python类Tree()的实例源码

def tree2semi_rel(tree):
    """
    Group a chunk structure into a list of 'semi-relations' of the form (list(str), ``Tree``). 

    In order to facilitate the construction of (``Tree``, string, ``Tree``) triples, this
    identifies pairs whose first member is a list (possibly empty) of terminal
    strings, and whose second member is a ``Tree`` of the form (NE_label, terminals).

    :param tree: a chunk tree
    :return: a list of pairs (list(str), ``Tree``)
    :rtype: list of tuple
    """

    from nltk.tree import Tree

    semi_rels = []
    semi_rel = [[], None]

    for dtr in tree:
        if not isinstance(dtr, Tree):
            semi_rel[0].append(dtr)
        else:
            # dtr is a Tree
            semi_rel[1] = dtr
            semi_rels.append(semi_rel)
            semi_rel = [[], None]
    return semi_rels

def conlltags2tree(sentence, chunk_types=('NP','PP','VP'),
                   root_label='S', strict=False):
    """
    Convert the CoNLL IOB format to a tree.
    """
    tree = Tree(root_label, [])
    for (word, postag, chunktag) in sentence:
        if chunktag is None:
            if strict:
                raise ValueError("Bad conll tag sequence")
            else:
                # Treat as O
                tree.append((word,postag))
        elif chunktag.startswith('B-'):
            tree.append(Tree(chunktag[2:], [(word,postag)]))
        elif chunktag.startswith('I-'):
            if (len(tree)==0 or not isinstance(tree[-1], Tree) or
                tree[-1].label() != chunktag[2:]):
                if strict:
                    raise ValueError("Bad conll tag sequence")
                else:
                    # Treat as B-*
                    tree.append(Tree(chunktag[2:], [(word,postag)]))
            else:
                tree[-1].append((word,postag))
        elif chunktag == 'O':
            tree.append((word,postag))
        else:
            raise ValueError("Bad conll tag %r" % chunktag)
    return tree

def _untag(self, tree):
        for i, child in enumerate(tree):
            if isinstance(child, Tree):
                self._untag(child)
            elif isinstance(child, tuple):
                tree[i] = child[0]
            else:
                raise ValueError('expected child to be Tree or tuple')
        return tree