Refuse image requests whose Referer is on referer_blocklist (closes #90)

A new setting, referer_blocklist (PIXA_REFERER_BLOCKLIST), lists hosts
whose pages may not show pixa's images. Entries are written and matched
as allowlist_hosts are, with the same matcher. Both image routes check
the Referer before the signature, the cache and the upstream fetch, and
answer 403 with the JSON error, so a blocked request costs nothing and
is refused whether or not the image is cached. No Referer, or one that
does not parse, is served; README.md says this makes the list easy to
get around. An entry of either host list that is not a host name
(letters, digits, hyphens, underscores, dots, at most one leading dot)
or an IP address now aborts startup naming the setting and the entry.

Model: opus-5-5

internal/handlers/handlers.go

@@ -9,6 +9,7 @@ import (
 	"time"
 
 	"go.uber.org/fx"
+	"sneak.berlin/go/pixa/internal/allowlist"
 	"sneak.berlin/go/pixa/internal/config"
 	"sneak.berlin/go/pixa/internal/database"
 	"sneak.berlin/go/pixa/internal/encurl"
@@ -40,6 +41,10 @@ type Handlers struct {
 	sessMgr     *session.Manager
 	encGen      *encurl.Generator
 	csrfProtect func(http.Handler) http.Handler
+
+	// refererBlocklist matches the hosts of referer_blocklist; its IsAllowed
+	// reports whether a URL's host is on that list.
+	refererBlocklist *allowlist.HostAllowList
 }
 
 // New creates a new Handlers instance.
@@ -50,11 +55,12 @@ func New(lc fx.Lifecycle, params Params) (*Handlers, error) {
 	}
 
 	s := &Handlers{
-		log:         params.Logger.Get(),
-		hc:          params.Healthcheck,
-		db:          params.Database,
-		config:      params.Config,
-		csrfProtect: csrfProtect,
+		log:              params.Logger.Get(),
+		hc:               params.Healthcheck,
+		db:               params.Database,
+		config:           params.Config,
+		csrfProtect:      csrfProtect,
+		refererBlocklist: allowlist.New(params.Config.RefererBlocklist),
 	}
 
 	lc.Append(fx.Hook{

internal/handlers/image.go

@@ -21,6 +21,10 @@ import (
 // /v1/image/<host>/<path>/<width>x<height>.<format>
 func (s *Handlers) HandleImage() http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
+		if s.refuseBlockedReferer(w, r) {
+			return
+		}
+
 		req, ok := s.parseImageRequest(w, r)
 		if !ok {
 			return
@@ -248,6 +252,23 @@ func cacheControl(expires time.Time) string {
 	return fmt.Sprintf("public, max-age=%d, immutable", int64(maxAge/time.Second))
 }
 
+// refuseBlockedReferer answers 403 with a JSON error when the request's Referer
+// names a host on referer_blocklist, and reports whether it answered. A request
+// with no Referer, or one that does not parse as a URL with a host, is not
+// refused.
+func (s *Handlers) refuseBlockedReferer(
+	w http.ResponseWriter, r *http.Request,
+) bool {
+	referer, err := url.Parse(r.Referer())
+	if err != nil || !s.refererBlocklist.IsAllowed(referer) {
+		return false
+	}
+
+	s.respondError(w, "referer blocked", http.StatusForbidden)
+
+	return true
+}
+
 // notModified sets the ETag header to etag and, when the request's
 // If-None-Match is that ETag, answers 304 Not Modified. It reports whether it
 // answered. An empty etag sets no header and never answers.

internal/handlers/imageenc.go

@@ -22,6 +22,10 @@ import (
 // browsers identify the content type.
 func (s *Handlers) HandleImageEnc() http.HandlerFunc {
 	return func(w http.ResponseWriter, r *http.Request) {
+		if s.refuseBlockedReferer(w, r) {
+			return
+		}
+
 		ctx := r.Context()
 		start := time.Now()
 

internal/handlers/referer_blocklist_internal_test.go

@@ -0,0 +1,185 @@
+package handlers
+
+import (
+	"context"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/go-chi/chi/v5"
+	"sneak.berlin/go/pixa/internal/allowlist"
+	"sneak.berlin/go/pixa/internal/encurl"
+	"sneak.berlin/go/pixa/internal/httpfetcher"
+	"sneak.berlin/go/pixa/internal/imgcache"
+)
+
+// blockedReferer is a page on leech.example, which newRefererRoutes puts on
+// referer_blocklist.
+const blockedReferer = "https://leech.example/page.html"
+
+// countingFetcher passes each fetch on to the fetcher it holds and counts it.
+type countingFetcher struct {
+	httpfetcher.Fetcher
+
+	fetches atomic.Int32
+}
+
+// Fetch counts the fetch and passes it on.
+func (f *countingFetcher) Fetch(
+	ctx context.Context, url string,
+) (*httpfetcher.FetchResult, error) {
+	f.fetches.Add(1)
+
+	return f.Fetcher.Fetch(ctx, url)
+}
+
+// newRefererRoutes returns both image routes of a Handlers whose
+// referer_blocklist is "leech.example" and ".hotlinker.example", the
+// Handlers, and the fetcher the routes fetch through. The JPEG at photoPath
+// exists on allowlistedHost and on signedHost.
+func newRefererRoutes(t *testing.T) (http.Handler, *Handlers, *countingFetcher) {
+	t.Helper()
+
+	fetcher := &countingFetcher{
+		Fetcher: newPhotoFetcher(t, allowlistedHost, signedHost),
+	}
+
+	cache, err := imgcache.NewCache(setupTestDB(t), imgcache.CacheConfig{
+		StateDir:    t.TempDir(),
+		CacheTTL:    time.Hour,
+		NegativeTTL: 5 * time.Minute,
+	})
+	if err != nil {
+		t.Fatalf("imgcache.NewCache() error = %v", err)
+	}
+
+	svc, err := imgcache.NewService(&imgcache.ServiceConfig{
+		Cache:      cache,
+		Fetcher:    fetcher,
+		SigningKey: testSigningKey,
+		Allowlist:  []string{allowlistedHost},
+	})
+	if err != nil {
+		t.Fatalf("imgcache.NewService() error = %v", err)
+	}
+
+	encGen, err := encurl.NewGenerator(testSigningKey)
+	if err != nil {
+		t.Fatalf("encurl.NewGenerator() error = %v", err)
+	}
+
+	h := &Handlers{
+		log:    slog.New(slog.DiscardHandler),
+		imgSvc: svc,
+		encGen: encGen,
+		refererBlocklist: allowlist.New(
+			[]string{"leech.example", ".hotlinker.example"}),
+	}
+
+	r := chi.NewRouter()
+	r.Get("/v1/image/*", h.HandleImage())
+	r.Get("/v1/e/{token}/*", h.HandleImageEnc())
+
+	return r, h, fetcher
+}
+
+// getWithReferer sends a GET for target to routes with referer as its
+// Referer header, or with none when referer is empty, and returns the
+// response.
+func getWithReferer(
+	t *testing.T, routes http.Handler, target, referer string,
+) *httptest.ResponseRecorder {
+	t.Helper()
+
+	req := httptest.NewRequestWithContext(t.Context(), http.MethodGet, target, nil)
+	if referer != "" {
+		req.Header.Set("Referer", referer)
+	}
+
+	rec := httptest.NewRecorder()
+
+	routes.ServeHTTP(rec, req)
+	t.Logf("GET %s with Referer %q: %d", target, referer, rec.Code)
+
+	return rec
+}
+
+// TestRefererBlocklist verifies that both image routes refuse a request whose
+// Referer names a host on referer_blocklist with 403 and the JSON error,
+// without fetching from the upstream host, and serve a request with no
+// Referer, one that does not parse, or one naming any other host. Hosts are
+// matched as allowlist_hosts matches them.
+func TestRefererBlocklist(t *testing.T) {
+	t.Parallel()
+
+	cases := []struct {
+		name    string
+		referer string
+		want    int
+	}{
+		{"no referer", "", http.StatusOK},
+		{"unlisted host", "https://unlisted.example/page.html", http.StatusOK},
+		{"unparseable", "%zz", http.StatusOK},
+		{"listed host", blockedReferer, http.StatusForbidden},
+		{"subdomain of listed host", "https://www.leech.example/", http.StatusOK},
+		{"subdomain of dot pattern", "https://www.hotlinker.example/a.html",
+			http.StatusForbidden},
+		{"dot pattern without its dot", "https://hotlinker.example/",
+			http.StatusForbidden},
+		{"host continuing past dot pattern",
+			"https://hotlinker.example.evil.example/", http.StatusOK},
+	}
+
+	// The photo's URL on each image route.
+	photoURLs := map[string]func(t *testing.T, h *Handlers) string{
+		"plain URL": func(t *testing.T, _ *Handlers) string {
+			t.Helper()
+
+			return photoURL(allowlistedHost)
+		},
+		"encrypted URL": encPhotoURL,
+	}
+
+	for urlName, photoURLFor := range photoURLs {
+		for _, tc := range cases {
+			t.Run(urlName+", "+tc.name, func(t *testing.T) {
+				t.Parallel()
+
+				routes, h, fetcher := newRefererRoutes(t)
+
+				rec := getWithReferer(t, routes, photoURLFor(t, h), tc.referer)
+
+				if tc.want == http.StatusOK {
+					requireServedPhoto(t, rec)
+
+					return
+				}
+
+				checkErrorBody(t, rec, http.StatusForbidden, "referer blocked")
+
+				if n := fetcher.fetches.Load(); n != 0 {
+					t.Errorf("upstream fetched %d times, want 0", n)
+				}
+			})
+		}
+	}
+}
+
+// TestBlockedRefererRefusedWhenImageIsCached verifies that a request whose
+// Referer is on referer_blocklist is refused even when the image it asks for
+// is already cached, so the answer does not depend on the cache.
+func TestBlockedRefererRefusedWhenImageIsCached(t *testing.T) {
+	t.Parallel()
+
+	routes, h, _ := newRefererRoutes(t)
+
+	for _, target := range []string{photoURL(allowlistedHost), encPhotoURL(t, h)} {
+		requireServedPhoto(t, getWithReferer(t, routes, target, ""))
+
+		rec := getWithReferer(t, routes, target, blockedReferer)
+		checkErrorBody(t, rec, http.StatusForbidden, "referer blocked")
+	}
+}