def test_parse_tree(self):
sentences = parse_tree(data)
self.assertEqual(len(sentences), 1)
root = sentences[0]
self.assertEqual(text(root), "TokenTree<token={id=5, form=jumps}, children=[...]>")
self.assertEqual(
root.token,
OrderedDict([
('id', 5),
('form', 'jumps'),
('lemma', 'jump'),
('upostag', 'VERB'),
('xpostag', 'VBZ'),
('feats', OrderedDict([
("Mood", "Ind"),
("Number", "Sing"),
("Person", "3"),
("Tense", "Pres"),
("VerbForm", "Fin"),
])),
('head', 0),
('deprel', 'root'),
('deps', None),
('misc', None)
])
)
self.assertEqual(
[text(child) for child in root.children],
[
"TokenTree<token={id=4, form=fox}, children=[...]>",
"TokenTree<token={id=9, form=dog}, children=[...]>",
"TokenTree<token={id=10, form=.}, children=None>",
]
)
self.assertEqual(
root.metadata["text"],
"The quick brown fox jumps over the lazy dog."
)
self.assertEqual(root.serialize(), data)
self.assertEqual(
capture_print(root.print_tree),
dedent("""\
(deprel:root) form:jumps lemma:jump upostag:VERB [5]
(deprel:nsubj) form:fox lemma:fox upostag:NOUN [4]
(deprel:det) form:The lemma:the upostag:DET [1]
(deprel:amod) form:quick lemma:quick upostag:ADJ [2]
(deprel:amod) form:brown lemma:brown upostag:ADJ [3]
(deprel:nmod) form:dog lemma:dog upostag:NOUN [9]
(deprel:case) form:over lemma:over upostag:ADP [6]
(deprel:det) form:the lemma:the upostag:DET [7]
(deprel:amod) form:lazy lemma:lazy upostag:ADJ [8]
(deprel:punct) form:. lemma:. upostag:PUNCT [10]
""")
)
def test_print_with_children(self):
tree = TokenTree(token={
"id": "X",
"deprel": "Y",
"test": "data"
},
children=[
TokenTree(token={
"id": "X",
"deprel": "Y",
"test": "data"
},
children=[]),
TokenTree(token={
"id": "X",
"deprel": "Y",
"test": "data"
},
children=[]),
])
result = capture_print(tree.print_tree)
self.assertEqual(
result,
dedent("""\
(deprel:Y) test:data [X]
(deprel:Y) test:data [X]
(deprel:Y) test:data [X]
"""))
def test_print_simple(self):
tree = TokenTree(token={
"id": "X",
"deprel": "Y",
"test": "data"
},
children=[])
result = capture_print(tree.print_tree)
self.assertEqual(result, "(deprel:Y) test:data [X]\n")
def test_tree_without_id(self):
tree = TokenTree(token={"form": "hej", "deprel": "nmod"}, children=[])
with self.assertRaises(ParseException):
capture_print(tree.print_tree)
def test_print_empty_list(self):
tree = TokenTree(None, [])
with self.assertRaises(ParseException):
capture_print(tree.print_tree)
