add support for uri format

sebastian-toepfer · Dec 6, 2024 · ed5d1a0 · ed5d1a0
1 parent 56b8b59
commit ed5d1a0
Show file tree

Hide file tree

Showing 4 changed files with 141 additions and 1 deletion.
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
@@ -41,6 +41,8 @@ final class Formats {
         Map.of(3339, "full-time"),
         "duration",
         Map.of(3339, "duration"),
+        "uri",
+        Map.of(3986, "URI"),
         "email",
         Map.of(5321, "mailbox"),
         "ipv4",

diff --git a/.../main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/rfc/Rfcs.java b/.../main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/rfc/Rfcs.java
@@ -27,7 +27,7 @@
 import java.util.Optional;
 import java.util.regex.Pattern;
 
-@SuppressWarnings({ "java:S5843", "java:S6035" })
+@SuppressWarnings({ "java:S5843", "java:S6035", "java:S5855" })
 public final class Rfcs {
 
     private static final String DATE = "\\d{4}\\-\\d{2}\\-\\d{2}";
@@ -62,6 +62,57 @@ public final class Rfcs {
                 )
             )
         ),
+        Map.entry(
+            3986,
+            Map.of(
+                "URI",
+                new RegExRule(
+                    Pattern.compile(
+                        "^([A-Za-z]([A-Za-z0-9]|\\+|\\-|\\.)*)\\:(//(((([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-" +
+                        "9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:)*)@)?((\\[((([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}\\:)?[0-9A-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})?\\:\\:)|([Vv][0-9A-Fa-f]+\\.(([-A-Z._a-z0-9]|~)|(\\!|\\$|" +
+                        "&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:)+))\\])|(\\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|2" +
+                        "5[0-5])\\.(\\d|[1-9]\\d|1\\d{2}|2[0-4]\\d|25[0-5])|((([-A-Z._a-z0-9]|~)|%[0-9A-F" +
+                        "a-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=))*))(\\:\\d*)?(/(([-A-Z._a-" +
+                        "z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:|@)*)*" +
+                        "|/((([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|" +
+                        "\\=)|\\:|@)+(/(([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|" +
+                        "\\*|\\+|,|;|\\=)|\\:|@)*)*)?|(([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|" +
+                        "\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:|@)+(/(([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-" +
+                        "Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:|@)*)*|MISSING-0(([-A-Z._a-z0-9]|" +
+                        "~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|\\:|@))(\\?((((" +
+                        "[-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|\\(|\\)|\\*|\\+|,|;|\\=)|" +
+                        "\\:|@)|/|\\?)*))?(#(((([-A-Z._a-z0-9]|~)|%[0-9A-Fa-f][0-9A-Fa-f]|(\\!|\\$|&|'|" +
+                        "\\(|\\)|\\*|\\+|,|;|\\=)|\\:|@)|/|\\?)*))?$"
+                    )
+                )
+            )
+        ),
         Map.entry(
             4291,
             Map.of(

diff --git a/vocabulary/format-assertion/src/main/resources/rfc/rfc3986 b/vocabulary/format-assertion/src/main/resources/rfc/rfc3986
@@ -0,0 +1,81 @@
+URI           = scheme ":" hier-part [ "?" query ] [ "#" fragment ]
+
+hier-part     = "//" authority path-abempty
+              / path-absolute
+              / path-rootless
+              / path-empty
+
+URI-reference = URI / relative-ref
+
+absolute-URI  = scheme ":" hier-part [ "?" query ]
+
+relative-ref  = relative-part [ "?" query ] [ "#" fragment ]
+
+relative-part = "//" authority path-abempty
+              / path-absolute
+              / path-noscheme
+              / path-empty
+
+scheme        = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
+
+authority     = [ userinfo "@" ] host [ ":" port ]
+userinfo      = *( unreserved / pct-encoded / sub-delims / ":" )
+host          = IP-literal / IPv4address / reg-name
+port          = *DIGIT
+
+IP-literal    = "[" ( IPv6address / IPvFuture  ) "]"
+
+IPvFuture     = "v" 1*HEXDIG "." 1*( unreserved / sub-delims / ":" )
+
+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 ] "::"
+
+h16           = 1*4HEXDIG
+ls32          = ( h16 ":" h16 ) / IPv4address
+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
+
+reg-name      = *( unreserved / pct-encoded / sub-delims )
+
+path          = path-abempty    ; begins with "/" or is empty
+              / path-absolute   ; begins with "/" but not "//"
+              / path-noscheme   ; begins with a non-colon segment
+              / path-rootless   ; begins with a segment
+              / path-empty      ; zero characters
+
+path-abempty  = *( "/" segment )
+path-absolute = "/" [ segment-nz *( "/" segment ) ]
+path-noscheme = segment-nz-nc *( "/" segment )
+path-rootless = segment-nz *( "/" segment )
+path-empty    = 0<pchar>
+
+segment       = *pchar
+segment-nz    = 1*pchar
+segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
+              ; non-zero-length segment without any colon ":"
+
+pchar         = unreserved / pct-encoded / sub-delims / ":" / "@"
+
+query         = *( pchar / "/" / "?" )
+
+fragment      = *( pchar / "/" / "?" )
+
+pct-encoded   = "%" HEXDIG HEXDIG
+
+unreserved    = ALPHA / DIGIT / "-" / "." / "_" / "~"
+reserved      = gen-delims / sub-delims
+gen-delims    = ":" / "/" / "?" / "#" / "[" / "]" / "@"
+sub-delims    = "!" / "$" / "&" / "'" / "(" / ")"
+              / "*" / "+" / "," / ";" / "="
diff --git a/...st/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/FormatsTest.java b/...st/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/FormatsTest.java
@@ -96,4 +96,10 @@ void should_found_ipv6Format() {
         //ipv4 only -> invalid!
         assertThat(new Formats().findByName("ipv6").applyTo("125.158.4589.1"), is(false));
     }
+
+    @Test
+    void should_found_uriformat() {
+        assertThat(new Formats().findByName("uri").applyTo("http://www.example.com"), is(true));
+        assertThat(new Formats().findByName("uri").applyTo("1://noUri"), is(false));
+    }
 }