pixa/internal/handlers/image_errors_internal_test.go

package handlers

import (
	"bytes"
	"context"
	"encoding/json"
	"fmt"
	"image/color"
	"io"
	"log/slog"
	"net/http"
	"net/http/httptest"
	"slices"
	"strings"
	"testing"
	"testing/fstest"
	"time"

	"github.com/go-chi/chi/v5"
	"github.com/go-chi/chi/v5/middleware"
	"github.com/prometheus/client_golang/prometheus"
	"sneak.berlin/go/pixa/internal/allowlist"
	"sneak.berlin/go/pixa/internal/httpfetcher"
	"sneak.berlin/go/pixa/internal/imageprocessor"
	"sneak.berlin/go/pixa/internal/imageproxy"
	"sneak.berlin/go/pixa/internal/imagerequest"
	"sneak.berlin/go/pixa/internal/imgcache"
	"sneak.berlin/go/pixa/internal/signature"
)

// allowlistedHost is the only host on the allowlist of the image route
// newImageRoute builds.
const allowlistedHost = "allowed.example.com"

// newImageRoute returns the image route of a Handlers whose service fetches
// with fetcher, and which checks signatures with testSigningKey.
func newImageRoute(t *testing.T, fetcher httpfetcher.Fetcher) http.Handler {
	t.Helper()

	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.Config{
		StateDir:    t.TempDir(),
		NegativeTTL: 5 * time.Minute,
		MaxBytes:    1 << 30,
	}, prometheus.NewRegistry())
	if err != nil {
		t.Fatalf("failed to create cache: %v", err)
	}

	svc, err := imageproxy.NewProxy(&imageproxy.Config{
		Cache:   cache,
		Fetcher: fetcher,
		Processor: imageprocessor.New(imageprocessor.Params{
			MaxInputBytes:           50 << 20,
			MaxConcurrentProcessing: 2,
		}),
		MaxResponseSize: 50 << 20,
	}, prometheus.NewRegistry())
	if err != nil {
		t.Fatalf("failed to create proxy: %v", err)
	}

	h := &Handlers{
		imgSvc:    svc,
		log:       slog.New(slog.DiscardHandler),
		signer:    signature.New(testSigningKey),
		allowlist: allowlist.New([]string{allowlistedHost}),
	}

	r := chi.NewRouter()
	r.Get("/v1/image/*", h.HandleImage())

	return r
}

// newPhotoFetcher returns a mock fetcher that serves a JPEG at photoPath on
// each of hosts, and answers any other source with an upstream error.
func newPhotoFetcher(t *testing.T, hosts ...string) *httpfetcher.MockFetcher {
	t.Helper()

	photo := &fstest.MapFile{
		Data: generateTestJPEG(t, 100, 100, color.RGBA{255, 0, 0, 255}),
	}

	files := fstest.MapFS{}
	for _, host := range hosts {
		files[host+photoPath] = photo
	}

	return httpfetcher.NewMock(files)
}

// photoURL returns the image route URL of photoPath on host, as a 50x50 JPEG.
func photoURL(host string) string {
	return "/v1/image/" + host + photoPath + "/50x50.jpeg"
}

// photoURLWithSig returns photoURL(host) with sig and expires as its sig and
// exp.
func photoURLWithSig(host, sig string, expires time.Time) string {
	return fmt.Sprintf("%s?sig=%s&exp=%d", photoURL(host), sig, expires.Unix())
}

// photoRequest returns the image request of photoURL(host) at the default
// quality and fit.
func photoRequest(host string) *imagerequest.Request {
	return &imagerequest.Request{
		Source: imagerequest.Source{
			Host: host,
			Path: photoPath,
		},
		Transform: imagerequest.Transform{
			Size:    imagerequest.Size{Width: 50, Height: 50},
			Format:  imagerequest.FormatJPEG,
			Quality: 85,
			FitMode: imagerequest.FitCover,
		},
	}
}

// photoSignature returns the signature of photoURL(host) at the default
// quality and fit, made with key and expiring at expires.
func photoSignature(key, host string, expires time.Time) string {
	return signature.New(key).Sign(photoRequest(host), expires)
}

// sendGet sends a GET for target to route and returns the response.
func sendGet(
	t *testing.T, route http.Handler, target string,
) *httptest.ResponseRecorder {
	t.Helper()

	req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, target, nil)
	rec := httptest.NewRecorder()

	route.ServeHTTP(rec, req)
	t.Logf("GET %s: %d", target, rec.Code)

	return rec
}

// checkErrorBody checks that rec has status wantStatus and the JSON error body
// the image route sends: wantError, wantStatus and the time in RFC 3339.
func checkErrorBody(
	t *testing.T, rec *httptest.ResponseRecorder, wantStatus int, wantError string,
) {
	t.Helper()

	if rec.Code != wantStatus {
		t.Errorf("status = %d, want %d", rec.Code, wantStatus)
	}

	if ct := rec.Header().Get("Content-Type"); ct != "application/json" {
		t.Errorf("Content-Type = %q, want application/json", ct)
	}

	var body struct {
		Error     string `json:"error"`
		Status    int    `json:"status"`
		Timestamp string `json:"timestamp"`
	}

	err := json.NewDecoder(rec.Body).Decode(&body)
	if err != nil {
		t.Fatalf("decoding response body: %v", err)
	}

	if body.Error != wantError || body.Status != wantStatus {
		t.Errorf("body error and status = %q %d, want %q %d",
			body.Error, body.Status, wantError, wantStatus)
	}

	_, err = time.Parse(time.RFC3339, body.Timestamp)
	if err != nil {
		t.Errorf("body timestamp: %v", err)
	}
}

// TestHandleImage_ErrorAnswers checks the status and the JSON error body the
// image route answers each request below with. The JPEG at photoPath exists on
// signedHost and on each host below that differs from it, so a request refused
// with 401 would otherwise be served.
func TestHandleImage_ErrorAnswers(t *testing.T) {
	t.Parallel()

	// A signature for signedHost must not verify for any of these.
	parentHost := "example.com"
	siblingHost := "other.example.com"
	subdomainHost := "img." + signedHost
	appendedHost := signedHost + ".example.net"

	photos := newPhotoFetcher(t,
		signedHost, parentHost, siblingHost, subdomainHost, appendedHost)
	// The real fetcher refuses localhost before any lookup or connection.
	realFetcher := httpfetcher.New(&httpfetcher.Config{
		Timeout:               30 * time.Second,
		MaxResponseSize:       50 << 20,
		MaxConnectionsPerHost: 20,
		MaxConnections:        64,
	})

	exp := time.Now().Add(time.Hour)
	expired := time.Now().Add(-time.Hour)
	sig := photoSignature(testSigningKey, signedHost, exp)
	otherKeySig := photoSignature("another-signing-key", signedHost, exp)
	expiredSig := photoSignature(testSigningKey, signedHost, expired)
	localhostSig := photoSignature(testSigningKey, "localhost", exp)

	// The error every request refused for its signature gets.
	const unauthorized = "unauthorized"

	tests := []struct {
		name       string
		fetcher    httpfetcher.Fetcher
		target     string
		wantStatus int
		wantError  string
	}{
		{"no sig or exp", photos, photoURL(signedHost),
			http.StatusUnauthorized, unauthorized},
		{"exp but no sig", photos,
			fmt.Sprintf("%s?exp=%d", photoURL(signedHost), exp.Unix()),
			http.StatusUnauthorized, unauthorized},
		{"sig made with another key", photos,
			photoURLWithSig(signedHost, otherKeySig, exp),
			http.StatusUnauthorized, unauthorized},
		{"sig without its = padding", photos,
			photoURLWithSig(signedHost, strings.TrimRight(sig, "="), exp),
			http.StatusUnauthorized, unauthorized},
		{"sig in upper case", photos,
			photoURLWithSig(signedHost, strings.ToUpper(sig), exp),
			http.StatusUnauthorized, unauthorized},
		{"expired sig", photos, photoURLWithSig(signedHost, expiredSig, expired),
			http.StatusUnauthorized, unauthorized},
		{"sig sent for the parent domain", photos,
			photoURLWithSig(parentHost, sig, exp),
			http.StatusUnauthorized, unauthorized},
		{"sig sent for a sibling host", photos,
			photoURLWithSig(siblingHost, sig, exp),
			http.StatusUnauthorized, unauthorized},
		{"sig sent for a subdomain", photos,
			photoURLWithSig(subdomainHost, sig, exp),
			http.StatusUnauthorized, unauthorized},
		{"sig sent with another domain appended", photos,
			photoURLWithSig(appendedHost, sig, exp),
			http.StatusUnauthorized, unauthorized},
		{"unparseable path", photos,
			"/v1/image/" + allowlistedHost + photoPath + "/big.jpeg",
			http.StatusBadRequest, "invalid image URL: invalid size format"},
		{"blocked upstream address", realFetcher,
			photoURLWithSig("localhost", localhostSig, exp),
			http.StatusForbidden, "forbidden"},
		{"upstream error", photos,
			"/v1/image/" + allowlistedHost + "/images/missing.jpg/50x50.jpeg",
			http.StatusBadGateway, "upstream error"},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			rec := sendGet(t, newImageRoute(t, tt.fetcher), tt.target)
			checkErrorBody(t, rec, tt.wantStatus, tt.wantError)
		})
	}
}

// TestHandleImage_AllowlistOrSignature checks that the image route serves an
// image without a signature for a host on the allowlist only, and for another
// host only with a valid signature.
func TestHandleImage_AllowlistOrSignature(t *testing.T) {
	t.Parallel()

	photos := newPhotoFetcher(t, allowlistedHost, signedHost)
	exp := time.Now().Add(time.Hour)
	sig := photoSignature(testSigningKey, signedHost, exp)

	tests := []struct {
		name       string
		target     string
		wantStatus int
	}{
		{"allowlisted host, no sig", photoURL(allowlistedHost), http.StatusOK},
		{"other host, no sig", photoURL(signedHost), http.StatusUnauthorized},
		{"other host, valid sig", photoURLWithSig(signedHost, sig, exp),
			http.StatusOK},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			rec := sendGet(t, newImageRoute(t, photos), tt.target)
			if rec.Code != tt.wantStatus {
				t.Errorf("status = %d, want %d", rec.Code, tt.wantStatus)
			}
		})
	}
}

// TestHandleImage_InvalidHost_Returns400 sends image URLs whose host no URL
// host can be, and checks that each is refused with 400 naming the host as
// decoded: allowlistedHost with a character after it that a URL host cannot
// hold, percent-encoded, an IPv6 address without brackets, and brackets
// around something that is not an IPv6 address. Later steps put the host
// unparsed into the allowlist check, the cache key and the upstream URL, so
// such a host is refused first.
func TestHandleImage_InvalidHost_Returns400(t *testing.T) {
	t.Parallel()

	photos := newPhotoFetcher(t, allowlistedHost)

	tests := []struct {
		name        string
		writtenHost string
		decodedHost string
	}{
		{"? written as %3F", allowlistedHost + "%3Fx=1", allowlistedHost + "?x=1"},
		{"# written as %23", allowlistedHost + "%23x", allowlistedHost + "#x"},
		{"% written as %25", allowlistedHost + "%253F", allowlistedHost + "%3F"},
		{`\ written as %5C`, allowlistedHost + "%5Cx", allowlistedHost + `\x`},
		{"space written as %20", allowlistedHost + "%20", allowlistedHost + " "},
		{"IPv6 address without brackets", "2001:db8::1", "2001:db8::1"},
		{"IPv4 address in brackets", "[203.0.113.5]", "[203.0.113.5]"},
		{"no address in brackets", "[abc]", "[abc]"},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			rec := sendGet(t, newImageRoute(t, photos), photoURL(tt.writtenHost))
			checkErrorBody(t, rec, http.StatusBadRequest,
				fmt.Sprintf("invalid image URL: invalid source host: %q",
					tt.decodedHost))
		})
	}
}

// TestHandleImage_HostForms_Served checks that the image route serves, with
// a valid signature, the image at photoPath on a host name, an IPv4 address,
// an IPv6 address in brackets, and a host followed by ":" with or without a
// port.
func TestHandleImage_HostForms_Served(t *testing.T) {
	t.Parallel()

	hosts := []string{
		allowlistedHost,
		"img_1.example.com",
		"203.0.113.5",
		"[2001:db8::1]",
		allowlistedHost + ":8443",
		"[2001:db8::1]:8443",
		allowlistedHost + ":",
	}

	photos := newPhotoFetcher(t, hosts...)
	exp := time.Now().Add(time.Hour)

	for _, host := range hosts {
		t.Run(host, func(t *testing.T) {
			t.Parallel()

			sig := photoSignature(testSigningKey, host, exp)

			rec := sendGet(t, newImageRoute(t, photos),
				photoURLWithSig(host, sig, exp))
			if rec.Code != http.StatusOK {
				t.Errorf("status = %d, want %d: %s",
					rec.Code, http.StatusOK, rec.Body)
			}
		})
	}
}

// TestHandleImage_HashInSourcePathOrQuery_Returns400 sends image URLs whose
// source path or source query holds a "#", written as %23, and checks that
// each is refused with 400, the one signed for that source path included.
// A "#" starts a URL's fragment, so neither the source path nor the source
// query may hold one.
func TestHandleImage_HashInSourcePathOrQuery_Returns400(t *testing.T) {
	t.Parallel()

	photos := newPhotoFetcher(t, allowlistedHost, signedHost)
	exp := time.Now().Add(time.Hour)

	sig := signature.New(testSigningKey).Sign(&imagerequest.Request{
		Source: imagerequest.Source{
			Host: signedHost,
			Path: photoPath + "#x",
		},
		Transform: imagerequest.Transform{
			Size:    imagerequest.Size{Width: 50, Height: 50},
			Format:  imagerequest.FormatJPEG,
			Quality: 85,
			FitMode: imagerequest.FitCover,
		},
	}, exp)

	tests := []struct {
		name   string
		target string
	}{
		{"# in the source path",
			"/v1/image/" + allowlistedHost + photoPath + "%23x/50x50.jpeg"},
		{"# in the source query",
			"/v1/image/" + allowlistedHost + photoPath + "%3Fv=1%23x/50x50.jpeg"},
		{"# in the source path, signed",
			fmt.Sprintf("/v1/image/%s%s%%23x/50x50.jpeg?sig=%s&exp=%d",
				signedHost, photoPath, sig, exp.Unix())},
	}

	for _, tt := range tests {
		t.Run(tt.name, func(t *testing.T) {
			t.Parallel()

			rec := sendGet(t, newImageRoute(t, photos), tt.target)
			checkErrorBody(t, rec, http.StatusBadRequest,
				`invalid image URL: invalid image path: `+
					`the source path or query holds a "#"`)
		})
	}
}

// failingFetcher answers every fetch with its error.
type failingFetcher struct {
	err error
}

// Fetch returns f's error.
func (f failingFetcher) Fetch(
	context.Context, imagerequest.Source,
) (*httpfetcher.FetchResult, error) {
	return nil, f.err
}

// photoURLsByRoute returns, for each image route, the function that makes the
// URL of the JPEG at photoPath on signedHost on that route.
func photoURLsByRoute() map[string]func(*testing.T, *Handlers) string {
	return map[string]func(*testing.T, *Handlers) string{
		"/v1/image/": signedPhotoURL,
		"/v1/e/":     encPhotoURL,
	}
}

// TestImageRoutes_SameErrorAnswers checks that both image routes answer each
// upstream fetch error below with the same status. They log it as "failed to
// get image" at the same level: error for the 500 and warn for the others.
// Each request gets routes of its own, so no request finds another's failed
// fetch in the negative cache.
func TestImageRoutes_SameErrorAnswers(t *testing.T) {
	t.Parallel()

	tests := []struct {
		name       string
		err        error
		wantStatus int
		wantLevel  slog.Level
	}{
		{"blocked upstream address", httpfetcher.ErrSSRFBlocked,
			http.StatusForbidden, slog.LevelWarn},
		{"upstream error status",
			fmt.Errorf("%w: status 404", httpfetcher.ErrUpstreamError),
			http.StatusBadGateway, slog.LevelWarn},
		{"no response headers within the fetch timeout",
			httpfetcher.ErrUpstreamTimeout, http.StatusGatewayTimeout,
			slog.LevelWarn},
		{"no free upstream connection", httpfetcher.ErrTooManyConnections,
			http.StatusServiceUnavailable, slog.LevelWarn},
		{"Content-Type not a source format",
			fmt.Errorf("%w: image/svg+xml", httpfetcher.ErrInvalidContentType),
			http.StatusUnsupportedMediaType, slog.LevelWarn},
		{"any other failure", io.ErrUnexpectedEOF,
			http.StatusInternalServerError, slog.LevelError},
	}

	for _, tt := range tests {
		for route, imageURL := range photoURLsByRoute() {
			t.Run(route+" "+tt.name, func(t *testing.T) {
				t.Parallel()

				var logs bytes.Buffer

				h, routes := newRoutesFetchingThrough(t,
					failingFetcher{err: tt.err},
					slog.New(slog.NewJSONHandler(&logs, nil)))

				rec := sendGet(t, routes, imageURL(t, h))
				if rec.Code != tt.wantStatus {
					t.Errorf("status = %d, want %d: %s",
						rec.Code, tt.wantStatus, rec.Body)
				}

				levels := loggedLevels(t, &logs)
				if !slices.Contains(levels[tt.wantLevel.String()],
					"failed to get image") {
					t.Errorf(`no "failed to get image" line logged at level %s`,
						tt.wantLevel)
				}

				if tt.wantLevel != slog.LevelError &&
					len(levels[slog.LevelError.String()]) != 0 {
					t.Errorf("logged at error level: %q",
						levels[slog.LevelError.String()])
				}
			})
		}
	}
}

// failingResponseWriter is a response writer whose Write always fails, as when
// the client has gone away.
type failingResponseWriter struct {
	*httptest.ResponseRecorder
}

// Write writes nothing and returns io.ErrClosedPipe.
func (failingResponseWriter) Write([]byte) (int, error) {
	return 0, io.ErrClosedPipe
}

// TestImageRoutes_FailedWriteLoggedOnce checks that both image routes log a
// failed write of the image once, at warn level, with the request's ID, the
// source host and path, the bytes served and the error. Neither may also log
// the image as served.
func TestImageRoutes_FailedWriteLoggedOnce(t *testing.T) {
	t.Parallel()

	const requestID = "test-request-id"

	for route, imageURL := range photoURLsByRoute() {
		t.Run(route, func(t *testing.T) {
			t.Parallel()

			var logs bytes.Buffer

			h, srv := newSignedHostServer(t,
				slog.New(slog.NewJSONHandler(&logs, nil)))

			ctx := context.WithValue(t.Context(),
				middleware.RequestIDKey, requestID)
			srv.ServeHTTP(failingResponseWriter{httptest.NewRecorder()},
				httptest.NewRequestWithContext(
					ctx, http.MethodGet, imageURL(t, h), nil))

			t.Logf("logged:\n%s", logs.String())

			var failedWrites []map[string]any

			dec := json.NewDecoder(&logs)
			for dec.More() {
				var line map[string]any

				err := dec.Decode(&line)
				if err != nil {
					t.Fatalf("decoding log line: %v", err)
				}

				switch line["msg"] {
				case "image served":
					t.Error(`"image served" logged after a failed write`)
				case "failed to write response":
					failedWrites = append(failedWrites, line)
				}
			}

			if len(failedWrites) != 1 {
				t.Fatalf(`"failed to write response" logged %d times, want 1`,
					len(failedWrites))
			}

			want := map[string]any{
				"level":        slog.LevelWarn.String(),
				"request_id":   requestID,
				"host":         signedHost,
				"path":         photoPath,
				"served_bytes": float64(0),
				"error":        io.ErrClosedPipe.Error(),
			}

			for key, wantValue := range want {
				if got := failedWrites[0][key]; got != wantValue {
					t.Errorf("%s = %v, want %v", key, got, wantValue)
				}
			}
		})
	}
}