import io

import pytest
from openpyxl import Workbook

from app.importing.parser import ImportParseError, parse_upload


def _xlsx_bytes(rows: list[list[object]]) -> bytes:
    wb = Workbook()
    ws = wb.active
    for row in rows:
        ws.append(row)
    buffer = io.BytesIO()
    wb.save(buffer)
    return buffer.getvalue()


def test_csv_semicolon_with_bom():
    raw = "Prénom;Nom;Email\nAlex;Martin;a@b.fr\n".encode()
    table = parse_upload("benevoles.csv", raw)
    assert table.headers == ["Prénom", "Nom", "Email"]
    assert table.as_dicts() == [
        {"Prénom": "Alex", "Nom": "Martin", "Email": "a@b.fr"}
    ]


def test_csv_comma_delimiter():
    raw = b"first,last\nSam,Nguyen\n"
    table = parse_upload("x.csv", raw)
    assert table.headers == ["first", "last"]
    assert table.rows == [["Sam", "Nguyen"]]


def test_csv_blank_lines_dropped_and_short_rows_padded():
    raw = b"a;b;c\n\n1;2\n3;4;5;6\n"
    table = parse_upload("x.csv", raw)
    assert table.rows == [["1", "2", ""], ["3", "4", "5"]]


def test_xlsx_detected_by_magic_without_extension():
    data = _xlsx_bytes([["Prénom", "Nom"], ["Alex", "Martin"], [None, None]])
    table = parse_upload("upload.dat", data)
    assert table.headers == ["Prénom", "Nom"]
    assert table.rows == [["Alex", "Martin"]]


def test_xlsx_numeric_cells_become_plain_strings():
    data = _xlsx_bytes([["Nom", "Tel"], ["Martin", 601020304]])
    table = parse_upload("x.xlsx", data)
    assert table.rows == [["Martin", "601020304"]]


def test_empty_file_raises():
    with pytest.raises(ImportParseError) as err:
        parse_upload("x.csv", b"")
    assert err.value.code == "import.error.empty_file"


def test_unreadable_xlsx_raises():
    with pytest.raises(ImportParseError) as err:
        parse_upload("x.xlsx", b"not a real workbook")
    assert err.value.code == "import.error.unreadable_file"