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

A new setting, referer_blocklist (PIXA_REFERER_BLOCKLIST), lists hosts
written and matched as allowlist_hosts are, with the same matcher and the
same entry check; a bad entry aborts startup naming the setting and the
entry. Both image routes check the Referer first and answer 403 with the
JSON error, so a blocked request fetches nothing and is refused whether or
not the image is cached. No Referer, or one that does not parse as a URL
with a host, is served; README.md and config.example.yml say this makes the
list easy to get around. The CIDR-list entry reader is renamed listEntries
now that host lists use it too.

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()