fix(wiki): exclude URL-shaped bibkeys from claim parsing
_parse_claims now skips matches where bibkey contains spaces or starts with "http", preventing Markdown hyperlinks like [text](https://...) from being misidentified as citations. Add two tests. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -121,6 +121,20 @@ def test_parse_claims_multiple() -> None:
|
||||
assert len(claims) == 2
|
||||
|
||||
|
||||
def test_parse_claims_ignores_markdown_links() -> None:
|
||||
"""Markdown hyperlinks like [text](https://example.com) are NOT parsed as claims."""
|
||||
md = "See the [related work](https://example.com) for details."
|
||||
claims = _parse_claims(md)
|
||||
assert claims == []
|
||||
|
||||
|
||||
def test_parse_claims_ignores_multi_word_bibkey() -> None:
|
||||
"""Multi-word 'bibkeys' (spaces inside) are not treated as real citations."""
|
||||
md = "Some text [not a bibkey here] and more."
|
||||
claims = _parse_claims(md)
|
||||
assert claims == []
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# _run_grounding_guard
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
Reference in New Issue
Block a user