github
/
boa
mirror of https://github.com/boa-dev/boa.git
1
0
Fork 0
Code Issues Releases Wiki Activity
Browse Source

Implement RegExp `v` flag (#3695)

pull/3700/head
raskad 9 months ago committed by GitHub
parent
01baec0444
commit
a7c2f5baa7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 95 additions and 48 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 4
      Cargo.lock
  2. 2
      Cargo.toml
  3. 124
      core/engine/src/builtins/regexp/mod.rs
  4. 12
      core/parser/src/lexer/regex.rs
  5. 1
      test262_config.toml

4
Cargo.lock generated
Unescape View File

@ -3058,9 +3058,9 @@ dependencies = [
[[package]] [[package]]
name = "regress" name = "regress"
version = "0.8.0" version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f5f39ba4513916c1b2657b72af6ec671f091cd637992f58d0ede5cae4e5dea0" checksum = "d06f9a1f7cd8473611ba1a480cf35f9c5cffc2954336ba90a982fdb7e7d7f51e"
dependencies = [ dependencies = [
"hashbrown 0.14.3", "hashbrown 0.14.3",
"memchr", "memchr",

2
Cargo.toml
Unescape View File

@ -61,7 +61,7 @@ once_cell = { version = "1.19.0", default-features = false }
phf = { version = "0.11.2", default-features = false } phf = { version = "0.11.2", default-features = false }
pollster = "0.3.0" pollster = "0.3.0"
regex = "1.10.3" regex = "1.10.3"
regress = { version="0.8.0", features = ["utf16"]} regress = { version="0.9.0", features = ["utf16"]}
rustc-hash = { version = "1.1.0", default-features = false } rustc-hash = { version = "1.1.0", default-features = false }
serde_json = "1.0.114" serde_json = "1.0.114"
serde = "1.0.197" serde = "1.0.197"

124
core/engine/src/builtins/regexp/mod.rs
Unescape View File

@ -75,6 +75,9 @@ impl IntrinsicObject for RegExp {
let get_unicode = BuiltInBuilder::callable(realm, Self::get_unicode) let get_unicode = BuiltInBuilder::callable(realm, Self::get_unicode)
.name(js_string!("get unicode")) .name(js_string!("get unicode"))
.build(); .build();
let get_unicode_sets = BuiltInBuilder::callable(realm, Self::get_unicode_sets)
.name(js_string!("get unicodeSets"))
.build();
let get_sticky = BuiltInBuilder::callable(realm, Self::get_sticky) let get_sticky = BuiltInBuilder::callable(realm, Self::get_sticky)
.name(js_string!("get sticky")) .name(js_string!("get sticky"))
.build(); .build();
@ -136,6 +139,12 @@ impl IntrinsicObject for RegExp {
None, None,
flag_attributes, flag_attributes,
) )
.accessor(
js_string!("unicodeSets"),
Some(get_unicode_sets),
None,
flag_attributes,
)
.accessor( .accessor(
js_string!("sticky"), js_string!("sticky"),
Some(get_sticky), Some(get_sticky),
@ -427,6 +436,7 @@ impl RegExp {
b's' => regexp.flags.contains(RegExpFlags::DOT_ALL), b's' => regexp.flags.contains(RegExpFlags::DOT_ALL),
b'i' => regexp.flags.contains(RegExpFlags::IGNORE_CASE), b'i' => regexp.flags.contains(RegExpFlags::IGNORE_CASE),
b'u' => regexp.flags.contains(RegExpFlags::UNICODE), b'u' => regexp.flags.contains(RegExpFlags::UNICODE),
b'v' => regexp.flags.contains(RegExpFlags::UNICODE_SETS),
b'y' => regexp.flags.contains(RegExpFlags::STICKY), b'y' => regexp.flags.contains(RegExpFlags::STICKY),
_ => unreachable!(), _ => unreachable!(),
})); }));
@ -447,6 +457,7 @@ impl RegExp {
b's' => "dotAll", b's' => "dotAll",
b'i' => "ignoreCase", b'i' => "ignoreCase",
b'u' => "unicode", b'u' => "unicode",
b'v' => "unicodeSets",
b'y' => "sticky", b'y' => "sticky",
_ => unreachable!(), _ => unreachable!(),
}; };
@ -565,6 +576,22 @@ impl RegExp {
Self::regexp_has_flag(this, b'u', context) Self::regexp_has_flag(this, b'u', context)
} }
/// `get RegExp.prototype.unicodeSets`
///
/// More information:
/// - [ECMAScript reference][spec]
/// - [MDN documentation][mdn]
///
/// [spec]: https://tc39.es/ecma262/#sec-get-regexp.prototype.unicodesets
/// [mdn]: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/RegExp/unicodeSets
pub(crate) fn get_unicode_sets(
this: &JsValue,
_: &[JsValue],
context: &mut Context,
) -> JsResult<JsValue> {
Self::regexp_has_flag(this, b'v', context)
}
/// `get RegExp.prototype.sticky` /// `get RegExp.prototype.sticky`
/// ///
/// This flag indicates that it matches only from the index indicated by the `lastIndex` property /// This flag indicates that it matches only from the index indicated by the `lastIndex` property
@ -601,58 +628,67 @@ impl RegExp {
context: &mut Context, context: &mut Context,
) -> JsResult<JsValue> { ) -> JsResult<JsValue> {
// 1. Let R be the this value. // 1. Let R be the this value.
// 2. If Type(R) is not Object, throw a TypeError exception. // 2. If R is not an Object, throw a TypeError exception.
if let Some(object) = this.as_object() { let Some(object) = this.as_object() else {
// 3. Let result be the empty String. return Err(JsNativeError::typ()
let mut result = String::new(); .with_message("RegExp.prototype.flags getter called on non-object")
.into());
};
// 4. Let hasIndices be ToBoolean(? Get(R, "hasIndices")). // 3. Let codeUnits be a new empty List.
// 5. If hasIndices is true, append the code unit 0x0064 (LATIN SMALL LETTER D) as the last code unit of result. let mut code_units = Vec::new();
if object.get(utf16!("hasIndices"), context)?.to_boolean() {
result.push('d');
}
// 6. Let global be ! ToBoolean(? Get(R, "global")). // 4. Let hasIndices be ToBoolean(? Get(R, "hasIndices")).
// 7. If global is true, append the code unit 0x0067 (LATIN SMALL LETTER G) as the last code unit of result. // 5. If hasIndices is true, append the code unit 0x0064 (LATIN SMALL LETTER D) to codeUnits.
if object.get(utf16!("global"), context)?.to_boolean() { if object.get(utf16!("hasIndices"), context)?.to_boolean() {
result.push('g'); code_units.extend_from_slice(utf16!("d"));
} }
// 8. Let ignoreCase be ! ToBoolean(? Get(R, "ignoreCase")).
// 9. If ignoreCase is true, append the code unit 0x0069 (LATIN SMALL LETTER I) as the last code unit of result.
if object.get(utf16!("ignoreCase"), context)?.to_boolean() {
result.push('i');
}
// 10. Let multiline be ! ToBoolean(? Get(R, "multiline")). // 6. Let global be ToBoolean(? Get(R, "global")).
// 11. If multiline is true, append the code unit 0x006D (LATIN SMALL LETTER M) as the last code unit of result. // 7. If global is true, append the code unit 0x0067 (LATIN SMALL LETTER G) to codeUnits.
if object.get(utf16!("multiline"), context)?.to_boolean() { if object.get(utf16!("global"), context)?.to_boolean() {
result.push('m'); code_units.extend_from_slice(utf16!("g"));
} }
// 12. Let dotAll be ! ToBoolean(? Get(R, "dotAll")). // 8. Let ignoreCase be ToBoolean(? Get(R, "ignoreCase")).
// 13. If dotAll is true, append the code unit 0x0073 (LATIN SMALL LETTER S) as the last code unit of result. // 9. If ignoreCase is true, append the code unit 0x0069 (LATIN SMALL LETTER I) to codeUnits.
if object.get(utf16!("dotAll"), context)?.to_boolean() { if object.get(utf16!("ignoreCase"), context)?.to_boolean() {
result.push('s'); code_units.extend_from_slice(utf16!("i"));
} }
// 14. Let unicode be ! ToBoolean(? Get(R, "unicode")).
// 15. If unicode is true, append the code unit 0x0075 (LATIN SMALL LETTER U) as the last code unit of result.
if object.get(utf16!("unicode"), context)?.to_boolean() {
result.push('u');
}
// 16. Let sticky be ! ToBoolean(? Get(R, "sticky")). // 10. Let multiline be ToBoolean(? Get(R, "multiline")).
// 17. If sticky is true, append the code unit 0x0079 (LATIN SMALL LETTER Y) as the last code unit of result. // 11. If multiline is true, append the code unit 0x006D (LATIN SMALL LETTER M) to codeUnits.
if object.get(utf16!("sticky"), context)?.to_boolean() { if object.get(utf16!("multiline"), context)?.to_boolean() {
result.push('y'); code_units.extend_from_slice(utf16!("m"));
} }
// 18. Return result. // 12. Let dotAll be ToBoolean(? Get(R, "dotAll")).
return Ok(js_string!(result).into()); // 13. If dotAll is true, append the code unit 0x0073 (LATIN SMALL LETTER S) to codeUnits.
if object.get(utf16!("dotAll"), context)?.to_boolean() {
code_units.extend_from_slice(utf16!("s"));
} }
Err(JsNativeError::typ() // 14. Let unicode be ToBoolean(? Get(R, "unicode")).
.with_message("RegExp.prototype.flags getter called on non-object") // 15. If unicode is true, append the code unit 0x0075 (LATIN SMALL LETTER U) to codeUnits.
.into()) if object.get(utf16!("unicode"), context)?.to_boolean() {
code_units.extend_from_slice(utf16!("u"));
}
// 16. Let unicodeSets be ToBoolean(? Get(R, "unicodeSets")).
// 17. If unicodeSets is true, append the code unit 0x0076 (LATIN SMALL LETTER V) to codeUnits.
if object.get(utf16!("unicodeSets"), context)?.to_boolean() {
code_units.extend_from_slice(utf16!("v"));
}
// 18. Let sticky be ToBoolean(? Get(R, "sticky")).
// 19. If sticky is true, append the code unit 0x0079 (LATIN SMALL LETTER Y) to codeUnits.
if object.get(utf16!("sticky"), context)?.to_boolean() {
code_units.extend_from_slice(utf16!("y"));
}
// 20. Return the String value whose code units are the elements of the List codeUnits.
// If codeUnits has no elements, the empty String is returned.
Ok(JsString::from(code_units).into())
} }
/// `get RegExp.prototype.source` /// `get RegExp.prototype.source`

12
core/parser/src/lexer/regex.rs
Unescape View File

@ -169,6 +169,9 @@ bitflags! {
/// Whether the regular expression result exposes the start and end indices of /// Whether the regular expression result exposes the start and end indices of
/// captured substrings. /// captured substrings.
const HAS_INDICES = 0b0100_0000; const HAS_INDICES = 0b0100_0000;
/// Whether or not UnicodeSets features are enabled.
const UNICODE_SETS = 0b1000_0000;
} }
} }
@ -186,6 +189,7 @@ impl FromStr for RegExpFlags {
b'u' => Self::UNICODE, b'u' => Self::UNICODE,
b'y' => Self::STICKY, b'y' => Self::STICKY,
b'd' => Self::HAS_INDICES, b'd' => Self::HAS_INDICES,
b'v' => Self::UNICODE_SETS,
_ => return Err(format!("invalid regular expression flag {}", char::from(c))), _ => return Err(format!("invalid regular expression flag {}", char::from(c))),
}; };
@ -198,6 +202,10 @@ impl FromStr for RegExpFlags {
flags.insert(new_flag); flags.insert(new_flag);
} }
if flags.contains(Self::UNICODE) && flags.contains(Self::UNICODE_SETS) {
return Err("cannot use both 'u' and 'v' flags".into());
}
Ok(flags) Ok(flags)
} }
} }
@ -233,6 +241,9 @@ impl ToString for RegExpFlags {
if self.contains(Self::STICKY) { if self.contains(Self::STICKY) {
s.push('y'); s.push('y');
} }
if self.contains(Self::UNICODE_SETS) {
s.push('v');
}
s s
} }
} }
@ -244,6 +255,7 @@ impl From<RegExpFlags> for Flags {
multiline: value.contains(RegExpFlags::MULTILINE), multiline: value.contains(RegExpFlags::MULTILINE),
dot_all: value.contains(RegExpFlags::DOT_ALL), dot_all: value.contains(RegExpFlags::DOT_ALL),
unicode: value.contains(RegExpFlags::UNICODE), unicode: value.contains(RegExpFlags::UNICODE),
unicode_sets: value.contains(RegExpFlags::UNICODE_SETS),
..Self::default() ..Self::default()
} }
} }

1
test262_config.toml
Unescape View File

@ -13,7 +13,6 @@ features = [
"Intl.DisplayNames", "Intl.DisplayNames",
"Intl.RelativeTimeFormat", "Intl.RelativeTimeFormat",
"Intl-enumeration", "Intl-enumeration",
"regexp-v-flag",
### Pending proposals ### Pending proposals

Write Preview
Loading…
Cancel
Save