Use a more restrictive regex for URI validation (#409)

The json schema uri format should follow rfc3986 for uri validation. I
have replaced the current regex with a more restrictive one in order to
have a stronger validation according the RFC

refs #408

Co-authored-by: Vincent Maurin <[email protected]>

Author: vmaurin

src/main/java/com/networknt/schema/JsonMetaSchema.java

@@ -47,7 +47,7 @@ static PatternFormat pattern(String name, String regex) {
                 "^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)$"));
         COMMON_BUILTIN_FORMATS.add(pattern("ipv6",
                 "^\\s*((([0-9A-Fa-f]{1,4}:){7}([0-9A-Fa-f]{1,4}|:))|(([0-9A-Fa-f]{1,4}:){6}(:[0-9A-Fa-f]{1,4}|((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){5}(((:[0-9A-Fa-f]{1,4}){1,2})|:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3})|:))|(([0-9A-Fa-f]{1,4}:){4}(((:[0-9A-Fa-f]{1,4}){1,3})|((:[0-9A-Fa-f]{1,4})?:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){3}(((:[0-9A-Fa-f]{1,4}){1,4})|((:[0-9A-Fa-f]{1,4}){0,2}:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){2}(((:[0-9A-Fa-f]{1,4}){1,5})|((:[0-9A-Fa-f]{1,4}){0,3}:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3}))|:))|(([0-9A-Fa-f]{1,4}:){1}(((:[0-9A-Fa-f]{1,4}){1,6})|((:[0-9A-Fa-f]{1,4}){0,4}:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3}))|:))|(:(((:[0-9A-Fa-f]{1,4}){1,7})|((:[0-9A-Fa-f]{1,4}){0,5}:((25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)(\\.(25[0-5]|2[0-4]\\d|1\\d\\d|[1-9]?\\d)){3}))|:)))(%.+)?\\s*$"));
-        COMMON_BUILTIN_FORMATS.add(pattern("uri", "(^[a-zA-Z][a-zA-Z0-9+-.]*:[^\\s]*$)|(^//[^\\s]*$)"));
+        COMMON_BUILTIN_FORMATS.add(pattern("uri", "^([A-Za-z][A-Za-z0-9+.-]+):(\\/\\/([^@]+@)?([A-Za-z0-9.\\-_~]+)(:\\d+)?)?((?:[A-Za-z0-9-._~]|%[A-Fa-f0-9]|[!$&'()*+,;=:@])+(?:\\/(?:[A-Za-z0-9-._~]|%[A-Fa-f0-9]|[!$&'()*+,;=:@])*)*|(?:\\/(?:[A-Za-z0-9-._~]|%[A-Fa-f0-9]|[!$&'()*+,;=:@])+)*)?(\\?(?:[A-Za-z0-9-._~]|%[A-Fa-f0-9]|[!$&'()*+,;=:@]|[/?])+)?(\\#(?:[A-Za-z0-9-._~]|%[A-Fa-f0-9]|[!$&'()*+,;=:@]|[/?])+)?$"));
         COMMON_BUILTIN_FORMATS.add(pattern("color",
                 "(#?([0-9A-Fa-f]{3,6})\\b)|(aqua)|(black)|(blue)|(fuchsia)|(gray)|(green)|(lime)|(maroon)|(navy)|(olive)|(orange)|(purple)|(red)|(silver)|(teal)|(white)|(yellow)|(rgb\\(\\s*\\b([0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])\\b\\s*,\\s*\\b([0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])\\b\\s*,\\s*\\b([0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])\\b\\s*\\))|(rgb\\(\\s*(\\d?\\d%|100%)+\\s*,\\s*(\\d?\\d%|100%)+\\s*,\\s*(\\d?\\d%|100%)+\\s*\\))"));
         COMMON_BUILTIN_FORMATS.add(pattern("hostname",

src/test/resources/draft4/optional/format.json

@@ -197,9 +197,9 @@
         "valid": true
       },
       {
-        "description": "a valid protocol-relative URI",
+        "description": "a scheme is mandatory in URI",
         "data": "//foo.bar/?baz=qux#quux",
-        "valid": true
+        "valid": false
       },
       {
         "description": "an invalid URI",
@@ -210,6 +210,11 @@
         "description": "an invalid URI though valid URI reference",
         "data": "abc",
         "valid": false
+      },
+      {
+        "description": "an invalid query string",
+        "data": "http://foo.bar/?baz=q|ux#quux",
+        "valid": false
       }
     ]
   },