def test_parse_large_text(self):
text = load_resource_document(
'lexnlp/extract/es/sample_es_regulations.txt', 'utf-8')
ret = parser.parse(text)
self.assertGreater(len(ret), 100)
html = annotate_text(text, ret)
save_test_document('sample_es_regulations.html', html)
def annotate_document(self, text: str, definitions: List[dict],
output_path: str) -> None:
annotations = []
index = 0
for df in definitions:
index += 1
ant = TextAnnotation(
(df["attrs"]["start"], df["attrs"]["end"]),
df["tags"]["Extracted Entity Definition Name"], index)
annotations.append(ant)
html = annotate_text(text, annotations)
save_test_document(output_path, html)
def annotate_document(self, text: str, definitions: List[dict],
output_path: str) -> None:
annotations = []
index = 0
for df in definitions:
index += 1
ant_text = df["tags"]["Extracted Entity Text"]
ant = DefinitionAnnotation(
name=df["tags"]["Extracted Entity Definition Name"],
coords=(df["attrs"]["start"], df["attrs"]["end"]),
text=ant_text,
locale="en")
annotations.append(ant)
html = annotate_text(text, annotations)
save_test_document(output_path, html)
def annotate_definitions_text(text: str, definitions: List[dict],
save_path: str) -> None:
ants = []
for df in definitions:
ref_text = df["tags"]["Extracted Entity Text"]
name = df["tags"]["Extracted Entity Definition Name"]
start = df["attrs"]["start"]
end = df["attrs"]["end"]
w_start = text.find(name, start, end + 1)
if w_start >= 0:
start = w_start
end = start + len(name)
ant = TextAnnotation((start, end), ref_text)
ants.append(ant)
markup = annotate_text(text, ants)
save_test_document(save_path, markup)
def annotate_definitions_text(text: str,
definitions: List[DefinitionAnnotation],
save_path: str) -> None:
markup = annotate_text(text, definitions)
save_test_document(save_path, markup)