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

//! Round-trip gate 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`: 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`:
//!    Direction 2 of the Roundtrip Invariant (DESIGN.md §"Roundtrip
//!    Invariant"). 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.
//!
//! 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`.

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"))
                .unwrap_or(false)
        })
        .collect();
    paths.sort();
    paths
}

/// Direction 2 of the Roundtrip Invariant (DESIGN.md §"Roundtrip
/// Invariant"): for every well-formed `.ail` text `t`, the
/// composition `parse → print → parse` is idempotent on the AST.
///
/// For the 57 `.ail` fixtures that have a JSON counterpart this
/// follows logically from `print_then_parse_round_trips_every_fixture`
/// + `every_ail_fixture_matches_its_json_counterpart`. This test
/// asserts the property directly so it stays robust for future
/// `.ail` fixtures without a JSON counterpart, and so the spec's
/// Direction-2 claim has a dedicated enforcement point.
#[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");
}

/// 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");
}