github/codegraph
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(extraction): land upstream declaration initializer walks (#1511) (#1802)

Browse Source 
Squash danusha2345's PR #1511 at d282f9e8 onto main 8c9c4761,
preserving its nine non-merge commits and main's existing Unreleased notes.
Calls in Kotlin, Java, TS/JS, Scala, Rust and Python declaration initializers
now retain the owner established by the upstream regression expectations.
Include the upstream CFML, dynamic-dispatch summary and viewer follow-ups.

Linux fail-to-pass validation (Node 22.19.0, rebuilt dist and native kernel):
- Before: TS load belonged to file:app.ts; Python/Kotlin/Scala/Rust calls
  vanished; Java lost the field-lambda, anonymous override and eager calls.
- After: all six languages PASS; 12 native/WASM LF/CRLF parity checks PASS.
- Focused initializer regressions: 10 passed with CODEGRAPH_KERNEL=0 and
  10 passed with the kernel enabled; Kotlin's grammar fallback is recorded.
- Related regression suites: 879 passed, 1 skipped across 15 test files.
- Evidence: /workspace/cg-1510-repro/before and /workspace/cg-1510-repro/after
  (combined test output: after/vitest.log).

Fixes #1510
Supersedes #1511

Co-authored-by: Colby McHenry <colbymchenry@users.noreply.github.com>
Co-authored-by: danusha2345 <ewidusoc498@gmail.com>
This commit is contained in:
Colby Mchenry
2026-09-08 17:33:45 -05:00
committed by GitHub
co-authored by Colby McHenry danusha2345
parent 8c9c4761b0
commit 9181dd1ef3
25 changed files with 884 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codegraph-kernel/src/java.rs
+10
View File
@@ -759,6 +759,16 @@ impl<'t> Walker<'t> {
if let Some(row) = row {
self.extract_decorators_for(node, row);
self.extract_type_annotations(node, row);
// Walk the initializer ATTRIBUTED to the declared field
// (#693, the Go fix): the dispatcher only fn-ref-scans this
// subtree, so a lambda / method reference / anonymous class
// in `private final Runnable r = () -> target();` emitted no
// call edge at all.
if let Some(value) = decl.child_by_field_name("value") {
self.stack.push(Scope { row, kind: field_kind, name: name.clone() });
self.visit_function_body(value);
self.stack.pop();
}
}
}
} else {
codegraph-kernel/src/kotlin.rs
+147 -24
View File
@@ -9,10 +9,10 @@
//! is source-order dependent) and extractModifiers (expect/actual platform
//! modifiers → the node DECORATORS wire field, on every created node — the
//! KMP synthesizer's input). Preserved on purpose: the FIELD_COUNT-0 dead
//! cluster (no signatures, ZERO type-annotation refs), hook-consumed property
//! initializers emitting nothing, the bodiless-class header re-walk asymmetry,
//! enum-entry bodies being invisible, KDoc (`multiline_comment`) never being
//! a docstring AND chain-breaking, comment-gluing into import/package extents,
//! cluster (no signatures, ZERO type-annotation refs), the bodiless-class
//! header re-walk asymmetry, enum-entry bodies being invisible, KDoc
//! (`multiline_comment`) never being a docstring AND chain-breaking,
//! comment-gluing into import/package extents,
//! `@Anno(args)` emitting nothing while `@Anno` emits decorates, zero
//! instantiates refs (constructors are capitalized `calls`), the qualified-
//! receiver `com::qext` bug, the paren-then-lambda `trailing()` garbage
@@ -87,6 +87,66 @@ fn strip_js_ws(s: &str) -> String {
s.chars().filter(|c| !is_js_space(*c)).collect()
}
/// A property's CODE children: the named child right after the `=` token, a
/// `property_delegate` (`by lazy { … }`), and an accessor the grammar nested
/// under the declaration (`val x: Int get() = compute()` — written on ONE line;
/// an accessor on its own line parses as a SIBLING of the property and is not
/// reachable from here). What stays unwalked is the declaration itself —
/// modifiers, the `val`/`var` keyword, the name+type, and an extension
/// receiver's type and type parameters. (Go's #693 fix walks the `value` field
/// for the same reason; this grammar exposes no fields at all, hence the `=`
/// anchor.)
fn property_initializers<'t>(node: Node<'t>) -> Vec<Node<'t>> {
let mut out: Vec<Node<'t>> = Vec::new();
let mut after_eq = false;
for i in 0..node.child_count() {
let Some(c) = node.child(i) else { continue };
if !c.is_named() {
if c.kind() == "=" {
after_eq = true;
}
continue;
}
if after_eq {
out.push(c);
after_eq = false;
} else if matches!(c.kind(), "property_delegate" | "getter" | "setter") {
out.push(c);
}
}
out
}
/// Accessors written on their OWN line parse as SIBLINGS of the property, not
/// as children of it (same-line ones nest — see property_initializers). Walking
/// back over any accessors between us and the declaration finds the property an
/// accessor belongs to; None when this accessor stands alone.
fn accessor_owner<'t>(node: Node<'t>) -> Option<Node<'t>> {
let mut p = node.prev_named_sibling();
while let Some(n) = p {
if matches!(n.kind(), "getter" | "setter") {
p = n.prev_named_sibling();
continue;
}
return if n.kind() == "property_declaration" { Some(n) } else { None };
}
None
}
/// The sibling accessors that follow a property declaration, in source order.
fn following_accessors<'t>(node: Node<'t>) -> Vec<Node<'t>> {
let mut out = Vec::new();
let mut n = node.next_named_sibling();
while let Some(c) = n {
if !matches!(c.kind(), "getter" | "setter") {
break;
}
out.push(c);
n = c.next_named_sibling();
}
out
}
struct Scope {
row: u32,
kind: &'static str,
@@ -583,25 +643,23 @@ impl<'t> Walker<'t> {
// --- the visitNode hook (property branch ONLY — fun-interface recovery is
// defer-shielded and not ported) ------------------------------------------------
fn try_visit_hook(&mut self, node: Node<'t>) -> bool {
if node.kind() != "property_declaration" {
return false;
}
/// A property's node kind, or None when the declaration mints no node at
/// all: destructuring, an unreadable name, or a local (inside a function
/// body / `init` block / lambda / accessor). Kind by enclosing scope — a
/// singleton `object` / `companion object` (and a top-level property) holds
/// SHARED values (`val`→constant, `var`→variable, the Scala-object rule; a
/// `const val` is just a val); a class/interface/enum instance `val`/`var`
/// is per-instance state → `field`.
fn property_kind(&self, node: Node<'t>) -> Option<&'static str> {
let var_decl = (0..node.named_child_count())
.filter_map(|i| node.named_child(i))
.find(|c| c.kind() == "variable_declaration");
let name_node = var_decl.and_then(|vd| {
(0..vd.named_child_count())
.filter_map(|i| vd.named_child(i))
.find(|c| c.kind() == "simple_identifier")
});
let Some(name_node) = name_node else { return false }; // destructuring → decline
let name = self.text(name_node).to_string();
if name.is_empty() {
return false;
.find(|c| c.kind() == "variable_declaration")?;
let name_node = (0..var_decl.named_child_count())
.filter_map(|i| var_decl.named_child(i))
.find(|c| c.kind() == "simple_identifier")?;
if self.text(name_node).is_empty() {
return None;
}
// Scope walk up the parent chain — first match wins.
let mut scope: &str = "const";
let mut p = node.parent();
while let Some(pn) = p {
@@ -624,24 +682,89 @@ impl<'t> Walker<'t> {
p = pn.parent();
}
if scope == "local" {
return true; // a local — extract nothing, subtree still scanned
return None;
}
let binding = (0..node.named_child_count())
.filter_map(|i| node.named_child(i))
.find(|c| c.kind() == "binding_pattern_kind");
let is_val = binding.map(|b| self.text(b) == "val").unwrap_or(false);
let kind: &'static str = if scope == "instance" {
Some(if scope == "instance" {
"field"
} else if is_val {
"constant"
} else {
"variable"
})
}
fn try_visit_hook(&mut self, node: Node<'t>) -> bool {
// An own-line accessor already walked by its owning property below. The
// ownership test re-derives the property's kind rather than remembering
// it: a destructured or local declaration mints no node, so its
// accessors were NOT consumed and must keep falling through.
if matches!(node.kind(), "getter" | "setter") {
return accessor_owner(node)
.and_then(|owner| self.property_kind(owner))
.is_some();
}
if node.kind() != "property_declaration" {
return false;
}
let var_decl = (0..node.named_child_count())
.filter_map(|i| node.named_child(i))
.find(|c| c.kind() == "variable_declaration");
let name_node = var_decl.and_then(|vd| {
(0..vd.named_child_count())
.filter_map(|i| vd.named_child(i))
.find(|c| c.kind() == "simple_identifier")
});
// Destructuring (`val (a, b) = makePair()`): NEITHER arm mints a symbol
// for the destructured names — declining just routes the node to
// extractField/extractVariable, which both find nothing for kotlin and
// end in the same fn-ref scan. But the RHS is CODE, and it was vanishing
// whole. Consume the node here and walk it at the ENCLOSING scope (no
// symbol of its own to attribute to).
let Some(name_node) = name_node else {
for init in property_initializers(node) {
self.visit_function_body(init);
}
return true;
};
let name = self.text(name_node).to_string();
if name.is_empty() {
return false;
}
let Some(kind) = self.property_kind(node) else {
// A local — no node is minted, but the initializer is still code.
// Walk it at the ENCLOSING scope: an `init { }` block's
// `val q = load()` is the CLASS calling load, and it used to
// disappear entirely (only the block's bare statements survived).
for init in property_initializers(node) {
self.visit_function_body(init);
}
return true;
};
// The `type`-field signature read is dead (zero fields) → signature
// undefined; NO docstring/visibility/isStatic — the modifiers merge in
// create_node still decorates expect/actual properties.
self.create_node(kind, &name, node, Extra::default());
let row = self.create_node(kind, &name, node, Extra::default());
// Walk the initializer ATTRIBUTED to the declared symbol (#693, the Go
// fix, ported): without this the subtree is only fn-ref-scanned, so a
// lambda / SAM / object initializer (`val cb = Runnable { target() }` —
// the idiomatic Android callback field) contributed NO call edge at all.
// The property also OWNS any accessor written on its own line, which the
// grammar makes a following SIBLING rather than a child; those bodies
// used to attribute to the enclosing class.
if let Some(row) = row {
self.stack.push(Scope { row, kind, name: name.clone() });
for init in property_initializers(node) {
self.visit_function_body(init);
}
for acc in following_accessors(node) {
self.visit_function_body(acc);
}
self.stack.pop();
}
true
}
codegraph-kernel/src/python.rs
+30 -7
View File
@@ -475,14 +475,37 @@ impl<'t> Walker<'t> {
let docstring = preceding_docstring(node, self.src);
let left = node.child_by_field_name("left").or_else(|| node.named_child(0));
let right = node.child_by_field_name("right").or_else(|| node.named_child(1));
let Some(left) = left else { return };
if !matches!(left.kind(), "identifier" | "constant") {
return;
let mut assigned: Option<(u32, String)> = None;
if let Some(left) = left {
if matches!(left.kind(), "identifier" | "constant") {
let name = self.text(left).to_string();
let signature = right.map(|r| util::init_signature(self.text(r)));
// No isConst hook ⇒ always `variable` (UPPER_CASE constants included).
let row = self.create_node(
"variable",
&name,
node,
Extra { docstring, signature, ..Extra::default() },
);
if let Some(row) = row {
assigned = Some((row, name));
}
}
}
// Walk the initializer ATTRIBUTED to the assigned name (#693): a
// module-level `app = FastAPI()` / `handler = lambda: run()` dropped
// every call on the right-hand side. A tuple target mints no symbol, so
// its RHS is walked at the enclosing scope rather than lost.
if let Some(right) = right {
match assigned {
Some((row, name)) => {
self.stack.push(Scope { row, kind: "variable", name });
self.visit_function_body(right);
self.stack.pop();
}
None => self.visit_function_body(right),
}
}
let name = self.text(left).to_string();
let signature = right.map(|r| util::init_signature(self.text(r)));
// No isConst hook ⇒ always `variable` (UPPER_CASE constants included).
self.create_node("variable", &name, node, Extra { docstring, signature, ..Extra::default() });
}
fn extract_import(&mut self, node: Node<'t>) {
codegraph-kernel/src/rustlang.rs
+23 -1
View File
@@ -667,6 +667,8 @@ impl<'t> Walker<'t> {
/// and the initializer value is never body-walked.
fn extract_variable(&mut self, node: Node<'t>) {
let docstring = preceding_docstring(node, self.src);
let name_field = node.child_by_field_name("name");
let mut declared: Option<(u32, String)> = None;
for i in 0..node.named_child_count() {
let Some(child) = node.named_child(i) else { continue };
if child.kind() != "identifier" {
@@ -674,7 +676,7 @@ impl<'t> Walker<'t> {
}
let name = self.text(child).to_string();
if !name.is_empty() {
self.create_node(
let row = self.create_node(
"variable",
&name,
child,
@@ -684,6 +686,26 @@ impl<'t> Walker<'t> {
..Extra::default()
},
);
if let (Some(row), Some(nf)) = (row, name_field) {
if child.start_byte() == nf.start_byte() {
declared = Some((row, name));
}
}
}
}
// Walk the initializer ATTRIBUTED to the declared symbol (#693):
// `const N: usize = compute()` and
// `static REGISTRY: Lazy<T> = Lazy::new(|| build())` dropped every call
// inside the initializer, so a handler table or a lazily-built
// singleton linked to nothing.
if let Some(value) = node.child_by_field_name("value") {
match declared {
Some((row, name)) => {
self.stack.push(Scope { row, kind: "variable", name });
self.visit_function_body(value);
self.stack.pop();
}
None => self.visit_function_body(value),
}
}
}
codegraph-kernel/src/scala.rs
+12
View File
@@ -656,6 +656,18 @@ impl<'t> Walker<'t> {
if let (Some(row), Some(t)) = (created, type_node) {
self.emit_scala_type_refs(t, row);
}
// Walk the initializer ATTRIBUTED to the declared symbol
// (#693, the Go fix): the hook consumes this subtree and the
// dispatcher only fn-ref-scans it, so `val cb = () => target()`
// — and even a plain `val x = compute()` — emitted no call edge
// at all.
if let Some(row) = created {
if let Some(value) = node.child_by_field_name("value") {
self.stack.push(Scope { row, kind, name: name.clone() });
self.visit_body(value);
self.stack.pop();
}
}
true
}
"enum_case_definitions" => {
codegraph-kernel/src/tsjs/extractors.rs
+19 -11
View File
@@ -483,18 +483,26 @@ impl<'t> Walker<'t> {
}
}
// Walk the initializer for calls — except the object/store shapes
// whose members are extracted method-by-method below.
// Walk the initializer for calls, ATTRIBUTED to the declared symbol
// (#693) — except the object/store shapes whose members are
// extracted method-by-method below (walking those too would
// double-count each member arrow's calls). Before this the walk ran
// with only the FILE on the stack (`const cfg = load()` recorded the
// file as load's caller) and object literals were skipped outright.
let members_extracted_separately = extract_object_methods
|| rtk_endpoints.is_some()
|| pinia_setup.is_some()
|| !store_collections.is_empty();
if let Some(v) = value {
let vk = v.kind();
if vk != "object"
&& vk != "object_expression"
&& !(extract_object_methods && vk == "call_expression")
&& rtk_endpoints.is_none()
&& pinia_setup.is_none()
&& store_collections.is_empty()
{
self.visit_function_body(v);
if !members_extracted_separately {
match var_row {
Some(row) => {
self.stack.push(Scope { row, kind, name: name.clone() });
self.visit_function_body(v);
self.stack.pop();
}
None => self.visit_function_body(v),
}
}
}