trueskill-tt/tests/validation.rs

//! Input validation must hold in **release**, where `debug_assert!` is gone.
//!
//! The engine guards itself with `debug_assert!`, which documents invariants
//! but vanishes in the profile users actually ship. Anything reachable from the
//! public API has to be rejected with an `InferenceError` instead, at the
//! boundary, rather than becoming NaN or an out-of-bounds panic deep inside
//! `run_chain`.
//!
//! `GameOptions` and `ConvergenceOptions` both have public fields, so the
//! eager asserts on `HistoryBuilder` do not cover the `Game` constructors —
//! a caller can build the options struct directly.

use smallvec::smallvec;
use trueskill_tt::{
    ConstantDrift, ConvergenceOptions, Event, Game, GameOptions, Gaussian, History, InferenceError,
    Member, Outcome, Rating, Team,
};

type R = Rating<i64, ConstantDrift>;

fn rating() -> R {
    R::new(
        Gaussian::from_ms(25.0, 25.0 / 3.0),
        25.0 / 6.0,
        ConstantDrift::new(0.0),
    )
}

fn options_with_alpha(alpha: f64) -> GameOptions {
    GameOptions {
        convergence: ConvergenceOptions {
            alpha,
            ..ConvergenceOptions::default()
        },
        ..GameOptions::default()
    }
}

/// `alpha == 0.0` leaves every EP update unapplied, so inference silently
/// returns the priors — the worst possible failure, since the output looks
/// entirely reasonable.
#[test]
fn ranked_rejects_a_zero_damping_factor() {
    let (a, b) = (rating(), rating());
    let err = Game::<i64, _>::ranked(
        &[&[a], &[b]],
        Outcome::winner(0, 2),
        &options_with_alpha(0.0),
    )
    .expect_err("alpha = 0 must be rejected");
    assert!(
        matches!(
            err,
            InferenceError::InvalidParameter {
                parameter: trueskill_tt::Parameter::Alpha,
                ..
            }
        ),
        "got {err:?}"
    );
}

#[test]
fn ranked_rejects_an_out_of_range_damping_factor() {
    let (a, b) = (rating(), rating());
    for alpha in [-0.5, 1.5, f64::NAN] {
        let err = Game::<i64, _>::ranked(
            &[&[a], &[b]],
            Outcome::winner(0, 2),
            &options_with_alpha(alpha),
        )
        .expect_err("alpha out of (0, 1] must be rejected");
        assert!(
            matches!(
                err,
                InferenceError::InvalidParameter {
                    parameter: trueskill_tt::Parameter::Alpha,
                    ..
                }
            ),
            "alpha={alpha}: got {err:?}"
        );
    }
}

#[test]
fn scored_rejects_a_bad_damping_factor() {
    let (a, b) = (rating(), rating());
    let err = Game::<i64, _>::scored(
        &[&[a], &[b]],
        Outcome::scores([21.0, 9.0]),
        &options_with_alpha(0.0),
    )
    .expect_err("alpha = 0 must be rejected");
    assert!(
        matches!(
            err,
            InferenceError::InvalidParameter {
                parameter: trueskill_tt::Parameter::Alpha,
                ..
            }
        ),
        "got {err:?}"
    );
}

/// Already covered by `Game::ranked`, asserted here so the release-mode
/// guarantee is stated in one place.
#[test]
fn ranked_rejects_an_out_of_range_draw_probability() {
    let (a, b) = (rating(), rating());
    for p_draw in [-0.5, 1.0, 1.5] {
        let options = GameOptions {
            p_draw,
            ..GameOptions::default()
        };
        assert!(
            Game::<i64, _>::ranked(&[&[a], &[b]], Outcome::winner(0, 2), &options).is_err(),
            "p_draw={p_draw} must be rejected"
        );
    }
}

#[test]
fn scored_rejects_a_non_positive_noise() {
    let (a, b) = (rating(), rating());
    for score_sigma in [0.0, -1.0, f64::NAN] {
        let options = GameOptions {
            score_sigma,
            ..GameOptions::default()
        };
        assert!(
            Game::<i64, _>::scored(&[&[a], &[b]], Outcome::scores([21.0, 9.0]), &options).is_err(),
            "score_sigma={score_sigma} must be rejected"
        );
    }
}

/// A tie with no draw probability makes the truncation margin zero and the
/// two-sided update evaluate 0/0. Ingestion must refuse it.
#[test]
fn ingestion_rejects_a_tie_without_a_draw_probability() {
    let mut h = History::builder().p_draw(0.0).build();
    let err = h
        .add_events(vec![Event {
            time: 0,
            teams: smallvec![
                Team::with_members([Member::new("a")]),
                Team::with_members([Member::new("b")]),
            ],
            outcome: Outcome::draw(2),
        }])
        .expect_err("a tie with p_draw = 0 must be rejected");
    assert!(
        matches!(err, InferenceError::TieWithoutDrawProbability { .. }),
        "got {err:?}"
    );
}

/// `Outcome::scores_with_noise` documents that a non-positive sigma is
/// accepted at construction and rejected at ingestion.
#[test]
fn ingestion_rejects_a_non_positive_per_event_score_sigma() {
    for sigma in [0.0, -1.0, f64::NAN] {
        let mut h = History::builder().build();
        let err = h
            .add_events(vec![Event {
                time: 0,
                teams: smallvec![
                    Team::with_members([Member::new("a")]),
                    Team::with_members([Member::new("b")]),
                ],
                outcome: Outcome::scores_with_noise([21.0, 9.0], sigma),
            }])
            .expect_err("a non-positive per-event sigma must be rejected");
        assert!(
            matches!(err, InferenceError::InvalidParameter { .. }),
            "sigma={sigma}: got {err:?}"
        );
    }
}

/// Per-team weights must match that team's membership. The top-level length
/// checks in ingestion do not cover the inner dimension.
#[test]
fn ingestion_rejects_weights_that_do_not_match_their_team() {
    let mut h = History::builder().build();
    let mut team = Team::with_members([Member::new("a"), Member::new("b")]);
    team.members[0].weight = 1.0;

    let err = h
        .event(0)
        .team(["a", "b"])
        .team(["c"])
        // Three weights for a two-member team.
        .weights([1.0, 1.0, 1.0])
        .winner(0)
        .commit()
        .expect_err("a weight/member length mismatch must be rejected");
    assert!(
        matches!(err, InferenceError::MismatchedShape { .. }),
        "got {err:?}"
    );
}

/// `mu`, `sigma` and `beta` were the last unvalidated setters on
/// `HistoryBuilder`, next to `p_draw`, `score_sigma` and `convergence`, which
/// all assert eagerly.
///
/// Two of the rejected values are the quiet kind. A negative `sigma` or `beta`
/// enters inference only as its square, so it produced bit-identical results
/// to the positive value — the sign was dropped without comment.
mod builder_parameters {
    use trueskill_tt::History;

    #[test]
    #[should_panic(expected = "mu must be finite")]
    fn a_non_finite_mu_is_rejected() {
        let _ = History::builder().mu(f64::NAN);
    }

    #[test]
    #[should_panic(expected = "sigma must be finite and positive")]
    fn a_zero_sigma_is_rejected() {
        let _ = History::builder().sigma(0.0);
    }

    #[test]
    #[should_panic(expected = "sigma must be finite and positive")]
    fn a_negative_sigma_is_rejected() {
        let _ = History::builder().sigma(-8.33);
    }

    #[test]
    #[should_panic(expected = "sigma must be finite and positive")]
    fn an_infinite_sigma_is_rejected() {
        let _ = History::builder().sigma(f64::INFINITY);
    }

    #[test]
    #[should_panic(expected = "beta must be finite and non-negative")]
    fn a_negative_beta_is_rejected() {
        let _ = History::builder().beta(-4.17);
    }

    #[test]
    #[should_panic(expected = "beta must be finite and non-negative")]
    fn a_non_finite_beta_is_rejected() {
        let _ = History::builder().beta(f64::NAN);
    }

    /// Zero beta is deliberately allowed: performance is then exactly skill.
    /// It has to reach a different fit than a positive beta, or "allowed"
    /// would just mean "not checked".
    #[test]
    fn a_zero_beta_is_allowed_and_changes_the_fit() {
        let fit = |beta: f64| {
            let mut h = History::builder()
                .mu(25.0)
                .sigma(25.0 / 3.0)
                .beta(beta)
                .build();
            h.record_winner(&"a", &"b", 1).unwrap();
            let _ = h.converge().unwrap();
            h.current_skill(&"a").unwrap()
        };
        let zero = fit(0.0);
        let positive = fit(25.0 / 6.0);
        // `variance` rather than `pi`: the natural parameters are the crate's
        // internal representation and no longer public. It is the same
        // quantity inverted, so a finite positive precision is a finite
        // positive variance.
        assert!(zero.variance().is_finite() && zero.variance() > 0.0);
        assert!(
            (zero.variance() - positive.variance()).abs() > 1e-6,
            "zero beta must not merely be ignored: {zero:?} vs {positive:?}"
        );
    }
}

/// The constructors below `HistoryBuilder`, which 0.8.0's validation did not
/// reach.
///
/// `sigma`, `beta` and `gamma` all enter inference only as squares, so a
/// negative value behaves as its absolute value and the sign vanishes without
/// comment. Measured before these guards: `from_ms(25.0, -8.33)` and
/// `Rating::new(_, -4.17, _)` returned results bit identical to their positive
/// counterparts, and `Rating::new(_, NaN, _)` reached `Game::ranked`, which
/// returned `Ok` carrying `Gaussian { pi: NaN, tau: NaN }`.
mod constructor_parameters {
    use trueskill_tt::{ConstantDrift, Gaussian, History, InferenceError, Rating};

    #[test]
    #[should_panic(expected = "sigma must not be negative")]
    fn a_negative_sigma_is_rejected_by_from_ms() {
        let _ = Gaussian::from_ms(25.0, -8.33);
    }

    /// NaN must pass, and that is deliberate: a broken fit produces a NaN
    /// sigma and `converge` reports it as `NonFiniteResult`. Rejecting it here
    /// would turn reporting into a panic inside inference.
    #[test]
    fn a_nan_sigma_passes_through_from_ms() {
        let g = Gaussian::from_ms(25.0, f64::NAN);
        // `sigma()` is NaN exactly when the precision is: it guards `pi <= 0`
        // (reporting `inf`) and `pi == inf` (reporting `0.0`), so NaN survives
        // only from a NaN precision.
        assert!(g.sigma().is_nan());
    }

    #[test]
    #[should_panic(expected = "beta must be finite and non-negative")]
    fn a_negative_beta_is_rejected_by_rating_new() {
        let _ =
            Rating::<i64, ConstantDrift>::new(Gaussian::default(), -4.17, ConstantDrift::new(0.0));
    }

    #[test]
    #[should_panic(expected = "beta must be finite and non-negative")]
    fn a_nan_beta_is_rejected_by_rating_new() {
        let _ = Rating::<i64, ConstantDrift>::new(
            Gaussian::default(),
            f64::NAN,
            ConstantDrift::new(0.0),
        );
    }

    #[test]
    fn a_zero_beta_is_accepted_by_rating_new() {
        let _ =
            Rating::<i64, ConstantDrift>::new(Gaussian::default(), 0.0, ConstantDrift::new(0.0));
    }

    /// `ConstantDrift` rejects at construction now that its field is private.
    #[test]
    #[should_panic(expected = "gamma must be finite and non-negative")]
    fn a_negative_gamma_is_rejected_by_constant_drift_new() {
        let _ = ConstantDrift::new(-0.0833);
    }

    #[test]
    #[should_panic(expected = "gamma must be finite and non-negative")]
    fn a_non_finite_gamma_is_rejected_by_constant_drift_new() {
        let _ = ConstantDrift::new(f64::NAN);
    }

    #[test]
    fn gamma_reads_back_what_was_given() {
        assert_eq!(ConstantDrift::new(0.25).gamma(), 0.25);
        assert_eq!(ConstantDrift::new(0.0).gamma(), 0.0);
    }

    /// `HistoryBuilder::drift` is generic and cannot inspect an arbitrary
    /// `Drift`, so the check on the variance each competitor accumulates is
    /// still needed — it is the only thing standing between a custom
    /// implementation and a NaN fit. `ConstantDrift` can no longer reach it,
    /// so this uses an implementation that can.
    #[test]
    fn a_custom_drift_returning_a_bad_variance_is_rejected_at_convergence() {
        #[derive(Clone, Copy, Debug)]
        struct BadDrift(f64);

        impl trueskill_tt::Drift<i64> for BadDrift {
            fn variance_delta(&self, _from: &i64, _to: &i64) -> f64 {
                self.0
            }
            fn variance_for_elapsed(&self, _elapsed: i64) -> f64 {
                self.0
            }
        }

        for bad in [f64::NAN, f64::INFINITY, -1.0] {
            let mut h = History::builder().drift(BadDrift(bad)).build();
            h.record_winner(&"a", &"b", 1).unwrap();
            h.record_winner(&"a", &"b", 5).unwrap();
            let err = h.converge().unwrap_err();
            assert!(
                matches!(
                    err,
                    InferenceError::InvalidParameter {
                        parameter: trueskill_tt::Parameter::DriftVariance,
                        ..
                    }
                ),
                "drift {bad}: {err:?}"
            );
        }
    }

    /// An ordinary drift is untouched.
    #[test]
    fn an_ordinary_drift_still_converges() {
        let mut h = History::builder()
            .drift(ConstantDrift::new(25.0 / 300.0))
            .build();
        h.record_winner(&"a", &"b", 1).unwrap();
        h.record_winner(&"a", &"b", 5).unwrap();
        assert!(h.converge().unwrap().converged);
    }
}