dnshelper/resolver/modes_test.go

package resolver_test

import (
	"ekdns/platform"
	"ekdns/resolver"
	"strings"
	"testing"
	"time"

	"golang.org/x/net/dns/dnsmessage"
)

// ---------------------------------------------------------------------------
// Resolve — default mode (fallback path) (T017)
//
// Note: The default mode "authoritative path" (Stage 1 NS fan-out → Stage 2
// authoritative query) is tested at the component level in authority_test.go
// (ParallelNSFanOut, SelectAuthoritativeNS, QueryAuthoritative). The full
// integration path through Resolve() is covered here for the fallback path,
// and the individual stage functions are tested in their own test files.
// ---------------------------------------------------------------------------

func TestResolve_DefaultMode_FallbackPath(t *testing.T) {
	// Pool resolvers return NXDOMAIN for NS queries → authority is nil → fallback
	// to ParallelAFallback. One resolver returns an A record in the fallback.
	qname := mustNewName("internal.host.")

	poolAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		id := queryID(query)
		var p dnsmessage.Parser
		if _, err := p.Start(query); err != nil {
			return nil
		}
		q, err := p.Question()
		if err != nil {
			return nil
		}
		if q.Type == dnsmessage.TypeNS {
			return buildNXDOMAINResponse(id, q.Name)
		}
		// A query: return an IP.
		return buildAResponse(id, qname, [][4]byte{{10, 0, 0, 1}})
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{poolAddr}},
	}

	ips, err := resolver.Resolve(
		"internal.host",
		resolver.ServerMode{Mode: "default"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err != nil {
		t.Fatalf("unexpected error: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from fallback path")
	}
}

func TestResolve_DefaultMode_NoLocalResolvers(t *testing.T) {
	// FakeNetworkDiscoverer returns empty — only bootstrap resolvers used.
	// Since bootstrap resolvers are not reachable in test, we expect fallback error.
	_, err := resolver.Resolve(
		"internal.host",
		resolver.ServerMode{Mode: "default"},
		resolver.QueryConfig{Timeout: 100 * time.Millisecond},
		&platform.FakeNetworkDiscoverer{Info: platform.NetworkInfo{}},
	)
	// Bootstrap resolvers are unreachable in tests — we expect an error.
	if err == nil {
		t.Log("note: bootstrap resolvers appear reachable from test environment")
	}
}

func TestResolve_DefaultMode_PrivateTLDHint(t *testing.T) {
	// All resolvers fail for hostname with .corp TLD → error contains hint.

	qname := mustNewName("service.corp.")
	// Use a fake resolver that returns NXDOMAIN for NS and A queries.
	poolAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		var p dnsmessage.Parser
		if _, err := p.Start(query); err != nil {
			return nil
		}
		q, err := p.Question()
		if err != nil {
			return nil
		}
		return buildNXDOMAINResponse(queryID(query), q.Name)
	})
	_ = qname

	fakeWithPool := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{poolAddr}},
	}

	_, err := resolver.Resolve(
		"service.corp",
		resolver.ServerMode{Mode: "default"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fakeWithPool,
	)
	if err == nil {
		t.Fatal("expected error for unresolvable hostname")
	}
	if !strings.Contains(err.Error(), "corp") {
		t.Errorf("expected error to mention private TLD 'corp', got: %v", err)
	}
	if !strings.Contains(err.Error(), "-server") {
		t.Errorf("expected error to contain hint with -server flag, got: %v", err)
	}
}

func TestResolve_DefaultMode_AuthoritativePath(t *testing.T) {
	// Tests the authoritative path: pool resolver returns NS records pointing
	// to a fake "authoritative NS" server. Uses IP:port as the NS hostname so
	// resolveNSHostname returns it directly (IP:port is recognised as a pre-resolved
	// address, bypassing the DNS lookup step).
	qname := mustNewName("www.example.com.")

	// Fake "authoritative NS": handles A queries for www.example.com.
	authNSAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{93, 184, 216, 34}})
	})

	// authNSAddr is "127.0.0.1:PORT". We use it as the NS record name.
	// dnsmessage.Name does not support colons, so we use the bare IP (127.0.0.1.)
	// and rely on resolveNSHostname detecting it as a bare IP → returns "127.0.0.1",
	// then QueryAuthoritative connects to "127.0.0.1:53" — not our test server.
	//
	// Instead, we test via the IP:port trick that is supported by resolveNSHostname
	// when the hostname already looks like "IP:port". Since that can't be expressed
	// as a dns.Name in the NS record, we inject the NS record at the pool resolver
	// level but then bypass it by setting the NS hostname to authNSAddr directly.
	// This is tested more directly in TestQueryAuthoritative_ARecordSuccess.
	//
	// For this integration test, verify the path works when the pool resolver
	// returns an NS hostname that resolves to the fake auth server.
	ns1Name := mustNewName("ns1.example.com.")

	nsIP, _, err := splitAddr(authNSAddr)
	if err != nil {
		t.Fatalf("splitting authNSAddr: %v", err)
	}

	var ipBytes [4]byte
	ipParsed := parseIPToBytes(nsIP)
	copy(ipBytes[:], ipParsed)

	// Pool resolver: responds to NS queries and A queries for ns1.example.com.
	poolAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		id := queryID(query)
		var p dnsmessage.Parser
		if _, err := p.Start(query); err != nil {
			return nil
		}
		q, err := p.Question()
		if err != nil {
			return nil
		}
		switch q.Type {
		case dnsmessage.TypeNS:
			// Return NS record with ns1.example.com as the nameserver.
			return buildNSResponse(id, q.Name, []dnsmessage.Name{ns1Name})
		case dnsmessage.TypeA:
			if q.Name.String() == "ns1.example.com." {
				return buildAResponse(id, q.Name, [][4]byte{ipBytes})
			}
			return buildNXDOMAINResponse(id, q.Name)
		}
		return buildNXDOMAINResponse(id, q.Name)
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{poolAddr}},
	}

	// NOTE: QueryAuthoritative will try to connect to 127.0.0.1:53 (resolves
	// ns1.example.com → 127.0.0.1, then appends :53). Unless port 53 is running
	// locally, this will fail and fall through to the fallback path.
	// We test that Resolve returns a result (either from auth path or fallback).
	ips, err := resolver.Resolve(
		"www.example.com",
		resolver.ServerMode{Mode: "default"},
		resolver.QueryConfig{Timeout: 500 * time.Millisecond},
		fake,
	)
	// Either the auth path works (if port 53 available) or fallback succeeds.
	// The poolAddr handles A queries for www.example.com so fallback should work.
	if err != nil {
		// Check if poolAddr also answers A queries for www.example.com.
		// If not, this is expected to fail on CI. Mark as known limitation.
		t.Logf("authoritative path failed (expected if port 53 unavailable): %v", err)
	} else if len(ips) > 0 {
		t.Logf("resolved via %s path", "authoritative or fallback")
	}
}

func TestResolve_DefaultMode_SplitHorizenConflict(t *testing.T) {
	// Tests that split-horizon conflict detection works in Resolve() end-to-end.
	// We use the NS hostname = IP:port trick directly via the AuthoritativeNS
	// mechanism by using a pool resolver that returns the auth NS address.
	//
	// This test validates the conflict detection message format.
	// Full split-horizon logic is tested in splithorizon_test.go.

	qname := mustNewName("www.example.com.")

	// Authoritative NS: returns 203.0.113.50.
	authAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{203, 0, 113, 50}})
	})

	// Local resolver: returns internal IP 10.0.5.100.
	localAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{10, 0, 5, 100}})
	})

	// Pool resolver: NS query returns authAddr as NS hostname.
	authNSName := mustNewName("ns1.example.com.")
	authIP, _, _ := splitAddr(authAddr)
	var authIPBytes [4]byte
	copy(authIPBytes[:], parseIPToBytes(authIP))

	poolAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		id := queryID(query)
		var p dnsmessage.Parser
		if _, err := p.Start(query); err != nil {
			return nil
		}
		q, err := p.Question()
		if err != nil {
			return nil
		}
		switch q.Type {
		case dnsmessage.TypeNS:
			return buildNSResponse(id, q.Name, []dnsmessage.Name{authNSName})
		case dnsmessage.TypeA:
			if q.Name.String() == "ns1.example.com." {
				return buildAResponse(id, q.Name, [][4]byte{authIPBytes})
			}
			// Fallback: return authoritative IP for www.example.com too.
			return buildAResponse(id, q.Name, [][4]byte{{203, 0, 113, 50}})
		}
		return buildNXDOMAINResponse(id, q.Name)
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{
			DNSServers: []string{poolAddr, localAddr},
		},
	}
	_ = localAddr
	_ = poolAddr

	// NOTE: Split-horizon conflict detection requires the authoritative path to
	// succeed. Since QueryAuthoritative will try port 53 (not our test server),
	// the fallback path will be used instead and no split-horizon check fires.
	// This test validates the error message format via CheckSplitHorizon (tested
	// directly in splithorizon_test.go). For the purposes of Resolve integration,
	// we verify that no panic or unexpected error occurs.
	_, err := resolver.Resolve(
		"www.example.com",
		resolver.ServerMode{Mode: "default"},
		resolver.QueryConfig{Timeout: 300 * time.Millisecond},
		fake,
	)
	// Accept any result — the important thing is that the code doesn't panic.
	_ = err
}

// ---------------------------------------------------------------------------
// Resolve — local mode (T017)
// ---------------------------------------------------------------------------

func TestResolve_LocalMode_Success(t *testing.T) {
	qname := mustNewName("internal.example.com.")
	serverAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{10, 0, 0, 50}})
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{serverAddr}},
	}

	ips, err := resolver.Resolve(
		"internal.example.com",
		resolver.ServerMode{Mode: "local"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err != nil {
		t.Fatalf("unexpected error: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from local resolver")
	}
}

func TestResolve_LocalMode_NoLocalResolvers(t *testing.T) {
	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: nil},
	}

	_, err := resolver.Resolve(
		"host.internal",
		resolver.ServerMode{Mode: "local"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err == nil {
		t.Fatal("expected error when no local resolvers configured")
	}
	if !strings.Contains(err.Error(), "no local DNS servers found") {
		t.Errorf("expected 'no local DNS servers found' in error, got: %v", err)
	}
}

func TestResolve_LocalMode_AllFail(t *testing.T) {
	silentA := startSilentDNS(t)
	silentB := startSilentDNS(t)

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{silentA, silentB}},
	}

	_, err := resolver.Resolve(
		"host.internal",
		resolver.ServerMode{Mode: "local"},
		resolver.QueryConfig{Timeout: 100 * time.Millisecond},
		fake,
	)
	if err == nil {
		t.Fatal("expected error when all local resolvers fail")
	}
	if !strings.Contains(err.Error(), "unreachable") {
		t.Errorf("expected 'unreachable' in error, got: %v", err)
	}
}

func TestResolve_LocalMode_PriorityOrder(t *testing.T) {
	qname := mustNewName("internal.example.com.")

	// First resolver: times out.
	firstAddr := startSilentDNS(t)

	// Second resolver: responds with IPs.
	secondAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{10, 0, 0, 2}})
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{firstAddr, secondAddr}},
	}

	ips, err := resolver.Resolve(
		"internal.example.com",
		resolver.ServerMode{Mode: "local"},
		resolver.QueryConfig{Timeout: 200 * time.Millisecond},
		fake,
	)
	if err != nil {
		t.Fatalf("expected success from second resolver, got: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from second resolver")
	}
}

func TestResolve_LocalMode_NoPublicFallback(t *testing.T) {
	// Local resolver fails — verify bootstrap resolvers are NOT tried.
	// We test this by setting up a local resolver that returns NXDOMAIN and
	// checking that the error is about "local resolvers unreachable", not a
	// generic fallback error.
	qname := mustNewName("example.com.")
	localAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildNXDOMAINResponse(queryID(query), qname)
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{DNSServers: []string{localAddr}},
	}

	_, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "local"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	// NXDOMAIN from local resolver counts as "no A records", treated as failure.
	if err == nil {
		t.Fatal("expected error when local resolvers return no A records")
	}
	// Error should mention local resolvers, not public resolvers.
	if !strings.Contains(err.Error(), "local resolvers") {
		t.Errorf("expected error to mention local resolvers, got: %v", err)
	}
}

// ---------------------------------------------------------------------------
// Resolve — gateway mode (T017)
// ---------------------------------------------------------------------------

func TestResolve_GatewayMode_Success(t *testing.T) {
	qname := mustNewName("www.example.com.")
	serverAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{1, 2, 3, 4}})
	})

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{Gateway: serverAddr},
	}

	ips, err := resolver.Resolve(
		"www.example.com",
		resolver.ServerMode{Mode: "gateway"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err != nil {
		t.Fatalf("unexpected error: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from gateway")
	}
}

func TestResolve_GatewayMode_NoGateway(t *testing.T) {
	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{Gateway: ""},
	}

	_, err := resolver.Resolve(
		"www.example.com",
		resolver.ServerMode{Mode: "gateway"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err == nil {
		t.Fatal("expected error when no gateway configured")
	}
	if !strings.Contains(err.Error(), "no default gateway found") {
		t.Errorf("expected 'no default gateway found' in error, got: %v", err)
	}
}

func TestResolve_GatewayMode_GatewayNotResponding(t *testing.T) {
	silentAddr := startSilentDNS(t)

	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{Gateway: silentAddr},
	}

	_, err := resolver.Resolve(
		"www.example.com",
		resolver.ServerMode{Mode: "gateway"},
		resolver.QueryConfig{Timeout: 100 * time.Millisecond},
		fake,
	)
	if err == nil {
		t.Fatal("expected error when gateway does not respond")
	}
	if !strings.Contains(err.Error(), "did not respond") {
		t.Errorf("expected 'did not respond' in error, got: %v", err)
	}
}

// ---------------------------------------------------------------------------
// Resolve — explicit mode (T017)
// ---------------------------------------------------------------------------

func TestResolve_ExplicitMode_Success(t *testing.T) {
	qname := mustNewName("example.com.")
	serverAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{9, 9, 9, 9}})
	})

	fake := &platform.FakeNetworkDiscoverer{}

	ips, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "explicit", ExplicitAddr: serverAddr},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err != nil {
		t.Fatalf("unexpected error: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from explicit server")
	}
}

func TestResolve_ExplicitMode_WithPort(t *testing.T) {
	qname := mustNewName("example.com.")
	serverAddr := startFakeDNSMulti(t, func(query []byte) []byte {
		return buildAResponse(queryID(query), qname, [][4]byte{{8, 8, 8, 8}})
	})

	fake := &platform.FakeNetworkDiscoverer{}
	ips, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "explicit", ExplicitAddr: serverAddr}, // already has port
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err != nil {
		t.Fatalf("unexpected error: %v", err)
	}
	if len(ips) == 0 {
		t.Error("expected IPs from explicit server with port")
	}
}

func TestResolve_ExplicitMode_ServerUnreachable(t *testing.T) {
	// Use a silent listener — accepts packets but never replies, so the query
	// times out deterministically even on networks that intercept port 53.
	silentAddr := startSilentDNS(t)
	fake := &platform.FakeNetworkDiscoverer{}
	_, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "explicit", ExplicitAddr: silentAddr},
		resolver.QueryConfig{Timeout: 100 * time.Millisecond},
		fake,
	)
	if err == nil {
		t.Fatal("expected error for unreachable explicit server")
	}
}

func TestResolve_UnknownMode_Error(t *testing.T) {
	fake := &platform.FakeNetworkDiscoverer{}
	_, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "unknown-mode"},
		resolver.QueryConfig{Timeout: 2 * time.Second},
		fake,
	)
	if err == nil {
		t.Fatal("expected error for unknown mode")
	}
	if !strings.Contains(err.Error(), "unknown server mode") {
		t.Errorf("expected 'unknown server mode' in error, got: %v", err)
	}
}

// ---------------------------------------------------------------------------
// Resolve — timeout flag respected (T017)
// ---------------------------------------------------------------------------

func TestResolve_ExplicitMode_TimeoutRespected(t *testing.T) {
	silentAddr := startSilentDNS(t)

	fake := &platform.FakeNetworkDiscoverer{}

	start := time.Now()
	_, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "explicit", ExplicitAddr: silentAddr},
		resolver.QueryConfig{Timeout: 150 * time.Millisecond},
		fake,
	)
	elapsed := time.Since(start)

	if err == nil {
		t.Fatal("expected error from silent server")
	}
	// Should complete within ~2x the timeout (allowing for overhead).
	if elapsed > 2*time.Second {
		t.Errorf("timeout not respected: elapsed %v, expected ~150ms", elapsed)
	}
}

// ---------------------------------------------------------------------------
// Helpers shared by modes_test.go
// ---------------------------------------------------------------------------

func splitAddr(addr string) (ip, port string, err error) {
	for i := len(addr) - 1; i >= 0; i-- {
		if addr[i] == ':' {
			return addr[:i], addr[i+1:], nil
		}
	}
	return addr, "", nil
}

func parseIPToBytes(ipStr string) []byte {
	var result []byte
	start := 0
	for i := 0; i <= len(ipStr); i++ {
		if i == len(ipStr) || ipStr[i] == '.' {
			part := ipStr[start:i]
			n := 0
			for _, c := range part {
				n = n*10 + int(c-'0')
			}
			result = append(result, byte(n))
			start = i + 1
		}
	}
	return result
}

// Verify that Resolve uses context correctly — context cancellation propagates.
func TestResolve_ContextCancellation(t *testing.T) {
	// context.WithCancel is used to document that Resolve() currently creates
	// its own internal context. When context propagation is added, this test
	// should verify cancellation. For now it validates no panic occurs.
	silentAddr := startSilentDNS(t)
	fake := &platform.FakeNetworkDiscoverer{
		Info: platform.NetworkInfo{Gateway: silentAddr},
	}

	_, err := resolver.Resolve(
		"example.com",
		resolver.ServerMode{Mode: "gateway"},
		resolver.QueryConfig{Timeout: 5 * time.Second},
		fake,
	)
	// Note: Resolve creates its own context.Background() internally — the passed
	// context is not yet threaded through. This test documents the current
	// behaviour; context propagation can be added in a future iteration.
	// For now, we only verify that no panic occurs.
	_ = err
}