[Temp] Try to remove finl_unicode methods

Author: LecrisUT

src/lib.rs

@@ -294,6 +294,104 @@ pub fn resourceprep(s: &str) -> Result<Cow<'_, str>, Error> {
     Ok(Cow::Owned(normalized))
 }
 
+fn is_combining_char(c: char) -> bool {
+    matches!(c, '\u{0300}'..='\u{0345}' |
+        '\u{0360}'..='\u{0361}' |
+        '\u{0483}'..='\u{0486}' |
+        '\u{0591}'..='\u{05A1}' |
+        '\u{05A3}'..='\u{05B9}' |
+        '\u{05BB}'..='\u{05BD}' |
+        '\u{05BF}' |
+        '\u{05C1}'..='\u{05C2}' |
+        '\u{05C4}' |
+        '\u{064B}'..='\u{0652}' |
+        '\u{0670}' |
+        '\u{06D6}'..='\u{06DC}' |
+        '\u{06DD}'..='\u{06DF}' |
+        '\u{06E0}'..='\u{06E4}' |
+        '\u{06E7}'..='\u{06E8}' |
+        '\u{06EA}'..='\u{06ED}' |
+        '\u{0901}'..='\u{0903}' |
+        '\u{093C}' |
+        '\u{093E}'..='\u{094C}' |
+        '\u{094D}' |
+        '\u{0951}'..='\u{0954}' |
+        '\u{0962}'..='\u{0963}' |
+        '\u{0981}'..='\u{0983}' |
+        '\u{09BC}' |
+        '\u{09BE}' |
+        '\u{09BF}' |
+        '\u{09C0}'..='\u{09C4}' |
+        '\u{09C7}'..='\u{09C8}' |
+        '\u{09CB}'..='\u{09CD}' |
+        '\u{09D7}' |
+        '\u{09E2}'..='\u{09E3}' |
+        '\u{0A02}' |
+        '\u{0A3C}' |
+        '\u{0A3E}' |
+        '\u{0A3F}' |
+        '\u{0A40}'..='\u{0A42}' |
+        '\u{0A47}'..='\u{0A48}' |
+        '\u{0A4B}'..='\u{0A4D}' |
+        '\u{0A70}'..='\u{0A71}' |
+        '\u{0A81}'..='\u{0A83}' |
+        '\u{0ABC}' |
+        '\u{0ABE}'..='\u{0AC5}' |
+        '\u{0AC7}'..='\u{0AC9}' |
+        '\u{0ACB}'..='\u{0ACD}' |
+        '\u{0B01}'..='\u{0B03}' |
+        '\u{0B3C}' |
+        '\u{0B3E}'..='\u{0B43}' |
+        '\u{0B47}'..='\u{0B48}' |
+        '\u{0B4B}'..='\u{0B4D}' |
+        '\u{0B56}'..='\u{0B57}' |
+        '\u{0B82}'..='\u{0B83}' |
+        '\u{0BBE}'..='\u{0BC2}' |
+        '\u{0BC6}'..='\u{0BC8}' |
+        '\u{0BCA}'..='\u{0BCD}' |
+        '\u{0BD7}' |
+        '\u{0C01}'..='\u{0C03}' |
+        '\u{0C3E}'..='\u{0C44}' |
+        '\u{0C46}'..='\u{0C48}' |
+        '\u{0C4A}'..='\u{0C4D}' |
+        '\u{0C55}'..='\u{0C56}' |
+        '\u{0C82}'..='\u{0C83}' |
+        '\u{0CBE}'..='\u{0CC4}' |
+        '\u{0CC6}'..='\u{0CC8}' |
+        '\u{0CCA}'..='\u{0CCD}' |
+        '\u{0CD5}'..='\u{0CD6}' |
+        '\u{0D02}'..='\u{0D03}' |
+        '\u{0D3E}'..='\u{0D43}' |
+        '\u{0D46}'..='\u{0D48}' |
+        '\u{0D4A}'..='\u{0D4D}' |
+        '\u{0D57}' |
+        '\u{0E31}' |
+        '\u{0E34}'..='\u{0E3A}' |
+        '\u{0E47}'..='\u{0E4E}' |
+        '\u{0EB1}' |
+        '\u{0EB4}'..='\u{0EB9}' |
+        '\u{0EBB}'..='\u{0EBC}' |
+        '\u{0EC8}'..='\u{0ECD}' |
+        '\u{0F18}'..='\u{0F19}' |
+        '\u{0F35}' |
+        '\u{0F37}' |
+        '\u{0F39}' |
+        '\u{0F3E}' |
+        '\u{0F3F}' |
+        '\u{0F71}'..='\u{0F84}' |
+        '\u{0F86}'..='\u{0F8B}' |
+        '\u{0F90}'..='\u{0F95}' |
+        '\u{0F97}' |
+        '\u{0F99}'..='\u{0FAD}' |
+        '\u{0FB1}'..='\u{0FB7}' |
+        '\u{0FB9}' |
+        '\u{20D0}'..='\u{20DC}' |
+        '\u{20E1}' |
+        '\u{302A}'..='\u{302F}' |
+        '\u{3099}' |
+        '\u{309A}')
+}
+
 /// Prepares a string according to the procedures described in Section 7 of
 /// [ITU-T Recommendation X.520 (2019)](https://www.itu.int/rec/T-REC-X.520-201910-I/en).
 ///
@@ -351,7 +449,7 @@ pub fn x520prep(s: &str, case_fold: bool) -> Result<Cow<'_, str>, Error> {
     // "The first code point of a string is prohibited from being a combining character."
     match s.chars().next() {
         Some(c) => {
-            if c.is_mark() {
+            if is_combining_char(c) {
                 return Err(Error(ErrorCause::StartsWithCombiningCharacter));
             }
         }

src/tables.rs

@@ -245,6 +245,6 @@ pub fn x520_mapped_to_nothing(c: char) -> bool {
 pub fn x520_mapped_to_space(c: char) -> bool {
     match c {
         '\u{09}' | '\u{0A}'..='\u{0D}' | '\u{85}' => true,
-        _ => c.is_separator(),
+        _ => c.is_whitespace(),
     }
 }