Skip to content

Commit

Permalink
add support for uri format
Browse files Browse the repository at this point in the history
  • Loading branch information
@sebastian-toepfer
sebastian-toepfer committed Dec 6, 2024
1 parent 776f674 commit 9aec969
Show file tree
Hide file tree
Showing 4 changed files with 141 additions and 1 deletion.
2 changes: 2 additions & 0 deletions ...c/main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/Formats.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,8 @@ final class Formats {
Map.of(3339, "full-time"),
"duration",
Map.of(3339, "duration"),
"uri",
Map.of(3986, "URI"),
"email",
Map.of(5321, "mailbox"),
"ipv4",
Expand Down
53 changes: 52 additions & 1 deletion .../main/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/rfc/Rfcs.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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}";
Expand Down Expand Up @@ -66,6 +66,57 @@ 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(
Expand Down
81 changes: 81 additions & 0 deletions vocabulary/format-assertion/src/main/resources/rfc/rfc3986
View file
Original file line number Diff line number Diff line change
@@ -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 = "!" / "$" / "&" / "'" / "(" / ")"
/ "*" / "+" / "," / ";" / "="
6 changes: 6 additions & 0 deletions ...st/java/io/github/sebastiantoepfer/jsonschema/vocabulary/formatassertion/FormatsTest.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -102,4 +102,10 @@ void should_found_hostname() {
assertThat(new Formats().findByName("hostname").applyTo("www"), is(true));
assertThat(new Formats().findByName("hostname").applyTo("bar_baz"), 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));
}
}

0 comments on commit 9aec969

Please sign in to comment.