"""Tests for the scraper article-processing cache."""

import sys
from pathlib import Path

import pytest

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from scraper.scraper import (  # noqa: E402
    get_processing_progress,
    load_processed_cache,
    mark_article_processed,
    save_processed_cache,
)


@pytest.fixture()
def cache_dir(tmp_path, monkeypatch):
    monkeypatch.chdir(tmp_path)
    (tmp_path / "articles").mkdir()
    return tmp_path


def test_load_missing_cache_returns_empty(cache_dir):
    assert load_processed_cache() == {}


def test_save_and_load_roundtrip(cache_dir):
    save_processed_cache({"a.html": {"status": "completed"}})
    cache = load_processed_cache()
    assert cache["a.html"]["status"] == "completed"


def test_mark_article_processed(cache_dir):
    mark_article_processed("articles/x/article.html")
    cache = load_processed_cache()
    entry = cache["articles/x/article.html"]
    assert entry["status"] == "completed"
    assert entry["embedding_status"] == "pending"
    assert "processed_date" in entry
    assert "last_updated" in entry


def test_processing_progress_empty(cache_dir):
    progress = get_processing_progress()
    assert progress["total_articles"] == 0
    assert progress["completed_articles"] == 0
    assert progress["embedded_articles"] == 0
    assert progress["completion_rate"] == 0


def test_processing_progress_mixed(cache_dir):
    mark_article_processed("a.html")
    mark_article_processed("b.html", status="failed")
    mark_article_processed("c.html", embedding_status="completed")
    progress = get_processing_progress()
    assert progress["total_articles"] == 3
    assert progress["completed_articles"] == 2
    assert progress["embedded_articles"] == 1
    assert progress["completion_rate"] == pytest.approx(2 / 3 * 100)