AILang/crates/ailang-core/src/lib.rs

//! Foundation crate of the AILang toolchain.
//!
//! `core` owns the data model that every other crate consumes:
//!
//! - **AST** — see [`ast`]. The source of an AILang translation unit is an
//!   [`ast::Module`] expressed as JSON; the types here mirror that schema
//!   one-to-one via serde.
//! - **Canonical JSON** — see [`canonical`]. A deterministic byte form
//!   (no whitespace, lexicographically sorted object keys) used as the
//!   pre-image for hashing.
//! - **Content-addressed hashes** — see [`hash`] and [`def_hash`]. Each
//!   definition gets a stable 16-hex-char BLAKE3 prefix derived from its
//!   canonical bytes, which is how the rest of the pipeline refers to it.
//! - **Pretty-printing** — see [`pretty`]. AST → human-readable text for
//!   diff/review. The JSON form remains the source of truth.
//! - **Workspace loading** — see [`workspace`] and [`load_workspace`].
//!   Resolves transitive imports of an entry module and returns a
//!   [`Workspace`].
//! - **AST → AST desugaring** — see [`desugar`]. Pure rewrite that runs
//!   *after* `load_module` and before the typechecker / codegen
//!   consume a module. Iter 16a flattens nested constructor patterns
//!   in `match` so downstream stages always see single-level patterns;
//!   canonical bytes / hashes are unaffected because the pass runs in
//!   memory only.
//!
//! ## Place in the pipeline
//!
//! `core` → `check` (typecheck) → `codegen` (LLVM emission) → `ail` CLI.
//! `core` has no upstream dependencies inside the workspace; everything
//! else depends on it.
//!
//! ## Central invariant
//!
//! Canonical JSON is **deterministic**: the byte output of
//! [`canonical::to_bytes`] for a given value never changes across runs,
//! versions of `serde_json`, or platforms. Hashes are
//! **content-addressed**: equal canonical bytes ⇒ equal hash. Schema
//! identifier is `ailang/v0`; a [`Module`] whose `schema` field disagrees
//! is rejected at load time. Schema extensions added in later iterations
//! (e.g. parameterised ADTs in Iter 13a) are written so that all
//! pre-existing on-disk hashes remain bit-identical — see
//! [`ast::TypeDef::vars`] and the `args` field of [`ast::Type::Con`].
//!
//! ## Entry points
//!
//! - Read a single module from disk: [`load_module`].
//! - Read an entry module plus all imports: [`load_workspace`].
//! - Hash a [`Def`]: [`def_hash`]. Hash a whole [`Module`]:
//!   [`workspace::module_hash`].
//! - Form-(A) text projection of a [`Module`]: see
//!   `ailang-surface::print` (round-trippable; the inverse of
//!   `ailang-surface::parse`).
//! - Diagnostic stringification (manifest summary, type/pattern
//!   for error messages): [`pretty::manifest`],
//!   [`pretty::type_to_string`], [`pretty::pattern_to_string`].

pub mod ast;
pub mod canonical;
pub mod desugar;
pub mod hash;
pub mod pretty;
pub mod primitives;
pub mod workspace;

pub use ast::{
    def_kind, def_name, ConstDef, Def, FnDef, Import, Literal, Module, Term, Type,
};
pub use hash::def_hash;
pub use workspace::{load_workspace, module_hash, Workspace, WorkspaceLoadError};

/// Errors raised while loading a single module file.
///
/// Workspace-level loading uses a richer enum that wraps this one; see
/// [`WorkspaceLoadError`].
#[derive(Debug, thiserror::Error)]
pub enum Error {
    /// Module file parses as JSON but its `schema` field does not match
    /// [`SCHEMA`].
    #[error("schema mismatch: expected {expected:?}, got {got:?}")]
    SchemaMismatch { expected: String, got: String },

    /// Module file failed to parse as JSON or did not match the AST
    /// schema (missing/unexpected fields).
    #[error("json: {0}")]
    Json(#[from] serde_json::Error),

    /// File could not be read.
    #[error("io: {0}")]
    Io(#[from] std::io::Error),
}

/// Result alias scoped to the crate-level [`Error`].
pub type Result<T> = std::result::Result<T, Error>;

/// Schema identifier this version of `core` accepts. Every loaded
/// [`Module`] must carry exactly this string in its `schema` field, or
/// loading fails with [`Error::SchemaMismatch`].
pub const SCHEMA: &str = "ailang/v0";

/// Iter 20f: complete LLM-targeted specification of Form-A — the
/// canonical authoring surface (Decision 6). Embedded verbatim into
/// any prompt that asks an LLM to produce or edit AILang code; in
/// particular, `ail merge-prose` includes it in the round-trip
/// prompt template. The string is the raw bytes of
/// `specs/form_a.md`, co-located with this crate so the spec sits
/// next to the AST it describes; a drift test
/// (`tests/spec_drift.rs`) walks every AST enum variant and asserts
/// its serde tag appears in this string. Adding a new variant
/// without updating the spec fails the test suite.
pub const FORM_A_SPEC: &str = include_str!("../specs/form_a.md");

/// Load a single module file, validate its schema, and deserialize it
/// into a [`Module`].
///
/// This is the lowest-level entry point and does **not** resolve imports
/// — for the transitive closure use [`load_workspace`]. Errors are
/// returned as [`Error::Io`] / [`Error::Json`] / [`Error::SchemaMismatch`].
pub fn load_module(path: &std::path::Path) -> Result<Module> {
    let bytes = std::fs::read(path)?;
    let module: Module = serde_json::from_slice(&bytes)?;
    if module.schema != SCHEMA {
        return Err(Error::SchemaMismatch {
            expected: SCHEMA.to_string(),
            got: module.schema,
        });
    }
    Ok(module)
}