batchCooking/apps/api/src/sources/quitoque.ts

import type {
  ParsedRecipe,
  RecipeSourceAdapter,
  RecipeSourceListItem,
  RecipeSourceListParams,
  RecipeSourceListResult,
} from "../lib/recipe-sources/recipe-source-adapter.js";
import {
  RecipeSourceFetchError,
  RecipeSourceParseError,
} from "../lib/recipe-sources/recipe-source-errors.js";
import { jsonLdRecipeAdapter } from "./json-ld-recipe.js";

const SOURCE_KEY = "quitoque";
const SITE_ORIGIN = "https://www.quitoque.fr";
const LIST_URL = `${SITE_ORIGIN}/recettes`;

/** One recipe card scraped off a quitoque.fr `/recettes` listing page — see {@link extractRecipeCards}. */
interface QuitoqueCard {
  url: string;
  title: string;
  image: string | null;
}

/**
 * Scrapes every recipe card out of a quitoque.fr `/recettes` listing page.
 * There's no `ItemList` JSON-LD to lean on (unlike marmiton.ts) — but each
 * card is a single `<a class="card__content_header" href="/recettes/…">`
 * wrapping its own `<img>`, so no "nearest preceding image" pairing is
 * needed (unlike 750g.ts). The real image URL is the `<img>`'s `data-src`
 * (a lazy-load attribute); its `src` is only a placeholder. `href` is a
 * root-relative path, resolved against {@link SITE_ORIGIN} here so callers
 * get a canonical absolute URL.
 *
 * Attribute-order-agnostic: matches every `<a>…</a>`, keeps the ones whose
 * `class` contains `card__content_header`, and reads `href`/`alt`/`data-src`
 * wherever they sit.
 */
function extractRecipeCards(html: string): QuitoqueCard[] {
  const cards: QuitoqueCard[] = [];
  const anchorPattern = /<a\s+([^>]*?)>([\s\S]*?)<\/a>/g;
  for (const match of html.matchAll(anchorPattern)) {
    const attrs = match[1] ?? "";
    if (!/class="[^"]*\bcard__content_header\b[^"]*"/.test(attrs)) continue;
    const href = /\bhref="(\/recettes\/[^"]+)"/.exec(attrs)?.[1];
    if (href === undefined) continue;
    const inner = match[2] ?? "";
    const title = /\balt="([^"]*)"/.exec(inner)?.[1] ?? "";
    if (title.length === 0) continue;
    cards.push({
      url: `${SITE_ORIGIN}${href}`,
      title,
      image: /\bdata-src="([^"]+)"/.exec(inner)?.[1] ?? null,
    });
  }
  return cards;
}

/**
 * Re-labels a `RecipeSourceFetchError`/`RecipeSourceParseError` thrown by
 * the generic `jsonLdRecipeAdapter` (`sourceKey` `"jsonLdRecipe"`) as having
 * come from this adapter (`sourceKey` `"quitoque"`) — same reasoning as
 * marmiton.ts's identically-named helper: `fetchDetail`/`parse` are thin
 * wrappers around the generic adapter, but a caller reading `.sourceKey`
 * off a caught `RecipeSourceError` should see the source it asked about.
 * (Not factored out into a shared helper — 750g/manger-bouger each keep
 * their own copy too; three near-identical five-liners aren't worth a
 * module.)
 */
function rekeySourceError(err: unknown): unknown {
  if (err instanceof RecipeSourceFetchError) {
    return new RecipeSourceFetchError(SOURCE_KEY, err.message, { cause: err.cause });
  }
  if (err instanceof RecipeSourceParseError) {
    return new RecipeSourceParseError(SOURCE_KEY, err.message, { cause: err.cause });
  }
  return err;
}

/**
 * quitoque.fr — a French meal-kit company whose site publishes a large
 * browsable recipe catalogue (`/recettes`, ~2700 recipes). Unofficial
 * (`official: false`, same reasoning as jsonLdRecipeAdapter/marmiton/750g/
 * mangerBouger): no published API, this reads ordinary pages and the
 * schema.org JSON-LD they embed for search engines. `robots.txt` allows
 * `/recettes` (and lists `ClaudeBot`/`GPTBot`/`Google-Extended` explicitly
 * under `allow: /`).
 *
 * The thinnest kind of wrapper — like marmiton.ts, `fetchDetail`/`parse`
 * delegate straight to {@link jsonLdRecipeAdapter} (a quitoque.fr recipe
 * page's JSON-LD is a plain schema.org `Recipe`, the sole element of a
 * top-level array, which `findRecipeNode` already handles). Only `list()`
 * is site-specific: `/recettes?page=N` with a card scrape (see
 * {@link extractRecipeCards}). The site has no real free-text search, so a
 * `query` is a best-effort substring filter over each page's card titles
 * (same accepted gap 750g.ts documents for its own search).
 */
export const quitoqueAdapter: RecipeSourceAdapter<{ html: string; url: string }> = {
  key: SOURCE_KEY,
  name: "Quitoque",
  official: false,
  iconUrl: `${SITE_ORIGIN}/favicon.ico`,
  // Le contenu de quitoque.fr (noms, ingrédients, instructions) est en
  // français — détermine contre quel modèle/locale d'étiquettes
  // d'ingrédients translateRecipe (recipe-translation.ts) résout les
  // recettes de cette source lors d'une prévisualisation/d'un import.
  locale: "fr",

  async list(params: RecipeSourceListParams): Promise<RecipeSourceListResult> {
    try {
      // Curseur opaque = numéro de page suivant ; quitoque.fr pagine via
      // `?page=N` (page 1 implicite quand le paramètre est absent), même
      // esprit que marmiton.ts/750g.ts.
      const page = params.cursor ? Number(params.cursor) : 1;
      const query = (params.query ?? "").trim().toLowerCase();
      const listUrl = `${LIST_URL}${page > 1 ? `?page=${page}` : ""}`;

      let response: Response;
      try {
        response = await fetch(listUrl);
      } catch (cause) {
        throw new RecipeSourceFetchError(
          SOURCE_KEY,
          `Network error listing Quitoque recipes (${listUrl})`,
          { cause },
        );
      }
      if (!response.ok) {
        throw new RecipeSourceFetchError(
          SOURCE_KEY,
          `Quitoque responded ${response.status} (${listUrl})`,
        );
      }
      const html = await response.text();

      const rawCards = extractRecipeCards(html);
      const cards =
        query.length > 0
          ? rawCards.filter((card) => card.title.toLowerCase().includes(query))
          : rawCards;

      const items: RecipeSourceListItem[] = cards.map((card) => ({
        externalId: card.url,
        title: card.title,
        picture: card.image,
        url: card.url,
      }));

      // Une page qui ne renvoie **aucune** carte est le signal de fin
      // (même logique que marmiton.ts). Basé sur le nombre de cartes
      // brutes, pas filtrées : une page qui a des cartes mais dont aucune
      // ne matche `query` peut quand même avoir une suite qui matche.
      const nextCursor = rawCards.length > 0 ? String(page + 1) : null;

      return { items, nextCursor };
    } catch (err) {
      // Rethrown as-is (already keyed "quitoque" by whichever branch above
      // threw it) — this adapter's only caller (`sources.service.ts`)
      // already handles/logs failures centrally; this method just isn't
      // allowed a bare `async` body without a try/catch per the repo's
      // convention. Same reasoning as `marmiton.ts`/`750g.ts`.
      throw err;
    }
  },

  // `externalId` est directement l'URL canonique de la recette sur
  // quitoque.fr (renvoyée telle quelle par `list()` ci-dessus) — même
  // convention que `jsonLdRecipeAdapter.fetchDetail`, à qui cette méthode
  // délègue entièrement.
  async fetchDetail(externalId: string): Promise<{ html: string; url: string }> {
    try {
      return await jsonLdRecipeAdapter.fetchDetail(externalId);
    } catch (err) {
      // Pas un simple re-throw : `rekeySourceError` est le traitement utile
      // que ce point d'appel doit faire de l'erreur (relabelliser sa
      // `sourceKey`), conformément à la convention await/try-catch du repo.
      throw rekeySourceError(err);
    }
  },

  parse(raw: { html: string; url: string }): ParsedRecipe {
    try {
      return jsonLdRecipeAdapter.parse(raw);
    } catch (err) {
      throw rekeySourceError(err);
    }
  },
};