marius/Open_Ultra_SAST
1
0
Fork 0
mirror of https://github.com/norandom/OpenUltraSAST.git synced 2026-10-17 20:19:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(p1): one source-facts module owns function ranges, callers, declaration tables and language aliases

Browse Source 
src/openultrasast/source.py replaces the copies in semantic/functions.py,
plane/tasks/repo_facts.py, learn/features.py, learn/excerpt.py and
plane/tasks/verify.py. Two engines share one sentinel (<module>), one
DECLARATION/KEYWORDS/RESERVED set and one alias map: the parser engine
(ranges, enclosing, bounds, call_sites, callers_of, facts_for) for the
scorer, the overlay and the hunter's annotations; the line-pattern engine
(declared_functions, enclosing_at, function_span, function_bounds, the brace
matcher) that labels, features, roles, excerpts and plane facts were built
on. learn no longer imports plane.tasks. Frozen records that store the old
sentinel are mapped on read (module_function).

Gate: labels rebuilt before and after are identical, 7,921 rows, after
sentinel normalisation (benchmarks/measurements/2026-10-13-source-module-
label-diff/record.json). 490 targeted tests pass; 3,312 collect. Net: 657
lines deleted, 212 added. benchmarks/unseen keeps <global> for its own
frozen manifests.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-13 12:00:37 +02:00
co-authored by Claude Fable 5.1
parent f63703a604
commit 062a7b780e
36 changed files with 1099 additions and 629 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_pair_corpus.py
+21 -12
View File
@@ -512,12 +512,17 @@ def test_known_limit_pairs_emit_no_improve_signals(tmp_path: Path) -> None:
def test_function_at_skips_anonymous_and_module_ranges() -> None:
from openultrasast.semantic.overlay import function_at
from openultrasast.source import FunctionRange
from openultrasast.source import enclosing as function_at
ranges = (("<module>", 1, 40), ("handler", 3, 20), ("<anon>", 5, 12))
ranges = (
FunctionRange("<module>", 1, 40, "module"),
FunctionRange("handler", 3, 20, "function"),
FunctionRange("<anon>", 5, 12, "anonymous"),
)
assert function_at(ranges, 7) == "handler" # innermost *named* function, never "<anon>"
assert function_at(ranges, 25) is None
assert function_at((("<anon>", 1, 9),), 4) is None
assert function_at(ranges, 25) == "<module>"
assert function_at((FunctionRange("<anon>", 1, 9, "anonymous"),), 4) == "<module>"
@pytest.mark.semantic
@@ -738,7 +743,8 @@ def test_unresolvable_function_label_is_a_visible_loss_not_a_silent_miss(tmp_pat
def test_named_function_ranges_use_declarator_names() -> None:
from openultrasast.semantic.extra import has_semantic_extra
from openultrasast.semantic.functions import declarator_name, named_function_ranges
from openultrasast.source import declarator_name
from openultrasast.source import ranges as named_function_ranges
assert declarator_name("const listProcessesOnPort = module.exports.listProcessesOnPort = async port => {") == "listProcessesOnPort"
assert declarator_name(" exec('df -k ' + path, function(err, stdout) {") is None
@@ -765,8 +771,8 @@ def test_named_function_ranges_use_declarator_names() -> None:
)
ranges = named_function_ranges("f.js", src, "javascript")
assert ranges is not None
assert {name for name, _, _ in ranges} >= {"a", "b", "c", "d", "e"}
assert "<anon>" not in {name for name, _, _ in ranges}
assert {name for name, _, _, _ in ranges} >= {"a", "b", "c", "d", "e"}
assert "<anon>" not in {name for name, _, _, _ in ranges}
# --- review round 4 remediation (RED first) -----------------------------------
@@ -775,17 +781,18 @@ def test_named_function_ranges_use_declarator_names() -> None:
@pytest.mark.semantic
def test_c_function_with_return_type_on_previous_line_keeps_its_parser_name() -> None:
from openultrasast.semantic.extra import has_semantic_extra
from openultrasast.semantic.functions import function_at, named_function_ranges
from openultrasast.source import enclosing as function_at
from openultrasast.source import ranges as named_function_ranges
if not has_semantic_extra():
pytest.skip("tree-sitter extra absent")
ranges = named_function_ranges("a.c", "static int\nfoo(int x)\n{\n return x;\n}\n", "c")
assert ranges is not None and any(name == "foo" and start <= 4 <= end for name, start, end in ranges)
assert ranges is not None and any(name == "foo" and start <= 4 <= end for name, start, end, _ in ranges)
assert function_at(ranges, 4) == "foo"
def test_declarator_name_knows_perl_subs_and_never_names_calls() -> None:
from openultrasast.semantic.functions import declarator_name
from openultrasast.source import declarator_name
assert declarator_name("sub link_hash_cert {") == "link_hash_cert"
assert declarator_name(" return foo(bar)") is None
@@ -798,7 +805,7 @@ def test_declarator_name_knows_perl_subs_and_never_names_calls() -> None:
def test_declarator_name_strips_cpp_qualification_to_match_unqualified_labels() -> None:
from openultrasast.semantic.functions import declarator_name
from openultrasast.source import declarator_name
assert declarator_name("bool FileReaderLoader::ArrayBufferResult(int a) {") == "ArrayBufferResult"
assert declarator_name("void ns::Klass::run(const std::string& s) const {") == "run"
@@ -808,7 +815,9 @@ def test_declarator_name_strips_cpp_qualification_to_match_unqualified_labels()
@pytest.mark.semantic
def test_cpp_qualified_method_range_is_found_by_its_unqualified_label() -> None:
from openultrasast.semantic.extra import has_semantic_extra
from openultrasast.semantic.functions import function_at, named_function_ranges, spans_named
from openultrasast.source import enclosing as function_at
from openultrasast.source import ranges as named_function_ranges
from openultrasast.source import spans_named
if not has_semantic_extra():
pytest.skip("tree-sitter extra absent")