webui4frpc/internal/httpapi/forward_revoke_test.go

package httpapi

import (
	"bytes"
	"context"
	"encoding/json"
	"net/http"
	"net/http/httptest"
	"path/filepath"
	"testing"

	"webui4frpc/internal/cluster"
	"webui4frpc/internal/process"
	"webui4frpc/internal/store"
)

// newRingTestHandler builds a Handler WITH a ring engine attached, so the
// paths that publish tasks into the token actually execute. newTestHandler
// leaves Ring nil, which silently skips them — a test built on it can pass
// while the publish side is completely broken.
func newRingTestHandler(t *testing.T) (*Handler, *cluster.Engine, *httptest.Server) {
	t.Helper()
	dir := t.TempDir()
	st, err := store.New(filepath.Join(dir, "test.db"))
	if err != nil {
		t.Fatal(err)
	}
	t.Cleanup(func() { _ = st.Close() })

	pm := process.NewManager(process.Options{
		ConfigsDir:      filepath.Join(dir, "configs"),
		LogsDir:         filepath.Join(dir, "logs"),
		BinaryPath:      func() string { return "" },
		Render:          func(string) ([]byte, error) { return []byte(`{}`), nil },
		AutoRestart:     func(string) bool { return false },
		RestartInterval: func() int { return 5 },
	})
	ring := cluster.NewEngine("n1", "n1:7500", "u", "p", "0.1.0", nil,
		&cluster.AppHandler{},
		func(ctx context.Context, next string, tk *cluster.Token) error { return nil },
		"n1:7500", true, "")
	h := &Handler{Store: st, Process: pm, WorkDir: dir, User: "admin", Password: "pw", Ring: ring}
	mux, err := NewServeMux(h)
	if err != nil {
		t.Fatal(err)
	}
	ts := httptest.NewServer(mux)
	t.Cleanup(ts.Close)
	return h, ring, ts
}

func saveCanvas(t *testing.T, srv *httptest.Server, body string) {
	t.Helper()
	req, _ := http.NewRequest(http.MethodPut, srv.URL+"/api/manager/canvas", bytes.NewBufferString(body))
	req.SetBasicAuth("admin", "pw")
	resp, err := srv.Client().Do(req)
	if err != nil {
		t.Fatal(err)
	}
	resp.Body.Close()
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("canvas save status = %d", resp.StatusCode)
	}
}

// TestStopForwardPublishesDisabledFlagInRevokeTask is the regression test for
// the actual defect.
//
// stopForward() read the link, called SetLinkDisabled(true), and then handed
// the STALE copy (disabled=false) to RevokeTask. The revoke travels to the
// node that OWNS the forward, and that node's Claim/Revoke path keys off the
// flag — so a stale false meant:
//   - the owner could not tell the stop was deliberate, and
//   - nothing retired the topology entry,
//
// so the next restart's reconcile re-claimed the forward and spawned a worker
// for something the user had stopped (seen live: endless connection-refused
// against an intentionally-down service).
//
// This asserts the flag ON THE PUBLISHED TASK, which is the value that was
// actually wrong. It cannot be satisfied by the store write alone.
func TestStopForwardPublishesDisabledFlagInRevokeTask(t *testing.T) {
	_, ring, ts := newRingTestHandler(t)

	saveCanvas(t, ts, `{
		"locals": [{"name":"svc","ip":"127.0.0.1","port":59999,"protocol":"tcp"}],
		"remotes": [{"name":"srv-a","ip":"1.2.3.4","port":7000,"enabled":true}],
		"links": [{"local":"svc","remote":"srv-a","remotePort":45999}]
	}`)

	// Stop the forward over the API.
	b, _ := json.Marshal(stopForwardReq{"svc", "srv-a", 45999})
	req, _ := http.NewRequest(http.MethodPost, ts.URL+"/api/manager/forwards/stop", bytes.NewReader(b))
	req.SetBasicAuth("admin", "pw")
	resp, err := ts.Client().Do(req)
	if err != nil {
		t.Fatal(err)
	}
	resp.Body.Close()
	if resp.StatusCode != http.StatusOK {
		t.Fatalf("stop status = %d", resp.StatusCode)
	}

	// Find the revoke task that was published into the token.
	var revoke *cluster.Task
	for _, tk := range ring.State().PendingList() {
		if tk.Revoke && tk.Local.Name == "svc" && tk.Link.RemotePort == 45999 {
			revoke = tk
			break
		}
	}
	if revoke == nil {
		t.Fatal("stop did not publish a revoke task for the forward")
	}
	if !revoke.Link.Disabled {
		t.Fatal("the published revoke task carries disabled=false — the owner node cannot tell " +
			"this stop was deliberate, which is the bug that let stopped forwards resurrect")
	}
}

// TestStopThenStartPublishesRestartTask guards the failure mode that
// mark-don't-remove introduces, and that only shows up on the WIRE.
//
// A stop keeps the topology entry (it is the carrier for the flag), so on
// re-enable:
//   - SubmitTask dedupes, because the entry exists;
//   - the claim path discards any task for a forward that already has an owner.
//
// Both channels therefore refuse, no task is published, the owner never learns
// about the re-enable, and the forward stays stopped forever — a forward the
// user can stop but never restart.
//
// Asserting the task is PUBLISHED is the point: asserting only that the flag
// cleared would pass while nothing reached the owner. (The earlier version of
// this test did exactly that and stayed green against the broken code.)
func TestStopThenStartPublishesRestartTask(t *testing.T) {
	_, ring, ts := newRingTestHandler(t)

	saveCanvas(t, ts, `{
		"locals": [{"name":"svc","ip":"127.0.0.1","port":59999,"protocol":"tcp"}],
		"remotes": [{"name":"srv-a","ip":"1.2.3.4","port":7000,"enabled":true}],
		"links": [{"local":"svc","remote":"srv-a","remotePort":45999}]
	}`)
	// Claim it so a topology entry exists (that is what makes the two normal
	// channels refuse later).
	if _, err := ring.OnToken(context.Background(), &cluster.Token{Cycle: 1, State: *ring.State()}); err != nil {
		t.Fatal(err)
	}
	if !ring.HasActiveTask("svc", "srv-a", 45999) {
		t.Fatalf("precondition: forward should be active, topo=%+v", ring.State().TopologyList())
	}

	forwards := func(action string) {
		t.Helper()
		b, _ := json.Marshal(stopForwardReq{"svc", "srv-a", 45999})
		req, _ := http.NewRequest(http.MethodPost, ts.URL+"/api/manager/forwards/"+action, bytes.NewReader(b))
		req.SetBasicAuth("admin", "pw")
		resp, err := ts.Client().Do(req)
		if err != nil {
			t.Fatal(err)
		}
		resp.Body.Close()
		if resp.StatusCode != http.StatusOK {
			t.Fatalf("%s status = %d", action, resp.StatusCode)
		}
	}

	// --- stop: entry kept, marked disabled -------------------------------
	forwards("stop")
	if d, known := ring.TopologyDisabled("svc", "srv-a", 45999); !known || !d {
		t.Fatalf("stop did not mark the topology entry disabled (known=%v disabled=%v)", known, d)
	}
	if ring.HasActiveTask("svc", "srv-a", 45999) {
		t.Fatal("a stopped forward must not count as active")
	}

	// --- start: a task MUST reach the owner ------------------------------
	forwards("start")
	if d, _ := ring.TopologyDisabled("svc", "srv-a", 45999); d {
		t.Fatal("start did not clear the disabled flag")
	}
	if !ring.HasActiveTask("svc", "srv-a", 45999) {
		t.Fatal("after start the forward must be active again")
	}

	// The actual regression: something has to be queued for the owner. The
	// re-enable must be published as a restart task, since a plain creation task
	// would be deduped or discarded.
	var restart *cluster.Task
	for _, tk := range ring.State().PendingList() {
		if tk.Restart && tk.Local.Name == "svc" && tk.Link.RemotePort == 45999 {
			restart = tk
			break
		}
	}
	if restart == nil {
		t.Fatalf("start published no restart task — the owner would never bring the "+
			"worker back, leaving the forward permanently stopped (pending=%+v)",
			ring.State().PendingList())
	}
	if restart.Link.Disabled {
		t.Fatal("the restart task carries disabled=true, so the owner would re-apply the stop")
	}
}