document.py 文件源码

def __init__(self, *elements):
        """Initialize a Document manually by passing one or more Document elements (Paragraph, Heading, Table, etc.)

        Strings that are passed to this constructor are automatically wrapped into Paragraph elements.

        :param list[chemdataextractor.doc.element.BaseElement|string] elements: Elements in this Document.
        """
        self._elements = []
        for element in elements:
            # Convert raw text to Paragraph elements
            if isinstance(element, six.text_type):
                element = Paragraph(element)
            elif isinstance(element, six.binary_type):
                # Try guess encoding if byte string
                encoding = get_encoding(element)
                log.warning('Guessed bytestring encoding as %s. Use unicode strings to avoid this warning.', encoding)
                element = Paragraph(element.decode(encoding))
            element.document = self
            self._elements.append(element)
        log.debug('%s: Initializing with %s elements' % (self.__class__.__name__, len(self.elements)))