ng-eventually/packages/polyfill/src/surface/read-model.ts

/**
 * read-model — the listing primitive of the polyfill: read a bounded, by-need set
 * of documents, each with its own anchored `sparql_query`, and return the triples
 * grouped per subject. This is the mechanism documented in docs/read-model.md.
 *
 * ── Why per-doc anchored, rather than an anchorless union-scan ─────────────
 * An anchored `sparql_query(sid, "SELECT ?s ?p ?o WHERE { ?s ?p ?o }", base, doc)`
 * is restricted to the anchor repo's graph: `resolve_target_for_sparql(Repo)` →
 * `Some(repo_graph_name)`, which becomes the query's default graph. A body with no
 * `GRAPH` wrapper reads only that default graph → only that doc's triples, O(1) per
 * doc, independent of how many other graphs the local store holds.
 *
 * The footgun this avoids: an anchorless query (`anchor` undefined → `UserSite` →
 * `set_default_graph_as_union`) spans EVERY named graph currently in the session
 * store. On a shared / bloated wallet that accumulates across runs, that is
 * O(wallet size) → the observed ~90s timeouts. So the read path never union-scans
 * all graphs — it reads exactly the bounded by-need set, one anchored query per doc.
 *
 * NB (verified, docs/read-model.md § probe step 4): an explicit `GRAPH ?g { … }`
 * body iterates the named graphs regardless of the default graph, so an anchor does
 * not bound such a body. The per-doc read therefore uses a default-graph body (no
 * `GRAPH` wrapper) so the anchor's one-repo restriction actually applies.
 *
 * ── Why not the reactive ORM fan-out ──────────────────────────────────────
 * `useShape({ graphs: […manyDocs] })` drives `orm_start_graph` over a fan-out of
 * per-entity graphs; a freshly-created / not-yet-synced doc in that fan-out makes
 * `RepoNotFound` abort the whole subscription → the readyPromise never resolves →
 * the ~75s hang (docs/nextgraph-current-state.md § The ORM fan-out hang). Listing
 * is instead a set of one-shot anchored `sparql_query`s. There is no reactive
 * union query, so reactivity is assembled by re-querying on a change signal.
 *
 * ── Generic by construction ───────────────────────────────────────────────
 * No application domain here: the consumer passes the doc NURIs to read (from
 * the discovery index for public events, or its own scope docs for my-entities)
 * and interprets the returned per-subject property bags. All NextGraph I/O routes
 * through the T01.a `docs` primitives (the real injected `ng`), so this module
 * imports no `@ng-org` package.
 *
 * At the real multi-store migration the per-doc anchored read is unchanged (native
 * SPARQL, anchored to one repo); only bringing a repo into the session (open by cap)
 * changes — the anchored query already resolves a same-session repo directly.
 */

import { docCreate, sparqlUpdate, sparqlQuery } from "./docs";
import { getCaps, getStoreRegistryDeps } from "../shared-wallet/bootstrap";
import { mustNotAttempt } from "../emulated-verifier/reach";
import { ensureReposOpen } from "../emulated-verifier/open-repo";
import { assertNuri } from "./sparql";
import { toNuri } from "../model/nuri";
import { isMachinerySubject } from "../emulated-verifier/machinery";
import type { Nuri, NuriLike } from "../model/types";

// Keep the primitives referenced so tree-shaking never drops the import used by
// the (side-effecting) open step below; `docCreate`/`sparqlUpdate` are not used
// here but the module intentionally depends only on the docs primitive surface.
void docCreate;
void sparqlUpdate;

/** One subject read from a doc, with its properties (predicate → values). */
// @provenance UnionSubject kind=invention level=none ref=none — no upstream type groups triples per (document, subject); a polyfill property bag, to be mapped into app types at the boundary
export interface UnionSubject {
  /**
   * The subject IRI (`?s`), exactly as the document carries it.
   *
   * Typed `string`, not `Nuri`: a subject is an ordinary RDF subject and may be ANY
   * IRI. An application that writes its entity under the document's own NURI gets a
   * NURI back here, but that is its convention, not this type's promise — a document
   * may hold several subjects under IRIs of the consumer's choosing, and each comes
   * back as written.
   *
   * The need that once made this `Nuri` is real and is met by {@link graph}: a
   * consumer must be able to pass back what it just read without a cast —
   * `shareNote(note.doc)`, `leaveMessage(note.doc)` — and a cast at that boundary
   * would re-open exactly the confusion the template literal types exist to close.
   * `graph` is the document reference, so that is the field to carry around.
   */
  subject: string;
  /**
   * The document this subject was read from — the reference the caller passed to
   * {@link readUnion}, unchanged. This is the anchor, it identifies the document
   * stably, and it is what goes back into any call of this surface.
   */
  graph: Nuri;
  /** predicate IRI → the list of object values (literals or IRIs) for it. */
  props: Record<string, string[]>;
}

/** Tolerant extraction of SPARQL SELECT bindings across possible shapes. */
function bindings(
  result: unknown,
): Array<Record<string, { value: string } | undefined>> {
  if (!result) return [];
  if (Array.isArray(result))
    return result as Array<Record<string, { value: string }>>;
  const anyRes = result as {
    results?: { bindings?: Array<Record<string, { value: string }>> };
  };
  return anyRes.results?.bindings ?? [];
}

async function sessionId(): Promise<string | number> {
  return (await getStoreRegistryDeps().getSession()).sessionId;
}

/**
 * Read one doc with an anchored default-graph query, tolerant per-doc.
 *
 * The anchor (`doc` NURI) restricts the query to that repo's graph as the default
 * graph (`resolve_target_for_sparql(Repo)` → `Some(repo_graph_name)`); a body with
 * no `GRAPH` wrapper reads exactly that default graph → only this doc's triples.
 * This is O(1) in the doc's own size and independent of the rest of the (possibly
 * bloated / shared) session store — it never iterates other graphs.
 *
 * COLD-START (fresh session, same persistent wallet): the repo is NOT in
 * `self.repos` until something opens it, and an anchored query against an unopened
 * repo silently returns 0 rows (never `RepoNotFound`). {@link readUnion} therefore
 * opens the batch's repos ({@link ensureReposOpen}) BEFORE this read runs, so the
 * anchored query resolves a same-session repo directly. A genuinely-absent repo
 * still yields `[]` (in isolation, never aborting the others). Returns the doc's
 * rows, or `[]` on failure.
 *
 * At the real multi-store migration this becomes a real sync: opening a per-user
 * store repo by cap is a native broker fetch (`verifier.rs:1423` `OpenRepo` TODO).
 */
async function readDoc(
  sid: string | number,
  doc: Nuri,
): Promise<Array<Record<string, { value: string } | undefined>>> {
  try {
    const nuri = assertNuri(doc);
    // Anchored to `nuri` → default graph = this repo. No `GRAPH ?g` wrapper, so
    // the anchor's one-repo restriction applies (an explicit `GRAPH ?g` body would
    // iterate all named graphs regardless of the anchor — see docs § probe step 4).
    const res = await sparqlQuery(
      sid,
      "SELECT ?s ?p ?o WHERE { ?s ?p ?o }",
      undefined,
      nuri,
      "readDoc",
    );
    return bindings(res);
  } catch (error) {
    console.error("[read-model] read failed for", doc, error);
    return [];
  }
}

/**
 * Read a BOUNDED, by-need set of docs — each with its OWN anchored query — and
 * return the triples grouped per subject. `docs` are the NURIs to read (the
 * consumer resolves them by need — index for public, own scope docs for mine).
 * Docs that fail are skipped (see {@link readDoc}); a failing doc never aborts the
 * batch.
 *
 * A document holding SEVERAL subjects yields several entries — one per distinct
 * subject, carrying that subject as written, all sharing the document as their
 * `graph`. Properties of different subjects are never merged. Placing one business
 * entity per document stays the recommended practice (a key is per repo, so
 * isolation needs a repo per entity), but it is a recommendation about writing: the
 * read reports what is there.
 *
 * Never an anchorless union-scan over all graphs (which is O(wallet size) and wrong
 * on a shared / bloated wallet — the footgun this path exists to avoid). Each doc is
 * read with an anchored default-graph query, O(1) per doc, independent of wallet
 * size — a non-empty wallet no longer matters. Reads run in parallel via `Promise.all`.
 */
// @provenance readUnion kind=aligned level=2 ref=sdk/js/lib-wasm/src/lib.rs:sparql_query — one anchored query per document — upstream's own anchoring (`resolve_target_for_sparql`), composed client-side
export async function readUnion(docsLike: NuriLike[]): Promise<UnionSubject[]> {
  const sid = await sessionId();
  // Drop the empties BEFORE validating, not after: this call has always tolerated a
  // list with holes in it — a scope index can carry a blank entry, and a caller
  // building a list from optional values should not have to compact it. Validating
  // first turned that tolerance into a throw, which took down a whole reconnect run.
  // Empty is absence, and absence is not a malformed reference.
  const unique = [...new Set(docsLike.filter(Boolean))].map((d) => toNuri(d, "readUnion"));
  if (unique.length === 0) return [];

  // COLD-START heal (polyfill-era): on a fresh session over a persistent wallet the
  // target repos are not yet in `self.repos`, so an anchored read would return 0
  // rows. Open/subscribe each repo ONCE (idempotent, per session) and await its
  // initial-state push before the anchored reads. No-op once opened / when the
  // injected `ng` has no `doc_subscribe` (unit fake). See open-repo.ts.
  //
  // Called on the WHOLE set, before the boundary is consulted, because opening is also
  // where a document in a PUBLIC store hands over its cap (see public-store.ts): a
  // document filtered out first would never get the chance to answer. `ensureRepoOpen`
  // still refuses to open what this user may not touch — it asks, it does not enter.
  await ensureReposOpen(unique);

  // RULE 2 — do not even attempt. Drop the documents whose cap this user does not
  // hold before reading anything: upstream you cannot address a repo you have no cap
  // for, so asking about one is not "a read that will be refused", it is a read that
  // has no meaning. (The passage points enforce rule 1 regardless — see reach.ts — so
  // a lapse here is caught, not exploited.)
  const reachable = unique.filter((d) => !mustNotAttempt(d));

  // One anchored query per doc, in parallel, tolerant (a bad doc yields []).
  const perDoc = await Promise.all(
    reachable.map(async (d) => ({ doc: assertNuri(d), rows: await readDoc(sid, d) })),
  );

  // Possession gate, kept as defence in depth behind rule 2 above: `reachable`
  // already excluded these, so this loop should never drop anything. The read is
  // anchored per document, so the unit of possession is the document: the cap key is
  // the doc NURI, whatever subjects that document turns out to carry.
  const caps = getCaps();

  // Keyed by (document, subject) — an entry is one subject INSIDE one graph, which is
  // the identity upstream gives an object too: the ORM carries `@id` and `@graph` as
  // two distinct read-only properties, and fabricates an `@id` when the writer leaves
  // it empty (`sdk/js/orm/src/connector/GraphOrmSubscription.ts`). Several objects per
  // graph is therefore the PROVIDED case, and `@id` is what tells them apart within a
  // `@graph`. Two documents carrying the same subject IRI stay two entries: they are
  // two objects, distinguished by their graph.
  //
  // Placing one business entity per document remains the recommended practice — a key
  // is per repo, so isolating an entity requires a repo of its own. That is a
  // recommendation about WRITING, and the read does not get to enforce it by making
  // the other arrangement invisible.
  const bySubject = new Map<string, UnionSubject>();
  for (const { doc, rows } of perDoc) {
    if (caps.isEnforcing() && caps.capFor(doc) === undefined) continue;
    // Anchored to `doc`, so every row belongs to `doc` — hence `graph` is the caller's
    // reference to it. The subject comes back exactly as the document carries it.
    for (const row of rows) {
      // The polyfill's own compartments live as reserved SUBJECTS inside the very
      // documents the consumer reads (the Header branch carrying a document's inbox
      // address is the first). They are machinery, not this entity's properties —
      // drop them here, once, for every compartment present and future.
      const s = row.s?.value;
      if (isMachinerySubject(s)) continue;
      const p = row.p?.value;
      const o = row.o?.value;
      if (s === undefined || !p || o === undefined) continue;
      // NUL cannot appear in an IRI, so the pair never collides with either half.
      const key = `${doc}\u0000${s}`;
      let entry = bySubject.get(key);
      if (!entry) {
        entry = { subject: s, graph: doc, props: {} };
        bySubject.set(key, entry);
      }
      (entry.props[p] ??= []).push(o);
    }
  }
  return [...bySubject.values()];
}