From 5325a083b3183aacc7824ceabe786a8c0e744f83 Mon Sep 17 00:00:00 2001
From: Jordan Harband <ljharb@gmail.com>
Date: Fri, 22 Mar 2024 15:18:43 -0700
Subject: [PATCH] [spec] hex-escape punctuators

Fixes 65
---
 spec.emu | 35 +++++++++++++----------------------
 1 file changed, 13 insertions(+), 22 deletions(-)

diff --git a/spec.emu b/spec.emu
index fc1e600..4f1dad3 100644
--- a/spec.emu
+++ b/spec.emu
@@ -15,26 +15,6 @@ contributors: Jordan Harband
   <emu-clause id="sec-regexp-regular-expression-objects" number="2">
     <h1>RegExp (Regular Expression) Objects</h1>
 
-    <emu-clause id="sec-patterns" number="1">
-      <h1>Patterns</h1>
-
-      <h2>Syntax</h2>
-      <p>Each `\\u` |HexTrailSurrogate| for which the choice of associated `u` |HexLeadSurrogate| is ambiguous shall be associated with the nearest possible `u` |HexLeadSurrogate| that would otherwise have no corresponding `\\u` |HexTrailSurrogate|.</p>
-      <emu-grammar type="definition">
-        HexNonSurrogate ::
-          Hex4Digits [> but only if the MV of |Hex4Digits| is not in the inclusive interval from 0xD800 to 0xDFFF]
-
-        IdentityEscape[UnicodeMode] ::
-          [+UnicodeMode] SyntaxCharacter
-          [+UnicodeMode] `/` <ins>`,` `-` `=` `<` `>` `#` `&` `!` `%` `:` `;` `@` `~` `'` `"` `\``</ins>
-          <ins>[+UnicodeMode] WhiteSpace</ins>
-          [~UnicodeMode] SourceCharacter but not UnicodeIDContinue
-
-        DecimalEscape ::
-          NonZeroDigit DecimalDigits[~Sep]? [lookahead &notin; DecimalDigit]
-      </emu-grammar>
-    </emu-clause>
-
     <emu-clause id="sec-properties-of-the-regexp-constructor" number="5">
       <h1>Properties of the RegExp Constructor</h1>
 
@@ -55,9 +35,20 @@ contributors: Jordan Harband
               1. Append code unit U+005C (REVERSE SOLIDUS) to _escapedList_.
               1. Append code unit U+0078 (LATIN SMALL LETTER X) to _escapedList_.
               1. Append code unit U+0033 (DIGIT THREE) to _escapedList_.
+              1. Append _c_ to _escapedList_.
             1. Else if _toEscape_ contains _c_ or _c_ is matched by |WhiteSpace|, then
-              1. Append code unit U+005C (REVERSE SOLIDUS) to _escapedList_.
-            1. Append _c_ to _escapedList_.
+              1. Let _hex_ be Number::toString(𝔽(_c_), *16*<sub>𝔽</sub>).
+              1. If the length of _hex_ is 1 or 2, then
+                1. Set _hex_ to StringPad(_hex_, 2, *"0"*, ~start~).
+                1. Append code unit U+0078 (LATIN SMALL LETTER X) to _escapedList_.
+                1. Append the code units in _hex_ to _escapedList_.
+              1. Else,
+                1. Assert: The length of _hex_ is at most 4.
+                1. Set _hex_ to StringPad(_hex_, 4, *"0"*, ~start~).
+                1. Append code unit U+0075 (LATIN SMALL LETTER U) to _escapedList_.
+                1. Append the code units in _hex_ to _escapedList_.
+            1. Else,
+              1. Append _c_ to _escapedList_.
           1. Return CodePointsToString(_escapedList_).
         </emu-alg>