entity: 0.30 says dec refs are 1-7 digits, hex 1-6.

kivikakk · Jul 10, 2024 · 685d8a6 · 685d8a6
1 parent 2d6743e
commit 685d8a6
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/src/entity.rs b/src/entity.rs
@@ -36,7 +36,11 @@ pub fn unescape(text: &[u8]) -> Option<(Vec<u8>, usize)> {
             0
         };
 
-        if (1..=8).contains(&num_digits) && i < text.len() && text[i] == b';' {
+        if i < text.len()
+            && text[i] == b';'
+            && (((text[1] == b'x' || text[1] == b'X') && (1..=6).contains(&num_digits))
+                || (1..=7).contains(&num_digits))
+        {
             if codepoint == 0 || (0xD800..=0xE000).contains(&codepoint) || codepoint >= 0x110000 {
                 codepoint = 0xFFFD;
             }

diff --git a/src/parser/inlines.rs b/src/parser/inlines.rs
@@ -1010,8 +1010,10 @@ impl<'a, 'r, 'o, 'd, 'i, 'c, 'subj> Subject<'a, 'r, 'o, 'd, 'i, 'c, 'subj> {
         if c == b'_' {
             (
                 numdelims,
-                left_flanking && (!right_flanking || before_char.is_punctuation() || before_char.is_symbol()),
-                right_flanking && (!left_flanking || after_char.is_punctuation() || after_char.is_symbol()),
+                left_flanking
+                    && (!right_flanking || before_char.is_punctuation() || before_char.is_symbol()),
+                right_flanking
+                    && (!left_flanking || after_char.is_punctuation() || after_char.is_symbol()),
             )
         } else if c == b'\'' || c == b'"' {
             (