AILang/crates/ailang-surface/tests/round_trip.rs

//! Roundtrip Invariant gate (in-process) for the form-(A) projection.
//!
//! Two complementary checks over `examples/*.ail`, each gathering
//! fixtures dynamically via `read_dir` (no hardcoded lists). The
//! tests are pure readers — they do not write into the working
//! tree.
//!
//! 1. `parse_is_deterministic_over_every_ail_fixture` — pins
//!    **parse-determinism** (property 1 of the post-form-a Roundtrip
//!    Invariant, design/contracts/0009-roundtrip-invariant.md). For every
//!    well-formed `.ail` text `t`, `parse(t)` produces the same
//!    canonical bytes every invocation. The parser is a pure
//!    function of input — no randomness, no time dependence, no
//!    environment leak. Hashing `canonical::to_bytes(parse(t))` is
//!    therefore well-defined for any `.ail` source.
//!
//! 2. `parse_then_print_then_parse_is_idempotent_on_every_ail_fixture`
//!    — pins **idempotency-under-print** (property 2). For every
//!    well-formed `.ail` text `t`, asserts
//!    `canonical_bytes(parse(t))` equals
//!    `canonical_bytes(parse(print(parse(t))))`. The printer is a
//!    left-inverse of the parser modulo canonical form.
//!
//! The other two properties of the post-form-a Roundtrip Invariant
//! live in sibling test crates: **CLI-pipeline-idempotency** is
//! pinned by `crates/ail/tests/roundtrip_cli.rs::cli_parse_then_render_then_parse_is_idempotent`,
//! and **carve-out-anchor** is pinned by
//! `crates/ailang-core/tests/carve_out_inventory.rs::examples_ail_json_inventory_matches_carve_outs`.
//!
//! Retired iter form-a.1 T9: `print_then_parse_round_trips_every_fixture`
//! (corpus shrunk to 8 carve-outs post-iter) and
//! `every_ail_fixture_matches_its_json_counterpart` (no longer
//! expressible: only one form is hand-authored post-iter).

use std::path::PathBuf;

fn examples_dir() -> PathBuf {
    // `CARGO_MANIFEST_DIR` is the surface crate root; examples live two
    // levels up.
    let crate_dir = PathBuf::from(env!("CARGO_MANIFEST_DIR"));
    crate_dir.parent().unwrap().parent().unwrap().join("examples")
}

// Retired iter form-a.1 T9:
// - `list_json_fixtures` helper (walked `.ail.json` for the two retired tests below).
// - `print_then_parse_round_trips_every_fixture`: corpus shrunk to 8 carve-outs
//   post-iter; property subsumed by `parse_is_deterministic_over_every_ail_fixture`
//   plus the surviving `parse_then_print_then_parse_is_idempotent_on_every_ail_fixture`.
// - `round_trip_one` helper (only consumer was the retired test above).
// - `every_ail_fixture_matches_its_json_counterpart`: no longer expressible —
//   only one form is hand-authored post-iter; counterparts are derived in-process
//   via `ail parse`.

/// Fixtures that intentionally do NOT parse — the `#55` cutover
/// reject corpus. Negative fixtures whose whole point is that the
/// parser rejects them, so the parse/round-trip properties below are
/// not meaningful for them and the corpus scan must skip them.
/// Mirrors the same list in `crates/ail/tests/roundtrip_cli.rs`.
///
/// - `bare_slot_reject.ail`: a bare fn-type slot with no mode. The
///   binary-ParamMode parser rejects it ("fn-type slot requires a
///   mode: write (own T) or (borrow T)").
const NON_PARSEABLE_FIXTURES: &[&str] = &["bare_slot_reject.ail"];

fn list_ail_fixtures() -> Vec<PathBuf> {
    let dir = examples_dir();
    let mut paths: Vec<PathBuf> = std::fs::read_dir(&dir)
        .unwrap_or_else(|e| panic!("read_dir({}): {e}", dir.display()))
        .filter_map(|entry| entry.ok())
        .map(|e| e.path())
        .filter(|p| {
            p.file_name()
                .and_then(|n| n.to_str())
                .map(|n| n.ends_with(".ail") && !NON_PARSEABLE_FIXTURES.contains(&n))
                .unwrap_or(false)
        })
        .collect();
    paths.sort();
    paths
}

/// Pins **idempotency-under-print** (property 2 of the post-form-a
/// Roundtrip Invariant, design/contracts/0009-roundtrip-invariant.md): for every
/// well-formed `.ail` text `t`, the composition `parse → print → parse`
/// is idempotent on the AST.
///
/// Direct enforcement complements the parse-determinism gate above
/// (which alone does not constrain the printer). Together they pin
/// `parse → print` as a left-inverse modulo canonical form for every
/// `.ail` fixture in the corpus.
#[test]
fn parse_then_print_then_parse_is_idempotent_on_every_ail_fixture() {
    let fixtures = list_ail_fixtures();
    assert!(
        !fixtures.is_empty(),
        "no .ail fixtures found under {}",
        examples_dir().display()
    );

    let mut failures = Vec::<String>::new();
    let mut passed = 0usize;
    for path in &fixtures {
        let text = match std::fs::read_to_string(path) {
            Ok(t) => t,
            Err(e) => {
                failures.push(format!("{}: read failed: {e}", path.display()));
                continue;
            }
        };
        let parsed_once = match ailang_surface::parse(&text) {
            Ok(m) => m,
            Err(e) => {
                failures.push(format!("{}: parse(t) failed: {e}", path.display()));
                continue;
            }
        };
        let printed = ailang_surface::print(&parsed_once);
        let parsed_twice = match ailang_surface::parse(&printed) {
            Ok(m) => m,
            Err(e) => {
                failures.push(format!(
                    "{}: parse(print(parse(t))) failed: {e}\n--- printed ---\n{printed}",
                    path.display()
                ));
                continue;
            }
        };
        let bytes_a = ailang_core::canonical::to_bytes(&parsed_once);
        let bytes_b = ailang_core::canonical::to_bytes(&parsed_twice);
        if bytes_a != bytes_b {
            let s_a = String::from_utf8_lossy(&bytes_a).into_owned();
            let s_b = String::from_utf8_lossy(&bytes_b).into_owned();
            failures.push(format!(
                "{}: parse → print → parse is NOT idempotent.\nparse(t):              {s_a}\nparse(print(parse(t))): {s_b}",
                path.display()
            ));
            continue;
        }
        passed += 1;
    }

    if !failures.is_empty() {
        panic!(
            "{} of {} .ail fixture(s) failed idempotency check (passed: {}):\n{}",
            failures.len(),
            fixtures.len(),
            passed,
            failures.join("\n\n")
        );
    }
    eprintln!("parse→print→parse idempotency ok for {passed} .ail fixtures");
}

/// prep.2 (kernel-extension-mechanics): pins the Form-A round-trip for
/// `(new T <type-arg> <value-arg>)`. The fixture exercises the
/// `parse_new` dispatcher + the `write_term` Term::New arm, including
/// the Type-vs-Value arg disambiguation on the parser side (head
/// keyword `con` → NewArg::Type; bare integer → NewArg::Value).
///
/// Inline rather than `examples/*.ail` because no existing fixture
/// uses `Term::New` and the iter's out-of-scope note explicitly
/// declines a fixture migration in prep.2 (the construct will only
/// see real fixtures once raw-buf's codegen lands).
#[test]
fn round_trip_term_new_mixed_args() {
    // (new Series (con Float) 3) — a Type-positional arg followed by
    // a Value-positional arg. The body lives inside an otherwise
    // minimal module shell that the printer emits in canonical form.
    let form_a = "(module new_demo\n  (data Series\n    (ctor MkSeries (con Int)))\n  (fn new\n    (type (fn-type (params (own (con Int))) (ret (own (con Series)))))\n    (params n)\n    (body (term-ctor Series MkSeries n)))\n  (fn main\n    (type (fn-type (params) (ret (own (con Series)))))\n    (params)\n    (body (new Series (con Float) 3))))";
    let parsed_once = ailang_surface::parse(form_a)
        .expect("Form-A round-trip fixture must parse");
    let printed = ailang_surface::print(&parsed_once);
    let parsed_twice = ailang_surface::parse(&printed).expect("print(parse(x)) must re-parse");
    let bytes_a = ailang_core::canonical::to_bytes(&parsed_once);
    let bytes_b = ailang_core::canonical::to_bytes(&parsed_twice);
    assert_eq!(
        bytes_a, bytes_b,
        "Term::New round-trip parse→print→parse is not idempotent.\nfirst:  {}\nprint:  {printed}\nsecond: {}",
        String::from_utf8_lossy(&bytes_a),
        String::from_utf8_lossy(&bytes_b),
    );
}

/// Parse-determinism (post-form-a-default-authoring §C3): for every
/// well-formed `.ail` text `t`, `parse(t)` produces the same canonical
/// bytes every invocation. Loader is a pure function of input — no
/// randomness, no time dependence, no environment leak.
#[test]
fn parse_is_deterministic_over_every_ail_fixture() {
    let mut checked = 0usize;
    for ail_path in list_ail_fixtures() {
        let text = std::fs::read_to_string(&ail_path)
            .unwrap_or_else(|e| panic!("read {ail_path:?}: {e}"));
        let m1 = ailang_surface::parse(&text)
            .unwrap_or_else(|e| panic!("parse {ail_path:?}: {e:?}"));
        let m2 = ailang_surface::parse(&text)
            .unwrap_or_else(|e| panic!("parse {ail_path:?} (2nd): {e:?}"));
        let b1 = ailang_core::canonical::to_bytes(&m1);
        let b2 = ailang_core::canonical::to_bytes(&m2);
        assert_eq!(
            b1, b2,
            "parse non-determinism on {ail_path:?}",
        );
        checked += 1;
    }
    assert!(checked > 0, "no .ail fixtures found");
}

/// prep.3 (kernel-extension-mechanics): the `(kernel)` module-header
/// attribute round-trips Form-A → JSON → Form-A bit-identical and
/// preserves the parsed bool through both halves.
#[test]
fn kernel_module_header_round_trips() {
    let src = "(module k\n  (kernel))\n";
    let m = ailang_surface::parse(src).expect("Form-A parse of (kernel) module");
    assert!(m.kernel, "parsed kernel: true");

    let printed = ailang_surface::print(&m);
    // Round-trip: print, re-parse, kernel still true.
    let m2 = ailang_surface::parse(&printed).expect("re-parse printed form");
    assert!(m2.kernel, "kernel: true survives round-trip");

    // Default form (no (kernel)) stays kernel: false.
    let plain = ailang_surface::parse("(module p)\n").expect("Form-A parse plain module");
    assert!(!plain.kernel);
}

/// prep.3 (kernel-extension-mechanics): the `(param-in (var t1 t2 ...))`
/// TypeDef attribute round-trips Form-A → JSON → Form-A bit-
/// identical and preserves the parsed BTreeMap through both halves,
/// including the BTreeSet's deterministic alphabetical iteration
/// order.
#[test]
fn typedef_param_in_round_trips_surface() {
    let src = concat!(
        "(module m\n",
        "  (data T (vars a)\n",
        "    (ctor MkT a)\n",
        "    (param-in (a Int Float))))\n",
    );
    let m = ailang_surface::parse(src).expect("Form-A parse of (param-in ...)");
    let td = match &m.defs[0] {
        ailang_core::ast::Def::Type(t) => t,
        _ => panic!("expected Type def"),
    };
    let allowed = td.param_in.get("a").expect("var `a` bound in param_in");
    assert!(allowed.contains("Int"));
    assert!(allowed.contains("Float"));
    assert_eq!(allowed.len(), 2);

    let printed = ailang_surface::print(&m);
    let m2 = ailang_surface::parse(&printed).expect("re-parse printed form");
    let td2 = match &m2.defs[0] {
        ailang_core::ast::Def::Type(t) => t,
        _ => panic!("expected Type def after round-trip"),
    };
    assert_eq!(td2.param_in, td.param_in, "param_in survives round-trip");
}