Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 16 additions & 3 deletions src/frameforge/semantic.py
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,22 @@ def evaluate(root, rule):
continue
# Comment filtering is intentionally conservative; not a language parser.
language = rule["language"]
pattern = (r'//[^\n]*|/\*[\s\S]*?\*/' if language == "csharp"
else r'--\[\[[\s\S]*?\]\]|--[^\n]*')
source = re.sub(pattern, lambda m: re.sub(r'[^\n]', ' ', m.group()), source)
if language == "csharp":
pattern = re.compile(
r'(?P<string>@"(?:""|[^"])*"|"(?:\\.|[^"\\])*"|\'(?:\\.|[^\'\\])*\')'
r'|(?P<comment>//[^\n]*|/\*[\s\S]*?\*/)'
)
else:
pattern = re.compile(
r'(?P<long_string>\[(?P<eq>=*)\[[\s\S]*?\](?P=eq)\])'
r'|(?P<string>"(?:\\.|[^"\\])*"|\'(?:\\.|[^\'\\])*\')'
r'|(?P<comment>--\[(?P<comment_eq>=*)\[[\s\S]*?\](?P=comment_eq)\]|--[^\n]*)'
)
source = pattern.sub(
lambda match: re.sub(r'[^\n]', ' ', match.group())
if match.group("comment") else match.group(),
source,
)
sources.append((relative, source))

if not sources:
Expand Down
25 changes: 25 additions & 0 deletions tests/test_semantic.py
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,31 @@ def test_positive_negative_and_comments(self):
f.write_text("Event += OnEvent;\nEvent -= OnEvent;")
self.assertEqual(evaluate(root,rule())["status"],"pattern_observed_control_flow_unverified")

def test_csharp_comment_markers_inside_strings_do_not_hide_code(self):
with tempfile.TemporaryDirectory() as d:
root = Path(d)
f = root/"Root.cs"
f.write_text('var url = "https://example.com"; Event += OnEvent; // Event -= OnEvent;\n')
result = evaluate(root, rule(["Root.cs"]))
self.assertEqual(result["status"], "review_needed")
self.assertEqual([item["token"] for item in result["evidence"]], ["Event += OnEvent;"])
self.assertEqual(result["missing_tokens"], ["Event -= OnEvent;"])

def test_lua_comment_markers_inside_strings_do_not_hide_code(self):
with tempfile.TemporaryDirectory() as d:
root = Path(d)
f = root/"transaction.lua"
f.write_text('local marker = "-- not a comment"; query(db, "COMMIT") -- query(db, "ROLLBACK")\n')
value = {
"plugin_id": "skynet", "id": "transaction", "topic": "transaction",
"recommendation": "review recovery", "language": "lua",
"paths": ["transaction.lua"], "tokens": ['"COMMIT"', '"ROLLBACK"'],
}
result = evaluate(root, value)
self.assertEqual(result["status"], "review_needed")
self.assertEqual([item["token"] for item in result["evidence"]], ['"COMMIT"'])
self.assertEqual(result["missing_tokens"], ['"ROLLBACK"'])

def test_relocation_and_absence(self):
with tempfile.TemporaryDirectory() as d:
root=Path(d)
Expand Down
Loading