fix(extraction): never fabricate an edge from a call-result receiver (#1748)

A member call whose receiver is itself a call — `d.setdefault(k, []).append(v)`,
`make().run()` — used to drop the receiver at extraction time, degrade to the
bare method name, and exact-match any top-level project symbol of that name
(Python and JavaScript/TypeScript). Keep the inner callee encoded as
`<inner>().<method>` in the TS extractor and native kernel; the name-matcher
refuses to guess for that shape (store-accessor exception only). Based on
#1692, rebased onto main after #1746. Fixes #1683.

Co-authored-by: Colby McHenry <colbymchenry@users.noreply.github.com>
This commit is contained in:
Colby Mchenry
2026-09-08 00:23:08 -05:00
committed by GitHub
co-authored by Colby McHenry
parent bffd50e4f1
commit bb1d3093eb
10 changed files with 226 additions and 3 deletions
+26
View File
@@ -4573,6 +4573,32 @@ export class TreeSitterExtractor {
// scope keywords: such calls previously emitted a bare method
// name, which either failed to resolve or resolved ambiguously.
calleeName = `${getNodeText(receiver, this.source)}.${methodName}`;
} else if (
(this.language === 'typescript' ||
this.language === 'javascript' ||
this.language === 'tsx' ||
this.language === 'jsx' ||
this.language === 'python') &&
receiver &&
(receiver.type === 'call_expression' || receiver.type === 'call')
) {
// Receiver that is itself a call — `d.setdefault(k, []).append(v)`,
// `make().run()`, `res.json().data` (#1683). The bare method name
// this used to emit exact-matched any top-level project symbol of
// that name and fabricated a call edge from an unrelated function
// (`append`, `get`, `run`…). Keep the inner callee, encoded as
// `<inner>().<method>` like the Java/Kotlin/C++ chains: the
// marker never appears in an ordinary ref, so nothing name-matches
// it, and a chain resolver can later infer the receiver's type
// from what the inner call returns. An inner callee that is not a
// plain name or member chain (`(await x)()`, `arr[0]()`) has no
// static receiver at all — emit nothing: a silent miss, never a
// wrong edge. The inner call is visited on its own either way.
// Mirrored in the kernel (tsjs/extractors.rs, python.rs).
const innerFn = getChildByField(receiver, 'function');
const innerCallee = innerFn ? getNodeText(innerFn, this.source).replace(/\s+/g, '') : '';
if (!/^[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)*$/.test(innerCallee)) return;
calleeName = `${innerCallee}().${methodName}`;
} else if (
this.language === 'go' &&
receiver &&
+13
View File
@@ -974,6 +974,19 @@ export class ReferenceResolver {
if (fwEarly) return fwEarly;
// Strategy 2: Try import-based resolution
// A TS/JS/Python call-receiver chain (`useStore.getState().reset`, #1683)
// names the ROOT's import, not the method's: letting resolveViaImport see
// it binds the call to the imported store constant and the method is
// never looked up. The name-matcher owns the chain shape for these
// languages — the Java/Kotlin/C++ chains keep their existing path.
if (
ref.referenceKind === 'calls' &&
CHAIN_SHAPE.test(ref.referenceName) &&
(ref.language === 'typescript' || ref.language === 'javascript' || ref.language === 'tsx' || ref.language === 'jsx' || ref.language === 'python')
) {
return this.gateLanguage(matchReference(ref, this.context), ref);
}
const tImp = this.profileStages ? process.hrtime.bigint() : 0n;
const importResult = this.gateLanguage(resolveViaImport(ref, this.context), ref);
if (this.profileStages) this.stageAdd('viaImport', ref, !!importResult, tImp);
+37
View File
@@ -2507,6 +2507,30 @@ function matchRustSelfFieldCall(
return null;
}
/**
* The one fallback a TS/JS/Python call-receiver chain keeps (#1683): a STORE
* ACCESSOR. Zustand's `get()` inside the store factory and
* `useStore.getState()` outside it hand back the store whose actions are
* indexed as functions (#1573), so a unique callable of the method's name in
* the same language family is what `get().reset()` reaches. Nothing else
* qualifies: a chain rooted in a project value still says nothing about what
* the inner call RETURNS — `db.prepare(sql).all()` would bind to any project
* function named `all` — so it resolves to nothing, exactly like a chain
* rooted in a parameter (`d.setdefault(k, []).append(v)`).
*/
function matchStoreAccessorChain(ref: UnresolvedRef, context: ResolutionContext): ResolvedRef | null {
const m = ref.referenceName.match(/^([\w$.]+)\(\)\.(\w+)$/);
if (!m || !m[1] || !m[2]) return null;
const inner = m[1];
const method = m[2];
if (!(inner === 'get' || inner === 'getState' || inner.endsWith('.getState'))) return null;
const callables = context
.getNodesByName(method)
.filter((n) => (n.kind === 'function' || n.kind === 'method') && sameLanguageFamily(n.language, ref.language) && n.id !== ref.fromNodeId);
if (callables.length !== 1) return null;
return { original: ref, targetNodeId: callables[0]!.id, confidence: 0.6, resolvedBy: 'exact-match' };
}
/**
* Split a camelCase or PascalCase string into words.
*/
@@ -2917,6 +2941,19 @@ export function matchReference(
if (result) return result;
}
// A call-receiver chain the extractor encoded as `<inner>().<method>` for a
// language with no chain resolver above (TS/JS, Python — #1683) is a
// receiver whose type is unknown. Nothing below may guess for it: the
// method-call pattern rejects the parens, exact name never matches, but the
// fuzzy strategy splits on `.` and would hand `make().run` to any `run` —
// the fabricated edge the encoding exists to prevent.
if (
ref.referenceName.includes('().') &&
(ref.language === 'typescript' || ref.language === 'javascript' || ref.language === 'tsx' || ref.language === 'jsx' || ref.language === 'python')
) {
return nmTimed('storeAccessorChain', ref, () => matchStoreAccessorChain(ref, context));
}
// 2. Method call pattern
result = nmTimed('methodCall', ref, () => matchMethodCall(ref, context));
if (result) return result;