Content
'
14 | return [DummyItem()]
15 |
16 | def test_process_epub(monkeypatch, tmp_path):
17 | epub_path = tmp_path / "test.epub"
18 | with open(epub_path, "wb") as f:
19 | f.write(b"dummy epub content")
20 | monkeypatch.setattr('ebooklib.epub.read_epub', lambda path: DummyBook())
21 | processor = SimpleEpubProcessor(extract_images=True)
22 | chapters, images_by_chapter, name, meta = processor.process_epub(str(epub_path), image_output_dir=str(tmp_path))
23 | assert isinstance(chapters, dict)
24 | assert isinstance(images_by_chapter, dict)
25 | assert name == "test"
26 | assert meta['title'] == 'Test Book'
27 |
28 | def test_process_epub_missing_file(tmp_path):
29 | processor = SimpleEpubProcessor()
30 | chapters, images_by_chapter, name, meta = processor.process_epub(str(tmp_path / "no_file.epub"))
31 | assert "Error" in chapters or "Failed" in list(chapters.values())[0]
32 |
33 | def test_process_epub_no_chapters(monkeypatch, tmp_path):
34 | class DummyBook:
35 | def get_metadata(self, *args, **kwargs):
36 | return {'title': [('Test Book',)]}
37 | def get_items(self):
38 | return []
39 | epub_path = tmp_path / "test.epub"
40 | with open(epub_path, "wb") as f:
41 | f.write(b"dummy epub content")
42 | monkeypatch.setattr('ebooklib.epub.read_epub', lambda path: DummyBook())
43 | processor = SimpleEpubProcessor()
44 | chapters, images_by_chapter, name, meta = processor.process_epub(str(epub_path), image_output_dir=str(tmp_path))
45 | assert "No Content" in chapters
46 |
47 | def test_has_content():
48 | processor = SimpleEpubProcessor()
49 | assert not processor._has_content("")
50 | assert not processor._has_content("\n\t ")
51 | assert processor._has_content("a" * 101)
52 |
53 | def test_extract_images_basic(tmp_path):
54 | processor = SimpleEpubProcessor()
55 | class DummyBook: pass
56 | class DummyItem: pass
57 | from bs4 import BeautifulSoup
58 | soup = BeautifulSoup('
', 'html.parser')
59 | images = processor._extract_images_basic(DummyBook(), DummyItem(), soup, str(tmp_path), "book", 1)
60 | assert len(images) == 2
61 | assert images[0]['filename'].endswith('.png')
62 | assert images[0]['alt'] == 'A'
63 |
64 | def test_extract_images_basic_malformed_html(tmp_path):
65 | processor = SimpleEpubProcessor()
66 | class DummyBook: pass
67 | class DummyItem: pass
68 | from bs4 import BeautifulSoup
69 | soup = BeautifulSoup('