Class Fill

pdf2docx/shape/Shape.py:268–331

Rectangular (bbox) filling area of a closed path. The semantic meaning may be table shading, or text style like highlight.

class Fill(Shape):
    ''' Rectangular (bbox) filling area of a closed path. 
        The semantic meaning may be table shading, or text style like highlight.
    '''

    def to_stroke(self, max_border_width:float):
        '''Convert to Stroke instance based on width criterion.

        Args:
            max_border_width (float): Stroke width must less than this value.

        Returns:
            Stroke: Stroke instance.
        
        .. note::
            A Fill from shape point of view may be a Stroke from content point of view.
            The criterion here is whether the width is smaller than defined ``max_border_width``.
        '''
        w = min(self.bbox.width, self.bbox.height)

        # not a stroke if exceed max border width
        if w > max_border_width:
            return None
        else:
            return Stroke({'width': w, 'color': self.color}).update_bbox(self.bbox)
    

    @property
    def default_type(self):
        '''Default semantic type for a Fill shape: table shading or text highlight.'''
        return RectType.SHADING.value | RectType.HIGHLIGHT.value
    
    def _semantic_type(self, line):
        '''Override. Check semantic type based on the position to a text line. Along the main dimension,
        text highlight never exceeds text line.

        Args:
            line (Line): A text line.

        Returns:
            RectType: Semantic type of this shape.
        
        .. note::
            Generally, table shading always contains at least one line, while text highlight never
            contains any lines. But in real cases, with margin exists, table shading may not 100% 
            contain a line.
        '''
        # check main dimension
        h_shape = self.bbox.width>self.bbox.height
        w_shape = self.bbox.width if h_shape else self.bbox.height

        # check orientation
        h_line = line.is_horizontal_text
        if h_shape != h_line: 
            return self.default_type

        if not self.get_main_bbox(line, threshold=constants.FACTOR_MAJOR): 
            return self.default_type