def test_writing_reading_test_data():
column_names = ('text', 'input_text_languages_str', 'input_int1_int',
'input_arg_bool', 'expected1', 'expected2')
texts = (None, 'text2', 'text3', '###text4')
values = ((('l1', '11', 'False', 'e11', 'e12'), ), (('l2', '22', 'True',
'e21', 'e22'), ),
(('l3', '33', 'False', 'e31', 'e32'),
('l3', '33', 'False', 'e31', 'e32'), 'string'), ())
file_name = None
try:
file_name = lexnlp_tests.write_test_data_text_and_tuple(
texts, values, column_names)
actual = [
(i, text, input_args, expected) for i, text, input_args, expected
in lexnlp_tests.iter_test_data_text_and_tuple(call_stack_offset=1)
]
a2 = actual[0]
e2 = (2, 'text2', {
'text_languages': 'l2',
'arg': True,
'int1': 22
}, [('e21', 'e22')])
print('Actual: {0}'.format(a2))
print('Expected: {0}'.format(e2))
assert_equals(a2[0], e2[0])
assert_equals(a2[1], e2[1])
assert_dict_equal(a2[2], e2[2])
assert_equals(len(a2[3]), len(e2[3]))
assert_tuple_equal(a2[3][0], e2[3][0])
finally:
if file_name:
os.remove(file_name)
def test_get_regulations():
"""
Test default get regulations behavior.
:return:
"""
lexnlp_tests.test_extraction_func_on_test_data(get_regulations,
expected_data_converter=lambda d:
[(reg_type, reg_code) for reg_type, reg_code, _reg_str in d],
return_source=False, as_dict=False)
lexnlp_tests.test_extraction_func_on_test_data(get_regulations,
expected_data_converter=lambda d:
[(reg_type, reg_code, reg_str) for reg_type, reg_code, reg_str in d],
return_source=True, as_dict=False)
# TODO Impl test_extraction_func_on_test_data() comparing lists of dicts
for (_i, text, _input_args, expected) in lexnlp_tests.iter_test_data_text_and_tuple():
expected_no_source_dict = [{'regulation_type': reg_type,
'regulation_code': reg_code}
for reg_type, reg_code, _reg_str in expected]
expected_source_dict = [{'regulation_type': reg_type,
'regulation_code': reg_code,
'regulation_str': reg_str}
for reg_type, reg_code, reg_str in expected]
assert_list_equal(
list(lexnlp_tests.benchmark_extraction_func(get_regulations, text, return_source=False, as_dict=True)),
expected_no_source_dict)
assert_list_equal(
list(lexnlp_tests.benchmark_extraction_func(get_regulations, text, return_source=True, as_dict=True)),
expected_source_dict)
def test_page_examples():
for (_i, text, _input_args, expected) in lexnlp_tests.iter_test_data_text_and_tuple():
def remove_whitespace(r):
return r.replace(" ", "").replace("\n", "").replace("\r", "").replace("\t", "")
# Get list of pages
page_list = list(lexnlp_tests.benchmark_extraction_func(get_pages, text))
assert len(page_list) == len(expected)
clean_result = [remove_whitespace(p) for p in expected]
for page in page_list:
assert remove_whitespace(page) in clean_result
def test_get_regulations_csv(self):
"""
Test default get regulations behavior.
:return:
"""
test_data_path = os.path.join(
lexnlp_test_path,
'lexnlp/extract/en/tests/test_regulations/test_get_regulations.csv'
)
lexnlp_tests.test_extraction_func_on_test_data(
get_regulations,
expected_data_converter=lambda d: [
(reg_type, reg_code) for reg_type, reg_code, _reg_str in d
],
return_source=False,
as_dict=False,
test_data_path=test_data_path)
lexnlp_tests.test_extraction_func_on_test_data(
get_regulations,
expected_data_converter=lambda d: [(reg_type, reg_code, reg_str)
for reg_type, reg_code, reg_str
in d],
return_source=True,
as_dict=False,
test_data_path=test_data_path)
cmp = DictionaryComparer(check_order=True)
errors = []
for (i, text, _input_args, expected) in \
lexnlp_tests.iter_test_data_text_and_tuple(file_name=test_data_path):
expected = [{
'regulation_type': reg_type,
'regulation_code': reg_code,
'regulation_text': reg_str
} for reg_type, reg_code, reg_str in expected]
actual = list(
lexnlp_tests.benchmark_extraction_func(get_regulations,
text,
return_source=True,
as_dict=True))
line_errors = cmp.compare_list_of_dicts(expected, actual)
if line_errors:
line_errors_str = '\n'.join(line_errors)
errors.append(f'Regulation tests, line [{i + 1}] errors:\n' +
line_errors_str)
if errors:
raise Exception('\n\n'.join(errors))
def test_page_examples(self):
file_path = os.path.join(self.TEST_PATH, 'test_page_examples.csv')
for (_i, text, _input_args,
expected) in lexnlp_tests.iter_test_data_text_and_tuple(
file_name=file_path):
def remove_blankspace(r):
return r.replace(" ",
"").replace("\n",
"").replace("\r",
"").replace("\t", "")
# Get list of pages
page_list = list(
lexnlp_tests.benchmark_extraction_func(get_pages, text))
assert len(page_list) == len(expected)
clean_result = [remove_blankspace(p) for p in expected]
for page in page_list:
assert remove_blankspace(page) in clean_result
def test_get_citations():
"""
Test default get citation behavior.
:return:
"""
for (_i, text, _input_args, expected) in lexnlp_tests.iter_test_data_text_and_tuple():
expected = [(int(volume) if volume else None,
reporter,
reporter_full_name,
int(page) if page else None,
page2,
court,
int(year) if year else None,
source_text)
for volume, reporter, reporter_full_name, page, page2, court, year, source_text in expected]
expected_without_sources = [v[:-1] for v in expected]
expected_with_sources = expected
lexnlp_tests.test_extraction_func(expected_without_sources, get_citations, text, return_source=False)
lexnlp_tests.test_extraction_func(expected_with_sources, get_citations, text, return_source=True)
def test_paragraph_examples():
for (_i, text, _input_args,
expected) in lexnlp_tests.iter_test_data_text_and_tuple():
run_paragraph_test(text, expected)
def test_paragraph_examples(self):
file_path = os.path.join(self.TEST_PATH, 'test_paragraph_examples.csv')
for (_i, text, _input_args,
expected) in lexnlp_tests.iter_test_data_text_and_tuple(
file_name=file_path):
self.run_paragraph_test(text, expected)
