def test_check_correct_entity_annotations(
text: Text, warnings: int, whitespace_tokenizer: WhitespaceTokenizer):
reader = RasaYAMLReader()
training_data = reader.reads(text)
whitespace_tokenizer.process_training_data(training_data)
with pytest.warns(UserWarning) as record:
EntityExtractorMixin.check_correct_entity_annotations(training_data)
assert len(record) == warnings
assert all([excerpt in record[0].message.args[0]]
for excerpt in ["Misaligned entity annotation in sentence"])
def test_convert_tags_to_entities(
text: Text,
tags: Dict[Text, List[Text]],
confidences: Dict[Text, List[float]],
expected_entities: List[Dict[Text, Any]],
whitespace_tokenizer: WhitespaceTokenizer,
):
extractor = EntityExtractorMixin()
message = Message(data={TEXT: text})
tokens = whitespace_tokenizer.tokenize(message, TEXT)
split_entities_config = {SPLIT_ENTITIES_BY_COMMA: True}
actual_entities = extractor.convert_predictions_into_entities(
text, tokens, tags, split_entities_config, confidences)
assert actual_entities == expected_entities
def test_split_entities_by_comma(
text: Text,
tags: Dict[Text, List[Text]],
confidences: Dict[Text, List[float]],
expected_entities: List[Dict[Text, Any]],
):
extractor = EntityExtractor()
tokenizer = WhitespaceTokenizer()
message = Message(data={TEXT: text})
tokens = tokenizer.tokenize(message, TEXT)
split_entities_config = {
SPLIT_ENTITIES_BY_COMMA: True,
"address": False,
"ingredient": True,
}
actual_entities = extractor.convert_predictions_into_entities(
text, tokens, tags, split_entities_config, confidences)
assert actual_entities == expected_entities