numolus/src/engine/workbook.ts

/**
 * Framework-agnostic spreadsheet model that ties the engine modules together.
 *
 * The addressable unit is a **table** (a table object on a Numbers-style
 * canvas). A `Workbook` owns a flat list of tables and, across all of them:
 *   - the raw text of every non-empty cell,
 *   - the parsed AST of every formula cell (or an `#ERR` marker),
 *   - the computed value of every cell,
 *   - the document-wide {@link DependencyGraph}.
 *
 * It implements {@link EngineHost} so the evaluator can read neighbouring cell
 * values through it. The Vue store wraps an instance of this class in `reactive`
 * and mirrors its computed values into a reactive map, which makes every formula
 * cell behave like a `computed` value in the UI.
 *
 * Recalculation is incremental: `setCell` reparses one cell, updates its graph
 * edges and recomputes only the affected sub-graph in topological order.
 * Structural edits (rename / delete table, add rows, ...) call `rebuild()` for a
 * full, still-cheap pass.
 */

import { DependencyGraph } from './graph';
import { collectRefs, parseFormula, type Node } from './parser';
import { rangeCells } from './refs';
import { parseDateTimeLiteral } from './dates';
import { buildFunctionIndex, expandUserFunctions, type FunctionDef } from './userFunctions';
import {
  FormulaError,
  isError,
  keyOf,
  parseKey,
  type CellRef,
  type CellValue,
  type EngineHost,
  type NamedRangeDef,
} from './types';
import { evaluate } from './evaluator';

export interface TableModel {
  id: string;
  /** table name, used as the qualifier in formulas -- unique *per sheet*
   *  only; the same name may occur on more than one sheet (see
   *  `sheetName` and {@link EngineHost.resolveTableName}). */
  name: string;
  /** name of the sheet this table lives on. */
  sheetName: string;
  cols: number;
  rows: number;
  /** key `${col},${row}` -> raw user input. Absent = empty cell. */
  inputs: Map<string, string>;
}

const NUMBER_RE = /^[+-]?(\d+\.?\d*|\.\d+)([eE][+-]?\d+)?$/;

function localKey(col: number, row: number): string {
  return `${col},${row}`;
}

/** Interpret a raw literal (non-formula) cell input. A recognized date/time
 *  (see dates.ts's parseDateTimeLiteral) becomes its serial number -- dates
 *  are just numbers in this engine, so `+`/`-`/comparisons work on them for
 *  free. Checked before NUMBER_RE; the two never collide (dates use `-`/`.`
 *  multi-part separators or `:`, which NUMBER_RE's single-decimal-point
 *  shape never matches). */
export function literalValue(raw: string): CellValue {
  const t = raw.trim();
  if (t === '') return null;
  const dt = parseDateTimeLiteral(t);
  if (dt) return dt.serial;
  if (NUMBER_RE.test(t)) return Number(t);
  return raw;
}

export class Workbook implements EngineHost {
  tables: TableModel[];
  /** transiently set to the home table while a formula is being evaluated */
  homeTableId = '';

  private readonly graph = new DependencyGraph();
  /** cellKey -> parsed formula AST, or an error marker for un-parsable input */
  private readonly asts = new Map<string, Node | FormulaError>();
  /** cellKey -> computed value */
  private readonly values = new Map<string, CellValue>();
  /** user-defined function library for this document, name.toUpperCase() -> def. */
  private readonly functionIndex: Map<string, FunctionDef>;
  /** document-wide named ranges (see NamedRangeDef's doc comment). */
  private readonly namedRanges: NamedRangeDef[];

  constructor(
    tables: TableModel[],
    functionDefs: FunctionDef[] = [],
    namedRanges: NamedRangeDef[] = [],
  ) {
    this.tables = tables;
    this.functionIndex = buildFunctionIndex(functionDefs);
    this.namedRanges = namedRanges;
    this.rebuild();
  }

  // ---- EngineHost ---------------------------------------------------------

  resolveTableName(name: string, sheetName?: string | null): string | null {
    const needle = name.trim().toLowerCase();
    const candidates = this.tables.filter((t) => t.name.trim().toLowerCase() === needle);
    if (candidates.length === 0) return null;

    if (sheetName != null) {
      const sheetNeedle = sheetName.trim().toLowerCase();
      const hit = candidates.find((t) => t.sheetName.trim().toLowerCase() === sheetNeedle);
      return hit ? hit.id : null;
    }
    if (candidates.length === 1) return candidates[0].id;

    // ambiguous (same name on more than one sheet) -- prefer a table on the
    // same sheet as the formula doing the referencing, if there is one
    const home = this.tableById(this.homeTableId);
    if (home) {
      const sameSheet = candidates.find((t) => t.sheetName === home.sheetName);
      if (sameSheet) return sameSheet.id;
    }
    return null; // still ambiguous -> #REF, needs an explicit sheet qualifier
  }

  resolveNamedRange(
    name: string,
  ): { qualifier: string; sheetQualifier?: string; start: { col: number; row: number }; end: { col: number; row: number } } | null {
    const needle = name.trim().toLowerCase();
    const def = this.namedRanges.find((d) => d.name.trim().toLowerCase() === needle);
    if (!def) return null;
    const table = this.tableById(def.tableId);
    if (!table) return null; // target table was since deleted -- #NAME?, same as a stale table rename
    return { qualifier: table.name, sheetQualifier: table.sheetName, start: def.start, end: def.end };
  }

  tableSize(tableId: string): { cols: number; rows: number } | null {
    const t = this.tableById(tableId);
    return t ? { cols: t.cols, rows: t.rows } : null;
  }

  getComputed(tableId: string, col: number, row: number): CellValue {
    if (col < 0 || row < 0) return new FormulaError('#REF');
    const v = this.values.get(keyOf(tableId, col, row));
    return v === undefined ? null : v;
  }

  // ---- reads ------------------------------------------------------------

  tableById(id: string): TableModel | undefined {
    return this.tables.find((t) => t.id === id);
  }

  getInput(tableId: string, col: number, row: number): string {
    return this.tableById(tableId)?.inputs.get(localKey(col, row)) ?? '';
  }

  /** Public computed-value read used by the store / UI. */
  cellValue(tableId: string, col: number, row: number): CellValue {
    const v = this.values.get(keyOf(tableId, col, row));
    return v === undefined ? null : v;
  }

  /** Direct precedents of a cell -- the cells its own formula reads (a
   *  formula's `#REF`/named-range/etc. resolution already baked into the
   *  graph edges, see `precedentsOf()` above). Public wrapper around the
   *  internal `DependencyGraph`, for UI features (the dependency-graph
   *  view) that need to *query* the graph -- evaluation itself never calls
   *  this, it only calls `setPrecedents`/`affected`/`topoOrder`. */
  graphPrecedents(tableId: string, col: number, row: number): CellRef[] {
    return [...this.graph.getPrecedents(keyOf(tableId, col, row))].map(parseKey);
  }
  /** Direct dependents of a cell -- every cell whose formula reads *this*
   *  one. See graphPrecedents() above. */
  graphDependents(tableId: string, col: number, row: number): CellRef[] {
    return [...this.graph.getDependents(keyOf(tableId, col, row))].map(parseKey);
  }

  // ---- writes ---------------------------------------------------------

  /** Set (or clear, with `''`) one cell and recalculate the affected cells. */
  setCell(tableId: string, col: number, row: number, raw: string): void {
    const table = this.tableById(tableId);
    if (!table) return;
    const lk = localKey(col, row);
    if (raw === '') table.inputs.delete(lk);
    else table.inputs.set(lk, raw);

    const key = keyOf(tableId, col, row);
    this.parseCell(key, tableId, raw);
    this.recalc([key]);
  }

  /** Reparse every formula, rebuild the graph, recompute everything. */
  rebuild(): void {
    this.graph.reset();
    this.asts.clear();
    const all: string[] = [];
    for (const table of this.tables) {
      for (const [lk, raw] of table.inputs) {
        const [c, r] = lk.split(',').map(Number);
        const key = keyOf(table.id, c, r);
        all.push(key);
        this.parseCell(key, table.id, raw);
      }
    }
    this.recalcAll(all);
  }

  // ---- internals ------------------------------------------------------

  /** Parse one cell's raw input and (re)wire its graph edges. */
  private parseCell(key: string, tableId: string, raw: string): void {
    if (!raw.startsWith('=')) {
      this.asts.delete(key);
      this.graph.clear(key);
      return;
    }
    let ast: Node;
    try {
      ast = parseFormula(raw);
      ast = expandUserFunctions(ast, this.functionIndex);
    } catch (e) {
      // a bad formula is a cell-level error, never a crash
      this.asts.set(key, new FormulaError('#ERR', (e as Error).message));
      this.graph.setPrecedents(key, []);
      return;
    }
    this.asts.set(key, ast);
    this.graph.setPrecedents(key, this.precedentsOf(ast, tableId));
  }

  /** Resolve every reference in `ast` to concrete cell keys (home = tableId). */
  private precedentsOf(ast: Node, tableId: string): string[] {
    // resolveTableName()'s "prefer the home sheet" ambiguity fallback reads
    // this.homeTableId -- set it here too (not just in evaluateCell) so graph
    // edges are wired using the *same* resolution an evaluation would use.
    this.homeTableId = tableId;
    const out: string[] = [];
    for (const ref of collectRefs(ast)) {
      // a named range isn't itself a qualifier/coords pair -- resolve it to
      // one first (same shape as a 'cell'/'range' ref), then fall through to
      // the identical edge-wiring below.
      const resolved = ref.kind === 'namedref' ? this.resolveNamedRange(ref.name) : ref;
      if (!resolved) continue; // unknown name -> no edge; evaluator emits #NAME?
      const target =
        resolved.qualifier == null
          ? tableId
          : this.resolveTableName(resolved.qualifier, resolved.sheetQualifier ?? null);
      if (!target) continue; // unknown table -> no edge; evaluator emits #REF
      if ('col' in resolved) {
        out.push(keyOf(target, resolved.col, resolved.row));
      } else {
        for (const c of rangeCells(resolved, this.tableSize(target))) {
          out.push(keyOf(target, c.col, c.row));
        }
      }
    }
    return out;
  }

  /** Incremental recalculation starting from `dirty`. */
  private recalc(dirty: string[]): void {
    this.evaluateSet(this.graph.affected(dirty));
  }

  /** Full recalculation of the given (complete) cell set. */
  private recalcAll(all: string[]): void {
    this.values.clear();
    this.evaluateSet(new Set(all));
  }

  private evaluateSet(affected: Set<string>): void {
    const { order, circular } = this.graph.topoOrder(affected);
    for (const key of circular) this.values.set(key, new FormulaError('#CIRC'));
    for (const key of order) this.values.set(key, this.evaluateCell(key));
  }

  private evaluateCell(key: string): CellValue {
    const ast = this.asts.get(key);
    if (ast === undefined) {
      const { tableId, col, row } = parseKey(key);
      return literalValue(this.getInput(tableId, col, row));
    }
    if (isError(ast)) return ast;
    this.homeTableId = parseKey(key).tableId;
    try {
      return evaluate(ast, this);
    } catch {
      return new FormulaError('#ERR', 'evaluation failed');
    }
  }

  /** Recompute order for a hand-picked dirty set -- exposed for tests. */
  debugOrder(dirty: string[]): { order: string[]; circular: string[] } {
    const { order, circular } = this.graph.topoOrder(this.graph.affected(dirty));
    return { order, circular: [...circular] };
  }
}