feat(schema): L1 body call nodes (callee null) from call sites

Author: rahlk

codeanalyzer/core.py

@@ -18,6 +18,7 @@
     model_validate_json,
 )
 from codeanalyzer.schema.assign_ids import assign_ids
+from codeanalyzer.schema.l1_body import populate_l1_body
 from codeanalyzer.schema.py_schema import PyCallEdge
 from codeanalyzer.semantic_analysis.call_graph import (
     filter_external_edges,
@@ -457,6 +458,7 @@ def analyze(self) -> PyApplication:
         )
 
         assign_ids(app, self.options.app_name or self.project_dir.name)
+        populate_l1_body(app)
 
         # L3/L4 dataflow emission rebuilt on the v2 tree in Stage 3+
 

codeanalyzer/schema/l1_body.py

@@ -0,0 +1,29 @@
+"""L1 body population: materialize `call` nodes from existing call sites.
+`callee` is left None here — the sanctioned null→id refinement happens at L2."""
+from __future__ import annotations
+from codeanalyzer.schema.py_schema import PyApplication, PyClass, PyCallable, BodyNode, Span, byte_offsets
+
+def _do_callable(source: str, c: PyCallable) -> None:
+    for cs in c.call_sites or []:
+        key = f"{cs.start_line}:{cs.start_column}"
+        span = Span(start=(cs.start_line, cs.start_column),
+                    end=(cs.end_line, cs.end_column),
+                    bytes=byte_offsets(source, cs.start_line, cs.start_column, cs.end_line, cs.end_column)) if source else None
+        c.body[key] = BodyNode(kind="call", span=span, callee=None)
+    for ic in (c.inner_callables or {}).values():
+        _do_callable(source, ic)
+    for icl in (c.inner_classes or {}).values():
+        _do_class(source, icl)
+
+def _do_class(source: str, cl: PyClass) -> None:
+    for m in (cl.methods or {}).values():
+        _do_callable(source, m)
+    for ic in (cl.inner_classes or {}).values():
+        _do_class(source, ic)
+
+def populate_l1_body(app: PyApplication) -> None:
+    for mod in app.symbol_table.values():
+        for fn in (mod.functions or {}).values():
+            _do_callable(mod.source, fn)
+        for cl in (mod.classes or {}).values():
+            _do_class(mod.source, cl)

test/test_v2_l1_body.py

@@ -0,0 +1,13 @@
+from codeanalyzer.schema.l1_body import populate_l1_body
+from codeanalyzer.schema.py_schema import PyApplication, PyModule, PyCallable, PyCallsite
+
+def test_l1_body_has_call_nodes_with_null_callee():
+    cs = PyCallsite(method_name="g", start_line=2, start_column=4, end_line=2,
+                    end_column=7, callee_signature="m.g")
+    fn = PyCallable(name="f", path="m.py", signature="m.f", call_sites=[cs])
+    mod = PyModule(file_path="m.py", module_name="m", functions={"f": fn})
+    app = PyApplication(symbol_table={"m.py": mod})
+    populate_l1_body(app)
+    node = fn.body["2:4"]
+    assert node.kind == "call"
+    assert node.callee is None  # L1: unresolved; backfilled at L2