: [\"A\"],\nfields: [],\nmethods: [],\ntype_vars: []\n}\n",
+]

nac3core/src/toplevel/test.rs

@@ -0,0 +1,801 @@
+use crate::{
+    codegen::CodeGenContext,
+    symbol_resolver::{SymbolResolver, ValueEnum},
+    toplevel::DefinitionId,
+    typecheck::{
+        type_inferencer::PrimitiveStore,
+        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>>,
+    id_to_def: Mutex<HashMap<StrRef, DefinitionId>>,
+    class_names: Mutex<HashMap<StrRef, Type>>,
+}
+
+impl ResolverInternal {
+    fn add_id_def(&self, id: StrRef, def: DefinitionId) {
+        self.id_to_def.lock().insert(id, def);
+    }
+
+    fn add_id_type(&self, id: StrRef, ty: Type) {
+        self.id_to_type.lock().insert(id, ty);
+    }
+}
+
+struct Resolver(Arc<ResolverInternal>);
+
+impl SymbolResolver for Resolver {
+    fn get_default_param_value(
+        &self,
+        _: &nac3parser::ast::Expr,
+    ) -> Option<crate::symbol_resolver::SymbolValue> {
+        unimplemented!()
+    }
+
+    fn get_symbol_type(
+        &self,
+        _: &mut Unifier,
+        _: &[Arc<RwLock<TopLevelDef>>],
+        _: &PrimitiveStore,
+        str: StrRef,
+    ) -> Result<Type, String> {
+        self.0
+            .id_to_type
+            .lock()
+            .get(&str)
+            .cloned()
+            .ok_or_else(|| format!("cannot find symbol `{}`", str))
+    }
+
+    fn get_symbol_value<'ctx, 'a>(
+        &self,
+        _: StrRef,
+        _: &mut CodeGenContext<'ctx, 'a>,
+    ) -> Option<ValueEnum<'ctx>> {
+        unimplemented!()
+    }
+
+    fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
+        self.0.id_to_def.lock().get(&id).cloned().ok_or_else(|| "Unknown identifier".to_string())
+    }
+
+    fn get_string_id(&self, _: &str) -> i32 {
+        unimplemented!()
+    }
+
+    fn get_exception_id(&self, _tyid: usize) -> usize {
+        unimplemented!()
+    }
+}
+
+#[test_case(
+    vec![
+        indoc! {"
+            def fun(a: int32) -> int32:
+                return a
+        "},
+        indoc! {"
+            class A:
+                def __init__(self):
+                    self.a: int32 = 3
+        "},
+        indoc! {"
+            class B:
+                def __init__(self):
+                    self.b: float = 4.3
+
+                def fun(self):
+                    self.b = self.b + 3.0
+        "},
+        indoc! {"
+            def foo(a: float):
+                a + 1.0
+        "},
+        indoc! {"
+            class C(B):
+                def __init__(self):
+                    self.c: int32 = 4
+                    self.a: bool = True
+        "}
+    ];
+    "register"
+)]
+fn test_simple_register(source: Vec<&str>) {
+    let mut composer: TopLevelComposer = Default::default();
+
+    for s in source {
+        let ast = parse_program(s, Default::default()).unwrap();
+        let ast = ast[0].clone();
+
+        composer.register_top_level(ast, None, "".into()).unwrap();
+    }
+}
+
+#[test_case(
+    vec![
+        indoc! {"
+            def fun(a: int32) -> int32:
+                return a
+        "},
+        indoc! {"
+            def foo(a: float):
+                a + 1.0
+        "},
+        indoc! {"
+            def f(b: int64) -> int32:
+                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: Vec<&str>, tys: Vec<&str>, names: Vec<&str>) {
+    let mut composer: TopLevelComposer = Default::default();
+
+    let internal_resolver = Arc::new(ResolverInternal {
+        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, Default::default()).unwrap();
+        let ast = ast[0].clone();
+
+        let (id, def_id, ty) =
+            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);
+        }
+    }
+
+    composer.start_analysis(true).unwrap();
+
+    for (i, (def, _)) in composer.definition_ast_list.iter().skip(composer.builtin_num).enumerate()
+    {
+        let def = &*def.read();
+        if let TopLevelDef::Function { signature, name, .. } = def {
+            let ty_str = composer.unifier.internal_stringify(
+                *signature,
+                &mut |id| id.to_string(),
+                &mut |id| id.to_string(),
+                &mut None,
+            );
+            assert_eq!(ty_str, tys[i]);
+            assert_eq!(name, names[i]);
+        }
+    }
+}
+
+#[test_case(
+    vec![
+        indoc! {"
+            class A():
+                a: int32
+                def __init__(self):
+                    self.a = 3
+                def fun(self, b: B):
+                    pass
+                def foo(self, a: T, b: V):
+                    pass
+        "},
+        indoc! {"
+            class B(C):
+                def __init__(self):
+                    pass
+        "},
+        indoc! {"
+            class C(A):
+                def __init__(self):
+                    pass
+                def fun(self, b: B):
+                    a = 1
+                    pass
+        "},
+        indoc! {"
+            def foo(a: A):
+                pass
+        "},
+        indoc! {"
+            def ff(a: T) -> V:
+                pass
+        "}
+    ],
+    vec![];
+    "simple class compose"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class Generic_A(Generic[V], B):
+                a: int64
+                def __init__(self):
+                    self.a = 123123123123
+                def fun(self, a: int32) -> V:
+                    pass
+        "},
+        indoc! {"
+            class B:
+                aa: bool
+                def __init__(self):
+                    self.aa = False
+                def foo(self, b: T):
+                    pass
+        "}
+    ],
+    vec![];
+    "generic class"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            def foo(a: list[int32], b: tuple[T, float]) -> A[B, bool]:
+                pass
+        "},
+        indoc! {"
+            class A(Generic[T, V]):
+                a: T
+                b: V
+                def __init__(self, v: V):
+                    self.a = 1
+                    self.b = v
+                def fun(self, a: T) -> V:
+                    pass
+        "},
+        indoc! {"
+            def gfun(a: A[list[float], int32]):
+                pass
+        "},
+        indoc! {"
+            class B:
+                def __init__(self):
+                    pass
+        "}
+    ],
+    vec![];
+    "list tuple generic"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A(Generic[T, V]):
+                a: A[float, bool]
+                b: B
+                def __init__(self, a: A[float, bool], b: B):
+                    self.a = a
+                    self.b = b
+                def fun(self, a: A[float, bool]) -> A[bool, int32]:
+                    pass
+        "},
+        indoc! {"
+            class B(A[int64, bool]):
+                def __init__(self):
+                    pass
+                def foo(self, b: B) -> B:
+                    pass
+                def bar(self, a: A[list[B], int32]) -> tuple[A[virtual[A[B, int32]], bool], B]:
+                    pass
+        "}
+    ],
+    vec![];
+    "self1"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A(Generic[T]):
+                a: int32
+                b: T
+                c: A[int64]
+                def __init__(self, t: T):
+                    self.a = 3
+                    self.b = T
+                def fun(self, a: int32, b: T) -> list[virtual[B[bool]]]:
+                    pass
+                def foo(self, c: C):
+                    pass
+        "},
+        indoc! {"
+            class B(Generic[V], A[float]):
+                d: C
+                def __init__(self):
+                    pass
+                def fun(self, a: int32, b: T) -> list[virtual[B[bool]]]:
+                    # override
+                    pass
+        "},
+        indoc! {"
+            class C(B[bool]):
+                e: int64
+                def __init__(self):
+                    pass
+        "}
+    ],
+    vec![];
+    "inheritance_override"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A(Generic[T]):
+                def __init__(self):
+                    pass
+                def fun(self, a: A[T]) -> A[T]:
+                    pass
+        "}
+    ],
+    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):
+                    pass
+        "},
+        indoc! {"
+            class B(A):
+                def __init__(self):
+                    pass
+        "}
+    ],
+    vec!["cyclic inheritance detected"];
+    "cyclic1"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A(B[bool, int64]):
+                def __init__(self):
+                    pass
+        "},
+        indoc! {"
+            class B(Generic[V, T], C[int32]):
+                def __init__(self):
+                    pass
+        "},
+        indoc! {"
+            class C(Generic[T], A):
+                def __init__(self):
+                    pass
+        "},
+    ],
+    vec!["cyclic inheritance detected"];
+    "cyclic2"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A:
+                pass
+        "}
+    ],
+    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(
+    vec![indoc! {"
+        class A:
+            def __init__():
+                pass
+    "}],
+    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):
+                    pass
+        "},
+        indoc! {"
+            class B:
+                def __init__(self):
+                    pass
+        "},
+        indoc! {"
+            class C:
+                def __init__(self):
+                    pass
+        "}
+
+    ],
+    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
+                b: T
+                c: A[int64]
+                def __init__(self, t: T):
+                    self.a = 3
+                    self.b = T
+                def fun(self, a: int32, b: T) -> list[virtual[B[bool]]]:
+                    pass
+        "},
+        indoc! {"
+            class B(Generic[V], A[float]):
+                def __init__(self):
+                    pass
+                def fun(self, a: int32, b: T) -> list[virtual[B[int32]]]:
+                    # override
+                    pass
+        "}
+    ],
+    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
+                b: T
+                c: A[int64]
+                def __init__(self, t: T):
+                    self.a = 3
+                    self.b = T
+                def fun(self, a: int32, b: T) -> list[virtual[B[bool]]]:
+                    pass
+        "},
+        indoc! {"
+            class B(Generic[V], A[float]):
+                a: int32
+                def __init__(self):
+                    pass
+                def fun(self, a: int32, b: T) -> list[virtual[B[bool]]]:
+                    # override
+                    pass
+        "}
+    ],
+    vec!["field `a` has already declared in the ancestor classes"];
+    "err_incompatible_inheritance_field"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A:
+                def __init__(self):
+                    pass
+        "},
+        indoc! {"
+            class A:
+                a: int32
+                def __init__(self):
+                    pass
+        "}
+    ],
+    vec!["duplicate definition of class `A` (at unknown: line 1 column 1)"];
+    "class same name"
+)]
+fn test_analyze(source: Vec<&str>, res: Vec<&str>) {
+    let print = false;
+    let mut composer: TopLevelComposer = Default::default();
+
+    let internal_resolver = make_internal_resolver_with_tvar(
+        vec![
+            ("T".into(), vec![]),
+            ("V".into(), vec![composer.primitives_ty.bool, composer.primitives_ty.int32]),
+            ("G".into(), vec![composer.primitives_ty.bool, composer.primitives_ty.int64]),
+        ],
+        &mut composer.unifier,
+        print,
+    );
+    let resolver =
+        Arc::new(Resolver(internal_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
+
+    for s in source {
+        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()), "".into()) {
+                Ok(x) => x,
+                Err(msg) => {
+                    if print {
+                        println!("{}", msg);
+                    } else {
+                        assert_eq!(res[0], msg);
+                    }
+                    return;
+                }
+            }
+        };
+        internal_resolver.add_id_def(id, def_id);
+        if let Some(ty) = ty {
+            internal_resolver.add_id_type(id, ty);
+        }
+    }
+
+    if let Err(msg) = composer.start_analysis(false) {
+        if print {
+            println!("{}", msg);
+        } else {
+            assert_eq!(res[0], msg);
+        }
+    } else {
+        // skip 5 to skip primitives
+        let mut res_vec: Vec<String> = Vec::new();
+        for (def, _) in composer.definition_ast_list.iter().skip(composer.builtin_num) {
+            let def = &*def.read();
+            res_vec.push(format!("{}\n", def.to_string(composer.unifier.borrow_mut())));
+        }
+        insta::assert_debug_snapshot!(res_vec);
+    }
+}
+
+#[test_case(
+    vec![
+        indoc! {"
+            def fun(a: int32, b: int32) -> int32:
+                return a + b
+        "},
+        indoc! {"
+            def fib(n: int32) -> int32:
+                if n <= 2:
+                    return 1
+                a = fib(n - 1)
+                b = fib(n - 2)
+                return fib(n - 1)
+        "}
+    ],
+    vec![];
+    "simple function"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A:
+                a: int32
+                def __init__(self):
+                    self.a = 3
+                def fun(self) -> int32:
+                    b = self.a + 3
+                    return b * self.a
+                def clone(self) -> A:
+                    SELF = self
+                    return SELF
+                def sum(self) -> int32:
+                    if self.a == 0:
+                        return self.a
+                    else:
+                        a = self.a
+                        self.a = self.a - 1
+                        return a + self.sum()
+                def fib(self, a: int32) -> int32:
+                    if a <= 2:
+                        return 1
+                    return self.fib(a - 1) + self.fib(a - 2)
+        "},
+        indoc! {"
+            def fun(a: A) -> int32:
+                return a.fun() + 2
+        "}
+    ],
+    vec![];
+    "simple class body"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            def fun(a: V, c: G, t: T) -> V:
+                b = a
+                cc = c
+                ret = fun(b, cc, t)
+                return ret * ret
+        "},
+        indoc! {"
+            def sum_three(l: list[V]) -> V:
+                return l[0] + l[1] + l[2]
+        "},
+        indoc! {"
+            def sum_sq_pair(p: tuple[V, V]) -> list[V]:
+                a = p[0]
+                b = p[1]
+                a = a**a
+                b = b**b
+                return [a, b]
+        "}
+    ],
+    vec![];
+    "type var fun"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A(Generic[G]):
+                a: G
+                b: bool
+                def __init__(self, aa: G):
+                    self.a = aa
+                    if 2 > 1:
+                        self.b = True
+                    else:
+                        # self.b = False
+                        pass
+                def fun(self, a: G) -> list[G]:
+                    ret = [a, self.a]
+                    return ret if self.b else self.fun(self.a)
+        "}
+    ],
+    vec![];
+    "type var class"
+)]
+#[test_case(
+    vec![
+        indoc! {"
+            class A:
+                def fun(self):
+                    pass
+        "},
+        indoc!{"
+            class B:
+                a: int32
+                b: bool
+                def __init__(self):
+                    # self.b = False
+                    if 3 > 2:
+                        self.a = 3
+                        self.b = False
+                    else:
+                        self.a = 4
+                        self.b = True
+        "}
+    ],
+    vec![];
+    "no_init_inst_check"
+)]
+fn test_inference(source: Vec<&str>, res: Vec<&str>) {
+    let print = true;
+    let mut composer: TopLevelComposer = Default::default();
+
+    let internal_resolver = make_internal_resolver_with_tvar(
+        vec![
+            ("T".into(), vec![]),
+            (
+                "V".into(),
+                vec![
+                    composer.primitives_ty.float,
+                    composer.primitives_ty.int32,
+                    composer.primitives_ty.int64,
+                ],
+            ),
+            ("G".into(), vec![composer.primitives_ty.bool, composer.primitives_ty.int64]),
+        ],
+        &mut composer.unifier,
+        print,
+    );
+    let resolver =
+        Arc::new(Resolver(internal_resolver.clone())) as Arc<dyn SymbolResolver + Send + Sync>;
+
+    for s in source {
+        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()), "".into()) {
+                Ok(x) => x,
+                Err(msg) => {
+                    if print {
+                        println!("{}", msg);
+                    } else {
+                        assert_eq!(res[0], msg);
+                    }
+                    return;
+                }
+            }
+        };
+        internal_resolver.add_id_def(id, def_id);
+        if let Some(ty) = ty {
+            internal_resolver.add_id_type(id, ty);
+        }
+    }
+
+    if let Err(msg) = composer.start_analysis(true) {
+        if print {
+            println!("{}", msg);
+        } else {
+            assert_eq!(res[0], msg);
+        }
+    } else {
+        // skip 5 to skip primitives
+        let mut stringify_folder = TypeToStringFolder { unifier: &mut composer.unifier };
+        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 {
+                println!(
+                    "=========`{}`: number of instances: {}===========",
+                    name,
+                    instance_to_stmt.len()
+                );
+                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());
+                        println!("--------------------");
+                    }
+                    println!("\n");
+                }
+            }
+        }
+    }
+}
+
+fn make_internal_resolver_with_tvar(
+    tvars: Vec<(StrRef, Vec<Type>)>,
+    unifier: &mut Unifier,
+    print: bool,
+) -> Arc<ResolverInternal> {
+    let res: Arc<ResolverInternal> = ResolverInternal {
+        id_to_def: Default::default(),
+        id_to_type: tvars
+            .into_iter()
+            .map(|(name, range)| {
+                (name, {
+                    let (ty, id) = unifier.get_fresh_var_with_range(range.as_slice(), None, None);
+                    if print {
+                        println!("{}: {:?}, typevar{}", name, ty, id);
+                    }
+                    ty
+                })
+            })
+            .collect::<HashMap<_, _>>()
+            .into(),
+        class_names: Default::default(),
+    }
+    .into();
+    if print {
+        println!();
+    }
+    res
+}
+
+struct TypeToStringFolder<'a> {
+    unifier: &'a mut Unifier,
+}
+
+impl<'a> Fold<Option<Type>> for TypeToStringFolder<'a> {
+    type TargetU = String;
+    type Error = String;
+    fn map_user(&mut self, user: Option<Type>) -> Result<Self::TargetU, Self::Error> {
+        Ok(if let Some(ty) = user {
+            self.unifier.internal_stringify(
+                ty,
+                &mut |id| format!("class{}", id.to_string()),
+                &mut |id| format!("typevar{}", id.to_string()),
+                &mut None,
+            )
+        } else {
+            "None".into()
+        })
+    }
+}

nac3core/src/toplevel/type_annotation.rs

@@ -0,0 +1,529 @@
+use super::*;
+
+#[derive(Clone, Debug)]
+pub enum TypeAnnotation {
+    Primitive(Type),
+    // we use type vars kind at params to represent self type
+    CustomClass {
+        id: DefinitionId,
+        // params can also be type var
+        params: Vec<TypeAnnotation>,
+    },
+    // can only be CustomClassKind
+    Virtual(Box<TypeAnnotation>),
+    TypeVar(Type),
+    List(Box<TypeAnnotation>),
+    Tuple(Vec<TypeAnnotation>),
+}
+
+impl TypeAnnotation {
+    pub fn stringify(&self, unifier: &mut Unifier) -> String {
+        use TypeAnnotation::*;
+        match self {
+            Primitive(ty) | TypeVar(ty) => unifier.stringify(*ty),
+            CustomClass { id, params } => {
+                let class_name = match unifier.top_level {
+                    Some(ref top) => {
+                        if let TopLevelDef::Class { name, .. } =
+                            &*top.definitions.read()[id.0].read()
+                        {
+                            (*name).into()
+                        } else {
+                            unreachable!()
+                        }
+                    }
+                    None => format!("class_def_{}", id.0),
+                };
+                format!(
+                    "{}{}",
+                    class_name,
+                    {
+                        let param_list = params.iter().map(|p| p.stringify(unifier)).collect_vec().join(", ");
+                        if param_list.is_empty() {
+                            "".into()
+                        } else {
+                            format!("[{}]", param_list)
+                        }
+                    }
+                )
+            }
+            Virtual(ty) => format!("virtual[{}]", ty.stringify(unifier)),
+            List(ty) => format!("list[{}]", ty.stringify(unifier)),
+            Tuple(types) => {
+                format!("tuple[{}]", types.iter().map(|p| p.stringify(unifier)).collect_vec().join(", "))
+            }
+        }
+    }
+}
+
+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>>,
+) -> Result<TypeAnnotation, String> {
+    let name_handle = |id: &StrRef,
+                       unifier: &mut Unifier,
+                       locked: HashMap<DefinitionId, Vec<Type>>| {
+        if id == &"int32".into() {
+            Ok(TypeAnnotation::Primitive(primitives.int32))
+        } else if id == &"int64".into() {
+            Ok(TypeAnnotation::Primitive(primitives.int64))
+        } else if id == &"uint32".into() {
+            Ok(TypeAnnotation::Primitive(primitives.uint32))
+        } else if id == &"uint64".into() {
+            Ok(TypeAnnotation::Primitive(primitives.uint64))
+        } else if id == &"float".into() {
+            Ok(TypeAnnotation::Primitive(primitives.float))
+        } else if id == &"bool".into() {
+            Ok(TypeAnnotation::Primitive(primitives.bool))
+        } else if id == &"str".into() {
+            Ok(TypeAnnotation::Primitive(primitives.str))
+        } else if id == &"Exception".into() {
+            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();
+                if let Some(def_read) = def_read {
+                    if let TopLevelDef::Class { type_vars, .. } = &*def_read {
+                        type_vars.clone()
+                    } else {
+                        return Err(format!(
+                            "function cannot be used as a type (at {})",
+                            expr.location
+                        ));
+                    }
+                } else {
+                    locked.get(&obj_id).unwrap().clone()
+                }
+            };
+            // check param number here
+            if !type_vars.is_empty() {
+                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)).0;
+                unifier.unify(var, ty).unwrap();
+                Ok(TypeAnnotation::TypeVar(ty))
+            } else {
+                Err(format!("`{}` is not a valid type annotation (at {})", id, expr.location))
+            }
+        } else {
+            Err(format!("`{}` is not a valid type annotation (at {})", id, expr.location))
+        }
+    };
+
+    let class_name_handle =
+        |id: &StrRef,
+         slice: &ast::Expr<T>,
+         unifier: &mut Unifier,
+         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 {
+                    if let TopLevelDef::Class { type_vars, .. } = &*def_read {
+                        type_vars.clone()
+                    } else {
+                        unreachable!("must be class here")
+                    }
+                } else {
+                    locked.get(&obj_id).unwrap().clone()
+                }
+            };
+            // we do not check whether the application of type variables are compatible here
+            let param_type_infos = {
+                let params_ast = if let ast::ExprKind::Tuple { elts, .. } = &slice.node {
+                    elts.iter().collect_vec()
+                } else {
+                    vec![slice]
+                };
+                if type_vars.len() != params_ast.len() {
+                    return Err(format!(
+                        "expect {} type parameters but got {} (at {})",
+                        type_vars.len(),
+                        params_ast.len(),
+                        params_ast[0].location,
+                    ));
+                }
+                let result = params_ast
+                    .iter()
+                    .map(|x| {
+                        parse_ast_to_type_annotation_kinds(
+                            resolver,
+                            top_level_defs,
+                            unifier,
+                            primitives,
+                            x,
+                            {
+                                locked.insert(obj_id, type_vars.clone());
+                                locked.clone()
+                            },
+                        )
+                    })
+                    .collect::<Result<Vec<_>, _>>()?;
+                // make sure the result do not contain any type vars
+                let no_type_var =
+                    result.iter().all(|x| get_type_var_contained_in_type_annotation(x).is_empty());
+                if no_type_var {
+                    result
+                } else {
+                    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
+        ast::ExprKind::Subscript { value, slice, .. }
+            if {
+                matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"virtual".into())
+            } =>
+        {
+            let def = parse_ast_to_type_annotation_kinds(
+                resolver,
+                top_level_defs,
+                unifier,
+                primitives,
+                slice.as_ref(),
+                locked,
+            )?;
+            if !matches!(def, TypeAnnotation::CustomClass { .. }) {
+                unreachable!("must be concretized custom class kind in the virtual")
+            }
+            Ok(TypeAnnotation::Virtual(def.into()))
+        }
+
+        // list
+        ast::ExprKind::Subscript { value, slice, .. }
+            if {
+                matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"list".into())
+            } =>
+        {
+            let def_ann = parse_ast_to_type_annotation_kinds(
+                resolver,
+                top_level_defs,
+                unifier,
+                primitives,
+                slice.as_ref(),
+                locked,
+            )?;
+            Ok(TypeAnnotation::List(def_ann.into()))
+        }
+
+        // option
+        ast::ExprKind::Subscript { value, slice, .. }
+            if {
+                matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"Option".into())
+            } =>
+        {
+            let def_ann = parse_ast_to_type_annotation_kinds(
+                resolver,
+                top_level_defs,
+                unifier,
+                primitives,
+                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] })
+        }
+
+        // tuple
+        ast::ExprKind::Subscript { value, slice, .. }
+            if {
+                matches!(&value.node, ast::ExprKind::Name { id, .. } if id == &"tuple".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| {
+                    parse_ast_to_type_annotation_kinds(
+                        resolver,
+                        top_level_defs,
+                        unifier,
+                        primitives,
+                        e,
+                        locked.clone(),
+                    )
+                })
+                .collect::<Result<Vec<_>, _>>()?;
+            Ok(TypeAnnotation::Tuple(type_annotations))
+        }
+
+        // custom class
+        ast::ExprKind::Subscript { value, slice, .. } => {
+            if let ast::ExprKind::Name { id, .. } = &value.node {
+                class_name_handle(id, slice, unifier, locked)
+            } else {
+                Err(format!("unsupported expression type for class name (at {})", value.location))
+            }
+        }
+
+        _ => Err(format!("unsupported expression for type annotation (at {})", expr.location)),
+    }
+}
+
+// no need to have the `locked` parameter, unlike the `parse_ast_to_type_annotation_kinds`, since
+// when calling this function, there should be no topleveldef::class being write, and this function
+// also only read the toplevedefs
+pub fn get_type_from_type_annotation_kinds(
+    top_level_defs: &[Arc<RwLock<TopLevelDef>>],
+    unifier: &mut Unifier,
+    primitives: &PrimitiveStore,
+    ann: &TypeAnnotation,
+    subst_list: &mut Option<Vec<Type>>
+) -> 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.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,
+                                subst_list
+                            )
+                        })
+                        .collect::<Result<Vec<_>, _>>()?;
+
+                    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 || {
+                                        let temp = unifier.get_fresh_var_with_range(
+                                            range.as_slice(),
+                                            *name,
+                                            *loc,
+                                        );
+                                        unifier.unify(temp.0, p).is_ok()
+                                    }
+                                };
+                                if ok {
+                                    result.insert(*id, p);
+                                } else {
+                                    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 None
+                                        ),
+                                        *id
+                                    ));
+                                }
+                            } else {
+                                unreachable!("must be generic type var")
+                            }
+                        }
+                        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);
+                        (*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,
+                    });
+                    if need_subst {
+                        subst_list.as_mut().map(|wl| wl.push(ty));
+                    }
+                    Ok(ty)
+                }
+            } else {
+                unreachable!("should be class def here")
+            }
+        }
+        TypeAnnotation::Primitive(ty) | TypeAnnotation::TypeVar(ty) => Ok(*ty),
+        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(),
+                subst_list
+            )?;
+            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)
+                })
+                .collect::<Result<Vec<_>, _>>()?;
+            Ok(unifier.add_ty(TypeEnum::TTuple { ty: tys }))
+        }
+    }
+}
+
+/// given an def id, return a type annotation of self \
+/// ```python
+/// class A(Generic[T, V]):
+///     def fun(self):
+/// ```
+/// 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
+/// the Type of their fields and methods will also be subst when application/instantiation
+pub fn make_self_type_annotation(type_vars: &[Type], object_id: DefinitionId) -> TypeAnnotation {
+    TypeAnnotation::CustomClass {
+        id: object_id,
+        params: type_vars.iter().map(|ty| TypeAnnotation::TypeVar(*ty)).collect_vec(),
+    }
+}
+
+/// 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
+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()))
+        }
+        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(..) => {}
+    }
+    result
+}
+
+/// check the type compatibility for overload
+pub fn check_overload_type_annotation_compatible(
+    this: &TypeAnnotation,
+    other: &TypeAnnotation,
+    unifier: &mut Unifier,
+) -> bool {
+    match (this, other) {
+        (TypeAnnotation::Primitive(a), TypeAnnotation::Primitive(b)) => a == b,
+        (TypeAnnotation::TypeVar(a), TypeAnnotation::TypeVar(b)) => {
+            let a = unifier.get_ty(*a);
+            let a = a.deref();
+            let b = unifier.get_ty(*b);
+            let b = b.deref();
+            if let (
+                TypeEnum::TVar { id: a, fields: None, .. },
+                TypeEnum::TVar { id: b, fields: None, .. },
+            ) = (a, b)
+            {
+                a == b
+            } else {
+                unreachable!("must be type var")
+            }
+        }
+        (TypeAnnotation::Virtual(a), TypeAnnotation::Virtual(b))
+        | (TypeAnnotation::List(a), TypeAnnotation::List(b)) => {
+            check_overload_type_annotation_compatible(a.as_ref(), b.as_ref(), unifier)
+        }
+
+        (TypeAnnotation::Tuple(a), TypeAnnotation::Tuple(b)) => {
+            a.len() == b.len() && {
+                a.iter()
+                    .zip(b)
+                    .all(|(a, b)| check_overload_type_annotation_compatible(a, b, unifier))
+            }
+        }
+
+        (
+            TypeAnnotation::CustomClass { id: a, params: a_p },
+            TypeAnnotation::CustomClass { id: b, params: b_p },
+        ) => {
+            a.0 == b.0 && {
+                a_p.len() == b_p.len() && {
+                    a_p.iter()
+                        .zip(b_p)
+                        .all(|(a, b)| check_overload_type_annotation_compatible(a, b, unifier))
+                }
+            }
+        }
+
+        _ => false,
+    }
+}

nac3core/src/typecheck/context/global_context.rs

@@ -1,109 +0,0 @@
-use super::super::typedef::*;
-use std::collections::HashMap;
-use std::rc::Rc;
-
-/// Structure for storing top-level type definitions.
-/// Used for collecting type signature from source code.
-/// Can be converted to `InferenceContext` for type inference in functions.
-pub struct GlobalContext<'a> {
-    /// List of primitive definitions.
-    pub(super) primitive_defs: Vec<TypeDef<'a>>,
-    /// List of class definitions.
-    pub(super) class_defs: Vec<ClassDef<'a>>,
-    /// List of parametric type definitions.
-    pub(super) parametric_defs: Vec<ParametricDef<'a>>,
-    /// List of type variable definitions.
-    pub(super) var_defs: Vec<VarDef<'a>>,
-    /// Function name to signature mapping.
-    pub(super) fn_table: HashMap<&'a str, FnDef>,
-
-    primitives: Vec<Type>,
-    variables: Vec<Type>,
-}
-
-impl<'a> GlobalContext<'a> {
-    pub fn new(primitive_defs: Vec<TypeDef<'a>>) -> GlobalContext {
-        let mut primitives = Vec::new();
-        for (i, t) in primitive_defs.iter().enumerate() {
-            primitives.push(TypeEnum::PrimitiveType(PrimitiveId(i)).into());
-        }
-        GlobalContext {
-            primitive_defs,
-            class_defs: Vec::new(),
-            parametric_defs: Vec::new(),
-            var_defs: Vec::new(),
-            fn_table: HashMap::new(),
-            primitives,
-            variables: Vec::new(),
-        }
-    }
-
-    pub fn add_class(&mut self, def: ClassDef<'a>) -> ClassId {
-        self.class_defs.push(def);
-        ClassId(self.class_defs.len() - 1)
-    }
-
-    pub fn add_parametric(&mut self, def: ParametricDef<'a>) -> ParamId {
-        self.parametric_defs.push(def);
-        ParamId(self.parametric_defs.len() - 1)
-    }
-
-    pub fn add_variable(&mut self, def: VarDef<'a>) -> VariableId {
-        self.add_variable_private(def)
-    }
-
-    pub fn add_variable_private(&mut self, def: VarDef<'a>) -> VariableId {
-        self.var_defs.push(def);
-        self.variables
-            .push(TypeEnum::TypeVariable(VariableId(self.var_defs.len() - 1)).into());
-        VariableId(self.var_defs.len() - 1)
-    }
-
-    pub fn add_fn(&mut self, name: &'a str, def: FnDef) {
-        self.fn_table.insert(name, def);
-    }
-
-    pub fn get_fn_def(&self, name: &str) -> Option<&FnDef> {
-        self.fn_table.get(name)
-    }
-
-    pub fn get_primitive_def_mut(&mut self, id: PrimitiveId) -> &mut TypeDef<'a> {
-        self.primitive_defs.get_mut(id.0).unwrap()
-    }
-
-    pub fn get_primitive_def(&self, id: PrimitiveId) -> &TypeDef {
-        self.primitive_defs.get(id.0).unwrap()
-    }
-
-    pub fn get_class_def_mut(&mut self, id: ClassId) -> &mut ClassDef<'a> {
-        self.class_defs.get_mut(id.0).unwrap()
-    }
-
-    pub fn get_class_def(&self, id: ClassId) -> &ClassDef {
-        self.class_defs.get(id.0).unwrap()
-    }
-
-    pub fn get_parametric_def_mut(&mut self, id: ParamId) -> &mut ParametricDef<'a> {
-        self.parametric_defs.get_mut(id.0).unwrap()
-    }
-
-    pub fn get_parametric_def(&self, id: ParamId) -> &ParametricDef {
-        self.parametric_defs.get(id.0).unwrap()
-    }
-
-    pub fn get_variable_def_mut(&mut self, id: VariableId) -> &mut VarDef<'a> {
-        self.var_defs.get_mut(id.0).unwrap()
-    }
-
-    pub fn get_variable_def(&self, id: VariableId) -> &VarDef {
-        self.var_defs.get(id.0).unwrap()
-    }
-
-    pub fn get_primitive(&self, id: PrimitiveId) -> Type {
-        self.primitives.get(id.0).unwrap().clone()
-    }
-
-    pub fn get_variable(&self, id: VariableId) -> Type {
-        self.variables.get(id.0).unwrap().clone()
-    }
-}

nac3core/src/typecheck/context/inference_context.rs

@@ -1,216 +0,0 @@
-use super::super::location::{FileID, Location};
-use super::super::symbol_resolver::*;
-use super::super::typedef::*;
-use super::GlobalContext;
-use rustpython_parser::ast;
-use std::boxed::Box;
-use std::collections::HashMap;
-
-pub struct ContextStack {
-    /// stack level, starts from 0
-    level: u32,
-    /// stack of symbol definitions containing (name, level) where `level` is the smallest level
-    /// where the name is assigned a value
-    sym_def: Vec<(String, u32)>,
-}
-
-pub struct InferenceContext<'a> {
-    /// global context
-    global: GlobalContext<'a>,
-    /// per source symbol resolver
-    resolver: Box<dyn SymbolResolver>,
-    /// File ID
-    file: FileID,
-
-    /// identifier to (type, readable, location) mapping.
-    /// an identifier might be defined earlier but has no value (for some code path), thus not
-    /// readable.
-    sym_table: HashMap<String, (Type, bool, Location)>,
-    /// stack
-    stack: ContextStack,
-}
-
-// non-trivial implementations here
-impl<'a> InferenceContext<'a> {
-    pub fn new(
-        global: GlobalContext,
-        resolver: Box<dyn SymbolResolver>,
-        file: FileID,
-    ) -> InferenceContext {
-        InferenceContext {
-            global,
-            resolver,
-            file,
-            sym_table: HashMap::new(),
-            stack: ContextStack {
-                level: 0,
-                sym_def: Vec::new(),
-            },
-        }
-    }
-
-    /// execute the function with new scope.
-    /// variable assignment would be limited within the scope (not readable outside), and type
-    /// returns the list of variables assigned within the scope, and the result of the function
-    pub fn with_scope<F, R>(&mut self, f: F) -> (Vec<(String, Type, Location)>, R)
-    where
-        F: FnOnce(&mut Self) -> R,
-    {
-        self.start_scope();
-        let result = f(self);
-        let poped_names = self.end_scope();
-        (poped_names, result)
-    }
-
-    pub fn start_scope(&mut self) {
-        self.stack.level += 1;
-    }
-
-    pub fn end_scope(&mut self) -> Vec<(String, Type, Location)> {
-        self.stack.level -= 1;
-        let mut poped_names = Vec::new();
-        while !self.stack.sym_def.is_empty() {
-            let (_, level) = self.stack.sym_def.last().unwrap();
-            if *level > self.stack.level {
-                let (name, _) = self.stack.sym_def.pop().unwrap();
-                let (t, b, l) = self.sym_table.get_mut(&name).unwrap();
-                // set it to be unreadable
-                *b = false;
-                poped_names.push((name, t.clone(), *l));
-            } else {
-                break;
-            }
-        }
-        poped_names
-    }
-
-    /// assign a type to an identifier.
-    /// may return error if the identifier was defined but with different type
-    pub fn assign(&mut self, name: String, ty: Type, loc: ast::Location) -> Result<Type, String> {
-        if let Some((t, x, _)) = self.sym_table.get_mut(&name) {
-            if t == &ty {
-                if !*x {
-                    self.stack.sym_def.push((name, self.stack.level));
-                }
-                *x = true;
-                Ok(ty)
-            } else {
-                Err("different types".into())
-            }
-        } else {
-            self.stack.sym_def.push((name.clone(), self.stack.level));
-            self.sym_table.insert(
-                name,
-                (ty.clone(), true, Location::CodeRange(self.file, loc)),
-            );
-            Ok(ty)
-        }
-    }
-
-    /// get the type of an identifier
-    /// may return error if the identifier is not defined, and cannot be resolved with the
-    /// resolution function.
-    pub fn resolve(&self, name: &str) -> Result<Type, String> {
-        if let Some((t, x, _)) = self.sym_table.get(name) {
-            if *x {
-                Ok(t.clone())
-            } else {
-                Err("may not be defined".into())
-            }
-        } else {
-            match self.resolver.get_symbol_type(name) {
-                Some(SymbolType::Identifier(t)) => Ok(t),
-                Some(SymbolType::TypeName(_)) => Err("is not a value".into()),
-                _ => Err("unbounded identifier".into()),
-            }
-        }
-    }
-
-    pub fn get_location(&self, name: &str) -> Option<Location> {
-        if let Some((_, _, l)) = self.sym_table.get(name) {
-            Some(*l)
-        } else {
-            self.resolver.get_symbol_location(name)
-        }
-    }
-
-    /// check if an identifier is already defined
-    pub fn defined(&self, name: &String) -> bool {
-        self.sym_table.get(name).is_some()
-    }
-}
-
-// trivial getters:
-impl<'a> InferenceContext<'a> {
-    pub fn get_primitive(&self, id: PrimitiveId) -> Type {
-        TypeEnum::PrimitiveType(id).into()
-    }
-
-    pub fn get_variable(&self, id: VariableId) -> Type {
-        TypeEnum::TypeVariable(id).into()
-    }
-
-    pub fn get_fn_def(&self, name: &str) -> Option<&FnDef> {
-        self.global.fn_table.get(name)
-    }
-    pub fn get_primitive_def(&self, id: PrimitiveId) -> &TypeDef {
-        self.global.primitive_defs.get(id.0).unwrap()
-    }
-    pub fn get_class_def(&self, id: ClassId) -> &ClassDef {
-        self.global.class_defs.get(id.0).unwrap()
-    }
-    pub fn get_parametric_def(&self, id: ParamId) -> &ParametricDef {
-        self.global.parametric_defs.get(id.0).unwrap()
-    }
-    pub fn get_variable_def(&self, id: VariableId) -> &VarDef {
-        self.global.var_defs.get(id.0).unwrap()
-    }
-    pub fn get_type(&self, name: &str) -> Result<Type, String> {
-        match self.resolver.get_symbol_type(name) {
-            Some(SymbolType::TypeName(t)) => Ok(t),
-            Some(SymbolType::Identifier(_)) => Err("not a type".into()),
-            _ => Err("unbounded identifier".into()),
-        }
-    }
-}
-
-impl TypeEnum {
-    pub fn subst(&self, map: &HashMap<VariableId, Type>) -> TypeEnum {
-        match self {
-            TypeEnum::TypeVariable(id) => map.get(id).map(|v| v.as_ref()).unwrap_or(self).clone(),
-            TypeEnum::ParametricType(id, params) => TypeEnum::ParametricType(
-                *id,
-                params
-                    .iter()
-                    .map(|v| v.as_ref().subst(map).into())
-                    .collect(),
-            ),
-            _ => self.clone(),
-        }
-    }
-
-    pub fn get_subst(&self, ctx: &InferenceContext) -> HashMap<VariableId, Type> {
-        match self {
-            TypeEnum::ParametricType(id, params) => {
-                let vars = &ctx.get_parametric_def(*id).params;
-                vars.iter()
-                    .zip(params)
-                    .map(|(v, p)| (*v, p.as_ref().clone().into()))
-                    .collect()
-            }
-            // if this proves to be slow, we can use option type
-            _ => HashMap::new(),
-        }
-    }
-
-    pub fn get_base<'b: 'a, 'a>(&'a self, ctx: &'b InferenceContext) -> Option<&'b TypeDef> {
-        match self {
-            TypeEnum::PrimitiveType(id) => Some(ctx.get_primitive_def(*id)),
-            TypeEnum::ClassType(id) | TypeEnum::VirtualClassType(id) => {
-                Some(&ctx.get_class_def(*id).base)
-            }
-            TypeEnum::ParametricType(id, _) => Some(&ctx.get_parametric_def(*id).base),
-            _ => None,
-        }
-    }
-}

nac3core/src/typecheck/context/mod.rs

@@ -1,4 +0,0 @@
-mod inference_context;
-mod global_context;
-pub use inference_context::InferenceContext;
-pub use global_context::GlobalContext;

nac3core/src/typecheck/function_check.rs

@@ -0,0 +1,306 @@
+use crate::typecheck::typedef::TypeEnum;
+
+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<(), String> {
+        if matches!(expr.custom, Some(ty) if self.unifier.unioned(ty, self.primitives.none)) {
+            Err(format!("Error at {}: cannot have value none", expr.location))
+        } else {
+            Ok(())
+        }
+    }
+
+    fn check_pattern(
+        &mut self,
+        pattern: &Expr<Option<Type>>,
+        defined_identifiers: &mut HashSet<StrRef>,
+    ) -> Result<(), String> {
+        match &pattern.node {
+            ast::ExprKind::Name { id, .. } if id == &"none".into() =>
+                Err(format!("cannot assign to a `none` (at {})", pattern.location)),
+            ExprKind::Name { id, .. } => {
+                if !defined_identifiers.contains(id) {
+                    defined_identifiers.insert(*id);
+                }
+                self.should_have_value(pattern)?;
+                Ok(())
+            }
+            ExprKind::Tuple { elts, .. } => {
+                for elt in elts.iter() {
+                    self.check_pattern(elt, defined_identifiers)?;
+                    self.should_have_value(elt)?;
+                }
+                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(format!(
+                        "Error at {}: cannot assign to tuple element",
+                        value.location
+                    ));
+                }
+                Ok(())
+            }
+            ExprKind::Constant { .. } => {
+                Err(format!("cannot assign to a constant (at {})", pattern.location))
+            }
+            _ => self.check_expr(pattern, defined_identifiers),
+        }
+    }
+
+    fn check_expr(
+        &mut self,
+        expr: &Expr<Option<Type>>,
+        defined_identifiers: &mut HashSet<StrRef>,
+    ) -> Result<(), String> {
+        // there are some cases where the custom field is None
+        if let Some(ty) = &expr.custom {
+            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(id) {
+                    match self.function_data.resolver.get_symbol_type(
+                        self.unifier,
+                        &self.top_level.definitions.read(),
+                        self.primitives,
+                        *id,
+                    ) {
+                        Ok(_) => {
+                            self.defined_identifiers.insert(*id);
+                        }
+                        Err(e) => {
+                            return Err(format!(
+                                "type error at identifier `{}` ({}) at {}",
+                                id, e, expr.location
+                            ));
+                        }
+                    }
+                }
+            }
+            ExprKind::List { elts, .. }
+            | ExprKind::Tuple { elts, .. }
+            | ExprKind::BoolOp { values: elts, .. } => {
+                for elt in elts.iter() {
+                    self.check_expr(elt, defined_identifiers)?;
+                    self.should_have_value(elt)?;
+                }
+            }
+            ExprKind::Attribute { value, .. } => {
+                self.check_expr(value, defined_identifiers)?;
+                self.should_have_value(value)?;
+            }
+            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)?;
+            }
+            ExprKind::UnaryOp { operand, .. } => {
+                self.check_expr(operand, defined_identifiers)?;
+                self.should_have_value(operand)?;
+            }
+            ExprKind::Compare { left, comparators, .. } => {
+                for elt in once(left.as_ref()).chain(comparators.iter()) {
+                    self.check_expr(elt, defined_identifiers)?;
+                    self.should_have_value(elt)?;
+                }
+            }
+            ExprKind::Subscript { value, slice, .. } => {
+                self.should_have_value(value)?;
+                self.check_expr(value, defined_identifiers)?;
+                self.check_expr(slice, defined_identifiers)?;
+            }
+            ExprKind::IfExp { test, body, orelse } => {
+                self.check_expr(test, defined_identifiers)?;
+                self.check_expr(body, defined_identifiers)?;
+                self.check_expr(orelse, defined_identifiers)?;
+            }
+            ExprKind::Slice { lower, upper, step } => {
+                for elt in [lower.as_ref(), upper.as_ref(), step.as_ref()].iter().flatten() {
+                    self.should_have_value(elt)?;
+                    self.check_expr(elt, defined_identifiers)?;
+                }
+            }
+            ExprKind::Lambda { args, body } => {
+                let mut defined_identifiers = defined_identifiers.clone();
+                for arg in args.args.iter() {
+                    // TODO: should we check the types here?
+                    if !defined_identifiers.contains(&arg.node.arg) {
+                        defined_identifiers.insert(arg.node.arg);
+                    }
+                }
+                self.check_expr(body, &mut defined_identifiers)?;
+            }
+            ExprKind::ListComp { elt, generators, .. } => {
+                // in our type inference stage, we already make sure that there is only 1 generator
+                let ast::Comprehension { target, iter, ifs, .. } = &generators[0];
+                self.check_expr(iter, defined_identifiers)?;
+                self.should_have_value(iter)?;
+                let mut defined_identifiers = defined_identifiers.clone();
+                self.check_pattern(target, &mut defined_identifiers)?;
+                self.should_have_value(target)?;
+                for term in once(elt.as_ref()).chain(ifs.iter()) {
+                    self.check_expr(term, &mut defined_identifiers)?;
+                    self.should_have_value(term)?;
+                }
+            }
+            ExprKind::Call { func, args, keywords } => {
+                for expr in once(func.as_ref())
+                    .chain(args.iter())
+                    .chain(keywords.iter().map(|v| v.node.value.as_ref()))
+                {
+                    self.check_expr(expr, defined_identifiers)?;
+                    self.should_have_value(expr)?;
+                }
+            }
+            ExprKind::Constant { .. } => {}
+            _ => {
+                unimplemented!()
+            }
+        }
+        Ok(())
+    }
+
+    // check statements for proper identifier def-use and return on all paths
+    fn check_stmt(
+        &mut self,
+        stmt: &Stmt<Option<Type>>,
+        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.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.iter() {
+                    self.check_stmt(stmt, &mut local_defined_identifiers)?;
+                }
+                Ok(false)
+            }
+            StmtKind::If { test, body, orelse, .. } => {
+                self.check_expr(test, defined_identifiers)?;
+                self.should_have_value(test)?;
+                let mut body_identifiers = defined_identifiers.clone();
+                let mut orelse_identifiers = defined_identifiers.clone();
+                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.iter() {
+                    if !defined_identifiers.contains(ident) && orelse_identifiers.contains(ident) {
+                        defined_identifiers.insert(*ident);
+                    }
+                }
+                Ok(body_returned && orelse_returned)
+            }
+            StmtKind::While { test, body, orelse, .. } => {
+                self.check_expr(test, defined_identifiers)?;
+                self.should_have_value(test)?;
+                let mut defined_identifiers = defined_identifiers.clone();
+                self.check_block(body, &mut defined_identifiers)?;
+                self.check_block(orelse, &mut defined_identifiers)?;
+                Ok(false)
+            }
+            StmtKind::With { items, body, .. } => {
+                let mut new_defined_identifiers = defined_identifiers.clone();
+                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)?;
+                    }
+                }
+                self.check_block(body, &mut new_defined_identifiers)?;
+                Ok(false)
+            }
+            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.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);
+                    }
+                    self.check_block(body, &mut defined_identifiers)?;
+                }
+                self.check_block(finalbody, defined_identifiers)?;
+                Ok(false)
+            }
+            StmtKind::Expr { value, .. } => {
+                self.check_expr(value, defined_identifiers)?;
+                Ok(false)
+            }
+            StmtKind::Assign { targets, value, .. } => {
+                self.check_expr(value, defined_identifiers)?;
+                self.should_have_value(value)?;
+                for target in targets {
+                    self.check_pattern(target, defined_identifiers)?;
+                }
+                Ok(false)
+            }
+            StmtKind::AnnAssign { target, value, .. } => {
+                if let Some(value) = value {
+                    self.check_expr(value, defined_identifiers)?;
+                    self.should_have_value(value)?;
+                    self.check_pattern(target, defined_identifiers)?;
+                }
+                Ok(false)
+            }
+            StmtKind::Return { value, .. } => {
+                if let Some(value) = value {
+                    self.check_expr(value, defined_identifiers)?;
+                    self.should_have_value(value)?;
+                }
+                Ok(true)
+            }
+            StmtKind::Raise { exc, .. } => {
+                if let Some(value) = exc {
+                    self.check_expr(value, defined_identifiers)?;
+                }
+                Ok(true)
+            }
+            // break, raise, etc.
+            _ => Ok(false),
+        }
+    }
+
+    pub fn check_block(
+        &mut self,
+        block: &[Stmt<Option<Type>>],
+        defined_identifiers: &mut HashSet<StrRef>,
+    ) -> Result<bool, String> {
+        let mut ret = false;
+        for stmt in block {
+            if ret {
+                return Err(format!("dead code at {:?}", stmt.location));
+            }
+            if self.check_stmt(stmt, defined_identifiers)? {
+                ret = true;
+            }
+        }
+        Ok(ret)
+    }
+}

nac3core/src/typecheck/inference_core.rs

@@ -1,526 +0,0 @@
-use super::context::InferenceContext;
-use super::typedef::{TypeEnum::*, *};
-use std::collections::HashMap;
-
-fn find_subst(
-    ctx: &InferenceContext,
-    valuation: &Option<(VariableId, Type)>,
-    sub: &mut HashMap<VariableId, Type>,
-    mut a: Type,
-    mut b: Type,
-) -> Result<(), String> {
-    // TODO: fix error messages later
-    if let TypeVariable(id) = a.as_ref() {
-        if let Some((assumption_id, t)) = valuation {
-            if assumption_id == id {
-                a = t.clone();
-            }
-        }
-    }
-
-    let mut substituted = false;
-    if let TypeVariable(id) = b.as_ref() {
-        if let Some(c) = sub.get(&id) {
-            b = c.clone();
-            substituted = true;
-        }
-    }
-
-    match (a.as_ref(), b.as_ref()) {
-        (BotType, _) => Ok(()),
-        (TypeVariable(id_a), TypeVariable(id_b)) => {
-            if substituted {
-                return if id_a == id_b {
-                    Ok(())
-                } else {
-                    Err("different variables".to_string())
-                };
-            }
-            let v_a = ctx.get_variable_def(*id_a);
-            let v_b = ctx.get_variable_def(*id_b);
-            if !v_b.bound.is_empty() {
-                if v_a.bound.is_empty() {
-                    return Err("unbounded a".to_string());
-                } else {
-                    let diff: Vec<_> = v_a
-                        .bound
-                        .iter()
-                        .filter(|x| !v_b.bound.contains(x))
-                        .collect();
-                    if !diff.is_empty() {
-                        return Err("different domain".to_string());
-                    }
-                }
-            }
-            sub.insert(*id_b, a.clone());
-            Ok(())
-        }
-        (TypeVariable(id_a), _) => {
-            let v_a = ctx.get_variable_def(*id_a);
-            if v_a.bound.len() == 1 && v_a.bound[0].as_ref() == b.as_ref() {
-                Ok(())
-            } else {
-                Err("different domain".to_string())
-            }
-        }
-        (_, TypeVariable(id_b)) => {
-            let v_b = ctx.get_variable_def(*id_b);
-            if v_b.bound.is_empty() || v_b.bound.contains(&a) {
-                sub.insert(*id_b, a.clone());
-                Ok(())
-            } else {
-                Err("different domain".to_string())
-            }
-        }
-        (_, VirtualClassType(id_b)) => {
-            let mut parents;
-            match a.as_ref() {
-                ClassType(id_a) => {
-                    parents = [*id_a].to_vec();
-                }
-                VirtualClassType(id_a) => {
-                    parents = [*id_a].to_vec();
-                }
-                _ => {
-                    return Err("cannot substitute non-class type into virtual class".to_string());
-                }
-            };
-            while !parents.is_empty() {
-                if *id_b == parents[0] {
-                    return Ok(());
-                }
-                let c = ctx.get_class_def(parents.remove(0));
-                parents.extend_from_slice(&c.parents);
-            }
-            Err("not subtype".to_string())
-        }
-        (ParametricType(id_a, param_a), ParametricType(id_b, param_b)) => {
-            if id_a != id_b || param_a.len() != param_b.len() {
-                Err("different parametric types".to_string())
-            } else {
-                for (x, y) in param_a.iter().zip(param_b.iter()) {
-                    find_subst(ctx, valuation, sub, x.clone(), y.clone())?;
-                }
-                Ok(())
-            }
-        }
-        (_, _) => {
-            if a == b {
-                Ok(())
-            } else {
-                Err("not equal".to_string())
-            }
-        }
-    }
-}
-
-fn resolve_call_rec(
-    ctx: &InferenceContext,
-    valuation: &Option<(VariableId, Type)>,
-    obj: Option<Type>,
-    func: &str,
-    args: &[Type],
-) -> Result<Option<Type>, String> {
-    let mut subst = obj
-        .as_ref()
-        .map(|v| v.get_subst(ctx))
-        .unwrap_or_else(HashMap::new);
-
-    let fun = match &obj {
-        Some(obj) => {
-            let base = match obj.as_ref() {
-                PrimitiveType(id) => &ctx.get_primitive_def(*id),
-                ClassType(id) | VirtualClassType(id) => &ctx.get_class_def(*id).base,
-                ParametricType(id, _) => &ctx.get_parametric_def(*id).base,
-                _ => return Err("not supported".to_string()),
-            };
-            base.methods.get(func)
-        }
-        None => ctx.get_fn_def(func),
-    }
-    .ok_or_else(|| "no such function".to_string())?;
-
-    if args.len() != fun.args.len() {
-        return Err("incorrect parameter number".to_string());
-    }
-    for (a, b) in args.iter().zip(fun.args.iter()) {
-        find_subst(ctx, valuation, &mut subst, a.clone(), b.clone())?;
-    }
-    let result = fun.result.as_ref().map(|v| v.subst(&subst));
-    Ok(result.map(|result| {
-        if let SelfType = result {
-            obj.unwrap()
-        } else {
-            result.into()
-        }
-    }))
-}
-
-pub fn resolve_call(
-    ctx: &InferenceContext,
-    obj: Option<Type>,
-    func: &str,
-    args: &[Type],
-) -> Result<Option<Type>, String> {
-    resolve_call_rec(ctx, &None, obj, func, args)
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use super::super::context::GlobalContext;
-    use super::super::primitives::*;
-    use std::rc::Rc;
-
-    fn get_inference_context(ctx: GlobalContext) -> InferenceContext {
-        // InferenceContext::new(ctx, Box::new(|_| Err("unbounded identifier".into())))
-        crate::typecheck::type_check::test::new_ctx().ctx
-    }
-
-    #[test]
-    fn test_simple_generic() {
-        let mut ctx = basic_ctx();
-        let v1 = ctx.add_variable(VarDef {
-            name: "V1",
-            bound: vec![ctx.get_primitive(INT32_TYPE), ctx.get_primitive(FLOAT_TYPE)],
-        });
-        let v1 = ctx.get_variable(v1);
-        let v2 = ctx.add_variable(VarDef {
-            name: "V2",
-            bound: vec![
-                ctx.get_primitive(BOOL_TYPE),
-                ctx.get_primitive(INT32_TYPE),
-                ctx.get_primitive(FLOAT_TYPE),
-            ],
-        });
-        let v2 = ctx.get_variable(v2);
-        let ctx = get_inference_context(ctx);
-
-        assert_eq!(
-            resolve_call(&ctx, None, "int32", &[ctx.get_primitive(FLOAT_TYPE)]),
-            Ok(Some(ctx.get_primitive(INT32_TYPE)))
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "int32", &[ctx.get_primitive(INT32_TYPE)],),
-            Ok(Some(ctx.get_primitive(INT32_TYPE)))
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "float", &[ctx.get_primitive(INT32_TYPE)]),
-            Ok(Some(ctx.get_primitive(FLOAT_TYPE)))
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "float", &[ctx.get_primitive(BOOL_TYPE)]),
-            Err("different domain".to_string())
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "float", &[]),
-            Err("incorrect parameter number".to_string())
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "float", &[v1]),
-            Ok(Some(ctx.get_primitive(FLOAT_TYPE)))
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "float", &[v2]),
-            Err("different domain".to_string())
-        );
-    }
-
-    #[test]
-    fn test_methods() {
-        let mut ctx = basic_ctx();
-
-        let v0 = ctx.add_variable(VarDef {
-            name: "V0",
-            bound: vec![],
-        });
-        let v0 = ctx.get_variable(v0);
-
-        let int32 = ctx.get_primitive(INT32_TYPE);
-        let int64 = ctx.get_primitive(INT64_TYPE);
-        let ctx = get_inference_context(ctx);
-
-        // simple cases
-        assert_eq!(
-            resolve_call(&ctx, Some(int32.clone()), "__add__", &[int32.clone()]),
-            Ok(Some(int32.clone()))
-        );
-
-        assert_ne!(
-            resolve_call(&ctx, Some(int32.clone()), "__add__", &[int32.clone()]),
-            Ok(Some(int64.clone()))
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, Some(int32), "__add__", &[int64]),
-            Err("not equal".to_string())
-        );
-
-        // with type variables
-        assert_eq!(
-            resolve_call(&ctx, Some(v0.clone()), "__add__", &[v0.clone()]),
-            Err("not supported".into())
-        );
-    }
-
-    #[test]
-    fn test_multi_generic() {
-        let mut ctx = basic_ctx();
-        let v0 = ctx.add_variable(VarDef {
-            name: "V0",
-            bound: vec![],
-        });
-        let v0 = ctx.get_variable(v0);
-        let v1 = ctx.add_variable(VarDef {
-            name: "V1",
-            bound: vec![],
-        });
-        let v1 = ctx.get_variable(v1);
-        let v2 = ctx.add_variable(VarDef {
-            name: "V2",
-            bound: vec![],
-        });
-        let v2 = ctx.get_variable(v2);
-        let v3 = ctx.add_variable(VarDef {
-            name: "V3",
-            bound: vec![],
-        });
-        let v3 = ctx.get_variable(v3);
-
-        ctx.add_fn(
-            "foo",
-            FnDef {
-                args: vec![v0.clone(), v0.clone(), v1.clone()],
-                result: Some(v0.clone()),
-            },
-        );
-
-        ctx.add_fn(
-            "foo1",
-            FnDef {
-                args: vec![ParametricType(TUPLE_TYPE, vec![v0.clone(), v0.clone(), v1]).into()],
-                result: Some(v0),
-            },
-        );
-        let ctx = get_inference_context(ctx);
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[v2.clone(), v2.clone(), v2.clone()]),
-            Ok(Some(v2.clone()))
-        );
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[v2.clone(), v2.clone(), v3.clone()]),
-            Ok(Some(v2.clone()))
-        );
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[v2.clone(), v3.clone(), v3.clone()]),
-            Err("different variables".to_string())
-        );
-
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                None,
-                "foo1",
-                &[ParametricType(TUPLE_TYPE, vec![v2.clone(), v2.clone(), v2.clone()]).into()]
-            ),
-            Ok(Some(v2.clone()))
-        );
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                None,
-                "foo1",
-                &[ParametricType(TUPLE_TYPE, vec![v2.clone(), v2.clone(), v3.clone()]).into()]
-            ),
-            Ok(Some(v2.clone()))
-        );
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                None,
-                "foo1",
-                &[ParametricType(TUPLE_TYPE, vec![v2, v3.clone(), v3]).into()]
-            ),
-            Err("different variables".to_string())
-        );
-    }
-
-    #[test]
-    fn test_class_generics() {
-        let mut ctx = basic_ctx();
-
-        let list = ctx.get_parametric_def_mut(LIST_TYPE);
-        let t = Rc::new(TypeVariable(list.params[0]));
-        list.base.methods.insert(
-            "head",
-            FnDef {
-                args: vec![],
-                result: Some(t.clone()),
-            },
-        );
-        list.base.methods.insert(
-            "append",
-            FnDef {
-                args: vec![t],
-                result: None,
-            },
-        );
-
-        let v0 = ctx.add_variable(VarDef {
-            name: "V0",
-            bound: vec![],
-        });
-        let v0 = ctx.get_variable(v0);
-        let v1 = ctx.add_variable(VarDef {
-            name: "V1",
-            bound: vec![],
-        });
-        let v1 = ctx.get_variable(v1);
-        let ctx = get_inference_context(ctx);
-
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                Some(ParametricType(LIST_TYPE, vec![v0.clone()]).into()),
-                "head",
-                &[]
-            ),
-            Ok(Some(v0.clone()))
-        );
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                Some(ParametricType(LIST_TYPE, vec![v0.clone()]).into()),
-                "append",
-                &[v0.clone()]
-            ),
-            Ok(None)
-        );
-        assert_eq!(
-            resolve_call(
-                &ctx,
-                Some(ParametricType(LIST_TYPE, vec![v0]).into()),
-                "append",
-                &[v1]
-            ),
-            Err("different variables".to_string())
-        );
-    }
-
-    #[test]
-    fn test_virtual_class() {
-        let mut ctx = basic_ctx();
-
-        let foo = ctx.add_class(ClassDef {
-            base: TypeDef {
-                name: "Foo",
-                methods: HashMap::new(),
-                fields: HashMap::new(),
-            },
-            parents: vec![],
-        });
-
-        let foo1 = ctx.add_class(ClassDef {
-            base: TypeDef {
-                name: "Foo1",
-                methods: HashMap::new(),
-                fields: HashMap::new(),
-            },
-            parents: vec![foo],
-        });
-
-        let foo2 = ctx.add_class(ClassDef {
-            base: TypeDef {
-                name: "Foo2",
-                methods: HashMap::new(),
-                fields: HashMap::new(),
-            },
-            parents: vec![foo1],
-        });
-
-        let bar = ctx.add_class(ClassDef {
-            base: TypeDef {
-                name: "bar",
-                methods: HashMap::new(),
-                fields: HashMap::new(),
-            },
-            parents: vec![],
-        });
-
-        ctx.add_fn(
-            "foo",
-            FnDef {
-                args: vec![VirtualClassType(foo).into()],
-                result: None,
-            },
-        );
-        ctx.add_fn(
-            "foo1",
-            FnDef {
-                args: vec![VirtualClassType(foo1).into()],
-                result: None,
-            },
-        );
-        let ctx = get_inference_context(ctx);
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[ClassType(foo).into()]),
-            Ok(None)
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[ClassType(foo1).into()]),
-            Ok(None)
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[ClassType(foo2).into()]),
-            Ok(None)
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[ClassType(bar).into()]),
-            Err("not subtype".to_string())
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo1", &[ClassType(foo1).into()]),
-            Ok(None)
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo1", &[ClassType(foo2).into()]),
-            Ok(None)
-        );
-
-        assert_eq!(
-            resolve_call(&ctx, None, "foo1", &[ClassType(foo).into()]),
-            Err("not subtype".to_string())
-        );
-
-        // virtual class substitution
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[VirtualClassType(foo).into()]),
-            Ok(None)
-        );
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[VirtualClassType(foo1).into()]),
-            Ok(None)
-        );
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[VirtualClassType(foo2).into()]),
-            Ok(None)
-        );
-        assert_eq!(
-            resolve_call(&ctx, None, "foo", &[VirtualClassType(bar).into()]),
-            Err("not subtype".to_string())
-        );
-    }
-}

nac3core/src/typecheck/location.rs

@@ -1,31 +0,0 @@
-use rustpython_parser::ast;
-use std::vec::Vec;
-
-#[derive(Clone, Copy, PartialEq)]
-pub struct FileID(pub u32);
-
-#[derive(Clone, Copy, PartialEq)]
-pub enum Location {
-    CodeRange(FileID, ast::Location),
-    Builtin
-}
-
-pub struct FileRegistry {
-    files: Vec<String>,
-}
-
-impl FileRegistry {
-    pub fn new() -> FileRegistry {
-        FileRegistry { files: Vec::new() }
-    }
-
-    pub fn add_file(&mut self, path: &str) -> FileID {
-        let index = self.files.len() as u32;
-        self.files.push(path.to_owned());
-        FileID(index)
-    }
-
-    pub fn query_file(&self, id: FileID) -> &str {
-        &self.files[id.0 as usize]
-    }
-}

nac3core/src/typecheck/magic_methods.rs

@@ -1,4 +1,11 @@
-use rustpython_parser::ast::{Cmpop, Operator, Unaryop};
+use crate::typecheck::{
+    type_inferencer::*,
+    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;
 
 pub fn binop_name(op: &Operator) -> &'static str {
     match op {
@@ -38,21 +45,286 @@ pub fn binop_assign_name(op: &Operator) -> &'static str {
 
 pub fn unaryop_name(op: &Unaryop) -> &'static str {
     match op {
-        Unaryop::UAdd   => "__pos__",
-        Unaryop::USub   => "__neg__",
-        Unaryop::Not    => "__not__",
+        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::Lt => Some("__lt__"),
+        Cmpop::LtE => Some("__le__"),
+        Cmpop::Gt => Some("__gt__"),
+        Cmpop::GtE => Some("__ge__"),
+        Cmpop::Eq => Some("__eq__"),
         Cmpop::NotEq => Some("__ne__"),
         _ => None,
     }
 }
+
+pub(super) fn with_fields<F>(unifier: &mut Unifier, ty: Type, f: F)
+where
+    F: FnOnce(&mut Unifier, &mut HashMap<StrRef, (Type, bool)>),
+{
+    let (id, mut fields, params) =
+        if let TypeEnum::TObj { obj_id, fields, params } = &*unifier.get_ty(ty) {
+            (*obj_id, fields.clone(), params.clone())
+        } else {
+            unreachable!()
+        };
+    f(unifier, &mut fields);
+    unsafe {
+        let unification_table = unifier.get_unification_table();
+        unification_table.set_value(ty, Rc::new(TypeEnum::TObj { obj_id: id, fields, params }));
+    }
+}
+
+pub fn impl_binop(
+    unifier: &mut Unifier,
+    store: &PrimitiveStore,
+    ty: Type,
+    other_ty: &[Type],
+    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 (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::<HashMap<_, _>>()
+        } else {
+            HashMap::new()
+        };
+        for op in ops {
+            fields.insert(binop_name(op).into(), {
+                (
+                    unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                        ret: ret_ty,
+                        vars: function_vars.clone(),
+                        args: vec![FuncArg {
+                            ty: other_ty,
+                            default_value: None,
+                            name: "other".into(),
+                        }],
+                    })),
+                    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,
+                )
+            });
+        }
+    });
+}
+
+pub fn impl_unaryop(unifier: &mut Unifier, ty: Type, ret_ty: Type, ops: &[ast::Unaryop]) {
+    with_fields(unifier, ty, |unifier, fields| {
+        for op in ops {
+            fields.insert(
+                unaryop_name(op).into(),
+                (
+                    unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                        ret: ret_ty,
+                        vars: HashMap::new(),
+                        args: vec![],
+                    })),
+                    false,
+                ),
+            );
+        }
+    });
+}
+
+pub fn impl_cmpop(
+    unifier: &mut Unifier,
+    store: &PrimitiveStore,
+    ty: Type,
+    other_ty: Type,
+    ops: &[ast::Cmpop],
+) {
+    with_fields(unifier, ty, |unifier, fields| {
+        for op in ops {
+            fields.insert(
+                comparison_name(op).unwrap().into(),
+                (
+                    unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                        ret: store.bool,
+                        vars: HashMap::new(),
+                        args: vec![FuncArg {
+                            ty: other_ty,
+                            default_value: None,
+                            name: "other".into(),
+                        }],
+                    })),
+                    false,
+                ),
+            );
+        }
+    });
+}
+
+/// Add, Sub, Mult
+pub fn impl_basic_arithmetic(
+    unifier: &mut Unifier,
+    store: &PrimitiveStore,
+    ty: Type,
+    other_ty: &[Type],
+    ret_ty: Type,
+) {
+    impl_binop(
+        unifier,
+        store,
+        ty,
+        other_ty,
+        ret_ty,
+        &[ast::Operator::Add, ast::Operator::Sub, ast::Operator::Mult],
+    )
+}
+
+/// Pow
+pub fn impl_pow(
+    unifier: &mut Unifier,
+    store: &PrimitiveStore,
+    ty: Type,
+    other_ty: &[Type],
+    ret_ty: Type,
+) {
+    impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::Pow])
+}
+
+/// BitOr, BitXor, BitAnd
+pub fn impl_bitwise_arithmetic(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
+    impl_binop(
+        unifier,
+        store,
+        ty,
+        &[ty],
+        ty,
+        &[ast::Operator::BitAnd, ast::Operator::BitOr, ast::Operator::BitXor],
+    )
+}
+
+/// 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])
+}
+
+/// 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: Type,
+) {
+    impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::FloorDiv])
+}
+
+/// Mod
+pub fn impl_mod(
+    unifier: &mut Unifier,
+    store: &PrimitiveStore,
+    ty: Type,
+    other_ty: &[Type],
+    ret_ty: Type,
+) {
+    impl_binop(unifier, store, ty, other_ty, ret_ty, &[ast::Operator::Mod])
+}
+
+/// UAdd, USub
+pub fn impl_sign(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type) {
+    impl_unaryop(unifier, ty, ty, &[ast::Unaryop::UAdd, ast::Unaryop::USub])
+}
+
+/// Invert
+pub fn impl_invert(unifier: &mut Unifier, _store: &PrimitiveStore, ty: Type) {
+    impl_unaryop(unifier, ty, ty, &[ast::Unaryop::Invert])
+}
+
+/// Not
+pub fn impl_not(unifier: &mut Unifier, store: &PrimitiveStore, ty: Type) {
+    impl_unaryop(unifier, ty, store.bool, &[ast::Unaryop::Not])
+}
+
+/// 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,
+        &[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) {
+    impl_cmpop(unifier, store, ty, ty, &[ast::Cmpop::Eq, ast::Cmpop::NotEq])
+}
+
+pub fn set_primitives_magic_methods(store: &PrimitiveStore, unifier: &mut Unifier) {
+    let PrimitiveStore {
+        int32: int32_t,
+        int64: int64_t,
+        float: float_t,
+        bool: bool_t,
+        uint32: uint32_t,
+        uint64: uint64_t,
+        ..
+    } = *store;
+    /* int ======== */
+    for t in [int32_t, int64_t, uint32_t, uint64_t] {
+        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]);
+        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);
+    }
+
+    /* float ======== */
+    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 ======== */
+    impl_not(unifier, store, bool_t);
+    impl_eq(unifier, store, bool_t);
+}

nac3core/src/typecheck/mod.rs

@@ -1,8 +1,6 @@
-pub mod context;
-pub mod inference_core;
-pub mod location;
+mod function_check;
 pub mod magic_methods;
-pub mod primitives;
-pub mod symbol_resolver;
+pub mod type_error;
+pub mod type_inferencer;
 pub mod typedef;
-pub mod type_check;
+mod unification_table;

nac3core/src/typecheck/primitives.rs

@@ -1,184 +0,0 @@
-use super::typedef::{TypeEnum::*, *};
-use super::context::*;
-use std::collections::HashMap;
-
-pub const TUPLE_TYPE: ParamId = ParamId(0);
-pub const LIST_TYPE: ParamId = ParamId(1);
-
-pub const BOOL_TYPE: PrimitiveId = PrimitiveId(0);
-pub const INT32_TYPE: PrimitiveId = PrimitiveId(1);
-pub const INT64_TYPE: PrimitiveId = PrimitiveId(2);
-pub const FLOAT_TYPE: PrimitiveId = PrimitiveId(3);
-
-fn impl_math(def: &mut TypeDef, ty: &Type) {
-    let result = Some(ty.clone());
-    let fun = FnDef {
-        args: vec![ty.clone()],
-        result: result.clone(),
-    };
-    def.methods.insert("__add__", fun.clone());
-    def.methods.insert("__sub__", fun.clone());
-    def.methods.insert("__mul__", fun.clone());
-    def.methods.insert(
-        "__neg__",
-        FnDef {
-            args: vec![],
-            result,
-        },
-    );
-    def.methods.insert(
-        "__truediv__",
-        FnDef {
-            args: vec![ty.clone()],
-            result: Some(PrimitiveType(FLOAT_TYPE).into()),
-        },
-    );
-    def.methods.insert("__floordiv__", fun.clone());
-    def.methods.insert("__mod__", fun.clone());
-    def.methods.insert("__pow__", fun);
-}
-
-fn impl_bits(def: &mut TypeDef, ty: &Type) {
-    let result = Some(ty.clone());
-    let fun = FnDef {
-        args: vec![PrimitiveType(INT32_TYPE).into()],
-        result,
-    };
-
-    def.methods.insert("__lshift__", fun.clone());
-    def.methods.insert("__rshift__", fun);
-    def.methods.insert(
-        "__xor__",
-        FnDef {
-            args: vec![ty.clone()],
-            result: Some(ty.clone()),
-        },
-    );
-}
-
-fn impl_eq(def: &mut TypeDef, ty: &Type) {
-    let fun = FnDef {
-        args: vec![ty.clone()],
-        result: Some(PrimitiveType(BOOL_TYPE).into()),
-    };
-
-    def.methods.insert("__eq__", fun.clone());
-    def.methods.insert("__ne__", fun);
-}
-
-fn impl_order(def: &mut TypeDef, ty: &Type) {
-    let fun = FnDef {
-        args: vec![ty.clone()],
-        result: Some(PrimitiveType(BOOL_TYPE).into()),
-    };
-
-    def.methods.insert("__lt__", fun.clone());
-    def.methods.insert("__gt__", fun.clone());
-    def.methods.insert("__le__", fun.clone());
-    def.methods.insert("__ge__", fun);
-}
-
-pub fn basic_ctx() -> GlobalContext<'static> {
-    let primitives = [
-        TypeDef {
-            name: "bool",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-        TypeDef {
-            name: "int32",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-        TypeDef {
-            name: "int64",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-        TypeDef {
-            name: "float",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-    ]
-    .to_vec();
-    let mut ctx = GlobalContext::new(primitives);
-
-    let b = ctx.get_primitive(BOOL_TYPE);
-    let b_def = ctx.get_primitive_def_mut(BOOL_TYPE);
-    impl_eq(b_def, &b);
-    let int32 = ctx.get_primitive(INT32_TYPE);
-    let int32_def = ctx.get_primitive_def_mut(INT32_TYPE);
-    impl_math(int32_def, &int32);
-    impl_bits(int32_def, &int32);
-    impl_order(int32_def, &int32);
-    impl_eq(int32_def, &int32);
-    let int64 = ctx.get_primitive(INT64_TYPE);
-    let int64_def = ctx.get_primitive_def_mut(INT64_TYPE);
-    impl_math(int64_def, &int64);
-    impl_bits(int64_def, &int64);
-    impl_order(int64_def, &int64);
-    impl_eq(int64_def, &int64);
-    let float = ctx.get_primitive(FLOAT_TYPE);
-    let float_def = ctx.get_primitive_def_mut(FLOAT_TYPE);
-    impl_math(float_def, &float);
-    impl_order(float_def, &float);
-    impl_eq(float_def, &float);
-
-    let t = ctx.add_variable_private(VarDef {
-        name: "T",
-        bound: vec![],
-    });
-
-    ctx.add_parametric(ParametricDef {
-        base: TypeDef {
-            name: "tuple",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-        // we have nothing for tuple, so no param def
-        params: vec![],
-    });
-
-    ctx.add_parametric(ParametricDef {
-        base: TypeDef {
-            name: "list",
-            fields: HashMap::new(),
-            methods: HashMap::new(),
-        },
-        params: vec![t],
-    });
-
-    let i = ctx.add_variable_private(VarDef {
-        name: "I",
-        bound: vec![
-            PrimitiveType(INT32_TYPE).into(),
-            PrimitiveType(INT64_TYPE).into(),
-            PrimitiveType(FLOAT_TYPE).into(),
-        ],
-    });
-    let args = vec![TypeVariable(i).into()];
-    ctx.add_fn(
-        "int32",
-        FnDef {
-            args: args.clone(),
-            result: Some(PrimitiveType(INT32_TYPE).into()),
-        },
-    );
-    ctx.add_fn(
-        "int64",
-        FnDef {
-            args: args.clone(),
-            result: Some(PrimitiveType(INT64_TYPE).into()),
-        },
-    );
-    ctx.add_fn(
-        "float",
-        FnDef {
-            args,
-            result: Some(PrimitiveType(FLOAT_TYPE).into()),
-        },
-    );
-
-    ctx
-}

nac3core/src/typecheck/symbol_resolver.rs

@@ -1,23 +0,0 @@
-use super::typedef::Type;
-use super::location::Location;
-
-pub enum SymbolType {
-    TypeName(Type),
-    Identifier(Type),
-}
-
-pub enum SymbolValue<'a> {
-    I32(i32),
-    I64(i64),
-    Double(f64),
-    Bool(bool),
-    Tuple(&'a [SymbolValue<'a>]),
-    Bytes(&'a [u8]),
-}
-
-pub trait SymbolResolver {
-    fn get_symbol_type(&self, str: &str) -> Option<SymbolType>;
-    fn get_symbol_value(&self, str: &str) -> Option<SymbolValue>;
-    fn get_symbol_location(&self, str: &str) -> Option<Location>;
-    // handle function call etc.
-}

nac3core/src/typecheck/type_check.rs

@@ -1,752 +0,0 @@
-use std::convert::TryInto;
-
-use crate::typecheck::context::InferenceContext;
-use crate::typecheck::inference_core;
-use crate::typecheck::magic_methods;
-use crate::typecheck::typedef::{Type, TypeEnum};
-use crate::typecheck::primitives;
-use rustpython_parser::ast;
-
-struct NaiveFolder;
-impl ast::fold::Fold<()> for NaiveFolder {
-    type TargetU = Option<Type>;
-    type Error = String;
-    fn map_user(&mut self, _user: ()) -> Result<Self::TargetU, Self::Error> {
-        Ok(None)
-    }
-}
-
-pub struct TypeInferencer<'a> {
-    pub ctx: InferenceContext<'a>,
-    pub error_stack: Vec<(String, ast::Location)>
-}
-
-impl<'a> ast::fold::Fold<()> for TypeInferencer<'a> {
-    type TargetU = Option<Type>;
-    type Error = String;
-
-    fn map_user(&mut self, _user: ()) -> Result<Self::TargetU, Self::Error> {
-        Ok(None)
-    }
-
-    fn fold_expr(&mut self, node: ast::Expr<()>) -> Result<ast::Expr<Self::TargetU>, Self::Error> {
-        
-        self.error_stack.push(("Checking ".to_string() + node.node.name(), node.location));
-
-        let expr = match &node.node {
-            ast::ExprKind::ListComp { .. } => return self.fold_listcomp(node),
-            _ => rustpython_parser::ast::fold::fold_expr(self, node)?
-        };
-
-        let ret = Ok(ast::Expr {
-            // compute type info and store in the custom field
-            custom: match &expr.node {
-                ast::ExprKind::Constant {value, kind: _} => self.infer_constant(value),
-                ast::ExprKind::Name {id, ctx: _} => Ok(Some(self.ctx.resolve(id)?)),
-                ast::ExprKind::List {elts, ctx: _} => self.infer_list(elts),
-                ast::ExprKind::Tuple {elts, ctx: _} => self.infer_tuple(elts),
-                ast::ExprKind::Attribute {value, attr, ctx: _} => self.infer_attribute(value, attr),
-                ast::ExprKind::BoolOp {op: _, values} => self.infer_bool_ops(values),
-                ast::ExprKind::BinOp {left, op, right} => self.infer_bin_ops(left, op, right),
-                ast::ExprKind::UnaryOp {op, operand} => self.infer_unary_ops(op, operand),
-                ast::ExprKind::Compare {left, ops, comparators} => self.infer_compare(left, ops, comparators),
-                ast::ExprKind::Call {func, args, keywords} => self.infer_call(func, args, keywords),
-                ast::ExprKind::Subscript {value, slice, ctx: _} => self.infer_subscript(value, slice),
-                ast::ExprKind::IfExp {test, body, orelse} => self.infer_if_expr(test, body, orelse),
-                ast::ExprKind::ListComp {elt: _, generators: _} => unreachable!("should not earch here, the list comp should have been folded before"), // already folded
-                ast::ExprKind::Slice { .. } => Ok(None), // special handling for slice, which is supported
-                _ => Err("not supported yet".into())
-            }?,
-            location: expr.location,
-            node: expr.node
-        });
-        self.error_stack.pop();
-        ret
-    }
-
-    fn fold_stmt(&mut self, node: ast::Stmt<()>) -> Result<ast::Stmt<Self::TargetU>, Self::Error> {
-        let stmt = match node.node {
-            ast::StmtKind::AnnAssign {target, annotation, value, simple} => {
-                let target_folded = Box::new(self.fold_expr( *target)?);
-                let value = if let Some(v) = value {
-                    let value_folded = Box::new(self.fold_expr(*v)?);
-                    if target_folded.custom == value_folded.custom {
-                        Some(value_folded)
-                    } else {
-                        return Err("Assignment LHF does not have the same type as RHS".into())
-                    }
-                } else {
-                    None
-                };
-                // TODO check consistency with type annotation
-                ast::Located {
-                    location: node.location,
-                    custom: None,
-                    node: ast::StmtKind::AnnAssign {
-                        target: target_folded, 
-                        annotation: Box::new(NaiveFolder.fold_expr(*annotation)?), 
-                        value, 
-                        simple
-                    },
-                }
-            }
-            _ => ast::fold::fold_stmt(self, node)?
-        };
-
-        match &stmt.node {
-            ast::StmtKind::For { target, iter, .. } => {
-                if let Some(TypeEnum::ParametricType(primitives::LIST_TYPE, ls)) = iter.custom.as_deref() {
-                    unimplemented!()
-                    // TODO
-                } else {
-                    return Err("can only iterate over list".into())
-                }
-            }
-            ast::StmtKind::If { test, .. } | ast::StmtKind::While { test, .. } => {
-                if test.custom != Some(self.ctx.get_primitive(primitives::BOOL_TYPE)) {
-                    return Err("Test should be bool".into());
-                }
-            }
-            ast::StmtKind::Assign { targets, value, .. } => {
-                unimplemented!();
-                // TODO
-            }
-            ast::StmtKind::AnnAssign { .. } | ast::StmtKind::Expr { .. } => {}
-            ast::StmtKind::Break | ast::StmtKind::Continue => {}
-            ast::StmtKind::Return { value } => {
-                unimplemented!()
-                // TODO
-            }
-            _ => return Err("Unsupported statement type".to_string()),
-        }
-
-        Ok(stmt)
-    }
-}
-
-impl<'a> TypeInferencer<'a> {
-    fn infer_constant(&self, constant: &ast::Constant) -> Result<Option<Type>, String> {
-        match constant {
-            ast::Constant::Bool(_) => 
-                Ok(Some(self.ctx.get_primitive(primitives::BOOL_TYPE))),
-            
-            ast::Constant::Int(val) => {
-                let int32: Result<i32, _> = val.try_into();
-                let int64: Result<i64, _> = val.try_into();
-                
-                if int32.is_ok() {
-                    Ok(Some(self.ctx.get_primitive(primitives::INT32_TYPE)))
-                } else if int64.is_ok() {
-                    Ok(Some(self.ctx.get_primitive(primitives::INT64_TYPE)))
-                } else {
-                    Err("Integer out of bound".into())
-                }
-            },
-    
-            ast::Constant::Float(_) => 
-                Ok(Some(self.ctx.get_primitive(primitives::FLOAT_TYPE))),
-
-            ast::Constant::Tuple(vals) => {
-                let result = vals
-                    .iter()
-                    .map(|x| self.infer_constant(x))
-                    .collect::<Vec<_>>();
-                
-                if result.iter().all(|x| x.is_ok()) {
-                    Ok(Some(TypeEnum::ParametricType(
-                        primitives::TUPLE_TYPE, 
-                        result
-                            .into_iter()
-                            .map(|x| x.unwrap().unwrap())
-                            .collect::<Vec<_>>(),
-                    ).into()))
-                } else {
-                    Err("Some elements in tuple cannot be typed".into())
-                }
-            }
-
-            _ => Err("not supported".into())
-        }
-    }
-
-    fn infer_list(&self, elts: &[ast::Expr<Option<Type>>]) -> Result<Option<Type>, String> {
-        if elts.is_empty() {
-            Ok(Some(TypeEnum::ParametricType(primitives::LIST_TYPE, vec![TypeEnum::BotType.into()]).into()))
-        } else {
-            let types = elts
-                .iter()
-                .map(|x| &x.custom)
-                .collect::<Vec<_>>();
-            
-            if types.iter().all(|x| x.is_some()) {
-                let head = types.iter().next().unwrap(); // here unwrap alone should be fine after the previous check
-                if types.iter().all(|x| x.eq(head)) {
-                    Ok(Some(TypeEnum::ParametricType(primitives::LIST_TYPE, vec![(*head).clone().unwrap()]).into()))
-                } else {
-                    Err("inhomogeneous list is not allowed".into())
-                }
-            } else {
-                Err("list elements must have some type".into())
-            }
-        }
-    }
-
-    fn infer_tuple(&self, elts: &[ast::Expr<Option<Type>>]) -> Result<Option<Type>, String> {
-        let types = elts
-            .iter()
-            .map(|x| (x.custom).clone())
-            .collect::<Vec<_>>();
-
-        if types.iter().all(|x| x.is_some()) {
-            Ok(Some(TypeEnum::ParametricType(
-                primitives::TUPLE_TYPE, 
-                types.into_iter().map(|x| x.unwrap()).collect()).into())) // unwrap alone should be fine after the previous check
-        } else {
-            Err("tuple elements must have some type".into())
-        }
-    }
-
-    fn infer_attribute(&self, value: &ast::Expr<Option<Type>>, attr: &str) -> Result<Option<Type>, String> {
-        let ty = value.custom.clone().ok_or_else(|| "no value".to_string())?;
-        if let TypeEnum::TypeVariable(id) = ty.as_ref() {
-            let v = self.ctx.get_variable_def(*id);
-            if v.bound.is_empty() {
-                return Err("no fields on unbounded type variable".into());
-            }
-            let ty = v.bound[0].get_base(&self.ctx).and_then(|v| v.fields.get(attr));
-            if ty.is_none() {
-                return Err("unknown field".into());
-            }
-            for x in v.bound[1..].iter() {
-                let ty1 = x.get_base(&self.ctx).and_then(|v| v.fields.get(attr));
-                if ty1 != ty {
-                    return Err("unknown field (type mismatch between variants)".into());
-                }
-            }
-            return Ok(Some(ty.unwrap().clone()));
-        }
-        
-        match ty.get_base(&self.ctx) {
-            Some(b) => match b.fields.get(attr) {
-                Some(t) => Ok(Some(t.clone())),
-                None => Err("no such field".into()),
-            },
-            None => Err("this object has no fields".into()),
-        }
-    }
-
-    fn infer_bool_ops(&self, values: &[ast::Expr<Option<Type>>]) -> Result<Option<Type>, String> {
-        assert_eq!(values.len(), 2); 
-        let left = values[0].custom.clone().ok_or_else(|| "no value".to_string())?;
-        let right = values[1].custom.clone().ok_or_else(|| "no value".to_string())?;
-        let b = self.ctx.get_primitive(primitives::BOOL_TYPE);
-        if left == b && right == b {
-            Ok(Some(b))
-        } else {
-            Err("bool operands must be bool".to_string())
-        }
-    }
-
-    fn infer_bin_ops(&self, left: &ast::Expr<Option<Type>>, op: &ast::Operator, right: &ast::Expr<Option<Type>>) -> Result<Option<Type>, String> {
-        inference_core::resolve_call(
-            &self.ctx, 
-            Some(left.custom.clone().ok_or_else(|| "no value".to_string())?), 
-            magic_methods::binop_name(op), 
-            &[right.custom.clone().ok_or_else(|| "no value".to_string())?])
-            .map_err(|_| "unsupported binary operator between the oprands".to_string())
-    }
-
-    fn infer_unary_ops(&self, op: &ast::Unaryop, operand: &ast::Expr<Option<Type>>) -> Result<Option<Type>, String> {
-        if let ast::Unaryop::Not = op {
-            if operand.custom == Some(self.ctx.get_primitive(primitives::BOOL_TYPE)) {
-                Ok(Some(self.ctx.get_primitive(primitives::BOOL_TYPE)))
-            } else {
-                Err("logical not must be applied to bool".into())
-            }
-        } else {
-            inference_core::resolve_call(&self.ctx, operand.custom.clone(), magic_methods::unaryop_name(op), &[])
-            .map_err(|_| "unsupported unary operator".to_string())
-        }
-    }
-
-    fn infer_compare(&self, left: &ast::Expr<Option<Type>>, ops: &[ast::Cmpop], comparators: &[ast::Expr<Option<Type>>]) -> Result<Option<Type>, String> {
-        if left.custom.is_none() || (!comparators.iter().all(|x| x.custom.is_some())) {
-            Err("comparison operands must have type".into())
-        } else {
-            let bool_type = Some(self.ctx.get_primitive(primitives::BOOL_TYPE));
-            let ty_first = inference_core::resolve_call(
-                &self.ctx, 
-                Some(left.custom.clone().ok_or_else(|| "comparator must be able to be typed".to_string())?), 
-                magic_methods::comparison_name(&ops[0]).ok_or_else(|| "unsupported comparison".to_string())?, 
-                &[comparators[0].custom.clone().ok_or_else(|| "comparator must be able to be typed".to_string())?])
-                .map_err(|_| "Comparison between the comparators are not supportes".to_string())?;
-            if ty_first != bool_type {
-                return Err("comparison result must be boolean".into());
-            }
-
-            for ((a, b), op) 
-            in comparators[..(comparators.len() - 1)]
-                .iter()
-                .zip(comparators[1..].iter())
-                .zip(ops[1..].iter()) {
-                    let ty = inference_core::resolve_call(
-                        &self.ctx, 
-                        Some(a.custom.clone().ok_or_else(|| "comparator must be able to be typed".to_string())?.clone()), 
-                        magic_methods::comparison_name(op).ok_or_else(|| "unsupported comparison".to_string())?,
-                        &[b.custom.clone().ok_or_else(|| "comparator must be able to be typed".to_string())?.clone()])
-                        .map_err(|_| "Comparison between the comparators are not supportes".to_string())?;
-                    if ty != bool_type {
-                        return Err("comparison result must be boolean".into());
-                    }
-                }
-            Ok(bool_type)
-        }
-    }
-
-    fn infer_call(&self, func: &ast::Expr<Option<Type>>, args: &[ast::Expr<Option<Type>>], _keywords: &[ast::Keyword<Option<Type>>]) -> Result<Option<Type>, String> {
-        if args.iter().all(|x| x.custom.is_some()) {
-            match &func.node {
-                ast::ExprKind::Name {id, ctx: _} 
-                    => inference_core::resolve_call(
-                        &self.ctx, 
-                        None, 
-                        id, 
-                        &args.iter().map(|x| x.custom.clone().unwrap()).collect::<Vec<_>>()),
-                
-                ast::ExprKind::Attribute {value, attr, ctx: _}
-                    => inference_core::resolve_call(
-                        &self.ctx, 
-                        Some(value.custom.clone().ok_or_else(|| "no value".to_string())?), 
-                        &attr, 
-                        &args.iter().map(|x| x.custom.clone().unwrap()).collect::<Vec<_>>()),
-                
-                _ => Err("not supported".into())
-            }
-        } else {
-            Err("function params must have type".into())
-        }
-    }
-
-    fn infer_subscript(&self, value: &ast::Expr<Option<Type>>, slice: &ast::Expr<Option<Type>>) -> Result<Option<Type>, String> {
-        let val_type = value.custom.as_ref().ok_or_else(|| "no value".to_string())?.as_ref();
-        if let TypeEnum::ParametricType(primitives::LIST_TYPE, ls) = val_type {
-            if let ast::ExprKind::Slice {lower, upper, step} = &slice.node {
-                let int32_type = self.ctx.get_primitive(primitives::INT32_TYPE);
-                let l = lower.as_ref().map_or(
-                    Ok(&int32_type),
-                    |x| x.custom.as_ref().ok_or_else(|| "lower bound cannot be typped".to_string()))?;
-                let u = upper.as_ref().map_or(
-                    Ok(&int32_type),
-                    |x| x.custom.as_ref().ok_or_else(|| "upper bound cannot be typped".to_string()))?;
-                let s = step.as_ref().map_or(
-                    Ok(&int32_type),
-                    |x| x.custom.as_ref().ok_or_else(|| "step cannot be typped".to_string()))?;
-                
-                if l == &int32_type && u == &int32_type && s == &int32_type {
-                    Ok(value.custom.clone())
-                } else {
-                    Err("slice must be int32 type".into())
-                }
-            } else if slice.custom == Some(self.ctx.get_primitive(primitives::INT32_TYPE)) {
-                Ok(Some(ls[0].clone()))
-            } else {
-                Err("slice or index must be int32 type".into())
-            }
-        } else if let TypeEnum::ParametricType(primitives::TUPLE_TYPE, ls) = val_type {
-            if let ast::ExprKind::Constant {kind: _, value: ast::Constant::Int(val)} = &slice.node {
-                let ind: Result<usize, _> = val.try_into();
-                if ind.is_ok() && ind.unwrap() < ls.len() {
-                    Ok(Some(ls[ind.unwrap()].clone()))
-                } else {
-                    Err("tuple constant index out of range".into())
-                }
-            } else {
-                Err("tuple index can only be constant".into())
-            }
-        } else {
-            Err("subscript is not supported for types other than list or tuple".into())
-        }
-    }
-
-    fn infer_if_expr(&self, test: &ast::Expr<Option<Type>>, body: &ast::Expr<Option<Type>>, orelse: &ast::Expr<Option<Type>>) -> Result<Option<Type>, String> {
-        if test.custom != Some(self.ctx.get_primitive(primitives::BOOL_TYPE)) {
-            Err("test should be bool".into())
-        } else if body.custom == orelse.custom {
-            Ok(body.custom.clone())
-        } else {
-            Err("divergent type at if expression".into())
-        }
-    }
-
-    fn _infer_list_comprehesion(&self, elt: &ast::Expr<Option<Type>>, generators: &[ast::Comprehension<Option<Type>>]) -> Result<Option<Type>, String> {
-        if generators[0]
-            .ifs
-            .iter()
-            .all(|x| x.custom == Some(self.ctx.get_primitive(primitives::BOOL_TYPE))) {
-                Ok(Some(TypeEnum::ParametricType(
-                    primitives::LIST_TYPE, 
-                    vec![elt.custom.clone().ok_or_else(|| "elements should have value".to_string())?]).into()))
-            } else {
-                Err("test must be bool".into())
-            }
-    }
-
-    // some pre-folds need special handling
-    fn fold_listcomp(&mut self, expr: ast::Expr<()>) -> Result<ast::Expr<Option<Type>>, String> {
-        
-        self.error_stack.push(("list comprehension at ".into(), expr.location));
-
-        if let ast::Expr {
-            location, 
-            custom: _, 
-            node: ast::ExprKind::ListComp {
-                elt, 
-                mut generators}} = expr {
-            // if is list comprehension, need special pre-fold
-            if generators.len() != 1 {
-                return Err("only 1 generator statement is supported".into());
-            }
-            let gen = generators.remove(0);
-            if gen.is_async {
-                return Err("async is not supported".into());
-            }
-
-            let ast::Comprehension {iter, 
-                target, 
-                ifs, 
-                is_async} = gen;
-            let iter_folded = Box::new(self.fold_expr(*iter)?);
-
-            let ret = if let TypeEnum::ParametricType(
-                primitives::LIST_TYPE, 
-                ls) = iter_folded
-                    .custom
-                    .as_ref()
-                    .ok_or_else(|| "no value".to_string())?
-                    .as_ref()
-                    .clone() {
-
-                let result: Result<ast::Expr<Option<Type>>, String>;
-                self.ctx.start_scope();
-                {
-                    self.infer_simple_binding(&target, ls[0].clone())?;
-                    let elt_folded = Box::new(self.fold_expr(*elt)?);
-                    let target_folded = Box::new(self.fold_expr(*target)?);
-                    let ifs_folded = ifs
-                        .into_iter()
-                        .map(|x| self.fold_expr(x))
-                        .collect::<Result<Vec<ast::Expr<Option<Type>>>, _>>()?;
-                    
-                    result = 
-                        if ifs_folded
-                        .iter()
-                        .all(|x| x.custom == Some(self.ctx.get_primitive(primitives::BOOL_TYPE))) {
-                        // only pop the error stack when return Ok(..)
-                        self.error_stack.pop();
-                        
-                        Ok(ast::Expr {
-                            location,
-                            custom: Some(TypeEnum::ParametricType(
-                                primitives::LIST_TYPE, 
-                                vec![elt_folded
-                                    .custom
-                                    .clone()
-                                    .ok_or_else(|| "elements cannot be typped".to_string())?]).into()),
-                            node: ast::ExprKind::ListComp {
-                                elt: elt_folded,
-                                generators: vec![ast::Comprehension {
-                                    target: target_folded,
-                                    ifs: ifs_folded,
-                                    iter: iter_folded,
-                                    is_async
-                                }]
-                            }
-                        })
-                    } else {
-                        Err("test must be bool".into())
-                    };
-                }
-                self.ctx.end_scope();                
-                result
-            } else {
-                Err("iteration is supported for list only".into())
-            };
-            ret
-        } else {
-            panic!("this function is for list comprehensions only!");
-        }
-    }
-
-    fn infer_simple_binding<T>(&mut self, name: &ast::Expr<T>, ty: Type) -> Result<(), String> {
-        self.error_stack.push(("resolving list comprehension variables".into(), name.location));
-        let ret = match &name.node {
-            ast::ExprKind::Name {id, ctx: _} => {
-                if id == "_" {
-                    self.error_stack.pop();
-                    Ok(())
-                } else if self.ctx.defined(id) {
-                    Err("duplicated naming".into())
-                } else {
-                    self.ctx.assign(id.clone(), ty, name.location)?;
-                    self.error_stack.pop();
-                    Ok(())
-                }
-            }
-    
-            ast::ExprKind::Tuple {elts, ctx: _} => {
-                if let TypeEnum::ParametricType(primitives::TUPLE_TYPE, ls) = ty.as_ref() {
-                    if elts.len() == ls.len() {
-                        for (a, b) in elts.iter().zip(ls.iter()) {
-                            self.infer_simple_binding(a, b.clone())?;
-                        }
-                        self.error_stack.pop();
-                        Ok(())
-                    } else {
-                        Err("different length".into())
-                    }
-                } else {
-                    Err("not supported".into())
-                }
-            }
-            _ => Err("not supported".into())
-        };
-        
-        ret
-    }
-
-    fn fold_expr(&mut self, node: ast::Expr<()>) -> Result<ast::Expr<Option<Type>>, String> {
-        let result = <Self as ast::fold::Fold<()>>::fold_expr(self, node);
-        if result.is_err() {
-            println!("{:?}", result);
-            println!("{:?}", self.error_stack.pop().unwrap());
-        }
-        result
-    }
-}
-
-#[cfg(test)]
-pub mod test {
-    use crate::typecheck::{symbol_resolver::SymbolResolver, symbol_resolver::*, location::*};
-    use rustpython_parser::ast::Expr;
-    use super::*;
-    
-    #[cfg(test)]
-    use test_case::test_case;
-    
-    pub fn new_ctx<'a>() -> TypeInferencer<'a> {
-        struct S;
-        impl SymbolResolver for S {
-            fn get_symbol_location(&self, _str: &str) -> Option<Location> { None }
-            fn get_symbol_type(&self, _str: &str) -> Option<SymbolType> { None }
-            fn get_symbol_value(&self, _str: &str) -> Option<SymbolValue> { None }
-        }
-
-        TypeInferencer {
-            ctx: InferenceContext::new(primitives::basic_ctx(), Box::new(S{}), FileID(3)),
-            error_stack: Vec::new()
-        }
-    }
-
-    #[test]
-    fn test_i32() {
-        let mut inferencer = new_ctx();
-        let ast: Expr = Expr {
-            location: ast::Location::new(0, 0),
-            custom: (),
-            node: ast::ExprKind::Constant {
-                value: ast::Constant::Int(123.into()),
-                kind: None
-            }
-        };
-
-        let new_ast = inferencer.fold_expr(ast);
-        assert_eq!(
-            new_ast,
-            Ok(ast::Expr {
-                location: ast::Location::new(0, 0),
-                custom: Some(inferencer.ctx.get_primitive(primitives::INT32_TYPE)),
-                node: ast::ExprKind::Constant {
-                    value: ast::Constant::Int(123.into()),
-                    kind: None
-                }
-            })
-        );
-    }
-
-    #[test]
-    fn test_i64() {
-        let mut inferencer = new_ctx();
-
-        let location = ast::Location::new(0, 0);
-        let num: i64 = 99999999999;
-
-        let ast: Expr = Expr {
-            location,
-            custom: (),
-            node: ast::ExprKind::Constant {
-                value: ast::Constant::Int(num.into()),
-                kind: None,
-            }
-        };
-        
-        let new_ast = inferencer.fold_expr(ast).unwrap();
-
-        assert_eq!(
-            new_ast, 
-            Expr {
-                location,
-                custom: Some(inferencer.ctx.get_primitive(primitives::INT64_TYPE)),
-                node: ast::ExprKind::Constant {
-                    value: ast::Constant::Int(num.into()),
-                    kind: None,
-                }
-            }
-        );
-    }
-
-    #[test]
-    fn test_tuple() {
-        let mut inferencer = new_ctx();
-        let i32_t = inferencer.ctx.get_primitive(primitives::INT32_TYPE);
-        let float_t = inferencer.ctx.get_primitive(primitives::FLOAT_TYPE);
-        let ast = rustpython_parser::parser::parse_expression("(123, 123.123, 999999999)").unwrap();
-        let loc = ast.location;
-        let folded = inferencer.fold_expr(ast).unwrap();
-        assert_eq!(
-            folded,
-            ast::Expr {
-                location: loc,
-                custom: Some(TypeEnum::ParametricType(primitives::TUPLE_TYPE, vec![i32_t.clone(), float_t.clone(), i32_t.clone()]).into()),
-                node: ast::ExprKind::Tuple {
-                    ctx: ast::ExprContext::Load, 
-                    elts: vec![
-                        ast::Expr {
-                            location: ast::Location::new(1, 2),
-                            custom: Some(i32_t.clone()),
-                            node: ast::ExprKind::Constant {
-                                value: ast::Constant::Int(123.into()),
-                                kind: None
-                            }
-                        },
-                        ast::Expr {
-                            location: ast::Location::new(1, 7),
-                            custom: Some(float_t),
-                            node: ast::ExprKind::Constant {
-                                value: ast::Constant::Float(123.123),
-                                kind: None
-                            }
-                        },
-                        ast::Expr {
-                            location: ast::Location::new(1, 16),
-                            custom: Some(i32_t),
-                            node: ast::ExprKind::Constant {
-                                value: ast::Constant::Int(999999999.into()),
-                                kind: None
-                            }
-                        },
-                    ]
-                }
-            }
-        );
-
-    }
-
-    #[test]
-    fn test_list() {
-        let mut inferencer = new_ctx();
-        let location = ast::Location::new(0, 0);
-
-        let ast: Expr = Expr {
-            location,
-            custom: (),
-            node: ast::ExprKind::List {
-                ctx: ast::ExprContext::Load,
-                elts: vec![
-                    Expr {
-                        location,
-                        custom: (),
-                        node: ast::ExprKind::Constant {
-                            value: ast::Constant::Int(1.into()),
-                            kind: None,
-                        },
-                    },
-
-                    Expr {
-                        location,
-                        custom: (),
-                        node: ast::ExprKind::Constant {
-                            value: ast::Constant::Int(2.into()),
-                            kind: None,
-                        },
-                    },
-                ],
-            }
-        };
-
-        let new_ast = inferencer.fold_expr(ast).unwrap();
-        assert_eq!(
-            new_ast,
-            Expr {
-                location,
-                custom: Some(TypeEnum::ParametricType(primitives::LIST_TYPE, vec![inferencer.ctx.get_primitive(primitives::INT32_TYPE)]).into()),
-                node: ast::ExprKind::List {
-                    ctx: ast::ExprContext::Load,
-                    elts: vec![
-                        Expr {
-                            location,
-                            custom: Some(inferencer.ctx.get_primitive(primitives::INT32_TYPE)),
-                            node: ast::ExprKind::Constant {
-                                value: ast::Constant::Int(1.into()),
-                                kind: None,
-                            },
-                        },
-
-                        Expr {
-                            location,
-                            custom: Some(inferencer.ctx.get_primitive(primitives::INT32_TYPE)),
-                            // custom: None,
-                            node: ast::ExprKind::Constant {
-                                value: ast::Constant::Int(2.into()),
-                                kind: None,
-                            },
-                        },
-                    ],
-                }
-            }
-        );
-    }
-
-    #[test_case("False == [True or True, False][0]")]
-    #[test_case("1 < 2 < 3")]
-    #[test_case("1 + [123, 1232][0]")]
-    #[test_case("not True")]
-    #[test_case("[[1]][0][0]")]
-    #[test_case("[[1]][0]")]
-    #[test_case("[[(1, 2), (2, 3), (3, 4)], [(2, 4), (4, 6)]][0]")]
-    #[test_case("[1, 2, 3, 4, 5][1: 2]")]
-    #[test_case("4 if False and True else 8")]
-    #[test_case("(1, 2, 3, 4)[1]")]
-    #[test_case("(1, True, 3, False)[1]")]
-    fn test_mix(prog: &'static str) {
-        let mut inf = new_ctx();
-        let ast = rustpython_parser::parser::parse_expression(prog).unwrap();
-        let folded = inf.fold_expr(ast).unwrap();
-        // println!("{:?}\n", folded.custom);
-    }
-
-    #[test_case("[1, True, 2]")]
-    #[test_case("True if 1 else False")]
-    #[test_case("1 if True else False")]
-    #[test_case("1 and 2")]
-    #[test_case("False or 1")]
-    #[test_case("1 + False")]
-    #[test_case("1 < 2 > False")]
-    #[test_case("not 2")]
-    #[test_case("-True")]
-    fn test_err_msg(prog: &'static str) {
-        let mut inf = new_ctx();
-        let ast = rustpython_parser::parser::parse_expression(prog).unwrap();
-        let _folded = inf.fold_expr(ast);
-        println!("")
-    }
-}

nac3core/src/typecheck/type_error.rs

@@ -0,0 +1,186 @@
+use std::collections::HashMap;
+use std::fmt::Display;
+
+use crate::typecheck::typedef::TypeEnum;
+
+use super::typedef::{RecordKey, Type, Unifier};
+use nac3parser::ast::{Location, StrRef};
+
+#[derive(Debug, Clone)]
+pub enum TypeErrorKind {
+    TooManyArguments {
+        expected: usize,
+        got: usize,
+    },
+    MissingArgs(String),
+    UnknownArgName(StrRef),
+    IncorrectArgType {
+        name: StrRef,
+        expected: Type,
+        got: Type,
+    },
+    FieldUnificationError {
+        field: RecordKey,
+        types: (Type, Type),
+        loc: (Option<Location>, Option<Location>),
+    },
+    IncompatibleRange(Type, Vec<Type>),
+    IncompatibleTypes(Type, Type),
+    MutationError(RecordKey, Type),
+    NoSuchField(RecordKey, Type),
+    TupleIndexOutOfBounds {
+        index: i32,
+        len: i32,
+    },
+    RequiresTypeAnn,
+    PolymorphicFunctionPointer,
+}
+
+#[derive(Debug, Clone)]
+pub struct TypeError {
+    pub kind: TypeErrorKind,
+    pub loc: Option<Location>,
+}
+
+impl TypeError {
+    pub fn new(kind: TypeErrorKind, loc: Option<Location>) -> TypeError {
+        TypeError { kind, loc }
+    }
+
+    pub fn at(mut self, loc: Option<Location>) -> TypeError {
+        self.loc = self.loc.or(loc);
+        self
+    }
+
+    pub fn to_display(self, unifier: &Unifier) -> DisplayTypeError {
+        DisplayTypeError { err: self, unifier }
+    }
+}
+
+pub struct DisplayTypeError<'a> {
+    pub err: TypeError,
+    pub unifier: &'a Unifier,
+}
+
+fn loc_to_str(loc: Option<Location>) -> String {
+    match loc {
+        Some(loc) => format!("(in {})", loc),
+        None => "".to_string(),
+    }
+}
+
+impl<'a> Display for DisplayTypeError<'a> {
+    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
+        use TypeErrorKind::*;
+        let mut notes = Some(HashMap::new());
+        match &self.err.kind {
+            TooManyArguments { expected, got } => {
+                write!(f, "Too many arguments. Expected {} but got {}", expected, got)
+            }
+            MissingArgs(args) => {
+                write!(f, "Missing arguments: {}", args)
+            }
+            UnknownArgName(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 {}. Expected {}, but got {}",
+                    name, expected, got
+                )
+            }
+            FieldUnificationError { field, types, loc } => {
+                let lhs = self.unifier.stringify_with_notes(types.0, &mut notes);
+                let rhs = self.unifier.stringify_with_notes(types.1, &mut notes);
+                write!(
+                    f,
+                    "Unable to unify field {}: Got types {}{} and {}{}",
+                    field,
+                    lhs,
+                    loc_to_str(loc.0),
+                    rhs,
+                    loc_to_str(loc.1)
+                )
+            }
+            IncompatibleRange(t, ts) => {
+                let t = self.unifier.stringify_with_notes(*t, &mut notes);
+                let ts = ts
+                    .iter()
+                    .map(|t| self.unifier.stringify_with_notes(*t, &mut notes))
+                    .collect::<Vec<_>>();
+                write!(f, "Expected any one of these types: {}, but got {}", ts.join(", "), t)
+            }
+            IncompatibleTypes(t1, t2) => {
+                let type1 = self.unifier.get_ty_immutable(*t1);
+                let type2 = self.unifier.get_ty_immutable(*t2);
+                match (&*type1, &*type2) {
+                    (TypeEnum::TCall(calls), _) => {
+                        let loc = self.unifier.calls[calls[0].0].loc;
+                        let result = write!(
+                            f,
+                            "{} is not callable",
+                            self.unifier.stringify_with_notes(*t2, &mut notes)
+                        );
+                        if let Some(loc) = loc {
+                            result?;
+                            write!(f, " (in {})", loc)?;
+                            return Ok(());
+                        }
+                        result
+                    }
+                    (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 {} 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: {} and {}", t1, t2)
+                    }
+                }
+            }
+            MutationError(name, t) => {
+                if let TypeEnum::TTuple { .. } = &*self.unifier.get_ty_immutable(*t) {
+                    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 {} of {}, which is immutable", name, t)
+                }
+            }
+            NoSuchField(name, t) => {
+                let t = self.unifier.stringify_with_notes(*t, &mut notes);
+                write!(f, "`{}::{}` field/method does not exist", t, name)
+            }
+            TupleIndexOutOfBounds { index, len } => {
+                write!(
+                    f,
+                    "Tuple index out of bounds. Got {} but tuple has only {} elements",
+                    index, len
+                )
+            }
+            RequiresTypeAnn => {
+                write!(f, "Unable to infer virtual object type: Type annotation required")
+            }
+            PolymorphicFunctionPointer => {
+                write!(f, "Polymorphic function pointers is not supported")
+            }
+        }?;
+        if let Some(loc) = self.err.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)?;
+            }
+        }
+        Ok(())
+    }
+}

nac3core/src/typecheck/type_inferencer/test.rs

@@ -0,0 +1,713 @@
+use super::super::{magic_methods::with_fields, typedef::*};
+use super::*;
+use crate::{
+    codegen::CodeGenContext,
+    symbol_resolver::ValueEnum,
+    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>,
+    id_to_def: HashMap<StrRef, DefinitionId>,
+    class_names: HashMap<StrRef, Type>,
+}
+
+impl SymbolResolver for Resolver {
+    fn get_default_param_value(
+        &self,
+        _: &nac3parser::ast::Expr,
+    ) -> Option<crate::symbol_resolver::SymbolValue> {
+        unimplemented!()
+    }
+
+    fn get_symbol_type(
+        &self,
+        _: &mut Unifier,
+        _: &[Arc<RwLock<TopLevelDef>>],
+        _: &PrimitiveStore,
+        str: StrRef,
+    ) -> Result<Type, String> {
+        self.id_to_type.get(&str).cloned().ok_or_else(|| format!("cannot find symbol `{}`", str))
+    }
+
+    fn get_symbol_value<'ctx, 'a>(
+        &self,
+        _: StrRef,
+        _: &mut CodeGenContext<'ctx, 'a>,
+    ) -> Option<ValueEnum<'ctx>> {
+        unimplemented!()
+    }
+
+    fn get_identifier_def(&self, id: StrRef) -> Result<DefinitionId, String> {
+        self.id_to_def.get(&id).cloned().ok_or_else(|| "Unknown identifier".to_string())
+    }
+
+    fn get_string_id(&self, _: &str) -> i32 {
+        unimplemented!()
+    }
+
+    fn get_exception_id(&self, _tyid: usize) -> usize {
+        unimplemented!()
+    }
+}
+
+struct TestEnvironment {
+    pub unifier: Unifier,
+    pub function_data: FunctionData,
+    pub primitives: PrimitiveStore,
+    pub id_to_name: HashMap<usize, StrRef>,
+    pub identifier_mapping: HashMap<StrRef, Type>,
+    pub virtual_checks: Vec<(Type, Type, nac3parser::ast::Location)>,
+    pub calls: HashMap<CodeLocation, CallId>,
+    pub top_level: TopLevelContext,
+}
+
+impl TestEnvironment {
+    pub fn basic_test_env() -> TestEnvironment {
+        let mut unifier = Unifier::new();
+
+        let int32 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(0),
+            fields: HashMap::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 }],
+                ret: int32,
+                vars: HashMap::new(),
+            }));
+            fields.insert("__add__".into(), (add_ty, false));
+        });
+        let int64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(1),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let float = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(2),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let bool = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(3),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let none = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(4),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let range = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(5),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let str = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(6),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let exception = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(7),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let uint32 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(8),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let uint64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(9),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let option = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(10),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let primitives = PrimitiveStore {
+            int32,
+            int64,
+            float,
+            bool,
+            none,
+            range,
+            str,
+            exception,
+            uint32,
+            uint64,
+            option,
+        };
+        set_primitives_magic_methods(&primitives, &mut unifier);
+
+        let id_to_name = [
+            (0, "int32".into()),
+            (1, "int64".into()),
+            (2, "float".into()),
+            (3, "bool".into()),
+            (4, "none".into()),
+            (5, "range".into()),
+            (6, "str".into()),
+            (7, "exception".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: Default::default(),
+            class_names: Default::default(),
+        }) as Arc<dyn SymbolResolver + Send + Sync>;
+
+        TestEnvironment {
+            top_level: TopLevelContext {
+                definitions: Default::default(),
+                unifiers: Default::default(),
+                personality_symbol: None,
+            },
+            unifier,
+            function_data: FunctionData {
+                resolver,
+                bound_variables: Vec::new(),
+                return_type: None,
+            },
+            primitives,
+            id_to_name,
+            identifier_mapping,
+            virtual_checks: Vec::new(),
+            calls: HashMap::new(),
+        }
+    }
+
+    fn new() -> TestEnvironment {
+        let mut unifier = Unifier::new();
+        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: DefinitionId(0),
+            fields: HashMap::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 }],
+                ret: int32,
+                vars: HashMap::new(),
+            }));
+            fields.insert("__add__".into(), (add_ty, false));
+        });
+        let int64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(1),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let float = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(2),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let bool = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(3),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let none = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(4),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let range = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(5),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let str = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(6),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let exception = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(7),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let uint32 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(8),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let uint64 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(9),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        let option = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(10),
+            fields: HashMap::new(),
+            params: HashMap::new(),
+        });
+        identifier_mapping.insert("None".into(), none);
+        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: Default::default(),
+                    fields: Default::default(),
+                    methods: Default::default(),
+                    ancestors: Default::default(),
+                    resolver: None,
+                    constructor: None,
+                    loc: None,
+                })
+                .into(),
+            );
+        }
+        let defs = 7;
+
+        let primitives = PrimitiveStore {
+            int32,
+            int64,
+            float,
+            bool,
+            none,
+            range,
+            str,
+            exception,
+            uint32,
+            uint64,
+            option,
+        };
+
+        let (v0, id) = unifier.get_dummy_var();
+
+        let foo_ty = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(defs + 1),
+            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![v0],
+                fields: [("a".into(), v0, true)].into(),
+                methods: Default::default(),
+                ancestors: Default::default(),
+                resolver: None,
+                constructor: None,
+                loc: None,
+            })
+            .into(),
+        );
+
+        identifier_mapping.insert(
+            "Foo".into(),
+            unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                args: vec![],
+                ret: foo_ty,
+                vars: [(id, v0)].iter().cloned().collect(),
+            })),
+        );
+
+        let fun = unifier.add_ty(TypeEnum::TFunc(FunSignature {
+            args: vec![],
+            ret: int32,
+            vars: Default::default(),
+        }));
+        let bar = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(defs + 2),
+            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: Default::default(),
+                fields: [("a".into(), int32, true), ("b".into(), fun, true)].into(),
+                methods: Default::default(),
+                ancestors: Default::default(),
+                resolver: None,
+                constructor: None,
+                loc: None,
+            })
+            .into(),
+        );
+        identifier_mapping.insert(
+            "Bar".into(),
+            unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                args: vec![],
+                ret: bar,
+                vars: Default::default(),
+            })),
+        );
+
+        let bar2 = unifier.add_ty(TypeEnum::TObj {
+            obj_id: DefinitionId(defs + 3),
+            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: Default::default(),
+                fields: [("a".into(), bool, true), ("b".into(), fun, false)].into(),
+                methods: Default::default(),
+                ancestors: Default::default(),
+                resolver: None,
+                constructor: None,
+                loc: None,
+            })
+            .into(),
+        );
+        identifier_mapping.insert(
+            "Bar2".into(),
+            unifier.add_ty(TypeEnum::TFunc(FunSignature {
+                args: vec![],
+                ret: bar2,
+                vars: Default::default(),
+            })),
+        );
+        let class_names = [("Bar".into(), bar), ("Bar2".into(), bar2)].iter().cloned().collect();
+
+        let id_to_name = [
+            "int32".into(),
+            "int64".into(),
+            "float".into(),
+            "bool".into(),
+            "none".into(),
+            "range".into(),
+            "str".into(),
+            "exception".into(),
+            "Foo".into(),
+            "Bar".into(),
+            "Bar2".into(),
+        ]
+        .iter()
+        .enumerate()
+        .map(|(a, b)| (a, *b))
+        .collect();
+
+        let top_level = TopLevelContext {
+            definitions: Arc::new(top_level_defs.into()),
+            unifiers: Default::default(),
+            personality_symbol: None,
+        };
+
+        let resolver = Arc::new(Resolver {
+            id_to_type: identifier_mapping.clone(),
+            id_to_def: [
+                ("Foo".into(), DefinitionId(defs + 1)),
+                ("Bar".into(), DefinitionId(defs + 2)),
+                ("Bar2".into(), DefinitionId(defs + 3)),
+            ]
+            .iter()
+            .cloned()
+            .collect(),
+            class_names,
+        }) as Arc<dyn SymbolResolver + Send + Sync>;
+
+        TestEnvironment {
+            unifier,
+            top_level,
+            function_data: FunctionData {
+                resolver,
+                bound_variables: Vec::new(),
+                return_type: None,
+            },
+            primitives,
+            id_to_name,
+            identifier_mapping,
+            virtual_checks: Vec::new(),
+            calls: HashMap::new(),
+        }
+    }
+
+    fn get_inferencer(&mut self) -> Inferencer {
+        Inferencer {
+            top_level: &self.top_level,
+            function_data: &mut self.function_data,
+            unifier: &mut self.unifier,
+            variable_mapping: Default::default(),
+            primitives: &mut self.primitives,
+            virtual_checks: &mut self.virtual_checks,
+            calls: &mut self.calls,
+            defined_identifiers: Default::default(),
+            in_handler: false,
+        }
+    }
+}
+
+#[test_case(indoc! {"
+        a = 1234
+        b = int64(2147483648)
+        c = 1.234
+        d = True
+    "},
+    [("a", "int32"), ("b", "int64"), ("c", "float"), ("d", "bool")].iter().cloned().collect(),
+    &[]
+    ; "primitives test")]
+#[test_case(indoc! {"
+        a = lambda x, y: x
+        b = lambda x: a(x, x)
+        c = 1.234
+        d = b(c)
+    "},
+    [("a", "fn[[x:float, y:float], float]"), ("b", "fn[[x:float], float]"), ("c", "float"), ("d", "float")].iter().cloned().collect(),
+    &[]
+    ; "lambda test")]
+#[test_case(indoc! {"
+        a = lambda x: x + x
+        b = lambda x: a(x) + x
+        a = b
+        c = b(1)
+    "},
+    [("a", "fn[[x:int32], int32]"), ("b", "fn[[x:int32], int32]"), ("c", "int32")].iter().cloned().collect(),
+    &[]
+    ; "lambda test 2")]
+#[test_case(indoc! {"
+        a = lambda x: x
+        b = lambda x: x
+
+        foo1 = Foo()
+        foo2 = Foo()
+        c = a(foo1.a)
+        d = b(foo2.a)
+
+        a(True)
+        b(123)
+
+    "},
+    [("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]")].iter().cloned().collect(),
+    &[]
+    ; "listcomp test")]
+#[test_case(indoc! {"
+        a = virtual(Bar(), Bar)
+        b = a.b()
+        a = virtual(Bar2())
+    "},
+    [("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]")].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);
+    let mut env = TestEnvironment::new();
+    let id_to_name = std::mem::take(&mut env.id_to_name);
+    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 = defined_identifiers.clone();
+    let statements = parse_program(source, Default::default()).unwrap();
+    let statements = statements
+        .into_iter()
+        .map(|v| inferencer.fold_stmt(v))
+        .collect::<Result<Vec<_>, _>>()
+        .unwrap();
+
+    inferencer.check_block(&statements, &mut defined_identifiers).unwrap();
+
+    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 None,
+        );
+        println!("{}: {}", k, name);
+    }
+    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 None,
+        );
+        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 None,
+        );
+        let b = inferencer.unifier.internal_stringify(
+            *b,
+            &mut |v| (*id_to_name.get(&v).unwrap()).into(),
+            &mut |v| format!("v{}", v),
+            &mut None,
+        );
+
+        assert_eq!(&a, x);
+        assert_eq!(&b, y);
+    }
+}
+
+#[test_case(indoc! {"
+        a = 2
+        b = 2
+        c = a + b
+        d = a - b
+        e = a * b
+        f = a / b
+        g = a // b
+        h = a % b
+    "},
+    [("a", "int32"),
+    ("b", "int32"),
+    ("c", "int32"),
+    ("d", "int32"),
+    ("e", "int32"),
+    ("f", "float"),
+    ("g", "int32"),
+    ("h", "int32")].iter().cloned().collect()
+    ; "int32")]
+#[test_case(
+    indoc! {"
+        a = 2.4
+        b = 3.6
+        c = a + b
+        d = a - b
+        e = a * b
+        f = a / b
+        g = a // b
+        h = a % b
+        i = a ** b
+        ii = 3
+        j = a ** b
+    "},
+    [("a", "float"),
+    ("b", "float"),
+    ("c", "float"),
+    ("d", "float"),
+    ("e", "float"),
+    ("f", "float"),
+    ("g", "float"),
+    ("h", "float"),
+    ("i", "float"),
+    ("ii", "int32"),
+    ("j", "float")].iter().cloned().collect()
+    ; "float"
+)]
+#[test_case(
+    indoc! {"
+        a = int64(12312312312)
+        b = int64(24242424424)
+        c = a + b
+        d = a - b
+        e = a * b
+        f = a / b
+        g = a // b
+        h = a % b
+        i = a == b
+        j = a > b
+        k = a < b
+        l = a != b
+    "},
+    [("a", "int64"),
+    ("b", "int64"),
+    ("c", "int64"),
+    ("d", "int64"),
+    ("e", "int64"),
+    ("f", "float"),
+    ("g", "int64"),
+    ("h", "int64"),
+    ("i", "bool"),
+    ("j", "bool"),
+    ("k", "bool"),
+    ("l", "bool")].iter().cloned().collect()
+    ; "int64"
+)]
+#[test_case(
+    indoc! {"
+        a = True
+        b = False
+        c = a == b
+        d = not a
+        e = a != b
+    "},
+    [("a", "bool"),
+    ("b", "bool"),
+    ("c", "bool"),
+    ("d", "bool"),
+    ("e", "bool")].iter().cloned().collect()
+    ; "boolean"
+)]
+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: HashSet<_> = env.identifier_mapping.keys().cloned().collect();
+    defined_identifiers.insert("virtual".into());
+    let mut inferencer = env.get_inferencer();
+    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))
+        .collect::<Result<Vec<_>, _>>()
+        .unwrap();
+
+    inferencer.check_block(&statements, &mut defined_identifiers).unwrap();
+
+    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 None,
+        );
+        println!("{}: {}", k, name);
+    }
+    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 None,
+        );
+        assert_eq!(format!("{}: {}", k, v), format!("{}: {}", k, name));
+    }
+}

nac3core/src/typecheck/typedef.rs

@@ -1,60 +0,0 @@
-use std::collections::HashMap;
-use std::rc::Rc;
-
-#[derive(PartialEq, Eq, Copy, Clone, Hash, Debug)]
-pub struct PrimitiveId(pub(crate) usize);
-
-#[derive(PartialEq, Eq, Copy, Clone, Hash, Debug)]
-pub struct ClassId(pub(crate) usize);
-
-#[derive(PartialEq, Eq, Copy, Clone, Hash, Debug)]
-pub struct ParamId(pub(crate) usize);
-
-#[derive(PartialEq, Eq, Copy, Clone, Hash, Debug)]
-pub struct VariableId(pub(crate) usize);
-
-#[derive(PartialEq, Eq, Clone, Hash, Debug)]
-pub enum TypeEnum {
-    BotType,
-    SelfType,
-    PrimitiveType(PrimitiveId),
-    ClassType(ClassId),
-    VirtualClassType(ClassId),
-    ParametricType(ParamId, Vec<Rc<TypeEnum>>),
-    TypeVariable(VariableId),
-}
-
-pub type Type = Rc<TypeEnum>;
-
-#[derive(Clone)]
-pub struct FnDef {
-    // we assume methods first argument to be SelfType,
-    // so the first argument is not contained here
-    pub args: Vec<Type>,
-    pub result: Option<Type>,
-}
-
-#[derive(Clone)]
-pub struct TypeDef<'a> {
-    pub name: &'a str,
-    pub fields: HashMap<&'a str, Type>,
-    pub methods: HashMap<&'a str, FnDef>,
-}
-
-#[derive(Clone)]
-pub struct ClassDef<'a> {
-    pub base: TypeDef<'a>,
-    pub parents: Vec<ClassId>,
-}
-
-#[derive(Clone)]
-pub struct ParametricDef<'a> {
-    pub base: TypeDef<'a>,
-    pub params: Vec<VariableId>,
-}
-
-#[derive(Clone)]
-pub struct VarDef<'a> {
-    pub name: &'a str,
-    pub bound: Vec<Type>,
-}

nac3core/src/typecheck/typedef/test.rs

@@ -0,0 +1,571 @@
+use super::super::magic_methods::with_fields;
+use super::*;
+use indoc::indoc;
+use itertools::Itertools;
+use std::collections::HashMap;
+use test_case::test_case;
+
+impl Unifier {
+    /// Check whether two types are equal.
+    fn eq(&mut self, a: Type, b: Type) -> bool {
+        if a == b {
+            return true;
+        }
+        let (ty_a, ty_b) = {
+            let table = &mut self.unification_table;
+            if table.unioned(a, b) {
+                return true;
+            }
+            (table.probe_value(a).clone(), table.probe_value(b).clone())
+        };
+
+        match (&*ty_a, &*ty_b) {
+            (
+                TypeEnum::TVar { fields: None, id: id1, .. },
+                TypeEnum::TVar { fields: None, id: id2, .. },
+            ) => id1 == id2,
+            (
+                TypeEnum::TVar { fields: Some(map1), .. },
+                TypeEnum::TVar { fields: Some(map2), .. },
+            ) => self.map_eq2(map1, map2),
+            (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::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),
+            // TCall and TFunc are not yet implemented
+            _ => false,
+        }
+    }
+
+    fn map_eq<K>(&mut self, map1: &Mapping<K>, map2: &Mapping<K>) -> bool
+    where
+        K: std::hash::Hash + std::cmp::Eq + std::clone::Clone,
+    {
+        if map1.len() != map2.len() {
+            return false;
+        }
+        for (k, v) in map1.iter() {
+            if !map2.get(k).map(|v1| self.eq(*v, *v1)).unwrap_or(false) {
+                return false;
+            }
+        }
+        true
+    }
+
+    fn map_eq2<K>(&mut self, map1: &Mapping<K, RecordField>, map2: &Mapping<K, RecordField>) -> bool
+    where
+        K: std::hash::Hash + std::cmp::Eq + std::clone::Clone,
+    {
+        if map1.len() != map2.len() {
+            return false;
+        }
+        for (k, v) in map1.iter() {
+            if !map2.get(k).map(|v1| self.eq(v.ty, v1.ty)).unwrap_or(false) {
+                return false;
+            }
+        }
+        true
+    }
+}
+
+struct TestEnvironment {
+    pub unifier: Unifier,
+    pub type_mapping: HashMap<String, Type>,
+}
+
+impl TestEnvironment {
+    fn new() -> TestEnvironment {
+        let mut unifier = Unifier::new();
+        let mut type_mapping = HashMap::new();
+
+        type_mapping.insert(
+            "int".into(),
+            unifier.add_ty(TypeEnum::TObj {
+                obj_id: DefinitionId(0),
+                fields: HashMap::new(),
+                params: HashMap::new(),
+            }),
+        );
+        type_mapping.insert(
+            "float".into(),
+            unifier.add_ty(TypeEnum::TObj {
+                obj_id: DefinitionId(1),
+                fields: HashMap::new(),
+                params: HashMap::new(),
+            }),
+        );
+        type_mapping.insert(
+            "bool".into(),
+            unifier.add_ty(TypeEnum::TObj {
+                obj_id: DefinitionId(2),
+                fields: HashMap::new(),
+                params: HashMap::new(),
+            }),
+        );
+        let (v0, id) = unifier.get_dummy_var();
+        type_mapping.insert(
+            "Foo".into(),
+            unifier.add_ty(TypeEnum::TObj {
+                obj_id: DefinitionId(3),
+                fields: [("a".into(), (v0, true))].iter().cloned().collect::<HashMap<_, _>>(),
+                params: [(id, v0)].iter().cloned().collect::<HashMap<_, _>>(),
+            }),
+        );
+
+        TestEnvironment { unifier, type_mapping }
+    }
+
+    fn parse(&mut self, typ: &str, mapping: &Mapping<String>) -> Type {
+        let result = self.internal_parse(typ, mapping);
+        assert!(result.1.is_empty());
+        result.0
+    }
+
+    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_else(|| typ.len());
+        match &typ[..end] {
+            "tuple" => {
+                let mut s = &typ[end..];
+                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 }), &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!(&s[0..1] == "[");
+                let mut fields = HashMap::new();
+                while &s[0..1] != "]" {
+                    let eq = s.find('=').unwrap();
+                    let key = s[1..eq].into();
+                    let result = self.internal_parse(&s[eq + 1..], mapping);
+                    fields.insert(key, RecordField::new(result.0, true, None));
+                    s = result.1;
+                }
+                (self.unifier.add_record(fields), &s[1..])
+            }
+            x => {
+                let mut s = &typ[end..];
+                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.as_ref() {
+                        if !params.is_empty() {
+                            assert!(&s[0..1] == "[");
+                            let mut p = Vec::new();
+                            while &s[0..1] != "]" {
+                                let result = self.internal_parse(&s[1..], mapping);
+                                p.push(result.0);
+                                s = result.1;
+                            }
+                            s = &s[1..];
+                            ty = self
+                                .unifier
+                                .subst(ty, &params.keys().cloned().zip(p.into_iter()).collect())
+                                .unwrap_or(ty);
+                        }
+                    }
+                    ty
+                });
+                (ty, s)
+            }
+        }
+    }
+
+    fn unify(&mut self, typ1: Type, typ2: Type) -> Result<(), String> {
+        self.unifier.unify(typ1, typ2).map_err(|e| e.to_display(&self.unifier).to_string())
+    }
+}
+
+#[test_case(2,
+    &[("v1", "v2"), ("v2", "float")],
+    &[("v1", "float"), ("v2", "float")]
+    ; "simple variable"
+)]
+#[test_case(2,
+    &[("v1", "list[v2]"), ("v1", "list[float]")],
+    &[("v1", "list[float]"), ("v2", "float")]
+    ; "list element"
+)]
+#[test_case(3,
+    &[
+        ("v1", "Record[a=v3,b=v3]"),
+        ("v2", "Record[b=float,c=v3]"),
+        ("v1", "v2")
+    ],
+    &[
+        ("v1", "Record[a=float,b=float,c=float]"),
+        ("v2", "Record[a=float,b=float,c=float]"),
+        ("v3", "float")
+    ]
+    ; "record merge"
+)]
+#[test_case(3,
+    &[
+        ("v1", "Record[a=float]"),
+        ("v2", "Foo[v3]"),
+        ("v1", "v2")
+    ],
+    &[
+        ("v1", "Foo[float]"),
+        ("v3", "float")
+    ]
+    ; "record obj merge"
+)]
+/// Test cases for valid unifications.
+fn test_unify(
+    variable_count: u32,
+    unify_pairs: &[(&'static str, &'static str)],
+    verify_pairs: &[(&'static str, &'static str)],
+) {
+    let unify_count = unify_pairs.len();
+    // test all permutations...
+    for perm in unify_pairs.iter().permutations(unify_count) {
+        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.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.iter() {
+            let t1 = env.parse(a, &mapping);
+            let t2 = env.parse(b, &mapping);
+            pairs.push((t1, t2));
+        }
+        for (t1, t2) in pairs {
+            env.unifier.unify(t1, t2).unwrap();
+        }
+        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));
+            assert!(env.unifier.eq(t1, t2));
+        }
+    }
+}
+
+#[test_case(2,
+    &[
+        ("v1", "tuple[int]"),
+        ("v2", "list[int]"),
+    ],
+    (("v1", "v2"), "Incompatible types: list[0] and tuple[0]")
+    ; "type mismatch"
+)]
+#[test_case(2,
+    &[
+        ("v1", "tuple[int]"),
+        ("v2", "tuple[float]"),
+    ],
+    (("v1", "v2"), "Incompatible types: 0 and 1")
+    ; "tuple parameter mismatch"
+)]
+#[test_case(2,
+    &[
+        ("v1", "tuple[int,int]"),
+        ("v2", "tuple[int]"),
+    ],
+    (("v1", "v2"), "Tuple length mismatch: got tuple[0, 0] and tuple[0]")
+    ; "tuple length mismatch"
+)]
+#[test_case(3,
+    &[
+        ("v1", "Record[a=float,b=int]"),
+        ("v2", "Foo[v3]"),
+    ],
+    (("v1", "v2"), "`3[typevar4]::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),
+) {
+    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.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.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));
+    for (a, b) in pairs {
+        env.unifier.unify(a, b).unwrap();
+    }
+    assert_eq!(env.unify(t1, t2), Err(erroneous_pair.1.to_string()));
+}
+
+#[test]
+fn test_recursive_subst() {
+    let mut env = TestEnvironment::new();
+    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));
+    });
+    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);
+    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]
+fn test_virtual() {
+    let mut env = TestEnvironment::new();
+    let int = env.parse("int", &HashMap::new());
+    let fun = env.unifier.add_ty(TypeEnum::TFunc(FunSignature {
+        args: vec![],
+        ret: int,
+        vars: HashMap::new(),
+    }));
+    let bar = env.unifier.add_ty(TypeEnum::TObj {
+        obj_id: DefinitionId(5),
+        fields: [("f".into(), (fun, false)), ("a".into(), (int, false))]
+            .iter()
+            .cloned()
+            .collect::<HashMap<StrRef, _>>(),
+        params: HashMap::new(),
+    });
+    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))].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))].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))].iter().cloned().collect());
+    assert_eq!(env.unify(b, d), Err("`virtual[5]::b` field/method does not exist".to_string()));
+}
+
+#[test]
+fn test_typevar_range() {
+    let mut env = TestEnvironment::new();
+    let int = env.parse("int", &HashMap::new());
+    let boolean = env.parse("bool", &HashMap::new());
+    let float = env.parse("float", &HashMap::new());
+    let int_list = env.parse("list[int]", &HashMap::new());
+    let float_list = env.parse("list[float]", &HashMap::new());
+
+    // unification between v and int
+    // where v in (int, bool)
+    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).0;
+    assert_eq!(
+        env.unify(int_list, v),
+        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).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).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).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).0;
+    // unification between v and list[float]
+    // where v in (int, list[v1]), v1 in (int, bool)
+    assert_eq!(
+        env.unify(float_list, v),
+        Err("Expected any one of these types: 0, list[typevar5], but got list[1]\n\nNotes:\n    typevar5 ∈ {0, 2}".to_string())
+    );
+
+    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).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).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::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).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::TList { ty: int });
+    assert_eq!(
+        env.unify(a_list, int_list),
+        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).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),
+        Err("Expected any one of these types: 0, 1, but got 2".into())
+    );
+}
+
+#[test]
+fn test_rigid_var() {
+    let mut env = TestEnvironment::new();
+    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: typevar3 and typevar2".to_string()));
+    env.unifier.unify(list_a, list_x).unwrap();
+    assert_eq!(env.unify(list_x, list_int), Err("Incompatible types: 0 and typevar2".to_string()));
+
+    env.unifier.replace_rigid_var(a, int);
+    env.unifier.unify(list_x, list_int).unwrap();
+}
+
+#[test]
+fn test_instantiation() {
+    let mut env = TestEnvironment::new();
+    let int = env.parse("int", &HashMap::new());
+    let boolean = env.parse("bool", &HashMap::new());
+    let float = env.parse("float", &HashMap::new());
+    let list_int = env.parse("list[int]", &HashMap::new());
+
+    let obj_map: HashMap<_, _> =
+        [(0usize, "int"), (1, "float"), (2, "bool")].iter().cloned().collect();
+
+    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)
+    // v2 = TypeVar('v2', 'list[int]', float)
+    // v3 = TypeVar('v3', tuple[v, v1, v2], t)
+    // what values can v3 take?
+
+    let types = env.unifier.get_instantiations(v3).unwrap();
+    let expected_types = indoc! {"
+        tuple[bool, int, float]
+        tuple[bool, int, list[int]]
+        tuple[bool, list[bool], float]
+        tuple[bool, list[bool], list[int]]
+        tuple[bool, list[int], float]
+        tuple[bool, list[int], list[int]]
+        tuple[int, int, float]
+        tuple[int, int, list[int]]
+        tuple[int, list[bool], float]
+        tuple[int, list[bool], list[int]]
+        tuple[int, list[int], float]
+        tuple[int, list[int], list[int]]
+        v5"
+    }
+    .split('\n')
+    .collect_vec();
+    let types = types
+        .iter()
+        .map(|ty| {
+            env.unifier.internal_stringify(
+                *ty,
+                &mut |i| obj_map.get(&i).unwrap().to_string(),
+                &mut |i| format!("v{}", i),
+                &mut None,
+            )
+        })
+        .sorted()
+        .collect_vec();
+    assert_eq!(expected_types, types);
+}

nac3core/src/typecheck/unification_table.rs

@@ -0,0 +1,169 @@
+use std::rc::Rc;
+
+use itertools::izip;
+
+#[derive(Copy, Clone, PartialEq, Eq, Debug, Hash)]
+pub struct UnificationKey(usize);
+
+#[derive(Clone)]
+pub struct UnificationTable<V> {
+    parents: Vec<usize>,
+    ranks: Vec<u32>,
+    values: Vec<Option<V>>,
+    log: Vec<Action<V>>,
+    generation: u32,
+}
+
+#[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,
+    }
+}
+
+impl<V> Default for UnificationTable<V> {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl<V> UnificationTable<V> {
+    pub fn new() -> UnificationTable<V> {
+        UnificationTable { parents: Vec::new(), ranks: Vec::new(), values: Vec::new(), log: Vec::new(), generation: 0 }
+    }
+
+    pub fn new_key(&mut self, v: V) -> UnificationKey {
+        let index = self.parents.len();
+        self.parents.push(index);
+        self.ranks.push(0);
+        self.values.push(Some(v));
+        UnificationKey(index)
+    }
+
+    pub fn unify(&mut self, a: UnificationKey, b: UnificationKey) {
+        let mut a = self.find(a);
+        let mut b = self.find(b);
+        if a == b {
+            return;
+        }
+        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.parents[b] = a;
+        if self.ranks[a] == self.ranks[b] {
+            self.log.push(Action::Rank { key: a, original_rank: self.ranks[a] });
+            self.ranks[a] += 1;
+        }
+    }
+
+    pub fn probe_value_immutable(&self, key: UnificationKey) -> &V {
+        let mut root = key.0;
+        let mut parent = self.parents[root];
+        while root != parent {
+            root = parent;
+            // parent = root.parent
+            parent = self.parents[parent];
+        }
+        self.values[parent].as_ref().unwrap()
+    }
+
+    pub fn probe_value(&mut self, a: UnificationKey) -> &V {
+        let index = self.find(a);
+        self.values[index].as_ref().unwrap()
+    }
+
+    pub fn set_value(&mut self, a: UnificationKey, v: V) {
+        let index = self.find(a);
+        let original_value = self.values[index].replace(v);
+        self.log.push(Action::Value { key: index, original_value });
+    }
+
+    pub fn unioned(&mut self, a: UnificationKey, b: UnificationKey) -> bool {
+        self.find(a) == self.find(b)
+    }
+
+    pub fn get_representative(&mut self, key: UnificationKey) -> UnificationKey {
+        UnificationKey(self.find(key))
+    }
+
+    fn find(&mut self, key: UnificationKey) -> usize {
+        let mut root = key.0;
+        let mut parent = self.parents[root];
+        while root != parent {
+            // 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.parents[root] = a;
+            root = parent;
+            // parent = root.parent
+            parent = a;
+        }
+        parent
+    }
+
+    pub fn get_snapshot(&mut self) -> (usize, u32) {
+        let generation = self.generation;
+        self.log.push(Action::Marker { generation });
+        self.generation += 1;
+        (self.log.len(), generation)
+    }
+
+    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");
+        for action in self.log.drain(log_len - 1..).rev() {
+            match action {
+                Action::Parent { key, original_parent } => {
+                    self.parents[key] = original_parent;
+                }
+                Action::Value { key, original_value } => {
+                    self.values[key] = original_value;
+                }
+                Action::Rank { key, original_rank } => {
+                    self.ranks[key] = original_rank;
+                }
+                Action::Marker { .. } => {}
+            }
+        }
+    }
+
+    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();
+    }
+}
+
+impl<V> UnificationTable<Rc<V>>
+where
+    V: Clone,
+{
+    pub fn get_send(&self) -> UnificationTable<V> {
+        let values = izip!(self.values.iter(), self.parents.iter())
+            .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 }
+    }
+
+    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 }
+    }
+}

nac3embedded/Cargo.toml

@@ -1,15 +0,0 @@
-[package]
-name = "nac3embedded"
-version = "0.1.0"
-authors = ["M-Labs"]
-edition = "2018"
-
-[lib]
-name = "nac3embedded"
-crate-type = ["cdylib"]
-
-[dependencies]
-pyo3 = { version = "0.12.4", features = ["extension-module"] }
-inkwell = { git = "https://github.com/TheDan64/inkwell", branch = "master", features = ["llvm10-0"] }
-rustpython-parser = { git = "https://github.com/RustPython/RustPython", branch = "master" }
-nac3core = { path = "../nac3core" }

nac3embedded/demo.py

@@ -1,11 +0,0 @@
-from language import *
-
-
-class Demo:
-    @kernel
-    def run(self: bool) -> bool:
-        return False
-
-
-if __name__ == "__main__":
-    Demo().run()

nac3embedded/language.py

@@ -1,19 +0,0 @@
-from functools import wraps
-
-import nac3embedded
-
-
-__all__ = ["kernel", "portable"]
-
-
-def kernel(function):
-    @wraps(function)
-    def run_on_core(self, *args, **kwargs):
-        nac3 = nac3embedded.NAC3()
-        nac3.register_host_object(self)
-        nac3.compile_method(self, function.__name__)
-    return run_on_core
-
-
-def portable(function):
-    return fn

nac3embedded/nac3embedded.so

@@ -1 +0,0 @@
-../target/release/libnac3embedded.so

nac3embedded/src/lib.rs

@@ -1,116 +0,0 @@
-use std::collections::HashMap;
-use std::collections::hash_map::Entry;
-
-use pyo3::prelude::*;
-use pyo3::exceptions;
-use rustpython_parser::{ast, parser};
-use inkwell::context::Context;
-use inkwell::targets::*;
-
-use nac3core::CodeGen;
-
-fn runs_on_core(decorator_list: &[ast::Expression]) -> bool {
-    for decorator in decorator_list.iter() {
-        if let ast::ExpressionType::Identifier { name } = &decorator.node {
-            if name == "kernel" || name == "portable" {
-                return true
-            }
-        }
-    }
-    false
-}
-
-#[pyclass(name=NAC3)]
-struct Nac3 {
-    type_definitions: HashMap<i64, ast::Program>,
-    host_objects: HashMap<i64, i64>,
-}
-
-#[pymethods]
-impl Nac3 {
-    #[new]
-    fn new() -> Self {
-        Nac3 {
-            type_definitions: HashMap::new(),
-            host_objects: HashMap::new(),
-        }
-    }
-
-    fn register_host_object(&mut self, obj: PyObject) -> PyResult<()> {
-        Python::with_gil(|py| -> PyResult<()> {
-            let obj: &PyAny = obj.extract(py)?;
-            let obj_type = obj.get_type();
-
-            let builtins = PyModule::import(py, "builtins")?;
-            let type_id = builtins.call1("id", (obj_type, ))?.extract()?;
-
-            let entry = self.type_definitions.entry(type_id);
-            if let Entry::Vacant(entry) = entry {
-                let source = PyModule::import(py, "inspect")?.call1("getsource", (obj_type, ))?;
-                let ast = parser::parse_program(source.extract()?).map_err(|e|
-                    exceptions::PySyntaxError::new_err(format!("failed to parse host object source: {}", e)))?;
-                entry.insert(ast);
-                // TODO: examine AST and recursively register dependencies
-            };
-
-            let obj_id = builtins.call1("id", (obj, ))?.extract()?;
-            match self.host_objects.entry(obj_id) {
-                Entry::Vacant(entry) => entry.insert(type_id),
-                Entry::Occupied(_) => return Err(
-                    exceptions::PyValueError::new_err("host object registered twice")),
-            };
-            // TODO: collect other information about host object, e.g. value of fields
-
-            Ok(())
-        })
-    }
-
-    fn compile_method(&self, obj: PyObject, name: String) -> PyResult<()> {
-        Python::with_gil(|py| -> PyResult<()> {
-            let obj: &PyAny = obj.extract(py)?;
-            let builtins = PyModule::import(py, "builtins")?;
-            let obj_id = builtins.call1("id", (obj, ))?.extract()?;
-
-            let type_id = self.host_objects.get(&obj_id).ok_or_else(||
-                exceptions::PyKeyError::new_err("type of host object not found"))?;
-            let ast = self.type_definitions.get(&type_id).ok_or_else(||
-                exceptions::PyKeyError::new_err("type definition not found"))?;
-
-            if let ast::StatementType::ClassDef {
-                    name: _,
-                    body,
-                    bases: _,
-                    keywords: _,
-                    decorator_list: _ } = &ast.statements[0].node {
-                for statement in body.iter() {
-                    if let ast::StatementType::FunctionDef {
-                            is_async: _,
-                            name: funcdef_name,
-                            args: _,
-                            body: _,
-                            decorator_list,
-                            returns: _ } = &statement.node {
-                        if runs_on_core(decorator_list) && funcdef_name == &name {
-                            let context = Context::create();
-                            let mut codegen = CodeGen::new(&context);
-                            codegen.compile_toplevel(&body[0]).map_err(|e|
-                                exceptions::PyRuntimeError::new_err(format!("compilation failed: {}", e)))?;
-                            codegen.print_ir();
-                        }
-                    }
-                }
-            } else {
-                return Err(exceptions::PyValueError::new_err("expected ClassDef for type definition"));
-            }
-
-            Ok(())
-        })
-    }
-}
-
-#[pymodule]
-fn nac3embedded(_py: Python, m: &PyModule) -> PyResult<()> {
-    Target::initialize_all(&InitializationConfig::default());
-    m.add_class::<Nac3>()?;
-    Ok(())
-}

nac3parser/Cargo.toml

@@ -0,0 +1,24 @@
+[package]
+name = "nac3parser"
+version = "0.1.2"
+description = "Parser for python code."
+authors = [ "RustPython Team", "M-Labs" ]
+build = "build.rs"
+license = "MIT"
+edition = "2018"
+
+[build-dependencies]
+lalrpop = "0.19.6"
+
+[dependencies]
+nac3ast = { path = "../nac3ast" }
+lalrpop-util = "0.19.6"
+log = "0.4.1"
+unic-emoji-char = "0.9"
+unic-ucd-ident  = "0.9"
+unicode_names2 = "0.4"
+phf = { version = "0.9", features = ["macros"] }
+ahash = "0.7.2"
+
+[dev-dependencies]
+insta = "=1.11.0"

nac3parser/README.md

@@ -0,0 +1,56 @@
+# nac3parser
+
+This directory has the code for python lexing, parsing and generating Abstract Syntax Trees (AST).
+
+This is the RustPython parser with modifications for NAC3.
+
+The steps are:
+- Lexical analysis: splits the source code into tokens.
+- Parsing and generating the AST: transforms those tokens into an AST. Uses `LALRPOP`, a Rust parser generator framework.
+
+The RustPython team wrote [a blog post](https://rustpython.github.io/2020/04/02/thing-explainer-parser.html) with screenshots and an explanation to help you understand the steps by seeing them in action.
+
+For more information on LALRPOP, here is a link to the [LALRPOP book](https://github.com/lalrpop/lalrpop).
+
+There is a readme in the `src` folder with the details of each file.
+
+
+## Directory content
+
+`build.rs`: The build script.
+`Cargo.toml`: The config file.
+
+The `src` directory has:
+
+**lib.rs**   
+This is the crate's root.
+
+**lexer.rs**   
+This module takes care of lexing python source text. This means source code is translated into separate tokens.
+
+**parser.rs**   
+A python parsing module. Use this module to parse python code into an AST. There are three ways to parse python code. You could parse a whole program, a single statement, or a single expression.
+
+**ast.rs**   
+ Implements abstract syntax tree (AST) nodes for the python language. Roughly equivalent to [the python AST](https://docs.python.org/3/library/ast.html).
+
+**python.lalrpop**   
+Python grammar.
+
+**token.rs**   
+Different token definitions. Loosely based on token.h from CPython source.
+
+**errors.rs**   
+Define internal parse error types. The goal is to provide a matching and a safe error API, masking errors from LALR.
+
+**fstring.rs**   
+Format strings.
+
+**function.rs**   
+Collection of functions for parsing parameters, arguments.
+
+**location.rs**   
+Datatypes to support source location information.
+
+**mode.rs**   
+Execution mode check. Allowed modes are `exec`, `eval` or `single`.

nac3parser/build.rs

@@ -0,0 +1,3 @@
+fn main() {
+    lalrpop::process_root().unwrap()
+}

nac3parser/src/config_comment_helper.rs

@@ -0,0 +1,85 @@
+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>
+) -> Result<Vec<Ident>, ParseError<Location, Tok, LexicalError>> {
+    if com_loc.column() != stmt_loc.column() && !nac3com_above.is_empty() {
+        return Err(ParseError::User {
+            error: LexicalError {
+                location: com_loc,
+                error: LexicalErrorType::OtherError(
+                    format!(
+                        "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()
+    )
+}
+
+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 {
+                location: com_above_loc,
+                error: LexicalErrorType::OtherError(
+                    format!(
+                        "config comment at top must have the same indentation with what it applies (comment at {}, statement at {})",
+                        com_above_loc,
+                        stmts[0].location,
+                    )
+                )
+            }
+        })
+    }
+    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])
+    );
+    Ok(())
+}
+
+fn apply_config_comments<U>(stmt: &mut Stmt<U>, comments: Vec<Ident>) {
+    match &mut stmt.node {
+        StmtKind::Pass { config_comment, .. }
+        | StmtKind::Delete { config_comment, .. }
+        | StmtKind::Expr { config_comment, .. }
+        | StmtKind::Assign { config_comment, .. }
+        | StmtKind::AugAssign { config_comment, .. }
+        | StmtKind::AnnAssign { config_comment, .. }
+        | StmtKind::Break { config_comment, .. }
+        | StmtKind::Continue { config_comment, .. }
+        | StmtKind::Return { config_comment, .. } 
+        | StmtKind::Raise { config_comment, .. }
+        | StmtKind::Import { config_comment, .. }
+        | StmtKind::ImportFrom { config_comment, .. }
+        | StmtKind::Global { config_comment, .. }
+        | StmtKind::Nonlocal { config_comment, .. }
+        | StmtKind::Assert { config_comment, .. } => config_comment.extend(comments),
+
+        _ => { unreachable!("only small statements should call this function") }
+    }
+}

nac3parser/src/error.rs

@@ -0,0 +1,239 @@
+//! Define internal parse error types
+//! The goal is to provide a matching and a safe error API, maksing errors from LALR
+use lalrpop_util::ParseError as LalrpopError;
+
+use crate::ast::Location;
+use crate::token::Tok;
+
+use std::error::Error;
+use std::fmt;
+
+/// Represents an error during lexical scanning.
+#[derive(Debug, PartialEq)]
+pub struct LexicalError {
+    pub error: LexicalErrorType,
+    pub location: Location,
+}
+
+#[derive(Debug, PartialEq)]
+pub enum LexicalErrorType {
+    StringError,
+    UnicodeError,
+    NestingError,
+    IndentationError,
+    TabError,
+    TabsAfterSpaces,
+    DefaultArgumentError,
+    PositionalArgumentError,
+    DuplicateKeywordArgumentError,
+    UnrecognizedToken { tok: char },
+    FStringError(FStringErrorType),
+    LineContinuationError,
+    Eof,
+    OtherError(String),
+}
+
+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::UnicodeError => write!(f, "Got unexpected unicode"),
+            LexicalErrorType::NestingError => write!(f, "Got unexpected nesting"),
+            LexicalErrorType::IndentationError => {
+                write!(f, "unindent does not match any outer indentation level")
+            }
+            LexicalErrorType::TabError => {
+                write!(f, "inconsistent use of tabs and spaces in indentation")
+            }
+            LexicalErrorType::TabsAfterSpaces => {
+                write!(f, "Tabs not allowed as part of indentation after spaces")
+            }
+            LexicalErrorType::DefaultArgumentError => {
+                write!(f, "non-default argument follows default argument")
+            }
+            LexicalErrorType::DuplicateKeywordArgumentError => {
+                write!(f, "keyword argument repeated")
+            }
+            LexicalErrorType::PositionalArgumentError => {
+                write!(f, "positional argument follows keyword argument")
+            }
+            LexicalErrorType::UnrecognizedToken { 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),
+        }
+    }
+}
+
+// TODO: consolidate these with ParseError
+#[derive(Debug, PartialEq)]
+pub struct FStringError {
+    pub error: FStringErrorType,
+    pub location: Location,
+}
+
+#[derive(Debug, PartialEq)]
+pub enum FStringErrorType {
+    UnclosedLbrace,
+    UnopenedRbrace,
+    ExpectedRbrace,
+    InvalidExpression(Box<ParseErrorType>),
+    InvalidConversionFlag,
+    EmptyExpression,
+    MismatchedDelimiter,
+    ExpressionNestedTooDeeply,
+}
+
+impl fmt::Display for FStringErrorType {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        match self {
+            FStringErrorType::UnclosedLbrace => write!(f, "Unclosed '{{'"),
+            FStringErrorType::UnopenedRbrace => write!(f, "Unopened '}}'"),
+            FStringErrorType::ExpectedRbrace => write!(f, "Expected '}}' after conversion flag."),
+            FStringErrorType::InvalidExpression(error) => {
+                write!(f, "Invalid expression: {}", error)
+            }
+            FStringErrorType::InvalidConversionFlag => write!(f, "Invalid conversion flag"),
+            FStringErrorType::EmptyExpression => write!(f, "Empty expression"),
+            FStringErrorType::MismatchedDelimiter => write!(f, "Mismatched delimiter"),
+            FStringErrorType::ExpressionNestedTooDeeply => {
+                write!(f, "expressions nested too deeply")
+            }
+        }
+    }
+}
+
+impl From<FStringError> for LalrpopError<Location, Tok, LexicalError> {
+    fn from(err: FStringError) -> Self {
+        lalrpop_util::ParseError::User {
+            error: LexicalError {
+                error: LexicalErrorType::FStringError(err.error),
+                location: err.location,
+            },
+        }
+    }
+}
+
+/// Represents an error during parsing
+#[derive(Debug, PartialEq)]
+pub struct ParseError {
+    pub error: ParseErrorType,
+    pub location: Location,
+}
+
+#[derive(Debug, PartialEq)]
+pub enum ParseErrorType {
+    /// Parser encountered an unexpected end of input
+    Eof,
+    /// Parser encountered an extra token
+    ExtraToken(Tok),
+    /// Parser encountered an invalid token
+    InvalidToken,
+    /// Parser encountered an unexpected token
+    UnrecognizedToken(Tok, Option<String>),
+    /// Maps to `User` type from `lalrpop-util`
+    Lexical(LexicalErrorType),
+}
+
+/// Convert `lalrpop_util::ParseError` to our internal type
+impl From<LalrpopError<Location, Tok, LexicalError>> for ParseError {
+    fn from(err: LalrpopError<Location, Tok, LexicalError>) -> Self {
+        match err {
+            // 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
+                };
+                ParseError {
+                    error: ParseErrorType::UnrecognizedToken(token.1, expected),
+                    location: token.0,
+                }
+            }
+            LalrpopError::UnrecognizedEOF { location, .. } => ParseError {
+                error: ParseErrorType::Eof,
+                location,
+            },
+        }
+    }
+}
+
+impl fmt::Display for ParseError {
+    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
+        write!(f, "{} at {}", self.error, self.location)
+    }
+}
+
+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::InvalidToken => write!(f, "Got invalid token"),
+            ParseErrorType::UnrecognizedToken(ref tok, ref expected) => {
+                if *tok == Tok::Indent {
+                    write!(f, "unexpected indent")
+                } else if expected.as_deref() == Some("Indent") {
+                    write!(f, "expected an indented block")
+                } else {
+                    write!(f, "Got unexpected token {}", tok)
+                }
+            }
+            ParseErrorType::Lexical(ref error) => write!(f, "{}", error),
+        }
+    }
+}
+
+impl Error for ParseErrorType {}
+
+impl ParseErrorType {
+    pub fn is_indentation_error(&self) -> bool {
+        match self {
+            ParseErrorType::Lexical(LexicalErrorType::IndentationError) => true,
+            ParseErrorType::UnrecognizedToken(token, expected) => {
+                *token == Tok::Indent || expected.clone() == Some("Indent".to_owned())
+            }
+            _ => false,
+        }
+    }
+    pub fn is_tab_error(&self) -> bool {
+        matches!(
+            self,
+            ParseErrorType::Lexical(LexicalErrorType::TabError)
+                | ParseErrorType::Lexical(LexicalErrorType::TabsAfterSpaces)
+        )
+    }
+}
+
+impl std::ops::Deref for ParseError {
+    type Target = ParseErrorType;
+    fn deref(&self) -> &Self::Target {
+        &self.error
+    }
+}
+
+impl Error for ParseError {
+    fn source(&self) -> Option<&(dyn Error + 'static)> {
+        None
+    }
+}

nac3parser/src/fstring.rs

@@ -0,0 +1,405 @@
+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::*;
+
+struct FStringParser<'a> {
+    chars: iter::Peekable<str::Chars<'a>>,
+    str_location: Location,
+}
+
+impl<'a> FStringParser<'a> {
+    fn new(source: &'a str, str_location: Location) -> Self {
+        Self {
+            chars: source.chars().peekable(),
+            str_location,
+        }
+    }
+
+    #[inline]
+    fn expr(&self, node: ExprKind) -> Expr {
+        Expr::new(self.str_location, node)
+    }
+
+    fn parse_formatted_value(&mut self) -> Result<Vec<Expr>, FStringErrorType> {
+        let mut expression = String::new();
+        let mut spec = None;
+        let mut delims = Vec::new();
+        let mut conversion = None;
+        let mut pred_expression_text = String::new();
+        let mut trailing_seq = String::new();
+
+        while let Some(ch) = self.chars.next() {
+            match ch {
+                // can be integrated better with the remainign code, but as a starting point ok
+                // in general I would do here a tokenizing of the fstrings to omit this peeking.
+                '!' if self.chars.peek() == Some(&'=') => {
+                    expression.push_str("!=");
+                    self.chars.next();
+                }
+
+                '=' if self.chars.peek() == Some(&'=') => {
+                    expression.push_str("==");
+                    self.chars.next();
+                }
+
+                '>' if self.chars.peek() == Some(&'=') => {
+                    expression.push_str(">=");
+                    self.chars.next();
+                }
+
+                '<' if self.chars.peek() == Some(&'=') => {
+                    expression.push_str("<=");
+                    self.chars.next();
+                }
+
+                '!' if delims.is_empty() && self.chars.peek() != Some(&'=') => {
+                    if expression.trim().is_empty() {
+                        return Err(EmptyExpression);
+                    }
+
+                    conversion = Some(match self.chars.next() {
+                        Some('s') => ConversionFlag::Str,
+                        Some('a') => ConversionFlag::Ascii,
+                        Some('r') => ConversionFlag::Repr,
+                        Some(_) => {
+                            return Err(InvalidConversionFlag);
+                        }
+                        None => {
+                            return Err(ExpectedRbrace);
+                        }
+                    });
+
+                    if let Some(&peek) = self.chars.peek() {
+                        if peek != '}' && peek != ':' {
+                            return Err(ExpectedRbrace);
+                        }
+                    } else {
+                        return Err(ExpectedRbrace);
+                    }
+                }
+
+                // match a python 3.8 self documenting expression
+                // format '{' PYTHON_EXPRESSION '=' FORMAT_SPECIFIER? '}'
+                '=' if self.chars.peek() != Some(&'=') && delims.is_empty() => {
+                    pred_expression_text = expression.to_string(); // safe expression before = to print it
+                }
+
+                ':' if delims.is_empty() => {
+                    let mut nested = false;
+                    let mut in_nested = false;
+                    let mut spec_expression = String::new();
+                    while let Some(&next) = self.chars.peek() {
+                        match next {
+                            '{' => {
+                                if in_nested {
+                                    return Err(ExpressionNestedTooDeeply);
+                                }
+                                in_nested = true;
+                                nested = true;
+                                self.chars.next();
+                                continue;
+                            }
+                            '}' => {
+                                if in_nested {
+                                    in_nested = false;
+                                    self.chars.next();
+                                }
+                                break;
+                            }
+                            _ => (),
+                        }
+                        spec_expression.push(next);
+                        self.chars.next();
+                    }
+                    if in_nested {
+                        return Err(UnclosedLbrace);
+                    }
+                    spec = Some(if nested {
+                        Box::new(
+                            self.expr(ExprKind::FormattedValue {
+                                value: Box::new(
+                                    parse_fstring_expr(&spec_expression)
+                                        .map_err(|e| InvalidExpression(Box::new(e.error)))?,
+                                ),
+                                conversion: None,
+                                format_spec: None,
+                            }),
+                        )
+                    } else {
+                        Box::new(self.expr(ExprKind::Constant {
+                            value: spec_expression.to_owned().into(),
+                            kind: None,
+                        }))
+                    })
+                }
+                '(' | '{' | '[' => {
+                    expression.push(ch);
+                    delims.push(ch);
+                }
+                ')' => {
+                    if delims.pop() != Some('(') {
+                        return Err(MismatchedDelimiter);
+                    }
+                    expression.push(ch);
+                }
+                ']' => {
+                    if delims.pop() != Some('[') {
+                        return Err(MismatchedDelimiter);
+                    }
+                    expression.push(ch);
+                }
+                '}' if !delims.is_empty() => {
+                    if delims.pop() != Some('{') {
+                        return Err(MismatchedDelimiter);
+                    }
+                    expression.push(ch);
+                }
+                '}' => {
+                    if expression.is_empty() {
+                        return Err(EmptyExpression);
+                    }
+                    let ret = if pred_expression_text.is_empty() {
+                        vec![self.expr(ExprKind::FormattedValue {
+                            value: Box::new(
+                                parse_fstring_expr(&expression)
+                                    .map_err(|e| InvalidExpression(Box::new(e.error)))?,
+                            ),
+                            conversion,
+                            format_spec: spec,
+                        })]
+                    } else {
+                        vec![
+                            self.expr(ExprKind::Constant {
+                                value: Constant::Str(pred_expression_text + "="),
+                                kind: None,
+                            }),
+                            self.expr(ExprKind::Constant {
+                                value: trailing_seq.into(),
+                                kind: None,
+                            }),
+                            self.expr(ExprKind::FormattedValue {
+                                value: Box::new(
+                                    parse_fstring_expr(&expression)
+                                        .map_err(|e| InvalidExpression(Box::new(e.error)))?,
+                                ),
+                                conversion,
+                                format_spec: spec,
+                            }),
+                        ]
+                    };
+                    return Ok(ret);
+                }
+                '"' | '\'' => {
+                    expression.push(ch);
+                    for next in &mut self.chars {
+                        expression.push(next);
+                        if next == ch {
+                            break;
+                        }
+                    }
+                }
+                ' ' if !pred_expression_text.is_empty() => {
+                    trailing_seq.push(ch);
+                }
+                _ => {
+                    expression.push(ch);
+                }
+            }
+        }
+        Err(UnclosedLbrace)
+    }
+
+    fn parse(mut self) -> Result<Expr, FStringErrorType> {
+        let mut content = String::new();
+        let mut values = vec![];
+
+        while let Some(ch) = self.chars.next() {
+            match ch {
+                '{' => {
+                    if let Some('{') = self.chars.peek() {
+                        self.chars.next();
+                        content.push('{');
+                    } else {
+                        if !content.is_empty() {
+                            values.push(self.expr(ExprKind::Constant {
+                                value: mem::take(&mut content).into(),
+                                kind: None,
+                            }));
+                        }
+
+                        values.extend(self.parse_formatted_value()?);
+                    }
+                }
+                '}' => {
+                    if let Some('}') = self.chars.peek() {
+                        self.chars.next();
+                        content.push('}');
+                    } else {
+                        return Err(UnopenedRbrace);
+                    }
+                }
+                _ => {
+                    content.push(ch);
+                }
+            }
+        }
+
+        if !content.is_empty() {
+            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,
+            }),
+            1 => values.into_iter().next().unwrap(),
+            _ => self.expr(ExprKind::JoinedStr { values }),
+        };
+        Ok(s)
+    }
+}
+
+fn parse_fstring_expr(source: &str) -> Result<Expr, ParseError> {
+    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 })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn parse_fstring(source: &str) -> Result<Expr, FStringErrorType> {
+        FStringParser::new(source, Location::default()).parse()
+    }
+
+    #[test]
+    fn test_parse_fstring() {
+        let source = "{a}{ b }{{foo}}";
+        let parse_ast = parse_fstring(&source).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_fstring_nested_spec() {
+        let source = "{foo:{spec}}";
+        let parse_ast = parse_fstring(&source).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_fstring_not_nested_spec() {
+        let source = "{foo:spec}";
+        let parse_ast = parse_fstring(&source).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_empty_fstring() {
+        insta::assert_debug_snapshot!(parse_fstring("").unwrap());
+    }
+
+    #[test]
+    fn test_fstring_parse_selfdocumenting_base() {
+        let src = "{user=}";
+        let parse_ast = parse_fstring(&src).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_fstring_parse_selfdocumenting_base_more() {
+        let src = "mix {user=} with text and {second=}";
+        let parse_ast = parse_fstring(&src).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_fstring_parse_selfdocumenting_format() {
+        let src = "{user=:>10}";
+        let parse_ast = parse_fstring(&src).unwrap();
+
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_invalid_fstring() {
+        assert_eq!(parse_fstring("{5!a"), Err(ExpectedRbrace));
+        assert_eq!(parse_fstring("{5!a1}"), Err(ExpectedRbrace));
+        assert_eq!(parse_fstring("{5!"), Err(ExpectedRbrace));
+        assert_eq!(parse_fstring("abc{!a 'cat'}"), Err(EmptyExpression));
+        assert_eq!(parse_fstring("{!a"), Err(EmptyExpression));
+        assert_eq!(parse_fstring("{ !a}"), Err(EmptyExpression));
+
+        assert_eq!(parse_fstring("{5!}"), Err(InvalidConversionFlag));
+        assert_eq!(parse_fstring("{5!x}"), Err(InvalidConversionFlag));
+
+        assert_eq!(parse_fstring("{a:{a:{b}}"), Err(ExpressionNestedTooDeeply));
+
+        assert_eq!(parse_fstring("{a:b}}"), Err(UnopenedRbrace));
+        assert_eq!(parse_fstring("}"), Err(UnopenedRbrace));
+        assert_eq!(parse_fstring("{a:{b}"), Err(UnclosedLbrace));
+        assert_eq!(parse_fstring("{"), Err(UnclosedLbrace));
+
+        assert_eq!(parse_fstring("{}"), Err(EmptyExpression));
+
+        // TODO: check for InvalidExpression enum?
+        assert!(parse_fstring("{class}").is_err());
+    }
+
+    #[test]
+    fn test_parse_fstring_not_equals() {
+        let source = "{1 != 2}";
+        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();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_fstring_selfdoc_prec_space() {
+        let source = "{x   =}";
+        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();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_fstring_yield_expr() {
+        let source = "{yield}";
+        let parse_ast = parse_fstring(&source).unwrap();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+}

nac3parser/src/function.rs

@@ -0,0 +1,96 @@
+use ahash::RandomState;
+use std::collections::HashSet;
+
+use crate::ast;
+use crate::error::{LexicalError, LexicalErrorType};
+
+pub struct ArgumentList {
+    pub args: Vec<ast::Expr>,
+    pub keywords: Vec<ast::Keyword>,
+}
+
+type ParameterDefs = (Vec<ast::Arg>, Vec<ast::Arg>, Vec<ast::Expr>);
+type ParameterDef = (ast::Arg, Option<ast::Expr>);
+
+pub fn parse_params(
+    params: (Vec<ParameterDef>, Vec<ParameterDef>),
+) -> Result<ParameterDefs, LexicalError> {
+    let mut posonly = Vec::with_capacity(params.0.len());
+    let mut names = Vec::with_capacity(params.1.len());
+    let mut defaults = vec![];
+
+    let mut try_default = |name: &ast::Arg, default| {
+        if let Some(default) = default {
+            defaults.push(default);
+        } else if !defaults.is_empty() {
+            // Once we have started with defaults, all remaining arguments must
+            // have defaults
+            return Err(LexicalError {
+                error: LexicalErrorType::DefaultArgumentError,
+                location: name.location,
+            });
+        }
+        Ok(())
+    };
+
+    for (name, default) in params.0 {
+        try_default(&name, default)?;
+        posonly.push(name);
+    }
+
+    for (name, default) in params.1 {
+        try_default(&name, default)?;
+        names.push(name);
+    }
+
+    Ok((posonly, names, defaults))
+}
+
+type FunctionArgument = (Option<(ast::Location, Option<String>)>, ast::Expr);
+
+pub fn parse_args(func_args: Vec<FunctionArgument>) -> Result<ArgumentList, LexicalError> {
+    let mut args = vec![];
+    let mut keywords = vec![];
+
+    let mut keyword_names = HashSet::with_capacity_and_hasher(func_args.len(), RandomState::new());
+    for (name, value) in func_args {
+        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::PositionalArgumentError,
+                        location: value.location,
+                    });
+                }
+
+                args.push(value);
+            }
+        }
+    }
+    Ok(ArgumentList { args, keywords })
+}
+
+fn is_starred(exp: &ast::Expr) -> bool {
+    matches!(exp.node, ast::ExprKind::Starred { .. })
+}

nac3parser/src/lib.rs

@@ -0,0 +1,35 @@
+//! This crate can be used to parse python sourcecode into a so
+//! called AST (abstract syntax tree).
+//!
+//! The stages involved in this process are lexical analysis and
+//! parsing. The lexical analysis splits the sourcecode into
+//! tokens, and the parsing transforms those tokens into an AST.
+//!
+//! For example, one could do this:
+//!
+//! ```
+//! use nac3parser::{parser, ast};
+//!
+//! let python_source = "print('Hello world')";
+//! let python_ast = parser::parse_expression(python_source).unwrap();
+//!
+//! ```
+
+#[macro_use]
+extern crate log;
+use lalrpop_util::lalrpop_mod;
+pub use nac3ast as ast;
+
+pub mod error;
+mod fstring;
+mod function;
+pub mod lexer;
+pub mod mode;
+pub mod parser;
+lalrpop_mod!(
+    #[allow(clippy::all)]
+    #[allow(unused)]
+    python
+);
+pub mod token;
+pub mod config_comment_helper;

nac3parser/src/mode.rs

@@ -0,0 +1,40 @@
+use crate::token::Tok;
+
+#[derive(Clone, Copy)]
+pub enum Mode {
+    Module,
+    Interactive,
+    Expression,
+}
+
+impl Mode {
+    pub(crate) fn to_marker(self) -> Tok {
+        match self {
+            Self::Module => Tok::StartModule,
+            Self::Interactive => Tok::StartInteractive,
+            Self::Expression => Tok::StartExpression,
+        }
+    }
+}
+
+impl std::str::FromStr for Mode {
+    type Err = ModeParseError;
+    fn from_str(s: &str) -> Result<Self, ModeParseError> {
+        match s {
+            "exec" | "single" => Ok(Mode::Module),
+            "eval" => Ok(Mode::Expression),
+            _ => Err(ModeParseError { _priv: () }),
+        }
+    }
+}
+
+#[derive(Debug)]
+pub struct ModeParseError {
+    _priv: (),
+}
+
+impl std::fmt::Display for ModeParseError {
+    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
+        write!(f, r#"mode should be "exec", "eval", or "single""#)
+    }
+}

nac3parser/src/parser.rs

@@ -0,0 +1,229 @@
+//! Python parsing.
+//!
+//! Use this module to parse python code into an AST.
+//! There are three ways to parse python code. You could
+//! parse a whole program, a single statement, or a single
+//! expression.
+
+use std::iter;
+
+use crate::ast::{self, FileName};
+use crate::error::ParseError;
+use crate::lexer;
+pub use crate::mode::Mode;
+use crate::python;
+
+/*
+ * Parse python code.
+ * Grammar may be inspired by antlr grammar for python:
+ * https://github.com/antlr/grammars-v4/tree/master/python3
+ */
+
+/// Parse a full python program, containing usually multiple lines.
+pub fn parse_program(source: &str, file: FileName) -> Result<ast::Suite, ParseError> {
+    parse(source, Mode::Module, file).map(|top| match top {
+        ast::Mod::Module { body, .. } => body,
+        _ => unreachable!(),
+    })
+}
+
+/// Parses a python expression
+///
+/// # Example
+/// ```
+/// use nac3parser::{parser, ast};
+/// let expr = parser::parse_expression("1 + 2").unwrap();
+///
+/// assert_eq!(
+///     expr,
+///     ast::Expr {
+///         location: ast::Location::new(1, 3, Default::default()),
+///         custom: (),
+///         node: ast::ExprKind::BinOp {
+///             left: Box::new(ast::Expr {
+///                 location: ast::Location::new(1, 1, Default::default()),
+///                 custom: (),
+///                 node: ast::ExprKind::Constant {
+///                     value: ast::Constant::Int(1.into()),
+///                     kind: None,
+///                 }
+///             }),
+///             op: ast::Operator::Add,
+///             right: Box::new(ast::Expr {
+///                 location: ast::Location::new(1, 5, Default::default()),
+///                 custom: (),
+///                 node: ast::ExprKind::Constant {
+///                     value: ast::Constant::Int(2.into()),
+///                     kind: None,
+///                 }
+///             })
+///         }
+///     },
+/// );
+///
+/// ```
+pub fn parse_expression(source: &str) -> Result<ast::Expr, ParseError> {
+    parse(source, Mode::Expression, Default::default()).map(|top| match top {
+        ast::Mod::Expression { body } => *body,
+        _ => unreachable!(),
+    })
+}
+
+// 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 = (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)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_parse_empty() {
+        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, 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, 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, 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, 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, Default::default()).unwrap();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_tuples() {
+        let source = "a, b = 4, 5";
+
+        insta::assert_debug_snapshot!(parse_program(source, Default::default()).unwrap());
+    }
+
+    #[test]
+    fn test_parse_class() {
+        let source = "\
+class Foo(A, B):
+ def __init__(self):
+  pass
+ def method_with_default(self, arg='default'):
+  pass";
+        insta::assert_debug_snapshot!(parse_program(source, Default::default()).unwrap());
+    }
+
+    #[test]
+    fn test_parse_dict_comprehension() {
+        let source = String::from("{x1: x2 for y in z}");
+        let parse_ast = parse_expression(&source).unwrap();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_list_comprehension() {
+        let source = String::from("[x for y in z]");
+        let parse_ast = parse_expression(&source).unwrap();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+
+    #[test]
+    fn test_parse_double_list_comprehension() {
+        let source = String::from("[x for y, y2 in z for a in b if a < 5 if a > 10]");
+        let parse_ast = parse_expression(&source).unwrap();
+        insta::assert_debug_snapshot!(parse_ast);
+    }
+    
+    #[test]
+    fn test_more_comment() {
+        let source = "\
+a: int # nac3: sf1
+# nac3: sdf4
+for i in (1, '12'): # nac3: sf2
+    a: int
+# nac3: 3
+# nac3: 5
+while i < 2: # nac3: 4
+    # nac3: real pass
+    pass
+    # nac3: expr1
+    # nac3: expr3
+    1 + 2 # nac3: expr2
+    # nac3: if3
+    # nac3: if1
+    if 1: # nac3: if2
+        3";
+        insta::assert_debug_snapshot!(parse_program(source, Default::default()).unwrap());
+    }
+    
+    #[test]
+    fn test_sample_comment() {
+        let source = "\
+# nac3: while1 
+# nac3: while2 
+# normal comment 
+while test: # nac3: while3 
+    # nac3: simple assign0 
+    a = 3 # nac3: simple assign1
+";
+        insta::assert_debug_snapshot!(parse_program(source, Default::default()).unwrap());
+    }
+
+    #[test]
+    fn test_comment_ambiguity() {
+        let source = "\
+if a: d; # nac3: for d
+if b: c # nac3: for c
+if d: # nac3: for if d
+    b; b + 3; # nac3: for b + 3
+a = 3; a + 3; b = a; # nac3: notif
+# nac3: smallsingle1
+# nac3: smallsingle3
+aa = 3 # nac3: smallsingle2
+if a: # nac3: small2
+    a
+for i in a: # nac3: for1
+    pass
+";
+        insta::assert_debug_snapshot!(parse_program(source, Default::default()).unwrap());
+    }
+
+    #[test]
+    fn test_comment_should_fail() {
+        let source = "\
+if a: # nac3: something
+a = 3
+";
+        assert!(parse_program(source, Default::default()).is_err());
+    }
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__fstring_parse_selfdocumenting_base.snap

@@ -0,0 +1,80 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 327
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "user=",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "user",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__fstring_parse_selfdocumenting_base_more.snap

@@ -0,0 +1,172 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 335
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "mix ",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "user=",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "user",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        " with text and ",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "second=",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "second",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__fstring_parse_selfdocumenting_format.snap

@@ -0,0 +1,97 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 343
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "user=",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "user",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: Some(
+                        Located {
+                            location: Location {
+                                row: 0,
+                                column: 0,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Constant {
+                                value: Str(
+                                    ">10",
+                                ),
+                                kind: None,
+                            },
+                        },
+                    ),
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_empty_fstring.snap

@@ -0,0 +1,22 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 319
+expression: "parse_fstring(\"\").unwrap()"
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: Constant {
+        value: Str(
+            "",
+        ),
+        kind: None,
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring.snap

@@ -0,0 +1,92 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 298
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "a",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 3,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "b",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "{foo}",
+                    ),
+                    kind: None,
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_equals.snap

@@ -0,0 +1,69 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 382
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: FormattedValue {
+        value: Located {
+            location: Location {
+                row: 1,
+                column: 5,
+                file: FileName(
+                    "unknown",
+                ),
+            },
+            custom: (),
+            node: Compare {
+                left: Located {
+                    location: Location {
+                        row: 1,
+                        column: 2,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Constant {
+                        value: Int(
+                            42,
+                        ),
+                        kind: None,
+                    },
+                },
+                ops: [
+                    Eq,
+                ],
+                comparators: [
+                    Located {
+                        location: Location {
+                            row: 1,
+                            column: 8,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Constant {
+                            value: Int(
+                                42,
+                            ),
+                            kind: None,
+                        },
+                    },
+                ],
+            },
+        },
+        conversion: None,
+        format_spec: None,
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_nested_spec.snap

@@ -0,0 +1,63 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 306
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: FormattedValue {
+        value: Located {
+            location: Location {
+                row: 1,
+                column: 2,
+                file: FileName(
+                    "unknown",
+                ),
+            },
+            custom: (),
+            node: Name {
+                id: "foo",
+                ctx: Load,
+            },
+        },
+        conversion: None,
+        format_spec: Some(
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "spec",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+        ),
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_not_equals.snap

@@ -0,0 +1,69 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 375
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: FormattedValue {
+        value: Located {
+            location: Location {
+                row: 1,
+                column: 4,
+                file: FileName(
+                    "unknown",
+                ),
+            },
+            custom: (),
+            node: Compare {
+                left: Located {
+                    location: Location {
+                        row: 1,
+                        column: 2,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Constant {
+                        value: Int(
+                            1,
+                        ),
+                        kind: None,
+                    },
+                },
+                ops: [
+                    NotEq,
+                ],
+                comparators: [
+                    Located {
+                        location: Location {
+                            row: 1,
+                            column: 7,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Constant {
+                            value: Int(
+                                2,
+                            ),
+                            kind: None,
+                        },
+                    },
+                ],
+            },
+        },
+        conversion: None,
+        format_spec: None,
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_not_nested_spec.snap

@@ -0,0 +1,51 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 314
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: FormattedValue {
+        value: Located {
+            location: Location {
+                row: 1,
+                column: 2,
+                file: FileName(
+                    "unknown",
+                ),
+            },
+            custom: (),
+            node: Name {
+                id: "foo",
+                ctx: Load,
+            },
+        },
+        conversion: None,
+        format_spec: Some(
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "spec",
+                    ),
+                    kind: None,
+                },
+            },
+        ),
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_selfdoc_prec_space.snap

@@ -0,0 +1,80 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 389
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "x   =",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "x",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_selfdoc_trailing_space.snap

@@ -0,0 +1,80 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 396
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: JoinedStr {
+        values: [
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "x=",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Str(
+                        "   ",
+                    ),
+                    kind: None,
+                },
+            },
+            Located {
+                location: Location {
+                    row: 0,
+                    column: 0,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: FormattedValue {
+                    value: Located {
+                        location: Location {
+                            row: 1,
+                            column: 2,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "x",
+                            ctx: Load,
+                        },
+                    },
+                    conversion: None,
+                    format_spec: None,
+                },
+            },
+        ],
+    },
+}

nac3parser/src/snapshots/nac3parser__fstring__tests__parse_fstring_yield_expr.snap

@@ -0,0 +1,33 @@
+---
+source: nac3parser/src/fstring.rs
+assertion_line: 403
+expression: parse_ast
+
+---
+Located {
+    location: Location {
+        row: 0,
+        column: 0,
+        file: FileName(
+            "unknown",
+        ),
+    },
+    custom: (),
+    node: FormattedValue {
+        value: Located {
+            location: Location {
+                row: 1,
+                column: 2,
+                file: FileName(
+                    "unknown",
+                ),
+            },
+            custom: (),
+            node: Yield {
+                value: None,
+            },
+        },
+        conversion: None,
+        format_spec: None,
+    },
+}

nac3parser/src/snapshots/nac3parser__parser__tests__comment_ambiguity.snap

@@ -0,0 +1,560 @@
+---
+source: nac3parser/src/parser.rs
+assertion_line: 218
+expression: "parse_program(&source, Default::default()).unwrap()"
+
+---
+[
+    Located {
+        location: Location {
+            row: 1,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: If {
+            test: Located {
+                location: Location {
+                    row: 1,
+                    column: 4,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "a",
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 1,
+                        column: 7,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 1,
+                                column: 7,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "d",
+                                ctx: Load,
+                            },
+                        },
+                        config_comment: [
+                            "for d",
+                        ],
+                    },
+                },
+            ],
+            orelse: [],
+            config_comment: [],
+        },
+    },
+    Located {
+        location: Location {
+            row: 2,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: If {
+            test: Located {
+                location: Location {
+                    row: 2,
+                    column: 4,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "b",
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 2,
+                        column: 7,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 2,
+                                column: 7,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "c",
+                                ctx: Load,
+                            },
+                        },
+                        config_comment: [
+                            "for c",
+                        ],
+                    },
+                },
+            ],
+            orelse: [],
+            config_comment: [],
+        },
+    },
+    Located {
+        location: Location {
+            row: 3,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: If {
+            test: Located {
+                location: Location {
+                    row: 3,
+                    column: 4,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "d",
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 4,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 4,
+                                column: 5,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "b",
+                                ctx: Load,
+                            },
+                        },
+                        config_comment: [],
+                    },
+                },
+                Located {
+                    location: Location {
+                        row: 4,
+                        column: 8,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 4,
+                                column: 10,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: BinOp {
+                                left: Located {
+                                    location: Location {
+                                        row: 4,
+                                        column: 8,
+                                        file: FileName(
+                                            "unknown",
+                                        ),
+                                    },
+                                    custom: (),
+                                    node: Name {
+                                        id: "b",
+                                        ctx: Load,
+                                    },
+                                },
+                                op: Add,
+                                right: Located {
+                                    location: Location {
+                                        row: 4,
+                                        column: 12,
+                                        file: FileName(
+                                            "unknown",
+                                        ),
+                                    },
+                                    custom: (),
+                                    node: Constant {
+                                        value: Int(
+                                            3,
+                                        ),
+                                        kind: None,
+                                    },
+                                },
+                            },
+                        },
+                        config_comment: [
+                            "for b + 3",
+                        ],
+                    },
+                },
+            ],
+            orelse: [],
+            config_comment: [
+                "for if d",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 5,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: Assign {
+            targets: [
+                Located {
+                    location: Location {
+                        row: 5,
+                        column: 1,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Name {
+                        id: "a",
+                        ctx: Load,
+                    },
+                },
+            ],
+            value: Located {
+                location: Location {
+                    row: 5,
+                    column: 5,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Int(
+                        3,
+                    ),
+                    kind: None,
+                },
+            },
+            type_comment: None,
+            config_comment: [],
+        },
+    },
+    Located {
+        location: Location {
+            row: 5,
+            column: 8,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: Expr {
+            value: Located {
+                location: Location {
+                    row: 5,
+                    column: 10,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: BinOp {
+                    left: Located {
+                        location: Location {
+                            row: 5,
+                            column: 8,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "a",
+                            ctx: Load,
+                        },
+                    },
+                    op: Add,
+                    right: Located {
+                        location: Location {
+                            row: 5,
+                            column: 12,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Constant {
+                            value: Int(
+                                3,
+                            ),
+                            kind: None,
+                        },
+                    },
+                },
+            },
+            config_comment: [],
+        },
+    },
+    Located {
+        location: Location {
+            row: 5,
+            column: 15,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: Assign {
+            targets: [
+                Located {
+                    location: Location {
+                        row: 5,
+                        column: 15,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Name {
+                        id: "b",
+                        ctx: Load,
+                    },
+                },
+            ],
+            value: Located {
+                location: Location {
+                    row: 5,
+                    column: 19,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "a",
+                    ctx: Load,
+                },
+            },
+            type_comment: None,
+            config_comment: [
+                "notif",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 8,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: Assign {
+            targets: [
+                Located {
+                    location: Location {
+                        row: 8,
+                        column: 1,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Name {
+                        id: "aa",
+                        ctx: Load,
+                    },
+                },
+            ],
+            value: Located {
+                location: Location {
+                    row: 8,
+                    column: 6,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Constant {
+                    value: Int(
+                        3,
+                    ),
+                    kind: None,
+                },
+            },
+            type_comment: None,
+            config_comment: [
+                "smallsingle1",
+                "smallsingle3",
+                "smallsingle2",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 9,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: If {
+            test: Located {
+                location: Location {
+                    row: 9,
+                    column: 4,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "a",
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 10,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 10,
+                                column: 5,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "a",
+                                ctx: Load,
+                            },
+                        },
+                        config_comment: [],
+                    },
+                },
+            ],
+            orelse: [],
+            config_comment: [
+                "small2",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 11,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: For {
+            target: Located {
+                location: Location {
+                    row: 11,
+                    column: 5,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "i",
+                    ctx: Load,
+                },
+            },
+            iter: Located {
+                location: Location {
+                    row: 11,
+                    column: 10,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "a",
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 12,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Pass {
+                        config_comment: [],
+                    },
+                },
+            ],
+            orelse: [],
+            type_comment: None,
+            config_comment: [
+                "for1",
+            ],
+        },
+    },
+]

nac3parser/src/snapshots/nac3parser__parser__tests__more_comment.snap

@@ -0,0 +1,386 @@
+---
+source: nac3parser/src/parser.rs
+assertion_line: 186
+expression: "parse_program(&source, Default::default()).unwrap()"
+
+---
+[
+    Located {
+        location: Location {
+            row: 1,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: AnnAssign {
+            target: Located {
+                location: Location {
+                    row: 1,
+                    column: 1,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "a",
+                    ctx: Load,
+                },
+            },
+            annotation: Located {
+                location: Location {
+                    row: 1,
+                    column: 4,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "int",
+                    ctx: Load,
+                },
+            },
+            value: None,
+            simple: true,
+            config_comment: [
+                "sf1",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 2,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: For {
+            target: Located {
+                location: Location {
+                    row: 3,
+                    column: 5,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Name {
+                    id: "i",
+                    ctx: Load,
+                },
+            },
+            iter: Located {
+                location: Location {
+                    row: 3,
+                    column: 11,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Tuple {
+                    elts: [
+                        Located {
+                            location: Location {
+                                row: 3,
+                                column: 11,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Constant {
+                                value: Int(
+                                    1,
+                                ),
+                                kind: None,
+                            },
+                        },
+                        Located {
+                            location: Location {
+                                row: 3,
+                                column: 15,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Constant {
+                                value: Str(
+                                    "12",
+                                ),
+                                kind: None,
+                            },
+                        },
+                    ],
+                    ctx: Load,
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 4,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: AnnAssign {
+                        target: Located {
+                            location: Location {
+                                row: 4,
+                                column: 5,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "a",
+                                ctx: Load,
+                            },
+                        },
+                        annotation: Located {
+                            location: Location {
+                                row: 4,
+                                column: 8,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Name {
+                                id: "int",
+                                ctx: Load,
+                            },
+                        },
+                        value: None,
+                        simple: true,
+                        config_comment: [],
+                    },
+                },
+            ],
+            orelse: [],
+            type_comment: None,
+            config_comment: [
+                "sdf4",
+                "sf2",
+            ],
+        },
+    },
+    Located {
+        location: Location {
+            row: 5,
+            column: 1,
+            file: FileName(
+                "unknown",
+            ),
+        },
+        custom: (),
+        node: While {
+            test: Located {
+                location: Location {
+                    row: 7,
+                    column: 9,
+                    file: FileName(
+                        "unknown",
+                    ),
+                },
+                custom: (),
+                node: Compare {
+                    left: Located {
+                        location: Location {
+                            row: 7,
+                            column: 7,
+                            file: FileName(
+                                "unknown",
+                            ),
+                        },
+                        custom: (),
+                        node: Name {
+                            id: "i",
+                            ctx: Load,
+                        },
+                    },
+                    ops: [
+                        Lt,
+                    ],
+                    comparators: [
+                        Located {
+                            location: Location {
+                                row: 7,
+                                column: 11,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Constant {
+                                value: Int(
+                                    2,
+                                ),
+                                kind: None,
+                            },
+                        },
+                    ],
+                },
+            },
+            body: [
+                Located {
+                    location: Location {
+                        row: 9,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Pass {
+                        config_comment: [
+                            "real pass",
+                        ],
+                    },
+                },
+                Located {
+                    location: Location {
+                        row: 12,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: Expr {
+                        value: Located {
+                            location: Location {
+                                row: 12,
+                                column: 7,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: BinOp {
+                                left: Located {
+                                    location: Location {
+                                        row: 12,
+                                        column: 5,
+                                        file: FileName(
+                                            "unknown",
+                                        ),
+                                    },
+                                    custom: (),
+                                    node: Constant {
+                                        value: Int(
+                                            1,
+                                        ),
+                                        kind: None,
+                                    },
+                                },
+                                op: Add,
+                                right: Located {
+                                    location: Location {
+                                        row: 12,
+                                        column: 9,
+                                        file: FileName(
+                                            "unknown",
+                                        ),
+                                    },
+                                    custom: (),
+                                    node: Constant {
+                                        value: Int(
+                                            2,
+                                        ),
+                                        kind: None,
+                                    },
+                                },
+                            },
+                        },
+                        config_comment: [
+                            "expr1",
+                            "expr3",
+                            "expr2",
+                        ],
+                    },
+                },
+                Located {
+                    location: Location {
+                        row: 13,
+                        column: 5,
+                        file: FileName(
+                            "unknown",
+                        ),
+                    },
+                    custom: (),
+                    node: If {
+                        test: Located {
+                            location: Location {
+                                row: 15,
+                                column: 8,
+                                file: FileName(
+                                    "unknown",
+                                ),
+                            },
+                            custom: (),
+                            node: Constant {
+                                value: Int(
+                                    1,
+                                ),
+                                kind: None,
+                            },
+                        },
+                        body: [
+                            Located {
+                                location: Location {
+                                    row: 16,
+                                    column: 9,
+                                    file: FileName(
+                                        "unknown",
+                                    ),
+                                },
+                                custom: (),
+                                node: Expr {
+                                    value: Located {
+                                        location: Location {
+                                            row: 16,
+                                            column: 9,
+                                            file: FileName(
+                                                "unknown",
+                                            ),
+                                        },
+                                        custom: (),
+                                        node: Constant {
+                                            value: Int(
+                                                3,
+                                            ),
+                                            kind: None,
+                                        },
+                                    },
+                                    config_comment: [],
+                                },
+                            },
+                        ],
+                        orelse: [],
+                        config_comment: [
+                            "if3",
+                            "if1",
+                            "if2",
+                        ],
+                    },
+                },
+            ],
+            orelse: [],
+            config_comment: [
+                "3",
+                "5",
+                "4",
+            ],
+        },
+    },
+]