from pathlib import Path

import pytest

from text_analyzer.core import analyze_file


def test_basic_analysis(tmp_path: Path) -> None:
    test_file = tmp_path / "test.txt"
    test_file.write_text("hello world\nhello python")

    res = analyze_file(test_file)
    assert res["lines"] == 2
    assert res["words"] == 4
    assert res["top_words"] == [("hello", 2), ("world", 1), ("python", 1)]


def test_file_not_found() -> None:
    with pytest.raises(FileNotFoundError):
        analyze_file(Path("non_existent_file_123.txt"))


def test_empty_file(tmp_path: Path) -> None:
    test_file = tmp_path / "empty.txt"
    test_file.write_text("")

    res = analyze_file(test_file)
    assert res["lines"] == 0
    assert res["words"] == 0
    assert res["top_words"] == []


@pytest.mark.parametrize(
    "min_len,expected_words",
    [
        (1, 4),
        (3, 2),
        (4, 1),
    ],
)
def test_min_length_filter(tmp_path: Path, min_len: int, expected_words: int) -> None:
    test_file = tmp_path / "filter.txt"
    test_file.write_text("a ab abc abcd")

    res = analyze_file(test_file, min_len=min_len)
    assert res["words"] == expected_words


def test_top_n_param(tmp_path: Path) -> None:
    test_file = tmp_path / "top.txt"
    test_file.write_text("one two two three three three")

    res = analyze_file(test_file, top_n=2)
    top_words = res["top_words"]
    assert isinstance(top_words, list)
    assert len(top_words) == 2


def test_punctuation_stripping(tmp_path: Path) -> None:
    test_file = tmp_path / "punct.txt"
    test_file.write_text("hello, world! hello...")

    res = analyze_file(test_file)
    assert res["top_words"] == [("hello", 2), ("world", 1)]