Class Story

src/__init__.py:15822–16374

class Story:

    def __init__( self, html='', user_css=None, em=12, archive=None):
        buffer_ = mupdf.fz_new_buffer_from_copied_data( html.encode('utf-8'))
        if archive and not isinstance(archive, Archive):
            archive = Archive(archive)
        arch = archive.this if archive else mupdf.FzArchive( None)
        if hasattr(mupdf, 'FzStoryS'):
            self.this = mupdf.FzStoryS( buffer_, user_css, em, arch)
        else:
            self.this = mupdf.FzStory( buffer_, user_css, em, arch)
    
    def add_header_ids(self):
        '''
        Look for `<h1..6>` items in `self` and adds unique `id`
        attributes if not already present.
        ''&#x27;
        dom = self.body
        i = 0
        x = dom.find(None, None, None)
        while x:
            name = x.tagname
            if len(name) == 2 and name[0]=="h" and name[1] in "123456":
                attr = x.get_attribute_value("id")
                if not attr:
                    id_ = f"h_id_{i}"
                    #log(f"{name=}: setting {id_=}")
                    x.set_attribute("id", id_)
                    i += 1
            x = x.find_next(None, None, None)

    @staticmethod
    def add_pdf_links(document_or_stream, positions):
        """
        Adds links to PDF document.
        Args:
            document_or_stream:
                A PDF `Document` or raw PDF content, for example an
                `io.BytesIO` instance.
            positions:
                List of `ElementPosition`&#x27;s for `document_or_stream`,
                typically from Story.element_positions(). We raise an
                exception if two or more positions have same id.
        Returns:
            `document_or_stream` if a `Document` instance, otherwise a
            new `Document` instance.
        We raise an exception if an `href` in `positions` refers to an
        internal position `#<name>` but no item in `positions` has `id =
        name`.
        """
        if isinstance(document_or_stream, Document):
            document = document_or_stream
        else:
            document = Document("pdf", document_or_stream)

        # Create dict from id to position, which we will use to find
        # link destinations.
        #