tree_utils.py 文件源码

def get_node_representation(tetre_format, token):
    """Given a format and a SpaCy node (spacy.token), returns this node representation using the NLTK tree (nltk.tree).
    It recursivelly builds a NLTK tree and returns it, not only the node itself.

    Args:
        tetre_format: The attributes of this node that will be part of its string representation.
        token: The SpaCy node itself (spacy.token).

    Returns:
        A NLTK Tree (nltk.tree)
    """

    params = tetre_format.split(",")
    node_representation = token.pos_

    if token.n_lefts + token.n_rights > 0:
        tree = Tree(node_representation,
                    [to_nltk_tree_general(child, attr_list=params, level=0) for child in token.children])
    else:
        tree = Tree(node_representation, [])

    return tree