batchCooking/apps/api/src/sources/manger-bouger.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 = "mangerBouger";

// "La Fabrique à Menus" — mangerbouger.fr's recipe tool (Santé publique
// France). Its listing page is a Next.js app with no JSON-LD `ItemList` at
// all (unlike marmiton.ts's search page) — but it's server-rendered, and a
// plain GET carries the exact same Redux state the client hydrates from as
// a `__NEXT_DATA__` script tag (see `extractNextData` below), which already
// has everything `list()` needs. Verified live: `?query=<free text>` really
// filters server-side (not just a client-side URL update over an
// already-fetched page), and `page`/`hasMorePages` behave as real,
// consistent pagination — the best-behaved of this adapter family's three
// sources on that front.
const LIST_URL = "https://www.mangerbouger.fr/manger-mieux/la-fabrique-a-menus/recettes";
const DETAIL_BASE_URL = "https://www.mangerbouger.fr/manger-mieux/la-fabrique-a-menus/recettes/";

/** Matches the `<script id="__NEXT_DATA__">…</script>` block every Next.js page ships — the site's own server-rendered hydration data, read instead of scraping HTML for both `list()` (the listing's recipe cards) and `parse()` (backfilling a gap in the detail page's JSON-LD, see {@link extractPortionsFromNextData}). */
const NEXT_DATA_PATTERN = /<script id="__NEXT_DATA__"[^>]*>([\s\S]*?)<\/script>/;

/** The one field of one `list[]` entry `list()` actually reads off the listing page's `__NEXT_DATA__` — that state carries the site's full internal `Recipe` shape (60+ fields: nutriscore, seasons, macros, …), none of which this adapter's contract has anywhere to put. */
interface MangerBougerListEntry {
  slug?: string;
  name?: string;
  image?: string | null;
}

/** The slice of `__NEXT_DATA__` this module reads off the *listing* page. */
interface MangerBougerListPageData {
  props?: {
    initialState?: {
      recipes?: {
        list?: MangerBougerListEntry[];
        /** Whether a further page exists for the current `page`/`query`/`diet` combination — verified live: an out-of-range page comes back `false` with an empty `list` rather than repeating the last page or erroring, a cleaner end-of-results signal than either `marmiton.ts` (infers it from a 404) or `750g.ts` (this search has no real pagination at all). */
        hasMorePages?: boolean;
      };
    };
  };
}

/** The slice of `__NEXT_DATA__` this module reads off a recipe *detail* page — a different shape than the listing page's (`initialState.recipe.recipe`, not `initialState.recipes.list[]`) since it's a different Redux slice entirely. */
interface MangerBougerDetailPageData {
  props?: {
    initialState?: {
      recipe?: {
        recipe?: {
          portions?: unknown;
        };
      };
    };
  };
}

/** Parses the page's `__NEXT_DATA__` block into `T`, or `null` if the block is missing or isn't valid JSON — callers degrade gracefully rather than throw, same as `marmiton.ts`'s "page has no ItemList at all" handling. */
function extractNextData<T>(html: string): T | null {
  const match = html.match(NEXT_DATA_PATTERN);
  if (!match) return null;
  try {
    return JSON.parse(match[1] ?? "") as T;
  } catch {
    return null;
  }
}

function detailUrl(slug: string): string {
  return `${DETAIL_BASE_URL}${slug}`;
}

/**
 * Matches the single `<script type="application/ld+json">…</script>` block
 * a mangerbouger.fr recipe *detail* page carries (verified live across a
 * sample of 9 recipes — always exactly one, always a bare `Recipe`, never
 * an `@graph`) — a much narrower pattern than `json-ld-recipe.ts`'s own
 * `JSON_LD_SCRIPT_PATTERN` (no `g` flag: this module only ever needs the
 * first/only block, to patch it — see {@link patchRecipeJsonLd}) or
 * `750g.ts`'s identically-named private copy (which does its own,
 * different, character-level repair over every block on the page).
 */
const JSON_LD_SCRIPT_PATTERN =
  /(<script[^>]*type\s*=\s*["']application\/ld\+json["'][^>]*>)([\s\S]*?)(<\/script>)/i;

/** One node of a Slate.js rich-text document — see {@link flattenSlateDocument}. */
interface SlateNode {
  type?: string;
  text?: string;
  children?: SlateNode[];
}

/** Concatenates a run of inline Slate nodes (leaf text, or further-nested inline runs) with no separator — bold/italic/underline marks (the only ones observed) carry no plain-text equivalent and are simply dropped. */
function flattenSlateInline(nodes: SlateNode[]): string {
  return nodes
    .map((node) =>
      typeof node.text === "string"
        ? node.text
        : node.children
          ? flattenSlateInline(node.children)
          : "",
    )
    .join("");
}

/**
 * Flattens a Slate.js document's top-level blocks into one line of plain
 * text each — verified live across every recipe step sampled (72 recipes):
 * only `paragraph` and `bulleted-list` (of `list-item`s) ever appear as
 * block types, so that's all this handles; any other/unrecognized block
 * type still degrades reasonably (its own children read as one inline run)
 * rather than being dropped outright.
 */
function flattenSlateBlocks(nodes: SlateNode[]): string[] {
  const lines: string[] = [];
  for (const node of nodes) {
    if (node.type === "bulleted-list" && node.children) {
      lines.push(...flattenSlateBlocks(node.children));
      continue;
    }
    if (node.type === "list-item" && node.children) {
      const text = flattenSlateInline(node.children);
      if (text.trim().length > 0) lines.push(`- ${text}`);
      continue;
    }
    if (node.children) {
      const text = flattenSlateInline(node.children);
      if (text.trim().length > 0) lines.push(text);
      continue;
    }
    if (typeof node.text === "string" && node.text.trim().length > 0) lines.push(node.text);
  }
  return lines;
}

/**
 * Flattens one `HowToStep.text` value into plain text. mangerbouger.fr's
 * own JSON-LD embeds this field pre-formatted for its own web app instead
 * of as prose: `text` is itself a JSON-serialized Slate.js rich-text
 * document (verified live: every one of 72 sampled recipe steps parses as
 * one) — handing that straight to `jsonLdRecipeAdapter.parse` would surface
 * the raw `[{"type":"paragraph","children":[{"text":"…` blob as a step's
 * description, unusable as-is. `json` that doesn't parse as an array (a
 * genuinely plain-text step, or some future/different shape) is returned
 * unchanged rather than mangled.
 */
function flattenSlateDocument(json: string): string {
  let doc: unknown;
  try {
    doc = JSON.parse(json);
  } catch {
    return json;
  }
  if (!Array.isArray(doc)) return json;
  return flattenSlateBlocks(doc as SlateNode[]).join("\n");
}

/** The two schema.org `Recipe` fields {@link patchRecipeJsonLd} patches, plus an index signature so every other field survives re-serialization untouched. */
interface JsonLdRecipeLike {
  recipeInstructions?: unknown;
  recipeYield?: unknown;
  [key: string]: unknown;
}

/** One `HowToStep`-shaped entry of `recipeInstructions`, as far as {@link patchRecipeJsonLd} needs to know. */
interface JsonLdHowToStepLike {
  text?: unknown;
  [key: string]: unknown;
}

/**
 * `state.recipe.recipe.portions` from the same detail page's `__NEXT_DATA__`
 * — the number `recipeYield` should have been (see {@link patchRecipeJsonLd}),
 * read from the site's own internal state rather than left unstated.
 */
function extractPortionsFromNextData(html: string): number | null {
  const data = extractNextData<MangerBougerDetailPageData>(html);
  const portions = data?.props?.initialState?.recipe?.recipe?.portions;
  return typeof portions === "number" ? portions : null;
}

/**
 * Repairs the two real gaps verified live in mangerbouger.fr's own
 * recipe-detail JSON-LD, then hands the patched HTML to
 * `jsonLdRecipeAdapter.parse` unmodified otherwise — same "fix what's
 * actually broken, delegate the rest" shape as `750g.ts`'s
 * `sanitizeJsonLdBlocks`/`decodeParsedRecipeText`, just structural (parse →
 * mutate → re-serialize the one JSON-LD object) rather than textual, since
 * both gaps need real understanding of the document, not character-level
 * fixups:
 *
 * - `recipeInstructions[].text` is Slate.js rich text, not prose — flattened
 *   via {@link flattenSlateDocument}.
 * - `recipeYield` is absent on every one of 9 sampled recipes (schema.org
 *   allows omitting it, and mangerbouger.fr's generator apparently always
 *   does) even though the site's own internal data has the serving count
 *   right there — backfilled from `__NEXT_DATA__` via
 *   {@link extractPortionsFromNextData} rather than left as a needless
 *   `portions: null` on every single imported recipe.
 *
 * A missing or malformed JSON-LD block is left completely untouched —
 * `jsonLdRecipeAdapter`'s own "no JSON-LD Recipe found"/"malformed block,
 * skip it" handling is exactly the right behavior for that, no need to
 * duplicate it here.
 */
function patchRecipeJsonLd(html: string): string {
  const match = html.match(JSON_LD_SCRIPT_PATTERN);
  if (!match) return html;

  let recipe: JsonLdRecipeLike;
  try {
    recipe = JSON.parse(match[2] ?? "{}") as JsonLdRecipeLike;
  } catch {
    return html;
  }

  if (Array.isArray(recipe.recipeInstructions)) {
    for (const step of recipe.recipeInstructions as JsonLdHowToStepLike[]) {
      if (step && typeof step === "object" && typeof step.text === "string") {
        step.text = flattenSlateDocument(step.text);
      }
    }
  }

  if (recipe.recipeYield === undefined) {
    const portions = extractPortionsFromNextData(html);
    if (portions !== null) recipe.recipeYield = portions;
  }

  const patchedJson = JSON.stringify(recipe);
  return html.replace(
    JSON_LD_SCRIPT_PATTERN,
    (_full, openTag: string, _json: string, closeTag: string) =>
      `${openTag}${patchedJson}${closeTag}`,
  );
}

/**
 * Re-labels a `RecipeSourceFetchError`/`RecipeSourceParseError` thrown by
 * the generic `jsonLdRecipeAdapter` (`sourceKey` `"jsonLdRecipe"`) as having
 * come from this adapter instead (`sourceKey` `"mangerBouger"`) — same
 * reasoning as `marmiton.ts`/`750g.ts`'s identically-named helpers.
 */
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;
}

/**
 * mangerbouger.fr ("La Fabrique à Menus") — Santé publique France's public
 * nutrition site. Unofficial (`official: false`): no published API, same
 * reasoning as every other adapter in this family — fetching ordinary pages
 * and reading data the site never committed to a stable contract, not a
 * maintained endpoint. `fetchDetail` delegates straight to
 * `jsonLdRecipeAdapter`; `parse` wraps it with {@link patchRecipeJsonLd}
 * (see that function's doc comment for the two real gaps it fixes).
 * `list()` doesn't use JSON-LD at all — see `LIST_URL`'s doc comment.
 */
export const mangerBougerAdapter: RecipeSourceAdapter<{ html: string; url: string }> = {
  key: SOURCE_KEY,
  name: "Manger Bouger",
  official: false,
  // Chemin fixe (pas d'icône versionnée/hashée comme sur d'autres sources
  // de cette famille) — répond correctement sans paramètre supplémentaire.
  iconUrl: "https://www.mangerbouger.fr/manger-mieux/la-fabrique-a-menus/favicon.ico",
  // Le contenu de mangerbouger.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 {
      const page = params.cursor ? Number(params.cursor) : 1;
      const query = params.query ?? "";
      const listUrl = `${LIST_URL}?diet=ALL&page=${page}&query=${encodeURIComponent(query)}`;

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

      const data = extractNextData<MangerBougerListPageData>(html);
      const state = data?.props?.initialState?.recipes;

      const items: RecipeSourceListItem[] = (state?.list ?? [])
        .filter((entry): entry is MangerBougerListEntry & { slug: string; name: string } =>
          Boolean(entry.slug && entry.name),
        )
        .map((entry) => ({
          externalId: detailUrl(entry.slug),
          title: entry.name,
          picture: entry.image ?? null,
          url: detailUrl(entry.slug),
        }));

      return { items, nextCursor: state?.hasMorePages ? String(page + 1) : null };
    } catch (err) {
      // Rethrown as-is (already keyed "mangerBouger" 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
  // mangerbouger.fr (renvoyée telle quelle par `list()` ci-dessus) — même
  // convention que `jsonLdRecipeAdapter.fetchDetail`, à qui cette méthode
  // délègue entièrement : la réparation du JSON-LD (voir
  // `patchRecipeJsonLd`) n'a lieu qu'à l'étape `parse()`, pas ici.
  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 {
      const patchedHtml = patchRecipeJsonLd(raw.html);
      return jsonLdRecipeAdapter.parse({ html: patchedHtml, url: raw.url });
    } catch (err) {
      throw rekeySourceError(err);
    }
  },
};