ng-eventually/packages/client/test/store-registry.test.ts

import { test, expect, mock, beforeEach, afterAll } from "bun:test";
import {
  ensureAccount,
  allAccounts,
  loadShim,
  resolveWriteGraph,
  resolveReadGraphs,
  resolveScopeGraph,
  resolveInboxAnchor,
  createEntityDoc,
  listEntityDocs,
  resetRegistryCache,
} from "../src/store-registry";
import type { RegistrySession } from "../src/store-registry";
import {
  configure,
  configureStoreRegistry,
  resetStoreRegistry,
  resetConfig,
} from "../src/polyfill";

// This suite injects a fake `ng` via configure(); bun runs test files in a
// shared process with a single module singleton, and may run this file BEFORE
// docs.test.ts's order-dependent "not configured" guard. Restore the un-
// configured state when we're done so that guard still sees a null config.
afterAll(() => {
  resetConfig();
  resetStoreRegistry();
});

// NOTE ORDER: the "not configured → throw" case MUST run first — configure*()
// sets module-level singletons and this suite never fully un-injects the real
// `ng` (docs' getConfig has no reset), so we exercise the registry-deps guard.

test("throws a clear error when configureStoreRegistry() was not called", async () => {
  resetStoreRegistry();
  resetRegistryCache();
  await expect(ensureAccount("alice")).rejects.toThrow(
    /configureStoreRegistry\(\) must be called before use/,
  );
});

// --- A stateful fake `ng` that emulates just enough SPARQL over an in-memory
// quad store: INSERT DATA parsing + the two SELECT shapes the registry issues.

interface Quad { g: string; s: string; p: string; o: string }

/** Reverse of the lib's escapeLiteral: single left-to-right pass over `\x`. */
function unescapeLiteral(s: string): string {
  let out = "";
  for (let i = 0; i < s.length; i++) {
    if (s[i] === "\\" && i + 1 < s.length) {
      const next = s[++i];
      out +=
        next === "n" ? "\n" : next === "r" ? "\r" : next === "t" ? "\t" : next;
    } else {
      out += s[i];
    }
  }
  return out;
}

function makeFakeNg() {
  const quads: Quad[] = [];
  let docCounter = 0;

  const doc_create = mock(async (..._a: unknown[]) => `did:ng:o:doc${++docCounter}`);

  // Parses `INSERT DATA { GRAPH <g> { <s> <p> "o"/<o>/;-lists } }`. The literal
  // pattern honours backslash-escapes (`\"`, `\\`, `\n`…) so an escaped quote
  // inside a value does NOT terminate the literal — this is what proves the
  // injection escaping keeps the query well-formed.
  const sparql_update = mock(async (...a: unknown[]) => {
    const query = a[1] as string;
    const anchor = a[2] as string | undefined;
    // TWO shapes coexist here:
    //  - the shim account write STILL uses `GRAPH <${privateStore}>` — the
    //    private STORE repo's graph name equals the plain store NURI, so it
    //    round-trips (login must not regress). Key it by that GRAPH IRI.
    //  - the per-entity INDEX write has NO explicit GRAPH — the real broker keys
    //    it by the ANCHORED repo's default graph (repo_graph_name(id, overlay)),
    //    so key it by the ANCHOR arg (a[2]). An explicit `GRAPH <indexDoc>`
    //    would target a phantom graph → must NOT round-trip.
    const gm = query.match(/GRAPH <([^>]+)>\s*\{([\s\S]*)\}/);
    let g: string;
    let body: string;
    if (gm) {
      g = gm[1]!;
      body = gm[2]!;
    } else {
      if (!anchor) return undefined;
      g = anchor;
      body = query.replace(/^\s*INSERT DATA\s*\{/, "").replace(/\}\s*$/, "");
    }
    // Subject is the first <...> token in the body.
    const sm = body.match(/<([^>]+)>/);
    if (!sm) return undefined;
    const s = sm[1]!;
    // Predicate/object pairs: `<p> "o"` (escape-aware) or `<p> <o>`; `a <type>`.
    const pairRe = /(?:a|<([^>]+)>)\s+(?:"((?:[^"\\]|\\.)*)"|<([^>]+)>)/g;
    let m: RegExpExecArray | null;
    // Skip the subject token so we don't treat it as a predicate.
    const after = body.slice(body.indexOf(sm[0]) + sm[0].length);
    while ((m = pairRe.exec(after)) !== null) {
      const p = m[1] ?? "urn:ng-eventually:shim:Account"; // `a` → rdf:type-ish
      const o = m[2] !== undefined ? unescapeLiteral(m[2]) : (m[3] ?? "");
      quads.push({ g, s, p, o });
    }
    return undefined;
  });

  const sparql_query = mock(async (...a: unknown[]) => {
    const query = a[1] as string;
    const anchor = a[3] as string | undefined;
    // Pointer SELECT: `<shim:root> <shim:shimDoc> ?shimDoc` in the store-root graph.
    if (query.includes("<urn:ng-eventually:shim:shimDoc>")) {
      const bindings = quads
        .filter((q) => q.g === anchor && q.p === "urn:ng-eventually:shim:shimDoc")
        .map((q) => ({ shimDoc: { value: q.o } }));
      return { results: { bindings } };
    }
    if (query.includes("<urn:ng-eventually:shim:id>")) {
      // Account SELECT, anchored to the doc-shim's default graph (records live in the
      // doc-shim now, no GRAPH wrapper). Two shapes: the full scan (`?acc a <Account>`)
      // and the TARGETED bounded resolve (`<subj> a <Account>`) — honour the subject.
      const subjM = query.match(/<([^>]+)>\s+a\s+<urn:ng-eventually:shim:Account>/);
      const onlySubject = subjM ? subjM[1]! : null;
      const bySubject = new Map<string, Record<string, string>>();
      for (const q of quads) {
        if (q.g !== anchor) continue;
        if (onlySubject !== null && q.s !== onlySubject) continue;
        const rec = bySubject.get(q.s) ?? {};
        if (q.p === "urn:ng-eventually:shim:id") rec.id = q.o;
        if (q.p === "urn:ng-eventually:shim:docPublic") rec.docPublic = q.o;
        if (q.p === "urn:ng-eventually:shim:docProtected") rec.docProtected = q.o;
        if (q.p === "urn:ng-eventually:shim:docPrivate") rec.docPrivate = q.o;
        bySubject.set(q.s, rec);
      }
      const bindings = [...bySubject.values()]
        .filter((r) => r.id)
        .map((r) => ({
          id: { value: r.id! },
          docPublic: { value: r.docPublic ?? "" },
          docProtected: { value: r.docProtected ?? "" },
          docPrivate: { value: r.docPrivate ?? "" },
        }));
      return { results: { bindings } };
    }
    // Entity-index SELECT: `<index> <contains> ?e` in the anchor graph.
    const bindings = quads
      .filter((q) => q.g === anchor && q.p === "urn:ng-eventually:shim:contains")
      .map((q) => ({ e: { value: q.o } }));
    return { results: { bindings } };
  });

  return { doc_create, sparql_update, sparql_query, _quads: quads };
}

const SESSION: RegistrySession = { sessionId: "sid-1", privateStoreId: "PRIV" };

function inject() {
  const ng = makeFakeNg();
  configure({ ng: ng as any, useShape: (() => {}) as any });
  configureStoreRegistry({
    getSession: async () => SESSION,
    normalizeId: (u) => u.trim().replace(/^@+/, "").toLowerCase(),
  });
  resetRegistryCache();
  return ng;
}

let fake: ReturnType<typeof makeFakeNg>;
beforeEach(() => {
  fake = inject();
});

test("ensureAccount creates 3 scope docs and persists them to the doc-shim", async () => {
  const rec = await ensureAccount("Alice");
  expect(rec.id).toBe("Alice");
  // 4 doc_create: 1 doc-shim (first login, resolveShimDoc) + 3 scope docs.
  expect(fake.doc_create).toHaveBeenCalledTimes(4);
  expect(rec.docPublic).toMatch(/^did:ng:o:doc/);
  expect(rec.docProtected).not.toBe(rec.docPublic);
  expect(rec.docPrivate).not.toBe(rec.docProtected);
  // The pointer (store-root -> doc-shim) was written into the store-root graph.
  const pointerWrite = fake.sparql_update.mock.calls.find(
    (c) => (c[1] as string).includes("<urn:ng-eventually:shim:shimDoc>"),
  );
  expect(pointerWrite?.[2]).toBe("did:ng:PRIV");
  // The account record was persisted into the doc-shim (a did:ng:o: repo), not the root.
  const recordWrite = fake.sparql_update.mock.calls.find(
    (c) => (c[1] as string).includes("<urn:ng-eventually:shim:docPublic>"),
  );
  expect(recordWrite?.[2]).toMatch(/^did:ng:o:doc/);
});

test("ensureAccount is idempotent (case/@-insensitive key), no extra docs", async () => {
  const a = await ensureAccount("Alice");
  const b = await ensureAccount("@alice");
  expect(b).toEqual(a);
  expect(fake.doc_create).toHaveBeenCalledTimes(4); // 1 doc-shim + 3 scope docs, not 7
});

test("ensureAccount de-dupes CONCURRENT provisions (anti-fork): one account, 3 docs", async () => {
  // The reconnection FORK: several callers (watchShape public+protected, the
  // container subs, the owned-events effect) hit ensureAccount(SAME id) BEFORE
  // the shim has synced, so each reads 0 rows and independently provisions a new
  // set of scope docs — N forks, N×3 docs, duplicate docPublic/docProtected in the
  // shim → a fresh reader picks a different canonical doc than the writer wrote to.
  // The in-flight de-dup collapses N concurrent provisions into ONE.
  const results = await Promise.all([
    ensureAccount("Bob"),
    ensureAccount("Bob"),
    ensureAccount("@bob"),
    ensureAccount("BOB"),
    ensureAccount("bob"),
  ]);
  // ONE set of 3 scope docs + 1 doc-shim (resolveShimDoc de-dupes concurrent pointer
  // resolution too) — 4 total, not 5×3.
  expect(fake.doc_create).toHaveBeenCalledTimes(4);
  // Every caller got the SAME record (same docs), so writer/reader can never
  // disagree on the canonical scope doc.
  for (const r of results) expect(r).toEqual(results[0]!);
});

test("loadShim round-trips a persisted account across a cache reset", async () => {
  await ensureAccount("Bob");
  resetRegistryCache(); // force a re-read from the fake store
  const map = await loadShim();
  const rec = map.get("bob");
  expect(rec?.id).toBe("Bob");
  expect(rec?.docPublic).toMatch(/^did:ng:o:doc/);
});

test("resolveWriteGraph returns the per-scope index doc; resolveReadGraphs fans out", async () => {
  const rec = await ensureAccount("Carol");
  expect(await resolveWriteGraph("carol", "protected")).toBe(rec.docProtected);
  expect(await resolveReadGraphs("public")).toEqual([rec.docPublic]);
});

test("resolveScopeGraph maps scopes to native store NURIs (no store-id leaks to the caller)", async () => {
  // Session with all three store ids: private → private store; public+protected
  // co-locate on the protected native store (the polyfill's Axis-A placement).
  const ng = makeFakeNg();
  configure({ ng: ng as any, useShape: (() => {}) as any });
  configureStoreRegistry({
    getSession: async () => ({
      sessionId: "sid-2",
      privateStoreId: "PRIV",
      protectedStoreId: "PROT",
      publicStoreId: "PUB",
    }),
  });
  resetRegistryCache();
  expect(await resolveScopeGraph("private")).toBe("did:ng:PRIV");
  expect(await resolveScopeGraph("protected")).toBe("did:ng:PROT");
  expect(await resolveScopeGraph("public")).toBe("did:ng:PROT"); // co-located
  // The inbox anchor is now a DEDICATED inbox DOCUMENT (a reserved account's
  // public scope doc, from docCreate) — NOT the private-store root — so inbox
  // deposits don't bloat the shim graph. It is a real repo NURI and STABLE
  // across calls (same reserved account → same document).
  const anchor = await resolveInboxAnchor();
  expect(anchor).toMatch(/^did:ng:o:doc/);
  expect(anchor).not.toBe("did:ng:PRIV");
  expect(await resolveInboxAnchor()).toBe(anchor); // stable
});

test("resolveScopeGraph falls back to the private store when no protected id is injected", async () => {
  // The default SESSION carries only privateStoreId — non-private scopes fall
  // back to the private store rather than emitting a broken NURI.
  expect(await resolveScopeGraph("protected")).toBe("did:ng:PRIV");
  expect(await resolveScopeGraph("public")).toBe("did:ng:PRIV");
});

test("createEntityDoc + listEntityDocs round-trip via the per-scope index", async () => {
  const rec = await ensureAccount("Dave");
  const e1 = await createEntityDoc("dave", "public");
  const e2 = await createEntityDoc("dave", "public");
  const other = await createEntityDoc("dave", "protected");
  // Public listing unions dave's public entities only.
  const pub = await listEntityDocs("public");
  expect(pub.sort()).toEqual([e1, e2].sort());
  const prot = await listEntityDocs("protected");
  expect(prot).toEqual([other]);
  // The index append targets the account's public index doc.
  expect(rec.docPublic).toMatch(/^did:ng:o:doc/);
});

test("listEntityDocs fans out across multiple accounts", async () => {
  await ensureAccount("Eve");
  await ensureAccount("Frank");
  const e = await createEntityDoc("eve", "public");
  const f = await createEntityDoc("frank", "public");
  expect((await listEntityDocs("public")).sort()).toEqual([e, f].sort());
});

test("allAccounts reflects every ensured account", async () => {
  await ensureAccount("Gina");
  await ensureAccount("Hank");
  const names = (await allAccounts()).map((a) => a.id).sort();
  expect(names).toEqual(["Gina", "Hank"]);
});

// --- SPARQL injection hardening (F1) --------------------------------------
//
// A malicious id must NOT be able to break out of the literal / IRI it
// lands in and inject arbitrary triples into the shim (the account→doc trust
// root). We inspect the exact SPARQL string the registry hands to sparql_update.

/** The raw INSERT DATA string produced by ensureAccount for `id`. */
async function insertFor(id: string): Promise<string> {
  await ensureAccount(id);
  const calls = fake.sparql_update.mock.calls;
  return calls[calls.length - 1]![1] as string;
}

/** Count RAW (un-escaped) double-quotes — i.e. `"` not preceded by a `\`.
 *  Strip escaped pairs (`\\`, `\"`, …) first so only delimiter quotes remain. */
function rawQuoteCount(s: string): number {
  const withoutEscapes = s.replace(/\\./g, "");
  return (withoutEscapes.match(/"/g) ?? []).length;
}

test("injection: id with a quote cannot open extra literals", async () => {
  const evil = 'x" ; <urn:evil> "pwn';
  const update = await insertFor(evil);
  // A well-formed INSERT DATA with 4 predicate literals has exactly 8 raw
  // quotes (the delimiters). The injected `"` must have been escaped, so the
  // count stays 8 — no extra literal was opened.
  expect(rawQuoteCount(update)).toBe(8);
  // The escaped id is present as a single literal value — the injected
  // `<urn:evil>` survives only as INERT text inside that literal (its
  // surrounding quotes are escaped `\"`), never as query syntax.
  expect(update).toContain('"x\\" ; <urn:evil> \\"pwn"');
});

test("injection: id with '>' cannot break out of the account-subject IRI", async () => {
  const evil = "x> <urn:evil";
  const update = await insertFor(evil);
  // The account subject is `<urn:ng-eventually:shim:account:...>` — the encoded
  // id must NOT contain a raw `>` that would close the IRI early.
  const subjMatch = update.match(/<urn:ng-eventually:shim:account:([^>]*)>/)!;
  expect(subjMatch).not.toBeNull();
  expect(subjMatch[1]).not.toMatch(/[<>" ]/); // fully percent-encoded
  expect(subjMatch[1]).toContain("%3E"); // the `>` became %3E
});

test("injection: newline / control chars in id are neutralised", async () => {
  const evil = "a\nb\tc";
  const update = await insertFor(evil);
  // In the literal: escaped to \n / \t (no raw control char).
  expect(update).toContain('"a\\nb\\tc"');
  // In the IRI subject: percent-encoded.
  const subjMatch = update.match(/<urn:ng-eventually:shim:account:([^>]*)>/)!;
  expect(subjMatch[1]).toContain("%0A");
  expect(subjMatch[1]).toContain("%09");
});

test("injection: '; DELETE'-style payload stays inert inside the literal", async () => {
  const evil = 'x"} ; DELETE WHERE { ?s ?p ?o } ; INSERT DATA { <a> <b> "';
  const update = await insertFor(evil);
  // The whole attack survives, escaped, as ONE literal value — the injected
  // `"}` cannot close the literal/graph, so DELETE/second-INSERT stay text.
  expect(update).toContain(escapeLiteralRef(evil));
  // Quote count stays even (all delimiters balanced; the injected `"` escaped):
  // 4 predicate literals → 8 raw delimiter quotes, nothing extra opened.
  expect(rawQuoteCount(update)).toBe(8);
  // The injected `"}` did not survive as raw syntax (it was escaped to `\"}`).
  expect(update).not.toMatch(/[^\\]"} ; DELETE/);
});

// Local mirror of the lib's escapeLiteral so the assertion is self-checking.
function escapeLiteralRef(v: string): string {
  return `"${v
    .replace(/\\/g, "\\\\")
    .replace(/"/g, '\\"')
    .replace(/\n/g, "\\n")
    .replace(/\r/g, "\\r")
    .replace(/\t/g, "\\t")}"`;
}

test("injection: a malicious id still round-trips through the shim", async () => {
  const evil = 'eve" ; <urn:evil> "x';
  const rec = await ensureAccount(evil);
  expect(rec.id).toBe(evil);
  resetRegistryCache();
  const map = await loadShim();
  // The stored id came back verbatim (escaping is lossless) under its
  // normalized key, and exactly ONE account exists (no injected extra subject).
  const key = evil.trim().replace(/^@+/, "").toLowerCase();
  expect(map.get(key)?.id).toBe(evil);
  expect(map.size).toBe(1);
});

test("normalizeId defaults to trim when not provided", async () => {
  const ng = makeFakeNg();
  configure({ ng: ng as any, useShape: (() => {}) as any });
  // Synchronous fake store → no sync lag; disable the anti-fork retry backoff.
  configureStoreRegistry({ getSession: async () => SESSION });
  resetRegistryCache();
  const a = await ensureAccount("  Ivy  ");
  const b = await ensureAccount("Ivy"); // trimmed key matches
  expect(b).toEqual(a);
  expect(ng.doc_create).toHaveBeenCalledTimes(4); // 1 doc-shim + 3 scope docs
});