traxys/tree-sitter
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Don't start with duplicate states in ts_query__analyze_patterns

Browse source 
This change exposes a new `primary_state_ids` field on the `TSLanguage`
struct, and populates it by tracking the first encountered state with a
given `core_id`. (For posterity: the initial change just exposed
`core_id` and deduplicated within `ts_analyze_query`).

With this `primary_state_ids` field in place, the
`ts_query__analyze_patterns` function only needs to populate its
subgraphs with starting states that are _primary_, since non-primary
states behave identically to primary ones. This leads to large savings
across the board, since most states are not primary.
This commit is contained in:
Alex Pinkus 2022-01-11 21:57:06 -08:00
parent bf210f0c9e
commit eaf9b170f1
6 changed files with 64 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

25
cli/src/generate/render.rs
View file

@ -106,6 +106,7 @@ impl Generator {
}
self.add_non_terminal_alias_map();
self.add_primary_state_id_list();
let mut main_lex_table = LexTable::default();
swap(&mut main_lex_table, &mut self.main_lex_table);
@ -565,6 +566,29 @@ impl Generator {
add_line!(self, "");
}
/// Produces a list of the "primary state" for every state in the grammar.
///
/// The "primary state" for a given state is the first encountered state that behaves
/// identically with respect to query analysis. We derive this by keeping track of the `core_id`
/// for each state and treating the first state with a given `core_id` as primary.
fn add_primary_state_id_list(&mut self) {
add_line!(
self,
"static const TSStateId ts_primary_state_ids[STATE_COUNT] = {{"
);
indent!(self);
let mut first_state_for_each_core_id = HashMap::new();
for (idx, state) in self.parse_table.states.iter().enumerate() {
let primary_state = first_state_for_each_core_id
.entry(state.core_id)
.or_insert(idx);
add_line!(self, "[{}] = {},", idx, primary_state);
}
dedent!(self);
add_line!(self, "}};");
add_line!(self, "");
}
fn add_field_sequences(&mut self) {
let mut flat_field_maps = vec![];
let mut next_flat_field_map_index = 0;
@ -1369,6 +1393,7 @@ impl Generator {
if !self.parse_table.production_infos.is_empty() {
add_line!(self, ".alias_sequences = &ts_alias_sequences[0][0],");
}
add_line!(self, ".ts_primary_state_ids = ts_primary_state_ids,");
// Lexing
add_line!(self, ".lex_modes = ts_lex_modes,");