"""Tests for src/cmos/runtime_validator.py.

Runtime validator runs at format time on a single candidate string with no
exemplar context. It checks type-independent structural sanity rules so the
formatter can self-retry when GPT-5's reasoning drift produces a malformed
entry. It is deliberately weaker than the scoring linter (which has access
to canonical fields and source type) but it catches the most common
nondeterministic failures: missing terminal period, stray Ibid., dropped
italic markers, unbalanced quotes/asterisks.
"""

from cmos.runtime_validator import validate


def test_clean_book_entry_passes():
    candidate = "Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020."
    result = validate(candidate)
    assert result.passed is True
    assert result.failures == []


def test_clean_journal_entry_passes():
    candidate = (
        'Kwon, Hyeyoung. "Inclusion Work: Children of Immigrants Claiming Membership in Everyday Life." '
        "*American Journal of Sociology* 127, no. 6 (2022): 1818–59. "
        "https://doi.org/10.1086/720277."
    )
    assert validate(candidate).passed


def test_missing_terminal_period_fails():
    result = validate("Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020")
    assert result.passed is False
    assert any("period" in f.lower() for f in result.failures)


def test_ibid_fails():
    result = validate("Ibid., 42.")
    assert result.passed is False
    assert any("ibid" in f.lower() for f in result.failures)


def test_missing_italics_anywhere_fails():
    # The "New Yorker" magazine regression we saw in iter 7 variance: italic
    # markers around the magazine name disappeared. This rule should catch
    # that — almost every CMOS bibliography entry italicizes something.
    candidate = 'Mead, Rebecca. "Terms of Aggrievement." New Yorker, December 18, 2023.'
    result = validate(candidate)
    assert result.passed is False
    assert any("italic" in f.lower() for f in result.failures)


# --- Shortened-form note carve-out (chunk 3 fix #3, Option D) -------------


def test_shortened_form_author_only_passes_without_italics():
    """CMOS shortened note form for an author-only reference (no page,
    no title) is just the author's last name with a period: 'Ettarh.',
    'Murch.', 'O'Mara.'. These contain no italics by definition.
    Without a carve-out, the validator's "must have italics" rule
    rejects them and the formatter's retry loop fires its full budget
    on valid output. Surfaced by the Anti-Communist Formations of LIS
    real-draft run; ~30 of 107 notes were correct shortened-forms
    that wasted ~60 API calls retrying.

    The carve-out: if a candidate has no italics AND looks like a
    shortened-form note (short, name-token shape, optional page,
    terminal period), the missing-italics check is skipped.
    """
    for candidate in ["Ettarh.", "Murch.", "O'Mara.", "Burden-Stelly."]:
        result = validate(candidate)
        assert result.passed is True, (
            f"shortened-form author-only note {candidate!r} should pass "
            f"validation; got failures {result.failures}"
        )


def test_shortened_form_author_plus_page_passes_without_italics():
    """The other common CMOS shortened form is author last name + page:
    'Rosen, 7.', 'Mitchell, 197.', 'CBS, 47.'. Same carve-out applies."""
    for candidate in [
        "Rosen, 7.",
        "Mitchell, 197.",
        "CBS, 47.",
        "Seybold, 282.",
        "Lawrence Powell, 45.",  # multi-word name
        "Mitchell, 137-39.",  # page range with hyphen
    ]:
        result = validate(candidate)
        assert result.passed is True, (
            f"shortened-form note {candidate!r} should pass validation; "
            f"got failures {result.failures}"
        )


def test_long_no_italic_output_still_fails():
    """The carve-out must NOT be a free pass for any short string.
    A long output with no italics is still likely a malformed
    full-form citation (model dropped the italic title), and the
    retry loop should still fire on it.
    """
    candidate = (
        "Steve Batterson, The Prosecution of Professor Chandler Davis: "
        "McCarthyism, Communism, and the Myth of Academic Freedom (NYU Press, 2023)."
    )
    result = validate(candidate)
    assert result.passed is False
    assert any("italic" in f.lower() for f in result.failures)


def test_short_but_unstructured_no_italic_output_still_fails():
    """A short but non-name-shaped string (e.g., a stray sentence
    fragment with no name structure) should still fail. The carve-out
    is NOT just "short and ends with period" — it requires the
    candidate to look like a shortened-form note specifically.
    """
    candidate = "this is some prose without italics."
    result = validate(candidate)
    assert result.passed is False, (
        "lowercase prose fragment must not be accepted as a shortened-form "
        "note; the carve-out should require name-token shape"
    )


def test_unbalanced_italic_markers_fails():
    candidate = "Yu, Charles. *Interior Chinatown. Pantheon Books, 2020."
    result = validate(candidate)
    assert result.passed is False
    assert any("italic" in f.lower() or "*" in f for f in result.failures)


def test_unbalanced_double_quotes_fails():
    candidate = 'Mead, Rebecca. "Terms of Aggrievement. *New Yorker*, December 18, 2023.'
    result = validate(candidate)
    assert result.passed is False
    assert any("quote" in f.lower() for f in result.failures)


def test_passed_property_is_negation_of_failures():
    # Sanity: passed should be True iff there are no failures.
    result = validate("Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020.")
    assert result.passed == (result.failures == [])