"""Tests para extract_null_mask.

No usa DuckDB real: inyecta un query_fn FAKE (closure) que devuelve filas
predefinidas (simulando el SELECT de bits 0/1) y, opcionalmente, captura el SQL
recibido para verificar la query generada (CASE WHEN ... IS NULL + LIMIT). Asi el
test es autocontenido y no depende de ningun backend.
"""

import os
import sys

sys.path.insert(0, os.path.dirname(__file__))

from extract_null_mask import extract_null_mask


def _fake_query(rows, captured=None, status="ok", error=None):
    """Crea un query_fn FAKE.

    `captured` (lista opcional) recibe el SQL ejecutado para poder inspeccionarlo.
    `status`/`error` permiten simular un fallo del backend.
    """

    def _q(sql):
        if captured is not None:
            captured.append(sql)
        if status != "ok":
            return {"status": "error", "error": error or "boom"}
        return {"status": "ok", "rows": rows}

    return _q


def test_golden_mask_alineada():
    """Golden: mask 0/1 por columna alineada por fila, n correcto, status ok."""
    # Cada fila simula el SELECT (CASE WHEN col IS NULL THEN 1 ELSE 0 END) AS col.
    rows = [
        {"email": 0, "telefono": 1, "edad": 0},
        {"email": 0, "telefono": 0, "edad": 1},
        {"email": 1, "telefono": 1, "edad": 0},
    ]
    res = extract_null_mask(_fake_query(rows), "clientes", ["email", "telefono", "edad"])
    assert res["status"] == "ok"
    assert res["table"] == "clientes"
    assert res["columns"] == ["email", "telefono", "edad"]
    assert res["n"] == 3
    assert res["mask"]["email"] == [0, 0, 1]
    assert res["mask"]["telefono"] == [1, 0, 1]
    assert res["mask"]["edad"] == [0, 1, 0]
    # Todas las listas con la misma longitud.
    assert all(len(v) == res["n"] for v in res["mask"].values())


def test_celda_none_cuenta_como_falta():
    """Una celda None se cuenta defensivamente como 1 (falta)."""
    rows = [
        {"email": 0, "telefono": None},
        {"email": None, "telefono": 1},
        {"email": 1, "telefono": 0},
    ]
    res = extract_null_mask(_fake_query(rows), "clientes", ["email", "telefono"])
    assert res["status"] == "ok"
    assert res["mask"]["email"] == [0, 1, 1]
    assert res["mask"]["telefono"] == [1, 1, 0]
    assert res["n"] == 3


def test_columns_vacia_status_error():
    """columns vacia -> status error con columns/mask/n vacios."""
    res = extract_null_mask(_fake_query([]), "clientes", [])
    assert res["status"] == "error"
    assert "columns" in res["error"]
    assert res["table"] == "clientes"
    assert res["columns"] == []
    assert res["mask"] == {}
    assert res["n"] == 0


def test_query_fn_status_error_propaga():
    """query_fn que devuelve status != ok -> se propaga como error, mask {}."""
    res = extract_null_mask(
        _fake_query([], status="error", error="db locked"),
        "clientes",
        ["email"],
    )
    assert res["status"] == "error"
    assert "db locked" in res["error"]
    assert res["mask"] == {}
    assert res["n"] == 0


def test_query_fn_none_da_error_sin_reventar():
    """query_fn None -> error degradado, sin excepcion."""
    res = extract_null_mask(None, "clientes", ["email"])
    assert res["status"] == "error"
    assert res["columns"] == []
    assert res["mask"] == {}
    assert res["n"] == 0


def test_sql_contiene_case_y_limit():
    """La query genera un CASE WHEN IS NULL por columna escapada + LIMIT sobre la tabla."""
    captured = []
    rows = [{"email": 0}]
    extract_null_mask(
        _fake_query(rows, captured),
        "clientes_tbl",
        ["email"],
        max_rows=123,
    )
    assert len(captured) == 1
    sql = captured[0]
    assert 'CASE WHEN "email" IS NULL THEN 1 ELSE 0 END' in sql
    assert 'AS "email"' in sql
    assert 'FROM "clientes_tbl"' in sql
    assert "LIMIT 123" in sql