fix: unicode surrogate pair parsing

Author: alexander-akait

src/__tests__/classes.js

@@ -246,3 +246,9 @@ test('class selector with escaping (33)', '.f\\+o\\+o', (t, tree) => {
     t.deepEqual(tree.nodes[0].nodes[0].type, 'class');
     t.deepEqual(tree.nodes[0].nodes[0].raws.value, 'f\\+o\\+o');
 });
+
+test('class selector with escaping (34)', '.\\1D306', (t, tree) => {
+    t.deepEqual(tree.nodes[0].nodes[0].value, '𝌆');
+    t.deepEqual(tree.nodes[0].nodes[0].type, 'class');
+    t.deepEqual(tree.nodes[0].nodes[0].raws.value, '\\1D306');
+});

src/util/unesc.js

@@ -1,11 +1,19 @@
-const HEX_ESC = /\\(?:([0-9a-fA-F]{6})|([0-9a-fA-F]{1,5})(?: |(?![0-9a-fA-F])))/g;
-const OTHER_ESC = /\\(.)/g;
+const whitespace = '[\\x20\\t\\r\\n\\f]';
+const unescapeRegExp = new RegExp('\\\\([\\da-f]{1,6}' + whitespace + '?|(' + whitespace + ')|.)', 'ig');
+
 export default function unesc (str) {
-    str = str.replace(HEX_ESC, (_, hex1, hex2) => {
-        let hex = hex1 || hex2;
-        let code = parseInt(hex, 16);
-        return String.fromCharCode(code);
+    return str.replace(unescapeRegExp, (_, escaped, escapedWhitespace) => {
+        const high = '0x' + escaped - 0x10000;
+
+        // NaN means non-codepoint
+        // Workaround erroneous numeric interpretation of +"0x"
+        // eslint-disable-next-line no-self-compare
+        return high !== high || escapedWhitespace
+            ? escaped
+            : high < 0
+                ? // BMP codepoint
+                String.fromCharCode(high + 0x10000)
+                : // Supplemental Plane codepoint (surrogate pair)
+                String.fromCharCode((high >> 10) | 0xd800, (high & 0x3ff) | 0xdc00);
     });
-    str = str.replace(OTHER_ESC, (_, char) => char);
-    return str;
 }