allow country TLDs in scheme-less links (#106)

* allow country TLDs in scheme-less links

* fix fmt

* fix manual ts types

Author: Simon-Laux

CHANGELOG.md

@@ -2,6 +2,8 @@
 
 ## Unreleased
 
+- allow country TLDs in scheme-less links
+
 ## 0.14.0 - Bug fixes and scheme-less links
 
 - Parse scheme-less links for some TLDs

message_parser_wasm/src/lib.rs

@@ -41,6 +41,7 @@ export type LinkDestination = {
   target: string;
   hostname: null | string;
   punycode: null | PunycodeWarning;
+  scheme: null | string;
 };
 export type ParsedElement =
   | { t: "Text"; c: string }

src/parser/link_url/allowed_tlds/country_tlds.rs

@@ -0,0 +1,19 @@
+// extracted from first table on https://de.wikipedia.org/wiki/Liste_länderspezifischer_Top-Level-Domains
+pub const COUNTRY_TLDS: [&str; 254] = [
+    "ac", "ad", "ae", "af", "ag", "ai", "al", "am", "ao", "aq", "ar", "as", "at", "au", "aw", "ax",
+    "az", "ba", "bb", "bd", "be", "bf", "bg", "bh", "bi", "bj", "bl", "bm", "bn", "bo", "bq", "br",
+    "bs", "bt", "bv", "bw", "by", "bz", "ca", "cc", "cd", "cf", "cg", "ch", "ci", "ck", "cl", "cm",
+    "cn", "co", "cr", "cu", "cv", "cw", "cx", "cy", "cz", "de", "dj", "dk", "dm", "do", "dz", "ec",
+    "ee", "eg", "eh", "er", "es", "et", "eu", "fi", "fj", "fk", "fm", "fo", "fr", "ga", "gb", "gd",
+    "ge", "gf", "gg", "gh", "gi", "gl", "gm", "gn", "gp", "gq", "gr", "gs", "gt", "gu", "gw", "gy",
+    "hk", "hm", "hn", "hr", "ht", "hu", "id", "ie", "il", "im", "in", "io", "iq", "ir", "is", "it",
+    "je", "jm", "jo", "jp", "ke", "kg", "kh", "ki", "km", "kn", "kp", "kr", "kw", "ky", "kz", "la",
+    "lb", "lc", "li", "lk", "lr", "ls", "lt", "lu", "lv", "ly", "ma", "mc", "md", "me", "mf", "mg",
+    "mh", "mk", "ml", "mm", "mn", "mo", "mp", "mq", "mr", "ms", "mt", "mu", "mv", "mw", "mx", "my",
+    "mz", "na", "nc", "ne", "nf", "ng", "ni", "nl", "no", "np", "nr", "nu", "nz", "om", "pa", "pe",
+    "pf", "pg", "ph", "pk", "pl", "pm", "pn", "pr", "ps", "pt", "pw", "py", "qa", "re", "ro", "rs",
+    "ru", "rw", "sa", "sb", "sc", "sd", "se", "sg", "sh", "si", "sj", "sk", "sl", "sm", "sn", "so",
+    "sr", "ss", "st", "su", "sv", "sx", "sy", "sz", "tc", "td", "tf", "tg", "th", "tj", "tk", "tl",
+    "tm", "tn", "to", "tp", "tr", "tt", "tv", "tw", "tz", "ua", "ug", "uk", "us", "uy", "uz", "va",
+    "vc", "ve", "vg", "vi", "vn", "vu", "wf", "ws", "ye", "yt", "za", "zm", "zr", "zw",
+];

src/parser/link_url/allowed_tlds/mod.rs

@@ -0,0 +1,36 @@
+mod country_tlds;
+
+const ALLOWED_TOP_LEVEL_DOMAINS: &[&str] = &[
+    // originals from RFC920 + net
+    "com", "org", "net", "edu", "gov", "mil", // for deltachat
+    "chat",
+];
+
+pub fn check_if_tld_is_allowed(tld: &str) -> bool {
+    if ALLOWED_TOP_LEVEL_DOMAINS.iter().any(|item| *item == tld) {
+        true
+    } else {
+        country_tlds::COUNTRY_TLDS.binary_search(&tld).is_ok()
+    }
+}
+
+#[cfg(test)]
+mod test {
+    use crate::parser::link_url::allowed_tlds::check_if_tld_is_allowed;
+
+    #[test]
+    fn test_check_tld() {
+        assert!(check_if_tld_is_allowed("chat"));
+        assert!(check_if_tld_is_allowed("com"));
+
+        assert!(check_if_tld_is_allowed("de"));
+        assert!(check_if_tld_is_allowed("at"));
+        assert!(check_if_tld_is_allowed("uk"));
+        assert!(check_if_tld_is_allowed("fr"));
+    }
+
+    #[test]
+    fn test_check_tld_not_allowed() {
+        assert!(!check_if_tld_is_allowed("doesnotexist"));
+    }
+}

src/parser/link_url/mod.rs

@@ -1,3 +1,4 @@
+mod allowed_tlds;
 mod ip;
 mod parenthesis_counter;
 mod parse_link;

src/parser/link_url/parse_link.rs

@@ -23,6 +23,7 @@ use crate::parser::{
 };
 
 use super::{
+    allowed_tlds::check_if_tld_is_allowed,
     parenthesis_counter::count_chars_in_complete_parenthesis,
     punycode_warning::get_puny_code_warning,
 };
@@ -46,14 +47,6 @@ fn is_allowed_generic_scheme(scheme: &str) -> bool {
     )
 }
 
-const ALLOWED_TOP_LEVEL_DOMAINS: &[&str] = &[
-    // originals from RFC920 + net
-    ".com", ".org", ".net", ".edu", ".gov", ".mil",
-    // for deltachat
-    ".chat",
-    // !todo country codes here next
-];
-
 // These ranges have been extracted from RFC3987, Page 8.
 const UCSCHAR_RANGES: [RangeInclusive<u32>; 17] = [
     0xa0..=0xd7ff,
@@ -294,10 +287,18 @@ fn parse_iri(input: &str) -> IResult<&str, LinkDestination, CustomError<&str>> {
 
     // now with host, if we dont have a scheme we need to check it for TLD
     if scheme.is_empty() {
-        ALLOWED_TOP_LEVEL_DOMAINS
-            .iter()
-            .find(|&&tld| host.ends_with(tld))
-            .ok_or(nom::Err::Failure(CustomError::<&str>::InvalidLink))?;
+        if !host.contains('.') {
+            return Err(nom::Err::Failure(CustomError::<&str>::InvalidLink));
+        }
+
+        let tld = host
+            .split('.')
+            .last()
+            .ok_or(nom::Err::Failure(CustomError::<&str>::InvalidLinkNoTLD))?;
+
+        if !check_if_tld_is_allowed(tld) {
+            return Err(nom::Err::Failure(CustomError::<&str>::InvalidLink));
+        }
     }
 
     let (input, path) = opt(alt((

src/parser/parse_from_text/base_parsers.rs

@@ -18,6 +18,7 @@ pub enum CustomError<I> {
     Nom(I, ErrorKind),
     InvalidEmail,
     InvalidLink,
+    InvalidLinkNoTLD,
     UnexpectedContent,
     PrecedingWhitespaceMissing,
     OptionIsUnexpectedNone,