Class Element

pdf2docx/common/Element.py:23–312

Boundary box with attribute in fitz.Rect type.

class Element(IText):
    '''Boundary box with attribute in fitz.Rect type.'''

    # all coordinates are related to un-rotated page in PyMuPDF
    # e.g. Matrix(0.0, 1.0, -1.0, 0.0, 842.0, 0.0)
    ROTATION_MATRIX = fitz.Matrix(0.0) # rotation angle = 0 degree by default


    @classmethod
    def set_rotation_matrix(cls, rotation_matrix):
        """Set global rotation matrix.

        Args:
            Rotation_matrix (fitz.Matrix): target matrix
        """
        if rotation_matrix and isinstance(rotation_matrix, fitz.Matrix):
            cls.ROTATION_MATRIX = rotation_matrix


    @classmethod
    def pure_rotation_matrix(cls):
        '''Pure rotation matrix used for calculating text direction after rotation.'''
        a,b,c,d,e,f = cls.ROTATION_MATRIX
        return fitz.Matrix(a,b,c,d,0,0)


    def __init__(self, raw:dict=None, parent=None):
        ''' Initialize Element and convert to the real (rotation considered) page CS.'''
        self.bbox = fitz.Rect()  # type: fitz.Rect
        self._parent = parent # type: Element

        # NOTE: Any coordinates provided in raw is in original page CS 
        # (without considering page rotation).
        if 'bbox' in (raw or {}):
            rect = fitz.Rect(raw['bbox']) * Element.ROTATION_MATRIX
            self.update_bbox(rect)


    def __bool__(self):
        '''Real object when bbox is defined.'''
        # NOTE inconsistent results of fitz.Rect for different version of pymupdf, e.g.,
        # a = fitz.Rect(3,3,2,2)
        #                   bool(a)      a.get_area()       a.is_empty
        # pymupdf 1.23.5      True            1.0              True
        # pymupdf 1.23.8      True            0.0              True
        # bool(fitz.Rect())==False
        # NOTE: do not use `return not self.bbox.is_empty` here
        return bool(self.bbox)


    def __repr__(self): return f'{self.__class__.__name__}({tuple(self.bbox)})'


    # ------------------------------------------------
    # parent element
    # ------------------------------------------------
    @property
    def parent(self): return self._parent