mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
Marius CiepluchandClaude Fable 5.1
c955721f92
One flatten too many turned "base,controlflow,typerel,callgraph,dataflowOss" into "b,a,s,e,...", and every real build then warned that its graph lacked the dataflow layer while carrying it. The compile test now asserts the shape on a real graph. Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
68 lines
3.3 KiB
Python
68 lines
3.3 KiB
Python
"""The CPG queries are 900 lines of Scala that nothing else in this suite compiles.
|
|
|
|
A signature change to `rowsFor` once shipped with 850 tests passing and broke every query at runtime. It was
|
|
found by a measurement failing hours later, not by CI -- which is the same shape as every other failure this
|
|
project keeps having: the thing that was never checked reported nothing, and nothing read as fine.
|
|
|
|
These tests need a real Joern, so they skip where it is absent. Skipping is honest here in a way it is not
|
|
elsewhere: the suite still runs everywhere, and the check runs wherever the engine it checks exists.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
QUERIES = Path("src/openultrasast/cpg/queries")
|
|
|
|
|
|
def _joern() -> str | None:
|
|
import shutil
|
|
|
|
return shutil.which("joern")
|
|
|
|
|
|
@pytest.mark.skipif(_joern() is None, reason="joern is not installed on this machine")
|
|
@pytest.mark.parametrize("name", ["taint", "dominance", "config", "census", "overlay"])
|
|
def test_each_query_compiles_and_answers(name: str, tmp_path: Path) -> None:
|
|
"""Compile and RUN each query against a graph, and require a fenced payload back.
|
|
|
|
Compiling alone would miss a runtime arity error inside a branch, so the query has to answer -- and the
|
|
answer has to parse, because a script that prints a stack trace still exits 0 often enough to matter.
|
|
"""
|
|
from openultrasast.cpg.backend import extract_payload
|
|
|
|
script = QUERIES / f"{name}.sc"
|
|
assert script.is_file(), f"{script} is missing"
|
|
|
|
source = tmp_path / "sample.php"
|
|
source.write_text("<?php\nfunction handler($x) {\n global $wpdb;\n return $wpdb->query($x);\n}\n")
|
|
cpg = tmp_path / "cpg.bin"
|
|
frontend = __import__("shutil").which("php2cpg")
|
|
if frontend is None:
|
|
pytest.skip("php2cpg is not installed")
|
|
built = subprocess.run([frontend, str(tmp_path), "-o", str(cpg)], capture_output=True, text=True, timeout=600, check=False)
|
|
if not cpg.is_file():
|
|
pytest.skip(f"could not build a sample cpg: {(built.stderr or '')[-200:]}")
|
|
|
|
command = [_joern() or "joern", "--script", str(script.resolve()), "--param", f"cpgFile={cpg}"]
|
|
if name not in {"census", "overlay"}:
|
|
requests = tmp_path / "requests.json"
|
|
requests.write_text(json.dumps({"0": {"sources": "$_GET", "sinks": "$wpdb->query", "function": "handler"}}))
|
|
command += ["--param", f"requestsFile={requests}"]
|
|
done = subprocess.run(command, capture_output=True, text=True, timeout=900, check=False, cwd=str(tmp_path))
|
|
|
|
assert done.returncode == 0, f"{name}.sc did not run: {(done.stderr or done.stdout or '')[-500:]}"
|
|
payload = extract_payload(done.stdout or "")
|
|
assert payload is not None, f"{name}.sc produced no parseable payload"
|
|
if name == "census":
|
|
# The overlay list is what the backend checks for the dataflow layer. It shipped once as a list of
|
|
# CHARACTERS (`b,a,s,e,...`) -- one `flatten` too many -- and every real build warned that its graph
|
|
# lacked `dataflowOss` while carrying it. `importCpg` applies the layer here, so it must be named.
|
|
overlays = str(payload.get("overlays", "")).split(",")
|
|
assert "dataflowOss" in overlays, f"census reports overlays {overlays!r}, which is not a list of layer names"
|
|
assert str(payload.get("maxHeapMB", "")).isdigit()
|