from __future__ import annotations

import json
from pathlib import Path

import pytest

import scripts.common as common
import scripts.scan_zpwiki as scanner


def write_page(path: Path, text: str) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_text(text, encoding="utf-8")


def test_scan_pages_creates_document_manifest(
    tmp_path: Path,
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    root = tmp_path / "zpwiki"
    pages = root / "pages"
    output = tmp_path / "data" / "documents.json"

    write_page(
        pages / "a" / "README.md",
        """---
title: Prvý dokument
published: true
taxonomy:
  category: [project]
  tag: [rag]
---
# Úvod

Prvý obsah.
""",
    )
    write_page(
        pages / "b" / "README.md",
        "# Druhý dokument\n\nDruhý obsah.",
    )

    monkeypatch.setattr(common, "ZPWIKI_ROOT", root)
    monkeypatch.setattr(common, "PAGES_ROOT", pages)
    monkeypatch.setattr(scanner, "ZPWIKI_ROOT", root)
    monkeypatch.setattr(scanner, "PAGES_ROOT", pages)
    monkeypatch.setattr(scanner, "DOCUMENTS_FILE", output)

    documents = scanner.scan_pages()

    assert len(documents) == 2
    assert output.exists()

    stored = json.loads(output.read_text(encoding="utf-8"))
    assert stored == documents
    assert all("content" not in document for document in documents)
    assert all("content_preview" in document for document in documents)
    assert all(document["content_length"] > 0 for document in documents)
    assert documents[0]["title"] == "Prvý dokument"
    assert documents[1]["title"] == "Druhý dokument"


def test_scan_pages_rejects_missing_pages_directory(
    tmp_path: Path,
    monkeypatch: pytest.MonkeyPatch,
) -> None:
    missing = tmp_path / "missing-pages"
    monkeypatch.setattr(scanner, "PAGES_ROOT", missing)

    with pytest.raises(SystemExit, match="Neexistuje priečinok"):
        scanner.scan_pages()