From 2212aa2388c4f6abae577daa2cbb27f8796939d4 Mon Sep 17 00:00:00 2001
From: Timothy Flynn <trflynn89@pm.me>
Date: Sat, 5 Feb 2022 10:43:13 -0500
Subject: [PATCH] LibRegex: Support non-ASCII whitespace characters when
 matching \s or \S

ECMA-262 defines \s as:

    Return the CharSet containing all characters corresponding to a code
    point on the right-hand side of the WhiteSpace or LineTerminator
    productions.

The LineTerminator production is simply: U+000A, U+000D, U+2028, or
U+2029. Unfortunately there isn't a Unicode property that covers just
those code points.

The WhiteSpace production is: U+0009, U+000B, U+000C, U+FEFF, or any
code point with the Space_Separator general category.

If the Unicode generators are disabled, this will fall back to ASCII
space code points.
---
 Tests/LibRegex/Regex.cpp                      |  9 +++++++++
 Userland/Libraries/LibRegex/RegexByteCode.cpp | 14 +++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/Tests/LibRegex/Regex.cpp b/Tests/LibRegex/Regex.cpp
index c7e699c194..7c4dfe80fe 100644
--- a/Tests/LibRegex/Regex.cpp
+++ b/Tests/LibRegex/Regex.cpp
@@ -706,6 +706,13 @@ TEST_CASE(ECMA262_match)
 
 TEST_CASE(ECMA262_unicode_match)
 {
+    constexpr auto space_and_line_terminator_code_points = Array { 0x0009, 0x000A, 0x000B, 0x000C, 0x000D, 0x0020, 0x00A0, 0x1680, 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, 0x2006, 0x2007, 0x2008, 0x2009, 0x200A, 0x2028, 0x2029, 0x202F, 0x205F, 0x3000, 0xFEFF };
+
+    StringBuilder builder;
+    for (u32 code_point : space_and_line_terminator_code_points)
+        builder.append_code_point(code_point);
+    auto space_and_line_terminators = builder.build();
+
     struct _test {
         StringView pattern;
         StringView subject;
@@ -729,6 +736,8 @@ TEST_CASE(ECMA262_unicode_match)
         { "(?<𝓑𝓻𝓸𝔀𝓷>brown)"sv, "brown"sv, true, ECMAScriptFlags::Unicode },
         { "(?<\\u{1d4d1}\\u{1d4fb}\\u{1d4f8}\\u{1d500}\\u{1d4f7}>brown)"sv, "brown"sv, true, ECMAScriptFlags::Unicode },
         { "(?<\\ud835\\udcd1\\ud835\\udcfb\\ud835\\udcf8\\ud835\\udd00\\ud835\\udcf7>brown)"sv, "brown"sv, true, ECMAScriptFlags::Unicode },
+        { "^\\s+$"sv, space_and_line_terminators },
+        { "^\\s+$"sv, space_and_line_terminators, true, ECMAScriptFlags::Unicode },
     };
 
     for (auto& test : tests) {
diff --git a/Userland/Libraries/LibRegex/RegexByteCode.cpp b/Userland/Libraries/LibRegex/RegexByteCode.cpp
index eb9b19dbc9..4a1021ff77 100644
--- a/Userland/Libraries/LibRegex/RegexByteCode.cpp
+++ b/Userland/Libraries/LibRegex/RegexByteCode.cpp
@@ -659,6 +659,18 @@ ALWAYS_INLINE bool OpCode_Compare::compare_string(MatchInput const& input, Match
 
 ALWAYS_INLINE void OpCode_Compare::compare_character_class(MatchInput const& input, MatchState& state, CharClass character_class, u32 ch, bool inverse, bool& inverse_matched)
 {
+    auto is_space_or_line_terminator = [](u32 code_point) {
+        static auto space_separator = Unicode::general_category_from_string("Space_Separator"sv);
+        if (!space_separator.has_value())
+            return is_ascii_space(code_point);
+
+        if ((code_point == 0x0a) || (code_point == 0x0d) || (code_point == 0x2028) || (code_point == 0x2029))
+            return true;
+        if ((code_point == 0x09) || (code_point == 0x0b) || (code_point == 0x0c) || (code_point == 0xfeff))
+            return true;
+        return Unicode::code_point_has_general_category(code_point, *space_separator);
+    };
+
     switch (character_class) {
     case CharClass::Alnum:
         if (is_ascii_alphanumeric(ch)) {
@@ -729,7 +741,7 @@ ALWAYS_INLINE void OpCode_Compare::compare_character_class(MatchInput const& inp
         }
         break;
     case CharClass::Space:
-        if (is_ascii_space(ch)) {
+        if (is_space_or_line_terminator(ch)) {
             if (inverse)
                 inverse_matched = true;
             else