improvise/crates/improvise-incremental/tests/support/mod.rs

//! Fixtures the integration tests share: the shipped corpus and the hand-built models.
#![allow(dead_code)]

use improvise_core::formula::ast::AggFunc;
use improvise_core::formula::parse_formula;
use improvise_core::model::Aggregation;
use improvise_core::model::Model;
use improvise_core::model::cell::{CellKey, CellValue};
use improvise_core::view::{Axis, View};
use improvise_incremental::{Derived, Eager, Edit, Evaluation, Incremental, Maintained, Reading};
use proptest::prelude::*;
use std::path::Path;

pub type Doc = (String, Model, Vec<String>, Vec<View>);

pub fn key(region: &str, product: &str, measure: &str) -> CellKey {
    CellKey::new(vec![
        ("Region".into(), region.into()),
        ("Product".into(), product.into()),
        ("_Measure".into(), measure.into()),
    ])
}

/// Region is the None category. Revenue and Cost are numbers; Note is text,
/// unanimous under A and conflicting under B.
pub 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
}

pub fn corpus() -> Vec<Doc> {
    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());
                let views = wb.views.values().cloned().collect();
                out.push((format!("{file}:{name}"), wb.model.clone(), none, views));
            }
        }
    }
    out.push(("hand".into(), hand_model(), vec!["Region".into()], vec![]));
    let hidden = hidden_workbook();
    let views = hidden.views.values().cloned().collect();
    let none = none_of(&hidden);
    out.push(("hidden".into(), hidden.model, none, views));
    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.
pub 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
}

pub 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
}

pub fn coastal() -> CellKey {
    key("Coastal", "A", "Revenue")
}

/// Six categories, four of them None in the one view: the cell it draws
/// drops four coordinates of every stored key.
pub fn wide_workbook() -> improvise_core::workbook::Workbook {
    let mut wb = improvise_core::workbook::Workbook::new("wide");
    for c in ["C0", "C1", "C2", "C3", "C4"] {
        wb.add_category(c).unwrap();
        wb.add_item(c, "a").unwrap();
    }
    wb.add_item("C0", "b").unwrap();
    wb.add_item("_Measure", "Revenue").unwrap();
    for (c0, v) in [("a", 1.0), ("b", 2.0)] {
        let k = CellKey::new(vec![
            ("C0".into(), c0.into()),
            ("C1".into(), "a".into()),
            ("C2".into(), "a".into()),
            ("C3".into(), "a".into()),
            ("C4".into(), "a".into()),
            ("_Measure".into(), "Revenue".into()),
        ]);
        wb.model.set_cell(k, CellValue::Number(v));
    }
    let view = wb.active_view_mut();
    view.set_axis("C0", Axis::Row);
    view.set_axis("_Measure", Axis::Column);
    for c in ["C1", "C2", "C3", "C4"] {
        view.set_axis(c, Axis::None);
    }
    wb
}

/// The None categories of the active view, virtual ones included: the set an
/// `Eager` standing for that view is built with.
pub fn none_of(wb: &improvise_core::workbook::Workbook) -> Vec<String> {
    let none = wb.active_view().categories_on(Axis::None);
    none.into_iter().map(String::from).collect()
}

/// East is hidden and Coastal is collapsed (a group is, by default), so the Coastal row folds West only;
/// Inland has a cell under A only, so B's column holds just Coastal's.
pub fn hidden_workbook() -> improvise_core::workbook::Workbook {
    let mut wb = improvise_core::workbook::Workbook::new("hidden");
    for c in ["Region", "Product"] {
        wb.add_category(c).unwrap();
    }
    wb.add_item_in_group("Region", "East", "Coastal").unwrap();
    wb.add_item_in_group("Region", "West", "Coastal").unwrap();
    wb.add_item("Region", "Inland").unwrap();
    wb.add_item("Product", "A").unwrap();
    wb.add_item("Product", "B").unwrap();
    wb.add_item("_Measure", "Revenue").unwrap();
    let cells = [
        ("East", "A", 10.0),
        ("West", "A", 5.0),
        ("East", "B", 20.0),
        ("West", "B", 1.0),
        ("Inland", "A", 2.0),
    ];
    for (r, p, v) in cells {
        wb.model
            .set_cell(key(r, p, "Revenue"), CellValue::Number(v));
    }
    let view = wb.active_view_mut();
    view.set_axis("Region", Axis::Row);
    view.set_axis("Product", Axis::Column);
    view.set_axis("_Measure", Axis::None);
    view.hide_item("Region", "East");
    wb
}

/// Nothing is hidden and Margin is a ratio: the pooled total of Margin is
/// Revenue over Cost summed across the rows, which no single row's fold gives.
pub fn ratio_workbook() -> improvise_core::workbook::Workbook {
    let mut wb = improvise_core::workbook::Workbook::new("ratio");
    for c in ["Region", "Product"] {
        wb.add_category(c).unwrap();
    }
    wb.add_item("Region", "East").unwrap();
    wb.add_item("Region", "West").unwrap();
    wb.add_item("Product", "A").unwrap();
    for m in ["Revenue", "Cost"] {
        wb.add_item("_Measure", m).unwrap();
    }
    for (r, rev, cost) in [("East", 10.0, 4.0), ("West", 5.0, 2.0)] {
        wb.model
            .set_cell(key(r, "A", "Revenue"), CellValue::Number(rev));
        wb.model
            .set_cell(key(r, "A", "Cost"), CellValue::Number(cost));
    }
    wb.model
        .add_formula(parse_formula("Margin = Revenue / Cost", "_Measure").unwrap());
    let view = wb.active_view_mut();
    view.set_axis("Region", Axis::Row);
    view.set_axis("_Measure", Axis::Column);
    view.set_axis("Product", Axis::None);
    wb
}

/// [`hidden_workbook`] drawn with the measure on the columns and Product folded: its cells
/// carry a measure, so the measure's aggregation reaches every row, total and collapsed group.
pub fn hidden_counted_workbook() -> improvise_core::workbook::Workbook {
    let mut wb = hidden_workbook();
    let view = wb.active_view_mut();
    view.set_axis("Product", Axis::None);
    view.set_axis("_Measure", Axis::Column);
    wb
}

/// Formulas the random tests add and remove, as `(text, target category)`: chains, a cycle,
/// aggregates over expressions, filters, a ratio, and two that target Region.
pub const FORMULA_POOL: [(&str, &str); 21] = [
    ("Profit = Revenue - Cost", "_Measure"),
    ("Margin = Profit / Revenue", "_Measure"),
    ("Weighted = SUM(Revenue * Units)", "_Measure"),
    ("Share = Revenue / SUM(Revenue)", "_Measure"),
    ("Bonus = Revenue * 0.1 WHERE Region = East", "_Measure"),
    ("Flag = IF(Revenue > Cost, 1, 0)", "_Measure"),
    ("Loop = Loop + 1", "_Measure"),
    ("Ping = Pong + 1", "_Measure"),
    ("Pong = Ping + 1", "_Measure"),
    ("Peak = MAX(Revenue WHERE Product = A)", "_Measure"),
    ("Mix = Revenue * (Region IS East) + Cost", "_Measure"),
    ("Cnt = COUNT(Revenue)", "_Measure"),
    ("Inverse = 1 / Units", "_Measure"),
    ("Both = Profit + Cnt", "_Measure"),
    ("Total = East + West", "Region"),
    ("EastRev = Revenue", "Region"),
    ("Recip = Units ^ -1", "_Measure"),
    ("Pa = A + Revenue", "_Measure"),
    ("NegZero = -0", "_Measure"),
    ("Flip = Units * -1", "_Measure"),
    ("Negate = -Cost", "_Measure"),
];

pub fn formula_edit(index: usize) -> Edit {
    let (raw, category) = FORMULA_POOL[index];
    Edit::AddFormula(parse_formula(raw, category).unwrap())
}

pub fn unformula_edit(index: usize) -> Edit {
    let (raw, category) = FORMULA_POOL[index];
    Edit::RemoveFormula {
        target: parse_formula(raw, category).unwrap().target,
        target_category: category.into(),
    }
}

/// Two regions by one product by three measures, with `Profit` and `Margin`, drawn with
/// Region on the rows and the measure on the columns.
pub fn formula_workbook() -> improvise_core::workbook::Workbook {
    let mut wb = improvise_core::workbook::Workbook::new("formulas");
    for c in ["Region", "Product"] {
        wb.add_category(c).unwrap();
    }
    for r in ["East", "West"] {
        wb.add_item("Region", r).unwrap();
    }
    wb.add_item("Product", "A").unwrap();
    for m in ["Revenue", "Cost", "Units"] {
        wb.add_item("_Measure", m).unwrap();
    }
    let mut n = 1.0;
    for r in ["East", "West"] {
        for (m, scale) in [("Revenue", 10.0), ("Cost", 4.0), ("Units", 2.0)] {
            wb.model
                .set_cell(key(r, "A", m), CellValue::Number(scale * n));
            n += 1.0;
        }
    }
    let profit = parse_formula("Profit = Revenue - Cost", "_Measure").unwrap();
    wb.model.add_formula(profit);
    let margin = parse_formula("Margin = Profit / Revenue", "_Measure").unwrap();
    wb.model.add_formula(margin);
    let view = wb.active_view_mut();
    view.set_axis("Region", Axis::Row);
    view.set_axis("_Measure", Axis::Column);
    view.set_axis("Product", Axis::None);
    wb
}

pub fn bump(region: &str, product: &str, measure: &str, to: f64) -> Edit {
    Edit::SetCell(key(region, product, measure), CellValue::Number(to))
}

/// Both backends told every edit; their models, formula cache included, must print alike.
pub fn same_model(
    model: &Model,
    none: &[String],
    edits: &[Edit],
    by: Evaluation,
) -> Result<(), String> {
    let mut eager = Eager::new(model.clone(), none.to_vec());
    let mut incremental = Incremental::new(model.clone(), none.to_vec()).with_evaluation(by);
    for edit in edits {
        eager.apply(edit);
        incremental.apply(edit);
    }
    let (want, got) = (
        format!("{:?}", eager.model()),
        format!("{:?}", incremental.model()),
    );
    match want == got {
        true => Ok(()),
        false => Err(format!(
            "after {edits:?}:\n eager {want}\n incremental {got}"
        )),
    }
}

fn any_formula_value() -> impl Strategy<Value = CellValue> {
    prop_oneof![
        // No +0.0 beside -0.0: eager's Min and Max of both zeros is platform-defined.
        prop_oneof![-2i32..0, 1i32..4].prop_map(|n| CellValue::Number(f64::from(n))),
        Just(CellValue::Number(-0.0)),
        Just(CellValue::Number(f64::NAN)),
        prop::sample::select(vec![0.1, 1e16, -1e16]).prop_map(CellValue::Number),
        Just(CellValue::Text("t".into())),
    ]
}

/// An edit to the formula fixture: a cell written or cleared (a region and a product the
/// fixture lacks included), a formula from the pool added or removed, or a new aggregation.
pub fn any_formula_edit() -> impl Strategy<Value = Edit> {
    let regions = prop::sample::select(vec!["East", "West", "North"]);
    let products = prop::sample::select(vec!["A", "B", "C"]);
    let measures = prop::sample::select(vec!["Revenue", "Cost", "Units", "Loop", "Pong", "Pa"]);
    let at = (regions, products, measures);
    let funcs = vec![
        AggFunc::Sum,
        AggFunc::Avg,
        AggFunc::Min,
        AggFunc::Max,
        AggFunc::Count,
    ];
    let aggregated = (
        prop::sample::select(vec!["Revenue", "Cost", "Units"]),
        prop::sample::select(funcs),
    );
    prop_oneof![
        3 => (at.clone(), any_formula_value()).prop_map(|((r, p, m), v)| Edit::SetCell(key(r, p, m), v)),
        2 => at.prop_map(|(r, p, m)| Edit::ClearCell(key(r, p, m))),
        2 => (0..FORMULA_POOL.len()).prop_map(formula_edit),
        1 => (0..FORMULA_POOL.len()).prop_map(unformula_edit),
        1 => aggregated.prop_map(|(m, func)| Edit::SetMeasureAgg { measure: m.into(), func }),
    ]
}

/// The same edits told to a backend that evaluates in dependency order and to one that runs
/// eager's passes: models, cache and zero signs must print alike after every edit.
pub fn same_orders(model: &Model, none: &[String], edits: &[Edit]) -> Result<(), String> {
    let side = |by| Incremental::new(model.clone(), none.to_vec()).with_evaluation(by);
    let (mut ordered, mut plain) = (side(Evaluation::Ordered), side(Evaluation::Plain));
    for (n, edit) in edits.iter().enumerate() {
        ordered.apply(edit);
        plain.apply(edit);
        let (want, got) = (
            format!("{:?}", plain.model()),
            format!("{:?}", ordered.model()),
        );
        if want != got {
            let told = &edits[..=n];
            return Err(format!("after {told:?}:\n plain {want}\n ordered {got}"));
        }
    }
    Ok(())
}

/// An `Eager` rebuilt from scratch on every edit: maintaining one in place
/// must give the same answers as building it afresh.
pub struct Fresh {
    pub model: Model,
    pub none: Vec<String>,
    pub 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)
    }

    fn covered(&self, k: &CellKey, r: &Reading) -> Option<CellValue> {
        self.eager.covered(k, r)
    }

    fn total(&self, k: &CellKey, over: &[String], r: &Reading) -> Option<CellValue> {
        self.eager.total(k, over, r)
    }

    fn occupancy(&self, p: &CellKey, r: &Reading) -> usize {
        self.eager.occupancy(p, r)
    }
}

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());
    }
}

pub 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))
}

pub 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())),
    ]
}

pub 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,
            }),
    ]
}