"""Tests para compute_vocabulary_stats."""

import os
import sys

sys.path.insert(
    0, os.path.join(os.path.dirname(__file__), "..", "..", "functions")
)

from datascience.compute_vocabulary_stats import compute_vocabulary_stats


def test_basico():
    # Corpus con repeticiones y hapax. Stopwords desactivadas para controlar
    # exactamente que tokens entran.
    texts = ["gato gato perro", "perro perro raton", "elefante"]
    r = compute_vocabulary_stats(texts, top_k=10, remove_stopwords=False)

    # n_types < n_tokens cuando hay repeticiones.
    assert r["n_types"] < r["n_tokens"]
    assert r["n_tokens"] == 7
    assert r["n_types"] == 4  # gato, perro, raton, elefante

    # ttr en (0, 1].
    assert 0 < r["ttr"] <= 1
    assert r["ttr"] == round(4 / 7, 4)

    # top_terms ordenado por count descendente.
    counts = [t["count"] for t in r["top_terms"]]
    assert counts == sorted(counts, reverse=True)
    assert r["top_terms"][0]["term"] == "perro"
    assert r["top_terms"][0]["count"] == 3

    # hapax: raton y elefante aparecen exactamente una vez.
    assert r["n_hapax"] == 2
    assert r["hapax_pct"] == round(2 / 4 * 100, 2)

    # pct coherente con count/n_tokens.
    assert r["top_terms"][0]["pct"] == round(3 / 7 * 100, 2)


def test_vacio():
    # Sin documentos validos -> ceros / None / [].
    for arg in ([], None, [None, 123, ""], ["123 456"]):
        r = compute_vocabulary_stats(arg)
        assert r["n_tokens"] == 0
        assert r["n_types"] == 0
        assert r["ttr"] is None
        assert r["n_hapax"] == 0
        assert r["hapax_pct"] is None
        assert r["top_terms"] == []


def test_stopwords_quitadas():
    texts = ["the gato the perro", "de la casa azul"]
    r = compute_vocabulary_stats(texts, remove_stopwords=True)
    terms = {t["term"] for t in r["top_terms"]}
    # Stopwords ES+EN no deben aparecer.
    assert "the" not in terms
    assert "de" not in terms
    assert "la" not in terms
    # Palabras de contenido si.
    assert "gato" in terms
    assert "casa" in terms


def test_stopwords_conservadas():
    texts = ["the gato the perro", "de la casa azul"]
    r = compute_vocabulary_stats(texts, remove_stopwords=False)
    terms = {t["term"] for t in r["top_terms"]}
    # Con el filtro desactivado, las stopwords se conservan.
    assert "the" in terms
    assert "de" in terms
    assert "la" in terms