mirror of
https://github.com/astral-sh/ruff.git
synced 2025-10-31 12:05:57 +00:00
c9dff5c7d5
## Summary Garbage collect ASTs once we are done checking a given file. Queries with a cross-file dependency on the AST will reparse the file on demand. This reduces ty's peak memory usage by ~20-30%. The primary change of this PR is adding a `node_index` field to every AST node, that is assigned by the parser. `ParsedModule` can use this to create a flat index of AST nodes any time the file is parsed (or reparsed). This allows `AstNodeRef` to simply index into the current instance of the `ParsedModule`, instead of storing a pointer directly. The indices are somewhat hackily (using an atomic integer) assigned by the `parsed_module` query instead of by the parser directly. Assigning the indices in source-order in the (recursive) parser turns out to be difficult, and collecting the nodes during semantic indexing is impossible as `SemanticIndex` does not hold onto a specific `ParsedModuleRef`, which the pointers in the flat AST are tied to. This means that we have to do an extra AST traversal to assign and collect the nodes into a flat index, but the small performance impact (~3% on cold runs) seems worth it for the memory savings. Part of https://github.com/astral-sh/ty/issues/214.
92 lines
2.7 KiB
Rust
92 lines
2.7 KiB
Rust
//! When building a semantic model, we often need to know which names in a given scope are declared
|
|
//! as `global`. This module provides data structures for storing and querying the set of `global`
|
|
//! names in a given scope.
|
|
|
|
use std::ops::Index;
|
|
|
|
use ruff_python_ast::{self as ast, Stmt};
|
|
use ruff_text_size::{Ranged, TextRange};
|
|
use rustc_hash::FxHashMap;
|
|
|
|
use ruff_index::{IndexVec, newtype_index};
|
|
use ruff_python_ast::statement_visitor::{StatementVisitor, walk_stmt};
|
|
|
|
/// Id uniquely identifying the set of global names for a given scope.
|
|
#[newtype_index]
|
|
pub struct GlobalsId;
|
|
|
|
#[derive(Debug, Default)]
|
|
pub(crate) struct GlobalsArena<'a>(IndexVec<GlobalsId, Globals<'a>>);
|
|
|
|
impl<'a> GlobalsArena<'a> {
|
|
/// Inserts a new set of global names into the global names arena and returns its unique id.
|
|
pub(crate) fn push(&mut self, globals: Globals<'a>) -> GlobalsId {
|
|
self.0.push(globals)
|
|
}
|
|
}
|
|
|
|
impl<'a> Index<GlobalsId> for GlobalsArena<'a> {
|
|
type Output = Globals<'a>;
|
|
|
|
#[inline]
|
|
fn index(&self, index: GlobalsId) -> &Self::Output {
|
|
&self.0[index]
|
|
}
|
|
}
|
|
|
|
/// The set of global names for a given scope, represented as a map from the name of the global to
|
|
/// the range of the declaration in the source code.
|
|
#[derive(Debug)]
|
|
pub struct Globals<'a>(FxHashMap<&'a str, TextRange>);
|
|
|
|
impl<'a> Globals<'a> {
|
|
/// Extracts the set of global names from a given scope, or return `None` if the scope does not
|
|
/// contain any `global` declarations.
|
|
pub fn from_body(body: &'a [Stmt]) -> Option<Self> {
|
|
let mut builder = GlobalsVisitor::new();
|
|
builder.visit_body(body);
|
|
builder.finish()
|
|
}
|
|
|
|
pub(crate) fn get(&self, name: &str) -> Option<TextRange> {
|
|
self.0.get(name).copied()
|
|
}
|
|
|
|
pub(crate) fn iter(&self) -> impl Iterator<Item = (&&'a str, &TextRange)> + '_ {
|
|
self.0.iter()
|
|
}
|
|
}
|
|
|
|
/// Extracts the set of global names from a given scope.
|
|
#[derive(Debug)]
|
|
struct GlobalsVisitor<'a>(FxHashMap<&'a str, TextRange>);
|
|
|
|
impl<'a> GlobalsVisitor<'a> {
|
|
fn new() -> Self {
|
|
Self(FxHashMap::default())
|
|
}
|
|
|
|
fn finish(self) -> Option<Globals<'a>> {
|
|
(!self.0.is_empty()).then_some(Globals(self.0))
|
|
}
|
|
}
|
|
|
|
impl<'a> StatementVisitor<'a> for GlobalsVisitor<'a> {
|
|
fn visit_stmt(&mut self, stmt: &'a Stmt) {
|
|
match stmt {
|
|
Stmt::Global(ast::StmtGlobal {
|
|
names,
|
|
range: _,
|
|
node_index: _,
|
|
}) => {
|
|
for name in names {
|
|
self.0.insert(name.as_str(), name.range());
|
|
}
|
|
}
|
|
Stmt::FunctionDef(_) | Stmt::ClassDef(_) => {
|
|
// Don't recurse.
|
|
}
|
|
_ => walk_stmt(self, stmt),
|
|
}
|
|
}
|
|
}
|