"""Tests para compute_text_duplicates.

Importa el modulo hoja directamente (`datascience.compute_text_duplicates`)
para no depender de que el paquete reexporte la funcion en su __init__.
datasketch normalmente NO esta instalada en el venv, asi que near_dup
degrada a available=False; los tests no requieren la libreria.
"""

from datascience.compute_text_duplicates import compute_text_duplicates


EXPECTED_KEYS = {"n_docs", "n_exact_dup", "exact_dup_pct", "n_unique", "near_dup"}


def test_duplicados_exactos():
    """3 copias del mismo texto + 2 únicos: n_exact_dup=2, pct>0."""
    texts = [
        "El gato come pescado",
        "El gato come pescado",
        "el  GATO   come pescado",  # mismo tras normalizar (espacios + case)
        "Un perro ladra",
        "La luna brilla",
    ]
    result = compute_text_duplicates(texts)

    assert set(result.keys()) == EXPECTED_KEYS
    assert result["n_docs"] == 5
    # 3 copias del primer texto (2 son repeticion) + 2 textos unicos.
    assert result["n_exact_dup"] == 2
    assert result["n_unique"] == 3
    assert result["exact_dup_pct"] is not None
    assert result["exact_dup_pct"] > 0
    # 2 / 5 * 100 = 40.0
    assert abs(result["exact_dup_pct"] - 40.0) < 1e-9


def test_sin_duplicados():
    """Corpus sin repeticiones: n_exact_dup=0, n_unique==n_docs."""
    texts = [
        "primero documento distinto",
        "segundo documento distinto",
        "tercero documento distinto",
    ]
    result = compute_text_duplicates(texts)

    assert result["n_docs"] == 3
    assert result["n_exact_dup"] == 0
    assert result["n_unique"] == 3
    assert abs(result["exact_dup_pct"] - 0.0) < 1e-9


def test_vacio():
    """Corpus vacio: n_docs 0, exact_dup_pct None, no lanza."""
    result = compute_text_duplicates([])

    assert set(result.keys()) == EXPECTED_KEYS
    assert result["n_docs"] == 0
    assert result["n_exact_dup"] == 0
    assert result["exact_dup_pct"] is None
    assert result["n_unique"] == 0
    assert result["near_dup"]["n_near_dup_docs"] == 0


def test_near_dup_degrada():
    """near_dup expone 'available' (bool) y no lanza aunque falte datasketch."""
    texts = ["uno dos tres cuatro", "uno dos tres cuatro cinco", "algo distinto"]
    result = compute_text_duplicates(texts)

    near = result["near_dup"]
    assert "available" in near
    assert isinstance(near["available"], bool)
    assert "n_near_dup_docs" in near
    assert isinstance(near["n_near_dup_docs"], int)
    # Tambien tolera None y entradas no-str sin lanzar.
    mixed = compute_text_duplicates(["hola", None, 123, "hola"])
    assert mixed["n_docs"] == 2
    assert mixed["n_exact_dup"] == 1