marius/Open_Ultra_SAST
1
0
Fork 0
mirror of https://github.com/norandom/OpenUltraSAST.git synced 2026-10-18 12:39:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(contributor-scan): retain declared Gruntfile and report census gaps honestly

Browse Source
This commit is contained in:
Marius Ciepluch
2026-09-14 08:07:06 +02:00
parent 88216c5072
commit 7c1c2d4475
18 changed files with 1048 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/openultrasast/model/partitions.py
+11 -7
View File
@@ -106,6 +106,9 @@ class PartitionGraph:
raw = batch(kind, selected) if callable(batch) else {rid: graph.run(kind, params) for rid, params in selected.items()}
if not isinstance(raw, Mapping):
continue
raw = dict(raw)
if not isinstance(raw.get("__census__"), list):
raw["__census__"] = []
for rid, rows in raw.items():
if rid in selected and isinstance(rows, list):
answers[rid] = self._normalize(rows)
@@ -117,17 +120,18 @@ class PartitionGraph:
observed = {p.removeprefix("./") for n in names if isinstance(n, list) for p in n if isinstance(p, str)}
if not named or not expected <= observed:
self.diagnostics.append("partition_file_census_incomplete" if named else "partition_file_census_unavailable")
reason = "partition_file_census_incomplete" if named else "partition_file_census_unavailable"
rows = [
{
"methods": 0,
"files": 0,
"shards": max((int(str(r.get("shards", 1))) for r in rows if isinstance(r, Mapping)), default=1),
}
]
dict(r, census_failure=reason, missing_file_names=sorted(expected - observed) if named else [])
for r in normalized
if isinstance(r, Mapping)
] or [{"census_failure": reason, "missing_file_names": []}]
# Preserve any individual empty or sharded graph's degradation.
previous = answers.get(rid, [])
if not previous or any(
isinstance(r, Mapping) and (int(str(r.get("methods", 0))) == 0 or int(str(r.get("shards", 1))) > 1) for r in rows
isinstance(r, Mapping)
and (r.get("census_failure") or int(str(r.get("methods", 0))) == 0 or int(str(r.get("shards", 1))) > 1)
for r in rows
):
answers[rid] = rows
return answers
src/openultrasast/model/scan.py
+20 -4
View File
@@ -355,6 +355,8 @@ def _scan_repository_impl(
in {
"files_unparsed",
"cpg_empty",
"partition_file_census_incomplete",
"partition_file_census_unavailable",
"cpg_sharded",
"cross_partition_semantics_unresolved",
"vendor_semantics_unresolved",
@@ -410,8 +412,14 @@ def _scan_repository_impl(
if census and not census_reported:
entry = census[0] if isinstance(census[0], Mapping) else {}
methods = int(str(entry.get("methods", "0")) or 0)
if methods == 0:
degradations.append({"stage": "model", "reason": "cpg_empty", "files": int(str(entry.get("files", "0")) or 0)})
if methods == 0 or entry.get("census_failure"):
degradations.append(
{
"stage": "model",
"reason": "cpg_empty" if "methods" in entry and methods == 0 else entry.get("census_failure", "cpg_empty"),
**{k: entry[k] for k in ("methods", "files", "missing_file_names") if k in entry},
}
)
# More than one graph means some files could only be built apart from the rest, and a
# flow whose source is in one shard and whose sink is in another does not exist for any
# question we can ask. Reporting the split is the difference between a partial answer and
@@ -508,6 +516,8 @@ def _scan_repository_impl(
in {
"files_unparsed",
"cpg_empty",
"partition_file_census_incomplete",
"partition_file_census_unavailable",
"cpg_sharded",
"cross_partition_semantics_unresolved",
"vendor_semantics_unresolved",
@@ -741,8 +751,14 @@ def _evidence_pass(
shards = int(str(entry.get("shards", "1")))
except ValueError:
methods, shards = 0, 1
if methods <= 0:
degradations.append({"stage": "model", "reason": "cpg_empty"})
if methods <= 0 or entry.get("census_failure"):
degradations.append(
{
"stage": "model",
"reason": "cpg_empty" if "methods" in entry and methods <= 0 else entry.get("census_failure", "cpg_empty"),
**{k: entry[k] for k in ("methods", "files", "missing_file_names") if k in entry},
}
)
if shards > 1:
degradations.append({"stage": "model", "reason": "cpg_sharded", "shards": shards})
by_rid = {rid: (region, spec) for rid, region, spec in work}