2026-06-17 21:13:51 +02:00
|
|
|
import pytest
|
|
|
|
|
|
2026-10-02 19:32:46 +02:00
|
|
|
from openultrasast.index import chunk_text_namespace
|
2026-06-17 21:13:51 +02:00
|
|
|
|
|
|
|
|
|
2026-10-02 19:32:46 +02:00
|
|
|
def test_namespace_chunks_are_metadata_scoped() -> None:
|
2026-06-17 21:13:51 +02:00
|
|
|
chunks = chunk_text_namespace(
|
|
|
|
|
namespace="skills",
|
|
|
|
|
path="semgrep.md",
|
|
|
|
|
text="Use Semgrep for variant mapping.\nKeep provenance.",
|
|
|
|
|
metadata={"language": "markdown", "vulnerability_class": "mapping"},
|
|
|
|
|
max_lines=1,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert len(chunks) == 2
|
|
|
|
|
assert chunks[0].namespace == "skills"
|
2026-10-02 19:32:46 +02:00
|
|
|
assert chunks[0].language == "markdown"
|
2026-06-17 21:13:51 +02:00
|
|
|
assert chunks[0].metadata["vulnerability_class"] == "mapping"
|
2026-10-02 19:32:46 +02:00
|
|
|
assert (chunks[0].start_line, chunks[0].end_line) == (1, 1)
|
|
|
|
|
assert chunks[0].chunk_id != chunks[1].chunk_id
|
2026-06-17 21:13:51 +02:00
|
|
|
|
|
|
|
|
|
2026-10-02 19:32:46 +02:00
|
|
|
def test_blank_blocks_are_skipped_and_the_language_defaults_to_text() -> None:
|
|
|
|
|
chunks = chunk_text_namespace(namespace="docs", path="README.md", text="alpha\n\n\nbeta\n", max_lines=1)
|
2026-06-17 21:13:51 +02:00
|
|
|
|
2026-10-02 19:32:46 +02:00
|
|
|
assert [chunk.text for chunk in chunks] == ["alpha", "beta"]
|
|
|
|
|
assert chunks[0].language == "text"
|
2026-06-17 21:13:51 +02:00
|
|
|
|
2026-10-02 19:32:46 +02:00
|
|
|
|
|
|
|
|
@pytest.mark.parametrize(("namespace", "max_lines"), [("unknown", 80), ("docs", 0)])
|
|
|
|
|
def test_invalid_namespace_or_window_is_rejected(namespace: str, max_lines: int) -> None:
|
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
|
chunk_text_namespace(namespace=namespace, path="x", text="y", max_lines=max_lines)
|