package atomfeed import ( "mime" "regexp" "strings" "golang.org/x/text/language" ) type ( EmailAddress string LanguageTag string MediaType string // URI string IRI string ) // func isValidURL(uri URI) bool { // _, err := url.ParseRequestURI(string(uri)) // return err == nil // } // // func isValidURN(uri URI) bool { // pattern := `\A(?i:urn:(?!urn:)(?[a-z0-9][a-z0-9-]{1,31}):(?(?:[-a-z0-9()+,.:=@;$_!*'&~\/]|%[0-9a-f]{2})+)(?:\?\+(?.*?))?(?:\?=(?.*?))?(?:#(?.*?))?)\z` // return regexp.MustCompile(pattern).MatchString(string(uri)) // } // // // isValidURI checks whether an URI is valid or not. // func isValidURI(uri URI) bool { // return isValidURL(uri) || isValidURN(uri) // } // isValidIRI checks whether an IRI is valid or not. // The used pattern stems from // https://www.w3.org/2011/04/XMLSchema/TypeLibrary-IRI-RFC3987.xsd func isValidIRI(iri IRI) bool { pattern := `((([A-Za-z])[A-Za-z0-9+\-\.]*):((//(((([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽!$&'()*+,;=:]|(%[0-9A-Fa-f][0-9A-Fa-f]))*@))?((\[((((([0-9A-Fa-f]{0,4}:)){6}(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|(::(([0-9A-Fa-f]{0,4}:)){5}(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|(([0-9A-Fa-f]{0,4})?::(([0-9A-Fa-f]{0,4}:)){4}(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|((((([0-9A-Fa-f]{0,4}:))?[0-9A-Fa-f]{0,4}))?::(([0-9A-Fa-f]{0,4}:)){3}(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|((((([0-9A-Fa-f]{0,4}:)){0,2}[0-9A-Fa-f]{0,4}))?::(([0-9A-Fa-f]{0,4}:)){2}(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|((((([0-9A-Fa-f]{0,4}:)){0,3}[0-9A-Fa-f]{0,4}))?::[0-9A-Fa-f]{0,4}:(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|((((([0-9A-Fa-f]{0,4}:)){0,4}[0-9A-Fa-f]{0,4}))?::(([0-9A-Fa-f]{0,4}:[0-9A-Fa-f]{0,4})|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))))|((((([0-9A-Fa-f]{0,4}:)){0,5}[0-9A-Fa-f]{0,4}))?::[0-9A-Fa-f]{0,4})|((((([0-9A-Fa-f]{0,4}:)){0,6}[0-9A-Fa-f]{0,4}))?::))|(v[0-9A-Fa-f]+\.[A-Za-z0-9\-\._~!$&'()*+,;=:]+))\])|(([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5]))\.([0-9]|([1-9][0-9])|(1([0-9]){2})|(2[0-4][0-9])|(25[0-5])))|(([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=]))*)((:[0-9]*))?)((/(([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@]))*))*)|(/(((([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@]))+((/(([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@]))*))*))?)|((([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@]))+((/(([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@]))*))*)|)((\?(([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@])|[-󰀀-󿿽􀀀-􏿽/?])*))?((#((([A-Za-z0-9\-\._~ -퟿豈-﷏ﷰ-￯𐀀-🿽𠀀-𯿽𰀀-𿿽񀀀-񏿽񐀀-񟿽񠀀-񯿽񰀀-񿿽򀀀-򏿽򐀀-򟿽򠀀-򯿽򰀀-򿿽󀀀-󏿽󐀀-󟿽󡀀-󯿽]|(%[0-9A-Fa-f][0-9A-Fa-f])|[!$&'()*+,;=:@])|/|\?))*))?)` return regexp.MustCompile(pattern).MatchString(string(iri)) } func isCorrectlyEscaped(text string) bool { relevantEntities := []string{"&", "<", ">", """, "'"} for _, entity := range relevantEntities { if strings.Contains(text, entity) { return false } } return true } func isCompositeMediaType(mediaType string) bool { mediaType, _, err := mime.ParseMediaType(mediaType) if err != nil { return false } return strings.HasPrefix(mediaType, "multipart/") || strings.HasPrefix(mediaType, "message/") } func isXMLMediaType(mediaType string) bool { mediaType, _, err := mime.ParseMediaType(mediaType) if err != nil { return false } return strings.HasSuffix(mediaType, "/xml") || strings.HasSuffix(mediaType, "+xml") } func isValidMediaType(mediaType string) bool { _, _, err := mime.ParseMediaType(mediaType) return err == nil } func isValidLanguageTag(tag LanguageTag) bool { _, err := language.Parse(string(tag)) return err == nil }