2020-08-12 10:06:49 -05:00
|
|
|
//! Lexing, bridging to parser (which does the actual parsing) and
|
2019-02-21 06:24:42 -06:00
|
|
|
//! incremental reparsing.
|
|
|
|
|
2019-02-20 07:24:39 -06:00
|
|
|
mod reparsing;
|
2019-02-20 06:47:32 -06:00
|
|
|
|
2021-12-26 07:47:10 -06:00
|
|
|
use rowan::TextRange;
|
|
|
|
|
2021-12-28 09:57:13 -06:00
|
|
|
use crate::{syntax_node::GreenNode, SyntaxError, SyntaxTreeBuilder};
|
2019-02-20 06:47:32 -06:00
|
|
|
|
2021-12-18 08:20:38 -06:00
|
|
|
pub(crate) use crate::parsing::reparsing::incremental_reparse;
|
2019-02-20 06:47:32 -06:00
|
|
|
|
|
|
|
pub(crate) fn parse_text(text: &str) -> (GreenNode, Vec<SyntaxError>) {
|
2021-12-18 08:20:38 -06:00
|
|
|
let lexed = parser::LexedStr::new(text);
|
2021-12-25 12:59:02 -06:00
|
|
|
let parser_input = lexed.to_input();
|
2021-12-28 10:13:30 -06:00
|
|
|
let parser_output = parser::TopEntryPoint::SourceFile.parse(&parser_input);
|
|
|
|
let (node, errors, _eof) = build_tree(lexed, parser_output);
|
internal: replace TreeSink with a data structure
The general theme of this is to make parser a better independent
library.
The specific thing we do here is replacing callback based TreeSink with
a data structure. That is, rather than calling user-provided tree
construction methods, the parser now spits out a very bare-bones tree,
effectively a log of a DFS traversal.
This makes the parser usable without any *specifc* tree sink, and allows
us to, eg, move tests into this crate.
Now, it's also true that this is a distinction without a difference, as
the old and the new interface are equivalent in expressiveness. Still,
this new thing seems somewhat simpler. But yeah, I admit I don't have a
suuper strong motivation here, just a hunch that this is better.
2021-12-19 08:36:23 -06:00
|
|
|
(node, errors)
|
2019-02-20 06:47:32 -06:00
|
|
|
}
|
2020-06-18 16:43:19 -05:00
|
|
|
|
2021-12-26 07:47:10 -06:00
|
|
|
pub(crate) fn build_tree(
|
|
|
|
lexed: parser::LexedStr<'_>,
|
|
|
|
parser_output: parser::Output,
|
|
|
|
) -> (GreenNode, Vec<SyntaxError>, bool) {
|
|
|
|
let mut builder = SyntaxTreeBuilder::default();
|
|
|
|
|
2021-12-28 10:13:30 -06:00
|
|
|
let is_eof = lexed.intersperse_trivia(&parser_output, &mut |step| match step {
|
2021-12-26 07:47:10 -06:00
|
|
|
parser::StrStep::Token { kind, text } => builder.token(kind, text),
|
|
|
|
parser::StrStep::Enter { kind } => builder.start_node(kind),
|
|
|
|
parser::StrStep::Exit => builder.finish_node(),
|
|
|
|
parser::StrStep::Error { msg, pos } => {
|
|
|
|
builder.error(msg.to_string(), pos.try_into().unwrap())
|
|
|
|
}
|
|
|
|
});
|
|
|
|
|
|
|
|
let (node, mut errors) = builder.finish_raw();
|
|
|
|
for (i, err) in lexed.errors() {
|
|
|
|
let text_range = lexed.text_range(i);
|
|
|
|
let text_range = TextRange::new(
|
|
|
|
text_range.start.try_into().unwrap(),
|
|
|
|
text_range.end.try_into().unwrap(),
|
|
|
|
);
|
|
|
|
errors.push(SyntaxError::new(err, text_range))
|
|
|
|
}
|
|
|
|
|
|
|
|
(node, errors, is_eof)
|
|
|
|
}
|