iowo/crates/lang/src/lst_parser/syntax_kind.rs

use enumset::EnumSet;
use logos::Logos;

pub fn lex(src: &str) -> Vec<(SyntaxKind, &str)> {
    let mut lex = SyntaxKind::lexer(src);
    let mut r = Vec::new();

    while let Some(tok_res) = lex.next() {
        r.push((tok_res.unwrap_or(SyntaxKind::LEX_ERR), lex.slice()))
    }

    r
}

#[derive(enumset::EnumSetType, Logos, Debug, PartialEq, Eq, Clone, Copy, Hash, PartialOrd, Ord)]
#[repr(u16)]
#[enumset(no_super_impls)]
#[allow(non_camel_case_types)]
pub enum SyntaxKind {
    #[token("def")]
    DEF_KW = 0,
    DEF,
    DEF_NAME,
    DEF_BODY,
    #[token("let")]
    LET_KW,
    #[token("in")]
    IN_KW,
    LET_IN,
    #[token("mod")]
    MOD_KW,
    MODULE,
    MODULE_NAME,
    MODULE_BODY,
    #[token("use")]
    USE_KW,
    USE_PAT,
    #[regex("[\\d]+")]
    INT_NUM,
    #[regex("[+-]?([\\d]+\\.[\\d]*|[\\d]*\\.[\\d]+)")]
    FLOAT_NUM,
    #[regex(r#""([^"\\]|\\["\\bnfrt]|u[a-fA-F0-9]{4})*""#)]
    STRING,
    MATRIX,
    MAT_ROW,
    VEC,
    LIST,
    // either of a vec, a matrix or a list
    COLLECTION_ITEM,
    DECL,
    PARENTHESIZED_EXPR,
    EXPR,
    LITERAL,
    #[token("(")]
    L_PAREN,
    #[token(")")]
    R_PAREN,
    #[token("{")]
    L_BRACE,
    #[token("}")]
    R_BRACE,
    #[token("[")]
    L_BRACK,
    #[token("]")]
    R_BRACK,
    #[token("<")]
    L_ANGLE,
    #[token(">")]
    R_ANGLE,
    #[token("+")]
    PLUS,
    #[token("-")]
    MINUS,
    #[token("*")]
    STAR,
    #[token("/")]
    SLASH,
    #[token("%")]
    PERCENT,
    #[token("^")]
    CARET,
    INSTR,
    INSTR_NAME,
    INSTR_PARAMS,
    ATTR_SET,
    ATTR,
    ATTR_NAME,
    ATTR_VALUE,
    #[regex("[a-zA-Z_]+[a-zA-Z_\\-\\d]*")]
    IDENT,
    #[regex("\\$[a-zA-Z0-9_\\-]+")]
    VAR,
    #[regex("\\@[a-zA-Z0-9_\\-]+")]
    INPUT_VAR,
    #[token("$")]
    DOLLAR,
    #[token("@")]
    AT,
    #[token(",")]
    COMMA,
    #[token("|")]
    PIPE,
    #[token("@|")]
    MAPPING_PIPE,
    #[token("!|")]
    NULL_PIPE,
    PIPELINE,
    #[token("=")]
    EQ,
    #[token(":")]
    COLON,
    #[token(";")]
    SEMICOLON,
    #[token(".")]
    DOT,
    #[token("!")]
    BANG,
    #[regex("[ \\t\\f]+")]
    WHITESPACE,
    #[token("\n")]
    NEWLINE,
    PARSE_ERR,
    LEX_ERR,
    ROOT,
    EOF,
    TOMBSTONE,
    ERROR,
}

pub type TokenSet = EnumSet<SyntaxKind>;

impl From<SyntaxKind> for rowan::SyntaxKind {
    fn from(kind: SyntaxKind) -> Self {
        Self(kind as u16)
    }
}

#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
pub enum Lang {}
impl rowan::Language for Lang {
    type Kind = SyntaxKind;
    #[allow(unsafe_code)]
    fn kind_from_raw(raw: rowan::SyntaxKind) -> Self::Kind {
        assert!(raw.0 <= SyntaxKind::ROOT as u16);
        unsafe { std::mem::transmute::<u16, SyntaxKind>(raw.0) }
    }
    fn kind_to_raw(kind: Self::Kind) -> rowan::SyntaxKind {
        kind.into()
    }
}