Files
AILang/crates/ailang-check/src/lib.rs
T
Brummel c75517ac79 Iter 10: Term::Seq sequencing operator
Adds `Term::Seq { lhs, rhs }` (serde tag "seq") as a first-class
AST node for sequencing effectful expressions. Equivalent in
behaviour to `let _ = lhs in rhs`, but the dedicated node gives the
pretty-printer and diagnostics a cleaner shape and surfaces the
intent ("run for effect, then yield rhs") to future tooling.

Typecheck: lhs must be Unit; rhs's type is the result; effects
accumulate.
Codegen: lower lhs (drop SSA), lower rhs (return).
Capture / deps walkers: recurse into both sides.

Refactored examples/list_map.ail.json's print_list to use seq
instead of `let _ = ...`. Output unchanged (2/4/6).

Hash stability: existing examples without Term::Seq serialise
bit-identical; only list_map.ail.json's hashes changed (deliberate
refactor).

Tests: 51 green (was 50). New unit test
`ailang_check::tests::seq_lhs_must_be_unit` covers the type-error
path; existing list_map e2e covers the happy path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 13:14:28 +02:00

1247 lines
45 KiB
Rust

//! Typechecker for AILang (MVP).
//!
//! Monomorphic HM subset: no type variables in the body; all top-level defs
//! must be fully annotated. Effects are propagated as a set and reconciled
//! against the annotation on the function type.
//!
//! Built-in operations are resolved via [`Builtins`].
use ailang_core::ast::*;
use ailang_core::Workspace;
use indexmap::IndexMap;
use std::collections::{BTreeMap, BTreeSet};
pub mod builtins;
pub mod diagnostic;
pub use diagnostic::{Diagnostic, Severity};
#[derive(Debug, thiserror::Error)]
pub enum CheckError {
#[error("def `{0}`: {1}")]
Def(String, Box<CheckError>),
#[error("type mismatch: expected {expected}, got {got}")]
TypeMismatch { expected: String, got: String },
#[error("unknown identifier: `{0}`")]
UnknownIdent(String),
#[error("unknown effect operation: `{0}`")]
UnknownEffectOp(String),
#[error("`{0}` is not a function (got {1})")]
NotAFunction(String, String),
#[error("arity mismatch for `{name}`: expected {expected} args, got {got}")]
ArityMismatch {
name: String,
expected: usize,
got: usize,
},
#[error("undeclared effect `{0}` used in body")]
UndeclaredEffect(String),
#[error("function type required for fn `{0}`, got {1}")]
FnTypeRequired(String, String),
#[error("param count mismatch in `{name}`: type has {ty_count}, params has {param_count}")]
ParamCountMismatch {
name: String,
ty_count: usize,
param_count: usize,
},
#[error("polymorphic types not supported in MVP body of `{0}`")]
PolymorphicNotSupported(String),
#[error("const `{0}` may not have effects (got !{1:?})")]
ConstHasEffects(String, Vec<String>),
#[error("unknown type: `{0}`")]
UnknownType(String),
#[error("type `{ty}` has no constructor `{ctor}`")]
UnknownCtor { ty: String, ctor: String },
#[error("unknown constructor `{0}` in pattern")]
UnknownCtorInPattern(String),
#[error("constructor `{ty}/{ctor}` arity: expected {expected} fields, got {got}")]
CtorArity {
ty: String,
ctor: String,
expected: usize,
got: usize,
},
#[error("non-exhaustive match on `{ty}`: missing cases {missing:?}")]
NonExhaustive { ty: String, missing: Vec<String> },
#[error("primitive type `{0}` requires a wildcard or variable arm in match")]
PrimitiveNeedsWildcard(String),
#[error("cannot match constructor pattern `{ctor}` against type `{ty}`")]
PatternTypeMismatch { ctor: String, ty: String },
#[error("duplicate type definition: `{0}`")]
DuplicateType(String),
#[error("duplicate constructor: `{ctor}` (in types `{a}` and `{b}`)")]
DuplicateCtor { ctor: String, a: String, b: String },
#[error("duplicate definition: `{0}`")]
DuplicateDef(String),
#[error("nested constructor pattern not allowed in MVP: `{0}`")]
NestedCtorPatternNotAllowed(String),
#[error("unknown module prefix `{module}` in qualified reference")]
UnknownModule { module: String },
#[error("module `{module}` has no top-level def `{name}`")]
UnknownImport { module: String, name: String },
#[error("invalid def name `{name}`: contains `.` (reserved for qualified refs)")]
InvalidDefName { name: String },
}
type Result<T> = std::result::Result<T, CheckError>;
impl CheckError {
/// Stable kebab-case code for machine consumption (`ail check --json`).
/// Passed through recursively via the `Def` wrapping — the inner error
/// carries the actual code, the wrapper only the def context.
pub fn code(&self) -> &'static str {
match self {
CheckError::Def(_, inner) => inner.code(),
CheckError::TypeMismatch { .. } => "type-mismatch",
CheckError::UnknownIdent(_) => "unbound-var",
CheckError::UnknownEffectOp(_) => "unknown-effect-op",
CheckError::NotAFunction(..) => "not-a-function",
CheckError::ArityMismatch { .. } => "arity-mismatch",
CheckError::UndeclaredEffect(_) => "undeclared-effect",
CheckError::FnTypeRequired(..) => "fn-type-required",
CheckError::ParamCountMismatch { .. } => "param-count-mismatch",
CheckError::PolymorphicNotSupported(_) => "polymorphic-not-supported",
CheckError::ConstHasEffects(..) => "const-has-effects",
CheckError::UnknownType(_) => "unknown-type",
CheckError::UnknownCtor { .. } => "unknown-ctor",
CheckError::UnknownCtorInPattern(_) => "unknown-ctor-in-pattern",
CheckError::CtorArity { .. } => "arity-mismatch",
CheckError::NonExhaustive { .. } => "non-exhaustive-match",
CheckError::PrimitiveNeedsWildcard(_) => "primitive-needs-wildcard",
CheckError::PatternTypeMismatch { .. } => "pattern-type-mismatch",
CheckError::DuplicateType(_) => "duplicate-type",
CheckError::DuplicateCtor { .. } => "duplicate-ctor",
CheckError::DuplicateDef(_) => "duplicate-def",
CheckError::NestedCtorPatternNotAllowed(_) => "nested-ctor-pattern-not-allowed",
CheckError::UnknownModule { .. } => "unknown-module",
CheckError::UnknownImport { .. } => "unknown-import",
CheckError::InvalidDefName { .. } => "invalid-def-name",
}
}
/// Structured context for a diagnostic. Lands directly in the JSON
/// under the key `ctx`. Empty object when no context is available.
pub fn ctx(&self) -> serde_json::Value {
match self {
CheckError::Def(_, inner) => inner.ctx(),
CheckError::TypeMismatch { expected, got } => {
serde_json::json!({"expected": expected, "actual": got})
}
CheckError::ArityMismatch { expected, got, .. } => {
serde_json::json!({"expected": expected, "actual": got})
}
CheckError::CtorArity {
expected, got, ..
} => serde_json::json!({"expected": expected, "actual": got}),
CheckError::ParamCountMismatch {
ty_count,
param_count,
..
} => serde_json::json!({"expected": ty_count, "actual": param_count}),
CheckError::NonExhaustive { missing, .. } => {
serde_json::json!({"missing": missing})
}
CheckError::UnknownModule { module } => {
serde_json::json!({"module": module})
}
CheckError::UnknownImport { module, name } => {
serde_json::json!({"module": module, "name": name})
}
CheckError::InvalidDefName { name } => {
serde_json::json!({"name": name, "reason": "contains-dot"})
}
_ => serde_json::Value::Object(serde_json::Map::new()),
}
}
/// If this error is wrapped by [`CheckError::Def`], returns the name
/// of the affected def. Otherwise `None`.
pub fn def(&self) -> Option<&str> {
match self {
CheckError::Def(n, _) => Some(n.as_str()),
_ => None,
}
}
/// Unwraps the error potentially wrapped by [`CheckError::Def`].
pub fn inner(&self) -> &CheckError {
match self {
CheckError::Def(_, inner) => inner.inner(),
other => other,
}
}
/// Non-`Def`-wrapped message. Without the `def: ...` prefix.
pub fn message(&self) -> String {
format!("{}", self.inner())
}
pub fn to_diagnostic(&self) -> Diagnostic {
let mut d = Diagnostic::error(self.code(), self.message()).with_ctx(self.ctx());
if let Some(name) = self.def() {
d = d.with_def(name);
}
d
}
}
/// Top-level API for structured diagnostics.
///
/// Empty Vec = green. From Iter 6 onwards the body-check phase is
/// multi-diagnose: each def in each module is checked independently and
/// failures accumulate, so a single `ail check` run reports every
/// independent body error in the workspace.
///
/// Pass-1 errors (top-level symbol-table construction:
/// `invalid-def-name`, `duplicate-def`) are still fail-fast — those
/// errors corrupt the symbol table, and any further diagnostic would be
/// unreliable. Likewise, the type-def installation is fail-fast within
/// a single module, but other modules continue being checked.
///
/// Backwards compatibility: a bare `&Module` is internally lifted into a
/// trivial workspace (`modules = {m.name: m}`, `entry = m.name`) so that
/// tooling checking individual modules avoids building a `Workspace`.
/// Modules with imports on other modules not present in the trivial
/// workspace will inevitably produce `unknown-module` errors on qualified
/// references — which is correct.
pub fn check_module(m: &Module) -> Vec<Diagnostic> {
let mut modules = BTreeMap::new();
modules.insert(m.name.clone(), m.clone());
let ws = Workspace {
entry: m.name.clone(),
modules,
root_dir: std::path::PathBuf::from("."),
};
check_workspace(&ws)
}
/// Top-level API for cross-module typecheck.
///
/// Iterates over all modules of the workspace and checks each with access
/// to the top-level symbol tables of all other modules. Qualified
/// references are resolved via the import map of the respective module:
/// `Term::Var { name }` with exactly one dot in the name is interpreted
/// as `<prefix>.<def>`; `<prefix>` is an import alias (or the module name,
/// if imported without an alias).
///
/// Multi-diagnose: pass-2 collects diagnostics per def across all modules.
/// Pass-1 (symbol table) stays fail-fast — see `check_module`.
/// Module iteration order is deterministic: entry first, then the rest in
/// BTreeMap order, so output ordering is stable.
pub fn check_workspace(ws: &Workspace) -> Vec<Diagnostic> {
// Pass 1: build per-module top-level symbol table — without checking
// bodies. This lets module A access defs from module B even when B
// comes later in the BTreeMap. Duplicate def names and dot-in-def
// names are reported here immediately, because without clean symbol
// tables all further diagnostics would be unreliable.
let module_globals = match build_module_globals(ws) {
Ok(g) => g,
Err(e) => return vec![e.to_diagnostic()],
};
// Pass 2: body-check per module. `check_in_workspace` builds the env
// with additional cross-module globals and an import map. Errors
// accumulate across modules.
let mut order: Vec<&String> = Vec::new();
if ws.modules.contains_key(&ws.entry) {
order.push(&ws.entry);
}
for name in ws.modules.keys() {
if name != &ws.entry {
order.push(name);
}
}
let mut diagnostics: Vec<Diagnostic> = Vec::new();
for name in order {
let m = &ws.modules[name];
for e in check_in_workspace(m, ws, &module_globals) {
diagnostics.push(e.to_diagnostic());
}
}
diagnostics
}
/// Result of typechecking a module: mapping from symbol name to
/// (type, hash) — ready for `manifest` output.
#[derive(Debug, Clone)]
pub struct CheckedModule {
pub symbols: IndexMap<String, (Type, String)>,
}
pub fn check(m: &Module) -> Result<CheckedModule> {
// Trivial workspace: the module alone, without cross-module resolution.
let mut modules = BTreeMap::new();
modules.insert(m.name.clone(), m.clone());
let ws = Workspace {
entry: m.name.clone(),
modules,
root_dir: std::path::PathBuf::from("."),
};
let module_globals = build_module_globals(&ws)?;
// `check` keeps single-error semantics for callers (snapshot tests,
// legacy code). Multi-diagnose is exposed via `check_module` /
// `check_workspace`.
if let Some(first) = check_in_workspace(m, &ws, &module_globals).into_iter().next() {
return Err(first);
}
// Collect symbols for the return value (existing semantics).
let mut symbols = IndexMap::new();
for def in &m.defs {
let h = ailang_core::hash::def_hash(def);
let ty = match def {
Def::Fn(f) => f.ty.clone(),
Def::Const(c) => c.ty.clone(),
Def::Type(_) => Type::Con {
name: def.name().to_string(),
},
};
symbols.insert(def.name().to_string(), (ty, h));
}
Ok(CheckedModule { symbols })
}
/// Builds the top-level symbol table per module (for cross-module lookup),
/// without checking bodies. Duplicates and dot-in-def names are reported
/// here as errors immediately — they would taint all further diagnostics.
fn build_module_globals(
ws: &Workspace,
) -> Result<BTreeMap<String, IndexMap<String, Type>>> {
let mut out: BTreeMap<String, IndexMap<String, Type>> = BTreeMap::new();
for (mname, m) in &ws.modules {
let mut globals = IndexMap::new();
for def in &m.defs {
let def_name = def.name();
if def_name.contains('.') {
return Err(CheckError::Def(
def_name.to_string(),
Box::new(CheckError::InvalidDefName {
name: def_name.to_string(),
}),
));
}
if globals.contains_key(def_name) {
return Err(CheckError::Def(
def_name.to_string(),
Box::new(CheckError::DuplicateDef(def_name.to_string())),
));
}
let ty = match def {
Def::Fn(f) => f.ty.clone(),
Def::Const(c) => c.ty.clone(),
Def::Type(_) => Type::Con {
name: def_name.to_string(),
},
};
globals.insert(def_name.to_string(), ty);
}
out.insert(mname.clone(), globals);
}
Ok(out)
}
/// Checks the bodies of a single module in the context of the workspace.
/// Assumption: `module_globals` already contains the top-level symbol
/// tables for **all** modules of the workspace (including `m`) — built
/// by `build_module_globals`.
///
/// Returns **all** errors found in this module, in def declaration order:
///
/// - The type-def setup phase is fail-fast within the module (duplicate
/// type or ctor names corrupt the env, so we abort *this* module after
/// the first such error and let the outer loop continue with others).
/// - The body-check phase is multi-diagnose: each def is checked
/// independently against the assembled env; a failure is recorded and
/// the next def is attempted.
fn check_in_workspace(
m: &Module,
ws: &Workspace,
module_globals: &BTreeMap<String, IndexMap<String, Type>>,
) -> Vec<CheckError> {
let mut env = Env::new();
builtins::install(&mut env);
let mut errors: Vec<CheckError> = Vec::new();
// Register type defs (local per module; cross-module ADT sharing is
// explicitly not part of 5b).
for def in &m.defs {
if let Def::Type(td) = def {
if env.types.contains_key(&td.name) {
errors.push(CheckError::Def(
td.name.clone(),
Box::new(CheckError::DuplicateType(td.name.clone())),
));
return errors;
}
for c in &td.ctors {
if let Some(prev) = env.ctor_index.get(&c.name) {
errors.push(CheckError::Def(
td.name.clone(),
Box::new(CheckError::DuplicateCtor {
ctor: c.name.clone(),
a: prev.type_name.clone(),
b: td.name.clone(),
}),
));
return errors;
}
env.ctor_index.insert(
c.name.clone(),
CtorRef {
type_name: td.name.clone(),
},
);
}
env.types.insert(td.name.clone(), td.clone());
}
}
// Take local globals from the previously built table.
if let Some(g) = module_globals.get(&m.name) {
for (n, t) in g {
env.globals.insert(n.clone(), t.clone());
}
}
// Build import map: alias (or module name, if without alias) →
// module name. Conflicts are not allowed in the MVP: the same `as`
// clause twice would stand out and should surface as a duplicate
// symbol name — currently "last wins", because Iter 5b doesn't
// introduce a dedicated diagnostic for it; if needed later →
// `ambiguous-import` code.
let mut import_map: BTreeMap<String, String> = BTreeMap::new();
for imp in &m.imports {
let key = imp.alias.clone().unwrap_or_else(|| imp.module.clone());
import_map.insert(key, imp.module.clone());
}
env.imports = import_map;
env.module_globals = module_globals.clone();
env.current_module = m.name.clone();
// Workspace isn't directly needed in the env; cross-module lookup uses
// only `module_globals`. But we keep the ws reference in the
// comment as a reminder, in case cross-module ADTs are added later.
let _ = ws;
for def in &m.defs {
if let Err(e) = check_def(def, &env) {
errors.push(CheckError::Def(def.name().to_string(), Box::new(e)));
}
}
errors
}
fn check_def(def: &Def, env: &Env) -> Result<()> {
match def {
Def::Fn(f) => check_fn(f, env),
Def::Const(c) => check_const(c, env),
Def::Type(td) => check_type_def(td, env),
}
}
fn check_type_def(td: &TypeDef, env: &Env) -> Result<()> {
// All fields must reference known types (or other ADTs from this
// module; recursion is allowed).
for c in &td.ctors {
for f in &c.fields {
check_type_well_formed(f, env)?;
}
}
Ok(())
}
fn check_type_well_formed(t: &Type, env: &Env) -> Result<()> {
match t {
Type::Con { name } => {
if matches!(name.as_str(), "Int" | "Bool" | "Unit" | "Str") {
Ok(())
} else if env.types.contains_key(name) {
Ok(())
} else {
Err(CheckError::UnknownType(name.clone()))
}
}
Type::Fn { params, ret, .. } => {
for p in params {
check_type_well_formed(p, env)?;
}
check_type_well_formed(ret, env)
}
Type::Var { .. } | Type::Forall { .. } => {
// No type-level polymorphism inside ADT fields in the MVP.
Err(CheckError::PolymorphicNotSupported(
"type def".into(),
))
}
}
}
fn check_fn(f: &FnDef, env: &Env) -> Result<()> {
let (param_tys, ret_ty, declared_effs) = match &f.ty {
Type::Fn { params, ret, effects } => {
(params.clone(), (**ret).clone(), effects.clone())
}
other => {
return Err(CheckError::FnTypeRequired(
f.name.clone(),
ailang_core::pretty::type_to_string(other),
));
}
};
if f.params.len() != param_tys.len() {
return Err(CheckError::ParamCountMismatch {
name: f.name.clone(),
ty_count: param_tys.len(),
param_count: f.params.len(),
});
}
let mut locals = IndexMap::new();
for (n, t) in f.params.iter().zip(param_tys.iter()) {
locals.insert(n.clone(), t.clone());
}
let mut effects = BTreeSet::new();
let body_ty = synth(&f.body, env, &mut locals, &mut effects, &f.name)?;
expect_eq(&ret_ty, &body_ty)?;
let declared: BTreeSet<String> = declared_effs.into_iter().collect();
for e in &effects {
if !declared.contains(e) {
return Err(CheckError::UndeclaredEffect(e.clone()));
}
}
Ok(())
}
fn check_const(c: &ConstDef, env: &Env) -> Result<()> {
let mut locals = IndexMap::new();
let mut effects = BTreeSet::new();
let v = synth(&c.value, env, &mut locals, &mut effects, &c.name)?;
expect_eq(&c.ty, &v)?;
if !effects.is_empty() {
return Err(CheckError::ConstHasEffects(
c.name.clone(),
effects.into_iter().collect(),
));
}
Ok(())
}
fn synth(
t: &Term,
env: &Env,
locals: &mut IndexMap<String, Type>,
effects: &mut BTreeSet<String>,
in_def: &str,
) -> Result<Type> {
match t {
Term::Lit { lit } => Ok(match lit {
Literal::Int { .. } => Type::int(),
Literal::Bool { .. } => Type::bool_(),
Literal::Str { .. } => Type::str_(),
Literal::Unit => Type::unit(),
}),
Term::Var { name } => {
// 1) Locals have highest priority — they can even shadow a
// qualified dotted name, if someone builds a
// letter-with-dot param. Not really reachable in the MVP,
// but harmless.
if let Some(t) = locals.get(name) {
return Ok(t.clone());
}
// 2) Local globals.
if let Some(t) = env.globals.get(name) {
return Ok(t.clone());
}
// 3) Exactly one dot → qualified cross-module reference.
// More than one dot is undefined in the current MVP
// and falls through below as `unbound-var`.
if name.matches('.').count() == 1 {
let (prefix, suffix) = name.split_once('.').expect("checked");
let target_module = match env.imports.get(prefix) {
Some(m) => m.clone(),
None => {
// Self-reference `<self>.def` without an import entry:
// we deliberately disallow this — by convention,
// qualified references only go through imports.
// That way the meaning of `name` stays locally stable.
return Err(CheckError::UnknownModule {
module: prefix.to_string(),
});
}
};
let g = env.module_globals.get(&target_module).ok_or_else(|| {
// Import map points at a module not loaded in the
// workspace. The workspace loader should have caught
// this already; defensive unknown-module here.
CheckError::UnknownModule {
module: target_module.clone(),
}
})?;
return g.get(suffix).cloned().ok_or_else(|| {
CheckError::UnknownImport {
module: target_module,
name: suffix.to_string(),
}
});
}
Err(CheckError::UnknownIdent(name.clone()))
}
Term::App { callee, args } => {
let cty = synth(callee, env, locals, effects, in_def)?;
let (params, ret, fx) = match &cty {
Type::Fn { params, ret, effects: fx } => {
(params.clone(), (**ret).clone(), fx.clone())
}
Type::Forall { .. } => {
return Err(CheckError::PolymorphicNotSupported(in_def.to_string()));
}
other => {
return Err(CheckError::NotAFunction(
callee_name(callee),
ailang_core::pretty::type_to_string(other),
));
}
};
if args.len() != params.len() {
return Err(CheckError::ArityMismatch {
name: callee_name(callee),
expected: params.len(),
got: args.len(),
});
}
for (a, exp) in args.iter().zip(params.iter()) {
let actual = synth(a, env, locals, effects, in_def)?;
expect_eq(exp, &actual)?;
}
for e in fx {
effects.insert(e);
}
Ok(ret)
}
Term::Let { name, value, body } => {
let v = synth(value, env, locals, effects, in_def)?;
let prev = locals.insert(name.clone(), v);
let r = synth(body, env, locals, effects, in_def)?;
match prev {
Some(p) => {
locals.insert(name.clone(), p);
}
None => {
locals.shift_remove(name);
}
}
Ok(r)
}
Term::If { cond, then, else_ } => {
let c = synth(cond, env, locals, effects, in_def)?;
expect_eq(&Type::bool_(), &c)?;
let t1 = synth(then, env, locals, effects, in_def)?;
let t2 = synth(else_, env, locals, effects, in_def)?;
expect_eq(&t1, &t2)?;
Ok(t1)
}
Term::Do { op, args } => {
let sig = env
.effect_ops
.get(op)
.ok_or_else(|| CheckError::UnknownEffectOp(op.clone()))?
.clone();
if args.len() != sig.params.len() {
return Err(CheckError::ArityMismatch {
name: op.clone(),
expected: sig.params.len(),
got: args.len(),
});
}
for (a, exp) in args.iter().zip(sig.params.iter()) {
let actual = synth(a, env, locals, effects, in_def)?;
expect_eq(exp, &actual)?;
}
effects.insert(sig.effect.clone());
Ok(sig.ret)
}
Term::Ctor { type_name, ctor, args } => {
let td = env
.types
.get(type_name)
.ok_or_else(|| CheckError::UnknownType(type_name.clone()))?
.clone();
let cdef = td
.ctors
.iter()
.find(|c| &c.name == ctor)
.ok_or_else(|| CheckError::UnknownCtor {
ty: type_name.clone(),
ctor: ctor.clone(),
})?
.clone();
if args.len() != cdef.fields.len() {
return Err(CheckError::CtorArity {
ty: type_name.clone(),
ctor: ctor.clone(),
expected: cdef.fields.len(),
got: args.len(),
});
}
for (a, exp) in args.iter().zip(cdef.fields.iter()) {
let actual = synth(a, env, locals, effects, in_def)?;
expect_eq(exp, &actual)?;
}
Ok(Type::Con {
name: type_name.clone(),
})
}
Term::Match { scrutinee, arms } => {
let s_ty = synth(scrutinee, env, locals, effects, in_def)?;
if arms.is_empty() {
return Err(CheckError::NonExhaustive {
ty: ailang_core::pretty::type_to_string(&s_ty),
missing: vec!["(no arms)".into()],
});
}
let mut covered_ctors: BTreeSet<String> = BTreeSet::new();
let mut has_open_arm = false;
let mut result_ty: Option<Type> = None;
for arm in arms {
// Collect local bindings and push into the env, check the
// body, pop again — done manually because patterns can
// produce multiple bindings.
let bindings = type_check_pattern(&arm.pat, &s_ty, env)?;
let mut pushed = Vec::new();
for (n, t) in &bindings {
let prev = locals.insert(n.clone(), t.clone());
pushed.push((n.clone(), prev));
}
let body_ty = synth(&arm.body, env, locals, effects, in_def)?;
// Undo bindings.
for (n, prev) in pushed.into_iter().rev() {
match prev {
Some(p) => {
locals.insert(n, p);
}
None => {
locals.shift_remove(&n);
}
}
}
if let Some(rt) = &result_ty {
expect_eq(rt, &body_ty)?;
} else {
result_ty = Some(body_ty);
}
match &arm.pat {
Pattern::Wild | Pattern::Var { .. } => {
has_open_arm = true;
}
Pattern::Ctor { ctor, .. } => {
covered_ctors.insert(ctor.clone());
}
Pattern::Lit { .. } => {
// Lit patterns don't structurally cover anything.
}
}
}
// Exhaustiveness.
if !has_open_arm {
match &s_ty {
Type::Con { name } if env.types.contains_key(name) => {
let td = &env.types[name];
let missing: Vec<String> = td
.ctors
.iter()
.filter(|c| !covered_ctors.contains(&c.name))
.map(|c| c.name.clone())
.collect();
if !missing.is_empty() {
return Err(CheckError::NonExhaustive {
ty: name.clone(),
missing,
});
}
}
_ => {
return Err(CheckError::PrimitiveNeedsWildcard(
ailang_core::pretty::type_to_string(&s_ty),
));
}
}
}
Ok(result_ty.expect("checked arms is non-empty"))
}
Term::Seq { lhs, rhs } => {
// Iter 10: `lhs ; rhs`. lhs must be Unit (its value is
// discarded). Effects from both sides accumulate. The
// expression's type is rhs's type.
let lty = synth(lhs, env, locals, effects, in_def)?;
expect_eq(&Type::unit(), &lty)?;
synth(rhs, env, locals, effects, in_def)
}
Term::Lam { params, param_tys, ret_ty, effects: lam_effects, body } => {
// Iter 8b: a lambda's type is the declared `Type::Fn`. Push
// params as locals, check the body's type matches `ret_ty`,
// and ensure body effects are a subset of the declared set.
// (We trust the JSON schema for params.len() == param_tys.len();
// serde would have rejected a malformed AST.)
let mut pushed: Vec<(String, Option<Type>)> = Vec::new();
for (n, t) in params.iter().zip(param_tys.iter()) {
let prev = locals.insert(n.clone(), t.clone());
pushed.push((n.clone(), prev));
}
let mut body_effects: BTreeSet<String> = BTreeSet::new();
let body_ty = synth(body, env, locals, &mut body_effects, in_def);
for (n, prev) in pushed.into_iter().rev() {
match prev {
Some(p) => {
locals.insert(n, p);
}
None => {
locals.shift_remove(&n);
}
}
}
let body_ty = body_ty?;
expect_eq(ret_ty, &body_ty)?;
// Constructing a lambda is pure — the body's effects are
// sealed into the lambda's type, not propagated to the
// outer effect set. Calling the lambda (Term::App) will
// pick those effects up via Type::Fn.effects.
// Body effects must be a subset of the declared lam_effects.
let declared: BTreeSet<String> = lam_effects.iter().cloned().collect();
for e in &body_effects {
if !declared.contains(e) {
return Err(CheckError::UndeclaredEffect(e.clone()));
}
}
Ok(Type::Fn {
params: param_tys.clone(),
ret: Box::new((**ret_ty).clone()),
effects: lam_effects.clone(),
})
}
}
}
/// Checks a pattern against an expected type and returns the bindings
/// introduced by the pattern.
fn type_check_pattern(
p: &Pattern,
expected: &Type,
env: &Env,
) -> Result<Vec<(String, Type)>> {
match p {
Pattern::Wild => Ok(vec![]),
Pattern::Var { name } => Ok(vec![(name.clone(), expected.clone())]),
Pattern::Lit { lit } => {
let lt = match lit {
Literal::Int { .. } => Type::int(),
Literal::Bool { .. } => Type::bool_(),
Literal::Str { .. } => Type::str_(),
Literal::Unit => Type::unit(),
};
expect_eq(expected, &lt)?;
Ok(vec![])
}
Pattern::Ctor { ctor, fields } => {
// MVP: sub-patterns of ctor patterns may only be `Var` or `Wild`.
// Nested ctor or lit patterns need decision-tree lowering,
// which we don't have in codegen yet.
for sub in fields {
if !matches!(sub, Pattern::Var { .. } | Pattern::Wild) {
return Err(CheckError::NestedCtorPatternNotAllowed(ctor.clone()));
}
}
let cref = env
.ctor_index
.get(ctor)
.ok_or_else(|| CheckError::UnknownCtorInPattern(ctor.clone()))?;
// expected must be this ADT.
match expected {
Type::Con { name } if name == &cref.type_name => {}
_ => {
return Err(CheckError::PatternTypeMismatch {
ctor: ctor.clone(),
ty: ailang_core::pretty::type_to_string(expected),
});
}
}
let td = &env.types[&cref.type_name];
let cdef = td
.ctors
.iter()
.find(|c| &c.name == ctor)
.expect("indexed ctor exists");
if fields.len() != cdef.fields.len() {
return Err(CheckError::CtorArity {
ty: cref.type_name.clone(),
ctor: ctor.clone(),
expected: cdef.fields.len(),
got: fields.len(),
});
}
let mut out = Vec::new();
for (sub, sub_ty) in fields.iter().zip(cdef.fields.iter()) {
out.extend(type_check_pattern(sub, sub_ty, env)?);
}
Ok(out)
}
}
}
fn callee_name(t: &Term) -> String {
match t {
Term::Var { name } => name.clone(),
_ => "<expr>".into(),
}
}
fn expect_eq(expected: &Type, got: &Type) -> Result<()> {
if expected == got {
Ok(())
} else {
Err(CheckError::TypeMismatch {
expected: ailang_core::pretty::type_to_string(expected),
got: ailang_core::pretty::type_to_string(got),
})
}
}
#[derive(Debug, Default)]
pub struct Env {
pub globals: IndexMap<String, Type>,
pub effect_ops: IndexMap<String, builtins::EffectOpSig>,
pub types: IndexMap<String, TypeDef>,
/// Inverse index: ctor name -> reference to the owning ADT.
pub ctor_index: IndexMap<String, CtorRef>,
/// Import map: alias-or-module-name → actual module name.
/// Used when `Term::Var { name }` contains a dot
/// (qualified cross-module reference).
pub imports: BTreeMap<String, String>,
/// Top-level symbol table per module of the workspace.
/// `check_in_workspace` populates this from `build_module_globals`.
pub module_globals: BTreeMap<String, IndexMap<String, Type>>,
/// Name of the currently checked module. Used during var lookup to
/// treat self-references (module name == own name) as local globals,
/// without touching the `imports` channel.
pub current_module: String,
}
#[derive(Debug, Clone)]
pub struct CtorRef {
pub type_name: String,
}
impl Env {
fn new() -> Self {
Self::default()
}
}
#[cfg(test)]
mod tests {
use super::*;
use ailang_core::SCHEMA;
fn fn_def(name: &str, ty: Type, params: Vec<&str>, body: Term) -> Def {
Def::Fn(FnDef {
name: name.into(),
ty,
params: params.into_iter().map(|s| s.into()).collect(),
body,
doc: None,
})
}
#[test]
fn checks_simple_arithmetic_fn() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"add",
Type::Fn {
params: vec![Type::int(), Type::int()],
ret: Box::new(Type::int()),
effects: vec![],
},
vec!["a", "b"],
Term::App {
callee: Box::new(Term::Var { name: "+".into() }),
args: vec![
Term::Var { name: "a".into() },
Term::Var { name: "b".into() },
],
},
)],
};
check(&m).expect("should typecheck");
}
#[test]
fn rejects_type_mismatch() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"bad",
Type::Fn {
params: vec![],
ret: Box::new(Type::int()),
effects: vec![],
},
vec![],
Term::Lit {
lit: Literal::Bool { value: true },
},
)],
};
let err = check(&m).unwrap_err();
let msg = format!("{err}");
assert!(msg.contains("type mismatch"), "got: {msg}");
}
#[test]
fn requires_effect_to_be_declared() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"leaks",
Type::Fn {
params: vec![],
ret: Box::new(Type::unit()),
effects: vec![], // !IO missing
},
vec![],
Term::Do {
op: "io/print_int".into(),
args: vec![Term::Lit {
lit: Literal::Int { value: 1 },
}],
},
)],
};
let err = check(&m).unwrap_err();
let msg = format!("{err}");
assert!(msg.contains("undeclared effect"), "got: {msg}");
}
#[test]
fn lets_local_shadow_global() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"f",
Type::Fn {
params: vec![],
ret: Box::new(Type::int()),
effects: vec![],
},
vec![],
Term::Let {
name: "x".into(),
value: Box::new(Term::Lit {
lit: Literal::Int { value: 7 },
}),
body: Box::new(Term::Var { name: "x".into() }),
},
)],
};
check(&m).expect("should typecheck");
}
#[test]
fn match_must_be_exhaustive() {
// Type Maybe = None | Some(Int); fn f only matches None -> error.
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![
Def::Type(TypeDef {
name: "Maybe".into(),
ctors: vec![
Ctor { name: "None".into(), fields: vec![] },
Ctor {
name: "Some".into(),
fields: vec![Type::int()],
},
],
doc: None,
}),
fn_def(
"f",
Type::Fn {
params: vec![Type::Con { name: "Maybe".into() }],
ret: Box::new(Type::int()),
effects: vec![],
},
vec!["m"],
Term::Match {
scrutinee: Box::new(Term::Var { name: "m".into() }),
arms: vec![Arm {
pat: Pattern::Ctor {
ctor: "None".into(),
fields: vec![],
},
body: Term::Lit {
lit: Literal::Int { value: 0 },
},
}],
},
),
],
};
let err = check(&m).unwrap_err();
let msg = format!("{err}");
assert!(msg.contains("non-exhaustive"), "got: {msg}");
assert!(msg.contains("Some"), "got: {msg}");
}
#[test]
fn match_with_wildcard_is_exhaustive() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![
Def::Type(TypeDef {
name: "Maybe".into(),
ctors: vec![
Ctor { name: "None".into(), fields: vec![] },
Ctor {
name: "Some".into(),
fields: vec![Type::int()],
},
],
doc: None,
}),
fn_def(
"f",
Type::Fn {
params: vec![Type::Con { name: "Maybe".into() }],
ret: Box::new(Type::int()),
effects: vec![],
},
vec!["m"],
Term::Match {
scrutinee: Box::new(Term::Var { name: "m".into() }),
arms: vec![
Arm {
pat: Pattern::Ctor {
ctor: "None".into(),
fields: vec![],
},
body: Term::Lit {
lit: Literal::Int { value: 0 },
},
},
Arm {
pat: Pattern::Wild,
body: Term::Lit {
lit: Literal::Int { value: 1 },
},
},
],
},
),
],
};
check(&m).expect("wildcard must satisfy exhaustiveness");
}
#[test]
fn if_branches_must_match() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"f",
Type::Fn {
params: vec![],
ret: Box::new(Type::int()),
effects: vec![],
},
vec![],
Term::If {
cond: Box::new(Term::Lit {
lit: Literal::Bool { value: true },
}),
then: Box::new(Term::Lit {
lit: Literal::Int { value: 1 },
}),
else_: Box::new(Term::Lit { lit: Literal::Unit }),
},
)],
};
let err = check(&m).unwrap_err();
assert!(format!("{err}").contains("type mismatch"));
}
/// Iter 10: `seq` requires lhs to be Unit. A non-Unit lhs is a
/// type error — the value of lhs gets discarded so a useful (non-
/// Unit) value would silently vanish.
#[test]
fn seq_lhs_must_be_unit() {
let m = Module {
schema: SCHEMA.into(),
name: "t".into(),
imports: vec![],
defs: vec![fn_def(
"f",
Type::Fn {
params: vec![],
ret: Box::new(Type::int()),
effects: vec![],
},
vec![],
Term::Seq {
lhs: Box::new(Term::Lit {
lit: Literal::Int { value: 7 },
}),
rhs: Box::new(Term::Lit {
lit: Literal::Int { value: 1 },
}),
},
)],
};
let err = check(&m).unwrap_err();
let msg = format!("{err}");
assert!(msg.contains("type mismatch"), "got: {msg}");
}
}