def __iterate(tree: ParentedTree, index: int = 1):
# clean the tags which contains '-'
if '-' in tree.label():
tree.set_label(tree.label().split('-')[0])
if _is_leaf(tree):
yield tree.label(), tree[0] # (tag, token)
tree[0] = index # replace the token with its index number
index += 1
else:
for subtree in tree:
for _item in __iterate(subtree, index):
yield _item
index += 1
def __iterate(tree: ParentedTree):
label = tree.label()
if _is_leaf(tree):
tree.set_label('{}|{}'.format(tree[0], label))
else:
for subtree in tree:
__iterate(subtree)
# just select the last one as the head if the tag is not covered by the head rules
if label not in self.head_rules:
index = tree[-1].label().split('|')[0]
tree.set_label('{}|{}'.format(index, label))
return
for rule in self.head_rules[label]:
sub_labels = [t.label().split('|') for t in tree]
if rule['direction'] == 'r':
sub_labels = sub_labels[::-1] # reverse
# this is the last rule, just select the first or last one as the head
if not rule['tags']:
index = sub_labels[0][0]
tree.set_label('{}|{}'.format(index, label))
return
for tag in rule['tags']:
if tag in {_tag for _i, _tag in sub_labels}:
index = next(_i for _i, _tag in sub_labels
if tag == _tag)
tree.set_label('{}|{}'.format(index, label))
return
