Answer 415 for a source whose first bytes do not match its Content-Type (closes #253)

A body whose first bytes are not those of the format its Content-Type
names answered 500 on both image routes, was logged as pixa's own
error, and was fetched again on every request. Both routes now answer
415 for each error the first-bytes check returns, and the image service
logs the refused source at warning level. The failure also gets a
negative cache entry, as an upstream error status does, so the source
URL is not fetched again for 5 minutes, and meanwhile an image that
would need that fetch answers 502. README.md says so.

The case of TestService_Get_ConcurrentMissesShareAFailure that expected
such a source to be fetched again now expects the negative cache, as
#280 (comment) allows.

Model: opus-5-5

internal/imgcache/concurrent_misses_internal_test.go

@@ -331,8 +331,7 @@ func TestService_Get_FirstRequestLeavingKeepsTheWork(t *testing.T) {
 // TestService_Get_ConcurrentMissesShareAFailure has several requests for an
 // image that cannot be served arrive while its fetch is held: the one fetch
 // answers all of them with its error. The request after them is answered from
-// the negative cache when the failure is kept there, and fetches again when it
-// is not.
+// the negative cache, where the failure is kept.
 func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
 	t.Parallel()
 
@@ -346,8 +345,8 @@ func TestService_Get_ConcurrentMissesShareAFailure(t *testing.T) {
 		{"upstream answers 404, kept in the negative cache",
 			"/images/missing.jpg", httpfetcher.ErrUpstreamError,
 			ErrNegativeCached, 1},
-		{"source fails the magic byte check, not kept",
-			"/images/text.png", magic.ErrUnknownFormat, magic.ErrUnknownFormat, 2},
+		{"source fails the magic byte check, kept in the negative cache",
+			"/images/text.png", magic.ErrUnknownFormat, ErrNegativeCached, 1},
 	}
 
 	for _, tc := range tests {

internal/imgcache/service.go

@@ -458,13 +458,7 @@ func (s *Service) fetchAndProcess(
 	if err != nil {
 		// Store negative cache for certain errors
 		if isNegativeCacheable(err) {
-			statusCode := extractStatusCode(err)
-
-			storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
-			if storeErr != nil {
-				s.log.Warn("failed to store negative cache entry",
-					"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
-			}
+			s.storeNegative(ctx, req, extractStatusCode(err), err)
 		}
 
 		return nil, fmt.Errorf("upstream fetch failed: %w", err)
@@ -510,9 +504,16 @@ func (s *Service) fetchAndProcess(
 		"cipher", fetchResult.TLSCipherSuite,
 	)
 
-	// Validate magic bytes match content type
+	// Validate magic bytes match content type. A body that does not is the
+	// upstream's error, so it gets a negative cache entry, as an upstream
+	// error status does.
 	err = magic.ValidateMagicBytes(sourceData, fetchResult.ContentType)
 	if err != nil {
+		s.log.Warn("source refused", "request_id", middleware.GetReqID(ctx),
+			"host", req.SourceHost, "path", req.SourcePath,
+			"content_type", fetchResult.ContentType, "error", err)
+		s.storeNegative(ctx, req, httpStatusUnsupportedMediaType, err)
+
 		return nil, fmt.Errorf("content validation failed: %w", err)
 	}
 
@@ -528,6 +529,19 @@ func (s *Service) fetchAndProcess(
 	)
 }
 
+// storeNegative stores a negative cache entry for req's source, whose fetch
+// failed with err, so the source is not fetched again until the entry
+// expires. A failure to store the entry is only logged.
+func (s *Service) storeNegative(
+	ctx context.Context, req *ImageRequest, statusCode int, err error,
+) {
+	storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
+	if storeErr != nil {
+		s.log.Warn("failed to store negative cache entry",
+			"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
+	}
+}
+
 // processedVariant is a variant as processAndStore made it. Each request that
 // shared its processing serves it through a reader of its own.
 type processedVariant struct {
@@ -642,8 +656,9 @@ func signatureRequest(req *ImageRequest) *signature.Request {
 
 // HTTP status codes for error responses.
 const (
-	httpStatusBadGateway    = 502
-	httpStatusInternalError = 500
+	httpStatusBadGateway           = 502
+	httpStatusInternalError        = 500
+	httpStatusUnsupportedMediaType = 415
 )
 
 // isNegativeCacheable returns true if the error should be cached.