Files
improvise/crates/improvise-incremental/tests/oracle.rs
T

634 lines
20 KiB
Rust

//! `Eager` against the evaluator, and the harness against wrong backends.
//! Evidence: `context/test-evidence/improvise-incremental.md`.
use improvise_core::formula::ast::AggFunc;
use improvise_core::formula::parse_formula;
use improvise_core::model::cell::{CellKey, CellValue};
use improvise_core::model::{Aggregation, Model};
use improvise_core::view::Axis;
use improvise_incremental::{
Derived, Divergence, Eager, Edit, Maintained, Probe, differential, probes, same_value,
};
use proptest::prelude::*;
use std::path::Path;
fn key(region: &str, product: &str, measure: &str) -> CellKey {
CellKey::new(vec![
("Region".into(), region.into()),
("Product".into(), product.into()),
("_Measure".into(), measure.into()),
])
}
fn partial(product: &str, measure: &str) -> CellKey {
CellKey::new(vec![
("Product".into(), product.into()),
("_Measure".into(), measure.into()),
])
}
fn num(n: f64) -> Option<CellValue> {
Some(CellValue::Number(n))
}
fn text(s: &str) -> Option<CellValue> {
Some(CellValue::Text(s.into()))
}
fn mixed() -> Option<CellValue> {
Some(CellValue::Error("mixed".into()))
}
/// Region is the None category. Revenue and Cost are numbers; Note is text,
/// unanimous under A and conflicting under B.
fn hand_model() -> Model {
let mut m = Model::new("hand");
for (cat, items) in [("Region", ["East", "West"]), ("Product", ["A", "B"])] {
m.add_category(cat).unwrap();
for item in items {
m.category_mut(cat).unwrap().add_item(item);
}
}
for measure in ["Revenue", "Cost", "Note"] {
m.category_mut("_Measure").unwrap().add_item(measure);
}
let rows = [
("East", "A", 10.0, 4.0, "n", "n"),
("West", "A", 5.0, 2.0, "n", "n"),
("East", "B", 7.0, 3.0, "x", "x"),
("West", "B", 1.0, 1.0, "y", "y"),
];
for (r, p, rev, cost, note, _) in rows {
m.set_cell(key(r, p, "Revenue"), CellValue::Number(rev));
m.set_cell(key(r, p, "Cost"), CellValue::Number(cost));
m.set_cell(key(r, p, "Note"), CellValue::Text(note.into()));
}
m.add_formula(parse_formula("Profit = Revenue - Cost", "_Measure").unwrap());
m
}
fn hand_eager() -> Eager {
Eager::new(hand_model(), vec!["Region".into()])
}
fn hand_edits() -> Vec<Edit> {
vec![
Edit::SetCell(key("East", "A", "Revenue"), CellValue::Number(20.0)),
Edit::SetMeasureAgg {
measure: "Revenue".into(),
func: AggFunc::Max,
},
Edit::ClearCell(key("West", "A", "Revenue")),
Edit::SetCell(key("West", "B", "Revenue"), CellValue::Text("oops".into())),
Edit::AddFormula(parse_formula("Double = Revenue * 2", "_Measure").unwrap()),
Edit::RemoveFormula {
target: "Profit".into(),
target_category: "_Measure".into(),
},
]
}
#[test]
fn eager_raw_fold_sums_by_default() {
assert_eq!(hand_eager().raw_fold(&partial("A", "Revenue")), num(15.0));
}
#[test]
fn eager_raw_fold_follows_the_measures_aggregation() {
let mut eager = hand_eager();
eager.apply(&Edit::SetMeasureAgg {
measure: "Revenue".into(),
func: AggFunc::Max,
});
assert_eq!(eager.raw_fold(&partial("A", "Revenue")), num(10.0));
assert_eq!(eager.raw_fold(&partial("A", "Cost")), num(6.0));
}
#[test]
fn eager_raw_fold_of_text_is_unanimous_or_mixed() {
let eager = hand_eager();
assert_eq!(eager.raw_fold(&partial("A", "Note")), text("n"));
assert_eq!(eager.raw_fold(&partial("B", "Note")), mixed());
}
#[test]
fn eager_value_reads_a_formula_exactly_and_folded() {
let eager = hand_eager();
assert_eq!(
eager.value(&key("East", "A", "Profit"), Aggregation::Exact),
num(6.0)
);
assert_eq!(
eager.value(&partial("A", "Profit"), Aggregation::OverHidden),
num(9.0)
);
}
#[test]
fn eager_follows_an_edit_to_the_cell_a_fold_reads() {
let mut eager = hand_eager();
eager.apply(&Edit::SetCell(
key("East", "A", "Revenue"),
CellValue::Number(20.0),
));
assert_eq!(eager.raw_fold(&partial("A", "Revenue")), num(25.0));
assert_eq!(
eager.value(&partial("A", "Profit"), Aggregation::OverHidden),
num(19.0)
);
}
#[test]
fn eager_numbers_among_text_are_mixed() {
let mut eager = hand_eager();
eager.apply(&Edit::SetCell(
key("West", "B", "Revenue"),
CellValue::Text("oops".into()),
));
assert_eq!(eager.raw_fold(&partial("B", "Revenue")), mixed());
}
fn corpus() -> Vec<(String, Model, Vec<String>)> {
let root = Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
let mut out = Vec::new();
for file in ["examples/demo.improv", "web/demo.improv"] {
let wb = improvise_io::persistence::load(&root.join(file)).unwrap();
let mut seen: Vec<Vec<String>> = Vec::new();
for (name, view) in &wb.views {
let none: Vec<String> = view
.categories_on(Axis::None)
.into_iter()
.map(String::from)
.collect();
if !seen.contains(&none) {
seen.push(none.clone());
out.push((format!("{file}:{name}"), wb.model.clone(), none));
}
}
}
out.push(("hand".into(), hand_model(), vec!["Region".into()]));
out
}
/// Edits built from the model's own first cell: overwrite, text, clear, a new
/// record, a new aggregation, and the first formula removed then restored.
fn edits_for(model: &Model) -> Vec<Edit> {
let Some((first, _)) = model.data.iter_cells().next() else {
return vec![];
};
let (last_cat, _) = first.0.last().unwrap().clone();
let measure = first.get("_Measure").map(String::from);
let fresh = first.clone().with(last_cat, "Zz-new");
let mut edits = vec![
Edit::SetCell(first.clone(), CellValue::Number(7.5)),
Edit::SetCell(first.clone(), CellValue::Text("t".into())),
Edit::SetCell(fresh.clone(), CellValue::Number(3.0)),
Edit::ClearCell(first),
];
edits.extend(measure.map(|m| Edit::SetMeasureAgg {
measure: m,
func: AggFunc::Max,
}));
if let Some(f) = model.formulas().first() {
edits.push(Edit::RemoveFormula {
target: f.target.clone(),
target_category: f.target_category.clone(),
});
edits.push(Edit::AddFormula(f.clone()));
}
edits.push(Edit::ClearCell(fresh));
edits
}
#[test]
fn eager_matches_the_evaluator_on_the_shipped_documents() {
for (name, model, none) in corpus() {
let eager = Eager::new(model.clone(), none.clone());
let mut direct = model.clone();
direct.recompute_formulas(&none);
let asked = probes(eager.model());
assert!(!asked.is_empty(), "{name}: no probes");
for probe in asked {
let want = match &probe {
Probe::Value(k, a) => direct.evaluate_aggregated(k, *a),
Probe::RawFold(k) if direct.formula_for(k).is_some() => None,
Probe::RawFold(k) => direct.evaluate_aggregated(k, Aggregation::OverHidden),
};
assert_eq!(probe.ask(&eager), want, "{name}: {probe:?}");
}
}
}
#[test]
fn eager_agrees_with_itself_over_every_corpus_edit_sequence() {
let mut files_done: Vec<String> = Vec::new();
for (name, model, none) in corpus() {
let file = name.split(':').next().unwrap().to_string();
if files_done.contains(&file) {
continue;
}
files_done.push(file);
let mut edits = edits_for(&model);
// Probes grow with the cells squared-ish, and a debug build pays for it.
if model.data.iter_cells().count() > 40 {
edits.truncate(4);
}
let report = differential(
&model,
&none,
Eager::new(model.clone(), none.clone()),
&edits,
)
.unwrap_or_else(|d| panic!("{name}: {d}"));
assert_eq!(report.steps, edits.len() + 1, "{name}");
assert!(report.probes > 0, "{name}");
}
}
fn grouped_model() -> Model {
let mut m = Model::new("grouped");
m.add_category("Region").unwrap();
m.add_category("Product").unwrap();
m.category_mut("Region")
.unwrap()
.add_group(improvise_core::model::category::Group::new("Coastal"));
let region = m.category_mut("Region").unwrap();
region.add_item_in_group("East", "Coastal");
region.add_item_in_group("West", "Coastal");
region.add_item("Inland");
m.category_mut("Product").unwrap().add_item("A");
m.category_mut("_Measure").unwrap().add_item("Revenue");
for (r, v) in [("East", 10.0), ("West", 5.0), ("Inland", 2.0)] {
m.set_cell(key(r, "A", "Revenue"), CellValue::Number(v));
}
m
}
fn coastal() -> CellKey {
key("Coastal", "A", "Revenue")
}
/// A wrong backend: an `Eager` told every edit, answering one thing wrongly.
#[derive(Clone, Copy)]
enum Fault {
IgnoresAggregation,
IgnoresMeasureAggregation,
GoesStaleAfterTwoEdits,
IgnoresClear,
WrongFoldedFormula,
IgnoresRemoveFormula,
WrongWhenTwoAreDropped,
RawFoldReturnsFormula,
WrongOnAGroup,
}
struct Rival {
inner: Eager,
fault: Fault,
seen: usize,
}
impl Rival {
fn over(inner: Eager, fault: Fault) -> Self {
Rival {
inner,
fault,
seen: 0,
}
}
fn of(fault: Fault) -> Self {
Self::over(hand_eager(), fault)
}
}
impl Derived for Rival {
fn value(&self, k: &CellKey, agg: Aggregation) -> Option<CellValue> {
let wrong = match self.fault {
Fault::WrongFoldedFormula => {
*k == partial("A", "Profit") && agg == Aggregation::OverHidden
}
Fault::WrongWhenTwoAreDropped => *k == only_revenue(),
Fault::WrongOnAGroup => *k == coastal() && agg == Aggregation::Exact,
_ => false,
};
match (wrong, self.fault) {
(true, _) => num(-999.0),
(_, Fault::IgnoresAggregation) => self.inner.value(k, Aggregation::Exact),
_ => self.inner.value(k, agg),
}
}
fn raw_fold(&self, p: &CellKey) -> Option<CellValue> {
match self.fault {
Fault::WrongWhenTwoAreDropped if *p == only_revenue() => num(-999.0),
Fault::RawFoldReturnsFormula => self.inner.value(p, Aggregation::OverHidden),
_ => self.inner.raw_fold(p),
}
}
}
impl Maintained for Rival {
fn apply(&mut self, edit: &Edit) {
self.seen += 1;
let skip = match (self.fault, edit) {
(Fault::IgnoresMeasureAggregation, Edit::SetMeasureAgg { .. }) => true,
(Fault::GoesStaleAfterTwoEdits, _) => self.seen > 2,
(Fault::IgnoresClear, Edit::ClearCell(_)) => true,
(Fault::IgnoresRemoveFormula, Edit::RemoveFormula { .. }) => true,
_ => false,
};
if !skip {
self.inner.apply(edit);
}
}
}
fn only_revenue() -> CellKey {
CellKey::new(vec![("_Measure".into(), "Revenue".into())])
}
fn measure_of(probe: &Probe) -> Option<&str> {
match probe {
Probe::Value(k, _) | Probe::RawFold(k) => k.get("_Measure"),
}
}
fn run_rival(fault: Fault) -> Result<improvise_incremental::Report, Divergence> {
differential(
&hand_model(),
&["Region".to_string()],
Rival::of(fault),
&hand_edits(),
)
}
#[test]
fn the_harness_passes_a_backend_that_is_right() {
let report = differential(
&hand_model(),
&["Region".to_string()],
hand_eager(),
&hand_edits(),
)
.unwrap();
assert_eq!(report.steps, hand_edits().len() + 1);
}
#[test]
fn the_harness_catches_a_backend_that_ignores_the_aggregation() {
let d = run_rival(Fault::IgnoresAggregation).unwrap_err();
assert_eq!(d.step, 0);
assert_eq!(
d.probe,
Probe::Value(key("East", "A", "Profit"), Aggregation::OverHidden)
);
assert_eq!((d.eager, d.candidate), (None, num(6.0)));
}
#[test]
fn the_harness_catches_a_backend_that_ignores_the_measure_aggregation() {
let d = run_rival(Fault::IgnoresMeasureAggregation).unwrap_err();
assert_eq!(d.step, 2, "{d}");
assert_eq!(measure_of(&d.probe), Some("Revenue"), "{d}");
}
#[test]
fn the_harness_catches_a_backend_that_goes_stale_after_two_edits() {
let d = run_rival(Fault::GoesStaleAfterTwoEdits).unwrap_err();
assert_eq!(d.step, 3, "{d}");
assert_eq!(measure_of(&d.probe), Some("Revenue"), "{d}");
}
#[test]
fn the_harness_catches_a_backend_that_ignores_a_clear() {
let d = run_rival(Fault::IgnoresClear).unwrap_err();
assert_eq!(d.step, 3, "{d}");
assert_eq!(measure_of(&d.probe), Some("Revenue"), "{d}");
assert!(d.to_string().starts_with("divergence at step 3:"), "{d}");
}
#[test]
fn the_harness_catches_a_wrong_folded_formula_value() {
let d = run_rival(Fault::WrongFoldedFormula).unwrap_err();
assert_eq!(d.step, 0);
assert_eq!(
d.probe,
Probe::Value(partial("A", "Profit"), Aggregation::OverHidden)
);
assert_eq!((d.eager, d.candidate), (num(9.0), num(-999.0)));
}
#[test]
fn the_harness_catches_a_backend_that_keeps_answering_for_a_removed_formula() {
let d = run_rival(Fault::IgnoresRemoveFormula).unwrap_err();
assert_eq!(d.step, hand_edits().len(), "{d}");
assert_eq!(measure_of(&d.probe), Some("Profit"), "{d}");
assert!(d.eager.is_none() && d.candidate.is_some(), "{d}");
}
#[test]
fn the_harness_catches_a_fault_that_only_shows_after_two_coordinates_are_dropped() {
let d = run_rival(Fault::WrongWhenTwoAreDropped).unwrap_err();
assert_eq!(d.step, 0);
assert_eq!(d.probe, Probe::Value(only_revenue(), Aggregation::Exact));
assert_eq!(d.candidate, num(-999.0));
}
#[test]
fn the_harness_catches_a_raw_fold_that_returns_a_formula() {
let d = run_rival(Fault::RawFoldReturnsFormula).unwrap_err();
assert_eq!(d.step, 0);
assert!(matches!(d.probe, Probe::RawFold(_)), "{d}");
assert_eq!(measure_of(&d.probe), Some("Profit"), "{d}");
assert!(d.eager.is_none() && d.candidate.is_some(), "{d}");
}
#[test]
fn the_harness_catches_a_wrong_group_fold() {
let eager = Eager::new(grouped_model(), vec![]);
let d = differential(
&grouped_model(),
&[],
Rival::over(eager, Fault::WrongOnAGroup),
&[],
)
.unwrap_err();
assert_eq!(d.probe, Probe::Value(coastal(), Aggregation::Exact));
assert_eq!((d.eager, d.candidate), (num(15.0), num(-999.0)));
}
#[test]
fn eager_folds_a_group_it_is_asked_about() {
let eager = Eager::new(grouped_model(), vec![]);
assert_eq!(eager.value(&coastal(), Aggregation::Exact), num(15.0));
}
#[test]
fn eager_raw_fold_is_never_a_formula() {
let eager = hand_eager();
assert_eq!(
eager.value(&partial("A", "Profit"), Aggregation::OverHidden),
num(9.0)
);
assert_eq!(eager.raw_fold(&partial("A", "Profit")), None);
}
#[test]
fn eager_add_and_remove_formula_change_what_a_key_reads() {
let mut eager = hand_eager();
let k = key("East", "A", "Double");
assert_eq!(eager.value(&k, Aggregation::Exact), None);
eager.apply(&Edit::AddFormula(
parse_formula("Double = Revenue * 2", "_Measure").unwrap(),
));
assert_eq!(eager.value(&k, Aggregation::Exact), num(20.0));
eager.apply(&Edit::RemoveFormula {
target: "Double".into(),
target_category: "_Measure".into(),
});
assert_eq!(eager.value(&k, Aggregation::Exact), None);
}
#[test]
fn eager_clear_cell_leaves_the_key_absent() {
let mut eager = hand_eager();
let k = key("East", "A", "Revenue");
eager.apply(&Edit::ClearCell(k.clone()));
assert_eq!(eager.value(&k, Aggregation::Exact), None);
assert_eq!(eager.model().get_cell(&k), None);
}
#[test]
fn same_value_follows_the_float_rules_and_is_exact_elsewhere() {
let n = |x: f64| num(x);
assert!(same_value(&n(f64::NAN), &n(f64::NAN)));
assert!(same_value(&n(-0.0), &n(0.0)));
assert!(!same_value(&n(1.0), &n(1.000_000_000_000_000_2)));
assert!(!same_value(&n(1.0), &n(f64::NAN)));
assert!(same_value(&text("a"), &text("a")));
assert!(!same_value(&text("a"), &text("b")));
let err = |s: &str| Some(CellValue::Error(s.into()));
assert!(same_value(&err("mixed"), &err("mixed")));
assert!(!same_value(&err("mixed"), &err("circular")));
assert!(!same_value(&None, &n(0.0)));
assert!(same_value(&None, &None));
}
#[test]
fn probes_cover_folds_formulas_measures_and_groups() {
let hand = probes(&hand_model());
let has = |p: Probe| hand.contains(&p);
assert!(has(Probe::RawFold(partial("A", "Revenue"))));
assert!(has(Probe::Value(
key("East", "A", "Revenue"),
Aggregation::Exact
)));
assert!(has(Probe::Value(
partial("A", "Profit"),
Aggregation::Exact
)));
assert!(has(Probe::Value(
partial("A", "Profit"),
Aggregation::OverHidden
)));
assert!(has(Probe::Value(only_revenue(), Aggregation::OverHidden)));
assert!(has(Probe::RawFold(CellKey::new(vec![]))));
let grouped = probes(&grouped_model());
assert!(grouped.contains(&Probe::Value(coastal(), Aggregation::Exact)));
}
#[test]
fn an_edit_names_its_key_as_two_value_probes_and_a_fold() {
let k = key("East", "A", "Revenue");
let asked = improvise_incremental::edit_probes(&Edit::ClearCell(k.clone()));
assert!(asked.contains(&Probe::Value(k.clone(), Aggregation::Exact)));
assert!(asked.contains(&Probe::Value(k.clone(), Aggregation::OverHidden)));
assert!(asked.contains(&Probe::RawFold(k)));
let none = improvise_incremental::edit_probes(&Edit::SetMeasureAgg {
measure: "Revenue".into(),
func: AggFunc::Max,
});
assert!(none.is_empty());
}
/// An `Eager` rebuilt from scratch on every edit: maintaining one in place
/// must give the same answers as building it afresh.
struct Fresh {
model: Model,
none: Vec<String>,
eager: Eager,
}
impl Derived for Fresh {
fn value(&self, k: &CellKey, agg: Aggregation) -> Option<CellValue> {
self.eager.value(k, agg)
}
fn raw_fold(&self, p: &CellKey) -> Option<CellValue> {
self.eager.raw_fold(p)
}
}
impl Maintained for Fresh {
fn apply(&mut self, edit: &Edit) {
edit.apply(&mut self.model);
self.eager = Eager::new(self.model.clone(), self.none.clone());
}
}
fn any_key() -> impl Strategy<Value = CellKey> {
(
prop::sample::select(vec!["East", "West"]),
prop::sample::select(vec!["A", "B"]),
prop::sample::select(vec!["Revenue", "Cost", "Note"]),
)
.prop_map(|(r, p, m)| key(r, p, m))
}
fn any_value() -> impl Strategy<Value = CellValue> {
prop_oneof![
(-4i32..5).prop_map(|n| CellValue::Number(f64::from(n))),
Just(CellValue::Number(-0.0)),
prop::sample::select(vec!["n", "x"]).prop_map(|t| CellValue::Text(t.into())),
]
}
fn any_edit() -> impl Strategy<Value = Edit> {
prop_oneof![
(any_key(), any_value()).prop_map(|(k, v)| Edit::SetCell(k, v)),
any_key().prop_map(Edit::ClearCell),
prop::sample::select(vec!["Profit = Revenue - Cost", "Double = Revenue * 2"])
.prop_map(|raw| Edit::AddFormula(parse_formula(raw, "_Measure").unwrap())),
prop::sample::select(vec!["Profit", "Double"]).prop_map(|t| Edit::RemoveFormula {
target: t.into(),
target_category: "_Measure".into(),
}),
(
prop::sample::select(vec!["Revenue", "Cost"]),
prop::sample::select(vec![AggFunc::Sum, AggFunc::Max, AggFunc::Min, AggFunc::Avg]),
)
.prop_map(|(m, func)| Edit::SetMeasureAgg {
measure: m.into(),
func,
}),
]
}
proptest! {
#[test]
fn a_maintained_eager_equals_a_fresh_one_over_random_edit_sequences(
edits in prop::collection::vec(any_edit(), 0..4)
) {
let model = hand_model();
let none = vec!["Region".to_string()];
let fresh = Fresh {
model: model.clone(),
none: none.clone(),
eager: Eager::new(model.clone(), none.clone()),
};
let run = differential(&model, &none, fresh, &edits);
prop_assert!(run.is_ok(), "{}", run.unwrap_err());
}
}