Stowage/ladybird
2
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2025-12-07 21:59:54 +00:00
Code Issues Projects Releases Packages Wiki Activity

LibRegex+LibUnicode: Add unicode string properties

Browse source
This commit is contained in:
aplefull 2025-07-24 00:16:08 +02:00 • committed by Tim Flynn
parent 8c8961171c
commit 7ce4abe330
Notes: github-actions[bot] 2025-10-24 17:26:08 +00:00
6 changed files with 139 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

59
Libraries/LibJS/Tests/builtins/RegExp/RegExp.js
View file

@ -97,3 +97,62 @@ test("Unicode non-ASCII matching", () => {
expect(result).toEqual(test.expected);
}
});
// Test from https://github.com/tc39/test262/blob/main/test/built-ins/RegExp/unicodeSets/generated/character-property-escape-difference-property-of-strings-escape.js
test("Unicode properties of strings", () => {
const regexes = [
/\p{Basic_Emoji}/v,
/\p{Emoji_Keycap_Sequence}/v,
/\p{RGI_Emoji_Modifier_Sequence}/v,
/\p{RGI_Emoji_Flag_Sequence}/v,
/\p{RGI_Emoji_Tag_Sequence}/v,
/\p{RGI_Emoji_ZWJ_Sequence}/v,
/\p{RGI_Emoji}/v,
];
for (const re of regexes) {
expect(() => {
re.test("test");
}).not.toThrow();
}
const matchStrings = [
"0",
"1",
"2",
"3",
"4",
"5",
"8",
"A",
"B",
"D",
"E",
"F",
"a",
"b",
"c",
"d",
"e",
"f",
];
const nonMatchStrings = [
"6\uFE0F\u20E3",
"7\uFE0F\u20E3",
"9\uFE0F\u20E3",
"\u2603",
"\u{1D306}",
"\u{1F1E7}\u{1F1EA}",
];
const re = /^[\p{ASCII_Hex_Digit}--\p{Emoji_Keycap_Sequence}]+$/v;
for (const str of matchStrings) {
expect(re.test(str)).toBeTrue();
}
for (const str of nonMatchStrings) {
expect(re.test(str)).toBeFalse();
}
});

39
Libraries/LibRegex/RegexDefs.h
View file

@ -9,25 +9,26 @@
enum __Regex_Error {
__Regex_NoError,
__Regex_InvalidPattern, // Invalid regular expression.
__Regex_InvalidCollationElement, // Invalid collating element referenced.
__Regex_InvalidCharacterClass, // Invalid character class type referenced.
__Regex_InvalidTrailingEscape, // Trailing \ in pattern.
__Regex_InvalidNumber, // Number in \digit invalid or in error.
__Regex_MismatchingBracket, // [ ] imbalance.
__Regex_MismatchingParen, // ( ) imbalance.
__Regex_MismatchingBrace, // { } imbalance.
__Regex_InvalidBraceContent, // Content of {} invalid: not a number, number too large, more than two numbers, first larger than second.
__Regex_InvalidBracketContent, // Content of [] invalid.
__Regex_InvalidRange, // Invalid endpoint in range expression.
__Regex_InvalidRepetitionMarker, // ?, * or + not preceded by valid regular expression.
__Regex_ReachedMaxRecursion, // MaximumRecursion has been reached.
__Regex_EmptySubExpression, // Sub expression has empty content.
__Regex_InvalidCaptureGroup, // Content of capture group is invalid.
__Regex_InvalidNameForCaptureGroup, // Name of capture group is invalid.
__Regex_InvalidNameForProperty, // Name of property is invalid.
__Regex_DuplicateNamedCapture, // Duplicate named capture group
__Regex_InvalidCharacterClassEscape, // Invalid escaped entity in character class.
__Regex_InvalidPattern, // Invalid regular expression.
__Regex_InvalidCollationElement, // Invalid collating element referenced.
__Regex_InvalidCharacterClass, // Invalid character class type referenced.
__Regex_InvalidTrailingEscape, // Trailing \ in pattern.
__Regex_InvalidNumber, // Number in \digit invalid or in error.
__Regex_MismatchingBracket, // [ ] imbalance.
__Regex_MismatchingParen, // ( ) imbalance.
__Regex_MismatchingBrace, // { } imbalance.
__Regex_InvalidBraceContent, // Content of {} invalid: not a number, number too large, more than two numbers, first larger than second.
__Regex_InvalidBracketContent, // Content of [] invalid.
__Regex_InvalidRange, // Invalid endpoint in range expression.
__Regex_InvalidRepetitionMarker, // ?, * or + not preceded by valid regular expression.
__Regex_ReachedMaxRecursion, // MaximumRecursion has been reached.
__Regex_EmptySubExpression, // Sub expression has empty content.
__Regex_InvalidCaptureGroup, // Content of capture group is invalid.
__Regex_InvalidNameForCaptureGroup, // Name of capture group is invalid.
__Regex_InvalidNameForProperty, // Name of property is invalid.
__Regex_DuplicateNamedCapture, // Duplicate named capture group
__Regex_InvalidCharacterClassEscape, // Invalid escaped entity in character class.
__Regex_NegatedCharacterClassStrings, // Negated character class cannot contain strings.
};
enum __RegexAllFlags {

41
Libraries/LibRegex/RegexError.h
View file

@ -14,25 +14,26 @@ namespace regex {
enum class Error : u8 {
NoError = __Regex_NoError,
InvalidPattern = __Regex_InvalidPattern, // Invalid regular expression.
InvalidCollationElement = __Regex_InvalidCollationElement, // Invalid collating element referenced.
InvalidCharacterClass = __Regex_InvalidCharacterClass, // Invalid character class type referenced.
InvalidTrailingEscape = __Regex_InvalidTrailingEscape, // Trailing \ in pattern.
InvalidNumber = __Regex_InvalidNumber, // Number in \digit invalid or in error.
MismatchingBracket = __Regex_MismatchingBracket, // [ ] imbalance.
MismatchingParen = __Regex_MismatchingParen, // ( ) imbalance.
MismatchingBrace = __Regex_MismatchingBrace, // { } imbalance.
InvalidBraceContent = __Regex_InvalidBraceContent, // Content of {} invalid: not a number, number too large, more than two numbers, first larger than second.
InvalidBracketContent = __Regex_InvalidBracketContent, // Content of [] invalid.
InvalidRange = __Regex_InvalidRange, // Invalid endpoint in range expression.
InvalidRepetitionMarker = __Regex_InvalidRepetitionMarker, // ?, * or + not preceded by valid regular expression.
ReachedMaxRecursion = __Regex_ReachedMaxRecursion, // MaximumRecursion has been reached.
EmptySubExpression = __Regex_EmptySubExpression, // Sub expression has empty content.
InvalidCaptureGroup = __Regex_InvalidCaptureGroup, // Content of capture group is invalid.
InvalidNameForCaptureGroup = __Regex_InvalidNameForCaptureGroup, // Name of capture group is invalid.
InvalidNameForProperty = __Regex_InvalidNameForProperty, // Name of property is invalid.
DuplicateNamedCapture = __Regex_DuplicateNamedCapture, // Name of property is invalid.
InvalidCharacterClassEscape = __Regex_InvalidCharacterClassEscape, // Invalid escaped entity in character class.
InvalidPattern = __Regex_InvalidPattern, // Invalid regular expression.
InvalidCollationElement = __Regex_InvalidCollationElement, // Invalid collating element referenced.
InvalidCharacterClass = __Regex_InvalidCharacterClass, // Invalid character class type referenced.
InvalidTrailingEscape = __Regex_InvalidTrailingEscape, // Trailing \ in pattern.
InvalidNumber = __Regex_InvalidNumber, // Number in \digit invalid or in error.
MismatchingBracket = __Regex_MismatchingBracket, // [ ] imbalance.
MismatchingParen = __Regex_MismatchingParen, // ( ) imbalance.
MismatchingBrace = __Regex_MismatchingBrace, // { } imbalance.
InvalidBraceContent = __Regex_InvalidBraceContent, // Content of {} invalid: not a number, number too large, more than two numbers, first larger than second.
InvalidBracketContent = __Regex_InvalidBracketContent, // Content of [] invalid.
InvalidRange = __Regex_InvalidRange, // Invalid endpoint in range expression.
InvalidRepetitionMarker = __Regex_InvalidRepetitionMarker, // ?, * or + not preceded by valid regular expression.
ReachedMaxRecursion = __Regex_ReachedMaxRecursion, // MaximumRecursion has been reached.
EmptySubExpression = __Regex_EmptySubExpression, // Sub expression has empty content.
InvalidCaptureGroup = __Regex_InvalidCaptureGroup, // Content of capture group is invalid.
InvalidNameForCaptureGroup = __Regex_InvalidNameForCaptureGroup, // Name of capture group is invalid.
InvalidNameForProperty = __Regex_InvalidNameForProperty, // Name of property is invalid.
DuplicateNamedCapture = __Regex_DuplicateNamedCapture, // Name of property is invalid.
InvalidCharacterClassEscape = __Regex_InvalidCharacterClassEscape, // Invalid escaped entity in character class.
NegatedCharacterClassStrings = __Regex_NegatedCharacterClassStrings, // Negated character class may contain strings.
};
inline StringView get_error_string(Error error)
@ -78,6 +79,8 @@ inline StringView get_error_string(Error error)
return "Duplicate capture group name"sv;
case Error::InvalidCharacterClassEscape:
return "Invalid escaped entity in character class."sv;
case Error::NegatedCharacterClassStrings:
return "Negated character class cannot contain strings"sv;
}
return "Undefined error."sv;
}

22
Libraries/LibRegex/RegexParser.cpp
View file

@ -2463,6 +2463,19 @@ bool ECMA262Parser::parse_nested_class(Vector<regex::CompareTypeAndValuePair>& c
compares.empend(CompareTypeAndValuePair { CharacterCompareType::Inverse, 0 });
property.visit(
[&](Unicode::Property property) {
if (Unicode::is_ecma262_string_property(property)) {
if (negated) {
set_error(Error::InvalidNameForProperty);
return;
}
for (auto const& compare : compares) {
if (compare.type == CharacterCompareType::Inverse) {
set_error(Error::NegatedCharacterClassStrings);
return;
}
}
}
compares.empend(CompareTypeAndValuePair { CharacterCompareType::Property, (ByteCodeValueType)property.value() });
},
[&](Unicode::GeneralCategory general_category) {
@ -2506,8 +2519,13 @@ bool ECMA262Parser::parse_unicode_property_escape(PropertyEscape& property, bool
property = move(*parsed_property);
return property.visit(
[this](Unicode::Property property) {
if (!Unicode::is_ecma262_property(property)) {
[this, negated](Unicode::Property property) {
if (Unicode::is_ecma262_string_property(property)) {
if (!m_parser_state.regex_options.has_flag_set(AllFlags::UnicodeSets) || negated) {
set_error(Error::InvalidNameForProperty);
return false;
}
} else if (!Unicode::is_ecma262_property(property)) {
set_error(Error::InvalidNameForProperty);
return false;
}

17
Libraries/LibUnicode/CharacterTypes.cpp
View file

@ -304,6 +304,23 @@ bool is_ecma262_property(Property property)
}
}
// https://tc39.es/ecma262/#table-binary-unicode-properties-of-strings
bool is_ecma262_string_property(Property property)
{
switch (property.value()) {
case UCHAR_BASIC_EMOJI:
case UCHAR_EMOJI_KEYCAP_SEQUENCE:
case UCHAR_RGI_EMOJI:
case UCHAR_RGI_EMOJI_FLAG_SEQUENCE:
case UCHAR_RGI_EMOJI_TAG_SEQUENCE:
case UCHAR_RGI_EMOJI_MODIFIER_SEQUENCE:
case UCHAR_RGI_EMOJI_ZWJ_SEQUENCE:
return true;
default:
return false;
}
}
Optional<Script> script_from_string(StringView script)
{
static auto script_names = []() {

1
Libraries/LibUnicode/CharacterTypes.h
View file

@ -39,6 +39,7 @@ bool code_point_has_variation_selector_property(u32 code_point);
bool code_point_has_white_space_property(u32 code_point);
bool is_ecma262_property(Property);
bool is_ecma262_string_property(Property);
Optional<Script> script_from_string(StringView);
bool code_point_has_script(u32 code_point, Script script);