from pathlib import Path

from src.mdx_text_atoms import compare_atom_sets, extract_text_atoms, normalize_text_atom


def test_extract_atoms_ignores_syntax_and_keeps_semantic_text():
    mdx = """---
title: demo
---

import Demo from './Demo.astro'

## 1. Title

- **Important** text
<details>
  <summary style={{cursor: 'pointer'}}>More info</summary>
  <div style={{ color: '#999' }}>
    <p>Nested semantic text</p>
  </div>
</details>

| A | B |
| :--- | :--- |
| one | two |

![Diagram caption](/assets/demo.png)
"""
    atoms = extract_text_atoms(mdx, source_name="demo.mdx")
    texts = [a.normalized for a in atoms]

    assert "1. Title" in texts
    assert "Important text" in texts
    assert "More info" in texts
    assert "Nested semantic text" in texts
    assert "A" in texts
    assert "B" in texts
    assert "one" in texts
    assert "two" in texts
    assert "Diagram caption" in texts
    assert not any("cursor" in t for t in texts)


def test_compare_atom_sets_reports_missing_and_added():
    original = extract_text_atoms("- Original text\n- Shared text\n", source_name="original")
    standardized = extract_text_atoms("- Shared text\n- Added text\n", source_name="standardized")

    result = compare_atom_sets(original, standardized)

    assert [a.normalized for a in result["missing_from_standardized"]] == ["Original text"]
    assert [a.normalized for a in result["added_in_standardized"]] == ["Added text"]


def test_normalize_text_atom_removes_markdown_markers_only():
    assert normalize_text_atom("**Digital** `Transformation`") == "Digital Transformation"