update abnf and regex for rfc4291

sebastian-toepfer · Dec 5, 2024 · 7c5f3ca · 7c5f3ca
1 parent fc43dc5
commit 7c5f3ca
Show file tree

Hide file tree

Showing 3 changed files with 47 additions and 14 deletions.
diff --git a/...c/main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/Formats.java b/...c/main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/Formats.java
@@ -48,7 +48,7 @@ final class Formats {
         Stream.of(
             new RfcBasedFormat("email", new Rfc5321(), "mailbox"),
             new RfcBasedFormat("ipv4", new Rfc2673(), "dotted-quad"),
-            new RfcBasedFormat("ipv6", new Rfc4291(), "address")
+            new RfcBasedFormat("ipv6", new Rfc4291(), "IPv6address")
         )
     )
         .map(Format.class::cast)

diff --git a/...in/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/rfc/Rfc4291.java b/...in/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/rfc/Rfc4291.java
@@ -30,13 +30,30 @@
 public final class Rfc4291 implements Rfc {
 
     private static final Map<String, Pattern> RULES = Map.of(
-        "address",
+        "IPv6address",
         Pattern.compile(
-            "^(([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){7})|" +
-            "([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){0,5})*\\:\\:([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){0,5})*|" +
-            "(((([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){5})\\:)|" +
-            "([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){0,4})*\\:\\:([0-9A-Fa-f]{1,4}(\\:[0-9A-Fa-f]{1,4}){0,4})*)" +
-            "\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}\\.\\d{1,3}))$"
+            "^(([0-9A-Fa-f]{1,4}\\:){6}(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|" +
+            "25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|" +
+            "25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5]))|\\:\\:([0-9A-Fa-f]{1,4}\\:){5}" +
+            "(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\." +
+            "(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\." +
+            "(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5]))|([0-9A-Fa-f]{1,4})?\\:\\:([0-9A-Fa-f]{1,4}\\:){4}" +
+            "(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|" +
+            "1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|" +
+            "2[0-4]\\d|25[0-5]))|(([0-9A-Fa-f]{1,4}\\:){0,1}[0-9A-Fa-f]{1,4})?\\:\\:([0-9A-Fa-f]{1,4}\\:){3}" +
+            "(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|" +
+            "1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|" +
+            "2[0-4]\\d|25[0-5]))|(([0-9A-Fa-f]{1,4}\\:){0,2}[0-9A-Fa-f]{1,4})?\\:\\:([0-9A-Fa-f]{1,4}\\:){2}" +
+            "(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|" +
+            "1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|" +
+            "2[0-4]\\d|25[0-5]))|(([0-9A-Fa-f]{1,4}\\:){0,3}[0-9A-Fa-f]{1,4})?\\:\\:[0-9A-Fa-f]{1,4}\\:" +
+            "(([0-9A-Fa-f]{1,4}\\:[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|" +
+            "1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|" +
+            "2[0-4]\\d|25[0-5]))|(([0-9A-Fa-f]{1,4}\\:){0,4}[0-9A-Fa-f]{1,4})?\\:\\:(([0-9A-Fa-f]{1,4}\\:" +
+            "[0-9A-Fa-f]{1,4})|(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|" +
+            "25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5]))|" +
+            "(([0-9A-Fa-f]{1,4}\\:){0,5}[0-9A-Fa-f]{1,4})?\\:\\:[0-9A-Fa-f]{1,4}|(([0-9A-Fa-f]{1,4}\\:){0,6}" +
+            "[0-9A-Fa-f]{1,4})?\\:\\:)$"
         )
     );
 

diff --git a/vocabulary/format-assertion/src/main/resources/rfc/rfc4291 b/vocabulary/format-assertion/src/main/resources/rfc/rfc4291
@@ -1,7 +1,23 @@
-; selfmade :( -> not effectiv
-dotted-quad      = decbyte "." decbyte "." decbyte "." decbyte
-decbyte          = 1*3DIGIT
-address          = (hexbytes 7(":" hexbytes) ) / *(hexbytes *5(":" hexbytes)) zeros *(hexbytes *5(":" hexbytes)) / ((((hexbytes 5(":" hexbytes) )  ":") / *(hexbytes *4(":" hexbytes)) zeros *(hexbytes *4(":" hexbytes))) dotted-quad)
-zeros            = "::"
-hexbytes         = 1*4hexValue
-hexValue         = DIGIT / %x41-46 / %x61-66
+IPv6address =                            6( h16 ":" ) ls32
+            /                       "::" 5( h16 ":" ) ls32
+            / [               h16 ] "::" 4( h16 ":" ) ls32
+            / [ *1( h16 ":" ) h16 ] "::" 3( h16 ":" ) ls32
+            / [ *2( h16 ":" ) h16 ] "::" 2( h16 ":" ) ls32
+            / [ *3( h16 ":" ) h16 ] "::"    h16 ":"   ls32
+            / [ *4( h16 ":" ) h16 ] "::"              ls32
+            / [ *5( h16 ":" ) h16 ] "::"              h16
+            / [ *6( h16 ":" ) h16 ] "::"
+
+ls32        = ( h16 ":" h16 ) / IPv4address
+            ; least-significant 32 bits of address
+
+h16         = 1*4HEXDIG
+            ; 16 bits of address represented in hexadecimal
+
+IPv4address = dec-octet "." dec-octet "." dec-octet "." dec-octet
+
+dec-octet   = DIGIT                 ; 0-9
+            / %x31-39 DIGIT         ; 10-99
+            / "1" 2DIGIT            ; 100-199
+            / "2" %x30-34 DIGIT     ; 200-249
+            / "25" %x30-35          ; 250-255