legal-ai/mcp-server/tests/test_court_citation.py

"""Unit tests for the X13 court-citation classifier."""

from __future__ import annotations

from legal_mcp.services.court_citation import (
    case_number_from_citation,
    citation_dedup_key,
    classify,
    normalize_case_number,
)


def test_dedup_key_is_designator_aware():
    """#143 — same docket across DIFFERENT courts must NOT collapse to one key
    (deduping on the bare number would wrongly merge distinct precedents)."""
    bagatz = citation_dedup_key('בג"ץ 389/87')
    civil = citation_dedup_key('ע"א 389/87')
    assert bagatz and civil and bagatz != civil, (bagatz, civil)
    # ...while gershayim/format variants of the SAME court+docket DO collapse.
    assert citation_dedup_key('עע"מ 9057/09') == citation_dedup_key("עע״מ 9057-09")
    # committee proceeding-type is part of the key (ערר ≠ בל"מ).
    assert citation_dedup_key("ערר 1192/18") != citation_dedup_key('בל"מ 1192/18')


def test_dedup_key_empty_without_number():
    assert citation_dedup_key("") == ""
    assert citation_dedup_key("פסק דין בלי מספר") == ""


def test_admin_filed_format_the_example():
    """The plan's example: עת"מ 46111-12-22 → admin, parsed into (46111,12,22)."""
    c = classify('עת"מ 46111-12-22 יכין-אפק בע"מ נ\' הוועדה המחוזית')
    assert c.tier == "admin"
    assert c.court_prefix in ('עת"מ', "עת״מ")
    assert c.case_number_raw == "46111-12-22"
    assert c.case_number_norm == "46111-12-22"
    assert (c.file_number, c.month, c.year) == ("46111", "12", "22")
    assert c.fetchable is True


def test_bare_filed_number_defaults_admin():
    c = classify("46111-12-22")
    assert c.tier == "admin"
    assert (c.file_number, c.month, c.year) == ("46111", "12", "22")


def test_supreme_prefixes():
    for cit, pref in [
        ('עע"מ 1234/22', "supreme"),
        ('בג"ץ 5678/21', "supreme"),
        ('ע"א 999/20', "supreme"),
        ('רע"א 4/19', "supreme"),
        ('בר"מ 8126/24', "supreme"),
    ]:
        c = classify(cit)
        assert c.tier == pref, f"{cit} -> {c.tier}"
        assert c.fetchable is True


def test_appeals_committee_is_skip():
    """ערר / בל"מ must never be auto-fetched (needs Nevo) — INV-CF6."""
    for cit in ['ערר 1110/20', 'בל"מ 8048/24', "ערר 1015-01-24 ירושלים שקופה"]:
        c = classify(cit)
        assert c.tier == "skip", f"{cit} -> {c.tier}"
        assert c.fetchable is False


def test_skip_wins_over_court_match():
    """An 'ערר' citation that also contains court-like digits stays skip."""
    c = classify("ראה החלטתי בערר 1041/24 ובהמשך")
    assert c.tier == "skip"


def test_admin_amn_prefix():
    c = classify('עמ"נ 12345-06-23')
    assert c.tier == "admin"
    assert (c.file_number, c.month, c.year) == ("12345", "06", "23")


def test_two_group_serial_has_no_filed_triple():
    """Supreme serial 1234/22 normalizes but yields no (file,month,year)."""
    c = classify('עע"מ 1234/22')
    assert c.case_number_norm == "1234-22"
    assert c.file_number is None


def test_implausible_month_not_parsed_as_filed():
    # 1234-22-05 has month=22 → not a valid filed triple.
    assert classify("1234-22-05").tier in ("unknown", "admin")
    c = classify("1234-22-05")
    if c.tier == "admin":
        assert c.month is None


def test_empty_and_garbage():
    assert classify("").tier == "unknown"
    assert classify("שלום עולם בלי ציטוט").tier == "unknown"


def test_normalize_case_number():
    assert normalize_case_number('עת"מ 46111/12/22') == "46111-12-22"
    assert normalize_case_number("1110/20") == "1110-20"


def test_case_number_from_citation_strips_party_names():
    """#137 — a full ועדת-ערר citation yields ONLY the number, never the
    display string with party names (INV-ID2). This is the exact precedent
    1bf0bae0 that planted ``85074-04-25) רפאל לוי …`` into case_number."""
    cit = 'ערר (ת"א 85074-04-25) רפאל לוי ואח\' נ\' הוועדה המקומית - חולון'
    assert case_number_from_citation(cit) == "85074-04-25"


def test_case_number_from_citation_various_forms():
    assert case_number_from_citation('ערר (ת"א 1198-12-25) זאטוס') == "1198-12-25"
    assert case_number_from_citation("85074-04-25") == "85074-04-25"
    assert case_number_from_citation('בל"מ 85074-09-24') == "85074-09-24"
    assert case_number_from_citation("ערר 8137/24") == "8137-24"


def test_case_number_from_citation_empty_when_unparseable():
    """No number → '' so the caller demands a manual number, never the raw
    citation (the #137 fallback that caused the bug)."""
    assert case_number_from_citation("") == ""
    assert case_number_from_citation("פסק דין בלי מספר") == ""


def test_supreme_with_net_format_triple():
    """A Supreme prefix carrying a נט-format number exposes the triple so the
    orchestrator can route it to Tier-1 (נט המשפט serves Supreme too)."""
    c = classify('בר"מ 72182-06-25 הימנותא נ\' הוועדה המקומית')
    assert c.tier == "supreme"
    assert (c.file_number, c.month, c.year) == ("72182", "06", "25")
    # serial-format Supreme has no triple → stays Tier-0-only
    s = classify('עע"מ 5886/24')
    assert s.tier == "supreme" and s.file_number is None