bendns' repos / rust-analyzer
Unnamed repository; edit this file 'description' to name the repository.
Diffstat (limited to 'crates/parser/src/output.rs')
-rw-r--r--crates/parser/src/output.rs76
1 files changed, 76 insertions, 0 deletions
diff --git a/crates/parser/src/output.rs b/crates/parser/src/output.rs
new file mode 100644
index 0000000000..b613df029f
--- /dev/null
+++ b/crates/parser/src/output.rs
@@ -0,0 +1,76 @@
+//! See [`Output`]
+
+use crate::SyntaxKind;
+
+/// Output of the parser -- a DFS traversal of a concrete syntax tree.
+///
+/// Use the [`Output::iter`] method to iterate over traversal steps and consume
+/// a syntax tree.
+///
+/// In a sense, this is just a sequence of [`SyntaxKind`]-colored parenthesis
+/// interspersed into the original [`crate::Input`]. The output is fundamentally
+/// coordinated with the input and `n_input_tokens` refers to the number of
+/// times [`crate::Input::push`] was called.
+#[derive(Default)]
+pub struct Output {
+ /// 32-bit encoding of events. If LSB is zero, then that's an index into the
+ /// error vector. Otherwise, it's one of the thee other variants, with data encoded as
+ ///
+ /// |16 bit kind|8 bit n_input_tokens|4 bit tag|4 bit leftover|
+ ///
+ event: Vec<u32>,
+ error: Vec<String>,
+}
+
+pub enum Step<'a> {
+ Token { kind: SyntaxKind, n_input_tokens: u8 },
+ Enter { kind: SyntaxKind },
+ Exit,
+ Error { msg: &'a str },
+}
+
+impl Output {
+ pub fn iter(&self) -> impl Iterator<Item = Step<'_>> {
+ self.event.iter().map(|&event| {
+ if event & 0b1 == 0 {
+ return Step::Error { msg: self.error[(event as usize) >> 1].as_str() };
+ }
+ let tag = ((event & 0x0000_00F0) >> 4) as u8;
+ match tag {
+ 0 => {
+ let kind: SyntaxKind = (((event & 0xFFFF_0000) >> 16) as u16).into();
+ let n_input_tokens = ((event & 0x0000_FF00) >> 8) as u8;
+ Step::Token { kind, n_input_tokens }
+ }
+ 1 => {
+ let kind: SyntaxKind = (((event & 0xFFFF_0000) >> 16) as u16).into();
+ Step::Enter { kind }
+ }
+ 2 => Step::Exit,
+ _ => unreachable!(),
+ }
+ })
+ }
+
+ pub(crate) fn token(&mut self, kind: SyntaxKind, n_tokens: u8) {
+ let e = ((kind as u16 as u32) << 16) | ((n_tokens as u32) << 8) | (0 << 4) | 1;
+ self.event.push(e)
+ }
+
+ pub(crate) fn enter_node(&mut self, kind: SyntaxKind) {
+ let e = ((kind as u16 as u32) << 16) | (1 << 4) | 1;
+ self.event.push(e)
+ }
+
+ pub(crate) fn leave_node(&mut self) {
+ let e = 2 << 4 | 1;
+ self.event.push(e)
+ }
+
+ pub(crate) fn error(&mut self, error: String) {
+ let idx = self.error.len();
+ self.error.push(error);
+ let e = (idx as u32) << 1;
+ self.event.push(e);
+ }
+}