Lower-case the image URL's host and require a signature for a port (closes #246)

With `cdn.example.com` allowlisted, other letter cases and a host with a port also passed the allowlist; each spelling was fetched and cached on its own with its own per-host connection limit, and a port let an unsigned URL reach any port of the host.

The image URL parser now lower-cases the host and refuses one holding `@` with 400. A host followed by `:`, with or without a port (read as Go's URL parser reads it, unbracketed IPv6 included), never counts as allowlisted, so it needs a signature. The host is signed lower-cased, as the URL writes it, so a signature made over an upper-case spelling is refused with 401.

Model: opus-5-5

internal/imgcache/service.go

@@ -9,6 +9,7 @@ import (
 	"log/slog"
 	"net/url"
 	"runtime/debug"
+	"strings"
 	"time"
 
 	"github.com/dustin/go-humanize"
@@ -218,7 +219,16 @@ func (s *Service) ValidateRequest(req *ImageRequest) error {
 		return fmt.Errorf("invalid source URL: %w", err)
 	}
 
-	if s.allowlist.IsAllowed(parsedURL) {
+	// An allowlist entry names no port, so a host followed by ":", with or
+	// without a port, needs a signature. The port is read from the parsed
+	// URL, as the fetcher reads it: in an IPv6 address written without
+	// brackets, such as 2001:db8::1:8443, it is what follows the last ":".
+	// This is checked here and not in allowlist.IsAllowed, which also matches
+	// referer_blocklist, where a Referer must be blocked whatever its port.
+	hostHasPort := parsedURL.Port() != "" ||
+		strings.HasSuffix(parsedURL.Host, ":")
+
+	if !hostHasPort && s.allowlist.IsAllowed(parsedURL) {
 		return nil
 	}
 

internal/imgcache/service_internal_test.go

@@ -250,6 +250,97 @@ func TestService_ValidateRequest_SignatureExactHostMatch(t *testing.T) {
 	}
 }
 
+// TestService_ValidateRequest_HostWithPortNeedsSignature verifies that a host
+// followed by a port, or by a colon with no port, matches no allowlist entry,
+// so that a request for it without a signature is refused, while the same
+// host with no port is allowlisted.
+func TestService_ValidateRequest_HostWithPortNeedsSignature(t *testing.T) {
+	t.Parallel()
+
+	svc, _ := SetupTestService(t,
+		WithSigningKey(testSigningKey),
+		WithAllowlist(testHostCDN, "203.0.113.5", "2001:db8::1"),
+	)
+
+	tests := []struct {
+		host        string
+		allowlisted bool
+	}{
+		{testHostCDN, true},
+		{"cdn.example.com:8443", false},
+		{"cdn.example.com:443", false},
+		{"cdn.example.com:", false},
+		{"203.0.113.5", true},
+		{"203.0.113.5:8080", false},
+		{"[2001:db8::1]", true},
+		{"[2001:db8::1]:8443", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.host, func(t *testing.T) {
+			t.Parallel()
+
+			req := &ImageRequest{
+				SourceHost: tt.host,
+				SourcePath: testPathCat,
+				Size:       Size{Width: 50, Height: 50},
+				Format:     FormatJPEG,
+				Quality:    85,
+				FitMode:    FitCover,
+			}
+
+			err := svc.ValidateRequest(req)
+			t.Logf("ValidateRequest() for host %q with no signature: %v",
+				tt.host, err)
+
+			if allowlisted := err == nil; allowlisted != tt.allowlisted {
+				t.Errorf("host %q served without a signature = %v, want %v",
+					tt.host, allowlisted, tt.allowlisted)
+			}
+		})
+	}
+}
+
+// TestService_ValidateRequest_UnbracketedIPv6PortNeedsSignature verifies that
+// an allowlisted IPv6 address written without brackets and followed by a
+// port, or by a colon with no port, needs a signature. Go's URL parser, which
+// the fetcher uses, reads 2001:db8::1:8443 as the host 2001:db8::1 with the
+// port 8443.
+func TestService_ValidateRequest_UnbracketedIPv6PortNeedsSignature(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	svc, _ := SetupTestService(t,
+		WithSigningKey(testSigningKey),
+		WithAllowlist("2001:db8::1"),
+	)
+
+	for _, host := range []string{"2001:db8::1:8443", "2001:db8::1:"} {
+		t.Run(host, func(t *testing.T) {
+			t.Parallel()
+
+			req := &ImageRequest{
+				SourceHost: host,
+				SourcePath: testPathCat,
+				Size:       Size{Width: 50, Height: 50},
+				Format:     FormatJPEG,
+				Quality:    85,
+				FitMode:    FitCover,
+			}
+
+			err := svc.ValidateRequest(req)
+			t.Logf("ValidateRequest() for host %q with no signature: %v",
+				host, err)
+
+			if err == nil {
+				t.Errorf("host %q served without a signature, want refused",
+					host)
+			}
+		})
+	}
+}
+
 func TestService_Get_InvalidFile(t *testing.T) {
 	t.Parallel()
 

internal/imgcache/urlparser.go

@@ -15,6 +15,7 @@ import (
 var (
 	ErrInvalidPath       = errors.New("invalid image path")
 	ErrMissingHost       = errors.New("missing source host")
+	ErrInvalidHost       = errors.New("invalid source host")
 	ErrMissingSize       = errors.New("missing size specification")
 	ErrInvalidSize       = errors.New("invalid size format")
 	ErrInvalidFormat     = errors.New("invalid or unsupported format")
@@ -143,6 +144,17 @@ func parseImageComponents(remainder string) (*ParsedURL, error) {
 		return nil, ErrMissingHost
 	}
 
+	// A URL reads what comes before "@" as a user name and password, and the
+	// rest as the host
+	if strings.Contains(host, "@") {
+		return nil, fmt.Errorf("%w: %q holds @", ErrInvalidHost, host)
+	}
+
+	// Host names do not depend on letter case, so the allowlist, the upstream
+	// connection limits, the cache and the signature see one spelling of each
+	// host
+	host = strings.ToLower(host)
+
 	// Extract query string if present in path
 	if qIndex := strings.Index(path, "?"); qIndex != -1 {
 		query = path[qIndex+1:]

internal/imgcache/urlparser_internal_test.go

@@ -234,6 +234,49 @@ func TestParseImagePath(t *testing.T) {
 	}
 }
 
+// TestParseImagePath_LowerCasesHost verifies that the host is lower-cased, so
+// that every spelling of its letter case is the same host to the allowlist,
+// the upstream connection limits and the cache, and that the path keeps its
+// case.
+func TestParseImagePath_LowerCasesHost(t *testing.T) {
+	t.Parallel()
+
+	got, err := ParseImagePath("CDN.Example.COM/Photos/Cat.jpg/800x600.webp")
+	if err != nil {
+		t.Fatalf("ParseImagePath() error = %v", err)
+	}
+
+	t.Logf("parsed host %q, path %q", got.Host, got.Path)
+
+	if got.Host != testHostCDN {
+		t.Errorf("Host = %q, want %q", got.Host, testHostCDN)
+	}
+
+	if got.Path != "/Photos/Cat.jpg" {
+		t.Errorf("Path = %q, want %q", got.Path, "/Photos/Cat.jpg")
+	}
+}
+
+// TestParseImagePath_RefusesUserinfo verifies that a host holding "@" is
+// refused: a URL reads what comes before the "@" as a user name and password
+// and the rest as the host.
+func TestParseImagePath_RefusesUserinfo(t *testing.T) {
+	t.Parallel()
+
+	for _, input := range []string{
+		"user@cdn.example.com/photos/cat.jpg/800x600.webp",
+		"user:password@cdn.example.com/photos/cat.jpg/800x600.webp",
+	} {
+		got, err := ParseImagePath(input)
+		t.Logf("ParseImagePath(%q) = %+v, error = %v", input, got, err)
+
+		if !errors.Is(err, ErrInvalidHost) {
+			t.Errorf("ParseImagePath(%q) error = %v, want %v",
+				input, err, ErrInvalidHost)
+		}
+	}
+}
+
 func TestParsedURL_ToImageRequest(t *testing.T) {
 	t.Parallel()