fix: drive background refresh and phishing update from alarms (closes #158)

tests/phishingDomains.test.js

@@ -1,17 +1,24 @@
-// Provide a localStorage mock for Node.js test environment.
-// Must be set before requiring the module since it calls loadDeltaFromStorage()
-// at module load time.
-const localStorageStore = {};
-global.localStorage = {
-    getItem: (key) =>
-        Object.prototype.hasOwnProperty.call(localStorageStore, key)
-            ? localStorageStore[key]
-            : null,
-    setItem: (key, value) => {
-        localStorageStore[key] = String(value);
-    },
-    removeItem: (key) => {
-        delete localStorageStore[key];
+// Extension storage stub for the Node test environment. The module resolves
+// the storage API on use, so this only has to exist before the first call.
+// Values round-trip through JSON the way structured cloning would, so a test
+// cannot pass by holding a live reference to the module's own array.
+const storageStore = {};
+global.chrome = {
+    storage: {
+        local: {
+            get: async (key) =>
+                Object.prototype.hasOwnProperty.call(storageStore, key)
+                    ? { [key]: JSON.parse(JSON.stringify(storageStore[key])) }
+                    : {},
+            set: async (items) => {
+                for (const [key, value] of Object.entries(items)) {
+                    storageStore[key] = JSON.parse(JSON.stringify(value));
+                }
+            },
+            remove: async (key) => {
+                delete storageStore[key];
+            },
+        },
     },
 };
 
@@ -21,19 +28,32 @@ const {
     getBlocklistSize,
     getDeltaSize,
     hostnameVariants,
+    DELTA_STORAGE_KEY,
     _reset,
     _getVendoredBlacklistSize,
     _getDeltaBlacklist,
 } = require("../src/shared/phishingDomains");
 
+function clearStorage() {
+    for (const key of Object.keys(storageStore)) {
+        delete storageStore[key];
+    }
+}
+
+// The MV3 service worker is torn down when idle and re-evaluated on the next
+// event, which wipes every module-level variable. Re-requiring the module with
+// the registry reset is exactly that: fresh in-memory state, same extension
+// storage underneath.
+function restartWorker() {
+    jest.resetModules();
+    return require("../src/shared/phishingDomains");
+}
+
 // Reset delta state before each test to avoid cross-test contamination.
 // Note: vendored sets are immutable and always present.
 beforeEach(() => {
     _reset();
-    // Clear localStorage mock between tests
-    for (const key of Object.keys(localStorageStore)) {
-        delete localStorageStore[key];
-    }
+    clearStorage();
 });
 
 describe("phishingDomains", () => {
@@ -169,15 +189,34 @@ describe("phishingDomains", () => {
         });
     });
 
-    describe("localStorage persistence", () => {
-        test("saveDeltaToStorage persists delta under 256KiB", () => {
-            loadConfig({
+    describe("extension storage persistence", () => {
+        test("delta is persisted to extension storage, not localStorage", async () => {
+            await loadConfig({
                 blacklist: ["persisted-scam-xyz.com"],
             });
-            const stored = localStorage.getItem("phishing-delta");
-            expect(stored).not.toBeNull();
-            const data = JSON.parse(stored);
-            expect(data.blacklist).toContain("persisted-scam-xyz.com");
+            const stored = storageStore[DELTA_STORAGE_KEY];
+            expect(stored).toBeDefined();
+            expect(stored.blacklist).toContain("persisted-scam-xyz.com");
+        });
+
+        test("the fetch timestamp is persisted alongside the delta", async () => {
+            const before = Date.now();
+            await loadConfig({ blacklist: ["timestamped-scam-xyz.com"] });
+            const stored = storageStore[DELTA_STORAGE_KEY];
+            expect(typeof stored.lastFetchTime).toBe("number");
+            expect(stored.lastFetchTime).toBeGreaterThanOrEqual(before);
+        });
+
+        test("an oversized delta is dropped entirely, timestamp included", async () => {
+            // A record above the 256 KiB cap is not worth keeping; the
+            // timestamp goes with it so the next start re-fetches rather than
+            // claiming freshness for a delta that was never stored.
+            const huge = [];
+            for (let i = 0; i < 20000; i++) {
+                huge.push(`oversize-scam-${i}-xyzxyzxyzxyzxyz.com`);
+            }
+            await loadConfig({ blacklist: huge });
+            expect(storageStore[DELTA_STORAGE_KEY]).toBeUndefined();
         });
 
         test("delta is cleared on _reset", () => {
@@ -203,3 +242,332 @@ describe("phishingDomains", () => {
         });
     });
 });
+
+describe("phishing list across a service worker restart", () => {
+    beforeEach(() => {
+        clearStorage();
+        jest.resetModules();
+    });
+
+    afterEach(() => {
+        delete global.fetch;
+    });
+
+    test("a revived worker restores the persisted delta without re-fetching", async () => {
+        const first = require("../src/shared/phishingDomains");
+        await first.loadConfig({ blacklist: ["restart-scam-xyz.com"] });
+
+        const revived = restartWorker();
+        // Nothing in memory yet — this is a brand new module instance.
+        expect(revived.getDeltaSize()).toBe(0);
+
+        global.fetch = jest.fn();
+        await revived.initPhishingList();
+
+        expect(global.fetch).not.toHaveBeenCalled();
+        expect(revived.getDeltaSize()).toBe(1);
+        expect(revived.isPhishingDomain("restart-scam-xyz.com")).toBe(true);
+    });
+
+    test("repeated wakes inside the cache window never re-fetch", async () => {
+        const first = require("../src/shared/phishingDomains");
+        await first.loadConfig({ blacklist: ["no-storm-scam-xyz.com"] });
+
+        global.fetch = jest.fn();
+        for (let i = 0; i < 5; i++) {
+            const revived = restartWorker();
+            await revived.initPhishingList();
+        }
+        expect(global.fetch).not.toHaveBeenCalled();
+    });
+
+    test("a persisted timestamp older than the TTL causes a fetch on startup", async () => {
+        const first = require("../src/shared/phishingDomains");
+        await first.loadConfig({ blacklist: ["stale-scam-xyz.com"] });
+
+        // Age the persisted record past the 24-hour TTL.
+        storageStore[first.DELTA_STORAGE_KEY].lastFetchTime =
+            Date.now() - first.CACHE_TTL_MS - 1000;
+
+        const revived = restartWorker();
+        global.fetch = jest.fn(async () => ({
+            ok: true,
+            json: async () => ({ blacklist: ["refreshed-scam-xyz.com"] }),
+        }));
+        await revived.initPhishingList();
+
+        expect(global.fetch).toHaveBeenCalledTimes(1);
+        expect(revived.isPhishingDomain("refreshed-scam-xyz.com")).toBe(true);
+        expect(revived.isPhishingDomain("stale-scam-xyz.com")).toBe(false);
+    });
+
+    test("a first start with nothing persisted fetches immediately", async () => {
+        const fresh = restartWorker();
+        global.fetch = jest.fn(async () => ({
+            ok: true,
+            json: async () => ({ blacklist: ["first-run-scam-xyz.com"] }),
+        }));
+        await fresh.initPhishingList();
+
+        expect(global.fetch).toHaveBeenCalledTimes(1);
+        expect(fresh.isPhishingDomain("first-run-scam-xyz.com")).toBe(true);
+    });
+
+    test("updatePhishingList honours the persisted timestamp on its own", async () => {
+        // The startup path calls updatePhishingList() directly, so it must
+        // load persisted state itself rather than relying on anything else
+        // having finished first.
+        const first = require("../src/shared/phishingDomains");
+        await first.loadConfig({ blacklist: ["alarm-tick-scam-xyz.com"] });
+
+        const revived = restartWorker();
+        global.fetch = jest.fn();
+        await revived.updatePhishingList();
+
+        expect(global.fetch).not.toHaveBeenCalled();
+        expect(revived.isPhishingDomain("alarm-tick-scam-xyz.com")).toBe(true);
+    });
+});
+
+// The alarm period alone must set the cadence. lastFetchTime is stamped when
+// the fetch completes, so it lands one fetch latency after the alarm that
+// caused it; a freshness guard timed to the alarm period therefore vetoes
+// every scheduled tick and halves the real refresh rate. These tests measure
+// the interval between fetches that actually happened.
+describe("phishing refresh steady-state cadence", () => {
+    const { PHISHING_REFRESH_PERIOD_MINUTES } = require("../src/shared/alarms");
+    const PERIOD_MS = PHISHING_REFRESH_PERIOD_MINUTES * 60 * 1000;
+
+    let clockSpy;
+    let now;
+
+    beforeEach(() => {
+        clearStorage();
+        jest.resetModules();
+        now = Date.UTC(2026, 0, 1, 0, 0, 0);
+        clockSpy = jest.spyOn(Date, "now").mockImplementation(() => now);
+    });
+
+    afterEach(() => {
+        clockSpy.mockRestore();
+        delete global.fetch;
+    });
+
+    function fetchStub(latencyMs, seen) {
+        return jest.fn(async () => {
+            seen.push(now);
+            // A network fetch takes time, and lastFetchTime is stamped after
+            // it, not when the alarm fired.
+            now += latencyMs;
+            return { ok: true, json: async () => ({ blacklist: [] }) };
+        });
+    }
+
+    test("ten alarm ticks produce ten fetches, one per period", async () => {
+        const fetchedAt = [];
+        global.fetch = fetchStub(5000, fetchedAt);
+
+        const startup = require("../src/shared/phishingDomains");
+        const T0 = now;
+        await startup.initPhishingList();
+        expect(fetchedAt).toEqual([T0]);
+
+        const TICKS = 10;
+        let tickAt = T0 + PERIOD_MS;
+        for (let i = 0; i < TICKS; i++) {
+            now = tickAt;
+            tickAt += PERIOD_MS;
+            // The browser wakes a terminated worker to deliver the alarm, so
+            // every tick starts from cold memory and the persisted record.
+            const revived = restartWorker();
+            await revived.refreshPhishingListOnSchedule();
+        }
+
+        expect(fetchedAt).toHaveLength(TICKS + 1);
+        const intervals = fetchedAt.slice(1).map((t, i) => t - fetchedAt[i]);
+        expect(intervals).toEqual(new Array(TICKS).fill(PERIOD_MS));
+    });
+
+    test("the scheduled tick fetches whatever the last fetch's latency was", async () => {
+        // The alarm fires one period after the previous alarm, which is
+        // `latency` short of one period since the fetch it caused completed.
+        for (const latency of [200, 1000, 5000]) {
+            clearStorage();
+            jest.resetModules();
+            storageStore[DELTA_STORAGE_KEY] = {
+                blacklist: [],
+                lastFetchTime: now - PERIOD_MS + latency,
+                lastAttemptTime: now - PERIOD_MS,
+            };
+            const mod = require("../src/shared/phishingDomains");
+            const fetchedAt = [];
+            global.fetch = fetchStub(latency, fetchedAt);
+
+            await mod.refreshPhishingListOnSchedule();
+            expect(fetchedAt).toHaveLength(1);
+        }
+    });
+
+    test("a worker wake inside the cache window still does not fetch", async () => {
+        // The TTL is not removed, only taken off the scheduled path. Chrome
+        // revives the worker every ~30 seconds and every revival runs the
+        // startup path, so the TTL still has to keep that off the network.
+        storageStore[DELTA_STORAGE_KEY] = {
+            blacklist: [],
+            lastFetchTime: now - PERIOD_MS + 5000,
+            lastAttemptTime: now - PERIOD_MS,
+        };
+        const mod = require("../src/shared/phishingDomains");
+        global.fetch = jest.fn();
+
+        await mod.initPhishingList();
+        expect(global.fetch).not.toHaveBeenCalled();
+    });
+});
+
+describe("phishing list timestamps that cannot be trusted", () => {
+    let clockSpy;
+    let now;
+
+    beforeEach(() => {
+        clearStorage();
+        jest.resetModules();
+        now = Date.UTC(2026, 0, 1, 0, 0, 0);
+        clockSpy = jest.spyOn(Date, "now").mockImplementation(() => now);
+    });
+
+    afterEach(() => {
+        clockSpy.mockRestore();
+        delete global.fetch;
+    });
+
+    function okFetch() {
+        return jest.fn(async () => ({
+            ok: true,
+            json: async () => ({ blacklist: ["recovered-scam-xyz.com"] }),
+        }));
+    }
+
+    // jest.resetModules() clears the call record of a jest.fn, and simulating
+    // a worker restart is exactly that call. Anything counted across restarts
+    // has to be counted outside the mock.
+    function countingFetch(counter, response) {
+        return async () => {
+            counter.calls++;
+            return response();
+        };
+    }
+
+    test("a lastFetchTime in the future is discarded rather than trusted", async () => {
+        // Clock skew or a restored profile backup writes one. Every guard
+        // measures `Date.now() - stamp` and only tests the lower bound, so a
+        // stamp a year ahead would suppress updates for a year, and now that
+        // the value is persisted it would outlive every worker.
+        storageStore[DELTA_STORAGE_KEY] = {
+            blacklist: ["poisoned-scam-xyz.com"],
+            lastFetchTime: now + 365 * 24 * 60 * 60 * 1000,
+            lastAttemptTime: 0,
+        };
+        const mod = require("../src/shared/phishingDomains");
+        global.fetch = okFetch();
+
+        await mod.initPhishingList();
+
+        expect(global.fetch).toHaveBeenCalledTimes(1);
+        expect(mod.isPhishingDomain("recovered-scam-xyz.com")).toBe(true);
+        // And the record it leaves behind is sane, so recovery is permanent.
+        expect(
+            storageStore[DELTA_STORAGE_KEY].lastFetchTime,
+        ).toBeLessThanOrEqual(now);
+    });
+
+    test("a lastAttemptTime in the future does not suppress the retry", async () => {
+        storageStore[DELTA_STORAGE_KEY] = {
+            lastAttemptTime: now + 365 * 24 * 60 * 60 * 1000,
+        };
+        const mod = require("../src/shared/phishingDomains");
+        global.fetch = okFetch();
+
+        await mod.initPhishingList();
+        expect(global.fetch).toHaveBeenCalledTimes(1);
+    });
+
+    test("an oversized delta does not re-download on every worker wake", async () => {
+        // The delta and its freshness claim are both dropped, which is right,
+        // but nothing then says a fetch just happened. Chrome cycles the
+        // worker roughly every 30 seconds idle, so without the attempt stamp
+        // this is a full blocklist download per wake, forever.
+        const huge = [];
+        for (let i = 0; i < 20000; i++) {
+            huge.push(`oversize-scam-${i}-xyzxyzxyzxyzxyz.com`);
+        }
+        const counter = { calls: 0 };
+        global.fetch = countingFetch(counter, () => ({
+            ok: true,
+            json: async () => ({ blacklist: huge }),
+        }));
+
+        for (let wake = 0; wake < 4; wake++) {
+            const revived = restartWorker();
+            await revived.initPhishingList();
+            now += 30 * 1000; // idle timeout, worker torn down and revived
+        }
+
+        expect(counter.calls).toBe(1);
+        expect(storageStore[DELTA_STORAGE_KEY].blacklist).toBeUndefined();
+        expect(typeof storageStore[DELTA_STORAGE_KEY].lastAttemptTime).toBe(
+            "number",
+        );
+    });
+
+    test("a failing fetch is not retried on every worker wake either", async () => {
+        const counter = { calls: 0 };
+        global.fetch = countingFetch(counter, () => ({
+            ok: false,
+            status: 503,
+        }));
+
+        for (let wake = 0; wake < 4; wake++) {
+            const revived = restartWorker();
+            await revived.initPhishingList();
+            now += 30 * 1000;
+        }
+
+        expect(counter.calls).toBe(1);
+    });
+
+    test("the retry floor expires, so a failure is not permanent", async () => {
+        const {
+            MIN_FETCH_ATTEMPT_INTERVAL_MS,
+        } = require("../src/shared/phishingDomains");
+        const counter = { calls: 0 };
+        global.fetch = countingFetch(counter, () => ({
+            ok: false,
+            status: 503,
+        }));
+
+        await restartWorker().initPhishingList();
+        expect(counter.calls).toBe(1);
+
+        // Still inside the floor: no retry.
+        now += MIN_FETCH_ATTEMPT_INTERVAL_MS - 1000;
+        await restartWorker().initPhishingList();
+        expect(counter.calls).toBe(1);
+
+        // Past it: the extension goes back to the network.
+        now += 2000;
+        await restartWorker().initPhishingList();
+        expect(counter.calls).toBe(2);
+    });
+
+    test("the scheduled tick ignores the retry floor", async () => {
+        // The alarm period is far above the floor, but the floor exists to
+        // throttle wakes, not the schedule.
+        storageStore[DELTA_STORAGE_KEY] = { lastAttemptTime: now - 1000 };
+        const mod = require("../src/shared/phishingDomains");
+        global.fetch = okFetch();
+
+        await mod.refreshPhishingListOnSchedule();
+        expect(global.fetch).toHaveBeenCalledTimes(1);
+    });
+});