batchCooking/apps/api/test/tech-step-matcher.test.ts

import { expect } from "chai";
import { prisma } from "../src/db/prisma.js";
import {
  type TechStepMappingRule,
  loadTechStepMappingRules,
  matchTechStep,
  normalizeText,
} from "../src/lib/tech-step-matcher.js";
import { resetDatabase } from "../test-support/reset-db.js";

describe("tech-step-matcher", () => {
  describe("normalizeText", () => {
    it("lowercases and strips accents", () => {
      expect(normalizeText("Déglacer AU FOUR")).to.equal("deglacer au four");
    });

    it("strips a variety of diacritics, including cedilla", () => {
      expect(normalizeText("Façon Œuf à l'Étouffée")).to.equal("facon œuf a l'etouffee");
    });

    it("leaves already-plain text unchanged, aside from casing", () => {
      expect(normalizeText("Mix everything")).to.equal("mix everything");
    });

    it("returns an empty string for an empty input", () => {
      expect(normalizeText("")).to.equal("");
    });
  });

  describe("matchTechStep", () => {
    const simmer: TechStepMappingRule = {
      techStepId: 1,
      expression: "\\bmijot(er|ez|e|ant|é)\\b",
      weight: 15,
    };
    const cook: TechStepMappingRule = {
      techStepId: 2,
      expression: "\\bcui(re|sez|sant|sson)\\b|\\bcuit(e|es|s)?\\b",
      weight: 10,
    };
    const bake: TechStepMappingRule = {
      techStepId: 3,
      expression:
        "\\bcuire au four\\b|\\bcuisson au four\\b|\\benfourn(er|ez|é|ée|ées)\\b|\\bau four\\b",
      weight: 25,
    };

    it("matches an exact expression", () => {
      expect(matchTechStep("Faire mijoter à feu doux", [simmer])).to.equal(1);
    });

    it("is case- and accent-insensitive, on both the description and the expression itself", () => {
      // `simmer`'s own expression source contains a literal "é" — exercises
      // normalizeText being applied to the expression, not just the description.
      expect(matchTechStep("FAIRE MIJOTER", [simmer])).to.equal(1);
      expect(matchTechStep("faire mijote", [simmer])).to.equal(1);
    });

    it("returns null when nothing matches", () => {
      expect(matchTechStep("Servir immédiatement", [simmer, cook, bake])).to.be.null;
    });

    it("returns null for an empty mappings list", () => {
      expect(matchTechStep("Faire mijoter à feu doux", [])).to.be.null;
    });

    it("returns null for an empty description", () => {
      expect(matchTechStep("", [simmer, cook, bake])).to.be.null;
    });

    it("picks the highest-weight match when several mappings match", () => {
      // "Cuire au four" matches both `cook` (weight 10) and `bake` (weight 25).
      expect(matchTechStep("Cuire au four pendant 30 minutes", [cook, bake])).to.equal(3);
      // Order-independent.
      expect(matchTechStep("Cuire au four pendant 30 minutes", [bake, cook])).to.equal(3);
    });

    it("breaks a weight tie by lowest techStepId", () => {
      const a: TechStepMappingRule = { techStepId: 5, expression: "\\bmelanger\\b", weight: 10 };
      const b: TechStepMappingRule = { techStepId: 2, expression: "\\bmelanger\\b", weight: 10 };
      expect(matchTechStep("Mélanger les ingrédients", [a, b])).to.equal(2);
    });

    it("still resolves to one techStep when two of its own mappings both match", () => {
      const wholeWord: TechStepMappingRule = {
        techStepId: 7,
        expression: "\\bmijoter\\b",
        weight: 15,
      };
      const withAdverb: TechStepMappingRule = {
        techStepId: 7,
        expression: "\\bmijoter à feu doux\\b",
        weight: 15,
      };
      expect(matchTechStep("Faire mijoter à feu doux", [wholeWord, withAdverb])).to.equal(7);
    });

    it("respects word boundaries — a technique's verb embedded in a longer word doesn't false-positive", () => {
      // "recuire"/"précuit" contain "cuire"/"cuit" as a substring, but not as
      // a standalone word — the \b-anchored expression must not match them.
      expect(matchTechStep("Faire recuire la sauce", [cook])).to.be.null;
      expect(matchTechStep("Un plat précuit", [cook])).to.be.null;
      // The standalone forms still match.
      expect(matchTechStep("Faire cuire la sauce", [cook])).to.equal(2);
      expect(matchTechStep("Le riz est cuit", [cook])).to.equal(2);
    });
  });

  describe("loadTechStepMappingRules", () => {
    beforeEach(async () => {
      await resetDatabase();
    });

    after(async () => {
      await prisma.$disconnect();
    });

    it("only returns mappings for the requested locale", async () => {
      const simmer = await prisma.techStep.findFirstOrThrow({ where: { key: "simmer" } });
      await prisma.techStepMapping.create({
        data: { techStepId: simmer.id, locale: "en", expression: "\\bsimmer\\b", weight: 15 },
      });

      // The seeded catalog (25 "fr" mappings) must be untouched by the extra
      // "en" row — same count, and none of them carry the English expression.
      const frRules = await loadTechStepMappingRules("fr");
      expect(frRules).to.have.length(25);
      expect(frRules.map((rule) => rule.expression)).to.not.include("\\bsimmer\\b");

      const enRules = await loadTechStepMappingRules("en");
      expect(enRules).to.deep.equal([
        { techStepId: simmer.id, expression: "\\bsimmer\\b", weight: 15 },
      ]);
    });

    it("returns an empty list for a locale with no mappings at all", async () => {
      expect(await loadTechStepMappingRules("de")).to.deep.equal([]);
    });
  });
});