stack/tests/llm/test_links.py

"""llm.links — kind-specific evidence deep links (pure)."""

from llm.links import for_source


class TestComment:
    def test_plain_comment_links_to_comment_page(self):
        url, label = for_source(
            {"kind": "comment", "comment_id": "CMS-2026-2377-3438"}, "snippet"
        )
        assert url == "https://www.regulations.gov/comment/CMS-2026-2377-3438"
        assert label == "CMS-2026-2377-3438"

    def test_pdf_attachment_chunk_links_to_page(self):
        url, label = for_source(
            {
                "kind": "comment",
                "comment_id": "CMS-2026-2377-3438",
                "attachment": "attachment_2.pdf",
                "page": "4",
            },
            "s",
        )
        assert url == (
            "https://downloads.regulations.gov/CMS-2026-2377-3438/attachment_2.pdf#page=4"
        )
        assert label == "CMS-2026-2377-3438 p.4"

    def test_non_pdf_attachment_no_page(self):
        url, label = for_source(
            {"kind": "comment", "comment_id": "C-1", "attachment": "attachment_1.docx"},
            "s",
        )
        assert url == "https://downloads.regulations.gov/C-1/attachment_1.docx"
        assert label == "C-1"

    def test_missing_comment_id_falls_back_to_item_key(self):
        url, label = for_source({"kind": "comment", "item_key": "ABCD1234"}, "s")
        assert label == "ABCD1234"
        assert url == ""


class TestRule:
    MD = {
        "kind": "rule",
        "html_url": "https://www.federalregister.gov/documents/2026/07/16/2026-14327/x",
        "p_id": "938",
        "page": "43949",
        "ordinal": "4",
        "fr_volume": "91",
    }

    def test_paragraph_link_with_highlight(self):
        url, label = for_source(
            self.MD,
            "In the FY 2027 Hospice proposed rule, CMS solicited comment. More.",
        )
        assert url == (
            "https://www.federalregister.gov/documents/2026/07/16/2026-14327/x#p-938"
            ":~:text=In%20the%20FY%202027%20Hospice%20proposed%20rule%2C%20CMS%20solicited%20comment."
        )
        assert label == "91 FR 43949 ¶4"

    def test_no_p_id_degrades_to_page_link(self):
        md = {**self.MD, "p_id": "", "ordinal": ""}
        url, label = for_source(md, "s")
        assert url.endswith("/x#page-43949")
        assert label == "91 FR 43949"

    def test_no_page_degrades_to_document(self):
        md = {
            "kind": "rule",
            "html_url": "https://fr.test/doc",
            "title": "CY2027 PFS NPRM",
        }
        url, label = for_source(md, "s")
        assert url == "https://fr.test/doc"
        assert label == "CY2027 PFS NPRM"


class TestCorpus:
    def test_item_url_and_short_title_with_year(self):
        url, label = for_source(
            {
                "kind": "corpus",
                "url": "https://pubmed.ncbi.nlm.nih.gov/19922199/",
                "title": "A consensus on palliative care quality metrics for hospital programs",
                "year": "2009",
            },
            "s",
        )
        assert url == "https://pubmed.ncbi.nlm.nih.gov/19922199/"
        assert (
            label
            == "A consensus on palliative care quality metrics for hospital… (2009)"
        )

    def test_pdf_url_gets_page(self):
        url, _ = for_source(
            {
                "kind": "corpus",
                "url": "https://x.test/report.pdf",
                "title": "R",
                "page": "7",
            },
            "s",
        )
        assert url == "https://x.test/report.pdf#page=7"

    def test_non_pdf_url_ignores_page(self):
        url, _ = for_source(
            {
                "kind": "corpus",
                "url": "https://x.test/report",
                "title": "R",
                "page": "7",
            },
            "s",
        )
        assert url == "https://x.test/report"

    def test_untitled_falls_back_to_item_key(self):
        _, label = for_source({"kind": "corpus", "item_key": "K1", "url": ""}, "s")
        assert label == "K1"


def test_unknown_kind_treated_as_corpus():
    url, label = for_source({"url": "https://u.test", "title": "T"}, "s")
    assert (url, label) == ("https://u.test", "T")


class TestAsSource:
    def test_shape_matches_rag_source(self):
        from llm.links import as_source

        s = as_source(
            {
                "kind": "comment",
                "comment_id": "CMS-2026-2377-1",
                "date": "2026-08-19",
                "title": "t",
                "docket": "CMS-2026-2377",
                "item_key": "ABCD1234",
                "seq": "3",
                "section": "Some Heading",
            },
            "body " * 200,
            0.123456,
        )
        assert set(s) == {
            "attachment",
            "page",
            "id",
            "label",
            "kind",
            "url",
            "title",
            "date",
            "docket",
            "comment_id",
            "snippet",
            "score",
            "item_key",
            "p_id",
            "seq",
            "section",
        }
        assert s["label"] == "CMS-2026-2377-1" and s["kind"] == "comment"
        assert len(s["snippet"]) <= 500 and s["score"] == 0.1235
        # non-rule kind: seq/section carried through, p_id blanked
        assert s["item_key"] == "ABCD1234" and s["seq"] == "3"
        assert s["section"] == "Some Heading" and s["p_id"] == ""

    def test_rule_kind_carries_p_id_not_seq(self):
        from llm.links import as_source

        s = as_source({**TestRule.MD, "item_key": "WXYZ5678", "seq": "9"}, "text", 0.0)
        assert s["item_key"] == "WXYZ5678"
        assert s["p_id"] == "938" and s["seq"] == ""

    def test_missing_keys_default_to_empty(self):
        from llm.links import as_source

        s = as_source({"kind": "corpus"}, "text", 0.0)
        assert s["item_key"] == "" and s["p_id"] == ""
        assert s["seq"] == "" and s["section"] == ""