"""Unit tests for db._canonical_case_number — #137 / INV-ID2 / X1 §1.

The write-time canonicalizer must extract the case-number TOKEN only and drop
any trailing display text (party names) that a mis-passed full citation glued
onto the number. A clean number is returned unchanged; no month is invented.
"""

from __future__ import annotations

from legal_mcp.services.db import _canonical_case_number as canon


def test_clean_numbers_unchanged():
    assert canon("8137-24") == "8137-24"
    assert canon("85074-09-24") == "85074-09-24"
    assert canon("8126-03-25") == "8126-03-25"
    # Legacy two-part number — month is NOT invented (X1 §1).
    assert canon("8126-25") == "8126-25"


def test_prefix_stripped():
    assert canon("ערר 8137/24") == "8137-24"
    assert canon('בל"מ 85074-09-24') == "85074-09-24"


def test_trailing_party_names_dropped():
    # The #137 symptom: ingest left "85074-04-25) רפאל לוי …" in the identifier.
    assert canon("85074-04-25) רפאל לוי ואח' נ' הוועדה המקומית - חולון") == "85074-04-25"
    assert canon("8137-24 פלוני נ' אלמוני") == "8137-24"


def test_empty_and_no_digit():
    assert canon("") == ""
    assert canon("ללא מספר") == ""