diff --git a/application/parser/file/epub_parser.py b/application/parser/file/epub_parser.py index 4f5e8711..9577d3c9 100644 --- a/application/parser/file/epub_parser.py +++ b/application/parser/file/epub_parser.py @@ -19,25 +19,10 @@ class EpubParser(BaseParser): def parse_file(self, file: Path, errors: str = "ignore") -> str: """Parse file.""" try: - import ebooklib - from ebooklib import epub + from fast_ebook import epub except ImportError: - raise ValueError("`EbookLib` is required to read Epub files.") - try: - import html2text - except ImportError: - raise ValueError("`html2text` is required to parse Epub files.") + raise ValueError("`fast-ebook` is required to read Epub files.") - text_list = [] - book = epub.read_epub(file, options={"ignore_ncx": True}) - - # Iterate through all chapters. - for item in book.get_items(): - # Chapters are typically located in epub documents items. - if item.get_type() == ebooklib.ITEM_DOCUMENT: - text_list.append( - html2text.html2text(item.get_content().decode("utf-8")) - ) - - text = "\n".join(text_list) + book = epub.read_epub(file) + text = book.to_markdown() return text diff --git a/application/requirements.txt b/application/requirements.txt index b3abe71f..c7a43582 100644 --- a/application/requirements.txt +++ b/application/requirements.txt @@ -11,7 +11,7 @@ rapidocr>=1.4.0 onnxruntime>=1.19.0 docx2txt==0.9 ddgs>=8.0.0 -ebooklib==0.20 +fast-ebook elevenlabs==2.41.0 Flask==3.1.3 faiss-cpu==1.13.2 @@ -23,7 +23,6 @@ google-auth-httplib2==0.3.1 google-auth-oauthlib==1.3.1 gTTS==2.5.4 gunicorn==25.3.0 -html2text==2025.4.15 jinja2==3.1.6 jiter==0.13.0 jmespath==1.1.0 diff --git a/tests/parser/file/test_epub_parser.py b/tests/parser/file/test_epub_parser.py index 519ae2a4..815b9e1c 100644 --- a/tests/parser/file/test_epub_parser.py +++ b/tests/parser/file/test_epub_parser.py @@ -20,133 +20,49 @@ def test_epub_init_parser(): assert parser.parser_config_set -def test_epub_parser_ebooklib_import_error(epub_parser): - """Test that ImportError is raised when ebooklib is not available.""" - with patch.dict(sys.modules, {"ebooklib": None}): - with pytest.raises(ValueError, match="`EbookLib` is required to read Epub files"): +def test_epub_parser_fast_ebook_import_error(epub_parser): + """Test that ImportError is raised when fast-ebook is not available.""" + with patch.dict(sys.modules, {"fast_ebook": None}): + with pytest.raises(ValueError, match="`fast-ebook` is required to read Epub files"): epub_parser.parse_file(Path("test.epub")) -def test_epub_parser_html2text_import_error(epub_parser): - """Test that ImportError is raised when html2text is not available.""" - fake_ebooklib = types.ModuleType("ebooklib") - fake_epub = types.ModuleType("ebooklib.epub") - fake_ebooklib.epub = fake_epub - - with patch.dict(sys.modules, {"ebooklib": fake_ebooklib, "ebooklib.epub": fake_epub}): - with patch.dict(sys.modules, {"html2text": None}): - with pytest.raises(ValueError, match="`html2text` is required to parse Epub files"): - epub_parser.parse_file(Path("test.epub")) - - def test_epub_parser_successful_parsing(epub_parser): """Test successful parsing of an epub file.""" + fake_fast_ebook = types.ModuleType("fast_ebook") + fake_epub = types.ModuleType("fast_ebook.epub") + fake_fast_ebook.epub = fake_epub - fake_ebooklib = types.ModuleType("ebooklib") - fake_epub = types.ModuleType("ebooklib.epub") - fake_html2text = types.ModuleType("html2text") - - # Mock ebooklib constants - fake_ebooklib.ITEM_DOCUMENT = "document" - fake_ebooklib.epub = fake_epub - - mock_item1 = MagicMock() - mock_item1.get_type.return_value = "document" - mock_item1.get_content.return_value = b"

Chapter 1

Content 1

" - - mock_item2 = MagicMock() - mock_item2.get_type.return_value = "document" - mock_item2.get_content.return_value = b"

Chapter 2

Content 2

" - - mock_item3 = MagicMock() - mock_item3.get_type.return_value = "other" # Should be ignored - mock_item3.get_content.return_value = b"

Other content

" - mock_book = MagicMock() - mock_book.get_items.return_value = [mock_item1, mock_item2, mock_item3] - + mock_book.to_markdown.return_value = "# Chapter 1\n\nContent 1\n\n# Chapter 2\n\nContent 2\n" + fake_epub.read_epub = MagicMock(return_value=mock_book) - - def mock_html2text_func(html_content): - if "Chapter 1" in html_content: - return "# Chapter 1\n\nContent 1\n" - elif "Chapter 2" in html_content: - return "# Chapter 2\n\nContent 2\n" - return "Other content\n" - - fake_html2text.html2text = mock_html2text_func - + with patch.dict(sys.modules, { - "ebooklib": fake_ebooklib, - "ebooklib.epub": fake_epub, - "html2text": fake_html2text + "fast_ebook": fake_fast_ebook, + "fast_ebook.epub": fake_epub, }): result = epub_parser.parse_file(Path("test.epub")) - - expected_result = "# Chapter 1\n\nContent 1\n\n# Chapter 2\n\nContent 2\n" - assert result == expected_result - - # Verify epub.read_epub was called with correct parameters - fake_epub.read_epub.assert_called_once_with(Path("test.epub"), options={"ignore_ncx": True}) + + assert result == "# Chapter 1\n\nContent 1\n\n# Chapter 2\n\nContent 2\n" + fake_epub.read_epub.assert_called_once_with(Path("test.epub")) def test_epub_parser_empty_book(epub_parser): - """Test parsing an epub file with no document items.""" - # Create mock modules - fake_ebooklib = types.ModuleType("ebooklib") - fake_epub = types.ModuleType("ebooklib.epub") - fake_html2text = types.ModuleType("html2text") - - fake_ebooklib.ITEM_DOCUMENT = "document" - fake_ebooklib.epub = fake_epub - - # Create mock book with no document items + """Test parsing an epub file with no content.""" + fake_fast_ebook = types.ModuleType("fast_ebook") + fake_epub = types.ModuleType("fast_ebook.epub") + fake_fast_ebook.epub = fake_epub + mock_book = MagicMock() - mock_book.get_items.return_value = [] - + mock_book.to_markdown.return_value = "" + fake_epub.read_epub = MagicMock(return_value=mock_book) - fake_html2text.html2text = MagicMock() - + with patch.dict(sys.modules, { - "ebooklib": fake_ebooklib, - "ebooklib.epub": fake_epub, - "html2text": fake_html2text + "fast_ebook": fake_fast_ebook, + "fast_ebook.epub": fake_epub, }): result = epub_parser.parse_file(Path("empty.epub")) + assert result == "" - - fake_html2text.html2text.assert_not_called() - - -def test_epub_parser_non_document_items_ignored(epub_parser): - """Test that non-document items are ignored during parsing.""" - fake_ebooklib = types.ModuleType("ebooklib") - fake_epub = types.ModuleType("ebooklib.epub") - fake_html2text = types.ModuleType("html2text") - - fake_ebooklib.ITEM_DOCUMENT = "document" - fake_ebooklib.epub = fake_epub - - mock_doc_item = MagicMock() - mock_doc_item.get_type.return_value = "document" - mock_doc_item.get_content.return_value = b"

Document content

" - - mock_other_item = MagicMock() - mock_other_item.get_type.return_value = "image" # Not a document - - mock_book = MagicMock() - mock_book.get_items.return_value = [mock_other_item, mock_doc_item] - - fake_epub.read_epub = MagicMock(return_value=mock_book) - fake_html2text.html2text = MagicMock(return_value="Document content\n") - - with patch.dict(sys.modules, { - "ebooklib": fake_ebooklib, - "ebooklib.epub": fake_epub, - "html2text": fake_html2text - }): - result = epub_parser.parse_file(Path("test.epub")) - - assert result == "Document content\n" - - fake_html2text.html2text.assert_called_once_with("

Document content

")