def test_create(self, con):
some_dict = {"id": "value"}
some_response = "value, " \
"{'title': None, 'excludeUttWithoutEntities': True, 'numWorkers': 8, 'chunk': 'PAGE', " \
"'searchDictionaries': [{'searchMode': 'ORDERED_SPAN', 'analyzeStrategy': 'SIMPLE'}]}"
model = Model()
extractor = Extractor()
model.add_extractor(extractor)
response = Mock()
response.json.return_value = some_dict
con.return_value = response
res = model.create()
self.assertEqual(str(res), some_response)
def test_add_extractor(self):
ex = Extractor()
ex.set_vocabulary('123')
ex.set_type(Type.DATETIME)
ex.set_mode(Mode.SIMPLE)
ex.set_stop_word_list(['stop'])
ex.set_synonym_list(['synonym'])
ex.set_validator('val')
some_list = [{
'vocabId': '123',
'vocabValueType': 'REGEX',
'dataType': 'DATETIME',
'searchMode': 'ORDERED_SPAN',
'analyzeStrategy': 'SIMPLE',
'stopwordList': ['stop'],
'synonymList': ['synonym'],
'phraseMatchingPattern': 'val'
}]
model = Model()
model.add_extractor(ex)
self.assertEqual(model.temp_dictionary["searchDictionaries"],
some_list)
vocabulary = Vocabulary()
vocabulary.add_entry("Industrials")
vocabulary.add_entry("Quasi-Governments")
vocabulary.add_entry("Governments")
vocabulary.name("Allocations (%)").create()
# 3- Creator Extractor - Regex must have 1 capturing group
extractor = Extractor()
extractor.set_vocabulary(vocabulary.get_id())
extractor.set_validator("^ +(\\d[\\d\\.\\,]+\\d)")
extractor.set_type(Type.DOUBLE)
# 4- Run
model = Model()
model.set_description("test data process")
model.add_extractor(extractor)
model.with_documents(list_of_documents)
model.create()
# 5- Wait to finish
model.wait_for_completion()
# 6- Export Field results
result = Result(model.get_id())
# print(result.read())
for item in result.read():
field_value = item.get_values()[0]
print(f"{item.get_str()} -> {field_value.get_str()}")
# 7- Export raw results to XLSX
result.result_xlsx_exporter("sample.xlsx")
def test_add_extractor_regex_err(self):
ex = Extractor()
ex.set_validator('[')
model = Model()
with self.assertRaises(QtArgumentError):
model.add_extractor(ex)