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

import { expect } from "chai";
import { prisma } from "../../src/db/prisma.js";
import {
  loadTechStepMappingRules,
  matchTechStepSpans,
  matchTechSteps,
  normalizeText,
  type TechStepMappingRule,
} from "../../src/lib/recipe-matching/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("matchTechSteps", () => {
    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,
    };
    const preheat: TechStepMappingRule = {
      techStepId: 4,
      expression: "\\bpr[ée]chauff(er|ez|é|ée)\\b",
      weight: 20,
    };
    const melt: TechStepMappingRule = {
      techStepId: 5,
      expression: "\\bfondre\\b|\\bfaire fondre\\b|\\bfaites fondre\\b",
      weight: 15,
    };

    it("matches an exact expression", () => {
      expect(matchTechSteps("Faire mijoter à feu doux", [simmer])).to.deep.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(matchTechSteps("FAIRE MIJOTER", [simmer])).to.deep.equal([1]);
      expect(matchTechSteps("faire mijote", [simmer])).to.deep.equal([1]);
    });

    it("returns an empty sequence when nothing matches", () => {
      expect(matchTechSteps("Servir immédiatement", [simmer, cook, bake])).to.deep.equal([]);
    });

    it("returns an empty sequence for an empty mappings list", () => {
      expect(matchTechSteps("Faire mijoter à feu doux", [])).to.deep.equal([]);
    });

    it("returns an empty sequence for an empty description", () => {
      expect(matchTechSteps("", [simmer, cook, bake])).to.deep.equal([]);
    });

    it("detects several distinct, non-overlapping techniques as an ordered sequence", () => {
      // The motivating case: "Dans une poêle chaude, faire chauffer une noix
      // de beurre" involves both preheating and melting — a step can name
      // more than one technique, in the order they're mentioned.
      expect(
        matchTechSteps("Préchauffer la poêle, puis faire fondre le beurre", [preheat, melt]),
      ).to.deep.equal([4, 5]);
      // Order in the output follows order of mention in the text, not
      // argument order.
      expect(
        matchTechSteps("Préchauffer la poêle, puis faire fondre le beurre", [melt, preheat]),
      ).to.deep.equal([4, 5]);
    });

    it("reverses the sequence when the techniques are mentioned in the opposite order", () => {
      expect(
        matchTechSteps("Faire fondre le beurre puis préchauffer le four", [preheat, melt]),
      ).to.deep.equal([5, 4]);
    });

    it("keeps only the highest-weight technique when two different techniques' expressions overlap the same words", () => {
      // "Cuire au four" matches both `cook` (weight 10) and `bake` (weight
      // 25) at essentially the same span — only the more specific `bake`
      // should survive, not both.
      expect(matchTechSteps("Cuire au four pendant 30 minutes", [cook, bake])).to.deep.equal([3]);
      // Order-independent.
      expect(matchTechSteps("Cuire au four pendant 30 minutes", [bake, cook])).to.deep.equal([3]);
    });

    it("still keeps a non-overlapping technique alongside an overlap-resolved one", () => {
      // `bake` wins over `cook` for "cuire au four" (overlap), but `melt`
      // matches an entirely different, non-overlapping span and survives.
      const result = matchTechSteps("Faire fondre le beurre, puis cuire au four", [
        cook,
        bake,
        melt,
      ]);
      expect(result).to.deep.equal([5, 3]);
    });

    it("breaks a same-span 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(matchTechSteps("Mélanger les ingrédients", [a, b])).to.deep.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(matchTechSteps("Faire mijoter à feu doux", [wholeWord, withAdverb])).to.deep.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(matchTechSteps("Faire recuire la sauce", [cook])).to.deep.equal([]);
      expect(matchTechSteps("Un plat précuit", [cook])).to.deep.equal([]);
      // The standalone forms still match.
      expect(matchTechSteps("Faire cuire la sauce", [cook])).to.deep.equal([2]);
      expect(matchTechSteps("Le riz est cuit", [cook])).to.deep.equal([2]);
    });
  });

  describe("matchTechStepSpans", () => {
    // Same fixtures as `matchTechSteps` above (kept local to this describe
    // block rather than shared — each block's fixtures should be readable
    // on their own).
    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,
    };
    const preheat: TechStepMappingRule = {
      techStepId: 4,
      expression: "\\bpr[ée]chauff(er|ez|é|ée)\\b",
      weight: 20,
    };
    const melt: TechStepMappingRule = {
      techStepId: 5,
      expression: "\\bfondre\\b|\\bfaire fondre\\b|\\bfaites fondre\\b",
      weight: 15,
    };

    it("returns the matched span alongside the techStepId for a simple match", () => {
      // "Faire mijoter à feu doux" — "mijoter" starts right after "Faire ".
      expect(matchTechStepSpans("Faire mijoter à feu doux", [simmer])).to.deep.equal([
        { techStepId: 1, start: 6, end: 13 },
      ]);
    });

    it("returns an empty list when nothing matches", () => {
      expect(matchTechStepSpans("Servir immédiatement", [simmer, cook, bake])).to.deep.equal([]);
    });

    it("returns each distinct technique's own span, in reading order", () => {
      const text = "Préchauffer la poêle, puis faire fondre le beurre";
      const result = matchTechStepSpans(text, [preheat, melt]);
      expect(result).to.have.length(2);
      expect(result[0].techStepId).to.equal(4);
      expect(result[1].techStepId).to.equal(5);
      // Each span, sliced back out of the original text, is exactly the
      // word(s) that triggered that match — what the frontend needs to
      // highlight the right characters.
      expect(text.slice(result[0].start, result[0].end).toLowerCase()).to.equal("préchauffer");
      expect(text.slice(result[1].start, result[1].end).toLowerCase()).to.equal("faire fondre");
    });

    it("keeps only the winning span when two techniques' expressions overlap", () => {
      // `bake` (weight 25) wins over `cook` (weight 10) for "cuire au four"
      // — only bake's span survives, not two overlapping entries.
      const text = "Cuire au four pendant 30 minutes";
      const result = matchTechStepSpans(text, [cook, bake]);
      expect(result).to.deep.equal([{ techStepId: 3, start: 0, end: 13 }]);
      expect(text.slice(0, 13)).to.equal("Cuire au four");
    });
  });

  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" } });
      // "de" has no seeded mappings at all (unlike "fr"/"en", which the
      // real catalog now both populate) — a clean locale to attach one
      // synthetic row to without conflating it with real seed data.
      await prisma.techStepMapping.create({
        data: { techStepId: simmer.id, locale: "de", expression: "\\bsimmer\\b", weight: 15 },
      });

      // The seeded catalog (26 "fr" mappings) must be untouched by the extra
      // "de" row — same count, and none of them carry its expression.
      const frRules = await loadTechStepMappingRules("fr");
      expect(frRules).to.have.length(26);
      expect(frRules.map((rule) => rule.expression)).to.not.include("\\bsimmer\\b");

      const deRules = await loadTechStepMappingRules("de");
      expect(deRules).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([]);
    });
  });
});