Files
AILang/crates/ailang-core/src/workspace.rs
T

2611 lines
103 KiB
Rust

//! Workspace loader: loads an entry module and recursively follows its
//! `imports`.
//!
//! Convention: an `import { module: "foo" }` is resolved relative to
//! the entry file's directory as `<root_dir>/foo.ail.json`. Module
//! names must match the file stem (the loader rejects mismatches).
//!
//! The single entry point is [`load_workspace`]; it returns a fully
//! populated [`Workspace`] or a structured [`WorkspaceLoadError`].
//! [`module_hash`] is the module-granularity counterpart to
//! [`crate::def_hash`] and is used both internally (to detect a module
//! re-loaded from disk with different content) and by the CLI.
//!
//! This module is responsible only for **finding** and consistently
//! **loading** all reachable modules. Cross-module typechecking lives
//! in `ailang-check`; codegen in `ailang-codegen`. Neither is run from
//! here.
//!
//! # Examples
//!
//! ```ignore
//! use ailang_core::load_workspace;
//! use std::path::Path;
//!
//! let ws = load_workspace(Path::new("examples/ws_main.ail.json"))?;
//! assert_eq!(ws.entry, "ws_main");
//! // All transitively imported modules are now in `ws.modules`.
//! for (name, m) in &ws.modules {
//! println!("{name}: {} defs", m.defs.len());
//! }
//! # Ok::<(), ailang_core::workspace::WorkspaceLoadError>(())
//! ```
use crate::ast::{ClassDef, Def, InstanceDef, Module, Term, Type};
use crate::canonical;
use crate::{load_module, Error as CoreError};
use std::collections::{BTreeMap, BTreeSet, HashSet};
use std::path::{Path, PathBuf};
/// Fully loaded workspace.
///
/// `entry` names the entry module (module name, **not** a path). All
/// transitively reachable modules are contained in `modules` and indexed
/// by `Module.name`. `root_dir` is the directory the entry file lives
/// in; all imports are resolved relative to it.
///
/// Iter 22b.1 (Decision 11): `registry` is the workspace-global
/// instance registry, built at the end of [`load_workspace`] after the
/// DFS over imports completes. It is empty for any workspace whose
/// modules contain no [`crate::ast::Def::Instance`] defs.
#[derive(Debug, Clone)]
pub struct Workspace {
/// Name of the entry module (the one passed to [`load_workspace`]).
pub entry: String,
/// Every module reachable from `entry`, indexed by module name.
/// `BTreeMap` is used so iteration order is deterministic, which
/// matters for downstream codegen and reporting.
pub modules: BTreeMap<String, Module>,
/// Directory the entry file lives in; all imports are resolved
/// relative to it.
pub root_dir: PathBuf,
/// Iter 22b.1: workspace-global typeclass instance registry.
pub registry: Registry,
}
/// Iter 22b.1: workspace-global instance registry (Decision 11).
///
/// Built at the end of [`load_workspace`] after all modules are
/// loaded. Keyed by `(class-name, canonical-type-hash)`; values are
/// the matching [`crate::ast::InstanceDef`] plus the name of the
/// module it was declared in. The hash key uses
/// [`canonical::type_hash`], so the key is stable against unrelated
/// whitespace / field-order differences in the source JSON.
///
/// 22b.1 enforces three coherence checks during build:
///
/// 1. **Coherence (orphan-freedom).** Every `instance C T` lives in
/// the module of `C` or in the module of `T` (per Decision 11
/// axis 3). Otherwise → [`WorkspaceLoadError::OrphanInstance`].
/// 2. **Uniqueness.** No two entries share a key. Otherwise →
/// [`WorkspaceLoadError::DuplicateInstance`].
/// 3. **Method completeness.** Each instance specifies a body for
/// every required (non-default) method of its class. Otherwise →
/// [`WorkspaceLoadError::MissingMethod`].
#[derive(Debug, Clone, Default)]
pub struct Registry {
/// Map from `(class-name, type-hash)` to the registry entry.
pub entries: BTreeMap<(String, String), RegistryEntry>,
/// ct.1.5a: workspace-wide map from user-defined type-name to its
/// defining module. Used by [`Self::normalize_type_for_lookup`] to
/// rewrite a bare `Type::Con.name` to its always-qualified form
/// before computing the registry key. Primitives are not present.
/// Populated in [`build_registry`] from the same scan that builds
/// the entry map.
///
/// Note: keyed by bare type name only. If two modules each define a
/// type with the same bare name (e.g. `type Foo` in both `M` and
/// `N`), the second `insert` overwrites the first, and
/// [`Self::normalize_type_for_lookup`] would collapse `M.Foo` and
/// `N.Foo` to whichever module wins the race. Acceptable for the
/// current corpus (all in-tree fixtures use distinct bare type
/// names across modules); revisit if a future workspace breaks the
/// assumption. Proper fix is to re-key as
/// `(owning_module, bare_name) -> defining_module` and thread the
/// calling module through every consumer site — out of ct.1's scope.
pub type_def_module: BTreeMap<String, String>,
}
impl Registry {
/// ct.1.5a: produce the canonical form of `t` for registry-key
/// hashing. Bare-non-primitive `Type::Con` names get qualified to
/// `<defining_module>.<name>`; already-qualified names stay; bare
/// names whose defining module is unknown stay as-is.
/// `Type::Fn`/`Type::Forall`/`Type::Var` recurse / pass through
/// structurally.
///
/// Every consumer that hashes an `inst.type_`-shaped expression to
/// look it up in [`Self::entries`] must funnel through this
/// helper, otherwise the registered-form and the queried-form
/// disagree on whether the leading qualifier is present.
pub fn normalize_type_for_lookup(&self, t: &Type) -> Type {
normalize_type_for_registry(t, &self.type_def_module)
}
}
/// One entry in the [`Registry`].
#[derive(Debug, Clone)]
pub struct RegistryEntry {
/// The instance declaration itself.
pub instance: InstanceDef,
/// Name of the module the instance was declared in.
pub defining_module: String,
}
/// Structured errors of the workspace loader.
///
/// `Cycle.path` is the chain of module names in which the cycle was
/// closed — the last element is the name already present in `visiting`.
#[derive(Debug, thiserror::Error)]
pub enum WorkspaceLoadError {
/// File I/O failed while reading a module file (typically: file
/// missing, permission denied).
#[error("io error for {path}: {source}")]
Io {
path: PathBuf,
#[source]
source: std::io::Error,
},
/// File contents failed to parse as a [`Module`] or had the wrong
/// schema tag. Wraps a [`CoreError`] (the single-module loader's
/// error type).
#[error("schema/parse error in {path}: {source}")]
Schema {
path: PathBuf,
#[source]
source: CoreError,
},
/// An `import { module: "foo" }` did not resolve to an existing
/// file at the expected path.
#[error("module `{name}` not found (expected at {expected_path})")]
ModuleNotFound { name: String, expected_path: PathBuf },
/// The `name` field in a loaded module file disagrees with the
/// file-stem-derived name the loader expected (i.e. the
/// `<name>.ail.json` convention is broken).
#[error(
"module name in file ({name_in_file:?}) does not match expected name from path ({name_from_path:?})"
)]
ModuleNameMismatch {
name_in_file: String,
name_from_path: String,
},
/// An import cycle was detected. `path` is the chain of module
/// names in which the cycle was closed — the last element is the
/// name that was already on the visit stack.
#[error("import cycle detected: {}", path.join(" -> "))]
Cycle { path: Vec<String> },
/// A module was reachable through two import paths, and its
/// on-disk content (compared via [`module_hash`]) differs between
/// the two reads. This typically means the file changed mid-load.
#[error(
"module `{name}` was loaded twice with differing content (hashes differ)"
)]
ModuleHashMismatch { name: String },
/// Iter 22b.1: an [`crate::ast::Def::Instance`] was declared in a
/// module that is neither the class's defining module nor the
/// instance type's defining module. Coherence violation per
/// Decision 11 axis 3 ("orphan-freedom"). The lookup is hard:
/// AILang does not provide a `--allow-orphans` flag.
#[error(
"orphan instance: `instance {class} {type_repr}` declared in module `{defining_module}`, \
but neither `{class}` (in `{class_module}`) nor `{type_repr}` (in `{type_module}`) lives there"
)]
OrphanInstance {
class: String,
type_repr: String,
defining_module: String,
class_module: String,
type_module: String,
},
/// Iter 22b.1: two [`crate::ast::Def::Instance`]s share the same
/// `(class, canonical-type-hash)` key. Coherence requires
/// uniqueness; the registry has no way to disambiguate at
/// resolution time. Per Decision 11 there is no
/// `AmbiguousInstance` diagnostic — coherence makes the lookup
/// unambiguous by construction, and a duplicate is a workspace
/// configuration error, not a per-call-site one.
#[error(
"duplicate instance: `instance {class} {type_repr}` declared in both `{first_module}` and `{second_module}`"
)]
DuplicateInstance {
class: String,
type_repr: String,
first_module: String,
second_module: String,
},
/// Iter 22b.1: an [`crate::ast::Def::Instance`] does not specify
/// a body for a required (non-default) method of its class.
/// Default-bearing methods may be inherited; non-default
/// (abstract-required) methods must be specified by every
/// instance. Per Decision 11 §"Defaults and superclasses".
#[error(
"instance `{class} {type_repr}` is missing a body for method `{method}` (no default)"
)]
MissingMethod {
class: String,
type_repr: String,
method: String,
},
/// Iter 22b.2: class-schema validation. The class parameter
/// appears in applied position (e.g. as the head of a
/// `Type::Con { name == param, args.len() > 0 }`) inside a method
/// signature. Decision 11 axis 5 forbids HKTs — class params are
/// kind `*` only.
#[error(
"kind mismatch in class `{class}`: parameter `{param}` is used in applied position \
inside method `{method}` (Decision 11 axis 5: class params are kind `*` only)"
)]
KindMismatch {
class: String,
param: String,
method: String,
defining_module: String,
},
/// Iter 22b.2: class-schema validation. A class's `superclass.type`
/// does not equal its own `param`. Decision 11 single-superclass
/// model requires the superclass to be applied to the same param
/// (e.g. `class Ord a extends Eq a`, not `extends Eq b`).
#[error(
"class `{class}` declares superclass `{superclass} {got_type}`, but its own parameter is `{expected_param}` \
— superclass `type` must equal class `param`"
)]
InvalidSuperclassParam {
class: String,
superclass: String,
expected_param: String,
got_type: String,
},
/// Iter 22b.2: class-schema validation. A class method's
/// signature contains a constraint referencing a type variable
/// that is neither bound by the method's `Forall.vars` nor equal
/// to the class's `param`.
#[error(
"in class `{class}` method `{method}`: constraint `{constraint_class} {var}` references unbound type variable `{var}`"
)]
UnboundConstraintTypeVar {
class: String,
method: String,
constraint_class: String,
var: String,
},
/// Iter 22b.2: an instance specifies a body for a method name
/// that the corresponding class does not declare. Symmetric to
/// `MissingMethod` but in the opposite direction.
#[error(
"instance `{class} {type_repr}` provides body for method `{method}`, but class `{class}` does not declare it"
)]
OverridingNonExistentMethod {
class: String,
type_repr: String,
method: String,
},
/// Iter 22b.2: a class-method name collides with another
/// class-method or with a top-level fn. `kind` is
/// `"class-class"` or `"class-fn"`.
#[error(
"method name `{method}` collides ({kind}): defined in `{first_origin}` and `{second_origin}`"
)]
MethodNameCollision {
method: String,
kind: &'static str,
first_origin: String,
second_origin: String,
},
/// Iter 22b.2: an instance `C T` was declared, but `C`'s
/// superclass `S` does not have an instance for the same type
/// `T`. Decision 11 single-superclass model requires `instance S
/// T` to exist whenever `instance C T` exists.
#[error(
"instance `{class} {type_repr}` requires superclass instance `{superclass} {type_repr}`, but none was found"
)]
MissingSuperclassInstance {
class: String,
superclass: String,
type_repr: String,
},
/// Iter 23.1: a user module attempted to use the reserved
/// module name `prelude`. The prelude is auto-injected by
/// the loader, so a user module of the same name would
/// collide silently. Reject explicitly.
#[error("module name {name:?} is reserved (auto-injected by the loader)")]
ReservedModuleName { name: String },
/// ct.1 (canonical-type-names): a `Type::Con` whose `name` is
/// neither a primitive nor a local TypeDef of the owning module
/// was encountered. Under the canonical-form rule, bare =
/// local; a bare cross-module ref is a schema violation.
/// `candidates` lists the qualified forms found by scanning the
/// owning module's imports in declaration order.
#[error(
"module `{module}` contains bare type name `{name}` that does not resolve to a local type. \
AILang's `.ail.json` requires cross-module type references to be qualified. \
Candidates from imports: {candidates:?}. Run `ail migrate-canonical-types` to fix legacy fixtures."
)]
BareCrossModuleTypeRef {
module: String,
name: String,
candidates: Vec<String>,
},
/// ct.1: a qualified `Type::Con` of the form `<owner>.<type>`
/// was encountered, but `<owner>` is not a known module in the
/// workspace, or `<owner>` is known but declares no TypeDef
/// named `<type>`.
#[error(
"module `{module}` references qualified type `{name}` but the owner module is not known \
or does not declare a type by that name"
)]
BadCrossModuleTypeRef {
module: String,
name: String,
},
/// ct.1: a class-reference field (`InstanceDef.class`,
/// `SuperclassRef.class`, `Constraint.class`, or
/// `ClassDef.name`) contains a `.` — under this milestone class
/// names are NOT module-qualified (see DESIGN spec §"Out of
/// scope: Class names"). The schema rejects qualified forms so
/// half-migrated files cannot silently load.
#[error(
"module `{module}` contains qualified class name `{name}` in field `{field}`. \
Class names are not module-qualified in this milestone; \
keep the bare form."
)]
QualifiedClassName {
module: String,
name: String,
field: &'static str,
},
}
/// Hash over the canonical bytes of a complete module.
///
/// Parallel to `def_hash`, but at module level. The workspace loader
/// uses this to verify double-loads; the CLI uses it to emit a stable
/// per-module identifier.
pub fn module_hash(m: &Module) -> String {
let bytes = canonical::to_bytes(m);
let h = blake3::hash(&bytes);
h.to_hex().as_str()[..16].to_string()
}
/// Iter 23.1: the prelude module is embedded into the binary at
/// compile time so the loader needs no on-disk resolution. The
/// canonical source-of-truth file remains
/// `examples/prelude.ail.json` (the file the LLM-author edits).
const PRELUDE_JSON: &str = include_str!(
"../../../examples/prelude.ail.json"
);
/// Iter 23.1: parse the embedded prelude source into a `Module`.
/// Panics on parse failure — the prelude is build-time-validated;
/// a failure here means the embedded file is malformed and is a
/// build-correctness bug, not a runtime concern.
fn load_prelude() -> Module {
serde_json::from_str(PRELUDE_JSON)
.expect("examples/prelude.ail.json must parse as a Module")
}
/// Load entry module plus all transitively reachable modules.
///
/// Algorithm: DFS over `imports`, with two sets:
/// - `loaded` (= `modules` map): modules whose subtree is already fully
/// processed. On a re-hit only hash consistency is checked.
/// - `visiting`: stack of modules whose DFS descent is still running.
/// A hit here = cycle.
pub fn load_workspace(entry_path: &Path) -> Result<Workspace, WorkspaceLoadError> {
let entry_path = entry_path.to_path_buf();
let root_dir = entry_path
.parent()
.map(Path::to_path_buf)
.unwrap_or_else(|| PathBuf::from("."));
// Load entry module + check name<->filename convention.
let entry_module = load_one(&entry_path)?;
let expected_entry_name = module_name_from_path(&entry_path);
if entry_module.name != expected_entry_name {
return Err(WorkspaceLoadError::ModuleNameMismatch {
name_in_file: entry_module.name.clone(),
name_from_path: expected_entry_name,
});
}
let entry_name = entry_module.name.clone();
let mut modules: BTreeMap<String, Module> = BTreeMap::new();
let mut visiting: Vec<String> = Vec::new();
let mut visiting_set: HashSet<String> = HashSet::new();
visit(
entry_module,
&root_dir,
&mut modules,
&mut visiting,
&mut visiting_set,
)?;
// Iter 23.1: inject the prelude module. It is implicitly
// part of every workspace, so the user's import graph
// does not name it. A user module that happens to be named
// "prelude" would collide here; reject explicitly so the
// failure is informative rather than silent.
if modules.contains_key("prelude") {
return Err(WorkspaceLoadError::ReservedModuleName {
name: "prelude".to_string(),
});
}
let prelude = load_prelude();
modules.insert("prelude".to_string(), prelude);
// ct.1: enforce the canonical-form rule on Type::Con and
// Term::Ctor.type_name. Runs before class-schema validation
// so a stale bare cross-module ref fires the canonical-form
// diagnostic instead of a downstream one.
validate_canonical_type_names(&modules)?;
// Iter 22b.2: class-schema validation runs before registry
// construction so that ill-kinded class definitions are rejected
// before any instance against them is registered.
validate_classdefs(&modules)?;
// Iter 22b.1: build the workspace-global instance registry. Three
// coherence checks fire here (Orphan / Duplicate / Missing-method);
// any violation is surfaced as a `WorkspaceLoadError`, not as a
// per-call-site diagnostic.
let registry = build_registry(&modules)?;
Ok(Workspace {
entry: entry_name,
modules,
root_dir,
registry,
})
}
/// Iter 22b.1: build the workspace-global typeclass instance registry.
///
/// Two passes:
///
/// 1. Scan every loaded module to build a "where is X defined" lookup
/// for class names and type names — needed for the coherence
/// (orphan) check below.
/// 2. For each [`crate::ast::Def::Instance`] in declaration order,
/// apply the three checks (coherence / uniqueness / method
/// completeness) and insert the entry on success.
///
/// Iteration is over the modules `BTreeMap` (alphabetical by name) so
/// the order in which collisions are detected is deterministic across
/// runs. Within a module, defs are scanned in source order.
fn build_registry(
modules: &BTreeMap<String, Module>,
) -> Result<Registry, WorkspaceLoadError> {
// Pass 1: collect "where is X defined" maps, plus a class lookup
// by name (needed for the method-completeness check).
let mut class_def_module: BTreeMap<String, String> = BTreeMap::new();
let mut type_def_module: BTreeMap<String, String> = BTreeMap::new();
let mut class_by_name: BTreeMap<String, &ClassDef> = BTreeMap::new();
for (mod_name, m) in modules {
for def in &m.defs {
match def {
Def::Class(c) => {
class_def_module.insert(c.name.clone(), mod_name.clone());
class_by_name.insert(c.name.clone(), c);
}
Def::Type(t) => {
type_def_module.insert(t.name.clone(), mod_name.clone());
}
_ => {}
}
}
}
// Iter 22b.2: method-name-collision pre-pass. Bare-name resolution
// (`foo x` rather than `A.foo x`) requires that a method name
// appears in at most one origin across the whole workspace. We
// walk every `Def::Class` and `Def::Fn` once, building a
// `method_origins` map; the first repeat fires the diagnostic.
// The `kind` field distinguishes class-method ↔ class-method from
// class-method ↔ top-level-fn; fn-fn collisions are a separate
// concern surfaced by `CheckError::DuplicateDef` in `ailang-check`,
// not here.
//
// Origins are kept structural (the `Origin` enum below) so the
// `kind` discriminator is a `match` on variants rather than a
// string-prefix check on a display form.
enum Origin {
Class { class_name: String, module: String },
Fn { name: String, module: String },
}
impl Origin {
fn format(&self) -> String {
match self {
Origin::Class { class_name, module } => {
format!("class {class_name} (in {module})")
}
Origin::Fn { name, module } => format!("fn {name} (in {module})"),
}
}
}
let mut method_origins: BTreeMap<String, Origin> = BTreeMap::new();
for (mod_name, m) in modules {
for def in &m.defs {
match def {
Def::Class(c) => {
for method in &c.methods {
let origin = Origin::Class {
class_name: c.name.clone(),
module: mod_name.clone(),
};
if let Some(prior) = method_origins.get(&method.name) {
let kind = match prior {
Origin::Class { .. } => "class-class",
Origin::Fn { .. } => "class-fn",
};
return Err(WorkspaceLoadError::MethodNameCollision {
method: method.name.clone(),
kind,
first_origin: prior.format(),
second_origin: origin.format(),
});
}
method_origins.insert(method.name.clone(), origin);
}
}
Def::Fn(f) => {
let origin = Origin::Fn {
name: f.name.clone(),
module: mod_name.clone(),
};
if let Some(prior) = method_origins.get(&f.name) {
// Only fire on class-fn collisions here. fn-fn
// collisions (two `Def::Fn` with the same name)
// are `CheckError::DuplicateDef`'s job in
// `ailang-check`; firing here with `kind:
// "class-fn"` would misreport.
if matches!(prior, Origin::Class { .. }) {
return Err(WorkspaceLoadError::MethodNameCollision {
method: f.name.clone(),
kind: "class-fn",
first_origin: prior.format(),
second_origin: origin.format(),
});
}
// prior is a fn: skip; do not overwrite.
} else {
method_origins.insert(f.name.clone(), origin);
}
}
_ => {}
}
}
}
// Pass 2: register each instance, with coherence / uniqueness /
// method-completeness checks.
let mut entries: BTreeMap<(String, String), RegistryEntry> = BTreeMap::new();
for (mod_name, m) in modules {
for def in &m.defs {
if let Def::Instance(inst) = def {
let type_repr = type_head_name(&inst.type_);
// Coherence (orphan-freedom): instance's module must
// equal the class's module or the type's module. A
// class declared inside the same module as the
// instance always satisfies the first leg; a
// user-defined type declared in the instance's module
// satisfies the second. Primitives have no
// user-defined module — instances on primitives
// therefore must live in the class's module.
let class_mod = class_def_module
.get(&inst.class)
.cloned()
.unwrap_or_else(|| "<unknown-class>".into());
let type_mod = type_def_module
.get(&type_repr)
.cloned()
.unwrap_or_else(|| "<primitive-or-unknown>".into());
let coherent = mod_name == &class_mod || mod_name == &type_mod;
if !coherent {
return Err(WorkspaceLoadError::OrphanInstance {
class: inst.class.clone(),
type_repr,
defining_module: mod_name.clone(),
class_module: class_mod,
type_module: type_mod,
});
}
// Uniqueness: a `(class, type-hash)` key must appear
// at most once across the whole workspace. ct.1.5a: the
// type expression is normalised to its always-qualified
// form before hashing so a bare-local declaration in
// the type's defining module and a qualified-cross-module
// declaration from elsewhere produce the same key (both
// refer to the same type under the canonical-form rule).
let type_hash = canonical::type_hash(
&normalize_type_for_registry(&inst.type_, &type_def_module),
);
let key = (inst.class.clone(), type_hash);
if let Some(prior) = entries.get(&key) {
return Err(WorkspaceLoadError::DuplicateInstance {
class: inst.class.clone(),
type_repr,
first_module: prior.defining_module.clone(),
second_module: mod_name.clone(),
});
}
// Method completeness: every non-default method of
// the class must have a body in this instance.
// Defaults may be inherited (no body required).
// Missing class declaration is deferred to 22b.2's
// typecheck arms — for 22b.1 we skip the
// completeness check rather than firing a separate
// diagnostic.
if let Some(class_def) = class_by_name.get(&inst.class) {
let provided: BTreeSet<&str> =
inst.methods.iter().map(|m| m.name.as_str()).collect();
for class_method in &class_def.methods {
if class_method.default.is_none()
&& !provided.contains(class_method.name.as_str())
{
return Err(WorkspaceLoadError::MissingMethod {
class: inst.class.clone(),
type_repr,
method: class_method.name.clone(),
});
}
}
// Symmetric to MissingMethod: an instance must
// not specify a body for a method name the class
// never declared. Decision 11 forbids ad-hoc
// additions to a class's method set at the
// instance site.
let declared: BTreeSet<&str> =
class_def.methods.iter().map(|m| m.name.as_str()).collect();
for inst_method in &inst.methods {
if !declared.contains(inst_method.name.as_str()) {
return Err(WorkspaceLoadError::OverridingNonExistentMethod {
class: inst.class.clone(),
type_repr: type_repr.clone(),
method: inst_method.name.clone(),
});
}
}
}
entries.insert(
key,
RegistryEntry {
instance: inst.clone(),
defining_module: mod_name.clone(),
},
);
}
}
}
// Iter 22b.2: superclass-instance completeness. For every entry,
// walk the class's superclass chain and require an entry for each
// step at the same type-hash.
for (key, entry) in entries.iter() {
let (class_name, type_hash) = key;
let type_repr = type_head_name(&entry.instance.type_);
// Iter 22b.2 leaves superclass-cycle detection to a future arm;
// here we just terminate the walk.
let mut visited: BTreeSet<&str> = BTreeSet::new();
let mut current = class_by_name.get(class_name.as_str()).copied();
while let Some(c) = current {
if !visited.insert(c.name.as_str()) {
break;
}
if let Some(sc) = &c.superclass {
let sc_key = (sc.class.clone(), type_hash.clone());
if !entries.contains_key(&sc_key) {
return Err(WorkspaceLoadError::MissingSuperclassInstance {
class: class_name.clone(),
superclass: sc.class.clone(),
type_repr: type_repr.clone(),
});
}
current = class_by_name.get(sc.class.as_str()).copied();
} else {
break;
}
}
}
Ok(Registry {
entries,
type_def_module,
})
}
/// Iter 22b.2: class-schema validation. Runs before `build_registry`.
/// Three diagnostics fire from here: `kind-mismatch`,
/// `invalid-superclass-param`, `constraint-references-unbound-type-var`.
fn validate_classdefs(
modules: &BTreeMap<String, Module>,
) -> Result<(), WorkspaceLoadError> {
for (mod_name, m) in modules {
for def in &m.defs {
if let Def::Class(c) = def {
for method in &c.methods {
walk_kind_mismatch(&method.ty, &c.param)
.map_err(|()| WorkspaceLoadError::KindMismatch {
class: c.name.clone(),
param: c.param.clone(),
method: method.name.clone(),
defining_module: mod_name.clone(),
})?;
}
if let Some(sc) = &c.superclass {
if sc.type_ != c.param {
return Err(WorkspaceLoadError::InvalidSuperclassParam {
class: c.name.clone(),
superclass: sc.class.clone(),
expected_param: c.param.clone(),
got_type: sc.type_.clone(),
});
}
}
for method in &c.methods {
if let Type::Forall { vars, constraints, .. } = &method.ty {
let mut bound: BTreeSet<&str> =
vars.iter().map(String::as_str).collect();
bound.insert(c.param.as_str());
for constr in constraints {
if let Type::Var { name } = &constr.type_ {
if !bound.contains(name.as_str()) {
return Err(WorkspaceLoadError::UnboundConstraintTypeVar {
class: c.name.clone(),
method: method.name.clone(),
constraint_class: constr.class.clone(),
var: name.clone(),
});
}
}
}
}
}
}
}
}
Ok(())
}
/// Walks a `Type` looking for any `Type::Con { name == param, args
/// non-empty }`. The class param is kind `*`; appearing as a
/// constructor with arguments is a kind-mismatch.
fn walk_kind_mismatch(t: &Type, param: &str) -> Result<(), ()> {
match t {
Type::Con { name, args } => {
if name == param && !args.is_empty() {
return Err(());
}
for a in args {
walk_kind_mismatch(a, param)?;
}
Ok(())
}
Type::Fn { params, ret, .. } => {
for p in params {
walk_kind_mismatch(p, param)?;
}
walk_kind_mismatch(ret, param)
}
Type::Forall { body, .. } => walk_kind_mismatch(body, param),
Type::Var { .. } => Ok(()),
}
}
/// ct.1: the five primitive type names that are always bare under
/// the canonical-form rule. Kept in sync with `Type::int`,
/// `Type::bool_`, `Type::str_`, `Type::unit`, `Type::float` in
/// `crate::ast`.
fn is_primitive_type_name(name: &str) -> bool {
matches!(name, "Int" | "Bool" | "Str" | "Unit" | "Float")
}
/// ct.1.5a: normalize a `Type` by qualifying every bare-non-primitive
/// `Type::Con.name` to its always-qualified form
/// (`<defining_module>.<name>`). Primitives stay bare; already-qualified
/// names stay as-is; bare names whose defining module is unknown stay
/// as-is (downstream diagnostics will catch them). `Type::Fn` /
/// `Type::Forall` / `Type::Var` recurse / pass through structurally.
///
/// Used by [`build_registry`] for registry-key canonicalisation so the
/// duplicate-instance check survives the asymmetric "bare = local,
/// qualified = cross-module" canonical-form rule: an instance declared
/// bare-local in the type's defining module and an equivalent one
/// declared qualified-cross-module from elsewhere produce the same
/// registry key.
///
/// The qualifier is the type's *defining* module (looked up in
/// `type_def_module`), not the instance's owning module. The two
/// coincide under a canonical-form-compliant workspace (bare implies
/// local-to-defining-module), but using the defining-module lookup is
/// robust against pre-`validate_canonical_type_names`-wired fixtures
/// that may still carry bare cross-module refs.
fn normalize_type_for_registry(
t: &Type,
type_def_module: &BTreeMap<String, String>,
) -> Type {
match t {
Type::Con { name, args } => {
let new_name = if name.contains('.') || is_primitive_type_name(name) {
name.clone()
} else if let Some(owner) = type_def_module.get(name) {
format!("{owner}.{name}")
} else {
// Unknown bare non-primitive — leave as-is. Either it is
// a class-param Type::Var miscoded as a Con (which is a
// separate well-formedness problem) or a stale ref that
// downstream diagnostics will catch.
name.clone()
};
Type::Con {
name: new_name,
args: args
.iter()
.map(|a| normalize_type_for_registry(a, type_def_module))
.collect(),
}
}
Type::Fn { params, param_modes, ret, ret_mode, effects } => Type::Fn {
params: params
.iter()
.map(|p| normalize_type_for_registry(p, type_def_module))
.collect(),
param_modes: param_modes.clone(),
ret: Box::new(normalize_type_for_registry(ret, type_def_module)),
ret_mode: *ret_mode,
effects: effects.clone(),
},
Type::Forall { vars, constraints, body } => Type::Forall {
vars: vars.clone(),
constraints: constraints
.iter()
.map(|c| crate::ast::Constraint {
class: c.class.clone(),
type_: normalize_type_for_registry(&c.type_, type_def_module),
})
.collect(),
body: Box::new(normalize_type_for_registry(body, type_def_module)),
},
Type::Var { name } => Type::Var { name: name.clone() },
}
}
/// ct.1: enforce the canonical-form rule on every `Type::Con` and
/// `Term::Ctor.type_name` reference in every loaded module. Runs
/// after prelude injection and before class-schema validation, so a
/// stale bare cross-module ref fires the canonical-form diagnostic
/// rather than a downstream one.
///
/// Rule per spec §Architecture:
/// 1. Qualified `<owner>.<type>`: `<owner>` must be a known module,
/// `<type>` must be one of its TypeDefs. Else `BadCrossModuleTypeRef`.
/// 2. Bare primitive (`Int`/`Bool`/`Str`/`Unit`/`Float`): accepted.
/// 3. Bare non-primitive: must be a TypeDef in the owning module.
/// Else `BareCrossModuleTypeRef` with `candidates` = qualified
/// forms found by scanning the owning module's imports.
pub(crate) fn validate_canonical_type_names(
modules: &BTreeMap<String, Module>,
) -> Result<(), WorkspaceLoadError> {
// Pre-pass: for each module, build a `BTreeSet<String>` of local
// TypeDef names. Used for both the owning-module local lookup
// and the per-import owner lookup.
let mut local_types: BTreeMap<String, BTreeSet<String>> = BTreeMap::new();
for (mod_name, m) in modules {
let mut s = BTreeSet::new();
for def in &m.defs {
if let Def::Type(t) = def {
s.insert(t.name.clone());
}
}
local_types.insert(mod_name.clone(), s);
}
for (mod_name, m) in modules {
// Imports in declaration order — used for both the
// qualified-`<owner>` known-module check and the bare-non-primitive
// candidates list.
let import_names: Vec<&str> = m.imports.iter().map(|i| i.module.as_str()).collect();
// Walk every Type in this module's defs and check each Type::Con name.
for def in &m.defs {
walk_def_types(def, &mut |t: &Type| {
if let Type::Con { name, .. } = t {
check_type_con_name(
name, mod_name, &local_types, &import_names,
)?;
}
Ok(())
})?;
walk_def_terms(def, &mut |type_name: &str| {
check_type_con_name(
type_name, mod_name, &local_types, &import_names,
)
})?;
check_class_name_fields(def, mod_name)?;
}
}
Ok(())
}
/// ct.1: apply the canonical-form rule to one `Type::Con.name`
/// (also reused for `Term::Ctor.type_name` in Task 2).
fn check_type_con_name(
name: &str,
owning_module: &str,
local_types: &BTreeMap<String, BTreeSet<String>>,
import_names: &[&str],
) -> Result<(), WorkspaceLoadError> {
if let Some((prefix, suffix)) = name.split_once('.') {
// Rule 1: qualified.
let owner_types = local_types
.get(prefix)
.ok_or_else(|| WorkspaceLoadError::BadCrossModuleTypeRef {
module: owning_module.to_string(),
name: name.to_string(),
})?;
if !owner_types.contains(suffix) {
return Err(WorkspaceLoadError::BadCrossModuleTypeRef {
module: owning_module.to_string(),
name: name.to_string(),
});
}
return Ok(());
}
// Bare.
if is_primitive_type_name(name) {
return Ok(()); // Rule 2.
}
// Rule 3: must be local.
if local_types
.get(owning_module)
.map(|s| s.contains(name))
.unwrap_or(false)
{
return Ok(());
}
// Bare cross-module — collect candidates from imports in declaration order.
// Prelude is implicit: scan it last as a fallback candidate (mirrors
// iter 23.2.4's implicit-prelude behaviour in codegen).
let mut candidates: Vec<String> = Vec::new();
for imp in import_names {
if local_types
.get(*imp)
.map(|s| s.contains(name))
.unwrap_or(false)
{
candidates.push(format!("{imp}.{name}"));
}
}
if !import_names.contains(&"prelude")
&& local_types
.get("prelude")
.map(|s| s.contains(name))
.unwrap_or(false)
{
candidates.push(format!("prelude.{name}"));
}
Err(WorkspaceLoadError::BareCrossModuleTypeRef {
module: owning_module.to_string(),
name: name.to_string(),
candidates,
})
}
/// ct.1: walk every `Type` reachable from a single `Def`, calling
/// `f` on each. Recurses into `Type::Fn.params/ret`, `Type::Con.args`,
/// `Type::Forall.constraints/body`, plus the obvious top-level fields
/// of each `Def` variant AND every Type annotation embedded in a Term
/// (`Term::Lam.param_tys`, `Term::Lam.ret_ty`, `Term::LetRec.ty`) —
/// because those are Type-position occurrences too. Term::Ctor name
/// walking is a separate concern handled in Task 2 since that field
/// is a `String`, not a `Type`.
fn walk_def_types<F>(def: &Def, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&Type) -> Result<(), WorkspaceLoadError>,
{
match def {
Def::Fn(fd) => {
walk_type(&fd.ty, f)?;
walk_term_embedded_types(&fd.body, f)
}
Def::Const(cd) => {
walk_type(&cd.ty, f)?;
walk_term_embedded_types(&cd.value, f)
}
Def::Type(td) => {
for c in &td.ctors {
for fty in &c.fields {
walk_type(fty, f)?;
}
}
Ok(())
}
Def::Class(cd) => {
for cm in &cd.methods {
walk_type(&cm.ty, f)?;
if let Some(body) = &cm.default {
walk_term_embedded_types(body, f)?;
}
}
Ok(())
}
Def::Instance(id) => {
walk_type(&id.type_, f)?;
for im in &id.methods {
walk_term_embedded_types(&im.body, f)?;
}
Ok(())
}
}
}
/// ct.1: walk a `Term` and call `f` on every Type annotation embedded
/// in it (Lam.param_tys, Lam.ret_ty, LetRec.ty). Recurses through
/// every Term sub-position. Does NOT fire on `Term::Ctor.type_name`
/// (that's a `String`, not a `Type`; handled by `walk_def_terms` in
/// Task 2).
fn walk_term_embedded_types<F>(t: &Term, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&Type) -> Result<(), WorkspaceLoadError>,
{
match t {
Term::Lit { .. } | Term::Var { .. } => Ok(()),
Term::App { callee, args, .. } => {
walk_term_embedded_types(callee, f)?;
for a in args { walk_term_embedded_types(a, f)?; }
Ok(())
}
Term::Let { value, body, .. } => {
walk_term_embedded_types(value, f)?;
walk_term_embedded_types(body, f)
}
Term::LetRec { ty, body, in_term, .. } => {
walk_type(ty, f)?;
walk_term_embedded_types(body, f)?;
walk_term_embedded_types(in_term, f)
}
Term::If { cond, then, else_ } => {
walk_term_embedded_types(cond, f)?;
walk_term_embedded_types(then, f)?;
walk_term_embedded_types(else_, f)
}
Term::Do { args, .. } => {
for a in args { walk_term_embedded_types(a, f)?; }
Ok(())
}
Term::Ctor { args, .. } => {
for a in args { walk_term_embedded_types(a, f)?; }
Ok(())
}
Term::Match { scrutinee, arms } => {
walk_term_embedded_types(scrutinee, f)?;
for arm in arms {
walk_term_embedded_types(&arm.body, f)?;
}
Ok(())
}
Term::Lam { param_tys, ret_ty, body, .. } => {
for pt in param_tys { walk_type(pt, f)?; }
walk_type(ret_ty, f)?;
walk_term_embedded_types(body, f)
}
Term::Seq { lhs, rhs } => {
walk_term_embedded_types(lhs, f)?;
walk_term_embedded_types(rhs, f)
}
Term::Clone { value } => walk_term_embedded_types(value, f),
Term::ReuseAs { source, body } => {
walk_term_embedded_types(source, f)?;
walk_term_embedded_types(body, f)
}
}
}
/// ct.1: recursive walk of a `Type`, calling `f` at every node.
fn walk_type<F>(t: &Type, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&Type) -> Result<(), WorkspaceLoadError>,
{
f(t)?;
match t {
Type::Con { args, .. } => {
for a in args {
walk_type(a, f)?;
}
Ok(())
}
Type::Fn { params, ret, .. } => {
for p in params {
walk_type(p, f)?;
}
walk_type(ret, f)
}
Type::Forall { body, constraints, .. } => {
for c in constraints {
walk_type(&c.type_, f)?;
}
walk_type(body, f)
}
Type::Var { .. } => Ok(()),
}
}
/// ct.1: walk every `Term::Ctor.type_name` reachable from a single
/// `Def`, calling `f` on the type_name strings. Used to enforce the
/// canonical-form rule on term-side type references.
fn walk_def_terms<F>(def: &Def, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&str) -> Result<(), WorkspaceLoadError>,
{
match def {
Def::Fn(fd) => walk_term(&fd.body, f),
Def::Const(cd) => walk_term(&cd.value, f),
Def::Type(_) => Ok(()),
Def::Class(cd) => {
for cm in &cd.methods {
if let Some(body) = &cm.default {
walk_term(body, f)?;
}
}
Ok(())
}
Def::Instance(id) => {
for im in &id.methods {
walk_term(&im.body, f)?;
}
Ok(())
}
}
}
/// ct.1: recursive walk of a `Term`, calling `f` on every
/// `Term::Ctor.type_name`. Embedded `Type` annotations (Lam param /
/// return types, LetRec types) ride the `walk_def_types` /
/// `walk_term_embedded_types` path — but `Term::Ctor.type_name` is
/// a `String`, not a `Type`, so it lives here.
fn walk_term<F>(t: &Term, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&str) -> Result<(), WorkspaceLoadError>,
{
match t {
Term::Lit { .. } | Term::Var { .. } => Ok(()),
Term::App { callee, args, .. } => {
walk_term(callee, f)?;
for a in args {
walk_term(a, f)?;
}
Ok(())
}
Term::Let { value, body, .. } => {
walk_term(value, f)?;
walk_term(body, f)
}
Term::LetRec { body, in_term, .. } => {
walk_term(body, f)?;
walk_term(in_term, f)
}
Term::If { cond, then, else_ } => {
walk_term(cond, f)?;
walk_term(then, f)?;
walk_term(else_, f)
}
Term::Do { args, .. } => {
for a in args {
walk_term(a, f)?;
}
Ok(())
}
Term::Ctor { type_name, args, .. } => {
f(type_name)?;
for a in args {
walk_term(a, f)?;
}
Ok(())
}
Term::Match { scrutinee, arms } => {
walk_term(scrutinee, f)?;
for arm in arms {
walk_pattern(&arm.pat, f)?;
walk_term(&arm.body, f)?;
}
Ok(())
}
Term::Lam { body, .. } => walk_term(body, f),
Term::Seq { lhs, rhs } => {
walk_term(lhs, f)?;
walk_term(rhs, f)
}
Term::Clone { value } => walk_term(value, f),
Term::ReuseAs { source, body } => {
walk_term(source, f)?;
walk_term(body, f)
}
}
}
/// ct.1: Pattern::Ctor carries a `ctor` name (matches against a
/// scrutinee's TypeDef) but NOT a type_name field — the type is
/// inferred from the scrutinee. So Pattern walking only recurses;
/// no canonical-form check fires here.
fn walk_pattern<F>(p: &crate::ast::Pattern, f: &mut F) -> Result<(), WorkspaceLoadError>
where
F: FnMut(&str) -> Result<(), WorkspaceLoadError>,
{
use crate::ast::Pattern;
match p {
Pattern::Wild | Pattern::Var { .. } | Pattern::Lit { .. } => Ok(()),
Pattern::Ctor { fields, .. } => {
for sub in fields {
walk_pattern(sub, f)?;
}
Ok(())
}
}
}
/// ct.1: reject any `.` in the four class-reference fields.
/// `ClassDef.name`, `InstanceDef.class`, `SuperclassRef.class`,
/// `Constraint.class`. Per spec §"Out of scope: Class names": class
/// names are NOT module-qualified in this milestone, so any
/// qualified form indicates a half-migrated file.
fn check_class_name_fields(
def: &Def,
owning_module: &str,
) -> Result<(), WorkspaceLoadError> {
fn fire(
owning_module: &str,
name: &str,
field: &'static str,
) -> WorkspaceLoadError {
WorkspaceLoadError::QualifiedClassName {
module: owning_module.to_string(),
name: name.to_string(),
field,
}
}
match def {
Def::Class(cd) => {
if cd.name.contains('.') {
return Err(fire(owning_module, &cd.name, "ClassDef.name"));
}
if let Some(sc) = &cd.superclass {
if sc.class.contains('.') {
return Err(fire(owning_module, &sc.class, "SuperclassRef.class"));
}
}
for m in &cd.methods {
if let Type::Forall { constraints, .. } = &m.ty {
for c in constraints {
if c.class.contains('.') {
return Err(fire(owning_module, &c.class, "Constraint.class"));
}
}
}
}
Ok(())
}
Def::Instance(id) => {
if id.class.contains('.') {
return Err(fire(owning_module, &id.class, "InstanceDef.class"));
}
Ok(())
}
Def::Fn(fd) => {
if let Type::Forall { constraints, .. } = &fd.ty {
for c in constraints {
if c.class.contains('.') {
return Err(fire(owning_module, &c.class, "Constraint.class"));
}
}
}
Ok(())
}
Def::Const(_) | Def::Type(_) => Ok(()),
}
}
/// Iter 22b.1: extract the head-constructor name of a type, for the
/// "where is this type defined" lookup and for diagnostic-message
/// rendering.
///
/// For `Type::Con { name, .. }` (the only legal head shape for a
/// non-orphan instance) returns `name`. Other variants (`Var`,
/// `Forall`, `Fn`) are not legal as instance heads — Decision 11
/// requires a concrete type expression at the instance head — so we
/// emit a stable fallback string. The fallback prevents diagnostic
/// rendering from panicking on a malformed fixture; the "real"
/// rejection of non-concrete instance heads will arrive as a
/// schema-validation diagnostic in 22b.2.
fn type_head_name(t: &Type) -> String {
match t {
Type::Con { name, .. } => name.clone(),
Type::Var { name } => format!("<var:{name}>"),
Type::Forall { .. } => "<forall>".into(),
Type::Fn { .. } => "<fn>".into(),
}
}
fn visit(
module: Module,
root_dir: &Path,
modules: &mut BTreeMap<String, Module>,
visiting: &mut Vec<String>,
visiting_set: &mut HashSet<String>,
) -> Result<(), WorkspaceLoadError> {
let name = module.name.clone();
// Already fully loaded? Then do nothing. Hash consistency is checked
// on re-encounter via imports (see below in the loop).
if modules.contains_key(&name) {
return Ok(());
}
// Cycle: same name currently on the DFS stack.
if visiting_set.contains(&name) {
let mut path = visiting.clone();
path.push(name);
return Err(WorkspaceLoadError::Cycle { path });
}
visiting.push(name.clone());
visiting_set.insert(name.clone());
// Process imports recursively.
let imports = module.imports.clone();
for imp in &imports {
let imp_path = root_dir.join(format!("{}.ail.json", imp.module));
if let Some(existing) = modules.get(&imp.module) {
// Already fully loaded — check hash consistency, in case the
// file on disk has changed.
let on_disk = match load_one(&imp_path) {
Ok(m) => m,
Err(WorkspaceLoadError::Io { .. }) => continue,
Err(e) => return Err(e),
};
if module_hash(existing) != module_hash(&on_disk) {
return Err(WorkspaceLoadError::ModuleHashMismatch {
name: imp.module.clone(),
});
}
continue;
}
if visiting_set.contains(&imp.module) {
let mut path = visiting.clone();
path.push(imp.module.clone());
return Err(WorkspaceLoadError::Cycle { path });
}
if !imp_path.exists() {
return Err(WorkspaceLoadError::ModuleNotFound {
name: imp.module.clone(),
expected_path: imp_path,
});
}
let imported = load_one(&imp_path)?;
if imported.name != imp.module {
return Err(WorkspaceLoadError::ModuleNameMismatch {
name_in_file: imported.name,
name_from_path: imp.module.clone(),
});
}
visit(imported, root_dir, modules, visiting, visiting_set)?;
}
visiting.pop();
visiting_set.remove(&name);
modules.insert(name, module);
Ok(())
}
fn load_one(path: &Path) -> Result<Module, WorkspaceLoadError> {
match load_module(path) {
Ok(m) => Ok(m),
Err(CoreError::Io(e)) => Err(WorkspaceLoadError::Io {
path: path.to_path_buf(),
source: e,
}),
Err(e) => Err(WorkspaceLoadError::Schema {
path: path.to_path_buf(),
source: e,
}),
}
}
fn module_name_from_path(p: &Path) -> String {
let file = p.file_name().and_then(|s| s.to_str()).unwrap_or("");
// Convention: `<name>.ail.json`.
if let Some(stripped) = file.strip_suffix(".ail.json") {
return stripped.to_string();
}
// Fallback: strip only the last extension.
Path::new(file)
.file_stem()
.and_then(|s| s.to_str())
.unwrap_or(file)
.to_string()
}
#[cfg(test)]
mod tests {
use super::*;
use std::fs;
fn write_module(dir: &Path, name: &str, imports: &[&str]) -> PathBuf {
let imports_json: Vec<serde_json::Value> = imports
.iter()
.map(|m| serde_json::json!({ "module": m }))
.collect();
let module = serde_json::json!({
"schema": crate::SCHEMA,
"name": name,
"imports": imports_json,
"defs": [],
});
let path = dir.join(format!("{name}.ail.json"));
fs::write(&path, serde_json::to_vec_pretty(&module).unwrap()).unwrap();
path
}
fn tmp_dir(tag: &str) -> PathBuf {
let d = std::env::temp_dir().join(format!(
"ailang_workspace_test_{tag}_{}",
std::process::id()
));
let _ = fs::remove_dir_all(&d);
fs::create_dir_all(&d).unwrap();
d
}
#[test]
fn loads_example_workspace_happy_path() {
// Uses the canonical example files under `examples/`. This
// test documents that the loader relies on the committed
// workspace example.
let manifest_dir = env!("CARGO_MANIFEST_DIR");
let workspace_root =
Path::new(manifest_dir).parent().unwrap().parent().unwrap();
let entry = workspace_root.join("examples").join("ws_main.ail.json");
let ws = load_workspace(&entry).expect("load workspace");
assert_eq!(ws.entry, "ws_main");
assert!(ws.modules.contains_key("ws_main"));
assert!(ws.modules.contains_key("ws_lib"));
// Iter 23.1: the loader auto-injects the `prelude` module,
// so the count is the user's two modules plus prelude.
assert_eq!(ws.modules.len(), 3);
}
#[test]
fn loads_workspace_auto_injects_prelude() {
// Iter 23.1: the prelude module is implicitly part of every
// workspace, regardless of whether the user's modules import
// it. Loading any well-formed workspace must result in
// `ws.modules["prelude"]` being present with the Ordering
// type def.
let manifest_dir = env!("CARGO_MANIFEST_DIR");
let workspace_root =
Path::new(manifest_dir).parent().unwrap().parent().unwrap();
let entry = workspace_root.join("examples").join("ws_main.ail.json");
let ws = load_workspace(&entry).expect("load workspace");
assert!(
ws.modules.contains_key("prelude"),
"prelude module must be auto-injected; modules present: {:?}",
ws.modules.keys().collect::<Vec<_>>()
);
let prelude = &ws.modules["prelude"];
assert_eq!(prelude.name, "prelude");
assert!(
prelude.defs.iter().any(|d| matches!(
d,
crate::ast::Def::Type(t) if t.name == "Ordering"
)),
"prelude must contain Ordering type def"
);
// Iter 23.2: prelude also ships the `Eq` class plus three
// primitive instances (Eq Int, Eq Bool, Eq Str).
assert!(
prelude.defs.iter().any(|d| matches!(
d,
crate::ast::Def::Class(c) if c.name == "Eq"
)),
"prelude must contain Eq class def"
);
let eq_instance_types: Vec<&str> = prelude
.defs
.iter()
.filter_map(|d| match d {
crate::ast::Def::Instance(i) if i.class == "Eq" => {
if let crate::ast::Type::Con { name, .. } = &i.type_ {
Some(name.as_str())
} else {
None
}
}
_ => None,
})
.collect();
assert!(
eq_instance_types.contains(&"Int"),
"prelude must contain `instance Eq Int`; saw Eq instances on: {eq_instance_types:?}"
);
assert!(
eq_instance_types.contains(&"Bool"),
"prelude must contain `instance Eq Bool`; saw Eq instances on: {eq_instance_types:?}"
);
assert!(
eq_instance_types.contains(&"Str"),
"prelude must contain `instance Eq Str`; saw Eq instances on: {eq_instance_types:?}"
);
// Iter 23.3: prelude also ships the `Ord` class plus three
// primitive instances (Ord Int, Ord Bool, Ord Str). Ord
// extends Eq (Decision 11 single-superclass closure), so its
// shape is the same as Eq's instance set; the loader uses the
// superclass walk to verify the Eq instances exist.
assert!(
prelude.defs.iter().any(|d| matches!(
d,
crate::ast::Def::Class(c) if c.name == "Ord"
)),
"prelude must contain Ord class def"
);
let ord_instance_types: Vec<&str> = prelude
.defs
.iter()
.filter_map(|d| match d {
crate::ast::Def::Instance(i) if i.class == "Ord" => {
if let crate::ast::Type::Con { name, .. } = &i.type_ {
Some(name.as_str())
} else {
None
}
}
_ => None,
})
.collect();
assert!(
ord_instance_types.contains(&"Int"),
"prelude must contain `instance Ord Int`; saw: {ord_instance_types:?}"
);
assert!(
ord_instance_types.contains(&"Bool"),
"prelude must contain `instance Ord Bool`; saw: {ord_instance_types:?}"
);
assert!(
ord_instance_types.contains(&"Str"),
"prelude must contain `instance Ord Str`; saw: {ord_instance_types:?}"
);
}
#[test]
fn user_module_named_prelude_is_rejected() {
// Iter 23.1: the loader auto-injects a module named "prelude",
// so a user module that also claims that name would collide
// silently. The collision is caught explicitly with
// `ReservedModuleName`.
let dir = tmp_dir("prelude_collision");
write_module(&dir, "prelude", &[]);
let entry = dir.join("prelude.ail.json");
let err = load_workspace(&entry).expect_err("must reject user prelude");
match err {
WorkspaceLoadError::ReservedModuleName { name } => {
assert_eq!(name, "prelude");
}
other => panic!(
"expected ReservedModuleName, got: {other:?}"
),
}
}
#[test]
fn detects_import_cycle() {
let dir = tmp_dir("cycle");
write_module(&dir, "a", &["b"]);
write_module(&dir, "b", &["a"]);
let entry = dir.join("a.ail.json");
let err = load_workspace(&entry).expect_err("must error on cycle");
match err {
WorkspaceLoadError::Cycle { path } => {
assert!(path.contains(&"a".to_string()));
assert!(path.contains(&"b".to_string()));
}
other => panic!("expected Cycle, got {other:?}"),
}
}
#[test]
fn module_not_found_yields_structured_error() {
let dir = tmp_dir("notfound");
write_module(&dir, "main", &["does_not_exist"]);
let entry = dir.join("main.ail.json");
let err = load_workspace(&entry).expect_err("must error on missing module");
match err {
WorkspaceLoadError::ModuleNotFound { name, expected_path } => {
assert_eq!(name, "does_not_exist");
assert!(expected_path.ends_with("does_not_exist.ail.json"));
}
other => panic!("expected ModuleNotFound, got {other:?}"),
}
}
/// Iter 22b.1: a workspace whose own modules contain no
/// `Def::Instance` defs produces no non-prelude registry entries.
/// This is the happy-path baseline for the registry-build pass —
/// every pre-22b workspace falls into this case. With the
/// auto-loaded prelude (iter 23.2) the registry is no longer
/// strictly empty, so the invariant is now "no entries whose
/// `defining_module` is anything other than `prelude`".
#[test]
fn iter22b1_workspace_with_no_classes_has_empty_registry() {
let manifest_dir = env!("CARGO_MANIFEST_DIR");
let workspace_root =
Path::new(manifest_dir).parent().unwrap().parent().unwrap();
let entry = workspace_root.join("examples").join("sum.ail.json");
let ws = load_workspace(&entry).expect("sum.ail.json loads");
assert!(
ws.registry.entries.values().all(|e| e.defining_module == "prelude"),
"pre-22b fixture has no class/instance defs of its own; \
all registry entries must come from the auto-injected prelude. \
got non-prelude entries: {:?}",
ws.registry.entries.values()
.filter(|e| e.defining_module != "prelude")
.map(|e| &e.defining_module)
.collect::<Vec<_>>()
);
}
fn examples_dir() -> PathBuf {
let manifest_dir = env!("CARGO_MANIFEST_DIR");
Path::new(manifest_dir)
.parent()
.unwrap()
.parent()
.unwrap()
.join("examples")
}
/// Iter 22b.1: a coherent instance (in the class's module)
/// loads cleanly and produces one registry entry from the
/// fixture itself. With the auto-loaded prelude (iter 23.2)
/// the registry also contains the prelude's own entries; the
/// invariant is filtered to fixture-only entries.
#[test]
fn iter22b1_instance_in_class_module_loads_clean() {
let entry = examples_dir().join("test_22b1_orphan_class.ail.json");
let ws = load_workspace(&entry).expect("coherent instance loads");
let fixture_entries: Vec<_> = ws.registry.entries.iter()
.filter(|(_, e)| e.defining_module != "prelude")
.collect();
assert_eq!(fixture_entries.len(), 1);
let (key, entry) = fixture_entries[0];
assert_eq!(&key.0, "Show");
assert_eq!(entry.defining_module, "test_22b1_orphan_class");
assert_eq!(entry.instance.class, "Show");
}
/// Iter 22b.1: an instance declared in a module that is neither
/// the class's module nor the type's module fires `OrphanInstance`.
/// The fixture imports `test_22b1_orphan_third_classmod` (which
/// owns `class Show`) and the entry module declares `instance
/// Show Int` itself — but the entry is not the class's module
/// and `Int` is primitive, so neither leg of coherence is
/// satisfied.
#[test]
fn iter22b1_orphan_instance_fires_diagnostic() {
let entry = examples_dir().join("test_22b1_orphan_third.ail.json");
let err = load_workspace(&entry).expect_err("must fire orphan");
match err {
WorkspaceLoadError::OrphanInstance {
class,
type_repr,
defining_module,
..
} => {
assert_eq!(class, "Show");
assert_eq!(type_repr, "Int");
assert_eq!(defining_module, "test_22b1_orphan_third");
}
other => panic!("expected OrphanInstance, got {other:?}"),
}
}
/// Iter 22b.1: two instances of the same `(class, type)` pair
/// declared from coherent positions (one in the class's module,
/// one in the type's module) collide on the registry's
/// uniqueness check. Setup per the JOURNAL hint:
/// - module A defines `class Show` and declares
/// `instance Show MyInt` (legal, A is class's module).
/// - module B defines `type MyInt` and declares
/// `instance Show MyInt` (legal, B is type's module).
/// - entry module imports both A and B.
/// The build_registry pass sees both instances under the same
/// `(Show, hash-of-MyInt)` key and fires `DuplicateInstance`.
#[test]
fn iter22b1_duplicate_instance_fires_diagnostic() {
let entry = examples_dir().join("test_22b1_dup_entry.ail.json");
let err = load_workspace(&entry).expect_err("must fire duplicate");
match err {
WorkspaceLoadError::DuplicateInstance {
class,
type_repr,
first_module,
second_module,
} => {
assert_eq!(class, "Show");
assert_eq!(type_repr, "MyInt");
assert_ne!(first_module, second_module);
let modules: BTreeSet<&str> =
[first_module.as_str(), second_module.as_str()].iter().copied().collect();
assert!(modules.contains("test_22b1_dup_a"));
assert!(modules.contains("test_22b1_dup_b"));
}
other => panic!("expected DuplicateInstance, got {other:?}"),
}
}
/// Iter 22b.1: an instance that omits a required (non-default)
/// method of its class fires `MissingMethod`. The fixture's
/// `class TEq` declares `teq` and `ne` as both non-default; the
/// instance only specifies `ne`, leaving `teq` missing.
/// (Class is `TEq` rather than `Eq` to avoid colliding with the
/// auto-loaded prelude's `class Eq`.)
#[test]
fn iter22b1_missing_method_fires_diagnostic() {
let entry = examples_dir().join("test_22b1_missing_method.ail.json");
let err = load_workspace(&entry).expect_err("must fire missing-method");
match err {
WorkspaceLoadError::MissingMethod {
class,
type_repr,
method,
} => {
assert_eq!(class, "TEq");
assert_eq!(type_repr, "Int");
assert_eq!(method, "teq");
}
other => panic!("expected MissingMethod, got {other:?}"),
}
}
/// ct.1: a class whose parameter `f` appears as a `Type::Con`
/// name (the malformed-but-historically-test-fixture shape used
/// to trigger `KindMismatch` pre-ct.1) is now caught earlier by
/// the canonical-type-names validator: `f` is bare,
/// non-primitive, and not a TypeDef in the owning module, so
/// `BareCrossModuleTypeRef` fires before `validate_classdefs`
/// gets a chance to run. The `KindMismatch` path stays in the
/// codebase as dead-but-defensive code; a future tidy may
/// retire it.
#[test]
fn class_param_in_applied_position_fires_canonical_form_rejection() {
let entry = std::path::PathBuf::from(
"../../examples/test_22b2_kind_mismatch.ail.json",
);
let err = load_workspace(&entry)
.expect_err("must fire canonical-form rejection");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { module, name, .. } => {
assert_eq!(module, "test_22b2_kind_mismatch");
assert_eq!(name, "f");
}
other => panic!(
"expected BareCrossModuleTypeRef (validator now fires first), got {other:?}",
),
}
}
/// Iter 22b.2: a class whose `superclass.type` differs from its
/// own `param` (e.g. `class Ord a extends Eq b`) must fire
/// `InvalidSuperclassParam`. Decision 11 axis 1 ("single
/// superclass, applied to the same param") makes the only legal
/// shape `extends Eq a` when the parent class has `param: "a"`.
#[test]
fn superclass_with_wrong_param_fires_invalid_superclass_param() {
let entry = std::path::PathBuf::from(
"../../examples/test_22b2_invalid_superclass_param.ail.json",
);
let err = load_workspace(&entry)
.expect_err("must fire invalid-superclass-param");
match err {
WorkspaceLoadError::InvalidSuperclassParam {
class, superclass, expected_param, got_type,
} => {
assert_eq!(class, "Ord");
assert_eq!(superclass, "Eq");
assert_eq!(expected_param, "a");
assert_eq!(got_type, "b");
}
other => panic!("expected InvalidSuperclassParam, got {other:?}"),
}
}
/// Iter 22b.2: an instance that specifies a body for a method
/// name the class never declared must fire
/// `OverridingNonExistentMethod`. Symmetric counterpart to
/// `MissingMethod`: the latter fires when the class declares a
/// non-default method that the instance omits; this one fires
/// when the instance provides a body the class did not ask for.
/// Decision 11 forbids ad-hoc additions to a class's method set
/// at the instance site.
/// (Class is `TEq` rather than `Eq` to avoid colliding with the
/// auto-loaded prelude's `class Eq`.)
#[test]
fn instance_overriding_nonexistent_method_fires() {
let entry = std::path::PathBuf::from(
"../../examples/test_22b2_overriding_nonexistent.ail.json",
);
let err = load_workspace(&entry)
.expect_err("must fire overriding-non-existent-method");
match err {
WorkspaceLoadError::OverridingNonExistentMethod {
class, type_repr, method,
} => {
assert_eq!(class, "TEq");
assert_eq!(type_repr, "Int");
assert_eq!(method, "ne");
}
other => panic!("expected OverridingNonExistentMethod, got {other:?}"),
}
}
/// Iter 22b.2: a class method's `Type::Forall` whose `constraints`
/// reference a type variable that is neither bound by `Forall.vars`
/// nor equal to the class's `param` must fire
/// `UnboundConstraintTypeVar`. The fixture's `class Foo a` declares
/// method `foo` with `forall a. (Bar z) => a -> Unit`; `z` is
/// bound nowhere, so the constraint is unsatisfiable by
/// construction.
#[test]
fn constraint_with_unbound_var_fires_unbound_constraint_type_var() {
let entry = std::path::PathBuf::from(
"../../examples/test_22b2_unbound_constraint_var.ail.json",
);
let err = load_workspace(&entry)
.expect_err("must fire constraint-references-unbound-type-var");
match err {
WorkspaceLoadError::UnboundConstraintTypeVar {
class, method, var, ..
} => {
assert_eq!(class, "Foo");
assert_eq!(method, "foo");
assert_eq!(var, "z");
}
other => panic!("expected UnboundConstraintTypeVar, got {other:?}"),
}
}
/// Iter 22b.2: two classes that declare a method with the same
/// name must fire `MethodNameCollision` with `kind == "class-class"`.
/// Decision 11 keeps method names workspace-unique so that bare
/// method-name resolution (`foo x` rather than `A.foo x`) is
/// unambiguous; if two classes both export `foo`, the registry has
/// no way to choose between them at a use site.
#[test]
fn class_class_method_name_collision_fires() {
let entry = examples_dir()
.join("test_22b2_method_name_collision_class_class.ail.json");
let err = load_workspace(&entry)
.expect_err("must fire method-name-collision");
match err {
WorkspaceLoadError::MethodNameCollision {
method,
kind,
first_origin,
second_origin,
} => {
assert_eq!(method, "foo");
assert_eq!(kind, "class-class");
assert!(
first_origin.starts_with("class A"),
"first_origin = {first_origin:?}",
);
assert!(
second_origin.starts_with("class B"),
"second_origin = {second_origin:?}",
);
}
other => panic!("expected MethodNameCollision, got {other:?}"),
}
}
/// Iter 22b.2: a class-method name that collides with a top-level
/// `fn` of the same name must fire `MethodNameCollision` with
/// `kind == "class-fn"`. Same rationale as the class-class case:
/// bare-name resolution must be unambiguous, and a class method
/// shadowing (or being shadowed by) a free function silently is
/// the worst possible failure mode.
#[test]
fn class_fn_method_name_collision_fires() {
let entry = examples_dir()
.join("test_22b2_method_name_collision_class_fn.ail.json");
let err = load_workspace(&entry)
.expect_err("must fire method-name-collision");
match err {
WorkspaceLoadError::MethodNameCollision {
method,
kind,
first_origin,
second_origin,
} => {
assert_eq!(method, "greet");
assert_eq!(kind, "class-fn");
assert!(
first_origin.starts_with("class Greet"),
"first_origin = {first_origin:?}",
);
assert!(
second_origin.starts_with("fn greet"),
"second_origin = {second_origin:?}",
);
}
other => panic!("expected MethodNameCollision, got {other:?}"),
}
}
/// Iter 22b.2: an instance `C T` whose class `C` declares a
/// superclass `S` requires that `instance S T` also exist in the
/// workspace. The fixture declares `class TEq a`, `class TOrd a
/// extends TEq a`, and `instance TOrd Int` — but no `instance TEq
/// Int` — so registry build must fire
/// `MissingSuperclassInstance`. Decision 11 single-superclass
/// model requires `instance S T` whenever `instance C T` exists.
/// (Classes are `TEq` / `TOrd` rather than `Eq` / `Ord` to avoid
/// colliding with the auto-loaded prelude's `class Eq`.)
#[test]
fn instance_without_superclass_instance_fires() {
let entry = examples_dir().join("test_22b2_missing_superclass_instance.ail.json");
let err = load_workspace(&entry)
.expect_err("must fire missing-superclass-instance");
match err {
WorkspaceLoadError::MissingSuperclassInstance {
class, superclass, type_repr,
} => {
assert_eq!(class, "TOrd");
assert_eq!(superclass, "TEq");
assert_eq!(type_repr, "Int");
}
other => panic!("expected MissingSuperclassInstance, got {other:?}"),
}
}
fn module_with_type_def(name: &str, type_name: &str) -> Module {
serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": name,
"imports": [],
"defs": [
{ "kind": "type", "name": type_name, "ctors": [] }
],
})).unwrap()
}
fn single_module_with_type_con(name: &str, type_con: &str) -> BTreeMap<String, Module> {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": name,
"imports": [],
"defs": [{
"kind": "fn",
"name": "f",
"type": { "k": "fn", "params": [], "ret": { "k": "con", "name": type_con }, "effects": [] },
"params": [],
"body": { "t": "lit", "lit": { "kind": "unit" } }
}],
})).unwrap();
let mut map = BTreeMap::new();
map.insert(name.to_string(), m);
map
}
fn single_module_with_local_type_and_ref(name: &str, type_name: &str) -> BTreeMap<String, Module> {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": name,
"imports": [],
"defs": [
{ "kind": "type", "name": type_name, "ctors": [] },
{ "kind": "fn", "name": "f",
"type": { "k": "fn", "params": [], "ret": { "k": "con", "name": type_name }, "effects": [] },
"params": [],
"body": { "t": "lit", "lit": { "kind": "unit" } } }
],
})).unwrap();
let mut map = BTreeMap::new();
map.insert(name.to_string(), m);
map
}
fn module_with_import_and_type_con(name: &str, import: &str, type_con: &str) -> Module {
serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": name,
"imports": [{ "module": import }],
"defs": [{
"kind": "fn",
"name": "f",
"type": { "k": "fn", "params": [], "ret": { "k": "con", "name": type_con }, "effects": [] },
"params": [],
"body": { "t": "lit", "lit": { "kind": "unit" } }
}],
})).unwrap()
}
/// ct.1: a `Type::Con` whose `name` is a primitive (`Int` / `Bool` /
/// `Str` / `Unit` / `Float`) must be accepted bare. The five
/// primitive names are the only legal bare-non-local Type::Con names
/// under the canonical-form rule.
#[test]
fn ct1_validator_accepts_primitive_type_cons() {
let modules = single_module_with_type_con("m", "Int");
validate_canonical_type_names(&modules).expect("Int must be accepted");
let modules = single_module_with_type_con("m", "Float");
validate_canonical_type_names(&modules).expect("Float must be accepted");
}
/// ct.1: a bare Type::Con whose `name` matches a local TypeDef in
/// the same module must be accepted (the canonical-form rule: bare =
/// local).
#[test]
fn ct1_validator_accepts_bare_local_type_con() {
let modules = single_module_with_local_type_and_ref("m", "Foo");
validate_canonical_type_names(&modules)
.expect("local Foo must be accepted");
}
/// ct.1: a bare Type::Con whose `name` is neither a primitive nor a
/// local TypeDef must fire `BareCrossModuleTypeRef`. With no imports,
/// the candidates list is empty.
#[test]
fn ct1_validator_rejects_bare_xmod_no_imports() {
let modules = single_module_with_type_con("m", "Ordering");
let err = validate_canonical_type_names(&modules)
.expect_err("Ordering must be rejected");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { module, name, candidates } => {
assert_eq!(module, "m");
assert_eq!(name, "Ordering");
assert!(candidates.is_empty(),
"no imports => no candidates; got {candidates:?}");
}
other => panic!("expected BareCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: a bare Type::Con whose `name` resolves to one imported
/// module's TypeDef must fire `BareCrossModuleTypeRef` with that
/// qualified form in `candidates` (so the diagnostic can suggest the
/// fix).
#[test]
fn ct1_validator_rejects_bare_xmod_with_import_candidate() {
let mut modules = BTreeMap::new();
modules.insert("other".to_string(), module_with_type_def("other", "Ordering"));
modules.insert("m".to_string(), module_with_import_and_type_con("m", "other", "Ordering"));
let err = validate_canonical_type_names(&modules)
.expect_err("Ordering must be rejected with candidate");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { name, candidates, .. } => {
assert_eq!(name, "Ordering");
assert_eq!(candidates, vec!["other.Ordering".to_string()]);
}
other => panic!("expected BareCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: a qualified Type::Con `<owner>.<type>` where `<owner>` is a
/// known module AND `<type>` is one of its TypeDefs must be accepted.
#[test]
fn ct1_validator_accepts_qualified_xmod_ref() {
let mut modules = BTreeMap::new();
modules.insert("other".to_string(), module_with_type_def("other", "Ordering"));
modules.insert("m".to_string(), module_with_import_and_type_con("m", "other", "other.Ordering"));
validate_canonical_type_names(&modules)
.expect("other.Ordering must be accepted");
}
/// ct.1: a qualified Type::Con `<owner>.<type>` where `<owner>` is
/// NOT a known module must fire `BadCrossModuleTypeRef`. Symmetric
/// case: `<owner>` known but no TypeDef `<type>` in it.
#[test]
fn ct1_validator_rejects_bad_qualified_ref() {
let modules = single_module_with_type_con("m", "Mystery.Type");
let err = validate_canonical_type_names(&modules)
.expect_err("Mystery.Type must be rejected");
match err {
WorkspaceLoadError::BadCrossModuleTypeRef { module, name } => {
assert_eq!(module, "m");
assert_eq!(name, "Mystery.Type");
}
other => panic!("expected BadCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: a Type::Con embedded inside a `Term::Lam.param_tys` is a
/// Type-position occurrence, just inside a Term tree. The validator
/// must walk into Lam-internal types so an LLM author can't smuggle
/// a bare cross-module ref past it by hiding it in a lambda
/// annotation.
#[test]
fn ct1_validator_walks_lam_embedded_types() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "fn",
"name": "f",
"type": { "k": "fn", "params": [], "ret": { "k": "con", "name": "Unit" }, "effects": [] },
"params": [],
"body": {
"t": "lam",
"params": ["x"],
"paramTypes": [{ "k": "con", "name": "Ordering" }],
"retType": { "k": "con", "name": "Unit" },
"effects": [],
"body": { "t": "lit", "lit": { "kind": "unit" } }
}
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("Lam-embedded Ordering must be rejected");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { name, .. } => {
assert_eq!(name, "Ordering");
}
other => panic!("expected BareCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: a `Term::Ctor` whose `type_name` is a bare cross-module ref
/// must fire `BareCrossModuleTypeRef`. Symmetric to the Type::Con
/// rule but the field lives on Term, not Type.
#[test]
fn ct1_validator_rejects_bare_term_ctor_type_name() {
let mut modules = BTreeMap::new();
modules.insert("prelude".to_string(),
module_with_type_def("prelude", "Ordering"));
// Module `m` has no imports, no local Ordering, but a Term::Ctor
// referencing bare `Ordering`.
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "fn",
"name": "f",
"type": { "k": "fn", "params": [], "ret": { "k": "con", "name": "Unit" }, "effects": [] },
"params": [],
"body": {
"t": "ctor",
"type": "Ordering",
"ctor": "LT",
"args": []
}
}],
})).unwrap();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("bare Term::Ctor type must be rejected");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { module, name, candidates } => {
assert_eq!(module, "m");
assert_eq!(name, "Ordering");
assert_eq!(candidates, vec!["prelude.Ordering".to_string()],
"prelude is implicit-fallback");
}
other => panic!("expected BareCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: a qualified `ClassDef.name` (e.g. `other.Eq`) must fire
/// `QualifiedClassName`. Class names stay bare in this milestone.
#[test]
fn ct1_validator_rejects_qualified_classdef_name() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "class",
"name": "other.MyEq",
"param": "a",
"methods": []
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("qualified ClassDef.name must be rejected");
match err {
WorkspaceLoadError::QualifiedClassName { module, name, field } => {
assert_eq!(module, "m");
assert_eq!(name, "other.MyEq");
assert_eq!(field, "ClassDef.name");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
/// ct.1: a qualified `InstanceDef.class` must fire
/// `QualifiedClassName`.
#[test]
fn ct1_validator_rejects_qualified_instancedef_class() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "instance",
"class": "other.MyEq",
"type": { "k": "con", "name": "Int" },
"methods": []
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("qualified InstanceDef.class must be rejected");
match err {
WorkspaceLoadError::QualifiedClassName { name, field, .. } => {
assert_eq!(name, "other.MyEq");
assert_eq!(field, "InstanceDef.class");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
/// ct.1: a qualified `SuperclassRef.class` must fire
/// `QualifiedClassName`.
#[test]
fn ct1_validator_rejects_qualified_superclassref_class() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "class",
"name": "MyOrd",
"param": "a",
"superclass": { "class": "other.MyEq", "type": "a" },
"methods": []
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("qualified SuperclassRef.class must be rejected");
match err {
WorkspaceLoadError::QualifiedClassName { name, field, .. } => {
assert_eq!(name, "other.MyEq");
assert_eq!(field, "SuperclassRef.class");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
/// ct.1: a qualified `Constraint.class` (inside a `Type::Forall`)
/// must fire `QualifiedClassName`.
#[test]
fn ct1_validator_rejects_qualified_constraint_class() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "fn",
"name": "f",
"type": {
"k": "forall",
"vars": ["a"],
"constraints": [
{ "class": "other.MyEq", "type": { "k": "var", "name": "a" } }
],
"body": {
"k": "fn", "params": [{ "k": "var", "name": "a" }],
"ret": { "k": "con", "name": "Unit" }, "effects": []
}
},
"params": ["x"],
"body": { "t": "lit", "lit": { "kind": "unit" } }
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("qualified Constraint.class must be rejected");
match err {
WorkspaceLoadError::QualifiedClassName { name, field, .. } => {
assert_eq!(name, "other.MyEq");
assert_eq!(field, "Constraint.class");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
/// ct.1.5a: registry-side duplicate detection survives the
/// asymmetric canonical-form representation. Two coherent instances
/// on the same type-def, one declared bare-local (in the type's
/// defining module) and one declared qualified-cross-module (in the
/// class's defining module), must collide on the registry's
/// `(class, type-hash)` key.
///
/// This is the regression that broke during the ct.1.5 migration
/// dry-run: after migrating `test_22b1_dup_a.ail.json` to qualified
/// `test_22b1_dup_b.MyInt`, the unmigrated `test_22b1_dup_b.ail.json`
/// (which keeps bare `MyInt` because the type IS local there)
/// produced a different type-hash, and the duplicate detection
/// silently missed.
///
/// The fixture is constructed in-memory rather than from disk so
/// the test stays focused on the registry behaviour rather than the
/// migration tool. Class `TShow` is named distinctly from the
/// prelude's `Eq`/`Show` to avoid collisions with the auto-loaded
/// prelude — but `build_registry` here is called directly on a flat
/// `BTreeMap` (no auto-prelude injection), so the choice is purely
/// belt-and-braces.
#[test]
fn ct1_registry_duplicate_detection_survives_mixed_canonical_form() {
// Module `cls`: declares `class TShow a` (custom name to avoid
// any future prelude collision) and the qualified-cross-module
// instance `instance TShow other.MyInt`.
let cls: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "cls",
"imports": [{ "module": "other" }],
"defs": [
{
"kind": "class",
"name": "TShow",
"param": "a",
"methods": [
{ "name": "tshow",
"type": { "k": "fn",
"params": [{ "k": "var", "name": "a" }],
"ret": { "k": "con", "name": "Str" },
"effects": [] } }
]
},
{
"kind": "instance",
"class": "TShow",
"type": { "k": "con", "name": "other.MyInt" },
"methods": [
{ "name": "tshow",
"body": { "t": "lit", "lit": { "kind": "str", "value": "cls-side" } } }
]
}
],
})).unwrap();
// Module `other`: declares `type MyInt` and the bare-local
// instance `instance TShow MyInt`. Imports `cls` for shape
// coherence (the dependency direction needed to bring `class
// TShow` into scope under the actual loader).
let other: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "other",
"imports": [{ "module": "cls" }],
"defs": [
{ "kind": "type", "name": "MyInt", "ctors": [{ "name": "MkMyInt", "fields": [] }] },
{
"kind": "instance",
"class": "TShow",
"type": { "k": "con", "name": "MyInt" },
"methods": [
{ "name": "tshow",
"body": { "t": "lit", "lit": { "kind": "str", "value": "other-side" } } }
]
}
],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("cls".to_string(), cls);
modules.insert("other".to_string(), other);
let err = build_registry(&modules).expect_err(
"registry build must fire DuplicateInstance for mixed canonical-form"
);
match err {
WorkspaceLoadError::DuplicateInstance {
class, first_module, second_module, ..
} => {
assert_eq!(class, "TShow");
let mods: BTreeSet<&str> =
[first_module.as_str(), second_module.as_str()].into_iter().collect();
assert!(mods.contains("cls"),
"got {first_module}, {second_module}");
assert!(mods.contains("other"),
"got {first_module}, {second_module}");
}
other => panic!("expected DuplicateInstance, got {other:?}"),
}
}
/// ct.1.5a follow-up: `normalize_type_for_registry` must recurse into
/// `Type::Forall.constraints[].type_` just like it does into
/// `Type::Forall.body`. A bare `Type::Con` nested inside a Forall
/// constraint that lives in a different module must be rewritten to
/// its qualified form, otherwise the registry key for a constrained
/// polymorphic type would disagree between bare-local and
/// qualified-cross-module call sites — the same divergence
/// `ct1_registry_duplicate_detection_survives_mixed_canonical_form`
/// guards against at the outer level.
#[test]
fn ct1_5a_normalize_recurses_into_forall_constraints() {
let mut type_def_module: BTreeMap<String, String> = BTreeMap::new();
type_def_module.insert("MyInt".to_string(), "other".to_string());
// Forall a. (TShow MyInt) => a -> a
// The constraint's type carries a bare `MyInt` that should be
// rewritten to `other.MyInt`.
let input = Type::Forall {
vars: vec!["a".to_string()],
constraints: vec![crate::ast::Constraint {
class: "TShow".to_string(),
type_: Type::Con {
name: "MyInt".to_string(),
args: vec![],
},
}],
body: Box::new(Type::Fn {
params: vec![Type::Var { name: "a".to_string() }],
param_modes: vec![],
ret: Box::new(Type::Var { name: "a".to_string() }),
ret_mode: Default::default(),
effects: vec![],
}),
};
let out = normalize_type_for_registry(&input, &type_def_module);
match out {
Type::Forall { constraints, .. } => {
assert_eq!(constraints.len(), 1);
match &constraints[0].type_ {
Type::Con { name, .. } => {
assert_eq!(
name, "other.MyInt",
"constraint type was not normalised; got {name}"
);
}
other => panic!("expected Type::Con, got {other:?}"),
}
}
other => panic!("expected Type::Forall, got {other:?}"),
}
}
/// ct.1: a qualified `Constraint.class` nested inside a
/// `ClassDef.methods[].ty.Forall.constraints` must fire
/// `QualifiedClassName`. Distinct from the `Def::Fn` site: the
/// `Def::Class` branch of `check_class_name_fields` has its own
/// per-method Forall walk that needs independent coverage.
#[test]
fn ct1_validator_rejects_qualified_constraint_class_in_classdef_method() {
let m: Module = serde_json::from_value(serde_json::json!({
"schema": crate::SCHEMA,
"name": "m",
"imports": [],
"defs": [{
"kind": "class",
"name": "Foo",
"param": "a",
"methods": [{
"name": "m",
"type": {
"k": "forall",
"vars": ["b"],
"constraints": [
{ "class": "other.MyEq", "type": { "k": "var", "name": "b" } }
],
"body": {
"k": "fn",
"params": [{ "k": "var", "name": "b" }],
"ret": { "k": "con", "name": "Unit" },
"effects": []
}
}
}]
}],
})).unwrap();
let mut modules = BTreeMap::new();
modules.insert("m".to_string(), m);
let err = validate_canonical_type_names(&modules)
.expect_err("qualified Constraint.class in ClassDef-method Forall must be rejected");
match err {
WorkspaceLoadError::QualifiedClassName { name, field, .. } => {
assert_eq!(name, "other.MyEq");
assert_eq!(field, "Constraint.class");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
/// ct.1: on-disk fixture for `BareCrossModuleTypeRef`. Bare
/// `Ordering` Term::Ctor with no imports; the validator catches it
/// after prelude injection (so the candidate list contains
/// `prelude.Ordering`).
#[test]
fn ct1_fixture_bare_xmod_rejected() {
let entry = examples_dir().join("test_ct1_bare_xmod_rejected.ail.json");
let err = load_workspace(&entry).expect_err("must reject bare Ordering");
match err {
WorkspaceLoadError::BareCrossModuleTypeRef { module, name, candidates } => {
assert_eq!(module, "test_ct1_bare_xmod_rejected");
assert_eq!(name, "Ordering");
assert_eq!(candidates, vec!["prelude.Ordering".to_string()]);
}
other => panic!("expected BareCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: on-disk fixture for `BadCrossModuleTypeRef`. Qualified
/// `Mystery.Type` with `Mystery` not a known module.
#[test]
fn ct1_fixture_bad_qualifier() {
let entry = examples_dir().join("test_ct1_bad_qualifier.ail.json");
let err = load_workspace(&entry).expect_err("must reject Mystery.Type");
match err {
WorkspaceLoadError::BadCrossModuleTypeRef { module, name } => {
assert_eq!(module, "test_ct1_bad_qualifier");
assert_eq!(name, "Mystery.Type");
}
other => panic!("expected BadCrossModuleTypeRef, got {other:?}"),
}
}
/// ct.1: on-disk fixture for `QualifiedClassName`. Qualified
/// `prelude.Eq` in an `InstanceDef.class` field — the schema
/// rejects this so half-migrated files cannot silently load.
#[test]
fn ct1_fixture_qualified_class_rejected() {
let entry = examples_dir().join("test_ct1_qualified_class_rejected.ail.json");
let err = load_workspace(&entry).expect_err("must reject prelude.Eq");
match err {
WorkspaceLoadError::QualifiedClassName { module, name, field } => {
assert_eq!(module, "test_ct1_qualified_class_rejected");
assert_eq!(name, "prelude.Eq");
assert_eq!(field, "InstanceDef.class");
}
other => panic!("expected QualifiedClassName, got {other:?}"),
}
}
}