from __future__ import annotations

from multi_swarm.metrics.diversity import population_prompt_diversity


def test_empty_or_single_prompt_zero_diversity() -> None:
    assert population_prompt_diversity([]) == 0.0
    assert population_prompt_diversity(["solo prompt"]) == 0.0


def test_identical_prompts_zero_diversity() -> None:
    prompts = ["Strategia RSI < 30 long"] * 5
    assert population_prompt_diversity(prompts) == 0.0


def test_completely_different_prompts_high_diversity() -> None:
    prompts = [
        "AAAAAA AAAA AAAAA",
        "BBBBBB BBBB BBBBB",
        "CCCCCC CCCC CCCCC",
        "DDDDDD DDDD DDDDD",
    ]
    d = population_prompt_diversity(prompts)
    # SequenceMatcher considera spazi e lunghezza simili → similarity > 0
    # anche su stringhe completamente "diverse". Soglia realistica: 0.8.
    assert d > 0.8


def test_partial_overlap_intermediate_diversity() -> None:
    prompts = [
        "Strategia momentum 1h con RSI",
        "Strategia momentum 1h con SMA",
        "Strategia momentum 4h con RSI",
    ]
    d = population_prompt_diversity(prompts)
    assert 0.05 < d < 0.5


def test_diversity_symmetric() -> None:
    prompts_a = ["x", "yy", "zzz"]
    prompts_b = ["zzz", "x", "yy"]
    assert (
        abs(population_prompt_diversity(prompts_a)
            - population_prompt_diversity(prompts_b)) < 1e-9
    )