fix(extract): drop Swift generic type parameters from references

A `struct Stack<Element>` / `func map<R>(...)` binds `Element`/`R` as local
names, not corpus symbols, but `_swift_collect_type_refs` appended the bare
identifiers used in a signature or stored-property type as type references and
ran them through the sourceless-stub path. Every generic type/function in the
corpus then collapsed its `T` onto one bare `t` node — a god node that pollutes
god-node rankings, since single-letter type parameters are not in the
analyzer's builtin-noise filter. C#, Java, TypeScript, Kotlin, Scala, C++, and
Go already exclude theirs.

Mirrors that pattern (and complements the `Self` keyword fix already in this
collector): a new `_swift_type_parameters_in_scope` helper walks up to every
enclosing declaration's `type_parameters` list and takes each `type_parameter`'s
first `type_identifier` as the bound name (a constraint like `T: Equatable` is a
separate `user_type`, left to reference), and `_swift_collect_type_refs`
auto-computes and threads that skip set. Genuine user types and the `Int`/
`String` builtin hubs are unaffected.

(cherry picked from commit 2e8a5c0f97)
This commit is contained in:
rajatnagda45 authored and safishamsi committed 2026-10-13 11:14:16 +01:00
1 parent 5299fb1e81
commit 786e8868a0
2 files changed
+91 -8

No files matched your search

+43 -8
View File
@@ -1193,28 +1193,63 @@ def _swift_user_type_name(user_type_node, source: bytes) -> str | None:
return text or None
return None
def _swift_collect_type_refs(node, source: bytes, generic: bool, out: list[tuple[str, str]]) -> None:
"""Walk a Swift type expression; append (name, role) tuples (role 'type' or 'generic_arg')."""
def _swift_type_parameters_in_scope(node, source: bytes) -> frozenset[str]:
"""Return Swift generic type-parameter names visible from ``node``.
A `struct Stack<Element>` / `func map<R>(...)` binds `Element`/`R` as local
names, not corpus symbols. Walking up to every enclosing declaration's
`type_parameters` list collects them; a parameter's name is the first
`type_identifier` of its `type_parameter` node (a constraint like
`T: Equatable` is a separate `user_type` and is left to reference).
"""
names: set[str] = set()
scope = node
while scope is not None:
for child in scope.children:
if child.type != "type_parameters":
continue
for param in child.children:
if param.type != "type_parameter":
continue
for sub in param.children:
if sub.type == "type_identifier":
name = _read_text(sub, source)
if name:
names.add(name)
break
scope = scope.parent
return frozenset(names)
def _swift_collect_type_refs(node, source: bytes, generic: bool, out: list[tuple[str, str]],
skip: frozenset[str] | None = None) -> None:
"""Walk a Swift type expression; append (name, role) tuples (role 'type' or 'generic_arg').
Generic type parameters in scope (``skip``) are local bindings, not
references; emitting one mints a sourceless stub (the bare `t` god node a
`<T>` type or function would otherwise share corpus-wide)."""
if node is None:
return
if skip is None:
skip = _swift_type_parameters_in_scope(node, source)
t = node.type
if t == "type_annotation":
for c in node.children:
if c.is_named:
_swift_collect_type_refs(c, source, generic, out)
_swift_collect_type_refs(c, source, generic, out, skip)
return
if t == "user_type":
for c in node.children:
if c.type == "type_identifier":
text = _read_text(c, source)
if text and text != "Self":
if text and text != "Self" and text not in skip:
out.append((text, "generic_arg" if generic else "type"))
break
for c in node.children:
if c.type == "type_arguments":
for arg in c.children:
if arg.is_named:
_swift_collect_type_refs(arg, source, True, out)
_swift_collect_type_refs(arg, source, True, out, skip)
return
if t == "type_identifier":
text = _read_text(node, source)
@@ -1223,19 +1258,19 @@ def _swift_collect_type_refs(node, source: bytes, generic: bool, out: list[tuple
# method collapses onto (a god node), the same keyword-type pitfall as
# Rust's `Self`. A genuine type (including `Int`/`String` builtin hubs)
# is unaffected.
if text and text != "Self":
if text and text != "Self" and text not in skip:
out.append((text, "generic_arg" if generic else "type"))
return
if t in ("optional_type", "implicitly_unwrapped_optional_type", "array_type",
"dictionary_type", "tuple_type"):
for c in node.children:
if c.is_named:
_swift_collect_type_refs(c, source, generic, out)
_swift_collect_type_refs(c, source, generic, out, skip)
return
if node.is_named:
for c in node.children:
if c.is_named:
_swift_collect_type_refs(c, source, generic, out)
_swift_collect_type_refs(c, source, generic, out, skip)
def _swift_property_type_node(property_node):
"""Return the type_annotation child of a Swift property_declaration, if any."""
+48
View File
@@ -0,0 +1,48 @@
"""Swift generic type parameters must not mint sourceless god nodes.
A `struct Stack<Element>` / `func map<R>(...)` binds `Element`/`R` as local
names, not corpus symbols. The Swift type-ref pass appended the bare
identifiers used in a signature or stored-property type as type references and
ran them through the sourceless-stub path, so every generic type/function in
the corpus collapsed its `T` onto one bare `t` node — a god node (single-letter
type params are not in the analyzer's builtin-noise filter). C#, Java,
TypeScript, Kotlin, Scala, C++, and Go already exclude their type parameters;
Swift now matches.
"""
from pathlib import Path
from graphify.extract import extract
def _sourceless(r):
return sorted({(n["id"], n.get("label")) for n in r["nodes"] if not n.get("source_file")})
def test_generic_struct_and_method_type_params_mint_no_stub(tmp_path):
(tmp_path / "s.swift").write_text(
"struct Stack<Element> {\n"
" var items: [Element]\n"
" func peek() -> Element? { return items.last }\n"
" func map<R>(_ f: (Element) -> R) -> [R] { return [] }\n"
"}\n"
)
r = extract([tmp_path / "s.swift"], cache_root=tmp_path, parallel=False)
assert _sourceless(r) == []
assert not any(e.get("target") in ("element", "r") for e in r["edges"])
def test_constrained_param_dropped_but_real_type_kept(tmp_path):
# `T` is a parameter (dropped); a genuine user type in the signature still
# references.
(tmp_path / "s.swift").write_text(
"struct User { var id: Int }\n"
"func wrap<T: Equatable>(_ x: T, u: User) -> User { return u }\n"
)
r = extract([tmp_path / "s.swift"], cache_root=tmp_path, parallel=False)
assert not any(e.get("target") == "t" for e in r["edges"])
refs = {
rn["label"]
for e in r["edges"] if e.get("relation") == "references"
for rn in r["nodes"] if rn["id"] == e["target"]
}
assert "User" in refs