def extract_elements_from_document(doc: Doc):
participants = []
svos = []
for sentence in doc.sents:
# print(sentence)
# utils.to_nltk_tree(sentence.root).pretty_print()
out_participants, out_svos = extract.extract_process_elements(sentence)
participants += out_participants
svos += out_svos
return participants, svos
def test_example_phrase_six(self):
filepath = "../examples/example_phrase_six"
nlp = spacy.load("en")
text = open(filepath).read().replace("\n", " ")
doc = nlp(text)
svos = []
for sentence in doc.sents:
utils.to_nltk_tree(sentence.root).pretty_print()
participants, svos = extract.extract_process_elements(sentence)
for svo in svos:
print(utils.svo_full_name(svo))
self.assertEqual(len(svos), 1, "SVO list length is incorrect")
def test_example_phrase_five(self):
filepath = "../examples/example_phrase_five"
nlp = spacy.load("en")
text = open(filepath).read().replace("\n", " ")
doc = nlp(text)
participants = []
for sentence in doc.sents:
[
utils.to_nltk_tree(sent.root).pretty_print()
for sent in doc.sents
]
participants, svos = extract.extract_process_elements(sentence)
for participant in participants:
print(utils.participant_full_name(participant))
self.assertEqual(len(participants), 1,
"Participants list length is incorrect")