arborist/tests/test_warrant_authorship.py

"""Tests for the authorship warrant ladder (#000026 Phase 3)."""

from __future__ import annotations

from arborist.qa.warrant_authorship import (
    NO_AUTHORSHIP_SIGNAL,
    TIER_RANK,
    diagnose_authorship_warrant,
)


# ---------- Question gating ------------------------------------------------


def test_non_authorship_question_returns_no_signal():
    """Sidecar should stay quiet on irrelevant questions."""
    out = diagnose_authorship_warrant(
        question_text="what is the capital of france?",
        answer_text="Paris.",
        cited_evidence_spans=["© 2024 Wikipedia Foundation"],
    )
    assert out["tier"] == NO_AUTHORSHIP_SIGNAL
    assert out["tier_rank"] == 99


def test_no_evidence_no_question_returns_no_signal():
    out = diagnose_authorship_warrant()
    assert out["tier"] == NO_AUTHORSHIP_SIGNAL


def test_no_evidence_with_authorship_question_returns_no_signal():
    """Authorship question but zero cited evidence — sidecar stays
    quiet rather than reporting tier-6 secondary on no evidence."""
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="Russell Ballestrini.",
    )
    assert out["tier"] == NO_AUTHORSHIP_SIGNAL


# ---------- Tier 1 — package metadata --------------------------------------


def test_tier1_python_pyproject_author():
    out = diagnose_authorship_warrant(
        question_text="who wrote arborist?",
        answer_text="Russell Ballestrini wrote arborist.",
        cited_evidence_spans=[
            'authors = [\n  { name = "Russell Ballestrini" },\n]'
        ],
    )
    assert out["tier"] == "AUTHOR_PACKAGE_METADATA"
    assert out["tier_rank"] == 1
    assert "Russell Ballestrini" in out["candidate_names"]


def test_tier1_python_setup_py_author():
    out = diagnose_authorship_warrant(
        question_text="who is the author of virt-back?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=['author="Russell Ballestrini"'],
    )
    assert out["tier"] == "AUTHOR_PACKAGE_METADATA"


def test_tier1_package_json_author():
    out = diagnose_authorship_warrant(
        question_text="who created this library?",
        answer_text="Foo Bar.",
        cited_evidence_spans=['{"name":"my-pkg","author":"Foo Bar"}'],
    )
    assert out["tier"] == "AUTHOR_PACKAGE_METADATA"


# ---------- Tier 2 — repository owner --------------------------------------


def test_tier2_github_uri_owner():
    out = diagnose_authorship_warrant(
        question_text="who maintains this?",
        answer_text="The repository is owned by russellballestrini.",
        cited_source_uris=["https://github.com/russellballestrini/virt-back"],
        cited_evidence_spans=["A README about the project."],
    )
    assert out["tier"] == "AUTHOR_REPOSITORY_OWNER"
    assert "russellballestrini" in out["candidate_names"]


def test_tier2_gitlab_uri_owner():
    out = diagnose_authorship_warrant(
        question_text="who owns this project?",
        answer_text="The team-arborist group.",
        cited_source_uris=[
            "https://gitlab.com/team-arborist/some-project",
        ],
        cited_evidence_spans=["x"],
    )
    assert out["tier"] == "AUTHOR_REPOSITORY_OWNER"


# ---------- Tier 3 — page byline -------------------------------------------


def test_tier3_byline_prose_by_pattern():
    out = diagnose_authorship_warrant(
        question_text="who wrote this article?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=["By Russell Ballestrini, posted 2024-01-01."],
    )
    assert out["tier"] == "AUTHOR_PAGE_BYLINE"


def test_tier3_byline_meta_html():
    out = diagnose_authorship_warrant(
        question_text="who is the author of this page?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=[
            '<meta name="author" content="Russell Ballestrini">'
        ],
    )
    assert out["tier"] == "AUTHOR_PAGE_BYLINE"


# ---------- Tier 4 — primary page title ------------------------------------


def test_tier4_primary_page_title_match():
    """Site host token appears in the cited title AND the answer
    references the same entity. The cited evidence is the entity's
    own primary page."""
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="russellballestrini wrote virt-back.",
        cited_source_uris=[
            "https://russellballestrini.net/virt-back-restoring-from-backups/",
        ],
        cited_source_titles=["virt-back: restoring from backups – Russell Ballestrini"],
        cited_evidence_spans=["A blog post about virt-back."],
    )
    # Should fire at tier 4 absent stronger signals (no package
    # metadata, no repo URL, no byline, no copyright).
    assert out["tier"] == "AUTHOR_PRIMARY_PAGE_TITLE"


def test_tier4_third_party_host_does_not_fire():
    """Wikipedia is a third-party indexer; primary-page heuristic
    must not fire even if tokens overlap."""
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="russell wrote virt-back.",
        cited_source_uris=[
            "https://en.wikipedia.org/wiki/virt-back-russell"
        ],
        cited_source_titles=["virt-back russell"],
        cited_evidence_spans=["x"],
    )
    # With NO other signals firing, falls through to secondary.
    assert out["tier"] == "AUTHOR_SECONDARY_SOURCE"


# ---------- Tier 5 — copyright footer --------------------------------------


def test_tier5_copyright_footer_with_year():
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="Russell Ballestrini wrote virt-back.",
        cited_evidence_spans=["© 2024 Russell Ballestrini"],
    )
    assert out["tier"] == "AUTHOR_COPYRIGHT_FOOTER"


def test_tier5_copyright_footer_no_year():
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=["© Russell Ballestrini"],
    )
    assert out["tier"] == "AUTHOR_COPYRIGHT_FOOTER"


def test_tier5_copyright_word_form():
    out = diagnose_authorship_warrant(
        question_text="who created this site?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=["Copyright 2024 Russell Ballestrini. All rights reserved."],
    )
    assert out["tier"] == "AUTHOR_COPYRIGHT_FOOTER"


# ---------- Tier 6 — secondary source --------------------------------------


def test_tier6_third_party_evidence_no_authorship_markers():
    """Question is authorship; cited evidence has none of the direct
    markers — falls through to secondary."""
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="Russell Ballestrini, according to the documentation.",
        cited_evidence_spans=[
            "virt-back is a tool for backing up libvirt VMs."
        ],
    )
    assert out["tier"] == "AUTHOR_SECONDARY_SOURCE"
    assert out["tier_rank"] == TIER_RANK["AUTHOR_SECONDARY_SOURCE"]


# ---------- Tier ordering: strongest wins ----------------------------------


def test_strongest_tier_wins_when_multiple_fire():
    """Both copyright AND package-metadata fire — the package-metadata
    signal is strictly stronger (tier 1 < tier 5)."""
    out = diagnose_authorship_warrant(
        question_text="who wrote virt-back?",
        answer_text="Russell Ballestrini.",
        cited_evidence_spans=[
            "© Russell Ballestrini",
            'author = "Russell Ballestrini"',
        ],
    )
    assert out["tier"] == "AUTHOR_PACKAGE_METADATA"
    # But signals list captures BOTH for the operator.
    tiers_seen = {s["tier"] for s in out["signals"]}
    assert "AUTHOR_PACKAGE_METADATA" in tiers_seen
    assert "AUTHOR_COPYRIGHT_FOOTER" in tiers_seen


# ---------- Sidecar contract -----------------------------------------------


def test_returns_dict_always():
    """Sidecar contract: never raises, always returns a dict."""
    out = diagnose_authorship_warrant(
        question_text=None,
        answer_text="",
        cited_evidence_spans=None,
        cited_source_uris=None,
        cited_source_titles=None,
    )
    assert isinstance(out, dict)
    assert "tier" in out
    assert "tier_rank" in out


def test_does_not_raise_on_garbage_input():
    out = diagnose_authorship_warrant(
        question_text="who wrote x?",
        answer_text="\x00\x01" * 100,
        cited_evidence_spans=["", None, "<<<>>>"],  # type: ignore
    )
    assert out["tier"] in (
        "NO_AUTHORSHIP_SIGNAL", "AUTHOR_SECONDARY_SOURCE",
        "AUTHOR_PACKAGE_METADATA", "AUTHOR_REPOSITORY_OWNER",
        "AUTHOR_PAGE_BYLINE", "AUTHOR_PRIMARY_PAGE_TITLE",
        "AUTHOR_COPYRIGHT_FOOTER",
    )


def test_noise_capitalized_words_not_classified_as_names():
    """`Author` / `Copyright` / etc. shouldn't slip through as names."""
    out = diagnose_authorship_warrant(
        question_text="who wrote x?",
        answer_text="x",
        cited_evidence_spans=[
            "Copyright Reserved",  # should NOT classify "Reserved" as name
            "Author All Rights",   # garbage shape
        ],
    )
    # Even if regex matches, _looks_like_noise filters; tier may fall
    # to secondary or no-signal.
    assert "Reserved" not in out.get("candidate_names", [])
    assert "All" not in out.get("candidate_names", [])


# ---------- Render-tail integration (#000026 Phase 3 wiring) ---------------


def test_render_tail_emits_warrant_when_authorship_set():
    """`_render_warrant_tail` adds ` · warrant: <readable-tier>` when
    result['authorship'] is populated with a non-quiet tier."""
    from arborist.cli import _render_warrant_tail
    result = {
        "violations": [],
        "authorship": {
            "tier": "AUTHOR_COPYRIGHT_FOOTER",
            "tier_rank": 5,
            "signals": [],
            "candidate_names": ["Russell Ballestrini"],
        },
    }
    tail = _render_warrant_tail(result)
    assert "warrant: copyright-footer" in tail


def test_render_tail_silent_for_no_authorship_signal():
    """Sidecar's quiet verdict (NO_AUTHORSHIP_SIGNAL) → no tail."""
    from arborist.cli import _render_warrant_tail
    result = {
        "violations": [],
        "authorship": {
            "tier": "NO_AUTHORSHIP_SIGNAL",
            "tier_rank": 99,
        },
    }
    tail = _render_warrant_tail(result)
    assert "warrant" not in tail


def test_render_tail_silent_when_no_authorship_field():
    """Backward-compat: results without an `authorship` key render
    unchanged (the tail-builder must not raise / must not emit)."""
    from arborist.cli import _render_warrant_tail
    result = {"violations": []}
    tail = _render_warrant_tail(result)
    assert "warrant" not in tail


def test_render_tail_warrant_uses_readable_token_per_tier():
    """Each tier renders with hyphen-lowercase and AUTHOR_ stripped."""
    from arborist.cli import _render_warrant_tail
    expectations = {
        "AUTHOR_PACKAGE_METADATA": "warrant: package-metadata",
        "AUTHOR_REPOSITORY_OWNER": "warrant: repository-owner",
        "AUTHOR_PAGE_BYLINE": "warrant: page-byline",
        "AUTHOR_PRIMARY_PAGE_TITLE": "warrant: primary-page-title",
        "AUTHOR_COPYRIGHT_FOOTER": "warrant: copyright-footer",
        "AUTHOR_SECONDARY_SOURCE": "warrant: secondary-source",
    }
    for tier, expected in expectations.items():
        tail = _render_warrant_tail({
            "violations": [],
            "authorship": {"tier": tier, "tier_rank": 1},
        })
        assert expected in tail, f"{tier} → tail={tail!r}"