Class Xml

src/__init__.py:2120–2712

class Xml:

    def __enter__(self):
        return self

    def __exit__(self, *args):
        pass

    def __init__(self, rhs):
        if isinstance(rhs, mupdf.FzXml):
            self.this = rhs
        elif isinstance(rhs, str):
            buff = mupdf.fz_new_buffer_from_copied_data(rhs)
            self.this = mupdf.fz_parse_xml_from_html5(buff)
        else:
            assert 0, f'Unsupported type for rhs: {type(rhs)}'
    
    def _get_node_tree( self):
        def show_node(node, items, shift):
            while node is not None:
                if node.is_text:
                    items.append((shift, f'"{node.text}"'))
                    node = node.next
                    continue
                items.append((shift, f"({node.tagname}"))
                for k, v in node.get_attributes().items():
                    items.append((shift, f"={k} '{v}'"))
                child = node.first_child
                if child:
                    items = show_node(child, items, shift + 1)
                items.append((shift, f"){node.tagname}"))
                node = node.next
            return items

        shift = 0
        items = []
        items = show_node(self, items, shift)
        return items
    
    def add_bullet_list(self):
        """Add bulleted list ("ul" tag)"""
        child = self.create_element("ul")
        self.append_child(child)
        return child

    def add_class(self, text):
        """Set some class via CSS. Replaces complete class spec."""
        cls = self.get_attribute_value("class")
        if cls is not None and text in cls:
            return self
        self.remove_attribute("class")
        if cls is None:
            cls = text
        else:
            cls += " " + text
        self.set_attribute("class", cls)
        return self