from voice_assistant.agent.text_chunker import TextChunker


def test_chunker_emits_sentence():
    chunker = TextChunker(min_chars=5)

    assert chunker.feed("Olá, tudo bem?") == [
        "Olá, tudo bem?"
    ]


def test_chunker_handles_incremental_deltas():
    chunker = TextChunker(min_chars=5)

    assert chunker.feed("Olá,") == []
    assert chunker.feed(" tudo") == []
    assert chunker.feed(" bem?") == [
        "Olá, tudo bem?"
    ]


def test_chunker_preserves_remaining_text():
    chunker = TextChunker(min_chars=5)

    assert chunker.feed("Olá, tudo bem? Posso ajudar") == [
        "Olá, tudo bem?"
    ]

    assert chunker.flush() == "Posso ajudar"


def test_chunker_breaks_long_text():
    chunker = TextChunker(
        min_chars=5,
        max_chars=20,
    )

    segments = chunker.feed(
        "Esta é uma frase bastante longa sem pontuação"
    )

    assert segments
    assert all(
        len(segment) <= 20
        for segment in segments
    )


def test_chunker_rejects_invalid_limits():
    try:
        TextChunker(min_chars=20, max_chars=10)
    except ValueError:
        pass
    else:
        raise AssertionError(
            "Expected ValueError for invalid limits."
        )