test for epubs with images.

2025-06-07 19:04:53 +02:00 · 2025-06-07 19:04:53 +02:00 · d40fcfe084
commit d40fcfe084
parent 87a313b3e7
1 changed files with 74 additions and 0 deletions
--- a/tests/test_epub_reader.py
+++ b/tests/test_epub_reader.py
@ -752,5 +752,79 @@ class TestEPUBIntegrationWithHTMLExtraction(unittest.TestCase):
        self.assertTrue(color_found, "Should find at least one colored text")


+    def test_epub_with_image(self):
+        """Test that images in EPUB are properly parsed."""
+        book = epub.EpubBook()
+        book.set_identifier('image-test-id')
+        book.set_title('Image Test Book')
+        book.set_language('en')
+        book.add_author('Test Author')
+        
+        # Create minimal JPEG data for testing
+        img_data = b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x01\x00H\x00H\x00\x00\xff\xdb\x00C\x00\x08\x06\x06\x07\x06\x05\x08\x07\x07\x07\t\t\x08\n\x0c\x14\r\x0c\x0b\x0b\x0c\x19\x12\x13\x0f\x14\x1d\x1a\x1f\x1e\x1d\x1a\x1c\x1c $.\' ",#\x1c\x1c(7),01444\x1f\'9=82<.342\xff\xc0\x00\x11\x08\x00d\x00d\x01\x01\x11\x00\x02\x11\x01\x03\x11\x01\xff\xc4\x00\x14\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x08\xff\xc4\x00\x14\x10\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xff\xda\x00\x0c\x03\x01\x00\x02\x11\x03\x11\x00\x3f\x00\xaa\xff\xd9'
+        
+        # Create an EpubImage item
+        image_item = epub.EpubImage()
+        image_item.id = 'test_img'
+        image_item.file_name = 'images/test_image.jpg'
+        image_item.media_type = 'image/jpeg'
+        image_item.content = img_data
+        
+        # Add image to book
+        book.add_item(image_item)
+        
+        # Create a chapter that references the image
+        chapter = epub.EpubHtml(
+            title='Image Chapter',
+            file_name='image_chapter.xhtml',
+            lang='en'
+        )
+        chapter.content = '''<html xmlns="http://www.w3.org/1999/xhtml">
+<head><title>Image Chapter</title></head>
+<body>
+    <h1>Chapter with Image</h1>
+    <p>This chapter contains an image:</p>
+    <img src="images/test_image.jpg" alt="Test image" width="300" height="200" />
+    <p>Text after the image.</p>
+</body>
+</html>'''
+        
+        book.add_item(chapter)
+        book.toc = (epub.Link("image_chapter.xhtml", "Image Chapter", "img_ch"),)
+        book.add_item(epub.EpubNcx())
+        book.add_item(epub.EpubNav())
+        book.spine = ['nav', chapter]
+        
+        # Write EPUB
+        epub_path = os.path.join(self.test_dir, f'test_image_{len(self.epub_files)}.epub')
+        epub.write_epub(epub_path, book, {})
+        self.epub_files.append(epub_path)
+        
+        # Read and analyze
+        parsed_book = read_epub(epub_path)
+        chapters = list(parsed_book.chapters)
+        self.assertEqual(len(chapters), 1)
+        
+        blocks = list(chapters[0].blocks)
+        self.assertGreater(len(blocks), 0)
+        
+        # Find blocks by type
+        heading_blocks = [block for block in blocks if isinstance(block, Heading)]
+        paragraph_blocks = [block for block in blocks if isinstance(block, Paragraph)]
+        image_blocks = [block for block in blocks if isinstance(block, Image)]
+        
+        # Verify we have the expected blocks
+        self.assertEqual(len(heading_blocks), 1, "Should find exactly one heading block")
+        self.assertGreaterEqual(len(paragraph_blocks), 2, "Should find at least two paragraph blocks")
+        self.assertEqual(len(image_blocks), 1, "Should find exactly one image block")
+        
+        # Verify image properties
+        image_block = image_blocks[0]
+        self.assertEqual(image_block.alt_text, "Test image")
+        self.assertEqual(image_block.width, 300)
+        self.assertEqual(image_block.height, 200)
+        self.assertIn("test_image.jpg", image_block.source)
+
+
 if __name__ == '__main__':
    unittest.main()