counters/internal/notify/notify_test.go

package notify

import (
	"context"
	"net/http"
	"net/http/httptest"
	"net/url"
	"strings"
	"sync"
	"sync/atomic"
	"testing"
	"time"
)

const tmpl = "https://admin.example/api/limits?level=$LEVEL&id=$ID&flow=$FLOW&period=$PERIOD&by=$ADDRESS&count=$COUNT&limit=$LIMIT"

func TestBuildURL(t *testing.T) {
	ev := Event{Level: "A", ID: "me@example.com", Flow: "o", Address: "me@example.com", Count: 100, Limit: 100}
	got := BuildURL(tmpl, ev)
	want := "https://admin.example/api/limits?level=A&id=me%40example.com&flow=o&period=d&by=me%40example.com&count=100&limit=100"
	if got != want {
		t.Errorf("BuildURL =\n %s\nwant\n %s", got, want)
	}
	// Dangerous characters in values are escaped, templates without placeholders pass through.
	ev.ID = "a b&c=d@x.y"
	u, err := url.Parse(BuildURL(tmpl, ev))
	if err != nil {
		t.Fatal(err)
	}
	if u.Query().Get("id") != "a b&c=d@x.y" {
		t.Errorf("id round-trip = %q", u.Query().Get("id"))
	}
	if got := BuildURL("https://x/static", ev); got != "https://x/static" {
		t.Errorf("static template changed: %s", got)
	}
}

func TestURLFor(t *testing.T) {
	cfg := Config{OrgURL: "o", AddressURL: "a", DomainURL: "d", WarnOrgURL: "wo", WarnAddressURL: "wa", WarnDomainURL: "wd"}
	for level, want := range map[string]string{"O": "o", "A": "a", "D": "d", "X": ""} {
		if got := cfg.URLFor(KindLimit, level); got != want {
			t.Errorf("URLFor(limit, %s) = %q, want %q", level, got, want)
		}
	}
	for level, want := range map[string]string{"O": "wo", "A": "wa", "D": "wd", "X": ""} {
		if got := cfg.URLFor(KindWarning, level); got != want {
			t.Errorf("URLFor(warning, %s) = %q, want %q", level, got, want)
		}
	}
}

// capture is an httptest handler recording requests.
type capture struct {
	mu       sync.Mutex
	requests []*http.Request
	status   []int // status to answer per call; last entry repeats
	calls    atomic.Int32
	delay    time.Duration
	inflight atomic.Int32
	maxSeen  atomic.Int32
}

func (c *capture) ServeHTTP(w http.ResponseWriter, r *http.Request) {
	n := c.inflight.Add(1)
	for {
		m := c.maxSeen.Load()
		if n <= m || c.maxSeen.CompareAndSwap(m, n) {
			break
		}
	}
	defer c.inflight.Add(-1)
	if c.delay > 0 {
		time.Sleep(c.delay)
	}
	i := int(c.calls.Add(1)) - 1
	c.mu.Lock()
	c.requests = append(c.requests, r.Clone(context.Background()))
	c.mu.Unlock()
	status := http.StatusOK
	if len(c.status) > 0 {
		if i < len(c.status) {
			status = c.status[i]
		} else {
			status = c.status[len(c.status)-1]
		}
	}
	w.WriteHeader(status)
}

type hooks struct {
	mu     sync.Mutex
	sent   []sentCall
	failed []failedCall
	done   chan struct{}
}
type sentCall struct {
	ev      Event
	url     string
	attempt int
}
type failedCall struct {
	ev       Event
	url      string
	attempts int
	err      error
}

func newHooks() *hooks { return &hooks{done: make(chan struct{}, 64)} }

func (h *hooks) Hooks() Hooks {
	return Hooks{
		Sent: func(ev Event, url string, attempt int) {
			h.mu.Lock()
			h.sent = append(h.sent, sentCall{ev, url, attempt})
			h.mu.Unlock()
			h.done <- struct{}{}
		},
		Failed: func(ev Event, url string, attempts int, err error) {
			h.mu.Lock()
			h.failed = append(h.failed, failedCall{ev, url, attempts, err})
			h.mu.Unlock()
			h.done <- struct{}{}
		},
	}
}

func (h *hooks) wait(t *testing.T, n int) {
	t.Helper()
	for i := 0; i < n; i++ {
		select {
		case <-h.done:
		case <-time.After(5 * time.Second):
			t.Fatalf("timeout waiting for notification outcome %d/%d", i+1, n)
		}
	}
}

func fastConfig(orgURL, addrURL, domURL string) Config {
	return Config{
		OrgURL: orgURL, AddressURL: addrURL, DomainURL: domURL,
		User: "api", Password: "secret",
		Timeout: 2 * time.Second, Attempts: 5, Backoff: time.Millisecond, MaxConcurrent: 8,
	}
}

func TestNotify_SendsToLevelURLWithBasicAuth(t *testing.T) {
	org, addr, dom := &capture{}, &capture{}, &capture{}
	so, sa, sd := httptest.NewServer(org), httptest.NewServer(addr), httptest.NewServer(dom)
	defer so.Close()
	defer sa.Close()
	defer sd.Close()
	q := "/api/limits?level=$LEVEL&id=$ID&flow=$FLOW&period=$PERIOD&by=$ADDRESS&count=$COUNT"
	h := newHooks()
	n := New(fastConfig(so.URL+q, sa.URL+q, sd.URL+q), h.Hooks())
	defer n.Shutdown(context.Background())

	ev := Event{TraceID: "tr", Level: "A", ID: "me@example.com", Flow: "o", Address: "me@example.com", Count: 100, Limit: 100}
	if !n.Notify(ev) {
		t.Fatal("Notify returned false for a configured level")
	}
	h.wait(t, 1)

	if org.calls.Load() != 0 || dom.calls.Load() != 0 || addr.calls.Load() != 1 {
		t.Fatalf("calls org=%d addr=%d dom=%d, want only addr", org.calls.Load(), addr.calls.Load(), dom.calls.Load())
	}
	r := addr.requests[0]
	if r.Method != http.MethodGet {
		t.Errorf("method = %s", r.Method)
	}
	if u, p, ok := r.BasicAuth(); !ok || u != "api" || p != "secret" {
		t.Errorf("basic auth = %q %q %v", u, p, ok)
	}
	qv := r.URL.Query()
	for k, want := range map[string]string{"level": "A", "id": "me@example.com", "flow": "o", "period": "d", "by": "me@example.com", "count": "100"} {
		if qv.Get(k) != want {
			t.Errorf("query %s = %q, want %q", k, qv.Get(k), want)
		}
	}
	if len(h.sent) != 1 || h.sent[0].attempt != 1 || h.sent[0].ev != ev || !strings.HasPrefix(h.sent[0].url, sa.URL) {
		t.Errorf("sent hook = %+v", h.sent)
	}

	// Org and domain levels route to their own URLs.
	n.Notify(Event{Level: "O", ID: "7"})
	n.Notify(Event{Level: "D", ID: "example.com"})
	h.wait(t, 2)
	if org.calls.Load() != 1 || dom.calls.Load() != 1 {
		t.Errorf("calls org=%d dom=%d, want 1 each", org.calls.Load(), dom.calls.Load())
	}
}

func TestNotify_EmptyURLSkips(t *testing.T) {
	h := newHooks()
	n := New(fastConfig("", "", ""), h.Hooks())
	if n.Notify(Event{Level: "A"}) || n.Notify(Event{Level: "Z"}) {
		t.Error("Notify should return false when no URL is configured for the level")
	}
	if err := n.Shutdown(context.Background()); err != nil {
		t.Fatal(err)
	}
	if len(h.sent)+len(h.failed) != 0 {
		t.Errorf("no hooks expected, got sent=%v failed=%v", h.sent, h.failed)
	}
}

func TestNotify_NoBasicAuthWithoutUser(t *testing.T) {
	c := &capture{}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.User, cfg.Password = "", ""
	n := New(cfg, h.Hooks())
	n.Notify(Event{Level: "O"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if _, _, ok := c.requests[0].BasicAuth(); ok {
		t.Error("Authorization header sent although no user is configured")
	}
}

func TestNotify_RetriesThenSucceeds(t *testing.T) {
	c := &capture{status: []int{500, 503, 200}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	n := New(fastConfig(s.URL+"/l?level=$LEVEL", "", ""), h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if c.calls.Load() != 3 || len(h.sent) != 1 || h.sent[0].attempt != 3 || len(h.failed) != 0 {
		t.Errorf("calls=%d sent=%+v failed=%+v; want success on attempt 3", c.calls.Load(), h.sent, h.failed)
	}
}

func TestNotify_GivesUpAfterAttempts(t *testing.T) {
	c := &capture{status: []int{500}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	n := New(fastConfig(s.URL+"/l?level=$LEVEL", "", ""), h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if c.calls.Load() != 5 || len(h.failed) != 1 || h.failed[0].attempts != 5 || len(h.sent) != 0 {
		t.Errorf("calls=%d failed=%+v sent=%+v; want 5 attempts then failure", c.calls.Load(), h.failed, h.sent)
	}
	if !strings.Contains(h.failed[0].err.Error(), "500") {
		t.Errorf("failure error should carry the status: %v", h.failed[0].err)
	}
}

// 4xx means a configuration problem (bad credentials, wrong URL): retrying is pointless.
func TestNotify_NoRetryOn4xx(t *testing.T) {
	c := &capture{status: []int{401}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	n := New(fastConfig(s.URL+"/l?level=$LEVEL", "", ""), h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if c.calls.Load() != 1 || len(h.failed) != 1 || h.failed[0].attempts != 1 {
		t.Errorf("calls=%d failed=%+v; want a single attempt", c.calls.Load(), h.failed)
	}
}

// The request reached the web app and only the answer is missing: it may have
// acted, so a retry could send the customer a second email.
func TestNotify_TimeoutAfterWriteIsNotRetried(t *testing.T) {
	c := &capture{delay: 300 * time.Millisecond}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.Timeout = 50 * time.Millisecond
	n := New(cfg, h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if len(h.failed) != 1 || h.failed[0].attempts != 1 {
		t.Fatalf("failed=%+v; want one failure after a single attempt", h.failed)
	}
	if !strings.Contains(h.failed[0].err.Error(), "outcome unknown") {
		t.Errorf("error should say the outcome is unknown: %v", h.failed[0].err)
	}
	waitCalls(t, c, 1)
	time.Sleep(100 * time.Millisecond)
	if c.calls.Load() != 1 {
		t.Errorf("web app calls = %d, want 1", c.calls.Load())
	}
}

// Nothing was delivered, so retrying cannot duplicate anything.
func TestNotify_RefusedConnectionIsRetried(t *testing.T) {
	s := httptest.NewServer(&capture{})
	addr := s.URL
	s.Close()
	h := newHooks()
	cfg := fastConfig(addr+"/l?level=$LEVEL", "", "")
	cfg.Attempts = 3
	n := New(cfg, h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	h.wait(t, 1)
	n.Shutdown(context.Background())
	if len(h.failed) != 1 || h.failed[0].attempts != 3 {
		t.Errorf("failed=%+v; want failure after 3 attempts", h.failed)
	}
}

// A notification waiting out its backoff must not hold a concurrency slot.
func TestNotify_BackoffReleasesSlot(t *testing.T) {
	c := &capture{status: []int{500, 200, 200}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.MaxConcurrent = 1
	cfg.Backoff = 400 * time.Millisecond
	n := New(cfg, h.Hooks())
	defer n.Shutdown(context.Background())
	n.Notify(Event{Level: "O", ID: "retrying"})
	waitCalls(t, c, 1)
	n.Notify(Event{Level: "O", ID: "second"})
	select {
	case <-h.done:
	case <-time.After(250 * time.Millisecond):
		t.Fatal("the second notification waited for the first one's backoff")
	}
	h.done <- struct{}{}
	h.wait(t, 2)
}

func waitCalls(t *testing.T, c *capture, n int32) {
	t.Helper()
	deadline := time.Now().Add(2 * time.Second)
	for c.calls.Load() < n {
		if time.Now().After(deadline) {
			t.Fatalf("calls = %d, want %d", c.calls.Load(), n)
		}
		time.Sleep(time.Millisecond)
	}
}

// Shutdown lets a pending retry finish while its deadline allows.
func TestNotify_ShutdownFinishesPendingRetries(t *testing.T) {
	c := &capture{status: []int{500, 200}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.Backoff = 100 * time.Millisecond
	n := New(cfg, h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	waitCalls(t, c, 1)
	ctx, cancel := context.WithTimeout(context.Background(), 3*time.Second)
	defer cancel()
	if err := n.Shutdown(ctx); err != nil {
		t.Fatal(err)
	}
	if len(h.sent) != 1 || h.sent[0].attempt != 2 || len(h.failed) != 0 {
		t.Errorf("sent=%+v failed=%+v; want delivery on attempt 2", h.sent, h.failed)
	}
}

// When the deadline cuts a retry short the failure reports the real attempt count.
func TestNotify_ShutdownDeadlineReportsRealAttempts(t *testing.T) {
	c := &capture{status: []int{500}}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.Backoff = 5 * time.Second
	n := New(cfg, h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})
	waitCalls(t, c, 1)
	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Millisecond)
	defer cancel()
	_ = n.Shutdown(ctx)
	h.wait(t, 1)
	if len(h.failed) != 1 || h.failed[0].attempts != 1 {
		t.Errorf("failed=%+v; want 1 real attempt", h.failed)
	}
}

func TestNotify_WarningUsesWarningURL(t *testing.T) {
	breach, warn := &capture{}, &capture{}
	sb, sw := httptest.NewServer(breach), httptest.NewServer(warn)
	defer sb.Close()
	defer sw.Close()
	h := newHooks()
	cfg := fastConfig(sb.URL+"/l?level=$LEVEL", "", "")
	cfg.WarnOrgURL = sw.URL + "/w?level=$LEVEL&limit=$LIMIT&percent=$PERCENT"
	n := New(cfg, h.Hooks())
	defer n.Shutdown(context.Background())
	if !n.Notify(Event{Kind: KindWarning, Level: "O", ID: "7", Limit: 100, Count: 80, Percent: 80}) {
		t.Fatal("warning refused")
	}
	h.wait(t, 1)
	if breach.calls.Load() != 0 || warn.calls.Load() != 1 {
		t.Fatalf("breach=%d warn=%d, want the warning URL only", breach.calls.Load(), warn.calls.Load())
	}
	if q := warn.requests[0].URL.Query(); q.Get("percent") != "80" || q.Get("limit") != "100" {
		t.Errorf("query = %v", q)
	}
	if n.Notify(Event{Kind: KindWarning, Level: "A"}) {
		t.Error("a level with no warning URL must be refused")
	}
}

func TestNotify_BoundedConcurrency(t *testing.T) {
	c := &capture{delay: 50 * time.Millisecond}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	cfg := fastConfig(s.URL+"/l?level=$LEVEL", "", "")
	cfg.MaxConcurrent = 2
	n := New(cfg, h.Hooks())
	for i := 0; i < 10; i++ {
		n.Notify(Event{Level: "O", ID: "7"})
	}
	h.wait(t, 10)
	n.Shutdown(context.Background())
	if c.maxSeen.Load() > 2 {
		t.Errorf("max concurrent requests = %d, want <= 2", c.maxSeen.Load())
	}
	if c.calls.Load() != 10 {
		t.Errorf("calls = %d, want 10", c.calls.Load())
	}
}

// Shutdown waits for in-flight notifications, bounded by the context.
func TestNotify_ShutdownDrainsAndRespectsContext(t *testing.T) {
	c := &capture{delay: 200 * time.Millisecond}
	s := httptest.NewServer(c)
	defer s.Close()
	h := newHooks()
	n := New(fastConfig(s.URL+"/l?level=$LEVEL", "", ""), h.Hooks())
	n.Notify(Event{Level: "O", ID: "7"})

	ctx, cancel := context.WithTimeout(context.Background(), 20*time.Millisecond)
	defer cancel()
	if err := n.Shutdown(ctx); err == nil {
		t.Error("Shutdown with an expired context should return its error")
	}
	if err := n.Shutdown(context.Background()); err != nil {
		t.Errorf("second Shutdown: %v", err)
	}
	if c.calls.Load() != 1 || len(h.sent) != 1 {
		t.Errorf("in-flight notification was not completed: calls=%d sent=%d", c.calls.Load(), len(h.sent))
	}
	if n.Notify(Event{Level: "O"}) {
		t.Error("Notify after Shutdown should be refused")
	}
}

func TestNew_Defaults(t *testing.T) {
	n := New(Config{OrgURL: "https://x/?level=$LEVEL"}, Hooks{})
	defer n.Shutdown(context.Background())
	if n.cfg.Attempts != 5 || n.cfg.Backoff != time.Second || n.cfg.MaxConcurrent != 8 || n.cfg.Timeout != 15*time.Second {
		t.Errorf("defaults not applied: %+v", n.cfg)
	}
}