"""Tests para compute_top_ngrams."""

import sys
import os

# sys.path estándar: añade `python/functions/` para importar por paquete raíz.
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))

from datascience.compute_top_ngrams import compute_top_ngrams


def test_bigramas():
    # "machine learning" se repite en cada documento -> bigrama más frecuente.
    texts = [
        "machine learning rocks",
        "machine learning is fun",
        "we love machine learning",
    ]
    result = compute_top_ngrams(texts, n=2, top_k=5)
    assert result["n"] == 2
    assert result["top"], "esperaba al menos un bigrama"
    assert result["top"][0]["ngram"] == "machine learning"
    assert result["top"][0]["count"] == 3
    # Cada entrada respeta el contrato {"ngram": str, "count": int}.
    for item in result["top"]:
        assert isinstance(item["ngram"], str)
        assert isinstance(item["count"], int)


def test_trigramas():
    texts = [
        "alpha beta gamma delta",
        "alpha beta gamma omega",
    ]
    # Con stopwords desactivadas para no descartar tokens de contenido.
    result = compute_top_ngrams(texts, n=3, top_k=5, remove_stopwords=False)
    assert result["n"] == 3
    ngrams = {item["ngram"]: item["count"] for item in result["top"]}
    # "alpha beta gamma" aparece en ambos documentos.
    assert ngrams.get("alpha beta gamma") == 2
    # Trigramas únicos de cada documento.
    assert ngrams.get("beta gamma delta") == 1
    assert ngrams.get("beta gamma omega") == 1


def test_vacio():
    assert compute_top_ngrams([], n=2) == {"n": 2, "top": []}
    # Documentos no-str / None se descartan -> corpus efectivamente vacío.
    assert compute_top_ngrams([None, 123, {"a": 1}], n=2) == {"n": 2, "top": []}


def test_stopwords():
    # "the cat" debería desaparecer al quitar stopwords ("the" es stopword EN).
    texts = ["the cat the cat the cat"]
    con = compute_top_ngrams(texts, n=2, top_k=10, remove_stopwords=True)
    sin = compute_top_ngrams(texts, n=2, top_k=10, remove_stopwords=False)

    con_ngrams = {item["ngram"] for item in con["top"]}
    sin_ngrams = {item["ngram"] for item in sin["top"]}

    # Sin filtrar, el bigrama dominante es "the cat".
    assert "the cat" in sin_ngrams
    # Al filtrar stopwords, ya no aparece "the cat" (queda solo "cat cat").
    assert "the cat" not in con_ngrams
    assert con_ngrams != sin_ngrams