from __future__ import annotations

import pytest

import scripts.build_chunks as chunking


def configure_small_chunks(
    monkeypatch: pytest.MonkeyPatch,
    *,
    maximum: int = 90,
    overlap: int = 18,
    minimum: int = 25,
) -> None:
    monkeypatch.setattr(chunking, "MAX_TOKENS", maximum)
    monkeypatch.setattr(chunking, "OVERLAP_TOKENS", overlap)
    monkeypatch.setattr(chunking, "MIN_CHUNK_TOKENS", minimum)


def body_without_context(text: str) -> str:
    parts = text.split("\n\n", maxsplit=1)
    return parts[1] if len(parts) == 2 else ""


def test_chunks_respect_token_limit_and_keep_context(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    configure_small_chunks(monkeypatch)

    sentences = [
        f"Veta {index} obsahuje dostatočne dlhý skúšobný text."
        for index in range(1, 30)
    ]
    markdown = "## Obsah\n\n" + " ".join(sentences)

    drafts = chunking.chunk_markdown(
        markdown,
        document_title="Testovací dokument",
    )

    assert len(drafts) > 1

    for draft in drafts:
        assert draft.text.startswith("Dokument: Testovací dokument")
        assert "Sekcia: Obsah" in draft.text
        assert chunking.TOKEN_COUNTER.count(draft.text) <= 90
        assert body_without_context(draft.text).startswith("Veta ")


def test_overlap_never_starts_in_middle_of_word_or_sentence(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    configure_small_chunks(monkeypatch, maximum=75, overlap=20, minimum=20)

    markdown = "## Sekcia\n\n" + " ".join(
        f"Presná veta číslo {index} sa končí bodkou."
        for index in range(1, 24)
    )

    drafts = chunking.chunk_markdown(markdown, document_title="Dokument")

    assert len(drafts) > 1

    for draft in drafts:
        body = body_without_context(draft.text)
        assert body.startswith("Presná veta číslo ")
        assert not body.startswith(("t is done", "he databases", "te down"))


def test_short_sections_are_merged_or_balanced(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    configure_small_chunks(monkeypatch, maximum=170, overlap=20, minimum=50)

    markdown = """
## Úlohy

Krátke zadanie.

## Výsledky

Táto sekcia obsahuje dlhší text s výsledkami a ďalším vysvetlením. Druhá veta dopĺňa kontext a umožní bezpečné spojenie krátkej časti.
"""

    drafts = chunking.chunk_markdown(markdown, document_title="Test")

    assert drafts
    assert any("Krátke zadanie." in draft.text for draft in drafts)
    assert all(draft.units for draft in drafts)
    assert all(
        draft.text.strip() not in {
            "Dokument: Test\nSekcia: Úlohy",
            "Dokument: Test\n\nSekcia: Úlohy",
        }
        for draft in drafts
    )


def test_empty_markdown_produces_no_chunks() -> None:
    assert chunking.chunk_markdown("", document_title="Prázdny") == []
    assert chunking.chunk_markdown("\n\n", document_title="Prázdny") == []


def test_heading_inside_code_fence_is_not_section(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    configure_small_chunks(monkeypatch, maximum=220, overlap=20, minimum=20)

    markdown = """
# Skutočná sekcia

```markdown
## Toto nie je nadpis
print("ahoj")
```

Text po bloku kódu.
"""

    drafts = chunking.chunk_markdown(markdown, document_title="Kód")

    assert drafts
    assert any("## Toto nie je nadpis" in draft.text for draft in drafts)
    assert all(
        "Toto nie je nadpis" not in path
        for draft in drafts
        for path in draft.heading_paths
    )


def test_no_chunk_exceeds_configured_limit(
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    configure_small_chunks(monkeypatch, maximum=60, overlap=10, minimum=10)

    markdown = "# Dlhý text\n\n" + " ".join(
        f"slovo{index}" for index in range(1, 250)
    )

    drafts = chunking.chunk_markdown(markdown, document_title="Limit")

    assert drafts
    assert max(chunking.TOKEN_COUNTER.count(draft.text) for draft in drafts) <= 60