"""§6.5.1 file-level codec — parse, caps, required columns (PUC-5a fixtures)."""
import pytest

from app.domains.products import FileRejected
from app.domains.products.codec import parse_csv


def _csv(*lines: str) -> bytes:
    return ("\n".join(lines) + "\n").encode()


GOOD = _csv(
    "Handle,Title,Variant Price,Bogus Column",
    "moon-mug,Moon Mug,18.00,x",
    "star-tee,Star Tee,24.00,y",
)


def test_parses_header_rows_and_unknown_columns():
    parsed = parse_csv(GOOD)
    assert parsed.dialect == "canonical"
    assert parsed.unknown_columns == ["Bogus Column"]
    assert [r.line_number for r in parsed.rows] == [2, 3]
    assert parsed.rows[0].cells["Handle"] == "moon-mug"
    assert parsed.rows[0].cells["Variant Price"] == "18.00"
    assert "Bogus Column" not in parsed.rows[0].cells


def test_bom_tolerated():
    parsed = parse_csv(b"\xef\xbb\xbf" + GOOD)
    assert parsed.rows[0].cells["Handle"] == "moon-mug"


def test_quoted_cells_rfc4180():
    parsed = parse_csv(_csv("Handle,Title,Tags", 'mug,"The ""Best"" Mug","a, b"'))
    assert parsed.rows[0].cells["Title"] == 'The "Best" Mug'
    assert parsed.rows[0].cells["Tags"] == "a, b"


def test_empty_rows_skipped_short_rows_padded():
    parsed = parse_csv(_csv("Handle,Title,Vendor", "mug,Mug", "", ",,", "tee,Tee,Acme"))
    assert [r.cells["Handle"] for r in parsed.rows] == ["mug", "tee"]
    assert parsed.rows[0].cells["Vendor"] == ""


@pytest.mark.parametrize(
    "data,code",
    [
        (b"\xff\xfe\x00garbage\x00", "not_csv"),
        (b"", "not_csv"),
        (_csv("Title,Vendor", "Mug,Acme"), "missing_required_column"),
        (_csv("Handle,Vendor", "mug,Acme"), "missing_required_column"),
        (
            _csv("Handle,Title", *(f"h{i},T{i}" for i in range(5001))),
            "too_many_rows",
        ),
        (b"Handle,Title\n" + b"x" * (10 * 1024 * 1024), "file_too_large"),
    ],
)
def test_file_level_rejections(data, code):
    with pytest.raises(FileRejected) as exc:
        parse_csv(data)
    assert exc.value.code == code


def test_missing_column_message_names_the_column():
    with pytest.raises(FileRejected) as exc:
        parse_csv(_csv("Handle,Vendor", "mug,Acme"))
    assert "'Title'" in exc.value.message


def test_parse_detects_and_maps_shopify():
    data = (
        "Handle,Title,Body (HTML),Cost per item,Variant Price,Variant Grams,Type,Gift Card\n"
        "mug,Moon Mug,<p>Grey</p>,9.50,18.00,300,Drinkware,false\n"
    ).encode("utf-8")
    parsed = parse_csv(data)
    assert parsed.dialect == "shopify"
    cells = parsed.rows[0].cells
    assert cells["Description"] == "<p>Grey</p>"
    assert cells["Variant Cost"] == "9.50"
    assert cells["Variant Weight"] == "300"
    assert cells["Variant Weight Unit"] == "g"  # synthesized
    # Type (free-text) and Gift Card warned, never mapped:
    assert "Type" in parsed.unknown_columns
    assert "Gift Card" in parsed.unknown_columns
    assert "product_type" not in str(cells)  # Type never reached canonical


def test_parse_canonical_unchanged():
    data = b"Handle,Title,Description,Variant Price\nmug,Moon Mug,Grey,18.00\n"
    parsed = parse_csv(data)
    assert parsed.dialect == "canonical"
    assert parsed.rows[0].cells["Description"] == "Grey"
    assert parsed.unknown_columns == []