ng-eventually/packages/polyfill/src/surface/docs.ts

/**
 * Low-level document + SPARQL primitives.
 *
 * These call the real injected `ng` (`getConfig().ng`) directly — never the
 * public `ng` proxy (`makeNg`). This is a validated hard constraint, not a style
 * choice: the public `ng` is a JS `Proxy` over `@ng-org/web`'s iframe-RPC proxy,
 * and layering our Proxy on top breaks `doc_create`'s `postMessage` marshaling
 * with **`DataCloneError: function ... could not be cloned`** — the footgun this
 * rule exists to prevent. Reaching the real `ng` held in the config avoids the
 * double-proxy. Do not import from `./ng-proxy`.
 *
 * Signatures mirror the real `@ng-org/web` `ng` surface (verified against the
 * app's storeRegistry usage), so this is a drop-in for those raw calls.
 */

import { getCaps, getConfig } from "../shared-wallet/bootstrap";
import { logAccess, enabled as accessLogEnabled } from "../shared-wallet/access-log";
import { isNuri, toNuri } from "../model/nuri";
import { assertMayReach, assertMayWrite } from "../emulated-verifier/reach";
import { fetchReadCap } from "../emulated-verifier/public-store";
import type { Nuri, NuriLike } from "../model/types";

// The low common point for ALL document access: every read in the SDK routes
// through `sparqlQuery`, every write through `sparqlUpdate` (+ container creation
// through `docCreate`) — each ultimately calling the real injected `ng` here. The
// access log is therefore instrumented HERE so no access path escapes it. Callers
// pass a semantic `label` (readDoc|readUnion|listMyEntityDocs|writeEntity|deposit
// |…); it is a lib-internal probe param, NOT forwarded to the real `ng` (the docs
// primitives forward the exact SDK signature — see test/docs.test.ts). When the
// log is OFF (default) the extra param is inert and costs one boolean read.

/** Count rows in a raw SPARQL SELECT result, tolerant of the possible shapes. */
function rowCount(result: unknown): number {
  if (!result) return 0;
  if (Array.isArray(result)) return result.length;
  const anyRes = result as { results?: { bindings?: unknown[] } };
  return anyRes.results?.bindings?.length ?? 0;
}

/**
 * Create one document → its NURI.
 *
 * Mirrors `ng.doc_create(session_id, crdt, cls, dest, store_repo?)`. For a graph
 * document in the (shared) private store: `docCreate(sid, "Graph", "data:graph",
 * "store")` (store_repo left undefined → private store).
 */
export async function docCreate(
  sessionId: string,
  crdt: string,
  cls: string,
  dest: string,
  store?: unknown,
): Promise<Nuri> {
  const { ng } = getConfig();
  const nuri = await ng.doc_create(sessionId, crdt, cls, dest, store);
  // The BROKER boundary. `ng` is a permissive property bag (`NgLike`), so what
  // comes back is `any` and this function's `Promise<Nuri>` would otherwise be an
  // unchecked promise — every typed NURI downstream rests on it. Validate once,
  // here, rather than let a non-reference propagate as a document.
  if (typeof nuri !== "string" || !isNuri(nuri)) {
    throw new Error(
      `[ng-eventually] docCreate: the broker returned something that is not a NextGraph reference: ${JSON.stringify(nuri)}`,
    );
  }
  // **Creating a document gives you its cap.** Upstream that is not a courtesy but
  // the mechanism: `doc_create` commits `AddRepo { read_cap }` to the store's Store
  // branch, so the creator holds it from the first instant. Without this, a caller
  // could create a document through this primitive and then be refused reading or
  // writing it — which is what the e2e run against the live broker exposed.
  //
  // `physical.ts`'s counterpart deliberately does NOT do this: the shim's own
  // documents belong to no virtual user, and `store-registry` files their caps
  // itself, where it knows whose they are.
  getCaps().mint(nuri);
  // A container creation is a WRITE; the NURI only exists after the call.
  logAccess("WRITE", nuri, "docCreate");
  return nuri;
}

/**
 * Run a SPARQL UPDATE (INSERT/DELETE DATA, etc.).
 *
 * Mirrors `ng.sparql_update(session_id, query, anchor?)`, where `anchor` is the
 * document NURI the update is scoped/base'd to (optional).
 */
export async function sparqlUpdate(
  sessionId: string,
  query: string,
  anchorLike?: NuriLike,
  label = "sparqlUpdate",
): Promise<void> {
  const { ng } = getConfig();
  const anchor = anchorLike === undefined ? undefined : toNuri(anchorLike, "docs.sparqlUpdate");
  // The boundary, in two questions that are NOT the same one.
  //
  // Reaching is possession. Writing is OWNERSHIP — upstream the right to write is
  // membership of the repo (`verify_permission`, reachable only from `Commit::verify`,
  // so on commits and never on reads), and how you came by the READ key changes nothing
  // about it. A public store hands its read cap to whoever asks; a cap deposited in your
  // inbox is a Link someone gave you. Neither makes you a member.
  //
  // NO public-store fetch here, unlike the read below: asking the network for a read key
  // has no bearing on a write.
  if (anchor !== undefined) {
    assertMayReach(anchor, "docs.sparqlUpdate");
    await assertMayWrite(anchor, "docs.sparqlUpdate");
  }
  // `label` is a lib-internal access-log tag, NOT forwarded to `ng`.
  logAccess("WRITE", anchor ?? "(no anchor)", label);
  return ng.sparql_update(sessionId, query, anchor);
}

/**
 * Run a SPARQL SELECT/CONSTRUCT/ASK query → the raw SDK result.
 *
 * Mirrors `ng.sparql_query(session_id, query, base?, anchor?)`. `base` is the
 * query base IRI (usually `undefined`); `anchor` is the document NURI to query.
 */
export async function sparqlQuery(
  sessionId: string,
  query: string,
  base?: string,
  anchorLike?: NuriLike,
  label = "sparqlQuery",
): Promise<unknown> {
  const { ng } = getConfig();
  const anchor = anchorLike === undefined ? undefined : toNuri(anchorLike, "docs.sparqlQuery");
  // The boundary: an ANCHORED read may only touch what the connected virtual user
  // reaches. An anchorless query spans the local union — a different problem (it is
  // O(wallet size), and the read path never uses it), not one this guard can bound.
  //
  // Asking the (emulated) network first, as `ensureRepoOpen` does: a document in a
  // public store gives its cap to whoever asks, and this is a door an application can
  // reach with nothing but a bare reference. Inert once the cap is held, memoised
  // otherwise — see public-store.ts.
  if (anchor !== undefined) {
    await fetchReadCap(anchor);
    assertMayReach(anchor, "docs.sparqlQuery");
  }
  // `label` is a lib-internal access-log tag, NOT forwarded to `ng`.
  const result = await ng.sparql_query(sessionId, query, base, anchor);
  // Log AFTER the read so the row count (a strong leak signal: a doc rendering
  // rows under an identity that should see nothing) can be appended. Skip the
  // rowCount work entirely when the log is off.
  if (accessLogEnabled()) {
    // `rows` here are raw RDF triple bindings (the SPARQL `?s ?p ?o` result), NOT
    // domain objects — one document's entity is spread across several triple rows.
    // Spell that out so the log isn't mistaken for an object count (the app-level
    // object/shape count is logged separately by useShapeQuery → dataStats).
    logAccess("READ", anchor ?? "(no anchor)", label, " → " + rowCount(result) + " triple-rows");
  }
  return result;
}