mirror of
https://github.com/TxtDot/dalet-rs.git
synced 2024-11-21 16:26:21 +03:00
refactor(lexer): make functions for specific tokens
This commit is contained in:
parent
aaa4328818
commit
ccc9773030
4 changed files with 136 additions and 106 deletions
|
@ -1,12 +1,12 @@
|
|||
use ariadne::{Color, Label, Report, ReportKind, Source};
|
||||
use chumsky::Parser;
|
||||
use dalet::daleth::{format::format, lexer::lexer};
|
||||
use dalet::daleth::{format::format, lexer::full_lexer};
|
||||
|
||||
fn main() {
|
||||
let src_file = "daleth.dlth";
|
||||
let src = include_str!("./daleth.dlth");
|
||||
|
||||
let parsed = lexer().parse(src);
|
||||
let parsed = full_lexer().parse(src);
|
||||
|
||||
match parsed.into_result() {
|
||||
Ok(t) => {
|
||||
|
|
|
@ -4,7 +4,36 @@ pub mod types;
|
|||
|
||||
pub fn lexer<'src>(
|
||||
) -> impl Parser<'src, &'src str, Vec<Spanned<Token<'src>>>, extra::Err<Rich<'src, char, Span>>> {
|
||||
let tag = choice((
|
||||
let token = choice((symbol(), tag(), argument(), textual()));
|
||||
|
||||
token
|
||||
.padded()
|
||||
.padded_by(comment())
|
||||
.map_with(|t, e| (t, e.span()))
|
||||
.repeated()
|
||||
.collect()
|
||||
}
|
||||
|
||||
pub fn full_lexer<'src>(
|
||||
) -> impl Parser<'src, &'src str, Vec<Spanned<Token<'src>>>, extra::Err<Rich<'src, char, Span>>> {
|
||||
let token = choice((
|
||||
empty_line(),
|
||||
comment(),
|
||||
symbol(),
|
||||
tag(),
|
||||
argument(),
|
||||
textual(),
|
||||
));
|
||||
|
||||
token
|
||||
.padded_by(text::whitespace().and_is(empty_line().not()).or_not())
|
||||
.map_with(|t, e| (t, e.span()))
|
||||
.repeated()
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn tag<'src>() -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>> {
|
||||
choice((
|
||||
just("el").to(Token::El),
|
||||
just("h").to(Token::H),
|
||||
just("p").to(Token::P),
|
||||
|
@ -39,16 +68,20 @@ pub fn lexer<'src>(
|
|||
just("pre").to(Token::Pre),
|
||||
just("meta").to(Token::Meta),
|
||||
)))
|
||||
.labelled("Tag");
|
||||
.labelled("Tag")
|
||||
}
|
||||
|
||||
let symbol = choice((
|
||||
fn symbol<'src>() -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>> {
|
||||
choice((
|
||||
just("[[").to(Token::ElOpen).labelled("[["),
|
||||
just("]]").to(Token::ElClose).labelled("]]"),
|
||||
just("[").to(Token::LSquare).labelled("["),
|
||||
just("]").to(Token::RSquare).labelled("]"),
|
||||
));
|
||||
))
|
||||
}
|
||||
|
||||
let argument = {
|
||||
fn argument<'src>() -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>>
|
||||
{
|
||||
let arg_escape = just('\\')
|
||||
.ignore_then(just('"'))
|
||||
.labelled("Escape sequence for argument");
|
||||
|
@ -68,9 +101,10 @@ pub fn lexer<'src>(
|
|||
.labelled("Text argument");
|
||||
|
||||
choice((number, text_argument))
|
||||
};
|
||||
}
|
||||
|
||||
let textual = {
|
||||
fn textual<'src>() -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>>
|
||||
{
|
||||
let escape = just('\\')
|
||||
.ignore_then(just('}'))
|
||||
.labelled("Multi-line escape sequence");
|
||||
|
@ -126,21 +160,17 @@ pub fn lexer<'src>(
|
|||
.labelled("Raw multiline text");
|
||||
|
||||
choice((paragraph, mlmstext, rmltext, mltext, text_body, text_tag))
|
||||
};
|
||||
|
||||
let comment = just('#')
|
||||
.ignore_then(none_of("\n").repeated().to_slice())
|
||||
.map(Token::Comment);
|
||||
|
||||
let empty_line = text::inline_whitespace()
|
||||
.delimited_by(text::newline(), text::newline())
|
||||
.to(Token::EmptyLine);
|
||||
|
||||
let token = choice((empty_line.clone(), comment, symbol, tag, argument, textual));
|
||||
|
||||
token
|
||||
.padded_by(text::whitespace().and_is(empty_line.not()).or_not())
|
||||
.map_with(|t, e| (t, e.span()))
|
||||
.repeated()
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn comment<'src>() -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>>
|
||||
{
|
||||
just('#')
|
||||
.ignore_then(none_of("\n").repeated().to_slice())
|
||||
.map(Token::Comment)
|
||||
}
|
||||
fn empty_line<'src>(
|
||||
) -> impl Parser<'src, &'src str, Token<'src>, extra::Err<Rich<'src, char, Span>>> {
|
||||
text::inline_whitespace()
|
||||
.delimited_by(text::newline(), text::newline())
|
||||
.to(Token::EmptyLine)
|
||||
}
|
||||
|
|
|
@ -28,11 +28,11 @@ pub enum Token<'src> {
|
|||
/// Raw Multi line text
|
||||
RMLText(&'src str),
|
||||
|
||||
/// Special
|
||||
// Special
|
||||
TextTag(&'src str),
|
||||
Paragraph(&'src str),
|
||||
|
||||
/// Special removed before parse
|
||||
// Special for formatting, ignored for parse
|
||||
Comment(&'src str),
|
||||
EmptyLine,
|
||||
|
||||
|
|
|
@ -4,7 +4,7 @@ use ariadne::{Color, Label, Report, ReportKind, Source};
|
|||
use chumsky::Parser;
|
||||
use clap::Parser as ClapParser;
|
||||
use commands::{Cli, Commands::*};
|
||||
use dalet::daleth::{format::format, lexer::lexer};
|
||||
use dalet::daleth::{format::format, lexer::full_lexer};
|
||||
use std::fs;
|
||||
|
||||
fn main() {
|
||||
|
@ -16,7 +16,7 @@ fn main() {
|
|||
let src_file = &path.to_string_lossy().to_string();
|
||||
let src = fs::read_to_string(src_file).unwrap();
|
||||
|
||||
let parsed = lexer().parse(&src);
|
||||
let parsed = full_lexer().parse(&src);
|
||||
|
||||
match parsed.into_result() {
|
||||
Ok(t) => {
|
||||
|
|
Loading…
Add table
Reference in a new issue