tests for epub reader

pyWebLayout/abstract/document.py

@@ -224,6 +224,26 @@ class Document:
         """
         self.set_metadata(MetadataType.TITLE, title)
     
+    @property
+    def title(self) -> Optional[str]:
+        """
+        Get the document title as a property.
+        
+        Returns:
+            The document title, or None if not set
+        """
+        return self.get_title()
+    
+    @title.setter
+    def title(self, title: str):
+        """
+        Set the document title as a property.
+        
+        Args:
+            title: The document title
+        """
+        self.set_title(title)
+    
     def find_blocks_by_type(self, block_type: BlockType) -> List[Block]:
         """
         Find all blocks of a specific type.

pyWebLayout/io/readers/epub_reader.py

@@ -14,7 +14,7 @@ import re
 import urllib.parse
 
 from pyWebLayout.abstract.document import Document, Book, Chapter, MetadataType
-from pyWebLayout.io.readers.html import parse_html_string as parse_html, read_html_file as html_to_document
+from pyWebLayout.io.readers.html_extraction import parse_html_string
 
 
 # XML namespaces used in EPUB files
@@ -346,6 +346,7 @@ class EPUBReader:
         add_to_toc_map(self.toc)
         
         # Process spine items
+        chapter_index = 0  # Keep track of actual content chapters
         for i, idref in enumerate(self.spine):
             if idref not in self.manifest:
                 continue
@@ -354,13 +355,20 @@ class EPUBReader:
             path = item['path']
             href = item['href']
             
+            # Skip navigation files
+            if (idref == 'nav' or 
+                item.get('media_type') == 'application/xhtml+xml' and 
+                ('nav' in href.lower() or 'toc' in href.lower())):
+                continue
+            
             # Check if this item is in the TOC
             chapter_title = None
             if href in toc_map:
                 chapter_title = toc_map[href]['label']
             
             # Create a chapter
-            chapter = self.book.create_chapter(chapter_title, i + 1)
+            chapter_index += 1
+            chapter = self.book.create_chapter(chapter_title, chapter_index)
             
             # Parse the HTML content
             try:
@@ -369,11 +377,10 @@ class EPUBReader:
                     html = f.read()
                 
                 # Parse HTML and add blocks to chapter
-                base_url = os.path.dirname(path)
-                document = parse_html(html, base_url=base_url)
+                blocks = parse_html_string(html)
                 
                 # Copy blocks to the chapter
-                for block in document.blocks:
+                for block in blocks:
                     chapter.add_block(block)
                 
             except Exception as e:

pyWebLayout/style/fonts.py

@@ -73,7 +73,7 @@ class Font:
                 if self._font_size != 12:  # Default size might not be 12
                     self._font = ImageFont.truetype(self._font.path, self._font_size)
         except Exception as e:
-            print(f"Error loading font: {e}")
+            # Silently fall back to default font
             self._font = ImageFont.load_default()
     
     @property