fix(csharp) support digit separators in binary literals and numeric type suffixes

CHANGES.md

@@ -7,6 +7,7 @@ Core Grammars:
 - fix(cmake) only highlight standalone numbers, not digits that begin an identifier (e.g. `3rdparty`), issue #4170 [MarkXian][]
 - fix(cpp) require a word boundary before numeric literals so digits inside identifiers aren't highlighted as numbers, issue #4231 [Mark Xian][]
 - fix(c) only match real `atomic_*` type names, not C11 atomic functions, issue #3837 [MarkXian][]
+- fix(csharp) support digit separators in binary literals and numeric type suffixes, and stop highlighting the leading `_` of an identifier, issue #4258 [Sarath Francis][]
 - enh(python) add missing builtins: `aiter` and `anext` (Python 3.10), `frozendict` and `sentinel` (Python 3.15) [Hugo van Kemenade][]
 
 Documentation:

src/languages/csharp.js

@@ -161,12 +161,18 @@ export default function(hljs) {
     literal: LITERAL_KEYWORDS
   };
   const TITLE_MODE = hljs.inherit(hljs.TITLE_MODE, { begin: '[a-zA-Z](\\.?\\w)*' });
+  // https://learn.microsoft.com/en-us/dotnet/csharp/language-reference/builtin-types/integral-numeric-types
+  // https://learn.microsoft.com/en-us/dotnet/csharp/language-reference/builtin-types/floating-point-numeric-types
+  // `_` separators sit between digits, and may also follow the `0x`/`0b` prefix
+  const DIGITS = '\\d(_*\\d)*';
+  const INTEGER_SUFFIX = '([uU][lL]?|[lL][uU]?)?';
+  const REAL_SUFFIX = '([fFdDmM]|[uU][lL]?|[lL][uU]?)?';
   const NUMBERS = {
     className: 'number',
     variants: [
-      { begin: '\\b(0b[01\']+)' },
-      { begin: '(-?)\\b([\\d\']+(\\.[\\d\']*)?|\\.[\\d\']+)(u|U|l|L|ul|UL|f|F|b|B)' },
-      { begin: '(-?)(\\b0[xX][a-fA-F0-9\'_]+|(\\b[\\d\'_]+(\\.[\\d\'_]*)?|\\.[\\d\'_]+)([eE][-+]?[\\d\'_]+)?)' }
+      { begin: '\\b0[bB]_*[01](_*[01])*' + INTEGER_SUFFIX },
+      { begin: '(-?)\\b0[xX]_*[a-fA-F0-9](_*[a-fA-F0-9])*' + INTEGER_SUFFIX },
+      { begin: '(-?)(\\b' + DIGITS + '(\\.(' + DIGITS + ')?)?|\\.' + DIGITS + ')([eE][-+]?' + DIGITS + ')?' + REAL_SUFFIX }
     ],
     relevance: 0
   };

test/markup/csharp/numbers.expect.txt

@@ -0,0 +1,11 @@
+<span class="hljs-built_in">int</span> bin = <span class="hljs-number">0b1010_1010</span>;
+<span class="hljs-built_in">int</span> binSeparatorFirst = <span class="hljs-number">0b_1010_1010</span>;
+<span class="hljs-built_in">ulong</span> hex = <span class="hljs-number">0xFF_FFUL</span>;
+<span class="hljs-built_in">uint</span> hexSuffix = <span class="hljs-number">0xFFu</span>;
+<span class="hljs-built_in">ulong</span> decSuffix = <span class="hljs-number">1_000_000UL</span>;
+<span class="hljs-built_in">decimal</span> price = <span class="hljs-number">19.99m</span>;
+<span class="hljs-built_in">double</span> ratio = <span class="hljs-number">3.14d</span>;
+<span class="hljs-built_in">decimal</span> big = <span class="hljs-number">1.5e10M</span>;
+<span class="hljs-comment">// _count and point._1 are identifiers, not numbers</span>
+<span class="hljs-built_in">int</span> _count = <span class="hljs-number">0</span>;
+<span class="hljs-built_in">int</span> index = point._1;

test/markup/csharp/numbers.txt

@@ -0,0 +1,11 @@
+int bin = 0b1010_1010;
+int binSeparatorFirst = 0b_1010_1010;
+ulong hex = 0xFF_FFUL;
+uint hexSuffix = 0xFFu;
+ulong decSuffix = 1_000_000UL;
+decimal price = 19.99m;
+double ratio = 3.14d;
+decimal big = 1.5e10M;
+// _count and point._1 are identifiers, not numbers
+int _count = 0;
+int index = point._1;