payslip-ingest/tests/test_meta_uk_parser.py

from datetime import date
from decimal import Decimal
from pathlib import Path

import pytest

from payslip_ingest.parsers.meta_uk import ParserError, parse_meta_uk

FIXTURES = Path(__file__).parent / "fixtures"


def _load(name: str) -> str:
    return (FIXTURES / name).read_text(encoding="utf-8")


def test_parses_variant_b_standard_month() -> None:
    """Feb 2026 — variant B, RSU vesting, no bonus, salary-sacrifice pension."""
    result = parse_meta_uk(_load("meta_uk_2026_02.txt"))

    assert result.pay_date == date(2026, 2, 27)
    assert result.pay_period_start == date(2026, 2, 1)
    assert result.pay_period_end == date(2026, 2, 27)
    assert result.employer == "Facebook UK Limited"
    assert result.currency == "GBP"

    assert result.salary == Decimal("10003.33")
    assert result.bonus == Decimal("0")
    assert result.pension_sacrifice == Decimal("600.20")
    # rsu_vest = RSU Tax Offset + RSU Excs Refund
    assert result.rsu_vest == Decimal("30479.76")
    assert result.rsu_offset == Decimal("0")

    assert result.gross_pay == Decimal("39882.89")
    assert result.income_tax == Decimal("31311.90")
    assert result.national_insurance == Decimal("1602.89")
    assert result.pension_employee == Decimal("0")
    assert result.student_loan == Decimal("0")
    assert result.net_pay == Decimal("6968.10")

    assert result.taxable_pay == Decimal("72096.92")
    assert result.ytd_tax_paid == Decimal("155626.37")
    assert result.ytd_taxable_pay == Decimal("373601.64")
    assert result.ytd_gross == Decimal("232630.34")


def test_parses_variant_b_with_bonus_and_rsu() -> None:
    """March 2025 — variant B, bonus month, RSU vesting, multiple other deductions."""
    result = parse_meta_uk(_load("meta_uk_2025_03.txt"))

    assert result.pay_date == date(2025, 3, 27)
    assert result.salary == Decimal("10000.00")
    assert result.bonus == Decimal("25000.00")
    assert result.pension_sacrifice == Decimal("1200.00")
    assert result.rsu_vest == Decimal("20000.00")

    assert result.gross_pay == Decimal("53720.00")
    assert result.income_tax == Decimal("45210.44")
    assert result.national_insurance == Decimal("2750.12")
    assert result.student_loan == Decimal("850.00")
    assert result.net_pay == Decimal("4753.69")

    # Private Medical comes from the Deductions column. Cycle To Work is a
    # negative Payments line — already subtracted from Total Payment, so it
    # does NOT belong in other_deductions (that would double-count).
    assert "Private Medical" in result.other_deductions
    assert result.other_deductions["Private Medical"] == Decimal("155.75")
    assert "Cycle To Work" not in result.other_deductions


def test_parses_variant_b_bonus_sacrificed() -> None:
    """March 2024 — variant B, full bonus sacrificed into pension, bonus line = 0."""
    result = parse_meta_uk(_load("meta_uk_2024_03_bonus_sacrificed.txt"))

    assert result.pay_date == date(2024, 3, 27)
    assert result.salary == Decimal("9500.00")
    # Bonus line present but zero — parser should surface this so the dashboard
    # can highlight the "bonus sacrificed" dip.
    assert result.bonus == Decimal("0")
    # Big pension sacrifice dwarfs the salary — this is the signal we care about.
    assert result.pension_sacrifice == Decimal("6200.00")
    assert result.rsu_vest == Decimal("0")

    assert result.gross_pay == Decimal("3300.00")
    assert result.net_pay == Decimal("2130.00")


def test_parses_variant_a_pre_2022() -> None:
    """July 2019 — variant A, pre-RSU, single-column layout.

    Variant A lists AE Pension EE as a positive deduction (pre-sacrifice gross),
    so it maps to `pension_employee` for the standard validation formula to hold.
    Variant B lists it as a negative payment (post-sacrifice gross) and maps to
    `pension_sacrifice` instead. Both represent money going into the pension.
    """
    result = parse_meta_uk(_load("meta_uk_2019_07.txt"))

    assert result.pay_date == date(2019, 7, 31)
    assert result.employer == "Facebook UK Limited"
    assert result.salary == Decimal("7083.33")
    assert result.bonus == Decimal("0")
    assert result.rsu_vest == Decimal("0")
    assert result.pension_sacrifice == Decimal("0")
    assert result.pension_employee == Decimal("500.00")

    assert result.gross_pay == Decimal("7083.33")
    assert result.income_tax == Decimal("1480.00")
    assert result.national_insurance == Decimal("564.73")
    assert result.student_loan == Decimal("120.00")
    assert result.net_pay == Decimal("4418.60")

    # Variant A carries a "Taxable Pay" line inline
    assert result.taxable_pay == Decimal("6583.33")


def test_raises_on_non_meta_payslip() -> None:
    with pytest.raises(ParserError):
        parse_meta_uk("This is not a Meta payslip\nRandom text\n")


def test_raises_on_empty_text() -> None:
    with pytest.raises(ParserError):
        parse_meta_uk("")


def test_raises_when_pay_date_missing() -> None:
    broken = "Facebook UK Limited\nPayslip\nSalary                     1000.00\nNet Pay: 800.00\n"
    with pytest.raises(ParserError):
        parse_meta_uk(broken)


@pytest.mark.parametrize("fixture_name", [
    "meta_uk_2026_02.txt",
    "meta_uk_2025_03.txt",
    "meta_uk_2024_03_bonus_sacrificed.txt",
    "meta_uk_2019_07.txt",
])
def test_all_fixtures_validate_totals(fixture_name: str) -> None:
    """Every fixture must satisfy gross - deductions ≈ net within 2p."""
    from payslip_ingest.schema import validate_totals

    result = parse_meta_uk(_load(fixture_name))
    assert validate_totals(result), (
        f"{fixture_name}: gross={result.gross_pay} "
        f"tax={result.income_tax} nic={result.national_insurance} "
        f"student={result.student_loan} other={result.other_deductions} "
        f"net={result.net_pay}")