Accept a source path or query holding %25 in an image URL

The path traversal check now reads only the host and source path, not
the source query, and keeps a "%" that does not start a percent-escape
as it is, decoding the escapes around it, instead of refusing the URL.
Stopping the decoding at that "%" would let a double-encoded ".."
elsewhere in the path through.

Model: opus-5-5

internal/imgcache/urlparser.go

@@ -47,6 +47,9 @@ func ValidateDimension(name string, value int) error {
 var sizeFormatRegex = regexp.MustCompile(
 	`^(\d+)x(\d+)(?:\.(\w+))?$|^(orig)(?:\.(\w+))?$`)
 
+// percentEscapeRegex matches one percent-escape, such as "%2e"
+var percentEscapeRegex = regexp.MustCompile(`%[0-9A-Fa-f]{2}`)
+
 // ParsedURL contains the parsed components of an image proxy URL.
 type ParsedURL struct {
 	// Host is the source origin host (e.g., "cdn.example.com")
@@ -100,12 +103,6 @@ func ParseImageURL(urlPath string) (*ParsedURL, error) {
 // parseImageComponents parses <host>/<path>/<size>.<format>, or
 // <host>/<path>/<size> for JPEG XL.
 func parseImageComponents(remainder string) (*ParsedURL, error) {
-	// Check for path traversal before any other processing
-	err := checkPathTraversal(remainder)
-	if err != nil {
-		return nil, err
-	}
-
 	// Find the last path segment, which holds "size" or "size.format"
 	lastSlash := strings.LastIndex(remainder, "/")
 	if lastSlash == -1 {
@@ -161,6 +158,13 @@ func parseImageComponents(remainder string) (*ParsedURL, error) {
 		path = path[:qIndex]
 	}
 
+	// The source query names no file on the upstream, so only the host and
+	// the source path are checked for path traversal
+	err = checkPathTraversal(host + path)
+	if err != nil {
+		return nil, err
+	}
+
 	// Ensure path starts with /
 	if !strings.HasPrefix(path, "/") {
 		path = "/" + path
@@ -186,12 +190,7 @@ func checkPathTraversal(path string) error {
 	// Decode multiple times to catch double-encoding
 	decoded := path
 	for range 3 {
-		newDecoded, err := url.PathUnescape(decoded)
-		if err != nil {
-			// Malformed encoding is suspicious
-			return ErrPathTraversal
-		}
-
+		newDecoded := decodePercentEscapes(decoded)
 		if newDecoded == decoded {
 			break
 		}
@@ -232,6 +231,18 @@ func checkPathTraversal(path string) error {
 	return nil
 }
 
+// decodePercentEscapes decodes every percent-escape in s, such as %2e, and
+// keeps a "%" that does not start one as it is, where url.PathUnescape would
+// refuse the whole string. A source path holding %25, a literal "%", has such
+// a "%" after one more decoding.
+func decodePercentEscapes(s string) string {
+	return percentEscapeRegex.ReplaceAllStringFunc(s, func(escape string) string {
+		decoded, _ := url.PathUnescape(escape)
+
+		return decoded
+	})
+}
+
 // parseSizeFormat parses strings like "800x600.webp", "orig.png" or "800x600"
 func parseSizeFormat(s string) (Size, ImageFormat, error) {
 	matches := sizeFormatRegex.FindStringSubmatch(s)