allow Relaxed to match punycode TLDs

For example, it should match "test.xn--8y0a063a" just like it matches
"test.联通".

Instead of doubling the size of the regexp by adding the punycode
version of every known TLD, simply match any valid punycode string which
follows "xn--". It's highly unlikely that this would cause false
positives.

Fixes #27.

Author: mvdan

xurls.go

@@ -72,7 +72,9 @@ func strictExp() string {
 }
 
 func relaxedExp() string {
-	site := domain + `(?i)` + anyOf(append(TLDs, PseudoTLDs...)...) + `(?-i)`
+	punycode := `xn--[a-z0-9-]+`
+	knownTLDs := anyOf(append(TLDs, PseudoTLDs...)...)
+	site := domain + `(?i)(` + punycode + `|` + knownTLDs + `)(?-i)`
 	hostName := `(` + site + `|` + ipAddr + `)`
 	webURL := hostName + port + `(/|/` + pathCont + `?|\b|$)`
 	return strictExp() + `|` + webURL

xurls_test.go

@@ -188,6 +188,11 @@ func TestRegexes(t *testing.T) {
 		{`foo.onion`, true},
 		{`中国.中国`, true},
 		{`中国.中国/foo中国`, true},
+		{`test.联通`, true},
+		{`test.xn--8y0a063a`, true},
+		{`test.xn--8y0a063a/foobar`, true},
+		{`test.xn-foo`, nil},
+		{`test.xn--`, nil},
 		{`foo.com/`, true},
 		{`1.1.1.1`, true},
 		{`10.50.23.250`, true},