routewatch/internal/server/handlers_internal_test.go

package server

import (
	"context"
	"encoding/json"
	"errors"
	"html"
	"net/http"
	"net/http/httptest"
	"runtime"
	"slices"
	"strconv"
	"strings"
	"sync/atomic"
	"testing"
	"time"

	"git.eeqj.de/sneak/routewatch/internal/config"
	"git.eeqj.de/sneak/routewatch/internal/database"
	"git.eeqj.de/sneak/routewatch/internal/logger"
	"git.eeqj.de/sneak/routewatch/internal/metrics"
	"git.eeqj.de/sneak/routewatch/internal/streamer"
	"git.eeqj.de/sneak/routewatch/pkg/asinfo"
)

// The prefix and peer addresses the prefix page tests store routes for.
const (
	testPrefixV4 = "192.0.2.0/24"
	testPeerV4   = "198.51.100.1"
	testPeerV6   = "2001:db8::1"
)

// Paths several tests request.
const (
	asPagePath           = "/as/64500"
	prefixLengthPagePath = "/prefixlength/24"
	statusJSONPath       = "/status.json"
	statsPath            = "/api/v1/stats"
)

// The names the stats handler tests report the two stats handlers by.
const (
	statusJSONHandlerName = "status.json"
	statsHandlerName      = "stats"
)

// blockingStatsDB embeds database.Store (left nil) and overrides only
// GetStatsContext, which blocks until release is closed. The stats handlers
// call it in a goroutine; every other Store method is unused on the timeout
// path and would panic if called.
type blockingStatsDB struct {
	database.Store

	release chan struct{}
}

func (d blockingStatsDB) GetStatsContext(_ context.Context) (database.Stats, error) {
	<-d.release

	return database.Stats{}, nil
}

// TestStatsHandlersDoNotLeakOnTimeout drives each stats handler repeatedly with
// a request whose context times out before the database responds, then releases
// the blocked queries and asserts the goroutine count returns to its starting
// value. Before the fix the per-request goroutine sent on an unbuffered channel
// that nothing received once the timeout won, so it blocked forever and every
// poll leaked one goroutine.
//
//nolint:paralleltest // counts goroutines, so no other test may run alongside
func TestStatsHandlersDoNotLeakOnTimeout(t *testing.T) {
	release := make(chan struct{})
	db := blockingStatsDB{release: release}
	s := New(db, streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})

	handlers := map[string]http.HandlerFunc{
		statusJSONHandlerName: s.handleStatusJSON(),
		statsHandlerName:      s.handleStats(),
	}

	baseline := settledGoroutineCount()

	const (
		iterations     = 20
		requestTimeout = 50 * time.Millisecond
	)
	for _, handler := range handlers {
		for range iterations {
			ctx, cancel := context.WithTimeout(context.Background(), requestTimeout)
			req := httptest.NewRequestWithContext(ctx, http.MethodGet, "/", nil)
			handler(httptest.NewRecorder(), req)
			cancel()
		}
	}

	// Let the blocked queries finish; with buffered channels each goroutine's
	// send now succeeds and the goroutine exits.
	close(release)

	if !waitForGoroutines(baseline) {
		t.Fatalf("goroutines did not return to baseline %d, got %d",
			baseline, runtime.NumGoroutine())
	}
}

// TestStatsHandlersAnswerFromMemory checks that both stats handlers answer 200
// with the live route counts and the prefix distribution while the database is
// closed, so that any query would fail: the request path reads them from
// memory. The prefix distribution query it used to run read every live route
// and, on a large database, took the whole 4-second deadline, so
// /api/v1/stats answered 500 (https://git.eeqj.de/sneak/routewatch/issues/30).
// The oldest and newest route times still come from one-row lookups at the ends
// of an index; with the database closed they are left out of the answer.
func TestStatsHandlersAnswerFromMemory(t *testing.T) {
	t.Parallel()

	db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
	if err != nil {
		t.Fatalf("database.New: %v", err)
	}

	ts := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)

	err = db.UpsertLiveRouteBatch([]*database.LiveRoute{
		{
			Prefix: "198.51.100.0/24", MaskLength: 24, IPVersion: 4,
			OriginASN: 64500, PeerIP: "192.0.2.1", ASPath: []int{64500},
			NextHop: "192.0.2.1", LastUpdated: ts,
		},
		{
			Prefix: "2001:db8::/32", MaskLength: 32, IPVersion: 6,
			OriginASN: 64501, PeerIP: testPeerV6, ASPath: []int{64501},
			NextHop: testPeerV6, LastUpdated: ts,
		},
	})
	if err != nil {
		t.Fatalf("UpsertLiveRouteBatch: %v", err)
	}

	err = db.Close()
	if err != nil {
		t.Fatalf("Close: %v", err)
	}

	s := New(db, streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
	handlers := map[string]http.HandlerFunc{
		statusJSONHandlerName: s.handleStatusJSON(),
		statsHandlerName:      s.handleStats(),
	}

	for name, handler := range handlers {
		rec := httptest.NewRecorder()
		handler(rec, httptest.NewRequestWithContext(t.Context(), http.MethodGet, "/", nil))

		if rec.Code != http.StatusOK {
			t.Errorf("%s: status %d, want %d; body %s",
				name, rec.Code, http.StatusOK, rec.Body)

			continue
		}

		//nolint:tagliatelle // field names are the existing JSON API
		var body struct {
			Data struct {
				IPv4Routes       int                           `json:"ipv4_routes"`
				IPv6Routes       int                           `json:"ipv6_routes"`
				IPv4Distribution []database.PrefixDistribution `json:"ipv4_prefix_distribution"`
				IPv6Distribution []database.PrefixDistribution `json:"ipv6_prefix_distribution"`
			} `json:"data"`
		}

		err := json.Unmarshal(rec.Body.Bytes(), &body)
		if err != nil {
			t.Fatalf("%s: decoding the answer: %v", name, err)
		}

		if body.Data.IPv4Routes != 1 || body.Data.IPv6Routes != 1 {
			t.Errorf("%s: routes = (v4 %d, v6 %d), want (1, 1)",
				name, body.Data.IPv4Routes, body.Data.IPv6Routes)
		}

		wantV4 := []database.PrefixDistribution{{MaskLength: 24, Count: 1}}
		if !slices.Equal(body.Data.IPv4Distribution, wantV4) {
			t.Errorf("%s: IPv4 distribution = %v, want %v",
				name, body.Data.IPv4Distribution, wantV4)
		}

		wantV6 := []database.PrefixDistribution{{MaskLength: 32, Count: 1}}
		if !slices.Equal(body.Data.IPv6Distribution, wantV6) {
			t.Errorf("%s: IPv6 distribution = %v, want %v",
				name, body.Data.IPv6Distribution, wantV6)
		}
	}
}

// newServerWithTestRoutes returns a server on a new database that holds a
// route for testPrefixV4 and one for 2001:db8::/32.
func newServerWithTestRoutes(t *testing.T) *Server {
	t.Helper()

	db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
	if err != nil {
		t.Fatalf("database.New: %v", err)
	}

	t.Cleanup(func() { _ = db.Close() })

	ts := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)

	err = db.UpsertLiveRouteBatch([]*database.LiveRoute{
		{
			Prefix: testPrefixV4, MaskLength: 24, IPVersion: 4,
			OriginASN: 64500, PeerIP: testPeerV4, ASPath: []int{64500},
			NextHop: testPeerV4, LastUpdated: ts,
		},
		{
			Prefix: "2001:db8::/32", MaskLength: 32, IPVersion: 6,
			OriginASN: 64501, PeerIP: testPeerV6, ASPath: []int{64501},
			NextHop: testPeerV6, LastUpdated: ts,
		},
	})
	if err != nil {
		t.Fatalf("UpsertLiveRouteBatch: %v", err)
	}

	return New(db, streamer.New(logger.New(), metrics.New()), logger.New(),
		&config.Config{})
}

// TestPrefixDetailHandlersParsePrefix checks that both prefix pages find a
// stored route whatever valid text form the URL writes its prefix in, and
// answer 400 for a prefix that does not parse. The tables store the form
// net/netip prints. Before the fix the URL text was looked up as typed, so
// "2001:DB8:0:0::/32" was not found although "2001:db8::/32" was stored, and
// "foo/24" answered 500 (https://git.eeqj.de/sneak/routewatch/issues/71). A
// prefix with its colons percent-encoded, as JavaScript's encodeURIComponent
// writes it, answered 400 (https://git.eeqj.de/sneak/routewatch/issues/103).
func TestPrefixDetailHandlersParsePrefix(t *testing.T) {
	t.Parallel()

	s := newServerWithTestRoutes(t)

	tests := []struct {
		path string
		want int
	}{
		{"/api/v1/prefix/foo/24", http.StatusBadRequest},
		{"/prefix/foo/24", http.StatusBadRequest},
		{"/api/v1/prefix/2001:DB8:0:0::/32", http.StatusOK},
		{"/prefix/2001:DB8:0:0::/32", http.StatusOK},
		{"/api/v1/prefix/192.0.2.1/24", http.StatusOK},
		{"/prefix/192.0.2.1/24", http.StatusOK},
		{"/api/v1/prefix/2001%3Adb8%3A%3A/32", http.StatusOK},
		{"/prefix/2001%3Adb8%3A%3A/32", http.StatusOK},
	}

	for _, tt := range tests {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, tt.path, nil))

		if rec.Code != tt.want {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.path, rec.Code, tt.want, rec.Body)
		}
	}
}

// TestIPLookupsReadPercentEncodedAddresses checks that the IP lookups find the
// addresses a URL asks for when it percent-encodes them, as the home page's
// lookup form does with encodeURIComponent. Before the fix the handler read
// "2001%3Adb8%3A%3A1" undecoded as a host name, which did not resolve, and
// answered 400, so the home page could look up no IPv6 address
// (https://git.eeqj.de/sneak/routewatch/issues/103).
func TestIPLookupsReadPercentEncodedAddresses(t *testing.T) {
	t.Parallel()

	s := newServerWithTestRoutes(t)

	tests := []struct {
		path    string
		wantIPs string // the addresses of the results, comma-separated
	}{
		{"/ip/2001%3Adb8%3A%3A1", "2001:db8::1"},
		{"/api/v1/ip/192.0.2.1%2C192.0.2.2", "192.0.2.1,192.0.2.2"},
	}

	for _, tt := range tests {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, tt.path, nil))

		if rec.Code != http.StatusOK {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.path, rec.Code, http.StatusOK, rec.Body)

			continue
		}

		var body struct {
			Data IPLookupResponse `json:"data"`
		}

		err := json.Unmarshal(rec.Body.Bytes(), &body)
		if err != nil {
			t.Errorf("%s: decoding the answer %q: %v", tt.path, rec.Body, err)

			continue
		}

		gotIPs := make([]string, 0, len(body.Data.Results))

		for _, result := range body.Data.Results {
			gotIPs = append(gotIPs, result.IP)
		}

		got := strings.Join(gotIPs, ",")
		if got != tt.wantIPs {
			t.Errorf("%s: results for %q, want %q", tt.path, got, tt.wantIPs)
		}
	}
}

// errASDetailsLookupFailed is what failingASDetailsDB answers every AS details
// lookup with.
var errASDetailsLookupFailed = errors.New("AS details lookup failed")

// failingASDetailsDB wraps a real store and fails every AS details lookup.
type failingASDetailsDB struct {
	database.Store
}

func (failingASDetailsDB) GetASDetailsContext(
	_ context.Context, _ int,
) (*database.ASN, []database.LiveRoute, error) {
	return nil, nil, errASDetailsLookupFailed
}

// TestPrefixDetailShowsOriginNames checks that the prefix page shows each
// origin AS's handle and description without looking up the AS's details,
// which also read every route the AS originates. Before the fix the page did
// that lookup once per origin, so with it failing the names were missing
// (https://git.eeqj.de/sneak/routewatch/issues/67). The AS path column shows
// handles too, so the test looks for the origin list's "(handle)" form.
func TestPrefixDetailShowsOriginNames(t *testing.T) {
	t.Parallel()

	db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
	if err != nil {
		t.Fatalf("database.New: %v", err)
	}

	t.Cleanup(func() { _ = db.Close() })

	ts := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
	origins := []int{15169, 13335}

	for _, asn := range origins {
		_, err := db.GetOrCreateASN(asn, ts)
		if err != nil {
			t.Fatalf("GetOrCreateASN(%d): %v", asn, err)
		}
	}

	err = db.UpsertLiveRouteBatch([]*database.LiveRoute{
		{
			Prefix: testPrefixV4, MaskLength: 24, IPVersion: 4,
			OriginASN: origins[0], PeerIP: testPeerV4,
			ASPath: []int{origins[0]}, NextHop: testPeerV4, LastUpdated: ts,
		},
		{
			Prefix: testPrefixV4, MaskLength: 24, IPVersion: 4,
			OriginASN: origins[1], PeerIP: "198.51.100.2",
			ASPath: []int{origins[1]}, NextHop: "198.51.100.2", LastUpdated: ts,
		},
	})
	if err != nil {
		t.Fatalf("UpsertLiveRouteBatch: %v", err)
	}

	s := New(failingASDetailsDB{db}, streamer.New(logger.New(), metrics.New()),
		logger.New(), &config.Config{})
	rec := httptest.NewRecorder()
	s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
		t.Context(), http.MethodGet, "/prefix/"+testPrefixV4, nil))

	if rec.Code != http.StatusOK {
		t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
	}

	page := rec.Body.String()

	for _, asn := range origins {
		info, ok := asinfo.Get(asn)
		if !ok {
			t.Fatalf("AS%d is not in the AS info data", asn)
		}

		want := "(" + html.EscapeString(info.Handle) + ")"
		if !strings.Contains(page, want) {
			t.Errorf("page does not show AS%d's handle %q", asn, want)
		}

		want = html.EscapeString(info.Description)
		if !strings.Contains(page, want) {
			t.Errorf("page does not show AS%d's description %q", asn, want)
		}
	}
}

// TestPagesSayOriginZeroIsNoKnownOrigin stores a route with origin 0, as the
// prefix handler stores a route whose AS path ends in an AS set of several
// members, and checks that the prefix page and the prefix length page say it
// has no known origin, without a link to AS0 or the description of the
// reserved AS 0 (https://git.eeqj.de/sneak/routewatch/issues/75).
func TestPagesSayOriginZeroIsNoKnownOrigin(t *testing.T) {
	t.Parallel()

	db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
	if err != nil {
		t.Fatalf("database.New: %v", err)
	}

	t.Cleanup(func() { _ = db.Close() })

	err = db.UpsertLiveRouteBatch([]*database.LiveRoute{{
		Prefix: testPrefixV4, MaskLength: 24, IPVersion: 4,
		OriginASN: 0, PeerIP: testPeerV4, ASPath: []int{64500, 64501, 64502},
		NextHop: testPeerV4, LastUpdated: time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC),
	}})
	if err != nil {
		t.Fatalf("UpsertLiveRouteBatch: %v", err)
	}

	reserved, ok := asinfo.Get(0)
	if !ok {
		t.Fatal("AS0 is not in the AS info data")
	}

	s := New(db, streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})

	for _, path := range []string{"/prefix/" + testPrefixV4, prefixLengthPagePath} {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, path, nil))

		if rec.Code != http.StatusOK {
			t.Fatalf("%s: status %d, want %d; body %s",
				path, rec.Code, http.StatusOK, rec.Body)
		}

		page := rec.Body.String()

		if !strings.Contains(page, "No known origin") {
			t.Errorf("%s does not say the route has no known origin", path)
		}

		if strings.Contains(page, `href="/as/0"`) {
			t.Errorf("%s links to AS0", path)
		}

		if strings.Contains(page, html.EscapeString(reserved.Description)) {
			t.Errorf("%s shows AS0's description %q", path, reserved.Description)
		}
	}
}

// shortRequestDeadline is the deadline the tests below give a request. The
// server's 30-second limit and the stats handlers' 4-second limit inherit it,
// so the tests do not wait for either.
const shortRequestDeadline = 50 * time.Millisecond

// TestRequestPastTimeLimitAnswers504 sends a request through the server's
// router to a page and to a JSON route whose handlers wait for the time limit
// to pass and return without answering. The page answers 504; the JSON route
// answers 504 with the JSON error body. Before the fix both answered 408,
// written by the time limit middleware from its own goroutine while the
// handler could still be writing.
func TestRequestPastTimeLimitAnswers504(t *testing.T) {
	t.Parallel()

	s := New(nil, streamer.New(logger.New(), metrics.New()), logger.New(),
		&config.Config{})

	waitForTimeLimit := func(_ http.ResponseWriter, r *http.Request) {
		<-r.Context().Done()
	}
	// Registered the way setupRoutes registers pages and JSON routes.
	s.router.Get("/slow-page", waitForTimeLimit)
	s.router.Get("/slow.json",
		JSONValidationMiddleware(http.HandlerFunc(waitForTimeLimit)).ServeHTTP)

	tests := []struct {
		path         string
		wantJSONBody bool
	}{
		{path: "/slow-page"},
		{path: "/slow.json", wantJSONBody: true},
	}

	for _, tt := range tests {
		ctx, cancel := context.WithTimeout(context.Background(),
			shortRequestDeadline)
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec,
			httptest.NewRequestWithContext(ctx, http.MethodGet, tt.path, nil))
		cancel()

		if rec.Code != http.StatusGatewayTimeout {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.path, rec.Code, http.StatusGatewayTimeout, rec.Body)
		}

		if tt.wantJSONBody {
			checkJSONErrorCode(t, tt.path, rec, http.StatusGatewayTimeout)
		}
	}
}

// TestStatsHandlersAnswer504WhenDatabaseReadRunsOut calls each stats handler
// with a store that does not answer before the handler's 4-second limit runs
// out, and checks that the handler itself answers 504 with the JSON error
// body. Before the fix status.json answered 408, and /api/v1/stats wrote
// nothing, which the JSON check on its route turned into 500.
func TestStatsHandlersAnswer504WhenDatabaseReadRunsOut(t *testing.T) {
	t.Parallel()

	release := make(chan struct{})
	defer close(release)

	db := blockingStatsDB{release: release}
	s := New(db, streamer.New(logger.New(), metrics.New()), logger.New(),
		&config.Config{})

	handlers := map[string]http.HandlerFunc{
		statusJSONHandlerName: s.handleStatusJSON(),
		statsHandlerName:      s.handleStats(),
	}

	for name, handler := range handlers {
		ctx, cancel := context.WithTimeout(context.Background(),
			shortRequestDeadline)
		rec := httptest.NewRecorder()
		handler(rec, httptest.NewRequestWithContext(ctx, http.MethodGet, "/", nil))
		cancel()

		if rec.Code != http.StatusGatewayTimeout {
			t.Errorf("%s: status %d, want %d; body %s",
				name, rec.Code, http.StatusGatewayTimeout, rec.Body)
		}

		checkJSONErrorCode(t, name, rec, http.StatusGatewayTimeout)
	}
}

// slowDB embeds database.Store (left nil) and overrides the reads the routes
// in TestRoutesAnswer504WhenDatabaseReadIsCutOff make. Each read waits until
// its context ends and then answers as the real store does when the time
// limit cuts it off: the IP read with the context's error, the prefix read
// that there is no route, and the others with what they had read, here
// nothing, and no error. Every other Store method is unused and would panic
// if called.
type slowDB struct {
	database.Store
}

func (slowDB) GetStatsContext(ctx context.Context) (database.Stats, error) {
	<-ctx.Done()

	return database.Stats{}, nil
}

func (slowDB) GetIPInfoContext(
	ctx context.Context, _ string,
) (*database.IPInfo, error) {
	<-ctx.Done()

	return nil, ctx.Err()
}

func (slowDB) GetASDetailsContext(
	ctx context.Context, asn int,
) (*database.ASN, []database.LiveRoute, error) {
	<-ctx.Done()

	return &database.ASN{ASN: asn}, nil, nil
}

func (slowDB) GetPrefixDetailsContext(
	ctx context.Context, _ string,
) ([]database.LiveRoute, map[int]database.ASN, error) {
	<-ctx.Done()

	return nil, nil, database.ErrNoRoute
}

func (slowDB) GetRandomPrefixesByLengthContext(
	ctx context.Context, _, _, _ int,
) ([]database.LiveRoute, error) {
	<-ctx.Done()

	return nil, nil
}

// TestRoutesAnswer504WhenDatabaseReadIsCutOff sends a request through the
// server's router for each route that reads the database, with a store whose
// reads are cut off when the request's time limit passes. Each route answers
// 504 with the time limit message. Without its check after the read, a route
// answers with what the cut-off read returned: 500, 404, 200, or, on a page
// that stops before rendering once the request has ended, 504 with an empty
// body. The health check is left out: it answers 503 when its own 2-second
// ping runs out.
func TestRoutesAnswer504WhenDatabaseReadIsCutOff(t *testing.T) {
	t.Parallel()

	s := New(slowDB{}, streamer.New(logger.New(), metrics.New()), logger.New(),
		&config.Config{})

	tests := []struct {
		path         string
		wantJSONBody bool
	}{
		{path: asPagePath},
		{path: "/prefix/192.0.2.0/24"},
		{path: prefixLengthPagePath},
		{path: "/prefixlength6/48"},
		{path: statusJSONPath, wantJSONBody: true},
		{path: "/ip/192.0.2.1", wantJSONBody: true},
		{path: statsPath, wantJSONBody: true},
		{path: "/api/v1/ip/192.0.2.1", wantJSONBody: true},
		{path: "/api/v1/as/64500", wantJSONBody: true},
		{path: "/api/v1/prefix/192.0.2.0/24", wantJSONBody: true},
	}

	for _, tt := range tests {
		checkRouteAnswers504(t, s, tt.path, tt.wantJSONBody)
	}
}

// slowSecondReadDB embeds database.Store (left nil) and overrides the reads
// of the routes that read the database twice. The first read answers at once;
// the second, the AS page's peers read or the stats routes' WHOIS read, waits
// until its context ends and then answers with the context's error, as the
// real store does.
type slowSecondReadDB struct {
	database.Store
}

func (slowSecondReadDB) GetASDetailsContext(
	_ context.Context, asn int,
) (*database.ASN, []database.LiveRoute, error) {
	return &database.ASN{ASN: asn}, nil, nil
}

func (slowSecondReadDB) GetASPeersContext(
	ctx context.Context, _ int,
) ([]database.ASPeer, error) {
	<-ctx.Done()

	return nil, ctx.Err()
}

func (slowSecondReadDB) GetStatsContext(_ context.Context) (database.Stats, error) {
	return database.Stats{}, nil
}

func (slowSecondReadDB) GetWHOISStats(
	ctx context.Context, _ time.Duration,
) (*database.WHOISStats, error) {
	<-ctx.Done()

	return nil, ctx.Err()
}

// idleASNFetcher is a WHOIS fetcher that does nothing. The stats handlers
// read the WHOIS stats only when the server has a fetcher.
type idleASNFetcher struct{}

func (idleASNFetcher) QueueImmediate(int) {}

func (idleASNFetcher) GetStats() ASNFetcherStats {
	return ASNFetcherStats{}
}

// TestRoutesAnswer504WhenSecondDatabaseReadIsCutOff sends a request through
// the server's router for each route that reads the database twice, with a
// store that answers the first read and cuts off the second when the
// request's time limit passes. Each route answers 504 with the time limit
// message. Without the check after the second read, the AS page answers 504
// with an empty body and the stats routes answer 200 without the WHOIS stats.
func TestRoutesAnswer504WhenSecondDatabaseReadIsCutOff(t *testing.T) {
	t.Parallel()

	s := New(slowSecondReadDB{}, streamer.New(logger.New(), metrics.New()),
		logger.New(), &config.Config{})
	s.SetASNFetcher(idleASNFetcher{})

	tests := []struct {
		path         string
		wantJSONBody bool
	}{
		{path: asPagePath},
		{path: statusJSONPath, wantJSONBody: true},
		{path: statsPath, wantJSONBody: true},
	}

	for _, tt := range tests {
		checkRouteAnswers504(t, s, tt.path, tt.wantJSONBody)
	}
}

// checkRouteAnswers504 sends a request for path through the server's router
// with a short deadline and checks that it answers 504 with the time limit
// message: the JSON error body on JSON routes, the plain message on pages.
func checkRouteAnswers504(
	t *testing.T, s *Server, path string, wantJSONBody bool,
) {
	t.Helper()

	ctx, cancel := context.WithTimeout(context.Background(), shortRequestDeadline)
	defer cancel()

	rec := httptest.NewRecorder()
	s.router.ServeHTTP(rec,
		httptest.NewRequestWithContext(ctx, http.MethodGet, path, nil))

	if rec.Code != http.StatusGatewayTimeout {
		t.Errorf("%s: status %d, want %d; body %s",
			path, rec.Code, http.StatusGatewayTimeout, rec.Body)
	}

	if wantJSONBody {
		checkJSONErrorCode(t, path, rec, http.StatusGatewayTimeout)

		return
	}

	body := strings.TrimSpace(rec.Body.String())
	if body != requestTimeoutMessage {
		t.Errorf("%s: body %q, want %q", path, body, requestTimeoutMessage)
	}
}

// checkJSONErrorCode checks that rec holds the JSON error body with the given
// code.
func checkJSONErrorCode(
	t *testing.T, name string, rec *httptest.ResponseRecorder, want int,
) {
	t.Helper()

	var body struct {
		Status string `json:"status"`
		Error  struct {
			Code int `json:"code"`
		} `json:"error"`
	}

	err := json.Unmarshal(rec.Body.Bytes(), &body)
	if err != nil {
		t.Errorf("%s: decoding the answer %q: %v", name, rec.Body, err)

		return
	}

	if body.Status != jsonStatusError || body.Error.Code != want {
		t.Errorf("%s: answer %s, want status \"error\" and error code %d",
			name, rec.Body, want)
	}
}

// errDiskIO is the database driver's error failingDB answers with.
var errDiskIO = errors.New("disk I/O error")

// failingDB embeds database.Store (left nil) and fails the reads of the JSON
// routes and the health check's ping with errDiskIO. Every other Store method
// is unused and would panic if called.
type failingDB struct {
	database.Store
}

func (failingDB) Ping(_ context.Context) error {
	return errDiskIO
}

func (failingDB) GetStatsContext(_ context.Context) (database.Stats, error) {
	return database.Stats{}, errDiskIO
}

func (failingDB) GetIPInfoContext(
	_ context.Context, _ string,
) (*database.IPInfo, error) {
	return nil, errDiskIO
}

func (failingDB) GetASDetailsContext(
	_ context.Context, _ int,
) (*database.ASN, []database.LiveRoute, error) {
	return nil, nil, errDiskIO
}

func (failingDB) GetPrefixDetailsContext(
	_ context.Context, _ string,
) ([]database.LiveRoute, map[int]database.ASN, error) {
	return nil, nil, errDiskIO
}

// TestJSONRoutesDoNotSendErrorDetails sends a request to each JSON route and
// the health check with a store whose reads fail with the driver's error text,
// and a prefix that does not parse, and checks that no answer carries the
// driver's or the prefix parser's text. Before the fix the answers sent it to
// the client (https://git.eeqj.de/sneak/routewatch/issues/108).
func TestJSONRoutesDoNotSendErrorDetails(t *testing.T) {
	t.Parallel()

	s := New(failingDB{}, streamer.New(logger.New(), metrics.New()), logger.New(),
		&config.Config{})

	tests := []struct {
		path     string
		wantCode int
	}{
		{"/.well-known/healthcheck.json", http.StatusServiceUnavailable},
		{statusJSONPath, http.StatusInternalServerError},
		{statsPath, http.StatusInternalServerError},
		{"/api/v1/as/64500", http.StatusInternalServerError},
		{"/api/v1/prefix/192.0.2.0/24", http.StatusInternalServerError},
		{"/api/v1/ip/192.0.2.1", http.StatusInternalServerError},
		{"/api/v1/prefix/foo/24", http.StatusBadRequest},
	}

	for _, tt := range tests {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, tt.path, nil))

		if rec.Code != tt.wantCode {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.path, rec.Code, tt.wantCode, rec.Body)
		}

		for _, detail := range []string{errDiskIO.Error(), "netip"} {
			if strings.Contains(rec.Body.String(), detail) {
				t.Errorf("%s: body %s carries the error text %q",
					tt.path, rec.Body, detail)
			}
		}
	}
}

// The addresses failingIPLookupDB fails the read of and finds a route for.
const (
	failingLookupIP = "192.0.2.1"
	routedLookupIP  = "192.0.2.2"
)

// failingIPLookupDB embeds database.Store (left nil) and answers the IP lookup
// with errDiskIO for failingLookupIP, a route for routedLookupIP, and no route
// for any other address. Every other Store method is unused and would panic if
// called.
type failingIPLookupDB struct {
	database.Store
}

func (failingIPLookupDB) GetIPInfoContext(
	_ context.Context, ip string,
) (*database.IPInfo, error) {
	switch ip {
	case failingLookupIP:
		return nil, errDiskIO
	case routedLookupIP:
		return &database.IPInfo{IP: ip}, nil
	default:
		return nil, database.ErrNoRoute
	}
}

// TestIPLookupAnswers500WhenDatabaseReadFails sends IP lookups through the
// server's router with a store whose read of one address fails with the
// driver's error. A lookup that asks for that address answers 500 with the
// JSON error body, as the AS and prefix JSON routes do; an address with no
// route still answers 404. Before the fix the failed read was reported as if
// the address had no route: 404 for that address alone, and 200 beside a
// routed address (https://git.eeqj.de/sneak/routewatch/issues/109).
func TestIPLookupAnswers500WhenDatabaseReadFails(t *testing.T) {
	t.Parallel()

	s := New(failingIPLookupDB{}, streamer.New(logger.New(), metrics.New()),
		logger.New(), &config.Config{})

	tests := []struct {
		path     string
		wantCode int
	}{
		{
			path:     "/api/v1/ip/" + failingLookupIP,
			wantCode: http.StatusInternalServerError,
		},
		{
			path:     "/api/v1/ip/" + failingLookupIP + "," + routedLookupIP,
			wantCode: http.StatusInternalServerError,
		},
		{
			path:     "/api/v1/ip/203.0.113.1",
			wantCode: http.StatusNotFound,
		},
	}

	for _, tt := range tests {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, tt.path, nil))

		if rec.Code != tt.wantCode {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.path, rec.Code, tt.wantCode, rec.Body)
		}

		checkJSONErrorCode(t, tt.path, rec, tt.wantCode)
	}
}

// errNoSuchHost is what fakeResolver answers a lookup it has no answer for
// with.
var errNoSuchHost = errors.New("no such host")

// fakeResolver answers a host name lookup with the addresses hosts lists for
// the name, and a PTR lookup with no names or, when ptrNeverAnswers is set,
// not at all: it waits until the lookup's context ends. hostLookups counts the
// host name lookups.
type fakeResolver struct {
	hosts           map[string][]string
	ptrNeverAnswers bool

	hostLookups atomic.Int64
}

func (r *fakeResolver) LookupHost(_ context.Context, host string) ([]string, error) {
	r.hostLookups.Add(1)

	addrs, ok := r.hosts[host]
	if !ok {
		return nil, errNoSuchHost
	}

	return addrs, nil
}

func (r *fakeResolver) LookupAddr(ctx context.Context, _ string) ([]string, error) {
	if r.ptrNeverAnswers {
		<-ctx.Done()

		return nil, ctx.Err()
	}

	return nil, errNoSuchHost
}

// countingIPLookupDB embeds database.Store (left nil) and counts its IP
// lookups, answering each that the address has no route. Every other Store
// method is unused and would panic if called.
type countingIPLookupDB struct {
	database.Store

	lookups atomic.Int64
}

func (d *countingIPLookupDB) GetIPInfoContext(
	_ context.Context, _ string,
) (*database.IPInfo, error) {
	d.lookups.Add(1)

	return nil, database.ErrNoRoute
}

// TestIPLookupRefusesTooManyAddresses sends IP lookups of maxLookupTargets
// addresses and of one more, listed or as a host name that resolves to them,
// and a lookup listing maxLookupTargets+1 host names. The longer lookups answer
// 400 without reading the database, and the list of host names without
// resolving any of them; the others read the database once per address. Before
// the fix every address was read and every name resolved, however many there
// were (https://git.eeqj.de/sneak/routewatch/issues/110).
func TestIPLookupRefusesTooManyAddresses(t *testing.T) {
	t.Parallel()

	addrs := make([]string, maxLookupTargets+1)
	names := make([]string, maxLookupTargets+1)

	for i := range addrs {
		addrs[i] = "192.0.2." + strconv.Itoa(i+1)
		names[i] = "host" + strconv.Itoa(i+1) + ".test"
	}

	hosts := map[string][]string{
		"most.test":     addrs[:maxLookupTargets],
		"too-many.test": addrs,
	}

	tests := []struct {
		target          string
		wantCode        int
		wantLookups     int64
		wantHostLookups int64
	}{
		{
			strings.Join(addrs[:maxLookupTargets], ","),
			http.StatusNotFound, maxLookupTargets, 0,
		},
		{strings.Join(addrs, ","), http.StatusBadRequest, 0, 0},
		{"most.test", http.StatusNotFound, maxLookupTargets, 1},
		{"too-many.test", http.StatusBadRequest, 0, 1},
		{strings.Join(names, ","), http.StatusBadRequest, 0, 0},
	}

	for _, tt := range tests {
		db := &countingIPLookupDB{}
		s := New(db, streamer.New(logger.New(), metrics.New()), logger.New(),
			&config.Config{})
		resolver := &fakeResolver{hosts: hosts}
		s.resolver = resolver

		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, "/api/v1/ip/"+tt.target, nil))

		if rec.Code != tt.wantCode {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.target, rec.Code, tt.wantCode, rec.Body)
		}

		checkJSONErrorCode(t, tt.target, rec, tt.wantCode)

		got := db.lookups.Load()
		if got != tt.wantLookups {
			t.Errorf("%s: %d database reads, want %d",
				tt.target, got, tt.wantLookups)
		}

		gotHostLookups := resolver.hostLookups.Load()
		if gotHostLookups != tt.wantHostLookups {
			t.Errorf("%s: %d host name lookups, want %d",
				tt.target, gotHostLookups, tt.wantHostLookups)
		}
	}
}

// addrInTestPrefixV4 is an address in testPrefixV4, which
// newServerWithTestRoutes stores a route for.
const addrInTestPrefixV4 = "192.0.2.1"

// TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer looks up a routed address
// with a resolver that never answers its PTR lookup. Once the PTR lookup's own
// limit passes, the lookup answers 200 with the route. Before the fix the PTR
// lookup ran until the request's time limit, and the lookup answered 504
// without the route (https://git.eeqj.de/sneak/routewatch/issues/110).
func TestIPLookupKeepsRouteWhenPTRLookupDoesNotAnswer(t *testing.T) {
	t.Parallel()

	s := newServerWithTestRoutes(t)
	s.resolver = &fakeResolver{ptrNeverAnswers: true}

	// The request's time limit passes after the PTR lookup's.
	ctx, cancel := context.WithTimeout(t.Context(), 2*ptrLookupTimeout)
	defer cancel()

	rec := httptest.NewRecorder()
	s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
		ctx, http.MethodGet, "/api/v1/ip/"+addrInTestPrefixV4, nil))

	if rec.Code != http.StatusOK {
		t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
	}

	var body struct {
		Data IPLookupResponse `json:"data"`
	}

	err := json.Unmarshal(rec.Body.Bytes(), &body)
	if err != nil {
		t.Fatalf("decoding the answer %q: %v", rec.Body, err)
	}

	if len(body.Data.Results) != 1 || body.Data.Results[0].Netblock != testPrefixV4 {
		t.Errorf("answer %s, want one result in %s", rec.Body, testPrefixV4)
	}
}

// The host name TestIPLookupHidesPrivateAddresses resolves to a private
// address, and that address.
const (
	internalHostName = "internal.test"
	internalHostAddr = "10.0.0.5"
)

// TestIPLookupHidesPrivateAddresses looks up host names that resolve to a
// private address, alone or beside a routed address. No answer carries the
// private address, and a name with no other address is reported as having no
// public address, in the 400 when nothing else is left to look up. Before the
// fix the private address was looked up and named in the answer, "No routes
// found: 10.0.0.5: no route found for IP 10.0.0.5", so the API showed what the
// deployment's own DNS knows (https://git.eeqj.de/sneak/routewatch/issues/110).
func TestIPLookupHidesPrivateAddresses(t *testing.T) {
	t.Parallel()

	s := newServerWithTestRoutes(t)
	s.resolver = &fakeResolver{hosts: map[string][]string{
		internalHostName: {internalHostAddr},
		"mixed.test":     {internalHostAddr, addrInTestPrefixV4},
	}}

	notPublic := internalHostName + ": " + hostNotPublicMessage

	tests := []struct {
		target      string
		wantCode    int
		wantMessage string
		wantErrors  []string
	}{
		{
			internalHostName, http.StatusBadRequest,
			"No valid IPs or hostnames provided: " + notPublic, nil,
		},
		{
			internalHostName + "," + addrInTestPrefixV4, http.StatusOK, "",
			[]string{notPublic},
		},
		{"mixed.test", http.StatusOK, "", nil},
	}

	for _, tt := range tests {
		rec := httptest.NewRecorder()
		s.router.ServeHTTP(rec, httptest.NewRequestWithContext(
			t.Context(), http.MethodGet, "/api/v1/ip/"+tt.target, nil))

		if rec.Code != tt.wantCode {
			t.Errorf("%s: status %d, want %d; body %s",
				tt.target, rec.Code, tt.wantCode, rec.Body)
		}

		if strings.Contains(rec.Body.String(), internalHostAddr) {
			t.Errorf("%s: body %s carries %s", tt.target, rec.Body, internalHostAddr)
		}

		var body struct {
			Data  IPLookupResponse `json:"data"`
			Error struct {
				Msg string `json:"msg"`
			} `json:"error"`
		}

		err := json.Unmarshal(rec.Body.Bytes(), &body)
		if err != nil {
			t.Errorf("%s: decoding the answer %q: %v", tt.target, rec.Body, err)

			continue
		}

		if body.Error.Msg != tt.wantMessage {
			t.Errorf("%s: error message %q, want %q",
				tt.target, body.Error.Msg, tt.wantMessage)
		}

		if !slices.Equal(body.Data.Errors, tt.wantErrors) {
			t.Errorf("%s: errors %q, want %q",
				tt.target, body.Data.Errors, tt.wantErrors)
		}
	}
}

// settledGoroutineCount lets transient goroutines finish, then reports the
// current count.
func settledGoroutineCount() int {
	prev := runtime.NumGoroutine()

	for range 20 {
		time.Sleep(10 * time.Millisecond)

		cur := runtime.NumGoroutine()
		if cur == prev {
			return cur
		}

		prev = cur
	}

	return prev
}

// waitForGoroutines waits until the goroutine count drops to target or below.
func waitForGoroutines(target int) bool {
	for range 100 {
		if runtime.NumGoroutine() <= target {
			return true
		}

		time.Sleep(10 * time.Millisecond)
	}

	return false
}