mirror of
https://github.com/storytold/vectorcraft.git
synced 2026-11-10 08:51:25 +00:00
dotCooCoo
ea319ebcda
is_id_start accepts the letter categories (Lu, Ll, Lt, Lm, Lo, Nl) and is_id_part adds Mn, Mc, Nd and Pc, read with unicode-general-category. A superscript digit (No) inside an identifier and a mark such as U+09BE at its start are now SyntaxErrors, and identifiers with marks outside the old list, such as the Bengali and Tamil viramas, now parse. Labels in scope are kept in a map, and duplicate labels in a chain and duplicate parameters of a strict function are found with a hash set, so long chains, many labeled statements and long parameter lists are checked in linear time.
68 lines
2.4 KiB
Rust
68 lines
2.4 KiB
Rust
//! Character classes of ECMA-262 5.1 section 7: white space, line terminators and the characters
|
|
//! identifiers are made of.
|
|
|
|
use unicode_general_category::{GeneralCategory as G, get_general_category};
|
|
|
|
/// A line terminator: LF, CR, U+2028 or U+2029 (section 7.3).
|
|
pub fn is_line_terminator(c: u32) -> bool {
|
|
matches!(c, 0x0A | 0x0D | 0x2028 | 0x2029)
|
|
}
|
|
|
|
/// White space (section 7.2): tab, vertical tab, form feed, space, no-break space, the byte order
|
|
/// mark and the other space separators (Unicode category Zs).
|
|
pub fn is_whitespace(c: u32) -> bool {
|
|
matches!(c, 0x09 | 0x0B | 0x0C | 0x20 | 0xA0 | 0xFEFF | 0x1680 | 0x2000..=0x200A | 0x202F | 0x205F | 0x3000)
|
|
}
|
|
|
|
/// A character an identifier may start with: a letter (categories Lu, Ll, Lt, Lm, Lo and Nl),
|
|
/// `$` or `_` (section 7.6). `\u` escapes are decoded before this check.
|
|
pub fn is_id_start(c: u32) -> bool {
|
|
match c {
|
|
0x24 | 0x5F => true,
|
|
0x41..=0x5A | 0x61..=0x7A => true,
|
|
0..=0x7F => false,
|
|
// U+2E2F VERTICAL TILDE is a letter (Lm) that Unicode leaves out of identifiers.
|
|
0x2E2F => false,
|
|
_ => category(c).is_some_and(|g| {
|
|
matches!(g, G::UppercaseLetter | G::LowercaseLetter | G::TitlecaseLetter | G::ModifierLetter | G::OtherLetter | G::LetterNumber)
|
|
}),
|
|
}
|
|
}
|
|
|
|
/// A character an identifier may hold after its first: those it may start with, decimal digits
|
|
/// (Nd), combining marks (Mn, Mc), connector punctuation (Pc), and the zero width non-joiner and
|
|
/// joiner.
|
|
pub fn is_id_part(c: u32) -> bool {
|
|
match c {
|
|
0x30..=0x39 => true,
|
|
0x200C | 0x200D => true,
|
|
0x2E2F => false,
|
|
_ if is_id_start(c) => true,
|
|
0..=0x7F => false,
|
|
_ => category(c).is_some_and(|g| matches!(g, G::NonspacingMark | G::SpacingMark | G::DecimalNumber | G::ConnectorPunctuation)),
|
|
}
|
|
}
|
|
|
|
/// The Unicode general category of a code point; `None` for a lone surrogate.
|
|
fn category(c: u32) -> Option<G> {
|
|
char::from_u32(c).map(get_general_category)
|
|
}
|
|
|
|
/// The value of a hexadecimal digit.
|
|
pub fn hex_value(c: u32) -> Option<u32> {
|
|
match c {
|
|
0x30..=0x39 => Some(c - 0x30),
|
|
0x41..=0x46 => Some(c - 0x41 + 10),
|
|
0x61..=0x66 => Some(c - 0x61 + 10),
|
|
_ => None,
|
|
}
|
|
}
|
|
|
|
pub fn is_decimal_digit(c: u32) -> bool {
|
|
(0x30..=0x39).contains(&c)
|
|
}
|
|
|
|
pub fn is_octal_digit(c: u32) -> bool {
|
|
(0x30..=0x37).contains(&c)
|
|
}
|